summaryrefslogtreecommitdiff
path: root/arch/x86
diff options
context:
space:
mode:
Diffstat (limited to 'arch/x86')
-rw-r--r--arch/x86/Kconfig74
-rw-r--r--arch/x86/Kconfig.assembler14
-rw-r--r--arch/x86/Kconfig.cpu24
-rw-r--r--arch/x86/Kconfig.cpufeatures4
-rw-r--r--arch/x86/Makefile6
-rw-r--r--arch/x86/boot/Makefile2
-rw-r--r--arch/x86/boot/bioscall.S4
-rw-r--r--arch/x86/boot/boot.h6
-rw-r--r--arch/x86/boot/compressed/Makefile15
-rw-r--r--arch/x86/boot/compressed/head_64.S1
-rw-r--r--arch/x86/boot/compressed/kaslr.c50
-rw-r--r--arch/x86/boot/compressed/misc.c1
-rw-r--r--arch/x86/boot/compressed/misc.h8
-rw-r--r--arch/x86/boot/compressed/pgtable.h18
-rw-r--r--arch/x86/boot/compressed/pgtable_64.c12
-rw-r--r--arch/x86/boot/compressed/sbat.S7
-rw-r--r--arch/x86/boot/compressed/sev-handle-vc.c134
-rw-r--r--arch/x86/boot/compressed/sev.c156
-rw-r--r--arch/x86/boot/compressed/sev.h21
-rw-r--r--arch/x86/boot/compressed/string.c8
-rw-r--r--arch/x86/boot/compressed/vmlinux.lds.S8
-rw-r--r--arch/x86/boot/copy.S8
-rw-r--r--arch/x86/boot/cpuflags.c13
-rw-r--r--arch/x86/boot/header.S47
-rw-r--r--arch/x86/boot/startup/Makefile30
-rw-r--r--arch/x86/boot/startup/efi-mixed.S253
-rw-r--r--arch/x86/boot/startup/gdt_idt.c71
-rw-r--r--arch/x86/boot/startup/la57toggle.S (renamed from arch/x86/boot/compressed/la57toggle.S)1
-rw-r--r--arch/x86/boot/startup/map_kernel.c217
-rw-r--r--arch/x86/boot/startup/sev-shared.c (renamed from arch/x86/coco/sev/shared.c)895
-rw-r--r--arch/x86/boot/startup/sev-startup.c368
-rw-r--r--arch/x86/boot/startup/sme.c (renamed from arch/x86/mm/mem_encrypt_identity.c)30
-rw-r--r--arch/x86/boot/string.c2
-rw-r--r--arch/x86/boot/video.c2
-rw-r--r--arch/x86/coco/core.c2
-rw-r--r--arch/x86/coco/sev/Makefile24
-rw-r--r--arch/x86/coco/sev/core.c1924
-rw-r--r--arch/x86/coco/sev/sev-nmi.c108
-rw-r--r--arch/x86/coco/sev/vc-handle.c1068
-rw-r--r--arch/x86/coco/sev/vc-shared.c504
-rw-r--r--arch/x86/coco/tdx/tdx.c50
-rw-r--r--arch/x86/configs/i386_defconfig20
-rw-r--r--arch/x86/configs/x86_64_defconfig9
-rw-r--r--arch/x86/crypto/Kconfig154
-rw-r--r--arch/x86/crypto/Makefile27
-rw-r--r--arch/x86/crypto/aegis128-aesni-glue.c53
-rw-r--r--arch/x86/crypto/aes-ctr-avx-x86_64.S47
-rw-r--r--arch/x86/crypto/aes-xts-avx-x86_64.S206
-rw-r--r--arch/x86/crypto/aesni-intel_glue.c174
-rw-r--r--arch/x86/crypto/aria_aesni_avx2_glue.c23
-rw-r--r--arch/x86/crypto/aria_aesni_avx_glue.c21
-rw-r--r--arch/x86/crypto/aria_gfni_avx512_glue.c22
-rw-r--r--arch/x86/crypto/blake2s-core.S256
-rw-r--r--arch/x86/crypto/blake2s-glue.c74
-rw-r--r--arch/x86/crypto/camellia_aesni_avx2_glue.c21
-rw-r--r--arch/x86/crypto/camellia_aesni_avx_glue.c22
-rw-r--r--arch/x86/crypto/camellia_glue.c1
-rw-r--r--arch/x86/crypto/cast5_avx_glue.c21
-rw-r--r--arch/x86/crypto/cast6_avx_glue.c20
-rw-r--r--arch/x86/crypto/chacha-avx2-x86_64.S1021
-rw-r--r--arch/x86/crypto/chacha-avx512vl-x86_64.S836
-rw-r--r--arch/x86/crypto/chacha-ssse3-x86_64.S791
-rw-r--r--arch/x86/crypto/chacha_glue.c311
-rw-r--r--arch/x86/crypto/curve25519-x86_64.c1
-rw-r--r--arch/x86/crypto/ghash-clmulni-intel_asm.S5
-rw-r--r--arch/x86/crypto/ghash-clmulni-intel_glue.c289
-rw-r--r--arch/x86/crypto/poly1305-x86_64-cryptogams.pl4248
-rw-r--r--arch/x86/crypto/poly1305_glue.c290
-rw-r--r--arch/x86/crypto/polyval-clmulni_glue.c72
-rw-r--r--arch/x86/crypto/serpent_avx2_glue.c21
-rw-r--r--arch/x86/crypto/serpent_avx_glue.c22
-rw-r--r--arch/x86/crypto/serpent_sse2_glue.c21
-rw-r--r--arch/x86/crypto/sha1_avx2_x86_64_asm.S700
-rw-r--r--arch/x86/crypto/sha1_ni_asm.S304
-rw-r--r--arch/x86/crypto/sha1_ssse3_asm.S554
-rw-r--r--arch/x86/crypto/sha1_ssse3_glue.c365
-rw-r--r--arch/x86/crypto/sha256-avx-asm.S499
-rw-r--r--arch/x86/crypto/sha256-avx2-asm.S774
-rw-r--r--arch/x86/crypto/sha256-ssse3-asm.S513
-rw-r--r--arch/x86/crypto/sha256_ni_asm.S200
-rw-r--r--arch/x86/crypto/sha256_ssse3_glue.c467
-rw-r--r--arch/x86/crypto/sha512-avx-asm.S423
-rw-r--r--arch/x86/crypto/sha512-avx2-asm.S750
-rw-r--r--arch/x86/crypto/sha512-ssse3-asm.S425
-rw-r--r--arch/x86/crypto/sha512_ssse3_glue.c347
-rw-r--r--arch/x86/crypto/sm3_avx_glue.c54
-rw-r--r--arch/x86/crypto/sm4_aesni_avx2_glue.c31
-rw-r--r--arch/x86/crypto/sm4_aesni_avx_glue.c32
-rw-r--r--arch/x86/crypto/twofish_avx_glue.c21
-rw-r--r--arch/x86/crypto/twofish_glue.c1
-rw-r--r--arch/x86/crypto/twofish_glue_3way.c1
-rw-r--r--arch/x86/entry/calling.h4
-rw-r--r--arch/x86/entry/entry.S8
-rw-r--r--arch/x86/entry/syscalls/syscall_32.tbl2
-rw-r--r--arch/x86/entry/syscalls/syscall_64.tbl2
-rw-r--r--arch/x86/entry/vdso/Makefile3
-rw-r--r--arch/x86/entry/vdso/vma.c35
-rw-r--r--arch/x86/entry/vsyscall/vsyscall_64.c2
-rw-r--r--arch/x86/events/amd/brs.c12
-rw-r--r--arch/x86/events/amd/core.c16
-rw-r--r--arch/x86/events/amd/ibs.c33
-rw-r--r--arch/x86/events/amd/iommu.c2
-rw-r--r--arch/x86/events/amd/lbr.c21
-rw-r--r--arch/x86/events/amd/power.c11
-rw-r--r--arch/x86/events/amd/uncore.c117
-rw-r--r--arch/x86/events/core.c91
-rw-r--r--arch/x86/events/intel/bts.c151
-rw-r--r--arch/x86/events/intel/core.c418
-rw-r--r--arch/x86/events/intel/cstate.c3
-rw-r--r--arch/x86/events/intel/ds.c68
-rw-r--r--arch/x86/events/intel/knc.c24
-rw-r--r--arch/x86/events/intel/lbr.c46
-rw-r--r--arch/x86/events/intel/p4.c28
-rw-r--r--arch/x86/events/intel/p6.c13
-rw-r--r--arch/x86/events/intel/pt.c37
-rw-r--r--arch/x86/events/intel/uncore.c22
-rw-r--r--arch/x86/events/intel/uncore.h2
-rw-r--r--arch/x86/events/intel/uncore_discovery.c100
-rw-r--r--arch/x86/events/intel/uncore_discovery.h7
-rw-r--r--arch/x86/events/intel/uncore_nhmex.c71
-rw-r--r--arch/x86/events/intel/uncore_snb.c122
-rw-r--r--arch/x86/events/intel/uncore_snbep.c55
-rw-r--r--arch/x86/events/msr.c4
-rw-r--r--arch/x86/events/perf_event.h72
-rw-r--r--arch/x86/events/perf_event_flags.h41
-rw-r--r--arch/x86/events/probe.c4
-rw-r--r--arch/x86/events/rapl.c9
-rw-r--r--arch/x86/events/utils.c1
-rw-r--r--arch/x86/events/zhaoxin/core.c20
-rw-r--r--arch/x86/hyperv/hv_apic.c11
-rw-r--r--arch/x86/hyperv/hv_init.c135
-rw-r--r--arch/x86/hyperv/hv_spinlock.c7
-rw-r--r--arch/x86/hyperv/hv_vtl.c66
-rw-r--r--arch/x86/hyperv/irqdomain.c69
-rw-r--r--arch/x86/hyperv/ivm.c17
-rw-r--r--arch/x86/hyperv/nested.c1
-rw-r--r--arch/x86/include/asm/acpi.h4
-rw-r--r--arch/x86/include/asm/acrn.h2
-rw-r--r--arch/x86/include/asm/alternative.h11
-rw-r--r--arch/x86/include/asm/amd/hsmp.h (renamed from arch/x86/include/asm/amd_hsmp.h)2
-rw-r--r--arch/x86/include/asm/amd/ibs.h (renamed from arch/x86/include/asm/amd-ibs.h)5
-rw-r--r--arch/x86/include/asm/amd/nb.h (renamed from arch/x86/include/asm/amd_nb.h)2
-rw-r--r--arch/x86/include/asm/amd/node.h (renamed from arch/x86/include/asm/amd_node.h)0
-rw-r--r--arch/x86/include/asm/apic.h86
-rw-r--r--arch/x86/include/asm/arch_hweight.h6
-rw-r--r--arch/x86/include/asm/asm.h24
-rw-r--r--arch/x86/include/asm/bitops.h7
-rw-r--r--arch/x86/include/asm/boot.h10
-rw-r--r--arch/x86/include/asm/bug.h56
-rw-r--r--arch/x86/include/asm/ce4100.h6
-rw-r--r--arch/x86/include/asm/cfi.h10
-rw-r--r--arch/x86/include/asm/coco.h2
-rw-r--r--arch/x86/include/asm/cpufeatures.h45
-rw-r--r--arch/x86/include/asm/cpuid/api.h96
-rw-r--r--arch/x86/include/asm/cpuid/types.h95
-rw-r--r--arch/x86/include/asm/debugreg.h35
-rw-r--r--arch/x86/include/asm/elf.h4
-rw-r--r--arch/x86/include/asm/entry-common.h5
-rw-r--r--arch/x86/include/asm/fpu/api.h3
-rw-r--r--arch/x86/include/asm/fpu/sched.h38
-rw-r--r--arch/x86/include/asm/fpu/types.h73
-rw-r--r--arch/x86/include/asm/fpu/xstate.h12
-rw-r--r--arch/x86/include/asm/fred.h1
-rw-r--r--arch/x86/include/asm/fsgsbase.h4
-rw-r--r--arch/x86/include/asm/hw_irq.h12
-rw-r--r--arch/x86/include/asm/inat.h6
-rw-r--r--arch/x86/include/asm/init.h2
-rw-r--r--arch/x86/include/asm/intel-family.h5
-rw-r--r--arch/x86/include/asm/intel_telemetry.h37
-rw-r--r--arch/x86/include/asm/io.h6
-rw-r--r--arch/x86/include/asm/irq_remapping.h17
-rw-r--r--arch/x86/include/asm/irqflags.h4
-rw-r--r--arch/x86/include/asm/kexec.h7
-rw-r--r--arch/x86/include/asm/kvm-x86-ops.h8
-rw-r--r--arch/x86/include/asm/kvm_host.h132
-rw-r--r--arch/x86/include/asm/linkage.h10
-rw-r--r--arch/x86/include/asm/mem_encrypt.h2
-rw-r--r--arch/x86/include/asm/microcode.h4
-rw-r--r--arch/x86/include/asm/mmu.h4
-rw-r--r--arch/x86/include/asm/mmu_context.h15
-rw-r--r--arch/x86/include/asm/module.h8
-rw-r--r--arch/x86/include/asm/mshyperv.h32
-rw-r--r--arch/x86/include/asm/msr-index.h24
-rw-r--r--arch/x86/include/asm/msr.h218
-rw-r--r--arch/x86/include/asm/mwait.h93
-rw-r--r--arch/x86/include/asm/nmi.h49
-rw-r--r--arch/x86/include/asm/nospec-branch.h41
-rw-r--r--arch/x86/include/asm/page_32_types.h1
-rw-r--r--arch/x86/include/asm/page_64.h2
-rw-r--r--arch/x86/include/asm/page_64_types.h11
-rw-r--r--arch/x86/include/asm/page_types.h4
-rw-r--r--arch/x86/include/asm/paravirt.h63
-rw-r--r--arch/x86/include/asm/paravirt_types.h12
-rw-r--r--arch/x86/include/asm/percpu.h20
-rw-r--r--arch/x86/include/asm/perf_event.h1
-rw-r--r--arch/x86/include/asm/pgtable-2level_types.h2
-rw-r--r--arch/x86/include/asm/pgtable-3level_types.h4
-rw-r--r--arch/x86/include/asm/pgtable.h84
-rw-r--r--arch/x86/include/asm/pgtable_64.h2
-rw-r--r--arch/x86/include/asm/pgtable_64_types.h26
-rw-r--r--arch/x86/include/asm/pgtable_types.h8
-rw-r--r--arch/x86/include/asm/posted_intr.h83
-rw-r--r--arch/x86/include/asm/processor.h16
-rw-r--r--arch/x86/include/asm/realmode.h2
-rw-r--r--arch/x86/include/asm/resctrl.h21
-rw-r--r--arch/x86/include/asm/set_memory.h2
-rw-r--r--arch/x86/include/asm/setup.h3
-rw-r--r--arch/x86/include/asm/sev-internal.h105
-rw-r--r--arch/x86/include/asm/sev.h116
-rw-r--r--arch/x86/include/asm/shared/tdx.h12
-rw-r--r--arch/x86/include/asm/sighandling.h22
-rw-r--r--arch/x86/include/asm/simd.h6
-rw-r--r--arch/x86/include/asm/smp.h23
-rw-r--r--arch/x86/include/asm/spec-ctrl.h2
-rw-r--r--arch/x86/include/asm/special_insns.h50
-rw-r--r--arch/x86/include/asm/string_32.h15
-rw-r--r--arch/x86/include/asm/suspend_32.h1
-rw-r--r--arch/x86/include/asm/suspend_64.h1
-rw-r--r--arch/x86/include/asm/svm.h23
-rw-r--r--arch/x86/include/asm/switch_to.h4
-rw-r--r--arch/x86/include/asm/syscall.h43
-rw-r--r--arch/x86/include/asm/tdx.h79
-rw-r--r--arch/x86/include/asm/tdx_global_metadata.h (renamed from arch/x86/virt/vmx/tdx/tdx_global_metadata.h)19
-rw-r--r--arch/x86/include/asm/text-patching.h29
-rw-r--r--arch/x86/include/asm/tlbflush.h5
-rw-r--r--arch/x86/include/asm/trace/common.h12
-rw-r--r--arch/x86/include/asm/trace/exceptions.h54
-rw-r--r--arch/x86/include/asm/trace/fpu.h20
-rw-r--r--arch/x86/include/asm/trace/irq_vectors.h1
-rw-r--r--arch/x86/include/asm/tsc.h55
-rw-r--r--arch/x86/include/asm/uaccess_64.h6
-rw-r--r--arch/x86/include/asm/vdso.h8
-rw-r--r--arch/x86/include/asm/vdso/processor.h8
-rw-r--r--arch/x86/include/asm/vmx.h2
-rw-r--r--arch/x86/include/asm/x86_init.h1
-rw-r--r--arch/x86/include/asm/xen/hypervisor.h2
-rw-r--r--arch/x86/include/uapi/asm/debugreg.h21
-rw-r--r--arch/x86/include/uapi/asm/kvm.h78
-rw-r--r--arch/x86/include/uapi/asm/setup_data.h13
-rw-r--r--arch/x86/include/uapi/asm/svm.h2
-rw-r--r--arch/x86/include/uapi/asm/vmx.h5
-rw-r--r--arch/x86/kernel/Makefile3
-rw-r--r--arch/x86/kernel/acpi/cppc.c10
-rw-r--r--arch/x86/kernel/acpi/cstate.c2
-rw-r--r--arch/x86/kernel/acpi/madt_wakeup.c2
-rw-r--r--arch/x86/kernel/acpi/sleep.c1
-rw-r--r--arch/x86/kernel/alternative.c556
-rw-r--r--arch/x86/kernel/amd_gart_64.c2
-rw-r--r--arch/x86/kernel/amd_nb.c11
-rw-r--r--arch/x86/kernel/amd_node.c2
-rw-r--r--arch/x86/kernel/aperture_64.c2
-rw-r--r--arch/x86/kernel/apic/apic.c17
-rw-r--r--arch/x86/kernel/apic/apic_noop.c8
-rw-r--r--arch/x86/kernel/apic/apic_numachip.c9
-rw-r--r--arch/x86/kernel/apic/io_apic.c4
-rw-r--r--arch/x86/kernel/apic/vector.c6
-rw-r--r--arch/x86/kernel/apic/x2apic_uv_x.c2
-rw-r--r--arch/x86/kernel/asm-offsets.c8
-rw-r--r--arch/x86/kernel/asm-offsets_32.c9
-rw-r--r--arch/x86/kernel/callthunks.c6
-rw-r--r--arch/x86/kernel/cet.c3
-rw-r--r--arch/x86/kernel/cpu/Makefile5
-rw-r--r--arch/x86/kernel/cpu/amd.c145
-rw-r--r--arch/x86/kernel/cpu/amd_cache_disable.c301
-rw-r--r--arch/x86/kernel/cpu/aperfmperf.c29
-rw-r--r--arch/x86/kernel/cpu/bugs.c1780
-rw-r--r--arch/x86/kernel/cpu/bus_lock.c19
-rw-r--r--arch/x86/kernel/cpu/cacheinfo.c1059
-rw-r--r--arch/x86/kernel/cpu/common.c200
-rw-r--r--arch/x86/kernel/cpu/cpu.h9
-rw-r--r--arch/x86/kernel/cpu/cpuid-deps.c5
-rw-r--r--arch/x86/kernel/cpu/cpuid_0x2_table.c128
-rw-r--r--arch/x86/kernel/cpu/feat_ctl.c5
-rw-r--r--arch/x86/kernel/cpu/hygon.c7
-rw-r--r--arch/x86/kernel/cpu/intel.c134
-rw-r--r--arch/x86/kernel/cpu/intel_epb.c12
-rw-r--r--arch/x86/kernel/cpu/mce/amd.c50
-rw-r--r--arch/x86/kernel/cpu/mce/core.c90
-rw-r--r--arch/x86/kernel/cpu/mce/inject.c35
-rw-r--r--arch/x86/kernel/cpu/mce/intel.c33
-rw-r--r--arch/x86/kernel/cpu/mce/internal.h2
-rw-r--r--arch/x86/kernel/cpu/microcode/amd.c14
-rw-r--r--arch/x86/kernel/cpu/microcode/amd_shas.c112
-rw-r--r--arch/x86/kernel/cpu/microcode/core.c19
-rw-r--r--arch/x86/kernel/cpu/microcode/intel-ucode-defs.h150
-rw-r--r--arch/x86/kernel/cpu/microcode/intel.c2
-rw-r--r--arch/x86/kernel/cpu/mshyperv.c13
-rw-r--r--arch/x86/kernel/cpu/mtrr/generic.c2
-rw-r--r--arch/x86/kernel/cpu/resctrl/Makefile2
-rw-r--r--arch/x86/kernel/cpu/resctrl/core.c48
-rw-r--r--arch/x86/kernel/cpu/resctrl/ctrlmondata.c635
-rw-r--r--arch/x86/kernel/cpu/resctrl/internal.h397
-rw-r--r--arch/x86/kernel/cpu/resctrl/monitor.c921
-rw-r--r--arch/x86/kernel/cpu/resctrl/pseudo_lock.c1119
-rw-r--r--arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h (renamed from arch/x86/kernel/cpu/resctrl/trace.h)26
-rw-r--r--arch/x86/kernel/cpu/resctrl/rdtgroup.c4173
-rw-r--r--arch/x86/kernel/cpu/scattered.c6
-rw-r--r--arch/x86/kernel/cpu/sgx/driver.h1
-rw-r--r--arch/x86/kernel/cpu/sgx/encl.c8
-rw-r--r--arch/x86/kernel/cpu/sgx/encl.h2
-rw-r--r--arch/x86/kernel/cpu/sgx/ioctl.c30
-rw-r--r--arch/x86/kernel/cpu/sgx/main.c5
-rw-r--r--arch/x86/kernel/cpu/topology.c3
-rw-r--r--arch/x86/kernel/cpu/topology_amd.c7
-rw-r--r--arch/x86/kernel/cpu/tsx.c21
-rw-r--r--arch/x86/kernel/cpu/umwait.c6
-rw-r--r--arch/x86/kernel/cpu/zhaoxin.c1
-rw-r--r--arch/x86/kernel/crash.c52
-rw-r--r--arch/x86/kernel/dumpstack.c2
-rw-r--r--arch/x86/kernel/e820.c18
-rw-r--r--arch/x86/kernel/early_printk.c9
-rw-r--r--arch/x86/kernel/fpu/context.h4
-rw-r--r--arch/x86/kernel/fpu/core.c181
-rw-r--r--arch/x86/kernel/fpu/init.c22
-rw-r--r--arch/x86/kernel/fpu/regset.c22
-rw-r--r--arch/x86/kernel/fpu/signal.c29
-rw-r--r--arch/x86/kernel/fpu/xstate.c217
-rw-r--r--arch/x86/kernel/fpu/xstate.h31
-rw-r--r--arch/x86/kernel/fred.c21
-rw-r--r--arch/x86/kernel/ftrace.c20
-rw-r--r--arch/x86/kernel/head64.c284
-rw-r--r--arch/x86/kernel/head_32.S8
-rw-r--r--arch/x86/kernel/head_64.S10
-rw-r--r--arch/x86/kernel/hpet.c5
-rw-r--r--arch/x86/kernel/ioport.c13
-rw-r--r--arch/x86/kernel/irq.c126
-rw-r--r--arch/x86/kernel/itmt.c23
-rw-r--r--arch/x86/kernel/jailhouse.c2
-rw-r--r--arch/x86/kernel/jump_label.c6
-rw-r--r--arch/x86/kernel/kexec-bzimage64.c58
-rw-r--r--arch/x86/kernel/kgdb.c2
-rw-r--r--arch/x86/kernel/kprobes/core.c22
-rw-r--r--arch/x86/kernel/kprobes/opt.c6
-rw-r--r--arch/x86/kernel/ksysfs.c8
-rw-r--r--arch/x86/kernel/kvm.c35
-rw-r--r--arch/x86/kernel/kvmclock.c6
-rw-r--r--arch/x86/kernel/machine_kexec_64.c70
-rw-r--r--arch/x86/kernel/mmconf-fam10h_64.c8
-rw-r--r--arch/x86/kernel/module.c2
-rw-r--r--arch/x86/kernel/nmi.c87
-rw-r--r--arch/x86/kernel/nmi_selftest.c52
-rw-r--r--arch/x86/kernel/paravirt.c3
-rw-r--r--arch/x86/kernel/process.c84
-rw-r--r--arch/x86/kernel/process_32.c9
-rw-r--r--arch/x86/kernel/process_64.c34
-rw-r--r--arch/x86/kernel/ptrace.c22
-rw-r--r--arch/x86/kernel/reboot_fixups_32.c2
-rw-r--r--arch/x86/kernel/relocate_kernel_32.S6
-rw-r--r--arch/x86/kernel/relocate_kernel_64.S250
-rw-r--r--arch/x86/kernel/setup.c87
-rw-r--r--arch/x86/kernel/shstk.c18
-rw-r--r--arch/x86/kernel/signal.c6
-rw-r--r--arch/x86/kernel/signal_32.c4
-rw-r--r--arch/x86/kernel/signal_64.c4
-rw-r--r--arch/x86/kernel/smp.c24
-rw-r--r--arch/x86/kernel/smpboot.c69
-rw-r--r--arch/x86/kernel/static_call.c2
-rw-r--r--arch/x86/kernel/trace_clock.c2
-rw-r--r--arch/x86/kernel/tracepoint.c21
-rw-r--r--arch/x86/kernel/traps.c55
-rw-r--r--arch/x86/kernel/tsc.c5
-rw-r--r--arch/x86/kernel/tsc_sync.c15
-rw-r--r--arch/x86/kernel/uprobes.c5
-rw-r--r--arch/x86/kernel/vmlinux.lds.S4
-rw-r--r--arch/x86/kvm/Kconfig22
-rw-r--r--arch/x86/kvm/Makefile8
-rw-r--r--arch/x86/kvm/cpuid.c75
-rw-r--r--arch/x86/kvm/cpuid.h33
-rw-r--r--arch/x86/kvm/hyperv.c15
-rw-r--r--arch/x86/kvm/hyperv.h3
-rw-r--r--arch/x86/kvm/i8254.c94
-rw-r--r--arch/x86/kvm/i8254.h17
-rw-r--r--arch/x86/kvm/i8259.c17
-rw-r--r--arch/x86/kvm/ioapic.c62
-rw-r--r--arch/x86/kvm/ioapic.h26
-rw-r--r--arch/x86/kvm/irq.c563
-rw-r--r--arch/x86/kvm/irq.h35
-rw-r--r--arch/x86/kvm/irq_comm.c442
-rw-r--r--arch/x86/kvm/lapic.c147
-rw-r--r--arch/x86/kvm/lapic.h32
-rw-r--r--arch/x86/kvm/mmu.h6
-rw-r--r--arch/x86/kvm/mmu/mmu.c128
-rw-r--r--arch/x86/kvm/mmu/mmu_internal.h8
-rw-r--r--arch/x86/kvm/mmu/page_track.c3
-rw-r--r--arch/x86/kvm/mmu/paging_tmpl.h8
-rw-r--r--arch/x86/kvm/mmu/spte.c68
-rw-r--r--arch/x86/kvm/mmu/spte.h11
-rw-r--r--arch/x86/kvm/mmu/tdp_mmu.c68
-rw-r--r--arch/x86/kvm/reverse_cpuid.h7
-rw-r--r--arch/x86/kvm/smm.h3
-rw-r--r--arch/x86/kvm/svm/avic.c691
-rw-r--r--arch/x86/kvm/svm/nested.c164
-rw-r--r--arch/x86/kvm/svm/sev.c385
-rw-r--r--arch/x86/kvm/svm/svm.c718
-rw-r--r--arch/x86/kvm/svm/svm.h151
-rw-r--r--arch/x86/kvm/svm/vmenter.S6
-rw-r--r--arch/x86/kvm/trace.h99
-rw-r--r--arch/x86/kvm/vmx/capabilities.h1
-rw-r--r--arch/x86/kvm/vmx/common.h180
-rw-r--r--arch/x86/kvm/vmx/main.c1086
-rw-r--r--arch/x86/kvm/vmx/nested.c92
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.c65
-rw-r--r--arch/x86/kvm/vmx/pmu_intel.h28
-rw-r--r--arch/x86/kvm/vmx/posted_intr.c175
-rw-r--r--arch/x86/kvm/vmx/posted_intr.h13
-rw-r--r--arch/x86/kvm/vmx/run_flags.h10
-rw-r--r--arch/x86/kvm/vmx/sgx.c9
-rw-r--r--arch/x86/kvm/vmx/tdx.c3643
-rw-r--r--arch/x86/kvm/vmx/tdx.h205
-rw-r--r--arch/x86/kvm/vmx/tdx_arch.h167
-rw-r--r--arch/x86/kvm/vmx/tdx_errno.h40
-rw-r--r--arch/x86/kvm/vmx/vmenter.S3
-rw-r--r--arch/x86/kvm/vmx/vmx.c681
-rw-r--r--arch/x86/kvm/vmx/vmx.h200
-rw-r--r--arch/x86/kvm/vmx/x86_ops.h41
-rw-r--r--arch/x86/kvm/x86.c577
-rw-r--r--arch/x86/kvm/x86.h89
-rw-r--r--arch/x86/kvm/xen.c20
-rw-r--r--arch/x86/lib/.gitignore4
-rw-r--r--arch/x86/lib/Makefile10
-rw-r--r--arch/x86/lib/cache-smp.c26
-rw-r--r--arch/x86/lib/crc-pclmul-consts.h195
-rw-r--r--arch/x86/lib/crc-pclmul-template.S582
-rw-r--r--arch/x86/lib/crc-pclmul-template.h76
-rw-r--r--arch/x86/lib/crc-t10dif-glue.c40
-rw-r--r--arch/x86/lib/crc16-msb-pclmul.S6
-rw-r--r--arch/x86/lib/crc32-glue.c111
-rw-r--r--arch/x86/lib/crc32-pclmul.S6
-rw-r--r--arch/x86/lib/crc32c-3way.S360
-rw-r--r--arch/x86/lib/crc64-glue.c50
-rw-r--r--arch/x86/lib/crc64-pclmul.S7
-rw-r--r--arch/x86/lib/delay.c2
-rw-r--r--arch/x86/lib/insn-eval.c20
-rw-r--r--arch/x86/lib/insn.c7
-rw-r--r--arch/x86/lib/iomem.c2
-rw-r--r--arch/x86/lib/kaslr.c2
-rw-r--r--arch/x86/lib/memcpy_64.S1
-rw-r--r--arch/x86/lib/memset_64.S1
-rw-r--r--arch/x86/lib/msr-smp.c16
-rw-r--r--arch/x86/lib/msr.c12
-rw-r--r--arch/x86/lib/retpoline.S2
-rw-r--r--arch/x86/lib/string_32.c17
-rw-r--r--arch/x86/lib/strstr_32.c6
-rw-r--r--arch/x86/lib/usercopy_32.c18
-rw-r--r--arch/x86/lib/x86-opcode-map.txt56
-rw-r--r--arch/x86/math-emu/fpu_aux.c2
-rw-r--r--arch/x86/math-emu/fpu_entry.c4
-rw-r--r--arch/x86/math-emu/fpu_system.h2
-rw-r--r--arch/x86/mm/Makefile10
-rw-r--r--arch/x86/mm/amdtopology.c2
-rw-r--r--arch/x86/mm/dump_pagetables.c71
-rw-r--r--arch/x86/mm/extable.c7
-rw-r--r--arch/x86/mm/fault.c8
-rw-r--r--arch/x86/mm/init.c47
-rw-r--r--arch/x86/mm/init_32.c10
-rw-r--r--arch/x86/mm/init_64.c34
-rw-r--r--arch/x86/mm/ioremap.c7
-rw-r--r--arch/x86/mm/mem_encrypt_amd.c2
-rw-r--r--arch/x86/mm/mm_internal.h4
-rw-r--r--arch/x86/mm/numa.c5
-rw-r--r--arch/x86/mm/numa_32.c61
-rw-r--r--arch/x86/mm/numa_64.c13
-rw-r--r--arch/x86/mm/numa_internal.h10
-rw-r--r--arch/x86/mm/pat/memtype.c225
-rw-r--r--arch/x86/mm/pat/memtype_interval.c63
-rw-r--r--arch/x86/mm/pat/set_memory.c20
-rw-r--r--arch/x86/mm/pgprot.c2
-rw-r--r--arch/x86/mm/pgtable.c165
-rw-r--r--arch/x86/mm/pti.c13
-rw-r--r--arch/x86/mm/tlb.c148
-rw-r--r--arch/x86/net/bpf_jit_comp.c12
-rw-r--r--arch/x86/pci/Makefile6
-rw-r--r--arch/x86/pci/amd_bus.c12
-rw-r--r--arch/x86/pci/fixup.c6
-rw-r--r--arch/x86/pci/intel_mid.c (renamed from arch/x86/pci/intel_mid_pci.c)0
-rw-r--r--arch/x86/pci/mmconfig-shared.c3
-rw-r--r--arch/x86/platform/ce4100/ce4100.c95
-rw-r--r--arch/x86/platform/efi/efi_64.c12
-rw-r--r--arch/x86/platform/olpc/olpc-xo1-rtc.c6
-rw-r--r--arch/x86/platform/olpc/olpc-xo1-sci.c2
-rw-r--r--arch/x86/platform/pvh/head.S3
-rw-r--r--arch/x86/power/cpu.c27
-rw-r--r--arch/x86/power/hibernate.c25
-rw-r--r--arch/x86/power/hibernate_asm_32.S3
-rw-r--r--arch/x86/power/hibernate_asm_64.S3
-rw-r--r--arch/x86/purgatory/Makefile2
-rw-r--r--arch/x86/purgatory/purgatory.c2
-rw-r--r--arch/x86/realmode/init.c5
-rw-r--r--arch/x86/tools/gen-insn-attr-x86.awk7
-rw-r--r--arch/x86/tools/insn_decoder_test.c2
-rw-r--r--arch/x86/tools/insn_sanity.c4
-rw-r--r--arch/x86/um/asm/checksum.h3
-rw-r--r--arch/x86/um/asm/processor.h8
-rw-r--r--arch/x86/um/asm/syscall.h2
-rw-r--r--arch/x86/um/os-Linux/mcontext.c218
-rw-r--r--arch/x86/um/ptrace.c86
-rw-r--r--arch/x86/um/shared/sysdep/kernel-offsets.h2
-rw-r--r--arch/x86/um/shared/sysdep/mcontext.h9
-rw-r--r--arch/x86/um/shared/sysdep/ptrace.h12
-rw-r--r--arch/x86/um/shared/sysdep/stub-data.h23
-rw-r--r--arch/x86/um/shared/sysdep/stub.h2
-rw-r--r--arch/x86/um/shared/sysdep/stub_32.h13
-rw-r--r--arch/x86/um/shared/sysdep/stub_64.h17
-rw-r--r--arch/x86/um/shared/sysdep/syscalls.h6
-rw-r--r--arch/x86/um/shared/sysdep/syscalls_32.h14
-rw-r--r--arch/x86/um/shared/sysdep/syscalls_64.h28
-rw-r--r--arch/x86/um/tls_32.c28
-rw-r--r--arch/x86/virt/svm/sev.c23
-rw-r--r--arch/x86/virt/vmx/tdx/seamcall.S3
-rw-r--r--arch/x86/virt/vmx/tdx/tdx.c428
-rw-r--r--arch/x86/virt/vmx/tdx/tdx.h48
-rw-r--r--arch/x86/virt/vmx/tdx/tdx_global_metadata.c50
-rw-r--r--arch/x86/xen/enlighten_pv.c63
-rw-r--r--arch/x86/xen/mmu_pv.c4
-rw-r--r--arch/x86/xen/pmu.c73
-rw-r--r--arch/x86/xen/suspend.c7
-rw-r--r--arch/x86/xen/xen-ops.h5
517 files changed, 21207 insertions, 35164 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index e21cca404943..58d890fe2100 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -38,6 +38,7 @@ config X86_64
select ARCH_HAS_ELFCORE_COMPAT
select ZONE_DMA32
select EXECMEM if DYNAMIC_FTRACE
+ select ACPI_MRRM if ACPI
config FORCE_DYNAMIC_FTRACE
def_bool y
@@ -74,13 +75,11 @@ config X86
select ARCH_ENABLE_SPLIT_PMD_PTLOCK if (PGTABLE_LEVELS > 2) && (X86_64 || X86_PAE)
select ARCH_ENABLE_THP_MIGRATION if X86_64 && TRANSPARENT_HUGEPAGE
select ARCH_HAS_ACPI_TABLE_UPGRADE if ACPI
+ select ARCH_HAS_CPU_ATTACK_VECTORS if CPU_MITIGATIONS
select ARCH_HAS_CACHE_LINE_SIZE
select ARCH_HAS_CPU_CACHE_INVALIDATE_MEMREGION
select ARCH_HAS_CPU_FINALIZE_INIT
select ARCH_HAS_CPU_PASID if IOMMU_SVA
- select ARCH_HAS_CRC32
- select ARCH_HAS_CRC64 if X86_64
- select ARCH_HAS_CRC_T10DIF
select ARCH_HAS_CURRENT_STACK_POINTER
select ARCH_HAS_DEBUG_VIRTUAL
select ARCH_HAS_DEBUG_VM_PGTABLE if !X86_PAE
@@ -88,7 +87,7 @@ config X86
select ARCH_HAS_DMA_OPS if GART_IOMMU || XEN
select ARCH_HAS_EARLY_DEBUG if KGDB
select ARCH_HAS_ELF_RANDOMIZE
- select ARCH_HAS_EXECMEM_ROX if X86_64
+ select ARCH_HAS_EXECMEM_ROX if X86_64 && STRICT_MODULE_RWX
select ARCH_HAS_FAST_MULTIPLIER
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
@@ -100,7 +99,6 @@ config X86
select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
select ARCH_HAS_PMEM_API if X86_64
select ARCH_HAS_PREEMPT_LAZY
- select ARCH_HAS_PTE_DEVMAP if X86_64
select ARCH_HAS_PTE_SPECIAL
select ARCH_HAS_HW_PTE_YOUNG
select ARCH_HAS_NONLEAF_PMD_YOUNG if PGTABLE_LEVELS > 2
@@ -125,6 +123,7 @@ config X86
select ARCH_SUPPORTS_ACPI
select ARCH_SUPPORTS_ATOMIC_RMW
select ARCH_SUPPORTS_DEBUG_PAGEALLOC
+ select ARCH_SUPPORTS_HUGETLBFS
select ARCH_SUPPORTS_PAGE_TABLE_CHECK if X86_64
select ARCH_SUPPORTS_NUMA_BALANCING if X86_64
select ARCH_SUPPORTS_KMAP_LOCAL_FORCE_MAP if NR_CPUS <= 4096
@@ -146,13 +145,14 @@ config X86
select ARCH_WANTS_DYNAMIC_TASK_STRUCT
select ARCH_WANTS_NO_INSTR
select ARCH_WANT_GENERAL_HUGETLB
- select ARCH_WANT_HUGE_PMD_SHARE
+ select ARCH_WANT_HUGE_PMD_SHARE if X86_64
select ARCH_WANT_LD_ORPHAN_WARN
select ARCH_WANT_OPTIMIZE_DAX_VMEMMAP if X86_64
select ARCH_WANT_OPTIMIZE_HUGETLB_VMEMMAP if X86_64
select ARCH_WANT_HUGETLB_VMEMMAP_PREINIT if X86_64
select ARCH_WANTS_THP_SWAP if X86_64
select ARCH_HAS_PARANOID_L1D_FLUSH
+ select ARCH_WANT_IRQS_OFF_ACTIVATE_MM
select BUILDTIME_TABLE_SORT
select CLKEVT_I8253
select CLOCKSOURCE_WATCHDOG
@@ -202,13 +202,13 @@ config X86
select HAVE_ARCH_KFENCE
select HAVE_ARCH_KMSAN if X86_64
select HAVE_ARCH_KGDB
+ select HAVE_ARCH_KSTACK_ERASE
select HAVE_ARCH_MMAP_RND_BITS if MMU
select HAVE_ARCH_MMAP_RND_COMPAT_BITS if MMU && COMPAT
select HAVE_ARCH_COMPAT_MMAP_BASES if MMU && COMPAT
select HAVE_ARCH_PREL32_RELOCATIONS
select HAVE_ARCH_SECCOMP_FILTER
select HAVE_ARCH_THREAD_STRUCT_WHITELIST
- select HAVE_ARCH_STACKLEAK
select HAVE_ARCH_TRACEHOOK
select HAVE_ARCH_TRANSPARENT_HUGEPAGE
select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
@@ -242,7 +242,6 @@ config X86
select HAVE_GUP_FAST
select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE
select HAVE_FTRACE_GRAPH_FUNC if HAVE_FUNCTION_GRAPH_TRACER
- select HAVE_FTRACE_MCOUNT_RECORD
select HAVE_FUNCTION_GRAPH_FREGS if HAVE_FUNCTION_GRAPH_TRACER
select HAVE_FUNCTION_GRAPH_TRACER if X86_32 || (X86_64 && DYNAMIC_FTRACE)
select HAVE_FUNCTION_TRACER
@@ -426,8 +425,7 @@ config DYNAMIC_PHYSICAL_MASK
config PGTABLE_LEVELS
int
- default 5 if X86_5LEVEL
- default 4 if X86_64
+ default 5 if X86_64
default 3 if X86_PAE
default 2
@@ -507,8 +505,9 @@ config X86_MPPARSE
config X86_CPU_RESCTRL
bool "x86 CPU resource control support"
depends on X86 && (CPU_SUP_INTEL || CPU_SUP_AMD)
- select KERNFS
- select PROC_CPU_RESCTRL if PROC_FS
+ depends on MISC_FILESYSTEMS
+ select ARCH_HAS_CPU_RESCTRL
+ select RESCTRL_FS
select RESCTRL_FS_PSEUDO_LOCK
help
Enable x86 CPU resource control support.
@@ -526,12 +525,6 @@ config X86_CPU_RESCTRL
Say N if unsure.
-config RESCTRL_FS_PSEUDO_LOCK
- bool
- help
- Software mechanism to pin data in a cache portion using
- micro-architecture specific knowledge.
-
config X86_FRED
bool "Flexible Return and Event Delivery"
depends on X86_64
@@ -799,6 +792,7 @@ config PARAVIRT
config PARAVIRT_XXL
bool
+ depends on X86_64
config PARAVIRT_DEBUG
bool "paravirt-ops debugging"
@@ -1463,27 +1457,6 @@ config X86_PAE
has the cost of more pagetable lookup overhead, and also
consumes more pagetable space per process.
-config X86_5LEVEL
- bool "Enable 5-level page tables support"
- default y
- select DYNAMIC_MEMORY_LAYOUT
- select SPARSEMEM_VMEMMAP
- depends on X86_64
- help
- 5-level paging enables access to larger address space:
- up to 128 PiB of virtual address space and 4 PiB of
- physical address space.
-
- It will be supported by future Intel CPUs.
-
- A kernel with the option enabled can be booted on machines that
- support 4- or 5-level paging.
-
- See Documentation/arch/x86/x86_64/5level-paging.rst for more
- information.
-
- Say N if unsure.
-
config X86_DIRECT_GBPAGES
def_bool y
depends on X86_64
@@ -1579,6 +1552,7 @@ config ARCH_SPARSEMEM_ENABLE
def_bool y
select SPARSEMEM_STATIC if X86_32
select SPARSEMEM_VMEMMAP_ENABLE if X86_64
+ select SPARSEMEM_VMEMMAP if X86_64
config ARCH_SPARSEMEM_DEFAULT
def_bool X86_64 || (NUMA && X86_32)
@@ -1881,8 +1855,7 @@ endchoice
config X86_SGX
bool "Software Guard eXtensions (SGX)"
depends on X86_64 && CPU_SUP_INTEL && X86_X2APIC
- depends on CRYPTO=y
- depends on CRYPTO_SHA256=y
+ select CRYPTO_LIB_SHA256
select MMU_NOTIFIER
select NUMA_KEEP_MEMINFO if NUMA
select XARRAY_MULTI
@@ -2029,6 +2002,9 @@ config ARCH_SUPPORTS_KEXEC_BZIMAGE_VERIFY_SIG
config ARCH_SUPPORTS_KEXEC_JUMP
def_bool y
+config ARCH_SUPPORTS_KEXEC_HANDOVER
+ def_bool X86_64
+
config ARCH_SUPPORTS_CRASH_DUMP
def_bool X86_64 || (X86_32 && HIGHMEM)
@@ -2167,17 +2143,10 @@ config PHYSICAL_ALIGN
Don't change this unless you know what you are doing.
-config DYNAMIC_MEMORY_LAYOUT
- bool
- help
- This option makes base addresses of vmalloc and vmemmap as well as
- __PAGE_OFFSET movable during boot.
-
config RANDOMIZE_MEMORY
bool "Randomize the kernel memory sections"
depends on X86_64
depends on RANDOMIZE_BASE
- select DYNAMIC_MEMORY_LAYOUT
default RANDOMIZE_BASE
help
Randomizes the base virtual address of kernel memory sections
@@ -2723,6 +2692,15 @@ config MITIGATION_ITS
disabled, mitigation cannot be enabled via cmdline.
See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst>
+config MITIGATION_TSA
+ bool "Mitigate Transient Scheduler Attacks"
+ depends on CPU_SUP_AMD
+ default y
+ help
+ Enable mitigation for Transient Scheduler Attacks. TSA is a hardware
+ security vulnerability on AMD CPUs which can lead to forwarding of
+ invalid info to subsequent instructions and thus can affect their
+ timing and thereby cause a leakage.
endif
config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
index 6d20a6ce0507..c827f694fb72 100644
--- a/arch/x86/Kconfig.assembler
+++ b/arch/x86/Kconfig.assembler
@@ -6,20 +6,6 @@ config AS_AVX512
help
Supported by binutils >= 2.25 and LLVM integrated assembler
-config AS_SHA1_NI
- def_bool $(as-instr,sha1msg1 %xmm0$(comma)%xmm1)
- help
- Supported by binutils >= 2.24 and LLVM integrated assembler
-
-config AS_SHA256_NI
- def_bool $(as-instr,sha256msg1 %xmm0$(comma)%xmm1)
- help
- Supported by binutils >= 2.24 and LLVM integrated assembler
-config AS_TPAUSE
- def_bool $(as-instr,tpause %ecx)
- help
- Supported by binutils >= 2.31.1 and LLVM integrated assembler >= V7
-
config AS_GFNI
def_bool $(as-instr,vgf2p8mulb %xmm0$(comma)%xmm1$(comma)%xmm2)
help
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
index 753b8763abae..f928cf6e3252 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -245,6 +245,30 @@ config MATOM
endchoice
+config CC_HAS_MARCH_NATIVE
+ # This flag might not be available in cross-compilers:
+ def_bool $(cc-option, -march=native)
+ # LLVM 18 has an easily triggered internal compiler error in core
+ # networking code with '-march=native' on certain systems:
+ # https://github.com/llvm/llvm-project/issues/72026
+ # LLVM 19 introduces an optimization that resolves some high stack
+ # usage warnings that only appear wth '-march=native'.
+ depends on CC_IS_GCC || CLANG_VERSION >= 190100
+
+config X86_NATIVE_CPU
+ bool "Build and optimize for local/native CPU"
+ depends on X86_64
+ depends on CC_HAS_MARCH_NATIVE
+ help
+ Optimize for the current CPU used to compile the kernel.
+ Use this option if you intend to build the kernel for your
+ local machine.
+
+ Note that such a kernel might not work optimally on a
+ different x86 machine.
+
+ If unsure, say N.
+
config X86_GENERIC
bool "Generic x86 support"
depends on X86_32
diff --git a/arch/x86/Kconfig.cpufeatures b/arch/x86/Kconfig.cpufeatures
index e12d5b7e39a2..250c10627ab3 100644
--- a/arch/x86/Kconfig.cpufeatures
+++ b/arch/x86/Kconfig.cpufeatures
@@ -132,10 +132,6 @@ config X86_DISABLED_FEATURE_OSPKE
def_bool y
depends on !X86_INTEL_MEMORY_PROTECTION_KEYS
-config X86_DISABLED_FEATURE_LA57
- def_bool y
- depends on !X86_5LEVEL
-
config X86_DISABLED_FEATURE_PTI
def_bool y
depends on !MITIGATION_PAGE_TABLE_ISOLATION
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
index 594723005d95..1913d342969b 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
@@ -173,8 +173,13 @@ else
# Use -mskip-rax-setup if supported.
KBUILD_CFLAGS += $(call cc-option,-mskip-rax-setup)
+ifdef CONFIG_X86_NATIVE_CPU
+ KBUILD_CFLAGS += -march=native
+ KBUILD_RUSTFLAGS += -Ctarget-cpu=native
+else
KBUILD_CFLAGS += -march=x86-64 -mtune=generic
KBUILD_RUSTFLAGS += -Ctarget-cpu=x86-64 -Ztune-cpu=generic
+endif
KBUILD_CFLAGS += -mno-red-zone
KBUILD_CFLAGS += -mcmodel=kernel
@@ -281,6 +286,7 @@ archprepare: $(cpufeaturemasks.hdr)
###
# Kernel objects
+core-y += arch/x86/boot/startup/
libs-y += arch/x86/lib/
# drivers-y are linked after core-y
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index 640fcac3af74..3f9fb3698d66 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -71,7 +71,7 @@ $(obj)/vmlinux.bin: $(obj)/compressed/vmlinux FORCE
SETUP_OBJS = $(addprefix $(obj)/,$(setup-y))
-sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_e\?data\|z_.*\)$$/\#define ZO_\2 0x\1/p'
+sed-zoffset := -e 's/^\([0-9a-fA-F]*\) [a-zA-Z] \(startup_32\|efi.._stub_entry\|efi\(32\)\?_pe_entry\|input_data\|kernel_info\|_end\|_ehead\|_text\|_e\?data\|_e\?sbat\|z_.*\)$$/\#define ZO_\2 0x\1/p'
quiet_cmd_zoffset = ZOFFSET $@
cmd_zoffset = $(NM) $< | sed -n $(sed-zoffset) > $@
diff --git a/arch/x86/boot/bioscall.S b/arch/x86/boot/bioscall.S
index aa9b96457584..cf4a6155714e 100644
--- a/arch/x86/boot/bioscall.S
+++ b/arch/x86/boot/bioscall.S
@@ -32,7 +32,7 @@ intcall:
movw %dx, %si
movw %sp, %di
movw $11, %cx
- rep; movsl
+ rep movsl
/* Pop full state from the stack */
popal
@@ -67,7 +67,7 @@ intcall:
jz 4f
movw %sp, %si
movw $11, %cx
- rep; movsl
+ rep movsl
4: addw $44, %sp
/* Restore state and return */
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index 38f17a1e1e36..60580836daf7 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -34,7 +34,7 @@
extern struct setup_header hdr;
extern struct boot_params boot_params;
-#define cpu_relax() asm volatile("rep; nop")
+#define cpu_relax() asm volatile("pause")
static inline void io_delay(void)
{
@@ -155,14 +155,14 @@ static inline void wrgs32(u32 v, addr_t addr)
static inline bool memcmp_fs(const void *s1, addr_t s2, size_t len)
{
bool diff;
- asm volatile("fs; repe; cmpsb" CC_SET(nz)
+ asm volatile("fs repe cmpsb" CC_SET(nz)
: CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
return diff;
}
static inline bool memcmp_gs(const void *s1, addr_t s2, size_t len)
{
bool diff;
- asm volatile("gs; repe; cmpsb" CC_SET(nz)
+ asm volatile("gs repe cmpsb" CC_SET(nz)
: CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
return diff;
}
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index fdbce022db55..3a38fdcdb9bd 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -44,10 +44,10 @@ KBUILD_CFLAGS += -D__DISABLE_EXPORTS
KBUILD_CFLAGS += $(call cc-option,-Wa$(comma)-mrelax-relocations=no)
KBUILD_CFLAGS += -include $(srctree)/include/linux/hidden.h
-# sev.c indirectly includes inat-table.h which is generated during
+# sev-decode-insn.c indirectly includes inat-table.c which is generated during
# compilation and stored in $(objtree). Add the directory to the includes so
# that the compiler finds it even with out-of-tree builds (make O=/some/path).
-CFLAGS_sev.o += -I$(objtree)/arch/x86/lib/
+CFLAGS_sev-handle-vc.o += -I$(objtree)/arch/x86/lib/
KBUILD_AFLAGS := $(KBUILD_CFLAGS) -D__ASSEMBLY__
@@ -73,7 +73,7 @@ LDFLAGS_vmlinux += -T
hostprogs := mkpiggy
HOST_EXTRACFLAGS += -I$(srctree)/tools/include
-sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABCDGRSTVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
+sed-voffset := -e 's/^\([0-9a-fA-F]*\) [ABbCDGRSTtVW] \(_text\|__start_rodata\|__bss_start\|_end\)$$/\#define VO_\2 _AC(0x\1,UL)/p'
quiet_cmd_voffset = VOFFSET $@
cmd_voffset = $(NM) $< | sed -n $(sed-voffset) > $@
@@ -96,8 +96,7 @@ ifdef CONFIG_X86_64
vmlinux-objs-y += $(obj)/idt_64.o $(obj)/idt_handlers_64.o
vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/mem_encrypt.o
vmlinux-objs-y += $(obj)/pgtable_64.o
- vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o
- vmlinux-objs-y += $(obj)/la57toggle.o
+ vmlinux-objs-$(CONFIG_AMD_MEM_ENCRYPT) += $(obj)/sev.o $(obj)/sev-handle-vc.o
endif
vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
@@ -106,6 +105,12 @@ vmlinux-objs-$(CONFIG_UNACCEPTED_MEMORY) += $(obj)/mem.o
vmlinux-objs-$(CONFIG_EFI) += $(obj)/efi.o
vmlinux-libs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
+vmlinux-libs-$(CONFIG_X86_64) += $(objtree)/arch/x86/boot/startup/lib.a
+vmlinux-objs-$(CONFIG_EFI_SBAT) += $(obj)/sbat.o
+
+ifdef CONFIG_EFI_SBAT
+$(obj)/sbat.o: $(CONFIG_EFI_SBAT_FILE)
+endif
$(obj)/vmlinux: $(vmlinux-objs-y) $(vmlinux-libs-y) FORCE
$(call if_changed,ld)
diff --git a/arch/x86/boot/compressed/head_64.S b/arch/x86/boot/compressed/head_64.S
index eafd4f185e77..d9dab940ff62 100644
--- a/arch/x86/boot/compressed/head_64.S
+++ b/arch/x86/boot/compressed/head_64.S
@@ -35,7 +35,6 @@
#include <asm/bootparam.h>
#include <asm/desc_defs.h>
#include <asm/trapnr.h>
-#include "pgtable.h"
/*
* Fix alignment at 16 bytes. Following CONFIG_FUNCTION_ALIGNMENT will result
diff --git a/arch/x86/boot/compressed/kaslr.c b/arch/x86/boot/compressed/kaslr.c
index f03d59ea6e40..3b0948ad449f 100644
--- a/arch/x86/boot/compressed/kaslr.c
+++ b/arch/x86/boot/compressed/kaslr.c
@@ -760,6 +760,49 @@ static void process_e820_entries(unsigned long minimum,
}
}
+/*
+ * If KHO is active, only process its scratch areas to ensure we are not
+ * stepping onto preserved memory.
+ */
+static bool process_kho_entries(unsigned long minimum, unsigned long image_size)
+{
+ struct kho_scratch *kho_scratch;
+ struct setup_data *ptr;
+ struct kho_data *kho;
+ int i, nr_areas = 0;
+
+ if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER))
+ return false;
+
+ ptr = (struct setup_data *)(unsigned long)boot_params_ptr->hdr.setup_data;
+ while (ptr) {
+ if (ptr->type == SETUP_KEXEC_KHO) {
+ kho = (struct kho_data *)(unsigned long)ptr->data;
+ kho_scratch = (void *)(unsigned long)kho->scratch_addr;
+ nr_areas = kho->scratch_size / sizeof(*kho_scratch);
+ break;
+ }
+
+ ptr = (struct setup_data *)(unsigned long)ptr->next;
+ }
+
+ if (!nr_areas)
+ return false;
+
+ for (i = 0; i < nr_areas; i++) {
+ struct kho_scratch *area = &kho_scratch[i];
+ struct mem_vector region = {
+ .start = area->addr,
+ .size = area->size,
+ };
+
+ if (process_mem_region(&region, minimum, image_size))
+ break;
+ }
+
+ return true;
+}
+
static unsigned long find_random_phys_addr(unsigned long minimum,
unsigned long image_size)
{
@@ -775,7 +818,12 @@ static unsigned long find_random_phys_addr(unsigned long minimum,
return 0;
}
- if (!process_efi_entries(minimum, image_size))
+ /*
+ * During kexec handover only process KHO scratch areas that are known
+ * not to contain any data that must be preserved.
+ */
+ if (!process_kho_entries(minimum, image_size) &&
+ !process_efi_entries(minimum, image_size))
process_e820_entries(minimum, image_size);
phys_addr = slots_fetch_random();
diff --git a/arch/x86/boot/compressed/misc.c b/arch/x86/boot/compressed/misc.c
index 1cdcd4aaf395..94b5991da001 100644
--- a/arch/x86/boot/compressed/misc.c
+++ b/arch/x86/boot/compressed/misc.c
@@ -14,7 +14,6 @@
#include "misc.h"
#include "error.h"
-#include "pgtable.h"
#include "../string.h"
#include "../voffset.h"
#include <asm/bootparam_utils.h>
diff --git a/arch/x86/boot/compressed/misc.h b/arch/x86/boot/compressed/misc.h
index dd8d1a85f671..db1048621ea2 100644
--- a/arch/x86/boot/compressed/misc.h
+++ b/arch/x86/boot/compressed/misc.h
@@ -136,6 +136,9 @@ static inline void console_init(void)
#endif
#ifdef CONFIG_AMD_MEM_ENCRYPT
+struct es_em_ctxt;
+struct insn;
+
void sev_enable(struct boot_params *bp);
void snp_check_features(void);
void sev_es_shutdown_ghcb(void);
@@ -143,6 +146,11 @@ extern bool sev_es_check_ghcb_fault(unsigned long address);
void snp_set_page_private(unsigned long paddr);
void snp_set_page_shared(unsigned long paddr);
void sev_prep_identity_maps(unsigned long top_level_pgt);
+
+enum es_result vc_decode_insn(struct es_em_ctxt *ctxt);
+bool insn_has_rep_prefix(struct insn *insn);
+void sev_insn_decode_init(void);
+bool early_setup_ghcb(void);
#else
static inline void sev_enable(struct boot_params *bp)
{
diff --git a/arch/x86/boot/compressed/pgtable.h b/arch/x86/boot/compressed/pgtable.h
deleted file mode 100644
index 6d595abe06b3..000000000000
--- a/arch/x86/boot/compressed/pgtable.h
+++ /dev/null
@@ -1,18 +0,0 @@
-#ifndef BOOT_COMPRESSED_PAGETABLE_H
-#define BOOT_COMPRESSED_PAGETABLE_H
-
-#define TRAMPOLINE_32BIT_SIZE (2 * PAGE_SIZE)
-
-#define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE
-#define TRAMPOLINE_32BIT_CODE_SIZE 0xA0
-
-#ifndef __ASSEMBLER__
-
-extern unsigned long *trampoline_32bit;
-
-extern void trampoline_32bit_src(void *trampoline, bool enable_5lvl);
-
-extern const u16 trampoline_ljmp_imm_offset;
-
-#endif /* __ASSEMBLER__ */
-#endif /* BOOT_COMPRESSED_PAGETABLE_H */
diff --git a/arch/x86/boot/compressed/pgtable_64.c b/arch/x86/boot/compressed/pgtable_64.c
index d8c5de40669d..bdd26050dff7 100644
--- a/arch/x86/boot/compressed/pgtable_64.c
+++ b/arch/x86/boot/compressed/pgtable_64.c
@@ -4,19 +4,16 @@
#include <asm/bootparam_utils.h>
#include <asm/e820/types.h>
#include <asm/processor.h>
-#include "pgtable.h"
#include "../string.h"
#include "efi.h"
#define BIOS_START_MIN 0x20000U /* 128K, less than this is insane */
#define BIOS_START_MAX 0x9f000U /* 640K, absolute maximum */
-#ifdef CONFIG_X86_5LEVEL
/* __pgtable_l5_enabled needs to be in .data to avoid being cleared along with .bss */
unsigned int __section(".data") __pgtable_l5_enabled;
unsigned int __section(".data") pgdir_shift = 39;
unsigned int __section(".data") ptrs_per_p4d = 1;
-#endif
/* Buffer to preserve trampoline memory */
static char trampoline_save[TRAMPOLINE_32BIT_SIZE];
@@ -115,18 +112,13 @@ asmlinkage void configure_5level_paging(struct boot_params *bp, void *pgtable)
* Check if LA57 is desired and supported.
*
* There are several parts to the check:
- * - if the kernel supports 5-level paging: CONFIG_X86_5LEVEL=y
* - if user asked to disable 5-level paging: no5lvl in cmdline
* - if the machine supports 5-level paging:
* + CPUID leaf 7 is supported
* + the leaf has the feature bit set
- *
- * That's substitute for boot_cpu_has() in early boot code.
*/
- if (IS_ENABLED(CONFIG_X86_5LEVEL) &&
- !cmdline_find_option_bool("no5lvl") &&
- native_cpuid_eax(0) >= 7 &&
- (native_cpuid_ecx(7) & (1 << (X86_FEATURE_LA57 & 31)))) {
+ if (!cmdline_find_option_bool("no5lvl") &&
+ native_cpuid_eax(0) >= 7 && (native_cpuid_ecx(7) & BIT(16))) {
l5_required = true;
/* Initialize variables for 5-level paging */
diff --git a/arch/x86/boot/compressed/sbat.S b/arch/x86/boot/compressed/sbat.S
new file mode 100644
index 000000000000..838f70a997dd
--- /dev/null
+++ b/arch/x86/boot/compressed/sbat.S
@@ -0,0 +1,7 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Embed SBAT data in the kernel.
+ */
+ .pushsection ".sbat", "a", @progbits
+ .incbin CONFIG_EFI_SBAT_FILE
+ .popsection
diff --git a/arch/x86/boot/compressed/sev-handle-vc.c b/arch/x86/boot/compressed/sev-handle-vc.c
new file mode 100644
index 000000000000..89dd02de2a0f
--- /dev/null
+++ b/arch/x86/boot/compressed/sev-handle-vc.c
@@ -0,0 +1,134 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include "misc.h"
+#include "sev.h"
+
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <asm/insn.h>
+#include <asm/pgtable_types.h>
+#include <asm/ptrace.h>
+#include <asm/sev.h>
+#include <asm/trapnr.h>
+#include <asm/trap_pf.h>
+#include <asm/fpu/xcr.h>
+
+#define __BOOT_COMPRESSED
+
+/* Basic instruction decoding support needed */
+#include "../../lib/inat.c"
+#include "../../lib/insn.c"
+
+/*
+ * Copy a version of this function here - insn-eval.c can't be used in
+ * pre-decompression code.
+ */
+bool insn_has_rep_prefix(struct insn *insn)
+{
+ insn_byte_t p;
+ int i;
+
+ insn_get_prefixes(insn);
+
+ for_each_insn_prefix(insn, i, p) {
+ if (p == 0xf2 || p == 0xf3)
+ return true;
+ }
+
+ return false;
+}
+
+enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+{
+ char buffer[MAX_INSN_SIZE];
+ int ret;
+
+ memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
+
+ ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
+ if (ret < 0)
+ return ES_DECODE_FAILED;
+
+ return ES_OK;
+}
+
+extern void sev_insn_decode_init(void) __alias(inat_init_tables);
+
+/*
+ * Only a dummy for insn_get_seg_base() - Early boot-code is 64bit only and
+ * doesn't use segments.
+ */
+static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
+{
+ return 0UL;
+}
+
+static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
+ void *dst, char *buf, size_t size)
+{
+ memcpy(dst, buf, size);
+
+ return ES_OK;
+}
+
+static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
+ void *src, char *buf, size_t size)
+{
+ memcpy(buf, src, size);
+
+ return ES_OK;
+}
+
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+ return ES_OK;
+}
+
+static bool fault_in_kernel_space(unsigned long address)
+{
+ return false;
+}
+
+#define sev_printk(fmt, ...)
+
+#include "../../coco/sev/vc-shared.c"
+
+void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
+{
+ struct es_em_ctxt ctxt;
+ enum es_result result;
+
+ if (!boot_ghcb && !early_setup_ghcb())
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+
+ vc_ghcb_invalidate(boot_ghcb);
+ result = vc_init_em_ctxt(&ctxt, regs, exit_code);
+ if (result != ES_OK)
+ goto finish;
+
+ result = vc_check_opcode_bytes(&ctxt, exit_code);
+ if (result != ES_OK)
+ goto finish;
+
+ switch (exit_code) {
+ case SVM_EXIT_RDTSC:
+ case SVM_EXIT_RDTSCP:
+ result = vc_handle_rdtsc(boot_ghcb, &ctxt, exit_code);
+ break;
+ case SVM_EXIT_IOIO:
+ result = vc_handle_ioio(boot_ghcb, &ctxt);
+ break;
+ case SVM_EXIT_CPUID:
+ result = vc_handle_cpuid(boot_ghcb, &ctxt);
+ break;
+ default:
+ result = ES_UNSUPPORTED;
+ break;
+ }
+
+finish:
+ if (result == ES_OK)
+ vc_finish_insn(&ctxt);
+ else if (result != ES_RETRY)
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+}
diff --git a/arch/x86/boot/compressed/sev.c b/arch/x86/boot/compressed/sev.c
index 0003e4416efd..fd1b67dfea22 100644
--- a/arch/x86/boot/compressed/sev.c
+++ b/arch/x86/boot/compressed/sev.c
@@ -21,99 +21,14 @@
#include <asm/fpu/xcr.h>
#include <asm/ptrace.h>
#include <asm/svm.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include "error.h"
-#include "../msr.h"
+#include "sev.h"
static struct ghcb boot_ghcb_page __aligned(PAGE_SIZE);
struct ghcb *boot_ghcb;
-/*
- * Copy a version of this function here - insn-eval.c can't be used in
- * pre-decompression code.
- */
-static bool insn_has_rep_prefix(struct insn *insn)
-{
- insn_byte_t p;
- int i;
-
- insn_get_prefixes(insn);
-
- for_each_insn_prefix(insn, i, p) {
- if (p == 0xf2 || p == 0xf3)
- return true;
- }
-
- return false;
-}
-
-/*
- * Only a dummy for insn_get_seg_base() - Early boot-code is 64bit only and
- * doesn't use segments.
- */
-static unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
-{
- return 0UL;
-}
-
-static inline u64 sev_es_rd_ghcb_msr(void)
-{
- struct msr m;
-
- boot_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m);
-
- return m.q;
-}
-
-static inline void sev_es_wr_ghcb_msr(u64 val)
-{
- struct msr m;
-
- m.q = val;
- boot_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m);
-}
-
-static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
-{
- char buffer[MAX_INSN_SIZE];
- int ret;
-
- memcpy(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
-
- ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
- if (ret < 0)
- return ES_DECODE_FAILED;
-
- return ES_OK;
-}
-
-static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
- void *dst, char *buf, size_t size)
-{
- memcpy(dst, buf, size);
-
- return ES_OK;
-}
-
-static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
- void *src, char *buf, size_t size)
-{
- memcpy(buf, src, size);
-
- return ES_OK;
-}
-
-static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
-{
- return ES_OK;
-}
-
-static bool fault_in_kernel_space(unsigned long address)
-{
- return false;
-}
-
#undef __init
#define __init
@@ -122,24 +37,27 @@ static bool fault_in_kernel_space(unsigned long address)
#define __BOOT_COMPRESSED
-/* Basic instruction decoding support needed */
-#include "../../lib/inat.c"
-#include "../../lib/insn.c"
+extern struct svsm_ca *boot_svsm_caa;
+extern u64 boot_svsm_caa_pa;
-/* Include code for early handlers */
-#include "../../coco/sev/shared.c"
-
-static struct svsm_ca *svsm_get_caa(void)
+struct svsm_ca *svsm_get_caa(void)
{
return boot_svsm_caa;
}
-static u64 svsm_get_caa_pa(void)
+u64 svsm_get_caa_pa(void)
{
return boot_svsm_caa_pa;
}
-static int svsm_perform_call_protocol(struct svsm_call *call)
+int svsm_perform_call_protocol(struct svsm_call *call);
+
+u8 snp_vmpl;
+
+/* Include code for early handlers */
+#include "../../boot/startup/sev-shared.c"
+
+int svsm_perform_call_protocol(struct svsm_call *call)
{
struct ghcb *ghcb;
int ret;
@@ -157,7 +75,7 @@ static int svsm_perform_call_protocol(struct svsm_call *call)
return ret;
}
-bool sev_snp_enabled(void)
+static bool sev_snp_enabled(void)
{
return sev_status & MSR_AMD64_SEV_SNP_ENABLED;
}
@@ -212,7 +130,7 @@ void snp_set_page_shared(unsigned long paddr)
__page_state_change(paddr, SNP_PAGE_STATE_SHARED);
}
-static bool early_setup_ghcb(void)
+bool early_setup_ghcb(void)
{
if (set_page_decrypted((unsigned long)&boot_ghcb_page))
return false;
@@ -223,7 +141,7 @@ static bool early_setup_ghcb(void)
boot_ghcb = &boot_ghcb_page;
/* Initialize lookup tables for the instruction decoder */
- inat_init_tables();
+ sev_insn_decode_init();
/* SNP guest requires the GHCB GPA must be registered */
if (sev_snp_enabled())
@@ -296,46 +214,6 @@ bool sev_es_check_ghcb_fault(unsigned long address)
return ((address & PAGE_MASK) == (unsigned long)&boot_ghcb_page);
}
-void do_boot_stage2_vc(struct pt_regs *regs, unsigned long exit_code)
-{
- struct es_em_ctxt ctxt;
- enum es_result result;
-
- if (!boot_ghcb && !early_setup_ghcb())
- sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-
- vc_ghcb_invalidate(boot_ghcb);
- result = vc_init_em_ctxt(&ctxt, regs, exit_code);
- if (result != ES_OK)
- goto finish;
-
- result = vc_check_opcode_bytes(&ctxt, exit_code);
- if (result != ES_OK)
- goto finish;
-
- switch (exit_code) {
- case SVM_EXIT_RDTSC:
- case SVM_EXIT_RDTSCP:
- result = vc_handle_rdtsc(boot_ghcb, &ctxt, exit_code);
- break;
- case SVM_EXIT_IOIO:
- result = vc_handle_ioio(boot_ghcb, &ctxt);
- break;
- case SVM_EXIT_CPUID:
- result = vc_handle_cpuid(boot_ghcb, &ctxt);
- break;
- default:
- result = ES_UNSUPPORTED;
- break;
- }
-
-finish:
- if (result == ES_OK)
- vc_finish_insn(&ctxt);
- else if (result != ES_RETRY)
- sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-}
-
/*
* SNP_FEATURES_IMPL_REQ is the mask of SNP features that will need
* guest side implementation for proper functioning of the guest. If any
diff --git a/arch/x86/boot/compressed/sev.h b/arch/x86/boot/compressed/sev.h
index d3900384b8ab..92f79c21939c 100644
--- a/arch/x86/boot/compressed/sev.h
+++ b/arch/x86/boot/compressed/sev.h
@@ -10,14 +10,31 @@
#ifdef CONFIG_AMD_MEM_ENCRYPT
-bool sev_snp_enabled(void);
+#include "../msr.h"
+
void snp_accept_memory(phys_addr_t start, phys_addr_t end);
u64 sev_get_status(void);
bool early_is_sevsnp_guest(void);
+static inline u64 sev_es_rd_ghcb_msr(void)
+{
+ struct msr m;
+
+ boot_rdmsr(MSR_AMD64_SEV_ES_GHCB, &m);
+
+ return m.q;
+}
+
+static inline void sev_es_wr_ghcb_msr(u64 val)
+{
+ struct msr m;
+
+ m.q = val;
+ boot_wrmsr(MSR_AMD64_SEV_ES_GHCB, &m);
+}
+
#else
-static inline bool sev_snp_enabled(void) { return false; }
static inline void snp_accept_memory(phys_addr_t start, phys_addr_t end) { }
static inline u64 sev_get_status(void) { return 0; }
static inline bool early_is_sevsnp_guest(void) { return false; }
diff --git a/arch/x86/boot/compressed/string.c b/arch/x86/boot/compressed/string.c
index 81fc1eaa3229..9af19d9614cb 100644
--- a/arch/x86/boot/compressed/string.c
+++ b/arch/x86/boot/compressed/string.c
@@ -15,9 +15,9 @@ static void *____memcpy(void *dest, const void *src, size_t n)
{
int d0, d1, d2;
asm volatile(
- "rep ; movsl\n\t"
+ "rep movsl\n\t"
"movl %4,%%ecx\n\t"
- "rep ; movsb\n\t"
+ "rep movsb"
: "=&c" (d0), "=&D" (d1), "=&S" (d2)
: "0" (n >> 2), "g" (n & 3), "1" (dest), "2" (src)
: "memory");
@@ -29,9 +29,9 @@ static void *____memcpy(void *dest, const void *src, size_t n)
{
long d0, d1, d2;
asm volatile(
- "rep ; movsq\n\t"
+ "rep movsq\n\t"
"movq %4,%%rcx\n\t"
- "rep ; movsb\n\t"
+ "rep movsb"
: "=&c" (d0), "=&D" (d1), "=&S" (d2)
: "0" (n >> 3), "g" (n & 7), "1" (dest), "2" (src)
: "memory");
diff --git a/arch/x86/boot/compressed/vmlinux.lds.S b/arch/x86/boot/compressed/vmlinux.lds.S
index 3b2bc61c9408..587ce3e7c504 100644
--- a/arch/x86/boot/compressed/vmlinux.lds.S
+++ b/arch/x86/boot/compressed/vmlinux.lds.S
@@ -43,6 +43,14 @@ SECTIONS
*(.rodata.*)
_erodata = . ;
}
+#ifdef CONFIG_EFI_SBAT
+ .sbat : ALIGN(0x1000) {
+ _sbat = . ;
+ *(.sbat)
+ _esbat = ALIGN(0x1000);
+ . = _esbat;
+ }
+#endif
.data : ALIGN(0x1000) {
_data = . ;
*(.data)
diff --git a/arch/x86/boot/copy.S b/arch/x86/boot/copy.S
index 6afd05e819d2..3973a67cd04e 100644
--- a/arch/x86/boot/copy.S
+++ b/arch/x86/boot/copy.S
@@ -22,10 +22,10 @@ SYM_FUNC_START_NOALIGN(memcpy)
movw %dx, %si
pushw %cx
shrw $2, %cx
- rep; movsl
+ rep movsl
popw %cx
andw $3, %cx
- rep; movsb
+ rep movsb
popw %di
popw %si
retl
@@ -38,10 +38,10 @@ SYM_FUNC_START_NOALIGN(memset)
imull $0x01010101,%eax
pushw %cx
shrw $2, %cx
- rep; stosl
+ rep stosl
popw %cx
andw $3, %cx
- rep; stosb
+ rep stosb
popw %di
retl
SYM_FUNC_END(memset)
diff --git a/arch/x86/boot/cpuflags.c b/arch/x86/boot/cpuflags.c
index 916bac09b464..63e037e94e4c 100644
--- a/arch/x86/boot/cpuflags.c
+++ b/arch/x86/boot/cpuflags.c
@@ -106,5 +106,18 @@ void get_cpuflags(void)
cpuid(0x80000001, &ignored, &ignored, &cpu.flags[6],
&cpu.flags[1]);
}
+
+ if (max_amd_level >= 0x8000001f) {
+ u32 ebx;
+
+ /*
+ * The X86_FEATURE_COHERENCY_SFW_NO feature bit is in
+ * the virtualization flags entry (word 8) and set by
+ * scattered.c, so the bit needs to be explicitly set.
+ */
+ cpuid(0x8000001f, &ignored, &ebx, &ignored, &ignored);
+ if (ebx & BIT(31))
+ set_bit(X86_FEATURE_COHERENCY_SFW_NO, cpu.flags);
+ }
}
}
diff --git a/arch/x86/boot/header.S b/arch/x86/boot/header.S
index b5c79f43359b..9bea5a1e2c52 100644
--- a/arch/x86/boot/header.S
+++ b/arch/x86/boot/header.S
@@ -43,7 +43,7 @@ SYSSEG = 0x1000 /* historical load address >> 4 */
.section ".bstext", "ax"
#ifdef CONFIG_EFI_STUB
# "MZ", MS-DOS header
- .word MZ_MAGIC
+ .word IMAGE_DOS_SIGNATURE
.org 0x38
#
# Offset to the PE header.
@@ -51,16 +51,16 @@ SYSSEG = 0x1000 /* historical load address >> 4 */
.long LINUX_PE_MAGIC
.long pe_header
pe_header:
- .long PE_MAGIC
+ .long IMAGE_NT_SIGNATURE
coff_header:
#ifdef CONFIG_X86_32
.set image_file_add_flags, IMAGE_FILE_32BIT_MACHINE
- .set pe_opt_magic, PE_OPT_MAGIC_PE32
+ .set pe_opt_magic, IMAGE_NT_OPTIONAL_HDR32_MAGIC
.word IMAGE_FILE_MACHINE_I386
#else
.set image_file_add_flags, 0
- .set pe_opt_magic, PE_OPT_MAGIC_PE32PLUS
+ .set pe_opt_magic, IMAGE_NT_OPTIONAL_HDR64_MAGIC
.word IMAGE_FILE_MACHINE_AMD64
#endif
.word section_count # nr_sections
@@ -111,7 +111,7 @@ extra_header_fields:
.long salign # SizeOfHeaders
.long 0 # CheckSum
.word IMAGE_SUBSYSTEM_EFI_APPLICATION # Subsystem (EFI application)
- .word IMAGE_DLL_CHARACTERISTICS_NX_COMPAT # DllCharacteristics
+ .word IMAGE_DLLCHARACTERISTICS_NX_COMPAT # DllCharacteristics
#ifdef CONFIG_X86_32
.long 0 # SizeOfStackReserve
.long 0 # SizeOfStackCommit
@@ -179,15 +179,11 @@ pecompat_fstart:
#else
.set pecompat_fstart, setup_size
#endif
- .ascii ".text"
- .byte 0
- .byte 0
- .byte 0
- .long ZO__data
- .long setup_size
- .long ZO__data # Size of initialized data
- # on disk
- .long setup_size
+ .ascii ".text\0\0\0"
+ .long textsize # VirtualSize
+ .long setup_size # VirtualAddress
+ .long textsize # SizeOfRawData
+ .long setup_size # PointerToRawData
.long 0 # PointerToRelocations
.long 0 # PointerToLineNumbers
.word 0 # NumberOfRelocations
@@ -196,6 +192,23 @@ pecompat_fstart:
IMAGE_SCN_MEM_READ | \
IMAGE_SCN_MEM_EXECUTE # Characteristics
+#ifdef CONFIG_EFI_SBAT
+ .ascii ".sbat\0\0\0"
+ .long ZO__esbat - ZO__sbat # VirtualSize
+ .long setup_size + ZO__sbat # VirtualAddress
+ .long ZO__esbat - ZO__sbat # SizeOfRawData
+ .long setup_size + ZO__sbat # PointerToRawData
+
+ .long 0, 0, 0
+ .long IMAGE_SCN_CNT_INITIALIZED_DATA | \
+ IMAGE_SCN_MEM_READ | \
+ IMAGE_SCN_MEM_DISCARDABLE # Characteristics
+
+ .set textsize, ZO__sbat
+#else
+ .set textsize, ZO__data
+#endif
+
.ascii ".data\0\0\0"
.long ZO__end - ZO__data # VirtualSize
.long setup_size + ZO__data # VirtualAddress
@@ -361,12 +374,8 @@ xloadflags:
#endif
#ifdef CONFIG_X86_64
-#ifdef CONFIG_X86_5LEVEL
#define XLF56 (XLF_5LEVEL|XLF_5LEVEL_ENABLED)
#else
-#define XLF56 XLF_5LEVEL
-#endif
-#else
#define XLF56 0
#endif
@@ -585,7 +594,7 @@ start_of_setup:
xorl %eax, %eax
subw %di, %cx
shrw $2, %cx
- rep; stosl
+ rep stosl
# Jump to C code (should not return)
calll main
diff --git a/arch/x86/boot/startup/Makefile b/arch/x86/boot/startup/Makefile
new file mode 100644
index 000000000000..b514f7e81332
--- /dev/null
+++ b/arch/x86/boot/startup/Makefile
@@ -0,0 +1,30 @@
+# SPDX-License-Identifier: GPL-2.0
+
+KBUILD_AFLAGS += -D__DISABLE_EXPORTS
+KBUILD_CFLAGS += -D__DISABLE_EXPORTS -mcmodel=small -fPIC \
+ -Os -DDISABLE_BRANCH_PROFILING \
+ $(DISABLE_STACKLEAK_PLUGIN) \
+ -fno-stack-protector -D__NO_FORTIFY \
+ -fno-jump-tables \
+ -include $(srctree)/include/linux/hidden.h
+
+# disable ftrace hooks and LTO
+KBUILD_CFLAGS := $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS))
+KBUILD_CFLAGS := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS))
+KASAN_SANITIZE := n
+KCSAN_SANITIZE := n
+KMSAN_SANITIZE := n
+UBSAN_SANITIZE := n
+KCOV_INSTRUMENT := n
+
+obj-$(CONFIG_X86_64) += gdt_idt.o map_kernel.o
+obj-$(CONFIG_AMD_MEM_ENCRYPT) += sme.o sev-startup.o
+
+lib-$(CONFIG_X86_64) += la57toggle.o
+lib-$(CONFIG_EFI_MIXED) += efi-mixed.o
+
+#
+# Disable objtool validation for all library code, which is intended
+# to be linked into the decompressor or the EFI stub but not vmlinux
+#
+$(patsubst %.o,$(obj)/%.o,$(lib-y)): OBJECT_FILES_NON_STANDARD := y
diff --git a/arch/x86/boot/startup/efi-mixed.S b/arch/x86/boot/startup/efi-mixed.S
new file mode 100644
index 000000000000..e04ed99bc449
--- /dev/null
+++ b/arch/x86/boot/startup/efi-mixed.S
@@ -0,0 +1,253 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2014, 2015 Intel Corporation; author Matt Fleming
+ *
+ * Early support for invoking 32-bit EFI services from a 64-bit kernel.
+ *
+ * Because this thunking occurs before ExitBootServices() we have to
+ * restore the firmware's 32-bit GDT and IDT before we make EFI service
+ * calls.
+ *
+ * On the plus side, we don't have to worry about mangling 64-bit
+ * addresses into 32-bits because we're executing with an identity
+ * mapped pagetable and haven't transitioned to 64-bit virtual addresses
+ * yet.
+ */
+
+#include <linux/linkage.h>
+#include <asm/desc_defs.h>
+#include <asm/msr.h>
+#include <asm/page_types.h>
+#include <asm/pgtable_types.h>
+#include <asm/processor-flags.h>
+#include <asm/segment.h>
+
+ .text
+ .code32
+#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
+SYM_FUNC_START(efi32_stub_entry)
+ call 1f
+1: popl %ecx
+
+ /* Clear BSS */
+ xorl %eax, %eax
+ leal (_bss - 1b)(%ecx), %edi
+ leal (_ebss - 1b)(%ecx), %ecx
+ subl %edi, %ecx
+ shrl $2, %ecx
+ cld
+ rep stosl
+
+ add $0x4, %esp /* Discard return address */
+ movl 8(%esp), %ebx /* struct boot_params pointer */
+ jmp efi32_startup
+SYM_FUNC_END(efi32_stub_entry)
+#endif
+
+/*
+ * Called using a far call from __efi64_thunk() below, using the x86_64 SysV
+ * ABI (except for R8/R9 which are inaccessible to 32-bit code - EAX/EBX are
+ * used instead). EBP+16 points to the arguments passed via the stack.
+ *
+ * The first argument (EDI) is a pointer to the boot service or protocol, to
+ * which the remaining arguments are passed, each truncated to 32 bits.
+ */
+SYM_FUNC_START_LOCAL(efi_enter32)
+ /*
+ * Convert x86-64 SysV ABI params to i386 ABI
+ */
+ pushl 32(%ebp) /* Up to 3 args passed via the stack */
+ pushl 24(%ebp)
+ pushl 16(%ebp)
+ pushl %ebx /* R9 */
+ pushl %eax /* R8 */
+ pushl %ecx
+ pushl %edx
+ pushl %esi
+
+ /* Disable paging */
+ movl %cr0, %eax
+ btrl $X86_CR0_PG_BIT, %eax
+ movl %eax, %cr0
+
+ /* Disable long mode via EFER */
+ movl $MSR_EFER, %ecx
+ rdmsr
+ btrl $_EFER_LME, %eax
+ wrmsr
+
+ call *%edi
+
+ /* We must preserve return value */
+ movl %eax, %edi
+
+ call efi32_enable_long_mode
+
+ addl $32, %esp
+ movl %edi, %eax
+ lret
+SYM_FUNC_END(efi_enter32)
+
+ .code64
+SYM_FUNC_START(__efi64_thunk)
+ push %rbp
+ movl %esp, %ebp
+ push %rbx
+
+ /* Move args #5 and #6 into 32-bit accessible registers */
+ movl %r8d, %eax
+ movl %r9d, %ebx
+
+ lcalll *efi32_call(%rip)
+
+ pop %rbx
+ pop %rbp
+ RET
+SYM_FUNC_END(__efi64_thunk)
+
+ .code32
+SYM_FUNC_START_LOCAL(efi32_enable_long_mode)
+ movl %cr4, %eax
+ btsl $(X86_CR4_PAE_BIT), %eax
+ movl %eax, %cr4
+
+ movl $MSR_EFER, %ecx
+ rdmsr
+ btsl $_EFER_LME, %eax
+ wrmsr
+
+ /* Disable interrupts - the firmware's IDT does not work in long mode */
+ cli
+
+ /* Enable paging */
+ movl %cr0, %eax
+ btsl $X86_CR0_PG_BIT, %eax
+ movl %eax, %cr0
+ ret
+SYM_FUNC_END(efi32_enable_long_mode)
+
+/*
+ * This is the common EFI stub entry point for mixed mode. It sets up the GDT
+ * and page tables needed for 64-bit execution, after which it calls the
+ * common 64-bit EFI entrypoint efi_stub_entry().
+ *
+ * Arguments: 0(%esp) image handle
+ * 4(%esp) EFI system table pointer
+ * %ebx struct boot_params pointer (or NULL)
+ *
+ * Since this is the point of no return for ordinary execution, no registers
+ * are considered live except for the function parameters. [Note that the EFI
+ * stub may still exit and return to the firmware using the Exit() EFI boot
+ * service.]
+ */
+SYM_FUNC_START_LOCAL(efi32_startup)
+ movl %esp, %ebp
+
+ subl $8, %esp
+ sgdtl (%esp) /* Save GDT descriptor to the stack */
+ movl 2(%esp), %esi /* Existing GDT pointer */
+ movzwl (%esp), %ecx /* Existing GDT limit */
+ inc %ecx /* Existing GDT size */
+ andl $~7, %ecx /* Ensure size is multiple of 8 */
+
+ subl %ecx, %esp /* Allocate new GDT */
+ andl $~15, %esp /* Realign the stack */
+ movl %esp, %edi /* New GDT address */
+ leal 7(%ecx), %eax /* New GDT limit */
+ pushw %cx /* Push 64-bit CS (for LJMP below) */
+ pushl %edi /* Push new GDT address */
+ pushw %ax /* Push new GDT limit */
+
+ /* Copy GDT to the stack and add a 64-bit code segment at the end */
+ movl $GDT_ENTRY(DESC_CODE64, 0, 0xfffff) & 0xffffffff, (%edi,%ecx)
+ movl $GDT_ENTRY(DESC_CODE64, 0, 0xfffff) >> 32, 4(%edi,%ecx)
+ shrl $2, %ecx
+ cld
+ rep movsl /* Copy the firmware GDT */
+ lgdtl (%esp) /* Switch to the new GDT */
+
+ call 1f
+1: pop %edi
+
+ /* Record mixed mode entry */
+ movb $0x0, (efi_is64 - 1b)(%edi)
+
+ /* Set up indirect far call to re-enter 32-bit mode */
+ leal (efi32_call - 1b)(%edi), %eax
+ addl %eax, (%eax)
+ movw %cs, 4(%eax)
+
+ /* Disable paging */
+ movl %cr0, %eax
+ btrl $X86_CR0_PG_BIT, %eax
+ movl %eax, %cr0
+
+ /* Set up 1:1 mapping */
+ leal (pte - 1b)(%edi), %eax
+ movl $_PAGE_PRESENT | _PAGE_RW | _PAGE_PSE, %ecx
+ leal (_PAGE_PRESENT | _PAGE_RW)(%eax), %edx
+2: movl %ecx, (%eax)
+ addl $8, %eax
+ addl $PMD_SIZE, %ecx
+ jnc 2b
+
+ movl $PAGE_SIZE, %ecx
+ .irpc l, 0123
+ movl %edx, \l * 8(%eax)
+ addl %ecx, %edx
+ .endr
+ addl %ecx, %eax
+ movl %edx, (%eax)
+ movl %eax, %cr3
+
+ call efi32_enable_long_mode
+
+ /* Set up far jump to 64-bit mode (CS is already on the stack) */
+ leal (efi_stub_entry - 1b)(%edi), %eax
+ movl %eax, 2(%esp)
+
+ movl 0(%ebp), %edi
+ movl 4(%ebp), %esi
+ movl %ebx, %edx
+ ljmpl *2(%esp)
+SYM_FUNC_END(efi32_startup)
+
+/*
+ * efi_status_t efi32_pe_entry(efi_handle_t image_handle,
+ * efi_system_table_32_t *sys_table)
+ */
+SYM_FUNC_START(efi32_pe_entry)
+ pushl %ebx // save callee-save registers
+
+ /* Check whether the CPU supports long mode */
+ movl $0x80000001, %eax // assume extended info support
+ cpuid
+ btl $29, %edx // check long mode bit
+ jnc 1f
+ leal 8(%esp), %esp // preserve stack alignment
+ xor %ebx, %ebx // no struct boot_params pointer
+ jmp efi32_startup // only ESP and EBX remain live
+1: movl $0x80000003, %eax // EFI_UNSUPPORTED
+ popl %ebx
+ RET
+SYM_FUNC_END(efi32_pe_entry)
+
+#ifdef CONFIG_EFI_HANDOVER_PROTOCOL
+ .org efi32_stub_entry + 0x200
+ .code64
+SYM_FUNC_START_NOALIGN(efi64_stub_entry)
+ jmp efi_handover_entry
+SYM_FUNC_END(efi64_stub_entry)
+#endif
+
+ .data
+ .balign 8
+SYM_DATA_START_LOCAL(efi32_call)
+ .long efi_enter32 - .
+ .word 0x0
+SYM_DATA_END(efi32_call)
+SYM_DATA(efi_is64, .byte 1)
+
+ .bss
+ .balign PAGE_SIZE
+SYM_DATA_LOCAL(pte, .fill 6 * PAGE_SIZE, 1, 0)
diff --git a/arch/x86/boot/startup/gdt_idt.c b/arch/x86/boot/startup/gdt_idt.c
new file mode 100644
index 000000000000..a3112a69b06a
--- /dev/null
+++ b/arch/x86/boot/startup/gdt_idt.c
@@ -0,0 +1,71 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/linkage.h>
+#include <linux/types.h>
+
+#include <asm/desc.h>
+#include <asm/init.h>
+#include <asm/setup.h>
+#include <asm/sev.h>
+#include <asm/trapnr.h>
+
+/*
+ * Data structures and code used for IDT setup in head_64.S. The bringup-IDT is
+ * used until the idt_table takes over. On the boot CPU this happens in
+ * x86_64_start_kernel(), on secondary CPUs in start_secondary(). In both cases
+ * this happens in the functions called from head_64.S.
+ *
+ * The idt_table can't be used that early because all the code modifying it is
+ * in idt.c and can be instrumented by tracing or KASAN, which both don't work
+ * during early CPU bringup. Also the idt_table has the runtime vectors
+ * configured which require certain CPU state to be setup already (like TSS),
+ * which also hasn't happened yet in early CPU bringup.
+ */
+static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data;
+
+/* This may run while still in the direct mapping */
+void __head startup_64_load_idt(void *vc_handler)
+{
+ struct desc_ptr desc = {
+ .address = (unsigned long)rip_rel_ptr(bringup_idt_table),
+ .size = sizeof(bringup_idt_table) - 1,
+ };
+ struct idt_data data;
+ gate_desc idt_desc;
+
+ /* @vc_handler is set only for a VMM Communication Exception */
+ if (vc_handler) {
+ init_idt_data(&data, X86_TRAP_VC, vc_handler);
+ idt_init_desc(&idt_desc, &data);
+ native_write_idt_entry((gate_desc *)desc.address, X86_TRAP_VC, &idt_desc);
+ }
+
+ native_load_idt(&desc);
+}
+
+/*
+ * Setup boot CPU state needed before kernel switches to virtual addresses.
+ */
+void __head startup_64_setup_gdt_idt(void)
+{
+ struct gdt_page *gp = rip_rel_ptr((void *)(__force unsigned long)&gdt_page);
+ void *handler = NULL;
+
+ struct desc_ptr startup_gdt_descr = {
+ .address = (unsigned long)gp->gdt,
+ .size = GDT_SIZE - 1,
+ };
+
+ /* Load GDT */
+ native_load_gdt(&startup_gdt_descr);
+
+ /* New GDT is live - reload data segment registers */
+ asm volatile("movl %%eax, %%ds\n"
+ "movl %%eax, %%ss\n"
+ "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory");
+
+ if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
+ handler = rip_rel_ptr(vc_no_ghcb);
+
+ startup_64_load_idt(handler);
+}
diff --git a/arch/x86/boot/compressed/la57toggle.S b/arch/x86/boot/startup/la57toggle.S
index 9ee002387eb1..370075b4d95b 100644
--- a/arch/x86/boot/compressed/la57toggle.S
+++ b/arch/x86/boot/startup/la57toggle.S
@@ -5,7 +5,6 @@
#include <asm/boot.h>
#include <asm/msr.h>
#include <asm/processor-flags.h>
-#include "pgtable.h"
/*
* This is the 32-bit trampoline that will be copied over to low memory. It
diff --git a/arch/x86/boot/startup/map_kernel.c b/arch/x86/boot/startup/map_kernel.c
new file mode 100644
index 000000000000..332dbe6688c4
--- /dev/null
+++ b/arch/x86/boot/startup/map_kernel.c
@@ -0,0 +1,217 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/init.h>
+#include <linux/linkage.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/pgtable.h>
+
+#include <asm/init.h>
+#include <asm/sections.h>
+#include <asm/setup.h>
+#include <asm/sev.h>
+
+extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
+extern unsigned int next_early_pgt;
+
+static inline bool check_la57_support(void)
+{
+ /*
+ * 5-level paging is detected and enabled at kernel decompression
+ * stage. Only check if it has been enabled there.
+ */
+ if (!(native_read_cr4() & X86_CR4_LA57))
+ return false;
+
+ __pgtable_l5_enabled = 1;
+ pgdir_shift = 48;
+ ptrs_per_p4d = 512;
+
+ return true;
+}
+
+static unsigned long __head sme_postprocess_startup(struct boot_params *bp,
+ pmdval_t *pmd,
+ unsigned long p2v_offset)
+{
+ unsigned long paddr, paddr_end;
+ int i;
+
+ /* Encrypt the kernel and related (if SME is active) */
+ sme_encrypt_kernel(bp);
+
+ /*
+ * Clear the memory encryption mask from the .bss..decrypted section.
+ * The bss section will be memset to zero later in the initialization so
+ * there is no need to zero it after changing the memory encryption
+ * attribute.
+ */
+ if (sme_get_me_mask()) {
+ paddr = (unsigned long)rip_rel_ptr(__start_bss_decrypted);
+ paddr_end = (unsigned long)rip_rel_ptr(__end_bss_decrypted);
+
+ for (; paddr < paddr_end; paddr += PMD_SIZE) {
+ /*
+ * On SNP, transition the page to shared in the RMP table so that
+ * it is consistent with the page table attribute change.
+ *
+ * __start_bss_decrypted has a virtual address in the high range
+ * mapping (kernel .text). PVALIDATE, by way of
+ * early_snp_set_memory_shared(), requires a valid virtual
+ * address but the kernel is currently running off of the identity
+ * mapping so use the PA to get a *currently* valid virtual address.
+ */
+ early_snp_set_memory_shared(paddr, paddr, PTRS_PER_PMD);
+
+ i = pmd_index(paddr - p2v_offset);
+ pmd[i] -= sme_get_me_mask();
+ }
+ }
+
+ /*
+ * Return the SME encryption mask (if SME is active) to be used as a
+ * modifier for the initial pgdir entry programmed into CR3.
+ */
+ return sme_get_me_mask();
+}
+
+/*
+ * This code is compiled using PIC codegen because it will execute from the
+ * early 1:1 mapping of memory, which deviates from the mapping expected by the
+ * linker. Due to this deviation, taking the address of a global variable will
+ * produce an ambiguous result when using the plain & operator. Instead,
+ * rip_rel_ptr() must be used, which will return the RIP-relative address in
+ * the 1:1 mapping of memory. Kernel virtual addresses can be determined by
+ * subtracting p2v_offset from the RIP-relative address.
+ */
+unsigned long __head __startup_64(unsigned long p2v_offset,
+ struct boot_params *bp)
+{
+ pmd_t (*early_pgts)[PTRS_PER_PMD] = rip_rel_ptr(early_dynamic_pgts);
+ unsigned long physaddr = (unsigned long)rip_rel_ptr(_text);
+ unsigned long va_text, va_end;
+ unsigned long pgtable_flags;
+ unsigned long load_delta;
+ pgdval_t *pgd;
+ p4dval_t *p4d;
+ pudval_t *pud;
+ pmdval_t *pmd, pmd_entry;
+ bool la57;
+ int i;
+
+ la57 = check_la57_support();
+
+ /* Is the address too large? */
+ if (physaddr >> MAX_PHYSMEM_BITS)
+ for (;;);
+
+ /*
+ * Compute the delta between the address I am compiled to run at
+ * and the address I am actually running at.
+ */
+ phys_base = load_delta = __START_KERNEL_map + p2v_offset;
+
+ /* Is the address not 2M aligned? */
+ if (load_delta & ~PMD_MASK)
+ for (;;);
+
+ va_text = physaddr - p2v_offset;
+ va_end = (unsigned long)rip_rel_ptr(_end) - p2v_offset;
+
+ /* Include the SME encryption mask in the fixup value */
+ load_delta += sme_get_me_mask();
+
+ /* Fixup the physical addresses in the page table */
+
+ pgd = rip_rel_ptr(early_top_pgt);
+ pgd[pgd_index(__START_KERNEL_map)] += load_delta;
+
+ if (la57) {
+ p4d = (p4dval_t *)rip_rel_ptr(level4_kernel_pgt);
+ p4d[MAX_PTRS_PER_P4D - 1] += load_delta;
+
+ pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE;
+ }
+
+ level3_kernel_pgt[PTRS_PER_PUD - 2].pud += load_delta;
+ level3_kernel_pgt[PTRS_PER_PUD - 1].pud += load_delta;
+
+ for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
+ level2_fixmap_pgt[i].pmd += load_delta;
+
+ /*
+ * Set up the identity mapping for the switchover. These
+ * entries should *NOT* have the global bit set! This also
+ * creates a bunch of nonsense entries but that is fine --
+ * it avoids problems around wraparound.
+ */
+
+ pud = &early_pgts[0]->pmd;
+ pmd = &early_pgts[1]->pmd;
+ next_early_pgt = 2;
+
+ pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
+
+ if (la57) {
+ p4d = &early_pgts[next_early_pgt++]->pmd;
+
+ i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
+ pgd[i + 0] = (pgdval_t)p4d + pgtable_flags;
+ pgd[i + 1] = (pgdval_t)p4d + pgtable_flags;
+
+ i = physaddr >> P4D_SHIFT;
+ p4d[(i + 0) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
+ p4d[(i + 1) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
+ } else {
+ i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
+ pgd[i + 0] = (pgdval_t)pud + pgtable_flags;
+ pgd[i + 1] = (pgdval_t)pud + pgtable_flags;
+ }
+
+ i = physaddr >> PUD_SHIFT;
+ pud[(i + 0) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
+ pud[(i + 1) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
+
+ pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
+ pmd_entry += sme_get_me_mask();
+ pmd_entry += physaddr;
+
+ for (i = 0; i < DIV_ROUND_UP(va_end - va_text, PMD_SIZE); i++) {
+ int idx = i + (physaddr >> PMD_SHIFT);
+
+ pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE;
+ }
+
+ /*
+ * Fixup the kernel text+data virtual addresses. Note that
+ * we might write invalid pmds, when the kernel is relocated
+ * cleanup_highmap() fixes this up along with the mappings
+ * beyond _end.
+ *
+ * Only the region occupied by the kernel image has so far
+ * been checked against the table of usable memory regions
+ * provided by the firmware, so invalidate pages outside that
+ * region. A page table entry that maps to a reserved area of
+ * memory would allow processor speculation into that area,
+ * and on some hardware (particularly the UV platform) even
+ * speculative access to some reserved areas is caught as an
+ * error, causing the BIOS to halt the system.
+ */
+
+ pmd = rip_rel_ptr(level2_kernel_pgt);
+
+ /* invalidate pages before the kernel image */
+ for (i = 0; i < pmd_index(va_text); i++)
+ pmd[i] &= ~_PAGE_PRESENT;
+
+ /* fixup pages that are part of the kernel image */
+ for (; i <= pmd_index(va_end); i++)
+ if (pmd[i] & _PAGE_PRESENT)
+ pmd[i] += load_delta;
+
+ /* invalidate pages after the kernel image */
+ for (; i < PTRS_PER_PMD; i++)
+ pmd[i] &= ~_PAGE_PRESENT;
+
+ return sme_postprocess_startup(bp, pmd, p2v_offset);
+}
diff --git a/arch/x86/coco/sev/shared.c b/arch/x86/boot/startup/sev-shared.c
index 2e4122f8aa6b..ac7dfd21ddd4 100644
--- a/arch/x86/coco/sev/shared.c
+++ b/arch/x86/boot/startup/sev-shared.c
@@ -14,76 +14,23 @@
#ifndef __BOOT_COMPRESSED
#define error(v) pr_err(v)
#define has_cpuflag(f) boot_cpu_has(f)
-#define sev_printk(fmt, ...) printk(fmt, ##__VA_ARGS__)
-#define sev_printk_rtl(fmt, ...) printk_ratelimited(fmt, ##__VA_ARGS__)
#else
#undef WARN
#define WARN(condition, format...) (!!(condition))
-#define sev_printk(fmt, ...)
-#define sev_printk_rtl(fmt, ...)
#undef vc_forward_exception
#define vc_forward_exception(c) panic("SNP: Hypervisor requested exception\n")
#endif
/*
* SVSM related information:
- * When running under an SVSM, the VMPL that Linux is executing at must be
- * non-zero. The VMPL is therefore used to indicate the presence of an SVSM.
- *
* During boot, the page tables are set up as identity mapped and later
* changed to use kernel virtual addresses. Maintain separate virtual and
* physical addresses for the CAA to allow SVSM functions to be used during
* early boot, both with identity mapped virtual addresses and proper kernel
* virtual addresses.
*/
-u8 snp_vmpl __ro_after_init;
-EXPORT_SYMBOL_GPL(snp_vmpl);
-static struct svsm_ca *boot_svsm_caa __ro_after_init;
-static u64 boot_svsm_caa_pa __ro_after_init;
-
-static struct svsm_ca *svsm_get_caa(void);
-static u64 svsm_get_caa_pa(void);
-static int svsm_perform_call_protocol(struct svsm_call *call);
-
-/* I/O parameters for CPUID-related helpers */
-struct cpuid_leaf {
- u32 fn;
- u32 subfn;
- u32 eax;
- u32 ebx;
- u32 ecx;
- u32 edx;
-};
-
-/*
- * Individual entries of the SNP CPUID table, as defined by the SNP
- * Firmware ABI, Revision 0.9, Section 7.1, Table 14.
- */
-struct snp_cpuid_fn {
- u32 eax_in;
- u32 ecx_in;
- u64 xcr0_in;
- u64 xss_in;
- u32 eax;
- u32 ebx;
- u32 ecx;
- u32 edx;
- u64 __reserved;
-} __packed;
-
-/*
- * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9,
- * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit
- * of 64 entries per CPUID table.
- */
-#define SNP_CPUID_COUNT_MAX 64
-
-struct snp_cpuid_table {
- u32 count;
- u32 __reserved1;
- u64 __reserved2;
- struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX];
-} __packed;
+struct svsm_ca *boot_svsm_caa __ro_after_init;
+u64 boot_svsm_caa_pa __ro_after_init;
/*
* Since feature negotiation related variables are set early in the boot
@@ -107,7 +54,7 @@ static u32 cpuid_std_range_max __ro_after_init;
static u32 cpuid_hyp_range_max __ro_after_init;
static u32 cpuid_ext_range_max __ro_after_init;
-static bool __init sev_es_check_cpu_features(void)
+bool __init sev_es_check_cpu_features(void)
{
if (!has_cpuflag(X86_FEATURE_RDRAND)) {
error("RDRAND instruction not supported - no trusted source of randomness available\n");
@@ -117,7 +64,7 @@ static bool __init sev_es_check_cpu_features(void)
return true;
}
-static void __head __noreturn
+void __head __noreturn
sev_es_terminate(unsigned int set, unsigned int reason)
{
u64 val = GHCB_MSR_TERM_REQ;
@@ -136,7 +83,7 @@ sev_es_terminate(unsigned int set, unsigned int reason)
/*
* The hypervisor features are available from GHCB version 2 onward.
*/
-static u64 get_hv_features(void)
+u64 get_hv_features(void)
{
u64 val;
@@ -153,7 +100,7 @@ static u64 get_hv_features(void)
return GHCB_MSR_HV_FT_RESP_VAL(val);
}
-static void snp_register_ghcb_early(unsigned long paddr)
+void snp_register_ghcb_early(unsigned long paddr)
{
unsigned long pfn = paddr >> PAGE_SHIFT;
u64 val;
@@ -169,7 +116,7 @@ static void snp_register_ghcb_early(unsigned long paddr)
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_REGISTER);
}
-static bool sev_es_negotiate_protocol(void)
+bool sev_es_negotiate_protocol(void)
{
u64 val;
@@ -190,39 +137,6 @@ static bool sev_es_negotiate_protocol(void)
return true;
}
-static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb)
-{
- ghcb->save.sw_exit_code = 0;
- __builtin_memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
-}
-
-static bool vc_decoding_needed(unsigned long exit_code)
-{
- /* Exceptions don't require to decode the instruction */
- return !(exit_code >= SVM_EXIT_EXCP_BASE &&
- exit_code <= SVM_EXIT_LAST_EXCP);
-}
-
-static enum es_result vc_init_em_ctxt(struct es_em_ctxt *ctxt,
- struct pt_regs *regs,
- unsigned long exit_code)
-{
- enum es_result ret = ES_OK;
-
- memset(ctxt, 0, sizeof(*ctxt));
- ctxt->regs = regs;
-
- if (vc_decoding_needed(exit_code))
- ret = vc_decode_insn(ctxt);
-
- return ret;
-}
-
-static void vc_finish_insn(struct es_em_ctxt *ctxt)
-{
- ctxt->regs->ip += ctxt->insn.length;
-}
-
static enum es_result verify_exception_info(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
{
u32 ret;
@@ -344,7 +258,7 @@ static int svsm_perform_ghcb_protocol(struct ghcb *ghcb, struct svsm_call *call)
* Fill in protocol and format specifiers. This can be called very early
* in the boot, so use rip-relative references as needed.
*/
- ghcb->protocol_version = RIP_REL_REF(ghcb_version);
+ ghcb->protocol_version = ghcb_version;
ghcb->ghcb_usage = GHCB_DEFAULT_USAGE;
ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_SNP_RUN_VMPL);
@@ -371,10 +285,10 @@ static int svsm_perform_ghcb_protocol(struct ghcb *ghcb, struct svsm_call *call)
return svsm_process_result_codes(call);
}
-static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
- struct es_em_ctxt *ctxt,
- u64 exit_code, u64 exit_info_1,
- u64 exit_info_2)
+enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt,
+ u64 exit_code, u64 exit_info_1,
+ u64 exit_info_2)
{
/* Fill in protocol and format specifiers */
ghcb->protocol_version = ghcb_version;
@@ -473,9 +387,9 @@ static int sev_cpuid_hv(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid
* while running with the initial identity mapping as well as the
* switch-over to kernel virtual addresses later.
*/
-static const struct snp_cpuid_table *snp_cpuid_get_table(void)
+const struct snp_cpuid_table *snp_cpuid_get_table(void)
{
- return &RIP_REL_REF(cpuid_table_copy);
+ return rip_rel_ptr(&cpuid_table_copy);
}
/*
@@ -672,7 +586,7 @@ snp_cpuid_postprocess(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
* Returns -EOPNOTSUPP if feature not enabled. Any other non-zero return value
* should be treated as fatal by caller.
*/
-static int __head
+int __head
snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
{
const struct snp_cpuid_table *cpuid_table = snp_cpuid_get_table();
@@ -701,9 +615,9 @@ snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf)
leaf->eax = leaf->ebx = leaf->ecx = leaf->edx = 0;
/* Skip post-processing for out-of-range zero leafs. */
- if (!(leaf->fn <= RIP_REL_REF(cpuid_std_range_max) ||
- (leaf->fn >= 0x40000000 && leaf->fn <= RIP_REL_REF(cpuid_hyp_range_max)) ||
- (leaf->fn >= 0x80000000 && leaf->fn <= RIP_REL_REF(cpuid_ext_range_max))))
+ if (!(leaf->fn <= cpuid_std_range_max ||
+ (leaf->fn >= 0x40000000 && leaf->fn <= cpuid_hyp_range_max) ||
+ (leaf->fn >= 0x80000000 && leaf->fn <= cpuid_ext_range_max)))
return 0;
}
@@ -782,391 +696,6 @@ fail:
sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
}
-static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt,
- unsigned long address,
- bool write)
-{
- if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) {
- ctxt->fi.vector = X86_TRAP_PF;
- ctxt->fi.error_code = X86_PF_USER;
- ctxt->fi.cr2 = address;
- if (write)
- ctxt->fi.error_code |= X86_PF_WRITE;
-
- return ES_EXCEPTION;
- }
-
- return ES_OK;
-}
-
-static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
- void *src, char *buf,
- unsigned int data_size,
- unsigned int count,
- bool backwards)
-{
- int i, b = backwards ? -1 : 1;
- unsigned long address = (unsigned long)src;
- enum es_result ret;
-
- ret = vc_insn_string_check(ctxt, address, false);
- if (ret != ES_OK)
- return ret;
-
- for (i = 0; i < count; i++) {
- void *s = src + (i * data_size * b);
- char *d = buf + (i * data_size);
-
- ret = vc_read_mem(ctxt, s, d, data_size);
- if (ret != ES_OK)
- break;
- }
-
- return ret;
-}
-
-static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
- void *dst, char *buf,
- unsigned int data_size,
- unsigned int count,
- bool backwards)
-{
- int i, s = backwards ? -1 : 1;
- unsigned long address = (unsigned long)dst;
- enum es_result ret;
-
- ret = vc_insn_string_check(ctxt, address, true);
- if (ret != ES_OK)
- return ret;
-
- for (i = 0; i < count; i++) {
- void *d = dst + (i * data_size * s);
- char *b = buf + (i * data_size);
-
- ret = vc_write_mem(ctxt, d, b, data_size);
- if (ret != ES_OK)
- break;
- }
-
- return ret;
-}
-
-#define IOIO_TYPE_STR BIT(2)
-#define IOIO_TYPE_IN 1
-#define IOIO_TYPE_INS (IOIO_TYPE_IN | IOIO_TYPE_STR)
-#define IOIO_TYPE_OUT 0
-#define IOIO_TYPE_OUTS (IOIO_TYPE_OUT | IOIO_TYPE_STR)
-
-#define IOIO_REP BIT(3)
-
-#define IOIO_ADDR_64 BIT(9)
-#define IOIO_ADDR_32 BIT(8)
-#define IOIO_ADDR_16 BIT(7)
-
-#define IOIO_DATA_32 BIT(6)
-#define IOIO_DATA_16 BIT(5)
-#define IOIO_DATA_8 BIT(4)
-
-#define IOIO_SEG_ES (0 << 10)
-#define IOIO_SEG_DS (3 << 10)
-
-static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
-{
- struct insn *insn = &ctxt->insn;
- size_t size;
- u64 port;
-
- *exitinfo = 0;
-
- switch (insn->opcode.bytes[0]) {
- /* INS opcodes */
- case 0x6c:
- case 0x6d:
- *exitinfo |= IOIO_TYPE_INS;
- *exitinfo |= IOIO_SEG_ES;
- port = ctxt->regs->dx & 0xffff;
- break;
-
- /* OUTS opcodes */
- case 0x6e:
- case 0x6f:
- *exitinfo |= IOIO_TYPE_OUTS;
- *exitinfo |= IOIO_SEG_DS;
- port = ctxt->regs->dx & 0xffff;
- break;
-
- /* IN immediate opcodes */
- case 0xe4:
- case 0xe5:
- *exitinfo |= IOIO_TYPE_IN;
- port = (u8)insn->immediate.value & 0xffff;
- break;
-
- /* OUT immediate opcodes */
- case 0xe6:
- case 0xe7:
- *exitinfo |= IOIO_TYPE_OUT;
- port = (u8)insn->immediate.value & 0xffff;
- break;
-
- /* IN register opcodes */
- case 0xec:
- case 0xed:
- *exitinfo |= IOIO_TYPE_IN;
- port = ctxt->regs->dx & 0xffff;
- break;
-
- /* OUT register opcodes */
- case 0xee:
- case 0xef:
- *exitinfo |= IOIO_TYPE_OUT;
- port = ctxt->regs->dx & 0xffff;
- break;
-
- default:
- return ES_DECODE_FAILED;
- }
-
- *exitinfo |= port << 16;
-
- switch (insn->opcode.bytes[0]) {
- case 0x6c:
- case 0x6e:
- case 0xe4:
- case 0xe6:
- case 0xec:
- case 0xee:
- /* Single byte opcodes */
- *exitinfo |= IOIO_DATA_8;
- size = 1;
- break;
- default:
- /* Length determined by instruction parsing */
- *exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16
- : IOIO_DATA_32;
- size = (insn->opnd_bytes == 2) ? 2 : 4;
- }
-
- switch (insn->addr_bytes) {
- case 2:
- *exitinfo |= IOIO_ADDR_16;
- break;
- case 4:
- *exitinfo |= IOIO_ADDR_32;
- break;
- case 8:
- *exitinfo |= IOIO_ADDR_64;
- break;
- }
-
- if (insn_has_rep_prefix(insn))
- *exitinfo |= IOIO_REP;
-
- return vc_ioio_check(ctxt, (u16)port, size);
-}
-
-static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
- struct pt_regs *regs = ctxt->regs;
- u64 exit_info_1, exit_info_2;
- enum es_result ret;
-
- ret = vc_ioio_exitinfo(ctxt, &exit_info_1);
- if (ret != ES_OK)
- return ret;
-
- if (exit_info_1 & IOIO_TYPE_STR) {
-
- /* (REP) INS/OUTS */
-
- bool df = ((regs->flags & X86_EFLAGS_DF) == X86_EFLAGS_DF);
- unsigned int io_bytes, exit_bytes;
- unsigned int ghcb_count, op_count;
- unsigned long es_base;
- u64 sw_scratch;
-
- /*
- * For the string variants with rep prefix the amount of in/out
- * operations per #VC exception is limited so that the kernel
- * has a chance to take interrupts and re-schedule while the
- * instruction is emulated.
- */
- io_bytes = (exit_info_1 >> 4) & 0x7;
- ghcb_count = sizeof(ghcb->shared_buffer) / io_bytes;
-
- op_count = (exit_info_1 & IOIO_REP) ? regs->cx : 1;
- exit_info_2 = min(op_count, ghcb_count);
- exit_bytes = exit_info_2 * io_bytes;
-
- es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
-
- /* Read bytes of OUTS into the shared buffer */
- if (!(exit_info_1 & IOIO_TYPE_IN)) {
- ret = vc_insn_string_read(ctxt,
- (void *)(es_base + regs->si),
- ghcb->shared_buffer, io_bytes,
- exit_info_2, df);
- if (ret)
- return ret;
- }
-
- /*
- * Issue an VMGEXIT to the HV to consume the bytes from the
- * shared buffer or to have it write them into the shared buffer
- * depending on the instruction: OUTS or INS.
- */
- sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer);
- ghcb_set_sw_scratch(ghcb, sw_scratch);
- ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO,
- exit_info_1, exit_info_2);
- if (ret != ES_OK)
- return ret;
-
- /* Read bytes from shared buffer into the guest's destination. */
- if (exit_info_1 & IOIO_TYPE_IN) {
- ret = vc_insn_string_write(ctxt,
- (void *)(es_base + regs->di),
- ghcb->shared_buffer, io_bytes,
- exit_info_2, df);
- if (ret)
- return ret;
-
- if (df)
- regs->di -= exit_bytes;
- else
- regs->di += exit_bytes;
- } else {
- if (df)
- regs->si -= exit_bytes;
- else
- regs->si += exit_bytes;
- }
-
- if (exit_info_1 & IOIO_REP)
- regs->cx -= exit_info_2;
-
- ret = regs->cx ? ES_RETRY : ES_OK;
-
- } else {
-
- /* IN/OUT into/from rAX */
-
- int bits = (exit_info_1 & 0x70) >> 1;
- u64 rax = 0;
-
- if (!(exit_info_1 & IOIO_TYPE_IN))
- rax = lower_bits(regs->ax, bits);
-
- ghcb_set_rax(ghcb, rax);
-
- ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0);
- if (ret != ES_OK)
- return ret;
-
- if (exit_info_1 & IOIO_TYPE_IN) {
- if (!ghcb_rax_is_valid(ghcb))
- return ES_VMM_ERROR;
- regs->ax = lower_bits(ghcb->save.rax, bits);
- }
- }
-
- return ret;
-}
-
-static int vc_handle_cpuid_snp(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
- struct pt_regs *regs = ctxt->regs;
- struct cpuid_leaf leaf;
- int ret;
-
- leaf.fn = regs->ax;
- leaf.subfn = regs->cx;
- ret = snp_cpuid(ghcb, ctxt, &leaf);
- if (!ret) {
- regs->ax = leaf.eax;
- regs->bx = leaf.ebx;
- regs->cx = leaf.ecx;
- regs->dx = leaf.edx;
- }
-
- return ret;
-}
-
-static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
- struct es_em_ctxt *ctxt)
-{
- struct pt_regs *regs = ctxt->regs;
- u32 cr4 = native_read_cr4();
- enum es_result ret;
- int snp_cpuid_ret;
-
- snp_cpuid_ret = vc_handle_cpuid_snp(ghcb, ctxt);
- if (!snp_cpuid_ret)
- return ES_OK;
- if (snp_cpuid_ret != -EOPNOTSUPP)
- return ES_VMM_ERROR;
-
- ghcb_set_rax(ghcb, regs->ax);
- ghcb_set_rcx(ghcb, regs->cx);
-
- if (cr4 & X86_CR4_OSXSAVE)
- /* Safe to read xcr0 */
- ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK));
- else
- /* xgetbv will cause #GP - use reset value for xcr0 */
- ghcb_set_xcr0(ghcb, 1);
-
- ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0);
- if (ret != ES_OK)
- return ret;
-
- if (!(ghcb_rax_is_valid(ghcb) &&
- ghcb_rbx_is_valid(ghcb) &&
- ghcb_rcx_is_valid(ghcb) &&
- ghcb_rdx_is_valid(ghcb)))
- return ES_VMM_ERROR;
-
- regs->ax = ghcb->save.rax;
- regs->bx = ghcb->save.rbx;
- regs->cx = ghcb->save.rcx;
- regs->dx = ghcb->save.rdx;
-
- return ES_OK;
-}
-
-static enum es_result vc_handle_rdtsc(struct ghcb *ghcb,
- struct es_em_ctxt *ctxt,
- unsigned long exit_code)
-{
- bool rdtscp = (exit_code == SVM_EXIT_RDTSCP);
- enum es_result ret;
-
- /*
- * The hypervisor should not be intercepting RDTSC/RDTSCP when Secure
- * TSC is enabled. A #VC exception will be generated if the RDTSC/RDTSCP
- * instructions are being intercepted. If this should occur and Secure
- * TSC is enabled, guest execution should be terminated as the guest
- * cannot rely on the TSC value provided by the hypervisor.
- */
- if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
- return ES_VMM_ERROR;
-
- ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0);
- if (ret != ES_OK)
- return ret;
-
- if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb) &&
- (!rdtscp || ghcb_rcx_is_valid(ghcb))))
- return ES_VMM_ERROR;
-
- ctxt->regs->ax = ghcb->save.rax;
- ctxt->regs->dx = ghcb->save.rdx;
- if (rdtscp)
- ctxt->regs->cx = ghcb->save.rcx;
-
- return ES_OK;
-}
-
struct cc_setup_data {
struct setup_data header;
u32 cc_blob_address;
@@ -1224,36 +753,14 @@ static void __head setup_cpuid_table(const struct cc_blob_sev_info *cc_info)
const struct snp_cpuid_fn *fn = &cpuid_table->fn[i];
if (fn->eax_in == 0x0)
- RIP_REL_REF(cpuid_std_range_max) = fn->eax;
+ cpuid_std_range_max = fn->eax;
else if (fn->eax_in == 0x40000000)
- RIP_REL_REF(cpuid_hyp_range_max) = fn->eax;
+ cpuid_hyp_range_max = fn->eax;
else if (fn->eax_in == 0x80000000)
- RIP_REL_REF(cpuid_ext_range_max) = fn->eax;
+ cpuid_ext_range_max = fn->eax;
}
}
-static inline void __pval_terminate(u64 pfn, bool action, unsigned int page_size,
- int ret, u64 svsm_ret)
-{
- WARN(1, "PVALIDATE failure: pfn: 0x%llx, action: %u, size: %u, ret: %d, svsm_ret: 0x%llx\n",
- pfn, action, page_size, ret, svsm_ret);
-
- sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
-}
-
-static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svsm_ret)
-{
- unsigned int page_size;
- bool action;
- u64 pfn;
-
- pfn = pc->entry[pc->cur_index].pfn;
- action = pc->entry[pc->cur_index].action;
- page_size = pc->entry[pc->cur_index].page_size;
-
- __pval_terminate(pfn, action, page_size, ret, svsm_ret);
-}
-
static void __head svsm_pval_4k_page(unsigned long paddr, bool validate)
{
struct svsm_pvalidate_call *pc;
@@ -1296,362 +803,20 @@ static void __head pvalidate_4k_page(unsigned long vaddr, unsigned long paddr,
{
int ret;
- /*
- * This can be called very early during boot, so use rIP-relative
- * references as needed.
- */
- if (RIP_REL_REF(snp_vmpl)) {
+ if (snp_vmpl) {
svsm_pval_4k_page(paddr, validate);
} else {
ret = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
if (ret)
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
}
-}
-
-static void pval_pages(struct snp_psc_desc *desc)
-{
- struct psc_entry *e;
- unsigned long vaddr;
- unsigned int size;
- unsigned int i;
- bool validate;
- u64 pfn;
- int rc;
-
- for (i = 0; i <= desc->hdr.end_entry; i++) {
- e = &desc->entries[i];
-
- pfn = e->gfn;
- vaddr = (unsigned long)pfn_to_kaddr(pfn);
- size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
- validate = e->operation == SNP_PAGE_STATE_PRIVATE;
-
- rc = pvalidate(vaddr, size, validate);
- if (!rc)
- continue;
-
- if (rc == PVALIDATE_FAIL_SIZEMISMATCH && size == RMP_PG_SIZE_2M) {
- unsigned long vaddr_end = vaddr + PMD_SIZE;
-
- for (; vaddr < vaddr_end; vaddr += PAGE_SIZE, pfn++) {
- rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
- if (rc)
- __pval_terminate(pfn, validate, RMP_PG_SIZE_4K, rc, 0);
- }
- } else {
- __pval_terminate(pfn, validate, size, rc, 0);
- }
- }
-}
-
-static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action,
- struct svsm_pvalidate_call *pc)
-{
- struct svsm_pvalidate_entry *pe;
-
- /* Nothing in the CA yet */
- pc->num_entries = 0;
- pc->cur_index = 0;
-
- pe = &pc->entry[0];
-
- while (pfn < pfn_end) {
- pe->page_size = RMP_PG_SIZE_4K;
- pe->action = action;
- pe->ignore_cf = 0;
- pe->pfn = pfn;
-
- pe++;
- pfn++;
-
- pc->num_entries++;
- if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
- break;
- }
-
- return pfn;
-}
-
-static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int desc_entry,
- struct svsm_pvalidate_call *pc)
-{
- struct svsm_pvalidate_entry *pe;
- struct psc_entry *e;
-
- /* Nothing in the CA yet */
- pc->num_entries = 0;
- pc->cur_index = 0;
-
- pe = &pc->entry[0];
- e = &desc->entries[desc_entry];
-
- while (desc_entry <= desc->hdr.end_entry) {
- pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
- pe->action = e->operation == SNP_PAGE_STATE_PRIVATE;
- pe->ignore_cf = 0;
- pe->pfn = e->gfn;
-
- pe++;
- e++;
-
- desc_entry++;
- pc->num_entries++;
- if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
- break;
- }
-
- return desc_entry;
-}
-
-static void svsm_pval_pages(struct snp_psc_desc *desc)
-{
- struct svsm_pvalidate_entry pv_4k[VMGEXIT_PSC_MAX_ENTRY];
- unsigned int i, pv_4k_count = 0;
- struct svsm_pvalidate_call *pc;
- struct svsm_call call = {};
- unsigned long flags;
- bool action;
- u64 pc_pa;
- int ret;
-
- /*
- * This can be called very early in the boot, use native functions in
- * order to avoid paravirt issues.
- */
- flags = native_local_irq_save();
-
- /*
- * The SVSM calling area (CA) can support processing 510 entries at a
- * time. Loop through the Page State Change descriptor until the CA is
- * full or the last entry in the descriptor is reached, at which time
- * the SVSM is invoked. This repeats until all entries in the descriptor
- * are processed.
- */
- call.caa = svsm_get_caa();
-
- pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
- pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
-
- /* Protocol 0, Call ID 1 */
- call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
- call.rcx = pc_pa;
-
- for (i = 0; i <= desc->hdr.end_entry;) {
- i = svsm_build_ca_from_psc_desc(desc, i, pc);
-
- do {
- ret = svsm_perform_call_protocol(&call);
- if (!ret)
- continue;
-
- /*
- * Check if the entry failed because of an RMP mismatch (a
- * PVALIDATE at 2M was requested, but the page is mapped in
- * the RMP as 4K).
- */
-
- if (call.rax_out == SVSM_PVALIDATE_FAIL_SIZEMISMATCH &&
- pc->entry[pc->cur_index].page_size == RMP_PG_SIZE_2M) {
- /* Save this entry for post-processing at 4K */
- pv_4k[pv_4k_count++] = pc->entry[pc->cur_index];
-
- /* Skip to the next one unless at the end of the list */
- pc->cur_index++;
- if (pc->cur_index < pc->num_entries)
- ret = -EAGAIN;
- else
- ret = 0;
- }
- } while (ret == -EAGAIN);
-
- if (ret)
- svsm_pval_terminate(pc, ret, call.rax_out);
- }
-
- /* Process any entries that failed to be validated at 2M and validate them at 4K */
- for (i = 0; i < pv_4k_count; i++) {
- u64 pfn, pfn_end;
-
- action = pv_4k[i].action;
- pfn = pv_4k[i].pfn;
- pfn_end = pfn + 512;
-
- while (pfn < pfn_end) {
- pfn = svsm_build_ca_from_pfn_range(pfn, pfn_end, action, pc);
-
- ret = svsm_perform_call_protocol(&call);
- if (ret)
- svsm_pval_terminate(pc, ret, call.rax_out);
- }
- }
-
- native_local_irq_restore(flags);
-}
-
-static void pvalidate_pages(struct snp_psc_desc *desc)
-{
- if (snp_vmpl)
- svsm_pval_pages(desc);
- else
- pval_pages(desc);
-}
-
-static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
-{
- int cur_entry, end_entry, ret = 0;
- struct snp_psc_desc *data;
- struct es_em_ctxt ctxt;
-
- vc_ghcb_invalidate(ghcb);
-
- /* Copy the input desc into GHCB shared buffer */
- data = (struct snp_psc_desc *)ghcb->shared_buffer;
- memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc)));
/*
- * As per the GHCB specification, the hypervisor can resume the guest
- * before processing all the entries. Check whether all the entries
- * are processed. If not, then keep retrying. Note, the hypervisor
- * will update the data memory directly to indicate the status, so
- * reference the data->hdr everywhere.
- *
- * The strategy here is to wait for the hypervisor to change the page
- * state in the RMP table before guest accesses the memory pages. If the
- * page state change was not successful, then later memory access will
- * result in a crash.
+ * If validating memory (making it private) and affected by the
+ * cache-coherency vulnerability, perform the cache eviction mitigation.
*/
- cur_entry = data->hdr.cur_entry;
- end_entry = data->hdr.end_entry;
-
- while (data->hdr.cur_entry <= data->hdr.end_entry) {
- ghcb_set_sw_scratch(ghcb, (u64)__pa(data));
-
- /* This will advance the shared buffer data points to. */
- ret = sev_es_ghcb_hv_call(ghcb, &ctxt, SVM_VMGEXIT_PSC, 0, 0);
-
- /*
- * Page State Change VMGEXIT can pass error code through
- * exit_info_2.
- */
- if (WARN(ret || ghcb->save.sw_exit_info_2,
- "SNP: PSC failed ret=%d exit_info_2=%llx\n",
- ret, ghcb->save.sw_exit_info_2)) {
- ret = 1;
- goto out;
- }
-
- /* Verify that reserved bit is not set */
- if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) {
- ret = 1;
- goto out;
- }
-
- /*
- * Sanity check that entry processing is not going backwards.
- * This will happen only if hypervisor is tricking us.
- */
- if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry,
-"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n",
- end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) {
- ret = 1;
- goto out;
- }
- }
-
-out:
- return ret;
-}
-
-static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt,
- unsigned long exit_code)
-{
- unsigned int opcode = (unsigned int)ctxt->insn.opcode.value;
- u8 modrm = ctxt->insn.modrm.value;
-
- switch (exit_code) {
-
- case SVM_EXIT_IOIO:
- case SVM_EXIT_NPF:
- /* handled separately */
- return ES_OK;
-
- case SVM_EXIT_CPUID:
- if (opcode == 0xa20f)
- return ES_OK;
- break;
-
- case SVM_EXIT_INVD:
- if (opcode == 0x080f)
- return ES_OK;
- break;
-
- case SVM_EXIT_MONITOR:
- /* MONITOR and MONITORX instructions generate the same error code */
- if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa))
- return ES_OK;
- break;
-
- case SVM_EXIT_MWAIT:
- /* MWAIT and MWAITX instructions generate the same error code */
- if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb))
- return ES_OK;
- break;
-
- case SVM_EXIT_MSR:
- /* RDMSR */
- if (opcode == 0x320f ||
- /* WRMSR */
- opcode == 0x300f)
- return ES_OK;
- break;
-
- case SVM_EXIT_RDPMC:
- if (opcode == 0x330f)
- return ES_OK;
- break;
-
- case SVM_EXIT_RDTSC:
- if (opcode == 0x310f)
- return ES_OK;
- break;
-
- case SVM_EXIT_RDTSCP:
- if (opcode == 0x010f && modrm == 0xf9)
- return ES_OK;
- break;
-
- case SVM_EXIT_READ_DR7:
- if (opcode == 0x210f &&
- X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
- return ES_OK;
- break;
-
- case SVM_EXIT_VMMCALL:
- if (opcode == 0x010f && modrm == 0xd9)
- return ES_OK;
-
- break;
-
- case SVM_EXIT_WRITE_DR7:
- if (opcode == 0x230f &&
- X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
- return ES_OK;
- break;
-
- case SVM_EXIT_WBINVD:
- if (opcode == 0x90f)
- return ES_OK;
- break;
-
- default:
- break;
- }
-
- sev_printk(KERN_ERR "Wrong/unhandled opcode bytes: 0x%x, exit_code: 0x%lx, rIP: 0x%lx\n",
- opcode, exit_code, ctxt->regs->ip);
-
- return ES_UNSUPPORTED;
+ if (validate && !has_cpuflag(X86_FEATURE_COHERENCY_SFW_NO))
+ sev_evict_cache((void *)vaddr, 1);
}
/*
@@ -1681,7 +846,7 @@ static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info)
* routine is running identity mapped when called, both by the decompressor
* code and the early kernel code.
*/
- if (!rmpadjust((unsigned long)&RIP_REL_REF(boot_ghcb_page), RMP_PG_SIZE_4K, 1))
+ if (!rmpadjust((unsigned long)rip_rel_ptr(&boot_ghcb_page), RMP_PG_SIZE_4K, 1))
return false;
/*
@@ -1698,7 +863,7 @@ static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info)
if (!secrets_page->svsm_guest_vmpl)
sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_VMPL0);
- RIP_REL_REF(snp_vmpl) = secrets_page->svsm_guest_vmpl;
+ snp_vmpl = secrets_page->svsm_guest_vmpl;
caa = secrets_page->svsm_caa;
@@ -1713,8 +878,8 @@ static bool __head svsm_setup_ca(const struct cc_blob_sev_info *cc_info)
* The CA is identity mapped when this routine is called, both by the
* decompressor code and the early kernel code.
*/
- RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)caa;
- RIP_REL_REF(boot_svsm_caa_pa) = caa;
+ boot_svsm_caa = (struct svsm_ca *)caa;
+ boot_svsm_caa_pa = caa;
/* Advertise the SVSM presence via CPUID. */
cpuid_table = (struct snp_cpuid_table *)snp_cpuid_get_table();
diff --git a/arch/x86/boot/startup/sev-startup.c b/arch/x86/boot/startup/sev-startup.c
new file mode 100644
index 000000000000..0b7e3b950183
--- /dev/null
+++ b/arch/x86/boot/startup/sev-startup.c
@@ -0,0 +1,368 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2019 SUSE
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt) "SEV: " fmt
+
+#include <linux/percpu-defs.h>
+#include <linux/cc_platform.h>
+#include <linux/printk.h>
+#include <linux/mm_types.h>
+#include <linux/set_memory.h>
+#include <linux/memblock.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/cpumask.h>
+#include <linux/efi.h>
+#include <linux/io.h>
+#include <linux/psp-sev.h>
+#include <uapi/linux/sev-guest.h>
+
+#include <asm/init.h>
+#include <asm/cpu_entry_area.h>
+#include <asm/stacktrace.h>
+#include <asm/sev.h>
+#include <asm/sev-internal.h>
+#include <asm/insn-eval.h>
+#include <asm/fpu/xcr.h>
+#include <asm/processor.h>
+#include <asm/realmode.h>
+#include <asm/setup.h>
+#include <asm/traps.h>
+#include <asm/svm.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/apic.h>
+#include <asm/cpuid/api.h>
+#include <asm/cmdline.h>
+
+/* For early boot hypervisor communication in SEV-ES enabled guests */
+struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
+
+/*
+ * Needs to be in the .data section because we need it NULL before bss is
+ * cleared
+ */
+struct ghcb *boot_ghcb __section(".data");
+
+/* Bitmap of SEV features supported by the hypervisor */
+u64 sev_hv_features __ro_after_init;
+
+/* Secrets page physical address from the CC blob */
+u64 sev_secrets_pa __ro_after_init;
+
+/* For early boot SVSM communication */
+struct svsm_ca boot_svsm_ca_page __aligned(PAGE_SIZE);
+
+DEFINE_PER_CPU(struct svsm_ca *, svsm_caa);
+DEFINE_PER_CPU(u64, svsm_caa_pa);
+
+/*
+ * Nothing shall interrupt this code path while holding the per-CPU
+ * GHCB. The backup GHCB is only for NMIs interrupting this path.
+ *
+ * Callers must disable local interrupts around it.
+ */
+noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
+{
+ struct sev_es_runtime_data *data;
+ struct ghcb *ghcb;
+
+ WARN_ON(!irqs_disabled());
+
+ data = this_cpu_read(runtime_data);
+ ghcb = &data->ghcb_page;
+
+ if (unlikely(data->ghcb_active)) {
+ /* GHCB is already in use - save its contents */
+
+ if (unlikely(data->backup_ghcb_active)) {
+ /*
+ * Backup-GHCB is also already in use. There is no way
+ * to continue here so just kill the machine. To make
+ * panic() work, mark GHCBs inactive so that messages
+ * can be printed out.
+ */
+ data->ghcb_active = false;
+ data->backup_ghcb_active = false;
+
+ instrumentation_begin();
+ panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
+ instrumentation_end();
+ }
+
+ /* Mark backup_ghcb active before writing to it */
+ data->backup_ghcb_active = true;
+
+ state->ghcb = &data->backup_ghcb;
+
+ /* Backup GHCB content */
+ *state->ghcb = *ghcb;
+ } else {
+ state->ghcb = NULL;
+ data->ghcb_active = true;
+ }
+
+ return ghcb;
+}
+
+/* Include code shared with pre-decompression boot stage */
+#include "sev-shared.c"
+
+noinstr void __sev_put_ghcb(struct ghcb_state *state)
+{
+ struct sev_es_runtime_data *data;
+ struct ghcb *ghcb;
+
+ WARN_ON(!irqs_disabled());
+
+ data = this_cpu_read(runtime_data);
+ ghcb = &data->ghcb_page;
+
+ if (state->ghcb) {
+ /* Restore GHCB from Backup */
+ *ghcb = *state->ghcb;
+ data->backup_ghcb_active = false;
+ state->ghcb = NULL;
+ } else {
+ /*
+ * Invalidate the GHCB so a VMGEXIT instruction issued
+ * from userspace won't appear to be valid.
+ */
+ vc_ghcb_invalidate(ghcb);
+ data->ghcb_active = false;
+ }
+}
+
+int svsm_perform_call_protocol(struct svsm_call *call)
+{
+ struct ghcb_state state;
+ unsigned long flags;
+ struct ghcb *ghcb;
+ int ret;
+
+ /*
+ * This can be called very early in the boot, use native functions in
+ * order to avoid paravirt issues.
+ */
+ flags = native_local_irq_save();
+
+ if (sev_cfg.ghcbs_initialized)
+ ghcb = __sev_get_ghcb(&state);
+ else if (boot_ghcb)
+ ghcb = boot_ghcb;
+ else
+ ghcb = NULL;
+
+ do {
+ ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call)
+ : svsm_perform_msr_protocol(call);
+ } while (ret == -EAGAIN);
+
+ if (sev_cfg.ghcbs_initialized)
+ __sev_put_ghcb(&state);
+
+ native_local_irq_restore(flags);
+
+ return ret;
+}
+
+void __head
+early_set_pages_state(unsigned long vaddr, unsigned long paddr,
+ unsigned long npages, enum psc_op op)
+{
+ unsigned long paddr_end;
+ u64 val;
+
+ vaddr = vaddr & PAGE_MASK;
+
+ paddr = paddr & PAGE_MASK;
+ paddr_end = paddr + (npages << PAGE_SHIFT);
+
+ while (paddr < paddr_end) {
+ /* Page validation must be rescinded before changing to shared */
+ if (op == SNP_PAGE_STATE_SHARED)
+ pvalidate_4k_page(vaddr, paddr, false);
+
+ /*
+ * Use the MSR protocol because this function can be called before
+ * the GHCB is established.
+ */
+ sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
+ VMGEXIT();
+
+ val = sev_es_rd_ghcb_msr();
+
+ if (GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP)
+ goto e_term;
+
+ if (GHCB_MSR_PSC_RESP_VAL(val))
+ goto e_term;
+
+ /* Page validation must be performed after changing to private */
+ if (op == SNP_PAGE_STATE_PRIVATE)
+ pvalidate_4k_page(vaddr, paddr, true);
+
+ vaddr += PAGE_SIZE;
+ paddr += PAGE_SIZE;
+ }
+
+ return;
+
+e_term:
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
+}
+
+void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
+ unsigned long npages)
+{
+ /*
+ * This can be invoked in early boot while running identity mapped, so
+ * use an open coded check for SNP instead of using cc_platform_has().
+ * This eliminates worries about jump tables or checking boot_cpu_data
+ * in the cc_platform_has() function.
+ */
+ if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+ return;
+
+ /*
+ * Ask the hypervisor to mark the memory pages as private in the RMP
+ * table.
+ */
+ early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_PRIVATE);
+}
+
+void __head early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
+ unsigned long npages)
+{
+ /*
+ * This can be invoked in early boot while running identity mapped, so
+ * use an open coded check for SNP instead of using cc_platform_has().
+ * This eliminates worries about jump tables or checking boot_cpu_data
+ * in the cc_platform_has() function.
+ */
+ if (!(sev_status & MSR_AMD64_SEV_SNP_ENABLED))
+ return;
+
+ /* Ask hypervisor to mark the memory pages shared in the RMP table. */
+ early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
+}
+
+/*
+ * Initial set up of SNP relies on information provided by the
+ * Confidential Computing blob, which can be passed to the kernel
+ * in the following ways, depending on how it is booted:
+ *
+ * - when booted via the boot/decompress kernel:
+ * - via boot_params
+ *
+ * - when booted directly by firmware/bootloader (e.g. CONFIG_PVH):
+ * - via a setup_data entry, as defined by the Linux Boot Protocol
+ *
+ * Scan for the blob in that order.
+ */
+static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
+{
+ struct cc_blob_sev_info *cc_info;
+
+ /* Boot kernel would have passed the CC blob via boot_params. */
+ if (bp->cc_blob_address) {
+ cc_info = (struct cc_blob_sev_info *)(unsigned long)bp->cc_blob_address;
+ goto found_cc_info;
+ }
+
+ /*
+ * If kernel was booted directly, without the use of the
+ * boot/decompression kernel, the CC blob may have been passed via
+ * setup_data instead.
+ */
+ cc_info = find_cc_blob_setup_data(bp);
+ if (!cc_info)
+ return NULL;
+
+found_cc_info:
+ if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC)
+ snp_abort();
+
+ return cc_info;
+}
+
+static __head void svsm_setup(struct cc_blob_sev_info *cc_info)
+{
+ struct svsm_call call = {};
+ int ret;
+ u64 pa;
+
+ /*
+ * Record the SVSM Calling Area address (CAA) if the guest is not
+ * running at VMPL0. The CA will be used to communicate with the
+ * SVSM to perform the SVSM services.
+ */
+ if (!svsm_setup_ca(cc_info))
+ return;
+
+ /*
+ * It is very early in the boot and the kernel is running identity
+ * mapped but without having adjusted the pagetables to where the
+ * kernel was loaded (physbase), so the get the CA address using
+ * RIP-relative addressing.
+ */
+ pa = (u64)rip_rel_ptr(&boot_svsm_ca_page);
+
+ /*
+ * Switch over to the boot SVSM CA while the current CA is still
+ * addressable. There is no GHCB at this point so use the MSR protocol.
+ *
+ * SVSM_CORE_REMAP_CA call:
+ * RAX = 0 (Protocol=0, CallID=0)
+ * RCX = New CA GPA
+ */
+ call.caa = svsm_get_caa();
+ call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
+ call.rcx = pa;
+ ret = svsm_perform_call_protocol(&call);
+ if (ret)
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_CA_REMAP_FAIL);
+
+ boot_svsm_caa = (struct svsm_ca *)pa;
+ boot_svsm_caa_pa = pa;
+}
+
+bool __head snp_init(struct boot_params *bp)
+{
+ struct cc_blob_sev_info *cc_info;
+
+ if (!bp)
+ return false;
+
+ cc_info = find_cc_blob(bp);
+ if (!cc_info)
+ return false;
+
+ if (cc_info->secrets_phys && cc_info->secrets_len == PAGE_SIZE)
+ sev_secrets_pa = cc_info->secrets_phys;
+ else
+ return false;
+
+ setup_cpuid_table(cc_info);
+
+ svsm_setup(cc_info);
+
+ /*
+ * The CC blob will be used later to access the secrets page. Cache
+ * it here like the boot kernel does.
+ */
+ bp->cc_blob_address = (u32)(unsigned long)cc_info;
+
+ return true;
+}
+
+void __head __noreturn snp_abort(void)
+{
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
+}
diff --git a/arch/x86/mm/mem_encrypt_identity.c b/arch/x86/boot/startup/sme.c
index 5eecdd92da10..70ea1748c0a7 100644
--- a/arch/x86/mm/mem_encrypt_identity.c
+++ b/arch/x86/boot/startup/sme.c
@@ -45,8 +45,6 @@
#include <asm/coco.h>
#include <asm/sev.h>
-#include "mm_internal.h"
-
#define PGD_FLAGS _KERNPG_TABLE_NOENC
#define P4D_FLAGS _KERNPG_TABLE_NOENC
#define PUD_FLAGS _KERNPG_TABLE_NOENC
@@ -299,8 +297,7 @@ void __head sme_encrypt_kernel(struct boot_params *bp)
* instrumentation or checking boot_cpu_data in the cc_platform_has()
* function.
*/
- if (!sme_get_me_mask() ||
- RIP_REL_REF(sev_status) & MSR_AMD64_SEV_ENABLED)
+ if (!sme_get_me_mask() || sev_status & MSR_AMD64_SEV_ENABLED)
return;
/*
@@ -318,8 +315,8 @@ void __head sme_encrypt_kernel(struct boot_params *bp)
* memory from being cached.
*/
- kernel_start = (unsigned long)RIP_REL_REF(_text);
- kernel_end = ALIGN((unsigned long)RIP_REL_REF(_end), PMD_SIZE);
+ kernel_start = (unsigned long)rip_rel_ptr(_text);
+ kernel_end = ALIGN((unsigned long)rip_rel_ptr(_end), PMD_SIZE);
kernel_len = kernel_end - kernel_start;
initrd_start = 0;
@@ -345,7 +342,7 @@ void __head sme_encrypt_kernel(struct boot_params *bp)
* pagetable structures for the encryption of the kernel
* pagetable structures for workarea (in case not currently mapped)
*/
- execute_start = workarea_start = (unsigned long)RIP_REL_REF(sme_workarea);
+ execute_start = workarea_start = (unsigned long)rip_rel_ptr(sme_workarea);
execute_end = execute_start + (PAGE_SIZE * 2) + PMD_SIZE;
execute_len = execute_end - execute_start;
@@ -526,7 +523,7 @@ void __head sme_enable(struct boot_params *bp)
me_mask = 1UL << (ebx & 0x3f);
/* Check the SEV MSR whether SEV or SME is enabled */
- RIP_REL_REF(sev_status) = msr = __rdmsr(MSR_AMD64_SEV);
+ sev_status = msr = native_rdmsrq(MSR_AMD64_SEV);
feature_mask = (msr & MSR_AMD64_SEV_ENABLED) ? AMD_SEV_BIT : AMD_SME_BIT;
/*
@@ -557,13 +554,22 @@ void __head sme_enable(struct boot_params *bp)
return;
/* For SME, check the SYSCFG MSR */
- msr = __rdmsr(MSR_AMD64_SYSCFG);
+ msr = native_rdmsrq(MSR_AMD64_SYSCFG);
if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
return;
}
- RIP_REL_REF(sme_me_mask) = me_mask;
- RIP_REL_REF(physical_mask) &= ~me_mask;
- RIP_REL_REF(cc_vendor) = CC_VENDOR_AMD;
+ sme_me_mask = me_mask;
+ physical_mask &= ~me_mask;
+ cc_vendor = CC_VENDOR_AMD;
cc_set_mask(me_mask);
}
+
+#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
+/* Local version for startup code, which never operates on user page tables */
+__weak
+pgd_t __pti_set_user_pgtbl(pgd_t *pgdp, pgd_t pgd)
+{
+ return pgd;
+}
+#endif
diff --git a/arch/x86/boot/string.c b/arch/x86/boot/string.c
index 84f7a883ce1e..f35369bb14c5 100644
--- a/arch/x86/boot/string.c
+++ b/arch/x86/boot/string.c
@@ -32,7 +32,7 @@
int memcmp(const void *s1, const void *s2, size_t len)
{
bool diff;
- asm("repe; cmpsb" CC_SET(nz)
+ asm("repe cmpsb" CC_SET(nz)
: CC_OUT(nz) (diff), "+D" (s1), "+S" (s2), "+c" (len));
return diff;
}
diff --git a/arch/x86/boot/video.c b/arch/x86/boot/video.c
index f2e96905b3fe..0641c8c46aee 100644
--- a/arch/x86/boot/video.c
+++ b/arch/x86/boot/video.c
@@ -292,7 +292,7 @@ static void restore_screen(void)
"shrw %%cx ; "
"jnc 1f ; "
"stosw \n\t"
- "1: rep;stosl ; "
+ "1: rep stosl ; "
"popw %%es"
: "+D" (dst), "+c" (npad)
: "bdS" (video_segment),
diff --git a/arch/x86/coco/core.c b/arch/x86/coco/core.c
index 9a0ddda3aa69..d4610af68114 100644
--- a/arch/x86/coco/core.c
+++ b/arch/x86/coco/core.c
@@ -18,7 +18,9 @@
#include <asm/processor.h>
enum cc_vendor cc_vendor __ro_after_init = CC_VENDOR_NONE;
+SYM_PIC_ALIAS(cc_vendor);
u64 cc_mask __ro_after_init;
+SYM_PIC_ALIAS(cc_mask);
static struct cc_attr_flags {
__u64 host_sev_snp : 1,
diff --git a/arch/x86/coco/sev/Makefile b/arch/x86/coco/sev/Makefile
index dcb06dc8b5ae..342d79f0ab6a 100644
--- a/arch/x86/coco/sev/Makefile
+++ b/arch/x86/coco/sev/Makefile
@@ -1,22 +1,10 @@
# SPDX-License-Identifier: GPL-2.0
-obj-y += core.o
-
-# jump tables are emitted using absolute references in non-PIC code
-# so they cannot be used in the early SEV startup code
-CFLAGS_core.o += -fno-jump-tables
-
-ifdef CONFIG_FUNCTION_TRACER
-CFLAGS_REMOVE_core.o = -pg
-endif
-
-KASAN_SANITIZE_core.o := n
-KMSAN_SANITIZE_core.o := n
-KCOV_INSTRUMENT_core.o := n
-
-# With some compiler versions the generated code results in boot hangs, caused
-# by several compilation units. To be safe, disable all instrumentation.
-KCSAN_SANITIZE := n
+obj-y += core.o sev-nmi.o vc-handle.o
# Clang 14 and older may fail to respect __no_sanitize_undefined when inlining
-UBSAN_SANITIZE := n
+UBSAN_SANITIZE_sev-nmi.o := n
+
+# GCC may fail to respect __no_sanitize_address or __no_kcsan when inlining
+KASAN_SANITIZE_sev-nmi.o := n
+KCSAN_SANITIZE_sev-nmi.o := n
diff --git a/arch/x86/coco/sev/core.c b/arch/x86/coco/sev/core.c
index 36beaac713c1..400a6ab75d45 100644
--- a/arch/x86/coco/sev/core.c
+++ b/arch/x86/coco/sev/core.c
@@ -31,6 +31,7 @@
#include <asm/cpu_entry_area.h>
#include <asm/stacktrace.h>
#include <asm/sev.h>
+#include <asm/sev-internal.h>
#include <asm/insn-eval.h>
#include <asm/fpu/xcr.h>
#include <asm/processor.h>
@@ -41,10 +42,9 @@
#include <asm/smp.h>
#include <asm/cpu.h>
#include <asm/apic.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/cmdline.h>
-
-#define DR7_RESET_VALUE 0x400
+#include <asm/msr.h>
/* AP INIT values as documented in the APM2 section "Processor Initialization State" */
#define AP_INIT_CS_LIMIT 0xffff
@@ -81,21 +81,6 @@ static const char * const sev_status_feat_names[] = {
[MSR_AMD64_SNP_SMT_PROT_BIT] = "SMTProt",
};
-/* For early boot hypervisor communication in SEV-ES enabled guests */
-static struct ghcb boot_ghcb_page __bss_decrypted __aligned(PAGE_SIZE);
-
-/*
- * Needs to be in the .data section because we need it NULL before bss is
- * cleared
- */
-static struct ghcb *boot_ghcb __section(".data");
-
-/* Bitmap of SEV features supported by the hypervisor */
-static u64 sev_hv_features __ro_after_init;
-
-/* Secrets page physical address from the CC blob */
-static u64 secrets_pa __ro_after_init;
-
/*
* For Secure TSC guests, the BSP fetches TSC_INFO using SNP guest messaging and
* initializes snp_tsc_scale and snp_tsc_offset. These values are replicated
@@ -103,560 +88,198 @@ static u64 secrets_pa __ro_after_init;
*/
static u64 snp_tsc_scale __ro_after_init;
static u64 snp_tsc_offset __ro_after_init;
-static u64 snp_tsc_freq_khz __ro_after_init;
-
-/* #VC handler runtime per-CPU data */
-struct sev_es_runtime_data {
- struct ghcb ghcb_page;
-
- /*
- * Reserve one page per CPU as backup storage for the unencrypted GHCB.
- * It is needed when an NMI happens while the #VC handler uses the real
- * GHCB, and the NMI handler itself is causing another #VC exception. In
- * that case the GHCB content of the first handler needs to be backed up
- * and restored.
- */
- struct ghcb backup_ghcb;
-
- /*
- * Mark the per-cpu GHCBs as in-use to detect nested #VC exceptions.
- * There is no need for it to be atomic, because nothing is written to
- * the GHCB between the read and the write of ghcb_active. So it is safe
- * to use it when a nested #VC exception happens before the write.
- *
- * This is necessary for example in the #VC->NMI->#VC case when the NMI
- * happens while the first #VC handler uses the GHCB. When the NMI code
- * raises a second #VC handler it might overwrite the contents of the
- * GHCB written by the first handler. To avoid this the content of the
- * GHCB is saved and restored when the GHCB is detected to be in use
- * already.
- */
- bool ghcb_active;
- bool backup_ghcb_active;
-
- /*
- * Cached DR7 value - write it on DR7 writes and return it on reads.
- * That value will never make it to the real hardware DR7 as debugging
- * is currently unsupported in SEV-ES guests.
- */
- unsigned long dr7;
-};
-
-struct ghcb_state {
- struct ghcb *ghcb;
-};
-
-/* For early boot SVSM communication */
-static struct svsm_ca boot_svsm_ca_page __aligned(PAGE_SIZE);
+static unsigned long snp_tsc_freq_khz __ro_after_init;
-static DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
-static DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
-static DEFINE_PER_CPU(struct svsm_ca *, svsm_caa);
-static DEFINE_PER_CPU(u64, svsm_caa_pa);
-
-static __always_inline bool on_vc_stack(struct pt_regs *regs)
-{
- unsigned long sp = regs->sp;
-
- /* User-mode RSP is not trusted */
- if (user_mode(regs))
- return false;
-
- /* SYSCALL gap still has user-mode RSP */
- if (ip_within_syscall_gap(regs))
- return false;
-
- return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
-}
+DEFINE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
+DEFINE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
/*
- * This function handles the case when an NMI is raised in the #VC
- * exception handler entry code, before the #VC handler has switched off
- * its IST stack. In this case, the IST entry for #VC must be adjusted,
- * so that any nested #VC exception will not overwrite the stack
- * contents of the interrupted #VC handler.
- *
- * The IST entry is adjusted unconditionally so that it can be also be
- * unconditionally adjusted back in __sev_es_ist_exit(). Otherwise a
- * nested sev_es_ist_exit() call may adjust back the IST entry too
- * early.
- *
- * The __sev_es_ist_enter() and __sev_es_ist_exit() functions always run
- * on the NMI IST stack, as they are only called from NMI handling code
- * right now.
+ * SVSM related information:
+ * When running under an SVSM, the VMPL that Linux is executing at must be
+ * non-zero. The VMPL is therefore used to indicate the presence of an SVSM.
*/
-void noinstr __sev_es_ist_enter(struct pt_regs *regs)
-{
- unsigned long old_ist, new_ist;
+u8 snp_vmpl __ro_after_init;
+EXPORT_SYMBOL_GPL(snp_vmpl);
- /* Read old IST entry */
- new_ist = old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
-
- /*
- * If NMI happened while on the #VC IST stack, set the new IST
- * value below regs->sp, so that the interrupted stack frame is
- * not overwritten by subsequent #VC exceptions.
- */
- if (on_vc_stack(regs))
- new_ist = regs->sp;
-
- /*
- * Reserve additional 8 bytes and store old IST value so this
- * adjustment can be unrolled in __sev_es_ist_exit().
- */
- new_ist -= sizeof(old_ist);
- *(unsigned long *)new_ist = old_ist;
-
- /* Set new IST entry */
- this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist);
-}
-
-void noinstr __sev_es_ist_exit(void)
+static u64 __init get_snp_jump_table_addr(void)
{
- unsigned long ist;
+ struct snp_secrets_page *secrets;
+ void __iomem *mem;
+ u64 addr;
- /* Read IST entry */
- ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
+ mem = ioremap_encrypted(sev_secrets_pa, PAGE_SIZE);
+ if (!mem) {
+ pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n");
+ return 0;
+ }
- if (WARN_ON(ist == __this_cpu_ist_top_va(VC)))
- return;
+ secrets = (__force struct snp_secrets_page *)mem;
+
+ addr = secrets->os_area.ap_jump_table_pa;
+ iounmap(mem);
- /* Read back old IST entry and write it to the TSS */
- this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist);
+ return addr;
}
-/*
- * Nothing shall interrupt this code path while holding the per-CPU
- * GHCB. The backup GHCB is only for NMIs interrupting this path.
- *
- * Callers must disable local interrupts around it.
- */
-static noinstr struct ghcb *__sev_get_ghcb(struct ghcb_state *state)
+static u64 __init get_jump_table_addr(void)
{
- struct sev_es_runtime_data *data;
+ struct ghcb_state state;
+ unsigned long flags;
struct ghcb *ghcb;
+ u64 ret = 0;
- WARN_ON(!irqs_disabled());
-
- data = this_cpu_read(runtime_data);
- ghcb = &data->ghcb_page;
-
- if (unlikely(data->ghcb_active)) {
- /* GHCB is already in use - save its contents */
-
- if (unlikely(data->backup_ghcb_active)) {
- /*
- * Backup-GHCB is also already in use. There is no way
- * to continue here so just kill the machine. To make
- * panic() work, mark GHCBs inactive so that messages
- * can be printed out.
- */
- data->ghcb_active = false;
- data->backup_ghcb_active = false;
-
- instrumentation_begin();
- panic("Unable to handle #VC exception! GHCB and Backup GHCB are already in use");
- instrumentation_end();
- }
-
- /* Mark backup_ghcb active before writing to it */
- data->backup_ghcb_active = true;
+ if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
+ return get_snp_jump_table_addr();
- state->ghcb = &data->backup_ghcb;
+ local_irq_save(flags);
- /* Backup GHCB content */
- *state->ghcb = *ghcb;
- } else {
- state->ghcb = NULL;
- data->ghcb_active = true;
- }
+ ghcb = __sev_get_ghcb(&state);
- return ghcb;
-}
+ vc_ghcb_invalidate(ghcb);
+ ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE);
+ ghcb_set_sw_exit_info_1(ghcb, SVM_VMGEXIT_GET_AP_JUMP_TABLE);
+ ghcb_set_sw_exit_info_2(ghcb, 0);
-static inline u64 sev_es_rd_ghcb_msr(void)
-{
- return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
-}
+ sev_es_wr_ghcb_msr(__pa(ghcb));
+ VMGEXIT();
-static __always_inline void sev_es_wr_ghcb_msr(u64 val)
-{
- u32 low, high;
+ if (ghcb_sw_exit_info_1_is_valid(ghcb) &&
+ ghcb_sw_exit_info_2_is_valid(ghcb))
+ ret = ghcb->save.sw_exit_info_2;
- low = (u32)(val);
- high = (u32)(val >> 32);
+ __sev_put_ghcb(&state);
- native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high);
-}
+ local_irq_restore(flags);
-static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt,
- unsigned char *buffer)
-{
- return copy_from_kernel_nofault(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
+ return ret;
}
-static enum es_result __vc_decode_user_insn(struct es_em_ctxt *ctxt)
+static inline void __pval_terminate(u64 pfn, bool action, unsigned int page_size,
+ int ret, u64 svsm_ret)
{
- char buffer[MAX_INSN_SIZE];
- int insn_bytes;
-
- insn_bytes = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
- if (insn_bytes == 0) {
- /* Nothing could be copied */
- ctxt->fi.vector = X86_TRAP_PF;
- ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
- ctxt->fi.cr2 = ctxt->regs->ip;
- return ES_EXCEPTION;
- } else if (insn_bytes == -EINVAL) {
- /* Effective RIP could not be calculated */
- ctxt->fi.vector = X86_TRAP_GP;
- ctxt->fi.error_code = 0;
- ctxt->fi.cr2 = 0;
- return ES_EXCEPTION;
- }
-
- if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, insn_bytes))
- return ES_DECODE_FAILED;
+ WARN(1, "PVALIDATE failure: pfn: 0x%llx, action: %u, size: %u, ret: %d, svsm_ret: 0x%llx\n",
+ pfn, action, page_size, ret, svsm_ret);
- if (ctxt->insn.immediate.got)
- return ES_OK;
- else
- return ES_DECODE_FAILED;
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PVALIDATE);
}
-static enum es_result __vc_decode_kern_insn(struct es_em_ctxt *ctxt)
+static void svsm_pval_terminate(struct svsm_pvalidate_call *pc, int ret, u64 svsm_ret)
{
- char buffer[MAX_INSN_SIZE];
- int res, ret;
+ unsigned int page_size;
+ bool action;
+ u64 pfn;
- res = vc_fetch_insn_kernel(ctxt, buffer);
- if (res) {
- ctxt->fi.vector = X86_TRAP_PF;
- ctxt->fi.error_code = X86_PF_INSTR;
- ctxt->fi.cr2 = ctxt->regs->ip;
- return ES_EXCEPTION;
- }
+ pfn = pc->entry[pc->cur_index].pfn;
+ action = pc->entry[pc->cur_index].action;
+ page_size = pc->entry[pc->cur_index].page_size;
- ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
- if (ret < 0)
- return ES_DECODE_FAILED;
- else
- return ES_OK;
+ __pval_terminate(pfn, action, page_size, ret, svsm_ret);
}
-static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+static void pval_pages(struct snp_psc_desc *desc)
{
- if (user_mode(ctxt->regs))
- return __vc_decode_user_insn(ctxt);
- else
- return __vc_decode_kern_insn(ctxt);
-}
+ struct psc_entry *e;
+ unsigned long vaddr;
+ unsigned int size;
+ unsigned int i;
+ bool validate;
+ u64 pfn;
+ int rc;
-static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
- char *dst, char *buf, size_t size)
-{
- unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;
+ for (i = 0; i <= desc->hdr.end_entry; i++) {
+ e = &desc->entries[i];
- /*
- * This function uses __put_user() independent of whether kernel or user
- * memory is accessed. This works fine because __put_user() does no
- * sanity checks of the pointer being accessed. All that it does is
- * to report when the access failed.
- *
- * Also, this function runs in atomic context, so __put_user() is not
- * allowed to sleep. The page-fault handler detects that it is running
- * in atomic context and will not try to take mmap_sem and handle the
- * fault, so additional pagefault_enable()/disable() calls are not
- * needed.
- *
- * The access can't be done via copy_to_user() here because
- * vc_write_mem() must not use string instructions to access unsafe
- * memory. The reason is that MOVS is emulated by the #VC handler by
- * splitting the move up into a read and a write and taking a nested #VC
- * exception on whatever of them is the MMIO access. Using string
- * instructions here would cause infinite nesting.
- */
- switch (size) {
- case 1: {
- u8 d1;
- u8 __user *target = (u8 __user *)dst;
-
- memcpy(&d1, buf, 1);
- if (__put_user(d1, target))
- goto fault;
- break;
- }
- case 2: {
- u16 d2;
- u16 __user *target = (u16 __user *)dst;
+ pfn = e->gfn;
+ vaddr = (unsigned long)pfn_to_kaddr(pfn);
+ size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
+ validate = e->operation == SNP_PAGE_STATE_PRIVATE;
- memcpy(&d2, buf, 2);
- if (__put_user(d2, target))
- goto fault;
- break;
- }
- case 4: {
- u32 d4;
- u32 __user *target = (u32 __user *)dst;
+ rc = pvalidate(vaddr, size, validate);
+ if (!rc)
+ continue;
- memcpy(&d4, buf, 4);
- if (__put_user(d4, target))
- goto fault;
- break;
- }
- case 8: {
- u64 d8;
- u64 __user *target = (u64 __user *)dst;
+ if (rc == PVALIDATE_FAIL_SIZEMISMATCH && size == RMP_PG_SIZE_2M) {
+ unsigned long vaddr_end = vaddr + PMD_SIZE;
- memcpy(&d8, buf, 8);
- if (__put_user(d8, target))
- goto fault;
- break;
- }
- default:
- WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
- return ES_UNSUPPORTED;
+ for (; vaddr < vaddr_end; vaddr += PAGE_SIZE, pfn++) {
+ rc = pvalidate(vaddr, RMP_PG_SIZE_4K, validate);
+ if (rc)
+ __pval_terminate(pfn, validate, RMP_PG_SIZE_4K, rc, 0);
+ }
+ } else {
+ __pval_terminate(pfn, validate, size, rc, 0);
+ }
}
-
- return ES_OK;
-
-fault:
- if (user_mode(ctxt->regs))
- error_code |= X86_PF_USER;
-
- ctxt->fi.vector = X86_TRAP_PF;
- ctxt->fi.error_code = error_code;
- ctxt->fi.cr2 = (unsigned long)dst;
-
- return ES_EXCEPTION;
}
-static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
- char *src, char *buf, size_t size)
+static u64 svsm_build_ca_from_pfn_range(u64 pfn, u64 pfn_end, bool action,
+ struct svsm_pvalidate_call *pc)
{
- unsigned long error_code = X86_PF_PROT;
+ struct svsm_pvalidate_entry *pe;
- /*
- * This function uses __get_user() independent of whether kernel or user
- * memory is accessed. This works fine because __get_user() does no
- * sanity checks of the pointer being accessed. All that it does is
- * to report when the access failed.
- *
- * Also, this function runs in atomic context, so __get_user() is not
- * allowed to sleep. The page-fault handler detects that it is running
- * in atomic context and will not try to take mmap_sem and handle the
- * fault, so additional pagefault_enable()/disable() calls are not
- * needed.
- *
- * The access can't be done via copy_from_user() here because
- * vc_read_mem() must not use string instructions to access unsafe
- * memory. The reason is that MOVS is emulated by the #VC handler by
- * splitting the move up into a read and a write and taking a nested #VC
- * exception on whatever of them is the MMIO access. Using string
- * instructions here would cause infinite nesting.
- */
- switch (size) {
- case 1: {
- u8 d1;
- u8 __user *s = (u8 __user *)src;
-
- if (__get_user(d1, s))
- goto fault;
- memcpy(buf, &d1, 1);
- break;
- }
- case 2: {
- u16 d2;
- u16 __user *s = (u16 __user *)src;
-
- if (__get_user(d2, s))
- goto fault;
- memcpy(buf, &d2, 2);
- break;
- }
- case 4: {
- u32 d4;
- u32 __user *s = (u32 __user *)src;
-
- if (__get_user(d4, s))
- goto fault;
- memcpy(buf, &d4, 4);
- break;
- }
- case 8: {
- u64 d8;
- u64 __user *s = (u64 __user *)src;
- if (__get_user(d8, s))
- goto fault;
- memcpy(buf, &d8, 8);
- break;
- }
- default:
- WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
- return ES_UNSUPPORTED;
- }
-
- return ES_OK;
+ /* Nothing in the CA yet */
+ pc->num_entries = 0;
+ pc->cur_index = 0;
-fault:
- if (user_mode(ctxt->regs))
- error_code |= X86_PF_USER;
-
- ctxt->fi.vector = X86_TRAP_PF;
- ctxt->fi.error_code = error_code;
- ctxt->fi.cr2 = (unsigned long)src;
-
- return ES_EXCEPTION;
-}
-
-static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
- unsigned long vaddr, phys_addr_t *paddr)
-{
- unsigned long va = (unsigned long)vaddr;
- unsigned int level;
- phys_addr_t pa;
- pgd_t *pgd;
- pte_t *pte;
+ pe = &pc->entry[0];
- pgd = __va(read_cr3_pa());
- pgd = &pgd[pgd_index(va)];
- pte = lookup_address_in_pgd(pgd, va, &level);
- if (!pte) {
- ctxt->fi.vector = X86_TRAP_PF;
- ctxt->fi.cr2 = vaddr;
- ctxt->fi.error_code = 0;
+ while (pfn < pfn_end) {
+ pe->page_size = RMP_PG_SIZE_4K;
+ pe->action = action;
+ pe->ignore_cf = 0;
+ pe->pfn = pfn;
- if (user_mode(ctxt->regs))
- ctxt->fi.error_code |= X86_PF_USER;
+ pe++;
+ pfn++;
- return ES_EXCEPTION;
+ pc->num_entries++;
+ if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
+ break;
}
- if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
- /* Emulated MMIO to/from encrypted memory not supported */
- return ES_UNSUPPORTED;
-
- pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
- pa |= va & ~page_level_mask(level);
-
- *paddr = pa;
-
- return ES_OK;
+ return pfn;
}
-static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+static int svsm_build_ca_from_psc_desc(struct snp_psc_desc *desc, unsigned int desc_entry,
+ struct svsm_pvalidate_call *pc)
{
- BUG_ON(size > 4);
-
- if (user_mode(ctxt->regs)) {
- struct thread_struct *t = &current->thread;
- struct io_bitmap *iobm = t->io_bitmap;
- size_t idx;
-
- if (!iobm)
- goto fault;
-
- for (idx = port; idx < port + size; ++idx) {
- if (test_bit(idx, iobm->bitmap))
- goto fault;
- }
- }
-
- return ES_OK;
+ struct svsm_pvalidate_entry *pe;
+ struct psc_entry *e;
-fault:
- ctxt->fi.vector = X86_TRAP_GP;
- ctxt->fi.error_code = 0;
+ /* Nothing in the CA yet */
+ pc->num_entries = 0;
+ pc->cur_index = 0;
- return ES_EXCEPTION;
-}
+ pe = &pc->entry[0];
+ e = &desc->entries[desc_entry];
-static __always_inline void vc_forward_exception(struct es_em_ctxt *ctxt)
-{
- long error_code = ctxt->fi.error_code;
- int trapnr = ctxt->fi.vector;
+ while (desc_entry <= desc->hdr.end_entry) {
+ pe->page_size = e->pagesize ? RMP_PG_SIZE_2M : RMP_PG_SIZE_4K;
+ pe->action = e->operation == SNP_PAGE_STATE_PRIVATE;
+ pe->ignore_cf = 0;
+ pe->pfn = e->gfn;
- ctxt->regs->orig_ax = ctxt->fi.error_code;
+ pe++;
+ e++;
- switch (trapnr) {
- case X86_TRAP_GP:
- exc_general_protection(ctxt->regs, error_code);
- break;
- case X86_TRAP_UD:
- exc_invalid_op(ctxt->regs);
- break;
- case X86_TRAP_PF:
- write_cr2(ctxt->fi.cr2);
- exc_page_fault(ctxt->regs, error_code);
- break;
- case X86_TRAP_AC:
- exc_alignment_check(ctxt->regs, error_code);
- break;
- default:
- pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
- BUG();
+ desc_entry++;
+ pc->num_entries++;
+ if (pc->num_entries == SVSM_PVALIDATE_MAX_COUNT)
+ break;
}
-}
-/* Include code shared with pre-decompression boot stage */
-#include "shared.c"
-
-static inline struct svsm_ca *svsm_get_caa(void)
-{
- /*
- * Use rIP-relative references when called early in the boot. If
- * ->use_cas is set, then it is late in the boot and no need
- * to worry about rIP-relative references.
- */
- if (RIP_REL_REF(sev_cfg).use_cas)
- return this_cpu_read(svsm_caa);
- else
- return RIP_REL_REF(boot_svsm_caa);
-}
-
-static u64 svsm_get_caa_pa(void)
-{
- /*
- * Use rIP-relative references when called early in the boot. If
- * ->use_cas is set, then it is late in the boot and no need
- * to worry about rIP-relative references.
- */
- if (RIP_REL_REF(sev_cfg).use_cas)
- return this_cpu_read(svsm_caa_pa);
- else
- return RIP_REL_REF(boot_svsm_caa_pa);
+ return desc_entry;
}
-static noinstr void __sev_put_ghcb(struct ghcb_state *state)
+static void svsm_pval_pages(struct snp_psc_desc *desc)
{
- struct sev_es_runtime_data *data;
- struct ghcb *ghcb;
-
- WARN_ON(!irqs_disabled());
-
- data = this_cpu_read(runtime_data);
- ghcb = &data->ghcb_page;
-
- if (state->ghcb) {
- /* Restore GHCB from Backup */
- *ghcb = *state->ghcb;
- data->backup_ghcb_active = false;
- state->ghcb = NULL;
- } else {
- /*
- * Invalidate the GHCB so a VMGEXIT instruction issued
- * from userspace won't appear to be valid.
- */
- vc_ghcb_invalidate(ghcb);
- data->ghcb_active = false;
- }
-}
-
-static int svsm_perform_call_protocol(struct svsm_call *call)
-{
- struct ghcb_state state;
+ struct svsm_pvalidate_entry pv_4k[VMGEXIT_PSC_MAX_ENTRY];
+ unsigned int i, pv_4k_count = 0;
+ struct svsm_pvalidate_call *pc;
+ struct svsm_call call = {};
unsigned long flags;
- struct ghcb *ghcb;
+ bool action;
+ u64 pc_pa;
int ret;
/*
@@ -666,180 +289,166 @@ static int svsm_perform_call_protocol(struct svsm_call *call)
flags = native_local_irq_save();
/*
- * Use rip-relative references when called early in the boot. If
- * ghcbs_initialized is set, then it is late in the boot and no need
- * to worry about rip-relative references in called functions.
+ * The SVSM calling area (CA) can support processing 510 entries at a
+ * time. Loop through the Page State Change descriptor until the CA is
+ * full or the last entry in the descriptor is reached, at which time
+ * the SVSM is invoked. This repeats until all entries in the descriptor
+ * are processed.
*/
- if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
- ghcb = __sev_get_ghcb(&state);
- else if (RIP_REL_REF(boot_ghcb))
- ghcb = RIP_REL_REF(boot_ghcb);
- else
- ghcb = NULL;
+ call.caa = svsm_get_caa();
- do {
- ret = ghcb ? svsm_perform_ghcb_protocol(ghcb, call)
- : svsm_perform_msr_protocol(call);
- } while (ret == -EAGAIN);
+ pc = (struct svsm_pvalidate_call *)call.caa->svsm_buffer;
+ pc_pa = svsm_get_caa_pa() + offsetof(struct svsm_ca, svsm_buffer);
- if (RIP_REL_REF(sev_cfg).ghcbs_initialized)
- __sev_put_ghcb(&state);
+ /* Protocol 0, Call ID 1 */
+ call.rax = SVSM_CORE_CALL(SVSM_CORE_PVALIDATE);
+ call.rcx = pc_pa;
- native_local_irq_restore(flags);
+ for (i = 0; i <= desc->hdr.end_entry;) {
+ i = svsm_build_ca_from_psc_desc(desc, i, pc);
- return ret;
-}
+ do {
+ ret = svsm_perform_call_protocol(&call);
+ if (!ret)
+ continue;
-void noinstr __sev_es_nmi_complete(void)
-{
- struct ghcb_state state;
- struct ghcb *ghcb;
+ /*
+ * Check if the entry failed because of an RMP mismatch (a
+ * PVALIDATE at 2M was requested, but the page is mapped in
+ * the RMP as 4K).
+ */
- ghcb = __sev_get_ghcb(&state);
+ if (call.rax_out == SVSM_PVALIDATE_FAIL_SIZEMISMATCH &&
+ pc->entry[pc->cur_index].page_size == RMP_PG_SIZE_2M) {
+ /* Save this entry for post-processing at 4K */
+ pv_4k[pv_4k_count++] = pc->entry[pc->cur_index];
+
+ /* Skip to the next one unless at the end of the list */
+ pc->cur_index++;
+ if (pc->cur_index < pc->num_entries)
+ ret = -EAGAIN;
+ else
+ ret = 0;
+ }
+ } while (ret == -EAGAIN);
- vc_ghcb_invalidate(ghcb);
- ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE);
- ghcb_set_sw_exit_info_1(ghcb, 0);
- ghcb_set_sw_exit_info_2(ghcb, 0);
+ if (ret)
+ svsm_pval_terminate(pc, ret, call.rax_out);
+ }
- sev_es_wr_ghcb_msr(__pa_nodebug(ghcb));
- VMGEXIT();
+ /* Process any entries that failed to be validated at 2M and validate them at 4K */
+ for (i = 0; i < pv_4k_count; i++) {
+ u64 pfn, pfn_end;
- __sev_put_ghcb(&state);
-}
+ action = pv_4k[i].action;
+ pfn = pv_4k[i].pfn;
+ pfn_end = pfn + 512;
-static u64 __init get_snp_jump_table_addr(void)
-{
- struct snp_secrets_page *secrets;
- void __iomem *mem;
- u64 addr;
+ while (pfn < pfn_end) {
+ pfn = svsm_build_ca_from_pfn_range(pfn, pfn_end, action, pc);
- mem = ioremap_encrypted(secrets_pa, PAGE_SIZE);
- if (!mem) {
- pr_err("Unable to locate AP jump table address: failed to map the SNP secrets page.\n");
- return 0;
+ ret = svsm_perform_call_protocol(&call);
+ if (ret)
+ svsm_pval_terminate(pc, ret, call.rax_out);
+ }
}
- secrets = (__force struct snp_secrets_page *)mem;
-
- addr = secrets->os_area.ap_jump_table_pa;
- iounmap(mem);
-
- return addr;
+ native_local_irq_restore(flags);
}
-static u64 __init get_jump_table_addr(void)
+static void pvalidate_pages(struct snp_psc_desc *desc)
{
- struct ghcb_state state;
- unsigned long flags;
- struct ghcb *ghcb;
- u64 ret = 0;
-
- if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
- return get_snp_jump_table_addr();
-
- local_irq_save(flags);
-
- ghcb = __sev_get_ghcb(&state);
-
- vc_ghcb_invalidate(ghcb);
- ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_AP_JUMP_TABLE);
- ghcb_set_sw_exit_info_1(ghcb, SVM_VMGEXIT_GET_AP_JUMP_TABLE);
- ghcb_set_sw_exit_info_2(ghcb, 0);
-
- sev_es_wr_ghcb_msr(__pa(ghcb));
- VMGEXIT();
+ struct psc_entry *e;
+ unsigned int i;
- if (ghcb_sw_exit_info_1_is_valid(ghcb) &&
- ghcb_sw_exit_info_2_is_valid(ghcb))
- ret = ghcb->save.sw_exit_info_2;
+ if (snp_vmpl)
+ svsm_pval_pages(desc);
+ else
+ pval_pages(desc);
- __sev_put_ghcb(&state);
+ /*
+ * If not affected by the cache-coherency vulnerability there is no need
+ * to perform the cache eviction mitigation.
+ */
+ if (cpu_feature_enabled(X86_FEATURE_COHERENCY_SFW_NO))
+ return;
- local_irq_restore(flags);
+ for (i = 0; i <= desc->hdr.end_entry; i++) {
+ e = &desc->entries[i];
- return ret;
+ /*
+ * If validating memory (making it private) perform the cache
+ * eviction mitigation.
+ */
+ if (e->operation == SNP_PAGE_STATE_PRIVATE)
+ sev_evict_cache(pfn_to_kaddr(e->gfn), e->pagesize ? 512 : 1);
+ }
}
-static void __head
-early_set_pages_state(unsigned long vaddr, unsigned long paddr,
- unsigned long npages, enum psc_op op)
+static int vmgexit_psc(struct ghcb *ghcb, struct snp_psc_desc *desc)
{
- unsigned long paddr_end;
- u64 val;
-
- vaddr = vaddr & PAGE_MASK;
+ int cur_entry, end_entry, ret = 0;
+ struct snp_psc_desc *data;
+ struct es_em_ctxt ctxt;
- paddr = paddr & PAGE_MASK;
- paddr_end = paddr + (npages << PAGE_SHIFT);
+ vc_ghcb_invalidate(ghcb);
- while (paddr < paddr_end) {
- /* Page validation must be rescinded before changing to shared */
- if (op == SNP_PAGE_STATE_SHARED)
- pvalidate_4k_page(vaddr, paddr, false);
+ /* Copy the input desc into GHCB shared buffer */
+ data = (struct snp_psc_desc *)ghcb->shared_buffer;
+ memcpy(ghcb->shared_buffer, desc, min_t(int, GHCB_SHARED_BUF_SIZE, sizeof(*desc)));
- /*
- * Use the MSR protocol because this function can be called before
- * the GHCB is established.
- */
- sev_es_wr_ghcb_msr(GHCB_MSR_PSC_REQ_GFN(paddr >> PAGE_SHIFT, op));
- VMGEXIT();
+ /*
+ * As per the GHCB specification, the hypervisor can resume the guest
+ * before processing all the entries. Check whether all the entries
+ * are processed. If not, then keep retrying. Note, the hypervisor
+ * will update the data memory directly to indicate the status, so
+ * reference the data->hdr everywhere.
+ *
+ * The strategy here is to wait for the hypervisor to change the page
+ * state in the RMP table before guest accesses the memory pages. If the
+ * page state change was not successful, then later memory access will
+ * result in a crash.
+ */
+ cur_entry = data->hdr.cur_entry;
+ end_entry = data->hdr.end_entry;
- val = sev_es_rd_ghcb_msr();
+ while (data->hdr.cur_entry <= data->hdr.end_entry) {
+ ghcb_set_sw_scratch(ghcb, (u64)__pa(data));
- if (GHCB_RESP_CODE(val) != GHCB_MSR_PSC_RESP)
- goto e_term;
+ /* This will advance the shared buffer data points to. */
+ ret = sev_es_ghcb_hv_call(ghcb, &ctxt, SVM_VMGEXIT_PSC, 0, 0);
- if (GHCB_MSR_PSC_RESP_VAL(val))
- goto e_term;
+ /*
+ * Page State Change VMGEXIT can pass error code through
+ * exit_info_2.
+ */
+ if (WARN(ret || ghcb->save.sw_exit_info_2,
+ "SNP: PSC failed ret=%d exit_info_2=%llx\n",
+ ret, ghcb->save.sw_exit_info_2)) {
+ ret = 1;
+ goto out;
+ }
- /* Page validation must be performed after changing to private */
- if (op == SNP_PAGE_STATE_PRIVATE)
- pvalidate_4k_page(vaddr, paddr, true);
+ /* Verify that reserved bit is not set */
+ if (WARN(data->hdr.reserved, "Reserved bit is set in the PSC header\n")) {
+ ret = 1;
+ goto out;
+ }
- vaddr += PAGE_SIZE;
- paddr += PAGE_SIZE;
+ /*
+ * Sanity check that entry processing is not going backwards.
+ * This will happen only if hypervisor is tricking us.
+ */
+ if (WARN(data->hdr.end_entry > end_entry || cur_entry > data->hdr.cur_entry,
+"SNP: PSC processing going backward, end_entry %d (got %d) cur_entry %d (got %d)\n",
+ end_entry, data->hdr.end_entry, cur_entry, data->hdr.cur_entry)) {
+ ret = 1;
+ goto out;
+ }
}
- return;
-
-e_term:
- sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_PSC);
-}
-
-void __head early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
- unsigned long npages)
-{
- /*
- * This can be invoked in early boot while running identity mapped, so
- * use an open coded check for SNP instead of using cc_platform_has().
- * This eliminates worries about jump tables or checking boot_cpu_data
- * in the cc_platform_has() function.
- */
- if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED))
- return;
-
- /*
- * Ask the hypervisor to mark the memory pages as private in the RMP
- * table.
- */
- early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_PRIVATE);
-}
-
-void __head early_snp_set_memory_shared(unsigned long vaddr, unsigned long paddr,
- unsigned long npages)
-{
- /*
- * This can be invoked in early boot while running identity mapped, so
- * use an open coded check for SNP instead of using cc_platform_has().
- * This eliminates worries about jump tables or checking boot_cpu_data
- * in the cc_platform_has() function.
- */
- if (!(RIP_REL_REF(sev_status) & MSR_AMD64_SEV_SNP_ENABLED))
- return;
-
- /* Ask hypervisor to mark the memory pages shared in the RMP table. */
- early_set_pages_state(vaddr, paddr, npages, SNP_PAGE_STATE_SHARED);
+out:
+ return ret;
}
static unsigned long __set_pages_state(struct snp_psc_desc *data, unsigned long vaddr,
@@ -1281,12 +890,12 @@ static void *snp_alloc_vmsa_page(int cpu)
return page_address(p + 1);
}
-static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
+static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip, unsigned int cpu)
{
struct sev_es_save_area *cur_vmsa, *vmsa;
struct svsm_ca *caa;
u8 sipi_vector;
- int cpu, ret;
+ int ret;
u64 cr4;
/*
@@ -1307,15 +916,6 @@ static int wakeup_cpu_via_vmgexit(u32 apic_id, unsigned long start_ip)
/* Override start_ip with known protected guest start IP */
start_ip = real_mode_header->sev_es_trampoline_start;
-
- /* Find the logical CPU for the APIC ID */
- for_each_present_cpu(cpu) {
- if (arch_match_cpu_phys_id(cpu, apic_id))
- break;
- }
- if (cpu >= nr_cpu_ids)
- return -EINVAL;
-
cur_vmsa = per_cpu(sev_vmsa, cpu);
/*
@@ -1466,11 +1066,13 @@ int __init sev_es_setup_ap_jump_table(struct real_mode_header *rmh)
* This is needed by the OVMF UEFI firmware which will use whatever it finds in
* the GHCB MSR as its GHCB to talk to the hypervisor. So make sure the per-cpu
* runtime GHCBs used by the kernel are also mapped in the EFI page-table.
+ *
+ * When running under SVSM the CA page is needed too, so map it as well.
*/
-int __init sev_es_efi_map_ghcbs(pgd_t *pgd)
+int __init sev_es_efi_map_ghcbs_cas(pgd_t *pgd)
{
+ unsigned long address, pflags, pflags_enc;
struct sev_es_runtime_data *data;
- unsigned long address, pflags;
int cpu;
u64 pfn;
@@ -1478,6 +1080,7 @@ int __init sev_es_efi_map_ghcbs(pgd_t *pgd)
return 0;
pflags = _PAGE_NX | _PAGE_RW;
+ pflags_enc = cc_mkenc(pflags);
for_each_possible_cpu(cpu) {
data = per_cpu(runtime_data, cpu);
@@ -1487,93 +1090,19 @@ int __init sev_es_efi_map_ghcbs(pgd_t *pgd)
if (kernel_map_pages_in_pgd(pgd, pfn, address, 1, pflags))
return 1;
- }
-
- return 0;
-}
-
-/* Writes to the SVSM CAA MSR are ignored */
-static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write)
-{
- if (write)
- return ES_OK;
-
- regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa));
- regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa));
-
- return ES_OK;
-}
-
-/*
- * TSC related accesses should not exit to the hypervisor when a guest is
- * executing with Secure TSC enabled, so special handling is required for
- * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ.
- */
-static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write)
-{
- u64 tsc;
- /*
- * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled.
- * Terminate the SNP guest when the interception is enabled.
- */
- if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ)
- return ES_VMM_ERROR;
-
- /*
- * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC
- * to return undefined values, so ignore all writes.
- *
- * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use
- * the value returned by rdtsc_ordered().
- */
- if (write) {
- WARN_ONCE(1, "TSC MSR writes are verboten!\n");
- return ES_OK;
- }
-
- tsc = rdtsc_ordered();
- regs->ax = lower_32_bits(tsc);
- regs->dx = upper_32_bits(tsc);
-
- return ES_OK;
-}
-
-static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
- struct pt_regs *regs = ctxt->regs;
- enum es_result ret;
- bool write;
-
- /* Is it a WRMSR? */
- write = ctxt->insn.opcode.bytes[1] == 0x30;
+ if (snp_vmpl) {
+ address = per_cpu(svsm_caa_pa, cpu);
+ if (!address)
+ return 1;
- switch (regs->cx) {
- case MSR_SVSM_CAA:
- return __vc_handle_msr_caa(regs, write);
- case MSR_IA32_TSC:
- case MSR_AMD64_GUEST_TSC_FREQ:
- if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
- return __vc_handle_secure_tsc_msrs(regs, write);
- break;
- default:
- break;
- }
-
- ghcb_set_rcx(ghcb, regs->cx);
- if (write) {
- ghcb_set_rax(ghcb, regs->ax);
- ghcb_set_rdx(ghcb, regs->dx);
- }
-
- ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, write, 0);
-
- if ((ret == ES_OK) && !write) {
- regs->ax = ghcb->save.rax;
- regs->dx = ghcb->save.rdx;
+ pfn = address >> PAGE_SHIFT;
+ if (kernel_map_pages_in_pgd(pgd, pfn, address, 1, pflags_enc))
+ return 1;
+ }
}
- return ret;
+ return 0;
}
static void snp_register_per_cpu_ghcb(void)
@@ -1788,748 +1317,6 @@ void __init sev_es_init_vc_handling(void)
initial_vc_handler = (unsigned long)kernel_exc_vmm_communication;
}
-static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt)
-{
- int trapnr = ctxt->fi.vector;
-
- if (trapnr == X86_TRAP_PF)
- native_write_cr2(ctxt->fi.cr2);
-
- ctxt->regs->orig_ax = ctxt->fi.error_code;
- do_early_exception(ctxt->regs, trapnr);
-}
-
-static long *vc_insn_get_rm(struct es_em_ctxt *ctxt)
-{
- long *reg_array;
- int offset;
-
- reg_array = (long *)ctxt->regs;
- offset = insn_get_modrm_rm_off(&ctxt->insn, ctxt->regs);
-
- if (offset < 0)
- return NULL;
-
- offset /= sizeof(long);
-
- return reg_array + offset;
-}
-static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
- unsigned int bytes, bool read)
-{
- u64 exit_code, exit_info_1, exit_info_2;
- unsigned long ghcb_pa = __pa(ghcb);
- enum es_result res;
- phys_addr_t paddr;
- void __user *ref;
-
- ref = insn_get_addr_ref(&ctxt->insn, ctxt->regs);
- if (ref == (void __user *)-1L)
- return ES_UNSUPPORTED;
-
- exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
-
- res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
- if (res != ES_OK) {
- if (res == ES_EXCEPTION && !read)
- ctxt->fi.error_code |= X86_PF_WRITE;
-
- return res;
- }
-
- exit_info_1 = paddr;
- /* Can never be greater than 8 */
- exit_info_2 = bytes;
-
- ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer));
-
- return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2);
-}
-
-/*
- * The MOVS instruction has two memory operands, which raises the
- * problem that it is not known whether the access to the source or the
- * destination caused the #VC exception (and hence whether an MMIO read
- * or write operation needs to be emulated).
- *
- * Instead of playing games with walking page-tables and trying to guess
- * whether the source or destination is an MMIO range, split the move
- * into two operations, a read and a write with only one memory operand.
- * This will cause a nested #VC exception on the MMIO address which can
- * then be handled.
- *
- * This implementation has the benefit that it also supports MOVS where
- * source _and_ destination are MMIO regions.
- *
- * It will slow MOVS on MMIO down a lot, but in SEV-ES guests it is a
- * rare operation. If it turns out to be a performance problem the split
- * operations can be moved to memcpy_fromio() and memcpy_toio().
- */
-static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
- unsigned int bytes)
-{
- unsigned long ds_base, es_base;
- unsigned char *src, *dst;
- unsigned char buffer[8];
- enum es_result ret;
- bool rep;
- int off;
-
- ds_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_DS);
- es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
-
- if (ds_base == -1L || es_base == -1L) {
- ctxt->fi.vector = X86_TRAP_GP;
- ctxt->fi.error_code = 0;
- return ES_EXCEPTION;
- }
-
- src = ds_base + (unsigned char *)ctxt->regs->si;
- dst = es_base + (unsigned char *)ctxt->regs->di;
-
- ret = vc_read_mem(ctxt, src, buffer, bytes);
- if (ret != ES_OK)
- return ret;
-
- ret = vc_write_mem(ctxt, dst, buffer, bytes);
- if (ret != ES_OK)
- return ret;
-
- if (ctxt->regs->flags & X86_EFLAGS_DF)
- off = -bytes;
- else
- off = bytes;
-
- ctxt->regs->si += off;
- ctxt->regs->di += off;
-
- rep = insn_has_rep_prefix(&ctxt->insn);
- if (rep)
- ctxt->regs->cx -= 1;
-
- if (!rep || ctxt->regs->cx == 0)
- return ES_OK;
- else
- return ES_RETRY;
-}
-
-static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
- struct insn *insn = &ctxt->insn;
- enum insn_mmio_type mmio;
- unsigned int bytes = 0;
- enum es_result ret;
- u8 sign_byte;
- long *reg_data;
-
- mmio = insn_decode_mmio(insn, &bytes);
- if (mmio == INSN_MMIO_DECODE_FAILED)
- return ES_DECODE_FAILED;
-
- if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
- reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
- if (!reg_data)
- return ES_DECODE_FAILED;
- }
-
- if (user_mode(ctxt->regs))
- return ES_UNSUPPORTED;
-
- switch (mmio) {
- case INSN_MMIO_WRITE:
- memcpy(ghcb->shared_buffer, reg_data, bytes);
- ret = vc_do_mmio(ghcb, ctxt, bytes, false);
- break;
- case INSN_MMIO_WRITE_IMM:
- memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
- ret = vc_do_mmio(ghcb, ctxt, bytes, false);
- break;
- case INSN_MMIO_READ:
- ret = vc_do_mmio(ghcb, ctxt, bytes, true);
- if (ret)
- break;
-
- /* Zero-extend for 32-bit operation */
- if (bytes == 4)
- *reg_data = 0;
-
- memcpy(reg_data, ghcb->shared_buffer, bytes);
- break;
- case INSN_MMIO_READ_ZERO_EXTEND:
- ret = vc_do_mmio(ghcb, ctxt, bytes, true);
- if (ret)
- break;
-
- /* Zero extend based on operand size */
- memset(reg_data, 0, insn->opnd_bytes);
- memcpy(reg_data, ghcb->shared_buffer, bytes);
- break;
- case INSN_MMIO_READ_SIGN_EXTEND:
- ret = vc_do_mmio(ghcb, ctxt, bytes, true);
- if (ret)
- break;
-
- if (bytes == 1) {
- u8 *val = (u8 *)ghcb->shared_buffer;
-
- sign_byte = (*val & 0x80) ? 0xff : 0x00;
- } else {
- u16 *val = (u16 *)ghcb->shared_buffer;
-
- sign_byte = (*val & 0x8000) ? 0xff : 0x00;
- }
-
- /* Sign extend based on operand size */
- memset(reg_data, sign_byte, insn->opnd_bytes);
- memcpy(reg_data, ghcb->shared_buffer, bytes);
- break;
- case INSN_MMIO_MOVS:
- ret = vc_handle_mmio_movs(ctxt, bytes);
- break;
- default:
- ret = ES_UNSUPPORTED;
- break;
- }
-
- return ret;
-}
-
-static enum es_result vc_handle_dr7_write(struct ghcb *ghcb,
- struct es_em_ctxt *ctxt)
-{
- struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
- long val, *reg = vc_insn_get_rm(ctxt);
- enum es_result ret;
-
- if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
- return ES_VMM_ERROR;
-
- if (!reg)
- return ES_DECODE_FAILED;
-
- val = *reg;
-
- /* Upper 32 bits must be written as zeroes */
- if (val >> 32) {
- ctxt->fi.vector = X86_TRAP_GP;
- ctxt->fi.error_code = 0;
- return ES_EXCEPTION;
- }
-
- /* Clear out other reserved bits and set bit 10 */
- val = (val & 0xffff23ffL) | BIT(10);
-
- /* Early non-zero writes to DR7 are not supported */
- if (!data && (val & ~DR7_RESET_VALUE))
- return ES_UNSUPPORTED;
-
- /* Using a value of 0 for ExitInfo1 means RAX holds the value */
- ghcb_set_rax(ghcb, val);
- ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
- if (ret != ES_OK)
- return ret;
-
- if (data)
- data->dr7 = val;
-
- return ES_OK;
-}
-
-static enum es_result vc_handle_dr7_read(struct ghcb *ghcb,
- struct es_em_ctxt *ctxt)
-{
- struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
- long *reg = vc_insn_get_rm(ctxt);
-
- if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
- return ES_VMM_ERROR;
-
- if (!reg)
- return ES_DECODE_FAILED;
-
- if (data)
- *reg = data->dr7;
- else
- *reg = DR7_RESET_VALUE;
-
- return ES_OK;
-}
-
-static enum es_result vc_handle_wbinvd(struct ghcb *ghcb,
- struct es_em_ctxt *ctxt)
-{
- return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0);
-}
-
-static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
-{
- enum es_result ret;
-
- ghcb_set_rcx(ghcb, ctxt->regs->cx);
-
- ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0);
- if (ret != ES_OK)
- return ret;
-
- if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb)))
- return ES_VMM_ERROR;
-
- ctxt->regs->ax = ghcb->save.rax;
- ctxt->regs->dx = ghcb->save.rdx;
-
- return ES_OK;
-}
-
-static enum es_result vc_handle_monitor(struct ghcb *ghcb,
- struct es_em_ctxt *ctxt)
-{
- /*
- * Treat it as a NOP and do not leak a physical address to the
- * hypervisor.
- */
- return ES_OK;
-}
-
-static enum es_result vc_handle_mwait(struct ghcb *ghcb,
- struct es_em_ctxt *ctxt)
-{
- /* Treat the same as MONITOR/MONITORX */
- return ES_OK;
-}
-
-static enum es_result vc_handle_vmmcall(struct ghcb *ghcb,
- struct es_em_ctxt *ctxt)
-{
- enum es_result ret;
-
- ghcb_set_rax(ghcb, ctxt->regs->ax);
- ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0);
-
- if (x86_platform.hyper.sev_es_hcall_prepare)
- x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs);
-
- ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0);
- if (ret != ES_OK)
- return ret;
-
- if (!ghcb_rax_is_valid(ghcb))
- return ES_VMM_ERROR;
-
- ctxt->regs->ax = ghcb->save.rax;
-
- /*
- * Call sev_es_hcall_finish() after regs->ax is already set.
- * This allows the hypervisor handler to overwrite it again if
- * necessary.
- */
- if (x86_platform.hyper.sev_es_hcall_finish &&
- !x86_platform.hyper.sev_es_hcall_finish(ghcb, ctxt->regs))
- return ES_VMM_ERROR;
-
- return ES_OK;
-}
-
-static enum es_result vc_handle_trap_ac(struct ghcb *ghcb,
- struct es_em_ctxt *ctxt)
-{
- /*
- * Calling ecx_alignment_check() directly does not work, because it
- * enables IRQs and the GHCB is active. Forward the exception and call
- * it later from vc_forward_exception().
- */
- ctxt->fi.vector = X86_TRAP_AC;
- ctxt->fi.error_code = 0;
- return ES_EXCEPTION;
-}
-
-static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
- struct ghcb *ghcb,
- unsigned long exit_code)
-{
- enum es_result result = vc_check_opcode_bytes(ctxt, exit_code);
-
- if (result != ES_OK)
- return result;
-
- switch (exit_code) {
- case SVM_EXIT_READ_DR7:
- result = vc_handle_dr7_read(ghcb, ctxt);
- break;
- case SVM_EXIT_WRITE_DR7:
- result = vc_handle_dr7_write(ghcb, ctxt);
- break;
- case SVM_EXIT_EXCP_BASE + X86_TRAP_AC:
- result = vc_handle_trap_ac(ghcb, ctxt);
- break;
- case SVM_EXIT_RDTSC:
- case SVM_EXIT_RDTSCP:
- result = vc_handle_rdtsc(ghcb, ctxt, exit_code);
- break;
- case SVM_EXIT_RDPMC:
- result = vc_handle_rdpmc(ghcb, ctxt);
- break;
- case SVM_EXIT_INVD:
- pr_err_ratelimited("#VC exception for INVD??? Seriously???\n");
- result = ES_UNSUPPORTED;
- break;
- case SVM_EXIT_CPUID:
- result = vc_handle_cpuid(ghcb, ctxt);
- break;
- case SVM_EXIT_IOIO:
- result = vc_handle_ioio(ghcb, ctxt);
- break;
- case SVM_EXIT_MSR:
- result = vc_handle_msr(ghcb, ctxt);
- break;
- case SVM_EXIT_VMMCALL:
- result = vc_handle_vmmcall(ghcb, ctxt);
- break;
- case SVM_EXIT_WBINVD:
- result = vc_handle_wbinvd(ghcb, ctxt);
- break;
- case SVM_EXIT_MONITOR:
- result = vc_handle_monitor(ghcb, ctxt);
- break;
- case SVM_EXIT_MWAIT:
- result = vc_handle_mwait(ghcb, ctxt);
- break;
- case SVM_EXIT_NPF:
- result = vc_handle_mmio(ghcb, ctxt);
- break;
- default:
- /*
- * Unexpected #VC exception
- */
- result = ES_UNSUPPORTED;
- }
-
- return result;
-}
-
-static __always_inline bool is_vc2_stack(unsigned long sp)
-{
- return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
-}
-
-static __always_inline bool vc_from_invalid_context(struct pt_regs *regs)
-{
- unsigned long sp, prev_sp;
-
- sp = (unsigned long)regs;
- prev_sp = regs->sp;
-
- /*
- * If the code was already executing on the VC2 stack when the #VC
- * happened, let it proceed to the normal handling routine. This way the
- * code executing on the VC2 stack can cause #VC exceptions to get handled.
- */
- return is_vc2_stack(sp) && !is_vc2_stack(prev_sp);
-}
-
-static bool vc_raw_handle_exception(struct pt_regs *regs, unsigned long error_code)
-{
- struct ghcb_state state;
- struct es_em_ctxt ctxt;
- enum es_result result;
- struct ghcb *ghcb;
- bool ret = true;
-
- ghcb = __sev_get_ghcb(&state);
-
- vc_ghcb_invalidate(ghcb);
- result = vc_init_em_ctxt(&ctxt, regs, error_code);
-
- if (result == ES_OK)
- result = vc_handle_exitcode(&ctxt, ghcb, error_code);
-
- __sev_put_ghcb(&state);
-
- /* Done - now check the result */
- switch (result) {
- case ES_OK:
- vc_finish_insn(&ctxt);
- break;
- case ES_UNSUPPORTED:
- pr_err_ratelimited("Unsupported exit-code 0x%02lx in #VC exception (IP: 0x%lx)\n",
- error_code, regs->ip);
- ret = false;
- break;
- case ES_VMM_ERROR:
- pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
- error_code, regs->ip);
- ret = false;
- break;
- case ES_DECODE_FAILED:
- pr_err_ratelimited("Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
- error_code, regs->ip);
- ret = false;
- break;
- case ES_EXCEPTION:
- vc_forward_exception(&ctxt);
- break;
- case ES_RETRY:
- /* Nothing to do */
- break;
- default:
- pr_emerg("Unknown result in %s():%d\n", __func__, result);
- /*
- * Emulating the instruction which caused the #VC exception
- * failed - can't continue so print debug information
- */
- BUG();
- }
-
- return ret;
-}
-
-static __always_inline bool vc_is_db(unsigned long error_code)
-{
- return error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB;
-}
-
-/*
- * Runtime #VC exception handler when raised from kernel mode. Runs in NMI mode
- * and will panic when an error happens.
- */
-DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
-{
- irqentry_state_t irq_state;
-
- /*
- * With the current implementation it is always possible to switch to a
- * safe stack because #VC exceptions only happen at known places, like
- * intercepted instructions or accesses to MMIO areas/IO ports. They can
- * also happen with code instrumentation when the hypervisor intercepts
- * #DB, but the critical paths are forbidden to be instrumented, so #DB
- * exceptions currently also only happen in safe places.
- *
- * But keep this here in case the noinstr annotations are violated due
- * to bug elsewhere.
- */
- if (unlikely(vc_from_invalid_context(regs))) {
- instrumentation_begin();
- panic("Can't handle #VC exception from unsupported context\n");
- instrumentation_end();
- }
-
- /*
- * Handle #DB before calling into !noinstr code to avoid recursive #DB.
- */
- if (vc_is_db(error_code)) {
- exc_debug(regs);
- return;
- }
-
- irq_state = irqentry_nmi_enter(regs);
-
- instrumentation_begin();
-
- if (!vc_raw_handle_exception(regs, error_code)) {
- /* Show some debug info */
- show_regs(regs);
-
- /* Ask hypervisor to sev_es_terminate */
- sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-
- /* If that fails and we get here - just panic */
- panic("Returned from Terminate-Request to Hypervisor\n");
- }
-
- instrumentation_end();
- irqentry_nmi_exit(regs, irq_state);
-}
-
-/*
- * Runtime #VC exception handler when raised from user mode. Runs in IRQ mode
- * and will kill the current task with SIGBUS when an error happens.
- */
-DEFINE_IDTENTRY_VC_USER(exc_vmm_communication)
-{
- /*
- * Handle #DB before calling into !noinstr code to avoid recursive #DB.
- */
- if (vc_is_db(error_code)) {
- noist_exc_debug(regs);
- return;
- }
-
- irqentry_enter_from_user_mode(regs);
- instrumentation_begin();
-
- if (!vc_raw_handle_exception(regs, error_code)) {
- /*
- * Do not kill the machine if user-space triggered the
- * exception. Send SIGBUS instead and let user-space deal with
- * it.
- */
- force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0);
- }
-
- instrumentation_end();
- irqentry_exit_to_user_mode(regs);
-}
-
-bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
-{
- unsigned long exit_code = regs->orig_ax;
- struct es_em_ctxt ctxt;
- enum es_result result;
-
- vc_ghcb_invalidate(boot_ghcb);
-
- result = vc_init_em_ctxt(&ctxt, regs, exit_code);
- if (result == ES_OK)
- result = vc_handle_exitcode(&ctxt, boot_ghcb, exit_code);
-
- /* Done - now check the result */
- switch (result) {
- case ES_OK:
- vc_finish_insn(&ctxt);
- break;
- case ES_UNSUPPORTED:
- early_printk("PANIC: Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n",
- exit_code, regs->ip);
- goto fail;
- case ES_VMM_ERROR:
- early_printk("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
- exit_code, regs->ip);
- goto fail;
- case ES_DECODE_FAILED:
- early_printk("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
- exit_code, regs->ip);
- goto fail;
- case ES_EXCEPTION:
- vc_early_forward_exception(&ctxt);
- break;
- case ES_RETRY:
- /* Nothing to do */
- break;
- default:
- BUG();
- }
-
- return true;
-
-fail:
- show_regs(regs);
-
- sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
-}
-
-/*
- * Initial set up of SNP relies on information provided by the
- * Confidential Computing blob, which can be passed to the kernel
- * in the following ways, depending on how it is booted:
- *
- * - when booted via the boot/decompress kernel:
- * - via boot_params
- *
- * - when booted directly by firmware/bootloader (e.g. CONFIG_PVH):
- * - via a setup_data entry, as defined by the Linux Boot Protocol
- *
- * Scan for the blob in that order.
- */
-static __head struct cc_blob_sev_info *find_cc_blob(struct boot_params *bp)
-{
- struct cc_blob_sev_info *cc_info;
-
- /* Boot kernel would have passed the CC blob via boot_params. */
- if (bp->cc_blob_address) {
- cc_info = (struct cc_blob_sev_info *)(unsigned long)bp->cc_blob_address;
- goto found_cc_info;
- }
-
- /*
- * If kernel was booted directly, without the use of the
- * boot/decompression kernel, the CC blob may have been passed via
- * setup_data instead.
- */
- cc_info = find_cc_blob_setup_data(bp);
- if (!cc_info)
- return NULL;
-
-found_cc_info:
- if (cc_info->magic != CC_BLOB_SEV_HDR_MAGIC)
- snp_abort();
-
- return cc_info;
-}
-
-static __head void svsm_setup(struct cc_blob_sev_info *cc_info)
-{
- struct svsm_call call = {};
- int ret;
- u64 pa;
-
- /*
- * Record the SVSM Calling Area address (CAA) if the guest is not
- * running at VMPL0. The CA will be used to communicate with the
- * SVSM to perform the SVSM services.
- */
- if (!svsm_setup_ca(cc_info))
- return;
-
- /*
- * It is very early in the boot and the kernel is running identity
- * mapped but without having adjusted the pagetables to where the
- * kernel was loaded (physbase), so the get the CA address using
- * RIP-relative addressing.
- */
- pa = (u64)&RIP_REL_REF(boot_svsm_ca_page);
-
- /*
- * Switch over to the boot SVSM CA while the current CA is still
- * addressable. There is no GHCB at this point so use the MSR protocol.
- *
- * SVSM_CORE_REMAP_CA call:
- * RAX = 0 (Protocol=0, CallID=0)
- * RCX = New CA GPA
- */
- call.caa = svsm_get_caa();
- call.rax = SVSM_CORE_CALL(SVSM_CORE_REMAP_CA);
- call.rcx = pa;
- ret = svsm_perform_call_protocol(&call);
- if (ret)
- sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SVSM_CA_REMAP_FAIL);
-
- RIP_REL_REF(boot_svsm_caa) = (struct svsm_ca *)pa;
- RIP_REL_REF(boot_svsm_caa_pa) = pa;
-}
-
-bool __head snp_init(struct boot_params *bp)
-{
- struct cc_blob_sev_info *cc_info;
-
- if (!bp)
- return false;
-
- cc_info = find_cc_blob(bp);
- if (!cc_info)
- return false;
-
- if (cc_info->secrets_phys && cc_info->secrets_len == PAGE_SIZE)
- secrets_pa = cc_info->secrets_phys;
- else
- return false;
-
- setup_cpuid_table(cc_info);
-
- svsm_setup(cc_info);
-
- /*
- * The CC blob will be used later to access the secrets page. Cache
- * it here like the boot kernel does.
- */
- bp->cc_blob_address = (u32)(unsigned long)cc_info;
-
- return true;
-}
-
-void __head __noreturn snp_abort(void)
-{
- sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SNP_UNSUPPORTED);
-}
-
/*
* SEV-SNP guests should only execute dmi_setup() if EFI_CONFIG_TABLES are
* enabled, as the alternative (fallback) logic for DMI probing in the legacy
@@ -2636,16 +1423,16 @@ int snp_issue_svsm_attest_req(u64 call_id, struct svsm_call *call,
}
EXPORT_SYMBOL_GPL(snp_issue_svsm_attest_req);
-static int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_data *input,
- struct snp_guest_request_ioctl *rio)
+static int snp_issue_guest_request(struct snp_guest_req *req)
{
+ struct snp_req_data *input = &req->input;
struct ghcb_state state;
struct es_em_ctxt ctxt;
unsigned long flags;
struct ghcb *ghcb;
int ret;
- rio->exitinfo2 = SEV_RET_NO_FW_CALL;
+ req->exitinfo2 = SEV_RET_NO_FW_CALL;
/*
* __sev_get_ghcb() needs to run with IRQs disabled because it is using
@@ -2670,8 +1457,8 @@ static int snp_issue_guest_request(struct snp_guest_req *req, struct snp_req_dat
if (ret)
goto e_put;
- rio->exitinfo2 = ghcb->save.sw_exit_info_2;
- switch (rio->exitinfo2) {
+ req->exitinfo2 = ghcb->save.sw_exit_info_2;
+ switch (req->exitinfo2) {
case 0:
break;
@@ -2700,11 +1487,74 @@ e_restore_irq:
return ret;
}
+/**
+ * snp_svsm_vtpm_probe() - Probe if SVSM provides a vTPM device
+ *
+ * Check that there is SVSM and that it supports at least TPM_SEND_COMMAND
+ * which is the only request used so far.
+ *
+ * Return: true if the platform provides a vTPM SVSM device, false otherwise.
+ */
+static bool snp_svsm_vtpm_probe(void)
+{
+ struct svsm_call call = {};
+
+ /* The vTPM device is available only if a SVSM is present */
+ if (!snp_vmpl)
+ return false;
+
+ call.caa = svsm_get_caa();
+ call.rax = SVSM_VTPM_CALL(SVSM_VTPM_QUERY);
+
+ if (svsm_perform_call_protocol(&call))
+ return false;
+
+ /* Check platform commands contains TPM_SEND_COMMAND - platform command 8 */
+ return call.rcx_out & BIT_ULL(8);
+}
+
+/**
+ * snp_svsm_vtpm_send_command() - Execute a vTPM operation on SVSM
+ * @buffer: A buffer used to both send the command and receive the response.
+ *
+ * Execute a SVSM_VTPM_CMD call as defined by
+ * "Secure VM Service Module for SEV-SNP Guests" Publication # 58019 Revision: 1.00
+ *
+ * All command request/response buffers have a common structure as specified by
+ * the following table:
+ * Byte Size     In/Out    Description
+ * Offset    (Bytes)
+ * 0x000     4          In        Platform command
+ *                         Out       Platform command response size
+ *
+ * Each command can build upon this common request/response structure to create
+ * a structure specific to the command. See include/linux/tpm_svsm.h for more
+ * details.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int snp_svsm_vtpm_send_command(u8 *buffer)
+{
+ struct svsm_call call = {};
+
+ call.caa = svsm_get_caa();
+ call.rax = SVSM_VTPM_CALL(SVSM_VTPM_CMD);
+ call.rcx = __pa(buffer);
+
+ return svsm_perform_call_protocol(&call);
+}
+EXPORT_SYMBOL_GPL(snp_svsm_vtpm_send_command);
+
static struct platform_device sev_guest_device = {
.name = "sev-guest",
.id = -1,
};
+static struct platform_device tpm_svsm_device = {
+ .name = "tpm-svsm",
+ .id = -1,
+};
+
static int __init snp_init_platform_device(void)
{
if (!cc_platform_has(CC_ATTR_GUEST_SEV_SNP))
@@ -2713,7 +1563,11 @@ static int __init snp_init_platform_device(void)
if (platform_device_register(&sev_guest_device))
return -ENODEV;
- pr_info("SNP guest platform device initialized.\n");
+ if (snp_svsm_vtpm_probe() &&
+ platform_device_register(&tpm_svsm_device))
+ return -ENODEV;
+
+ pr_info("SNP guest platform devices initialized.\n");
return 0;
}
device_initcall(snp_init_platform_device);
@@ -2910,7 +1764,7 @@ struct snp_msg_desc *snp_msg_alloc(void)
if (!mdesc)
return ERR_PTR(-ENOMEM);
- mem = ioremap_encrypted(secrets_pa, PAGE_SIZE);
+ mem = ioremap_encrypted(sev_secrets_pa, PAGE_SIZE);
if (!mem)
goto e_free_mdesc;
@@ -3099,8 +1953,7 @@ static int enc_payload(struct snp_msg_desc *mdesc, u64 seqno, struct snp_guest_r
return 0;
}
-static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req,
- struct snp_guest_request_ioctl *rio)
+static int __handle_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req)
{
unsigned long req_start = jiffies;
unsigned int override_npages = 0;
@@ -3114,7 +1967,7 @@ retry_request:
* sequence number must be incremented or the VMPCK must be deleted to
* prevent reuse of the IV.
*/
- rc = snp_issue_guest_request(req, &req->input, rio);
+ rc = snp_issue_guest_request(req);
switch (rc) {
case -ENOSPC:
/*
@@ -3167,7 +2020,7 @@ retry_request:
snp_inc_msg_seqno(mdesc);
if (override_err) {
- rio->exitinfo2 = override_err;
+ req->exitinfo2 = override_err;
/*
* If an extended guest request was issued and the supplied certificate
@@ -3185,12 +2038,20 @@ retry_request:
return rc;
}
-int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req,
- struct snp_guest_request_ioctl *rio)
+int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req)
{
u64 seqno;
int rc;
+ /*
+ * enc_payload() calls aesgcm_encrypt(), which can potentially offload to HW.
+ * The offload's DMA SG list of data to encrypt has to be in linear mapping.
+ */
+ if (!virt_addr_valid(req->req_buf) || !virt_addr_valid(req->resp_buf)) {
+ pr_warn("AES-GSM buffers must be in linear mapping");
+ return -EINVAL;
+ }
+
guard(mutex)(&snp_cmd_mutex);
/* Check if the VMPCK is not empty */
@@ -3223,14 +2084,14 @@ int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req
req->input.resp_gpa = __pa(mdesc->response);
req->input.data_gpa = req->certs_data ? __pa(req->certs_data) : 0;
- rc = __handle_guest_request(mdesc, req, rio);
+ rc = __handle_guest_request(mdesc, req);
if (rc) {
if (rc == -EIO &&
- rio->exitinfo2 == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN))
+ req->exitinfo2 == SNP_GUEST_VMM_ERR(SNP_GUEST_VMM_ERR_INVALID_LEN))
return rc;
pr_alert("Detected error from ASP request. rc: %d, exitinfo2: 0x%llx\n",
- rc, rio->exitinfo2);
+ rc, req->exitinfo2);
snp_disable_vmpck(mdesc);
return rc;
@@ -3249,11 +2110,10 @@ EXPORT_SYMBOL_GPL(snp_send_guest_request);
static int __init snp_get_tsc_info(void)
{
- struct snp_guest_request_ioctl *rio;
struct snp_tsc_info_resp *tsc_resp;
struct snp_tsc_info_req *tsc_req;
struct snp_msg_desc *mdesc;
- struct snp_guest_req *req;
+ struct snp_guest_req req = {};
int rc = -ENOMEM;
tsc_req = kzalloc(sizeof(*tsc_req), GFP_KERNEL);
@@ -3269,32 +2129,24 @@ static int __init snp_get_tsc_info(void)
if (!tsc_resp)
goto e_free_tsc_req;
- req = kzalloc(sizeof(*req), GFP_KERNEL);
- if (!req)
- goto e_free_tsc_resp;
-
- rio = kzalloc(sizeof(*rio), GFP_KERNEL);
- if (!rio)
- goto e_free_req;
-
mdesc = snp_msg_alloc();
if (IS_ERR_OR_NULL(mdesc))
- goto e_free_rio;
+ goto e_free_tsc_resp;
rc = snp_msg_init(mdesc, snp_vmpl);
if (rc)
goto e_free_mdesc;
- req->msg_version = MSG_HDR_VER;
- req->msg_type = SNP_MSG_TSC_INFO_REQ;
- req->vmpck_id = snp_vmpl;
- req->req_buf = tsc_req;
- req->req_sz = sizeof(*tsc_req);
- req->resp_buf = (void *)tsc_resp;
- req->resp_sz = sizeof(*tsc_resp) + AUTHTAG_LEN;
- req->exit_code = SVM_VMGEXIT_GUEST_REQUEST;
+ req.msg_version = MSG_HDR_VER;
+ req.msg_type = SNP_MSG_TSC_INFO_REQ;
+ req.vmpck_id = snp_vmpl;
+ req.req_buf = tsc_req;
+ req.req_sz = sizeof(*tsc_req);
+ req.resp_buf = (void *)tsc_resp;
+ req.resp_sz = sizeof(*tsc_resp) + AUTHTAG_LEN;
+ req.exit_code = SVM_VMGEXIT_GUEST_REQUEST;
- rc = snp_send_guest_request(mdesc, req, rio);
+ rc = snp_send_guest_request(mdesc, &req);
if (rc)
goto e_request;
@@ -3315,11 +2167,7 @@ e_request:
memzero_explicit(tsc_resp, sizeof(*tsc_resp) + AUTHTAG_LEN);
e_free_mdesc:
snp_msg_free(mdesc);
-e_free_rio:
- kfree(rio);
-e_free_req:
- kfree(req);
- e_free_tsc_resp:
+e_free_tsc_resp:
kfree(tsc_resp);
e_free_tsc_req:
kfree(tsc_req);
@@ -3347,15 +2195,31 @@ static unsigned long securetsc_get_tsc_khz(void)
void __init snp_secure_tsc_init(void)
{
- unsigned long long tsc_freq_mhz;
+ struct snp_secrets_page *secrets;
+ unsigned long tsc_freq_mhz;
+ void *mem;
if (!cc_platform_has(CC_ATTR_GUEST_SNP_SECURE_TSC))
return;
+ mem = early_memremap_encrypted(sev_secrets_pa, PAGE_SIZE);
+ if (!mem) {
+ pr_err("Unable to get TSC_FACTOR: failed to map the SNP secrets page.\n");
+ sev_es_terminate(SEV_TERM_SET_LINUX, GHCB_TERM_SECURE_TSC);
+ }
+
+ secrets = (__force struct snp_secrets_page *)mem;
+
setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
- rdmsrl(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz);
- snp_tsc_freq_khz = (unsigned long)(tsc_freq_mhz * 1000);
+ rdmsrq(MSR_AMD64_GUEST_TSC_FREQ, tsc_freq_mhz);
+
+ /* Extract the GUEST TSC MHZ from BIT[17:0], rest is reserved space */
+ tsc_freq_mhz &= GENMASK_ULL(17, 0);
+
+ snp_tsc_freq_khz = SNP_SCALE_TSC_FREQ(tsc_freq_mhz * 1000, secrets->tsc_factor);
x86_platform.calibrate_cpu = securetsc_get_tsc_khz;
x86_platform.calibrate_tsc = securetsc_get_tsc_khz;
+
+ early_memunmap(mem, PAGE_SIZE);
}
diff --git a/arch/x86/coco/sev/sev-nmi.c b/arch/x86/coco/sev/sev-nmi.c
new file mode 100644
index 000000000000..d8dfaddfb367
--- /dev/null
+++ b/arch/x86/coco/sev/sev-nmi.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2019 SUSE
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt) "SEV: " fmt
+
+#include <linux/bug.h>
+#include <linux/kernel.h>
+
+#include <asm/cpu_entry_area.h>
+#include <asm/msr.h>
+#include <asm/ptrace.h>
+#include <asm/sev.h>
+#include <asm/sev-internal.h>
+
+static __always_inline bool on_vc_stack(struct pt_regs *regs)
+{
+ unsigned long sp = regs->sp;
+
+ /* User-mode RSP is not trusted */
+ if (user_mode(regs))
+ return false;
+
+ /* SYSCALL gap still has user-mode RSP */
+ if (ip_within_syscall_gap(regs))
+ return false;
+
+ return ((sp >= __this_cpu_ist_bottom_va(VC)) && (sp < __this_cpu_ist_top_va(VC)));
+}
+
+/*
+ * This function handles the case when an NMI is raised in the #VC
+ * exception handler entry code, before the #VC handler has switched off
+ * its IST stack. In this case, the IST entry for #VC must be adjusted,
+ * so that any nested #VC exception will not overwrite the stack
+ * contents of the interrupted #VC handler.
+ *
+ * The IST entry is adjusted unconditionally so that it can be also be
+ * unconditionally adjusted back in __sev_es_ist_exit(). Otherwise a
+ * nested sev_es_ist_exit() call may adjust back the IST entry too
+ * early.
+ *
+ * The __sev_es_ist_enter() and __sev_es_ist_exit() functions always run
+ * on the NMI IST stack, as they are only called from NMI handling code
+ * right now.
+ */
+void noinstr __sev_es_ist_enter(struct pt_regs *regs)
+{
+ unsigned long old_ist, new_ist;
+
+ /* Read old IST entry */
+ new_ist = old_ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
+
+ /*
+ * If NMI happened while on the #VC IST stack, set the new IST
+ * value below regs->sp, so that the interrupted stack frame is
+ * not overwritten by subsequent #VC exceptions.
+ */
+ if (on_vc_stack(regs))
+ new_ist = regs->sp;
+
+ /*
+ * Reserve additional 8 bytes and store old IST value so this
+ * adjustment can be unrolled in __sev_es_ist_exit().
+ */
+ new_ist -= sizeof(old_ist);
+ *(unsigned long *)new_ist = old_ist;
+
+ /* Set new IST entry */
+ this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], new_ist);
+}
+
+void noinstr __sev_es_ist_exit(void)
+{
+ unsigned long ist;
+
+ /* Read IST entry */
+ ist = __this_cpu_read(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC]);
+
+ if (WARN_ON(ist == __this_cpu_ist_top_va(VC)))
+ return;
+
+ /* Read back old IST entry and write it to the TSS */
+ this_cpu_write(cpu_tss_rw.x86_tss.ist[IST_INDEX_VC], *(unsigned long *)ist);
+}
+
+void noinstr __sev_es_nmi_complete(void)
+{
+ struct ghcb_state state;
+ struct ghcb *ghcb;
+
+ ghcb = __sev_get_ghcb(&state);
+
+ vc_ghcb_invalidate(ghcb);
+ ghcb_set_sw_exit_code(ghcb, SVM_VMGEXIT_NMI_COMPLETE);
+ ghcb_set_sw_exit_info_1(ghcb, 0);
+ ghcb_set_sw_exit_info_2(ghcb, 0);
+
+ sev_es_wr_ghcb_msr(__pa_nodebug(ghcb));
+ VMGEXIT();
+
+ __sev_put_ghcb(&state);
+}
diff --git a/arch/x86/coco/sev/vc-handle.c b/arch/x86/coco/sev/vc-handle.c
new file mode 100644
index 000000000000..faf1fce89ed4
--- /dev/null
+++ b/arch/x86/coco/sev/vc-handle.c
@@ -0,0 +1,1068 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * AMD Memory Encryption Support
+ *
+ * Copyright (C) 2019 SUSE
+ *
+ * Author: Joerg Roedel <jroedel@suse.de>
+ */
+
+#define pr_fmt(fmt) "SEV: " fmt
+
+#include <linux/sched/debug.h> /* For show_regs() */
+#include <linux/cc_platform.h>
+#include <linux/printk.h>
+#include <linux/mm_types.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/io.h>
+#include <linux/psp-sev.h>
+#include <linux/efi.h>
+#include <uapi/linux/sev-guest.h>
+
+#include <asm/init.h>
+#include <asm/stacktrace.h>
+#include <asm/sev.h>
+#include <asm/sev-internal.h>
+#include <asm/insn-eval.h>
+#include <asm/fpu/xcr.h>
+#include <asm/processor.h>
+#include <asm/setup.h>
+#include <asm/traps.h>
+#include <asm/svm.h>
+#include <asm/smp.h>
+#include <asm/cpu.h>
+#include <asm/apic.h>
+#include <asm/cpuid/api.h>
+
+static enum es_result vc_slow_virt_to_phys(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+ unsigned long vaddr, phys_addr_t *paddr)
+{
+ unsigned long va = (unsigned long)vaddr;
+ unsigned int level;
+ phys_addr_t pa;
+ pgd_t *pgd;
+ pte_t *pte;
+
+ pgd = __va(read_cr3_pa());
+ pgd = &pgd[pgd_index(va)];
+ pte = lookup_address_in_pgd(pgd, va, &level);
+ if (!pte) {
+ ctxt->fi.vector = X86_TRAP_PF;
+ ctxt->fi.cr2 = vaddr;
+ ctxt->fi.error_code = 0;
+
+ if (user_mode(ctxt->regs))
+ ctxt->fi.error_code |= X86_PF_USER;
+
+ return ES_EXCEPTION;
+ }
+
+ if (WARN_ON_ONCE(pte_val(*pte) & _PAGE_ENC))
+ /* Emulated MMIO to/from encrypted memory not supported */
+ return ES_UNSUPPORTED;
+
+ pa = (phys_addr_t)pte_pfn(*pte) << PAGE_SHIFT;
+ pa |= va & ~page_level_mask(level);
+
+ *paddr = pa;
+
+ return ES_OK;
+}
+
+static enum es_result vc_ioio_check(struct es_em_ctxt *ctxt, u16 port, size_t size)
+{
+ BUG_ON(size > 4);
+
+ if (user_mode(ctxt->regs)) {
+ struct thread_struct *t = &current->thread;
+ struct io_bitmap *iobm = t->io_bitmap;
+ size_t idx;
+
+ if (!iobm)
+ goto fault;
+
+ for (idx = port; idx < port + size; ++idx) {
+ if (test_bit(idx, iobm->bitmap))
+ goto fault;
+ }
+ }
+
+ return ES_OK;
+
+fault:
+ ctxt->fi.vector = X86_TRAP_GP;
+ ctxt->fi.error_code = 0;
+
+ return ES_EXCEPTION;
+}
+
+void vc_forward_exception(struct es_em_ctxt *ctxt)
+{
+ long error_code = ctxt->fi.error_code;
+ int trapnr = ctxt->fi.vector;
+
+ ctxt->regs->orig_ax = ctxt->fi.error_code;
+
+ switch (trapnr) {
+ case X86_TRAP_GP:
+ exc_general_protection(ctxt->regs, error_code);
+ break;
+ case X86_TRAP_UD:
+ exc_invalid_op(ctxt->regs);
+ break;
+ case X86_TRAP_PF:
+ write_cr2(ctxt->fi.cr2);
+ exc_page_fault(ctxt->regs, error_code);
+ break;
+ case X86_TRAP_AC:
+ exc_alignment_check(ctxt->regs, error_code);
+ break;
+ default:
+ pr_emerg("Unsupported exception in #VC instruction emulation - can't continue\n");
+ BUG();
+ }
+}
+
+static int vc_fetch_insn_kernel(struct es_em_ctxt *ctxt,
+ unsigned char *buffer)
+{
+ return copy_from_kernel_nofault(buffer, (unsigned char *)ctxt->regs->ip, MAX_INSN_SIZE);
+}
+
+static enum es_result __vc_decode_user_insn(struct es_em_ctxt *ctxt)
+{
+ char buffer[MAX_INSN_SIZE];
+ int insn_bytes;
+
+ insn_bytes = insn_fetch_from_user_inatomic(ctxt->regs, buffer);
+ if (insn_bytes == 0) {
+ /* Nothing could be copied */
+ ctxt->fi.vector = X86_TRAP_PF;
+ ctxt->fi.error_code = X86_PF_INSTR | X86_PF_USER;
+ ctxt->fi.cr2 = ctxt->regs->ip;
+ return ES_EXCEPTION;
+ } else if (insn_bytes == -EINVAL) {
+ /* Effective RIP could not be calculated */
+ ctxt->fi.vector = X86_TRAP_GP;
+ ctxt->fi.error_code = 0;
+ ctxt->fi.cr2 = 0;
+ return ES_EXCEPTION;
+ }
+
+ if (!insn_decode_from_regs(&ctxt->insn, ctxt->regs, buffer, insn_bytes))
+ return ES_DECODE_FAILED;
+
+ if (ctxt->insn.immediate.got)
+ return ES_OK;
+ else
+ return ES_DECODE_FAILED;
+}
+
+static enum es_result __vc_decode_kern_insn(struct es_em_ctxt *ctxt)
+{
+ char buffer[MAX_INSN_SIZE];
+ int res, ret;
+
+ res = vc_fetch_insn_kernel(ctxt, buffer);
+ if (res) {
+ ctxt->fi.vector = X86_TRAP_PF;
+ ctxt->fi.error_code = X86_PF_INSTR;
+ ctxt->fi.cr2 = ctxt->regs->ip;
+ return ES_EXCEPTION;
+ }
+
+ ret = insn_decode(&ctxt->insn, buffer, MAX_INSN_SIZE, INSN_MODE_64);
+ if (ret < 0)
+ return ES_DECODE_FAILED;
+ else
+ return ES_OK;
+}
+
+/*
+ * User instruction decoding is also required for the EFI runtime. Even though
+ * the EFI runtime is running in kernel mode, it uses special EFI virtual
+ * address mappings that require the use of efi_mm to properly address and
+ * decode.
+ */
+static enum es_result vc_decode_insn(struct es_em_ctxt *ctxt)
+{
+ if (user_mode(ctxt->regs) || mm_is_efi(current->active_mm))
+ return __vc_decode_user_insn(ctxt);
+ else
+ return __vc_decode_kern_insn(ctxt);
+}
+
+static enum es_result vc_write_mem(struct es_em_ctxt *ctxt,
+ char *dst, char *buf, size_t size)
+{
+ unsigned long error_code = X86_PF_PROT | X86_PF_WRITE;
+
+ /*
+ * This function uses __put_user() independent of whether kernel or user
+ * memory is accessed. This works fine because __put_user() does no
+ * sanity checks of the pointer being accessed. All that it does is
+ * to report when the access failed.
+ *
+ * Also, this function runs in atomic context, so __put_user() is not
+ * allowed to sleep. The page-fault handler detects that it is running
+ * in atomic context and will not try to take mmap_sem and handle the
+ * fault, so additional pagefault_enable()/disable() calls are not
+ * needed.
+ *
+ * The access can't be done via copy_to_user() here because
+ * vc_write_mem() must not use string instructions to access unsafe
+ * memory. The reason is that MOVS is emulated by the #VC handler by
+ * splitting the move up into a read and a write and taking a nested #VC
+ * exception on whatever of them is the MMIO access. Using string
+ * instructions here would cause infinite nesting.
+ */
+ switch (size) {
+ case 1: {
+ u8 d1;
+ u8 __user *target = (u8 __user *)dst;
+
+ memcpy(&d1, buf, 1);
+ if (__put_user(d1, target))
+ goto fault;
+ break;
+ }
+ case 2: {
+ u16 d2;
+ u16 __user *target = (u16 __user *)dst;
+
+ memcpy(&d2, buf, 2);
+ if (__put_user(d2, target))
+ goto fault;
+ break;
+ }
+ case 4: {
+ u32 d4;
+ u32 __user *target = (u32 __user *)dst;
+
+ memcpy(&d4, buf, 4);
+ if (__put_user(d4, target))
+ goto fault;
+ break;
+ }
+ case 8: {
+ u64 d8;
+ u64 __user *target = (u64 __user *)dst;
+
+ memcpy(&d8, buf, 8);
+ if (__put_user(d8, target))
+ goto fault;
+ break;
+ }
+ default:
+ WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
+ return ES_UNSUPPORTED;
+ }
+
+ return ES_OK;
+
+fault:
+ if (user_mode(ctxt->regs))
+ error_code |= X86_PF_USER;
+
+ ctxt->fi.vector = X86_TRAP_PF;
+ ctxt->fi.error_code = error_code;
+ ctxt->fi.cr2 = (unsigned long)dst;
+
+ return ES_EXCEPTION;
+}
+
+static enum es_result vc_read_mem(struct es_em_ctxt *ctxt,
+ char *src, char *buf, size_t size)
+{
+ unsigned long error_code = X86_PF_PROT;
+
+ /*
+ * This function uses __get_user() independent of whether kernel or user
+ * memory is accessed. This works fine because __get_user() does no
+ * sanity checks of the pointer being accessed. All that it does is
+ * to report when the access failed.
+ *
+ * Also, this function runs in atomic context, so __get_user() is not
+ * allowed to sleep. The page-fault handler detects that it is running
+ * in atomic context and will not try to take mmap_sem and handle the
+ * fault, so additional pagefault_enable()/disable() calls are not
+ * needed.
+ *
+ * The access can't be done via copy_from_user() here because
+ * vc_read_mem() must not use string instructions to access unsafe
+ * memory. The reason is that MOVS is emulated by the #VC handler by
+ * splitting the move up into a read and a write and taking a nested #VC
+ * exception on whatever of them is the MMIO access. Using string
+ * instructions here would cause infinite nesting.
+ */
+ switch (size) {
+ case 1: {
+ u8 d1;
+ u8 __user *s = (u8 __user *)src;
+
+ if (__get_user(d1, s))
+ goto fault;
+ memcpy(buf, &d1, 1);
+ break;
+ }
+ case 2: {
+ u16 d2;
+ u16 __user *s = (u16 __user *)src;
+
+ if (__get_user(d2, s))
+ goto fault;
+ memcpy(buf, &d2, 2);
+ break;
+ }
+ case 4: {
+ u32 d4;
+ u32 __user *s = (u32 __user *)src;
+
+ if (__get_user(d4, s))
+ goto fault;
+ memcpy(buf, &d4, 4);
+ break;
+ }
+ case 8: {
+ u64 d8;
+ u64 __user *s = (u64 __user *)src;
+ if (__get_user(d8, s))
+ goto fault;
+ memcpy(buf, &d8, 8);
+ break;
+ }
+ default:
+ WARN_ONCE(1, "%s: Invalid size: %zu\n", __func__, size);
+ return ES_UNSUPPORTED;
+ }
+
+ return ES_OK;
+
+fault:
+ if (user_mode(ctxt->regs))
+ error_code |= X86_PF_USER;
+
+ ctxt->fi.vector = X86_TRAP_PF;
+ ctxt->fi.error_code = error_code;
+ ctxt->fi.cr2 = (unsigned long)src;
+
+ return ES_EXCEPTION;
+}
+
+#define sev_printk(fmt, ...) printk(fmt, ##__VA_ARGS__)
+
+#include "vc-shared.c"
+
+/* Writes to the SVSM CAA MSR are ignored */
+static enum es_result __vc_handle_msr_caa(struct pt_regs *regs, bool write)
+{
+ if (write)
+ return ES_OK;
+
+ regs->ax = lower_32_bits(this_cpu_read(svsm_caa_pa));
+ regs->dx = upper_32_bits(this_cpu_read(svsm_caa_pa));
+
+ return ES_OK;
+}
+
+/*
+ * TSC related accesses should not exit to the hypervisor when a guest is
+ * executing with Secure TSC enabled, so special handling is required for
+ * accesses of MSR_IA32_TSC and MSR_AMD64_GUEST_TSC_FREQ.
+ */
+static enum es_result __vc_handle_secure_tsc_msrs(struct pt_regs *regs, bool write)
+{
+ u64 tsc;
+
+ /*
+ * GUEST_TSC_FREQ should not be intercepted when Secure TSC is enabled.
+ * Terminate the SNP guest when the interception is enabled.
+ */
+ if (regs->cx == MSR_AMD64_GUEST_TSC_FREQ)
+ return ES_VMM_ERROR;
+
+ /*
+ * Writes: Writing to MSR_IA32_TSC can cause subsequent reads of the TSC
+ * to return undefined values, so ignore all writes.
+ *
+ * Reads: Reads of MSR_IA32_TSC should return the current TSC value, use
+ * the value returned by rdtsc_ordered().
+ */
+ if (write) {
+ WARN_ONCE(1, "TSC MSR writes are verboten!\n");
+ return ES_OK;
+ }
+
+ tsc = rdtsc_ordered();
+ regs->ax = lower_32_bits(tsc);
+ regs->dx = upper_32_bits(tsc);
+
+ return ES_OK;
+}
+
+static enum es_result vc_handle_msr(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+ struct pt_regs *regs = ctxt->regs;
+ enum es_result ret;
+ bool write;
+
+ /* Is it a WRMSR? */
+ write = ctxt->insn.opcode.bytes[1] == 0x30;
+
+ switch (regs->cx) {
+ case MSR_SVSM_CAA:
+ return __vc_handle_msr_caa(regs, write);
+ case MSR_IA32_TSC:
+ case MSR_AMD64_GUEST_TSC_FREQ:
+ if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
+ return __vc_handle_secure_tsc_msrs(regs, write);
+ break;
+ default:
+ break;
+ }
+
+ ghcb_set_rcx(ghcb, regs->cx);
+ if (write) {
+ ghcb_set_rax(ghcb, regs->ax);
+ ghcb_set_rdx(ghcb, regs->dx);
+ }
+
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_MSR, write, 0);
+
+ if ((ret == ES_OK) && !write) {
+ regs->ax = ghcb->save.rax;
+ regs->dx = ghcb->save.rdx;
+ }
+
+ return ret;
+}
+
+static void __init vc_early_forward_exception(struct es_em_ctxt *ctxt)
+{
+ int trapnr = ctxt->fi.vector;
+
+ if (trapnr == X86_TRAP_PF)
+ native_write_cr2(ctxt->fi.cr2);
+
+ ctxt->regs->orig_ax = ctxt->fi.error_code;
+ do_early_exception(ctxt->regs, trapnr);
+}
+
+static long *vc_insn_get_rm(struct es_em_ctxt *ctxt)
+{
+ long *reg_array;
+ int offset;
+
+ reg_array = (long *)ctxt->regs;
+ offset = insn_get_modrm_rm_off(&ctxt->insn, ctxt->regs);
+
+ if (offset < 0)
+ return NULL;
+
+ offset /= sizeof(long);
+
+ return reg_array + offset;
+}
+static enum es_result vc_do_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt,
+ unsigned int bytes, bool read)
+{
+ u64 exit_code, exit_info_1, exit_info_2;
+ unsigned long ghcb_pa = __pa(ghcb);
+ enum es_result res;
+ phys_addr_t paddr;
+ void __user *ref;
+
+ ref = insn_get_addr_ref(&ctxt->insn, ctxt->regs);
+ if (ref == (void __user *)-1L)
+ return ES_UNSUPPORTED;
+
+ exit_code = read ? SVM_VMGEXIT_MMIO_READ : SVM_VMGEXIT_MMIO_WRITE;
+
+ res = vc_slow_virt_to_phys(ghcb, ctxt, (unsigned long)ref, &paddr);
+ if (res != ES_OK) {
+ if (res == ES_EXCEPTION && !read)
+ ctxt->fi.error_code |= X86_PF_WRITE;
+
+ return res;
+ }
+
+ exit_info_1 = paddr;
+ /* Can never be greater than 8 */
+ exit_info_2 = bytes;
+
+ ghcb_set_sw_scratch(ghcb, ghcb_pa + offsetof(struct ghcb, shared_buffer));
+
+ return sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, exit_info_1, exit_info_2);
+}
+
+/*
+ * The MOVS instruction has two memory operands, which raises the
+ * problem that it is not known whether the access to the source or the
+ * destination caused the #VC exception (and hence whether an MMIO read
+ * or write operation needs to be emulated).
+ *
+ * Instead of playing games with walking page-tables and trying to guess
+ * whether the source or destination is an MMIO range, split the move
+ * into two operations, a read and a write with only one memory operand.
+ * This will cause a nested #VC exception on the MMIO address which can
+ * then be handled.
+ *
+ * This implementation has the benefit that it also supports MOVS where
+ * source _and_ destination are MMIO regions.
+ *
+ * It will slow MOVS on MMIO down a lot, but in SEV-ES guests it is a
+ * rare operation. If it turns out to be a performance problem the split
+ * operations can be moved to memcpy_fromio() and memcpy_toio().
+ */
+static enum es_result vc_handle_mmio_movs(struct es_em_ctxt *ctxt,
+ unsigned int bytes)
+{
+ unsigned long ds_base, es_base;
+ unsigned char *src, *dst;
+ unsigned char buffer[8];
+ enum es_result ret;
+ bool rep;
+ int off;
+
+ ds_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_DS);
+ es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
+
+ if (ds_base == -1L || es_base == -1L) {
+ ctxt->fi.vector = X86_TRAP_GP;
+ ctxt->fi.error_code = 0;
+ return ES_EXCEPTION;
+ }
+
+ src = ds_base + (unsigned char *)ctxt->regs->si;
+ dst = es_base + (unsigned char *)ctxt->regs->di;
+
+ ret = vc_read_mem(ctxt, src, buffer, bytes);
+ if (ret != ES_OK)
+ return ret;
+
+ ret = vc_write_mem(ctxt, dst, buffer, bytes);
+ if (ret != ES_OK)
+ return ret;
+
+ if (ctxt->regs->flags & X86_EFLAGS_DF)
+ off = -bytes;
+ else
+ off = bytes;
+
+ ctxt->regs->si += off;
+ ctxt->regs->di += off;
+
+ rep = insn_has_rep_prefix(&ctxt->insn);
+ if (rep)
+ ctxt->regs->cx -= 1;
+
+ if (!rep || ctxt->regs->cx == 0)
+ return ES_OK;
+ else
+ return ES_RETRY;
+}
+
+static enum es_result vc_handle_mmio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+ struct insn *insn = &ctxt->insn;
+ enum insn_mmio_type mmio;
+ unsigned int bytes = 0;
+ enum es_result ret;
+ u8 sign_byte;
+ long *reg_data;
+
+ mmio = insn_decode_mmio(insn, &bytes);
+ if (mmio == INSN_MMIO_DECODE_FAILED)
+ return ES_DECODE_FAILED;
+
+ if (mmio != INSN_MMIO_WRITE_IMM && mmio != INSN_MMIO_MOVS) {
+ reg_data = insn_get_modrm_reg_ptr(insn, ctxt->regs);
+ if (!reg_data)
+ return ES_DECODE_FAILED;
+ }
+
+ if (user_mode(ctxt->regs))
+ return ES_UNSUPPORTED;
+
+ switch (mmio) {
+ case INSN_MMIO_WRITE:
+ memcpy(ghcb->shared_buffer, reg_data, bytes);
+ ret = vc_do_mmio(ghcb, ctxt, bytes, false);
+ break;
+ case INSN_MMIO_WRITE_IMM:
+ memcpy(ghcb->shared_buffer, insn->immediate1.bytes, bytes);
+ ret = vc_do_mmio(ghcb, ctxt, bytes, false);
+ break;
+ case INSN_MMIO_READ:
+ ret = vc_do_mmio(ghcb, ctxt, bytes, true);
+ if (ret)
+ break;
+
+ /* Zero-extend for 32-bit operation */
+ if (bytes == 4)
+ *reg_data = 0;
+
+ memcpy(reg_data, ghcb->shared_buffer, bytes);
+ break;
+ case INSN_MMIO_READ_ZERO_EXTEND:
+ ret = vc_do_mmio(ghcb, ctxt, bytes, true);
+ if (ret)
+ break;
+
+ /* Zero extend based on operand size */
+ memset(reg_data, 0, insn->opnd_bytes);
+ memcpy(reg_data, ghcb->shared_buffer, bytes);
+ break;
+ case INSN_MMIO_READ_SIGN_EXTEND:
+ ret = vc_do_mmio(ghcb, ctxt, bytes, true);
+ if (ret)
+ break;
+
+ if (bytes == 1) {
+ u8 *val = (u8 *)ghcb->shared_buffer;
+
+ sign_byte = (*val & 0x80) ? 0xff : 0x00;
+ } else {
+ u16 *val = (u16 *)ghcb->shared_buffer;
+
+ sign_byte = (*val & 0x8000) ? 0xff : 0x00;
+ }
+
+ /* Sign extend based on operand size */
+ memset(reg_data, sign_byte, insn->opnd_bytes);
+ memcpy(reg_data, ghcb->shared_buffer, bytes);
+ break;
+ case INSN_MMIO_MOVS:
+ ret = vc_handle_mmio_movs(ctxt, bytes);
+ break;
+ default:
+ ret = ES_UNSUPPORTED;
+ break;
+ }
+
+ return ret;
+}
+
+static enum es_result vc_handle_dr7_write(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt)
+{
+ struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
+ long val, *reg = vc_insn_get_rm(ctxt);
+ enum es_result ret;
+
+ if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
+ return ES_VMM_ERROR;
+
+ if (!reg)
+ return ES_DECODE_FAILED;
+
+ val = *reg;
+
+ /* Upper 32 bits must be written as zeroes */
+ if (val >> 32) {
+ ctxt->fi.vector = X86_TRAP_GP;
+ ctxt->fi.error_code = 0;
+ return ES_EXCEPTION;
+ }
+
+ /* Clear out other reserved bits and set bit 10 */
+ val = (val & 0xffff23ffL) | BIT(10);
+
+ /* Early non-zero writes to DR7 are not supported */
+ if (!data && (val & ~DR7_RESET_VALUE))
+ return ES_UNSUPPORTED;
+
+ /* Using a value of 0 for ExitInfo1 means RAX holds the value */
+ ghcb_set_rax(ghcb, val);
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WRITE_DR7, 0, 0);
+ if (ret != ES_OK)
+ return ret;
+
+ if (data)
+ data->dr7 = val;
+
+ return ES_OK;
+}
+
+static enum es_result vc_handle_dr7_read(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt)
+{
+ struct sev_es_runtime_data *data = this_cpu_read(runtime_data);
+ long *reg = vc_insn_get_rm(ctxt);
+
+ if (sev_status & MSR_AMD64_SNP_DEBUG_SWAP)
+ return ES_VMM_ERROR;
+
+ if (!reg)
+ return ES_DECODE_FAILED;
+
+ if (data)
+ *reg = data->dr7;
+ else
+ *reg = DR7_RESET_VALUE;
+
+ return ES_OK;
+}
+
+static enum es_result vc_handle_wbinvd(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt)
+{
+ return sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_WBINVD, 0, 0);
+}
+
+static enum es_result vc_handle_rdpmc(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+ enum es_result ret;
+
+ ghcb_set_rcx(ghcb, ctxt->regs->cx);
+
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_RDPMC, 0, 0);
+ if (ret != ES_OK)
+ return ret;
+
+ if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb)))
+ return ES_VMM_ERROR;
+
+ ctxt->regs->ax = ghcb->save.rax;
+ ctxt->regs->dx = ghcb->save.rdx;
+
+ return ES_OK;
+}
+
+static enum es_result vc_handle_monitor(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt)
+{
+ /*
+ * Treat it as a NOP and do not leak a physical address to the
+ * hypervisor.
+ */
+ return ES_OK;
+}
+
+static enum es_result vc_handle_mwait(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt)
+{
+ /* Treat the same as MONITOR/MONITORX */
+ return ES_OK;
+}
+
+static enum es_result vc_handle_vmmcall(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt)
+{
+ enum es_result ret;
+
+ ghcb_set_rax(ghcb, ctxt->regs->ax);
+ ghcb_set_cpl(ghcb, user_mode(ctxt->regs) ? 3 : 0);
+
+ if (x86_platform.hyper.sev_es_hcall_prepare)
+ x86_platform.hyper.sev_es_hcall_prepare(ghcb, ctxt->regs);
+
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_VMMCALL, 0, 0);
+ if (ret != ES_OK)
+ return ret;
+
+ if (!ghcb_rax_is_valid(ghcb))
+ return ES_VMM_ERROR;
+
+ ctxt->regs->ax = ghcb->save.rax;
+
+ /*
+ * Call sev_es_hcall_finish() after regs->ax is already set.
+ * This allows the hypervisor handler to overwrite it again if
+ * necessary.
+ */
+ if (x86_platform.hyper.sev_es_hcall_finish &&
+ !x86_platform.hyper.sev_es_hcall_finish(ghcb, ctxt->regs))
+ return ES_VMM_ERROR;
+
+ return ES_OK;
+}
+
+static enum es_result vc_handle_trap_ac(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt)
+{
+ /*
+ * Calling ecx_alignment_check() directly does not work, because it
+ * enables IRQs and the GHCB is active. Forward the exception and call
+ * it later from vc_forward_exception().
+ */
+ ctxt->fi.vector = X86_TRAP_AC;
+ ctxt->fi.error_code = 0;
+ return ES_EXCEPTION;
+}
+
+static enum es_result vc_handle_exitcode(struct es_em_ctxt *ctxt,
+ struct ghcb *ghcb,
+ unsigned long exit_code)
+{
+ enum es_result result = vc_check_opcode_bytes(ctxt, exit_code);
+
+ if (result != ES_OK)
+ return result;
+
+ switch (exit_code) {
+ case SVM_EXIT_READ_DR7:
+ result = vc_handle_dr7_read(ghcb, ctxt);
+ break;
+ case SVM_EXIT_WRITE_DR7:
+ result = vc_handle_dr7_write(ghcb, ctxt);
+ break;
+ case SVM_EXIT_EXCP_BASE + X86_TRAP_AC:
+ result = vc_handle_trap_ac(ghcb, ctxt);
+ break;
+ case SVM_EXIT_RDTSC:
+ case SVM_EXIT_RDTSCP:
+ result = vc_handle_rdtsc(ghcb, ctxt, exit_code);
+ break;
+ case SVM_EXIT_RDPMC:
+ result = vc_handle_rdpmc(ghcb, ctxt);
+ break;
+ case SVM_EXIT_INVD:
+ pr_err_ratelimited("#VC exception for INVD??? Seriously???\n");
+ result = ES_UNSUPPORTED;
+ break;
+ case SVM_EXIT_CPUID:
+ result = vc_handle_cpuid(ghcb, ctxt);
+ break;
+ case SVM_EXIT_IOIO:
+ result = vc_handle_ioio(ghcb, ctxt);
+ break;
+ case SVM_EXIT_MSR:
+ result = vc_handle_msr(ghcb, ctxt);
+ break;
+ case SVM_EXIT_VMMCALL:
+ result = vc_handle_vmmcall(ghcb, ctxt);
+ break;
+ case SVM_EXIT_WBINVD:
+ result = vc_handle_wbinvd(ghcb, ctxt);
+ break;
+ case SVM_EXIT_MONITOR:
+ result = vc_handle_monitor(ghcb, ctxt);
+ break;
+ case SVM_EXIT_MWAIT:
+ result = vc_handle_mwait(ghcb, ctxt);
+ break;
+ case SVM_EXIT_NPF:
+ result = vc_handle_mmio(ghcb, ctxt);
+ break;
+ default:
+ /*
+ * Unexpected #VC exception
+ */
+ result = ES_UNSUPPORTED;
+ }
+
+ return result;
+}
+
+static __always_inline bool is_vc2_stack(unsigned long sp)
+{
+ return (sp >= __this_cpu_ist_bottom_va(VC2) && sp < __this_cpu_ist_top_va(VC2));
+}
+
+static __always_inline bool vc_from_invalid_context(struct pt_regs *regs)
+{
+ unsigned long sp, prev_sp;
+
+ sp = (unsigned long)regs;
+ prev_sp = regs->sp;
+
+ /*
+ * If the code was already executing on the VC2 stack when the #VC
+ * happened, let it proceed to the normal handling routine. This way the
+ * code executing on the VC2 stack can cause #VC exceptions to get handled.
+ */
+ return is_vc2_stack(sp) && !is_vc2_stack(prev_sp);
+}
+
+static bool vc_raw_handle_exception(struct pt_regs *regs, unsigned long error_code)
+{
+ struct ghcb_state state;
+ struct es_em_ctxt ctxt;
+ enum es_result result;
+ struct ghcb *ghcb;
+ bool ret = true;
+
+ ghcb = __sev_get_ghcb(&state);
+
+ vc_ghcb_invalidate(ghcb);
+ result = vc_init_em_ctxt(&ctxt, regs, error_code);
+
+ if (result == ES_OK)
+ result = vc_handle_exitcode(&ctxt, ghcb, error_code);
+
+ __sev_put_ghcb(&state);
+
+ /* Done - now check the result */
+ switch (result) {
+ case ES_OK:
+ vc_finish_insn(&ctxt);
+ break;
+ case ES_UNSUPPORTED:
+ pr_err_ratelimited("Unsupported exit-code 0x%02lx in #VC exception (IP: 0x%lx)\n",
+ error_code, regs->ip);
+ ret = false;
+ break;
+ case ES_VMM_ERROR:
+ pr_err_ratelimited("Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
+ error_code, regs->ip);
+ ret = false;
+ break;
+ case ES_DECODE_FAILED:
+ pr_err_ratelimited("Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
+ error_code, regs->ip);
+ ret = false;
+ break;
+ case ES_EXCEPTION:
+ vc_forward_exception(&ctxt);
+ break;
+ case ES_RETRY:
+ /* Nothing to do */
+ break;
+ default:
+ pr_emerg("Unknown result in %s():%d\n", __func__, result);
+ /*
+ * Emulating the instruction which caused the #VC exception
+ * failed - can't continue so print debug information
+ */
+ BUG();
+ }
+
+ return ret;
+}
+
+static __always_inline bool vc_is_db(unsigned long error_code)
+{
+ return error_code == SVM_EXIT_EXCP_BASE + X86_TRAP_DB;
+}
+
+/*
+ * Runtime #VC exception handler when raised from kernel mode. Runs in NMI mode
+ * and will panic when an error happens.
+ */
+DEFINE_IDTENTRY_VC_KERNEL(exc_vmm_communication)
+{
+ irqentry_state_t irq_state;
+
+ /*
+ * With the current implementation it is always possible to switch to a
+ * safe stack because #VC exceptions only happen at known places, like
+ * intercepted instructions or accesses to MMIO areas/IO ports. They can
+ * also happen with code instrumentation when the hypervisor intercepts
+ * #DB, but the critical paths are forbidden to be instrumented, so #DB
+ * exceptions currently also only happen in safe places.
+ *
+ * But keep this here in case the noinstr annotations are violated due
+ * to bug elsewhere.
+ */
+ if (unlikely(vc_from_invalid_context(regs))) {
+ instrumentation_begin();
+ panic("Can't handle #VC exception from unsupported context\n");
+ instrumentation_end();
+ }
+
+ /*
+ * Handle #DB before calling into !noinstr code to avoid recursive #DB.
+ */
+ if (vc_is_db(error_code)) {
+ exc_debug(regs);
+ return;
+ }
+
+ irq_state = irqentry_nmi_enter(regs);
+
+ instrumentation_begin();
+
+ if (!vc_raw_handle_exception(regs, error_code)) {
+ /* Show some debug info */
+ show_regs(regs);
+
+ /* Ask hypervisor to sev_es_terminate */
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+
+ /* If that fails and we get here - just panic */
+ panic("Returned from Terminate-Request to Hypervisor\n");
+ }
+
+ instrumentation_end();
+ irqentry_nmi_exit(regs, irq_state);
+}
+
+/*
+ * Runtime #VC exception handler when raised from user mode. Runs in IRQ mode
+ * and will kill the current task with SIGBUS when an error happens.
+ */
+DEFINE_IDTENTRY_VC_USER(exc_vmm_communication)
+{
+ /*
+ * Handle #DB before calling into !noinstr code to avoid recursive #DB.
+ */
+ if (vc_is_db(error_code)) {
+ noist_exc_debug(regs);
+ return;
+ }
+
+ irqentry_enter_from_user_mode(regs);
+ instrumentation_begin();
+
+ if (!vc_raw_handle_exception(regs, error_code)) {
+ /*
+ * Do not kill the machine if user-space triggered the
+ * exception. Send SIGBUS instead and let user-space deal with
+ * it.
+ */
+ force_sig_fault(SIGBUS, BUS_OBJERR, (void __user *)0);
+ }
+
+ instrumentation_end();
+ irqentry_exit_to_user_mode(regs);
+}
+
+bool __init handle_vc_boot_ghcb(struct pt_regs *regs)
+{
+ unsigned long exit_code = regs->orig_ax;
+ struct es_em_ctxt ctxt;
+ enum es_result result;
+
+ vc_ghcb_invalidate(boot_ghcb);
+
+ result = vc_init_em_ctxt(&ctxt, regs, exit_code);
+ if (result == ES_OK)
+ result = vc_handle_exitcode(&ctxt, boot_ghcb, exit_code);
+
+ /* Done - now check the result */
+ switch (result) {
+ case ES_OK:
+ vc_finish_insn(&ctxt);
+ break;
+ case ES_UNSUPPORTED:
+ early_printk("PANIC: Unsupported exit-code 0x%02lx in early #VC exception (IP: 0x%lx)\n",
+ exit_code, regs->ip);
+ goto fail;
+ case ES_VMM_ERROR:
+ early_printk("PANIC: Failure in communication with VMM (exit-code 0x%02lx IP: 0x%lx)\n",
+ exit_code, regs->ip);
+ goto fail;
+ case ES_DECODE_FAILED:
+ early_printk("PANIC: Failed to decode instruction (exit-code 0x%02lx IP: 0x%lx)\n",
+ exit_code, regs->ip);
+ goto fail;
+ case ES_EXCEPTION:
+ vc_early_forward_exception(&ctxt);
+ break;
+ case ES_RETRY:
+ /* Nothing to do */
+ break;
+ default:
+ BUG();
+ }
+
+ return true;
+
+fail:
+ show_regs(regs);
+
+ sev_es_terminate(SEV_TERM_SET_GEN, GHCB_SEV_ES_GEN_REQ);
+}
+
diff --git a/arch/x86/coco/sev/vc-shared.c b/arch/x86/coco/sev/vc-shared.c
new file mode 100644
index 000000000000..2c0ab0fdc060
--- /dev/null
+++ b/arch/x86/coco/sev/vc-shared.c
@@ -0,0 +1,504 @@
+// SPDX-License-Identifier: GPL-2.0
+
+static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt,
+ unsigned long exit_code)
+{
+ unsigned int opcode = (unsigned int)ctxt->insn.opcode.value;
+ u8 modrm = ctxt->insn.modrm.value;
+
+ switch (exit_code) {
+
+ case SVM_EXIT_IOIO:
+ case SVM_EXIT_NPF:
+ /* handled separately */
+ return ES_OK;
+
+ case SVM_EXIT_CPUID:
+ if (opcode == 0xa20f)
+ return ES_OK;
+ break;
+
+ case SVM_EXIT_INVD:
+ if (opcode == 0x080f)
+ return ES_OK;
+ break;
+
+ case SVM_EXIT_MONITOR:
+ /* MONITOR and MONITORX instructions generate the same error code */
+ if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa))
+ return ES_OK;
+ break;
+
+ case SVM_EXIT_MWAIT:
+ /* MWAIT and MWAITX instructions generate the same error code */
+ if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb))
+ return ES_OK;
+ break;
+
+ case SVM_EXIT_MSR:
+ /* RDMSR */
+ if (opcode == 0x320f ||
+ /* WRMSR */
+ opcode == 0x300f)
+ return ES_OK;
+ break;
+
+ case SVM_EXIT_RDPMC:
+ if (opcode == 0x330f)
+ return ES_OK;
+ break;
+
+ case SVM_EXIT_RDTSC:
+ if (opcode == 0x310f)
+ return ES_OK;
+ break;
+
+ case SVM_EXIT_RDTSCP:
+ if (opcode == 0x010f && modrm == 0xf9)
+ return ES_OK;
+ break;
+
+ case SVM_EXIT_READ_DR7:
+ if (opcode == 0x210f &&
+ X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
+ return ES_OK;
+ break;
+
+ case SVM_EXIT_VMMCALL:
+ if (opcode == 0x010f && modrm == 0xd9)
+ return ES_OK;
+
+ break;
+
+ case SVM_EXIT_WRITE_DR7:
+ if (opcode == 0x230f &&
+ X86_MODRM_REG(ctxt->insn.modrm.value) == 7)
+ return ES_OK;
+ break;
+
+ case SVM_EXIT_WBINVD:
+ if (opcode == 0x90f)
+ return ES_OK;
+ break;
+
+ default:
+ break;
+ }
+
+ sev_printk(KERN_ERR "Wrong/unhandled opcode bytes: 0x%x, exit_code: 0x%lx, rIP: 0x%lx\n",
+ opcode, exit_code, ctxt->regs->ip);
+
+ return ES_UNSUPPORTED;
+}
+
+static bool vc_decoding_needed(unsigned long exit_code)
+{
+ /* Exceptions don't require to decode the instruction */
+ return !(exit_code >= SVM_EXIT_EXCP_BASE &&
+ exit_code <= SVM_EXIT_LAST_EXCP);
+}
+
+static enum es_result vc_init_em_ctxt(struct es_em_ctxt *ctxt,
+ struct pt_regs *regs,
+ unsigned long exit_code)
+{
+ enum es_result ret = ES_OK;
+
+ memset(ctxt, 0, sizeof(*ctxt));
+ ctxt->regs = regs;
+
+ if (vc_decoding_needed(exit_code))
+ ret = vc_decode_insn(ctxt);
+
+ return ret;
+}
+
+static void vc_finish_insn(struct es_em_ctxt *ctxt)
+{
+ ctxt->regs->ip += ctxt->insn.length;
+}
+
+static enum es_result vc_insn_string_check(struct es_em_ctxt *ctxt,
+ unsigned long address,
+ bool write)
+{
+ if (user_mode(ctxt->regs) && fault_in_kernel_space(address)) {
+ ctxt->fi.vector = X86_TRAP_PF;
+ ctxt->fi.error_code = X86_PF_USER;
+ ctxt->fi.cr2 = address;
+ if (write)
+ ctxt->fi.error_code |= X86_PF_WRITE;
+
+ return ES_EXCEPTION;
+ }
+
+ return ES_OK;
+}
+
+static enum es_result vc_insn_string_read(struct es_em_ctxt *ctxt,
+ void *src, char *buf,
+ unsigned int data_size,
+ unsigned int count,
+ bool backwards)
+{
+ int i, b = backwards ? -1 : 1;
+ unsigned long address = (unsigned long)src;
+ enum es_result ret;
+
+ ret = vc_insn_string_check(ctxt, address, false);
+ if (ret != ES_OK)
+ return ret;
+
+ for (i = 0; i < count; i++) {
+ void *s = src + (i * data_size * b);
+ char *d = buf + (i * data_size);
+
+ ret = vc_read_mem(ctxt, s, d, data_size);
+ if (ret != ES_OK)
+ break;
+ }
+
+ return ret;
+}
+
+static enum es_result vc_insn_string_write(struct es_em_ctxt *ctxt,
+ void *dst, char *buf,
+ unsigned int data_size,
+ unsigned int count,
+ bool backwards)
+{
+ int i, s = backwards ? -1 : 1;
+ unsigned long address = (unsigned long)dst;
+ enum es_result ret;
+
+ ret = vc_insn_string_check(ctxt, address, true);
+ if (ret != ES_OK)
+ return ret;
+
+ for (i = 0; i < count; i++) {
+ void *d = dst + (i * data_size * s);
+ char *b = buf + (i * data_size);
+
+ ret = vc_write_mem(ctxt, d, b, data_size);
+ if (ret != ES_OK)
+ break;
+ }
+
+ return ret;
+}
+
+#define IOIO_TYPE_STR BIT(2)
+#define IOIO_TYPE_IN 1
+#define IOIO_TYPE_INS (IOIO_TYPE_IN | IOIO_TYPE_STR)
+#define IOIO_TYPE_OUT 0
+#define IOIO_TYPE_OUTS (IOIO_TYPE_OUT | IOIO_TYPE_STR)
+
+#define IOIO_REP BIT(3)
+
+#define IOIO_ADDR_64 BIT(9)
+#define IOIO_ADDR_32 BIT(8)
+#define IOIO_ADDR_16 BIT(7)
+
+#define IOIO_DATA_32 BIT(6)
+#define IOIO_DATA_16 BIT(5)
+#define IOIO_DATA_8 BIT(4)
+
+#define IOIO_SEG_ES (0 << 10)
+#define IOIO_SEG_DS (3 << 10)
+
+static enum es_result vc_ioio_exitinfo(struct es_em_ctxt *ctxt, u64 *exitinfo)
+{
+ struct insn *insn = &ctxt->insn;
+ size_t size;
+ u64 port;
+
+ *exitinfo = 0;
+
+ switch (insn->opcode.bytes[0]) {
+ /* INS opcodes */
+ case 0x6c:
+ case 0x6d:
+ *exitinfo |= IOIO_TYPE_INS;
+ *exitinfo |= IOIO_SEG_ES;
+ port = ctxt->regs->dx & 0xffff;
+ break;
+
+ /* OUTS opcodes */
+ case 0x6e:
+ case 0x6f:
+ *exitinfo |= IOIO_TYPE_OUTS;
+ *exitinfo |= IOIO_SEG_DS;
+ port = ctxt->regs->dx & 0xffff;
+ break;
+
+ /* IN immediate opcodes */
+ case 0xe4:
+ case 0xe5:
+ *exitinfo |= IOIO_TYPE_IN;
+ port = (u8)insn->immediate.value & 0xffff;
+ break;
+
+ /* OUT immediate opcodes */
+ case 0xe6:
+ case 0xe7:
+ *exitinfo |= IOIO_TYPE_OUT;
+ port = (u8)insn->immediate.value & 0xffff;
+ break;
+
+ /* IN register opcodes */
+ case 0xec:
+ case 0xed:
+ *exitinfo |= IOIO_TYPE_IN;
+ port = ctxt->regs->dx & 0xffff;
+ break;
+
+ /* OUT register opcodes */
+ case 0xee:
+ case 0xef:
+ *exitinfo |= IOIO_TYPE_OUT;
+ port = ctxt->regs->dx & 0xffff;
+ break;
+
+ default:
+ return ES_DECODE_FAILED;
+ }
+
+ *exitinfo |= port << 16;
+
+ switch (insn->opcode.bytes[0]) {
+ case 0x6c:
+ case 0x6e:
+ case 0xe4:
+ case 0xe6:
+ case 0xec:
+ case 0xee:
+ /* Single byte opcodes */
+ *exitinfo |= IOIO_DATA_8;
+ size = 1;
+ break;
+ default:
+ /* Length determined by instruction parsing */
+ *exitinfo |= (insn->opnd_bytes == 2) ? IOIO_DATA_16
+ : IOIO_DATA_32;
+ size = (insn->opnd_bytes == 2) ? 2 : 4;
+ }
+
+ switch (insn->addr_bytes) {
+ case 2:
+ *exitinfo |= IOIO_ADDR_16;
+ break;
+ case 4:
+ *exitinfo |= IOIO_ADDR_32;
+ break;
+ case 8:
+ *exitinfo |= IOIO_ADDR_64;
+ break;
+ }
+
+ if (insn_has_rep_prefix(insn))
+ *exitinfo |= IOIO_REP;
+
+ return vc_ioio_check(ctxt, (u16)port, size);
+}
+
+static enum es_result vc_handle_ioio(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+ struct pt_regs *regs = ctxt->regs;
+ u64 exit_info_1, exit_info_2;
+ enum es_result ret;
+
+ ret = vc_ioio_exitinfo(ctxt, &exit_info_1);
+ if (ret != ES_OK)
+ return ret;
+
+ if (exit_info_1 & IOIO_TYPE_STR) {
+
+ /* (REP) INS/OUTS */
+
+ bool df = ((regs->flags & X86_EFLAGS_DF) == X86_EFLAGS_DF);
+ unsigned int io_bytes, exit_bytes;
+ unsigned int ghcb_count, op_count;
+ unsigned long es_base;
+ u64 sw_scratch;
+
+ /*
+ * For the string variants with rep prefix the amount of in/out
+ * operations per #VC exception is limited so that the kernel
+ * has a chance to take interrupts and re-schedule while the
+ * instruction is emulated.
+ */
+ io_bytes = (exit_info_1 >> 4) & 0x7;
+ ghcb_count = sizeof(ghcb->shared_buffer) / io_bytes;
+
+ op_count = (exit_info_1 & IOIO_REP) ? regs->cx : 1;
+ exit_info_2 = min(op_count, ghcb_count);
+ exit_bytes = exit_info_2 * io_bytes;
+
+ es_base = insn_get_seg_base(ctxt->regs, INAT_SEG_REG_ES);
+
+ /* Read bytes of OUTS into the shared buffer */
+ if (!(exit_info_1 & IOIO_TYPE_IN)) {
+ ret = vc_insn_string_read(ctxt,
+ (void *)(es_base + regs->si),
+ ghcb->shared_buffer, io_bytes,
+ exit_info_2, df);
+ if (ret)
+ return ret;
+ }
+
+ /*
+ * Issue an VMGEXIT to the HV to consume the bytes from the
+ * shared buffer or to have it write them into the shared buffer
+ * depending on the instruction: OUTS or INS.
+ */
+ sw_scratch = __pa(ghcb) + offsetof(struct ghcb, shared_buffer);
+ ghcb_set_sw_scratch(ghcb, sw_scratch);
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO,
+ exit_info_1, exit_info_2);
+ if (ret != ES_OK)
+ return ret;
+
+ /* Read bytes from shared buffer into the guest's destination. */
+ if (exit_info_1 & IOIO_TYPE_IN) {
+ ret = vc_insn_string_write(ctxt,
+ (void *)(es_base + regs->di),
+ ghcb->shared_buffer, io_bytes,
+ exit_info_2, df);
+ if (ret)
+ return ret;
+
+ if (df)
+ regs->di -= exit_bytes;
+ else
+ regs->di += exit_bytes;
+ } else {
+ if (df)
+ regs->si -= exit_bytes;
+ else
+ regs->si += exit_bytes;
+ }
+
+ if (exit_info_1 & IOIO_REP)
+ regs->cx -= exit_info_2;
+
+ ret = regs->cx ? ES_RETRY : ES_OK;
+
+ } else {
+
+ /* IN/OUT into/from rAX */
+
+ int bits = (exit_info_1 & 0x70) >> 1;
+ u64 rax = 0;
+
+ if (!(exit_info_1 & IOIO_TYPE_IN))
+ rax = lower_bits(regs->ax, bits);
+
+ ghcb_set_rax(ghcb, rax);
+
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_IOIO, exit_info_1, 0);
+ if (ret != ES_OK)
+ return ret;
+
+ if (exit_info_1 & IOIO_TYPE_IN) {
+ if (!ghcb_rax_is_valid(ghcb))
+ return ES_VMM_ERROR;
+ regs->ax = lower_bits(ghcb->save.rax, bits);
+ }
+ }
+
+ return ret;
+}
+
+static int vc_handle_cpuid_snp(struct ghcb *ghcb, struct es_em_ctxt *ctxt)
+{
+ struct pt_regs *regs = ctxt->regs;
+ struct cpuid_leaf leaf;
+ int ret;
+
+ leaf.fn = regs->ax;
+ leaf.subfn = regs->cx;
+ ret = snp_cpuid(ghcb, ctxt, &leaf);
+ if (!ret) {
+ regs->ax = leaf.eax;
+ regs->bx = leaf.ebx;
+ regs->cx = leaf.ecx;
+ regs->dx = leaf.edx;
+ }
+
+ return ret;
+}
+
+static enum es_result vc_handle_cpuid(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt)
+{
+ struct pt_regs *regs = ctxt->regs;
+ u32 cr4 = native_read_cr4();
+ enum es_result ret;
+ int snp_cpuid_ret;
+
+ snp_cpuid_ret = vc_handle_cpuid_snp(ghcb, ctxt);
+ if (!snp_cpuid_ret)
+ return ES_OK;
+ if (snp_cpuid_ret != -EOPNOTSUPP)
+ return ES_VMM_ERROR;
+
+ ghcb_set_rax(ghcb, regs->ax);
+ ghcb_set_rcx(ghcb, regs->cx);
+
+ if (cr4 & X86_CR4_OSXSAVE)
+ /* Safe to read xcr0 */
+ ghcb_set_xcr0(ghcb, xgetbv(XCR_XFEATURE_ENABLED_MASK));
+ else
+ /* xgetbv will cause #GP - use reset value for xcr0 */
+ ghcb_set_xcr0(ghcb, 1);
+
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, SVM_EXIT_CPUID, 0, 0);
+ if (ret != ES_OK)
+ return ret;
+
+ if (!(ghcb_rax_is_valid(ghcb) &&
+ ghcb_rbx_is_valid(ghcb) &&
+ ghcb_rcx_is_valid(ghcb) &&
+ ghcb_rdx_is_valid(ghcb)))
+ return ES_VMM_ERROR;
+
+ regs->ax = ghcb->save.rax;
+ regs->bx = ghcb->save.rbx;
+ regs->cx = ghcb->save.rcx;
+ regs->dx = ghcb->save.rdx;
+
+ return ES_OK;
+}
+
+static enum es_result vc_handle_rdtsc(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt,
+ unsigned long exit_code)
+{
+ bool rdtscp = (exit_code == SVM_EXIT_RDTSCP);
+ enum es_result ret;
+
+ /*
+ * The hypervisor should not be intercepting RDTSC/RDTSCP when Secure
+ * TSC is enabled. A #VC exception will be generated if the RDTSC/RDTSCP
+ * instructions are being intercepted. If this should occur and Secure
+ * TSC is enabled, guest execution should be terminated as the guest
+ * cannot rely on the TSC value provided by the hypervisor.
+ */
+ if (sev_status & MSR_AMD64_SNP_SECURE_TSC)
+ return ES_VMM_ERROR;
+
+ ret = sev_es_ghcb_hv_call(ghcb, ctxt, exit_code, 0, 0);
+ if (ret != ES_OK)
+ return ret;
+
+ if (!(ghcb_rax_is_valid(ghcb) && ghcb_rdx_is_valid(ghcb) &&
+ (!rdtscp || ghcb_rcx_is_valid(ghcb))))
+ return ES_VMM_ERROR;
+
+ ctxt->regs->ax = ghcb->save.rax;
+ ctxt->regs->dx = ghcb->save.rdx;
+ if (rdtscp)
+ ctxt->regs->cx = ghcb->save.rcx;
+
+ return ES_OK;
+}
diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
index edab6d6049be..7b2833705d47 100644
--- a/arch/x86/coco/tdx/tdx.c
+++ b/arch/x86/coco/tdx/tdx.c
@@ -36,6 +36,7 @@
/* TDX Module call error codes */
#define TDCALL_RETURN_CODE(a) ((a) >> 32)
#define TDCALL_INVALID_OPERAND 0xc0000100
+#define TDCALL_OPERAND_BUSY 0x80000200
#define TDREPORT_SUBTYPE_0 0
@@ -109,12 +110,13 @@ static inline u64 tdg_vm_wr(u64 field, u64 value, u64 mask)
* REPORTDATA to be included into TDREPORT.
* @tdreport: Address of the output buffer to store TDREPORT.
*
- * Refer to section titled "TDG.MR.REPORT leaf" in the TDX Module
- * v1.0 specification for more information on TDG.MR.REPORT TDCALL.
+ * Refer to section titled "TDG.MR.REPORT leaf" in the TDX Module v1.0
+ * specification for more information on TDG.MR.REPORT TDCALL.
+ *
* It is used in the TDX guest driver module to get the TDREPORT0.
*
- * Return 0 on success, -EINVAL for invalid operands, or -EIO on
- * other TDCALL failures.
+ * Return 0 on success, -ENXIO for invalid operands, -EBUSY for busy operation,
+ * or -EIO on other TDCALL failures.
*/
int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport)
{
@@ -128,7 +130,9 @@ int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport)
ret = __tdcall(TDG_MR_REPORT, &args);
if (ret) {
if (TDCALL_RETURN_CODE(ret) == TDCALL_INVALID_OPERAND)
- return -EINVAL;
+ return -ENXIO;
+ else if (TDCALL_RETURN_CODE(ret) == TDCALL_OPERAND_BUSY)
+ return -EBUSY;
return -EIO;
}
@@ -137,6 +141,42 @@ int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport)
EXPORT_SYMBOL_GPL(tdx_mcall_get_report0);
/**
+ * tdx_mcall_extend_rtmr() - Wrapper to extend RTMR registers using
+ * TDG.MR.RTMR.EXTEND TDCALL.
+ * @index: Index of RTMR register to be extended.
+ * @data: Address of the input buffer with RTMR register extend data.
+ *
+ * Refer to section titled "TDG.MR.RTMR.EXTEND leaf" in the TDX Module v1.0
+ * specification for more information on TDG.MR.RTMR.EXTEND TDCALL.
+ *
+ * It is used in the TDX guest driver module to allow user to extend the RTMR
+ * registers.
+ *
+ * Return 0 on success, -ENXIO for invalid operands, -EBUSY for busy operation,
+ * or -EIO on other TDCALL failures.
+ */
+int tdx_mcall_extend_rtmr(u8 index, u8 *data)
+{
+ struct tdx_module_args args = {
+ .rcx = virt_to_phys(data),
+ .rdx = index,
+ };
+ u64 ret;
+
+ ret = __tdcall(TDG_MR_RTMR_EXTEND, &args);
+ if (ret) {
+ if (TDCALL_RETURN_CODE(ret) == TDCALL_INVALID_OPERAND)
+ return -ENXIO;
+ if (TDCALL_RETURN_CODE(ret) == TDCALL_OPERAND_BUSY)
+ return -EBUSY;
+ return -EIO;
+ }
+
+ return 0;
+}
+EXPORT_SYMBOL_GPL(tdx_mcall_extend_rtmr);
+
+/**
* tdx_hcall_get_quote() - Wrapper to request TD Quote using GetQuote
* hypercall.
* @buf: Address of the directly mapped shared kernel buffer which
diff --git a/arch/x86/configs/i386_defconfig b/arch/x86/configs/i386_defconfig
index 91801138b10b..79fa38ca954d 100644
--- a/arch/x86/configs/i386_defconfig
+++ b/arch/x86/configs/i386_defconfig
@@ -1,7 +1,6 @@
CONFIG_WERROR=y
CONFIG_SYSVIPC=y
CONFIG_POSIX_MQUEUE=y
-CONFIG_USELIB=y
CONFIG_AUDIT=y
CONFIG_NO_HZ=y
CONFIG_HIGH_RES_TIMERS=y
@@ -28,10 +27,12 @@ CONFIG_CGROUP_DEBUG=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_KALLSYMS_ALL=y
CONFIG_PROFILING=y
+CONFIG_KEXEC=y
+# Do not remove this as it results in non-bootable kernels
+# CONFIG_64BIT is not set
CONFIG_SMP=y
CONFIG_HYPERVISOR_GUEST=y
CONFIG_PARAVIRT=y
-CONFIG_NR_CPUS=8
CONFIG_X86_REROUTE_FOR_BROKEN_BOOT_IRQS=y
CONFIG_X86_MSR=y
CONFIG_X86_CPUID=y
@@ -40,9 +41,6 @@ CONFIG_X86_CHECK_BIOS_CORRUPTION=y
CONFIG_EFI=y
CONFIG_EFI_STUB=y
CONFIG_HZ_1000=y
-CONFIG_KEXEC=y
-CONFIG_CRASH_DUMP=y
-# CONFIG_MITIGATION_RETHUNK is not set
CONFIG_HIBERNATION=y
CONFIG_PM_DEBUG=y
CONFIG_PM_TRACE_RTC=y
@@ -53,7 +51,6 @@ CONFIG_CPU_FREQ_GOV_ONDEMAND=y
CONFIG_X86_ACPI_CPUFREQ=y
CONFIG_KPROBES=y
CONFIG_JUMP_LABEL=y
-CONFIG_COMPAT_32BIT_TIME=y
CONFIG_MODULES=y
CONFIG_MODULE_UNLOAD=y
CONFIG_MODULE_FORCE_UNLOAD=y
@@ -64,9 +61,7 @@ CONFIG_BINFMT_MISC=y
# CONFIG_COMPAT_BRK is not set
CONFIG_NET=y
CONFIG_PACKET=y
-CONFIG_UNIX=y
CONFIG_XFRM_USER=y
-CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
CONFIG_IP_MULTIPLE_TABLES=y
@@ -135,7 +130,6 @@ CONFIG_DEVTMPFS=y
CONFIG_DEVTMPFS_MOUNT=y
CONFIG_DEBUG_DEVRES=y
CONFIG_CONNECTOR=y
-CONFIG_EFI_CAPSULE_LOADER=y
CONFIG_BLK_DEV_LOOP=y
CONFIG_VIRTIO_BLK=y
CONFIG_BLK_DEV_SD=y
@@ -211,7 +205,6 @@ CONFIG_SND_HDA_INTEL=y
CONFIG_SND_HDA_HWDEP=y
CONFIG_HIDRAW=y
CONFIG_HID_GYRATION=y
-CONFIG_LOGITECH_FF=y
CONFIG_HID_NTRIG=y
CONFIG_HID_PANTHERLORD=y
CONFIG_PANTHERLORD_FF=y
@@ -242,7 +235,6 @@ CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
CONFIG_QUOTA=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
-# CONFIG_PRINT_QUOTA_WARNING is not set
CONFIG_QFMT_V2=y
CONFIG_AUTOFS_FS=y
CONFIG_ISO9660_FS=y
@@ -267,19 +259,13 @@ CONFIG_SECURITY=y
CONFIG_SECURITY_NETWORK=y
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_KERNEL=y
-CONFIG_FRAME_WARN=1024
CONFIG_MAGIC_SYSRQ=y
-CONFIG_DEBUG_WX=y
CONFIG_DEBUG_STACK_USAGE=y
-# CONFIG_SCHED_DEBUG is not set
CONFIG_SCHEDSTATS=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
CONFIG_EARLY_PRINTK_DBGP=y
CONFIG_DEBUG_BOOT_PARAMS=y
-CONFIG_UNWINDER_FRAME_POINTER=y
CONFIG_DEBUG_ENTRY=y
-# CONFIG_64BIT is not set
diff --git a/arch/x86/configs/x86_64_defconfig b/arch/x86/configs/x86_64_defconfig
index 61e25f6209ed..7d7310cdf8b0 100644
--- a/arch/x86/configs/x86_64_defconfig
+++ b/arch/x86/configs/x86_64_defconfig
@@ -27,6 +27,7 @@ CONFIG_CGROUP_DEBUG=y
CONFIG_BLK_DEV_INITRD=y
CONFIG_KALLSYMS_ALL=y
CONFIG_PROFILING=y
+CONFIG_KEXEC=y
CONFIG_SMP=y
CONFIG_HYPERVISOR_GUEST=y
CONFIG_PARAVIRT=y
@@ -40,8 +41,6 @@ CONFIG_EFI=y
CONFIG_EFI_STUB=y
CONFIG_EFI_MIXED=y
CONFIG_HZ_1000=y
-CONFIG_KEXEC=y
-CONFIG_CRASH_DUMP=y
CONFIG_HIBERNATION=y
CONFIG_PM_DEBUG=y
CONFIG_PM_TRACE_RTC=y
@@ -63,9 +62,7 @@ CONFIG_BINFMT_MISC=y
# CONFIG_COMPAT_BRK is not set
CONFIG_NET=y
CONFIG_PACKET=y
-CONFIG_UNIX=y
CONFIG_XFRM_USER=y
-CONFIG_INET=y
CONFIG_IP_MULTICAST=y
CONFIG_IP_ADVANCED_ROUTER=y
CONFIG_IP_MULTIPLE_TABLES=y
@@ -205,7 +202,6 @@ CONFIG_SND_HDA_INTEL=y
CONFIG_SND_HDA_HWDEP=y
CONFIG_HIDRAW=y
CONFIG_HID_GYRATION=y
-CONFIG_LOGITECH_FF=y
CONFIG_HID_NTRIG=y
CONFIG_HID_PANTHERLORD=y
CONFIG_PANTHERLORD_FF=y
@@ -239,7 +235,6 @@ CONFIG_EXT4_FS_POSIX_ACL=y
CONFIG_EXT4_FS_SECURITY=y
CONFIG_QUOTA=y
CONFIG_QUOTA_NETLINK_INTERFACE=y
-# CONFIG_PRINT_QUOTA_WARNING is not set
CONFIG_QFMT_V2=y
CONFIG_AUTOFS_FS=y
CONFIG_ISO9660_FS=y
@@ -264,13 +259,11 @@ CONFIG_SECURITY=y
CONFIG_SECURITY_NETWORK=y
CONFIG_SECURITY_SELINUX=y
CONFIG_SECURITY_SELINUX_BOOTPARAM=y
-CONFIG_SECURITY_SELINUX_DISABLE=y
CONFIG_PRINTK_TIME=y
CONFIG_DEBUG_KERNEL=y
CONFIG_MAGIC_SYSRQ=y
CONFIG_DEBUG_WX=y
CONFIG_DEBUG_STACK_USAGE=y
-# CONFIG_SCHED_DEBUG is not set
CONFIG_SCHEDSTATS=y
CONFIG_BLK_DEV_IO_TRACE=y
CONFIG_PROVIDE_OHCI1394_DMA_INIT=y
diff --git a/arch/x86/crypto/Kconfig b/arch/x86/crypto/Kconfig
index 3d948f10c94c..94016c60561e 100644
--- a/arch/x86/crypto/Kconfig
+++ b/arch/x86/crypto/Kconfig
@@ -4,7 +4,7 @@ menu "Accelerated Cryptographic Algorithms for CPU (x86)"
config CRYPTO_CURVE25519_X86
tristate
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_KPP
select CRYPTO_LIB_CURVE25519_GENERIC
select CRYPTO_ARCH_HAVE_LIB_CURVE25519
@@ -17,13 +17,11 @@ config CRYPTO_CURVE25519_X86
config CRYPTO_AES_NI_INTEL
tristate "Ciphers: AES, modes: ECB, CBC, CTS, CTR, XCTR, XTS, GCM (AES-NI/VAES)"
- depends on X86
select CRYPTO_AEAD
select CRYPTO_LIB_AES
select CRYPTO_LIB_GF128MUL
select CRYPTO_ALGAPI
select CRYPTO_SKCIPHER
- select CRYPTO_SIMD
help
Block cipher: AES cipher algorithms
AEAD cipher: AES with GCM
@@ -38,7 +36,7 @@ config CRYPTO_AES_NI_INTEL
config CRYPTO_BLOWFISH_X86_64
tristate "Ciphers: Blowfish, modes: ECB, CBC"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
select CRYPTO_BLOWFISH_COMMON
imply CRYPTO_CTR
@@ -50,7 +48,7 @@ config CRYPTO_BLOWFISH_X86_64
config CRYPTO_CAMELLIA_X86_64
tristate "Ciphers: Camellia with modes: ECB, CBC"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
imply CRYPTO_CTR
help
@@ -61,10 +59,9 @@ config CRYPTO_CAMELLIA_X86_64
config CRYPTO_CAMELLIA_AESNI_AVX_X86_64
tristate "Ciphers: Camellia with modes: ECB, CBC (AES-NI/AVX)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
select CRYPTO_CAMELLIA_X86_64
- select CRYPTO_SIMD
imply CRYPTO_XTS
help
Length-preserving ciphers: Camellia with ECB and CBC modes
@@ -75,7 +72,7 @@ config CRYPTO_CAMELLIA_AESNI_AVX_X86_64
config CRYPTO_CAMELLIA_AESNI_AVX2_X86_64
tristate "Ciphers: Camellia with modes: ECB, CBC (AES-NI/AVX2)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_CAMELLIA_AESNI_AVX_X86_64
help
Length-preserving ciphers: Camellia with ECB and CBC modes
@@ -86,11 +83,10 @@ config CRYPTO_CAMELLIA_AESNI_AVX2_X86_64
config CRYPTO_CAST5_AVX_X86_64
tristate "Ciphers: CAST5 with modes: ECB, CBC (AVX)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
select CRYPTO_CAST5
select CRYPTO_CAST_COMMON
- select CRYPTO_SIMD
imply CRYPTO_CTR
help
Length-preserving ciphers: CAST5 (CAST-128) cipher algorithm
@@ -103,11 +99,10 @@ config CRYPTO_CAST5_AVX_X86_64
config CRYPTO_CAST6_AVX_X86_64
tristate "Ciphers: CAST6 with modes: ECB, CBC (AVX)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
select CRYPTO_CAST6
select CRYPTO_CAST_COMMON
- select CRYPTO_SIMD
imply CRYPTO_XTS
imply CRYPTO_CTR
help
@@ -121,7 +116,7 @@ config CRYPTO_CAST6_AVX_X86_64
config CRYPTO_DES3_EDE_X86_64
tristate "Ciphers: Triple DES EDE with modes: ECB, CBC"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
select CRYPTO_LIB_DES
imply CRYPTO_CTR
@@ -135,10 +130,9 @@ config CRYPTO_DES3_EDE_X86_64
config CRYPTO_SERPENT_SSE2_X86_64
tristate "Ciphers: Serpent with modes: ECB, CBC (SSE2)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
select CRYPTO_SERPENT
- select CRYPTO_SIMD
imply CRYPTO_CTR
help
Length-preserving ciphers: Serpent cipher algorithm
@@ -151,10 +145,9 @@ config CRYPTO_SERPENT_SSE2_X86_64
config CRYPTO_SERPENT_SSE2_586
tristate "Ciphers: Serpent with modes: ECB, CBC (32-bit with SSE2)"
- depends on X86 && !64BIT
+ depends on !64BIT
select CRYPTO_SKCIPHER
select CRYPTO_SERPENT
- select CRYPTO_SIMD
imply CRYPTO_CTR
help
Length-preserving ciphers: Serpent cipher algorithm
@@ -167,10 +160,9 @@ config CRYPTO_SERPENT_SSE2_586
config CRYPTO_SERPENT_AVX_X86_64
tristate "Ciphers: Serpent with modes: ECB, CBC (AVX)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
select CRYPTO_SERPENT
- select CRYPTO_SIMD
imply CRYPTO_XTS
imply CRYPTO_CTR
help
@@ -184,7 +176,7 @@ config CRYPTO_SERPENT_AVX_X86_64
config CRYPTO_SERPENT_AVX2_X86_64
tristate "Ciphers: Serpent with modes: ECB, CBC (AVX2)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SERPENT_AVX_X86_64
help
Length-preserving ciphers: Serpent cipher algorithm
@@ -197,9 +189,8 @@ config CRYPTO_SERPENT_AVX2_X86_64
config CRYPTO_SM4_AESNI_AVX_X86_64
tristate "Ciphers: SM4 with modes: ECB, CBC, CTR (AES-NI/AVX)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
- select CRYPTO_SIMD
select CRYPTO_ALGAPI
select CRYPTO_SM4
help
@@ -218,9 +209,8 @@ config CRYPTO_SM4_AESNI_AVX_X86_64
config CRYPTO_SM4_AESNI_AVX2_X86_64
tristate "Ciphers: SM4 with modes: ECB, CBC, CTR (AES-NI/AVX2)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
- select CRYPTO_SIMD
select CRYPTO_ALGAPI
select CRYPTO_SM4
select CRYPTO_SM4_AESNI_AVX_X86_64
@@ -240,7 +230,7 @@ config CRYPTO_SM4_AESNI_AVX2_X86_64
config CRYPTO_TWOFISH_586
tristate "Ciphers: Twofish (32-bit)"
- depends on (X86 || UML_X86) && !64BIT
+ depends on !64BIT
select CRYPTO_ALGAPI
select CRYPTO_TWOFISH_COMMON
imply CRYPTO_CTR
@@ -251,7 +241,7 @@ config CRYPTO_TWOFISH_586
config CRYPTO_TWOFISH_X86_64
tristate "Ciphers: Twofish"
- depends on (X86 || UML_X86) && 64BIT
+ depends on 64BIT
select CRYPTO_ALGAPI
select CRYPTO_TWOFISH_COMMON
imply CRYPTO_CTR
@@ -262,7 +252,7 @@ config CRYPTO_TWOFISH_X86_64
config CRYPTO_TWOFISH_X86_64_3WAY
tristate "Ciphers: Twofish with modes: ECB, CBC (3-way parallel)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
select CRYPTO_TWOFISH_COMMON
select CRYPTO_TWOFISH_X86_64
@@ -277,9 +267,8 @@ config CRYPTO_TWOFISH_X86_64_3WAY
config CRYPTO_TWOFISH_AVX_X86_64
tristate "Ciphers: Twofish with modes: ECB, CBC (AVX)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
- select CRYPTO_SIMD
select CRYPTO_TWOFISH_COMMON
select CRYPTO_TWOFISH_X86_64
select CRYPTO_TWOFISH_X86_64_3WAY
@@ -295,9 +284,8 @@ config CRYPTO_TWOFISH_AVX_X86_64
config CRYPTO_ARIA_AESNI_AVX_X86_64
tristate "Ciphers: ARIA with modes: ECB, CTR (AES-NI/AVX/GFNI)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
- select CRYPTO_SIMD
select CRYPTO_ALGAPI
select CRYPTO_ARIA
help
@@ -313,9 +301,8 @@ config CRYPTO_ARIA_AESNI_AVX_X86_64
config CRYPTO_ARIA_AESNI_AVX2_X86_64
tristate "Ciphers: ARIA with modes: ECB, CTR (AES-NI/AVX2/GFNI)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_SKCIPHER
- select CRYPTO_SIMD
select CRYPTO_ALGAPI
select CRYPTO_ARIA
select CRYPTO_ARIA_AESNI_AVX_X86_64
@@ -332,9 +319,8 @@ config CRYPTO_ARIA_AESNI_AVX2_X86_64
config CRYPTO_ARIA_GFNI_AVX512_X86_64
tristate "Ciphers: ARIA with modes: ECB, CTR (AVX512/GFNI)"
- depends on X86 && 64BIT && AS_AVX512 && AS_GFNI
+ depends on 64BIT && AS_GFNI
select CRYPTO_SKCIPHER
- select CRYPTO_SIMD
select CRYPTO_ALGAPI
select CRYPTO_ARIA
select CRYPTO_ARIA_AESNI_AVX_X86_64
@@ -349,27 +335,10 @@ config CRYPTO_ARIA_GFNI_AVX512_X86_64
Processes 64 blocks in parallel.
-config CRYPTO_CHACHA20_X86_64
- tristate
- depends on X86 && 64BIT
- select CRYPTO_SKCIPHER
- select CRYPTO_LIB_CHACHA_GENERIC
- select CRYPTO_ARCH_HAVE_LIB_CHACHA
- default CRYPTO_LIB_CHACHA_INTERNAL
- help
- Length-preserving ciphers: ChaCha20, XChaCha20, and XChaCha12
- stream cipher algorithms
-
- Architecture: x86_64 using:
- - SSSE3 (Supplemental SSE3)
- - AVX2 (Advanced Vector Extensions 2)
- - AVX-512VL (Advanced Vector Extensions-512VL)
-
config CRYPTO_AEGIS128_AESNI_SSE2
tristate "AEAD ciphers: AEGIS-128 (AES-NI/SSE4.1)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_AEAD
- select CRYPTO_SIMD
help
AEGIS-128 AEAD algorithm
@@ -379,7 +348,7 @@ config CRYPTO_AEGIS128_AESNI_SSE2
config CRYPTO_NHPOLY1305_SSE2
tristate "Hash functions: NHPoly1305 (SSE2)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_NHPOLY1305
help
NHPoly1305 hash function for Adiantum
@@ -389,7 +358,7 @@ config CRYPTO_NHPOLY1305_SSE2
config CRYPTO_NHPOLY1305_AVX2
tristate "Hash functions: NHPoly1305 (AVX2)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_NHPOLY1305
help
NHPoly1305 hash function for Adiantum
@@ -397,21 +366,9 @@ config CRYPTO_NHPOLY1305_AVX2
Architecture: x86_64 using:
- AVX2 (Advanced Vector Extensions 2)
-config CRYPTO_BLAKE2S_X86
- bool "Hash functions: BLAKE2s (SSSE3/AVX-512)"
- depends on X86 && 64BIT
- select CRYPTO_LIB_BLAKE2S_GENERIC
- select CRYPTO_ARCH_HAVE_LIB_BLAKE2S
- help
- BLAKE2s cryptographic hash function (RFC 7693)
-
- Architecture: x86_64 using:
- - SSSE3 (Supplemental SSE3)
- - AVX-512 (Advanced Vector Extensions-512)
-
config CRYPTO_POLYVAL_CLMUL_NI
tristate "Hash functions: POLYVAL (CLMUL-NI)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_POLYVAL
help
POLYVAL hash function for HCTR2
@@ -419,66 +376,11 @@ config CRYPTO_POLYVAL_CLMUL_NI
Architecture: x86_64 using:
- CLMUL-NI (carry-less multiplication new instructions)
-config CRYPTO_POLY1305_X86_64
- tristate
- depends on X86 && 64BIT
- select CRYPTO_HASH
- select CRYPTO_LIB_POLY1305_GENERIC
- select CRYPTO_ARCH_HAVE_LIB_POLY1305
- default CRYPTO_LIB_POLY1305_INTERNAL
- help
- Poly1305 authenticator algorithm (RFC7539)
-
- Architecture: x86_64 using:
- - SSE2 (Streaming SIMD Extensions 2)
- - AVX2 (Advanced Vector Extensions 2)
-
-config CRYPTO_SHA1_SSSE3
- tristate "Hash functions: SHA-1 (SSSE3/AVX/AVX2/SHA-NI)"
- depends on X86 && 64BIT
- select CRYPTO_SHA1
- select CRYPTO_HASH
- help
- SHA-1 secure hash algorithm (FIPS 180)
-
- Architecture: x86_64 using:
- - SSSE3 (Supplemental SSE3)
- - AVX (Advanced Vector Extensions)
- - AVX2 (Advanced Vector Extensions 2)
- - SHA-NI (SHA Extensions New Instructions)
-
-config CRYPTO_SHA256_SSSE3
- tristate "Hash functions: SHA-224 and SHA-256 (SSSE3/AVX/AVX2/SHA-NI)"
- depends on X86 && 64BIT
- select CRYPTO_SHA256
- select CRYPTO_HASH
- help
- SHA-224 and SHA-256 secure hash algorithms (FIPS 180)
-
- Architecture: x86_64 using:
- - SSSE3 (Supplemental SSE3)
- - AVX (Advanced Vector Extensions)
- - AVX2 (Advanced Vector Extensions 2)
- - SHA-NI (SHA Extensions New Instructions)
-
-config CRYPTO_SHA512_SSSE3
- tristate "Hash functions: SHA-384 and SHA-512 (SSSE3/AVX/AVX2)"
- depends on X86 && 64BIT
- select CRYPTO_SHA512
- select CRYPTO_HASH
- help
- SHA-384 and SHA-512 secure hash algorithms (FIPS 180)
-
- Architecture: x86_64 using:
- - SSSE3 (Supplemental SSE3)
- - AVX (Advanced Vector Extensions)
- - AVX2 (Advanced Vector Extensions 2)
-
config CRYPTO_SM3_AVX_X86_64
tristate "Hash functions: SM3 (AVX)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_HASH
- select CRYPTO_SM3
+ select CRYPTO_LIB_SM3
help
SM3 secure hash function as defined by OSCCA GM/T 0004-2012 SM3
@@ -489,7 +391,7 @@ config CRYPTO_SM3_AVX_X86_64
config CRYPTO_GHASH_CLMUL_NI_INTEL
tristate "Hash functions: GHASH (CLMUL-NI)"
- depends on X86 && 64BIT
+ depends on 64BIT
select CRYPTO_CRYPTD
help
GCM GHASH hash function (NIST SP800-38D)
diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile
index 5d19f41bde58..d402963d6b57 100644
--- a/arch/x86/crypto/Makefile
+++ b/arch/x86/crypto/Makefile
@@ -42,10 +42,6 @@ cast6-avx-x86_64-y := cast6-avx-x86_64-asm_64.o cast6_avx_glue.o
obj-$(CONFIG_CRYPTO_AEGIS128_AESNI_SSE2) += aegis128-aesni.o
aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
-obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o
-chacha-x86_64-y := chacha-avx2-x86_64.o chacha-ssse3-x86_64.o chacha_glue.o
-chacha-x86_64-$(CONFIG_AS_AVX512) += chacha-avx512vl-x86_64.o
-
obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o
aesni-intel-$(CONFIG_64BIT) += aes-ctr-avx-x86_64.o \
@@ -55,30 +51,12 @@ ifeq ($(CONFIG_AS_VAES)$(CONFIG_AS_VPCLMULQDQ),yy)
aesni-intel-$(CONFIG_64BIT) += aes-gcm-avx10-x86_64.o
endif
-obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o
-sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ssse3_glue.o
-sha1-ssse3-$(CONFIG_AS_SHA1_NI) += sha1_ni_asm.o
-
-obj-$(CONFIG_CRYPTO_SHA256_SSSE3) += sha256-ssse3.o
-sha256-ssse3-y := sha256-ssse3-asm.o sha256-avx-asm.o sha256-avx2-asm.o sha256_ssse3_glue.o
-sha256-ssse3-$(CONFIG_AS_SHA256_NI) += sha256_ni_asm.o
-
-obj-$(CONFIG_CRYPTO_SHA512_SSSE3) += sha512-ssse3.o
-sha512-ssse3-y := sha512-ssse3-asm.o sha512-avx-asm.o sha512-avx2-asm.o sha512_ssse3_glue.o
-
-obj-$(CONFIG_CRYPTO_BLAKE2S_X86) += libblake2s-x86_64.o
-libblake2s-x86_64-y := blake2s-core.o blake2s-glue.o
-
obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
ghash-clmulni-intel-y := ghash-clmulni-intel_asm.o ghash-clmulni-intel_glue.o
obj-$(CONFIG_CRYPTO_POLYVAL_CLMUL_NI) += polyval-clmulni.o
polyval-clmulni-y := polyval-clmulni_asm.o polyval-clmulni_glue.o
-obj-$(CONFIG_CRYPTO_POLY1305_X86_64) += poly1305-x86_64.o
-poly1305-x86_64-y := poly1305-x86_64-cryptogams.o poly1305_glue.o
-targets += poly1305-x86_64-cryptogams.S
-
obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o
obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o
@@ -104,10 +82,5 @@ aria-aesni-avx2-x86_64-y := aria-aesni-avx2-asm_64.o aria_aesni_avx2_glue.o
obj-$(CONFIG_CRYPTO_ARIA_GFNI_AVX512_X86_64) += aria-gfni-avx512-x86_64.o
aria-gfni-avx512-x86_64-y := aria-gfni-avx512-asm_64.o aria_gfni_avx512_glue.o
-quiet_cmd_perlasm = PERLASM $@
- cmd_perlasm = $(PERL) $< > $@
-$(obj)/%.S: $(src)/%.pl FORCE
- $(call if_changed,perlasm)
-
# Disable GCOV in odd or sensitive code
GCOV_PROFILE_curve25519-x86_64.o := n
diff --git a/arch/x86/crypto/aegis128-aesni-glue.c b/arch/x86/crypto/aegis128-aesni-glue.c
index 26786e15abac..f1adfba1a76e 100644
--- a/arch/x86/crypto/aegis128-aesni-glue.c
+++ b/arch/x86/crypto/aegis128-aesni-glue.c
@@ -8,7 +8,6 @@
*/
#include <crypto/internal/aead.h>
-#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <crypto/scatterwalk.h>
#include <linux/module.h>
@@ -105,10 +104,12 @@ static void crypto_aegis128_aesni_process_ad(
}
}
-static __always_inline void
+static __always_inline int
crypto_aegis128_aesni_process_crypt(struct aegis_state *state,
struct skcipher_walk *walk, bool enc)
{
+ int err = 0;
+
while (walk->nbytes >= AEGIS128_BLOCK_SIZE) {
if (enc)
aegis128_aesni_enc(state, walk->src.virt.addr,
@@ -120,7 +121,10 @@ crypto_aegis128_aesni_process_crypt(struct aegis_state *state,
walk->dst.virt.addr,
round_down(walk->nbytes,
AEGIS128_BLOCK_SIZE));
- skcipher_walk_done(walk, walk->nbytes % AEGIS128_BLOCK_SIZE);
+ kernel_fpu_end();
+ err = skcipher_walk_done(walk,
+ walk->nbytes % AEGIS128_BLOCK_SIZE);
+ kernel_fpu_begin();
}
if (walk->nbytes) {
@@ -132,8 +136,11 @@ crypto_aegis128_aesni_process_crypt(struct aegis_state *state,
aegis128_aesni_dec_tail(state, walk->src.virt.addr,
walk->dst.virt.addr,
walk->nbytes);
- skcipher_walk_done(walk, 0);
+ kernel_fpu_end();
+ err = skcipher_walk_done(walk, 0);
+ kernel_fpu_begin();
}
+ return err;
}
static struct aegis_ctx *crypto_aegis128_aesni_ctx(struct crypto_aead *aead)
@@ -166,7 +173,7 @@ static int crypto_aegis128_aesni_setauthsize(struct crypto_aead *tfm,
return 0;
}
-static __always_inline void
+static __always_inline int
crypto_aegis128_aesni_crypt(struct aead_request *req,
struct aegis_block *tag_xor,
unsigned int cryptlen, bool enc)
@@ -175,20 +182,24 @@ crypto_aegis128_aesni_crypt(struct aead_request *req,
struct aegis_ctx *ctx = crypto_aegis128_aesni_ctx(tfm);
struct skcipher_walk walk;
struct aegis_state state;
+ int err;
if (enc)
- skcipher_walk_aead_encrypt(&walk, req, true);
+ err = skcipher_walk_aead_encrypt(&walk, req, false);
else
- skcipher_walk_aead_decrypt(&walk, req, true);
+ err = skcipher_walk_aead_decrypt(&walk, req, false);
+ if (err)
+ return err;
kernel_fpu_begin();
aegis128_aesni_init(&state, &ctx->key, req->iv);
crypto_aegis128_aesni_process_ad(&state, req->src, req->assoclen);
- crypto_aegis128_aesni_process_crypt(&state, &walk, enc);
- aegis128_aesni_final(&state, tag_xor, req->assoclen, cryptlen);
-
+ err = crypto_aegis128_aesni_process_crypt(&state, &walk, enc);
+ if (err == 0)
+ aegis128_aesni_final(&state, tag_xor, req->assoclen, cryptlen);
kernel_fpu_end();
+ return err;
}
static int crypto_aegis128_aesni_encrypt(struct aead_request *req)
@@ -197,8 +208,11 @@ static int crypto_aegis128_aesni_encrypt(struct aead_request *req)
struct aegis_block tag = {};
unsigned int authsize = crypto_aead_authsize(tfm);
unsigned int cryptlen = req->cryptlen;
+ int err;
- crypto_aegis128_aesni_crypt(req, &tag, cryptlen, true);
+ err = crypto_aegis128_aesni_crypt(req, &tag, cryptlen, true);
+ if (err)
+ return err;
scatterwalk_map_and_copy(tag.bytes, req->dst,
req->assoclen + cryptlen, authsize, 1);
@@ -213,11 +227,14 @@ static int crypto_aegis128_aesni_decrypt(struct aead_request *req)
struct aegis_block tag;
unsigned int authsize = crypto_aead_authsize(tfm);
unsigned int cryptlen = req->cryptlen - authsize;
+ int err;
scatterwalk_map_and_copy(tag.bytes, req->src,
req->assoclen + cryptlen, authsize, 0);
- crypto_aegis128_aesni_crypt(req, &tag, cryptlen, false);
+ err = crypto_aegis128_aesni_crypt(req, &tag, cryptlen, false);
+ if (err)
+ return err;
return crypto_memneq(tag.bytes, zeros.bytes, authsize) ? -EBADMSG : 0;
}
@@ -233,21 +250,18 @@ static struct aead_alg crypto_aegis128_aesni_alg = {
.chunksize = AEGIS128_BLOCK_SIZE,
.base = {
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = 1,
.cra_ctxsize = sizeof(struct aegis_ctx) +
__alignof__(struct aegis_ctx),
.cra_priority = 400,
- .cra_name = "__aegis128",
- .cra_driver_name = "__aegis128-aesni",
+ .cra_name = "aegis128",
+ .cra_driver_name = "aegis128-aesni",
.cra_module = THIS_MODULE,
}
};
-static struct simd_aead_alg *simd_alg;
-
static int __init crypto_aegis128_aesni_module_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM4_1) ||
@@ -255,13 +269,12 @@ static int __init crypto_aegis128_aesni_module_init(void)
!cpu_has_xfeatures(XFEATURE_MASK_SSE, NULL))
return -ENODEV;
- return simd_register_aeads_compat(&crypto_aegis128_aesni_alg, 1,
- &simd_alg);
+ return crypto_register_aead(&crypto_aegis128_aesni_alg);
}
static void __exit crypto_aegis128_aesni_module_exit(void)
{
- simd_unregister_aeads(&crypto_aegis128_aesni_alg, 1, &simd_alg);
+ crypto_unregister_aead(&crypto_aegis128_aesni_alg);
}
module_init(crypto_aegis128_aesni_module_init);
diff --git a/arch/x86/crypto/aes-ctr-avx-x86_64.S b/arch/x86/crypto/aes-ctr-avx-x86_64.S
index 1685d8b24b2c..bbbfd80f5a50 100644
--- a/arch/x86/crypto/aes-ctr-avx-x86_64.S
+++ b/arch/x86/crypto/aes-ctr-avx-x86_64.S
@@ -48,8 +48,7 @@
// using the following sets of CPU features:
// - AES-NI && AVX
// - VAES && AVX2
-// - VAES && (AVX10/256 || (AVX512BW && AVX512VL)) && BMI2
-// - VAES && (AVX10/512 || (AVX512BW && AVX512VL)) && BMI2
+// - VAES && AVX512BW && AVX512VL && BMI2
//
// See the function definitions at the bottom of the file for more information.
@@ -76,7 +75,6 @@
.text
// Move a vector between memory and a register.
-// The register operand must be in the first 16 vector registers.
.macro _vmovdqu src, dst
.if VL < 64
vmovdqu \src, \dst
@@ -86,7 +84,6 @@
.endm
// Move a vector between registers.
-// The registers must be in the first 16 vector registers.
.macro _vmovdqa src, dst
.if VL < 64
vmovdqa \src, \dst
@@ -96,7 +93,7 @@
.endm
// Broadcast a 128-bit value from memory to all 128-bit lanes of a vector
-// register. The register operand must be in the first 16 vector registers.
+// register.
.macro _vbroadcast128 src, dst
.if VL == 16
vmovdqu \src, \dst
@@ -108,7 +105,6 @@
.endm
// XOR two vectors together.
-// Any register operands must be in the first 16 vector registers.
.macro _vpxor src1, src2, dst
.if VL < 64
vpxor \src1, \src2, \dst
@@ -199,8 +195,8 @@
// XOR each with the zero-th round key. Also update LE_CTR if !\final.
.macro _prepare_2_ctr_vecs is_xctr, i0, i1, final=0
.if \is_xctr
- .if USE_AVX10
- _vmovdqa LE_CTR, AESDATA\i0
+ .if USE_AVX512
+ vmovdqa64 LE_CTR, AESDATA\i0
vpternlogd $0x96, XCTR_IV, RNDKEY0, AESDATA\i0
.else
vpxor XCTR_IV, LE_CTR, AESDATA\i0
@@ -208,7 +204,7 @@
.endif
vpaddq LE_CTR_INC1, LE_CTR, AESDATA\i1
- .if USE_AVX10
+ .if USE_AVX512
vpternlogd $0x96, XCTR_IV, RNDKEY0, AESDATA\i1
.else
vpxor XCTR_IV, AESDATA\i1, AESDATA\i1
@@ -481,18 +477,12 @@
.Lxor_tail_partial_vec_0\@:
// XOR the remaining 1 <= LEN < VL bytes. It's easy if masked
// loads/stores are available; otherwise it's a bit harder...
-.if USE_AVX10
- .if VL <= 32
- mov $-1, %eax
- bzhi LEN, %eax, %eax
- kmovd %eax, %k1
- .else
+.if USE_AVX512
mov $-1, %rax
bzhi LEN64, %rax, %rax
kmovq %rax, %k1
- .endif
vmovdqu8 (SRC), AESDATA1{%k1}{z}
- _vpxor AESDATA1, AESDATA0, AESDATA0
+ vpxord AESDATA1, AESDATA0, AESDATA0
vmovdqu8 AESDATA0, (DST){%k1}
.else
.if VL == 32
@@ -554,7 +544,7 @@
// eliminates carries. |ctr| is the per-message block counter starting at 1.
.set VL, 16
-.set USE_AVX10, 0
+.set USE_AVX512, 0
SYM_TYPED_FUNC_START(aes_ctr64_crypt_aesni_avx)
_aes_ctr_crypt 0
SYM_FUNC_END(aes_ctr64_crypt_aesni_avx)
@@ -564,7 +554,7 @@ SYM_FUNC_END(aes_xctr_crypt_aesni_avx)
#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
.set VL, 32
-.set USE_AVX10, 0
+.set USE_AVX512, 0
SYM_TYPED_FUNC_START(aes_ctr64_crypt_vaes_avx2)
_aes_ctr_crypt 0
SYM_FUNC_END(aes_ctr64_crypt_vaes_avx2)
@@ -572,21 +562,12 @@ SYM_TYPED_FUNC_START(aes_xctr_crypt_vaes_avx2)
_aes_ctr_crypt 1
SYM_FUNC_END(aes_xctr_crypt_vaes_avx2)
-.set VL, 32
-.set USE_AVX10, 1
-SYM_TYPED_FUNC_START(aes_ctr64_crypt_vaes_avx10_256)
- _aes_ctr_crypt 0
-SYM_FUNC_END(aes_ctr64_crypt_vaes_avx10_256)
-SYM_TYPED_FUNC_START(aes_xctr_crypt_vaes_avx10_256)
- _aes_ctr_crypt 1
-SYM_FUNC_END(aes_xctr_crypt_vaes_avx10_256)
-
.set VL, 64
-.set USE_AVX10, 1
-SYM_TYPED_FUNC_START(aes_ctr64_crypt_vaes_avx10_512)
+.set USE_AVX512, 1
+SYM_TYPED_FUNC_START(aes_ctr64_crypt_vaes_avx512)
_aes_ctr_crypt 0
-SYM_FUNC_END(aes_ctr64_crypt_vaes_avx10_512)
-SYM_TYPED_FUNC_START(aes_xctr_crypt_vaes_avx10_512)
+SYM_FUNC_END(aes_ctr64_crypt_vaes_avx512)
+SYM_TYPED_FUNC_START(aes_xctr_crypt_vaes_avx512)
_aes_ctr_crypt 1
-SYM_FUNC_END(aes_xctr_crypt_vaes_avx10_512)
+SYM_FUNC_END(aes_xctr_crypt_vaes_avx512)
#endif // CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ
diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S
index 93ba0ddbe009..db79cdf81588 100644
--- a/arch/x86/crypto/aes-xts-avx-x86_64.S
+++ b/arch/x86/crypto/aes-xts-avx-x86_64.S
@@ -52,32 +52,25 @@
* different code, it uses a macro to generate several implementations that
* share similar source code but are targeted at different CPUs, listed below:
*
- * AES-NI + AVX
+ * AES-NI && AVX
* - 128-bit vectors (1 AES block per vector)
* - VEX-coded instructions
* - xmm0-xmm15
* - This is for older CPUs that lack VAES but do have AVX.
*
- * VAES + VPCLMULQDQ + AVX2
+ * VAES && VPCLMULQDQ && AVX2
* - 256-bit vectors (2 AES blocks per vector)
* - VEX-coded instructions
* - ymm0-ymm15
- * - This is for CPUs that have VAES but lack AVX512 or AVX10,
- * e.g. Intel's Alder Lake and AMD's Zen 3.
+ * - This is for CPUs that have VAES but either lack AVX512 (e.g. Intel's
+ * Alder Lake and AMD's Zen 3) or downclock too eagerly when using zmm
+ * registers (e.g. Intel's Ice Lake).
*
- * VAES + VPCLMULQDQ + AVX10/256 + BMI2
- * - 256-bit vectors (2 AES blocks per vector)
+ * VAES && VPCLMULQDQ && AVX512BW && AVX512VL && BMI2
+ * - 512-bit vectors (4 AES blocks per vector)
* - EVEX-coded instructions
- * - ymm0-ymm31
- * - This is for CPUs that have AVX512 but where using zmm registers causes
- * downclocking, and for CPUs that have AVX10/256 but not AVX10/512.
- * - By "AVX10/256" we really mean (AVX512BW + AVX512VL) || AVX10/256.
- * To avoid confusion with 512-bit, we just write AVX10/256.
- *
- * VAES + VPCLMULQDQ + AVX10/512 + BMI2
- * - Same as the previous one, but upgrades to 512-bit vectors
- * (4 AES blocks per vector) in zmm0-zmm31.
- * - This is for CPUs that have good AVX512 or AVX10/512 support.
+ * - zmm0-zmm31
+ * - This is for CPUs that have good AVX512 support.
*
* This file doesn't have an implementation for AES-NI alone (without AVX), as
* the lack of VEX would make all the assembly code different.
@@ -107,9 +100,20 @@
// exists when there's a carry out of the low 64 bits of the tweak.
.quad 0x87, 1
+ // These are the shift amounts that are needed when multiplying by [x^0,
+ // x^1, x^2, x^3] to compute the first vector of tweaks when VL=64.
+ //
+ // The right shifts by 64 are expected to zeroize the destination.
+ // 'vpsrlvq' is indeed defined to do that; i.e. it doesn't truncate the
+ // amount to 64 & 63 = 0 like the 'shr' scalar shift instruction would.
+.Lrshift_amounts:
+ .byte 64, 64, 63, 63, 62, 62, 61, 61
+.Llshift_amounts:
+ .byte 0, 0, 1, 1, 2, 2, 3, 3
+
// This table contains constants for vpshufb and vpblendvb, used to
// handle variable byte shifts and blending during ciphertext stealing
- // on CPUs that don't support AVX10-style masking.
+ // on CPUs that don't support AVX512-style masking.
.Lcts_permute_table:
.byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
.byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80
@@ -138,7 +142,7 @@
.irp i, 0,1,2,3,4,5,6,7,8,9,10,11,12,13,14,15
_define_Vi \i
.endr
-.if USE_AVX10
+.if USE_AVX512
.irp i, 16,17,18,19,20,21,22,23,24,25,26,27,28,29,30,31
_define_Vi \i
.endr
@@ -193,7 +197,7 @@
// keys to the *end* of this register range. I.e., AES-128 uses
// KEY5-KEY14, AES-192 uses KEY3-KEY14, and AES-256 uses KEY1-KEY14.
// (All also use KEY0 for the XOR-only "round" at the beginning.)
-.if USE_AVX10
+.if USE_AVX512
.set KEY1_XMM, %xmm16
.set KEY1, V16
.set KEY2_XMM, %xmm17
@@ -227,7 +231,6 @@
.endm
// Move a vector between memory and a register.
-// The register operand must be in the first 16 vector registers.
.macro _vmovdqu src, dst
.if VL < 64
vmovdqu \src, \dst
@@ -238,9 +241,9 @@
// Broadcast a 128-bit value into a vector.
.macro _vbroadcast128 src, dst
-.if VL == 16 && !USE_AVX10
+.if VL == 16
vmovdqu \src, \dst
-.elseif VL == 32 && !USE_AVX10
+.elseif VL == 32
vbroadcasti128 \src, \dst
.else
vbroadcasti32x4 \src, \dst
@@ -248,7 +251,6 @@
.endm
// XOR two vectors together.
-// Any register operands must be in the first 16 vector registers.
.macro _vpxor src1, src2, dst
.if VL < 64
vpxor \src1, \src2, \dst
@@ -259,7 +261,7 @@
// XOR three vectors together.
.macro _xor3 src1, src2, src3_and_dst
-.if USE_AVX10
+.if USE_AVX512
// vpternlogd with immediate 0x96 is a three-argument XOR.
vpternlogd $0x96, \src1, \src2, \src3_and_dst
.else
@@ -274,7 +276,7 @@
vpshufd $0x13, \src, \tmp
vpaddq \src, \src, \dst
vpsrad $31, \tmp, \tmp
-.if USE_AVX10
+.if USE_AVX512
vpternlogd $0x78, GF_POLY_XMM, \tmp, \dst
.else
vpand GF_POLY_XMM, \tmp, \tmp
@@ -303,52 +305,75 @@
// Given the first XTS tweak at (TWEAK), compute the first set of tweaks and
// store them in the vector registers TWEAK0-TWEAK3. Clobbers V0-V5.
.macro _compute_first_set_of_tweaks
- vmovdqu (TWEAK), TWEAK0_XMM
- _vbroadcast128 .Lgf_poly(%rip), GF_POLY
.if VL == 16
- // With VL=16, multiplying by x serially is fastest.
+ vmovdqu (TWEAK), TWEAK0_XMM
+ vmovdqu .Lgf_poly(%rip), GF_POLY
_next_tweak TWEAK0, %xmm0, TWEAK1
_next_tweak TWEAK1, %xmm0, TWEAK2
_next_tweak TWEAK2, %xmm0, TWEAK3
-.else
-.if VL == 32
- // Compute the second block of TWEAK0.
+.elseif VL == 32
+ vmovdqu (TWEAK), TWEAK0_XMM
+ vbroadcasti128 .Lgf_poly(%rip), GF_POLY
+
+ // Compute the first vector of tweaks.
_next_tweak TWEAK0_XMM, %xmm0, %xmm1
vinserti128 $1, %xmm1, TWEAK0, TWEAK0
-.elseif VL == 64
- // Compute the remaining blocks of TWEAK0.
- _next_tweak TWEAK0_XMM, %xmm0, %xmm1
- _next_tweak %xmm1, %xmm0, %xmm2
- _next_tweak %xmm2, %xmm0, %xmm3
- vinserti32x4 $1, %xmm1, TWEAK0, TWEAK0
- vinserti32x4 $2, %xmm2, TWEAK0, TWEAK0
- vinserti32x4 $3, %xmm3, TWEAK0, TWEAK0
-.endif
- // Compute TWEAK[1-3] from TWEAK0.
- vpsrlq $64 - 1*VL/16, TWEAK0, V0
- vpsrlq $64 - 2*VL/16, TWEAK0, V2
- vpsrlq $64 - 3*VL/16, TWEAK0, V4
+
+ // Compute the next three vectors of tweaks:
+ // TWEAK1 = TWEAK0 * [x^2, x^2]
+ // TWEAK2 = TWEAK0 * [x^4, x^4]
+ // TWEAK3 = TWEAK0 * [x^6, x^6]
+ vpsrlq $64 - 2, TWEAK0, V0
+ vpsrlq $64 - 4, TWEAK0, V2
+ vpsrlq $64 - 6, TWEAK0, V4
vpclmulqdq $0x01, GF_POLY, V0, V1
vpclmulqdq $0x01, GF_POLY, V2, V3
vpclmulqdq $0x01, GF_POLY, V4, V5
vpslldq $8, V0, V0
vpslldq $8, V2, V2
vpslldq $8, V4, V4
- vpsllq $1*VL/16, TWEAK0, TWEAK1
- vpsllq $2*VL/16, TWEAK0, TWEAK2
- vpsllq $3*VL/16, TWEAK0, TWEAK3
-.if USE_AVX10
- vpternlogd $0x96, V0, V1, TWEAK1
- vpternlogd $0x96, V2, V3, TWEAK2
- vpternlogd $0x96, V4, V5, TWEAK3
-.else
+ vpsllq $2, TWEAK0, TWEAK1
+ vpsllq $4, TWEAK0, TWEAK2
+ vpsllq $6, TWEAK0, TWEAK3
vpxor V0, TWEAK1, TWEAK1
vpxor V2, TWEAK2, TWEAK2
vpxor V4, TWEAK3, TWEAK3
vpxor V1, TWEAK1, TWEAK1
vpxor V3, TWEAK2, TWEAK2
vpxor V5, TWEAK3, TWEAK3
-.endif
+.else
+ vbroadcasti32x4 (TWEAK), TWEAK0
+ vbroadcasti32x4 .Lgf_poly(%rip), GF_POLY
+
+ // Compute the first vector of tweaks:
+ // TWEAK0 = broadcast128(TWEAK) * [x^0, x^1, x^2, x^3]
+ vpmovzxbq .Lrshift_amounts(%rip), V4
+ vpsrlvq V4, TWEAK0, V0
+ vpclmulqdq $0x01, GF_POLY, V0, V1
+ vpmovzxbq .Llshift_amounts(%rip), V4
+ vpslldq $8, V0, V0
+ vpsllvq V4, TWEAK0, TWEAK0
+ vpternlogd $0x96, V0, V1, TWEAK0
+
+ // Compute the next three vectors of tweaks:
+ // TWEAK1 = TWEAK0 * [x^4, x^4, x^4, x^4]
+ // TWEAK2 = TWEAK0 * [x^8, x^8, x^8, x^8]
+ // TWEAK3 = TWEAK0 * [x^12, x^12, x^12, x^12]
+ // x^8 only needs byte-aligned shifts, so optimize accordingly.
+ vpsrlq $64 - 4, TWEAK0, V0
+ vpsrldq $(64 - 8) / 8, TWEAK0, V2
+ vpsrlq $64 - 12, TWEAK0, V4
+ vpclmulqdq $0x01, GF_POLY, V0, V1
+ vpclmulqdq $0x01, GF_POLY, V2, V3
+ vpclmulqdq $0x01, GF_POLY, V4, V5
+ vpslldq $8, V0, V0
+ vpslldq $8, V4, V4
+ vpsllq $4, TWEAK0, TWEAK1
+ vpslldq $8 / 8, TWEAK0, TWEAK2
+ vpsllq $12, TWEAK0, TWEAK3
+ vpternlogd $0x96, V0, V1, TWEAK1
+ vpxord V3, TWEAK2, TWEAK2
+ vpternlogd $0x96, V4, V5, TWEAK3
.endif
.endm
@@ -474,26 +499,26 @@
lea OFFS-16(KEY, KEYLEN64, 4), KEY
// If all 32 SIMD registers are available, cache all the round keys.
-.if USE_AVX10
+.if USE_AVX512
cmp $24, KEYLEN
jl .Laes128\@
je .Laes192\@
- _vbroadcast128 -6*16(KEY), KEY1
- _vbroadcast128 -5*16(KEY), KEY2
+ vbroadcasti32x4 -6*16(KEY), KEY1
+ vbroadcasti32x4 -5*16(KEY), KEY2
.Laes192\@:
- _vbroadcast128 -4*16(KEY), KEY3
- _vbroadcast128 -3*16(KEY), KEY4
+ vbroadcasti32x4 -4*16(KEY), KEY3
+ vbroadcasti32x4 -3*16(KEY), KEY4
.Laes128\@:
- _vbroadcast128 -2*16(KEY), KEY5
- _vbroadcast128 -1*16(KEY), KEY6
- _vbroadcast128 0*16(KEY), KEY7
- _vbroadcast128 1*16(KEY), KEY8
- _vbroadcast128 2*16(KEY), KEY9
- _vbroadcast128 3*16(KEY), KEY10
- _vbroadcast128 4*16(KEY), KEY11
- _vbroadcast128 5*16(KEY), KEY12
- _vbroadcast128 6*16(KEY), KEY13
- _vbroadcast128 7*16(KEY), KEY14
+ vbroadcasti32x4 -2*16(KEY), KEY5
+ vbroadcasti32x4 -1*16(KEY), KEY6
+ vbroadcasti32x4 0*16(KEY), KEY7
+ vbroadcasti32x4 1*16(KEY), KEY8
+ vbroadcasti32x4 2*16(KEY), KEY9
+ vbroadcasti32x4 3*16(KEY), KEY10
+ vbroadcasti32x4 4*16(KEY), KEY11
+ vbroadcasti32x4 5*16(KEY), KEY12
+ vbroadcasti32x4 6*16(KEY), KEY13
+ vbroadcasti32x4 7*16(KEY), KEY14
.endif
.endm
@@ -521,7 +546,7 @@
// using the same key for all block(s). The round key is loaded from the
// appropriate register or memory location for round \i. May clobber \tmp.
.macro _vaes_1x enc, i, xmm_suffix, data, tmp
-.if USE_AVX10
+.if USE_AVX512
_vaes \enc, KEY\i\xmm_suffix, \data
.else
.ifnb \xmm_suffix
@@ -538,7 +563,7 @@
// appropriate register or memory location for round \i. In addition, does two
// steps of the computation of the next set of tweaks. May clobber V4 and V5.
.macro _vaes_4x enc, i
-.if USE_AVX10
+.if USE_AVX512
_tweak_step (2*(\i-5))
_vaes \enc, KEY\i, V0
_vaes \enc, KEY\i, V1
@@ -574,7 +599,7 @@
.irp i, 5,6,7,8,9,10,11,12,13
_vaes_1x \enc, \i, \xmm_suffix, \data, tmp=\tmp
.endr
-.if USE_AVX10
+.if USE_AVX512
vpxord KEY14\xmm_suffix, \tweak, \tmp
.else
.ifnb \xmm_suffix
@@ -617,11 +642,11 @@
// This is the main loop, en/decrypting 4*VL bytes per iteration.
// XOR each source block with its tweak and the zero-th round key.
-.if USE_AVX10
- _vmovdqu 0*VL(SRC), V0
- _vmovdqu 1*VL(SRC), V1
- _vmovdqu 2*VL(SRC), V2
- _vmovdqu 3*VL(SRC), V3
+.if USE_AVX512
+ vmovdqu8 0*VL(SRC), V0
+ vmovdqu8 1*VL(SRC), V1
+ vmovdqu8 2*VL(SRC), V2
+ vmovdqu8 3*VL(SRC), V3
vpternlogd $0x96, TWEAK0, KEY0, V0
vpternlogd $0x96, TWEAK1, KEY0, V1
vpternlogd $0x96, TWEAK2, KEY0, V2
@@ -654,7 +679,7 @@
// Reduce latency by doing the XOR before the vaesenclast, utilizing the
// property vaesenclast(key, a) ^ b == vaesenclast(key ^ b, a)
// (and likewise for vaesdeclast).
-.if USE_AVX10
+.if USE_AVX512
_tweak_step 18
_tweak_step 19
vpxord TWEAK0, KEY14, V4
@@ -762,7 +787,7 @@
_aes_crypt \enc, _XMM, TWEAK1_XMM, %xmm0, tmp=%xmm1
.endif
-.if USE_AVX10
+.if USE_AVX512
// Create a mask that has the first LEN bits set.
mov $-1, %r9d
bzhi LEN, %r9d, %r9d
@@ -811,7 +836,7 @@
// u8 iv[AES_BLOCK_SIZE]);
//
// Encrypt |iv| using the AES key |tweak_key| to get the first tweak. Assumes
-// that the CPU supports AES-NI and AVX, but not necessarily VAES or AVX10.
+// that the CPU supports AES-NI and AVX, but not necessarily VAES or AVX512.
SYM_TYPED_FUNC_START(aes_xts_encrypt_iv)
.set TWEAK_KEY, %rdi
.set IV, %rsi
@@ -853,7 +878,7 @@ SYM_FUNC_END(aes_xts_encrypt_iv)
// multiple of 16, then this function updates |tweak| to contain the next tweak.
.set VL, 16
-.set USE_AVX10, 0
+.set USE_AVX512, 0
SYM_TYPED_FUNC_START(aes_xts_encrypt_aesni_avx)
_aes_xts_crypt 1
SYM_FUNC_END(aes_xts_encrypt_aesni_avx)
@@ -863,7 +888,7 @@ SYM_FUNC_END(aes_xts_decrypt_aesni_avx)
#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
.set VL, 32
-.set USE_AVX10, 0
+.set USE_AVX512, 0
SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx2)
_aes_xts_crypt 1
SYM_FUNC_END(aes_xts_encrypt_vaes_avx2)
@@ -871,21 +896,12 @@ SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx2)
_aes_xts_crypt 0
SYM_FUNC_END(aes_xts_decrypt_vaes_avx2)
-.set VL, 32
-.set USE_AVX10, 1
-SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx10_256)
- _aes_xts_crypt 1
-SYM_FUNC_END(aes_xts_encrypt_vaes_avx10_256)
-SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx10_256)
- _aes_xts_crypt 0
-SYM_FUNC_END(aes_xts_decrypt_vaes_avx10_256)
-
.set VL, 64
-.set USE_AVX10, 1
-SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx10_512)
+.set USE_AVX512, 1
+SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx512)
_aes_xts_crypt 1
-SYM_FUNC_END(aes_xts_encrypt_vaes_avx10_512)
-SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx10_512)
+SYM_FUNC_END(aes_xts_encrypt_vaes_avx512)
+SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx512)
_aes_xts_crypt 0
-SYM_FUNC_END(aes_xts_decrypt_vaes_avx10_512)
+SYM_FUNC_END(aes_xts_decrypt_vaes_avx512)
#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c
index bc655d794a95..061b1ced93c5 100644
--- a/arch/x86/crypto/aesni-intel_glue.c
+++ b/arch/x86/crypto/aesni-intel_glue.c
@@ -566,10 +566,9 @@ static struct crypto_alg aesni_cipher_alg = {
static struct skcipher_alg aesni_skciphers[] = {
{
.base = {
- .cra_name = "__ecb(aes)",
- .cra_driver_name = "__ecb-aes-aesni",
+ .cra_name = "ecb(aes)",
+ .cra_driver_name = "ecb-aes-aesni",
.cra_priority = 400,
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = CRYPTO_AES_CTX_SIZE,
.cra_module = THIS_MODULE,
@@ -581,10 +580,9 @@ static struct skcipher_alg aesni_skciphers[] = {
.decrypt = ecb_decrypt,
}, {
.base = {
- .cra_name = "__cbc(aes)",
- .cra_driver_name = "__cbc-aes-aesni",
+ .cra_name = "cbc(aes)",
+ .cra_driver_name = "cbc-aes-aesni",
.cra_priority = 400,
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = CRYPTO_AES_CTX_SIZE,
.cra_module = THIS_MODULE,
@@ -597,10 +595,9 @@ static struct skcipher_alg aesni_skciphers[] = {
.decrypt = cbc_decrypt,
}, {
.base = {
- .cra_name = "__cts(cbc(aes))",
- .cra_driver_name = "__cts-cbc-aes-aesni",
+ .cra_name = "cts(cbc(aes))",
+ .cra_driver_name = "cts-cbc-aes-aesni",
.cra_priority = 400,
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = CRYPTO_AES_CTX_SIZE,
.cra_module = THIS_MODULE,
@@ -615,10 +612,9 @@ static struct skcipher_alg aesni_skciphers[] = {
#ifdef CONFIG_X86_64
}, {
.base = {
- .cra_name = "__ctr(aes)",
- .cra_driver_name = "__ctr-aes-aesni",
+ .cra_name = "ctr(aes)",
+ .cra_driver_name = "ctr-aes-aesni",
.cra_priority = 400,
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = 1,
.cra_ctxsize = CRYPTO_AES_CTX_SIZE,
.cra_module = THIS_MODULE,
@@ -633,10 +629,9 @@ static struct skcipher_alg aesni_skciphers[] = {
#endif
}, {
.base = {
- .cra_name = "__xts(aes)",
- .cra_driver_name = "__xts-aes-aesni",
+ .cra_name = "xts(aes)",
+ .cra_driver_name = "xts-aes-aesni",
.cra_priority = 401,
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = AES_BLOCK_SIZE,
.cra_ctxsize = XTS_AES_CTX_SIZE,
.cra_module = THIS_MODULE,
@@ -651,9 +646,6 @@ static struct skcipher_alg aesni_skciphers[] = {
}
};
-static
-struct simd_skcipher_alg *aesni_simd_skciphers[ARRAY_SIZE(aesni_skciphers)];
-
#ifdef CONFIG_X86_64
asmlinkage void aes_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key,
u8 iv[AES_BLOCK_SIZE]);
@@ -792,10 +784,9 @@ static int xctr_crypt_##suffix(struct skcipher_request *req) \
} \
\
static struct skcipher_alg skcipher_algs_##suffix[] = {{ \
- .base.cra_name = "__xts(aes)", \
- .base.cra_driver_name = "__xts-aes-" driver_name_suffix, \
+ .base.cra_name = "xts(aes)", \
+ .base.cra_driver_name = "xts-aes-" driver_name_suffix, \
.base.cra_priority = priority, \
- .base.cra_flags = CRYPTO_ALG_INTERNAL, \
.base.cra_blocksize = AES_BLOCK_SIZE, \
.base.cra_ctxsize = XTS_AES_CTX_SIZE, \
.base.cra_module = THIS_MODULE, \
@@ -807,10 +798,9 @@ static struct skcipher_alg skcipher_algs_##suffix[] = {{ \
.encrypt = xts_encrypt_##suffix, \
.decrypt = xts_decrypt_##suffix, \
}, { \
- .base.cra_name = "__ctr(aes)", \
- .base.cra_driver_name = "__ctr-aes-" driver_name_suffix, \
+ .base.cra_name = "ctr(aes)", \
+ .base.cra_driver_name = "ctr-aes-" driver_name_suffix, \
.base.cra_priority = priority, \
- .base.cra_flags = CRYPTO_ALG_INTERNAL, \
.base.cra_blocksize = 1, \
.base.cra_ctxsize = CRYPTO_AES_CTX_SIZE, \
.base.cra_module = THIS_MODULE, \
@@ -822,10 +812,9 @@ static struct skcipher_alg skcipher_algs_##suffix[] = {{ \
.encrypt = ctr_crypt_##suffix, \
.decrypt = ctr_crypt_##suffix, \
}, { \
- .base.cra_name = "__xctr(aes)", \
- .base.cra_driver_name = "__xctr-aes-" driver_name_suffix, \
+ .base.cra_name = "xctr(aes)", \
+ .base.cra_driver_name = "xctr-aes-" driver_name_suffix, \
.base.cra_priority = priority, \
- .base.cra_flags = CRYPTO_ALG_INTERNAL, \
.base.cra_blocksize = 1, \
.base.cra_ctxsize = CRYPTO_AES_CTX_SIZE, \
.base.cra_module = THIS_MODULE, \
@@ -836,16 +825,12 @@ static struct skcipher_alg skcipher_algs_##suffix[] = {{ \
.setkey = aesni_skcipher_setkey, \
.encrypt = xctr_crypt_##suffix, \
.decrypt = xctr_crypt_##suffix, \
-}}; \
- \
-static struct simd_skcipher_alg * \
-simd_skcipher_algs_##suffix[ARRAY_SIZE(skcipher_algs_##suffix)]
+}}
DEFINE_AVX_SKCIPHER_ALGS(aesni_avx, "aesni-avx", 500);
#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
DEFINE_AVX_SKCIPHER_ALGS(vaes_avx2, "vaes-avx2", 600);
-DEFINE_AVX_SKCIPHER_ALGS(vaes_avx10_256, "vaes-avx10_256", 700);
-DEFINE_AVX_SKCIPHER_ALGS(vaes_avx10_512, "vaes-avx10_512", 800);
+DEFINE_AVX_SKCIPHER_ALGS(vaes_avx512, "vaes-avx512", 800);
#endif
/* The common part of the x86_64 AES-GCM key struct */
@@ -1499,10 +1484,9 @@ static struct aead_alg aes_gcm_algs_##suffix[] = { { \
.chunksize = AES_BLOCK_SIZE, \
.maxauthsize = 16, \
.base = { \
- .cra_name = "__gcm(aes)", \
- .cra_driver_name = "__" generic_driver_name, \
+ .cra_name = "gcm(aes)", \
+ .cra_driver_name = generic_driver_name, \
.cra_priority = (priority), \
- .cra_flags = CRYPTO_ALG_INTERNAL, \
.cra_blocksize = 1, \
.cra_ctxsize = (ctxsize), \
.cra_module = THIS_MODULE, \
@@ -1516,17 +1500,14 @@ static struct aead_alg aes_gcm_algs_##suffix[] = { { \
.chunksize = AES_BLOCK_SIZE, \
.maxauthsize = 16, \
.base = { \
- .cra_name = "__rfc4106(gcm(aes))", \
- .cra_driver_name = "__" rfc_driver_name, \
+ .cra_name = "rfc4106(gcm(aes))", \
+ .cra_driver_name = rfc_driver_name, \
.cra_priority = (priority), \
- .cra_flags = CRYPTO_ALG_INTERNAL, \
.cra_blocksize = 1, \
.cra_ctxsize = (ctxsize), \
.cra_module = THIS_MODULE, \
}, \
-} }; \
- \
-static struct simd_aead_alg *aes_gcm_simdalgs_##suffix[2] \
+} }
/* aes_gcm_algs_aesni */
DEFINE_GCM_ALGS(aesni, /* no flags */ 0,
@@ -1556,14 +1537,12 @@ static int __init register_avx_algs(void)
if (!boot_cpu_has(X86_FEATURE_AVX))
return 0;
- err = simd_register_skciphers_compat(skcipher_algs_aesni_avx,
- ARRAY_SIZE(skcipher_algs_aesni_avx),
- simd_skcipher_algs_aesni_avx);
+ err = crypto_register_skciphers(skcipher_algs_aesni_avx,
+ ARRAY_SIZE(skcipher_algs_aesni_avx));
if (err)
return err;
- err = simd_register_aeads_compat(aes_gcm_algs_aesni_avx,
- ARRAY_SIZE(aes_gcm_algs_aesni_avx),
- aes_gcm_simdalgs_aesni_avx);
+ err = crypto_register_aeads(aes_gcm_algs_aesni_avx,
+ ARRAY_SIZE(aes_gcm_algs_aesni_avx));
if (err)
return err;
/*
@@ -1579,9 +1558,8 @@ static int __init register_avx_algs(void)
!boot_cpu_has(X86_FEATURE_PCLMULQDQ) ||
!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
return 0;
- err = simd_register_skciphers_compat(skcipher_algs_vaes_avx2,
- ARRAY_SIZE(skcipher_algs_vaes_avx2),
- simd_skcipher_algs_vaes_avx2);
+ err = crypto_register_skciphers(skcipher_algs_vaes_avx2,
+ ARRAY_SIZE(skcipher_algs_vaes_avx2));
if (err)
return err;
@@ -1592,76 +1570,52 @@ static int __init register_avx_algs(void)
XFEATURE_MASK_AVX512, NULL))
return 0;
- err = simd_register_skciphers_compat(skcipher_algs_vaes_avx10_256,
- ARRAY_SIZE(skcipher_algs_vaes_avx10_256),
- simd_skcipher_algs_vaes_avx10_256);
- if (err)
- return err;
- err = simd_register_aeads_compat(aes_gcm_algs_vaes_avx10_256,
- ARRAY_SIZE(aes_gcm_algs_vaes_avx10_256),
- aes_gcm_simdalgs_vaes_avx10_256);
+ err = crypto_register_aeads(aes_gcm_algs_vaes_avx10_256,
+ ARRAY_SIZE(aes_gcm_algs_vaes_avx10_256));
if (err)
return err;
if (boot_cpu_has(X86_FEATURE_PREFER_YMM)) {
int i;
- for (i = 0; i < ARRAY_SIZE(skcipher_algs_vaes_avx10_512); i++)
- skcipher_algs_vaes_avx10_512[i].base.cra_priority = 1;
+ for (i = 0; i < ARRAY_SIZE(skcipher_algs_vaes_avx512); i++)
+ skcipher_algs_vaes_avx512[i].base.cra_priority = 1;
for (i = 0; i < ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512); i++)
aes_gcm_algs_vaes_avx10_512[i].base.cra_priority = 1;
}
- err = simd_register_skciphers_compat(skcipher_algs_vaes_avx10_512,
- ARRAY_SIZE(skcipher_algs_vaes_avx10_512),
- simd_skcipher_algs_vaes_avx10_512);
+ err = crypto_register_skciphers(skcipher_algs_vaes_avx512,
+ ARRAY_SIZE(skcipher_algs_vaes_avx512));
if (err)
return err;
- err = simd_register_aeads_compat(aes_gcm_algs_vaes_avx10_512,
- ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512),
- aes_gcm_simdalgs_vaes_avx10_512);
+ err = crypto_register_aeads(aes_gcm_algs_vaes_avx10_512,
+ ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512));
if (err)
return err;
#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */
return 0;
}
+#define unregister_skciphers(A) \
+ if (refcount_read(&(A)[0].base.cra_refcnt) != 0) \
+ crypto_unregister_skciphers((A), ARRAY_SIZE(A))
+#define unregister_aeads(A) \
+ if (refcount_read(&(A)[0].base.cra_refcnt) != 0) \
+ crypto_unregister_aeads((A), ARRAY_SIZE(A))
+
static void unregister_avx_algs(void)
{
- if (simd_skcipher_algs_aesni_avx[0])
- simd_unregister_skciphers(skcipher_algs_aesni_avx,
- ARRAY_SIZE(skcipher_algs_aesni_avx),
- simd_skcipher_algs_aesni_avx);
- if (aes_gcm_simdalgs_aesni_avx[0])
- simd_unregister_aeads(aes_gcm_algs_aesni_avx,
- ARRAY_SIZE(aes_gcm_algs_aesni_avx),
- aes_gcm_simdalgs_aesni_avx);
+ unregister_skciphers(skcipher_algs_aesni_avx);
+ unregister_aeads(aes_gcm_algs_aesni_avx);
#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ)
- if (simd_skcipher_algs_vaes_avx2[0])
- simd_unregister_skciphers(skcipher_algs_vaes_avx2,
- ARRAY_SIZE(skcipher_algs_vaes_avx2),
- simd_skcipher_algs_vaes_avx2);
- if (simd_skcipher_algs_vaes_avx10_256[0])
- simd_unregister_skciphers(skcipher_algs_vaes_avx10_256,
- ARRAY_SIZE(skcipher_algs_vaes_avx10_256),
- simd_skcipher_algs_vaes_avx10_256);
- if (aes_gcm_simdalgs_vaes_avx10_256[0])
- simd_unregister_aeads(aes_gcm_algs_vaes_avx10_256,
- ARRAY_SIZE(aes_gcm_algs_vaes_avx10_256),
- aes_gcm_simdalgs_vaes_avx10_256);
- if (simd_skcipher_algs_vaes_avx10_512[0])
- simd_unregister_skciphers(skcipher_algs_vaes_avx10_512,
- ARRAY_SIZE(skcipher_algs_vaes_avx10_512),
- simd_skcipher_algs_vaes_avx10_512);
- if (aes_gcm_simdalgs_vaes_avx10_512[0])
- simd_unregister_aeads(aes_gcm_algs_vaes_avx10_512,
- ARRAY_SIZE(aes_gcm_algs_vaes_avx10_512),
- aes_gcm_simdalgs_vaes_avx10_512);
+ unregister_skciphers(skcipher_algs_vaes_avx2);
+ unregister_skciphers(skcipher_algs_vaes_avx512);
+ unregister_aeads(aes_gcm_algs_vaes_avx10_256);
+ unregister_aeads(aes_gcm_algs_vaes_avx10_512);
#endif
}
#else /* CONFIG_X86_64 */
static struct aead_alg aes_gcm_algs_aesni[0];
-static struct simd_aead_alg *aes_gcm_simdalgs_aesni[0];
static int __init register_avx_algs(void)
{
@@ -1690,15 +1644,13 @@ static int __init aesni_init(void)
if (err)
return err;
- err = simd_register_skciphers_compat(aesni_skciphers,
- ARRAY_SIZE(aesni_skciphers),
- aesni_simd_skciphers);
+ err = crypto_register_skciphers(aesni_skciphers,
+ ARRAY_SIZE(aesni_skciphers));
if (err)
goto unregister_cipher;
- err = simd_register_aeads_compat(aes_gcm_algs_aesni,
- ARRAY_SIZE(aes_gcm_algs_aesni),
- aes_gcm_simdalgs_aesni);
+ err = crypto_register_aeads(aes_gcm_algs_aesni,
+ ARRAY_SIZE(aes_gcm_algs_aesni));
if (err)
goto unregister_skciphers;
@@ -1710,12 +1662,11 @@ static int __init aesni_init(void)
unregister_avx:
unregister_avx_algs();
- simd_unregister_aeads(aes_gcm_algs_aesni,
- ARRAY_SIZE(aes_gcm_algs_aesni),
- aes_gcm_simdalgs_aesni);
+ crypto_unregister_aeads(aes_gcm_algs_aesni,
+ ARRAY_SIZE(aes_gcm_algs_aesni));
unregister_skciphers:
- simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
- aesni_simd_skciphers);
+ crypto_unregister_skciphers(aesni_skciphers,
+ ARRAY_SIZE(aesni_skciphers));
unregister_cipher:
crypto_unregister_alg(&aesni_cipher_alg);
return err;
@@ -1723,11 +1674,10 @@ unregister_cipher:
static void __exit aesni_exit(void)
{
- simd_unregister_aeads(aes_gcm_algs_aesni,
- ARRAY_SIZE(aes_gcm_algs_aesni),
- aes_gcm_simdalgs_aesni);
- simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers),
- aesni_simd_skciphers);
+ crypto_unregister_aeads(aes_gcm_algs_aesni,
+ ARRAY_SIZE(aes_gcm_algs_aesni));
+ crypto_unregister_skciphers(aesni_skciphers,
+ ARRAY_SIZE(aesni_skciphers));
crypto_unregister_alg(&aesni_cipher_alg);
unregister_avx_algs();
}
diff --git a/arch/x86/crypto/aria_aesni_avx2_glue.c b/arch/x86/crypto/aria_aesni_avx2_glue.c
index 87a11804fc77..007b250f774c 100644
--- a/arch/x86/crypto/aria_aesni_avx2_glue.c
+++ b/arch/x86/crypto/aria_aesni_avx2_glue.c
@@ -6,10 +6,10 @@
*/
#include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
#include <crypto/aria.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <linux/export.h>
#include <linux/module.h>
#include <linux/types.h>
@@ -165,10 +165,9 @@ static int aria_avx2_init_tfm(struct crypto_skcipher *tfm)
static struct skcipher_alg aria_algs[] = {
{
- .base.cra_name = "__ecb(aria)",
- .base.cra_driver_name = "__ecb-aria-avx2",
+ .base.cra_name = "ecb(aria)",
+ .base.cra_driver_name = "ecb-aria-avx2",
.base.cra_priority = 500,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = ARIA_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct aria_ctx),
.base.cra_module = THIS_MODULE,
@@ -178,11 +177,10 @@ static struct skcipher_alg aria_algs[] = {
.encrypt = aria_avx2_ecb_encrypt,
.decrypt = aria_avx2_ecb_decrypt,
}, {
- .base.cra_name = "__ctr(aria)",
- .base.cra_driver_name = "__ctr-aria-avx2",
+ .base.cra_name = "ctr(aria)",
+ .base.cra_driver_name = "ctr-aria-avx2",
.base.cra_priority = 500,
- .base.cra_flags = CRYPTO_ALG_INTERNAL |
- CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE,
+ .base.cra_flags = CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct aria_ctx),
.base.cra_module = THIS_MODULE,
@@ -197,8 +195,6 @@ static struct skcipher_alg aria_algs[] = {
}
};
-static struct simd_skcipher_alg *aria_simd_algs[ARRAY_SIZE(aria_algs)];
-
static int __init aria_avx2_init(void)
{
const char *feature_name;
@@ -233,15 +229,12 @@ static int __init aria_avx2_init(void)
aria_ops.aria_ctr_crypt_32way = aria_aesni_avx2_ctr_crypt_32way;
}
- return simd_register_skciphers_compat(aria_algs,
- ARRAY_SIZE(aria_algs),
- aria_simd_algs);
+ return crypto_register_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
}
static void __exit aria_avx2_exit(void)
{
- simd_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs),
- aria_simd_algs);
+ crypto_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
}
module_init(aria_avx2_init);
diff --git a/arch/x86/crypto/aria_aesni_avx_glue.c b/arch/x86/crypto/aria_aesni_avx_glue.c
index 4e1516b76669..4c88ef4eba82 100644
--- a/arch/x86/crypto/aria_aesni_avx_glue.c
+++ b/arch/x86/crypto/aria_aesni_avx_glue.c
@@ -6,10 +6,10 @@
*/
#include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
#include <crypto/aria.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <linux/export.h>
#include <linux/module.h>
#include <linux/types.h>
@@ -152,10 +152,9 @@ static int aria_avx_init_tfm(struct crypto_skcipher *tfm)
static struct skcipher_alg aria_algs[] = {
{
- .base.cra_name = "__ecb(aria)",
- .base.cra_driver_name = "__ecb-aria-avx",
+ .base.cra_name = "ecb(aria)",
+ .base.cra_driver_name = "ecb-aria-avx",
.base.cra_priority = 400,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = ARIA_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct aria_ctx),
.base.cra_module = THIS_MODULE,
@@ -165,10 +164,9 @@ static struct skcipher_alg aria_algs[] = {
.encrypt = aria_avx_ecb_encrypt,
.decrypt = aria_avx_ecb_decrypt,
}, {
- .base.cra_name = "__ctr(aria)",
- .base.cra_driver_name = "__ctr-aria-avx",
+ .base.cra_name = "ctr(aria)",
+ .base.cra_driver_name = "ctr-aria-avx",
.base.cra_priority = 400,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct aria_ctx),
.base.cra_module = THIS_MODULE,
@@ -184,8 +182,6 @@ static struct skcipher_alg aria_algs[] = {
}
};
-static struct simd_skcipher_alg *aria_simd_algs[ARRAY_SIZE(aria_algs)];
-
static int __init aria_avx_init(void)
{
const char *feature_name;
@@ -213,15 +209,12 @@ static int __init aria_avx_init(void)
aria_ops.aria_ctr_crypt_16way = aria_aesni_avx_ctr_crypt_16way;
}
- return simd_register_skciphers_compat(aria_algs,
- ARRAY_SIZE(aria_algs),
- aria_simd_algs);
+ return crypto_register_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
}
static void __exit aria_avx_exit(void)
{
- simd_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs),
- aria_simd_algs);
+ crypto_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
}
module_init(aria_avx_init);
diff --git a/arch/x86/crypto/aria_gfni_avx512_glue.c b/arch/x86/crypto/aria_gfni_avx512_glue.c
index f4a2208d2638..363cbf4399cc 100644
--- a/arch/x86/crypto/aria_gfni_avx512_glue.c
+++ b/arch/x86/crypto/aria_gfni_avx512_glue.c
@@ -6,7 +6,6 @@
*/
#include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
#include <crypto/aria.h>
#include <linux/crypto.h>
#include <linux/err.h>
@@ -165,10 +164,9 @@ static int aria_avx512_init_tfm(struct crypto_skcipher *tfm)
static struct skcipher_alg aria_algs[] = {
{
- .base.cra_name = "__ecb(aria)",
- .base.cra_driver_name = "__ecb-aria-avx512",
+ .base.cra_name = "ecb(aria)",
+ .base.cra_driver_name = "ecb-aria-avx512",
.base.cra_priority = 600,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = ARIA_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct aria_ctx),
.base.cra_module = THIS_MODULE,
@@ -178,11 +176,10 @@ static struct skcipher_alg aria_algs[] = {
.encrypt = aria_avx512_ecb_encrypt,
.decrypt = aria_avx512_ecb_decrypt,
}, {
- .base.cra_name = "__ctr(aria)",
- .base.cra_driver_name = "__ctr-aria-avx512",
+ .base.cra_name = "ctr(aria)",
+ .base.cra_driver_name = "ctr-aria-avx512",
.base.cra_priority = 600,
- .base.cra_flags = CRYPTO_ALG_INTERNAL |
- CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE,
+ .base.cra_flags = CRYPTO_ALG_SKCIPHER_REQSIZE_LARGE,
.base.cra_blocksize = 1,
.base.cra_ctxsize = sizeof(struct aria_ctx),
.base.cra_module = THIS_MODULE,
@@ -197,8 +194,6 @@ static struct skcipher_alg aria_algs[] = {
}
};
-static struct simd_skcipher_alg *aria_simd_algs[ARRAY_SIZE(aria_algs)];
-
static int __init aria_avx512_init(void)
{
const char *feature_name;
@@ -229,15 +224,12 @@ static int __init aria_avx512_init(void)
aria_ops.aria_decrypt_64way = aria_gfni_avx512_decrypt_64way;
aria_ops.aria_ctr_crypt_64way = aria_gfni_avx512_ctr_crypt_64way;
- return simd_register_skciphers_compat(aria_algs,
- ARRAY_SIZE(aria_algs),
- aria_simd_algs);
+ return crypto_register_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
}
static void __exit aria_avx512_exit(void)
{
- simd_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs),
- aria_simd_algs);
+ crypto_unregister_skciphers(aria_algs, ARRAY_SIZE(aria_algs));
}
module_init(aria_avx512_init);
diff --git a/arch/x86/crypto/blake2s-core.S b/arch/x86/crypto/blake2s-core.S
deleted file mode 100644
index b50b35ff1fdb..000000000000
--- a/arch/x86/crypto/blake2s-core.S
+++ /dev/null
@@ -1,256 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 OR MIT */
-/*
- * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- * Copyright (C) 2017-2019 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved.
- */
-
-#include <linux/linkage.h>
-
-.section .rodata.cst32.BLAKE2S_IV, "aM", @progbits, 32
-.align 32
-IV: .octa 0xA54FF53A3C6EF372BB67AE856A09E667
- .octa 0x5BE0CD191F83D9AB9B05688C510E527F
-.section .rodata.cst16.ROT16, "aM", @progbits, 16
-.align 16
-ROT16: .octa 0x0D0C0F0E09080B0A0504070601000302
-.section .rodata.cst16.ROR328, "aM", @progbits, 16
-.align 16
-ROR328: .octa 0x0C0F0E0D080B0A090407060500030201
-.section .rodata.cst64.BLAKE2S_SIGMA, "aM", @progbits, 160
-.align 64
-SIGMA:
-.byte 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13
-.byte 14, 4, 9, 13, 10, 8, 15, 6, 5, 1, 0, 11, 3, 12, 2, 7
-.byte 11, 12, 5, 15, 8, 0, 2, 13, 9, 10, 3, 7, 4, 14, 6, 1
-.byte 7, 3, 13, 11, 9, 1, 12, 14, 15, 2, 5, 4, 8, 6, 10, 0
-.byte 9, 5, 2, 10, 0, 7, 4, 15, 3, 14, 11, 6, 13, 1, 12, 8
-.byte 2, 6, 0, 8, 12, 10, 11, 3, 1, 4, 7, 15, 9, 13, 5, 14
-.byte 12, 1, 14, 4, 5, 15, 13, 10, 8, 0, 6, 9, 11, 7, 3, 2
-.byte 13, 7, 12, 3, 11, 14, 1, 9, 2, 5, 15, 8, 10, 0, 4, 6
-.byte 6, 14, 11, 0, 15, 9, 3, 8, 10, 12, 13, 1, 5, 2, 7, 4
-.byte 10, 8, 7, 1, 2, 4, 6, 5, 13, 15, 9, 3, 0, 11, 14, 12
-#ifdef CONFIG_AS_AVX512
-.section .rodata.cst64.BLAKE2S_SIGMA2, "aM", @progbits, 640
-.align 64
-SIGMA2:
-.long 0, 2, 4, 6, 1, 3, 5, 7, 14, 8, 10, 12, 15, 9, 11, 13
-.long 8, 2, 13, 15, 10, 9, 12, 3, 6, 4, 0, 14, 5, 11, 1, 7
-.long 11, 13, 8, 6, 5, 10, 14, 3, 2, 4, 12, 15, 1, 0, 7, 9
-.long 11, 10, 7, 0, 8, 15, 1, 13, 3, 6, 2, 12, 4, 14, 9, 5
-.long 4, 10, 9, 14, 15, 0, 11, 8, 1, 7, 3, 13, 2, 5, 6, 12
-.long 2, 11, 4, 15, 14, 3, 10, 8, 13, 6, 5, 7, 0, 12, 1, 9
-.long 4, 8, 15, 9, 14, 11, 13, 5, 3, 2, 1, 12, 6, 10, 7, 0
-.long 6, 13, 0, 14, 12, 2, 1, 11, 15, 4, 5, 8, 7, 9, 3, 10
-.long 15, 5, 4, 13, 10, 7, 3, 11, 12, 2, 0, 6, 9, 8, 1, 14
-.long 8, 7, 14, 11, 13, 15, 0, 12, 10, 4, 5, 6, 3, 2, 1, 9
-#endif /* CONFIG_AS_AVX512 */
-
-.text
-SYM_FUNC_START(blake2s_compress_ssse3)
- testq %rdx,%rdx
- je .Lendofloop
- movdqu (%rdi),%xmm0
- movdqu 0x10(%rdi),%xmm1
- movdqa ROT16(%rip),%xmm12
- movdqa ROR328(%rip),%xmm13
- movdqu 0x20(%rdi),%xmm14
- movq %rcx,%xmm15
- leaq SIGMA+0xa0(%rip),%r8
- jmp .Lbeginofloop
- .align 32
-.Lbeginofloop:
- movdqa %xmm0,%xmm10
- movdqa %xmm1,%xmm11
- paddq %xmm15,%xmm14
- movdqa IV(%rip),%xmm2
- movdqa %xmm14,%xmm3
- pxor IV+0x10(%rip),%xmm3
- leaq SIGMA(%rip),%rcx
-.Lroundloop:
- movzbl (%rcx),%eax
- movd (%rsi,%rax,4),%xmm4
- movzbl 0x1(%rcx),%eax
- movd (%rsi,%rax,4),%xmm5
- movzbl 0x2(%rcx),%eax
- movd (%rsi,%rax,4),%xmm6
- movzbl 0x3(%rcx),%eax
- movd (%rsi,%rax,4),%xmm7
- punpckldq %xmm5,%xmm4
- punpckldq %xmm7,%xmm6
- punpcklqdq %xmm6,%xmm4
- paddd %xmm4,%xmm0
- paddd %xmm1,%xmm0
- pxor %xmm0,%xmm3
- pshufb %xmm12,%xmm3
- paddd %xmm3,%xmm2
- pxor %xmm2,%xmm1
- movdqa %xmm1,%xmm8
- psrld $0xc,%xmm1
- pslld $0x14,%xmm8
- por %xmm8,%xmm1
- movzbl 0x4(%rcx),%eax
- movd (%rsi,%rax,4),%xmm5
- movzbl 0x5(%rcx),%eax
- movd (%rsi,%rax,4),%xmm6
- movzbl 0x6(%rcx),%eax
- movd (%rsi,%rax,4),%xmm7
- movzbl 0x7(%rcx),%eax
- movd (%rsi,%rax,4),%xmm4
- punpckldq %xmm6,%xmm5
- punpckldq %xmm4,%xmm7
- punpcklqdq %xmm7,%xmm5
- paddd %xmm5,%xmm0
- paddd %xmm1,%xmm0
- pxor %xmm0,%xmm3
- pshufb %xmm13,%xmm3
- paddd %xmm3,%xmm2
- pxor %xmm2,%xmm1
- movdqa %xmm1,%xmm8
- psrld $0x7,%xmm1
- pslld $0x19,%xmm8
- por %xmm8,%xmm1
- pshufd $0x93,%xmm0,%xmm0
- pshufd $0x4e,%xmm3,%xmm3
- pshufd $0x39,%xmm2,%xmm2
- movzbl 0x8(%rcx),%eax
- movd (%rsi,%rax,4),%xmm6
- movzbl 0x9(%rcx),%eax
- movd (%rsi,%rax,4),%xmm7
- movzbl 0xa(%rcx),%eax
- movd (%rsi,%rax,4),%xmm4
- movzbl 0xb(%rcx),%eax
- movd (%rsi,%rax,4),%xmm5
- punpckldq %xmm7,%xmm6
- punpckldq %xmm5,%xmm4
- punpcklqdq %xmm4,%xmm6
- paddd %xmm6,%xmm0
- paddd %xmm1,%xmm0
- pxor %xmm0,%xmm3
- pshufb %xmm12,%xmm3
- paddd %xmm3,%xmm2
- pxor %xmm2,%xmm1
- movdqa %xmm1,%xmm8
- psrld $0xc,%xmm1
- pslld $0x14,%xmm8
- por %xmm8,%xmm1
- movzbl 0xc(%rcx),%eax
- movd (%rsi,%rax,4),%xmm7
- movzbl 0xd(%rcx),%eax
- movd (%rsi,%rax,4),%xmm4
- movzbl 0xe(%rcx),%eax
- movd (%rsi,%rax,4),%xmm5
- movzbl 0xf(%rcx),%eax
- movd (%rsi,%rax,4),%xmm6
- punpckldq %xmm4,%xmm7
- punpckldq %xmm6,%xmm5
- punpcklqdq %xmm5,%xmm7
- paddd %xmm7,%xmm0
- paddd %xmm1,%xmm0
- pxor %xmm0,%xmm3
- pshufb %xmm13,%xmm3
- paddd %xmm3,%xmm2
- pxor %xmm2,%xmm1
- movdqa %xmm1,%xmm8
- psrld $0x7,%xmm1
- pslld $0x19,%xmm8
- por %xmm8,%xmm1
- pshufd $0x39,%xmm0,%xmm0
- pshufd $0x4e,%xmm3,%xmm3
- pshufd $0x93,%xmm2,%xmm2
- addq $0x10,%rcx
- cmpq %r8,%rcx
- jnz .Lroundloop
- pxor %xmm2,%xmm0
- pxor %xmm3,%xmm1
- pxor %xmm10,%xmm0
- pxor %xmm11,%xmm1
- addq $0x40,%rsi
- decq %rdx
- jnz .Lbeginofloop
- movdqu %xmm0,(%rdi)
- movdqu %xmm1,0x10(%rdi)
- movdqu %xmm14,0x20(%rdi)
-.Lendofloop:
- RET
-SYM_FUNC_END(blake2s_compress_ssse3)
-
-#ifdef CONFIG_AS_AVX512
-SYM_FUNC_START(blake2s_compress_avx512)
- vmovdqu (%rdi),%xmm0
- vmovdqu 0x10(%rdi),%xmm1
- vmovdqu 0x20(%rdi),%xmm4
- vmovq %rcx,%xmm5
- vmovdqa IV(%rip),%xmm14
- vmovdqa IV+16(%rip),%xmm15
- jmp .Lblake2s_compress_avx512_mainloop
-.align 32
-.Lblake2s_compress_avx512_mainloop:
- vmovdqa %xmm0,%xmm10
- vmovdqa %xmm1,%xmm11
- vpaddq %xmm5,%xmm4,%xmm4
- vmovdqa %xmm14,%xmm2
- vpxor %xmm15,%xmm4,%xmm3
- vmovdqu (%rsi),%ymm6
- vmovdqu 0x20(%rsi),%ymm7
- addq $0x40,%rsi
- leaq SIGMA2(%rip),%rax
- movb $0xa,%cl
-.Lblake2s_compress_avx512_roundloop:
- addq $0x40,%rax
- vmovdqa -0x40(%rax),%ymm8
- vmovdqa -0x20(%rax),%ymm9
- vpermi2d %ymm7,%ymm6,%ymm8
- vpermi2d %ymm7,%ymm6,%ymm9
- vmovdqa %ymm8,%ymm6
- vmovdqa %ymm9,%ymm7
- vpaddd %xmm8,%xmm0,%xmm0
- vpaddd %xmm1,%xmm0,%xmm0
- vpxor %xmm0,%xmm3,%xmm3
- vprord $0x10,%xmm3,%xmm3
- vpaddd %xmm3,%xmm2,%xmm2
- vpxor %xmm2,%xmm1,%xmm1
- vprord $0xc,%xmm1,%xmm1
- vextracti128 $0x1,%ymm8,%xmm8
- vpaddd %xmm8,%xmm0,%xmm0
- vpaddd %xmm1,%xmm0,%xmm0
- vpxor %xmm0,%xmm3,%xmm3
- vprord $0x8,%xmm3,%xmm3
- vpaddd %xmm3,%xmm2,%xmm2
- vpxor %xmm2,%xmm1,%xmm1
- vprord $0x7,%xmm1,%xmm1
- vpshufd $0x93,%xmm0,%xmm0
- vpshufd $0x4e,%xmm3,%xmm3
- vpshufd $0x39,%xmm2,%xmm2
- vpaddd %xmm9,%xmm0,%xmm0
- vpaddd %xmm1,%xmm0,%xmm0
- vpxor %xmm0,%xmm3,%xmm3
- vprord $0x10,%xmm3,%xmm3
- vpaddd %xmm3,%xmm2,%xmm2
- vpxor %xmm2,%xmm1,%xmm1
- vprord $0xc,%xmm1,%xmm1
- vextracti128 $0x1,%ymm9,%xmm9
- vpaddd %xmm9,%xmm0,%xmm0
- vpaddd %xmm1,%xmm0,%xmm0
- vpxor %xmm0,%xmm3,%xmm3
- vprord $0x8,%xmm3,%xmm3
- vpaddd %xmm3,%xmm2,%xmm2
- vpxor %xmm2,%xmm1,%xmm1
- vprord $0x7,%xmm1,%xmm1
- vpshufd $0x39,%xmm0,%xmm0
- vpshufd $0x4e,%xmm3,%xmm3
- vpshufd $0x93,%xmm2,%xmm2
- decb %cl
- jne .Lblake2s_compress_avx512_roundloop
- vpxor %xmm10,%xmm0,%xmm0
- vpxor %xmm11,%xmm1,%xmm1
- vpxor %xmm2,%xmm0,%xmm0
- vpxor %xmm3,%xmm1,%xmm1
- decq %rdx
- jne .Lblake2s_compress_avx512_mainloop
- vmovdqu %xmm0,(%rdi)
- vmovdqu %xmm1,0x10(%rdi)
- vmovdqu %xmm4,0x20(%rdi)
- vzeroupper
- RET
-SYM_FUNC_END(blake2s_compress_avx512)
-#endif /* CONFIG_AS_AVX512 */
diff --git a/arch/x86/crypto/blake2s-glue.c b/arch/x86/crypto/blake2s-glue.c
deleted file mode 100644
index 0313f9673f56..000000000000
--- a/arch/x86/crypto/blake2s-glue.c
+++ /dev/null
@@ -1,74 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR MIT
-/*
- * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- */
-
-#include <crypto/internal/blake2s.h>
-
-#include <linux/types.h>
-#include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/sizes.h>
-
-#include <asm/cpufeature.h>
-#include <asm/fpu/api.h>
-#include <asm/processor.h>
-#include <asm/simd.h>
-
-asmlinkage void blake2s_compress_ssse3(struct blake2s_state *state,
- const u8 *block, const size_t nblocks,
- const u32 inc);
-asmlinkage void blake2s_compress_avx512(struct blake2s_state *state,
- const u8 *block, const size_t nblocks,
- const u32 inc);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_ssse3);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(blake2s_use_avx512);
-
-void blake2s_compress(struct blake2s_state *state, const u8 *block,
- size_t nblocks, const u32 inc)
-{
- /* SIMD disables preemption, so relax after processing each page. */
- BUILD_BUG_ON(SZ_4K / BLAKE2S_BLOCK_SIZE < 8);
-
- if (!static_branch_likely(&blake2s_use_ssse3) || !may_use_simd()) {
- blake2s_compress_generic(state, block, nblocks, inc);
- return;
- }
-
- do {
- const size_t blocks = min_t(size_t, nblocks,
- SZ_4K / BLAKE2S_BLOCK_SIZE);
-
- kernel_fpu_begin();
- if (IS_ENABLED(CONFIG_AS_AVX512) &&
- static_branch_likely(&blake2s_use_avx512))
- blake2s_compress_avx512(state, block, blocks, inc);
- else
- blake2s_compress_ssse3(state, block, blocks, inc);
- kernel_fpu_end();
-
- nblocks -= blocks;
- block += blocks * BLAKE2S_BLOCK_SIZE;
- } while (nblocks);
-}
-EXPORT_SYMBOL(blake2s_compress);
-
-static int __init blake2s_mod_init(void)
-{
- if (boot_cpu_has(X86_FEATURE_SSSE3))
- static_branch_enable(&blake2s_use_ssse3);
-
- if (IS_ENABLED(CONFIG_AS_AVX512) &&
- boot_cpu_has(X86_FEATURE_AVX) &&
- boot_cpu_has(X86_FEATURE_AVX2) &&
- boot_cpu_has(X86_FEATURE_AVX512F) &&
- boot_cpu_has(X86_FEATURE_AVX512VL) &&
- cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM |
- XFEATURE_MASK_AVX512, NULL))
- static_branch_enable(&blake2s_use_avx512);
-
- return 0;
-}
-
-subsys_initcall(blake2s_mod_init);
diff --git a/arch/x86/crypto/camellia_aesni_avx2_glue.c b/arch/x86/crypto/camellia_aesni_avx2_glue.c
index e7e4d64e9577..2d2f4e16537c 100644
--- a/arch/x86/crypto/camellia_aesni_avx2_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx2_glue.c
@@ -6,7 +6,6 @@
*/
#include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
#include <linux/crypto.h>
#include <linux/err.h>
#include <linux/module.h>
@@ -69,10 +68,9 @@ static int cbc_decrypt(struct skcipher_request *req)
static struct skcipher_alg camellia_algs[] = {
{
- .base.cra_name = "__ecb(camellia)",
- .base.cra_driver_name = "__ecb-camellia-aesni-avx2",
+ .base.cra_name = "ecb(camellia)",
+ .base.cra_driver_name = "ecb-camellia-aesni-avx2",
.base.cra_priority = 500,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = CAMELLIA_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct camellia_ctx),
.base.cra_module = THIS_MODULE,
@@ -82,10 +80,9 @@ static struct skcipher_alg camellia_algs[] = {
.encrypt = ecb_encrypt,
.decrypt = ecb_decrypt,
}, {
- .base.cra_name = "__cbc(camellia)",
- .base.cra_driver_name = "__cbc-camellia-aesni-avx2",
+ .base.cra_name = "cbc(camellia)",
+ .base.cra_driver_name = "cbc-camellia-aesni-avx2",
.base.cra_priority = 500,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = CAMELLIA_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct camellia_ctx),
.base.cra_module = THIS_MODULE,
@@ -98,8 +95,6 @@ static struct skcipher_alg camellia_algs[] = {
},
};
-static struct simd_skcipher_alg *camellia_simd_algs[ARRAY_SIZE(camellia_algs)];
-
static int __init camellia_aesni_init(void)
{
const char *feature_name;
@@ -118,15 +113,13 @@ static int __init camellia_aesni_init(void)
return -ENODEV;
}
- return simd_register_skciphers_compat(camellia_algs,
- ARRAY_SIZE(camellia_algs),
- camellia_simd_algs);
+ return crypto_register_skciphers(camellia_algs,
+ ARRAY_SIZE(camellia_algs));
}
static void __exit camellia_aesni_fini(void)
{
- simd_unregister_skciphers(camellia_algs, ARRAY_SIZE(camellia_algs),
- camellia_simd_algs);
+ crypto_unregister_skciphers(camellia_algs, ARRAY_SIZE(camellia_algs));
}
module_init(camellia_aesni_init);
diff --git a/arch/x86/crypto/camellia_aesni_avx_glue.c b/arch/x86/crypto/camellia_aesni_avx_glue.c
index c7ccf63e741e..5c321f255eb7 100644
--- a/arch/x86/crypto/camellia_aesni_avx_glue.c
+++ b/arch/x86/crypto/camellia_aesni_avx_glue.c
@@ -6,9 +6,9 @@
*/
#include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <linux/export.h>
#include <linux/module.h>
#include <linux/types.h>
@@ -69,10 +69,9 @@ static int cbc_decrypt(struct skcipher_request *req)
static struct skcipher_alg camellia_algs[] = {
{
- .base.cra_name = "__ecb(camellia)",
- .base.cra_driver_name = "__ecb-camellia-aesni",
+ .base.cra_name = "ecb(camellia)",
+ .base.cra_driver_name = "ecb-camellia-aesni",
.base.cra_priority = 400,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = CAMELLIA_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct camellia_ctx),
.base.cra_module = THIS_MODULE,
@@ -82,10 +81,9 @@ static struct skcipher_alg camellia_algs[] = {
.encrypt = ecb_encrypt,
.decrypt = ecb_decrypt,
}, {
- .base.cra_name = "__cbc(camellia)",
- .base.cra_driver_name = "__cbc-camellia-aesni",
+ .base.cra_name = "cbc(camellia)",
+ .base.cra_driver_name = "cbc-camellia-aesni",
.base.cra_priority = 400,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = CAMELLIA_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct camellia_ctx),
.base.cra_module = THIS_MODULE,
@@ -98,8 +96,6 @@ static struct skcipher_alg camellia_algs[] = {
}
};
-static struct simd_skcipher_alg *camellia_simd_algs[ARRAY_SIZE(camellia_algs)];
-
static int __init camellia_aesni_init(void)
{
const char *feature_name;
@@ -117,15 +113,13 @@ static int __init camellia_aesni_init(void)
return -ENODEV;
}
- return simd_register_skciphers_compat(camellia_algs,
- ARRAY_SIZE(camellia_algs),
- camellia_simd_algs);
+ return crypto_register_skciphers(camellia_algs,
+ ARRAY_SIZE(camellia_algs));
}
static void __exit camellia_aesni_fini(void)
{
- simd_unregister_skciphers(camellia_algs, ARRAY_SIZE(camellia_algs),
- camellia_simd_algs);
+ crypto_unregister_skciphers(camellia_algs, ARRAY_SIZE(camellia_algs));
}
module_init(camellia_aesni_init);
diff --git a/arch/x86/crypto/camellia_glue.c b/arch/x86/crypto/camellia_glue.c
index 3bd37d664121..cbede120e5f2 100644
--- a/arch/x86/crypto/camellia_glue.c
+++ b/arch/x86/crypto/camellia_glue.c
@@ -10,6 +10,7 @@
#include <linux/unaligned.h>
#include <linux/crypto.h>
+#include <linux/export.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/types.h>
diff --git a/arch/x86/crypto/cast5_avx_glue.c b/arch/x86/crypto/cast5_avx_glue.c
index 3976a87f92ad..3aca04d43b34 100644
--- a/arch/x86/crypto/cast5_avx_glue.c
+++ b/arch/x86/crypto/cast5_avx_glue.c
@@ -8,7 +8,6 @@
#include <crypto/algapi.h>
#include <crypto/cast5.h>
-#include <crypto/internal/simd.h>
#include <linux/crypto.h>
#include <linux/err.h>
#include <linux/module.h>
@@ -64,10 +63,9 @@ static int cbc_decrypt(struct skcipher_request *req)
static struct skcipher_alg cast5_algs[] = {
{
- .base.cra_name = "__ecb(cast5)",
- .base.cra_driver_name = "__ecb-cast5-avx",
+ .base.cra_name = "ecb(cast5)",
+ .base.cra_driver_name = "ecb-cast5-avx",
.base.cra_priority = 200,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = CAST5_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct cast5_ctx),
.base.cra_module = THIS_MODULE,
@@ -77,10 +75,9 @@ static struct skcipher_alg cast5_algs[] = {
.encrypt = ecb_encrypt,
.decrypt = ecb_decrypt,
}, {
- .base.cra_name = "__cbc(cast5)",
- .base.cra_driver_name = "__cbc-cast5-avx",
+ .base.cra_name = "cbc(cast5)",
+ .base.cra_driver_name = "cbc-cast5-avx",
.base.cra_priority = 200,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = CAST5_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct cast5_ctx),
.base.cra_module = THIS_MODULE,
@@ -93,8 +90,6 @@ static struct skcipher_alg cast5_algs[] = {
}
};
-static struct simd_skcipher_alg *cast5_simd_algs[ARRAY_SIZE(cast5_algs)];
-
static int __init cast5_init(void)
{
const char *feature_name;
@@ -105,15 +100,13 @@ static int __init cast5_init(void)
return -ENODEV;
}
- return simd_register_skciphers_compat(cast5_algs,
- ARRAY_SIZE(cast5_algs),
- cast5_simd_algs);
+ return crypto_register_skciphers(cast5_algs,
+ ARRAY_SIZE(cast5_algs));
}
static void __exit cast5_exit(void)
{
- simd_unregister_skciphers(cast5_algs, ARRAY_SIZE(cast5_algs),
- cast5_simd_algs);
+ crypto_unregister_skciphers(cast5_algs, ARRAY_SIZE(cast5_algs));
}
module_init(cast5_init);
diff --git a/arch/x86/crypto/cast6_avx_glue.c b/arch/x86/crypto/cast6_avx_glue.c
index 7e2aea372349..c4dd28c30303 100644
--- a/arch/x86/crypto/cast6_avx_glue.c
+++ b/arch/x86/crypto/cast6_avx_glue.c
@@ -14,7 +14,6 @@
#include <linux/err.h>
#include <crypto/algapi.h>
#include <crypto/cast6.h>
-#include <crypto/internal/simd.h>
#include "ecb_cbc_helpers.h"
@@ -64,10 +63,9 @@ static int cbc_decrypt(struct skcipher_request *req)
static struct skcipher_alg cast6_algs[] = {
{
- .base.cra_name = "__ecb(cast6)",
- .base.cra_driver_name = "__ecb-cast6-avx",
+ .base.cra_name = "ecb(cast6)",
+ .base.cra_driver_name = "ecb-cast6-avx",
.base.cra_priority = 200,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = CAST6_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct cast6_ctx),
.base.cra_module = THIS_MODULE,
@@ -77,10 +75,9 @@ static struct skcipher_alg cast6_algs[] = {
.encrypt = ecb_encrypt,
.decrypt = ecb_decrypt,
}, {
- .base.cra_name = "__cbc(cast6)",
- .base.cra_driver_name = "__cbc-cast6-avx",
+ .base.cra_name = "cbc(cast6)",
+ .base.cra_driver_name = "cbc-cast6-avx",
.base.cra_priority = 200,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = CAST6_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct cast6_ctx),
.base.cra_module = THIS_MODULE,
@@ -93,8 +90,6 @@ static struct skcipher_alg cast6_algs[] = {
},
};
-static struct simd_skcipher_alg *cast6_simd_algs[ARRAY_SIZE(cast6_algs)];
-
static int __init cast6_init(void)
{
const char *feature_name;
@@ -105,15 +100,12 @@ static int __init cast6_init(void)
return -ENODEV;
}
- return simd_register_skciphers_compat(cast6_algs,
- ARRAY_SIZE(cast6_algs),
- cast6_simd_algs);
+ return crypto_register_skciphers(cast6_algs, ARRAY_SIZE(cast6_algs));
}
static void __exit cast6_exit(void)
{
- simd_unregister_skciphers(cast6_algs, ARRAY_SIZE(cast6_algs),
- cast6_simd_algs);
+ crypto_unregister_skciphers(cast6_algs, ARRAY_SIZE(cast6_algs));
}
module_init(cast6_init);
diff --git a/arch/x86/crypto/chacha-avx2-x86_64.S b/arch/x86/crypto/chacha-avx2-x86_64.S
deleted file mode 100644
index f3d8fc018249..000000000000
--- a/arch/x86/crypto/chacha-avx2-x86_64.S
+++ /dev/null
@@ -1,1021 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * ChaCha 256-bit cipher algorithm, x64 AVX2 functions
- *
- * Copyright (C) 2015 Martin Willi
- */
-
-#include <linux/linkage.h>
-
-.section .rodata.cst32.ROT8, "aM", @progbits, 32
-.align 32
-ROT8: .octa 0x0e0d0c0f0a09080b0605040702010003
- .octa 0x0e0d0c0f0a09080b0605040702010003
-
-.section .rodata.cst32.ROT16, "aM", @progbits, 32
-.align 32
-ROT16: .octa 0x0d0c0f0e09080b0a0504070601000302
- .octa 0x0d0c0f0e09080b0a0504070601000302
-
-.section .rodata.cst32.CTRINC, "aM", @progbits, 32
-.align 32
-CTRINC: .octa 0x00000003000000020000000100000000
- .octa 0x00000007000000060000000500000004
-
-.section .rodata.cst32.CTR2BL, "aM", @progbits, 32
-.align 32
-CTR2BL: .octa 0x00000000000000000000000000000000
- .octa 0x00000000000000000000000000000001
-
-.section .rodata.cst32.CTR4BL, "aM", @progbits, 32
-.align 32
-CTR4BL: .octa 0x00000000000000000000000000000002
- .octa 0x00000000000000000000000000000003
-
-.text
-
-SYM_FUNC_START(chacha_2block_xor_avx2)
- # %rdi: Input state matrix, s
- # %rsi: up to 2 data blocks output, o
- # %rdx: up to 2 data blocks input, i
- # %rcx: input/output length in bytes
- # %r8d: nrounds
-
- # This function encrypts two ChaCha blocks by loading the state
- # matrix twice across four AVX registers. It performs matrix operations
- # on four words in each matrix in parallel, but requires shuffling to
- # rearrange the words after each round.
-
- vzeroupper
-
- # x0..3[0-2] = s0..3
- vbroadcasti128 0x00(%rdi),%ymm0
- vbroadcasti128 0x10(%rdi),%ymm1
- vbroadcasti128 0x20(%rdi),%ymm2
- vbroadcasti128 0x30(%rdi),%ymm3
-
- vpaddd CTR2BL(%rip),%ymm3,%ymm3
-
- vmovdqa %ymm0,%ymm8
- vmovdqa %ymm1,%ymm9
- vmovdqa %ymm2,%ymm10
- vmovdqa %ymm3,%ymm11
-
- vmovdqa ROT8(%rip),%ymm4
- vmovdqa ROT16(%rip),%ymm5
-
- mov %rcx,%rax
-
-.Ldoubleround:
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 16)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxor %ymm0,%ymm3,%ymm3
- vpshufb %ymm5,%ymm3,%ymm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 12)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxor %ymm2,%ymm1,%ymm1
- vmovdqa %ymm1,%ymm6
- vpslld $12,%ymm6,%ymm6
- vpsrld $20,%ymm1,%ymm1
- vpor %ymm6,%ymm1,%ymm1
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 8)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxor %ymm0,%ymm3,%ymm3
- vpshufb %ymm4,%ymm3,%ymm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 7)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxor %ymm2,%ymm1,%ymm1
- vmovdqa %ymm1,%ymm7
- vpslld $7,%ymm7,%ymm7
- vpsrld $25,%ymm1,%ymm1
- vpor %ymm7,%ymm1,%ymm1
-
- # x1 = shuffle32(x1, MASK(0, 3, 2, 1))
- vpshufd $0x39,%ymm1,%ymm1
- # x2 = shuffle32(x2, MASK(1, 0, 3, 2))
- vpshufd $0x4e,%ymm2,%ymm2
- # x3 = shuffle32(x3, MASK(2, 1, 0, 3))
- vpshufd $0x93,%ymm3,%ymm3
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 16)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxor %ymm0,%ymm3,%ymm3
- vpshufb %ymm5,%ymm3,%ymm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 12)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxor %ymm2,%ymm1,%ymm1
- vmovdqa %ymm1,%ymm6
- vpslld $12,%ymm6,%ymm6
- vpsrld $20,%ymm1,%ymm1
- vpor %ymm6,%ymm1,%ymm1
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 8)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxor %ymm0,%ymm3,%ymm3
- vpshufb %ymm4,%ymm3,%ymm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 7)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxor %ymm2,%ymm1,%ymm1
- vmovdqa %ymm1,%ymm7
- vpslld $7,%ymm7,%ymm7
- vpsrld $25,%ymm1,%ymm1
- vpor %ymm7,%ymm1,%ymm1
-
- # x1 = shuffle32(x1, MASK(2, 1, 0, 3))
- vpshufd $0x93,%ymm1,%ymm1
- # x2 = shuffle32(x2, MASK(1, 0, 3, 2))
- vpshufd $0x4e,%ymm2,%ymm2
- # x3 = shuffle32(x3, MASK(0, 3, 2, 1))
- vpshufd $0x39,%ymm3,%ymm3
-
- sub $2,%r8d
- jnz .Ldoubleround
-
- # o0 = i0 ^ (x0 + s0)
- vpaddd %ymm8,%ymm0,%ymm7
- cmp $0x10,%rax
- jl .Lxorpart2
- vpxor 0x00(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x00(%rsi)
- vextracti128 $1,%ymm7,%xmm0
- # o1 = i1 ^ (x1 + s1)
- vpaddd %ymm9,%ymm1,%ymm7
- cmp $0x20,%rax
- jl .Lxorpart2
- vpxor 0x10(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x10(%rsi)
- vextracti128 $1,%ymm7,%xmm1
- # o2 = i2 ^ (x2 + s2)
- vpaddd %ymm10,%ymm2,%ymm7
- cmp $0x30,%rax
- jl .Lxorpart2
- vpxor 0x20(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x20(%rsi)
- vextracti128 $1,%ymm7,%xmm2
- # o3 = i3 ^ (x3 + s3)
- vpaddd %ymm11,%ymm3,%ymm7
- cmp $0x40,%rax
- jl .Lxorpart2
- vpxor 0x30(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x30(%rsi)
- vextracti128 $1,%ymm7,%xmm3
-
- # xor and write second block
- vmovdqa %xmm0,%xmm7
- cmp $0x50,%rax
- jl .Lxorpart2
- vpxor 0x40(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x40(%rsi)
-
- vmovdqa %xmm1,%xmm7
- cmp $0x60,%rax
- jl .Lxorpart2
- vpxor 0x50(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x50(%rsi)
-
- vmovdqa %xmm2,%xmm7
- cmp $0x70,%rax
- jl .Lxorpart2
- vpxor 0x60(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x60(%rsi)
-
- vmovdqa %xmm3,%xmm7
- cmp $0x80,%rax
- jl .Lxorpart2
- vpxor 0x70(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x70(%rsi)
-
-.Ldone2:
- vzeroupper
- RET
-
-.Lxorpart2:
- # xor remaining bytes from partial register into output
- mov %rax,%r9
- and $0x0f,%r9
- jz .Ldone2
- and $~0x0f,%rax
-
- mov %rsi,%r11
-
- lea 8(%rsp),%r10
- sub $0x10,%rsp
- and $~31,%rsp
-
- lea (%rdx,%rax),%rsi
- mov %rsp,%rdi
- mov %r9,%rcx
- rep movsb
-
- vpxor 0x00(%rsp),%xmm7,%xmm7
- vmovdqa %xmm7,0x00(%rsp)
-
- mov %rsp,%rsi
- lea (%r11,%rax),%rdi
- mov %r9,%rcx
- rep movsb
-
- lea -8(%r10),%rsp
- jmp .Ldone2
-
-SYM_FUNC_END(chacha_2block_xor_avx2)
-
-SYM_FUNC_START(chacha_4block_xor_avx2)
- # %rdi: Input state matrix, s
- # %rsi: up to 4 data blocks output, o
- # %rdx: up to 4 data blocks input, i
- # %rcx: input/output length in bytes
- # %r8d: nrounds
-
- # This function encrypts four ChaCha blocks by loading the state
- # matrix four times across eight AVX registers. It performs matrix
- # operations on four words in two matrices in parallel, sequentially
- # to the operations on the four words of the other two matrices. The
- # required word shuffling has a rather high latency, we can do the
- # arithmetic on two matrix-pairs without much slowdown.
-
- vzeroupper
-
- # x0..3[0-4] = s0..3
- vbroadcasti128 0x00(%rdi),%ymm0
- vbroadcasti128 0x10(%rdi),%ymm1
- vbroadcasti128 0x20(%rdi),%ymm2
- vbroadcasti128 0x30(%rdi),%ymm3
-
- vmovdqa %ymm0,%ymm4
- vmovdqa %ymm1,%ymm5
- vmovdqa %ymm2,%ymm6
- vmovdqa %ymm3,%ymm7
-
- vpaddd CTR2BL(%rip),%ymm3,%ymm3
- vpaddd CTR4BL(%rip),%ymm7,%ymm7
-
- vmovdqa %ymm0,%ymm11
- vmovdqa %ymm1,%ymm12
- vmovdqa %ymm2,%ymm13
- vmovdqa %ymm3,%ymm14
- vmovdqa %ymm7,%ymm15
-
- vmovdqa ROT8(%rip),%ymm8
- vmovdqa ROT16(%rip),%ymm9
-
- mov %rcx,%rax
-
-.Ldoubleround4:
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 16)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxor %ymm0,%ymm3,%ymm3
- vpshufb %ymm9,%ymm3,%ymm3
-
- vpaddd %ymm5,%ymm4,%ymm4
- vpxor %ymm4,%ymm7,%ymm7
- vpshufb %ymm9,%ymm7,%ymm7
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 12)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxor %ymm2,%ymm1,%ymm1
- vmovdqa %ymm1,%ymm10
- vpslld $12,%ymm10,%ymm10
- vpsrld $20,%ymm1,%ymm1
- vpor %ymm10,%ymm1,%ymm1
-
- vpaddd %ymm7,%ymm6,%ymm6
- vpxor %ymm6,%ymm5,%ymm5
- vmovdqa %ymm5,%ymm10
- vpslld $12,%ymm10,%ymm10
- vpsrld $20,%ymm5,%ymm5
- vpor %ymm10,%ymm5,%ymm5
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 8)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxor %ymm0,%ymm3,%ymm3
- vpshufb %ymm8,%ymm3,%ymm3
-
- vpaddd %ymm5,%ymm4,%ymm4
- vpxor %ymm4,%ymm7,%ymm7
- vpshufb %ymm8,%ymm7,%ymm7
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 7)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxor %ymm2,%ymm1,%ymm1
- vmovdqa %ymm1,%ymm10
- vpslld $7,%ymm10,%ymm10
- vpsrld $25,%ymm1,%ymm1
- vpor %ymm10,%ymm1,%ymm1
-
- vpaddd %ymm7,%ymm6,%ymm6
- vpxor %ymm6,%ymm5,%ymm5
- vmovdqa %ymm5,%ymm10
- vpslld $7,%ymm10,%ymm10
- vpsrld $25,%ymm5,%ymm5
- vpor %ymm10,%ymm5,%ymm5
-
- # x1 = shuffle32(x1, MASK(0, 3, 2, 1))
- vpshufd $0x39,%ymm1,%ymm1
- vpshufd $0x39,%ymm5,%ymm5
- # x2 = shuffle32(x2, MASK(1, 0, 3, 2))
- vpshufd $0x4e,%ymm2,%ymm2
- vpshufd $0x4e,%ymm6,%ymm6
- # x3 = shuffle32(x3, MASK(2, 1, 0, 3))
- vpshufd $0x93,%ymm3,%ymm3
- vpshufd $0x93,%ymm7,%ymm7
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 16)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxor %ymm0,%ymm3,%ymm3
- vpshufb %ymm9,%ymm3,%ymm3
-
- vpaddd %ymm5,%ymm4,%ymm4
- vpxor %ymm4,%ymm7,%ymm7
- vpshufb %ymm9,%ymm7,%ymm7
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 12)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxor %ymm2,%ymm1,%ymm1
- vmovdqa %ymm1,%ymm10
- vpslld $12,%ymm10,%ymm10
- vpsrld $20,%ymm1,%ymm1
- vpor %ymm10,%ymm1,%ymm1
-
- vpaddd %ymm7,%ymm6,%ymm6
- vpxor %ymm6,%ymm5,%ymm5
- vmovdqa %ymm5,%ymm10
- vpslld $12,%ymm10,%ymm10
- vpsrld $20,%ymm5,%ymm5
- vpor %ymm10,%ymm5,%ymm5
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 8)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxor %ymm0,%ymm3,%ymm3
- vpshufb %ymm8,%ymm3,%ymm3
-
- vpaddd %ymm5,%ymm4,%ymm4
- vpxor %ymm4,%ymm7,%ymm7
- vpshufb %ymm8,%ymm7,%ymm7
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 7)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxor %ymm2,%ymm1,%ymm1
- vmovdqa %ymm1,%ymm10
- vpslld $7,%ymm10,%ymm10
- vpsrld $25,%ymm1,%ymm1
- vpor %ymm10,%ymm1,%ymm1
-
- vpaddd %ymm7,%ymm6,%ymm6
- vpxor %ymm6,%ymm5,%ymm5
- vmovdqa %ymm5,%ymm10
- vpslld $7,%ymm10,%ymm10
- vpsrld $25,%ymm5,%ymm5
- vpor %ymm10,%ymm5,%ymm5
-
- # x1 = shuffle32(x1, MASK(2, 1, 0, 3))
- vpshufd $0x93,%ymm1,%ymm1
- vpshufd $0x93,%ymm5,%ymm5
- # x2 = shuffle32(x2, MASK(1, 0, 3, 2))
- vpshufd $0x4e,%ymm2,%ymm2
- vpshufd $0x4e,%ymm6,%ymm6
- # x3 = shuffle32(x3, MASK(0, 3, 2, 1))
- vpshufd $0x39,%ymm3,%ymm3
- vpshufd $0x39,%ymm7,%ymm7
-
- sub $2,%r8d
- jnz .Ldoubleround4
-
- # o0 = i0 ^ (x0 + s0), first block
- vpaddd %ymm11,%ymm0,%ymm10
- cmp $0x10,%rax
- jl .Lxorpart4
- vpxor 0x00(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x00(%rsi)
- vextracti128 $1,%ymm10,%xmm0
- # o1 = i1 ^ (x1 + s1), first block
- vpaddd %ymm12,%ymm1,%ymm10
- cmp $0x20,%rax
- jl .Lxorpart4
- vpxor 0x10(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x10(%rsi)
- vextracti128 $1,%ymm10,%xmm1
- # o2 = i2 ^ (x2 + s2), first block
- vpaddd %ymm13,%ymm2,%ymm10
- cmp $0x30,%rax
- jl .Lxorpart4
- vpxor 0x20(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x20(%rsi)
- vextracti128 $1,%ymm10,%xmm2
- # o3 = i3 ^ (x3 + s3), first block
- vpaddd %ymm14,%ymm3,%ymm10
- cmp $0x40,%rax
- jl .Lxorpart4
- vpxor 0x30(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x30(%rsi)
- vextracti128 $1,%ymm10,%xmm3
-
- # xor and write second block
- vmovdqa %xmm0,%xmm10
- cmp $0x50,%rax
- jl .Lxorpart4
- vpxor 0x40(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x40(%rsi)
-
- vmovdqa %xmm1,%xmm10
- cmp $0x60,%rax
- jl .Lxorpart4
- vpxor 0x50(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x50(%rsi)
-
- vmovdqa %xmm2,%xmm10
- cmp $0x70,%rax
- jl .Lxorpart4
- vpxor 0x60(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x60(%rsi)
-
- vmovdqa %xmm3,%xmm10
- cmp $0x80,%rax
- jl .Lxorpart4
- vpxor 0x70(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x70(%rsi)
-
- # o0 = i0 ^ (x0 + s0), third block
- vpaddd %ymm11,%ymm4,%ymm10
- cmp $0x90,%rax
- jl .Lxorpart4
- vpxor 0x80(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x80(%rsi)
- vextracti128 $1,%ymm10,%xmm4
- # o1 = i1 ^ (x1 + s1), third block
- vpaddd %ymm12,%ymm5,%ymm10
- cmp $0xa0,%rax
- jl .Lxorpart4
- vpxor 0x90(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x90(%rsi)
- vextracti128 $1,%ymm10,%xmm5
- # o2 = i2 ^ (x2 + s2), third block
- vpaddd %ymm13,%ymm6,%ymm10
- cmp $0xb0,%rax
- jl .Lxorpart4
- vpxor 0xa0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xa0(%rsi)
- vextracti128 $1,%ymm10,%xmm6
- # o3 = i3 ^ (x3 + s3), third block
- vpaddd %ymm15,%ymm7,%ymm10
- cmp $0xc0,%rax
- jl .Lxorpart4
- vpxor 0xb0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xb0(%rsi)
- vextracti128 $1,%ymm10,%xmm7
-
- # xor and write fourth block
- vmovdqa %xmm4,%xmm10
- cmp $0xd0,%rax
- jl .Lxorpart4
- vpxor 0xc0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xc0(%rsi)
-
- vmovdqa %xmm5,%xmm10
- cmp $0xe0,%rax
- jl .Lxorpart4
- vpxor 0xd0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xd0(%rsi)
-
- vmovdqa %xmm6,%xmm10
- cmp $0xf0,%rax
- jl .Lxorpart4
- vpxor 0xe0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xe0(%rsi)
-
- vmovdqa %xmm7,%xmm10
- cmp $0x100,%rax
- jl .Lxorpart4
- vpxor 0xf0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xf0(%rsi)
-
-.Ldone4:
- vzeroupper
- RET
-
-.Lxorpart4:
- # xor remaining bytes from partial register into output
- mov %rax,%r9
- and $0x0f,%r9
- jz .Ldone4
- and $~0x0f,%rax
-
- mov %rsi,%r11
-
- lea 8(%rsp),%r10
- sub $0x10,%rsp
- and $~31,%rsp
-
- lea (%rdx,%rax),%rsi
- mov %rsp,%rdi
- mov %r9,%rcx
- rep movsb
-
- vpxor 0x00(%rsp),%xmm10,%xmm10
- vmovdqa %xmm10,0x00(%rsp)
-
- mov %rsp,%rsi
- lea (%r11,%rax),%rdi
- mov %r9,%rcx
- rep movsb
-
- lea -8(%r10),%rsp
- jmp .Ldone4
-
-SYM_FUNC_END(chacha_4block_xor_avx2)
-
-SYM_FUNC_START(chacha_8block_xor_avx2)
- # %rdi: Input state matrix, s
- # %rsi: up to 8 data blocks output, o
- # %rdx: up to 8 data blocks input, i
- # %rcx: input/output length in bytes
- # %r8d: nrounds
-
- # This function encrypts eight consecutive ChaCha blocks by loading
- # the state matrix in AVX registers eight times. As we need some
- # scratch registers, we save the first four registers on the stack. The
- # algorithm performs each operation on the corresponding word of each
- # state matrix, hence requires no word shuffling. For final XORing step
- # we transpose the matrix by interleaving 32-, 64- and then 128-bit
- # words, which allows us to do XOR in AVX registers. 8/16-bit word
- # rotation is done with the slightly better performing byte shuffling,
- # 7/12-bit word rotation uses traditional shift+OR.
-
- vzeroupper
- # 4 * 32 byte stack, 32-byte aligned
- lea 8(%rsp),%r10
- and $~31, %rsp
- sub $0x80, %rsp
- mov %rcx,%rax
-
- # x0..15[0-7] = s[0..15]
- vpbroadcastd 0x00(%rdi),%ymm0
- vpbroadcastd 0x04(%rdi),%ymm1
- vpbroadcastd 0x08(%rdi),%ymm2
- vpbroadcastd 0x0c(%rdi),%ymm3
- vpbroadcastd 0x10(%rdi),%ymm4
- vpbroadcastd 0x14(%rdi),%ymm5
- vpbroadcastd 0x18(%rdi),%ymm6
- vpbroadcastd 0x1c(%rdi),%ymm7
- vpbroadcastd 0x20(%rdi),%ymm8
- vpbroadcastd 0x24(%rdi),%ymm9
- vpbroadcastd 0x28(%rdi),%ymm10
- vpbroadcastd 0x2c(%rdi),%ymm11
- vpbroadcastd 0x30(%rdi),%ymm12
- vpbroadcastd 0x34(%rdi),%ymm13
- vpbroadcastd 0x38(%rdi),%ymm14
- vpbroadcastd 0x3c(%rdi),%ymm15
- # x0..3 on stack
- vmovdqa %ymm0,0x00(%rsp)
- vmovdqa %ymm1,0x20(%rsp)
- vmovdqa %ymm2,0x40(%rsp)
- vmovdqa %ymm3,0x60(%rsp)
-
- vmovdqa CTRINC(%rip),%ymm1
- vmovdqa ROT8(%rip),%ymm2
- vmovdqa ROT16(%rip),%ymm3
-
- # x12 += counter values 0-3
- vpaddd %ymm1,%ymm12,%ymm12
-
-.Ldoubleround8:
- # x0 += x4, x12 = rotl32(x12 ^ x0, 16)
- vpaddd 0x00(%rsp),%ymm4,%ymm0
- vmovdqa %ymm0,0x00(%rsp)
- vpxor %ymm0,%ymm12,%ymm12
- vpshufb %ymm3,%ymm12,%ymm12
- # x1 += x5, x13 = rotl32(x13 ^ x1, 16)
- vpaddd 0x20(%rsp),%ymm5,%ymm0
- vmovdqa %ymm0,0x20(%rsp)
- vpxor %ymm0,%ymm13,%ymm13
- vpshufb %ymm3,%ymm13,%ymm13
- # x2 += x6, x14 = rotl32(x14 ^ x2, 16)
- vpaddd 0x40(%rsp),%ymm6,%ymm0
- vmovdqa %ymm0,0x40(%rsp)
- vpxor %ymm0,%ymm14,%ymm14
- vpshufb %ymm3,%ymm14,%ymm14
- # x3 += x7, x15 = rotl32(x15 ^ x3, 16)
- vpaddd 0x60(%rsp),%ymm7,%ymm0
- vmovdqa %ymm0,0x60(%rsp)
- vpxor %ymm0,%ymm15,%ymm15
- vpshufb %ymm3,%ymm15,%ymm15
-
- # x8 += x12, x4 = rotl32(x4 ^ x8, 12)
- vpaddd %ymm12,%ymm8,%ymm8
- vpxor %ymm8,%ymm4,%ymm4
- vpslld $12,%ymm4,%ymm0
- vpsrld $20,%ymm4,%ymm4
- vpor %ymm0,%ymm4,%ymm4
- # x9 += x13, x5 = rotl32(x5 ^ x9, 12)
- vpaddd %ymm13,%ymm9,%ymm9
- vpxor %ymm9,%ymm5,%ymm5
- vpslld $12,%ymm5,%ymm0
- vpsrld $20,%ymm5,%ymm5
- vpor %ymm0,%ymm5,%ymm5
- # x10 += x14, x6 = rotl32(x6 ^ x10, 12)
- vpaddd %ymm14,%ymm10,%ymm10
- vpxor %ymm10,%ymm6,%ymm6
- vpslld $12,%ymm6,%ymm0
- vpsrld $20,%ymm6,%ymm6
- vpor %ymm0,%ymm6,%ymm6
- # x11 += x15, x7 = rotl32(x7 ^ x11, 12)
- vpaddd %ymm15,%ymm11,%ymm11
- vpxor %ymm11,%ymm7,%ymm7
- vpslld $12,%ymm7,%ymm0
- vpsrld $20,%ymm7,%ymm7
- vpor %ymm0,%ymm7,%ymm7
-
- # x0 += x4, x12 = rotl32(x12 ^ x0, 8)
- vpaddd 0x00(%rsp),%ymm4,%ymm0
- vmovdqa %ymm0,0x00(%rsp)
- vpxor %ymm0,%ymm12,%ymm12
- vpshufb %ymm2,%ymm12,%ymm12
- # x1 += x5, x13 = rotl32(x13 ^ x1, 8)
- vpaddd 0x20(%rsp),%ymm5,%ymm0
- vmovdqa %ymm0,0x20(%rsp)
- vpxor %ymm0,%ymm13,%ymm13
- vpshufb %ymm2,%ymm13,%ymm13
- # x2 += x6, x14 = rotl32(x14 ^ x2, 8)
- vpaddd 0x40(%rsp),%ymm6,%ymm0
- vmovdqa %ymm0,0x40(%rsp)
- vpxor %ymm0,%ymm14,%ymm14
- vpshufb %ymm2,%ymm14,%ymm14
- # x3 += x7, x15 = rotl32(x15 ^ x3, 8)
- vpaddd 0x60(%rsp),%ymm7,%ymm0
- vmovdqa %ymm0,0x60(%rsp)
- vpxor %ymm0,%ymm15,%ymm15
- vpshufb %ymm2,%ymm15,%ymm15
-
- # x8 += x12, x4 = rotl32(x4 ^ x8, 7)
- vpaddd %ymm12,%ymm8,%ymm8
- vpxor %ymm8,%ymm4,%ymm4
- vpslld $7,%ymm4,%ymm0
- vpsrld $25,%ymm4,%ymm4
- vpor %ymm0,%ymm4,%ymm4
- # x9 += x13, x5 = rotl32(x5 ^ x9, 7)
- vpaddd %ymm13,%ymm9,%ymm9
- vpxor %ymm9,%ymm5,%ymm5
- vpslld $7,%ymm5,%ymm0
- vpsrld $25,%ymm5,%ymm5
- vpor %ymm0,%ymm5,%ymm5
- # x10 += x14, x6 = rotl32(x6 ^ x10, 7)
- vpaddd %ymm14,%ymm10,%ymm10
- vpxor %ymm10,%ymm6,%ymm6
- vpslld $7,%ymm6,%ymm0
- vpsrld $25,%ymm6,%ymm6
- vpor %ymm0,%ymm6,%ymm6
- # x11 += x15, x7 = rotl32(x7 ^ x11, 7)
- vpaddd %ymm15,%ymm11,%ymm11
- vpxor %ymm11,%ymm7,%ymm7
- vpslld $7,%ymm7,%ymm0
- vpsrld $25,%ymm7,%ymm7
- vpor %ymm0,%ymm7,%ymm7
-
- # x0 += x5, x15 = rotl32(x15 ^ x0, 16)
- vpaddd 0x00(%rsp),%ymm5,%ymm0
- vmovdqa %ymm0,0x00(%rsp)
- vpxor %ymm0,%ymm15,%ymm15
- vpshufb %ymm3,%ymm15,%ymm15
- # x1 += x6, x12 = rotl32(x12 ^ x1, 16)%ymm0
- vpaddd 0x20(%rsp),%ymm6,%ymm0
- vmovdqa %ymm0,0x20(%rsp)
- vpxor %ymm0,%ymm12,%ymm12
- vpshufb %ymm3,%ymm12,%ymm12
- # x2 += x7, x13 = rotl32(x13 ^ x2, 16)
- vpaddd 0x40(%rsp),%ymm7,%ymm0
- vmovdqa %ymm0,0x40(%rsp)
- vpxor %ymm0,%ymm13,%ymm13
- vpshufb %ymm3,%ymm13,%ymm13
- # x3 += x4, x14 = rotl32(x14 ^ x3, 16)
- vpaddd 0x60(%rsp),%ymm4,%ymm0
- vmovdqa %ymm0,0x60(%rsp)
- vpxor %ymm0,%ymm14,%ymm14
- vpshufb %ymm3,%ymm14,%ymm14
-
- # x10 += x15, x5 = rotl32(x5 ^ x10, 12)
- vpaddd %ymm15,%ymm10,%ymm10
- vpxor %ymm10,%ymm5,%ymm5
- vpslld $12,%ymm5,%ymm0
- vpsrld $20,%ymm5,%ymm5
- vpor %ymm0,%ymm5,%ymm5
- # x11 += x12, x6 = rotl32(x6 ^ x11, 12)
- vpaddd %ymm12,%ymm11,%ymm11
- vpxor %ymm11,%ymm6,%ymm6
- vpslld $12,%ymm6,%ymm0
- vpsrld $20,%ymm6,%ymm6
- vpor %ymm0,%ymm6,%ymm6
- # x8 += x13, x7 = rotl32(x7 ^ x8, 12)
- vpaddd %ymm13,%ymm8,%ymm8
- vpxor %ymm8,%ymm7,%ymm7
- vpslld $12,%ymm7,%ymm0
- vpsrld $20,%ymm7,%ymm7
- vpor %ymm0,%ymm7,%ymm7
- # x9 += x14, x4 = rotl32(x4 ^ x9, 12)
- vpaddd %ymm14,%ymm9,%ymm9
- vpxor %ymm9,%ymm4,%ymm4
- vpslld $12,%ymm4,%ymm0
- vpsrld $20,%ymm4,%ymm4
- vpor %ymm0,%ymm4,%ymm4
-
- # x0 += x5, x15 = rotl32(x15 ^ x0, 8)
- vpaddd 0x00(%rsp),%ymm5,%ymm0
- vmovdqa %ymm0,0x00(%rsp)
- vpxor %ymm0,%ymm15,%ymm15
- vpshufb %ymm2,%ymm15,%ymm15
- # x1 += x6, x12 = rotl32(x12 ^ x1, 8)
- vpaddd 0x20(%rsp),%ymm6,%ymm0
- vmovdqa %ymm0,0x20(%rsp)
- vpxor %ymm0,%ymm12,%ymm12
- vpshufb %ymm2,%ymm12,%ymm12
- # x2 += x7, x13 = rotl32(x13 ^ x2, 8)
- vpaddd 0x40(%rsp),%ymm7,%ymm0
- vmovdqa %ymm0,0x40(%rsp)
- vpxor %ymm0,%ymm13,%ymm13
- vpshufb %ymm2,%ymm13,%ymm13
- # x3 += x4, x14 = rotl32(x14 ^ x3, 8)
- vpaddd 0x60(%rsp),%ymm4,%ymm0
- vmovdqa %ymm0,0x60(%rsp)
- vpxor %ymm0,%ymm14,%ymm14
- vpshufb %ymm2,%ymm14,%ymm14
-
- # x10 += x15, x5 = rotl32(x5 ^ x10, 7)
- vpaddd %ymm15,%ymm10,%ymm10
- vpxor %ymm10,%ymm5,%ymm5
- vpslld $7,%ymm5,%ymm0
- vpsrld $25,%ymm5,%ymm5
- vpor %ymm0,%ymm5,%ymm5
- # x11 += x12, x6 = rotl32(x6 ^ x11, 7)
- vpaddd %ymm12,%ymm11,%ymm11
- vpxor %ymm11,%ymm6,%ymm6
- vpslld $7,%ymm6,%ymm0
- vpsrld $25,%ymm6,%ymm6
- vpor %ymm0,%ymm6,%ymm6
- # x8 += x13, x7 = rotl32(x7 ^ x8, 7)
- vpaddd %ymm13,%ymm8,%ymm8
- vpxor %ymm8,%ymm7,%ymm7
- vpslld $7,%ymm7,%ymm0
- vpsrld $25,%ymm7,%ymm7
- vpor %ymm0,%ymm7,%ymm7
- # x9 += x14, x4 = rotl32(x4 ^ x9, 7)
- vpaddd %ymm14,%ymm9,%ymm9
- vpxor %ymm9,%ymm4,%ymm4
- vpslld $7,%ymm4,%ymm0
- vpsrld $25,%ymm4,%ymm4
- vpor %ymm0,%ymm4,%ymm4
-
- sub $2,%r8d
- jnz .Ldoubleround8
-
- # x0..15[0-3] += s[0..15]
- vpbroadcastd 0x00(%rdi),%ymm0
- vpaddd 0x00(%rsp),%ymm0,%ymm0
- vmovdqa %ymm0,0x00(%rsp)
- vpbroadcastd 0x04(%rdi),%ymm0
- vpaddd 0x20(%rsp),%ymm0,%ymm0
- vmovdqa %ymm0,0x20(%rsp)
- vpbroadcastd 0x08(%rdi),%ymm0
- vpaddd 0x40(%rsp),%ymm0,%ymm0
- vmovdqa %ymm0,0x40(%rsp)
- vpbroadcastd 0x0c(%rdi),%ymm0
- vpaddd 0x60(%rsp),%ymm0,%ymm0
- vmovdqa %ymm0,0x60(%rsp)
- vpbroadcastd 0x10(%rdi),%ymm0
- vpaddd %ymm0,%ymm4,%ymm4
- vpbroadcastd 0x14(%rdi),%ymm0
- vpaddd %ymm0,%ymm5,%ymm5
- vpbroadcastd 0x18(%rdi),%ymm0
- vpaddd %ymm0,%ymm6,%ymm6
- vpbroadcastd 0x1c(%rdi),%ymm0
- vpaddd %ymm0,%ymm7,%ymm7
- vpbroadcastd 0x20(%rdi),%ymm0
- vpaddd %ymm0,%ymm8,%ymm8
- vpbroadcastd 0x24(%rdi),%ymm0
- vpaddd %ymm0,%ymm9,%ymm9
- vpbroadcastd 0x28(%rdi),%ymm0
- vpaddd %ymm0,%ymm10,%ymm10
- vpbroadcastd 0x2c(%rdi),%ymm0
- vpaddd %ymm0,%ymm11,%ymm11
- vpbroadcastd 0x30(%rdi),%ymm0
- vpaddd %ymm0,%ymm12,%ymm12
- vpbroadcastd 0x34(%rdi),%ymm0
- vpaddd %ymm0,%ymm13,%ymm13
- vpbroadcastd 0x38(%rdi),%ymm0
- vpaddd %ymm0,%ymm14,%ymm14
- vpbroadcastd 0x3c(%rdi),%ymm0
- vpaddd %ymm0,%ymm15,%ymm15
-
- # x12 += counter values 0-3
- vpaddd %ymm1,%ymm12,%ymm12
-
- # interleave 32-bit words in state n, n+1
- vmovdqa 0x00(%rsp),%ymm0
- vmovdqa 0x20(%rsp),%ymm1
- vpunpckldq %ymm1,%ymm0,%ymm2
- vpunpckhdq %ymm1,%ymm0,%ymm1
- vmovdqa %ymm2,0x00(%rsp)
- vmovdqa %ymm1,0x20(%rsp)
- vmovdqa 0x40(%rsp),%ymm0
- vmovdqa 0x60(%rsp),%ymm1
- vpunpckldq %ymm1,%ymm0,%ymm2
- vpunpckhdq %ymm1,%ymm0,%ymm1
- vmovdqa %ymm2,0x40(%rsp)
- vmovdqa %ymm1,0x60(%rsp)
- vmovdqa %ymm4,%ymm0
- vpunpckldq %ymm5,%ymm0,%ymm4
- vpunpckhdq %ymm5,%ymm0,%ymm5
- vmovdqa %ymm6,%ymm0
- vpunpckldq %ymm7,%ymm0,%ymm6
- vpunpckhdq %ymm7,%ymm0,%ymm7
- vmovdqa %ymm8,%ymm0
- vpunpckldq %ymm9,%ymm0,%ymm8
- vpunpckhdq %ymm9,%ymm0,%ymm9
- vmovdqa %ymm10,%ymm0
- vpunpckldq %ymm11,%ymm0,%ymm10
- vpunpckhdq %ymm11,%ymm0,%ymm11
- vmovdqa %ymm12,%ymm0
- vpunpckldq %ymm13,%ymm0,%ymm12
- vpunpckhdq %ymm13,%ymm0,%ymm13
- vmovdqa %ymm14,%ymm0
- vpunpckldq %ymm15,%ymm0,%ymm14
- vpunpckhdq %ymm15,%ymm0,%ymm15
-
- # interleave 64-bit words in state n, n+2
- vmovdqa 0x00(%rsp),%ymm0
- vmovdqa 0x40(%rsp),%ymm2
- vpunpcklqdq %ymm2,%ymm0,%ymm1
- vpunpckhqdq %ymm2,%ymm0,%ymm2
- vmovdqa %ymm1,0x00(%rsp)
- vmovdqa %ymm2,0x40(%rsp)
- vmovdqa 0x20(%rsp),%ymm0
- vmovdqa 0x60(%rsp),%ymm2
- vpunpcklqdq %ymm2,%ymm0,%ymm1
- vpunpckhqdq %ymm2,%ymm0,%ymm2
- vmovdqa %ymm1,0x20(%rsp)
- vmovdqa %ymm2,0x60(%rsp)
- vmovdqa %ymm4,%ymm0
- vpunpcklqdq %ymm6,%ymm0,%ymm4
- vpunpckhqdq %ymm6,%ymm0,%ymm6
- vmovdqa %ymm5,%ymm0
- vpunpcklqdq %ymm7,%ymm0,%ymm5
- vpunpckhqdq %ymm7,%ymm0,%ymm7
- vmovdqa %ymm8,%ymm0
- vpunpcklqdq %ymm10,%ymm0,%ymm8
- vpunpckhqdq %ymm10,%ymm0,%ymm10
- vmovdqa %ymm9,%ymm0
- vpunpcklqdq %ymm11,%ymm0,%ymm9
- vpunpckhqdq %ymm11,%ymm0,%ymm11
- vmovdqa %ymm12,%ymm0
- vpunpcklqdq %ymm14,%ymm0,%ymm12
- vpunpckhqdq %ymm14,%ymm0,%ymm14
- vmovdqa %ymm13,%ymm0
- vpunpcklqdq %ymm15,%ymm0,%ymm13
- vpunpckhqdq %ymm15,%ymm0,%ymm15
-
- # interleave 128-bit words in state n, n+4
- # xor/write first four blocks
- vmovdqa 0x00(%rsp),%ymm1
- vperm2i128 $0x20,%ymm4,%ymm1,%ymm0
- cmp $0x0020,%rax
- jl .Lxorpart8
- vpxor 0x0000(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x0000(%rsi)
- vperm2i128 $0x31,%ymm4,%ymm1,%ymm4
-
- vperm2i128 $0x20,%ymm12,%ymm8,%ymm0
- cmp $0x0040,%rax
- jl .Lxorpart8
- vpxor 0x0020(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x0020(%rsi)
- vperm2i128 $0x31,%ymm12,%ymm8,%ymm12
-
- vmovdqa 0x40(%rsp),%ymm1
- vperm2i128 $0x20,%ymm6,%ymm1,%ymm0
- cmp $0x0060,%rax
- jl .Lxorpart8
- vpxor 0x0040(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x0040(%rsi)
- vperm2i128 $0x31,%ymm6,%ymm1,%ymm6
-
- vperm2i128 $0x20,%ymm14,%ymm10,%ymm0
- cmp $0x0080,%rax
- jl .Lxorpart8
- vpxor 0x0060(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x0060(%rsi)
- vperm2i128 $0x31,%ymm14,%ymm10,%ymm14
-
- vmovdqa 0x20(%rsp),%ymm1
- vperm2i128 $0x20,%ymm5,%ymm1,%ymm0
- cmp $0x00a0,%rax
- jl .Lxorpart8
- vpxor 0x0080(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x0080(%rsi)
- vperm2i128 $0x31,%ymm5,%ymm1,%ymm5
-
- vperm2i128 $0x20,%ymm13,%ymm9,%ymm0
- cmp $0x00c0,%rax
- jl .Lxorpart8
- vpxor 0x00a0(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x00a0(%rsi)
- vperm2i128 $0x31,%ymm13,%ymm9,%ymm13
-
- vmovdqa 0x60(%rsp),%ymm1
- vperm2i128 $0x20,%ymm7,%ymm1,%ymm0
- cmp $0x00e0,%rax
- jl .Lxorpart8
- vpxor 0x00c0(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x00c0(%rsi)
- vperm2i128 $0x31,%ymm7,%ymm1,%ymm7
-
- vperm2i128 $0x20,%ymm15,%ymm11,%ymm0
- cmp $0x0100,%rax
- jl .Lxorpart8
- vpxor 0x00e0(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x00e0(%rsi)
- vperm2i128 $0x31,%ymm15,%ymm11,%ymm15
-
- # xor remaining blocks, write to output
- vmovdqa %ymm4,%ymm0
- cmp $0x0120,%rax
- jl .Lxorpart8
- vpxor 0x0100(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x0100(%rsi)
-
- vmovdqa %ymm12,%ymm0
- cmp $0x0140,%rax
- jl .Lxorpart8
- vpxor 0x0120(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x0120(%rsi)
-
- vmovdqa %ymm6,%ymm0
- cmp $0x0160,%rax
- jl .Lxorpart8
- vpxor 0x0140(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x0140(%rsi)
-
- vmovdqa %ymm14,%ymm0
- cmp $0x0180,%rax
- jl .Lxorpart8
- vpxor 0x0160(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x0160(%rsi)
-
- vmovdqa %ymm5,%ymm0
- cmp $0x01a0,%rax
- jl .Lxorpart8
- vpxor 0x0180(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x0180(%rsi)
-
- vmovdqa %ymm13,%ymm0
- cmp $0x01c0,%rax
- jl .Lxorpart8
- vpxor 0x01a0(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x01a0(%rsi)
-
- vmovdqa %ymm7,%ymm0
- cmp $0x01e0,%rax
- jl .Lxorpart8
- vpxor 0x01c0(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x01c0(%rsi)
-
- vmovdqa %ymm15,%ymm0
- cmp $0x0200,%rax
- jl .Lxorpart8
- vpxor 0x01e0(%rdx),%ymm0,%ymm0
- vmovdqu %ymm0,0x01e0(%rsi)
-
-.Ldone8:
- vzeroupper
- lea -8(%r10),%rsp
- RET
-
-.Lxorpart8:
- # xor remaining bytes from partial register into output
- mov %rax,%r9
- and $0x1f,%r9
- jz .Ldone8
- and $~0x1f,%rax
-
- mov %rsi,%r11
-
- lea (%rdx,%rax),%rsi
- mov %rsp,%rdi
- mov %r9,%rcx
- rep movsb
-
- vpxor 0x00(%rsp),%ymm0,%ymm0
- vmovdqa %ymm0,0x00(%rsp)
-
- mov %rsp,%rsi
- lea (%r11,%rax),%rdi
- mov %r9,%rcx
- rep movsb
-
- jmp .Ldone8
-
-SYM_FUNC_END(chacha_8block_xor_avx2)
diff --git a/arch/x86/crypto/chacha-avx512vl-x86_64.S b/arch/x86/crypto/chacha-avx512vl-x86_64.S
deleted file mode 100644
index 259383e1ad44..000000000000
--- a/arch/x86/crypto/chacha-avx512vl-x86_64.S
+++ /dev/null
@@ -1,836 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0+ */
-/*
- * ChaCha 256-bit cipher algorithm, x64 AVX-512VL functions
- *
- * Copyright (C) 2018 Martin Willi
- */
-
-#include <linux/linkage.h>
-
-.section .rodata.cst32.CTR2BL, "aM", @progbits, 32
-.align 32
-CTR2BL: .octa 0x00000000000000000000000000000000
- .octa 0x00000000000000000000000000000001
-
-.section .rodata.cst32.CTR4BL, "aM", @progbits, 32
-.align 32
-CTR4BL: .octa 0x00000000000000000000000000000002
- .octa 0x00000000000000000000000000000003
-
-.section .rodata.cst32.CTR8BL, "aM", @progbits, 32
-.align 32
-CTR8BL: .octa 0x00000003000000020000000100000000
- .octa 0x00000007000000060000000500000004
-
-.text
-
-SYM_FUNC_START(chacha_2block_xor_avx512vl)
- # %rdi: Input state matrix, s
- # %rsi: up to 2 data blocks output, o
- # %rdx: up to 2 data blocks input, i
- # %rcx: input/output length in bytes
- # %r8d: nrounds
-
- # This function encrypts two ChaCha blocks by loading the state
- # matrix twice across four AVX registers. It performs matrix operations
- # on four words in each matrix in parallel, but requires shuffling to
- # rearrange the words after each round.
-
- vzeroupper
-
- # x0..3[0-2] = s0..3
- vbroadcasti128 0x00(%rdi),%ymm0
- vbroadcasti128 0x10(%rdi),%ymm1
- vbroadcasti128 0x20(%rdi),%ymm2
- vbroadcasti128 0x30(%rdi),%ymm3
-
- vpaddd CTR2BL(%rip),%ymm3,%ymm3
-
- vmovdqa %ymm0,%ymm8
- vmovdqa %ymm1,%ymm9
- vmovdqa %ymm2,%ymm10
- vmovdqa %ymm3,%ymm11
-
-.Ldoubleround:
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 16)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxord %ymm0,%ymm3,%ymm3
- vprold $16,%ymm3,%ymm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 12)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxord %ymm2,%ymm1,%ymm1
- vprold $12,%ymm1,%ymm1
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 8)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxord %ymm0,%ymm3,%ymm3
- vprold $8,%ymm3,%ymm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 7)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxord %ymm2,%ymm1,%ymm1
- vprold $7,%ymm1,%ymm1
-
- # x1 = shuffle32(x1, MASK(0, 3, 2, 1))
- vpshufd $0x39,%ymm1,%ymm1
- # x2 = shuffle32(x2, MASK(1, 0, 3, 2))
- vpshufd $0x4e,%ymm2,%ymm2
- # x3 = shuffle32(x3, MASK(2, 1, 0, 3))
- vpshufd $0x93,%ymm3,%ymm3
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 16)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxord %ymm0,%ymm3,%ymm3
- vprold $16,%ymm3,%ymm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 12)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxord %ymm2,%ymm1,%ymm1
- vprold $12,%ymm1,%ymm1
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 8)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxord %ymm0,%ymm3,%ymm3
- vprold $8,%ymm3,%ymm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 7)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxord %ymm2,%ymm1,%ymm1
- vprold $7,%ymm1,%ymm1
-
- # x1 = shuffle32(x1, MASK(2, 1, 0, 3))
- vpshufd $0x93,%ymm1,%ymm1
- # x2 = shuffle32(x2, MASK(1, 0, 3, 2))
- vpshufd $0x4e,%ymm2,%ymm2
- # x3 = shuffle32(x3, MASK(0, 3, 2, 1))
- vpshufd $0x39,%ymm3,%ymm3
-
- sub $2,%r8d
- jnz .Ldoubleround
-
- # o0 = i0 ^ (x0 + s0)
- vpaddd %ymm8,%ymm0,%ymm7
- cmp $0x10,%rcx
- jl .Lxorpart2
- vpxord 0x00(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x00(%rsi)
- vextracti128 $1,%ymm7,%xmm0
- # o1 = i1 ^ (x1 + s1)
- vpaddd %ymm9,%ymm1,%ymm7
- cmp $0x20,%rcx
- jl .Lxorpart2
- vpxord 0x10(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x10(%rsi)
- vextracti128 $1,%ymm7,%xmm1
- # o2 = i2 ^ (x2 + s2)
- vpaddd %ymm10,%ymm2,%ymm7
- cmp $0x30,%rcx
- jl .Lxorpart2
- vpxord 0x20(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x20(%rsi)
- vextracti128 $1,%ymm7,%xmm2
- # o3 = i3 ^ (x3 + s3)
- vpaddd %ymm11,%ymm3,%ymm7
- cmp $0x40,%rcx
- jl .Lxorpart2
- vpxord 0x30(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x30(%rsi)
- vextracti128 $1,%ymm7,%xmm3
-
- # xor and write second block
- vmovdqa %xmm0,%xmm7
- cmp $0x50,%rcx
- jl .Lxorpart2
- vpxord 0x40(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x40(%rsi)
-
- vmovdqa %xmm1,%xmm7
- cmp $0x60,%rcx
- jl .Lxorpart2
- vpxord 0x50(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x50(%rsi)
-
- vmovdqa %xmm2,%xmm7
- cmp $0x70,%rcx
- jl .Lxorpart2
- vpxord 0x60(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x60(%rsi)
-
- vmovdqa %xmm3,%xmm7
- cmp $0x80,%rcx
- jl .Lxorpart2
- vpxord 0x70(%rdx),%xmm7,%xmm6
- vmovdqu %xmm6,0x70(%rsi)
-
-.Ldone2:
- vzeroupper
- RET
-
-.Lxorpart2:
- # xor remaining bytes from partial register into output
- mov %rcx,%rax
- and $0xf,%rcx
- jz .Ldone2
- mov %rax,%r9
- and $~0xf,%r9
-
- mov $1,%rax
- shld %cl,%rax,%rax
- sub $1,%rax
- kmovq %rax,%k1
-
- vmovdqu8 (%rdx,%r9),%xmm1{%k1}{z}
- vpxord %xmm7,%xmm1,%xmm1
- vmovdqu8 %xmm1,(%rsi,%r9){%k1}
-
- jmp .Ldone2
-
-SYM_FUNC_END(chacha_2block_xor_avx512vl)
-
-SYM_FUNC_START(chacha_4block_xor_avx512vl)
- # %rdi: Input state matrix, s
- # %rsi: up to 4 data blocks output, o
- # %rdx: up to 4 data blocks input, i
- # %rcx: input/output length in bytes
- # %r8d: nrounds
-
- # This function encrypts four ChaCha blocks by loading the state
- # matrix four times across eight AVX registers. It performs matrix
- # operations on four words in two matrices in parallel, sequentially
- # to the operations on the four words of the other two matrices. The
- # required word shuffling has a rather high latency, we can do the
- # arithmetic on two matrix-pairs without much slowdown.
-
- vzeroupper
-
- # x0..3[0-4] = s0..3
- vbroadcasti128 0x00(%rdi),%ymm0
- vbroadcasti128 0x10(%rdi),%ymm1
- vbroadcasti128 0x20(%rdi),%ymm2
- vbroadcasti128 0x30(%rdi),%ymm3
-
- vmovdqa %ymm0,%ymm4
- vmovdqa %ymm1,%ymm5
- vmovdqa %ymm2,%ymm6
- vmovdqa %ymm3,%ymm7
-
- vpaddd CTR2BL(%rip),%ymm3,%ymm3
- vpaddd CTR4BL(%rip),%ymm7,%ymm7
-
- vmovdqa %ymm0,%ymm11
- vmovdqa %ymm1,%ymm12
- vmovdqa %ymm2,%ymm13
- vmovdqa %ymm3,%ymm14
- vmovdqa %ymm7,%ymm15
-
-.Ldoubleround4:
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 16)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxord %ymm0,%ymm3,%ymm3
- vprold $16,%ymm3,%ymm3
-
- vpaddd %ymm5,%ymm4,%ymm4
- vpxord %ymm4,%ymm7,%ymm7
- vprold $16,%ymm7,%ymm7
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 12)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxord %ymm2,%ymm1,%ymm1
- vprold $12,%ymm1,%ymm1
-
- vpaddd %ymm7,%ymm6,%ymm6
- vpxord %ymm6,%ymm5,%ymm5
- vprold $12,%ymm5,%ymm5
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 8)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxord %ymm0,%ymm3,%ymm3
- vprold $8,%ymm3,%ymm3
-
- vpaddd %ymm5,%ymm4,%ymm4
- vpxord %ymm4,%ymm7,%ymm7
- vprold $8,%ymm7,%ymm7
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 7)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxord %ymm2,%ymm1,%ymm1
- vprold $7,%ymm1,%ymm1
-
- vpaddd %ymm7,%ymm6,%ymm6
- vpxord %ymm6,%ymm5,%ymm5
- vprold $7,%ymm5,%ymm5
-
- # x1 = shuffle32(x1, MASK(0, 3, 2, 1))
- vpshufd $0x39,%ymm1,%ymm1
- vpshufd $0x39,%ymm5,%ymm5
- # x2 = shuffle32(x2, MASK(1, 0, 3, 2))
- vpshufd $0x4e,%ymm2,%ymm2
- vpshufd $0x4e,%ymm6,%ymm6
- # x3 = shuffle32(x3, MASK(2, 1, 0, 3))
- vpshufd $0x93,%ymm3,%ymm3
- vpshufd $0x93,%ymm7,%ymm7
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 16)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxord %ymm0,%ymm3,%ymm3
- vprold $16,%ymm3,%ymm3
-
- vpaddd %ymm5,%ymm4,%ymm4
- vpxord %ymm4,%ymm7,%ymm7
- vprold $16,%ymm7,%ymm7
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 12)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxord %ymm2,%ymm1,%ymm1
- vprold $12,%ymm1,%ymm1
-
- vpaddd %ymm7,%ymm6,%ymm6
- vpxord %ymm6,%ymm5,%ymm5
- vprold $12,%ymm5,%ymm5
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 8)
- vpaddd %ymm1,%ymm0,%ymm0
- vpxord %ymm0,%ymm3,%ymm3
- vprold $8,%ymm3,%ymm3
-
- vpaddd %ymm5,%ymm4,%ymm4
- vpxord %ymm4,%ymm7,%ymm7
- vprold $8,%ymm7,%ymm7
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 7)
- vpaddd %ymm3,%ymm2,%ymm2
- vpxord %ymm2,%ymm1,%ymm1
- vprold $7,%ymm1,%ymm1
-
- vpaddd %ymm7,%ymm6,%ymm6
- vpxord %ymm6,%ymm5,%ymm5
- vprold $7,%ymm5,%ymm5
-
- # x1 = shuffle32(x1, MASK(2, 1, 0, 3))
- vpshufd $0x93,%ymm1,%ymm1
- vpshufd $0x93,%ymm5,%ymm5
- # x2 = shuffle32(x2, MASK(1, 0, 3, 2))
- vpshufd $0x4e,%ymm2,%ymm2
- vpshufd $0x4e,%ymm6,%ymm6
- # x3 = shuffle32(x3, MASK(0, 3, 2, 1))
- vpshufd $0x39,%ymm3,%ymm3
- vpshufd $0x39,%ymm7,%ymm7
-
- sub $2,%r8d
- jnz .Ldoubleround4
-
- # o0 = i0 ^ (x0 + s0), first block
- vpaddd %ymm11,%ymm0,%ymm10
- cmp $0x10,%rcx
- jl .Lxorpart4
- vpxord 0x00(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x00(%rsi)
- vextracti128 $1,%ymm10,%xmm0
- # o1 = i1 ^ (x1 + s1), first block
- vpaddd %ymm12,%ymm1,%ymm10
- cmp $0x20,%rcx
- jl .Lxorpart4
- vpxord 0x10(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x10(%rsi)
- vextracti128 $1,%ymm10,%xmm1
- # o2 = i2 ^ (x2 + s2), first block
- vpaddd %ymm13,%ymm2,%ymm10
- cmp $0x30,%rcx
- jl .Lxorpart4
- vpxord 0x20(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x20(%rsi)
- vextracti128 $1,%ymm10,%xmm2
- # o3 = i3 ^ (x3 + s3), first block
- vpaddd %ymm14,%ymm3,%ymm10
- cmp $0x40,%rcx
- jl .Lxorpart4
- vpxord 0x30(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x30(%rsi)
- vextracti128 $1,%ymm10,%xmm3
-
- # xor and write second block
- vmovdqa %xmm0,%xmm10
- cmp $0x50,%rcx
- jl .Lxorpart4
- vpxord 0x40(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x40(%rsi)
-
- vmovdqa %xmm1,%xmm10
- cmp $0x60,%rcx
- jl .Lxorpart4
- vpxord 0x50(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x50(%rsi)
-
- vmovdqa %xmm2,%xmm10
- cmp $0x70,%rcx
- jl .Lxorpart4
- vpxord 0x60(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x60(%rsi)
-
- vmovdqa %xmm3,%xmm10
- cmp $0x80,%rcx
- jl .Lxorpart4
- vpxord 0x70(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x70(%rsi)
-
- # o0 = i0 ^ (x0 + s0), third block
- vpaddd %ymm11,%ymm4,%ymm10
- cmp $0x90,%rcx
- jl .Lxorpart4
- vpxord 0x80(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x80(%rsi)
- vextracti128 $1,%ymm10,%xmm4
- # o1 = i1 ^ (x1 + s1), third block
- vpaddd %ymm12,%ymm5,%ymm10
- cmp $0xa0,%rcx
- jl .Lxorpart4
- vpxord 0x90(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0x90(%rsi)
- vextracti128 $1,%ymm10,%xmm5
- # o2 = i2 ^ (x2 + s2), third block
- vpaddd %ymm13,%ymm6,%ymm10
- cmp $0xb0,%rcx
- jl .Lxorpart4
- vpxord 0xa0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xa0(%rsi)
- vextracti128 $1,%ymm10,%xmm6
- # o3 = i3 ^ (x3 + s3), third block
- vpaddd %ymm15,%ymm7,%ymm10
- cmp $0xc0,%rcx
- jl .Lxorpart4
- vpxord 0xb0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xb0(%rsi)
- vextracti128 $1,%ymm10,%xmm7
-
- # xor and write fourth block
- vmovdqa %xmm4,%xmm10
- cmp $0xd0,%rcx
- jl .Lxorpart4
- vpxord 0xc0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xc0(%rsi)
-
- vmovdqa %xmm5,%xmm10
- cmp $0xe0,%rcx
- jl .Lxorpart4
- vpxord 0xd0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xd0(%rsi)
-
- vmovdqa %xmm6,%xmm10
- cmp $0xf0,%rcx
- jl .Lxorpart4
- vpxord 0xe0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xe0(%rsi)
-
- vmovdqa %xmm7,%xmm10
- cmp $0x100,%rcx
- jl .Lxorpart4
- vpxord 0xf0(%rdx),%xmm10,%xmm9
- vmovdqu %xmm9,0xf0(%rsi)
-
-.Ldone4:
- vzeroupper
- RET
-
-.Lxorpart4:
- # xor remaining bytes from partial register into output
- mov %rcx,%rax
- and $0xf,%rcx
- jz .Ldone4
- mov %rax,%r9
- and $~0xf,%r9
-
- mov $1,%rax
- shld %cl,%rax,%rax
- sub $1,%rax
- kmovq %rax,%k1
-
- vmovdqu8 (%rdx,%r9),%xmm1{%k1}{z}
- vpxord %xmm10,%xmm1,%xmm1
- vmovdqu8 %xmm1,(%rsi,%r9){%k1}
-
- jmp .Ldone4
-
-SYM_FUNC_END(chacha_4block_xor_avx512vl)
-
-SYM_FUNC_START(chacha_8block_xor_avx512vl)
- # %rdi: Input state matrix, s
- # %rsi: up to 8 data blocks output, o
- # %rdx: up to 8 data blocks input, i
- # %rcx: input/output length in bytes
- # %r8d: nrounds
-
- # This function encrypts eight consecutive ChaCha blocks by loading
- # the state matrix in AVX registers eight times. Compared to AVX2, this
- # mostly benefits from the new rotate instructions in VL and the
- # additional registers.
-
- vzeroupper
-
- # x0..15[0-7] = s[0..15]
- vpbroadcastd 0x00(%rdi),%ymm0
- vpbroadcastd 0x04(%rdi),%ymm1
- vpbroadcastd 0x08(%rdi),%ymm2
- vpbroadcastd 0x0c(%rdi),%ymm3
- vpbroadcastd 0x10(%rdi),%ymm4
- vpbroadcastd 0x14(%rdi),%ymm5
- vpbroadcastd 0x18(%rdi),%ymm6
- vpbroadcastd 0x1c(%rdi),%ymm7
- vpbroadcastd 0x20(%rdi),%ymm8
- vpbroadcastd 0x24(%rdi),%ymm9
- vpbroadcastd 0x28(%rdi),%ymm10
- vpbroadcastd 0x2c(%rdi),%ymm11
- vpbroadcastd 0x30(%rdi),%ymm12
- vpbroadcastd 0x34(%rdi),%ymm13
- vpbroadcastd 0x38(%rdi),%ymm14
- vpbroadcastd 0x3c(%rdi),%ymm15
-
- # x12 += counter values 0-3
- vpaddd CTR8BL(%rip),%ymm12,%ymm12
-
- vmovdqa64 %ymm0,%ymm16
- vmovdqa64 %ymm1,%ymm17
- vmovdqa64 %ymm2,%ymm18
- vmovdqa64 %ymm3,%ymm19
- vmovdqa64 %ymm4,%ymm20
- vmovdqa64 %ymm5,%ymm21
- vmovdqa64 %ymm6,%ymm22
- vmovdqa64 %ymm7,%ymm23
- vmovdqa64 %ymm8,%ymm24
- vmovdqa64 %ymm9,%ymm25
- vmovdqa64 %ymm10,%ymm26
- vmovdqa64 %ymm11,%ymm27
- vmovdqa64 %ymm12,%ymm28
- vmovdqa64 %ymm13,%ymm29
- vmovdqa64 %ymm14,%ymm30
- vmovdqa64 %ymm15,%ymm31
-
-.Ldoubleround8:
- # x0 += x4, x12 = rotl32(x12 ^ x0, 16)
- vpaddd %ymm0,%ymm4,%ymm0
- vpxord %ymm0,%ymm12,%ymm12
- vprold $16,%ymm12,%ymm12
- # x1 += x5, x13 = rotl32(x13 ^ x1, 16)
- vpaddd %ymm1,%ymm5,%ymm1
- vpxord %ymm1,%ymm13,%ymm13
- vprold $16,%ymm13,%ymm13
- # x2 += x6, x14 = rotl32(x14 ^ x2, 16)
- vpaddd %ymm2,%ymm6,%ymm2
- vpxord %ymm2,%ymm14,%ymm14
- vprold $16,%ymm14,%ymm14
- # x3 += x7, x15 = rotl32(x15 ^ x3, 16)
- vpaddd %ymm3,%ymm7,%ymm3
- vpxord %ymm3,%ymm15,%ymm15
- vprold $16,%ymm15,%ymm15
-
- # x8 += x12, x4 = rotl32(x4 ^ x8, 12)
- vpaddd %ymm12,%ymm8,%ymm8
- vpxord %ymm8,%ymm4,%ymm4
- vprold $12,%ymm4,%ymm4
- # x9 += x13, x5 = rotl32(x5 ^ x9, 12)
- vpaddd %ymm13,%ymm9,%ymm9
- vpxord %ymm9,%ymm5,%ymm5
- vprold $12,%ymm5,%ymm5
- # x10 += x14, x6 = rotl32(x6 ^ x10, 12)
- vpaddd %ymm14,%ymm10,%ymm10
- vpxord %ymm10,%ymm6,%ymm6
- vprold $12,%ymm6,%ymm6
- # x11 += x15, x7 = rotl32(x7 ^ x11, 12)
- vpaddd %ymm15,%ymm11,%ymm11
- vpxord %ymm11,%ymm7,%ymm7
- vprold $12,%ymm7,%ymm7
-
- # x0 += x4, x12 = rotl32(x12 ^ x0, 8)
- vpaddd %ymm0,%ymm4,%ymm0
- vpxord %ymm0,%ymm12,%ymm12
- vprold $8,%ymm12,%ymm12
- # x1 += x5, x13 = rotl32(x13 ^ x1, 8)
- vpaddd %ymm1,%ymm5,%ymm1
- vpxord %ymm1,%ymm13,%ymm13
- vprold $8,%ymm13,%ymm13
- # x2 += x6, x14 = rotl32(x14 ^ x2, 8)
- vpaddd %ymm2,%ymm6,%ymm2
- vpxord %ymm2,%ymm14,%ymm14
- vprold $8,%ymm14,%ymm14
- # x3 += x7, x15 = rotl32(x15 ^ x3, 8)
- vpaddd %ymm3,%ymm7,%ymm3
- vpxord %ymm3,%ymm15,%ymm15
- vprold $8,%ymm15,%ymm15
-
- # x8 += x12, x4 = rotl32(x4 ^ x8, 7)
- vpaddd %ymm12,%ymm8,%ymm8
- vpxord %ymm8,%ymm4,%ymm4
- vprold $7,%ymm4,%ymm4
- # x9 += x13, x5 = rotl32(x5 ^ x9, 7)
- vpaddd %ymm13,%ymm9,%ymm9
- vpxord %ymm9,%ymm5,%ymm5
- vprold $7,%ymm5,%ymm5
- # x10 += x14, x6 = rotl32(x6 ^ x10, 7)
- vpaddd %ymm14,%ymm10,%ymm10
- vpxord %ymm10,%ymm6,%ymm6
- vprold $7,%ymm6,%ymm6
- # x11 += x15, x7 = rotl32(x7 ^ x11, 7)
- vpaddd %ymm15,%ymm11,%ymm11
- vpxord %ymm11,%ymm7,%ymm7
- vprold $7,%ymm7,%ymm7
-
- # x0 += x5, x15 = rotl32(x15 ^ x0, 16)
- vpaddd %ymm0,%ymm5,%ymm0
- vpxord %ymm0,%ymm15,%ymm15
- vprold $16,%ymm15,%ymm15
- # x1 += x6, x12 = rotl32(x12 ^ x1, 16)
- vpaddd %ymm1,%ymm6,%ymm1
- vpxord %ymm1,%ymm12,%ymm12
- vprold $16,%ymm12,%ymm12
- # x2 += x7, x13 = rotl32(x13 ^ x2, 16)
- vpaddd %ymm2,%ymm7,%ymm2
- vpxord %ymm2,%ymm13,%ymm13
- vprold $16,%ymm13,%ymm13
- # x3 += x4, x14 = rotl32(x14 ^ x3, 16)
- vpaddd %ymm3,%ymm4,%ymm3
- vpxord %ymm3,%ymm14,%ymm14
- vprold $16,%ymm14,%ymm14
-
- # x10 += x15, x5 = rotl32(x5 ^ x10, 12)
- vpaddd %ymm15,%ymm10,%ymm10
- vpxord %ymm10,%ymm5,%ymm5
- vprold $12,%ymm5,%ymm5
- # x11 += x12, x6 = rotl32(x6 ^ x11, 12)
- vpaddd %ymm12,%ymm11,%ymm11
- vpxord %ymm11,%ymm6,%ymm6
- vprold $12,%ymm6,%ymm6
- # x8 += x13, x7 = rotl32(x7 ^ x8, 12)
- vpaddd %ymm13,%ymm8,%ymm8
- vpxord %ymm8,%ymm7,%ymm7
- vprold $12,%ymm7,%ymm7
- # x9 += x14, x4 = rotl32(x4 ^ x9, 12)
- vpaddd %ymm14,%ymm9,%ymm9
- vpxord %ymm9,%ymm4,%ymm4
- vprold $12,%ymm4,%ymm4
-
- # x0 += x5, x15 = rotl32(x15 ^ x0, 8)
- vpaddd %ymm0,%ymm5,%ymm0
- vpxord %ymm0,%ymm15,%ymm15
- vprold $8,%ymm15,%ymm15
- # x1 += x6, x12 = rotl32(x12 ^ x1, 8)
- vpaddd %ymm1,%ymm6,%ymm1
- vpxord %ymm1,%ymm12,%ymm12
- vprold $8,%ymm12,%ymm12
- # x2 += x7, x13 = rotl32(x13 ^ x2, 8)
- vpaddd %ymm2,%ymm7,%ymm2
- vpxord %ymm2,%ymm13,%ymm13
- vprold $8,%ymm13,%ymm13
- # x3 += x4, x14 = rotl32(x14 ^ x3, 8)
- vpaddd %ymm3,%ymm4,%ymm3
- vpxord %ymm3,%ymm14,%ymm14
- vprold $8,%ymm14,%ymm14
-
- # x10 += x15, x5 = rotl32(x5 ^ x10, 7)
- vpaddd %ymm15,%ymm10,%ymm10
- vpxord %ymm10,%ymm5,%ymm5
- vprold $7,%ymm5,%ymm5
- # x11 += x12, x6 = rotl32(x6 ^ x11, 7)
- vpaddd %ymm12,%ymm11,%ymm11
- vpxord %ymm11,%ymm6,%ymm6
- vprold $7,%ymm6,%ymm6
- # x8 += x13, x7 = rotl32(x7 ^ x8, 7)
- vpaddd %ymm13,%ymm8,%ymm8
- vpxord %ymm8,%ymm7,%ymm7
- vprold $7,%ymm7,%ymm7
- # x9 += x14, x4 = rotl32(x4 ^ x9, 7)
- vpaddd %ymm14,%ymm9,%ymm9
- vpxord %ymm9,%ymm4,%ymm4
- vprold $7,%ymm4,%ymm4
-
- sub $2,%r8d
- jnz .Ldoubleround8
-
- # x0..15[0-3] += s[0..15]
- vpaddd %ymm16,%ymm0,%ymm0
- vpaddd %ymm17,%ymm1,%ymm1
- vpaddd %ymm18,%ymm2,%ymm2
- vpaddd %ymm19,%ymm3,%ymm3
- vpaddd %ymm20,%ymm4,%ymm4
- vpaddd %ymm21,%ymm5,%ymm5
- vpaddd %ymm22,%ymm6,%ymm6
- vpaddd %ymm23,%ymm7,%ymm7
- vpaddd %ymm24,%ymm8,%ymm8
- vpaddd %ymm25,%ymm9,%ymm9
- vpaddd %ymm26,%ymm10,%ymm10
- vpaddd %ymm27,%ymm11,%ymm11
- vpaddd %ymm28,%ymm12,%ymm12
- vpaddd %ymm29,%ymm13,%ymm13
- vpaddd %ymm30,%ymm14,%ymm14
- vpaddd %ymm31,%ymm15,%ymm15
-
- # interleave 32-bit words in state n, n+1
- vpunpckldq %ymm1,%ymm0,%ymm16
- vpunpckhdq %ymm1,%ymm0,%ymm17
- vpunpckldq %ymm3,%ymm2,%ymm18
- vpunpckhdq %ymm3,%ymm2,%ymm19
- vpunpckldq %ymm5,%ymm4,%ymm20
- vpunpckhdq %ymm5,%ymm4,%ymm21
- vpunpckldq %ymm7,%ymm6,%ymm22
- vpunpckhdq %ymm7,%ymm6,%ymm23
- vpunpckldq %ymm9,%ymm8,%ymm24
- vpunpckhdq %ymm9,%ymm8,%ymm25
- vpunpckldq %ymm11,%ymm10,%ymm26
- vpunpckhdq %ymm11,%ymm10,%ymm27
- vpunpckldq %ymm13,%ymm12,%ymm28
- vpunpckhdq %ymm13,%ymm12,%ymm29
- vpunpckldq %ymm15,%ymm14,%ymm30
- vpunpckhdq %ymm15,%ymm14,%ymm31
-
- # interleave 64-bit words in state n, n+2
- vpunpcklqdq %ymm18,%ymm16,%ymm0
- vpunpcklqdq %ymm19,%ymm17,%ymm1
- vpunpckhqdq %ymm18,%ymm16,%ymm2
- vpunpckhqdq %ymm19,%ymm17,%ymm3
- vpunpcklqdq %ymm22,%ymm20,%ymm4
- vpunpcklqdq %ymm23,%ymm21,%ymm5
- vpunpckhqdq %ymm22,%ymm20,%ymm6
- vpunpckhqdq %ymm23,%ymm21,%ymm7
- vpunpcklqdq %ymm26,%ymm24,%ymm8
- vpunpcklqdq %ymm27,%ymm25,%ymm9
- vpunpckhqdq %ymm26,%ymm24,%ymm10
- vpunpckhqdq %ymm27,%ymm25,%ymm11
- vpunpcklqdq %ymm30,%ymm28,%ymm12
- vpunpcklqdq %ymm31,%ymm29,%ymm13
- vpunpckhqdq %ymm30,%ymm28,%ymm14
- vpunpckhqdq %ymm31,%ymm29,%ymm15
-
- # interleave 128-bit words in state n, n+4
- # xor/write first four blocks
- vmovdqa64 %ymm0,%ymm16
- vperm2i128 $0x20,%ymm4,%ymm0,%ymm0
- cmp $0x0020,%rcx
- jl .Lxorpart8
- vpxord 0x0000(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x0000(%rsi)
- vmovdqa64 %ymm16,%ymm0
- vperm2i128 $0x31,%ymm4,%ymm0,%ymm4
-
- vperm2i128 $0x20,%ymm12,%ymm8,%ymm0
- cmp $0x0040,%rcx
- jl .Lxorpart8
- vpxord 0x0020(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x0020(%rsi)
- vperm2i128 $0x31,%ymm12,%ymm8,%ymm12
-
- vperm2i128 $0x20,%ymm6,%ymm2,%ymm0
- cmp $0x0060,%rcx
- jl .Lxorpart8
- vpxord 0x0040(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x0040(%rsi)
- vperm2i128 $0x31,%ymm6,%ymm2,%ymm6
-
- vperm2i128 $0x20,%ymm14,%ymm10,%ymm0
- cmp $0x0080,%rcx
- jl .Lxorpart8
- vpxord 0x0060(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x0060(%rsi)
- vperm2i128 $0x31,%ymm14,%ymm10,%ymm14
-
- vperm2i128 $0x20,%ymm5,%ymm1,%ymm0
- cmp $0x00a0,%rcx
- jl .Lxorpart8
- vpxord 0x0080(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x0080(%rsi)
- vperm2i128 $0x31,%ymm5,%ymm1,%ymm5
-
- vperm2i128 $0x20,%ymm13,%ymm9,%ymm0
- cmp $0x00c0,%rcx
- jl .Lxorpart8
- vpxord 0x00a0(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x00a0(%rsi)
- vperm2i128 $0x31,%ymm13,%ymm9,%ymm13
-
- vperm2i128 $0x20,%ymm7,%ymm3,%ymm0
- cmp $0x00e0,%rcx
- jl .Lxorpart8
- vpxord 0x00c0(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x00c0(%rsi)
- vperm2i128 $0x31,%ymm7,%ymm3,%ymm7
-
- vperm2i128 $0x20,%ymm15,%ymm11,%ymm0
- cmp $0x0100,%rcx
- jl .Lxorpart8
- vpxord 0x00e0(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x00e0(%rsi)
- vperm2i128 $0x31,%ymm15,%ymm11,%ymm15
-
- # xor remaining blocks, write to output
- vmovdqa64 %ymm4,%ymm0
- cmp $0x0120,%rcx
- jl .Lxorpart8
- vpxord 0x0100(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x0100(%rsi)
-
- vmovdqa64 %ymm12,%ymm0
- cmp $0x0140,%rcx
- jl .Lxorpart8
- vpxord 0x0120(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x0120(%rsi)
-
- vmovdqa64 %ymm6,%ymm0
- cmp $0x0160,%rcx
- jl .Lxorpart8
- vpxord 0x0140(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x0140(%rsi)
-
- vmovdqa64 %ymm14,%ymm0
- cmp $0x0180,%rcx
- jl .Lxorpart8
- vpxord 0x0160(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x0160(%rsi)
-
- vmovdqa64 %ymm5,%ymm0
- cmp $0x01a0,%rcx
- jl .Lxorpart8
- vpxord 0x0180(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x0180(%rsi)
-
- vmovdqa64 %ymm13,%ymm0
- cmp $0x01c0,%rcx
- jl .Lxorpart8
- vpxord 0x01a0(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x01a0(%rsi)
-
- vmovdqa64 %ymm7,%ymm0
- cmp $0x01e0,%rcx
- jl .Lxorpart8
- vpxord 0x01c0(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x01c0(%rsi)
-
- vmovdqa64 %ymm15,%ymm0
- cmp $0x0200,%rcx
- jl .Lxorpart8
- vpxord 0x01e0(%rdx),%ymm0,%ymm0
- vmovdqu64 %ymm0,0x01e0(%rsi)
-
-.Ldone8:
- vzeroupper
- RET
-
-.Lxorpart8:
- # xor remaining bytes from partial register into output
- mov %rcx,%rax
- and $0x1f,%rcx
- jz .Ldone8
- mov %rax,%r9
- and $~0x1f,%r9
-
- mov $1,%rax
- shld %cl,%rax,%rax
- sub $1,%rax
- kmovq %rax,%k1
-
- vmovdqu8 (%rdx,%r9),%ymm1{%k1}{z}
- vpxord %ymm0,%ymm1,%ymm1
- vmovdqu8 %ymm1,(%rsi,%r9){%k1}
-
- jmp .Ldone8
-
-SYM_FUNC_END(chacha_8block_xor_avx512vl)
diff --git a/arch/x86/crypto/chacha-ssse3-x86_64.S b/arch/x86/crypto/chacha-ssse3-x86_64.S
deleted file mode 100644
index 7111949cd5b9..000000000000
--- a/arch/x86/crypto/chacha-ssse3-x86_64.S
+++ /dev/null
@@ -1,791 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * ChaCha 256-bit cipher algorithm, x64 SSSE3 functions
- *
- * Copyright (C) 2015 Martin Willi
- */
-
-#include <linux/linkage.h>
-#include <asm/frame.h>
-
-.section .rodata.cst16.ROT8, "aM", @progbits, 16
-.align 16
-ROT8: .octa 0x0e0d0c0f0a09080b0605040702010003
-.section .rodata.cst16.ROT16, "aM", @progbits, 16
-.align 16
-ROT16: .octa 0x0d0c0f0e09080b0a0504070601000302
-.section .rodata.cst16.CTRINC, "aM", @progbits, 16
-.align 16
-CTRINC: .octa 0x00000003000000020000000100000000
-
-.text
-
-/*
- * chacha_permute - permute one block
- *
- * Permute one 64-byte block where the state matrix is in %xmm0-%xmm3. This
- * function performs matrix operations on four words in parallel, but requires
- * shuffling to rearrange the words after each round. 8/16-bit word rotation is
- * done with the slightly better performing SSSE3 byte shuffling, 7/12-bit word
- * rotation uses traditional shift+OR.
- *
- * The round count is given in %r8d.
- *
- * Clobbers: %r8d, %xmm4-%xmm7
- */
-SYM_FUNC_START_LOCAL(chacha_permute)
-
- movdqa ROT8(%rip),%xmm4
- movdqa ROT16(%rip),%xmm5
-
-.Ldoubleround:
- # x0 += x1, x3 = rotl32(x3 ^ x0, 16)
- paddd %xmm1,%xmm0
- pxor %xmm0,%xmm3
- pshufb %xmm5,%xmm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 12)
- paddd %xmm3,%xmm2
- pxor %xmm2,%xmm1
- movdqa %xmm1,%xmm6
- pslld $12,%xmm6
- psrld $20,%xmm1
- por %xmm6,%xmm1
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 8)
- paddd %xmm1,%xmm0
- pxor %xmm0,%xmm3
- pshufb %xmm4,%xmm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 7)
- paddd %xmm3,%xmm2
- pxor %xmm2,%xmm1
- movdqa %xmm1,%xmm7
- pslld $7,%xmm7
- psrld $25,%xmm1
- por %xmm7,%xmm1
-
- # x1 = shuffle32(x1, MASK(0, 3, 2, 1))
- pshufd $0x39,%xmm1,%xmm1
- # x2 = shuffle32(x2, MASK(1, 0, 3, 2))
- pshufd $0x4e,%xmm2,%xmm2
- # x3 = shuffle32(x3, MASK(2, 1, 0, 3))
- pshufd $0x93,%xmm3,%xmm3
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 16)
- paddd %xmm1,%xmm0
- pxor %xmm0,%xmm3
- pshufb %xmm5,%xmm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 12)
- paddd %xmm3,%xmm2
- pxor %xmm2,%xmm1
- movdqa %xmm1,%xmm6
- pslld $12,%xmm6
- psrld $20,%xmm1
- por %xmm6,%xmm1
-
- # x0 += x1, x3 = rotl32(x3 ^ x0, 8)
- paddd %xmm1,%xmm0
- pxor %xmm0,%xmm3
- pshufb %xmm4,%xmm3
-
- # x2 += x3, x1 = rotl32(x1 ^ x2, 7)
- paddd %xmm3,%xmm2
- pxor %xmm2,%xmm1
- movdqa %xmm1,%xmm7
- pslld $7,%xmm7
- psrld $25,%xmm1
- por %xmm7,%xmm1
-
- # x1 = shuffle32(x1, MASK(2, 1, 0, 3))
- pshufd $0x93,%xmm1,%xmm1
- # x2 = shuffle32(x2, MASK(1, 0, 3, 2))
- pshufd $0x4e,%xmm2,%xmm2
- # x3 = shuffle32(x3, MASK(0, 3, 2, 1))
- pshufd $0x39,%xmm3,%xmm3
-
- sub $2,%r8d
- jnz .Ldoubleround
-
- RET
-SYM_FUNC_END(chacha_permute)
-
-SYM_FUNC_START(chacha_block_xor_ssse3)
- # %rdi: Input state matrix, s
- # %rsi: up to 1 data block output, o
- # %rdx: up to 1 data block input, i
- # %rcx: input/output length in bytes
- # %r8d: nrounds
- FRAME_BEGIN
-
- # x0..3 = s0..3
- movdqu 0x00(%rdi),%xmm0
- movdqu 0x10(%rdi),%xmm1
- movdqu 0x20(%rdi),%xmm2
- movdqu 0x30(%rdi),%xmm3
- movdqa %xmm0,%xmm8
- movdqa %xmm1,%xmm9
- movdqa %xmm2,%xmm10
- movdqa %xmm3,%xmm11
-
- mov %rcx,%rax
- call chacha_permute
-
- # o0 = i0 ^ (x0 + s0)
- paddd %xmm8,%xmm0
- cmp $0x10,%rax
- jl .Lxorpart
- movdqu 0x00(%rdx),%xmm4
- pxor %xmm4,%xmm0
- movdqu %xmm0,0x00(%rsi)
- # o1 = i1 ^ (x1 + s1)
- paddd %xmm9,%xmm1
- movdqa %xmm1,%xmm0
- cmp $0x20,%rax
- jl .Lxorpart
- movdqu 0x10(%rdx),%xmm0
- pxor %xmm1,%xmm0
- movdqu %xmm0,0x10(%rsi)
- # o2 = i2 ^ (x2 + s2)
- paddd %xmm10,%xmm2
- movdqa %xmm2,%xmm0
- cmp $0x30,%rax
- jl .Lxorpart
- movdqu 0x20(%rdx),%xmm0
- pxor %xmm2,%xmm0
- movdqu %xmm0,0x20(%rsi)
- # o3 = i3 ^ (x3 + s3)
- paddd %xmm11,%xmm3
- movdqa %xmm3,%xmm0
- cmp $0x40,%rax
- jl .Lxorpart
- movdqu 0x30(%rdx),%xmm0
- pxor %xmm3,%xmm0
- movdqu %xmm0,0x30(%rsi)
-
-.Ldone:
- FRAME_END
- RET
-
-.Lxorpart:
- # xor remaining bytes from partial register into output
- mov %rax,%r9
- and $0x0f,%r9
- jz .Ldone
- and $~0x0f,%rax
-
- mov %rsi,%r11
-
- lea 8(%rsp),%r10
- sub $0x10,%rsp
- and $~31,%rsp
-
- lea (%rdx,%rax),%rsi
- mov %rsp,%rdi
- mov %r9,%rcx
- rep movsb
-
- pxor 0x00(%rsp),%xmm0
- movdqa %xmm0,0x00(%rsp)
-
- mov %rsp,%rsi
- lea (%r11,%rax),%rdi
- mov %r9,%rcx
- rep movsb
-
- lea -8(%r10),%rsp
- jmp .Ldone
-
-SYM_FUNC_END(chacha_block_xor_ssse3)
-
-SYM_FUNC_START(hchacha_block_ssse3)
- # %rdi: Input state matrix, s
- # %rsi: output (8 32-bit words)
- # %edx: nrounds
- FRAME_BEGIN
-
- movdqu 0x00(%rdi),%xmm0
- movdqu 0x10(%rdi),%xmm1
- movdqu 0x20(%rdi),%xmm2
- movdqu 0x30(%rdi),%xmm3
-
- mov %edx,%r8d
- call chacha_permute
-
- movdqu %xmm0,0x00(%rsi)
- movdqu %xmm3,0x10(%rsi)
-
- FRAME_END
- RET
-SYM_FUNC_END(hchacha_block_ssse3)
-
-SYM_FUNC_START(chacha_4block_xor_ssse3)
- # %rdi: Input state matrix, s
- # %rsi: up to 4 data blocks output, o
- # %rdx: up to 4 data blocks input, i
- # %rcx: input/output length in bytes
- # %r8d: nrounds
-
- # This function encrypts four consecutive ChaCha blocks by loading the
- # the state matrix in SSE registers four times. As we need some scratch
- # registers, we save the first four registers on the stack. The
- # algorithm performs each operation on the corresponding word of each
- # state matrix, hence requires no word shuffling. For final XORing step
- # we transpose the matrix by interleaving 32- and then 64-bit words,
- # which allows us to do XOR in SSE registers. 8/16-bit word rotation is
- # done with the slightly better performing SSSE3 byte shuffling,
- # 7/12-bit word rotation uses traditional shift+OR.
-
- lea 8(%rsp),%r10
- sub $0x80,%rsp
- and $~63,%rsp
- mov %rcx,%rax
-
- # x0..15[0-3] = s0..3[0..3]
- movq 0x00(%rdi),%xmm1
- pshufd $0x00,%xmm1,%xmm0
- pshufd $0x55,%xmm1,%xmm1
- movq 0x08(%rdi),%xmm3
- pshufd $0x00,%xmm3,%xmm2
- pshufd $0x55,%xmm3,%xmm3
- movq 0x10(%rdi),%xmm5
- pshufd $0x00,%xmm5,%xmm4
- pshufd $0x55,%xmm5,%xmm5
- movq 0x18(%rdi),%xmm7
- pshufd $0x00,%xmm7,%xmm6
- pshufd $0x55,%xmm7,%xmm7
- movq 0x20(%rdi),%xmm9
- pshufd $0x00,%xmm9,%xmm8
- pshufd $0x55,%xmm9,%xmm9
- movq 0x28(%rdi),%xmm11
- pshufd $0x00,%xmm11,%xmm10
- pshufd $0x55,%xmm11,%xmm11
- movq 0x30(%rdi),%xmm13
- pshufd $0x00,%xmm13,%xmm12
- pshufd $0x55,%xmm13,%xmm13
- movq 0x38(%rdi),%xmm15
- pshufd $0x00,%xmm15,%xmm14
- pshufd $0x55,%xmm15,%xmm15
- # x0..3 on stack
- movdqa %xmm0,0x00(%rsp)
- movdqa %xmm1,0x10(%rsp)
- movdqa %xmm2,0x20(%rsp)
- movdqa %xmm3,0x30(%rsp)
-
- movdqa CTRINC(%rip),%xmm1
- movdqa ROT8(%rip),%xmm2
- movdqa ROT16(%rip),%xmm3
-
- # x12 += counter values 0-3
- paddd %xmm1,%xmm12
-
-.Ldoubleround4:
- # x0 += x4, x12 = rotl32(x12 ^ x0, 16)
- movdqa 0x00(%rsp),%xmm0
- paddd %xmm4,%xmm0
- movdqa %xmm0,0x00(%rsp)
- pxor %xmm0,%xmm12
- pshufb %xmm3,%xmm12
- # x1 += x5, x13 = rotl32(x13 ^ x1, 16)
- movdqa 0x10(%rsp),%xmm0
- paddd %xmm5,%xmm0
- movdqa %xmm0,0x10(%rsp)
- pxor %xmm0,%xmm13
- pshufb %xmm3,%xmm13
- # x2 += x6, x14 = rotl32(x14 ^ x2, 16)
- movdqa 0x20(%rsp),%xmm0
- paddd %xmm6,%xmm0
- movdqa %xmm0,0x20(%rsp)
- pxor %xmm0,%xmm14
- pshufb %xmm3,%xmm14
- # x3 += x7, x15 = rotl32(x15 ^ x3, 16)
- movdqa 0x30(%rsp),%xmm0
- paddd %xmm7,%xmm0
- movdqa %xmm0,0x30(%rsp)
- pxor %xmm0,%xmm15
- pshufb %xmm3,%xmm15
-
- # x8 += x12, x4 = rotl32(x4 ^ x8, 12)
- paddd %xmm12,%xmm8
- pxor %xmm8,%xmm4
- movdqa %xmm4,%xmm0
- pslld $12,%xmm0
- psrld $20,%xmm4
- por %xmm0,%xmm4
- # x9 += x13, x5 = rotl32(x5 ^ x9, 12)
- paddd %xmm13,%xmm9
- pxor %xmm9,%xmm5
- movdqa %xmm5,%xmm0
- pslld $12,%xmm0
- psrld $20,%xmm5
- por %xmm0,%xmm5
- # x10 += x14, x6 = rotl32(x6 ^ x10, 12)
- paddd %xmm14,%xmm10
- pxor %xmm10,%xmm6
- movdqa %xmm6,%xmm0
- pslld $12,%xmm0
- psrld $20,%xmm6
- por %xmm0,%xmm6
- # x11 += x15, x7 = rotl32(x7 ^ x11, 12)
- paddd %xmm15,%xmm11
- pxor %xmm11,%xmm7
- movdqa %xmm7,%xmm0
- pslld $12,%xmm0
- psrld $20,%xmm7
- por %xmm0,%xmm7
-
- # x0 += x4, x12 = rotl32(x12 ^ x0, 8)
- movdqa 0x00(%rsp),%xmm0
- paddd %xmm4,%xmm0
- movdqa %xmm0,0x00(%rsp)
- pxor %xmm0,%xmm12
- pshufb %xmm2,%xmm12
- # x1 += x5, x13 = rotl32(x13 ^ x1, 8)
- movdqa 0x10(%rsp),%xmm0
- paddd %xmm5,%xmm0
- movdqa %xmm0,0x10(%rsp)
- pxor %xmm0,%xmm13
- pshufb %xmm2,%xmm13
- # x2 += x6, x14 = rotl32(x14 ^ x2, 8)
- movdqa 0x20(%rsp),%xmm0
- paddd %xmm6,%xmm0
- movdqa %xmm0,0x20(%rsp)
- pxor %xmm0,%xmm14
- pshufb %xmm2,%xmm14
- # x3 += x7, x15 = rotl32(x15 ^ x3, 8)
- movdqa 0x30(%rsp),%xmm0
- paddd %xmm7,%xmm0
- movdqa %xmm0,0x30(%rsp)
- pxor %xmm0,%xmm15
- pshufb %xmm2,%xmm15
-
- # x8 += x12, x4 = rotl32(x4 ^ x8, 7)
- paddd %xmm12,%xmm8
- pxor %xmm8,%xmm4
- movdqa %xmm4,%xmm0
- pslld $7,%xmm0
- psrld $25,%xmm4
- por %xmm0,%xmm4
- # x9 += x13, x5 = rotl32(x5 ^ x9, 7)
- paddd %xmm13,%xmm9
- pxor %xmm9,%xmm5
- movdqa %xmm5,%xmm0
- pslld $7,%xmm0
- psrld $25,%xmm5
- por %xmm0,%xmm5
- # x10 += x14, x6 = rotl32(x6 ^ x10, 7)
- paddd %xmm14,%xmm10
- pxor %xmm10,%xmm6
- movdqa %xmm6,%xmm0
- pslld $7,%xmm0
- psrld $25,%xmm6
- por %xmm0,%xmm6
- # x11 += x15, x7 = rotl32(x7 ^ x11, 7)
- paddd %xmm15,%xmm11
- pxor %xmm11,%xmm7
- movdqa %xmm7,%xmm0
- pslld $7,%xmm0
- psrld $25,%xmm7
- por %xmm0,%xmm7
-
- # x0 += x5, x15 = rotl32(x15 ^ x0, 16)
- movdqa 0x00(%rsp),%xmm0
- paddd %xmm5,%xmm0
- movdqa %xmm0,0x00(%rsp)
- pxor %xmm0,%xmm15
- pshufb %xmm3,%xmm15
- # x1 += x6, x12 = rotl32(x12 ^ x1, 16)
- movdqa 0x10(%rsp),%xmm0
- paddd %xmm6,%xmm0
- movdqa %xmm0,0x10(%rsp)
- pxor %xmm0,%xmm12
- pshufb %xmm3,%xmm12
- # x2 += x7, x13 = rotl32(x13 ^ x2, 16)
- movdqa 0x20(%rsp),%xmm0
- paddd %xmm7,%xmm0
- movdqa %xmm0,0x20(%rsp)
- pxor %xmm0,%xmm13
- pshufb %xmm3,%xmm13
- # x3 += x4, x14 = rotl32(x14 ^ x3, 16)
- movdqa 0x30(%rsp),%xmm0
- paddd %xmm4,%xmm0
- movdqa %xmm0,0x30(%rsp)
- pxor %xmm0,%xmm14
- pshufb %xmm3,%xmm14
-
- # x10 += x15, x5 = rotl32(x5 ^ x10, 12)
- paddd %xmm15,%xmm10
- pxor %xmm10,%xmm5
- movdqa %xmm5,%xmm0
- pslld $12,%xmm0
- psrld $20,%xmm5
- por %xmm0,%xmm5
- # x11 += x12, x6 = rotl32(x6 ^ x11, 12)
- paddd %xmm12,%xmm11
- pxor %xmm11,%xmm6
- movdqa %xmm6,%xmm0
- pslld $12,%xmm0
- psrld $20,%xmm6
- por %xmm0,%xmm6
- # x8 += x13, x7 = rotl32(x7 ^ x8, 12)
- paddd %xmm13,%xmm8
- pxor %xmm8,%xmm7
- movdqa %xmm7,%xmm0
- pslld $12,%xmm0
- psrld $20,%xmm7
- por %xmm0,%xmm7
- # x9 += x14, x4 = rotl32(x4 ^ x9, 12)
- paddd %xmm14,%xmm9
- pxor %xmm9,%xmm4
- movdqa %xmm4,%xmm0
- pslld $12,%xmm0
- psrld $20,%xmm4
- por %xmm0,%xmm4
-
- # x0 += x5, x15 = rotl32(x15 ^ x0, 8)
- movdqa 0x00(%rsp),%xmm0
- paddd %xmm5,%xmm0
- movdqa %xmm0,0x00(%rsp)
- pxor %xmm0,%xmm15
- pshufb %xmm2,%xmm15
- # x1 += x6, x12 = rotl32(x12 ^ x1, 8)
- movdqa 0x10(%rsp),%xmm0
- paddd %xmm6,%xmm0
- movdqa %xmm0,0x10(%rsp)
- pxor %xmm0,%xmm12
- pshufb %xmm2,%xmm12
- # x2 += x7, x13 = rotl32(x13 ^ x2, 8)
- movdqa 0x20(%rsp),%xmm0
- paddd %xmm7,%xmm0
- movdqa %xmm0,0x20(%rsp)
- pxor %xmm0,%xmm13
- pshufb %xmm2,%xmm13
- # x3 += x4, x14 = rotl32(x14 ^ x3, 8)
- movdqa 0x30(%rsp),%xmm0
- paddd %xmm4,%xmm0
- movdqa %xmm0,0x30(%rsp)
- pxor %xmm0,%xmm14
- pshufb %xmm2,%xmm14
-
- # x10 += x15, x5 = rotl32(x5 ^ x10, 7)
- paddd %xmm15,%xmm10
- pxor %xmm10,%xmm5
- movdqa %xmm5,%xmm0
- pslld $7,%xmm0
- psrld $25,%xmm5
- por %xmm0,%xmm5
- # x11 += x12, x6 = rotl32(x6 ^ x11, 7)
- paddd %xmm12,%xmm11
- pxor %xmm11,%xmm6
- movdqa %xmm6,%xmm0
- pslld $7,%xmm0
- psrld $25,%xmm6
- por %xmm0,%xmm6
- # x8 += x13, x7 = rotl32(x7 ^ x8, 7)
- paddd %xmm13,%xmm8
- pxor %xmm8,%xmm7
- movdqa %xmm7,%xmm0
- pslld $7,%xmm0
- psrld $25,%xmm7
- por %xmm0,%xmm7
- # x9 += x14, x4 = rotl32(x4 ^ x9, 7)
- paddd %xmm14,%xmm9
- pxor %xmm9,%xmm4
- movdqa %xmm4,%xmm0
- pslld $7,%xmm0
- psrld $25,%xmm4
- por %xmm0,%xmm4
-
- sub $2,%r8d
- jnz .Ldoubleround4
-
- # x0[0-3] += s0[0]
- # x1[0-3] += s0[1]
- movq 0x00(%rdi),%xmm3
- pshufd $0x00,%xmm3,%xmm2
- pshufd $0x55,%xmm3,%xmm3
- paddd 0x00(%rsp),%xmm2
- movdqa %xmm2,0x00(%rsp)
- paddd 0x10(%rsp),%xmm3
- movdqa %xmm3,0x10(%rsp)
- # x2[0-3] += s0[2]
- # x3[0-3] += s0[3]
- movq 0x08(%rdi),%xmm3
- pshufd $0x00,%xmm3,%xmm2
- pshufd $0x55,%xmm3,%xmm3
- paddd 0x20(%rsp),%xmm2
- movdqa %xmm2,0x20(%rsp)
- paddd 0x30(%rsp),%xmm3
- movdqa %xmm3,0x30(%rsp)
-
- # x4[0-3] += s1[0]
- # x5[0-3] += s1[1]
- movq 0x10(%rdi),%xmm3
- pshufd $0x00,%xmm3,%xmm2
- pshufd $0x55,%xmm3,%xmm3
- paddd %xmm2,%xmm4
- paddd %xmm3,%xmm5
- # x6[0-3] += s1[2]
- # x7[0-3] += s1[3]
- movq 0x18(%rdi),%xmm3
- pshufd $0x00,%xmm3,%xmm2
- pshufd $0x55,%xmm3,%xmm3
- paddd %xmm2,%xmm6
- paddd %xmm3,%xmm7
-
- # x8[0-3] += s2[0]
- # x9[0-3] += s2[1]
- movq 0x20(%rdi),%xmm3
- pshufd $0x00,%xmm3,%xmm2
- pshufd $0x55,%xmm3,%xmm3
- paddd %xmm2,%xmm8
- paddd %xmm3,%xmm9
- # x10[0-3] += s2[2]
- # x11[0-3] += s2[3]
- movq 0x28(%rdi),%xmm3
- pshufd $0x00,%xmm3,%xmm2
- pshufd $0x55,%xmm3,%xmm3
- paddd %xmm2,%xmm10
- paddd %xmm3,%xmm11
-
- # x12[0-3] += s3[0]
- # x13[0-3] += s3[1]
- movq 0x30(%rdi),%xmm3
- pshufd $0x00,%xmm3,%xmm2
- pshufd $0x55,%xmm3,%xmm3
- paddd %xmm2,%xmm12
- paddd %xmm3,%xmm13
- # x14[0-3] += s3[2]
- # x15[0-3] += s3[3]
- movq 0x38(%rdi),%xmm3
- pshufd $0x00,%xmm3,%xmm2
- pshufd $0x55,%xmm3,%xmm3
- paddd %xmm2,%xmm14
- paddd %xmm3,%xmm15
-
- # x12 += counter values 0-3
- paddd %xmm1,%xmm12
-
- # interleave 32-bit words in state n, n+1
- movdqa 0x00(%rsp),%xmm0
- movdqa 0x10(%rsp),%xmm1
- movdqa %xmm0,%xmm2
- punpckldq %xmm1,%xmm2
- punpckhdq %xmm1,%xmm0
- movdqa %xmm2,0x00(%rsp)
- movdqa %xmm0,0x10(%rsp)
- movdqa 0x20(%rsp),%xmm0
- movdqa 0x30(%rsp),%xmm1
- movdqa %xmm0,%xmm2
- punpckldq %xmm1,%xmm2
- punpckhdq %xmm1,%xmm0
- movdqa %xmm2,0x20(%rsp)
- movdqa %xmm0,0x30(%rsp)
- movdqa %xmm4,%xmm0
- punpckldq %xmm5,%xmm4
- punpckhdq %xmm5,%xmm0
- movdqa %xmm0,%xmm5
- movdqa %xmm6,%xmm0
- punpckldq %xmm7,%xmm6
- punpckhdq %xmm7,%xmm0
- movdqa %xmm0,%xmm7
- movdqa %xmm8,%xmm0
- punpckldq %xmm9,%xmm8
- punpckhdq %xmm9,%xmm0
- movdqa %xmm0,%xmm9
- movdqa %xmm10,%xmm0
- punpckldq %xmm11,%xmm10
- punpckhdq %xmm11,%xmm0
- movdqa %xmm0,%xmm11
- movdqa %xmm12,%xmm0
- punpckldq %xmm13,%xmm12
- punpckhdq %xmm13,%xmm0
- movdqa %xmm0,%xmm13
- movdqa %xmm14,%xmm0
- punpckldq %xmm15,%xmm14
- punpckhdq %xmm15,%xmm0
- movdqa %xmm0,%xmm15
-
- # interleave 64-bit words in state n, n+2
- movdqa 0x00(%rsp),%xmm0
- movdqa 0x20(%rsp),%xmm1
- movdqa %xmm0,%xmm2
- punpcklqdq %xmm1,%xmm2
- punpckhqdq %xmm1,%xmm0
- movdqa %xmm2,0x00(%rsp)
- movdqa %xmm0,0x20(%rsp)
- movdqa 0x10(%rsp),%xmm0
- movdqa 0x30(%rsp),%xmm1
- movdqa %xmm0,%xmm2
- punpcklqdq %xmm1,%xmm2
- punpckhqdq %xmm1,%xmm0
- movdqa %xmm2,0x10(%rsp)
- movdqa %xmm0,0x30(%rsp)
- movdqa %xmm4,%xmm0
- punpcklqdq %xmm6,%xmm4
- punpckhqdq %xmm6,%xmm0
- movdqa %xmm0,%xmm6
- movdqa %xmm5,%xmm0
- punpcklqdq %xmm7,%xmm5
- punpckhqdq %xmm7,%xmm0
- movdqa %xmm0,%xmm7
- movdqa %xmm8,%xmm0
- punpcklqdq %xmm10,%xmm8
- punpckhqdq %xmm10,%xmm0
- movdqa %xmm0,%xmm10
- movdqa %xmm9,%xmm0
- punpcklqdq %xmm11,%xmm9
- punpckhqdq %xmm11,%xmm0
- movdqa %xmm0,%xmm11
- movdqa %xmm12,%xmm0
- punpcklqdq %xmm14,%xmm12
- punpckhqdq %xmm14,%xmm0
- movdqa %xmm0,%xmm14
- movdqa %xmm13,%xmm0
- punpcklqdq %xmm15,%xmm13
- punpckhqdq %xmm15,%xmm0
- movdqa %xmm0,%xmm15
-
- # xor with corresponding input, write to output
- movdqa 0x00(%rsp),%xmm0
- cmp $0x10,%rax
- jl .Lxorpart4
- movdqu 0x00(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0x00(%rsi)
-
- movdqu %xmm4,%xmm0
- cmp $0x20,%rax
- jl .Lxorpart4
- movdqu 0x10(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0x10(%rsi)
-
- movdqu %xmm8,%xmm0
- cmp $0x30,%rax
- jl .Lxorpart4
- movdqu 0x20(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0x20(%rsi)
-
- movdqu %xmm12,%xmm0
- cmp $0x40,%rax
- jl .Lxorpart4
- movdqu 0x30(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0x30(%rsi)
-
- movdqa 0x20(%rsp),%xmm0
- cmp $0x50,%rax
- jl .Lxorpart4
- movdqu 0x40(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0x40(%rsi)
-
- movdqu %xmm6,%xmm0
- cmp $0x60,%rax
- jl .Lxorpart4
- movdqu 0x50(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0x50(%rsi)
-
- movdqu %xmm10,%xmm0
- cmp $0x70,%rax
- jl .Lxorpart4
- movdqu 0x60(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0x60(%rsi)
-
- movdqu %xmm14,%xmm0
- cmp $0x80,%rax
- jl .Lxorpart4
- movdqu 0x70(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0x70(%rsi)
-
- movdqa 0x10(%rsp),%xmm0
- cmp $0x90,%rax
- jl .Lxorpart4
- movdqu 0x80(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0x80(%rsi)
-
- movdqu %xmm5,%xmm0
- cmp $0xa0,%rax
- jl .Lxorpart4
- movdqu 0x90(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0x90(%rsi)
-
- movdqu %xmm9,%xmm0
- cmp $0xb0,%rax
- jl .Lxorpart4
- movdqu 0xa0(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0xa0(%rsi)
-
- movdqu %xmm13,%xmm0
- cmp $0xc0,%rax
- jl .Lxorpart4
- movdqu 0xb0(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0xb0(%rsi)
-
- movdqa 0x30(%rsp),%xmm0
- cmp $0xd0,%rax
- jl .Lxorpart4
- movdqu 0xc0(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0xc0(%rsi)
-
- movdqu %xmm7,%xmm0
- cmp $0xe0,%rax
- jl .Lxorpart4
- movdqu 0xd0(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0xd0(%rsi)
-
- movdqu %xmm11,%xmm0
- cmp $0xf0,%rax
- jl .Lxorpart4
- movdqu 0xe0(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0xe0(%rsi)
-
- movdqu %xmm15,%xmm0
- cmp $0x100,%rax
- jl .Lxorpart4
- movdqu 0xf0(%rdx),%xmm1
- pxor %xmm1,%xmm0
- movdqu %xmm0,0xf0(%rsi)
-
-.Ldone4:
- lea -8(%r10),%rsp
- RET
-
-.Lxorpart4:
- # xor remaining bytes from partial register into output
- mov %rax,%r9
- and $0x0f,%r9
- jz .Ldone4
- and $~0x0f,%rax
-
- mov %rsi,%r11
-
- lea (%rdx,%rax),%rsi
- mov %rsp,%rdi
- mov %r9,%rcx
- rep movsb
-
- pxor 0x00(%rsp),%xmm0
- movdqa %xmm0,0x00(%rsp)
-
- mov %rsp,%rsi
- lea (%r11,%rax),%rdi
- mov %r9,%rcx
- rep movsb
-
- jmp .Ldone4
-
-SYM_FUNC_END(chacha_4block_xor_ssse3)
diff --git a/arch/x86/crypto/chacha_glue.c b/arch/x86/crypto/chacha_glue.c
deleted file mode 100644
index 8bb74a272879..000000000000
--- a/arch/x86/crypto/chacha_glue.c
+++ /dev/null
@@ -1,311 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * x64 SIMD accelerated ChaCha and XChaCha stream ciphers,
- * including ChaCha20 (RFC7539)
- *
- * Copyright (C) 2015 Martin Willi
- */
-
-#include <crypto/algapi.h>
-#include <crypto/internal/chacha.h>
-#include <crypto/internal/simd.h>
-#include <crypto/internal/skcipher.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/sizes.h>
-#include <asm/simd.h>
-
-asmlinkage void chacha_block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void chacha_4block_xor_ssse3(u32 *state, u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void hchacha_block_ssse3(const u32 *state, u32 *out, int nrounds);
-
-asmlinkage void chacha_2block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void chacha_4block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void chacha_8block_xor_avx2(u32 *state, u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-
-asmlinkage void chacha_2block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void chacha_4block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-asmlinkage void chacha_8block_xor_avx512vl(u32 *state, u8 *dst, const u8 *src,
- unsigned int len, int nrounds);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_simd);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx2);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(chacha_use_avx512vl);
-
-static unsigned int chacha_advance(unsigned int len, unsigned int maxblocks)
-{
- len = min(len, maxblocks * CHACHA_BLOCK_SIZE);
- return round_up(len, CHACHA_BLOCK_SIZE) / CHACHA_BLOCK_SIZE;
-}
-
-static void chacha_dosimd(u32 *state, u8 *dst, const u8 *src,
- unsigned int bytes, int nrounds)
-{
- if (IS_ENABLED(CONFIG_AS_AVX512) &&
- static_branch_likely(&chacha_use_avx512vl)) {
- while (bytes >= CHACHA_BLOCK_SIZE * 8) {
- chacha_8block_xor_avx512vl(state, dst, src, bytes,
- nrounds);
- bytes -= CHACHA_BLOCK_SIZE * 8;
- src += CHACHA_BLOCK_SIZE * 8;
- dst += CHACHA_BLOCK_SIZE * 8;
- state[12] += 8;
- }
- if (bytes > CHACHA_BLOCK_SIZE * 4) {
- chacha_8block_xor_avx512vl(state, dst, src, bytes,
- nrounds);
- state[12] += chacha_advance(bytes, 8);
- return;
- }
- if (bytes > CHACHA_BLOCK_SIZE * 2) {
- chacha_4block_xor_avx512vl(state, dst, src, bytes,
- nrounds);
- state[12] += chacha_advance(bytes, 4);
- return;
- }
- if (bytes) {
- chacha_2block_xor_avx512vl(state, dst, src, bytes,
- nrounds);
- state[12] += chacha_advance(bytes, 2);
- return;
- }
- }
-
- if (static_branch_likely(&chacha_use_avx2)) {
- while (bytes >= CHACHA_BLOCK_SIZE * 8) {
- chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
- bytes -= CHACHA_BLOCK_SIZE * 8;
- src += CHACHA_BLOCK_SIZE * 8;
- dst += CHACHA_BLOCK_SIZE * 8;
- state[12] += 8;
- }
- if (bytes > CHACHA_BLOCK_SIZE * 4) {
- chacha_8block_xor_avx2(state, dst, src, bytes, nrounds);
- state[12] += chacha_advance(bytes, 8);
- return;
- }
- if (bytes > CHACHA_BLOCK_SIZE * 2) {
- chacha_4block_xor_avx2(state, dst, src, bytes, nrounds);
- state[12] += chacha_advance(bytes, 4);
- return;
- }
- if (bytes > CHACHA_BLOCK_SIZE) {
- chacha_2block_xor_avx2(state, dst, src, bytes, nrounds);
- state[12] += chacha_advance(bytes, 2);
- return;
- }
- }
-
- while (bytes >= CHACHA_BLOCK_SIZE * 4) {
- chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
- bytes -= CHACHA_BLOCK_SIZE * 4;
- src += CHACHA_BLOCK_SIZE * 4;
- dst += CHACHA_BLOCK_SIZE * 4;
- state[12] += 4;
- }
- if (bytes > CHACHA_BLOCK_SIZE) {
- chacha_4block_xor_ssse3(state, dst, src, bytes, nrounds);
- state[12] += chacha_advance(bytes, 4);
- return;
- }
- if (bytes) {
- chacha_block_xor_ssse3(state, dst, src, bytes, nrounds);
- state[12]++;
- }
-}
-
-void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
-{
- if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable()) {
- hchacha_block_generic(state, stream, nrounds);
- } else {
- kernel_fpu_begin();
- hchacha_block_ssse3(state, stream, nrounds);
- kernel_fpu_end();
- }
-}
-EXPORT_SYMBOL(hchacha_block_arch);
-
-void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
- int nrounds)
-{
- if (!static_branch_likely(&chacha_use_simd) || !crypto_simd_usable() ||
- bytes <= CHACHA_BLOCK_SIZE)
- return chacha_crypt_generic(state, dst, src, bytes, nrounds);
-
- do {
- unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
-
- kernel_fpu_begin();
- chacha_dosimd(state, dst, src, todo, nrounds);
- kernel_fpu_end();
-
- bytes -= todo;
- src += todo;
- dst += todo;
- } while (bytes);
-}
-EXPORT_SYMBOL(chacha_crypt_arch);
-
-static int chacha_simd_stream_xor(struct skcipher_request *req,
- const struct chacha_ctx *ctx, const u8 *iv)
-{
- u32 state[CHACHA_STATE_WORDS] __aligned(8);
- struct skcipher_walk walk;
- int err;
-
- err = skcipher_walk_virt(&walk, req, false);
-
- chacha_init(state, ctx->key, iv);
-
- while (walk.nbytes > 0) {
- unsigned int nbytes = walk.nbytes;
-
- if (nbytes < walk.total)
- nbytes = round_down(nbytes, walk.stride);
-
- if (!static_branch_likely(&chacha_use_simd) ||
- !crypto_simd_usable()) {
- chacha_crypt_generic(state, walk.dst.virt.addr,
- walk.src.virt.addr, nbytes,
- ctx->nrounds);
- } else {
- kernel_fpu_begin();
- chacha_dosimd(state, walk.dst.virt.addr,
- walk.src.virt.addr, nbytes,
- ctx->nrounds);
- kernel_fpu_end();
- }
- err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
- }
-
- return err;
-}
-
-static int chacha_simd(struct skcipher_request *req)
-{
- struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
-
- return chacha_simd_stream_xor(req, ctx, req->iv);
-}
-
-static int xchacha_simd(struct skcipher_request *req)
-{
- struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
- struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
- u32 state[CHACHA_STATE_WORDS] __aligned(8);
- struct chacha_ctx subctx;
- u8 real_iv[16];
-
- chacha_init(state, ctx->key, req->iv);
-
- if (req->cryptlen > CHACHA_BLOCK_SIZE && crypto_simd_usable()) {
- kernel_fpu_begin();
- hchacha_block_ssse3(state, subctx.key, ctx->nrounds);
- kernel_fpu_end();
- } else {
- hchacha_block_generic(state, subctx.key, ctx->nrounds);
- }
- subctx.nrounds = ctx->nrounds;
-
- memcpy(&real_iv[0], req->iv + 24, 8);
- memcpy(&real_iv[8], req->iv + 16, 8);
- return chacha_simd_stream_xor(req, &subctx, real_iv);
-}
-
-static struct skcipher_alg algs[] = {
- {
- .base.cra_name = "chacha20",
- .base.cra_driver_name = "chacha20-simd",
- .base.cra_priority = 300,
- .base.cra_blocksize = 1,
- .base.cra_ctxsize = sizeof(struct chacha_ctx),
- .base.cra_module = THIS_MODULE,
-
- .min_keysize = CHACHA_KEY_SIZE,
- .max_keysize = CHACHA_KEY_SIZE,
- .ivsize = CHACHA_IV_SIZE,
- .chunksize = CHACHA_BLOCK_SIZE,
- .setkey = chacha20_setkey,
- .encrypt = chacha_simd,
- .decrypt = chacha_simd,
- }, {
- .base.cra_name = "xchacha20",
- .base.cra_driver_name = "xchacha20-simd",
- .base.cra_priority = 300,
- .base.cra_blocksize = 1,
- .base.cra_ctxsize = sizeof(struct chacha_ctx),
- .base.cra_module = THIS_MODULE,
-
- .min_keysize = CHACHA_KEY_SIZE,
- .max_keysize = CHACHA_KEY_SIZE,
- .ivsize = XCHACHA_IV_SIZE,
- .chunksize = CHACHA_BLOCK_SIZE,
- .setkey = chacha20_setkey,
- .encrypt = xchacha_simd,
- .decrypt = xchacha_simd,
- }, {
- .base.cra_name = "xchacha12",
- .base.cra_driver_name = "xchacha12-simd",
- .base.cra_priority = 300,
- .base.cra_blocksize = 1,
- .base.cra_ctxsize = sizeof(struct chacha_ctx),
- .base.cra_module = THIS_MODULE,
-
- .min_keysize = CHACHA_KEY_SIZE,
- .max_keysize = CHACHA_KEY_SIZE,
- .ivsize = XCHACHA_IV_SIZE,
- .chunksize = CHACHA_BLOCK_SIZE,
- .setkey = chacha12_setkey,
- .encrypt = xchacha_simd,
- .decrypt = xchacha_simd,
- },
-};
-
-static int __init chacha_simd_mod_init(void)
-{
- if (!boot_cpu_has(X86_FEATURE_SSSE3))
- return 0;
-
- static_branch_enable(&chacha_use_simd);
-
- if (boot_cpu_has(X86_FEATURE_AVX) &&
- boot_cpu_has(X86_FEATURE_AVX2) &&
- cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
- static_branch_enable(&chacha_use_avx2);
-
- if (IS_ENABLED(CONFIG_AS_AVX512) &&
- boot_cpu_has(X86_FEATURE_AVX512VL) &&
- boot_cpu_has(X86_FEATURE_AVX512BW)) /* kmovq */
- static_branch_enable(&chacha_use_avx512vl);
- }
- return IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) ?
- crypto_register_skciphers(algs, ARRAY_SIZE(algs)) : 0;
-}
-
-static void __exit chacha_simd_mod_fini(void)
-{
- if (IS_REACHABLE(CONFIG_CRYPTO_SKCIPHER) && boot_cpu_has(X86_FEATURE_SSSE3))
- crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
-}
-
-module_init(chacha_simd_mod_init);
-module_exit(chacha_simd_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Martin Willi <martin@strongswan.org>");
-MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (x64 SIMD accelerated)");
-MODULE_ALIAS_CRYPTO("chacha20");
-MODULE_ALIAS_CRYPTO("chacha20-simd");
-MODULE_ALIAS_CRYPTO("xchacha20");
-MODULE_ALIAS_CRYPTO("xchacha20-simd");
-MODULE_ALIAS_CRYPTO("xchacha12");
-MODULE_ALIAS_CRYPTO("xchacha12-simd");
diff --git a/arch/x86/crypto/curve25519-x86_64.c b/arch/x86/crypto/curve25519-x86_64.c
index dcfc0de333de..d587f05c3c8c 100644
--- a/arch/x86/crypto/curve25519-x86_64.c
+++ b/arch/x86/crypto/curve25519-x86_64.c
@@ -7,6 +7,7 @@
#include <crypto/curve25519.h>
#include <crypto/internal/kpp.h>
+#include <linux/export.h>
#include <linux/types.h>
#include <linux/jump_label.h>
#include <linux/kernel.h>
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
index 99cb983ded9e..c4fbaa82ed7a 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_asm.S
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -103,8 +103,8 @@ SYM_FUNC_START(clmul_ghash_mul)
SYM_FUNC_END(clmul_ghash_mul)
/*
- * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
- * const le128 *shash);
+ * int clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
+ * const le128 *shash);
*/
SYM_FUNC_START(clmul_ghash_update)
FRAME_BEGIN
@@ -127,6 +127,7 @@ SYM_FUNC_START(clmul_ghash_update)
pshufb BSWAP, DATA
movups DATA, (%rdi)
.Lupdate_just_ret:
+ mov %rdx, %rax
FRAME_END
RET
SYM_FUNC_END(clmul_ghash_update)
diff --git a/arch/x86/crypto/ghash-clmulni-intel_glue.c b/arch/x86/crypto/ghash-clmulni-intel_glue.c
index c759ec808bf1..aea5d4d06be7 100644
--- a/arch/x86/crypto/ghash-clmulni-intel_glue.c
+++ b/arch/x86/crypto/ghash-clmulni-intel_glue.c
@@ -7,41 +7,27 @@
* Author: Huang Ying <ying.huang@intel.com>
*/
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/crypto.h>
-#include <crypto/algapi.h>
-#include <crypto/cryptd.h>
-#include <crypto/gf128mul.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
#include <asm/cpu_device_id.h>
#include <asm/simd.h>
+#include <crypto/b128ops.h>
+#include <crypto/ghash.h>
+#include <crypto/internal/hash.h>
+#include <crypto/utils.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/string.h>
#include <linux/unaligned.h>
-#define GHASH_BLOCK_SIZE 16
-#define GHASH_DIGEST_SIZE 16
+asmlinkage void clmul_ghash_mul(char *dst, const le128 *shash);
-void clmul_ghash_mul(char *dst, const le128 *shash);
+asmlinkage int clmul_ghash_update(char *dst, const char *src,
+ unsigned int srclen, const le128 *shash);
-void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
- const le128 *shash);
-
-struct ghash_async_ctx {
- struct cryptd_ahash *cryptd_tfm;
-};
-
-struct ghash_ctx {
+struct x86_ghash_ctx {
le128 shash;
};
-struct ghash_desc_ctx {
- u8 buffer[GHASH_BLOCK_SIZE];
- u32 bytes;
-};
-
static int ghash_init(struct shash_desc *desc)
{
struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
@@ -54,7 +40,7 @@ static int ghash_init(struct shash_desc *desc)
static int ghash_setkey(struct crypto_shash *tfm,
const u8 *key, unsigned int keylen)
{
- struct ghash_ctx *ctx = crypto_shash_ctx(tfm);
+ struct x86_ghash_ctx *ctx = crypto_shash_ctx(tfm);
u64 a, b;
if (keylen != GHASH_BLOCK_SIZE)
@@ -95,64 +81,38 @@ static int ghash_setkey(struct crypto_shash *tfm,
static int ghash_update(struct shash_desc *desc,
const u8 *src, unsigned int srclen)
{
+ struct x86_ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
- struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
u8 *dst = dctx->buffer;
+ int remain;
kernel_fpu_begin();
- if (dctx->bytes) {
- int n = min(srclen, dctx->bytes);
- u8 *pos = dst + (GHASH_BLOCK_SIZE - dctx->bytes);
-
- dctx->bytes -= n;
- srclen -= n;
-
- while (n--)
- *pos++ ^= *src++;
-
- if (!dctx->bytes)
- clmul_ghash_mul(dst, &ctx->shash);
- }
-
- clmul_ghash_update(dst, src, srclen, &ctx->shash);
+ remain = clmul_ghash_update(dst, src, srclen, &ctx->shash);
kernel_fpu_end();
-
- if (srclen & 0xf) {
- src += srclen - (srclen & 0xf);
- srclen &= 0xf;
- dctx->bytes = GHASH_BLOCK_SIZE - srclen;
- while (srclen--)
- *dst++ ^= *src++;
- }
-
- return 0;
+ return remain;
}
-static void ghash_flush(struct ghash_ctx *ctx, struct ghash_desc_ctx *dctx)
+static void ghash_flush(struct x86_ghash_ctx *ctx, struct ghash_desc_ctx *dctx,
+ const u8 *src, unsigned int len)
{
u8 *dst = dctx->buffer;
- if (dctx->bytes) {
- u8 *tmp = dst + (GHASH_BLOCK_SIZE - dctx->bytes);
-
- while (dctx->bytes--)
- *tmp++ ^= 0;
-
- kernel_fpu_begin();
+ kernel_fpu_begin();
+ if (len) {
+ crypto_xor(dst, src, len);
clmul_ghash_mul(dst, &ctx->shash);
- kernel_fpu_end();
}
-
- dctx->bytes = 0;
+ kernel_fpu_end();
}
-static int ghash_final(struct shash_desc *desc, u8 *dst)
+static int ghash_finup(struct shash_desc *desc, const u8 *src,
+ unsigned int len, u8 *dst)
{
+ struct x86_ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
- struct ghash_ctx *ctx = crypto_shash_ctx(desc->tfm);
u8 *buf = dctx->buffer;
- ghash_flush(ctx, dctx);
+ ghash_flush(ctx, dctx, src, len);
memcpy(dst, buf, GHASH_BLOCK_SIZE);
return 0;
@@ -162,186 +122,20 @@ static struct shash_alg ghash_alg = {
.digestsize = GHASH_DIGEST_SIZE,
.init = ghash_init,
.update = ghash_update,
- .final = ghash_final,
+ .finup = ghash_finup,
.setkey = ghash_setkey,
.descsize = sizeof(struct ghash_desc_ctx),
.base = {
- .cra_name = "__ghash",
- .cra_driver_name = "__ghash-pclmulqdqni",
- .cra_priority = 0,
- .cra_flags = CRYPTO_ALG_INTERNAL,
+ .cra_name = "ghash",
+ .cra_driver_name = "ghash-pclmulqdqni",
+ .cra_priority = 400,
+ .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
.cra_blocksize = GHASH_BLOCK_SIZE,
- .cra_ctxsize = sizeof(struct ghash_ctx),
+ .cra_ctxsize = sizeof(struct x86_ghash_ctx),
.cra_module = THIS_MODULE,
},
};
-static int ghash_async_init(struct ahash_request *req)
-{
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
- struct ahash_request *cryptd_req = ahash_request_ctx(req);
- struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
- struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
- struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
- desc->tfm = child;
- return crypto_shash_init(desc);
-}
-
-static void ghash_init_cryptd_req(struct ahash_request *req)
-{
- struct ahash_request *cryptd_req = ahash_request_ctx(req);
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
- struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
- ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
- ahash_request_set_callback(cryptd_req, req->base.flags,
- req->base.complete, req->base.data);
- ahash_request_set_crypt(cryptd_req, req->src, req->result,
- req->nbytes);
-}
-
-static int ghash_async_update(struct ahash_request *req)
-{
- struct ahash_request *cryptd_req = ahash_request_ctx(req);
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
- struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
- if (!crypto_simd_usable() ||
- (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
- ghash_init_cryptd_req(req);
- return crypto_ahash_update(cryptd_req);
- } else {
- struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
- return shash_ahash_update(req, desc);
- }
-}
-
-static int ghash_async_final(struct ahash_request *req)
-{
- struct ahash_request *cryptd_req = ahash_request_ctx(req);
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
- struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
- if (!crypto_simd_usable() ||
- (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
- ghash_init_cryptd_req(req);
- return crypto_ahash_final(cryptd_req);
- } else {
- struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
- return crypto_shash_final(desc, req->result);
- }
-}
-
-static int ghash_async_import(struct ahash_request *req, const void *in)
-{
- struct ahash_request *cryptd_req = ahash_request_ctx(req);
- struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
- struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-
- ghash_async_init(req);
- memcpy(dctx, in, sizeof(*dctx));
- return 0;
-
-}
-
-static int ghash_async_export(struct ahash_request *req, void *out)
-{
- struct ahash_request *cryptd_req = ahash_request_ctx(req);
- struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
- struct ghash_desc_ctx *dctx = shash_desc_ctx(desc);
-
- memcpy(out, dctx, sizeof(*dctx));
- return 0;
-
-}
-
-static int ghash_async_digest(struct ahash_request *req)
-{
- struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
- struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
- struct ahash_request *cryptd_req = ahash_request_ctx(req);
- struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
- if (!crypto_simd_usable() ||
- (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
- ghash_init_cryptd_req(req);
- return crypto_ahash_digest(cryptd_req);
- } else {
- struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
- struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
- desc->tfm = child;
- return shash_ahash_digest(req, desc);
- }
-}
-
-static int ghash_async_setkey(struct crypto_ahash *tfm, const u8 *key,
- unsigned int keylen)
-{
- struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
- struct crypto_ahash *child = &ctx->cryptd_tfm->base;
-
- crypto_ahash_clear_flags(child, CRYPTO_TFM_REQ_MASK);
- crypto_ahash_set_flags(child, crypto_ahash_get_flags(tfm)
- & CRYPTO_TFM_REQ_MASK);
- return crypto_ahash_setkey(child, key, keylen);
-}
-
-static int ghash_async_init_tfm(struct crypto_tfm *tfm)
-{
- struct cryptd_ahash *cryptd_tfm;
- struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
-
- cryptd_tfm = cryptd_alloc_ahash("__ghash-pclmulqdqni",
- CRYPTO_ALG_INTERNAL,
- CRYPTO_ALG_INTERNAL);
- if (IS_ERR(cryptd_tfm))
- return PTR_ERR(cryptd_tfm);
- ctx->cryptd_tfm = cryptd_tfm;
- crypto_ahash_set_reqsize(__crypto_ahash_cast(tfm),
- sizeof(struct ahash_request) +
- crypto_ahash_reqsize(&cryptd_tfm->base));
-
- return 0;
-}
-
-static void ghash_async_exit_tfm(struct crypto_tfm *tfm)
-{
- struct ghash_async_ctx *ctx = crypto_tfm_ctx(tfm);
-
- cryptd_free_ahash(ctx->cryptd_tfm);
-}
-
-static struct ahash_alg ghash_async_alg = {
- .init = ghash_async_init,
- .update = ghash_async_update,
- .final = ghash_async_final,
- .setkey = ghash_async_setkey,
- .digest = ghash_async_digest,
- .export = ghash_async_export,
- .import = ghash_async_import,
- .halg = {
- .digestsize = GHASH_DIGEST_SIZE,
- .statesize = sizeof(struct ghash_desc_ctx),
- .base = {
- .cra_name = "ghash",
- .cra_driver_name = "ghash-clmulni",
- .cra_priority = 400,
- .cra_ctxsize = sizeof(struct ghash_async_ctx),
- .cra_flags = CRYPTO_ALG_ASYNC,
- .cra_blocksize = GHASH_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- .cra_init = ghash_async_init_tfm,
- .cra_exit = ghash_async_exit_tfm,
- },
- },
-};
-
static const struct x86_cpu_id pcmul_cpu_id[] = {
X86_MATCH_FEATURE(X86_FEATURE_PCLMULQDQ, NULL), /* Pickle-Mickle-Duck */
{}
@@ -350,29 +144,14 @@ MODULE_DEVICE_TABLE(x86cpu, pcmul_cpu_id);
static int __init ghash_pclmulqdqni_mod_init(void)
{
- int err;
-
if (!x86_match_cpu(pcmul_cpu_id))
return -ENODEV;
- err = crypto_register_shash(&ghash_alg);
- if (err)
- goto err_out;
- err = crypto_register_ahash(&ghash_async_alg);
- if (err)
- goto err_shash;
-
- return 0;
-
-err_shash:
- crypto_unregister_shash(&ghash_alg);
-err_out:
- return err;
+ return crypto_register_shash(&ghash_alg);
}
static void __exit ghash_pclmulqdqni_mod_exit(void)
{
- crypto_unregister_ahash(&ghash_async_alg);
crypto_unregister_shash(&ghash_alg);
}
diff --git a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl b/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
deleted file mode 100644
index b9abcd79c1f4..000000000000
--- a/arch/x86/crypto/poly1305-x86_64-cryptogams.pl
+++ /dev/null
@@ -1,4248 +0,0 @@
-#!/usr/bin/env perl
-# SPDX-License-Identifier: GPL-2.0 OR BSD-3-Clause
-#
-# Copyright (C) 2017-2018 Samuel Neves <sneves@dei.uc.pt>. All Rights Reserved.
-# Copyright (C) 2017-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
-# Copyright (C) 2006-2017 CRYPTOGAMS by <appro@openssl.org>. All Rights Reserved.
-#
-# This code is taken from the OpenSSL project but the author, Andy Polyakov,
-# has relicensed it under the licenses specified in the SPDX header above.
-# The original headers, including the original license headers, are
-# included below for completeness.
-#
-# ====================================================================
-# Written by Andy Polyakov <appro@openssl.org> for the OpenSSL
-# project. The module is, however, dual licensed under OpenSSL and
-# CRYPTOGAMS licenses depending on where you obtain it. For further
-# details see http://www.openssl.org/~appro/cryptogams/.
-# ====================================================================
-#
-# This module implements Poly1305 hash for x86_64.
-#
-# March 2015
-#
-# Initial release.
-#
-# December 2016
-#
-# Add AVX512F+VL+BW code path.
-#
-# November 2017
-#
-# Convert AVX512F+VL+BW code path to pure AVX512F, so that it can be
-# executed even on Knights Landing. Trigger for modification was
-# observation that AVX512 code paths can negatively affect overall
-# Skylake-X system performance. Since we are likely to suppress
-# AVX512F capability flag [at least on Skylake-X], conversion serves
-# as kind of "investment protection". Note that next *lake processor,
-# Cannonlake, has AVX512IFMA code path to execute...
-#
-# Numbers are cycles per processed byte with poly1305_blocks alone,
-# measured with rdtsc at fixed clock frequency.
-#
-# IALU/gcc-4.8(*) AVX(**) AVX2 AVX-512
-# P4 4.46/+120% -
-# Core 2 2.41/+90% -
-# Westmere 1.88/+120% -
-# Sandy Bridge 1.39/+140% 1.10
-# Haswell 1.14/+175% 1.11 0.65
-# Skylake[-X] 1.13/+120% 0.96 0.51 [0.35]
-# Silvermont 2.83/+95% -
-# Knights L 3.60/? 1.65 1.10 0.41(***)
-# Goldmont 1.70/+180% -
-# VIA Nano 1.82/+150% -
-# Sledgehammer 1.38/+160% -
-# Bulldozer 2.30/+130% 0.97
-# Ryzen 1.15/+200% 1.08 1.18
-#
-# (*) improvement coefficients relative to clang are more modest and
-# are ~50% on most processors, in both cases we are comparing to
-# __int128 code;
-# (**) SSE2 implementation was attempted, but among non-AVX processors
-# it was faster than integer-only code only on older Intel P4 and
-# Core processors, 50-30%, less newer processor is, but slower on
-# contemporary ones, for example almost 2x slower on Atom, and as
-# former are naturally disappearing, SSE2 is deemed unnecessary;
-# (***) strangely enough performance seems to vary from core to core,
-# listed result is best case;
-
-$flavour = shift;
-$output = shift;
-if ($flavour =~ /\./) { $output = $flavour; undef $flavour; }
-
-$win64=0; $win64=1 if ($flavour =~ /[nm]asm|mingw64/ || $output =~ /\.asm$/);
-$kernel=0; $kernel=1 if (!$flavour && !$output);
-
-if (!$kernel) {
- $0 =~ m/(.*[\/\\])[^\/\\]+$/; $dir=$1;
- ( $xlate="${dir}x86_64-xlate.pl" and -f $xlate ) or
- ( $xlate="${dir}../../perlasm/x86_64-xlate.pl" and -f $xlate) or
- die "can't locate x86_64-xlate.pl";
-
- open OUT,"| \"$^X\" \"$xlate\" $flavour \"$output\"";
- *STDOUT=*OUT;
-
- if (`$ENV{CC} -Wa,-v -c -o /dev/null -x assembler /dev/null 2>&1`
- =~ /GNU assembler version ([2-9]\.[0-9]+)/) {
- $avx = ($1>=2.19) + ($1>=2.22) + ($1>=2.25);
- }
-
- if (!$avx && $win64 && ($flavour =~ /nasm/ || $ENV{ASM} =~ /nasm/) &&
- `nasm -v 2>&1` =~ /NASM version ([2-9]\.[0-9]+)(?:\.([0-9]+))?/) {
- $avx = ($1>=2.09) + ($1>=2.10) + ($1>=2.12);
- $avx += 1 if ($1==2.11 && $2>=8);
- }
-
- if (!$avx && $win64 && ($flavour =~ /masm/ || $ENV{ASM} =~ /ml64/) &&
- `ml64 2>&1` =~ /Version ([0-9]+)\./) {
- $avx = ($1>=10) + ($1>=11);
- }
-
- if (!$avx && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|.*based on LLVM) ([3-9]\.[0-9]+)/) {
- $avx = ($2>=3.0) + ($2>3.0);
- }
-} else {
- $avx = 4; # The kernel uses ifdefs for this.
-}
-
-sub declare_function() {
- my ($name, $align, $nargs) = @_;
- if($kernel) {
- $code .= "SYM_FUNC_START($name)\n";
- $code .= ".L$name:\n";
- } else {
- $code .= ".globl $name\n";
- $code .= ".type $name,\@function,$nargs\n";
- $code .= ".align $align\n";
- $code .= "$name:\n";
- }
-}
-
-sub end_function() {
- my ($name) = @_;
- if($kernel) {
- $code .= "SYM_FUNC_END($name)\n";
- } else {
- $code .= ".size $name,.-$name\n";
- }
-}
-
-$code.=<<___ if $kernel;
-#include <linux/linkage.h>
-___
-
-if ($avx) {
-$code.=<<___ if $kernel;
-.section .rodata
-___
-$code.=<<___;
-.align 64
-.Lconst:
-.Lmask24:
-.long 0x0ffffff,0,0x0ffffff,0,0x0ffffff,0,0x0ffffff,0
-.L129:
-.long `1<<24`,0,`1<<24`,0,`1<<24`,0,`1<<24`,0
-.Lmask26:
-.long 0x3ffffff,0,0x3ffffff,0,0x3ffffff,0,0x3ffffff,0
-.Lpermd_avx2:
-.long 2,2,2,3,2,0,2,1
-.Lpermd_avx512:
-.long 0,0,0,1, 0,2,0,3, 0,4,0,5, 0,6,0,7
-
-.L2_44_inp_permd:
-.long 0,1,1,2,2,3,7,7
-.L2_44_inp_shift:
-.quad 0,12,24,64
-.L2_44_mask:
-.quad 0xfffffffffff,0xfffffffffff,0x3ffffffffff,0xffffffffffffffff
-.L2_44_shift_rgt:
-.quad 44,44,42,64
-.L2_44_shift_lft:
-.quad 8,8,10,64
-
-.align 64
-.Lx_mask44:
-.quad 0xfffffffffff,0xfffffffffff,0xfffffffffff,0xfffffffffff
-.quad 0xfffffffffff,0xfffffffffff,0xfffffffffff,0xfffffffffff
-.Lx_mask42:
-.quad 0x3ffffffffff,0x3ffffffffff,0x3ffffffffff,0x3ffffffffff
-.quad 0x3ffffffffff,0x3ffffffffff,0x3ffffffffff,0x3ffffffffff
-___
-}
-$code.=<<___ if (!$kernel);
-.asciz "Poly1305 for x86_64, CRYPTOGAMS by <appro\@openssl.org>"
-.align 16
-___
-
-my ($ctx,$inp,$len,$padbit)=("%rdi","%rsi","%rdx","%rcx");
-my ($mac,$nonce)=($inp,$len); # *_emit arguments
-my ($d1,$d2,$d3, $r0,$r1,$s1)=("%r8","%r9","%rdi","%r11","%r12","%r13");
-my ($h0,$h1,$h2)=("%r14","%rbx","%r10");
-
-sub poly1305_iteration {
-# input: copy of $r1 in %rax, $h0-$h2, $r0-$r1
-# output: $h0-$h2 *= $r0-$r1
-$code.=<<___;
- mulq $h0 # h0*r1
- mov %rax,$d2
- mov $r0,%rax
- mov %rdx,$d3
-
- mulq $h0 # h0*r0
- mov %rax,$h0 # future $h0
- mov $r0,%rax
- mov %rdx,$d1
-
- mulq $h1 # h1*r0
- add %rax,$d2
- mov $s1,%rax
- adc %rdx,$d3
-
- mulq $h1 # h1*s1
- mov $h2,$h1 # borrow $h1
- add %rax,$h0
- adc %rdx,$d1
-
- imulq $s1,$h1 # h2*s1
- add $h1,$d2
- mov $d1,$h1
- adc \$0,$d3
-
- imulq $r0,$h2 # h2*r0
- add $d2,$h1
- mov \$-4,%rax # mask value
- adc $h2,$d3
-
- and $d3,%rax # last reduction step
- mov $d3,$h2
- shr \$2,$d3
- and \$3,$h2
- add $d3,%rax
- add %rax,$h0
- adc \$0,$h1
- adc \$0,$h2
-___
-}
-
-########################################################################
-# Layout of opaque area is following.
-#
-# unsigned __int64 h[3]; # current hash value base 2^64
-# unsigned __int64 r[2]; # key value base 2^64
-
-$code.=<<___;
-.text
-___
-$code.=<<___ if (!$kernel);
-.extern OPENSSL_ia32cap_P
-
-.globl poly1305_init_x86_64
-.hidden poly1305_init_x86_64
-.globl poly1305_blocks_x86_64
-.hidden poly1305_blocks_x86_64
-.globl poly1305_emit_x86_64
-.hidden poly1305_emit_x86_64
-___
-&declare_function("poly1305_init_x86_64", 32, 3);
-$code.=<<___;
- xor %eax,%eax
- mov %rax,0($ctx) # initialize hash value
- mov %rax,8($ctx)
- mov %rax,16($ctx)
-
- test $inp,$inp
- je .Lno_key
-___
-$code.=<<___ if (!$kernel);
- lea poly1305_blocks_x86_64(%rip),%r10
- lea poly1305_emit_x86_64(%rip),%r11
-___
-$code.=<<___ if (!$kernel && $avx);
- mov OPENSSL_ia32cap_P+4(%rip),%r9
- lea poly1305_blocks_avx(%rip),%rax
- lea poly1305_emit_avx(%rip),%rcx
- bt \$`60-32`,%r9 # AVX?
- cmovc %rax,%r10
- cmovc %rcx,%r11
-___
-$code.=<<___ if (!$kernel && $avx>1);
- lea poly1305_blocks_avx2(%rip),%rax
- bt \$`5+32`,%r9 # AVX2?
- cmovc %rax,%r10
-___
-$code.=<<___ if (!$kernel && $avx>3);
- mov \$`(1<<31|1<<21|1<<16)`,%rax
- shr \$32,%r9
- and %rax,%r9
- cmp %rax,%r9
- je .Linit_base2_44
-___
-$code.=<<___;
- mov \$0x0ffffffc0fffffff,%rax
- mov \$0x0ffffffc0ffffffc,%rcx
- and 0($inp),%rax
- and 8($inp),%rcx
- mov %rax,24($ctx)
- mov %rcx,32($ctx)
-___
-$code.=<<___ if (!$kernel && $flavour !~ /elf32/);
- mov %r10,0(%rdx)
- mov %r11,8(%rdx)
-___
-$code.=<<___ if (!$kernel && $flavour =~ /elf32/);
- mov %r10d,0(%rdx)
- mov %r11d,4(%rdx)
-___
-$code.=<<___;
- mov \$1,%eax
-.Lno_key:
- RET
-___
-&end_function("poly1305_init_x86_64");
-
-&declare_function("poly1305_blocks_x86_64", 32, 4);
-$code.=<<___;
-.cfi_startproc
-.Lblocks:
- shr \$4,$len
- jz .Lno_data # too short
-
- push %rbx
-.cfi_push %rbx
- push %r12
-.cfi_push %r12
- push %r13
-.cfi_push %r13
- push %r14
-.cfi_push %r14
- push %r15
-.cfi_push %r15
- push $ctx
-.cfi_push $ctx
-.Lblocks_body:
-
- mov $len,%r15 # reassign $len
-
- mov 24($ctx),$r0 # load r
- mov 32($ctx),$s1
-
- mov 0($ctx),$h0 # load hash value
- mov 8($ctx),$h1
- mov 16($ctx),$h2
-
- mov $s1,$r1
- shr \$2,$s1
- mov $r1,%rax
- add $r1,$s1 # s1 = r1 + (r1 >> 2)
- jmp .Loop
-
-.align 32
-.Loop:
- add 0($inp),$h0 # accumulate input
- adc 8($inp),$h1
- lea 16($inp),$inp
- adc $padbit,$h2
-___
-
- &poly1305_iteration();
-
-$code.=<<___;
- mov $r1,%rax
- dec %r15 # len-=16
- jnz .Loop
-
- mov 0(%rsp),$ctx
-.cfi_restore $ctx
-
- mov $h0,0($ctx) # store hash value
- mov $h1,8($ctx)
- mov $h2,16($ctx)
-
- mov 8(%rsp),%r15
-.cfi_restore %r15
- mov 16(%rsp),%r14
-.cfi_restore %r14
- mov 24(%rsp),%r13
-.cfi_restore %r13
- mov 32(%rsp),%r12
-.cfi_restore %r12
- mov 40(%rsp),%rbx
-.cfi_restore %rbx
- lea 48(%rsp),%rsp
-.cfi_adjust_cfa_offset -48
-.Lno_data:
-.Lblocks_epilogue:
- RET
-.cfi_endproc
-___
-&end_function("poly1305_blocks_x86_64");
-
-&declare_function("poly1305_emit_x86_64", 32, 3);
-$code.=<<___;
-.Lemit:
- mov 0($ctx),%r8 # load hash value
- mov 8($ctx),%r9
- mov 16($ctx),%r10
-
- mov %r8,%rax
- add \$5,%r8 # compare to modulus
- mov %r9,%rcx
- adc \$0,%r9
- adc \$0,%r10
- shr \$2,%r10 # did 130-bit value overflow?
- cmovnz %r8,%rax
- cmovnz %r9,%rcx
-
- add 0($nonce),%rax # accumulate nonce
- adc 8($nonce),%rcx
- mov %rax,0($mac) # write result
- mov %rcx,8($mac)
-
- RET
-___
-&end_function("poly1305_emit_x86_64");
-if ($avx) {
-
-########################################################################
-# Layout of opaque area is following.
-#
-# unsigned __int32 h[5]; # current hash value base 2^26
-# unsigned __int32 is_base2_26;
-# unsigned __int64 r[2]; # key value base 2^64
-# unsigned __int64 pad;
-# struct { unsigned __int32 r^2, r^1, r^4, r^3; } r[9];
-#
-# where r^n are base 2^26 digits of degrees of multiplier key. There are
-# 5 digits, but last four are interleaved with multiples of 5, totalling
-# in 9 elements: r0, r1, 5*r1, r2, 5*r2, r3, 5*r3, r4, 5*r4.
-
-my ($H0,$H1,$H2,$H3,$H4, $T0,$T1,$T2,$T3,$T4, $D0,$D1,$D2,$D3,$D4, $MASK) =
- map("%xmm$_",(0..15));
-
-$code.=<<___;
-.type __poly1305_block,\@abi-omnipotent
-.align 32
-__poly1305_block:
- push $ctx
-___
- &poly1305_iteration();
-$code.=<<___;
- pop $ctx
- RET
-.size __poly1305_block,.-__poly1305_block
-
-.type __poly1305_init_avx,\@abi-omnipotent
-.align 32
-__poly1305_init_avx:
- push %rbp
- mov %rsp,%rbp
- mov $r0,$h0
- mov $r1,$h1
- xor $h2,$h2
-
- lea 48+64($ctx),$ctx # size optimization
-
- mov $r1,%rax
- call __poly1305_block # r^2
-
- mov \$0x3ffffff,%eax # save interleaved r^2 and r base 2^26
- mov \$0x3ffffff,%edx
- mov $h0,$d1
- and $h0#d,%eax
- mov $r0,$d2
- and $r0#d,%edx
- mov %eax,`16*0+0-64`($ctx)
- shr \$26,$d1
- mov %edx,`16*0+4-64`($ctx)
- shr \$26,$d2
-
- mov \$0x3ffffff,%eax
- mov \$0x3ffffff,%edx
- and $d1#d,%eax
- and $d2#d,%edx
- mov %eax,`16*1+0-64`($ctx)
- lea (%rax,%rax,4),%eax # *5
- mov %edx,`16*1+4-64`($ctx)
- lea (%rdx,%rdx,4),%edx # *5
- mov %eax,`16*2+0-64`($ctx)
- shr \$26,$d1
- mov %edx,`16*2+4-64`($ctx)
- shr \$26,$d2
-
- mov $h1,%rax
- mov $r1,%rdx
- shl \$12,%rax
- shl \$12,%rdx
- or $d1,%rax
- or $d2,%rdx
- and \$0x3ffffff,%eax
- and \$0x3ffffff,%edx
- mov %eax,`16*3+0-64`($ctx)
- lea (%rax,%rax,4),%eax # *5
- mov %edx,`16*3+4-64`($ctx)
- lea (%rdx,%rdx,4),%edx # *5
- mov %eax,`16*4+0-64`($ctx)
- mov $h1,$d1
- mov %edx,`16*4+4-64`($ctx)
- mov $r1,$d2
-
- mov \$0x3ffffff,%eax
- mov \$0x3ffffff,%edx
- shr \$14,$d1
- shr \$14,$d2
- and $d1#d,%eax
- and $d2#d,%edx
- mov %eax,`16*5+0-64`($ctx)
- lea (%rax,%rax,4),%eax # *5
- mov %edx,`16*5+4-64`($ctx)
- lea (%rdx,%rdx,4),%edx # *5
- mov %eax,`16*6+0-64`($ctx)
- shr \$26,$d1
- mov %edx,`16*6+4-64`($ctx)
- shr \$26,$d2
-
- mov $h2,%rax
- shl \$24,%rax
- or %rax,$d1
- mov $d1#d,`16*7+0-64`($ctx)
- lea ($d1,$d1,4),$d1 # *5
- mov $d2#d,`16*7+4-64`($ctx)
- lea ($d2,$d2,4),$d2 # *5
- mov $d1#d,`16*8+0-64`($ctx)
- mov $d2#d,`16*8+4-64`($ctx)
-
- mov $r1,%rax
- call __poly1305_block # r^3
-
- mov \$0x3ffffff,%eax # save r^3 base 2^26
- mov $h0,$d1
- and $h0#d,%eax
- shr \$26,$d1
- mov %eax,`16*0+12-64`($ctx)
-
- mov \$0x3ffffff,%edx
- and $d1#d,%edx
- mov %edx,`16*1+12-64`($ctx)
- lea (%rdx,%rdx,4),%edx # *5
- shr \$26,$d1
- mov %edx,`16*2+12-64`($ctx)
-
- mov $h1,%rax
- shl \$12,%rax
- or $d1,%rax
- and \$0x3ffffff,%eax
- mov %eax,`16*3+12-64`($ctx)
- lea (%rax,%rax,4),%eax # *5
- mov $h1,$d1
- mov %eax,`16*4+12-64`($ctx)
-
- mov \$0x3ffffff,%edx
- shr \$14,$d1
- and $d1#d,%edx
- mov %edx,`16*5+12-64`($ctx)
- lea (%rdx,%rdx,4),%edx # *5
- shr \$26,$d1
- mov %edx,`16*6+12-64`($ctx)
-
- mov $h2,%rax
- shl \$24,%rax
- or %rax,$d1
- mov $d1#d,`16*7+12-64`($ctx)
- lea ($d1,$d1,4),$d1 # *5
- mov $d1#d,`16*8+12-64`($ctx)
-
- mov $r1,%rax
- call __poly1305_block # r^4
-
- mov \$0x3ffffff,%eax # save r^4 base 2^26
- mov $h0,$d1
- and $h0#d,%eax
- shr \$26,$d1
- mov %eax,`16*0+8-64`($ctx)
-
- mov \$0x3ffffff,%edx
- and $d1#d,%edx
- mov %edx,`16*1+8-64`($ctx)
- lea (%rdx,%rdx,4),%edx # *5
- shr \$26,$d1
- mov %edx,`16*2+8-64`($ctx)
-
- mov $h1,%rax
- shl \$12,%rax
- or $d1,%rax
- and \$0x3ffffff,%eax
- mov %eax,`16*3+8-64`($ctx)
- lea (%rax,%rax,4),%eax # *5
- mov $h1,$d1
- mov %eax,`16*4+8-64`($ctx)
-
- mov \$0x3ffffff,%edx
- shr \$14,$d1
- and $d1#d,%edx
- mov %edx,`16*5+8-64`($ctx)
- lea (%rdx,%rdx,4),%edx # *5
- shr \$26,$d1
- mov %edx,`16*6+8-64`($ctx)
-
- mov $h2,%rax
- shl \$24,%rax
- or %rax,$d1
- mov $d1#d,`16*7+8-64`($ctx)
- lea ($d1,$d1,4),$d1 # *5
- mov $d1#d,`16*8+8-64`($ctx)
-
- lea -48-64($ctx),$ctx # size [de-]optimization
- pop %rbp
- RET
-.size __poly1305_init_avx,.-__poly1305_init_avx
-___
-
-&declare_function("poly1305_blocks_avx", 32, 4);
-$code.=<<___;
-.cfi_startproc
- mov 20($ctx),%r8d # is_base2_26
- cmp \$128,$len
- jae .Lblocks_avx
- test %r8d,%r8d
- jz .Lblocks
-
-.Lblocks_avx:
- and \$-16,$len
- jz .Lno_data_avx
-
- vzeroupper
-
- test %r8d,%r8d
- jz .Lbase2_64_avx
-
- test \$31,$len
- jz .Leven_avx
-
- push %rbp
-.cfi_push %rbp
- mov %rsp,%rbp
- push %rbx
-.cfi_push %rbx
- push %r12
-.cfi_push %r12
- push %r13
-.cfi_push %r13
- push %r14
-.cfi_push %r14
- push %r15
-.cfi_push %r15
-.Lblocks_avx_body:
-
- mov $len,%r15 # reassign $len
-
- mov 0($ctx),$d1 # load hash value
- mov 8($ctx),$d2
- mov 16($ctx),$h2#d
-
- mov 24($ctx),$r0 # load r
- mov 32($ctx),$s1
-
- ################################# base 2^26 -> base 2^64
- mov $d1#d,$h0#d
- and \$`-1*(1<<31)`,$d1
- mov $d2,$r1 # borrow $r1
- mov $d2#d,$h1#d
- and \$`-1*(1<<31)`,$d2
-
- shr \$6,$d1
- shl \$52,$r1
- add $d1,$h0
- shr \$12,$h1
- shr \$18,$d2
- add $r1,$h0
- adc $d2,$h1
-
- mov $h2,$d1
- shl \$40,$d1
- shr \$24,$h2
- add $d1,$h1
- adc \$0,$h2 # can be partially reduced...
-
- mov \$-4,$d2 # ... so reduce
- mov $h2,$d1
- and $h2,$d2
- shr \$2,$d1
- and \$3,$h2
- add $d2,$d1 # =*5
- add $d1,$h0
- adc \$0,$h1
- adc \$0,$h2
-
- mov $s1,$r1
- mov $s1,%rax
- shr \$2,$s1
- add $r1,$s1 # s1 = r1 + (r1 >> 2)
-
- add 0($inp),$h0 # accumulate input
- adc 8($inp),$h1
- lea 16($inp),$inp
- adc $padbit,$h2
-
- call __poly1305_block
-
- test $padbit,$padbit # if $padbit is zero,
- jz .Lstore_base2_64_avx # store hash in base 2^64 format
-
- ################################# base 2^64 -> base 2^26
- mov $h0,%rax
- mov $h0,%rdx
- shr \$52,$h0
- mov $h1,$r0
- mov $h1,$r1
- shr \$26,%rdx
- and \$0x3ffffff,%rax # h[0]
- shl \$12,$r0
- and \$0x3ffffff,%rdx # h[1]
- shr \$14,$h1
- or $r0,$h0
- shl \$24,$h2
- and \$0x3ffffff,$h0 # h[2]
- shr \$40,$r1
- and \$0x3ffffff,$h1 # h[3]
- or $r1,$h2 # h[4]
-
- sub \$16,%r15
- jz .Lstore_base2_26_avx
-
- vmovd %rax#d,$H0
- vmovd %rdx#d,$H1
- vmovd $h0#d,$H2
- vmovd $h1#d,$H3
- vmovd $h2#d,$H4
- jmp .Lproceed_avx
-
-.align 32
-.Lstore_base2_64_avx:
- mov $h0,0($ctx)
- mov $h1,8($ctx)
- mov $h2,16($ctx) # note that is_base2_26 is zeroed
- jmp .Ldone_avx
-
-.align 16
-.Lstore_base2_26_avx:
- mov %rax#d,0($ctx) # store hash value base 2^26
- mov %rdx#d,4($ctx)
- mov $h0#d,8($ctx)
- mov $h1#d,12($ctx)
- mov $h2#d,16($ctx)
-.align 16
-.Ldone_avx:
- pop %r15
-.cfi_restore %r15
- pop %r14
-.cfi_restore %r14
- pop %r13
-.cfi_restore %r13
- pop %r12
-.cfi_restore %r12
- pop %rbx
-.cfi_restore %rbx
- pop %rbp
-.cfi_restore %rbp
-.Lno_data_avx:
-.Lblocks_avx_epilogue:
- RET
-.cfi_endproc
-
-.align 32
-.Lbase2_64_avx:
-.cfi_startproc
- push %rbp
-.cfi_push %rbp
- mov %rsp,%rbp
- push %rbx
-.cfi_push %rbx
- push %r12
-.cfi_push %r12
- push %r13
-.cfi_push %r13
- push %r14
-.cfi_push %r14
- push %r15
-.cfi_push %r15
-.Lbase2_64_avx_body:
-
- mov $len,%r15 # reassign $len
-
- mov 24($ctx),$r0 # load r
- mov 32($ctx),$s1
-
- mov 0($ctx),$h0 # load hash value
- mov 8($ctx),$h1
- mov 16($ctx),$h2#d
-
- mov $s1,$r1
- mov $s1,%rax
- shr \$2,$s1
- add $r1,$s1 # s1 = r1 + (r1 >> 2)
-
- test \$31,$len
- jz .Linit_avx
-
- add 0($inp),$h0 # accumulate input
- adc 8($inp),$h1
- lea 16($inp),$inp
- adc $padbit,$h2
- sub \$16,%r15
-
- call __poly1305_block
-
-.Linit_avx:
- ################################# base 2^64 -> base 2^26
- mov $h0,%rax
- mov $h0,%rdx
- shr \$52,$h0
- mov $h1,$d1
- mov $h1,$d2
- shr \$26,%rdx
- and \$0x3ffffff,%rax # h[0]
- shl \$12,$d1
- and \$0x3ffffff,%rdx # h[1]
- shr \$14,$h1
- or $d1,$h0
- shl \$24,$h2
- and \$0x3ffffff,$h0 # h[2]
- shr \$40,$d2
- and \$0x3ffffff,$h1 # h[3]
- or $d2,$h2 # h[4]
-
- vmovd %rax#d,$H0
- vmovd %rdx#d,$H1
- vmovd $h0#d,$H2
- vmovd $h1#d,$H3
- vmovd $h2#d,$H4
- movl \$1,20($ctx) # set is_base2_26
-
- call __poly1305_init_avx
-
-.Lproceed_avx:
- mov %r15,$len
- pop %r15
-.cfi_restore %r15
- pop %r14
-.cfi_restore %r14
- pop %r13
-.cfi_restore %r13
- pop %r12
-.cfi_restore %r12
- pop %rbx
-.cfi_restore %rbx
- pop %rbp
-.cfi_restore %rbp
-.Lbase2_64_avx_epilogue:
- jmp .Ldo_avx
-.cfi_endproc
-
-.align 32
-.Leven_avx:
-.cfi_startproc
- vmovd 4*0($ctx),$H0 # load hash value
- vmovd 4*1($ctx),$H1
- vmovd 4*2($ctx),$H2
- vmovd 4*3($ctx),$H3
- vmovd 4*4($ctx),$H4
-
-.Ldo_avx:
-___
-$code.=<<___ if (!$win64);
- lea 8(%rsp),%r10
-.cfi_def_cfa_register %r10
- and \$-32,%rsp
- sub \$-8,%rsp
- lea -0x58(%rsp),%r11
- sub \$0x178,%rsp
-___
-$code.=<<___ if ($win64);
- lea -0xf8(%rsp),%r11
- sub \$0x218,%rsp
- vmovdqa %xmm6,0x50(%r11)
- vmovdqa %xmm7,0x60(%r11)
- vmovdqa %xmm8,0x70(%r11)
- vmovdqa %xmm9,0x80(%r11)
- vmovdqa %xmm10,0x90(%r11)
- vmovdqa %xmm11,0xa0(%r11)
- vmovdqa %xmm12,0xb0(%r11)
- vmovdqa %xmm13,0xc0(%r11)
- vmovdqa %xmm14,0xd0(%r11)
- vmovdqa %xmm15,0xe0(%r11)
-.Ldo_avx_body:
-___
-$code.=<<___;
- sub \$64,$len
- lea -32($inp),%rax
- cmovc %rax,$inp
-
- vmovdqu `16*3`($ctx),$D4 # preload r0^2
- lea `16*3+64`($ctx),$ctx # size optimization
- lea .Lconst(%rip),%rcx
-
- ################################################################
- # load input
- vmovdqu 16*2($inp),$T0
- vmovdqu 16*3($inp),$T1
- vmovdqa 64(%rcx),$MASK # .Lmask26
-
- vpsrldq \$6,$T0,$T2 # splat input
- vpsrldq \$6,$T1,$T3
- vpunpckhqdq $T1,$T0,$T4 # 4
- vpunpcklqdq $T1,$T0,$T0 # 0:1
- vpunpcklqdq $T3,$T2,$T3 # 2:3
-
- vpsrlq \$40,$T4,$T4 # 4
- vpsrlq \$26,$T0,$T1
- vpand $MASK,$T0,$T0 # 0
- vpsrlq \$4,$T3,$T2
- vpand $MASK,$T1,$T1 # 1
- vpsrlq \$30,$T3,$T3
- vpand $MASK,$T2,$T2 # 2
- vpand $MASK,$T3,$T3 # 3
- vpor 32(%rcx),$T4,$T4 # padbit, yes, always
-
- jbe .Lskip_loop_avx
-
- # expand and copy pre-calculated table to stack
- vmovdqu `16*1-64`($ctx),$D1
- vmovdqu `16*2-64`($ctx),$D2
- vpshufd \$0xEE,$D4,$D3 # 34xx -> 3434
- vpshufd \$0x44,$D4,$D0 # xx12 -> 1212
- vmovdqa $D3,-0x90(%r11)
- vmovdqa $D0,0x00(%rsp)
- vpshufd \$0xEE,$D1,$D4
- vmovdqu `16*3-64`($ctx),$D0
- vpshufd \$0x44,$D1,$D1
- vmovdqa $D4,-0x80(%r11)
- vmovdqa $D1,0x10(%rsp)
- vpshufd \$0xEE,$D2,$D3
- vmovdqu `16*4-64`($ctx),$D1
- vpshufd \$0x44,$D2,$D2
- vmovdqa $D3,-0x70(%r11)
- vmovdqa $D2,0x20(%rsp)
- vpshufd \$0xEE,$D0,$D4
- vmovdqu `16*5-64`($ctx),$D2
- vpshufd \$0x44,$D0,$D0
- vmovdqa $D4,-0x60(%r11)
- vmovdqa $D0,0x30(%rsp)
- vpshufd \$0xEE,$D1,$D3
- vmovdqu `16*6-64`($ctx),$D0
- vpshufd \$0x44,$D1,$D1
- vmovdqa $D3,-0x50(%r11)
- vmovdqa $D1,0x40(%rsp)
- vpshufd \$0xEE,$D2,$D4
- vmovdqu `16*7-64`($ctx),$D1
- vpshufd \$0x44,$D2,$D2
- vmovdqa $D4,-0x40(%r11)
- vmovdqa $D2,0x50(%rsp)
- vpshufd \$0xEE,$D0,$D3
- vmovdqu `16*8-64`($ctx),$D2
- vpshufd \$0x44,$D0,$D0
- vmovdqa $D3,-0x30(%r11)
- vmovdqa $D0,0x60(%rsp)
- vpshufd \$0xEE,$D1,$D4
- vpshufd \$0x44,$D1,$D1
- vmovdqa $D4,-0x20(%r11)
- vmovdqa $D1,0x70(%rsp)
- vpshufd \$0xEE,$D2,$D3
- vmovdqa 0x00(%rsp),$D4 # preload r0^2
- vpshufd \$0x44,$D2,$D2
- vmovdqa $D3,-0x10(%r11)
- vmovdqa $D2,0x80(%rsp)
-
- jmp .Loop_avx
-
-.align 32
-.Loop_avx:
- ################################################################
- # ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2
- # ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^3+inp[7]*r
- # \___________________/
- # ((inp[0]*r^4+inp[2]*r^2+inp[4])*r^4+inp[6]*r^2+inp[8])*r^2
- # ((inp[1]*r^4+inp[3]*r^2+inp[5])*r^4+inp[7]*r^2+inp[9])*r
- # \___________________/ \____________________/
- #
- # Note that we start with inp[2:3]*r^2. This is because it
- # doesn't depend on reduction in previous iteration.
- ################################################################
- # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
- # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
- # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
- # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
- # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
- #
- # though note that $Tx and $Hx are "reversed" in this section,
- # and $D4 is preloaded with r0^2...
-
- vpmuludq $T0,$D4,$D0 # d0 = h0*r0
- vpmuludq $T1,$D4,$D1 # d1 = h1*r0
- vmovdqa $H2,0x20(%r11) # offload hash
- vpmuludq $T2,$D4,$D2 # d3 = h2*r0
- vmovdqa 0x10(%rsp),$H2 # r1^2
- vpmuludq $T3,$D4,$D3 # d3 = h3*r0
- vpmuludq $T4,$D4,$D4 # d4 = h4*r0
-
- vmovdqa $H0,0x00(%r11) #
- vpmuludq 0x20(%rsp),$T4,$H0 # h4*s1
- vmovdqa $H1,0x10(%r11) #
- vpmuludq $T3,$H2,$H1 # h3*r1
- vpaddq $H0,$D0,$D0 # d0 += h4*s1
- vpaddq $H1,$D4,$D4 # d4 += h3*r1
- vmovdqa $H3,0x30(%r11) #
- vpmuludq $T2,$H2,$H0 # h2*r1
- vpmuludq $T1,$H2,$H1 # h1*r1
- vpaddq $H0,$D3,$D3 # d3 += h2*r1
- vmovdqa 0x30(%rsp),$H3 # r2^2
- vpaddq $H1,$D2,$D2 # d2 += h1*r1
- vmovdqa $H4,0x40(%r11) #
- vpmuludq $T0,$H2,$H2 # h0*r1
- vpmuludq $T2,$H3,$H0 # h2*r2
- vpaddq $H2,$D1,$D1 # d1 += h0*r1
-
- vmovdqa 0x40(%rsp),$H4 # s2^2
- vpaddq $H0,$D4,$D4 # d4 += h2*r2
- vpmuludq $T1,$H3,$H1 # h1*r2
- vpmuludq $T0,$H3,$H3 # h0*r2
- vpaddq $H1,$D3,$D3 # d3 += h1*r2
- vmovdqa 0x50(%rsp),$H2 # r3^2
- vpaddq $H3,$D2,$D2 # d2 += h0*r2
- vpmuludq $T4,$H4,$H0 # h4*s2
- vpmuludq $T3,$H4,$H4 # h3*s2
- vpaddq $H0,$D1,$D1 # d1 += h4*s2
- vmovdqa 0x60(%rsp),$H3 # s3^2
- vpaddq $H4,$D0,$D0 # d0 += h3*s2
-
- vmovdqa 0x80(%rsp),$H4 # s4^2
- vpmuludq $T1,$H2,$H1 # h1*r3
- vpmuludq $T0,$H2,$H2 # h0*r3
- vpaddq $H1,$D4,$D4 # d4 += h1*r3
- vpaddq $H2,$D3,$D3 # d3 += h0*r3
- vpmuludq $T4,$H3,$H0 # h4*s3
- vpmuludq $T3,$H3,$H1 # h3*s3
- vpaddq $H0,$D2,$D2 # d2 += h4*s3
- vmovdqu 16*0($inp),$H0 # load input
- vpaddq $H1,$D1,$D1 # d1 += h3*s3
- vpmuludq $T2,$H3,$H3 # h2*s3
- vpmuludq $T2,$H4,$T2 # h2*s4
- vpaddq $H3,$D0,$D0 # d0 += h2*s3
-
- vmovdqu 16*1($inp),$H1 #
- vpaddq $T2,$D1,$D1 # d1 += h2*s4
- vpmuludq $T3,$H4,$T3 # h3*s4
- vpmuludq $T4,$H4,$T4 # h4*s4
- vpsrldq \$6,$H0,$H2 # splat input
- vpaddq $T3,$D2,$D2 # d2 += h3*s4
- vpaddq $T4,$D3,$D3 # d3 += h4*s4
- vpsrldq \$6,$H1,$H3 #
- vpmuludq 0x70(%rsp),$T0,$T4 # h0*r4
- vpmuludq $T1,$H4,$T0 # h1*s4
- vpunpckhqdq $H1,$H0,$H4 # 4
- vpaddq $T4,$D4,$D4 # d4 += h0*r4
- vmovdqa -0x90(%r11),$T4 # r0^4
- vpaddq $T0,$D0,$D0 # d0 += h1*s4
-
- vpunpcklqdq $H1,$H0,$H0 # 0:1
- vpunpcklqdq $H3,$H2,$H3 # 2:3
-
- #vpsrlq \$40,$H4,$H4 # 4
- vpsrldq \$`40/8`,$H4,$H4 # 4
- vpsrlq \$26,$H0,$H1
- vpand $MASK,$H0,$H0 # 0
- vpsrlq \$4,$H3,$H2
- vpand $MASK,$H1,$H1 # 1
- vpand 0(%rcx),$H4,$H4 # .Lmask24
- vpsrlq \$30,$H3,$H3
- vpand $MASK,$H2,$H2 # 2
- vpand $MASK,$H3,$H3 # 3
- vpor 32(%rcx),$H4,$H4 # padbit, yes, always
-
- vpaddq 0x00(%r11),$H0,$H0 # add hash value
- vpaddq 0x10(%r11),$H1,$H1
- vpaddq 0x20(%r11),$H2,$H2
- vpaddq 0x30(%r11),$H3,$H3
- vpaddq 0x40(%r11),$H4,$H4
-
- lea 16*2($inp),%rax
- lea 16*4($inp),$inp
- sub \$64,$len
- cmovc %rax,$inp
-
- ################################################################
- # Now we accumulate (inp[0:1]+hash)*r^4
- ################################################################
- # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
- # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
- # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
- # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
- # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
-
- vpmuludq $H0,$T4,$T0 # h0*r0
- vpmuludq $H1,$T4,$T1 # h1*r0
- vpaddq $T0,$D0,$D0
- vpaddq $T1,$D1,$D1
- vmovdqa -0x80(%r11),$T2 # r1^4
- vpmuludq $H2,$T4,$T0 # h2*r0
- vpmuludq $H3,$T4,$T1 # h3*r0
- vpaddq $T0,$D2,$D2
- vpaddq $T1,$D3,$D3
- vpmuludq $H4,$T4,$T4 # h4*r0
- vpmuludq -0x70(%r11),$H4,$T0 # h4*s1
- vpaddq $T4,$D4,$D4
-
- vpaddq $T0,$D0,$D0 # d0 += h4*s1
- vpmuludq $H2,$T2,$T1 # h2*r1
- vpmuludq $H3,$T2,$T0 # h3*r1
- vpaddq $T1,$D3,$D3 # d3 += h2*r1
- vmovdqa -0x60(%r11),$T3 # r2^4
- vpaddq $T0,$D4,$D4 # d4 += h3*r1
- vpmuludq $H1,$T2,$T1 # h1*r1
- vpmuludq $H0,$T2,$T2 # h0*r1
- vpaddq $T1,$D2,$D2 # d2 += h1*r1
- vpaddq $T2,$D1,$D1 # d1 += h0*r1
-
- vmovdqa -0x50(%r11),$T4 # s2^4
- vpmuludq $H2,$T3,$T0 # h2*r2
- vpmuludq $H1,$T3,$T1 # h1*r2
- vpaddq $T0,$D4,$D4 # d4 += h2*r2
- vpaddq $T1,$D3,$D3 # d3 += h1*r2
- vmovdqa -0x40(%r11),$T2 # r3^4
- vpmuludq $H0,$T3,$T3 # h0*r2
- vpmuludq $H4,$T4,$T0 # h4*s2
- vpaddq $T3,$D2,$D2 # d2 += h0*r2
- vpaddq $T0,$D1,$D1 # d1 += h4*s2
- vmovdqa -0x30(%r11),$T3 # s3^4
- vpmuludq $H3,$T4,$T4 # h3*s2
- vpmuludq $H1,$T2,$T1 # h1*r3
- vpaddq $T4,$D0,$D0 # d0 += h3*s2
-
- vmovdqa -0x10(%r11),$T4 # s4^4
- vpaddq $T1,$D4,$D4 # d4 += h1*r3
- vpmuludq $H0,$T2,$T2 # h0*r3
- vpmuludq $H4,$T3,$T0 # h4*s3
- vpaddq $T2,$D3,$D3 # d3 += h0*r3
- vpaddq $T0,$D2,$D2 # d2 += h4*s3
- vmovdqu 16*2($inp),$T0 # load input
- vpmuludq $H3,$T3,$T2 # h3*s3
- vpmuludq $H2,$T3,$T3 # h2*s3
- vpaddq $T2,$D1,$D1 # d1 += h3*s3
- vmovdqu 16*3($inp),$T1 #
- vpaddq $T3,$D0,$D0 # d0 += h2*s3
-
- vpmuludq $H2,$T4,$H2 # h2*s4
- vpmuludq $H3,$T4,$H3 # h3*s4
- vpsrldq \$6,$T0,$T2 # splat input
- vpaddq $H2,$D1,$D1 # d1 += h2*s4
- vpmuludq $H4,$T4,$H4 # h4*s4
- vpsrldq \$6,$T1,$T3 #
- vpaddq $H3,$D2,$H2 # h2 = d2 + h3*s4
- vpaddq $H4,$D3,$H3 # h3 = d3 + h4*s4
- vpmuludq -0x20(%r11),$H0,$H4 # h0*r4
- vpmuludq $H1,$T4,$H0
- vpunpckhqdq $T1,$T0,$T4 # 4
- vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4
- vpaddq $H0,$D0,$H0 # h0 = d0 + h1*s4
-
- vpunpcklqdq $T1,$T0,$T0 # 0:1
- vpunpcklqdq $T3,$T2,$T3 # 2:3
-
- #vpsrlq \$40,$T4,$T4 # 4
- vpsrldq \$`40/8`,$T4,$T4 # 4
- vpsrlq \$26,$T0,$T1
- vmovdqa 0x00(%rsp),$D4 # preload r0^2
- vpand $MASK,$T0,$T0 # 0
- vpsrlq \$4,$T3,$T2
- vpand $MASK,$T1,$T1 # 1
- vpand 0(%rcx),$T4,$T4 # .Lmask24
- vpsrlq \$30,$T3,$T3
- vpand $MASK,$T2,$T2 # 2
- vpand $MASK,$T3,$T3 # 3
- vpor 32(%rcx),$T4,$T4 # padbit, yes, always
-
- ################################################################
- # lazy reduction as discussed in "NEON crypto" by D.J. Bernstein
- # and P. Schwabe
-
- vpsrlq \$26,$H3,$D3
- vpand $MASK,$H3,$H3
- vpaddq $D3,$H4,$H4 # h3 -> h4
-
- vpsrlq \$26,$H0,$D0
- vpand $MASK,$H0,$H0
- vpaddq $D0,$D1,$H1 # h0 -> h1
-
- vpsrlq \$26,$H4,$D0
- vpand $MASK,$H4,$H4
-
- vpsrlq \$26,$H1,$D1
- vpand $MASK,$H1,$H1
- vpaddq $D1,$H2,$H2 # h1 -> h2
-
- vpaddq $D0,$H0,$H0
- vpsllq \$2,$D0,$D0
- vpaddq $D0,$H0,$H0 # h4 -> h0
-
- vpsrlq \$26,$H2,$D2
- vpand $MASK,$H2,$H2
- vpaddq $D2,$H3,$H3 # h2 -> h3
-
- vpsrlq \$26,$H0,$D0
- vpand $MASK,$H0,$H0
- vpaddq $D0,$H1,$H1 # h0 -> h1
-
- vpsrlq \$26,$H3,$D3
- vpand $MASK,$H3,$H3
- vpaddq $D3,$H4,$H4 # h3 -> h4
-
- ja .Loop_avx
-
-.Lskip_loop_avx:
- ################################################################
- # multiply (inp[0:1]+hash) or inp[2:3] by r^2:r^1
-
- vpshufd \$0x10,$D4,$D4 # r0^n, xx12 -> x1x2
- add \$32,$len
- jnz .Long_tail_avx
-
- vpaddq $H2,$T2,$T2
- vpaddq $H0,$T0,$T0
- vpaddq $H1,$T1,$T1
- vpaddq $H3,$T3,$T3
- vpaddq $H4,$T4,$T4
-
-.Long_tail_avx:
- vmovdqa $H2,0x20(%r11)
- vmovdqa $H0,0x00(%r11)
- vmovdqa $H1,0x10(%r11)
- vmovdqa $H3,0x30(%r11)
- vmovdqa $H4,0x40(%r11)
-
- # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
- # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
- # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
- # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
- # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
-
- vpmuludq $T2,$D4,$D2 # d2 = h2*r0
- vpmuludq $T0,$D4,$D0 # d0 = h0*r0
- vpshufd \$0x10,`16*1-64`($ctx),$H2 # r1^n
- vpmuludq $T1,$D4,$D1 # d1 = h1*r0
- vpmuludq $T3,$D4,$D3 # d3 = h3*r0
- vpmuludq $T4,$D4,$D4 # d4 = h4*r0
-
- vpmuludq $T3,$H2,$H0 # h3*r1
- vpaddq $H0,$D4,$D4 # d4 += h3*r1
- vpshufd \$0x10,`16*2-64`($ctx),$H3 # s1^n
- vpmuludq $T2,$H2,$H1 # h2*r1
- vpaddq $H1,$D3,$D3 # d3 += h2*r1
- vpshufd \$0x10,`16*3-64`($ctx),$H4 # r2^n
- vpmuludq $T1,$H2,$H0 # h1*r1
- vpaddq $H0,$D2,$D2 # d2 += h1*r1
- vpmuludq $T0,$H2,$H2 # h0*r1
- vpaddq $H2,$D1,$D1 # d1 += h0*r1
- vpmuludq $T4,$H3,$H3 # h4*s1
- vpaddq $H3,$D0,$D0 # d0 += h4*s1
-
- vpshufd \$0x10,`16*4-64`($ctx),$H2 # s2^n
- vpmuludq $T2,$H4,$H1 # h2*r2
- vpaddq $H1,$D4,$D4 # d4 += h2*r2
- vpmuludq $T1,$H4,$H0 # h1*r2
- vpaddq $H0,$D3,$D3 # d3 += h1*r2
- vpshufd \$0x10,`16*5-64`($ctx),$H3 # r3^n
- vpmuludq $T0,$H4,$H4 # h0*r2
- vpaddq $H4,$D2,$D2 # d2 += h0*r2
- vpmuludq $T4,$H2,$H1 # h4*s2
- vpaddq $H1,$D1,$D1 # d1 += h4*s2
- vpshufd \$0x10,`16*6-64`($ctx),$H4 # s3^n
- vpmuludq $T3,$H2,$H2 # h3*s2
- vpaddq $H2,$D0,$D0 # d0 += h3*s2
-
- vpmuludq $T1,$H3,$H0 # h1*r3
- vpaddq $H0,$D4,$D4 # d4 += h1*r3
- vpmuludq $T0,$H3,$H3 # h0*r3
- vpaddq $H3,$D3,$D3 # d3 += h0*r3
- vpshufd \$0x10,`16*7-64`($ctx),$H2 # r4^n
- vpmuludq $T4,$H4,$H1 # h4*s3
- vpaddq $H1,$D2,$D2 # d2 += h4*s3
- vpshufd \$0x10,`16*8-64`($ctx),$H3 # s4^n
- vpmuludq $T3,$H4,$H0 # h3*s3
- vpaddq $H0,$D1,$D1 # d1 += h3*s3
- vpmuludq $T2,$H4,$H4 # h2*s3
- vpaddq $H4,$D0,$D0 # d0 += h2*s3
-
- vpmuludq $T0,$H2,$H2 # h0*r4
- vpaddq $H2,$D4,$D4 # h4 = d4 + h0*r4
- vpmuludq $T4,$H3,$H1 # h4*s4
- vpaddq $H1,$D3,$D3 # h3 = d3 + h4*s4
- vpmuludq $T3,$H3,$H0 # h3*s4
- vpaddq $H0,$D2,$D2 # h2 = d2 + h3*s4
- vpmuludq $T2,$H3,$H1 # h2*s4
- vpaddq $H1,$D1,$D1 # h1 = d1 + h2*s4
- vpmuludq $T1,$H3,$H3 # h1*s4
- vpaddq $H3,$D0,$D0 # h0 = d0 + h1*s4
-
- jz .Lshort_tail_avx
-
- vmovdqu 16*0($inp),$H0 # load input
- vmovdqu 16*1($inp),$H1
-
- vpsrldq \$6,$H0,$H2 # splat input
- vpsrldq \$6,$H1,$H3
- vpunpckhqdq $H1,$H0,$H4 # 4
- vpunpcklqdq $H1,$H0,$H0 # 0:1
- vpunpcklqdq $H3,$H2,$H3 # 2:3
-
- vpsrlq \$40,$H4,$H4 # 4
- vpsrlq \$26,$H0,$H1
- vpand $MASK,$H0,$H0 # 0
- vpsrlq \$4,$H3,$H2
- vpand $MASK,$H1,$H1 # 1
- vpsrlq \$30,$H3,$H3
- vpand $MASK,$H2,$H2 # 2
- vpand $MASK,$H3,$H3 # 3
- vpor 32(%rcx),$H4,$H4 # padbit, yes, always
-
- vpshufd \$0x32,`16*0-64`($ctx),$T4 # r0^n, 34xx -> x3x4
- vpaddq 0x00(%r11),$H0,$H0
- vpaddq 0x10(%r11),$H1,$H1
- vpaddq 0x20(%r11),$H2,$H2
- vpaddq 0x30(%r11),$H3,$H3
- vpaddq 0x40(%r11),$H4,$H4
-
- ################################################################
- # multiply (inp[0:1]+hash) by r^4:r^3 and accumulate
-
- vpmuludq $H0,$T4,$T0 # h0*r0
- vpaddq $T0,$D0,$D0 # d0 += h0*r0
- vpmuludq $H1,$T4,$T1 # h1*r0
- vpaddq $T1,$D1,$D1 # d1 += h1*r0
- vpmuludq $H2,$T4,$T0 # h2*r0
- vpaddq $T0,$D2,$D2 # d2 += h2*r0
- vpshufd \$0x32,`16*1-64`($ctx),$T2 # r1^n
- vpmuludq $H3,$T4,$T1 # h3*r0
- vpaddq $T1,$D3,$D3 # d3 += h3*r0
- vpmuludq $H4,$T4,$T4 # h4*r0
- vpaddq $T4,$D4,$D4 # d4 += h4*r0
-
- vpmuludq $H3,$T2,$T0 # h3*r1
- vpaddq $T0,$D4,$D4 # d4 += h3*r1
- vpshufd \$0x32,`16*2-64`($ctx),$T3 # s1
- vpmuludq $H2,$T2,$T1 # h2*r1
- vpaddq $T1,$D3,$D3 # d3 += h2*r1
- vpshufd \$0x32,`16*3-64`($ctx),$T4 # r2
- vpmuludq $H1,$T2,$T0 # h1*r1
- vpaddq $T0,$D2,$D2 # d2 += h1*r1
- vpmuludq $H0,$T2,$T2 # h0*r1
- vpaddq $T2,$D1,$D1 # d1 += h0*r1
- vpmuludq $H4,$T3,$T3 # h4*s1
- vpaddq $T3,$D0,$D0 # d0 += h4*s1
-
- vpshufd \$0x32,`16*4-64`($ctx),$T2 # s2
- vpmuludq $H2,$T4,$T1 # h2*r2
- vpaddq $T1,$D4,$D4 # d4 += h2*r2
- vpmuludq $H1,$T4,$T0 # h1*r2
- vpaddq $T0,$D3,$D3 # d3 += h1*r2
- vpshufd \$0x32,`16*5-64`($ctx),$T3 # r3
- vpmuludq $H0,$T4,$T4 # h0*r2
- vpaddq $T4,$D2,$D2 # d2 += h0*r2
- vpmuludq $H4,$T2,$T1 # h4*s2
- vpaddq $T1,$D1,$D1 # d1 += h4*s2
- vpshufd \$0x32,`16*6-64`($ctx),$T4 # s3
- vpmuludq $H3,$T2,$T2 # h3*s2
- vpaddq $T2,$D0,$D0 # d0 += h3*s2
-
- vpmuludq $H1,$T3,$T0 # h1*r3
- vpaddq $T0,$D4,$D4 # d4 += h1*r3
- vpmuludq $H0,$T3,$T3 # h0*r3
- vpaddq $T3,$D3,$D3 # d3 += h0*r3
- vpshufd \$0x32,`16*7-64`($ctx),$T2 # r4
- vpmuludq $H4,$T4,$T1 # h4*s3
- vpaddq $T1,$D2,$D2 # d2 += h4*s3
- vpshufd \$0x32,`16*8-64`($ctx),$T3 # s4
- vpmuludq $H3,$T4,$T0 # h3*s3
- vpaddq $T0,$D1,$D1 # d1 += h3*s3
- vpmuludq $H2,$T4,$T4 # h2*s3
- vpaddq $T4,$D0,$D0 # d0 += h2*s3
-
- vpmuludq $H0,$T2,$T2 # h0*r4
- vpaddq $T2,$D4,$D4 # d4 += h0*r4
- vpmuludq $H4,$T3,$T1 # h4*s4
- vpaddq $T1,$D3,$D3 # d3 += h4*s4
- vpmuludq $H3,$T3,$T0 # h3*s4
- vpaddq $T0,$D2,$D2 # d2 += h3*s4
- vpmuludq $H2,$T3,$T1 # h2*s4
- vpaddq $T1,$D1,$D1 # d1 += h2*s4
- vpmuludq $H1,$T3,$T3 # h1*s4
- vpaddq $T3,$D0,$D0 # d0 += h1*s4
-
-.Lshort_tail_avx:
- ################################################################
- # horizontal addition
-
- vpsrldq \$8,$D4,$T4
- vpsrldq \$8,$D3,$T3
- vpsrldq \$8,$D1,$T1
- vpsrldq \$8,$D0,$T0
- vpsrldq \$8,$D2,$T2
- vpaddq $T3,$D3,$D3
- vpaddq $T4,$D4,$D4
- vpaddq $T0,$D0,$D0
- vpaddq $T1,$D1,$D1
- vpaddq $T2,$D2,$D2
-
- ################################################################
- # lazy reduction
-
- vpsrlq \$26,$D3,$H3
- vpand $MASK,$D3,$D3
- vpaddq $H3,$D4,$D4 # h3 -> h4
-
- vpsrlq \$26,$D0,$H0
- vpand $MASK,$D0,$D0
- vpaddq $H0,$D1,$D1 # h0 -> h1
-
- vpsrlq \$26,$D4,$H4
- vpand $MASK,$D4,$D4
-
- vpsrlq \$26,$D1,$H1
- vpand $MASK,$D1,$D1
- vpaddq $H1,$D2,$D2 # h1 -> h2
-
- vpaddq $H4,$D0,$D0
- vpsllq \$2,$H4,$H4
- vpaddq $H4,$D0,$D0 # h4 -> h0
-
- vpsrlq \$26,$D2,$H2
- vpand $MASK,$D2,$D2
- vpaddq $H2,$D3,$D3 # h2 -> h3
-
- vpsrlq \$26,$D0,$H0
- vpand $MASK,$D0,$D0
- vpaddq $H0,$D1,$D1 # h0 -> h1
-
- vpsrlq \$26,$D3,$H3
- vpand $MASK,$D3,$D3
- vpaddq $H3,$D4,$D4 # h3 -> h4
-
- vmovd $D0,`4*0-48-64`($ctx) # save partially reduced
- vmovd $D1,`4*1-48-64`($ctx)
- vmovd $D2,`4*2-48-64`($ctx)
- vmovd $D3,`4*3-48-64`($ctx)
- vmovd $D4,`4*4-48-64`($ctx)
-___
-$code.=<<___ if ($win64);
- vmovdqa 0x50(%r11),%xmm6
- vmovdqa 0x60(%r11),%xmm7
- vmovdqa 0x70(%r11),%xmm8
- vmovdqa 0x80(%r11),%xmm9
- vmovdqa 0x90(%r11),%xmm10
- vmovdqa 0xa0(%r11),%xmm11
- vmovdqa 0xb0(%r11),%xmm12
- vmovdqa 0xc0(%r11),%xmm13
- vmovdqa 0xd0(%r11),%xmm14
- vmovdqa 0xe0(%r11),%xmm15
- lea 0xf8(%r11),%rsp
-.Ldo_avx_epilogue:
-___
-$code.=<<___ if (!$win64);
- lea -8(%r10),%rsp
-.cfi_def_cfa_register %rsp
-___
-$code.=<<___;
- vzeroupper
- RET
-.cfi_endproc
-___
-&end_function("poly1305_blocks_avx");
-
-&declare_function("poly1305_emit_avx", 32, 3);
-$code.=<<___;
- cmpl \$0,20($ctx) # is_base2_26?
- je .Lemit
-
- mov 0($ctx),%eax # load hash value base 2^26
- mov 4($ctx),%ecx
- mov 8($ctx),%r8d
- mov 12($ctx),%r11d
- mov 16($ctx),%r10d
-
- shl \$26,%rcx # base 2^26 -> base 2^64
- mov %r8,%r9
- shl \$52,%r8
- add %rcx,%rax
- shr \$12,%r9
- add %rax,%r8 # h0
- adc \$0,%r9
-
- shl \$14,%r11
- mov %r10,%rax
- shr \$24,%r10
- add %r11,%r9
- shl \$40,%rax
- add %rax,%r9 # h1
- adc \$0,%r10 # h2
-
- mov %r10,%rax # could be partially reduced, so reduce
- mov %r10,%rcx
- and \$3,%r10
- shr \$2,%rax
- and \$-4,%rcx
- add %rcx,%rax
- add %rax,%r8
- adc \$0,%r9
- adc \$0,%r10
-
- mov %r8,%rax
- add \$5,%r8 # compare to modulus
- mov %r9,%rcx
- adc \$0,%r9
- adc \$0,%r10
- shr \$2,%r10 # did 130-bit value overflow?
- cmovnz %r8,%rax
- cmovnz %r9,%rcx
-
- add 0($nonce),%rax # accumulate nonce
- adc 8($nonce),%rcx
- mov %rax,0($mac) # write result
- mov %rcx,8($mac)
-
- RET
-___
-&end_function("poly1305_emit_avx");
-
-if ($avx>1) {
-
-my ($H0,$H1,$H2,$H3,$H4, $MASK, $T4,$T0,$T1,$T2,$T3, $D0,$D1,$D2,$D3,$D4) =
- map("%ymm$_",(0..15));
-my $S4=$MASK;
-
-sub poly1305_blocks_avxN {
- my ($avx512) = @_;
- my $suffix = $avx512 ? "_avx512" : "";
-$code.=<<___;
-.cfi_startproc
- mov 20($ctx),%r8d # is_base2_26
- cmp \$128,$len
- jae .Lblocks_avx2$suffix
- test %r8d,%r8d
- jz .Lblocks
-
-.Lblocks_avx2$suffix:
- and \$-16,$len
- jz .Lno_data_avx2$suffix
-
- vzeroupper
-
- test %r8d,%r8d
- jz .Lbase2_64_avx2$suffix
-
- test \$63,$len
- jz .Leven_avx2$suffix
-
- push %rbp
-.cfi_push %rbp
- mov %rsp,%rbp
- push %rbx
-.cfi_push %rbx
- push %r12
-.cfi_push %r12
- push %r13
-.cfi_push %r13
- push %r14
-.cfi_push %r14
- push %r15
-.cfi_push %r15
-.Lblocks_avx2_body$suffix:
-
- mov $len,%r15 # reassign $len
-
- mov 0($ctx),$d1 # load hash value
- mov 8($ctx),$d2
- mov 16($ctx),$h2#d
-
- mov 24($ctx),$r0 # load r
- mov 32($ctx),$s1
-
- ################################# base 2^26 -> base 2^64
- mov $d1#d,$h0#d
- and \$`-1*(1<<31)`,$d1
- mov $d2,$r1 # borrow $r1
- mov $d2#d,$h1#d
- and \$`-1*(1<<31)`,$d2
-
- shr \$6,$d1
- shl \$52,$r1
- add $d1,$h0
- shr \$12,$h1
- shr \$18,$d2
- add $r1,$h0
- adc $d2,$h1
-
- mov $h2,$d1
- shl \$40,$d1
- shr \$24,$h2
- add $d1,$h1
- adc \$0,$h2 # can be partially reduced...
-
- mov \$-4,$d2 # ... so reduce
- mov $h2,$d1
- and $h2,$d2
- shr \$2,$d1
- and \$3,$h2
- add $d2,$d1 # =*5
- add $d1,$h0
- adc \$0,$h1
- adc \$0,$h2
-
- mov $s1,$r1
- mov $s1,%rax
- shr \$2,$s1
- add $r1,$s1 # s1 = r1 + (r1 >> 2)
-
-.Lbase2_26_pre_avx2$suffix:
- add 0($inp),$h0 # accumulate input
- adc 8($inp),$h1
- lea 16($inp),$inp
- adc $padbit,$h2
- sub \$16,%r15
-
- call __poly1305_block
- mov $r1,%rax
-
- test \$63,%r15
- jnz .Lbase2_26_pre_avx2$suffix
-
- test $padbit,$padbit # if $padbit is zero,
- jz .Lstore_base2_64_avx2$suffix # store hash in base 2^64 format
-
- ################################# base 2^64 -> base 2^26
- mov $h0,%rax
- mov $h0,%rdx
- shr \$52,$h0
- mov $h1,$r0
- mov $h1,$r1
- shr \$26,%rdx
- and \$0x3ffffff,%rax # h[0]
- shl \$12,$r0
- and \$0x3ffffff,%rdx # h[1]
- shr \$14,$h1
- or $r0,$h0
- shl \$24,$h2
- and \$0x3ffffff,$h0 # h[2]
- shr \$40,$r1
- and \$0x3ffffff,$h1 # h[3]
- or $r1,$h2 # h[4]
-
- test %r15,%r15
- jz .Lstore_base2_26_avx2$suffix
-
- vmovd %rax#d,%x#$H0
- vmovd %rdx#d,%x#$H1
- vmovd $h0#d,%x#$H2
- vmovd $h1#d,%x#$H3
- vmovd $h2#d,%x#$H4
- jmp .Lproceed_avx2$suffix
-
-.align 32
-.Lstore_base2_64_avx2$suffix:
- mov $h0,0($ctx)
- mov $h1,8($ctx)
- mov $h2,16($ctx) # note that is_base2_26 is zeroed
- jmp .Ldone_avx2$suffix
-
-.align 16
-.Lstore_base2_26_avx2$suffix:
- mov %rax#d,0($ctx) # store hash value base 2^26
- mov %rdx#d,4($ctx)
- mov $h0#d,8($ctx)
- mov $h1#d,12($ctx)
- mov $h2#d,16($ctx)
-.align 16
-.Ldone_avx2$suffix:
- pop %r15
-.cfi_restore %r15
- pop %r14
-.cfi_restore %r14
- pop %r13
-.cfi_restore %r13
- pop %r12
-.cfi_restore %r12
- pop %rbx
-.cfi_restore %rbx
- pop %rbp
-.cfi_restore %rbp
-.Lno_data_avx2$suffix:
-.Lblocks_avx2_epilogue$suffix:
- RET
-.cfi_endproc
-
-.align 32
-.Lbase2_64_avx2$suffix:
-.cfi_startproc
- push %rbp
-.cfi_push %rbp
- mov %rsp,%rbp
- push %rbx
-.cfi_push %rbx
- push %r12
-.cfi_push %r12
- push %r13
-.cfi_push %r13
- push %r14
-.cfi_push %r14
- push %r15
-.cfi_push %r15
-.Lbase2_64_avx2_body$suffix:
-
- mov $len,%r15 # reassign $len
-
- mov 24($ctx),$r0 # load r
- mov 32($ctx),$s1
-
- mov 0($ctx),$h0 # load hash value
- mov 8($ctx),$h1
- mov 16($ctx),$h2#d
-
- mov $s1,$r1
- mov $s1,%rax
- shr \$2,$s1
- add $r1,$s1 # s1 = r1 + (r1 >> 2)
-
- test \$63,$len
- jz .Linit_avx2$suffix
-
-.Lbase2_64_pre_avx2$suffix:
- add 0($inp),$h0 # accumulate input
- adc 8($inp),$h1
- lea 16($inp),$inp
- adc $padbit,$h2
- sub \$16,%r15
-
- call __poly1305_block
- mov $r1,%rax
-
- test \$63,%r15
- jnz .Lbase2_64_pre_avx2$suffix
-
-.Linit_avx2$suffix:
- ################################# base 2^64 -> base 2^26
- mov $h0,%rax
- mov $h0,%rdx
- shr \$52,$h0
- mov $h1,$d1
- mov $h1,$d2
- shr \$26,%rdx
- and \$0x3ffffff,%rax # h[0]
- shl \$12,$d1
- and \$0x3ffffff,%rdx # h[1]
- shr \$14,$h1
- or $d1,$h0
- shl \$24,$h2
- and \$0x3ffffff,$h0 # h[2]
- shr \$40,$d2
- and \$0x3ffffff,$h1 # h[3]
- or $d2,$h2 # h[4]
-
- vmovd %rax#d,%x#$H0
- vmovd %rdx#d,%x#$H1
- vmovd $h0#d,%x#$H2
- vmovd $h1#d,%x#$H3
- vmovd $h2#d,%x#$H4
- movl \$1,20($ctx) # set is_base2_26
-
- call __poly1305_init_avx
-
-.Lproceed_avx2$suffix:
- mov %r15,$len # restore $len
-___
-$code.=<<___ if (!$kernel);
- mov OPENSSL_ia32cap_P+8(%rip),%r9d
- mov \$`(1<<31|1<<30|1<<16)`,%r11d
-___
-$code.=<<___;
- pop %r15
-.cfi_restore %r15
- pop %r14
-.cfi_restore %r14
- pop %r13
-.cfi_restore %r13
- pop %r12
-.cfi_restore %r12
- pop %rbx
-.cfi_restore %rbx
- pop %rbp
-.cfi_restore %rbp
-.Lbase2_64_avx2_epilogue$suffix:
- jmp .Ldo_avx2$suffix
-.cfi_endproc
-
-.align 32
-.Leven_avx2$suffix:
-.cfi_startproc
-___
-$code.=<<___ if (!$kernel);
- mov OPENSSL_ia32cap_P+8(%rip),%r9d
-___
-$code.=<<___;
- vmovd 4*0($ctx),%x#$H0 # load hash value base 2^26
- vmovd 4*1($ctx),%x#$H1
- vmovd 4*2($ctx),%x#$H2
- vmovd 4*3($ctx),%x#$H3
- vmovd 4*4($ctx),%x#$H4
-
-.Ldo_avx2$suffix:
-___
-$code.=<<___ if (!$kernel && $avx>2);
- cmp \$512,$len
- jb .Lskip_avx512
- and %r11d,%r9d
- test \$`1<<16`,%r9d # check for AVX512F
- jnz .Lblocks_avx512
-.Lskip_avx512$suffix:
-___
-$code.=<<___ if ($avx > 2 && $avx512 && $kernel);
- cmp \$512,$len
- jae .Lblocks_avx512
-___
-$code.=<<___ if (!$win64);
- lea 8(%rsp),%r10
-.cfi_def_cfa_register %r10
- sub \$0x128,%rsp
-___
-$code.=<<___ if ($win64);
- lea 8(%rsp),%r10
- sub \$0x1c8,%rsp
- vmovdqa %xmm6,-0xb0(%r10)
- vmovdqa %xmm7,-0xa0(%r10)
- vmovdqa %xmm8,-0x90(%r10)
- vmovdqa %xmm9,-0x80(%r10)
- vmovdqa %xmm10,-0x70(%r10)
- vmovdqa %xmm11,-0x60(%r10)
- vmovdqa %xmm12,-0x50(%r10)
- vmovdqa %xmm13,-0x40(%r10)
- vmovdqa %xmm14,-0x30(%r10)
- vmovdqa %xmm15,-0x20(%r10)
-.Ldo_avx2_body$suffix:
-___
-$code.=<<___;
- lea .Lconst(%rip),%rcx
- lea 48+64($ctx),$ctx # size optimization
- vmovdqa 96(%rcx),$T0 # .Lpermd_avx2
-
- # expand and copy pre-calculated table to stack
- vmovdqu `16*0-64`($ctx),%x#$T2
- and \$-512,%rsp
- vmovdqu `16*1-64`($ctx),%x#$T3
- vmovdqu `16*2-64`($ctx),%x#$T4
- vmovdqu `16*3-64`($ctx),%x#$D0
- vmovdqu `16*4-64`($ctx),%x#$D1
- vmovdqu `16*5-64`($ctx),%x#$D2
- lea 0x90(%rsp),%rax # size optimization
- vmovdqu `16*6-64`($ctx),%x#$D3
- vpermd $T2,$T0,$T2 # 00003412 -> 14243444
- vmovdqu `16*7-64`($ctx),%x#$D4
- vpermd $T3,$T0,$T3
- vmovdqu `16*8-64`($ctx),%x#$MASK
- vpermd $T4,$T0,$T4
- vmovdqa $T2,0x00(%rsp)
- vpermd $D0,$T0,$D0
- vmovdqa $T3,0x20-0x90(%rax)
- vpermd $D1,$T0,$D1
- vmovdqa $T4,0x40-0x90(%rax)
- vpermd $D2,$T0,$D2
- vmovdqa $D0,0x60-0x90(%rax)
- vpermd $D3,$T0,$D3
- vmovdqa $D1,0x80-0x90(%rax)
- vpermd $D4,$T0,$D4
- vmovdqa $D2,0xa0-0x90(%rax)
- vpermd $MASK,$T0,$MASK
- vmovdqa $D3,0xc0-0x90(%rax)
- vmovdqa $D4,0xe0-0x90(%rax)
- vmovdqa $MASK,0x100-0x90(%rax)
- vmovdqa 64(%rcx),$MASK # .Lmask26
-
- ################################################################
- # load input
- vmovdqu 16*0($inp),%x#$T0
- vmovdqu 16*1($inp),%x#$T1
- vinserti128 \$1,16*2($inp),$T0,$T0
- vinserti128 \$1,16*3($inp),$T1,$T1
- lea 16*4($inp),$inp
-
- vpsrldq \$6,$T0,$T2 # splat input
- vpsrldq \$6,$T1,$T3
- vpunpckhqdq $T1,$T0,$T4 # 4
- vpunpcklqdq $T3,$T2,$T2 # 2:3
- vpunpcklqdq $T1,$T0,$T0 # 0:1
-
- vpsrlq \$30,$T2,$T3
- vpsrlq \$4,$T2,$T2
- vpsrlq \$26,$T0,$T1
- vpsrlq \$40,$T4,$T4 # 4
- vpand $MASK,$T2,$T2 # 2
- vpand $MASK,$T0,$T0 # 0
- vpand $MASK,$T1,$T1 # 1
- vpand $MASK,$T3,$T3 # 3
- vpor 32(%rcx),$T4,$T4 # padbit, yes, always
-
- vpaddq $H2,$T2,$H2 # accumulate input
- sub \$64,$len
- jz .Ltail_avx2$suffix
- jmp .Loop_avx2$suffix
-
-.align 32
-.Loop_avx2$suffix:
- ################################################################
- # ((inp[0]*r^4+inp[4])*r^4+inp[ 8])*r^4
- # ((inp[1]*r^4+inp[5])*r^4+inp[ 9])*r^3
- # ((inp[2]*r^4+inp[6])*r^4+inp[10])*r^2
- # ((inp[3]*r^4+inp[7])*r^4+inp[11])*r^1
- # \________/\__________/
- ################################################################
- #vpaddq $H2,$T2,$H2 # accumulate input
- vpaddq $H0,$T0,$H0
- vmovdqa `32*0`(%rsp),$T0 # r0^4
- vpaddq $H1,$T1,$H1
- vmovdqa `32*1`(%rsp),$T1 # r1^4
- vpaddq $H3,$T3,$H3
- vmovdqa `32*3`(%rsp),$T2 # r2^4
- vpaddq $H4,$T4,$H4
- vmovdqa `32*6-0x90`(%rax),$T3 # s3^4
- vmovdqa `32*8-0x90`(%rax),$S4 # s4^4
-
- # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
- # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
- # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
- # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
- # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
- #
- # however, as h2 is "chronologically" first one available pull
- # corresponding operations up, so it's
- #
- # d4 = h2*r2 + h4*r0 + h3*r1 + h1*r3 + h0*r4
- # d3 = h2*r1 + h3*r0 + h1*r2 + h0*r3 + h4*5*r4
- # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
- # d1 = h2*5*r4 + h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3
- # d0 = h2*5*r3 + h0*r0 + h4*5*r1 + h3*5*r2 + h1*5*r4
-
- vpmuludq $H2,$T0,$D2 # d2 = h2*r0
- vpmuludq $H2,$T1,$D3 # d3 = h2*r1
- vpmuludq $H2,$T2,$D4 # d4 = h2*r2
- vpmuludq $H2,$T3,$D0 # d0 = h2*s3
- vpmuludq $H2,$S4,$D1 # d1 = h2*s4
-
- vpmuludq $H0,$T1,$T4 # h0*r1
- vpmuludq $H1,$T1,$H2 # h1*r1, borrow $H2 as temp
- vpaddq $T4,$D1,$D1 # d1 += h0*r1
- vpaddq $H2,$D2,$D2 # d2 += h1*r1
- vpmuludq $H3,$T1,$T4 # h3*r1
- vpmuludq `32*2`(%rsp),$H4,$H2 # h4*s1
- vpaddq $T4,$D4,$D4 # d4 += h3*r1
- vpaddq $H2,$D0,$D0 # d0 += h4*s1
- vmovdqa `32*4-0x90`(%rax),$T1 # s2
-
- vpmuludq $H0,$T0,$T4 # h0*r0
- vpmuludq $H1,$T0,$H2 # h1*r0
- vpaddq $T4,$D0,$D0 # d0 += h0*r0
- vpaddq $H2,$D1,$D1 # d1 += h1*r0
- vpmuludq $H3,$T0,$T4 # h3*r0
- vpmuludq $H4,$T0,$H2 # h4*r0
- vmovdqu 16*0($inp),%x#$T0 # load input
- vpaddq $T4,$D3,$D3 # d3 += h3*r0
- vpaddq $H2,$D4,$D4 # d4 += h4*r0
- vinserti128 \$1,16*2($inp),$T0,$T0
-
- vpmuludq $H3,$T1,$T4 # h3*s2
- vpmuludq $H4,$T1,$H2 # h4*s2
- vmovdqu 16*1($inp),%x#$T1
- vpaddq $T4,$D0,$D0 # d0 += h3*s2
- vpaddq $H2,$D1,$D1 # d1 += h4*s2
- vmovdqa `32*5-0x90`(%rax),$H2 # r3
- vpmuludq $H1,$T2,$T4 # h1*r2
- vpmuludq $H0,$T2,$T2 # h0*r2
- vpaddq $T4,$D3,$D3 # d3 += h1*r2
- vpaddq $T2,$D2,$D2 # d2 += h0*r2
- vinserti128 \$1,16*3($inp),$T1,$T1
- lea 16*4($inp),$inp
-
- vpmuludq $H1,$H2,$T4 # h1*r3
- vpmuludq $H0,$H2,$H2 # h0*r3
- vpsrldq \$6,$T0,$T2 # splat input
- vpaddq $T4,$D4,$D4 # d4 += h1*r3
- vpaddq $H2,$D3,$D3 # d3 += h0*r3
- vpmuludq $H3,$T3,$T4 # h3*s3
- vpmuludq $H4,$T3,$H2 # h4*s3
- vpsrldq \$6,$T1,$T3
- vpaddq $T4,$D1,$D1 # d1 += h3*s3
- vpaddq $H2,$D2,$D2 # d2 += h4*s3
- vpunpckhqdq $T1,$T0,$T4 # 4
-
- vpmuludq $H3,$S4,$H3 # h3*s4
- vpmuludq $H4,$S4,$H4 # h4*s4
- vpunpcklqdq $T1,$T0,$T0 # 0:1
- vpaddq $H3,$D2,$H2 # h2 = d2 + h3*r4
- vpaddq $H4,$D3,$H3 # h3 = d3 + h4*r4
- vpunpcklqdq $T3,$T2,$T3 # 2:3
- vpmuludq `32*7-0x90`(%rax),$H0,$H4 # h0*r4
- vpmuludq $H1,$S4,$H0 # h1*s4
- vmovdqa 64(%rcx),$MASK # .Lmask26
- vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4
- vpaddq $H0,$D0,$H0 # h0 = d0 + h1*s4
-
- ################################################################
- # lazy reduction (interleaved with tail of input splat)
-
- vpsrlq \$26,$H3,$D3
- vpand $MASK,$H3,$H3
- vpaddq $D3,$H4,$H4 # h3 -> h4
-
- vpsrlq \$26,$H0,$D0
- vpand $MASK,$H0,$H0
- vpaddq $D0,$D1,$H1 # h0 -> h1
-
- vpsrlq \$26,$H4,$D4
- vpand $MASK,$H4,$H4
-
- vpsrlq \$4,$T3,$T2
-
- vpsrlq \$26,$H1,$D1
- vpand $MASK,$H1,$H1
- vpaddq $D1,$H2,$H2 # h1 -> h2
-
- vpaddq $D4,$H0,$H0
- vpsllq \$2,$D4,$D4
- vpaddq $D4,$H0,$H0 # h4 -> h0
-
- vpand $MASK,$T2,$T2 # 2
- vpsrlq \$26,$T0,$T1
-
- vpsrlq \$26,$H2,$D2
- vpand $MASK,$H2,$H2
- vpaddq $D2,$H3,$H3 # h2 -> h3
-
- vpaddq $T2,$H2,$H2 # modulo-scheduled
- vpsrlq \$30,$T3,$T3
-
- vpsrlq \$26,$H0,$D0
- vpand $MASK,$H0,$H0
- vpaddq $D0,$H1,$H1 # h0 -> h1
-
- vpsrlq \$40,$T4,$T4 # 4
-
- vpsrlq \$26,$H3,$D3
- vpand $MASK,$H3,$H3
- vpaddq $D3,$H4,$H4 # h3 -> h4
-
- vpand $MASK,$T0,$T0 # 0
- vpand $MASK,$T1,$T1 # 1
- vpand $MASK,$T3,$T3 # 3
- vpor 32(%rcx),$T4,$T4 # padbit, yes, always
-
- sub \$64,$len
- jnz .Loop_avx2$suffix
-
- .byte 0x66,0x90
-.Ltail_avx2$suffix:
- ################################################################
- # while above multiplications were by r^4 in all lanes, in last
- # iteration we multiply least significant lane by r^4 and most
- # significant one by r, so copy of above except that references
- # to the precomputed table are displaced by 4...
-
- #vpaddq $H2,$T2,$H2 # accumulate input
- vpaddq $H0,$T0,$H0
- vmovdqu `32*0+4`(%rsp),$T0 # r0^4
- vpaddq $H1,$T1,$H1
- vmovdqu `32*1+4`(%rsp),$T1 # r1^4
- vpaddq $H3,$T3,$H3
- vmovdqu `32*3+4`(%rsp),$T2 # r2^4
- vpaddq $H4,$T4,$H4
- vmovdqu `32*6+4-0x90`(%rax),$T3 # s3^4
- vmovdqu `32*8+4-0x90`(%rax),$S4 # s4^4
-
- vpmuludq $H2,$T0,$D2 # d2 = h2*r0
- vpmuludq $H2,$T1,$D3 # d3 = h2*r1
- vpmuludq $H2,$T2,$D4 # d4 = h2*r2
- vpmuludq $H2,$T3,$D0 # d0 = h2*s3
- vpmuludq $H2,$S4,$D1 # d1 = h2*s4
-
- vpmuludq $H0,$T1,$T4 # h0*r1
- vpmuludq $H1,$T1,$H2 # h1*r1
- vpaddq $T4,$D1,$D1 # d1 += h0*r1
- vpaddq $H2,$D2,$D2 # d2 += h1*r1
- vpmuludq $H3,$T1,$T4 # h3*r1
- vpmuludq `32*2+4`(%rsp),$H4,$H2 # h4*s1
- vpaddq $T4,$D4,$D4 # d4 += h3*r1
- vpaddq $H2,$D0,$D0 # d0 += h4*s1
-
- vpmuludq $H0,$T0,$T4 # h0*r0
- vpmuludq $H1,$T0,$H2 # h1*r0
- vpaddq $T4,$D0,$D0 # d0 += h0*r0
- vmovdqu `32*4+4-0x90`(%rax),$T1 # s2
- vpaddq $H2,$D1,$D1 # d1 += h1*r0
- vpmuludq $H3,$T0,$T4 # h3*r0
- vpmuludq $H4,$T0,$H2 # h4*r0
- vpaddq $T4,$D3,$D3 # d3 += h3*r0
- vpaddq $H2,$D4,$D4 # d4 += h4*r0
-
- vpmuludq $H3,$T1,$T4 # h3*s2
- vpmuludq $H4,$T1,$H2 # h4*s2
- vpaddq $T4,$D0,$D0 # d0 += h3*s2
- vpaddq $H2,$D1,$D1 # d1 += h4*s2
- vmovdqu `32*5+4-0x90`(%rax),$H2 # r3
- vpmuludq $H1,$T2,$T4 # h1*r2
- vpmuludq $H0,$T2,$T2 # h0*r2
- vpaddq $T4,$D3,$D3 # d3 += h1*r2
- vpaddq $T2,$D2,$D2 # d2 += h0*r2
-
- vpmuludq $H1,$H2,$T4 # h1*r3
- vpmuludq $H0,$H2,$H2 # h0*r3
- vpaddq $T4,$D4,$D4 # d4 += h1*r3
- vpaddq $H2,$D3,$D3 # d3 += h0*r3
- vpmuludq $H3,$T3,$T4 # h3*s3
- vpmuludq $H4,$T3,$H2 # h4*s3
- vpaddq $T4,$D1,$D1 # d1 += h3*s3
- vpaddq $H2,$D2,$D2 # d2 += h4*s3
-
- vpmuludq $H3,$S4,$H3 # h3*s4
- vpmuludq $H4,$S4,$H4 # h4*s4
- vpaddq $H3,$D2,$H2 # h2 = d2 + h3*r4
- vpaddq $H4,$D3,$H3 # h3 = d3 + h4*r4
- vpmuludq `32*7+4-0x90`(%rax),$H0,$H4 # h0*r4
- vpmuludq $H1,$S4,$H0 # h1*s4
- vmovdqa 64(%rcx),$MASK # .Lmask26
- vpaddq $H4,$D4,$H4 # h4 = d4 + h0*r4
- vpaddq $H0,$D0,$H0 # h0 = d0 + h1*s4
-
- ################################################################
- # horizontal addition
-
- vpsrldq \$8,$D1,$T1
- vpsrldq \$8,$H2,$T2
- vpsrldq \$8,$H3,$T3
- vpsrldq \$8,$H4,$T4
- vpsrldq \$8,$H0,$T0
- vpaddq $T1,$D1,$D1
- vpaddq $T2,$H2,$H2
- vpaddq $T3,$H3,$H3
- vpaddq $T4,$H4,$H4
- vpaddq $T0,$H0,$H0
-
- vpermq \$0x2,$H3,$T3
- vpermq \$0x2,$H4,$T4
- vpermq \$0x2,$H0,$T0
- vpermq \$0x2,$D1,$T1
- vpermq \$0x2,$H2,$T2
- vpaddq $T3,$H3,$H3
- vpaddq $T4,$H4,$H4
- vpaddq $T0,$H0,$H0
- vpaddq $T1,$D1,$D1
- vpaddq $T2,$H2,$H2
-
- ################################################################
- # lazy reduction
-
- vpsrlq \$26,$H3,$D3
- vpand $MASK,$H3,$H3
- vpaddq $D3,$H4,$H4 # h3 -> h4
-
- vpsrlq \$26,$H0,$D0
- vpand $MASK,$H0,$H0
- vpaddq $D0,$D1,$H1 # h0 -> h1
-
- vpsrlq \$26,$H4,$D4
- vpand $MASK,$H4,$H4
-
- vpsrlq \$26,$H1,$D1
- vpand $MASK,$H1,$H1
- vpaddq $D1,$H2,$H2 # h1 -> h2
-
- vpaddq $D4,$H0,$H0
- vpsllq \$2,$D4,$D4
- vpaddq $D4,$H0,$H0 # h4 -> h0
-
- vpsrlq \$26,$H2,$D2
- vpand $MASK,$H2,$H2
- vpaddq $D2,$H3,$H3 # h2 -> h3
-
- vpsrlq \$26,$H0,$D0
- vpand $MASK,$H0,$H0
- vpaddq $D0,$H1,$H1 # h0 -> h1
-
- vpsrlq \$26,$H3,$D3
- vpand $MASK,$H3,$H3
- vpaddq $D3,$H4,$H4 # h3 -> h4
-
- vmovd %x#$H0,`4*0-48-64`($ctx)# save partially reduced
- vmovd %x#$H1,`4*1-48-64`($ctx)
- vmovd %x#$H2,`4*2-48-64`($ctx)
- vmovd %x#$H3,`4*3-48-64`($ctx)
- vmovd %x#$H4,`4*4-48-64`($ctx)
-___
-$code.=<<___ if ($win64);
- vmovdqa -0xb0(%r10),%xmm6
- vmovdqa -0xa0(%r10),%xmm7
- vmovdqa -0x90(%r10),%xmm8
- vmovdqa -0x80(%r10),%xmm9
- vmovdqa -0x70(%r10),%xmm10
- vmovdqa -0x60(%r10),%xmm11
- vmovdqa -0x50(%r10),%xmm12
- vmovdqa -0x40(%r10),%xmm13
- vmovdqa -0x30(%r10),%xmm14
- vmovdqa -0x20(%r10),%xmm15
- lea -8(%r10),%rsp
-.Ldo_avx2_epilogue$suffix:
-___
-$code.=<<___ if (!$win64);
- lea -8(%r10),%rsp
-.cfi_def_cfa_register %rsp
-___
-$code.=<<___;
- vzeroupper
- RET
-.cfi_endproc
-___
-if($avx > 2 && $avx512) {
-my ($R0,$R1,$R2,$R3,$R4, $S1,$S2,$S3,$S4) = map("%zmm$_",(16..24));
-my ($M0,$M1,$M2,$M3,$M4) = map("%zmm$_",(25..29));
-my $PADBIT="%zmm30";
-
-map(s/%y/%z/,($T4,$T0,$T1,$T2,$T3)); # switch to %zmm domain
-map(s/%y/%z/,($D0,$D1,$D2,$D3,$D4));
-map(s/%y/%z/,($H0,$H1,$H2,$H3,$H4));
-map(s/%y/%z/,($MASK));
-
-$code.=<<___;
-.cfi_startproc
-.Lblocks_avx512:
- mov \$15,%eax
- kmovw %eax,%k2
-___
-$code.=<<___ if (!$win64);
- lea 8(%rsp),%r10
-.cfi_def_cfa_register %r10
- sub \$0x128,%rsp
-___
-$code.=<<___ if ($win64);
- lea 8(%rsp),%r10
- sub \$0x1c8,%rsp
- vmovdqa %xmm6,-0xb0(%r10)
- vmovdqa %xmm7,-0xa0(%r10)
- vmovdqa %xmm8,-0x90(%r10)
- vmovdqa %xmm9,-0x80(%r10)
- vmovdqa %xmm10,-0x70(%r10)
- vmovdqa %xmm11,-0x60(%r10)
- vmovdqa %xmm12,-0x50(%r10)
- vmovdqa %xmm13,-0x40(%r10)
- vmovdqa %xmm14,-0x30(%r10)
- vmovdqa %xmm15,-0x20(%r10)
-.Ldo_avx512_body:
-___
-$code.=<<___;
- lea .Lconst(%rip),%rcx
- lea 48+64($ctx),$ctx # size optimization
- vmovdqa 96(%rcx),%y#$T2 # .Lpermd_avx2
-
- # expand pre-calculated table
- vmovdqu `16*0-64`($ctx),%x#$D0 # will become expanded ${R0}
- and \$-512,%rsp
- vmovdqu `16*1-64`($ctx),%x#$D1 # will become ... ${R1}
- mov \$0x20,%rax
- vmovdqu `16*2-64`($ctx),%x#$T0 # ... ${S1}
- vmovdqu `16*3-64`($ctx),%x#$D2 # ... ${R2}
- vmovdqu `16*4-64`($ctx),%x#$T1 # ... ${S2}
- vmovdqu `16*5-64`($ctx),%x#$D3 # ... ${R3}
- vmovdqu `16*6-64`($ctx),%x#$T3 # ... ${S3}
- vmovdqu `16*7-64`($ctx),%x#$D4 # ... ${R4}
- vmovdqu `16*8-64`($ctx),%x#$T4 # ... ${S4}
- vpermd $D0,$T2,$R0 # 00003412 -> 14243444
- vpbroadcastq 64(%rcx),$MASK # .Lmask26
- vpermd $D1,$T2,$R1
- vpermd $T0,$T2,$S1
- vpermd $D2,$T2,$R2
- vmovdqa64 $R0,0x00(%rsp){%k2} # save in case $len%128 != 0
- vpsrlq \$32,$R0,$T0 # 14243444 -> 01020304
- vpermd $T1,$T2,$S2
- vmovdqu64 $R1,0x00(%rsp,%rax){%k2}
- vpsrlq \$32,$R1,$T1
- vpermd $D3,$T2,$R3
- vmovdqa64 $S1,0x40(%rsp){%k2}
- vpermd $T3,$T2,$S3
- vpermd $D4,$T2,$R4
- vmovdqu64 $R2,0x40(%rsp,%rax){%k2}
- vpermd $T4,$T2,$S4
- vmovdqa64 $S2,0x80(%rsp){%k2}
- vmovdqu64 $R3,0x80(%rsp,%rax){%k2}
- vmovdqa64 $S3,0xc0(%rsp){%k2}
- vmovdqu64 $R4,0xc0(%rsp,%rax){%k2}
- vmovdqa64 $S4,0x100(%rsp){%k2}
-
- ################################################################
- # calculate 5th through 8th powers of the key
- #
- # d0 = r0'*r0 + r1'*5*r4 + r2'*5*r3 + r3'*5*r2 + r4'*5*r1
- # d1 = r0'*r1 + r1'*r0 + r2'*5*r4 + r3'*5*r3 + r4'*5*r2
- # d2 = r0'*r2 + r1'*r1 + r2'*r0 + r3'*5*r4 + r4'*5*r3
- # d3 = r0'*r3 + r1'*r2 + r2'*r1 + r3'*r0 + r4'*5*r4
- # d4 = r0'*r4 + r1'*r3 + r2'*r2 + r3'*r1 + r4'*r0
-
- vpmuludq $T0,$R0,$D0 # d0 = r0'*r0
- vpmuludq $T0,$R1,$D1 # d1 = r0'*r1
- vpmuludq $T0,$R2,$D2 # d2 = r0'*r2
- vpmuludq $T0,$R3,$D3 # d3 = r0'*r3
- vpmuludq $T0,$R4,$D4 # d4 = r0'*r4
- vpsrlq \$32,$R2,$T2
-
- vpmuludq $T1,$S4,$M0
- vpmuludq $T1,$R0,$M1
- vpmuludq $T1,$R1,$M2
- vpmuludq $T1,$R2,$M3
- vpmuludq $T1,$R3,$M4
- vpsrlq \$32,$R3,$T3
- vpaddq $M0,$D0,$D0 # d0 += r1'*5*r4
- vpaddq $M1,$D1,$D1 # d1 += r1'*r0
- vpaddq $M2,$D2,$D2 # d2 += r1'*r1
- vpaddq $M3,$D3,$D3 # d3 += r1'*r2
- vpaddq $M4,$D4,$D4 # d4 += r1'*r3
-
- vpmuludq $T2,$S3,$M0
- vpmuludq $T2,$S4,$M1
- vpmuludq $T2,$R1,$M3
- vpmuludq $T2,$R2,$M4
- vpmuludq $T2,$R0,$M2
- vpsrlq \$32,$R4,$T4
- vpaddq $M0,$D0,$D0 # d0 += r2'*5*r3
- vpaddq $M1,$D1,$D1 # d1 += r2'*5*r4
- vpaddq $M3,$D3,$D3 # d3 += r2'*r1
- vpaddq $M4,$D4,$D4 # d4 += r2'*r2
- vpaddq $M2,$D2,$D2 # d2 += r2'*r0
-
- vpmuludq $T3,$S2,$M0
- vpmuludq $T3,$R0,$M3
- vpmuludq $T3,$R1,$M4
- vpmuludq $T3,$S3,$M1
- vpmuludq $T3,$S4,$M2
- vpaddq $M0,$D0,$D0 # d0 += r3'*5*r2
- vpaddq $M3,$D3,$D3 # d3 += r3'*r0
- vpaddq $M4,$D4,$D4 # d4 += r3'*r1
- vpaddq $M1,$D1,$D1 # d1 += r3'*5*r3
- vpaddq $M2,$D2,$D2 # d2 += r3'*5*r4
-
- vpmuludq $T4,$S4,$M3
- vpmuludq $T4,$R0,$M4
- vpmuludq $T4,$S1,$M0
- vpmuludq $T4,$S2,$M1
- vpmuludq $T4,$S3,$M2
- vpaddq $M3,$D3,$D3 # d3 += r2'*5*r4
- vpaddq $M4,$D4,$D4 # d4 += r2'*r0
- vpaddq $M0,$D0,$D0 # d0 += r2'*5*r1
- vpaddq $M1,$D1,$D1 # d1 += r2'*5*r2
- vpaddq $M2,$D2,$D2 # d2 += r2'*5*r3
-
- ################################################################
- # load input
- vmovdqu64 16*0($inp),%z#$T3
- vmovdqu64 16*4($inp),%z#$T4
- lea 16*8($inp),$inp
-
- ################################################################
- # lazy reduction
-
- vpsrlq \$26,$D3,$M3
- vpandq $MASK,$D3,$D3
- vpaddq $M3,$D4,$D4 # d3 -> d4
-
- vpsrlq \$26,$D0,$M0
- vpandq $MASK,$D0,$D0
- vpaddq $M0,$D1,$D1 # d0 -> d1
-
- vpsrlq \$26,$D4,$M4
- vpandq $MASK,$D4,$D4
-
- vpsrlq \$26,$D1,$M1
- vpandq $MASK,$D1,$D1
- vpaddq $M1,$D2,$D2 # d1 -> d2
-
- vpaddq $M4,$D0,$D0
- vpsllq \$2,$M4,$M4
- vpaddq $M4,$D0,$D0 # d4 -> d0
-
- vpsrlq \$26,$D2,$M2
- vpandq $MASK,$D2,$D2
- vpaddq $M2,$D3,$D3 # d2 -> d3
-
- vpsrlq \$26,$D0,$M0
- vpandq $MASK,$D0,$D0
- vpaddq $M0,$D1,$D1 # d0 -> d1
-
- vpsrlq \$26,$D3,$M3
- vpandq $MASK,$D3,$D3
- vpaddq $M3,$D4,$D4 # d3 -> d4
-
- ################################################################
- # at this point we have 14243444 in $R0-$S4 and 05060708 in
- # $D0-$D4, ...
-
- vpunpcklqdq $T4,$T3,$T0 # transpose input
- vpunpckhqdq $T4,$T3,$T4
-
- # ... since input 64-bit lanes are ordered as 73625140, we could
- # "vperm" it to 76543210 (here and in each loop iteration), *or*
- # we could just flow along, hence the goal for $R0-$S4 is
- # 1858286838784888 ...
-
- vmovdqa32 128(%rcx),$M0 # .Lpermd_avx512:
- mov \$0x7777,%eax
- kmovw %eax,%k1
-
- vpermd $R0,$M0,$R0 # 14243444 -> 1---2---3---4---
- vpermd $R1,$M0,$R1
- vpermd $R2,$M0,$R2
- vpermd $R3,$M0,$R3
- vpermd $R4,$M0,$R4
-
- vpermd $D0,$M0,${R0}{%k1} # 05060708 -> 1858286838784888
- vpermd $D1,$M0,${R1}{%k1}
- vpermd $D2,$M0,${R2}{%k1}
- vpermd $D3,$M0,${R3}{%k1}
- vpermd $D4,$M0,${R4}{%k1}
-
- vpslld \$2,$R1,$S1 # *5
- vpslld \$2,$R2,$S2
- vpslld \$2,$R3,$S3
- vpslld \$2,$R4,$S4
- vpaddd $R1,$S1,$S1
- vpaddd $R2,$S2,$S2
- vpaddd $R3,$S3,$S3
- vpaddd $R4,$S4,$S4
-
- vpbroadcastq 32(%rcx),$PADBIT # .L129
-
- vpsrlq \$52,$T0,$T2 # splat input
- vpsllq \$12,$T4,$T3
- vporq $T3,$T2,$T2
- vpsrlq \$26,$T0,$T1
- vpsrlq \$14,$T4,$T3
- vpsrlq \$40,$T4,$T4 # 4
- vpandq $MASK,$T2,$T2 # 2
- vpandq $MASK,$T0,$T0 # 0
- #vpandq $MASK,$T1,$T1 # 1
- #vpandq $MASK,$T3,$T3 # 3
- #vporq $PADBIT,$T4,$T4 # padbit, yes, always
-
- vpaddq $H2,$T2,$H2 # accumulate input
- sub \$192,$len
- jbe .Ltail_avx512
- jmp .Loop_avx512
-
-.align 32
-.Loop_avx512:
- ################################################################
- # ((inp[0]*r^8+inp[ 8])*r^8+inp[16])*r^8
- # ((inp[1]*r^8+inp[ 9])*r^8+inp[17])*r^7
- # ((inp[2]*r^8+inp[10])*r^8+inp[18])*r^6
- # ((inp[3]*r^8+inp[11])*r^8+inp[19])*r^5
- # ((inp[4]*r^8+inp[12])*r^8+inp[20])*r^4
- # ((inp[5]*r^8+inp[13])*r^8+inp[21])*r^3
- # ((inp[6]*r^8+inp[14])*r^8+inp[22])*r^2
- # ((inp[7]*r^8+inp[15])*r^8+inp[23])*r^1
- # \________/\___________/
- ################################################################
- #vpaddq $H2,$T2,$H2 # accumulate input
-
- # d4 = h4*r0 + h3*r1 + h2*r2 + h1*r3 + h0*r4
- # d3 = h3*r0 + h2*r1 + h1*r2 + h0*r3 + h4*5*r4
- # d2 = h2*r0 + h1*r1 + h0*r2 + h4*5*r3 + h3*5*r4
- # d1 = h1*r0 + h0*r1 + h4*5*r2 + h3*5*r3 + h2*5*r4
- # d0 = h0*r0 + h4*5*r1 + h3*5*r2 + h2*5*r3 + h1*5*r4
- #
- # however, as h2 is "chronologically" first one available pull
- # corresponding operations up, so it's
- #
- # d3 = h2*r1 + h0*r3 + h1*r2 + h3*r0 + h4*5*r4
- # d4 = h2*r2 + h0*r4 + h1*r3 + h3*r1 + h4*r0
- # d0 = h2*5*r3 + h0*r0 + h1*5*r4 + h3*5*r2 + h4*5*r1
- # d1 = h2*5*r4 + h0*r1 + h1*r0 + h3*5*r3 + h4*5*r2
- # d2 = h2*r0 + h0*r2 + h1*r1 + h3*5*r4 + h4*5*r3
-
- vpmuludq $H2,$R1,$D3 # d3 = h2*r1
- vpaddq $H0,$T0,$H0
- vpmuludq $H2,$R2,$D4 # d4 = h2*r2
- vpandq $MASK,$T1,$T1 # 1
- vpmuludq $H2,$S3,$D0 # d0 = h2*s3
- vpandq $MASK,$T3,$T3 # 3
- vpmuludq $H2,$S4,$D1 # d1 = h2*s4
- vporq $PADBIT,$T4,$T4 # padbit, yes, always
- vpmuludq $H2,$R0,$D2 # d2 = h2*r0
- vpaddq $H1,$T1,$H1 # accumulate input
- vpaddq $H3,$T3,$H3
- vpaddq $H4,$T4,$H4
-
- vmovdqu64 16*0($inp),$T3 # load input
- vmovdqu64 16*4($inp),$T4
- lea 16*8($inp),$inp
- vpmuludq $H0,$R3,$M3
- vpmuludq $H0,$R4,$M4
- vpmuludq $H0,$R0,$M0
- vpmuludq $H0,$R1,$M1
- vpaddq $M3,$D3,$D3 # d3 += h0*r3
- vpaddq $M4,$D4,$D4 # d4 += h0*r4
- vpaddq $M0,$D0,$D0 # d0 += h0*r0
- vpaddq $M1,$D1,$D1 # d1 += h0*r1
-
- vpmuludq $H1,$R2,$M3
- vpmuludq $H1,$R3,$M4
- vpmuludq $H1,$S4,$M0
- vpmuludq $H0,$R2,$M2
- vpaddq $M3,$D3,$D3 # d3 += h1*r2
- vpaddq $M4,$D4,$D4 # d4 += h1*r3
- vpaddq $M0,$D0,$D0 # d0 += h1*s4
- vpaddq $M2,$D2,$D2 # d2 += h0*r2
-
- vpunpcklqdq $T4,$T3,$T0 # transpose input
- vpunpckhqdq $T4,$T3,$T4
-
- vpmuludq $H3,$R0,$M3
- vpmuludq $H3,$R1,$M4
- vpmuludq $H1,$R0,$M1
- vpmuludq $H1,$R1,$M2
- vpaddq $M3,$D3,$D3 # d3 += h3*r0
- vpaddq $M4,$D4,$D4 # d4 += h3*r1
- vpaddq $M1,$D1,$D1 # d1 += h1*r0
- vpaddq $M2,$D2,$D2 # d2 += h1*r1
-
- vpmuludq $H4,$S4,$M3
- vpmuludq $H4,$R0,$M4
- vpmuludq $H3,$S2,$M0
- vpmuludq $H3,$S3,$M1
- vpaddq $M3,$D3,$D3 # d3 += h4*s4
- vpmuludq $H3,$S4,$M2
- vpaddq $M4,$D4,$D4 # d4 += h4*r0
- vpaddq $M0,$D0,$D0 # d0 += h3*s2
- vpaddq $M1,$D1,$D1 # d1 += h3*s3
- vpaddq $M2,$D2,$D2 # d2 += h3*s4
-
- vpmuludq $H4,$S1,$M0
- vpmuludq $H4,$S2,$M1
- vpmuludq $H4,$S3,$M2
- vpaddq $M0,$D0,$H0 # h0 = d0 + h4*s1
- vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2
- vpaddq $M2,$D2,$H2 # h2 = d3 + h4*s3
-
- ################################################################
- # lazy reduction (interleaved with input splat)
-
- vpsrlq \$52,$T0,$T2 # splat input
- vpsllq \$12,$T4,$T3
-
- vpsrlq \$26,$D3,$H3
- vpandq $MASK,$D3,$D3
- vpaddq $H3,$D4,$H4 # h3 -> h4
-
- vporq $T3,$T2,$T2
-
- vpsrlq \$26,$H0,$D0
- vpandq $MASK,$H0,$H0
- vpaddq $D0,$H1,$H1 # h0 -> h1
-
- vpandq $MASK,$T2,$T2 # 2
-
- vpsrlq \$26,$H4,$D4
- vpandq $MASK,$H4,$H4
-
- vpsrlq \$26,$H1,$D1
- vpandq $MASK,$H1,$H1
- vpaddq $D1,$H2,$H2 # h1 -> h2
-
- vpaddq $D4,$H0,$H0
- vpsllq \$2,$D4,$D4
- vpaddq $D4,$H0,$H0 # h4 -> h0
-
- vpaddq $T2,$H2,$H2 # modulo-scheduled
- vpsrlq \$26,$T0,$T1
-
- vpsrlq \$26,$H2,$D2
- vpandq $MASK,$H2,$H2
- vpaddq $D2,$D3,$H3 # h2 -> h3
-
- vpsrlq \$14,$T4,$T3
-
- vpsrlq \$26,$H0,$D0
- vpandq $MASK,$H0,$H0
- vpaddq $D0,$H1,$H1 # h0 -> h1
-
- vpsrlq \$40,$T4,$T4 # 4
-
- vpsrlq \$26,$H3,$D3
- vpandq $MASK,$H3,$H3
- vpaddq $D3,$H4,$H4 # h3 -> h4
-
- vpandq $MASK,$T0,$T0 # 0
- #vpandq $MASK,$T1,$T1 # 1
- #vpandq $MASK,$T3,$T3 # 3
- #vporq $PADBIT,$T4,$T4 # padbit, yes, always
-
- sub \$128,$len
- ja .Loop_avx512
-
-.Ltail_avx512:
- ################################################################
- # while above multiplications were by r^8 in all lanes, in last
- # iteration we multiply least significant lane by r^8 and most
- # significant one by r, that's why table gets shifted...
-
- vpsrlq \$32,$R0,$R0 # 0105020603070408
- vpsrlq \$32,$R1,$R1
- vpsrlq \$32,$R2,$R2
- vpsrlq \$32,$S3,$S3
- vpsrlq \$32,$S4,$S4
- vpsrlq \$32,$R3,$R3
- vpsrlq \$32,$R4,$R4
- vpsrlq \$32,$S1,$S1
- vpsrlq \$32,$S2,$S2
-
- ################################################################
- # load either next or last 64 byte of input
- lea ($inp,$len),$inp
-
- #vpaddq $H2,$T2,$H2 # accumulate input
- vpaddq $H0,$T0,$H0
-
- vpmuludq $H2,$R1,$D3 # d3 = h2*r1
- vpmuludq $H2,$R2,$D4 # d4 = h2*r2
- vpmuludq $H2,$S3,$D0 # d0 = h2*s3
- vpandq $MASK,$T1,$T1 # 1
- vpmuludq $H2,$S4,$D1 # d1 = h2*s4
- vpandq $MASK,$T3,$T3 # 3
- vpmuludq $H2,$R0,$D2 # d2 = h2*r0
- vporq $PADBIT,$T4,$T4 # padbit, yes, always
- vpaddq $H1,$T1,$H1 # accumulate input
- vpaddq $H3,$T3,$H3
- vpaddq $H4,$T4,$H4
-
- vmovdqu 16*0($inp),%x#$T0
- vpmuludq $H0,$R3,$M3
- vpmuludq $H0,$R4,$M4
- vpmuludq $H0,$R0,$M0
- vpmuludq $H0,$R1,$M1
- vpaddq $M3,$D3,$D3 # d3 += h0*r3
- vpaddq $M4,$D4,$D4 # d4 += h0*r4
- vpaddq $M0,$D0,$D0 # d0 += h0*r0
- vpaddq $M1,$D1,$D1 # d1 += h0*r1
-
- vmovdqu 16*1($inp),%x#$T1
- vpmuludq $H1,$R2,$M3
- vpmuludq $H1,$R3,$M4
- vpmuludq $H1,$S4,$M0
- vpmuludq $H0,$R2,$M2
- vpaddq $M3,$D3,$D3 # d3 += h1*r2
- vpaddq $M4,$D4,$D4 # d4 += h1*r3
- vpaddq $M0,$D0,$D0 # d0 += h1*s4
- vpaddq $M2,$D2,$D2 # d2 += h0*r2
-
- vinserti128 \$1,16*2($inp),%y#$T0,%y#$T0
- vpmuludq $H3,$R0,$M3
- vpmuludq $H3,$R1,$M4
- vpmuludq $H1,$R0,$M1
- vpmuludq $H1,$R1,$M2
- vpaddq $M3,$D3,$D3 # d3 += h3*r0
- vpaddq $M4,$D4,$D4 # d4 += h3*r1
- vpaddq $M1,$D1,$D1 # d1 += h1*r0
- vpaddq $M2,$D2,$D2 # d2 += h1*r1
-
- vinserti128 \$1,16*3($inp),%y#$T1,%y#$T1
- vpmuludq $H4,$S4,$M3
- vpmuludq $H4,$R0,$M4
- vpmuludq $H3,$S2,$M0
- vpmuludq $H3,$S3,$M1
- vpmuludq $H3,$S4,$M2
- vpaddq $M3,$D3,$H3 # h3 = d3 + h4*s4
- vpaddq $M4,$D4,$D4 # d4 += h4*r0
- vpaddq $M0,$D0,$D0 # d0 += h3*s2
- vpaddq $M1,$D1,$D1 # d1 += h3*s3
- vpaddq $M2,$D2,$D2 # d2 += h3*s4
-
- vpmuludq $H4,$S1,$M0
- vpmuludq $H4,$S2,$M1
- vpmuludq $H4,$S3,$M2
- vpaddq $M0,$D0,$H0 # h0 = d0 + h4*s1
- vpaddq $M1,$D1,$H1 # h1 = d2 + h4*s2
- vpaddq $M2,$D2,$H2 # h2 = d3 + h4*s3
-
- ################################################################
- # horizontal addition
-
- mov \$1,%eax
- vpermq \$0xb1,$H3,$D3
- vpermq \$0xb1,$D4,$H4
- vpermq \$0xb1,$H0,$D0
- vpermq \$0xb1,$H1,$D1
- vpermq \$0xb1,$H2,$D2
- vpaddq $D3,$H3,$H3
- vpaddq $D4,$H4,$H4
- vpaddq $D0,$H0,$H0
- vpaddq $D1,$H1,$H1
- vpaddq $D2,$H2,$H2
-
- kmovw %eax,%k3
- vpermq \$0x2,$H3,$D3
- vpermq \$0x2,$H4,$D4
- vpermq \$0x2,$H0,$D0
- vpermq \$0x2,$H1,$D1
- vpermq \$0x2,$H2,$D2
- vpaddq $D3,$H3,$H3
- vpaddq $D4,$H4,$H4
- vpaddq $D0,$H0,$H0
- vpaddq $D1,$H1,$H1
- vpaddq $D2,$H2,$H2
-
- vextracti64x4 \$0x1,$H3,%y#$D3
- vextracti64x4 \$0x1,$H4,%y#$D4
- vextracti64x4 \$0x1,$H0,%y#$D0
- vextracti64x4 \$0x1,$H1,%y#$D1
- vextracti64x4 \$0x1,$H2,%y#$D2
- vpaddq $D3,$H3,${H3}{%k3}{z} # keep single qword in case
- vpaddq $D4,$H4,${H4}{%k3}{z} # it's passed to .Ltail_avx2
- vpaddq $D0,$H0,${H0}{%k3}{z}
- vpaddq $D1,$H1,${H1}{%k3}{z}
- vpaddq $D2,$H2,${H2}{%k3}{z}
-___
-map(s/%z/%y/,($T0,$T1,$T2,$T3,$T4, $PADBIT));
-map(s/%z/%y/,($H0,$H1,$H2,$H3,$H4, $D0,$D1,$D2,$D3,$D4, $MASK));
-$code.=<<___;
- ################################################################
- # lazy reduction (interleaved with input splat)
-
- vpsrlq \$26,$H3,$D3
- vpand $MASK,$H3,$H3
- vpsrldq \$6,$T0,$T2 # splat input
- vpsrldq \$6,$T1,$T3
- vpunpckhqdq $T1,$T0,$T4 # 4
- vpaddq $D3,$H4,$H4 # h3 -> h4
-
- vpsrlq \$26,$H0,$D0
- vpand $MASK,$H0,$H0
- vpunpcklqdq $T3,$T2,$T2 # 2:3
- vpunpcklqdq $T1,$T0,$T0 # 0:1
- vpaddq $D0,$H1,$H1 # h0 -> h1
-
- vpsrlq \$26,$H4,$D4
- vpand $MASK,$H4,$H4
-
- vpsrlq \$26,$H1,$D1
- vpand $MASK,$H1,$H1
- vpsrlq \$30,$T2,$T3
- vpsrlq \$4,$T2,$T2
- vpaddq $D1,$H2,$H2 # h1 -> h2
-
- vpaddq $D4,$H0,$H0
- vpsllq \$2,$D4,$D4
- vpsrlq \$26,$T0,$T1
- vpsrlq \$40,$T4,$T4 # 4
- vpaddq $D4,$H0,$H0 # h4 -> h0
-
- vpsrlq \$26,$H2,$D2
- vpand $MASK,$H2,$H2
- vpand $MASK,$T2,$T2 # 2
- vpand $MASK,$T0,$T0 # 0
- vpaddq $D2,$H3,$H3 # h2 -> h3
-
- vpsrlq \$26,$H0,$D0
- vpand $MASK,$H0,$H0
- vpaddq $H2,$T2,$H2 # accumulate input for .Ltail_avx2
- vpand $MASK,$T1,$T1 # 1
- vpaddq $D0,$H1,$H1 # h0 -> h1
-
- vpsrlq \$26,$H3,$D3
- vpand $MASK,$H3,$H3
- vpand $MASK,$T3,$T3 # 3
- vpor 32(%rcx),$T4,$T4 # padbit, yes, always
- vpaddq $D3,$H4,$H4 # h3 -> h4
-
- lea 0x90(%rsp),%rax # size optimization for .Ltail_avx2
- add \$64,$len
- jnz .Ltail_avx2$suffix
-
- vpsubq $T2,$H2,$H2 # undo input accumulation
- vmovd %x#$H0,`4*0-48-64`($ctx)# save partially reduced
- vmovd %x#$H1,`4*1-48-64`($ctx)
- vmovd %x#$H2,`4*2-48-64`($ctx)
- vmovd %x#$H3,`4*3-48-64`($ctx)
- vmovd %x#$H4,`4*4-48-64`($ctx)
- vzeroall
-___
-$code.=<<___ if ($win64);
- movdqa -0xb0(%r10),%xmm6
- movdqa -0xa0(%r10),%xmm7
- movdqa -0x90(%r10),%xmm8
- movdqa -0x80(%r10),%xmm9
- movdqa -0x70(%r10),%xmm10
- movdqa -0x60(%r10),%xmm11
- movdqa -0x50(%r10),%xmm12
- movdqa -0x40(%r10),%xmm13
- movdqa -0x30(%r10),%xmm14
- movdqa -0x20(%r10),%xmm15
- lea -8(%r10),%rsp
-.Ldo_avx512_epilogue:
-___
-$code.=<<___ if (!$win64);
- lea -8(%r10),%rsp
-.cfi_def_cfa_register %rsp
-___
-$code.=<<___;
- RET
-.cfi_endproc
-___
-
-}
-
-}
-
-&declare_function("poly1305_blocks_avx2", 32, 4);
-poly1305_blocks_avxN(0);
-&end_function("poly1305_blocks_avx2");
-
-#######################################################################
-if ($avx>2) {
-# On entry we have input length divisible by 64. But since inner loop
-# processes 128 bytes per iteration, cases when length is not divisible
-# by 128 are handled by passing tail 64 bytes to .Ltail_avx2. For this
-# reason stack layout is kept identical to poly1305_blocks_avx2. If not
-# for this tail, we wouldn't have to even allocate stack frame...
-
-if($kernel) {
- $code .= "#ifdef CONFIG_AS_AVX512\n";
-}
-
-&declare_function("poly1305_blocks_avx512", 32, 4);
-poly1305_blocks_avxN(1);
-&end_function("poly1305_blocks_avx512");
-
-if ($kernel) {
- $code .= "#endif\n";
-}
-
-if (!$kernel && $avx>3) {
-########################################################################
-# VPMADD52 version using 2^44 radix.
-#
-# One can argue that base 2^52 would be more natural. Well, even though
-# some operations would be more natural, one has to recognize couple of
-# things. Base 2^52 doesn't provide advantage over base 2^44 if you look
-# at amount of multiply-n-accumulate operations. Secondly, it makes it
-# impossible to pre-compute multiples of 5 [referred to as s[]/sN in
-# reference implementations], which means that more such operations
-# would have to be performed in inner loop, which in turn makes critical
-# path longer. In other words, even though base 2^44 reduction might
-# look less elegant, overall critical path is actually shorter...
-
-########################################################################
-# Layout of opaque area is following.
-#
-# unsigned __int64 h[3]; # current hash value base 2^44
-# unsigned __int64 s[2]; # key value*20 base 2^44
-# unsigned __int64 r[3]; # key value base 2^44
-# struct { unsigned __int64 r^1, r^3, r^2, r^4; } R[4];
-# # r^n positions reflect
-# # placement in register, not
-# # memory, R[3] is R[1]*20
-
-$code.=<<___;
-.type poly1305_init_base2_44,\@function,3
-.align 32
-poly1305_init_base2_44:
- xor %eax,%eax
- mov %rax,0($ctx) # initialize hash value
- mov %rax,8($ctx)
- mov %rax,16($ctx)
-
-.Linit_base2_44:
- lea poly1305_blocks_vpmadd52(%rip),%r10
- lea poly1305_emit_base2_44(%rip),%r11
-
- mov \$0x0ffffffc0fffffff,%rax
- mov \$0x0ffffffc0ffffffc,%rcx
- and 0($inp),%rax
- mov \$0x00000fffffffffff,%r8
- and 8($inp),%rcx
- mov \$0x00000fffffffffff,%r9
- and %rax,%r8
- shrd \$44,%rcx,%rax
- mov %r8,40($ctx) # r0
- and %r9,%rax
- shr \$24,%rcx
- mov %rax,48($ctx) # r1
- lea (%rax,%rax,4),%rax # *5
- mov %rcx,56($ctx) # r2
- shl \$2,%rax # magic <<2
- lea (%rcx,%rcx,4),%rcx # *5
- shl \$2,%rcx # magic <<2
- mov %rax,24($ctx) # s1
- mov %rcx,32($ctx) # s2
- movq \$-1,64($ctx) # write impossible value
-___
-$code.=<<___ if ($flavour !~ /elf32/);
- mov %r10,0(%rdx)
- mov %r11,8(%rdx)
-___
-$code.=<<___ if ($flavour =~ /elf32/);
- mov %r10d,0(%rdx)
- mov %r11d,4(%rdx)
-___
-$code.=<<___;
- mov \$1,%eax
- RET
-.size poly1305_init_base2_44,.-poly1305_init_base2_44
-___
-{
-my ($H0,$H1,$H2,$r2r1r0,$r1r0s2,$r0s2s1,$Dlo,$Dhi) = map("%ymm$_",(0..5,16,17));
-my ($T0,$inp_permd,$inp_shift,$PAD) = map("%ymm$_",(18..21));
-my ($reduc_mask,$reduc_rght,$reduc_left) = map("%ymm$_",(22..25));
-
-$code.=<<___;
-.type poly1305_blocks_vpmadd52,\@function,4
-.align 32
-poly1305_blocks_vpmadd52:
- shr \$4,$len
- jz .Lno_data_vpmadd52 # too short
-
- shl \$40,$padbit
- mov 64($ctx),%r8 # peek on power of the key
-
- # if powers of the key are not calculated yet, process up to 3
- # blocks with this single-block subroutine, otherwise ensure that
- # length is divisible by 2 blocks and pass the rest down to next
- # subroutine...
-
- mov \$3,%rax
- mov \$1,%r10
- cmp \$4,$len # is input long
- cmovae %r10,%rax
- test %r8,%r8 # is power value impossible?
- cmovns %r10,%rax
-
- and $len,%rax # is input of favourable length?
- jz .Lblocks_vpmadd52_4x
-
- sub %rax,$len
- mov \$7,%r10d
- mov \$1,%r11d
- kmovw %r10d,%k7
- lea .L2_44_inp_permd(%rip),%r10
- kmovw %r11d,%k1
-
- vmovq $padbit,%x#$PAD
- vmovdqa64 0(%r10),$inp_permd # .L2_44_inp_permd
- vmovdqa64 32(%r10),$inp_shift # .L2_44_inp_shift
- vpermq \$0xcf,$PAD,$PAD
- vmovdqa64 64(%r10),$reduc_mask # .L2_44_mask
-
- vmovdqu64 0($ctx),${Dlo}{%k7}{z} # load hash value
- vmovdqu64 40($ctx),${r2r1r0}{%k7}{z} # load keys
- vmovdqu64 32($ctx),${r1r0s2}{%k7}{z}
- vmovdqu64 24($ctx),${r0s2s1}{%k7}{z}
-
- vmovdqa64 96(%r10),$reduc_rght # .L2_44_shift_rgt
- vmovdqa64 128(%r10),$reduc_left # .L2_44_shift_lft
-
- jmp .Loop_vpmadd52
-
-.align 32
-.Loop_vpmadd52:
- vmovdqu32 0($inp),%x#$T0 # load input as ----3210
- lea 16($inp),$inp
-
- vpermd $T0,$inp_permd,$T0 # ----3210 -> --322110
- vpsrlvq $inp_shift,$T0,$T0
- vpandq $reduc_mask,$T0,$T0
- vporq $PAD,$T0,$T0
-
- vpaddq $T0,$Dlo,$Dlo # accumulate input
-
- vpermq \$0,$Dlo,${H0}{%k7}{z} # smash hash value
- vpermq \$0b01010101,$Dlo,${H1}{%k7}{z}
- vpermq \$0b10101010,$Dlo,${H2}{%k7}{z}
-
- vpxord $Dlo,$Dlo,$Dlo
- vpxord $Dhi,$Dhi,$Dhi
-
- vpmadd52luq $r2r1r0,$H0,$Dlo
- vpmadd52huq $r2r1r0,$H0,$Dhi
-
- vpmadd52luq $r1r0s2,$H1,$Dlo
- vpmadd52huq $r1r0s2,$H1,$Dhi
-
- vpmadd52luq $r0s2s1,$H2,$Dlo
- vpmadd52huq $r0s2s1,$H2,$Dhi
-
- vpsrlvq $reduc_rght,$Dlo,$T0 # 0 in topmost qword
- vpsllvq $reduc_left,$Dhi,$Dhi # 0 in topmost qword
- vpandq $reduc_mask,$Dlo,$Dlo
-
- vpaddq $T0,$Dhi,$Dhi
-
- vpermq \$0b10010011,$Dhi,$Dhi # 0 in lowest qword
-
- vpaddq $Dhi,$Dlo,$Dlo # note topmost qword :-)
-
- vpsrlvq $reduc_rght,$Dlo,$T0 # 0 in topmost word
- vpandq $reduc_mask,$Dlo,$Dlo
-
- vpermq \$0b10010011,$T0,$T0
-
- vpaddq $T0,$Dlo,$Dlo
-
- vpermq \$0b10010011,$Dlo,${T0}{%k1}{z}
-
- vpaddq $T0,$Dlo,$Dlo
- vpsllq \$2,$T0,$T0
-
- vpaddq $T0,$Dlo,$Dlo
-
- dec %rax # len-=16
- jnz .Loop_vpmadd52
-
- vmovdqu64 $Dlo,0($ctx){%k7} # store hash value
-
- test $len,$len
- jnz .Lblocks_vpmadd52_4x
-
-.Lno_data_vpmadd52:
- RET
-.size poly1305_blocks_vpmadd52,.-poly1305_blocks_vpmadd52
-___
-}
-{
-########################################################################
-# As implied by its name 4x subroutine processes 4 blocks in parallel
-# (but handles even 4*n+2 blocks lengths). It takes up to 4th key power
-# and is handled in 256-bit %ymm registers.
-
-my ($H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2) = map("%ymm$_",(0..5,16,17));
-my ($D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi) = map("%ymm$_",(18..23));
-my ($T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD) = map("%ymm$_",(24..31));
-
-$code.=<<___;
-.type poly1305_blocks_vpmadd52_4x,\@function,4
-.align 32
-poly1305_blocks_vpmadd52_4x:
- shr \$4,$len
- jz .Lno_data_vpmadd52_4x # too short
-
- shl \$40,$padbit
- mov 64($ctx),%r8 # peek on power of the key
-
-.Lblocks_vpmadd52_4x:
- vpbroadcastq $padbit,$PAD
-
- vmovdqa64 .Lx_mask44(%rip),$mask44
- mov \$5,%eax
- vmovdqa64 .Lx_mask42(%rip),$mask42
- kmovw %eax,%k1 # used in 2x path
-
- test %r8,%r8 # is power value impossible?
- js .Linit_vpmadd52 # if it is, then init R[4]
-
- vmovq 0($ctx),%x#$H0 # load current hash value
- vmovq 8($ctx),%x#$H1
- vmovq 16($ctx),%x#$H2
-
- test \$3,$len # is length 4*n+2?
- jnz .Lblocks_vpmadd52_2x_do
-
-.Lblocks_vpmadd52_4x_do:
- vpbroadcastq 64($ctx),$R0 # load 4th power of the key
- vpbroadcastq 96($ctx),$R1
- vpbroadcastq 128($ctx),$R2
- vpbroadcastq 160($ctx),$S1
-
-.Lblocks_vpmadd52_4x_key_loaded:
- vpsllq \$2,$R2,$S2 # S2 = R2*5*4
- vpaddq $R2,$S2,$S2
- vpsllq \$2,$S2,$S2
-
- test \$7,$len # is len 8*n?
- jz .Lblocks_vpmadd52_8x
-
- vmovdqu64 16*0($inp),$T2 # load data
- vmovdqu64 16*2($inp),$T3
- lea 16*4($inp),$inp
-
- vpunpcklqdq $T3,$T2,$T1 # transpose data
- vpunpckhqdq $T3,$T2,$T3
-
- # at this point 64-bit lanes are ordered as 3-1-2-0
-
- vpsrlq \$24,$T3,$T2 # splat the data
- vporq $PAD,$T2,$T2
- vpaddq $T2,$H2,$H2 # accumulate input
- vpandq $mask44,$T1,$T0
- vpsrlq \$44,$T1,$T1
- vpsllq \$20,$T3,$T3
- vporq $T3,$T1,$T1
- vpandq $mask44,$T1,$T1
-
- sub \$4,$len
- jz .Ltail_vpmadd52_4x
- jmp .Loop_vpmadd52_4x
- ud2
-
-.align 32
-.Linit_vpmadd52:
- vmovq 24($ctx),%x#$S1 # load key
- vmovq 56($ctx),%x#$H2
- vmovq 32($ctx),%x#$S2
- vmovq 40($ctx),%x#$R0
- vmovq 48($ctx),%x#$R1
-
- vmovdqa $R0,$H0
- vmovdqa $R1,$H1
- vmovdqa $H2,$R2
-
- mov \$2,%eax
-
-.Lmul_init_vpmadd52:
- vpxorq $D0lo,$D0lo,$D0lo
- vpmadd52luq $H2,$S1,$D0lo
- vpxorq $D0hi,$D0hi,$D0hi
- vpmadd52huq $H2,$S1,$D0hi
- vpxorq $D1lo,$D1lo,$D1lo
- vpmadd52luq $H2,$S2,$D1lo
- vpxorq $D1hi,$D1hi,$D1hi
- vpmadd52huq $H2,$S2,$D1hi
- vpxorq $D2lo,$D2lo,$D2lo
- vpmadd52luq $H2,$R0,$D2lo
- vpxorq $D2hi,$D2hi,$D2hi
- vpmadd52huq $H2,$R0,$D2hi
-
- vpmadd52luq $H0,$R0,$D0lo
- vpmadd52huq $H0,$R0,$D0hi
- vpmadd52luq $H0,$R1,$D1lo
- vpmadd52huq $H0,$R1,$D1hi
- vpmadd52luq $H0,$R2,$D2lo
- vpmadd52huq $H0,$R2,$D2hi
-
- vpmadd52luq $H1,$S2,$D0lo
- vpmadd52huq $H1,$S2,$D0hi
- vpmadd52luq $H1,$R0,$D1lo
- vpmadd52huq $H1,$R0,$D1hi
- vpmadd52luq $H1,$R1,$D2lo
- vpmadd52huq $H1,$R1,$D2hi
-
- ################################################################
- # partial reduction
- vpsrlq \$44,$D0lo,$tmp
- vpsllq \$8,$D0hi,$D0hi
- vpandq $mask44,$D0lo,$H0
- vpaddq $tmp,$D0hi,$D0hi
-
- vpaddq $D0hi,$D1lo,$D1lo
-
- vpsrlq \$44,$D1lo,$tmp
- vpsllq \$8,$D1hi,$D1hi
- vpandq $mask44,$D1lo,$H1
- vpaddq $tmp,$D1hi,$D1hi
-
- vpaddq $D1hi,$D2lo,$D2lo
-
- vpsrlq \$42,$D2lo,$tmp
- vpsllq \$10,$D2hi,$D2hi
- vpandq $mask42,$D2lo,$H2
- vpaddq $tmp,$D2hi,$D2hi
-
- vpaddq $D2hi,$H0,$H0
- vpsllq \$2,$D2hi,$D2hi
-
- vpaddq $D2hi,$H0,$H0
-
- vpsrlq \$44,$H0,$tmp # additional step
- vpandq $mask44,$H0,$H0
-
- vpaddq $tmp,$H1,$H1
-
- dec %eax
- jz .Ldone_init_vpmadd52
-
- vpunpcklqdq $R1,$H1,$R1 # 1,2
- vpbroadcastq %x#$H1,%x#$H1 # 2,2
- vpunpcklqdq $R2,$H2,$R2
- vpbroadcastq %x#$H2,%x#$H2
- vpunpcklqdq $R0,$H0,$R0
- vpbroadcastq %x#$H0,%x#$H0
-
- vpsllq \$2,$R1,$S1 # S1 = R1*5*4
- vpsllq \$2,$R2,$S2 # S2 = R2*5*4
- vpaddq $R1,$S1,$S1
- vpaddq $R2,$S2,$S2
- vpsllq \$2,$S1,$S1
- vpsllq \$2,$S2,$S2
-
- jmp .Lmul_init_vpmadd52
- ud2
-
-.align 32
-.Ldone_init_vpmadd52:
- vinserti128 \$1,%x#$R1,$H1,$R1 # 1,2,3,4
- vinserti128 \$1,%x#$R2,$H2,$R2
- vinserti128 \$1,%x#$R0,$H0,$R0
-
- vpermq \$0b11011000,$R1,$R1 # 1,3,2,4
- vpermq \$0b11011000,$R2,$R2
- vpermq \$0b11011000,$R0,$R0
-
- vpsllq \$2,$R1,$S1 # S1 = R1*5*4
- vpaddq $R1,$S1,$S1
- vpsllq \$2,$S1,$S1
-
- vmovq 0($ctx),%x#$H0 # load current hash value
- vmovq 8($ctx),%x#$H1
- vmovq 16($ctx),%x#$H2
-
- test \$3,$len # is length 4*n+2?
- jnz .Ldone_init_vpmadd52_2x
-
- vmovdqu64 $R0,64($ctx) # save key powers
- vpbroadcastq %x#$R0,$R0 # broadcast 4th power
- vmovdqu64 $R1,96($ctx)
- vpbroadcastq %x#$R1,$R1
- vmovdqu64 $R2,128($ctx)
- vpbroadcastq %x#$R2,$R2
- vmovdqu64 $S1,160($ctx)
- vpbroadcastq %x#$S1,$S1
-
- jmp .Lblocks_vpmadd52_4x_key_loaded
- ud2
-
-.align 32
-.Ldone_init_vpmadd52_2x:
- vmovdqu64 $R0,64($ctx) # save key powers
- vpsrldq \$8,$R0,$R0 # 0-1-0-2
- vmovdqu64 $R1,96($ctx)
- vpsrldq \$8,$R1,$R1
- vmovdqu64 $R2,128($ctx)
- vpsrldq \$8,$R2,$R2
- vmovdqu64 $S1,160($ctx)
- vpsrldq \$8,$S1,$S1
- jmp .Lblocks_vpmadd52_2x_key_loaded
- ud2
-
-.align 32
-.Lblocks_vpmadd52_2x_do:
- vmovdqu64 128+8($ctx),${R2}{%k1}{z}# load 2nd and 1st key powers
- vmovdqu64 160+8($ctx),${S1}{%k1}{z}
- vmovdqu64 64+8($ctx),${R0}{%k1}{z}
- vmovdqu64 96+8($ctx),${R1}{%k1}{z}
-
-.Lblocks_vpmadd52_2x_key_loaded:
- vmovdqu64 16*0($inp),$T2 # load data
- vpxorq $T3,$T3,$T3
- lea 16*2($inp),$inp
-
- vpunpcklqdq $T3,$T2,$T1 # transpose data
- vpunpckhqdq $T3,$T2,$T3
-
- # at this point 64-bit lanes are ordered as x-1-x-0
-
- vpsrlq \$24,$T3,$T2 # splat the data
- vporq $PAD,$T2,$T2
- vpaddq $T2,$H2,$H2 # accumulate input
- vpandq $mask44,$T1,$T0
- vpsrlq \$44,$T1,$T1
- vpsllq \$20,$T3,$T3
- vporq $T3,$T1,$T1
- vpandq $mask44,$T1,$T1
-
- jmp .Ltail_vpmadd52_2x
- ud2
-
-.align 32
-.Loop_vpmadd52_4x:
- #vpaddq $T2,$H2,$H2 # accumulate input
- vpaddq $T0,$H0,$H0
- vpaddq $T1,$H1,$H1
-
- vpxorq $D0lo,$D0lo,$D0lo
- vpmadd52luq $H2,$S1,$D0lo
- vpxorq $D0hi,$D0hi,$D0hi
- vpmadd52huq $H2,$S1,$D0hi
- vpxorq $D1lo,$D1lo,$D1lo
- vpmadd52luq $H2,$S2,$D1lo
- vpxorq $D1hi,$D1hi,$D1hi
- vpmadd52huq $H2,$S2,$D1hi
- vpxorq $D2lo,$D2lo,$D2lo
- vpmadd52luq $H2,$R0,$D2lo
- vpxorq $D2hi,$D2hi,$D2hi
- vpmadd52huq $H2,$R0,$D2hi
-
- vmovdqu64 16*0($inp),$T2 # load data
- vmovdqu64 16*2($inp),$T3
- lea 16*4($inp),$inp
- vpmadd52luq $H0,$R0,$D0lo
- vpmadd52huq $H0,$R0,$D0hi
- vpmadd52luq $H0,$R1,$D1lo
- vpmadd52huq $H0,$R1,$D1hi
- vpmadd52luq $H0,$R2,$D2lo
- vpmadd52huq $H0,$R2,$D2hi
-
- vpunpcklqdq $T3,$T2,$T1 # transpose data
- vpunpckhqdq $T3,$T2,$T3
- vpmadd52luq $H1,$S2,$D0lo
- vpmadd52huq $H1,$S2,$D0hi
- vpmadd52luq $H1,$R0,$D1lo
- vpmadd52huq $H1,$R0,$D1hi
- vpmadd52luq $H1,$R1,$D2lo
- vpmadd52huq $H1,$R1,$D2hi
-
- ################################################################
- # partial reduction (interleaved with data splat)
- vpsrlq \$44,$D0lo,$tmp
- vpsllq \$8,$D0hi,$D0hi
- vpandq $mask44,$D0lo,$H0
- vpaddq $tmp,$D0hi,$D0hi
-
- vpsrlq \$24,$T3,$T2
- vporq $PAD,$T2,$T2
- vpaddq $D0hi,$D1lo,$D1lo
-
- vpsrlq \$44,$D1lo,$tmp
- vpsllq \$8,$D1hi,$D1hi
- vpandq $mask44,$D1lo,$H1
- vpaddq $tmp,$D1hi,$D1hi
-
- vpandq $mask44,$T1,$T0
- vpsrlq \$44,$T1,$T1
- vpsllq \$20,$T3,$T3
- vpaddq $D1hi,$D2lo,$D2lo
-
- vpsrlq \$42,$D2lo,$tmp
- vpsllq \$10,$D2hi,$D2hi
- vpandq $mask42,$D2lo,$H2
- vpaddq $tmp,$D2hi,$D2hi
-
- vpaddq $T2,$H2,$H2 # accumulate input
- vpaddq $D2hi,$H0,$H0
- vpsllq \$2,$D2hi,$D2hi
-
- vpaddq $D2hi,$H0,$H0
- vporq $T3,$T1,$T1
- vpandq $mask44,$T1,$T1
-
- vpsrlq \$44,$H0,$tmp # additional step
- vpandq $mask44,$H0,$H0
-
- vpaddq $tmp,$H1,$H1
-
- sub \$4,$len # len-=64
- jnz .Loop_vpmadd52_4x
-
-.Ltail_vpmadd52_4x:
- vmovdqu64 128($ctx),$R2 # load all key powers
- vmovdqu64 160($ctx),$S1
- vmovdqu64 64($ctx),$R0
- vmovdqu64 96($ctx),$R1
-
-.Ltail_vpmadd52_2x:
- vpsllq \$2,$R2,$S2 # S2 = R2*5*4
- vpaddq $R2,$S2,$S2
- vpsllq \$2,$S2,$S2
-
- #vpaddq $T2,$H2,$H2 # accumulate input
- vpaddq $T0,$H0,$H0
- vpaddq $T1,$H1,$H1
-
- vpxorq $D0lo,$D0lo,$D0lo
- vpmadd52luq $H2,$S1,$D0lo
- vpxorq $D0hi,$D0hi,$D0hi
- vpmadd52huq $H2,$S1,$D0hi
- vpxorq $D1lo,$D1lo,$D1lo
- vpmadd52luq $H2,$S2,$D1lo
- vpxorq $D1hi,$D1hi,$D1hi
- vpmadd52huq $H2,$S2,$D1hi
- vpxorq $D2lo,$D2lo,$D2lo
- vpmadd52luq $H2,$R0,$D2lo
- vpxorq $D2hi,$D2hi,$D2hi
- vpmadd52huq $H2,$R0,$D2hi
-
- vpmadd52luq $H0,$R0,$D0lo
- vpmadd52huq $H0,$R0,$D0hi
- vpmadd52luq $H0,$R1,$D1lo
- vpmadd52huq $H0,$R1,$D1hi
- vpmadd52luq $H0,$R2,$D2lo
- vpmadd52huq $H0,$R2,$D2hi
-
- vpmadd52luq $H1,$S2,$D0lo
- vpmadd52huq $H1,$S2,$D0hi
- vpmadd52luq $H1,$R0,$D1lo
- vpmadd52huq $H1,$R0,$D1hi
- vpmadd52luq $H1,$R1,$D2lo
- vpmadd52huq $H1,$R1,$D2hi
-
- ################################################################
- # horizontal addition
-
- mov \$1,%eax
- kmovw %eax,%k1
- vpsrldq \$8,$D0lo,$T0
- vpsrldq \$8,$D0hi,$H0
- vpsrldq \$8,$D1lo,$T1
- vpsrldq \$8,$D1hi,$H1
- vpaddq $T0,$D0lo,$D0lo
- vpaddq $H0,$D0hi,$D0hi
- vpsrldq \$8,$D2lo,$T2
- vpsrldq \$8,$D2hi,$H2
- vpaddq $T1,$D1lo,$D1lo
- vpaddq $H1,$D1hi,$D1hi
- vpermq \$0x2,$D0lo,$T0
- vpermq \$0x2,$D0hi,$H0
- vpaddq $T2,$D2lo,$D2lo
- vpaddq $H2,$D2hi,$D2hi
-
- vpermq \$0x2,$D1lo,$T1
- vpermq \$0x2,$D1hi,$H1
- vpaddq $T0,$D0lo,${D0lo}{%k1}{z}
- vpaddq $H0,$D0hi,${D0hi}{%k1}{z}
- vpermq \$0x2,$D2lo,$T2
- vpermq \$0x2,$D2hi,$H2
- vpaddq $T1,$D1lo,${D1lo}{%k1}{z}
- vpaddq $H1,$D1hi,${D1hi}{%k1}{z}
- vpaddq $T2,$D2lo,${D2lo}{%k1}{z}
- vpaddq $H2,$D2hi,${D2hi}{%k1}{z}
-
- ################################################################
- # partial reduction
- vpsrlq \$44,$D0lo,$tmp
- vpsllq \$8,$D0hi,$D0hi
- vpandq $mask44,$D0lo,$H0
- vpaddq $tmp,$D0hi,$D0hi
-
- vpaddq $D0hi,$D1lo,$D1lo
-
- vpsrlq \$44,$D1lo,$tmp
- vpsllq \$8,$D1hi,$D1hi
- vpandq $mask44,$D1lo,$H1
- vpaddq $tmp,$D1hi,$D1hi
-
- vpaddq $D1hi,$D2lo,$D2lo
-
- vpsrlq \$42,$D2lo,$tmp
- vpsllq \$10,$D2hi,$D2hi
- vpandq $mask42,$D2lo,$H2
- vpaddq $tmp,$D2hi,$D2hi
-
- vpaddq $D2hi,$H0,$H0
- vpsllq \$2,$D2hi,$D2hi
-
- vpaddq $D2hi,$H0,$H0
-
- vpsrlq \$44,$H0,$tmp # additional step
- vpandq $mask44,$H0,$H0
-
- vpaddq $tmp,$H1,$H1
- # at this point $len is
- # either 4*n+2 or 0...
- sub \$2,$len # len-=32
- ja .Lblocks_vpmadd52_4x_do
-
- vmovq %x#$H0,0($ctx)
- vmovq %x#$H1,8($ctx)
- vmovq %x#$H2,16($ctx)
- vzeroall
-
-.Lno_data_vpmadd52_4x:
- RET
-.size poly1305_blocks_vpmadd52_4x,.-poly1305_blocks_vpmadd52_4x
-___
-}
-{
-########################################################################
-# As implied by its name 8x subroutine processes 8 blocks in parallel...
-# This is intermediate version, as it's used only in cases when input
-# length is either 8*n, 8*n+1 or 8*n+2...
-
-my ($H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2) = map("%ymm$_",(0..5,16,17));
-my ($D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi) = map("%ymm$_",(18..23));
-my ($T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD) = map("%ymm$_",(24..31));
-my ($RR0,$RR1,$RR2,$SS1,$SS2) = map("%ymm$_",(6..10));
-
-$code.=<<___;
-.type poly1305_blocks_vpmadd52_8x,\@function,4
-.align 32
-poly1305_blocks_vpmadd52_8x:
- shr \$4,$len
- jz .Lno_data_vpmadd52_8x # too short
-
- shl \$40,$padbit
- mov 64($ctx),%r8 # peek on power of the key
-
- vmovdqa64 .Lx_mask44(%rip),$mask44
- vmovdqa64 .Lx_mask42(%rip),$mask42
-
- test %r8,%r8 # is power value impossible?
- js .Linit_vpmadd52 # if it is, then init R[4]
-
- vmovq 0($ctx),%x#$H0 # load current hash value
- vmovq 8($ctx),%x#$H1
- vmovq 16($ctx),%x#$H2
-
-.Lblocks_vpmadd52_8x:
- ################################################################
- # fist we calculate more key powers
-
- vmovdqu64 128($ctx),$R2 # load 1-3-2-4 powers
- vmovdqu64 160($ctx),$S1
- vmovdqu64 64($ctx),$R0
- vmovdqu64 96($ctx),$R1
-
- vpsllq \$2,$R2,$S2 # S2 = R2*5*4
- vpaddq $R2,$S2,$S2
- vpsllq \$2,$S2,$S2
-
- vpbroadcastq %x#$R2,$RR2 # broadcast 4th power
- vpbroadcastq %x#$R0,$RR0
- vpbroadcastq %x#$R1,$RR1
-
- vpxorq $D0lo,$D0lo,$D0lo
- vpmadd52luq $RR2,$S1,$D0lo
- vpxorq $D0hi,$D0hi,$D0hi
- vpmadd52huq $RR2,$S1,$D0hi
- vpxorq $D1lo,$D1lo,$D1lo
- vpmadd52luq $RR2,$S2,$D1lo
- vpxorq $D1hi,$D1hi,$D1hi
- vpmadd52huq $RR2,$S2,$D1hi
- vpxorq $D2lo,$D2lo,$D2lo
- vpmadd52luq $RR2,$R0,$D2lo
- vpxorq $D2hi,$D2hi,$D2hi
- vpmadd52huq $RR2,$R0,$D2hi
-
- vpmadd52luq $RR0,$R0,$D0lo
- vpmadd52huq $RR0,$R0,$D0hi
- vpmadd52luq $RR0,$R1,$D1lo
- vpmadd52huq $RR0,$R1,$D1hi
- vpmadd52luq $RR0,$R2,$D2lo
- vpmadd52huq $RR0,$R2,$D2hi
-
- vpmadd52luq $RR1,$S2,$D0lo
- vpmadd52huq $RR1,$S2,$D0hi
- vpmadd52luq $RR1,$R0,$D1lo
- vpmadd52huq $RR1,$R0,$D1hi
- vpmadd52luq $RR1,$R1,$D2lo
- vpmadd52huq $RR1,$R1,$D2hi
-
- ################################################################
- # partial reduction
- vpsrlq \$44,$D0lo,$tmp
- vpsllq \$8,$D0hi,$D0hi
- vpandq $mask44,$D0lo,$RR0
- vpaddq $tmp,$D0hi,$D0hi
-
- vpaddq $D0hi,$D1lo,$D1lo
-
- vpsrlq \$44,$D1lo,$tmp
- vpsllq \$8,$D1hi,$D1hi
- vpandq $mask44,$D1lo,$RR1
- vpaddq $tmp,$D1hi,$D1hi
-
- vpaddq $D1hi,$D2lo,$D2lo
-
- vpsrlq \$42,$D2lo,$tmp
- vpsllq \$10,$D2hi,$D2hi
- vpandq $mask42,$D2lo,$RR2
- vpaddq $tmp,$D2hi,$D2hi
-
- vpaddq $D2hi,$RR0,$RR0
- vpsllq \$2,$D2hi,$D2hi
-
- vpaddq $D2hi,$RR0,$RR0
-
- vpsrlq \$44,$RR0,$tmp # additional step
- vpandq $mask44,$RR0,$RR0
-
- vpaddq $tmp,$RR1,$RR1
-
- ################################################################
- # At this point Rx holds 1324 powers, RRx - 5768, and the goal
- # is 15263748, which reflects how data is loaded...
-
- vpunpcklqdq $R2,$RR2,$T2 # 3748
- vpunpckhqdq $R2,$RR2,$R2 # 1526
- vpunpcklqdq $R0,$RR0,$T0
- vpunpckhqdq $R0,$RR0,$R0
- vpunpcklqdq $R1,$RR1,$T1
- vpunpckhqdq $R1,$RR1,$R1
-___
-######## switch to %zmm
-map(s/%y/%z/, $H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2);
-map(s/%y/%z/, $D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi);
-map(s/%y/%z/, $T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD);
-map(s/%y/%z/, $RR0,$RR1,$RR2,$SS1,$SS2);
-
-$code.=<<___;
- vshufi64x2 \$0x44,$R2,$T2,$RR2 # 15263748
- vshufi64x2 \$0x44,$R0,$T0,$RR0
- vshufi64x2 \$0x44,$R1,$T1,$RR1
-
- vmovdqu64 16*0($inp),$T2 # load data
- vmovdqu64 16*4($inp),$T3
- lea 16*8($inp),$inp
-
- vpsllq \$2,$RR2,$SS2 # S2 = R2*5*4
- vpsllq \$2,$RR1,$SS1 # S1 = R1*5*4
- vpaddq $RR2,$SS2,$SS2
- vpaddq $RR1,$SS1,$SS1
- vpsllq \$2,$SS2,$SS2
- vpsllq \$2,$SS1,$SS1
-
- vpbroadcastq $padbit,$PAD
- vpbroadcastq %x#$mask44,$mask44
- vpbroadcastq %x#$mask42,$mask42
-
- vpbroadcastq %x#$SS1,$S1 # broadcast 8th power
- vpbroadcastq %x#$SS2,$S2
- vpbroadcastq %x#$RR0,$R0
- vpbroadcastq %x#$RR1,$R1
- vpbroadcastq %x#$RR2,$R2
-
- vpunpcklqdq $T3,$T2,$T1 # transpose data
- vpunpckhqdq $T3,$T2,$T3
-
- # at this point 64-bit lanes are ordered as 73625140
-
- vpsrlq \$24,$T3,$T2 # splat the data
- vporq $PAD,$T2,$T2
- vpaddq $T2,$H2,$H2 # accumulate input
- vpandq $mask44,$T1,$T0
- vpsrlq \$44,$T1,$T1
- vpsllq \$20,$T3,$T3
- vporq $T3,$T1,$T1
- vpandq $mask44,$T1,$T1
-
- sub \$8,$len
- jz .Ltail_vpmadd52_8x
- jmp .Loop_vpmadd52_8x
-
-.align 32
-.Loop_vpmadd52_8x:
- #vpaddq $T2,$H2,$H2 # accumulate input
- vpaddq $T0,$H0,$H0
- vpaddq $T1,$H1,$H1
-
- vpxorq $D0lo,$D0lo,$D0lo
- vpmadd52luq $H2,$S1,$D0lo
- vpxorq $D0hi,$D0hi,$D0hi
- vpmadd52huq $H2,$S1,$D0hi
- vpxorq $D1lo,$D1lo,$D1lo
- vpmadd52luq $H2,$S2,$D1lo
- vpxorq $D1hi,$D1hi,$D1hi
- vpmadd52huq $H2,$S2,$D1hi
- vpxorq $D2lo,$D2lo,$D2lo
- vpmadd52luq $H2,$R0,$D2lo
- vpxorq $D2hi,$D2hi,$D2hi
- vpmadd52huq $H2,$R0,$D2hi
-
- vmovdqu64 16*0($inp),$T2 # load data
- vmovdqu64 16*4($inp),$T3
- lea 16*8($inp),$inp
- vpmadd52luq $H0,$R0,$D0lo
- vpmadd52huq $H0,$R0,$D0hi
- vpmadd52luq $H0,$R1,$D1lo
- vpmadd52huq $H0,$R1,$D1hi
- vpmadd52luq $H0,$R2,$D2lo
- vpmadd52huq $H0,$R2,$D2hi
-
- vpunpcklqdq $T3,$T2,$T1 # transpose data
- vpunpckhqdq $T3,$T2,$T3
- vpmadd52luq $H1,$S2,$D0lo
- vpmadd52huq $H1,$S2,$D0hi
- vpmadd52luq $H1,$R0,$D1lo
- vpmadd52huq $H1,$R0,$D1hi
- vpmadd52luq $H1,$R1,$D2lo
- vpmadd52huq $H1,$R1,$D2hi
-
- ################################################################
- # partial reduction (interleaved with data splat)
- vpsrlq \$44,$D0lo,$tmp
- vpsllq \$8,$D0hi,$D0hi
- vpandq $mask44,$D0lo,$H0
- vpaddq $tmp,$D0hi,$D0hi
-
- vpsrlq \$24,$T3,$T2
- vporq $PAD,$T2,$T2
- vpaddq $D0hi,$D1lo,$D1lo
-
- vpsrlq \$44,$D1lo,$tmp
- vpsllq \$8,$D1hi,$D1hi
- vpandq $mask44,$D1lo,$H1
- vpaddq $tmp,$D1hi,$D1hi
-
- vpandq $mask44,$T1,$T0
- vpsrlq \$44,$T1,$T1
- vpsllq \$20,$T3,$T3
- vpaddq $D1hi,$D2lo,$D2lo
-
- vpsrlq \$42,$D2lo,$tmp
- vpsllq \$10,$D2hi,$D2hi
- vpandq $mask42,$D2lo,$H2
- vpaddq $tmp,$D2hi,$D2hi
-
- vpaddq $T2,$H2,$H2 # accumulate input
- vpaddq $D2hi,$H0,$H0
- vpsllq \$2,$D2hi,$D2hi
-
- vpaddq $D2hi,$H0,$H0
- vporq $T3,$T1,$T1
- vpandq $mask44,$T1,$T1
-
- vpsrlq \$44,$H0,$tmp # additional step
- vpandq $mask44,$H0,$H0
-
- vpaddq $tmp,$H1,$H1
-
- sub \$8,$len # len-=128
- jnz .Loop_vpmadd52_8x
-
-.Ltail_vpmadd52_8x:
- #vpaddq $T2,$H2,$H2 # accumulate input
- vpaddq $T0,$H0,$H0
- vpaddq $T1,$H1,$H1
-
- vpxorq $D0lo,$D0lo,$D0lo
- vpmadd52luq $H2,$SS1,$D0lo
- vpxorq $D0hi,$D0hi,$D0hi
- vpmadd52huq $H2,$SS1,$D0hi
- vpxorq $D1lo,$D1lo,$D1lo
- vpmadd52luq $H2,$SS2,$D1lo
- vpxorq $D1hi,$D1hi,$D1hi
- vpmadd52huq $H2,$SS2,$D1hi
- vpxorq $D2lo,$D2lo,$D2lo
- vpmadd52luq $H2,$RR0,$D2lo
- vpxorq $D2hi,$D2hi,$D2hi
- vpmadd52huq $H2,$RR0,$D2hi
-
- vpmadd52luq $H0,$RR0,$D0lo
- vpmadd52huq $H0,$RR0,$D0hi
- vpmadd52luq $H0,$RR1,$D1lo
- vpmadd52huq $H0,$RR1,$D1hi
- vpmadd52luq $H0,$RR2,$D2lo
- vpmadd52huq $H0,$RR2,$D2hi
-
- vpmadd52luq $H1,$SS2,$D0lo
- vpmadd52huq $H1,$SS2,$D0hi
- vpmadd52luq $H1,$RR0,$D1lo
- vpmadd52huq $H1,$RR0,$D1hi
- vpmadd52luq $H1,$RR1,$D2lo
- vpmadd52huq $H1,$RR1,$D2hi
-
- ################################################################
- # horizontal addition
-
- mov \$1,%eax
- kmovw %eax,%k1
- vpsrldq \$8,$D0lo,$T0
- vpsrldq \$8,$D0hi,$H0
- vpsrldq \$8,$D1lo,$T1
- vpsrldq \$8,$D1hi,$H1
- vpaddq $T0,$D0lo,$D0lo
- vpaddq $H0,$D0hi,$D0hi
- vpsrldq \$8,$D2lo,$T2
- vpsrldq \$8,$D2hi,$H2
- vpaddq $T1,$D1lo,$D1lo
- vpaddq $H1,$D1hi,$D1hi
- vpermq \$0x2,$D0lo,$T0
- vpermq \$0x2,$D0hi,$H0
- vpaddq $T2,$D2lo,$D2lo
- vpaddq $H2,$D2hi,$D2hi
-
- vpermq \$0x2,$D1lo,$T1
- vpermq \$0x2,$D1hi,$H1
- vpaddq $T0,$D0lo,$D0lo
- vpaddq $H0,$D0hi,$D0hi
- vpermq \$0x2,$D2lo,$T2
- vpermq \$0x2,$D2hi,$H2
- vpaddq $T1,$D1lo,$D1lo
- vpaddq $H1,$D1hi,$D1hi
- vextracti64x4 \$1,$D0lo,%y#$T0
- vextracti64x4 \$1,$D0hi,%y#$H0
- vpaddq $T2,$D2lo,$D2lo
- vpaddq $H2,$D2hi,$D2hi
-
- vextracti64x4 \$1,$D1lo,%y#$T1
- vextracti64x4 \$1,$D1hi,%y#$H1
- vextracti64x4 \$1,$D2lo,%y#$T2
- vextracti64x4 \$1,$D2hi,%y#$H2
-___
-######## switch back to %ymm
-map(s/%z/%y/, $H0,$H1,$H2,$R0,$R1,$R2,$S1,$S2);
-map(s/%z/%y/, $D0lo,$D0hi,$D1lo,$D1hi,$D2lo,$D2hi);
-map(s/%z/%y/, $T0,$T1,$T2,$T3,$mask44,$mask42,$tmp,$PAD);
-
-$code.=<<___;
- vpaddq $T0,$D0lo,${D0lo}{%k1}{z}
- vpaddq $H0,$D0hi,${D0hi}{%k1}{z}
- vpaddq $T1,$D1lo,${D1lo}{%k1}{z}
- vpaddq $H1,$D1hi,${D1hi}{%k1}{z}
- vpaddq $T2,$D2lo,${D2lo}{%k1}{z}
- vpaddq $H2,$D2hi,${D2hi}{%k1}{z}
-
- ################################################################
- # partial reduction
- vpsrlq \$44,$D0lo,$tmp
- vpsllq \$8,$D0hi,$D0hi
- vpandq $mask44,$D0lo,$H0
- vpaddq $tmp,$D0hi,$D0hi
-
- vpaddq $D0hi,$D1lo,$D1lo
-
- vpsrlq \$44,$D1lo,$tmp
- vpsllq \$8,$D1hi,$D1hi
- vpandq $mask44,$D1lo,$H1
- vpaddq $tmp,$D1hi,$D1hi
-
- vpaddq $D1hi,$D2lo,$D2lo
-
- vpsrlq \$42,$D2lo,$tmp
- vpsllq \$10,$D2hi,$D2hi
- vpandq $mask42,$D2lo,$H2
- vpaddq $tmp,$D2hi,$D2hi
-
- vpaddq $D2hi,$H0,$H0
- vpsllq \$2,$D2hi,$D2hi
-
- vpaddq $D2hi,$H0,$H0
-
- vpsrlq \$44,$H0,$tmp # additional step
- vpandq $mask44,$H0,$H0
-
- vpaddq $tmp,$H1,$H1
-
- ################################################################
-
- vmovq %x#$H0,0($ctx)
- vmovq %x#$H1,8($ctx)
- vmovq %x#$H2,16($ctx)
- vzeroall
-
-.Lno_data_vpmadd52_8x:
- RET
-.size poly1305_blocks_vpmadd52_8x,.-poly1305_blocks_vpmadd52_8x
-___
-}
-$code.=<<___;
-.type poly1305_emit_base2_44,\@function,3
-.align 32
-poly1305_emit_base2_44:
- mov 0($ctx),%r8 # load hash value
- mov 8($ctx),%r9
- mov 16($ctx),%r10
-
- mov %r9,%rax
- shr \$20,%r9
- shl \$44,%rax
- mov %r10,%rcx
- shr \$40,%r10
- shl \$24,%rcx
-
- add %rax,%r8
- adc %rcx,%r9
- adc \$0,%r10
-
- mov %r8,%rax
- add \$5,%r8 # compare to modulus
- mov %r9,%rcx
- adc \$0,%r9
- adc \$0,%r10
- shr \$2,%r10 # did 130-bit value overflow?
- cmovnz %r8,%rax
- cmovnz %r9,%rcx
-
- add 0($nonce),%rax # accumulate nonce
- adc 8($nonce),%rcx
- mov %rax,0($mac) # write result
- mov %rcx,8($mac)
-
- RET
-.size poly1305_emit_base2_44,.-poly1305_emit_base2_44
-___
-} } }
-}
-
-if (!$kernel)
-{ # chacha20-poly1305 helpers
-my ($out,$inp,$otp,$len)=$win64 ? ("%rcx","%rdx","%r8", "%r9") : # Win64 order
- ("%rdi","%rsi","%rdx","%rcx"); # Unix order
-$code.=<<___;
-.globl xor128_encrypt_n_pad
-.type xor128_encrypt_n_pad,\@abi-omnipotent
-.align 16
-xor128_encrypt_n_pad:
- sub $otp,$inp
- sub $otp,$out
- mov $len,%r10 # put len aside
- shr \$4,$len # len / 16
- jz .Ltail_enc
- nop
-.Loop_enc_xmm:
- movdqu ($inp,$otp),%xmm0
- pxor ($otp),%xmm0
- movdqu %xmm0,($out,$otp)
- movdqa %xmm0,($otp)
- lea 16($otp),$otp
- dec $len
- jnz .Loop_enc_xmm
-
- and \$15,%r10 # len % 16
- jz .Ldone_enc
-
-.Ltail_enc:
- mov \$16,$len
- sub %r10,$len
- xor %eax,%eax
-.Loop_enc_byte:
- mov ($inp,$otp),%al
- xor ($otp),%al
- mov %al,($out,$otp)
- mov %al,($otp)
- lea 1($otp),$otp
- dec %r10
- jnz .Loop_enc_byte
-
- xor %eax,%eax
-.Loop_enc_pad:
- mov %al,($otp)
- lea 1($otp),$otp
- dec $len
- jnz .Loop_enc_pad
-
-.Ldone_enc:
- mov $otp,%rax
- RET
-.size xor128_encrypt_n_pad,.-xor128_encrypt_n_pad
-
-.globl xor128_decrypt_n_pad
-.type xor128_decrypt_n_pad,\@abi-omnipotent
-.align 16
-xor128_decrypt_n_pad:
- sub $otp,$inp
- sub $otp,$out
- mov $len,%r10 # put len aside
- shr \$4,$len # len / 16
- jz .Ltail_dec
- nop
-.Loop_dec_xmm:
- movdqu ($inp,$otp),%xmm0
- movdqa ($otp),%xmm1
- pxor %xmm0,%xmm1
- movdqu %xmm1,($out,$otp)
- movdqa %xmm0,($otp)
- lea 16($otp),$otp
- dec $len
- jnz .Loop_dec_xmm
-
- pxor %xmm1,%xmm1
- and \$15,%r10 # len % 16
- jz .Ldone_dec
-
-.Ltail_dec:
- mov \$16,$len
- sub %r10,$len
- xor %eax,%eax
- xor %r11d,%r11d
-.Loop_dec_byte:
- mov ($inp,$otp),%r11b
- mov ($otp),%al
- xor %r11b,%al
- mov %al,($out,$otp)
- mov %r11b,($otp)
- lea 1($otp),$otp
- dec %r10
- jnz .Loop_dec_byte
-
- xor %eax,%eax
-.Loop_dec_pad:
- mov %al,($otp)
- lea 1($otp),$otp
- dec $len
- jnz .Loop_dec_pad
-
-.Ldone_dec:
- mov $otp,%rax
- RET
-.size xor128_decrypt_n_pad,.-xor128_decrypt_n_pad
-___
-}
-
-# EXCEPTION_DISPOSITION handler (EXCEPTION_RECORD *rec,ULONG64 frame,
-# CONTEXT *context,DISPATCHER_CONTEXT *disp)
-if ($win64) {
-$rec="%rcx";
-$frame="%rdx";
-$context="%r8";
-$disp="%r9";
-
-$code.=<<___;
-.extern __imp_RtlVirtualUnwind
-.type se_handler,\@abi-omnipotent
-.align 16
-se_handler:
- push %rsi
- push %rdi
- push %rbx
- push %rbp
- push %r12
- push %r13
- push %r14
- push %r15
- pushfq
- sub \$64,%rsp
-
- mov 120($context),%rax # pull context->Rax
- mov 248($context),%rbx # pull context->Rip
-
- mov 8($disp),%rsi # disp->ImageBase
- mov 56($disp),%r11 # disp->HandlerData
-
- mov 0(%r11),%r10d # HandlerData[0]
- lea (%rsi,%r10),%r10 # prologue label
- cmp %r10,%rbx # context->Rip<.Lprologue
- jb .Lcommon_seh_tail
-
- mov 152($context),%rax # pull context->Rsp
-
- mov 4(%r11),%r10d # HandlerData[1]
- lea (%rsi,%r10),%r10 # epilogue label
- cmp %r10,%rbx # context->Rip>=.Lepilogue
- jae .Lcommon_seh_tail
-
- lea 48(%rax),%rax
-
- mov -8(%rax),%rbx
- mov -16(%rax),%rbp
- mov -24(%rax),%r12
- mov -32(%rax),%r13
- mov -40(%rax),%r14
- mov -48(%rax),%r15
- mov %rbx,144($context) # restore context->Rbx
- mov %rbp,160($context) # restore context->Rbp
- mov %r12,216($context) # restore context->R12
- mov %r13,224($context) # restore context->R13
- mov %r14,232($context) # restore context->R14
- mov %r15,240($context) # restore context->R14
-
- jmp .Lcommon_seh_tail
-.size se_handler,.-se_handler
-
-.type avx_handler,\@abi-omnipotent
-.align 16
-avx_handler:
- push %rsi
- push %rdi
- push %rbx
- push %rbp
- push %r12
- push %r13
- push %r14
- push %r15
- pushfq
- sub \$64,%rsp
-
- mov 120($context),%rax # pull context->Rax
- mov 248($context),%rbx # pull context->Rip
-
- mov 8($disp),%rsi # disp->ImageBase
- mov 56($disp),%r11 # disp->HandlerData
-
- mov 0(%r11),%r10d # HandlerData[0]
- lea (%rsi,%r10),%r10 # prologue label
- cmp %r10,%rbx # context->Rip<prologue label
- jb .Lcommon_seh_tail
-
- mov 152($context),%rax # pull context->Rsp
-
- mov 4(%r11),%r10d # HandlerData[1]
- lea (%rsi,%r10),%r10 # epilogue label
- cmp %r10,%rbx # context->Rip>=epilogue label
- jae .Lcommon_seh_tail
-
- mov 208($context),%rax # pull context->R11
-
- lea 0x50(%rax),%rsi
- lea 0xf8(%rax),%rax
- lea 512($context),%rdi # &context.Xmm6
- mov \$20,%ecx
- .long 0xa548f3fc # cld; rep movsq
-
-.Lcommon_seh_tail:
- mov 8(%rax),%rdi
- mov 16(%rax),%rsi
- mov %rax,152($context) # restore context->Rsp
- mov %rsi,168($context) # restore context->Rsi
- mov %rdi,176($context) # restore context->Rdi
-
- mov 40($disp),%rdi # disp->ContextRecord
- mov $context,%rsi # context
- mov \$154,%ecx # sizeof(CONTEXT)
- .long 0xa548f3fc # cld; rep movsq
-
- mov $disp,%rsi
- xor %ecx,%ecx # arg1, UNW_FLAG_NHANDLER
- mov 8(%rsi),%rdx # arg2, disp->ImageBase
- mov 0(%rsi),%r8 # arg3, disp->ControlPc
- mov 16(%rsi),%r9 # arg4, disp->FunctionEntry
- mov 40(%rsi),%r10 # disp->ContextRecord
- lea 56(%rsi),%r11 # &disp->HandlerData
- lea 24(%rsi),%r12 # &disp->EstablisherFrame
- mov %r10,32(%rsp) # arg5
- mov %r11,40(%rsp) # arg6
- mov %r12,48(%rsp) # arg7
- mov %rcx,56(%rsp) # arg8, (NULL)
- call *__imp_RtlVirtualUnwind(%rip)
-
- mov \$1,%eax # ExceptionContinueSearch
- add \$64,%rsp
- popfq
- pop %r15
- pop %r14
- pop %r13
- pop %r12
- pop %rbp
- pop %rbx
- pop %rdi
- pop %rsi
- RET
-.size avx_handler,.-avx_handler
-
-.section .pdata
-.align 4
- .rva .LSEH_begin_poly1305_init_x86_64
- .rva .LSEH_end_poly1305_init_x86_64
- .rva .LSEH_info_poly1305_init_x86_64
-
- .rva .LSEH_begin_poly1305_blocks_x86_64
- .rva .LSEH_end_poly1305_blocks_x86_64
- .rva .LSEH_info_poly1305_blocks_x86_64
-
- .rva .LSEH_begin_poly1305_emit_x86_64
- .rva .LSEH_end_poly1305_emit_x86_64
- .rva .LSEH_info_poly1305_emit_x86_64
-___
-$code.=<<___ if ($avx);
- .rva .LSEH_begin_poly1305_blocks_avx
- .rva .Lbase2_64_avx
- .rva .LSEH_info_poly1305_blocks_avx_1
-
- .rva .Lbase2_64_avx
- .rva .Leven_avx
- .rva .LSEH_info_poly1305_blocks_avx_2
-
- .rva .Leven_avx
- .rva .LSEH_end_poly1305_blocks_avx
- .rva .LSEH_info_poly1305_blocks_avx_3
-
- .rva .LSEH_begin_poly1305_emit_avx
- .rva .LSEH_end_poly1305_emit_avx
- .rva .LSEH_info_poly1305_emit_avx
-___
-$code.=<<___ if ($avx>1);
- .rva .LSEH_begin_poly1305_blocks_avx2
- .rva .Lbase2_64_avx2
- .rva .LSEH_info_poly1305_blocks_avx2_1
-
- .rva .Lbase2_64_avx2
- .rva .Leven_avx2
- .rva .LSEH_info_poly1305_blocks_avx2_2
-
- .rva .Leven_avx2
- .rva .LSEH_end_poly1305_blocks_avx2
- .rva .LSEH_info_poly1305_blocks_avx2_3
-___
-$code.=<<___ if ($avx>2);
- .rva .LSEH_begin_poly1305_blocks_avx512
- .rva .LSEH_end_poly1305_blocks_avx512
- .rva .LSEH_info_poly1305_blocks_avx512
-___
-$code.=<<___;
-.section .xdata
-.align 8
-.LSEH_info_poly1305_init_x86_64:
- .byte 9,0,0,0
- .rva se_handler
- .rva .LSEH_begin_poly1305_init_x86_64,.LSEH_begin_poly1305_init_x86_64
-
-.LSEH_info_poly1305_blocks_x86_64:
- .byte 9,0,0,0
- .rva se_handler
- .rva .Lblocks_body,.Lblocks_epilogue
-
-.LSEH_info_poly1305_emit_x86_64:
- .byte 9,0,0,0
- .rva se_handler
- .rva .LSEH_begin_poly1305_emit_x86_64,.LSEH_begin_poly1305_emit_x86_64
-___
-$code.=<<___ if ($avx);
-.LSEH_info_poly1305_blocks_avx_1:
- .byte 9,0,0,0
- .rva se_handler
- .rva .Lblocks_avx_body,.Lblocks_avx_epilogue # HandlerData[]
-
-.LSEH_info_poly1305_blocks_avx_2:
- .byte 9,0,0,0
- .rva se_handler
- .rva .Lbase2_64_avx_body,.Lbase2_64_avx_epilogue # HandlerData[]
-
-.LSEH_info_poly1305_blocks_avx_3:
- .byte 9,0,0,0
- .rva avx_handler
- .rva .Ldo_avx_body,.Ldo_avx_epilogue # HandlerData[]
-
-.LSEH_info_poly1305_emit_avx:
- .byte 9,0,0,0
- .rva se_handler
- .rva .LSEH_begin_poly1305_emit_avx,.LSEH_begin_poly1305_emit_avx
-___
-$code.=<<___ if ($avx>1);
-.LSEH_info_poly1305_blocks_avx2_1:
- .byte 9,0,0,0
- .rva se_handler
- .rva .Lblocks_avx2_body,.Lblocks_avx2_epilogue # HandlerData[]
-
-.LSEH_info_poly1305_blocks_avx2_2:
- .byte 9,0,0,0
- .rva se_handler
- .rva .Lbase2_64_avx2_body,.Lbase2_64_avx2_epilogue # HandlerData[]
-
-.LSEH_info_poly1305_blocks_avx2_3:
- .byte 9,0,0,0
- .rva avx_handler
- .rva .Ldo_avx2_body,.Ldo_avx2_epilogue # HandlerData[]
-___
-$code.=<<___ if ($avx>2);
-.LSEH_info_poly1305_blocks_avx512:
- .byte 9,0,0,0
- .rva avx_handler
- .rva .Ldo_avx512_body,.Ldo_avx512_epilogue # HandlerData[]
-___
-}
-
-open SELF,$0;
-while(<SELF>) {
- next if (/^#!/);
- last if (!s/^#/\/\// and !/^$/);
- print;
-}
-close SELF;
-
-foreach (split('\n',$code)) {
- s/\`([^\`]*)\`/eval($1)/ge;
- s/%r([a-z]+)#d/%e$1/g;
- s/%r([0-9]+)#d/%r$1d/g;
- s/%x#%[yz]/%x/g or s/%y#%z/%y/g or s/%z#%[yz]/%z/g;
-
- if ($kernel) {
- s/(^\.type.*),[0-9]+$/\1/;
- s/(^\.type.*),\@abi-omnipotent+$/\1,\@function/;
- next if /^\.cfi.*/;
- }
-
- print $_,"\n";
-}
-close STDOUT;
diff --git a/arch/x86/crypto/poly1305_glue.c b/arch/x86/crypto/poly1305_glue.c
deleted file mode 100644
index 08ff4b489f7e..000000000000
--- a/arch/x86/crypto/poly1305_glue.c
+++ /dev/null
@@ -1,290 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0 OR MIT
-/*
- * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved.
- */
-
-#include <crypto/algapi.h>
-#include <crypto/internal/hash.h>
-#include <crypto/internal/poly1305.h>
-#include <crypto/internal/simd.h>
-#include <linux/crypto.h>
-#include <linux/jump_label.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/sizes.h>
-#include <asm/cpu_device_id.h>
-#include <asm/simd.h>
-
-asmlinkage void poly1305_init_x86_64(void *ctx,
- const u8 key[POLY1305_BLOCK_SIZE]);
-asmlinkage void poly1305_blocks_x86_64(void *ctx, const u8 *inp,
- const size_t len, const u32 padbit);
-asmlinkage void poly1305_emit_x86_64(void *ctx, u8 mac[POLY1305_DIGEST_SIZE],
- const u32 nonce[4]);
-asmlinkage void poly1305_emit_avx(void *ctx, u8 mac[POLY1305_DIGEST_SIZE],
- const u32 nonce[4]);
-asmlinkage void poly1305_blocks_avx(void *ctx, const u8 *inp, const size_t len,
- const u32 padbit);
-asmlinkage void poly1305_blocks_avx2(void *ctx, const u8 *inp, const size_t len,
- const u32 padbit);
-asmlinkage void poly1305_blocks_avx512(void *ctx, const u8 *inp,
- const size_t len, const u32 padbit);
-
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx2);
-static __ro_after_init DEFINE_STATIC_KEY_FALSE(poly1305_use_avx512);
-
-struct poly1305_arch_internal {
- union {
- struct {
- u32 h[5];
- u32 is_base2_26;
- };
- u64 hs[3];
- };
- u64 r[2];
- u64 pad;
- struct { u32 r2, r1, r4, r3; } rn[9];
-};
-
-/* The AVX code uses base 2^26, while the scalar code uses base 2^64. If we hit
- * the unfortunate situation of using AVX and then having to go back to scalar
- * -- because the user is silly and has called the update function from two
- * separate contexts -- then we need to convert back to the original base before
- * proceeding. It is possible to reason that the initial reduction below is
- * sufficient given the implementation invariants. However, for an avoidance of
- * doubt and because this is not performance critical, we do the full reduction
- * anyway. Z3 proof of below function: https://xn--4db.cc/ltPtHCKN/py
- */
-static void convert_to_base2_64(void *ctx)
-{
- struct poly1305_arch_internal *state = ctx;
- u32 cy;
-
- if (!state->is_base2_26)
- return;
-
- cy = state->h[0] >> 26; state->h[0] &= 0x3ffffff; state->h[1] += cy;
- cy = state->h[1] >> 26; state->h[1] &= 0x3ffffff; state->h[2] += cy;
- cy = state->h[2] >> 26; state->h[2] &= 0x3ffffff; state->h[3] += cy;
- cy = state->h[3] >> 26; state->h[3] &= 0x3ffffff; state->h[4] += cy;
- state->hs[0] = ((u64)state->h[2] << 52) | ((u64)state->h[1] << 26) | state->h[0];
- state->hs[1] = ((u64)state->h[4] << 40) | ((u64)state->h[3] << 14) | (state->h[2] >> 12);
- state->hs[2] = state->h[4] >> 24;
-#define ULT(a, b) ((a ^ ((a ^ b) | ((a - b) ^ b))) >> (sizeof(a) * 8 - 1))
- cy = (state->hs[2] >> 2) + (state->hs[2] & ~3ULL);
- state->hs[2] &= 3;
- state->hs[0] += cy;
- state->hs[1] += (cy = ULT(state->hs[0], cy));
- state->hs[2] += ULT(state->hs[1], cy);
-#undef ULT
- state->is_base2_26 = 0;
-}
-
-static void poly1305_simd_init(void *ctx, const u8 key[POLY1305_BLOCK_SIZE])
-{
- poly1305_init_x86_64(ctx, key);
-}
-
-static void poly1305_simd_blocks(void *ctx, const u8 *inp, size_t len,
- const u32 padbit)
-{
- struct poly1305_arch_internal *state = ctx;
-
- /* SIMD disables preemption, so relax after processing each page. */
- BUILD_BUG_ON(SZ_4K < POLY1305_BLOCK_SIZE ||
- SZ_4K % POLY1305_BLOCK_SIZE);
-
- if (!static_branch_likely(&poly1305_use_avx) ||
- (len < (POLY1305_BLOCK_SIZE * 18) && !state->is_base2_26) ||
- !crypto_simd_usable()) {
- convert_to_base2_64(ctx);
- poly1305_blocks_x86_64(ctx, inp, len, padbit);
- return;
- }
-
- do {
- const size_t bytes = min_t(size_t, len, SZ_4K);
-
- kernel_fpu_begin();
- if (IS_ENABLED(CONFIG_AS_AVX512) && static_branch_likely(&poly1305_use_avx512))
- poly1305_blocks_avx512(ctx, inp, bytes, padbit);
- else if (static_branch_likely(&poly1305_use_avx2))
- poly1305_blocks_avx2(ctx, inp, bytes, padbit);
- else
- poly1305_blocks_avx(ctx, inp, bytes, padbit);
- kernel_fpu_end();
-
- len -= bytes;
- inp += bytes;
- } while (len);
-}
-
-static void poly1305_simd_emit(void *ctx, u8 mac[POLY1305_DIGEST_SIZE],
- const u32 nonce[4])
-{
- if (!static_branch_likely(&poly1305_use_avx))
- poly1305_emit_x86_64(ctx, mac, nonce);
- else
- poly1305_emit_avx(ctx, mac, nonce);
-}
-
-void poly1305_init_arch(struct poly1305_desc_ctx *dctx, const u8 key[POLY1305_KEY_SIZE])
-{
- poly1305_simd_init(&dctx->h, key);
- dctx->s[0] = get_unaligned_le32(&key[16]);
- dctx->s[1] = get_unaligned_le32(&key[20]);
- dctx->s[2] = get_unaligned_le32(&key[24]);
- dctx->s[3] = get_unaligned_le32(&key[28]);
- dctx->buflen = 0;
- dctx->sset = true;
-}
-EXPORT_SYMBOL(poly1305_init_arch);
-
-static unsigned int crypto_poly1305_setdctxkey(struct poly1305_desc_ctx *dctx,
- const u8 *inp, unsigned int len)
-{
- unsigned int acc = 0;
- if (unlikely(!dctx->sset)) {
- if (!dctx->rset && len >= POLY1305_BLOCK_SIZE) {
- poly1305_simd_init(&dctx->h, inp);
- inp += POLY1305_BLOCK_SIZE;
- len -= POLY1305_BLOCK_SIZE;
- acc += POLY1305_BLOCK_SIZE;
- dctx->rset = 1;
- }
- if (len >= POLY1305_BLOCK_SIZE) {
- dctx->s[0] = get_unaligned_le32(&inp[0]);
- dctx->s[1] = get_unaligned_le32(&inp[4]);
- dctx->s[2] = get_unaligned_le32(&inp[8]);
- dctx->s[3] = get_unaligned_le32(&inp[12]);
- acc += POLY1305_BLOCK_SIZE;
- dctx->sset = true;
- }
- }
- return acc;
-}
-
-void poly1305_update_arch(struct poly1305_desc_ctx *dctx, const u8 *src,
- unsigned int srclen)
-{
- unsigned int bytes, used;
-
- if (unlikely(dctx->buflen)) {
- bytes = min(srclen, POLY1305_BLOCK_SIZE - dctx->buflen);
- memcpy(dctx->buf + dctx->buflen, src, bytes);
- src += bytes;
- srclen -= bytes;
- dctx->buflen += bytes;
-
- if (dctx->buflen == POLY1305_BLOCK_SIZE) {
- if (likely(!crypto_poly1305_setdctxkey(dctx, dctx->buf, POLY1305_BLOCK_SIZE)))
- poly1305_simd_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 1);
- dctx->buflen = 0;
- }
- }
-
- if (likely(srclen >= POLY1305_BLOCK_SIZE)) {
- bytes = round_down(srclen, POLY1305_BLOCK_SIZE);
- srclen -= bytes;
- used = crypto_poly1305_setdctxkey(dctx, src, bytes);
- if (likely(bytes - used))
- poly1305_simd_blocks(&dctx->h, src + used, bytes - used, 1);
- src += bytes;
- }
-
- if (unlikely(srclen)) {
- dctx->buflen = srclen;
- memcpy(dctx->buf, src, srclen);
- }
-}
-EXPORT_SYMBOL(poly1305_update_arch);
-
-void poly1305_final_arch(struct poly1305_desc_ctx *dctx, u8 *dst)
-{
- if (unlikely(dctx->buflen)) {
- dctx->buf[dctx->buflen++] = 1;
- memset(dctx->buf + dctx->buflen, 0,
- POLY1305_BLOCK_SIZE - dctx->buflen);
- poly1305_simd_blocks(&dctx->h, dctx->buf, POLY1305_BLOCK_SIZE, 0);
- }
-
- poly1305_simd_emit(&dctx->h, dst, dctx->s);
- memzero_explicit(dctx, sizeof(*dctx));
-}
-EXPORT_SYMBOL(poly1305_final_arch);
-
-static int crypto_poly1305_init(struct shash_desc *desc)
-{
- struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
- *dctx = (struct poly1305_desc_ctx){};
- return 0;
-}
-
-static int crypto_poly1305_update(struct shash_desc *desc,
- const u8 *src, unsigned int srclen)
-{
- struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
- poly1305_update_arch(dctx, src, srclen);
- return 0;
-}
-
-static int crypto_poly1305_final(struct shash_desc *desc, u8 *dst)
-{
- struct poly1305_desc_ctx *dctx = shash_desc_ctx(desc);
-
- if (unlikely(!dctx->sset))
- return -ENOKEY;
-
- poly1305_final_arch(dctx, dst);
- return 0;
-}
-
-static struct shash_alg alg = {
- .digestsize = POLY1305_DIGEST_SIZE,
- .init = crypto_poly1305_init,
- .update = crypto_poly1305_update,
- .final = crypto_poly1305_final,
- .descsize = sizeof(struct poly1305_desc_ctx),
- .base = {
- .cra_name = "poly1305",
- .cra_driver_name = "poly1305-simd",
- .cra_priority = 300,
- .cra_blocksize = POLY1305_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- },
-};
-
-static int __init poly1305_simd_mod_init(void)
-{
- if (boot_cpu_has(X86_FEATURE_AVX) &&
- cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
- static_branch_enable(&poly1305_use_avx);
- if (boot_cpu_has(X86_FEATURE_AVX) && boot_cpu_has(X86_FEATURE_AVX2) &&
- cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL))
- static_branch_enable(&poly1305_use_avx2);
- if (IS_ENABLED(CONFIG_AS_AVX512) && boot_cpu_has(X86_FEATURE_AVX) &&
- boot_cpu_has(X86_FEATURE_AVX2) && boot_cpu_has(X86_FEATURE_AVX512F) &&
- cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | XFEATURE_MASK_AVX512, NULL) &&
- /* Skylake downclocks unacceptably much when using zmm, but later generations are fast. */
- boot_cpu_data.x86_vfm != INTEL_SKYLAKE_X)
- static_branch_enable(&poly1305_use_avx512);
- return IS_REACHABLE(CONFIG_CRYPTO_HASH) ? crypto_register_shash(&alg) : 0;
-}
-
-static void __exit poly1305_simd_mod_exit(void)
-{
- if (IS_REACHABLE(CONFIG_CRYPTO_HASH))
- crypto_unregister_shash(&alg);
-}
-
-module_init(poly1305_simd_mod_init);
-module_exit(poly1305_simd_mod_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Jason A. Donenfeld <Jason@zx2c4.com>");
-MODULE_DESCRIPTION("Poly1305 authenticator");
-MODULE_ALIAS_CRYPTO("poly1305");
-MODULE_ALIAS_CRYPTO("poly1305-simd");
diff --git a/arch/x86/crypto/polyval-clmulni_glue.c b/arch/x86/crypto/polyval-clmulni_glue.c
index 8fa58b0f3cb3..6b466867f91a 100644
--- a/arch/x86/crypto/polyval-clmulni_glue.c
+++ b/arch/x86/crypto/polyval-clmulni_glue.c
@@ -16,16 +16,15 @@
* operations.
*/
-#include <crypto/algapi.h>
+#include <asm/cpu_device_id.h>
+#include <asm/fpu/api.h>
#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
#include <crypto/polyval.h>
-#include <linux/crypto.h>
-#include <linux/init.h>
+#include <crypto/utils.h>
+#include <linux/errno.h>
#include <linux/kernel.h>
#include <linux/module.h>
-#include <asm/cpu_device_id.h>
-#include <asm/simd.h>
+#include <linux/string.h>
#define POLYVAL_ALIGN 16
#define POLYVAL_ALIGN_ATTR __aligned(POLYVAL_ALIGN)
@@ -42,7 +41,6 @@ struct polyval_tfm_ctx {
struct polyval_desc_ctx {
u8 buffer[POLYVAL_BLOCK_SIZE];
- u32 bytes;
};
asmlinkage void clmul_polyval_update(const struct polyval_tfm_ctx *keys,
@@ -57,25 +55,16 @@ static inline struct polyval_tfm_ctx *polyval_tfm_ctx(struct crypto_shash *tfm)
static void internal_polyval_update(const struct polyval_tfm_ctx *keys,
const u8 *in, size_t nblocks, u8 *accumulator)
{
- if (likely(crypto_simd_usable())) {
- kernel_fpu_begin();
- clmul_polyval_update(keys, in, nblocks, accumulator);
- kernel_fpu_end();
- } else {
- polyval_update_non4k(keys->key_powers[NUM_KEY_POWERS-1], in,
- nblocks, accumulator);
- }
+ kernel_fpu_begin();
+ clmul_polyval_update(keys, in, nblocks, accumulator);
+ kernel_fpu_end();
}
static void internal_polyval_mul(u8 *op1, const u8 *op2)
{
- if (likely(crypto_simd_usable())) {
- kernel_fpu_begin();
- clmul_polyval_mul(op1, op2);
- kernel_fpu_end();
- } else {
- polyval_mul_non4k(op1, op2);
- }
+ kernel_fpu_begin();
+ clmul_polyval_mul(op1, op2);
+ kernel_fpu_end();
}
static int polyval_x86_setkey(struct crypto_shash *tfm,
@@ -112,49 +101,27 @@ static int polyval_x86_update(struct shash_desc *desc,
{
struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
- u8 *pos;
unsigned int nblocks;
- unsigned int n;
-
- if (dctx->bytes) {
- n = min(srclen, dctx->bytes);
- pos = dctx->buffer + POLYVAL_BLOCK_SIZE - dctx->bytes;
-
- dctx->bytes -= n;
- srclen -= n;
-
- while (n--)
- *pos++ ^= *src++;
- if (!dctx->bytes)
- internal_polyval_mul(dctx->buffer,
- tctx->key_powers[NUM_KEY_POWERS-1]);
- }
-
- while (srclen >= POLYVAL_BLOCK_SIZE) {
+ do {
/* Allow rescheduling every 4K bytes. */
nblocks = min(srclen, 4096U) / POLYVAL_BLOCK_SIZE;
internal_polyval_update(tctx, src, nblocks, dctx->buffer);
srclen -= nblocks * POLYVAL_BLOCK_SIZE;
src += nblocks * POLYVAL_BLOCK_SIZE;
- }
+ } while (srclen >= POLYVAL_BLOCK_SIZE);
- if (srclen) {
- dctx->bytes = POLYVAL_BLOCK_SIZE - srclen;
- pos = dctx->buffer;
- while (srclen--)
- *pos++ ^= *src++;
- }
-
- return 0;
+ return srclen;
}
-static int polyval_x86_final(struct shash_desc *desc, u8 *dst)
+static int polyval_x86_finup(struct shash_desc *desc, const u8 *src,
+ unsigned int len, u8 *dst)
{
struct polyval_desc_ctx *dctx = shash_desc_ctx(desc);
const struct polyval_tfm_ctx *tctx = polyval_tfm_ctx(desc->tfm);
- if (dctx->bytes) {
+ if (len) {
+ crypto_xor(dctx->buffer, src, len);
internal_polyval_mul(dctx->buffer,
tctx->key_powers[NUM_KEY_POWERS-1]);
}
@@ -168,13 +135,14 @@ static struct shash_alg polyval_alg = {
.digestsize = POLYVAL_DIGEST_SIZE,
.init = polyval_x86_init,
.update = polyval_x86_update,
- .final = polyval_x86_final,
+ .finup = polyval_x86_finup,
.setkey = polyval_x86_setkey,
.descsize = sizeof(struct polyval_desc_ctx),
.base = {
.cra_name = "polyval",
.cra_driver_name = "polyval-clmulni",
.cra_priority = 200,
+ .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY,
.cra_blocksize = POLYVAL_BLOCK_SIZE,
.cra_ctxsize = POLYVAL_CTX_SIZE,
.cra_module = THIS_MODULE,
diff --git a/arch/x86/crypto/serpent_avx2_glue.c b/arch/x86/crypto/serpent_avx2_glue.c
index 347e97f4b713..f5f2121b7956 100644
--- a/arch/x86/crypto/serpent_avx2_glue.c
+++ b/arch/x86/crypto/serpent_avx2_glue.c
@@ -10,7 +10,6 @@
#include <linux/crypto.h>
#include <linux/err.h>
#include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
#include <crypto/serpent.h>
#include "serpent-avx.h"
@@ -65,10 +64,9 @@ static int cbc_decrypt(struct skcipher_request *req)
static struct skcipher_alg serpent_algs[] = {
{
- .base.cra_name = "__ecb(serpent)",
- .base.cra_driver_name = "__ecb-serpent-avx2",
+ .base.cra_name = "ecb(serpent)",
+ .base.cra_driver_name = "ecb-serpent-avx2",
.base.cra_priority = 600,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = SERPENT_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct serpent_ctx),
.base.cra_module = THIS_MODULE,
@@ -78,10 +76,9 @@ static struct skcipher_alg serpent_algs[] = {
.encrypt = ecb_encrypt,
.decrypt = ecb_decrypt,
}, {
- .base.cra_name = "__cbc(serpent)",
- .base.cra_driver_name = "__cbc-serpent-avx2",
+ .base.cra_name = "cbc(serpent)",
+ .base.cra_driver_name = "cbc-serpent-avx2",
.base.cra_priority = 600,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = SERPENT_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct serpent_ctx),
.base.cra_module = THIS_MODULE,
@@ -94,8 +91,6 @@ static struct skcipher_alg serpent_algs[] = {
},
};
-static struct simd_skcipher_alg *serpent_simd_algs[ARRAY_SIZE(serpent_algs)];
-
static int __init serpent_avx2_init(void)
{
const char *feature_name;
@@ -110,15 +105,13 @@ static int __init serpent_avx2_init(void)
return -ENODEV;
}
- return simd_register_skciphers_compat(serpent_algs,
- ARRAY_SIZE(serpent_algs),
- serpent_simd_algs);
+ return crypto_register_skciphers(serpent_algs,
+ ARRAY_SIZE(serpent_algs));
}
static void __exit serpent_avx2_fini(void)
{
- simd_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs),
- serpent_simd_algs);
+ crypto_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs));
}
module_init(serpent_avx2_init);
diff --git a/arch/x86/crypto/serpent_avx_glue.c b/arch/x86/crypto/serpent_avx_glue.c
index 6c248e1ea4ef..9c8b3a335d5c 100644
--- a/arch/x86/crypto/serpent_avx_glue.c
+++ b/arch/x86/crypto/serpent_avx_glue.c
@@ -12,8 +12,8 @@
#include <linux/types.h>
#include <linux/crypto.h>
#include <linux/err.h>
+#include <linux/export.h>
#include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
#include <crypto/serpent.h>
#include "serpent-avx.h"
@@ -71,10 +71,9 @@ static int cbc_decrypt(struct skcipher_request *req)
static struct skcipher_alg serpent_algs[] = {
{
- .base.cra_name = "__ecb(serpent)",
- .base.cra_driver_name = "__ecb-serpent-avx",
+ .base.cra_name = "ecb(serpent)",
+ .base.cra_driver_name = "ecb-serpent-avx",
.base.cra_priority = 500,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = SERPENT_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct serpent_ctx),
.base.cra_module = THIS_MODULE,
@@ -84,10 +83,9 @@ static struct skcipher_alg serpent_algs[] = {
.encrypt = ecb_encrypt,
.decrypt = ecb_decrypt,
}, {
- .base.cra_name = "__cbc(serpent)",
- .base.cra_driver_name = "__cbc-serpent-avx",
+ .base.cra_name = "cbc(serpent)",
+ .base.cra_driver_name = "cbc-serpent-avx",
.base.cra_priority = 500,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = SERPENT_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct serpent_ctx),
.base.cra_module = THIS_MODULE,
@@ -100,8 +98,6 @@ static struct skcipher_alg serpent_algs[] = {
},
};
-static struct simd_skcipher_alg *serpent_simd_algs[ARRAY_SIZE(serpent_algs)];
-
static int __init serpent_init(void)
{
const char *feature_name;
@@ -112,15 +108,13 @@ static int __init serpent_init(void)
return -ENODEV;
}
- return simd_register_skciphers_compat(serpent_algs,
- ARRAY_SIZE(serpent_algs),
- serpent_simd_algs);
+ return crypto_register_skciphers(serpent_algs,
+ ARRAY_SIZE(serpent_algs));
}
static void __exit serpent_exit(void)
{
- simd_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs),
- serpent_simd_algs);
+ crypto_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs));
}
module_init(serpent_init);
diff --git a/arch/x86/crypto/serpent_sse2_glue.c b/arch/x86/crypto/serpent_sse2_glue.c
index d78f37e9b2cf..80ee17ec21b4 100644
--- a/arch/x86/crypto/serpent_sse2_glue.c
+++ b/arch/x86/crypto/serpent_sse2_glue.c
@@ -18,7 +18,6 @@
#include <linux/err.h>
#include <crypto/algapi.h>
#include <crypto/b128ops.h>
-#include <crypto/internal/simd.h>
#include <crypto/serpent.h>
#include "serpent-sse2.h"
@@ -74,10 +73,9 @@ static int cbc_decrypt(struct skcipher_request *req)
static struct skcipher_alg serpent_algs[] = {
{
- .base.cra_name = "__ecb(serpent)",
- .base.cra_driver_name = "__ecb-serpent-sse2",
+ .base.cra_name = "ecb(serpent)",
+ .base.cra_driver_name = "ecb-serpent-sse2",
.base.cra_priority = 400,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = SERPENT_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct serpent_ctx),
.base.cra_module = THIS_MODULE,
@@ -87,10 +85,9 @@ static struct skcipher_alg serpent_algs[] = {
.encrypt = ecb_encrypt,
.decrypt = ecb_decrypt,
}, {
- .base.cra_name = "__cbc(serpent)",
- .base.cra_driver_name = "__cbc-serpent-sse2",
+ .base.cra_name = "cbc(serpent)",
+ .base.cra_driver_name = "cbc-serpent-sse2",
.base.cra_priority = 400,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = SERPENT_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct serpent_ctx),
.base.cra_module = THIS_MODULE,
@@ -103,8 +100,6 @@ static struct skcipher_alg serpent_algs[] = {
},
};
-static struct simd_skcipher_alg *serpent_simd_algs[ARRAY_SIZE(serpent_algs)];
-
static int __init serpent_sse2_init(void)
{
if (!boot_cpu_has(X86_FEATURE_XMM2)) {
@@ -112,15 +107,13 @@ static int __init serpent_sse2_init(void)
return -ENODEV;
}
- return simd_register_skciphers_compat(serpent_algs,
- ARRAY_SIZE(serpent_algs),
- serpent_simd_algs);
+ return crypto_register_skciphers(serpent_algs,
+ ARRAY_SIZE(serpent_algs));
}
static void __exit serpent_sse2_exit(void)
{
- simd_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs),
- serpent_simd_algs);
+ crypto_unregister_skciphers(serpent_algs, ARRAY_SIZE(serpent_algs));
}
module_init(serpent_sse2_init);
diff --git a/arch/x86/crypto/sha1_avx2_x86_64_asm.S b/arch/x86/crypto/sha1_avx2_x86_64_asm.S
deleted file mode 100644
index 4b49bdc95265..000000000000
--- a/arch/x86/crypto/sha1_avx2_x86_64_asm.S
+++ /dev/null
@@ -1,700 +0,0 @@
-/*
- * Implement fast SHA-1 with AVX2 instructions. (x86_64)
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Ilya Albrekht <ilya.albrekht@intel.com>
- * Maxim Locktyukhin <maxim.locktyukhin@intel.com>
- * Ronen Zohar <ronen.zohar@intel.com>
- * Chandramouli Narayanan <mouli@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2014 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-/*
- * SHA-1 implementation with Intel(R) AVX2 instruction set extensions.
- *
- *This implementation is based on the previous SSSE3 release:
- *Visit http://software.intel.com/en-us/articles/
- *and refer to improving-the-performance-of-the-secure-hash-algorithm-1/
- *
- *Updates 20-byte SHA-1 record at start of 'state', from 'input', for
- *even number of 'blocks' consecutive 64-byte blocks.
- *
- *extern "C" void sha1_transform_avx2(
- * struct sha1_state *state, const u8* input, int blocks );
- */
-
-#include <linux/linkage.h>
-
-#define CTX %rdi /* arg1 */
-#define BUF %rsi /* arg2 */
-#define CNT %rdx /* arg3 */
-
-#define REG_A %ecx
-#define REG_B %esi
-#define REG_C %edi
-#define REG_D %eax
-#define REG_E %edx
-#define REG_TB %ebx
-#define REG_TA %r12d
-#define REG_RA %rcx
-#define REG_RB %rsi
-#define REG_RC %rdi
-#define REG_RD %rax
-#define REG_RE %rdx
-#define REG_RTA %r12
-#define REG_RTB %rbx
-#define REG_T1 %r11d
-#define xmm_mov vmovups
-#define avx2_zeroupper vzeroupper
-#define RND_F1 1
-#define RND_F2 2
-#define RND_F3 3
-
-.macro REGALLOC
- .set A, REG_A
- .set B, REG_B
- .set C, REG_C
- .set D, REG_D
- .set E, REG_E
- .set TB, REG_TB
- .set TA, REG_TA
-
- .set RA, REG_RA
- .set RB, REG_RB
- .set RC, REG_RC
- .set RD, REG_RD
- .set RE, REG_RE
-
- .set RTA, REG_RTA
- .set RTB, REG_RTB
-
- .set T1, REG_T1
-.endm
-
-#define HASH_PTR %r9
-#define BLOCKS_CTR %r8
-#define BUFFER_PTR %r10
-#define BUFFER_PTR2 %r13
-
-#define PRECALC_BUF %r14
-#define WK_BUF %r15
-
-#define W_TMP %xmm0
-#define WY_TMP %ymm0
-#define WY_TMP2 %ymm9
-
-# AVX2 variables
-#define WY0 %ymm3
-#define WY4 %ymm5
-#define WY08 %ymm7
-#define WY12 %ymm8
-#define WY16 %ymm12
-#define WY20 %ymm13
-#define WY24 %ymm14
-#define WY28 %ymm15
-
-#define YMM_SHUFB_BSWAP %ymm10
-
-/*
- * Keep 2 iterations precalculated at a time:
- * - 80 DWORDs per iteration * 2
- */
-#define W_SIZE (80*2*2 +16)
-
-#define WK(t) ((((t) % 80) / 4)*32 + ( (t) % 4)*4 + ((t)/80)*16 )(WK_BUF)
-#define PRECALC_WK(t) ((t)*2*2)(PRECALC_BUF)
-
-
-.macro UPDATE_HASH hash, val
- add \hash, \val
- mov \val, \hash
-.endm
-
-.macro PRECALC_RESET_WY
- .set WY_00, WY0
- .set WY_04, WY4
- .set WY_08, WY08
- .set WY_12, WY12
- .set WY_16, WY16
- .set WY_20, WY20
- .set WY_24, WY24
- .set WY_28, WY28
- .set WY_32, WY_00
-.endm
-
-.macro PRECALC_ROTATE_WY
- /* Rotate macros */
- .set WY_32, WY_28
- .set WY_28, WY_24
- .set WY_24, WY_20
- .set WY_20, WY_16
- .set WY_16, WY_12
- .set WY_12, WY_08
- .set WY_08, WY_04
- .set WY_04, WY_00
- .set WY_00, WY_32
-
- /* Define register aliases */
- .set WY, WY_00
- .set WY_minus_04, WY_04
- .set WY_minus_08, WY_08
- .set WY_minus_12, WY_12
- .set WY_minus_16, WY_16
- .set WY_minus_20, WY_20
- .set WY_minus_24, WY_24
- .set WY_minus_28, WY_28
- .set WY_minus_32, WY
-.endm
-
-.macro PRECALC_00_15
- .if (i == 0) # Initialize and rotate registers
- PRECALC_RESET_WY
- PRECALC_ROTATE_WY
- .endif
-
- /* message scheduling pre-compute for rounds 0-15 */
- .if ((i & 7) == 0)
- /*
- * blended AVX2 and ALU instruction scheduling
- * 1 vector iteration per 8 rounds
- */
- vmovdqu (i * 2)(BUFFER_PTR), W_TMP
- .elseif ((i & 7) == 1)
- vinsertf128 $1, ((i-1) * 2)(BUFFER_PTR2),\
- WY_TMP, WY_TMP
- .elseif ((i & 7) == 2)
- vpshufb YMM_SHUFB_BSWAP, WY_TMP, WY
- .elseif ((i & 7) == 4)
- vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP
- .elseif ((i & 7) == 7)
- vmovdqu WY_TMP, PRECALC_WK(i&~7)
-
- PRECALC_ROTATE_WY
- .endif
-.endm
-
-.macro PRECALC_16_31
- /*
- * message scheduling pre-compute for rounds 16-31
- * calculating last 32 w[i] values in 8 XMM registers
- * pre-calculate K+w[i] values and store to mem
- * for later load by ALU add instruction
- *
- * "brute force" vectorization for rounds 16-31 only
- * due to w[i]->w[i-3] dependency
- */
- .if ((i & 7) == 0)
- /*
- * blended AVX2 and ALU instruction scheduling
- * 1 vector iteration per 8 rounds
- */
- /* w[i-14] */
- vpalignr $8, WY_minus_16, WY_minus_12, WY
- vpsrldq $4, WY_minus_04, WY_TMP /* w[i-3] */
- .elseif ((i & 7) == 1)
- vpxor WY_minus_08, WY, WY
- vpxor WY_minus_16, WY_TMP, WY_TMP
- .elseif ((i & 7) == 2)
- vpxor WY_TMP, WY, WY
- vpslldq $12, WY, WY_TMP2
- .elseif ((i & 7) == 3)
- vpslld $1, WY, WY_TMP
- vpsrld $31, WY, WY
- .elseif ((i & 7) == 4)
- vpor WY, WY_TMP, WY_TMP
- vpslld $2, WY_TMP2, WY
- .elseif ((i & 7) == 5)
- vpsrld $30, WY_TMP2, WY_TMP2
- vpxor WY, WY_TMP, WY_TMP
- .elseif ((i & 7) == 7)
- vpxor WY_TMP2, WY_TMP, WY
- vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP
- vmovdqu WY_TMP, PRECALC_WK(i&~7)
-
- PRECALC_ROTATE_WY
- .endif
-.endm
-
-.macro PRECALC_32_79
- /*
- * in SHA-1 specification:
- * w[i] = (w[i-3] ^ w[i-8] ^ w[i-14] ^ w[i-16]) rol 1
- * instead we do equal:
- * w[i] = (w[i-6] ^ w[i-16] ^ w[i-28] ^ w[i-32]) rol 2
- * allows more efficient vectorization
- * since w[i]=>w[i-3] dependency is broken
- */
-
- .if ((i & 7) == 0)
- /*
- * blended AVX2 and ALU instruction scheduling
- * 1 vector iteration per 8 rounds
- */
- vpalignr $8, WY_minus_08, WY_minus_04, WY_TMP
- .elseif ((i & 7) == 1)
- /* W is W_minus_32 before xor */
- vpxor WY_minus_28, WY, WY
- .elseif ((i & 7) == 2)
- vpxor WY_minus_16, WY_TMP, WY_TMP
- .elseif ((i & 7) == 3)
- vpxor WY_TMP, WY, WY
- .elseif ((i & 7) == 4)
- vpslld $2, WY, WY_TMP
- .elseif ((i & 7) == 5)
- vpsrld $30, WY, WY
- vpor WY, WY_TMP, WY
- .elseif ((i & 7) == 7)
- vpaddd K_XMM + K_XMM_AR(%rip), WY, WY_TMP
- vmovdqu WY_TMP, PRECALC_WK(i&~7)
-
- PRECALC_ROTATE_WY
- .endif
-.endm
-
-.macro PRECALC r, s
- .set i, \r
-
- .if (i < 40)
- .set K_XMM, 32*0
- .elseif (i < 80)
- .set K_XMM, 32*1
- .elseif (i < 120)
- .set K_XMM, 32*2
- .else
- .set K_XMM, 32*3
- .endif
-
- .if (i<32)
- PRECALC_00_15 \s
- .elseif (i<64)
- PRECALC_16_31 \s
- .elseif (i < 160)
- PRECALC_32_79 \s
- .endif
-.endm
-
-.macro ROTATE_STATE
- .set T_REG, E
- .set E, D
- .set D, C
- .set C, B
- .set B, TB
- .set TB, A
- .set A, T_REG
-
- .set T_REG, RE
- .set RE, RD
- .set RD, RC
- .set RC, RB
- .set RB, RTB
- .set RTB, RA
- .set RA, T_REG
-.endm
-
-/* Macro relies on saved ROUND_Fx */
-
-.macro RND_FUN f, r
- .if (\f == RND_F1)
- ROUND_F1 \r
- .elseif (\f == RND_F2)
- ROUND_F2 \r
- .elseif (\f == RND_F3)
- ROUND_F3 \r
- .endif
-.endm
-
-.macro RR r
- .set round_id, (\r % 80)
-
- .if (round_id == 0) /* Precalculate F for first round */
- .set ROUND_FUNC, RND_F1
- mov B, TB
-
- rorx $(32-30), B, B /* b>>>2 */
- andn D, TB, T1
- and C, TB
- xor T1, TB
- .endif
-
- RND_FUN ROUND_FUNC, \r
- ROTATE_STATE
-
- .if (round_id == 18)
- .set ROUND_FUNC, RND_F2
- .elseif (round_id == 38)
- .set ROUND_FUNC, RND_F3
- .elseif (round_id == 58)
- .set ROUND_FUNC, RND_F2
- .endif
-
- .set round_id, ( (\r+1) % 80)
-
- RND_FUN ROUND_FUNC, (\r+1)
- ROTATE_STATE
-.endm
-
-.macro ROUND_F1 r
- add WK(\r), E
-
- andn C, A, T1 /* ~b&d */
- lea (RE,RTB), E /* Add F from the previous round */
-
- rorx $(32-5), A, TA /* T2 = A >>> 5 */
- rorx $(32-30),A, TB /* b>>>2 for next round */
-
- PRECALC (\r) /* msg scheduling for next 2 blocks */
-
- /*
- * Calculate F for the next round
- * (b & c) ^ andn[b, d]
- */
- and B, A /* b&c */
- xor T1, A /* F1 = (b&c) ^ (~b&d) */
-
- lea (RE,RTA), E /* E += A >>> 5 */
-.endm
-
-.macro ROUND_F2 r
- add WK(\r), E
- lea (RE,RTB), E /* Add F from the previous round */
-
- /* Calculate F for the next round */
- rorx $(32-5), A, TA /* T2 = A >>> 5 */
- .if ((round_id) < 79)
- rorx $(32-30), A, TB /* b>>>2 for next round */
- .endif
- PRECALC (\r) /* msg scheduling for next 2 blocks */
-
- .if ((round_id) < 79)
- xor B, A
- .endif
-
- add TA, E /* E += A >>> 5 */
-
- .if ((round_id) < 79)
- xor C, A
- .endif
-.endm
-
-.macro ROUND_F3 r
- add WK(\r), E
- PRECALC (\r) /* msg scheduling for next 2 blocks */
-
- lea (RE,RTB), E /* Add F from the previous round */
-
- mov B, T1
- or A, T1
-
- rorx $(32-5), A, TA /* T2 = A >>> 5 */
- rorx $(32-30), A, TB /* b>>>2 for next round */
-
- /* Calculate F for the next round
- * (b and c) or (d and (b or c))
- */
- and C, T1
- and B, A
- or T1, A
-
- add TA, E /* E += A >>> 5 */
-
-.endm
-
-/* Add constant only if (%2 > %3) condition met (uses RTA as temp)
- * %1 + %2 >= %3 ? %4 : 0
- */
-.macro ADD_IF_GE a, b, c, d
- mov \a, RTA
- add $\d, RTA
- cmp $\c, \b
- cmovge RTA, \a
-.endm
-
-/*
- * macro implements 80 rounds of SHA-1, for multiple blocks with s/w pipelining
- */
-.macro SHA1_PIPELINED_MAIN_BODY
-
- REGALLOC
-
- mov (HASH_PTR), A
- mov 4(HASH_PTR), B
- mov 8(HASH_PTR), C
- mov 12(HASH_PTR), D
- mov 16(HASH_PTR), E
-
- mov %rsp, PRECALC_BUF
- lea (2*4*80+32)(%rsp), WK_BUF
-
- # Precalc WK for first 2 blocks
- ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 2, 64
- .set i, 0
- .rept 160
- PRECALC i
- .set i, i + 1
- .endr
-
- /* Go to next block if needed */
- ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 3, 128
- ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
- xchg WK_BUF, PRECALC_BUF
-
- .align 32
-.L_loop:
- /*
- * code loops through more than one block
- * we use K_BASE value as a signal of a last block,
- * it is set below by: cmovae BUFFER_PTR, K_BASE
- */
- test BLOCKS_CTR, BLOCKS_CTR
- jnz .L_begin
- .align 32
- jmp .L_end
- .align 32
-.L_begin:
-
- /*
- * Do first block
- * rounds: 0,2,4,6,8
- */
- .set j, 0
- .rept 5
- RR j
- .set j, j+2
- .endr
-
- /*
- * rounds:
- * 10,12,14,16,18
- * 20,22,24,26,28
- * 30,32,34,36,38
- * 40,42,44,46,48
- * 50,52,54,56,58
- */
- .rept 25
- RR j
- .set j, j+2
- .endr
-
- /* Update Counter */
- sub $1, BLOCKS_CTR
- /* Move to the next block only if needed*/
- ADD_IF_GE BUFFER_PTR, BLOCKS_CTR, 4, 128
- /*
- * rounds
- * 60,62,64,66,68
- * 70,72,74,76,78
- */
- .rept 10
- RR j
- .set j, j+2
- .endr
-
- UPDATE_HASH (HASH_PTR), A
- UPDATE_HASH 4(HASH_PTR), TB
- UPDATE_HASH 8(HASH_PTR), C
- UPDATE_HASH 12(HASH_PTR), D
- UPDATE_HASH 16(HASH_PTR), E
-
- test BLOCKS_CTR, BLOCKS_CTR
- jz .L_loop
-
- mov TB, B
-
- /* Process second block */
- /*
- * rounds
- * 0+80, 2+80, 4+80, 6+80, 8+80
- * 10+80,12+80,14+80,16+80,18+80
- */
-
- .set j, 0
- .rept 10
- RR j+80
- .set j, j+2
- .endr
-
- /*
- * rounds
- * 20+80,22+80,24+80,26+80,28+80
- * 30+80,32+80,34+80,36+80,38+80
- */
- .rept 10
- RR j+80
- .set j, j+2
- .endr
-
- /*
- * rounds
- * 40+80,42+80,44+80,46+80,48+80
- * 50+80,52+80,54+80,56+80,58+80
- */
- .rept 10
- RR j+80
- .set j, j+2
- .endr
-
- /* update counter */
- sub $1, BLOCKS_CTR
- /* Move to the next block only if needed*/
- ADD_IF_GE BUFFER_PTR2, BLOCKS_CTR, 4, 128
-
- /*
- * rounds
- * 60+80,62+80,64+80,66+80,68+80
- * 70+80,72+80,74+80,76+80,78+80
- */
- .rept 10
- RR j+80
- .set j, j+2
- .endr
-
- UPDATE_HASH (HASH_PTR), A
- UPDATE_HASH 4(HASH_PTR), TB
- UPDATE_HASH 8(HASH_PTR), C
- UPDATE_HASH 12(HASH_PTR), D
- UPDATE_HASH 16(HASH_PTR), E
-
- /* Reset state for AVX2 reg permutation */
- mov A, TA
- mov TB, A
- mov C, TB
- mov E, C
- mov D, B
- mov TA, D
-
- REGALLOC
-
- xchg WK_BUF, PRECALC_BUF
-
- jmp .L_loop
-
- .align 32
-.L_end:
-
-.endm
-/*
- * macro implements SHA-1 function's body for several 64-byte blocks
- * param: function's name
- */
-.macro SHA1_VECTOR_ASM name
- SYM_FUNC_START(\name)
-
- push %rbx
- push %r12
- push %r13
- push %r14
- push %r15
-
- RESERVE_STACK = (W_SIZE*4 + 8+24)
-
- /* Align stack */
- push %rbp
- mov %rsp, %rbp
- and $~(0x20-1), %rsp
- sub $RESERVE_STACK, %rsp
-
- avx2_zeroupper
-
- /* Setup initial values */
- mov CTX, HASH_PTR
- mov BUF, BUFFER_PTR
-
- mov BUF, BUFFER_PTR2
- mov CNT, BLOCKS_CTR
-
- xmm_mov BSWAP_SHUFB_CTL(%rip), YMM_SHUFB_BSWAP
-
- SHA1_PIPELINED_MAIN_BODY
-
- avx2_zeroupper
-
- mov %rbp, %rsp
- pop %rbp
-
- pop %r15
- pop %r14
- pop %r13
- pop %r12
- pop %rbx
-
- RET
-
- SYM_FUNC_END(\name)
-.endm
-
-.section .rodata
-
-#define K1 0x5a827999
-#define K2 0x6ed9eba1
-#define K3 0x8f1bbcdc
-#define K4 0xca62c1d6
-
-.align 128
-K_XMM_AR:
- .long K1, K1, K1, K1
- .long K1, K1, K1, K1
- .long K2, K2, K2, K2
- .long K2, K2, K2, K2
- .long K3, K3, K3, K3
- .long K3, K3, K3, K3
- .long K4, K4, K4, K4
- .long K4, K4, K4, K4
-
-BSWAP_SHUFB_CTL:
- .long 0x00010203
- .long 0x04050607
- .long 0x08090a0b
- .long 0x0c0d0e0f
- .long 0x00010203
- .long 0x04050607
- .long 0x08090a0b
- .long 0x0c0d0e0f
-.text
-
-SHA1_VECTOR_ASM sha1_transform_avx2
diff --git a/arch/x86/crypto/sha1_ni_asm.S b/arch/x86/crypto/sha1_ni_asm.S
deleted file mode 100644
index cade913d4882..000000000000
--- a/arch/x86/crypto/sha1_ni_asm.S
+++ /dev/null
@@ -1,304 +0,0 @@
-/*
- * Intel SHA Extensions optimized implementation of a SHA-1 update function
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Sean Gulley <sean.m.gulley@intel.com>
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-#include <linux/linkage.h>
-#include <linux/cfi_types.h>
-
-#define DIGEST_PTR %rdi /* 1st arg */
-#define DATA_PTR %rsi /* 2nd arg */
-#define NUM_BLKS %rdx /* 3rd arg */
-
-/* gcc conversion */
-#define FRAME_SIZE 32 /* space for 2x16 bytes */
-
-#define ABCD %xmm0
-#define E0 %xmm1 /* Need two E's b/c they ping pong */
-#define E1 %xmm2
-#define MSG0 %xmm3
-#define MSG1 %xmm4
-#define MSG2 %xmm5
-#define MSG3 %xmm6
-#define SHUF_MASK %xmm7
-
-
-/*
- * Intel SHA Extensions optimized implementation of a SHA-1 update function
- *
- * The function takes a pointer to the current hash values, a pointer to the
- * input data, and a number of 64 byte blocks to process. Once all blocks have
- * been processed, the digest pointer is updated with the resulting hash value.
- * The function only processes complete blocks, there is no functionality to
- * store partial blocks. All message padding and hash value initialization must
- * be done outside the update function.
- *
- * The indented lines in the loop are instructions related to rounds processing.
- * The non-indented lines are instructions related to the message schedule.
- *
- * void sha1_ni_transform(uint32_t *digest, const void *data,
- uint32_t numBlocks)
- * digest : pointer to digest
- * data: pointer to input data
- * numBlocks: Number of blocks to process
- */
-.text
-SYM_TYPED_FUNC_START(sha1_ni_transform)
- push %rbp
- mov %rsp, %rbp
- sub $FRAME_SIZE, %rsp
- and $~0xF, %rsp
-
- shl $6, NUM_BLKS /* convert to bytes */
- jz .Ldone_hash
- add DATA_PTR, NUM_BLKS /* pointer to end of data */
-
- /* load initial hash values */
- pinsrd $3, 1*16(DIGEST_PTR), E0
- movdqu 0*16(DIGEST_PTR), ABCD
- pand UPPER_WORD_MASK(%rip), E0
- pshufd $0x1B, ABCD, ABCD
-
- movdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK
-
-.Lloop0:
- /* Save hash values for addition after rounds */
- movdqa E0, (0*16)(%rsp)
- movdqa ABCD, (1*16)(%rsp)
-
- /* Rounds 0-3 */
- movdqu 0*16(DATA_PTR), MSG0
- pshufb SHUF_MASK, MSG0
- paddd MSG0, E0
- movdqa ABCD, E1
- sha1rnds4 $0, E0, ABCD
-
- /* Rounds 4-7 */
- movdqu 1*16(DATA_PTR), MSG1
- pshufb SHUF_MASK, MSG1
- sha1nexte MSG1, E1
- movdqa ABCD, E0
- sha1rnds4 $0, E1, ABCD
- sha1msg1 MSG1, MSG0
-
- /* Rounds 8-11 */
- movdqu 2*16(DATA_PTR), MSG2
- pshufb SHUF_MASK, MSG2
- sha1nexte MSG2, E0
- movdqa ABCD, E1
- sha1rnds4 $0, E0, ABCD
- sha1msg1 MSG2, MSG1
- pxor MSG2, MSG0
-
- /* Rounds 12-15 */
- movdqu 3*16(DATA_PTR), MSG3
- pshufb SHUF_MASK, MSG3
- sha1nexte MSG3, E1
- movdqa ABCD, E0
- sha1msg2 MSG3, MSG0
- sha1rnds4 $0, E1, ABCD
- sha1msg1 MSG3, MSG2
- pxor MSG3, MSG1
-
- /* Rounds 16-19 */
- sha1nexte MSG0, E0
- movdqa ABCD, E1
- sha1msg2 MSG0, MSG1
- sha1rnds4 $0, E0, ABCD
- sha1msg1 MSG0, MSG3
- pxor MSG0, MSG2
-
- /* Rounds 20-23 */
- sha1nexte MSG1, E1
- movdqa ABCD, E0
- sha1msg2 MSG1, MSG2
- sha1rnds4 $1, E1, ABCD
- sha1msg1 MSG1, MSG0
- pxor MSG1, MSG3
-
- /* Rounds 24-27 */
- sha1nexte MSG2, E0
- movdqa ABCD, E1
- sha1msg2 MSG2, MSG3
- sha1rnds4 $1, E0, ABCD
- sha1msg1 MSG2, MSG1
- pxor MSG2, MSG0
-
- /* Rounds 28-31 */
- sha1nexte MSG3, E1
- movdqa ABCD, E0
- sha1msg2 MSG3, MSG0
- sha1rnds4 $1, E1, ABCD
- sha1msg1 MSG3, MSG2
- pxor MSG3, MSG1
-
- /* Rounds 32-35 */
- sha1nexte MSG0, E0
- movdqa ABCD, E1
- sha1msg2 MSG0, MSG1
- sha1rnds4 $1, E0, ABCD
- sha1msg1 MSG0, MSG3
- pxor MSG0, MSG2
-
- /* Rounds 36-39 */
- sha1nexte MSG1, E1
- movdqa ABCD, E0
- sha1msg2 MSG1, MSG2
- sha1rnds4 $1, E1, ABCD
- sha1msg1 MSG1, MSG0
- pxor MSG1, MSG3
-
- /* Rounds 40-43 */
- sha1nexte MSG2, E0
- movdqa ABCD, E1
- sha1msg2 MSG2, MSG3
- sha1rnds4 $2, E0, ABCD
- sha1msg1 MSG2, MSG1
- pxor MSG2, MSG0
-
- /* Rounds 44-47 */
- sha1nexte MSG3, E1
- movdqa ABCD, E0
- sha1msg2 MSG3, MSG0
- sha1rnds4 $2, E1, ABCD
- sha1msg1 MSG3, MSG2
- pxor MSG3, MSG1
-
- /* Rounds 48-51 */
- sha1nexte MSG0, E0
- movdqa ABCD, E1
- sha1msg2 MSG0, MSG1
- sha1rnds4 $2, E0, ABCD
- sha1msg1 MSG0, MSG3
- pxor MSG0, MSG2
-
- /* Rounds 52-55 */
- sha1nexte MSG1, E1
- movdqa ABCD, E0
- sha1msg2 MSG1, MSG2
- sha1rnds4 $2, E1, ABCD
- sha1msg1 MSG1, MSG0
- pxor MSG1, MSG3
-
- /* Rounds 56-59 */
- sha1nexte MSG2, E0
- movdqa ABCD, E1
- sha1msg2 MSG2, MSG3
- sha1rnds4 $2, E0, ABCD
- sha1msg1 MSG2, MSG1
- pxor MSG2, MSG0
-
- /* Rounds 60-63 */
- sha1nexte MSG3, E1
- movdqa ABCD, E0
- sha1msg2 MSG3, MSG0
- sha1rnds4 $3, E1, ABCD
- sha1msg1 MSG3, MSG2
- pxor MSG3, MSG1
-
- /* Rounds 64-67 */
- sha1nexte MSG0, E0
- movdqa ABCD, E1
- sha1msg2 MSG0, MSG1
- sha1rnds4 $3, E0, ABCD
- sha1msg1 MSG0, MSG3
- pxor MSG0, MSG2
-
- /* Rounds 68-71 */
- sha1nexte MSG1, E1
- movdqa ABCD, E0
- sha1msg2 MSG1, MSG2
- sha1rnds4 $3, E1, ABCD
- pxor MSG1, MSG3
-
- /* Rounds 72-75 */
- sha1nexte MSG2, E0
- movdqa ABCD, E1
- sha1msg2 MSG2, MSG3
- sha1rnds4 $3, E0, ABCD
-
- /* Rounds 76-79 */
- sha1nexte MSG3, E1
- movdqa ABCD, E0
- sha1rnds4 $3, E1, ABCD
-
- /* Add current hash values with previously saved */
- sha1nexte (0*16)(%rsp), E0
- paddd (1*16)(%rsp), ABCD
-
- /* Increment data pointer and loop if more to process */
- add $64, DATA_PTR
- cmp NUM_BLKS, DATA_PTR
- jne .Lloop0
-
- /* Write hash values back in the correct order */
- pshufd $0x1B, ABCD, ABCD
- movdqu ABCD, 0*16(DIGEST_PTR)
- pextrd $3, E0, 1*16(DIGEST_PTR)
-
-.Ldone_hash:
- mov %rbp, %rsp
- pop %rbp
-
- RET
-SYM_FUNC_END(sha1_ni_transform)
-
-.section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16
-.align 16
-PSHUFFLE_BYTE_FLIP_MASK:
- .octa 0x000102030405060708090a0b0c0d0e0f
-
-.section .rodata.cst16.UPPER_WORD_MASK, "aM", @progbits, 16
-.align 16
-UPPER_WORD_MASK:
- .octa 0xFFFFFFFF000000000000000000000000
diff --git a/arch/x86/crypto/sha1_ssse3_asm.S b/arch/x86/crypto/sha1_ssse3_asm.S
deleted file mode 100644
index f54988c80eb4..000000000000
--- a/arch/x86/crypto/sha1_ssse3_asm.S
+++ /dev/null
@@ -1,554 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * This is a SIMD SHA-1 implementation. It requires the Intel(R) Supplemental
- * SSE3 instruction set extensions introduced in Intel Core Microarchitecture
- * processors. CPUs supporting Intel(R) AVX extensions will get an additional
- * boost.
- *
- * This work was inspired by the vectorized implementation of Dean Gaudet.
- * Additional information on it can be found at:
- * http://www.arctic.org/~dean/crypto/sha1.html
- *
- * It was improved upon with more efficient vectorization of the message
- * scheduling. This implementation has also been optimized for all current and
- * several future generations of Intel CPUs.
- *
- * See this article for more information about the implementation details:
- * http://software.intel.com/en-us/articles/improving-the-performance-of-the-secure-hash-algorithm-1/
- *
- * Copyright (C) 2010, Intel Corp.
- * Authors: Maxim Locktyukhin <maxim.locktyukhin@intel.com>
- * Ronen Zohar <ronen.zohar@intel.com>
- *
- * Converted to AT&T syntax and adapted for inclusion in the Linux kernel:
- * Author: Mathias Krause <minipli@googlemail.com>
- */
-
-#include <linux/linkage.h>
-#include <linux/cfi_types.h>
-
-#define CTX %rdi // arg1
-#define BUF %rsi // arg2
-#define CNT %rdx // arg3
-
-#define REG_A %ecx
-#define REG_B %esi
-#define REG_C %edi
-#define REG_D %r12d
-#define REG_E %edx
-
-#define REG_T1 %eax
-#define REG_T2 %ebx
-
-#define K_BASE %r8
-#define HASH_PTR %r9
-#define BUFFER_PTR %r10
-#define BUFFER_END %r11
-
-#define W_TMP1 %xmm0
-#define W_TMP2 %xmm9
-
-#define W0 %xmm1
-#define W4 %xmm2
-#define W8 %xmm3
-#define W12 %xmm4
-#define W16 %xmm5
-#define W20 %xmm6
-#define W24 %xmm7
-#define W28 %xmm8
-
-#define XMM_SHUFB_BSWAP %xmm10
-
-/* we keep window of 64 w[i]+K pre-calculated values in a circular buffer */
-#define WK(t) (((t) & 15) * 4)(%rsp)
-#define W_PRECALC_AHEAD 16
-
-/*
- * This macro implements the SHA-1 function's body for single 64-byte block
- * param: function's name
- */
-.macro SHA1_VECTOR_ASM name
- SYM_TYPED_FUNC_START(\name)
-
- push %rbx
- push %r12
- push %rbp
- mov %rsp, %rbp
-
- sub $64, %rsp # allocate workspace
- and $~15, %rsp # align stack
-
- mov CTX, HASH_PTR
- mov BUF, BUFFER_PTR
-
- shl $6, CNT # multiply by 64
- add BUF, CNT
- mov CNT, BUFFER_END
-
- lea K_XMM_AR(%rip), K_BASE
- xmm_mov BSWAP_SHUFB_CTL(%rip), XMM_SHUFB_BSWAP
-
- SHA1_PIPELINED_MAIN_BODY
-
- # cleanup workspace
- mov $8, %ecx
- mov %rsp, %rdi
- xor %eax, %eax
- rep stosq
-
- mov %rbp, %rsp # deallocate workspace
- pop %rbp
- pop %r12
- pop %rbx
- RET
-
- SYM_FUNC_END(\name)
-.endm
-
-/*
- * This macro implements 80 rounds of SHA-1 for one 64-byte block
- */
-.macro SHA1_PIPELINED_MAIN_BODY
- INIT_REGALLOC
-
- mov (HASH_PTR), A
- mov 4(HASH_PTR), B
- mov 8(HASH_PTR), C
- mov 12(HASH_PTR), D
- mov 16(HASH_PTR), E
-
- .set i, 0
- .rept W_PRECALC_AHEAD
- W_PRECALC i
- .set i, (i+1)
- .endr
-
-.align 4
-1:
- RR F1,A,B,C,D,E,0
- RR F1,D,E,A,B,C,2
- RR F1,B,C,D,E,A,4
- RR F1,E,A,B,C,D,6
- RR F1,C,D,E,A,B,8
-
- RR F1,A,B,C,D,E,10
- RR F1,D,E,A,B,C,12
- RR F1,B,C,D,E,A,14
- RR F1,E,A,B,C,D,16
- RR F1,C,D,E,A,B,18
-
- RR F2,A,B,C,D,E,20
- RR F2,D,E,A,B,C,22
- RR F2,B,C,D,E,A,24
- RR F2,E,A,B,C,D,26
- RR F2,C,D,E,A,B,28
-
- RR F2,A,B,C,D,E,30
- RR F2,D,E,A,B,C,32
- RR F2,B,C,D,E,A,34
- RR F2,E,A,B,C,D,36
- RR F2,C,D,E,A,B,38
-
- RR F3,A,B,C,D,E,40
- RR F3,D,E,A,B,C,42
- RR F3,B,C,D,E,A,44
- RR F3,E,A,B,C,D,46
- RR F3,C,D,E,A,B,48
-
- RR F3,A,B,C,D,E,50
- RR F3,D,E,A,B,C,52
- RR F3,B,C,D,E,A,54
- RR F3,E,A,B,C,D,56
- RR F3,C,D,E,A,B,58
-
- add $64, BUFFER_PTR # move to the next 64-byte block
- cmp BUFFER_END, BUFFER_PTR # if the current is the last one use
- cmovae K_BASE, BUFFER_PTR # dummy source to avoid buffer overrun
-
- RR F4,A,B,C,D,E,60
- RR F4,D,E,A,B,C,62
- RR F4,B,C,D,E,A,64
- RR F4,E,A,B,C,D,66
- RR F4,C,D,E,A,B,68
-
- RR F4,A,B,C,D,E,70
- RR F4,D,E,A,B,C,72
- RR F4,B,C,D,E,A,74
- RR F4,E,A,B,C,D,76
- RR F4,C,D,E,A,B,78
-
- UPDATE_HASH (HASH_PTR), A
- UPDATE_HASH 4(HASH_PTR), B
- UPDATE_HASH 8(HASH_PTR), C
- UPDATE_HASH 12(HASH_PTR), D
- UPDATE_HASH 16(HASH_PTR), E
-
- RESTORE_RENAMED_REGS
- cmp K_BASE, BUFFER_PTR # K_BASE means, we reached the end
- jne 1b
-.endm
-
-.macro INIT_REGALLOC
- .set A, REG_A
- .set B, REG_B
- .set C, REG_C
- .set D, REG_D
- .set E, REG_E
- .set T1, REG_T1
- .set T2, REG_T2
-.endm
-
-.macro RESTORE_RENAMED_REGS
- # order is important (REG_C is where it should be)
- mov B, REG_B
- mov D, REG_D
- mov A, REG_A
- mov E, REG_E
-.endm
-
-.macro SWAP_REG_NAMES a, b
- .set _T, \a
- .set \a, \b
- .set \b, _T
-.endm
-
-.macro F1 b, c, d
- mov \c, T1
- SWAP_REG_NAMES \c, T1
- xor \d, T1
- and \b, T1
- xor \d, T1
-.endm
-
-.macro F2 b, c, d
- mov \d, T1
- SWAP_REG_NAMES \d, T1
- xor \c, T1
- xor \b, T1
-.endm
-
-.macro F3 b, c ,d
- mov \c, T1
- SWAP_REG_NAMES \c, T1
- mov \b, T2
- or \b, T1
- and \c, T2
- and \d, T1
- or T2, T1
-.endm
-
-.macro F4 b, c, d
- F2 \b, \c, \d
-.endm
-
-.macro UPDATE_HASH hash, val
- add \hash, \val
- mov \val, \hash
-.endm
-
-/*
- * RR does two rounds of SHA-1 back to back with W[] pre-calc
- * t1 = F(b, c, d); e += w(i)
- * e += t1; b <<= 30; d += w(i+1);
- * t1 = F(a, b, c);
- * d += t1; a <<= 5;
- * e += a;
- * t1 = e; a >>= 7;
- * t1 <<= 5;
- * d += t1;
- */
-.macro RR F, a, b, c, d, e, round
- add WK(\round), \e
- \F \b, \c, \d # t1 = F(b, c, d);
- W_PRECALC (\round + W_PRECALC_AHEAD)
- rol $30, \b
- add T1, \e
- add WK(\round + 1), \d
-
- \F \a, \b, \c
- W_PRECALC (\round + W_PRECALC_AHEAD + 1)
- rol $5, \a
- add \a, \e
- add T1, \d
- ror $7, \a # (a <<r 5) >>r 7) => a <<r 30)
-
- mov \e, T1
- SWAP_REG_NAMES \e, T1
-
- rol $5, T1
- add T1, \d
-
- # write: \a, \b
- # rotate: \a<=\d, \b<=\e, \c<=\a, \d<=\b, \e<=\c
-.endm
-
-.macro W_PRECALC r
- .set i, \r
-
- .if (i < 20)
- .set K_XMM, 0
- .elseif (i < 40)
- .set K_XMM, 16
- .elseif (i < 60)
- .set K_XMM, 32
- .elseif (i < 80)
- .set K_XMM, 48
- .endif
-
- .if ((i < 16) || ((i >= 80) && (i < (80 + W_PRECALC_AHEAD))))
- .set i, ((\r) % 80) # pre-compute for the next iteration
- .if (i == 0)
- W_PRECALC_RESET
- .endif
- W_PRECALC_00_15
- .elseif (i<32)
- W_PRECALC_16_31
- .elseif (i < 80) // rounds 32-79
- W_PRECALC_32_79
- .endif
-.endm
-
-.macro W_PRECALC_RESET
- .set W, W0
- .set W_minus_04, W4
- .set W_minus_08, W8
- .set W_minus_12, W12
- .set W_minus_16, W16
- .set W_minus_20, W20
- .set W_minus_24, W24
- .set W_minus_28, W28
- .set W_minus_32, W
-.endm
-
-.macro W_PRECALC_ROTATE
- .set W_minus_32, W_minus_28
- .set W_minus_28, W_minus_24
- .set W_minus_24, W_minus_20
- .set W_minus_20, W_minus_16
- .set W_minus_16, W_minus_12
- .set W_minus_12, W_minus_08
- .set W_minus_08, W_minus_04
- .set W_minus_04, W
- .set W, W_minus_32
-.endm
-
-.macro W_PRECALC_SSSE3
-
-.macro W_PRECALC_00_15
- W_PRECALC_00_15_SSSE3
-.endm
-.macro W_PRECALC_16_31
- W_PRECALC_16_31_SSSE3
-.endm
-.macro W_PRECALC_32_79
- W_PRECALC_32_79_SSSE3
-.endm
-
-/* message scheduling pre-compute for rounds 0-15 */
-.macro W_PRECALC_00_15_SSSE3
- .if ((i & 3) == 0)
- movdqu (i*4)(BUFFER_PTR), W_TMP1
- .elseif ((i & 3) == 1)
- pshufb XMM_SHUFB_BSWAP, W_TMP1
- movdqa W_TMP1, W
- .elseif ((i & 3) == 2)
- paddd (K_BASE), W_TMP1
- .elseif ((i & 3) == 3)
- movdqa W_TMP1, WK(i&~3)
- W_PRECALC_ROTATE
- .endif
-.endm
-
-/* message scheduling pre-compute for rounds 16-31
- *
- * - calculating last 32 w[i] values in 8 XMM registers
- * - pre-calculate K+w[i] values and store to mem, for later load by ALU add
- * instruction
- *
- * some "heavy-lifting" vectorization for rounds 16-31 due to w[i]->w[i-3]
- * dependency, but improves for 32-79
- */
-.macro W_PRECALC_16_31_SSSE3
- # blended scheduling of vector and scalar instruction streams, one 4-wide
- # vector iteration / 4 scalar rounds
- .if ((i & 3) == 0)
- movdqa W_minus_12, W
- palignr $8, W_minus_16, W # w[i-14]
- movdqa W_minus_04, W_TMP1
- psrldq $4, W_TMP1 # w[i-3]
- pxor W_minus_08, W
- .elseif ((i & 3) == 1)
- pxor W_minus_16, W_TMP1
- pxor W_TMP1, W
- movdqa W, W_TMP2
- movdqa W, W_TMP1
- pslldq $12, W_TMP2
- .elseif ((i & 3) == 2)
- psrld $31, W
- pslld $1, W_TMP1
- por W, W_TMP1
- movdqa W_TMP2, W
- psrld $30, W_TMP2
- pslld $2, W
- .elseif ((i & 3) == 3)
- pxor W, W_TMP1
- pxor W_TMP2, W_TMP1
- movdqa W_TMP1, W
- paddd K_XMM(K_BASE), W_TMP1
- movdqa W_TMP1, WK(i&~3)
- W_PRECALC_ROTATE
- .endif
-.endm
-
-/* message scheduling pre-compute for rounds 32-79
- *
- * in SHA-1 specification: w[i] = (w[i-3] ^ w[i-8] ^ w[i-14] ^ w[i-16]) rol 1
- * instead we do equal: w[i] = (w[i-6] ^ w[i-16] ^ w[i-28] ^ w[i-32]) rol 2
- * allows more efficient vectorization since w[i]=>w[i-3] dependency is broken
- */
-.macro W_PRECALC_32_79_SSSE3
- .if ((i & 3) == 0)
- movdqa W_minus_04, W_TMP1
- pxor W_minus_28, W # W is W_minus_32 before xor
- palignr $8, W_minus_08, W_TMP1
- .elseif ((i & 3) == 1)
- pxor W_minus_16, W
- pxor W_TMP1, W
- movdqa W, W_TMP1
- .elseif ((i & 3) == 2)
- psrld $30, W
- pslld $2, W_TMP1
- por W, W_TMP1
- .elseif ((i & 3) == 3)
- movdqa W_TMP1, W
- paddd K_XMM(K_BASE), W_TMP1
- movdqa W_TMP1, WK(i&~3)
- W_PRECALC_ROTATE
- .endif
-.endm
-
-.endm // W_PRECALC_SSSE3
-
-
-#define K1 0x5a827999
-#define K2 0x6ed9eba1
-#define K3 0x8f1bbcdc
-#define K4 0xca62c1d6
-
-.section .rodata
-.align 16
-
-K_XMM_AR:
- .long K1, K1, K1, K1
- .long K2, K2, K2, K2
- .long K3, K3, K3, K3
- .long K4, K4, K4, K4
-
-BSWAP_SHUFB_CTL:
- .long 0x00010203
- .long 0x04050607
- .long 0x08090a0b
- .long 0x0c0d0e0f
-
-
-.section .text
-
-W_PRECALC_SSSE3
-.macro xmm_mov a, b
- movdqu \a,\b
-.endm
-
-/*
- * SSSE3 optimized implementation:
- *
- * extern "C" void sha1_transform_ssse3(struct sha1_state *state,
- * const u8 *data, int blocks);
- *
- * Note that struct sha1_state is assumed to begin with u32 state[5].
- */
-SHA1_VECTOR_ASM sha1_transform_ssse3
-
-.macro W_PRECALC_AVX
-
-.purgem W_PRECALC_00_15
-.macro W_PRECALC_00_15
- W_PRECALC_00_15_AVX
-.endm
-.purgem W_PRECALC_16_31
-.macro W_PRECALC_16_31
- W_PRECALC_16_31_AVX
-.endm
-.purgem W_PRECALC_32_79
-.macro W_PRECALC_32_79
- W_PRECALC_32_79_AVX
-.endm
-
-.macro W_PRECALC_00_15_AVX
- .if ((i & 3) == 0)
- vmovdqu (i*4)(BUFFER_PTR), W_TMP1
- .elseif ((i & 3) == 1)
- vpshufb XMM_SHUFB_BSWAP, W_TMP1, W
- .elseif ((i & 3) == 2)
- vpaddd (K_BASE), W, W_TMP1
- .elseif ((i & 3) == 3)
- vmovdqa W_TMP1, WK(i&~3)
- W_PRECALC_ROTATE
- .endif
-.endm
-
-.macro W_PRECALC_16_31_AVX
- .if ((i & 3) == 0)
- vpalignr $8, W_minus_16, W_minus_12, W # w[i-14]
- vpsrldq $4, W_minus_04, W_TMP1 # w[i-3]
- vpxor W_minus_08, W, W
- vpxor W_minus_16, W_TMP1, W_TMP1
- .elseif ((i & 3) == 1)
- vpxor W_TMP1, W, W
- vpslldq $12, W, W_TMP2
- vpslld $1, W, W_TMP1
- .elseif ((i & 3) == 2)
- vpsrld $31, W, W
- vpor W, W_TMP1, W_TMP1
- vpslld $2, W_TMP2, W
- vpsrld $30, W_TMP2, W_TMP2
- .elseif ((i & 3) == 3)
- vpxor W, W_TMP1, W_TMP1
- vpxor W_TMP2, W_TMP1, W
- vpaddd K_XMM(K_BASE), W, W_TMP1
- vmovdqu W_TMP1, WK(i&~3)
- W_PRECALC_ROTATE
- .endif
-.endm
-
-.macro W_PRECALC_32_79_AVX
- .if ((i & 3) == 0)
- vpalignr $8, W_minus_08, W_minus_04, W_TMP1
- vpxor W_minus_28, W, W # W is W_minus_32 before xor
- .elseif ((i & 3) == 1)
- vpxor W_minus_16, W_TMP1, W_TMP1
- vpxor W_TMP1, W, W
- .elseif ((i & 3) == 2)
- vpslld $2, W, W_TMP1
- vpsrld $30, W, W
- vpor W, W_TMP1, W
- .elseif ((i & 3) == 3)
- vpaddd K_XMM(K_BASE), W, W_TMP1
- vmovdqu W_TMP1, WK(i&~3)
- W_PRECALC_ROTATE
- .endif
-.endm
-
-.endm // W_PRECALC_AVX
-
-W_PRECALC_AVX
-.purgem xmm_mov
-.macro xmm_mov a, b
- vmovdqu \a,\b
-.endm
-
-
-/* AVX optimized implementation:
- * extern "C" void sha1_transform_avx(struct sha1_state *state,
- * const u8 *data, int blocks);
- */
-SHA1_VECTOR_ASM sha1_transform_avx
diff --git a/arch/x86/crypto/sha1_ssse3_glue.c b/arch/x86/crypto/sha1_ssse3_glue.c
deleted file mode 100644
index ab8bc54f254d..000000000000
--- a/arch/x86/crypto/sha1_ssse3_glue.c
+++ /dev/null
@@ -1,365 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Cryptographic API.
- *
- * Glue code for the SHA1 Secure Hash Algorithm assembler implementations
- * using SSSE3, AVX, AVX2, and SHA-NI instructions.
- *
- * This file is based on sha1_generic.c
- *
- * Copyright (c) Alan Smithee.
- * Copyright (c) Andrew McDonald <andrew@mcdonald.org.uk>
- * Copyright (c) Jean-Francois Dive <jef@linuxbe.org>
- * Copyright (c) Mathias Krause <minipli@googlemail.com>
- * Copyright (c) Chandramouli Narayanan <mouli@linux.intel.com>
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <crypto/sha1.h>
-#include <crypto/sha1_base.h>
-#include <asm/cpu_device_id.h>
-#include <asm/simd.h>
-
-static const struct x86_cpu_id module_cpu_ids[] = {
-#ifdef CONFIG_AS_SHA1_NI
- X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL),
-#endif
- X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
- X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL),
- X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL),
- {}
-};
-MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids);
-
-static int sha1_update(struct shash_desc *desc, const u8 *data,
- unsigned int len, sha1_block_fn *sha1_xform)
-{
- struct sha1_state *sctx = shash_desc_ctx(desc);
-
- if (!crypto_simd_usable() ||
- (sctx->count % SHA1_BLOCK_SIZE) + len < SHA1_BLOCK_SIZE)
- return crypto_sha1_update(desc, data, len);
-
- /*
- * Make sure struct sha1_state begins directly with the SHA1
- * 160-bit internal state, as this is what the asm functions expect.
- */
- BUILD_BUG_ON(offsetof(struct sha1_state, state) != 0);
-
- kernel_fpu_begin();
- sha1_base_do_update(desc, data, len, sha1_xform);
- kernel_fpu_end();
-
- return 0;
-}
-
-static int sha1_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out, sha1_block_fn *sha1_xform)
-{
- if (!crypto_simd_usable())
- return crypto_sha1_finup(desc, data, len, out);
-
- kernel_fpu_begin();
- if (len)
- sha1_base_do_update(desc, data, len, sha1_xform);
- sha1_base_do_finalize(desc, sha1_xform);
- kernel_fpu_end();
-
- return sha1_base_finish(desc, out);
-}
-
-asmlinkage void sha1_transform_ssse3(struct sha1_state *state,
- const u8 *data, int blocks);
-
-static int sha1_ssse3_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return sha1_update(desc, data, len, sha1_transform_ssse3);
-}
-
-static int sha1_ssse3_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha1_finup(desc, data, len, out, sha1_transform_ssse3);
-}
-
-/* Add padding and return the message digest. */
-static int sha1_ssse3_final(struct shash_desc *desc, u8 *out)
-{
- return sha1_ssse3_finup(desc, NULL, 0, out);
-}
-
-static struct shash_alg sha1_ssse3_alg = {
- .digestsize = SHA1_DIGEST_SIZE,
- .init = sha1_base_init,
- .update = sha1_ssse3_update,
- .final = sha1_ssse3_final,
- .finup = sha1_ssse3_finup,
- .descsize = sizeof(struct sha1_state),
- .base = {
- .cra_name = "sha1",
- .cra_driver_name = "sha1-ssse3",
- .cra_priority = 150,
- .cra_blocksize = SHA1_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-};
-
-static int register_sha1_ssse3(void)
-{
- if (boot_cpu_has(X86_FEATURE_SSSE3))
- return crypto_register_shash(&sha1_ssse3_alg);
- return 0;
-}
-
-static void unregister_sha1_ssse3(void)
-{
- if (boot_cpu_has(X86_FEATURE_SSSE3))
- crypto_unregister_shash(&sha1_ssse3_alg);
-}
-
-asmlinkage void sha1_transform_avx(struct sha1_state *state,
- const u8 *data, int blocks);
-
-static int sha1_avx_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return sha1_update(desc, data, len, sha1_transform_avx);
-}
-
-static int sha1_avx_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha1_finup(desc, data, len, out, sha1_transform_avx);
-}
-
-static int sha1_avx_final(struct shash_desc *desc, u8 *out)
-{
- return sha1_avx_finup(desc, NULL, 0, out);
-}
-
-static struct shash_alg sha1_avx_alg = {
- .digestsize = SHA1_DIGEST_SIZE,
- .init = sha1_base_init,
- .update = sha1_avx_update,
- .final = sha1_avx_final,
- .finup = sha1_avx_finup,
- .descsize = sizeof(struct sha1_state),
- .base = {
- .cra_name = "sha1",
- .cra_driver_name = "sha1-avx",
- .cra_priority = 160,
- .cra_blocksize = SHA1_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-};
-
-static bool avx_usable(void)
-{
- if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
- if (boot_cpu_has(X86_FEATURE_AVX))
- pr_info("AVX detected but unusable.\n");
- return false;
- }
-
- return true;
-}
-
-static int register_sha1_avx(void)
-{
- if (avx_usable())
- return crypto_register_shash(&sha1_avx_alg);
- return 0;
-}
-
-static void unregister_sha1_avx(void)
-{
- if (avx_usable())
- crypto_unregister_shash(&sha1_avx_alg);
-}
-
-#define SHA1_AVX2_BLOCK_OPTSIZE 4 /* optimal 4*64 bytes of SHA1 blocks */
-
-asmlinkage void sha1_transform_avx2(struct sha1_state *state,
- const u8 *data, int blocks);
-
-static bool avx2_usable(void)
-{
- if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2)
- && boot_cpu_has(X86_FEATURE_BMI1)
- && boot_cpu_has(X86_FEATURE_BMI2))
- return true;
-
- return false;
-}
-
-static void sha1_apply_transform_avx2(struct sha1_state *state,
- const u8 *data, int blocks)
-{
- /* Select the optimal transform based on data block size */
- if (blocks >= SHA1_AVX2_BLOCK_OPTSIZE)
- sha1_transform_avx2(state, data, blocks);
- else
- sha1_transform_avx(state, data, blocks);
-}
-
-static int sha1_avx2_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return sha1_update(desc, data, len, sha1_apply_transform_avx2);
-}
-
-static int sha1_avx2_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha1_finup(desc, data, len, out, sha1_apply_transform_avx2);
-}
-
-static int sha1_avx2_final(struct shash_desc *desc, u8 *out)
-{
- return sha1_avx2_finup(desc, NULL, 0, out);
-}
-
-static struct shash_alg sha1_avx2_alg = {
- .digestsize = SHA1_DIGEST_SIZE,
- .init = sha1_base_init,
- .update = sha1_avx2_update,
- .final = sha1_avx2_final,
- .finup = sha1_avx2_finup,
- .descsize = sizeof(struct sha1_state),
- .base = {
- .cra_name = "sha1",
- .cra_driver_name = "sha1-avx2",
- .cra_priority = 170,
- .cra_blocksize = SHA1_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-};
-
-static int register_sha1_avx2(void)
-{
- if (avx2_usable())
- return crypto_register_shash(&sha1_avx2_alg);
- return 0;
-}
-
-static void unregister_sha1_avx2(void)
-{
- if (avx2_usable())
- crypto_unregister_shash(&sha1_avx2_alg);
-}
-
-#ifdef CONFIG_AS_SHA1_NI
-asmlinkage void sha1_ni_transform(struct sha1_state *digest, const u8 *data,
- int rounds);
-
-static int sha1_ni_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return sha1_update(desc, data, len, sha1_ni_transform);
-}
-
-static int sha1_ni_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha1_finup(desc, data, len, out, sha1_ni_transform);
-}
-
-static int sha1_ni_final(struct shash_desc *desc, u8 *out)
-{
- return sha1_ni_finup(desc, NULL, 0, out);
-}
-
-static struct shash_alg sha1_ni_alg = {
- .digestsize = SHA1_DIGEST_SIZE,
- .init = sha1_base_init,
- .update = sha1_ni_update,
- .final = sha1_ni_final,
- .finup = sha1_ni_finup,
- .descsize = sizeof(struct sha1_state),
- .base = {
- .cra_name = "sha1",
- .cra_driver_name = "sha1-ni",
- .cra_priority = 250,
- .cra_blocksize = SHA1_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-};
-
-static int register_sha1_ni(void)
-{
- if (boot_cpu_has(X86_FEATURE_SHA_NI))
- return crypto_register_shash(&sha1_ni_alg);
- return 0;
-}
-
-static void unregister_sha1_ni(void)
-{
- if (boot_cpu_has(X86_FEATURE_SHA_NI))
- crypto_unregister_shash(&sha1_ni_alg);
-}
-
-#else
-static inline int register_sha1_ni(void) { return 0; }
-static inline void unregister_sha1_ni(void) { }
-#endif
-
-static int __init sha1_ssse3_mod_init(void)
-{
- if (!x86_match_cpu(module_cpu_ids))
- return -ENODEV;
-
- if (register_sha1_ssse3())
- goto fail;
-
- if (register_sha1_avx()) {
- unregister_sha1_ssse3();
- goto fail;
- }
-
- if (register_sha1_avx2()) {
- unregister_sha1_avx();
- unregister_sha1_ssse3();
- goto fail;
- }
-
- if (register_sha1_ni()) {
- unregister_sha1_avx2();
- unregister_sha1_avx();
- unregister_sha1_ssse3();
- goto fail;
- }
-
- return 0;
-fail:
- return -ENODEV;
-}
-
-static void __exit sha1_ssse3_mod_fini(void)
-{
- unregister_sha1_ni();
- unregister_sha1_avx2();
- unregister_sha1_avx();
- unregister_sha1_ssse3();
-}
-
-module_init(sha1_ssse3_mod_init);
-module_exit(sha1_ssse3_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA1 Secure Hash Algorithm, Supplemental SSE3 accelerated");
-
-MODULE_ALIAS_CRYPTO("sha1");
-MODULE_ALIAS_CRYPTO("sha1-ssse3");
-MODULE_ALIAS_CRYPTO("sha1-avx");
-MODULE_ALIAS_CRYPTO("sha1-avx2");
-#ifdef CONFIG_AS_SHA1_NI
-MODULE_ALIAS_CRYPTO("sha1-ni");
-#endif
diff --git a/arch/x86/crypto/sha256-avx-asm.S b/arch/x86/crypto/sha256-avx-asm.S
deleted file mode 100644
index 53de72bdd851..000000000000
--- a/arch/x86/crypto/sha256-avx-asm.S
+++ /dev/null
@@ -1,499 +0,0 @@
-########################################################################
-# Implement fast SHA-256 with AVX1 instructions. (x86_64)
-#
-# Copyright (C) 2013 Intel Corporation.
-#
-# Authors:
-# James Guilford <james.guilford@intel.com>
-# Kirk Yap <kirk.s.yap@intel.com>
-# Tim Chen <tim.c.chen@linux.intel.com>
-#
-# This software is available to you under a choice of one of two
-# licenses. You may choose to be licensed under the terms of the GNU
-# General Public License (GPL) Version 2, available from the file
-# COPYING in the main directory of this source tree, or the
-# OpenIB.org BSD license below:
-#
-# Redistribution and use in source and binary forms, with or
-# without modification, are permitted provided that the following
-# conditions are met:
-#
-# - Redistributions of source code must retain the above
-# copyright notice, this list of conditions and the following
-# disclaimer.
-#
-# - Redistributions in binary form must reproduce the above
-# copyright notice, this list of conditions and the following
-# disclaimer in the documentation and/or other materials
-# provided with the distribution.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-########################################################################
-#
-# This code is described in an Intel White-Paper:
-# "Fast SHA-256 Implementations on Intel Architecture Processors"
-#
-# To find it, surf to http://www.intel.com/p/en_US/embedded
-# and search for that title.
-#
-########################################################################
-# This code schedules 1 block at a time, with 4 lanes per block
-########################################################################
-
-#include <linux/linkage.h>
-#include <linux/cfi_types.h>
-
-## assume buffers not aligned
-#define VMOVDQ vmovdqu
-
-################################ Define Macros
-
-# addm [mem], reg
-# Add reg to mem using reg-mem add and store
-.macro addm p1 p2
- add \p1, \p2
- mov \p2, \p1
-.endm
-
-
-.macro MY_ROR p1 p2
- shld $(32-(\p1)), \p2, \p2
-.endm
-
-################################
-
-# COPY_XMM_AND_BSWAP xmm, [mem], byte_flip_mask
-# Load xmm with mem and byte swap each dword
-.macro COPY_XMM_AND_BSWAP p1 p2 p3
- VMOVDQ \p2, \p1
- vpshufb \p3, \p1, \p1
-.endm
-
-################################
-
-X0 = %xmm4
-X1 = %xmm5
-X2 = %xmm6
-X3 = %xmm7
-
-XTMP0 = %xmm0
-XTMP1 = %xmm1
-XTMP2 = %xmm2
-XTMP3 = %xmm3
-XTMP4 = %xmm8
-XFER = %xmm9
-XTMP5 = %xmm11
-
-SHUF_00BA = %xmm10 # shuffle xBxA -> 00BA
-SHUF_DC00 = %xmm12 # shuffle xDxC -> DC00
-BYTE_FLIP_MASK = %xmm13
-
-NUM_BLKS = %rdx # 3rd arg
-INP = %rsi # 2nd arg
-CTX = %rdi # 1st arg
-
-SRND = %rsi # clobbers INP
-c = %ecx
-d = %r8d
-e = %edx
-TBL = %r12
-a = %eax
-b = %ebx
-
-f = %r9d
-g = %r10d
-h = %r11d
-
-y0 = %r13d
-y1 = %r14d
-y2 = %r15d
-
-
-_INP_END_SIZE = 8
-_INP_SIZE = 8
-_XFER_SIZE = 16
-_XMM_SAVE_SIZE = 0
-
-_INP_END = 0
-_INP = _INP_END + _INP_END_SIZE
-_XFER = _INP + _INP_SIZE
-_XMM_SAVE = _XFER + _XFER_SIZE
-STACK_SIZE = _XMM_SAVE + _XMM_SAVE_SIZE
-
-# rotate_Xs
-# Rotate values of symbols X0...X3
-.macro rotate_Xs
-X_ = X0
-X0 = X1
-X1 = X2
-X2 = X3
-X3 = X_
-.endm
-
-# ROTATE_ARGS
-# Rotate values of symbols a...h
-.macro ROTATE_ARGS
-TMP_ = h
-h = g
-g = f
-f = e
-e = d
-d = c
-c = b
-b = a
-a = TMP_
-.endm
-
-.macro FOUR_ROUNDS_AND_SCHED
- ## compute s0 four at a time and s1 two at a time
- ## compute W[-16] + W[-7] 4 at a time
-
- mov e, y0 # y0 = e
- MY_ROR (25-11), y0 # y0 = e >> (25-11)
- mov a, y1 # y1 = a
- vpalignr $4, X2, X3, XTMP0 # XTMP0 = W[-7]
- MY_ROR (22-13), y1 # y1 = a >> (22-13)
- xor e, y0 # y0 = e ^ (e >> (25-11))
- mov f, y2 # y2 = f
- MY_ROR (11-6), y0 # y0 = (e >> (11-6)) ^ (e >> (25-6))
- xor a, y1 # y1 = a ^ (a >> (22-13)
- xor g, y2 # y2 = f^g
- vpaddd X0, XTMP0, XTMP0 # XTMP0 = W[-7] + W[-16]
- xor e, y0 # y0 = e ^ (e >> (11-6)) ^ (e >> (25-6))
- and e, y2 # y2 = (f^g)&e
- MY_ROR (13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
- ## compute s0
- vpalignr $4, X0, X1, XTMP1 # XTMP1 = W[-15]
- xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
- MY_ROR 6, y0 # y0 = S1 = (e>>6) & (e>>11) ^ (e>>25)
- xor g, y2 # y2 = CH = ((f^g)&e)^g
- MY_ROR 2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
- add y0, y2 # y2 = S1 + CH
- add _XFER(%rsp), y2 # y2 = k + w + S1 + CH
- mov a, y0 # y0 = a
- add y2, h # h = h + S1 + CH + k + w
- mov a, y2 # y2 = a
- vpsrld $7, XTMP1, XTMP2
- or c, y0 # y0 = a|c
- add h, d # d = d + h + S1 + CH + k + w
- and c, y2 # y2 = a&c
- vpslld $(32-7), XTMP1, XTMP3
- and b, y0 # y0 = (a|c)&b
- add y1, h # h = h + S1 + CH + k + w + S0
- vpor XTMP2, XTMP3, XTMP3 # XTMP1 = W[-15] MY_ROR 7
- or y2, y0 # y0 = MAJ = (a|c)&b)|(a&c)
- add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
- ROTATE_ARGS
- mov e, y0 # y0 = e
- mov a, y1 # y1 = a
- MY_ROR (25-11), y0 # y0 = e >> (25-11)
- xor e, y0 # y0 = e ^ (e >> (25-11))
- mov f, y2 # y2 = f
- MY_ROR (22-13), y1 # y1 = a >> (22-13)
- vpsrld $18, XTMP1, XTMP2 #
- xor a, y1 # y1 = a ^ (a >> (22-13)
- MY_ROR (11-6), y0 # y0 = (e >> (11-6)) ^ (e >> (25-6))
- xor g, y2 # y2 = f^g
- vpsrld $3, XTMP1, XTMP4 # XTMP4 = W[-15] >> 3
- MY_ROR (13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
- xor e, y0 # y0 = e ^ (e >> (11-6)) ^ (e >> (25-6))
- and e, y2 # y2 = (f^g)&e
- MY_ROR 6, y0 # y0 = S1 = (e>>6) & (e>>11) ^ (e>>25)
- vpslld $(32-18), XTMP1, XTMP1
- xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
- xor g, y2 # y2 = CH = ((f^g)&e)^g
- vpxor XTMP1, XTMP3, XTMP3 #
- add y0, y2 # y2 = S1 + CH
- add (1*4 + _XFER)(%rsp), y2 # y2 = k + w + S1 + CH
- MY_ROR 2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
- vpxor XTMP2, XTMP3, XTMP3 # XTMP1 = W[-15] MY_ROR 7 ^ W[-15] MY_ROR
- mov a, y0 # y0 = a
- add y2, h # h = h + S1 + CH + k + w
- mov a, y2 # y2 = a
- vpxor XTMP4, XTMP3, XTMP1 # XTMP1 = s0
- or c, y0 # y0 = a|c
- add h, d # d = d + h + S1 + CH + k + w
- and c, y2 # y2 = a&c
- ## compute low s1
- vpshufd $0b11111010, X3, XTMP2 # XTMP2 = W[-2] {BBAA}
- and b, y0 # y0 = (a|c)&b
- add y1, h # h = h + S1 + CH + k + w + S0
- vpaddd XTMP1, XTMP0, XTMP0 # XTMP0 = W[-16] + W[-7] + s0
- or y2, y0 # y0 = MAJ = (a|c)&b)|(a&c)
- add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
- ROTATE_ARGS
- mov e, y0 # y0 = e
- mov a, y1 # y1 = a
- MY_ROR (25-11), y0 # y0 = e >> (25-11)
- xor e, y0 # y0 = e ^ (e >> (25-11))
- MY_ROR (22-13), y1 # y1 = a >> (22-13)
- mov f, y2 # y2 = f
- xor a, y1 # y1 = a ^ (a >> (22-13)
- MY_ROR (11-6), y0 # y0 = (e >> (11-6)) ^ (e >> (25-6))
- vpsrld $10, XTMP2, XTMP4 # XTMP4 = W[-2] >> 10 {BBAA}
- xor g, y2 # y2 = f^g
- vpsrlq $19, XTMP2, XTMP3 # XTMP3 = W[-2] MY_ROR 19 {xBxA}
- xor e, y0 # y0 = e ^ (e >> (11-6)) ^ (e >> (25-6))
- and e, y2 # y2 = (f^g)&e
- vpsrlq $17, XTMP2, XTMP2 # XTMP2 = W[-2] MY_ROR 17 {xBxA}
- MY_ROR (13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
- xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
- xor g, y2 # y2 = CH = ((f^g)&e)^g
- MY_ROR 6, y0 # y0 = S1 = (e>>6) & (e>>11) ^ (e>>25)
- vpxor XTMP3, XTMP2, XTMP2 #
- add y0, y2 # y2 = S1 + CH
- MY_ROR 2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
- add (2*4 + _XFER)(%rsp), y2 # y2 = k + w + S1 + CH
- vpxor XTMP2, XTMP4, XTMP4 # XTMP4 = s1 {xBxA}
- mov a, y0 # y0 = a
- add y2, h # h = h + S1 + CH + k + w
- mov a, y2 # y2 = a
- vpshufb SHUF_00BA, XTMP4, XTMP4 # XTMP4 = s1 {00BA}
- or c, y0 # y0 = a|c
- add h, d # d = d + h + S1 + CH + k + w
- and c, y2 # y2 = a&c
- vpaddd XTMP4, XTMP0, XTMP0 # XTMP0 = {..., ..., W[1], W[0]}
- and b, y0 # y0 = (a|c)&b
- add y1, h # h = h + S1 + CH + k + w + S0
- ## compute high s1
- vpshufd $0b01010000, XTMP0, XTMP2 # XTMP2 = W[-2] {DDCC}
- or y2, y0 # y0 = MAJ = (a|c)&b)|(a&c)
- add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
- ROTATE_ARGS
- mov e, y0 # y0 = e
- MY_ROR (25-11), y0 # y0 = e >> (25-11)
- mov a, y1 # y1 = a
- MY_ROR (22-13), y1 # y1 = a >> (22-13)
- xor e, y0 # y0 = e ^ (e >> (25-11))
- mov f, y2 # y2 = f
- MY_ROR (11-6), y0 # y0 = (e >> (11-6)) ^ (e >> (25-6))
- vpsrld $10, XTMP2, XTMP5 # XTMP5 = W[-2] >> 10 {DDCC}
- xor a, y1 # y1 = a ^ (a >> (22-13)
- xor g, y2 # y2 = f^g
- vpsrlq $19, XTMP2, XTMP3 # XTMP3 = W[-2] MY_ROR 19 {xDxC}
- xor e, y0 # y0 = e ^ (e >> (11-6)) ^ (e >> (25-6))
- and e, y2 # y2 = (f^g)&e
- MY_ROR (13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
- vpsrlq $17, XTMP2, XTMP2 # XTMP2 = W[-2] MY_ROR 17 {xDxC}
- xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
- MY_ROR 6, y0 # y0 = S1 = (e>>6) & (e>>11) ^ (e>>25)
- xor g, y2 # y2 = CH = ((f^g)&e)^g
- vpxor XTMP3, XTMP2, XTMP2
- MY_ROR 2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
- add y0, y2 # y2 = S1 + CH
- add (3*4 + _XFER)(%rsp), y2 # y2 = k + w + S1 + CH
- vpxor XTMP2, XTMP5, XTMP5 # XTMP5 = s1 {xDxC}
- mov a, y0 # y0 = a
- add y2, h # h = h + S1 + CH + k + w
- mov a, y2 # y2 = a
- vpshufb SHUF_DC00, XTMP5, XTMP5 # XTMP5 = s1 {DC00}
- or c, y0 # y0 = a|c
- add h, d # d = d + h + S1 + CH + k + w
- and c, y2 # y2 = a&c
- vpaddd XTMP0, XTMP5, X0 # X0 = {W[3], W[2], W[1], W[0]}
- and b, y0 # y0 = (a|c)&b
- add y1, h # h = h + S1 + CH + k + w + S0
- or y2, y0 # y0 = MAJ = (a|c)&b)|(a&c)
- add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
- ROTATE_ARGS
- rotate_Xs
-.endm
-
-## input is [rsp + _XFER + %1 * 4]
-.macro DO_ROUND round
- mov e, y0 # y0 = e
- MY_ROR (25-11), y0 # y0 = e >> (25-11)
- mov a, y1 # y1 = a
- xor e, y0 # y0 = e ^ (e >> (25-11))
- MY_ROR (22-13), y1 # y1 = a >> (22-13)
- mov f, y2 # y2 = f
- xor a, y1 # y1 = a ^ (a >> (22-13)
- MY_ROR (11-6), y0 # y0 = (e >> (11-6)) ^ (e >> (25-6))
- xor g, y2 # y2 = f^g
- xor e, y0 # y0 = e ^ (e >> (11-6)) ^ (e >> (25-6))
- MY_ROR (13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
- and e, y2 # y2 = (f^g)&e
- xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
- MY_ROR 6, y0 # y0 = S1 = (e>>6) & (e>>11) ^ (e>>25)
- xor g, y2 # y2 = CH = ((f^g)&e)^g
- add y0, y2 # y2 = S1 + CH
- MY_ROR 2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
- offset = \round * 4 + _XFER #
- add offset(%rsp), y2 # y2 = k + w + S1 + CH
- mov a, y0 # y0 = a
- add y2, h # h = h + S1 + CH + k + w
- mov a, y2 # y2 = a
- or c, y0 # y0 = a|c
- add h, d # d = d + h + S1 + CH + k + w
- and c, y2 # y2 = a&c
- and b, y0 # y0 = (a|c)&b
- add y1, h # h = h + S1 + CH + k + w + S0
- or y2, y0 # y0 = MAJ = (a|c)&b)|(a&c)
- add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
- ROTATE_ARGS
-.endm
-
-########################################################################
-## void sha256_transform_avx(state sha256_state *state, const u8 *data, int blocks)
-## arg 1 : pointer to state
-## arg 2 : pointer to input data
-## arg 3 : Num blocks
-########################################################################
-.text
-SYM_TYPED_FUNC_START(sha256_transform_avx)
- pushq %rbx
- pushq %r12
- pushq %r13
- pushq %r14
- pushq %r15
- pushq %rbp
- movq %rsp, %rbp
-
- subq $STACK_SIZE, %rsp # allocate stack space
- and $~15, %rsp # align stack pointer
-
- shl $6, NUM_BLKS # convert to bytes
- jz .Ldone_hash
- add INP, NUM_BLKS # pointer to end of data
- mov NUM_BLKS, _INP_END(%rsp)
-
- ## load initial digest
- mov 4*0(CTX), a
- mov 4*1(CTX), b
- mov 4*2(CTX), c
- mov 4*3(CTX), d
- mov 4*4(CTX), e
- mov 4*5(CTX), f
- mov 4*6(CTX), g
- mov 4*7(CTX), h
-
- vmovdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK
- vmovdqa _SHUF_00BA(%rip), SHUF_00BA
- vmovdqa _SHUF_DC00(%rip), SHUF_DC00
-.Lloop0:
- lea K256(%rip), TBL
-
- ## byte swap first 16 dwords
- COPY_XMM_AND_BSWAP X0, 0*16(INP), BYTE_FLIP_MASK
- COPY_XMM_AND_BSWAP X1, 1*16(INP), BYTE_FLIP_MASK
- COPY_XMM_AND_BSWAP X2, 2*16(INP), BYTE_FLIP_MASK
- COPY_XMM_AND_BSWAP X3, 3*16(INP), BYTE_FLIP_MASK
-
- mov INP, _INP(%rsp)
-
- ## schedule 48 input dwords, by doing 3 rounds of 16 each
- mov $3, SRND
-.align 16
-.Lloop1:
- vpaddd (TBL), X0, XFER
- vmovdqa XFER, _XFER(%rsp)
- FOUR_ROUNDS_AND_SCHED
-
- vpaddd 1*16(TBL), X0, XFER
- vmovdqa XFER, _XFER(%rsp)
- FOUR_ROUNDS_AND_SCHED
-
- vpaddd 2*16(TBL), X0, XFER
- vmovdqa XFER, _XFER(%rsp)
- FOUR_ROUNDS_AND_SCHED
-
- vpaddd 3*16(TBL), X0, XFER
- vmovdqa XFER, _XFER(%rsp)
- add $4*16, TBL
- FOUR_ROUNDS_AND_SCHED
-
- sub $1, SRND
- jne .Lloop1
-
- mov $2, SRND
-.Lloop2:
- vpaddd (TBL), X0, XFER
- vmovdqa XFER, _XFER(%rsp)
- DO_ROUND 0
- DO_ROUND 1
- DO_ROUND 2
- DO_ROUND 3
-
- vpaddd 1*16(TBL), X1, XFER
- vmovdqa XFER, _XFER(%rsp)
- add $2*16, TBL
- DO_ROUND 0
- DO_ROUND 1
- DO_ROUND 2
- DO_ROUND 3
-
- vmovdqa X2, X0
- vmovdqa X3, X1
-
- sub $1, SRND
- jne .Lloop2
-
- addm (4*0)(CTX),a
- addm (4*1)(CTX),b
- addm (4*2)(CTX),c
- addm (4*3)(CTX),d
- addm (4*4)(CTX),e
- addm (4*5)(CTX),f
- addm (4*6)(CTX),g
- addm (4*7)(CTX),h
-
- mov _INP(%rsp), INP
- add $64, INP
- cmp _INP_END(%rsp), INP
- jne .Lloop0
-
-.Ldone_hash:
-
- mov %rbp, %rsp
- popq %rbp
- popq %r15
- popq %r14
- popq %r13
- popq %r12
- popq %rbx
- RET
-SYM_FUNC_END(sha256_transform_avx)
-
-.section .rodata.cst256.K256, "aM", @progbits, 256
-.align 64
-K256:
- .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
- .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
- .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
- .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
- .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
- .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
- .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
- .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
- .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
- .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
- .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
- .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
- .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
- .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
- .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
- .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
-
-.section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16
-.align 16
-PSHUFFLE_BYTE_FLIP_MASK:
- .octa 0x0c0d0e0f08090a0b0405060700010203
-
-.section .rodata.cst16._SHUF_00BA, "aM", @progbits, 16
-.align 16
-# shuffle xBxA -> 00BA
-_SHUF_00BA:
- .octa 0xFFFFFFFFFFFFFFFF0b0a090803020100
-
-.section .rodata.cst16._SHUF_DC00, "aM", @progbits, 16
-.align 16
-# shuffle xDxC -> DC00
-_SHUF_DC00:
- .octa 0x0b0a090803020100FFFFFFFFFFFFFFFF
diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S
deleted file mode 100644
index 0bbec1c75cd0..000000000000
--- a/arch/x86/crypto/sha256-avx2-asm.S
+++ /dev/null
@@ -1,774 +0,0 @@
-########################################################################
-# Implement fast SHA-256 with AVX2 instructions. (x86_64)
-#
-# Copyright (C) 2013 Intel Corporation.
-#
-# Authors:
-# James Guilford <james.guilford@intel.com>
-# Kirk Yap <kirk.s.yap@intel.com>
-# Tim Chen <tim.c.chen@linux.intel.com>
-#
-# This software is available to you under a choice of one of two
-# licenses. You may choose to be licensed under the terms of the GNU
-# General Public License (GPL) Version 2, available from the file
-# COPYING in the main directory of this source tree, or the
-# OpenIB.org BSD license below:
-#
-# Redistribution and use in source and binary forms, with or
-# without modification, are permitted provided that the following
-# conditions are met:
-#
-# - Redistributions of source code must retain the above
-# copyright notice, this list of conditions and the following
-# disclaimer.
-#
-# - Redistributions in binary form must reproduce the above
-# copyright notice, this list of conditions and the following
-# disclaimer in the documentation and/or other materials
-# provided with the distribution.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-#
-########################################################################
-#
-# This code is described in an Intel White-Paper:
-# "Fast SHA-256 Implementations on Intel Architecture Processors"
-#
-# To find it, surf to http://www.intel.com/p/en_US/embedded
-# and search for that title.
-#
-########################################################################
-# This code schedules 2 blocks at a time, with 4 lanes per block
-########################################################################
-
-#include <linux/linkage.h>
-#include <linux/cfi_types.h>
-
-## assume buffers not aligned
-#define VMOVDQ vmovdqu
-
-################################ Define Macros
-
-# addm [mem], reg
-# Add reg to mem using reg-mem add and store
-.macro addm p1 p2
- add \p1, \p2
- mov \p2, \p1
-.endm
-
-################################
-
-X0 = %ymm4
-X1 = %ymm5
-X2 = %ymm6
-X3 = %ymm7
-
-# XMM versions of above
-XWORD0 = %xmm4
-XWORD1 = %xmm5
-XWORD2 = %xmm6
-XWORD3 = %xmm7
-
-XTMP0 = %ymm0
-XTMP1 = %ymm1
-XTMP2 = %ymm2
-XTMP3 = %ymm3
-XTMP4 = %ymm8
-XFER = %ymm9
-XTMP5 = %ymm11
-
-SHUF_00BA = %ymm10 # shuffle xBxA -> 00BA
-SHUF_DC00 = %ymm12 # shuffle xDxC -> DC00
-BYTE_FLIP_MASK = %ymm13
-
-X_BYTE_FLIP_MASK = %xmm13 # XMM version of BYTE_FLIP_MASK
-
-NUM_BLKS = %rdx # 3rd arg
-INP = %rsi # 2nd arg
-CTX = %rdi # 1st arg
-c = %ecx
-d = %r8d
-e = %edx # clobbers NUM_BLKS
-y3 = %esi # clobbers INP
-
-SRND = CTX # SRND is same register as CTX
-
-a = %eax
-b = %ebx
-f = %r9d
-g = %r10d
-h = %r11d
-old_h = %r11d
-
-T1 = %r12d
-y0 = %r13d
-y1 = %r14d
-y2 = %r15d
-
-
-_XFER_SIZE = 2*64*4 # 2 blocks, 64 rounds, 4 bytes/round
-_XMM_SAVE_SIZE = 0
-_INP_END_SIZE = 8
-_INP_SIZE = 8
-_CTX_SIZE = 8
-
-_XFER = 0
-_XMM_SAVE = _XFER + _XFER_SIZE
-_INP_END = _XMM_SAVE + _XMM_SAVE_SIZE
-_INP = _INP_END + _INP_END_SIZE
-_CTX = _INP + _INP_SIZE
-STACK_SIZE = _CTX + _CTX_SIZE
-
-# rotate_Xs
-# Rotate values of symbols X0...X3
-.macro rotate_Xs
- X_ = X0
- X0 = X1
- X1 = X2
- X2 = X3
- X3 = X_
-.endm
-
-# ROTATE_ARGS
-# Rotate values of symbols a...h
-.macro ROTATE_ARGS
- old_h = h
- TMP_ = h
- h = g
- g = f
- f = e
- e = d
- d = c
- c = b
- b = a
- a = TMP_
-.endm
-
-.macro FOUR_ROUNDS_AND_SCHED disp
-################################### RND N + 0 ############################
-
- mov a, y3 # y3 = a # MAJA
- rorx $25, e, y0 # y0 = e >> 25 # S1A
- rorx $11, e, y1 # y1 = e >> 11 # S1B
-
- addl \disp(%rsp, SRND), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
- vpalignr $4, X2, X3, XTMP0 # XTMP0 = W[-7]
- mov f, y2 # y2 = f # CH
- rorx $13, a, T1 # T1 = a >> 13 # S0B
-
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
- xor g, y2 # y2 = f^g # CH
- vpaddd X0, XTMP0, XTMP0 # XTMP0 = W[-7] + W[-16]# y1 = (e >> 6)# S1
- rorx $6, e, y1 # y1 = (e >> 6) # S1
-
- and e, y2 # y2 = (f^g)&e # CH
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
- rorx $22, a, y1 # y1 = a >> 22 # S0A
- add h, d # d = k + w + h + d # --
-
- and b, y3 # y3 = (a|c)&b # MAJA
- vpalignr $4, X0, X1, XTMP1 # XTMP1 = W[-15]
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) # S0
- rorx $2, a, T1 # T1 = (a >> 2) # S0
-
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
- vpsrld $7, XTMP1, XTMP2
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
- mov a, T1 # T1 = a # MAJB
- and c, T1 # T1 = a&c # MAJB
-
- add y0, y2 # y2 = S1 + CH # --
- vpslld $(32-7), XTMP1, XTMP3
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
-
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
- vpor XTMP2, XTMP3, XTMP3 # XTMP3 = W[-15] ror 7
-
- vpsrld $18, XTMP1, XTMP2
- add y2, h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- add y3, h # h = t1 + S0 + MAJ # --
-
-
- ROTATE_ARGS
-
-################################### RND N + 1 ############################
-
- mov a, y3 # y3 = a # MAJA
- rorx $25, e, y0 # y0 = e >> 25 # S1A
- rorx $11, e, y1 # y1 = e >> 11 # S1B
- offset = \disp + 1*4
- addl offset(%rsp, SRND), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
-
- vpsrld $3, XTMP1, XTMP4 # XTMP4 = W[-15] >> 3
- mov f, y2 # y2 = f # CH
- rorx $13, a, T1 # T1 = a >> 13 # S0B
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
- xor g, y2 # y2 = f^g # CH
-
-
- rorx $6, e, y1 # y1 = (e >> 6) # S1
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
- rorx $22, a, y1 # y1 = a >> 22 # S0A
- and e, y2 # y2 = (f^g)&e # CH
- add h, d # d = k + w + h + d # --
-
- vpslld $(32-18), XTMP1, XTMP1
- and b, y3 # y3 = (a|c)&b # MAJA
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) # S0
-
- vpxor XTMP1, XTMP3, XTMP3
- rorx $2, a, T1 # T1 = (a >> 2) # S0
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
-
- vpxor XTMP2, XTMP3, XTMP3 # XTMP3 = W[-15] ror 7 ^ W[-15] ror 18
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
- mov a, T1 # T1 = a # MAJB
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
-
- vpxor XTMP4, XTMP3, XTMP1 # XTMP1 = s0
- vpshufd $0b11111010, X3, XTMP2 # XTMP2 = W[-2] {BBAA}
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
-
- vpaddd XTMP1, XTMP0, XTMP0 # XTMP0 = W[-16] + W[-7] + s0
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
- add y2, h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- add y3, h # h = t1 + S0 + MAJ # --
-
- vpsrld $10, XTMP2, XTMP4 # XTMP4 = W[-2] >> 10 {BBAA}
-
-
- ROTATE_ARGS
-
-################################### RND N + 2 ############################
-
- mov a, y3 # y3 = a # MAJA
- rorx $25, e, y0 # y0 = e >> 25 # S1A
- offset = \disp + 2*4
- addl offset(%rsp, SRND), h # h = k + w + h # --
-
- vpsrlq $19, XTMP2, XTMP3 # XTMP3 = W[-2] ror 19 {xBxA}
- rorx $11, e, y1 # y1 = e >> 11 # S1B
- or c, y3 # y3 = a|c # MAJA
- mov f, y2 # y2 = f # CH
- xor g, y2 # y2 = f^g # CH
-
- rorx $13, a, T1 # T1 = a >> 13 # S0B
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
- vpsrlq $17, XTMP2, XTMP2 # XTMP2 = W[-2] ror 17 {xBxA}
- and e, y2 # y2 = (f^g)&e # CH
-
- rorx $6, e, y1 # y1 = (e >> 6) # S1
- vpxor XTMP3, XTMP2, XTMP2
- add h, d # d = k + w + h + d # --
- and b, y3 # y3 = (a|c)&b # MAJA
-
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
- rorx $22, a, y1 # y1 = a >> 22 # S0A
- vpxor XTMP2, XTMP4, XTMP4 # XTMP4 = s1 {xBxA}
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
-
- vpshufb SHUF_00BA, XTMP4, XTMP4 # XTMP4 = s1 {00BA}
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) # S0
- rorx $2, a ,T1 # T1 = (a >> 2) # S0
- vpaddd XTMP4, XTMP0, XTMP0 # XTMP0 = {..., ..., W[1], W[0]}
-
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
- mov a, T1 # T1 = a # MAJB
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
- vpshufd $0b01010000, XTMP0, XTMP2 # XTMP2 = W[-2] {DDCC}
-
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1,h # h = k + w + h + S0 # --
- add y2,d # d = k + w + h + d + S1 + CH = d + t1 # --
- add y2,h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
-
- add y3,h # h = t1 + S0 + MAJ # --
-
-
- ROTATE_ARGS
-
-################################### RND N + 3 ############################
-
- mov a, y3 # y3 = a # MAJA
- rorx $25, e, y0 # y0 = e >> 25 # S1A
- rorx $11, e, y1 # y1 = e >> 11 # S1B
- offset = \disp + 3*4
- addl offset(%rsp, SRND), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
-
- vpsrld $10, XTMP2, XTMP5 # XTMP5 = W[-2] >> 10 {DDCC}
- mov f, y2 # y2 = f # CH
- rorx $13, a, T1 # T1 = a >> 13 # S0B
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
- xor g, y2 # y2 = f^g # CH
-
-
- vpsrlq $19, XTMP2, XTMP3 # XTMP3 = W[-2] ror 19 {xDxC}
- rorx $6, e, y1 # y1 = (e >> 6) # S1
- and e, y2 # y2 = (f^g)&e # CH
- add h, d # d = k + w + h + d # --
- and b, y3 # y3 = (a|c)&b # MAJA
-
- vpsrlq $17, XTMP2, XTMP2 # XTMP2 = W[-2] ror 17 {xDxC}
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
-
- vpxor XTMP3, XTMP2, XTMP2
- rorx $22, a, y1 # y1 = a >> 22 # S0A
- add y0, y2 # y2 = S1 + CH # --
-
- vpxor XTMP2, XTMP5, XTMP5 # XTMP5 = s1 {xDxC}
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) # S0
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
-
- rorx $2, a, T1 # T1 = (a >> 2) # S0
- vpshufb SHUF_DC00, XTMP5, XTMP5 # XTMP5 = s1 {DC00}
-
- vpaddd XTMP0, XTMP5, X0 # X0 = {W[3], W[2], W[1], W[0]}
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
- mov a, T1 # T1 = a # MAJB
- and c, T1 # T1 = a&c # MAJB
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
-
- add y1, h # h = k + w + h + S0 # --
- add y2, h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- add y3, h # h = t1 + S0 + MAJ # --
-
- ROTATE_ARGS
- rotate_Xs
-.endm
-
-.macro DO_4ROUNDS disp
-################################### RND N + 0 ###########################
-
- mov f, y2 # y2 = f # CH
- rorx $25, e, y0 # y0 = e >> 25 # S1A
- rorx $11, e, y1 # y1 = e >> 11 # S1B
- xor g, y2 # y2 = f^g # CH
-
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
- rorx $6, e, y1 # y1 = (e >> 6) # S1
- and e, y2 # y2 = (f^g)&e # CH
-
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
- rorx $13, a, T1 # T1 = a >> 13 # S0B
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
- rorx $22, a, y1 # y1 = a >> 22 # S0A
- mov a, y3 # y3 = a # MAJA
-
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) # S0
- rorx $2, a, T1 # T1 = (a >> 2) # S0
- addl \disp(%rsp, SRND), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
- mov a, T1 # T1 = a # MAJB
- and b, y3 # y3 = (a|c)&b # MAJA
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
-
-
- add h, d # d = k + w + h + d # --
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
-
- ROTATE_ARGS
-
-################################### RND N + 1 ###########################
-
- add y2, old_h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- mov f, y2 # y2 = f # CH
- rorx $25, e, y0 # y0 = e >> 25 # S1A
- rorx $11, e, y1 # y1 = e >> 11 # S1B
- xor g, y2 # y2 = f^g # CH
-
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
- rorx $6, e, y1 # y1 = (e >> 6) # S1
- and e, y2 # y2 = (f^g)&e # CH
- add y3, old_h # h = t1 + S0 + MAJ # --
-
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
- rorx $13, a, T1 # T1 = a >> 13 # S0B
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
- rorx $22, a, y1 # y1 = a >> 22 # S0A
- mov a, y3 # y3 = a # MAJA
-
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) # S0
- rorx $2, a, T1 # T1 = (a >> 2) # S0
- offset = 4*1 + \disp
- addl offset(%rsp, SRND), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
- mov a, T1 # T1 = a # MAJB
- and b, y3 # y3 = (a|c)&b # MAJA
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
-
-
- add h, d # d = k + w + h + d # --
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
-
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
-
- ROTATE_ARGS
-
-################################### RND N + 2 ##############################
-
- add y2, old_h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- mov f, y2 # y2 = f # CH
- rorx $25, e, y0 # y0 = e >> 25 # S1A
- rorx $11, e, y1 # y1 = e >> 11 # S1B
- xor g, y2 # y2 = f^g # CH
-
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
- rorx $6, e, y1 # y1 = (e >> 6) # S1
- and e, y2 # y2 = (f^g)&e # CH
- add y3, old_h # h = t1 + S0 + MAJ # --
-
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
- rorx $13, a, T1 # T1 = a >> 13 # S0B
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
- rorx $22, a, y1 # y1 = a >> 22 # S0A
- mov a, y3 # y3 = a # MAJA
-
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) # S0
- rorx $2, a, T1 # T1 = (a >> 2) # S0
- offset = 4*2 + \disp
- addl offset(%rsp, SRND), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
- mov a, T1 # T1 = a # MAJB
- and b, y3 # y3 = (a|c)&b # MAJA
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
-
-
- add h, d # d = k + w + h + d # --
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
-
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
-
- ROTATE_ARGS
-
-################################### RND N + 3 ###########################
-
- add y2, old_h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- mov f, y2 # y2 = f # CH
- rorx $25, e, y0 # y0 = e >> 25 # S1A
- rorx $11, e, y1 # y1 = e >> 11 # S1B
- xor g, y2 # y2 = f^g # CH
-
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) # S1
- rorx $6, e, y1 # y1 = (e >> 6) # S1
- and e, y2 # y2 = (f^g)&e # CH
- add y3, old_h # h = t1 + S0 + MAJ # --
-
- xor y1, y0 # y0 = (e>>25) ^ (e>>11) ^ (e>>6) # S1
- rorx $13, a, T1 # T1 = a >> 13 # S0B
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
- rorx $22, a, y1 # y1 = a >> 22 # S0A
- mov a, y3 # y3 = a # MAJA
-
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) # S0
- rorx $2, a, T1 # T1 = (a >> 2) # S0
- offset = 4*3 + \disp
- addl offset(%rsp, SRND), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
- xor T1, y1 # y1 = (a>>22) ^ (a>>13) ^ (a>>2) # S0
- mov a, T1 # T1 = a # MAJB
- and b, y3 # y3 = (a|c)&b # MAJA
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
-
-
- add h, d # d = k + w + h + d # --
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
-
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
-
-
- add y2, h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
-
- add y3, h # h = t1 + S0 + MAJ # --
-
- ROTATE_ARGS
-
-.endm
-
-########################################################################
-## void sha256_transform_rorx(struct sha256_state *state, const u8 *data, int blocks)
-## arg 1 : pointer to state
-## arg 2 : pointer to input data
-## arg 3 : Num blocks
-########################################################################
-.text
-SYM_TYPED_FUNC_START(sha256_transform_rorx)
- pushq %rbx
- pushq %r12
- pushq %r13
- pushq %r14
- pushq %r15
-
- push %rbp
- mov %rsp, %rbp
-
- subq $STACK_SIZE, %rsp
- and $-32, %rsp # align rsp to 32 byte boundary
-
- shl $6, NUM_BLKS # convert to bytes
- jz .Ldone_hash
- lea -64(INP, NUM_BLKS), NUM_BLKS # pointer to last block
- mov NUM_BLKS, _INP_END(%rsp)
-
- cmp NUM_BLKS, INP
- je .Lonly_one_block
-
- ## load initial digest
- mov (CTX), a
- mov 4*1(CTX), b
- mov 4*2(CTX), c
- mov 4*3(CTX), d
- mov 4*4(CTX), e
- mov 4*5(CTX), f
- mov 4*6(CTX), g
- mov 4*7(CTX), h
-
- vmovdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK
- vmovdqa _SHUF_00BA(%rip), SHUF_00BA
- vmovdqa _SHUF_DC00(%rip), SHUF_DC00
-
- mov CTX, _CTX(%rsp)
-
-.Lloop0:
- ## Load first 16 dwords from two blocks
- VMOVDQ 0*32(INP),XTMP0
- VMOVDQ 1*32(INP),XTMP1
- VMOVDQ 2*32(INP),XTMP2
- VMOVDQ 3*32(INP),XTMP3
-
- ## byte swap data
- vpshufb BYTE_FLIP_MASK, XTMP0, XTMP0
- vpshufb BYTE_FLIP_MASK, XTMP1, XTMP1
- vpshufb BYTE_FLIP_MASK, XTMP2, XTMP2
- vpshufb BYTE_FLIP_MASK, XTMP3, XTMP3
-
- ## transpose data into high/low halves
- vperm2i128 $0x20, XTMP2, XTMP0, X0
- vperm2i128 $0x31, XTMP2, XTMP0, X1
- vperm2i128 $0x20, XTMP3, XTMP1, X2
- vperm2i128 $0x31, XTMP3, XTMP1, X3
-
-.Llast_block_enter:
- add $64, INP
- mov INP, _INP(%rsp)
-
- ## schedule 48 input dwords, by doing 3 rounds of 12 each
- xor SRND, SRND
-
-.align 16
-.Lloop1:
- leaq K256+0*32(%rip), INP ## reuse INP as scratch reg
- vpaddd (INP, SRND), X0, XFER
- vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
- FOUR_ROUNDS_AND_SCHED (_XFER + 0*32)
-
- leaq K256+1*32(%rip), INP
- vpaddd (INP, SRND), X0, XFER
- vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
- FOUR_ROUNDS_AND_SCHED (_XFER + 1*32)
-
- leaq K256+2*32(%rip), INP
- vpaddd (INP, SRND), X0, XFER
- vmovdqa XFER, 2*32+_XFER(%rsp, SRND)
- FOUR_ROUNDS_AND_SCHED (_XFER + 2*32)
-
- leaq K256+3*32(%rip), INP
- vpaddd (INP, SRND), X0, XFER
- vmovdqa XFER, 3*32+_XFER(%rsp, SRND)
- FOUR_ROUNDS_AND_SCHED (_XFER + 3*32)
-
- add $4*32, SRND
- cmp $3*4*32, SRND
- jb .Lloop1
-
-.Lloop2:
- ## Do last 16 rounds with no scheduling
- leaq K256+0*32(%rip), INP
- vpaddd (INP, SRND), X0, XFER
- vmovdqa XFER, 0*32+_XFER(%rsp, SRND)
- DO_4ROUNDS (_XFER + 0*32)
-
- leaq K256+1*32(%rip), INP
- vpaddd (INP, SRND), X1, XFER
- vmovdqa XFER, 1*32+_XFER(%rsp, SRND)
- DO_4ROUNDS (_XFER + 1*32)
- add $2*32, SRND
-
- vmovdqa X2, X0
- vmovdqa X3, X1
-
- cmp $4*4*32, SRND
- jb .Lloop2
-
- mov _CTX(%rsp), CTX
- mov _INP(%rsp), INP
-
- addm (4*0)(CTX),a
- addm (4*1)(CTX),b
- addm (4*2)(CTX),c
- addm (4*3)(CTX),d
- addm (4*4)(CTX),e
- addm (4*5)(CTX),f
- addm (4*6)(CTX),g
- addm (4*7)(CTX),h
-
- cmp _INP_END(%rsp), INP
- ja .Ldone_hash
-
- #### Do second block using previously scheduled results
- xor SRND, SRND
-.align 16
-.Lloop3:
- DO_4ROUNDS (_XFER + 0*32 + 16)
- DO_4ROUNDS (_XFER + 1*32 + 16)
- add $2*32, SRND
- cmp $4*4*32, SRND
- jb .Lloop3
-
- mov _CTX(%rsp), CTX
- mov _INP(%rsp), INP
- add $64, INP
-
- addm (4*0)(CTX),a
- addm (4*1)(CTX),b
- addm (4*2)(CTX),c
- addm (4*3)(CTX),d
- addm (4*4)(CTX),e
- addm (4*5)(CTX),f
- addm (4*6)(CTX),g
- addm (4*7)(CTX),h
-
- cmp _INP_END(%rsp), INP
- jb .Lloop0
- ja .Ldone_hash
-
-.Ldo_last_block:
- VMOVDQ 0*16(INP),XWORD0
- VMOVDQ 1*16(INP),XWORD1
- VMOVDQ 2*16(INP),XWORD2
- VMOVDQ 3*16(INP),XWORD3
-
- vpshufb X_BYTE_FLIP_MASK, XWORD0, XWORD0
- vpshufb X_BYTE_FLIP_MASK, XWORD1, XWORD1
- vpshufb X_BYTE_FLIP_MASK, XWORD2, XWORD2
- vpshufb X_BYTE_FLIP_MASK, XWORD3, XWORD3
-
- jmp .Llast_block_enter
-
-.Lonly_one_block:
-
- ## load initial digest
- mov (4*0)(CTX),a
- mov (4*1)(CTX),b
- mov (4*2)(CTX),c
- mov (4*3)(CTX),d
- mov (4*4)(CTX),e
- mov (4*5)(CTX),f
- mov (4*6)(CTX),g
- mov (4*7)(CTX),h
-
- vmovdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK
- vmovdqa _SHUF_00BA(%rip), SHUF_00BA
- vmovdqa _SHUF_DC00(%rip), SHUF_DC00
-
- mov CTX, _CTX(%rsp)
- jmp .Ldo_last_block
-
-.Ldone_hash:
-
- mov %rbp, %rsp
- pop %rbp
-
- popq %r15
- popq %r14
- popq %r13
- popq %r12
- popq %rbx
- vzeroupper
- RET
-SYM_FUNC_END(sha256_transform_rorx)
-
-.section .rodata.cst512.K256, "aM", @progbits, 512
-.align 64
-K256:
- .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
- .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
- .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
- .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
- .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
- .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
- .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
- .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
- .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
- .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
- .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
- .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
- .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
- .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
- .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
- .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
- .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
- .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
- .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
- .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
- .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
- .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
- .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
- .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
- .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
- .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
- .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
- .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
- .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
- .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
- .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
- .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
-
-.section .rodata.cst32.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 32
-.align 32
-PSHUFFLE_BYTE_FLIP_MASK:
- .octa 0x0c0d0e0f08090a0b0405060700010203,0x0c0d0e0f08090a0b0405060700010203
-
-# shuffle xBxA -> 00BA
-.section .rodata.cst32._SHUF_00BA, "aM", @progbits, 32
-.align 32
-_SHUF_00BA:
- .octa 0xFFFFFFFFFFFFFFFF0b0a090803020100,0xFFFFFFFFFFFFFFFF0b0a090803020100
-
-# shuffle xDxC -> DC00
-.section .rodata.cst32._SHUF_DC00, "aM", @progbits, 32
-.align 32
-_SHUF_DC00:
- .octa 0x0b0a090803020100FFFFFFFFFFFFFFFF,0x0b0a090803020100FFFFFFFFFFFFFFFF
diff --git a/arch/x86/crypto/sha256-ssse3-asm.S b/arch/x86/crypto/sha256-ssse3-asm.S
deleted file mode 100644
index 93264ee44543..000000000000
--- a/arch/x86/crypto/sha256-ssse3-asm.S
+++ /dev/null
@@ -1,513 +0,0 @@
-########################################################################
-# Implement fast SHA-256 with SSSE3 instructions. (x86_64)
-#
-# Copyright (C) 2013 Intel Corporation.
-#
-# Authors:
-# James Guilford <james.guilford@intel.com>
-# Kirk Yap <kirk.s.yap@intel.com>
-# Tim Chen <tim.c.chen@linux.intel.com>
-#
-# This software is available to you under a choice of one of two
-# licenses. You may choose to be licensed under the terms of the GNU
-# General Public License (GPL) Version 2, available from the file
-# COPYING in the main directory of this source tree, or the
-# OpenIB.org BSD license below:
-#
-# Redistribution and use in source and binary forms, with or
-# without modification, are permitted provided that the following
-# conditions are met:
-#
-# - Redistributions of source code must retain the above
-# copyright notice, this list of conditions and the following
-# disclaimer.
-#
-# - Redistributions in binary form must reproduce the above
-# copyright notice, this list of conditions and the following
-# disclaimer in the documentation and/or other materials
-# provided with the distribution.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-#
-########################################################################
-#
-# This code is described in an Intel White-Paper:
-# "Fast SHA-256 Implementations on Intel Architecture Processors"
-#
-# To find it, surf to http://www.intel.com/p/en_US/embedded
-# and search for that title.
-#
-########################################################################
-
-#include <linux/linkage.h>
-#include <linux/cfi_types.h>
-
-## assume buffers not aligned
-#define MOVDQ movdqu
-
-################################ Define Macros
-
-# addm [mem], reg
-# Add reg to mem using reg-mem add and store
-.macro addm p1 p2
- add \p1, \p2
- mov \p2, \p1
-.endm
-
-################################
-
-# COPY_XMM_AND_BSWAP xmm, [mem], byte_flip_mask
-# Load xmm with mem and byte swap each dword
-.macro COPY_XMM_AND_BSWAP p1 p2 p3
- MOVDQ \p2, \p1
- pshufb \p3, \p1
-.endm
-
-################################
-
-X0 = %xmm4
-X1 = %xmm5
-X2 = %xmm6
-X3 = %xmm7
-
-XTMP0 = %xmm0
-XTMP1 = %xmm1
-XTMP2 = %xmm2
-XTMP3 = %xmm3
-XTMP4 = %xmm8
-XFER = %xmm9
-
-SHUF_00BA = %xmm10 # shuffle xBxA -> 00BA
-SHUF_DC00 = %xmm11 # shuffle xDxC -> DC00
-BYTE_FLIP_MASK = %xmm12
-
-NUM_BLKS = %rdx # 3rd arg
-INP = %rsi # 2nd arg
-CTX = %rdi # 1st arg
-
-SRND = %rsi # clobbers INP
-c = %ecx
-d = %r8d
-e = %edx
-TBL = %r12
-a = %eax
-b = %ebx
-
-f = %r9d
-g = %r10d
-h = %r11d
-
-y0 = %r13d
-y1 = %r14d
-y2 = %r15d
-
-
-
-_INP_END_SIZE = 8
-_INP_SIZE = 8
-_XFER_SIZE = 16
-_XMM_SAVE_SIZE = 0
-
-_INP_END = 0
-_INP = _INP_END + _INP_END_SIZE
-_XFER = _INP + _INP_SIZE
-_XMM_SAVE = _XFER + _XFER_SIZE
-STACK_SIZE = _XMM_SAVE + _XMM_SAVE_SIZE
-
-# rotate_Xs
-# Rotate values of symbols X0...X3
-.macro rotate_Xs
-X_ = X0
-X0 = X1
-X1 = X2
-X2 = X3
-X3 = X_
-.endm
-
-# ROTATE_ARGS
-# Rotate values of symbols a...h
-.macro ROTATE_ARGS
-TMP_ = h
-h = g
-g = f
-f = e
-e = d
-d = c
-c = b
-b = a
-a = TMP_
-.endm
-
-.macro FOUR_ROUNDS_AND_SCHED
- ## compute s0 four at a time and s1 two at a time
- ## compute W[-16] + W[-7] 4 at a time
- movdqa X3, XTMP0
- mov e, y0 # y0 = e
- ror $(25-11), y0 # y0 = e >> (25-11)
- mov a, y1 # y1 = a
- palignr $4, X2, XTMP0 # XTMP0 = W[-7]
- ror $(22-13), y1 # y1 = a >> (22-13)
- xor e, y0 # y0 = e ^ (e >> (25-11))
- mov f, y2 # y2 = f
- ror $(11-6), y0 # y0 = (e >> (11-6)) ^ (e >> (25-6))
- movdqa X1, XTMP1
- xor a, y1 # y1 = a ^ (a >> (22-13)
- xor g, y2 # y2 = f^g
- paddd X0, XTMP0 # XTMP0 = W[-7] + W[-16]
- xor e, y0 # y0 = e ^ (e >> (11-6)) ^ (e >> (25-6))
- and e, y2 # y2 = (f^g)&e
- ror $(13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
- ## compute s0
- palignr $4, X0, XTMP1 # XTMP1 = W[-15]
- xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
- ror $6, y0 # y0 = S1 = (e>>6) & (e>>11) ^ (e>>25)
- xor g, y2 # y2 = CH = ((f^g)&e)^g
- movdqa XTMP1, XTMP2 # XTMP2 = W[-15]
- ror $2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
- add y0, y2 # y2 = S1 + CH
- add _XFER(%rsp) , y2 # y2 = k + w + S1 + CH
- movdqa XTMP1, XTMP3 # XTMP3 = W[-15]
- mov a, y0 # y0 = a
- add y2, h # h = h + S1 + CH + k + w
- mov a, y2 # y2 = a
- pslld $(32-7), XTMP1 #
- or c, y0 # y0 = a|c
- add h, d # d = d + h + S1 + CH + k + w
- and c, y2 # y2 = a&c
- psrld $7, XTMP2 #
- and b, y0 # y0 = (a|c)&b
- add y1, h # h = h + S1 + CH + k + w + S0
- por XTMP2, XTMP1 # XTMP1 = W[-15] ror 7
- or y2, y0 # y0 = MAJ = (a|c)&b)|(a&c)
- add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
- #
- ROTATE_ARGS #
- movdqa XTMP3, XTMP2 # XTMP2 = W[-15]
- mov e, y0 # y0 = e
- mov a, y1 # y1 = a
- movdqa XTMP3, XTMP4 # XTMP4 = W[-15]
- ror $(25-11), y0 # y0 = e >> (25-11)
- xor e, y0 # y0 = e ^ (e >> (25-11))
- mov f, y2 # y2 = f
- ror $(22-13), y1 # y1 = a >> (22-13)
- pslld $(32-18), XTMP3 #
- xor a, y1 # y1 = a ^ (a >> (22-13)
- ror $(11-6), y0 # y0 = (e >> (11-6)) ^ (e >> (25-6))
- xor g, y2 # y2 = f^g
- psrld $18, XTMP2 #
- ror $(13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
- xor e, y0 # y0 = e ^ (e >> (11-6)) ^ (e >> (25-6))
- and e, y2 # y2 = (f^g)&e
- ror $6, y0 # y0 = S1 = (e>>6) & (e>>11) ^ (e>>25)
- pxor XTMP3, XTMP1
- xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
- xor g, y2 # y2 = CH = ((f^g)&e)^g
- psrld $3, XTMP4 # XTMP4 = W[-15] >> 3
- add y0, y2 # y2 = S1 + CH
- add (1*4 + _XFER)(%rsp), y2 # y2 = k + w + S1 + CH
- ror $2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
- pxor XTMP2, XTMP1 # XTMP1 = W[-15] ror 7 ^ W[-15] ror 18
- mov a, y0 # y0 = a
- add y2, h # h = h + S1 + CH + k + w
- mov a, y2 # y2 = a
- pxor XTMP4, XTMP1 # XTMP1 = s0
- or c, y0 # y0 = a|c
- add h, d # d = d + h + S1 + CH + k + w
- and c, y2 # y2 = a&c
- ## compute low s1
- pshufd $0b11111010, X3, XTMP2 # XTMP2 = W[-2] {BBAA}
- and b, y0 # y0 = (a|c)&b
- add y1, h # h = h + S1 + CH + k + w + S0
- paddd XTMP1, XTMP0 # XTMP0 = W[-16] + W[-7] + s0
- or y2, y0 # y0 = MAJ = (a|c)&b)|(a&c)
- add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
-
- ROTATE_ARGS
- movdqa XTMP2, XTMP3 # XTMP3 = W[-2] {BBAA}
- mov e, y0 # y0 = e
- mov a, y1 # y1 = a
- ror $(25-11), y0 # y0 = e >> (25-11)
- movdqa XTMP2, XTMP4 # XTMP4 = W[-2] {BBAA}
- xor e, y0 # y0 = e ^ (e >> (25-11))
- ror $(22-13), y1 # y1 = a >> (22-13)
- mov f, y2 # y2 = f
- xor a, y1 # y1 = a ^ (a >> (22-13)
- ror $(11-6), y0 # y0 = (e >> (11-6)) ^ (e >> (25-6))
- psrlq $17, XTMP2 # XTMP2 = W[-2] ror 17 {xBxA}
- xor g, y2 # y2 = f^g
- psrlq $19, XTMP3 # XTMP3 = W[-2] ror 19 {xBxA}
- xor e, y0 # y0 = e ^ (e >> (11-6)) ^ (e >> (25-6))
- and e, y2 # y2 = (f^g)&e
- psrld $10, XTMP4 # XTMP4 = W[-2] >> 10 {BBAA}
- ror $(13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
- xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
- xor g, y2 # y2 = CH = ((f^g)&e)^g
- ror $6, y0 # y0 = S1 = (e>>6) & (e>>11) ^ (e>>25)
- pxor XTMP3, XTMP2
- add y0, y2 # y2 = S1 + CH
- ror $2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
- add (2*4 + _XFER)(%rsp), y2 # y2 = k + w + S1 + CH
- pxor XTMP2, XTMP4 # XTMP4 = s1 {xBxA}
- mov a, y0 # y0 = a
- add y2, h # h = h + S1 + CH + k + w
- mov a, y2 # y2 = a
- pshufb SHUF_00BA, XTMP4 # XTMP4 = s1 {00BA}
- or c, y0 # y0 = a|c
- add h, d # d = d + h + S1 + CH + k + w
- and c, y2 # y2 = a&c
- paddd XTMP4, XTMP0 # XTMP0 = {..., ..., W[1], W[0]}
- and b, y0 # y0 = (a|c)&b
- add y1, h # h = h + S1 + CH + k + w + S0
- ## compute high s1
- pshufd $0b01010000, XTMP0, XTMP2 # XTMP2 = W[-2] {BBAA}
- or y2, y0 # y0 = MAJ = (a|c)&b)|(a&c)
- add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
- #
- ROTATE_ARGS #
- movdqa XTMP2, XTMP3 # XTMP3 = W[-2] {DDCC}
- mov e, y0 # y0 = e
- ror $(25-11), y0 # y0 = e >> (25-11)
- mov a, y1 # y1 = a
- movdqa XTMP2, X0 # X0 = W[-2] {DDCC}
- ror $(22-13), y1 # y1 = a >> (22-13)
- xor e, y0 # y0 = e ^ (e >> (25-11))
- mov f, y2 # y2 = f
- ror $(11-6), y0 # y0 = (e >> (11-6)) ^ (e >> (25-6))
- psrlq $17, XTMP2 # XTMP2 = W[-2] ror 17 {xDxC}
- xor a, y1 # y1 = a ^ (a >> (22-13)
- xor g, y2 # y2 = f^g
- psrlq $19, XTMP3 # XTMP3 = W[-2] ror 19 {xDxC}
- xor e, y0 # y0 = e ^ (e >> (11-6)) ^ (e >> (25
- and e, y2 # y2 = (f^g)&e
- ror $(13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
- psrld $10, X0 # X0 = W[-2] >> 10 {DDCC}
- xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22
- ror $6, y0 # y0 = S1 = (e>>6) & (e>>11) ^ (e>>2
- xor g, y2 # y2 = CH = ((f^g)&e)^g
- pxor XTMP3, XTMP2 #
- ror $2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>2
- add y0, y2 # y2 = S1 + CH
- add (3*4 + _XFER)(%rsp), y2 # y2 = k + w + S1 + CH
- pxor XTMP2, X0 # X0 = s1 {xDxC}
- mov a, y0 # y0 = a
- add y2, h # h = h + S1 + CH + k + w
- mov a, y2 # y2 = a
- pshufb SHUF_DC00, X0 # X0 = s1 {DC00}
- or c, y0 # y0 = a|c
- add h, d # d = d + h + S1 + CH + k + w
- and c, y2 # y2 = a&c
- paddd XTMP0, X0 # X0 = {W[3], W[2], W[1], W[0]}
- and b, y0 # y0 = (a|c)&b
- add y1, h # h = h + S1 + CH + k + w + S0
- or y2, y0 # y0 = MAJ = (a|c)&b)|(a&c)
- add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
-
- ROTATE_ARGS
- rotate_Xs
-.endm
-
-## input is [rsp + _XFER + %1 * 4]
-.macro DO_ROUND round
- mov e, y0 # y0 = e
- ror $(25-11), y0 # y0 = e >> (25-11)
- mov a, y1 # y1 = a
- xor e, y0 # y0 = e ^ (e >> (25-11))
- ror $(22-13), y1 # y1 = a >> (22-13)
- mov f, y2 # y2 = f
- xor a, y1 # y1 = a ^ (a >> (22-13)
- ror $(11-6), y0 # y0 = (e >> (11-6)) ^ (e >> (25-6))
- xor g, y2 # y2 = f^g
- xor e, y0 # y0 = e ^ (e >> (11-6)) ^ (e >> (25-6))
- ror $(13-2), y1 # y1 = (a >> (13-2)) ^ (a >> (22-2))
- and e, y2 # y2 = (f^g)&e
- xor a, y1 # y1 = a ^ (a >> (13-2)) ^ (a >> (22-2))
- ror $6, y0 # y0 = S1 = (e>>6) & (e>>11) ^ (e>>25)
- xor g, y2 # y2 = CH = ((f^g)&e)^g
- add y0, y2 # y2 = S1 + CH
- ror $2, y1 # y1 = S0 = (a>>2) ^ (a>>13) ^ (a>>22)
- offset = \round * 4 + _XFER
- add offset(%rsp), y2 # y2 = k + w + S1 + CH
- mov a, y0 # y0 = a
- add y2, h # h = h + S1 + CH + k + w
- mov a, y2 # y2 = a
- or c, y0 # y0 = a|c
- add h, d # d = d + h + S1 + CH + k + w
- and c, y2 # y2 = a&c
- and b, y0 # y0 = (a|c)&b
- add y1, h # h = h + S1 + CH + k + w + S0
- or y2, y0 # y0 = MAJ = (a|c)&b)|(a&c)
- add y0, h # h = h + S1 + CH + k + w + S0 + MAJ
- ROTATE_ARGS
-.endm
-
-########################################################################
-## void sha256_transform_ssse3(struct sha256_state *state, const u8 *data,
-## int blocks);
-## arg 1 : pointer to state
-## (struct sha256_state is assumed to begin with u32 state[8])
-## arg 2 : pointer to input data
-## arg 3 : Num blocks
-########################################################################
-.text
-SYM_TYPED_FUNC_START(sha256_transform_ssse3)
- pushq %rbx
- pushq %r12
- pushq %r13
- pushq %r14
- pushq %r15
- pushq %rbp
- mov %rsp, %rbp
-
- subq $STACK_SIZE, %rsp
- and $~15, %rsp
-
- shl $6, NUM_BLKS # convert to bytes
- jz .Ldone_hash
- add INP, NUM_BLKS
- mov NUM_BLKS, _INP_END(%rsp) # pointer to end of data
-
- ## load initial digest
- mov 4*0(CTX), a
- mov 4*1(CTX), b
- mov 4*2(CTX), c
- mov 4*3(CTX), d
- mov 4*4(CTX), e
- mov 4*5(CTX), f
- mov 4*6(CTX), g
- mov 4*7(CTX), h
-
- movdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK
- movdqa _SHUF_00BA(%rip), SHUF_00BA
- movdqa _SHUF_DC00(%rip), SHUF_DC00
-
-.Lloop0:
- lea K256(%rip), TBL
-
- ## byte swap first 16 dwords
- COPY_XMM_AND_BSWAP X0, 0*16(INP), BYTE_FLIP_MASK
- COPY_XMM_AND_BSWAP X1, 1*16(INP), BYTE_FLIP_MASK
- COPY_XMM_AND_BSWAP X2, 2*16(INP), BYTE_FLIP_MASK
- COPY_XMM_AND_BSWAP X3, 3*16(INP), BYTE_FLIP_MASK
-
- mov INP, _INP(%rsp)
-
- ## schedule 48 input dwords, by doing 3 rounds of 16 each
- mov $3, SRND
-.align 16
-.Lloop1:
- movdqa (TBL), XFER
- paddd X0, XFER
- movdqa XFER, _XFER(%rsp)
- FOUR_ROUNDS_AND_SCHED
-
- movdqa 1*16(TBL), XFER
- paddd X0, XFER
- movdqa XFER, _XFER(%rsp)
- FOUR_ROUNDS_AND_SCHED
-
- movdqa 2*16(TBL), XFER
- paddd X0, XFER
- movdqa XFER, _XFER(%rsp)
- FOUR_ROUNDS_AND_SCHED
-
- movdqa 3*16(TBL), XFER
- paddd X0, XFER
- movdqa XFER, _XFER(%rsp)
- add $4*16, TBL
- FOUR_ROUNDS_AND_SCHED
-
- sub $1, SRND
- jne .Lloop1
-
- mov $2, SRND
-.Lloop2:
- paddd (TBL), X0
- movdqa X0, _XFER(%rsp)
- DO_ROUND 0
- DO_ROUND 1
- DO_ROUND 2
- DO_ROUND 3
- paddd 1*16(TBL), X1
- movdqa X1, _XFER(%rsp)
- add $2*16, TBL
- DO_ROUND 0
- DO_ROUND 1
- DO_ROUND 2
- DO_ROUND 3
-
- movdqa X2, X0
- movdqa X3, X1
-
- sub $1, SRND
- jne .Lloop2
-
- addm (4*0)(CTX),a
- addm (4*1)(CTX),b
- addm (4*2)(CTX),c
- addm (4*3)(CTX),d
- addm (4*4)(CTX),e
- addm (4*5)(CTX),f
- addm (4*6)(CTX),g
- addm (4*7)(CTX),h
-
- mov _INP(%rsp), INP
- add $64, INP
- cmp _INP_END(%rsp), INP
- jne .Lloop0
-
-.Ldone_hash:
-
- mov %rbp, %rsp
- popq %rbp
- popq %r15
- popq %r14
- popq %r13
- popq %r12
- popq %rbx
-
- RET
-SYM_FUNC_END(sha256_transform_ssse3)
-
-.section .rodata.cst256.K256, "aM", @progbits, 256
-.align 64
-K256:
- .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
- .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
- .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
- .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
- .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
- .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
- .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
- .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
- .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
- .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
- .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
- .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
- .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
- .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
- .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
- .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
-
-.section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16
-.align 16
-PSHUFFLE_BYTE_FLIP_MASK:
- .octa 0x0c0d0e0f08090a0b0405060700010203
-
-.section .rodata.cst16._SHUF_00BA, "aM", @progbits, 16
-.align 16
-# shuffle xBxA -> 00BA
-_SHUF_00BA:
- .octa 0xFFFFFFFFFFFFFFFF0b0a090803020100
-
-.section .rodata.cst16._SHUF_DC00, "aM", @progbits, 16
-.align 16
-# shuffle xDxC -> DC00
-_SHUF_DC00:
- .octa 0x0b0a090803020100FFFFFFFFFFFFFFFF
diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S
deleted file mode 100644
index d515a55a3bc1..000000000000
--- a/arch/x86/crypto/sha256_ni_asm.S
+++ /dev/null
@@ -1,200 +0,0 @@
-/*
- * Intel SHA Extensions optimized implementation of a SHA-256 update function
- *
- * This file is provided under a dual BSD/GPLv2 license. When using or
- * redistributing this file, you may do so under either license.
- *
- * GPL LICENSE SUMMARY
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of version 2 of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
- * General Public License for more details.
- *
- * Contact Information:
- * Sean Gulley <sean.m.gulley@intel.com>
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * BSD LICENSE
- *
- * Copyright(c) 2015 Intel Corporation.
- *
- * Redistribution and use in source and binary forms, with or without
- * modification, are permitted provided that the following conditions
- * are met:
- *
- * * Redistributions of source code must retain the above copyright
- * notice, this list of conditions and the following disclaimer.
- * * Redistributions in binary form must reproduce the above copyright
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * Neither the name of Intel Corporation nor the names of its
- * contributors may be used to endorse or promote products derived
- * from this software without specific prior written permission.
- *
- * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
- * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
- * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
- * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
- * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
- * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
- * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
- * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
- * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
- * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
- * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-#include <linux/linkage.h>
-#include <linux/cfi_types.h>
-
-#define DIGEST_PTR %rdi /* 1st arg */
-#define DATA_PTR %rsi /* 2nd arg */
-#define NUM_BLKS %rdx /* 3rd arg */
-
-#define SHA256CONSTANTS %rax
-
-#define MSG %xmm0 /* sha256rnds2 implicit operand */
-#define STATE0 %xmm1
-#define STATE1 %xmm2
-#define MSG0 %xmm3
-#define MSG1 %xmm4
-#define MSG2 %xmm5
-#define MSG3 %xmm6
-#define TMP %xmm7
-
-#define SHUF_MASK %xmm8
-
-#define ABEF_SAVE %xmm9
-#define CDGH_SAVE %xmm10
-
-.macro do_4rounds i, m0, m1, m2, m3
-.if \i < 16
- movdqu \i*4(DATA_PTR), \m0
- pshufb SHUF_MASK, \m0
-.endif
- movdqa (\i-32)*4(SHA256CONSTANTS), MSG
- paddd \m0, MSG
- sha256rnds2 STATE0, STATE1
-.if \i >= 12 && \i < 60
- movdqa \m0, TMP
- palignr $4, \m3, TMP
- paddd TMP, \m1
- sha256msg2 \m0, \m1
-.endif
- punpckhqdq MSG, MSG
- sha256rnds2 STATE1, STATE0
-.if \i >= 4 && \i < 52
- sha256msg1 \m0, \m3
-.endif
-.endm
-
-/*
- * Intel SHA Extensions optimized implementation of a SHA-256 update function
- *
- * The function takes a pointer to the current hash values, a pointer to the
- * input data, and a number of 64 byte blocks to process. Once all blocks have
- * been processed, the digest pointer is updated with the resulting hash value.
- * The function only processes complete blocks, there is no functionality to
- * store partial blocks. All message padding and hash value initialization must
- * be done outside the update function.
- *
- * void sha256_ni_transform(uint32_t *digest, const void *data,
- uint32_t numBlocks);
- * digest : pointer to digest
- * data: pointer to input data
- * numBlocks: Number of blocks to process
- */
-
-.text
-SYM_TYPED_FUNC_START(sha256_ni_transform)
-
- shl $6, NUM_BLKS /* convert to bytes */
- jz .Ldone_hash
- add DATA_PTR, NUM_BLKS /* pointer to end of data */
-
- /*
- * load initial hash values
- * Need to reorder these appropriately
- * DCBA, HGFE -> ABEF, CDGH
- */
- movdqu 0*16(DIGEST_PTR), STATE0 /* DCBA */
- movdqu 1*16(DIGEST_PTR), STATE1 /* HGFE */
-
- movdqa STATE0, TMP
- punpcklqdq STATE1, STATE0 /* FEBA */
- punpckhqdq TMP, STATE1 /* DCHG */
- pshufd $0x1B, STATE0, STATE0 /* ABEF */
- pshufd $0xB1, STATE1, STATE1 /* CDGH */
-
- movdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK
- lea K256+32*4(%rip), SHA256CONSTANTS
-
-.Lloop0:
- /* Save hash values for addition after rounds */
- movdqa STATE0, ABEF_SAVE
- movdqa STATE1, CDGH_SAVE
-
-.irp i, 0, 16, 32, 48
- do_4rounds (\i + 0), MSG0, MSG1, MSG2, MSG3
- do_4rounds (\i + 4), MSG1, MSG2, MSG3, MSG0
- do_4rounds (\i + 8), MSG2, MSG3, MSG0, MSG1
- do_4rounds (\i + 12), MSG3, MSG0, MSG1, MSG2
-.endr
-
- /* Add current hash values with previously saved */
- paddd ABEF_SAVE, STATE0
- paddd CDGH_SAVE, STATE1
-
- /* Increment data pointer and loop if more to process */
- add $64, DATA_PTR
- cmp NUM_BLKS, DATA_PTR
- jne .Lloop0
-
- /* Write hash values back in the correct order */
- movdqa STATE0, TMP
- punpcklqdq STATE1, STATE0 /* GHEF */
- punpckhqdq TMP, STATE1 /* ABCD */
- pshufd $0xB1, STATE0, STATE0 /* HGFE */
- pshufd $0x1B, STATE1, STATE1 /* DCBA */
-
- movdqu STATE1, 0*16(DIGEST_PTR)
- movdqu STATE0, 1*16(DIGEST_PTR)
-
-.Ldone_hash:
-
- RET
-SYM_FUNC_END(sha256_ni_transform)
-
-.section .rodata.cst256.K256, "aM", @progbits, 256
-.align 64
-K256:
- .long 0x428a2f98,0x71374491,0xb5c0fbcf,0xe9b5dba5
- .long 0x3956c25b,0x59f111f1,0x923f82a4,0xab1c5ed5
- .long 0xd807aa98,0x12835b01,0x243185be,0x550c7dc3
- .long 0x72be5d74,0x80deb1fe,0x9bdc06a7,0xc19bf174
- .long 0xe49b69c1,0xefbe4786,0x0fc19dc6,0x240ca1cc
- .long 0x2de92c6f,0x4a7484aa,0x5cb0a9dc,0x76f988da
- .long 0x983e5152,0xa831c66d,0xb00327c8,0xbf597fc7
- .long 0xc6e00bf3,0xd5a79147,0x06ca6351,0x14292967
- .long 0x27b70a85,0x2e1b2138,0x4d2c6dfc,0x53380d13
- .long 0x650a7354,0x766a0abb,0x81c2c92e,0x92722c85
- .long 0xa2bfe8a1,0xa81a664b,0xc24b8b70,0xc76c51a3
- .long 0xd192e819,0xd6990624,0xf40e3585,0x106aa070
- .long 0x19a4c116,0x1e376c08,0x2748774c,0x34b0bcb5
- .long 0x391c0cb3,0x4ed8aa4a,0x5b9cca4f,0x682e6ff3
- .long 0x748f82ee,0x78a5636f,0x84c87814,0x8cc70208
- .long 0x90befffa,0xa4506ceb,0xbef9a3f7,0xc67178f2
-
-.section .rodata.cst16.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 16
-.align 16
-PSHUFFLE_BYTE_FLIP_MASK:
- .octa 0x0c0d0e0f08090a0b0405060700010203
diff --git a/arch/x86/crypto/sha256_ssse3_glue.c b/arch/x86/crypto/sha256_ssse3_glue.c
deleted file mode 100644
index e04a43d9f7d5..000000000000
--- a/arch/x86/crypto/sha256_ssse3_glue.c
+++ /dev/null
@@ -1,467 +0,0 @@
-/*
- * Cryptographic API.
- *
- * Glue code for the SHA256 Secure Hash Algorithm assembler implementations
- * using SSSE3, AVX, AVX2, and SHA-NI instructions.
- *
- * This file is based on sha256_generic.c
- *
- * Copyright (C) 2013 Intel Corporation.
- *
- * Author:
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/types.h>
-#include <crypto/sha2.h>
-#include <crypto/sha256_base.h>
-#include <linux/string.h>
-#include <asm/cpu_device_id.h>
-#include <asm/simd.h>
-
-asmlinkage void sha256_transform_ssse3(struct sha256_state *state,
- const u8 *data, int blocks);
-
-static const struct x86_cpu_id module_cpu_ids[] = {
-#ifdef CONFIG_AS_SHA256_NI
- X86_MATCH_FEATURE(X86_FEATURE_SHA_NI, NULL),
-#endif
- X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
- X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL),
- X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL),
- {}
-};
-MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids);
-
-static int _sha256_update(struct shash_desc *desc, const u8 *data,
- unsigned int len, sha256_block_fn *sha256_xform)
-{
- struct sha256_state *sctx = shash_desc_ctx(desc);
-
- if (!crypto_simd_usable() ||
- (sctx->count % SHA256_BLOCK_SIZE) + len < SHA256_BLOCK_SIZE)
- return crypto_sha256_update(desc, data, len);
-
- /*
- * Make sure struct sha256_state begins directly with the SHA256
- * 256-bit internal state, as this is what the asm functions expect.
- */
- BUILD_BUG_ON(offsetof(struct sha256_state, state) != 0);
-
- kernel_fpu_begin();
- sha256_base_do_update(desc, data, len, sha256_xform);
- kernel_fpu_end();
-
- return 0;
-}
-
-static int sha256_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out, sha256_block_fn *sha256_xform)
-{
- if (!crypto_simd_usable())
- return crypto_sha256_finup(desc, data, len, out);
-
- kernel_fpu_begin();
- if (len)
- sha256_base_do_update(desc, data, len, sha256_xform);
- sha256_base_do_finalize(desc, sha256_xform);
- kernel_fpu_end();
-
- return sha256_base_finish(desc, out);
-}
-
-static int sha256_ssse3_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return _sha256_update(desc, data, len, sha256_transform_ssse3);
-}
-
-static int sha256_ssse3_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha256_finup(desc, data, len, out, sha256_transform_ssse3);
-}
-
-/* Add padding and return the message digest. */
-static int sha256_ssse3_final(struct shash_desc *desc, u8 *out)
-{
- return sha256_ssse3_finup(desc, NULL, 0, out);
-}
-
-static int sha256_ssse3_digest(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha256_base_init(desc) ?:
- sha256_ssse3_finup(desc, data, len, out);
-}
-
-static struct shash_alg sha256_ssse3_algs[] = { {
- .digestsize = SHA256_DIGEST_SIZE,
- .init = sha256_base_init,
- .update = sha256_ssse3_update,
- .final = sha256_ssse3_final,
- .finup = sha256_ssse3_finup,
- .digest = sha256_ssse3_digest,
- .descsize = sizeof(struct sha256_state),
- .base = {
- .cra_name = "sha256",
- .cra_driver_name = "sha256-ssse3",
- .cra_priority = 150,
- .cra_blocksize = SHA256_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-}, {
- .digestsize = SHA224_DIGEST_SIZE,
- .init = sha224_base_init,
- .update = sha256_ssse3_update,
- .final = sha256_ssse3_final,
- .finup = sha256_ssse3_finup,
- .descsize = sizeof(struct sha256_state),
- .base = {
- .cra_name = "sha224",
- .cra_driver_name = "sha224-ssse3",
- .cra_priority = 150,
- .cra_blocksize = SHA224_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-} };
-
-static int register_sha256_ssse3(void)
-{
- if (boot_cpu_has(X86_FEATURE_SSSE3))
- return crypto_register_shashes(sha256_ssse3_algs,
- ARRAY_SIZE(sha256_ssse3_algs));
- return 0;
-}
-
-static void unregister_sha256_ssse3(void)
-{
- if (boot_cpu_has(X86_FEATURE_SSSE3))
- crypto_unregister_shashes(sha256_ssse3_algs,
- ARRAY_SIZE(sha256_ssse3_algs));
-}
-
-asmlinkage void sha256_transform_avx(struct sha256_state *state,
- const u8 *data, int blocks);
-
-static int sha256_avx_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return _sha256_update(desc, data, len, sha256_transform_avx);
-}
-
-static int sha256_avx_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha256_finup(desc, data, len, out, sha256_transform_avx);
-}
-
-static int sha256_avx_final(struct shash_desc *desc, u8 *out)
-{
- return sha256_avx_finup(desc, NULL, 0, out);
-}
-
-static int sha256_avx_digest(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha256_base_init(desc) ?:
- sha256_avx_finup(desc, data, len, out);
-}
-
-static struct shash_alg sha256_avx_algs[] = { {
- .digestsize = SHA256_DIGEST_SIZE,
- .init = sha256_base_init,
- .update = sha256_avx_update,
- .final = sha256_avx_final,
- .finup = sha256_avx_finup,
- .digest = sha256_avx_digest,
- .descsize = sizeof(struct sha256_state),
- .base = {
- .cra_name = "sha256",
- .cra_driver_name = "sha256-avx",
- .cra_priority = 160,
- .cra_blocksize = SHA256_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-}, {
- .digestsize = SHA224_DIGEST_SIZE,
- .init = sha224_base_init,
- .update = sha256_avx_update,
- .final = sha256_avx_final,
- .finup = sha256_avx_finup,
- .descsize = sizeof(struct sha256_state),
- .base = {
- .cra_name = "sha224",
- .cra_driver_name = "sha224-avx",
- .cra_priority = 160,
- .cra_blocksize = SHA224_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-} };
-
-static bool avx_usable(void)
-{
- if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
- if (boot_cpu_has(X86_FEATURE_AVX))
- pr_info("AVX detected but unusable.\n");
- return false;
- }
-
- return true;
-}
-
-static int register_sha256_avx(void)
-{
- if (avx_usable())
- return crypto_register_shashes(sha256_avx_algs,
- ARRAY_SIZE(sha256_avx_algs));
- return 0;
-}
-
-static void unregister_sha256_avx(void)
-{
- if (avx_usable())
- crypto_unregister_shashes(sha256_avx_algs,
- ARRAY_SIZE(sha256_avx_algs));
-}
-
-asmlinkage void sha256_transform_rorx(struct sha256_state *state,
- const u8 *data, int blocks);
-
-static int sha256_avx2_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return _sha256_update(desc, data, len, sha256_transform_rorx);
-}
-
-static int sha256_avx2_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha256_finup(desc, data, len, out, sha256_transform_rorx);
-}
-
-static int sha256_avx2_final(struct shash_desc *desc, u8 *out)
-{
- return sha256_avx2_finup(desc, NULL, 0, out);
-}
-
-static int sha256_avx2_digest(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha256_base_init(desc) ?:
- sha256_avx2_finup(desc, data, len, out);
-}
-
-static struct shash_alg sha256_avx2_algs[] = { {
- .digestsize = SHA256_DIGEST_SIZE,
- .init = sha256_base_init,
- .update = sha256_avx2_update,
- .final = sha256_avx2_final,
- .finup = sha256_avx2_finup,
- .digest = sha256_avx2_digest,
- .descsize = sizeof(struct sha256_state),
- .base = {
- .cra_name = "sha256",
- .cra_driver_name = "sha256-avx2",
- .cra_priority = 170,
- .cra_blocksize = SHA256_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-}, {
- .digestsize = SHA224_DIGEST_SIZE,
- .init = sha224_base_init,
- .update = sha256_avx2_update,
- .final = sha256_avx2_final,
- .finup = sha256_avx2_finup,
- .descsize = sizeof(struct sha256_state),
- .base = {
- .cra_name = "sha224",
- .cra_driver_name = "sha224-avx2",
- .cra_priority = 170,
- .cra_blocksize = SHA224_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-} };
-
-static bool avx2_usable(void)
-{
- if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) &&
- boot_cpu_has(X86_FEATURE_BMI2))
- return true;
-
- return false;
-}
-
-static int register_sha256_avx2(void)
-{
- if (avx2_usable())
- return crypto_register_shashes(sha256_avx2_algs,
- ARRAY_SIZE(sha256_avx2_algs));
- return 0;
-}
-
-static void unregister_sha256_avx2(void)
-{
- if (avx2_usable())
- crypto_unregister_shashes(sha256_avx2_algs,
- ARRAY_SIZE(sha256_avx2_algs));
-}
-
-#ifdef CONFIG_AS_SHA256_NI
-asmlinkage void sha256_ni_transform(struct sha256_state *digest,
- const u8 *data, int rounds);
-
-static int sha256_ni_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return _sha256_update(desc, data, len, sha256_ni_transform);
-}
-
-static int sha256_ni_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha256_finup(desc, data, len, out, sha256_ni_transform);
-}
-
-static int sha256_ni_final(struct shash_desc *desc, u8 *out)
-{
- return sha256_ni_finup(desc, NULL, 0, out);
-}
-
-static int sha256_ni_digest(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha256_base_init(desc) ?:
- sha256_ni_finup(desc, data, len, out);
-}
-
-static struct shash_alg sha256_ni_algs[] = { {
- .digestsize = SHA256_DIGEST_SIZE,
- .init = sha256_base_init,
- .update = sha256_ni_update,
- .final = sha256_ni_final,
- .finup = sha256_ni_finup,
- .digest = sha256_ni_digest,
- .descsize = sizeof(struct sha256_state),
- .base = {
- .cra_name = "sha256",
- .cra_driver_name = "sha256-ni",
- .cra_priority = 250,
- .cra_blocksize = SHA256_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-}, {
- .digestsize = SHA224_DIGEST_SIZE,
- .init = sha224_base_init,
- .update = sha256_ni_update,
- .final = sha256_ni_final,
- .finup = sha256_ni_finup,
- .descsize = sizeof(struct sha256_state),
- .base = {
- .cra_name = "sha224",
- .cra_driver_name = "sha224-ni",
- .cra_priority = 250,
- .cra_blocksize = SHA224_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-} };
-
-static int register_sha256_ni(void)
-{
- if (boot_cpu_has(X86_FEATURE_SHA_NI))
- return crypto_register_shashes(sha256_ni_algs,
- ARRAY_SIZE(sha256_ni_algs));
- return 0;
-}
-
-static void unregister_sha256_ni(void)
-{
- if (boot_cpu_has(X86_FEATURE_SHA_NI))
- crypto_unregister_shashes(sha256_ni_algs,
- ARRAY_SIZE(sha256_ni_algs));
-}
-
-#else
-static inline int register_sha256_ni(void) { return 0; }
-static inline void unregister_sha256_ni(void) { }
-#endif
-
-static int __init sha256_ssse3_mod_init(void)
-{
- if (!x86_match_cpu(module_cpu_ids))
- return -ENODEV;
-
- if (register_sha256_ssse3())
- goto fail;
-
- if (register_sha256_avx()) {
- unregister_sha256_ssse3();
- goto fail;
- }
-
- if (register_sha256_avx2()) {
- unregister_sha256_avx();
- unregister_sha256_ssse3();
- goto fail;
- }
-
- if (register_sha256_ni()) {
- unregister_sha256_avx2();
- unregister_sha256_avx();
- unregister_sha256_ssse3();
- goto fail;
- }
-
- return 0;
-fail:
- return -ENODEV;
-}
-
-static void __exit sha256_ssse3_mod_fini(void)
-{
- unregister_sha256_ni();
- unregister_sha256_avx2();
- unregister_sha256_avx();
- unregister_sha256_ssse3();
-}
-
-module_init(sha256_ssse3_mod_init);
-module_exit(sha256_ssse3_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA256 Secure Hash Algorithm, Supplemental SSE3 accelerated");
-
-MODULE_ALIAS_CRYPTO("sha256");
-MODULE_ALIAS_CRYPTO("sha256-ssse3");
-MODULE_ALIAS_CRYPTO("sha256-avx");
-MODULE_ALIAS_CRYPTO("sha256-avx2");
-MODULE_ALIAS_CRYPTO("sha224");
-MODULE_ALIAS_CRYPTO("sha224-ssse3");
-MODULE_ALIAS_CRYPTO("sha224-avx");
-MODULE_ALIAS_CRYPTO("sha224-avx2");
-#ifdef CONFIG_AS_SHA256_NI
-MODULE_ALIAS_CRYPTO("sha256-ni");
-MODULE_ALIAS_CRYPTO("sha224-ni");
-#endif
diff --git a/arch/x86/crypto/sha512-avx-asm.S b/arch/x86/crypto/sha512-avx-asm.S
deleted file mode 100644
index 5bfce4b045fd..000000000000
--- a/arch/x86/crypto/sha512-avx-asm.S
+++ /dev/null
@@ -1,423 +0,0 @@
-########################################################################
-# Implement fast SHA-512 with AVX instructions. (x86_64)
-#
-# Copyright (C) 2013 Intel Corporation.
-#
-# Authors:
-# James Guilford <james.guilford@intel.com>
-# Kirk Yap <kirk.s.yap@intel.com>
-# David Cote <david.m.cote@intel.com>
-# Tim Chen <tim.c.chen@linux.intel.com>
-#
-# This software is available to you under a choice of one of two
-# licenses. You may choose to be licensed under the terms of the GNU
-# General Public License (GPL) Version 2, available from the file
-# COPYING in the main directory of this source tree, or the
-# OpenIB.org BSD license below:
-#
-# Redistribution and use in source and binary forms, with or
-# without modification, are permitted provided that the following
-# conditions are met:
-#
-# - Redistributions of source code must retain the above
-# copyright notice, this list of conditions and the following
-# disclaimer.
-#
-# - Redistributions in binary form must reproduce the above
-# copyright notice, this list of conditions and the following
-# disclaimer in the documentation and/or other materials
-# provided with the distribution.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-#
-########################################################################
-#
-# This code is described in an Intel White-Paper:
-# "Fast SHA-512 Implementations on Intel Architecture Processors"
-#
-# To find it, surf to http://www.intel.com/p/en_US/embedded
-# and search for that title.
-#
-########################################################################
-
-#include <linux/linkage.h>
-#include <linux/cfi_types.h>
-
-.text
-
-# Virtual Registers
-# ARG1
-digest = %rdi
-# ARG2
-msg = %rsi
-# ARG3
-msglen = %rdx
-T1 = %rcx
-T2 = %r8
-a_64 = %r9
-b_64 = %r10
-c_64 = %r11
-d_64 = %r12
-e_64 = %r13
-f_64 = %r14
-g_64 = %r15
-h_64 = %rbx
-tmp0 = %rax
-
-# Local variables (stack frame)
-
-# Message Schedule
-W_SIZE = 80*8
-# W[t] + K[t] | W[t+1] + K[t+1]
-WK_SIZE = 2*8
-
-frame_W = 0
-frame_WK = frame_W + W_SIZE
-frame_size = frame_WK + WK_SIZE
-
-# Useful QWORD "arrays" for simpler memory references
-# MSG, DIGEST, K_t, W_t are arrays
-# WK_2(t) points to 1 of 2 qwords at frame.WK depending on t being odd/even
-
-# Input message (arg1)
-#define MSG(i) 8*i(msg)
-
-# Output Digest (arg2)
-#define DIGEST(i) 8*i(digest)
-
-# SHA Constants (static mem)
-#define K_t(i) 8*i+K512(%rip)
-
-# Message Schedule (stack frame)
-#define W_t(i) 8*i+frame_W(%rsp)
-
-# W[t]+K[t] (stack frame)
-#define WK_2(i) 8*((i%2))+frame_WK(%rsp)
-
-.macro RotateState
- # Rotate symbols a..h right
- TMP = h_64
- h_64 = g_64
- g_64 = f_64
- f_64 = e_64
- e_64 = d_64
- d_64 = c_64
- c_64 = b_64
- b_64 = a_64
- a_64 = TMP
-.endm
-
-.macro RORQ p1 p2
- # shld is faster than ror on Sandybridge
- shld $(64-\p2), \p1, \p1
-.endm
-
-.macro SHA512_Round rnd
- # Compute Round %%t
- mov f_64, T1 # T1 = f
- mov e_64, tmp0 # tmp = e
- xor g_64, T1 # T1 = f ^ g
- RORQ tmp0, 23 # 41 # tmp = e ror 23
- and e_64, T1 # T1 = (f ^ g) & e
- xor e_64, tmp0 # tmp = (e ror 23) ^ e
- xor g_64, T1 # T1 = ((f ^ g) & e) ^ g = CH(e,f,g)
- idx = \rnd
- add WK_2(idx), T1 # W[t] + K[t] from message scheduler
- RORQ tmp0, 4 # 18 # tmp = ((e ror 23) ^ e) ror 4
- xor e_64, tmp0 # tmp = (((e ror 23) ^ e) ror 4) ^ e
- mov a_64, T2 # T2 = a
- add h_64, T1 # T1 = CH(e,f,g) + W[t] + K[t] + h
- RORQ tmp0, 14 # 14 # tmp = ((((e ror23)^e)ror4)^e)ror14 = S1(e)
- add tmp0, T1 # T1 = CH(e,f,g) + W[t] + K[t] + S1(e)
- mov a_64, tmp0 # tmp = a
- xor c_64, T2 # T2 = a ^ c
- and c_64, tmp0 # tmp = a & c
- and b_64, T2 # T2 = (a ^ c) & b
- xor tmp0, T2 # T2 = ((a ^ c) & b) ^ (a & c) = Maj(a,b,c)
- mov a_64, tmp0 # tmp = a
- RORQ tmp0, 5 # 39 # tmp = a ror 5
- xor a_64, tmp0 # tmp = (a ror 5) ^ a
- add T1, d_64 # e(next_state) = d + T1
- RORQ tmp0, 6 # 34 # tmp = ((a ror 5) ^ a) ror 6
- xor a_64, tmp0 # tmp = (((a ror 5) ^ a) ror 6) ^ a
- lea (T1, T2), h_64 # a(next_state) = T1 + Maj(a,b,c)
- RORQ tmp0, 28 # 28 # tmp = ((((a ror5)^a)ror6)^a)ror28 = S0(a)
- add tmp0, h_64 # a(next_state) = T1 + Maj(a,b,c) S0(a)
- RotateState
-.endm
-
-.macro SHA512_2Sched_2Round_avx rnd
- # Compute rounds t-2 and t-1
- # Compute message schedule QWORDS t and t+1
-
- # Two rounds are computed based on the values for K[t-2]+W[t-2] and
- # K[t-1]+W[t-1] which were previously stored at WK_2 by the message
- # scheduler.
- # The two new schedule QWORDS are stored at [W_t(t)] and [W_t(t+1)].
- # They are then added to their respective SHA512 constants at
- # [K_t(t)] and [K_t(t+1)] and stored at dqword [WK_2(t)]
- # For brievity, the comments following vectored instructions only refer to
- # the first of a pair of QWORDS.
- # Eg. XMM4=W[t-2] really means XMM4={W[t-2]|W[t-1]}
- # The computation of the message schedule and the rounds are tightly
- # stitched to take advantage of instruction-level parallelism.
-
- idx = \rnd - 2
- vmovdqa W_t(idx), %xmm4 # XMM4 = W[t-2]
- idx = \rnd - 15
- vmovdqu W_t(idx), %xmm5 # XMM5 = W[t-15]
- mov f_64, T1
- vpsrlq $61, %xmm4, %xmm0 # XMM0 = W[t-2]>>61
- mov e_64, tmp0
- vpsrlq $1, %xmm5, %xmm6 # XMM6 = W[t-15]>>1
- xor g_64, T1
- RORQ tmp0, 23 # 41
- vpsrlq $19, %xmm4, %xmm1 # XMM1 = W[t-2]>>19
- and e_64, T1
- xor e_64, tmp0
- vpxor %xmm1, %xmm0, %xmm0 # XMM0 = W[t-2]>>61 ^ W[t-2]>>19
- xor g_64, T1
- idx = \rnd
- add WK_2(idx), T1#
- vpsrlq $8, %xmm5, %xmm7 # XMM7 = W[t-15]>>8
- RORQ tmp0, 4 # 18
- vpsrlq $6, %xmm4, %xmm2 # XMM2 = W[t-2]>>6
- xor e_64, tmp0
- mov a_64, T2
- add h_64, T1
- vpxor %xmm7, %xmm6, %xmm6 # XMM6 = W[t-15]>>1 ^ W[t-15]>>8
- RORQ tmp0, 14 # 14
- add tmp0, T1
- vpsrlq $7, %xmm5, %xmm8 # XMM8 = W[t-15]>>7
- mov a_64, tmp0
- xor c_64, T2
- vpsllq $(64-61), %xmm4, %xmm3 # XMM3 = W[t-2]<<3
- and c_64, tmp0
- and b_64, T2
- vpxor %xmm3, %xmm2, %xmm2 # XMM2 = W[t-2]>>6 ^ W[t-2]<<3
- xor tmp0, T2
- mov a_64, tmp0
- vpsllq $(64-1), %xmm5, %xmm9 # XMM9 = W[t-15]<<63
- RORQ tmp0, 5 # 39
- vpxor %xmm9, %xmm8, %xmm8 # XMM8 = W[t-15]>>7 ^ W[t-15]<<63
- xor a_64, tmp0
- add T1, d_64
- RORQ tmp0, 6 # 34
- xor a_64, tmp0
- vpxor %xmm8, %xmm6, %xmm6 # XMM6 = W[t-15]>>1 ^ W[t-15]>>8 ^
- # W[t-15]>>7 ^ W[t-15]<<63
- lea (T1, T2), h_64
- RORQ tmp0, 28 # 28
- vpsllq $(64-19), %xmm4, %xmm4 # XMM4 = W[t-2]<<25
- add tmp0, h_64
- RotateState
- vpxor %xmm4, %xmm0, %xmm0 # XMM0 = W[t-2]>>61 ^ W[t-2]>>19 ^
- # W[t-2]<<25
- mov f_64, T1
- vpxor %xmm2, %xmm0, %xmm0 # XMM0 = s1(W[t-2])
- mov e_64, tmp0
- xor g_64, T1
- idx = \rnd - 16
- vpaddq W_t(idx), %xmm0, %xmm0 # XMM0 = s1(W[t-2]) + W[t-16]
- idx = \rnd - 7
- vmovdqu W_t(idx), %xmm1 # XMM1 = W[t-7]
- RORQ tmp0, 23 # 41
- and e_64, T1
- xor e_64, tmp0
- xor g_64, T1
- vpsllq $(64-8), %xmm5, %xmm5 # XMM5 = W[t-15]<<56
- idx = \rnd + 1
- add WK_2(idx), T1
- vpxor %xmm5, %xmm6, %xmm6 # XMM6 = s0(W[t-15])
- RORQ tmp0, 4 # 18
- vpaddq %xmm6, %xmm0, %xmm0 # XMM0 = s1(W[t-2]) + W[t-16] + s0(W[t-15])
- xor e_64, tmp0
- vpaddq %xmm1, %xmm0, %xmm0 # XMM0 = W[t] = s1(W[t-2]) + W[t-7] +
- # s0(W[t-15]) + W[t-16]
- mov a_64, T2
- add h_64, T1
- RORQ tmp0, 14 # 14
- add tmp0, T1
- idx = \rnd
- vmovdqa %xmm0, W_t(idx) # Store W[t]
- vpaddq K_t(idx), %xmm0, %xmm0 # Compute W[t]+K[t]
- vmovdqa %xmm0, WK_2(idx) # Store W[t]+K[t] for next rounds
- mov a_64, tmp0
- xor c_64, T2
- and c_64, tmp0
- and b_64, T2
- xor tmp0, T2
- mov a_64, tmp0
- RORQ tmp0, 5 # 39
- xor a_64, tmp0
- add T1, d_64
- RORQ tmp0, 6 # 34
- xor a_64, tmp0
- lea (T1, T2), h_64
- RORQ tmp0, 28 # 28
- add tmp0, h_64
- RotateState
-.endm
-
-########################################################################
-# void sha512_transform_avx(sha512_state *state, const u8 *data, int blocks)
-# Purpose: Updates the SHA512 digest stored at "state" with the message
-# stored in "data".
-# The size of the message pointed to by "data" must be an integer multiple
-# of SHA512 message blocks.
-# "blocks" is the message length in SHA512 blocks
-########################################################################
-SYM_TYPED_FUNC_START(sha512_transform_avx)
- test msglen, msglen
- je .Lnowork
-
- # Save GPRs
- push %rbx
- push %r12
- push %r13
- push %r14
- push %r15
-
- # Allocate Stack Space
- push %rbp
- mov %rsp, %rbp
- sub $frame_size, %rsp
- and $~(0x20 - 1), %rsp
-
-.Lupdateblock:
-
- # Load state variables
- mov DIGEST(0), a_64
- mov DIGEST(1), b_64
- mov DIGEST(2), c_64
- mov DIGEST(3), d_64
- mov DIGEST(4), e_64
- mov DIGEST(5), f_64
- mov DIGEST(6), g_64
- mov DIGEST(7), h_64
-
- t = 0
- .rept 80/2 + 1
- # (80 rounds) / (2 rounds/iteration) + (1 iteration)
- # +1 iteration because the scheduler leads hashing by 1 iteration
- .if t < 2
- # BSWAP 2 QWORDS
- vmovdqa XMM_QWORD_BSWAP(%rip), %xmm1
- vmovdqu MSG(t), %xmm0
- vpshufb %xmm1, %xmm0, %xmm0 # BSWAP
- vmovdqa %xmm0, W_t(t) # Store Scheduled Pair
- vpaddq K_t(t), %xmm0, %xmm0 # Compute W[t]+K[t]
- vmovdqa %xmm0, WK_2(t) # Store into WK for rounds
- .elseif t < 16
- # BSWAP 2 QWORDS# Compute 2 Rounds
- vmovdqu MSG(t), %xmm0
- vpshufb %xmm1, %xmm0, %xmm0 # BSWAP
- SHA512_Round t-2 # Round t-2
- vmovdqa %xmm0, W_t(t) # Store Scheduled Pair
- vpaddq K_t(t), %xmm0, %xmm0 # Compute W[t]+K[t]
- SHA512_Round t-1 # Round t-1
- vmovdqa %xmm0, WK_2(t)# Store W[t]+K[t] into WK
- .elseif t < 79
- # Schedule 2 QWORDS# Compute 2 Rounds
- SHA512_2Sched_2Round_avx t
- .else
- # Compute 2 Rounds
- SHA512_Round t-2
- SHA512_Round t-1
- .endif
- t = t+2
- .endr
-
- # Update digest
- add a_64, DIGEST(0)
- add b_64, DIGEST(1)
- add c_64, DIGEST(2)
- add d_64, DIGEST(3)
- add e_64, DIGEST(4)
- add f_64, DIGEST(5)
- add g_64, DIGEST(6)
- add h_64, DIGEST(7)
-
- # Advance to next message block
- add $16*8, msg
- dec msglen
- jnz .Lupdateblock
-
- # Restore Stack Pointer
- mov %rbp, %rsp
- pop %rbp
-
- # Restore GPRs
- pop %r15
- pop %r14
- pop %r13
- pop %r12
- pop %rbx
-
-.Lnowork:
- RET
-SYM_FUNC_END(sha512_transform_avx)
-
-########################################################################
-### Binary Data
-
-.section .rodata.cst16.XMM_QWORD_BSWAP, "aM", @progbits, 16
-.align 16
-# Mask for byte-swapping a couple of qwords in an XMM register using (v)pshufb.
-XMM_QWORD_BSWAP:
- .octa 0x08090a0b0c0d0e0f0001020304050607
-
-# Mergeable 640-byte rodata section. This allows linker to merge the table
-# with other, exactly the same 640-byte fragment of another rodata section
-# (if such section exists).
-.section .rodata.cst640.K512, "aM", @progbits, 640
-.align 64
-# K[t] used in SHA512 hashing
-K512:
- .quad 0x428a2f98d728ae22,0x7137449123ef65cd
- .quad 0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc
- .quad 0x3956c25bf348b538,0x59f111f1b605d019
- .quad 0x923f82a4af194f9b,0xab1c5ed5da6d8118
- .quad 0xd807aa98a3030242,0x12835b0145706fbe
- .quad 0x243185be4ee4b28c,0x550c7dc3d5ffb4e2
- .quad 0x72be5d74f27b896f,0x80deb1fe3b1696b1
- .quad 0x9bdc06a725c71235,0xc19bf174cf692694
- .quad 0xe49b69c19ef14ad2,0xefbe4786384f25e3
- .quad 0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65
- .quad 0x2de92c6f592b0275,0x4a7484aa6ea6e483
- .quad 0x5cb0a9dcbd41fbd4,0x76f988da831153b5
- .quad 0x983e5152ee66dfab,0xa831c66d2db43210
- .quad 0xb00327c898fb213f,0xbf597fc7beef0ee4
- .quad 0xc6e00bf33da88fc2,0xd5a79147930aa725
- .quad 0x06ca6351e003826f,0x142929670a0e6e70
- .quad 0x27b70a8546d22ffc,0x2e1b21385c26c926
- .quad 0x4d2c6dfc5ac42aed,0x53380d139d95b3df
- .quad 0x650a73548baf63de,0x766a0abb3c77b2a8
- .quad 0x81c2c92e47edaee6,0x92722c851482353b
- .quad 0xa2bfe8a14cf10364,0xa81a664bbc423001
- .quad 0xc24b8b70d0f89791,0xc76c51a30654be30
- .quad 0xd192e819d6ef5218,0xd69906245565a910
- .quad 0xf40e35855771202a,0x106aa07032bbd1b8
- .quad 0x19a4c116b8d2d0c8,0x1e376c085141ab53
- .quad 0x2748774cdf8eeb99,0x34b0bcb5e19b48a8
- .quad 0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb
- .quad 0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3
- .quad 0x748f82ee5defb2fc,0x78a5636f43172f60
- .quad 0x84c87814a1f0ab72,0x8cc702081a6439ec
- .quad 0x90befffa23631e28,0xa4506cebde82bde9
- .quad 0xbef9a3f7b2c67915,0xc67178f2e372532b
- .quad 0xca273eceea26619c,0xd186b8c721c0c207
- .quad 0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178
- .quad 0x06f067aa72176fba,0x0a637dc5a2c898a6
- .quad 0x113f9804bef90dae,0x1b710b35131c471b
- .quad 0x28db77f523047d84,0x32caab7b40c72493
- .quad 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c
- .quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a
- .quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817
diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S
deleted file mode 100644
index 24973f42c43f..000000000000
--- a/arch/x86/crypto/sha512-avx2-asm.S
+++ /dev/null
@@ -1,750 +0,0 @@
-########################################################################
-# Implement fast SHA-512 with AVX2 instructions. (x86_64)
-#
-# Copyright (C) 2013 Intel Corporation.
-#
-# Authors:
-# James Guilford <james.guilford@intel.com>
-# Kirk Yap <kirk.s.yap@intel.com>
-# David Cote <david.m.cote@intel.com>
-# Tim Chen <tim.c.chen@linux.intel.com>
-#
-# This software is available to you under a choice of one of two
-# licenses. You may choose to be licensed under the terms of the GNU
-# General Public License (GPL) Version 2, available from the file
-# COPYING in the main directory of this source tree, or the
-# OpenIB.org BSD license below:
-#
-# Redistribution and use in source and binary forms, with or
-# without modification, are permitted provided that the following
-# conditions are met:
-#
-# - Redistributions of source code must retain the above
-# copyright notice, this list of conditions and the following
-# disclaimer.
-#
-# - Redistributions in binary form must reproduce the above
-# copyright notice, this list of conditions and the following
-# disclaimer in the documentation and/or other materials
-# provided with the distribution.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-#
-########################################################################
-#
-# This code is described in an Intel White-Paper:
-# "Fast SHA-512 Implementations on Intel Architecture Processors"
-#
-# To find it, surf to http://www.intel.com/p/en_US/embedded
-# and search for that title.
-#
-########################################################################
-# This code schedules 1 blocks at a time, with 4 lanes per block
-########################################################################
-
-#include <linux/linkage.h>
-#include <linux/cfi_types.h>
-
-.text
-
-# Virtual Registers
-Y_0 = %ymm4
-Y_1 = %ymm5
-Y_2 = %ymm6
-Y_3 = %ymm7
-
-YTMP0 = %ymm0
-YTMP1 = %ymm1
-YTMP2 = %ymm2
-YTMP3 = %ymm3
-YTMP4 = %ymm8
-XFER = YTMP0
-
-BYTE_FLIP_MASK = %ymm9
-
-# 1st arg is %rdi, which is saved to the stack and accessed later via %r12
-CTX1 = %rdi
-CTX2 = %r12
-# 2nd arg
-INP = %rsi
-# 3rd arg
-NUM_BLKS = %rdx
-
-c = %rcx
-d = %r8
-e = %rdx
-y3 = %rsi
-
-TBL = %rdi # clobbers CTX1
-
-a = %rax
-b = %rbx
-
-f = %r9
-g = %r10
-h = %r11
-old_h = %r11
-
-T1 = %r12 # clobbers CTX2
-y0 = %r13
-y1 = %r14
-y2 = %r15
-
-# Local variables (stack frame)
-XFER_SIZE = 4*8
-SRND_SIZE = 1*8
-INP_SIZE = 1*8
-INPEND_SIZE = 1*8
-CTX_SIZE = 1*8
-
-frame_XFER = 0
-frame_SRND = frame_XFER + XFER_SIZE
-frame_INP = frame_SRND + SRND_SIZE
-frame_INPEND = frame_INP + INP_SIZE
-frame_CTX = frame_INPEND + INPEND_SIZE
-frame_size = frame_CTX + CTX_SIZE
-
-## assume buffers not aligned
-#define VMOVDQ vmovdqu
-
-# addm [mem], reg
-# Add reg to mem using reg-mem add and store
-.macro addm p1 p2
- add \p1, \p2
- mov \p2, \p1
-.endm
-
-
-# COPY_YMM_AND_BSWAP ymm, [mem], byte_flip_mask
-# Load ymm with mem and byte swap each dword
-.macro COPY_YMM_AND_BSWAP p1 p2 p3
- VMOVDQ \p2, \p1
- vpshufb \p3, \p1, \p1
-.endm
-# rotate_Ys
-# Rotate values of symbols Y0...Y3
-.macro rotate_Ys
- Y_ = Y_0
- Y_0 = Y_1
- Y_1 = Y_2
- Y_2 = Y_3
- Y_3 = Y_
-.endm
-
-# RotateState
-.macro RotateState
- # Rotate symbols a..h right
- old_h = h
- TMP_ = h
- h = g
- g = f
- f = e
- e = d
- d = c
- c = b
- b = a
- a = TMP_
-.endm
-
-# macro MY_VPALIGNR YDST, YSRC1, YSRC2, RVAL
-# YDST = {YSRC1, YSRC2} >> RVAL*8
-.macro MY_VPALIGNR YDST YSRC1 YSRC2 RVAL
- vperm2f128 $0x3, \YSRC2, \YSRC1, \YDST # YDST = {YS1_LO, YS2_HI}
- vpalignr $\RVAL, \YSRC2, \YDST, \YDST # YDST = {YDS1, YS2} >> RVAL*8
-.endm
-
-.macro FOUR_ROUNDS_AND_SCHED
-################################### RND N + 0 #########################################
-
- # Extract w[t-7]
- MY_VPALIGNR YTMP0, Y_3, Y_2, 8 # YTMP0 = W[-7]
- # Calculate w[t-16] + w[t-7]
- vpaddq Y_0, YTMP0, YTMP0 # YTMP0 = W[-7] + W[-16]
- # Extract w[t-15]
- MY_VPALIGNR YTMP1, Y_1, Y_0, 8 # YTMP1 = W[-15]
-
- # Calculate sigma0
-
- # Calculate w[t-15] ror 1
- vpsrlq $1, YTMP1, YTMP2
- vpsllq $(64-1), YTMP1, YTMP3
- vpor YTMP2, YTMP3, YTMP3 # YTMP3 = W[-15] ror 1
- # Calculate w[t-15] shr 7
- vpsrlq $7, YTMP1, YTMP4 # YTMP4 = W[-15] >> 7
-
- mov a, y3 # y3 = a # MAJA
- rorx $41, e, y0 # y0 = e >> 41 # S1A
- rorx $18, e, y1 # y1 = e >> 18 # S1B
- add frame_XFER(%rsp),h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
- mov f, y2 # y2 = f # CH
- rorx $34, a, T1 # T1 = a >> 34 # S0B
-
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) # S1
- xor g, y2 # y2 = f^g # CH
- rorx $14, e, y1 # y1 = (e >> 14) # S1
-
- and e, y2 # y2 = (f^g)&e # CH
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) ^ (e>>14) # S1
- rorx $39, a, y1 # y1 = a >> 39 # S0A
- add h, d # d = k + w + h + d # --
-
- and b, y3 # y3 = (a|c)&b # MAJA
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) # S0
- rorx $28, a, T1 # T1 = (a >> 28) # S0
-
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) ^ (a>>28) # S0
- mov a, T1 # T1 = a # MAJB
- and c, T1 # T1 = a&c # MAJB
-
- add y0, y2 # y2 = S1 + CH # --
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
-
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
-
- add y2, h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- add y3, h # h = t1 + S0 + MAJ # --
-
- RotateState
-
-################################### RND N + 1 #########################################
-
- # Calculate w[t-15] ror 8
- vpsrlq $8, YTMP1, YTMP2
- vpsllq $(64-8), YTMP1, YTMP1
- vpor YTMP2, YTMP1, YTMP1 # YTMP1 = W[-15] ror 8
- # XOR the three components
- vpxor YTMP4, YTMP3, YTMP3 # YTMP3 = W[-15] ror 1 ^ W[-15] >> 7
- vpxor YTMP1, YTMP3, YTMP1 # YTMP1 = s0
-
-
- # Add three components, w[t-16], w[t-7] and sigma0
- vpaddq YTMP1, YTMP0, YTMP0 # YTMP0 = W[-16] + W[-7] + s0
- # Move to appropriate lanes for calculating w[16] and w[17]
- vperm2f128 $0x0, YTMP0, YTMP0, Y_0 # Y_0 = W[-16] + W[-7] + s0 {BABA}
- # Move to appropriate lanes for calculating w[18] and w[19]
- vpand MASK_YMM_LO(%rip), YTMP0, YTMP0 # YTMP0 = W[-16] + W[-7] + s0 {DC00}
-
- # Calculate w[16] and w[17] in both 128 bit lanes
-
- # Calculate sigma1 for w[16] and w[17] on both 128 bit lanes
- vperm2f128 $0x11, Y_3, Y_3, YTMP2 # YTMP2 = W[-2] {BABA}
- vpsrlq $6, YTMP2, YTMP4 # YTMP4 = W[-2] >> 6 {BABA}
-
-
- mov a, y3 # y3 = a # MAJA
- rorx $41, e, y0 # y0 = e >> 41 # S1A
- rorx $18, e, y1 # y1 = e >> 18 # S1B
- add 1*8+frame_XFER(%rsp), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
-
- mov f, y2 # y2 = f # CH
- rorx $34, a, T1 # T1 = a >> 34 # S0B
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) # S1
- xor g, y2 # y2 = f^g # CH
-
-
- rorx $14, e, y1 # y1 = (e >> 14) # S1
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) ^ (e>>14) # S1
- rorx $39, a, y1 # y1 = a >> 39 # S0A
- and e, y2 # y2 = (f^g)&e # CH
- add h, d # d = k + w + h + d # --
-
- and b, y3 # y3 = (a|c)&b # MAJA
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) # S0
-
- rorx $28, a, T1 # T1 = (a >> 28) # S0
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) ^ (a>>28) # S0
- mov a, T1 # T1 = a # MAJB
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
-
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
-
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
- add y2, h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- add y3, h # h = t1 + S0 + MAJ # --
-
- RotateState
-
-
-################################### RND N + 2 #########################################
-
- vpsrlq $19, YTMP2, YTMP3 # YTMP3 = W[-2] >> 19 {BABA}
- vpsllq $(64-19), YTMP2, YTMP1 # YTMP1 = W[-2] << 19 {BABA}
- vpor YTMP1, YTMP3, YTMP3 # YTMP3 = W[-2] ror 19 {BABA}
- vpxor YTMP3, YTMP4, YTMP4 # YTMP4 = W[-2] ror 19 ^ W[-2] >> 6 {BABA}
- vpsrlq $61, YTMP2, YTMP3 # YTMP3 = W[-2] >> 61 {BABA}
- vpsllq $(64-61), YTMP2, YTMP1 # YTMP1 = W[-2] << 61 {BABA}
- vpor YTMP1, YTMP3, YTMP3 # YTMP3 = W[-2] ror 61 {BABA}
- vpxor YTMP3, YTMP4, YTMP4 # YTMP4 = s1 = (W[-2] ror 19) ^
- # (W[-2] ror 61) ^ (W[-2] >> 6) {BABA}
-
- # Add sigma1 to the other compunents to get w[16] and w[17]
- vpaddq YTMP4, Y_0, Y_0 # Y_0 = {W[1], W[0], W[1], W[0]}
-
- # Calculate sigma1 for w[18] and w[19] for upper 128 bit lane
- vpsrlq $6, Y_0, YTMP4 # YTMP4 = W[-2] >> 6 {DC--}
-
- mov a, y3 # y3 = a # MAJA
- rorx $41, e, y0 # y0 = e >> 41 # S1A
- add 2*8+frame_XFER(%rsp), h # h = k + w + h # --
-
- rorx $18, e, y1 # y1 = e >> 18 # S1B
- or c, y3 # y3 = a|c # MAJA
- mov f, y2 # y2 = f # CH
- xor g, y2 # y2 = f^g # CH
-
- rorx $34, a, T1 # T1 = a >> 34 # S0B
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) # S1
- and e, y2 # y2 = (f^g)&e # CH
-
- rorx $14, e, y1 # y1 = (e >> 14) # S1
- add h, d # d = k + w + h + d # --
- and b, y3 # y3 = (a|c)&b # MAJA
-
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) ^ (e>>14) # S1
- rorx $39, a, y1 # y1 = a >> 39 # S0A
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) # S0
- rorx $28, a, T1 # T1 = (a >> 28) # S0
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) ^ (a>>28) # S0
- mov a, T1 # T1 = a # MAJB
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
-
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
- add y2, h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
-
- add y3, h # h = t1 + S0 + MAJ # --
-
- RotateState
-
-################################### RND N + 3 #########################################
-
- vpsrlq $19, Y_0, YTMP3 # YTMP3 = W[-2] >> 19 {DC--}
- vpsllq $(64-19), Y_0, YTMP1 # YTMP1 = W[-2] << 19 {DC--}
- vpor YTMP1, YTMP3, YTMP3 # YTMP3 = W[-2] ror 19 {DC--}
- vpxor YTMP3, YTMP4, YTMP4 # YTMP4 = W[-2] ror 19 ^ W[-2] >> 6 {DC--}
- vpsrlq $61, Y_0, YTMP3 # YTMP3 = W[-2] >> 61 {DC--}
- vpsllq $(64-61), Y_0, YTMP1 # YTMP1 = W[-2] << 61 {DC--}
- vpor YTMP1, YTMP3, YTMP3 # YTMP3 = W[-2] ror 61 {DC--}
- vpxor YTMP3, YTMP4, YTMP4 # YTMP4 = s1 = (W[-2] ror 19) ^
- # (W[-2] ror 61) ^ (W[-2] >> 6) {DC--}
-
- # Add the sigma0 + w[t-7] + w[t-16] for w[18] and w[19]
- # to newly calculated sigma1 to get w[18] and w[19]
- vpaddq YTMP4, YTMP0, YTMP2 # YTMP2 = {W[3], W[2], --, --}
-
- # Form w[19, w[18], w17], w[16]
- vpblendd $0xF0, YTMP2, Y_0, Y_0 # Y_0 = {W[3], W[2], W[1], W[0]}
-
- mov a, y3 # y3 = a # MAJA
- rorx $41, e, y0 # y0 = e >> 41 # S1A
- rorx $18, e, y1 # y1 = e >> 18 # S1B
- add 3*8+frame_XFER(%rsp), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
-
- mov f, y2 # y2 = f # CH
- rorx $34, a, T1 # T1 = a >> 34 # S0B
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) # S1
- xor g, y2 # y2 = f^g # CH
-
-
- rorx $14, e, y1 # y1 = (e >> 14) # S1
- and e, y2 # y2 = (f^g)&e # CH
- add h, d # d = k + w + h + d # --
- and b, y3 # y3 = (a|c)&b # MAJA
-
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) ^ (e>>14) # S1
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
-
- rorx $39, a, y1 # y1 = a >> 39 # S0A
- add y0, y2 # y2 = S1 + CH # --
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) # S0
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
-
- rorx $28, a, T1 # T1 = (a >> 28) # S0
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) ^ (a>>28) # S0
- mov a, T1 # T1 = a # MAJB
- and c, T1 # T1 = a&c # MAJB
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
-
- add y1, h # h = k + w + h + S0 # --
- add y2, h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- add y3, h # h = t1 + S0 + MAJ # --
-
- RotateState
-
- rotate_Ys
-.endm
-
-.macro DO_4ROUNDS
-
-################################### RND N + 0 #########################################
-
- mov f, y2 # y2 = f # CH
- rorx $41, e, y0 # y0 = e >> 41 # S1A
- rorx $18, e, y1 # y1 = e >> 18 # S1B
- xor g, y2 # y2 = f^g # CH
-
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) # S1
- rorx $14, e, y1 # y1 = (e >> 14) # S1
- and e, y2 # y2 = (f^g)&e # CH
-
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) ^ (e>>14) # S1
- rorx $34, a, T1 # T1 = a >> 34 # S0B
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
- rorx $39, a, y1 # y1 = a >> 39 # S0A
- mov a, y3 # y3 = a # MAJA
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) # S0
- rorx $28, a, T1 # T1 = (a >> 28) # S0
- add frame_XFER(%rsp), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) ^ (a>>28) # S0
- mov a, T1 # T1 = a # MAJB
- and b, y3 # y3 = (a|c)&b # MAJA
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
-
- add h, d # d = k + w + h + d # --
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
-
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
-
- RotateState
-
-################################### RND N + 1 #########################################
-
- add y2, old_h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- mov f, y2 # y2 = f # CH
- rorx $41, e, y0 # y0 = e >> 41 # S1A
- rorx $18, e, y1 # y1 = e >> 18 # S1B
- xor g, y2 # y2 = f^g # CH
-
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) # S1
- rorx $14, e, y1 # y1 = (e >> 14) # S1
- and e, y2 # y2 = (f^g)&e # CH
- add y3, old_h # h = t1 + S0 + MAJ # --
-
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) ^ (e>>14) # S1
- rorx $34, a, T1 # T1 = a >> 34 # S0B
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
- rorx $39, a, y1 # y1 = a >> 39 # S0A
- mov a, y3 # y3 = a # MAJA
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) # S0
- rorx $28, a, T1 # T1 = (a >> 28) # S0
- add 8*1+frame_XFER(%rsp), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) ^ (a>>28) # S0
- mov a, T1 # T1 = a # MAJB
- and b, y3 # y3 = (a|c)&b # MAJA
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
-
- add h, d # d = k + w + h + d # --
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
-
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
-
- RotateState
-
-################################### RND N + 2 #########################################
-
- add y2, old_h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- mov f, y2 # y2 = f # CH
- rorx $41, e, y0 # y0 = e >> 41 # S1A
- rorx $18, e, y1 # y1 = e >> 18 # S1B
- xor g, y2 # y2 = f^g # CH
-
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) # S1
- rorx $14, e, y1 # y1 = (e >> 14) # S1
- and e, y2 # y2 = (f^g)&e # CH
- add y3, old_h # h = t1 + S0 + MAJ # --
-
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) ^ (e>>14) # S1
- rorx $34, a, T1 # T1 = a >> 34 # S0B
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
- rorx $39, a, y1 # y1 = a >> 39 # S0A
- mov a, y3 # y3 = a # MAJA
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) # S0
- rorx $28, a, T1 # T1 = (a >> 28) # S0
- add 8*2+frame_XFER(%rsp), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) ^ (a>>28) # S0
- mov a, T1 # T1 = a # MAJB
- and b, y3 # y3 = (a|c)&b # MAJA
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
-
- add h, d # d = k + w + h + d # --
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
-
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
-
- RotateState
-
-################################### RND N + 3 #########################################
-
- add y2, old_h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
- mov f, y2 # y2 = f # CH
- rorx $41, e, y0 # y0 = e >> 41 # S1A
- rorx $18, e, y1 # y1 = e >> 18 # S1B
- xor g, y2 # y2 = f^g # CH
-
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) # S1
- rorx $14, e, y1 # y1 = (e >> 14) # S1
- and e, y2 # y2 = (f^g)&e # CH
- add y3, old_h # h = t1 + S0 + MAJ # --
-
- xor y1, y0 # y0 = (e>>41) ^ (e>>18) ^ (e>>14) # S1
- rorx $34, a, T1 # T1 = a >> 34 # S0B
- xor g, y2 # y2 = CH = ((f^g)&e)^g # CH
- rorx $39, a, y1 # y1 = a >> 39 # S0A
- mov a, y3 # y3 = a # MAJA
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) # S0
- rorx $28, a, T1 # T1 = (a >> 28) # S0
- add 8*3+frame_XFER(%rsp), h # h = k + w + h # --
- or c, y3 # y3 = a|c # MAJA
-
- xor T1, y1 # y1 = (a>>39) ^ (a>>34) ^ (a>>28) # S0
- mov a, T1 # T1 = a # MAJB
- and b, y3 # y3 = (a|c)&b # MAJA
- and c, T1 # T1 = a&c # MAJB
- add y0, y2 # y2 = S1 + CH # --
-
-
- add h, d # d = k + w + h + d # --
- or T1, y3 # y3 = MAJ = (a|c)&b)|(a&c) # MAJ
- add y1, h # h = k + w + h + S0 # --
-
- add y2, d # d = k + w + h + d + S1 + CH = d + t1 # --
-
- add y2, h # h = k + w + h + S0 + S1 + CH = t1 + S0# --
-
- add y3, h # h = t1 + S0 + MAJ # --
-
- RotateState
-
-.endm
-
-########################################################################
-# void sha512_transform_rorx(sha512_state *state, const u8 *data, int blocks)
-# Purpose: Updates the SHA512 digest stored at "state" with the message
-# stored in "data".
-# The size of the message pointed to by "data" must be an integer multiple
-# of SHA512 message blocks.
-# "blocks" is the message length in SHA512 blocks
-########################################################################
-SYM_TYPED_FUNC_START(sha512_transform_rorx)
- # Save GPRs
- push %rbx
- push %r12
- push %r13
- push %r14
- push %r15
-
- # Allocate Stack Space
- push %rbp
- mov %rsp, %rbp
- sub $frame_size, %rsp
- and $~(0x20 - 1), %rsp
-
- shl $7, NUM_BLKS # convert to bytes
- jz .Ldone_hash
- add INP, NUM_BLKS # pointer to end of data
- mov NUM_BLKS, frame_INPEND(%rsp)
-
- ## load initial digest
- mov 8*0(CTX1), a
- mov 8*1(CTX1), b
- mov 8*2(CTX1), c
- mov 8*3(CTX1), d
- mov 8*4(CTX1), e
- mov 8*5(CTX1), f
- mov 8*6(CTX1), g
- mov 8*7(CTX1), h
-
- # save %rdi (CTX) before it gets clobbered
- mov %rdi, frame_CTX(%rsp)
-
- vmovdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), BYTE_FLIP_MASK
-
-.Lloop0:
- lea K512(%rip), TBL
-
- ## byte swap first 16 dwords
- COPY_YMM_AND_BSWAP Y_0, (INP), BYTE_FLIP_MASK
- COPY_YMM_AND_BSWAP Y_1, 1*32(INP), BYTE_FLIP_MASK
- COPY_YMM_AND_BSWAP Y_2, 2*32(INP), BYTE_FLIP_MASK
- COPY_YMM_AND_BSWAP Y_3, 3*32(INP), BYTE_FLIP_MASK
-
- mov INP, frame_INP(%rsp)
-
- ## schedule 64 input dwords, by doing 12 rounds of 4 each
- movq $4, frame_SRND(%rsp)
-
-.align 16
-.Lloop1:
- vpaddq (TBL), Y_0, XFER
- vmovdqa XFER, frame_XFER(%rsp)
- FOUR_ROUNDS_AND_SCHED
-
- vpaddq 1*32(TBL), Y_0, XFER
- vmovdqa XFER, frame_XFER(%rsp)
- FOUR_ROUNDS_AND_SCHED
-
- vpaddq 2*32(TBL), Y_0, XFER
- vmovdqa XFER, frame_XFER(%rsp)
- FOUR_ROUNDS_AND_SCHED
-
- vpaddq 3*32(TBL), Y_0, XFER
- vmovdqa XFER, frame_XFER(%rsp)
- add $(4*32), TBL
- FOUR_ROUNDS_AND_SCHED
-
- subq $1, frame_SRND(%rsp)
- jne .Lloop1
-
- movq $2, frame_SRND(%rsp)
-.Lloop2:
- vpaddq (TBL), Y_0, XFER
- vmovdqa XFER, frame_XFER(%rsp)
- DO_4ROUNDS
- vpaddq 1*32(TBL), Y_1, XFER
- vmovdqa XFER, frame_XFER(%rsp)
- add $(2*32), TBL
- DO_4ROUNDS
-
- vmovdqa Y_2, Y_0
- vmovdqa Y_3, Y_1
-
- subq $1, frame_SRND(%rsp)
- jne .Lloop2
-
- mov frame_CTX(%rsp), CTX2
- addm 8*0(CTX2), a
- addm 8*1(CTX2), b
- addm 8*2(CTX2), c
- addm 8*3(CTX2), d
- addm 8*4(CTX2), e
- addm 8*5(CTX2), f
- addm 8*6(CTX2), g
- addm 8*7(CTX2), h
-
- mov frame_INP(%rsp), INP
- add $128, INP
- cmp frame_INPEND(%rsp), INP
- jne .Lloop0
-
-.Ldone_hash:
-
- # Restore Stack Pointer
- mov %rbp, %rsp
- pop %rbp
-
- # Restore GPRs
- pop %r15
- pop %r14
- pop %r13
- pop %r12
- pop %rbx
-
- vzeroupper
- RET
-SYM_FUNC_END(sha512_transform_rorx)
-
-########################################################################
-### Binary Data
-
-
-# Mergeable 640-byte rodata section. This allows linker to merge the table
-# with other, exactly the same 640-byte fragment of another rodata section
-# (if such section exists).
-.section .rodata.cst640.K512, "aM", @progbits, 640
-.align 64
-# K[t] used in SHA512 hashing
-K512:
- .quad 0x428a2f98d728ae22,0x7137449123ef65cd
- .quad 0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc
- .quad 0x3956c25bf348b538,0x59f111f1b605d019
- .quad 0x923f82a4af194f9b,0xab1c5ed5da6d8118
- .quad 0xd807aa98a3030242,0x12835b0145706fbe
- .quad 0x243185be4ee4b28c,0x550c7dc3d5ffb4e2
- .quad 0x72be5d74f27b896f,0x80deb1fe3b1696b1
- .quad 0x9bdc06a725c71235,0xc19bf174cf692694
- .quad 0xe49b69c19ef14ad2,0xefbe4786384f25e3
- .quad 0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65
- .quad 0x2de92c6f592b0275,0x4a7484aa6ea6e483
- .quad 0x5cb0a9dcbd41fbd4,0x76f988da831153b5
- .quad 0x983e5152ee66dfab,0xa831c66d2db43210
- .quad 0xb00327c898fb213f,0xbf597fc7beef0ee4
- .quad 0xc6e00bf33da88fc2,0xd5a79147930aa725
- .quad 0x06ca6351e003826f,0x142929670a0e6e70
- .quad 0x27b70a8546d22ffc,0x2e1b21385c26c926
- .quad 0x4d2c6dfc5ac42aed,0x53380d139d95b3df
- .quad 0x650a73548baf63de,0x766a0abb3c77b2a8
- .quad 0x81c2c92e47edaee6,0x92722c851482353b
- .quad 0xa2bfe8a14cf10364,0xa81a664bbc423001
- .quad 0xc24b8b70d0f89791,0xc76c51a30654be30
- .quad 0xd192e819d6ef5218,0xd69906245565a910
- .quad 0xf40e35855771202a,0x106aa07032bbd1b8
- .quad 0x19a4c116b8d2d0c8,0x1e376c085141ab53
- .quad 0x2748774cdf8eeb99,0x34b0bcb5e19b48a8
- .quad 0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb
- .quad 0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3
- .quad 0x748f82ee5defb2fc,0x78a5636f43172f60
- .quad 0x84c87814a1f0ab72,0x8cc702081a6439ec
- .quad 0x90befffa23631e28,0xa4506cebde82bde9
- .quad 0xbef9a3f7b2c67915,0xc67178f2e372532b
- .quad 0xca273eceea26619c,0xd186b8c721c0c207
- .quad 0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178
- .quad 0x06f067aa72176fba,0x0a637dc5a2c898a6
- .quad 0x113f9804bef90dae,0x1b710b35131c471b
- .quad 0x28db77f523047d84,0x32caab7b40c72493
- .quad 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c
- .quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a
- .quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817
-
-.section .rodata.cst32.PSHUFFLE_BYTE_FLIP_MASK, "aM", @progbits, 32
-.align 32
-# Mask for byte-swapping a couple of qwords in an XMM register using (v)pshufb.
-PSHUFFLE_BYTE_FLIP_MASK:
- .octa 0x08090a0b0c0d0e0f0001020304050607
- .octa 0x18191a1b1c1d1e1f1011121314151617
-
-.section .rodata.cst32.MASK_YMM_LO, "aM", @progbits, 32
-.align 32
-MASK_YMM_LO:
- .octa 0x00000000000000000000000000000000
- .octa 0xFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF
diff --git a/arch/x86/crypto/sha512-ssse3-asm.S b/arch/x86/crypto/sha512-ssse3-asm.S
deleted file mode 100644
index 30a2c4777f9d..000000000000
--- a/arch/x86/crypto/sha512-ssse3-asm.S
+++ /dev/null
@@ -1,425 +0,0 @@
-########################################################################
-# Implement fast SHA-512 with SSSE3 instructions. (x86_64)
-#
-# Copyright (C) 2013 Intel Corporation.
-#
-# Authors:
-# James Guilford <james.guilford@intel.com>
-# Kirk Yap <kirk.s.yap@intel.com>
-# David Cote <david.m.cote@intel.com>
-# Tim Chen <tim.c.chen@linux.intel.com>
-#
-# This software is available to you under a choice of one of two
-# licenses. You may choose to be licensed under the terms of the GNU
-# General Public License (GPL) Version 2, available from the file
-# COPYING in the main directory of this source tree, or the
-# OpenIB.org BSD license below:
-#
-# Redistribution and use in source and binary forms, with or
-# without modification, are permitted provided that the following
-# conditions are met:
-#
-# - Redistributions of source code must retain the above
-# copyright notice, this list of conditions and the following
-# disclaimer.
-#
-# - Redistributions in binary form must reproduce the above
-# copyright notice, this list of conditions and the following
-# disclaimer in the documentation and/or other materials
-# provided with the distribution.
-#
-# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
-# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
-# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
-# NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
-# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
-# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
-# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-# SOFTWARE.
-#
-########################################################################
-#
-# This code is described in an Intel White-Paper:
-# "Fast SHA-512 Implementations on Intel Architecture Processors"
-#
-# To find it, surf to http://www.intel.com/p/en_US/embedded
-# and search for that title.
-#
-########################################################################
-
-#include <linux/linkage.h>
-#include <linux/cfi_types.h>
-
-.text
-
-# Virtual Registers
-# ARG1
-digest = %rdi
-# ARG2
-msg = %rsi
-# ARG3
-msglen = %rdx
-T1 = %rcx
-T2 = %r8
-a_64 = %r9
-b_64 = %r10
-c_64 = %r11
-d_64 = %r12
-e_64 = %r13
-f_64 = %r14
-g_64 = %r15
-h_64 = %rbx
-tmp0 = %rax
-
-# Local variables (stack frame)
-
-W_SIZE = 80*8
-WK_SIZE = 2*8
-
-frame_W = 0
-frame_WK = frame_W + W_SIZE
-frame_size = frame_WK + WK_SIZE
-
-# Useful QWORD "arrays" for simpler memory references
-# MSG, DIGEST, K_t, W_t are arrays
-# WK_2(t) points to 1 of 2 qwords at frame.WK depending on t being odd/even
-
-# Input message (arg1)
-#define MSG(i) 8*i(msg)
-
-# Output Digest (arg2)
-#define DIGEST(i) 8*i(digest)
-
-# SHA Constants (static mem)
-#define K_t(i) 8*i+K512(%rip)
-
-# Message Schedule (stack frame)
-#define W_t(i) 8*i+frame_W(%rsp)
-
-# W[t]+K[t] (stack frame)
-#define WK_2(i) 8*((i%2))+frame_WK(%rsp)
-
-.macro RotateState
- # Rotate symbols a..h right
- TMP = h_64
- h_64 = g_64
- g_64 = f_64
- f_64 = e_64
- e_64 = d_64
- d_64 = c_64
- c_64 = b_64
- b_64 = a_64
- a_64 = TMP
-.endm
-
-.macro SHA512_Round rnd
-
- # Compute Round %%t
- mov f_64, T1 # T1 = f
- mov e_64, tmp0 # tmp = e
- xor g_64, T1 # T1 = f ^ g
- ror $23, tmp0 # 41 # tmp = e ror 23
- and e_64, T1 # T1 = (f ^ g) & e
- xor e_64, tmp0 # tmp = (e ror 23) ^ e
- xor g_64, T1 # T1 = ((f ^ g) & e) ^ g = CH(e,f,g)
- idx = \rnd
- add WK_2(idx), T1 # W[t] + K[t] from message scheduler
- ror $4, tmp0 # 18 # tmp = ((e ror 23) ^ e) ror 4
- xor e_64, tmp0 # tmp = (((e ror 23) ^ e) ror 4) ^ e
- mov a_64, T2 # T2 = a
- add h_64, T1 # T1 = CH(e,f,g) + W[t] + K[t] + h
- ror $14, tmp0 # 14 # tmp = ((((e ror23)^e)ror4)^e)ror14 = S1(e)
- add tmp0, T1 # T1 = CH(e,f,g) + W[t] + K[t] + S1(e)
- mov a_64, tmp0 # tmp = a
- xor c_64, T2 # T2 = a ^ c
- and c_64, tmp0 # tmp = a & c
- and b_64, T2 # T2 = (a ^ c) & b
- xor tmp0, T2 # T2 = ((a ^ c) & b) ^ (a & c) = Maj(a,b,c)
- mov a_64, tmp0 # tmp = a
- ror $5, tmp0 # 39 # tmp = a ror 5
- xor a_64, tmp0 # tmp = (a ror 5) ^ a
- add T1, d_64 # e(next_state) = d + T1
- ror $6, tmp0 # 34 # tmp = ((a ror 5) ^ a) ror 6
- xor a_64, tmp0 # tmp = (((a ror 5) ^ a) ror 6) ^ a
- lea (T1, T2), h_64 # a(next_state) = T1 + Maj(a,b,c)
- ror $28, tmp0 # 28 # tmp = ((((a ror5)^a)ror6)^a)ror28 = S0(a)
- add tmp0, h_64 # a(next_state) = T1 + Maj(a,b,c) S0(a)
- RotateState
-.endm
-
-.macro SHA512_2Sched_2Round_sse rnd
-
- # Compute rounds t-2 and t-1
- # Compute message schedule QWORDS t and t+1
-
- # Two rounds are computed based on the values for K[t-2]+W[t-2] and
- # K[t-1]+W[t-1] which were previously stored at WK_2 by the message
- # scheduler.
- # The two new schedule QWORDS are stored at [W_t(%%t)] and [W_t(%%t+1)].
- # They are then added to their respective SHA512 constants at
- # [K_t(%%t)] and [K_t(%%t+1)] and stored at dqword [WK_2(%%t)]
- # For brievity, the comments following vectored instructions only refer to
- # the first of a pair of QWORDS.
- # Eg. XMM2=W[t-2] really means XMM2={W[t-2]|W[t-1]}
- # The computation of the message schedule and the rounds are tightly
- # stitched to take advantage of instruction-level parallelism.
- # For clarity, integer instructions (for the rounds calculation) are indented
- # by one tab. Vectored instructions (for the message scheduler) are indented
- # by two tabs.
-
- mov f_64, T1
- idx = \rnd -2
- movdqa W_t(idx), %xmm2 # XMM2 = W[t-2]
- xor g_64, T1
- and e_64, T1
- movdqa %xmm2, %xmm0 # XMM0 = W[t-2]
- xor g_64, T1
- idx = \rnd
- add WK_2(idx), T1
- idx = \rnd - 15
- movdqu W_t(idx), %xmm5 # XMM5 = W[t-15]
- mov e_64, tmp0
- ror $23, tmp0 # 41
- movdqa %xmm5, %xmm3 # XMM3 = W[t-15]
- xor e_64, tmp0
- ror $4, tmp0 # 18
- psrlq $61-19, %xmm0 # XMM0 = W[t-2] >> 42
- xor e_64, tmp0
- ror $14, tmp0 # 14
- psrlq $(8-7), %xmm3 # XMM3 = W[t-15] >> 1
- add tmp0, T1
- add h_64, T1
- pxor %xmm2, %xmm0 # XMM0 = (W[t-2] >> 42) ^ W[t-2]
- mov a_64, T2
- xor c_64, T2
- pxor %xmm5, %xmm3 # XMM3 = (W[t-15] >> 1) ^ W[t-15]
- and b_64, T2
- mov a_64, tmp0
- psrlq $(19-6), %xmm0 # XMM0 = ((W[t-2]>>42)^W[t-2])>>13
- and c_64, tmp0
- xor tmp0, T2
- psrlq $(7-1), %xmm3 # XMM3 = ((W[t-15]>>1)^W[t-15])>>6
- mov a_64, tmp0
- ror $5, tmp0 # 39
- pxor %xmm2, %xmm0 # XMM0 = (((W[t-2]>>42)^W[t-2])>>13)^W[t-2]
- xor a_64, tmp0
- ror $6, tmp0 # 34
- pxor %xmm5, %xmm3 # XMM3 = (((W[t-15]>>1)^W[t-15])>>6)^W[t-15]
- xor a_64, tmp0
- ror $28, tmp0 # 28
- psrlq $6, %xmm0 # XMM0 = ((((W[t-2]>>42)^W[t-2])>>13)^W[t-2])>>6
- add tmp0, T2
- add T1, d_64
- psrlq $1, %xmm3 # XMM3 = (((W[t-15]>>1)^W[t-15])>>6)^W[t-15]>>1
- lea (T1, T2), h_64
- RotateState
- movdqa %xmm2, %xmm1 # XMM1 = W[t-2]
- mov f_64, T1
- xor g_64, T1
- movdqa %xmm5, %xmm4 # XMM4 = W[t-15]
- and e_64, T1
- xor g_64, T1
- psllq $(64-19)-(64-61) , %xmm1 # XMM1 = W[t-2] << 42
- idx = \rnd + 1
- add WK_2(idx), T1
- mov e_64, tmp0
- psllq $(64-1)-(64-8), %xmm4 # XMM4 = W[t-15] << 7
- ror $23, tmp0 # 41
- xor e_64, tmp0
- pxor %xmm2, %xmm1 # XMM1 = (W[t-2] << 42)^W[t-2]
- ror $4, tmp0 # 18
- xor e_64, tmp0
- pxor %xmm5, %xmm4 # XMM4 = (W[t-15]<<7)^W[t-15]
- ror $14, tmp0 # 14
- add tmp0, T1
- psllq $(64-61), %xmm1 # XMM1 = ((W[t-2] << 42)^W[t-2])<<3
- add h_64, T1
- mov a_64, T2
- psllq $(64-8), %xmm4 # XMM4 = ((W[t-15]<<7)^W[t-15])<<56
- xor c_64, T2
- and b_64, T2
- pxor %xmm1, %xmm0 # XMM0 = s1(W[t-2])
- mov a_64, tmp0
- and c_64, tmp0
- idx = \rnd - 7
- movdqu W_t(idx), %xmm1 # XMM1 = W[t-7]
- xor tmp0, T2
- pxor %xmm4, %xmm3 # XMM3 = s0(W[t-15])
- mov a_64, tmp0
- paddq %xmm3, %xmm0 # XMM0 = s1(W[t-2]) + s0(W[t-15])
- ror $5, tmp0 # 39
- idx =\rnd-16
- paddq W_t(idx), %xmm0 # XMM0 = s1(W[t-2]) + s0(W[t-15]) + W[t-16]
- xor a_64, tmp0
- paddq %xmm1, %xmm0 # XMM0 = s1(W[t-2]) + W[t-7] + s0(W[t-15]) + W[t-16]
- ror $6, tmp0 # 34
- movdqa %xmm0, W_t(\rnd) # Store scheduled qwords
- xor a_64, tmp0
- paddq K_t(\rnd), %xmm0 # Compute W[t]+K[t]
- ror $28, tmp0 # 28
- idx = \rnd
- movdqa %xmm0, WK_2(idx) # Store W[t]+K[t] for next rounds
- add tmp0, T2
- add T1, d_64
- lea (T1, T2), h_64
- RotateState
-.endm
-
-########################################################################
-## void sha512_transform_ssse3(struct sha512_state *state, const u8 *data,
-## int blocks);
-# (struct sha512_state is assumed to begin with u64 state[8])
-# Purpose: Updates the SHA512 digest stored at "state" with the message
-# stored in "data".
-# The size of the message pointed to by "data" must be an integer multiple
-# of SHA512 message blocks.
-# "blocks" is the message length in SHA512 blocks.
-########################################################################
-SYM_TYPED_FUNC_START(sha512_transform_ssse3)
-
- test msglen, msglen
- je .Lnowork
-
- # Save GPRs
- push %rbx
- push %r12
- push %r13
- push %r14
- push %r15
-
- # Allocate Stack Space
- push %rbp
- mov %rsp, %rbp
- sub $frame_size, %rsp
- and $~(0x20 - 1), %rsp
-
-.Lupdateblock:
-
-# Load state variables
- mov DIGEST(0), a_64
- mov DIGEST(1), b_64
- mov DIGEST(2), c_64
- mov DIGEST(3), d_64
- mov DIGEST(4), e_64
- mov DIGEST(5), f_64
- mov DIGEST(6), g_64
- mov DIGEST(7), h_64
-
- t = 0
- .rept 80/2 + 1
- # (80 rounds) / (2 rounds/iteration) + (1 iteration)
- # +1 iteration because the scheduler leads hashing by 1 iteration
- .if t < 2
- # BSWAP 2 QWORDS
- movdqa XMM_QWORD_BSWAP(%rip), %xmm1
- movdqu MSG(t), %xmm0
- pshufb %xmm1, %xmm0 # BSWAP
- movdqa %xmm0, W_t(t) # Store Scheduled Pair
- paddq K_t(t), %xmm0 # Compute W[t]+K[t]
- movdqa %xmm0, WK_2(t) # Store into WK for rounds
- .elseif t < 16
- # BSWAP 2 QWORDS# Compute 2 Rounds
- movdqu MSG(t), %xmm0
- pshufb %xmm1, %xmm0 # BSWAP
- SHA512_Round t-2 # Round t-2
- movdqa %xmm0, W_t(t) # Store Scheduled Pair
- paddq K_t(t), %xmm0 # Compute W[t]+K[t]
- SHA512_Round t-1 # Round t-1
- movdqa %xmm0, WK_2(t) # Store W[t]+K[t] into WK
- .elseif t < 79
- # Schedule 2 QWORDS# Compute 2 Rounds
- SHA512_2Sched_2Round_sse t
- .else
- # Compute 2 Rounds
- SHA512_Round t-2
- SHA512_Round t-1
- .endif
- t = t+2
- .endr
-
- # Update digest
- add a_64, DIGEST(0)
- add b_64, DIGEST(1)
- add c_64, DIGEST(2)
- add d_64, DIGEST(3)
- add e_64, DIGEST(4)
- add f_64, DIGEST(5)
- add g_64, DIGEST(6)
- add h_64, DIGEST(7)
-
- # Advance to next message block
- add $16*8, msg
- dec msglen
- jnz .Lupdateblock
-
- # Restore Stack Pointer
- mov %rbp, %rsp
- pop %rbp
-
- # Restore GPRs
- pop %r15
- pop %r14
- pop %r13
- pop %r12
- pop %rbx
-
-.Lnowork:
- RET
-SYM_FUNC_END(sha512_transform_ssse3)
-
-########################################################################
-### Binary Data
-
-.section .rodata.cst16.XMM_QWORD_BSWAP, "aM", @progbits, 16
-.align 16
-# Mask for byte-swapping a couple of qwords in an XMM register using (v)pshufb.
-XMM_QWORD_BSWAP:
- .octa 0x08090a0b0c0d0e0f0001020304050607
-
-# Mergeable 640-byte rodata section. This allows linker to merge the table
-# with other, exactly the same 640-byte fragment of another rodata section
-# (if such section exists).
-.section .rodata.cst640.K512, "aM", @progbits, 640
-.align 64
-# K[t] used in SHA512 hashing
-K512:
- .quad 0x428a2f98d728ae22,0x7137449123ef65cd
- .quad 0xb5c0fbcfec4d3b2f,0xe9b5dba58189dbbc
- .quad 0x3956c25bf348b538,0x59f111f1b605d019
- .quad 0x923f82a4af194f9b,0xab1c5ed5da6d8118
- .quad 0xd807aa98a3030242,0x12835b0145706fbe
- .quad 0x243185be4ee4b28c,0x550c7dc3d5ffb4e2
- .quad 0x72be5d74f27b896f,0x80deb1fe3b1696b1
- .quad 0x9bdc06a725c71235,0xc19bf174cf692694
- .quad 0xe49b69c19ef14ad2,0xefbe4786384f25e3
- .quad 0x0fc19dc68b8cd5b5,0x240ca1cc77ac9c65
- .quad 0x2de92c6f592b0275,0x4a7484aa6ea6e483
- .quad 0x5cb0a9dcbd41fbd4,0x76f988da831153b5
- .quad 0x983e5152ee66dfab,0xa831c66d2db43210
- .quad 0xb00327c898fb213f,0xbf597fc7beef0ee4
- .quad 0xc6e00bf33da88fc2,0xd5a79147930aa725
- .quad 0x06ca6351e003826f,0x142929670a0e6e70
- .quad 0x27b70a8546d22ffc,0x2e1b21385c26c926
- .quad 0x4d2c6dfc5ac42aed,0x53380d139d95b3df
- .quad 0x650a73548baf63de,0x766a0abb3c77b2a8
- .quad 0x81c2c92e47edaee6,0x92722c851482353b
- .quad 0xa2bfe8a14cf10364,0xa81a664bbc423001
- .quad 0xc24b8b70d0f89791,0xc76c51a30654be30
- .quad 0xd192e819d6ef5218,0xd69906245565a910
- .quad 0xf40e35855771202a,0x106aa07032bbd1b8
- .quad 0x19a4c116b8d2d0c8,0x1e376c085141ab53
- .quad 0x2748774cdf8eeb99,0x34b0bcb5e19b48a8
- .quad 0x391c0cb3c5c95a63,0x4ed8aa4ae3418acb
- .quad 0x5b9cca4f7763e373,0x682e6ff3d6b2b8a3
- .quad 0x748f82ee5defb2fc,0x78a5636f43172f60
- .quad 0x84c87814a1f0ab72,0x8cc702081a6439ec
- .quad 0x90befffa23631e28,0xa4506cebde82bde9
- .quad 0xbef9a3f7b2c67915,0xc67178f2e372532b
- .quad 0xca273eceea26619c,0xd186b8c721c0c207
- .quad 0xeada7dd6cde0eb1e,0xf57d4f7fee6ed178
- .quad 0x06f067aa72176fba,0x0a637dc5a2c898a6
- .quad 0x113f9804bef90dae,0x1b710b35131c471b
- .quad 0x28db77f523047d84,0x32caab7b40c72493
- .quad 0x3c9ebe0a15c9bebc,0x431d67c49c100d4c
- .quad 0x4cc5d4becb3e42b6,0x597f299cfc657e2a
- .quad 0x5fcb6fab3ad6faec,0x6c44198c4a475817
diff --git a/arch/x86/crypto/sha512_ssse3_glue.c b/arch/x86/crypto/sha512_ssse3_glue.c
deleted file mode 100644
index 6d3b85e53d0e..000000000000
--- a/arch/x86/crypto/sha512_ssse3_glue.c
+++ /dev/null
@@ -1,347 +0,0 @@
-/*
- * Cryptographic API.
- *
- * Glue code for the SHA512 Secure Hash Algorithm assembler
- * implementation using supplemental SSE3 / AVX / AVX2 instructions.
- *
- * This file is based on sha512_generic.c
- *
- * Copyright (C) 2013 Intel Corporation
- * Author: Tim Chen <tim.c.chen@linux.intel.com>
- *
- * This program is free software; you can redistribute it and/or modify it
- * under the terms of the GNU General Public License as published by the Free
- * Software Foundation; either version 2 of the License, or (at your option)
- * any later version.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- *
- */
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <crypto/internal/hash.h>
-#include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/mm.h>
-#include <linux/string.h>
-#include <linux/types.h>
-#include <crypto/sha2.h>
-#include <crypto/sha512_base.h>
-#include <asm/cpu_device_id.h>
-#include <asm/simd.h>
-
-asmlinkage void sha512_transform_ssse3(struct sha512_state *state,
- const u8 *data, int blocks);
-
-static int sha512_update(struct shash_desc *desc, const u8 *data,
- unsigned int len, sha512_block_fn *sha512_xform)
-{
- struct sha512_state *sctx = shash_desc_ctx(desc);
-
- if (!crypto_simd_usable() ||
- (sctx->count[0] % SHA512_BLOCK_SIZE) + len < SHA512_BLOCK_SIZE)
- return crypto_sha512_update(desc, data, len);
-
- /*
- * Make sure struct sha512_state begins directly with the SHA512
- * 512-bit internal state, as this is what the asm functions expect.
- */
- BUILD_BUG_ON(offsetof(struct sha512_state, state) != 0);
-
- kernel_fpu_begin();
- sha512_base_do_update(desc, data, len, sha512_xform);
- kernel_fpu_end();
-
- return 0;
-}
-
-static int sha512_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out, sha512_block_fn *sha512_xform)
-{
- if (!crypto_simd_usable())
- return crypto_sha512_finup(desc, data, len, out);
-
- kernel_fpu_begin();
- if (len)
- sha512_base_do_update(desc, data, len, sha512_xform);
- sha512_base_do_finalize(desc, sha512_xform);
- kernel_fpu_end();
-
- return sha512_base_finish(desc, out);
-}
-
-static int sha512_ssse3_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return sha512_update(desc, data, len, sha512_transform_ssse3);
-}
-
-static int sha512_ssse3_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha512_finup(desc, data, len, out, sha512_transform_ssse3);
-}
-
-/* Add padding and return the message digest. */
-static int sha512_ssse3_final(struct shash_desc *desc, u8 *out)
-{
- return sha512_ssse3_finup(desc, NULL, 0, out);
-}
-
-static struct shash_alg sha512_ssse3_algs[] = { {
- .digestsize = SHA512_DIGEST_SIZE,
- .init = sha512_base_init,
- .update = sha512_ssse3_update,
- .final = sha512_ssse3_final,
- .finup = sha512_ssse3_finup,
- .descsize = sizeof(struct sha512_state),
- .base = {
- .cra_name = "sha512",
- .cra_driver_name = "sha512-ssse3",
- .cra_priority = 150,
- .cra_blocksize = SHA512_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-}, {
- .digestsize = SHA384_DIGEST_SIZE,
- .init = sha384_base_init,
- .update = sha512_ssse3_update,
- .final = sha512_ssse3_final,
- .finup = sha512_ssse3_finup,
- .descsize = sizeof(struct sha512_state),
- .base = {
- .cra_name = "sha384",
- .cra_driver_name = "sha384-ssse3",
- .cra_priority = 150,
- .cra_blocksize = SHA384_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-} };
-
-static int register_sha512_ssse3(void)
-{
- if (boot_cpu_has(X86_FEATURE_SSSE3))
- return crypto_register_shashes(sha512_ssse3_algs,
- ARRAY_SIZE(sha512_ssse3_algs));
- return 0;
-}
-
-static void unregister_sha512_ssse3(void)
-{
- if (boot_cpu_has(X86_FEATURE_SSSE3))
- crypto_unregister_shashes(sha512_ssse3_algs,
- ARRAY_SIZE(sha512_ssse3_algs));
-}
-
-asmlinkage void sha512_transform_avx(struct sha512_state *state,
- const u8 *data, int blocks);
-static bool avx_usable(void)
-{
- if (!cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) {
- if (boot_cpu_has(X86_FEATURE_AVX))
- pr_info("AVX detected but unusable.\n");
- return false;
- }
-
- return true;
-}
-
-static int sha512_avx_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return sha512_update(desc, data, len, sha512_transform_avx);
-}
-
-static int sha512_avx_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha512_finup(desc, data, len, out, sha512_transform_avx);
-}
-
-/* Add padding and return the message digest. */
-static int sha512_avx_final(struct shash_desc *desc, u8 *out)
-{
- return sha512_avx_finup(desc, NULL, 0, out);
-}
-
-static struct shash_alg sha512_avx_algs[] = { {
- .digestsize = SHA512_DIGEST_SIZE,
- .init = sha512_base_init,
- .update = sha512_avx_update,
- .final = sha512_avx_final,
- .finup = sha512_avx_finup,
- .descsize = sizeof(struct sha512_state),
- .base = {
- .cra_name = "sha512",
- .cra_driver_name = "sha512-avx",
- .cra_priority = 160,
- .cra_blocksize = SHA512_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-}, {
- .digestsize = SHA384_DIGEST_SIZE,
- .init = sha384_base_init,
- .update = sha512_avx_update,
- .final = sha512_avx_final,
- .finup = sha512_avx_finup,
- .descsize = sizeof(struct sha512_state),
- .base = {
- .cra_name = "sha384",
- .cra_driver_name = "sha384-avx",
- .cra_priority = 160,
- .cra_blocksize = SHA384_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-} };
-
-static int register_sha512_avx(void)
-{
- if (avx_usable())
- return crypto_register_shashes(sha512_avx_algs,
- ARRAY_SIZE(sha512_avx_algs));
- return 0;
-}
-
-static void unregister_sha512_avx(void)
-{
- if (avx_usable())
- crypto_unregister_shashes(sha512_avx_algs,
- ARRAY_SIZE(sha512_avx_algs));
-}
-
-asmlinkage void sha512_transform_rorx(struct sha512_state *state,
- const u8 *data, int blocks);
-
-static int sha512_avx2_update(struct shash_desc *desc, const u8 *data,
- unsigned int len)
-{
- return sha512_update(desc, data, len, sha512_transform_rorx);
-}
-
-static int sha512_avx2_finup(struct shash_desc *desc, const u8 *data,
- unsigned int len, u8 *out)
-{
- return sha512_finup(desc, data, len, out, sha512_transform_rorx);
-}
-
-/* Add padding and return the message digest. */
-static int sha512_avx2_final(struct shash_desc *desc, u8 *out)
-{
- return sha512_avx2_finup(desc, NULL, 0, out);
-}
-
-static struct shash_alg sha512_avx2_algs[] = { {
- .digestsize = SHA512_DIGEST_SIZE,
- .init = sha512_base_init,
- .update = sha512_avx2_update,
- .final = sha512_avx2_final,
- .finup = sha512_avx2_finup,
- .descsize = sizeof(struct sha512_state),
- .base = {
- .cra_name = "sha512",
- .cra_driver_name = "sha512-avx2",
- .cra_priority = 170,
- .cra_blocksize = SHA512_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-}, {
- .digestsize = SHA384_DIGEST_SIZE,
- .init = sha384_base_init,
- .update = sha512_avx2_update,
- .final = sha512_avx2_final,
- .finup = sha512_avx2_finup,
- .descsize = sizeof(struct sha512_state),
- .base = {
- .cra_name = "sha384",
- .cra_driver_name = "sha384-avx2",
- .cra_priority = 170,
- .cra_blocksize = SHA384_BLOCK_SIZE,
- .cra_module = THIS_MODULE,
- }
-} };
-
-static bool avx2_usable(void)
-{
- if (avx_usable() && boot_cpu_has(X86_FEATURE_AVX2) &&
- boot_cpu_has(X86_FEATURE_BMI2))
- return true;
-
- return false;
-}
-
-static int register_sha512_avx2(void)
-{
- if (avx2_usable())
- return crypto_register_shashes(sha512_avx2_algs,
- ARRAY_SIZE(sha512_avx2_algs));
- return 0;
-}
-static const struct x86_cpu_id module_cpu_ids[] = {
- X86_MATCH_FEATURE(X86_FEATURE_AVX2, NULL),
- X86_MATCH_FEATURE(X86_FEATURE_AVX, NULL),
- X86_MATCH_FEATURE(X86_FEATURE_SSSE3, NULL),
- {}
-};
-MODULE_DEVICE_TABLE(x86cpu, module_cpu_ids);
-
-static void unregister_sha512_avx2(void)
-{
- if (avx2_usable())
- crypto_unregister_shashes(sha512_avx2_algs,
- ARRAY_SIZE(sha512_avx2_algs));
-}
-
-static int __init sha512_ssse3_mod_init(void)
-{
- if (!x86_match_cpu(module_cpu_ids))
- return -ENODEV;
-
- if (register_sha512_ssse3())
- goto fail;
-
- if (register_sha512_avx()) {
- unregister_sha512_ssse3();
- goto fail;
- }
-
- if (register_sha512_avx2()) {
- unregister_sha512_avx();
- unregister_sha512_ssse3();
- goto fail;
- }
-
- return 0;
-fail:
- return -ENODEV;
-}
-
-static void __exit sha512_ssse3_mod_fini(void)
-{
- unregister_sha512_avx2();
- unregister_sha512_avx();
- unregister_sha512_ssse3();
-}
-
-module_init(sha512_ssse3_mod_init);
-module_exit(sha512_ssse3_mod_fini);
-
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("SHA512 Secure Hash Algorithm, Supplemental SSE3 accelerated");
-
-MODULE_ALIAS_CRYPTO("sha512");
-MODULE_ALIAS_CRYPTO("sha512-ssse3");
-MODULE_ALIAS_CRYPTO("sha512-avx");
-MODULE_ALIAS_CRYPTO("sha512-avx2");
-MODULE_ALIAS_CRYPTO("sha384");
-MODULE_ALIAS_CRYPTO("sha384-ssse3");
-MODULE_ALIAS_CRYPTO("sha384-avx");
-MODULE_ALIAS_CRYPTO("sha384-avx2");
diff --git a/arch/x86/crypto/sm3_avx_glue.c b/arch/x86/crypto/sm3_avx_glue.c
index 661b6f22ffcd..6e8c42b9dc8e 100644
--- a/arch/x86/crypto/sm3_avx_glue.c
+++ b/arch/x86/crypto/sm3_avx_glue.c
@@ -10,12 +10,11 @@
#include <crypto/internal/hash.h>
#include <crypto/internal/simd.h>
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/types.h>
#include <crypto/sm3.h>
#include <crypto/sm3_base.h>
-#include <asm/simd.h>
+#include <linux/cpufeature.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
asmlinkage void sm3_transform_avx(struct sm3_state *state,
const u8 *data, int nblocks);
@@ -23,13 +22,7 @@ asmlinkage void sm3_transform_avx(struct sm3_state *state,
static int sm3_avx_update(struct shash_desc *desc, const u8 *data,
unsigned int len)
{
- struct sm3_state *sctx = shash_desc_ctx(desc);
-
- if (!crypto_simd_usable() ||
- (sctx->count % SM3_BLOCK_SIZE) + len < SM3_BLOCK_SIZE) {
- sm3_update(sctx, data, len);
- return 0;
- }
+ int remain;
/*
* Make sure struct sm3_state begins directly with the SM3
@@ -38,45 +31,17 @@ static int sm3_avx_update(struct shash_desc *desc, const u8 *data,
BUILD_BUG_ON(offsetof(struct sm3_state, state) != 0);
kernel_fpu_begin();
- sm3_base_do_update(desc, data, len, sm3_transform_avx);
+ remain = sm3_base_do_update_blocks(desc, data, len, sm3_transform_avx);
kernel_fpu_end();
-
- return 0;
+ return remain;
}
static int sm3_avx_finup(struct shash_desc *desc, const u8 *data,
unsigned int len, u8 *out)
{
- if (!crypto_simd_usable()) {
- struct sm3_state *sctx = shash_desc_ctx(desc);
-
- if (len)
- sm3_update(sctx, data, len);
-
- sm3_final(sctx, out);
- return 0;
- }
-
kernel_fpu_begin();
- if (len)
- sm3_base_do_update(desc, data, len, sm3_transform_avx);
- sm3_base_do_finalize(desc, sm3_transform_avx);
+ sm3_base_do_finup(desc, data, len, sm3_transform_avx);
kernel_fpu_end();
-
- return sm3_base_finish(desc, out);
-}
-
-static int sm3_avx_final(struct shash_desc *desc, u8 *out)
-{
- if (!crypto_simd_usable()) {
- sm3_final(shash_desc_ctx(desc), out);
- return 0;
- }
-
- kernel_fpu_begin();
- sm3_base_do_finalize(desc, sm3_transform_avx);
- kernel_fpu_end();
-
return sm3_base_finish(desc, out);
}
@@ -84,13 +49,14 @@ static struct shash_alg sm3_avx_alg = {
.digestsize = SM3_DIGEST_SIZE,
.init = sm3_base_init,
.update = sm3_avx_update,
- .final = sm3_avx_final,
.finup = sm3_avx_finup,
- .descsize = sizeof(struct sm3_state),
+ .descsize = SM3_STATE_SIZE,
.base = {
.cra_name = "sm3",
.cra_driver_name = "sm3-avx",
.cra_priority = 300,
+ .cra_flags = CRYPTO_AHASH_ALG_BLOCK_ONLY |
+ CRYPTO_AHASH_ALG_FINUP_MAX,
.cra_blocksize = SM3_BLOCK_SIZE,
.cra_module = THIS_MODULE,
}
diff --git a/arch/x86/crypto/sm4_aesni_avx2_glue.c b/arch/x86/crypto/sm4_aesni_avx2_glue.c
index 1148fd4cd57f..fec0ab7a63dd 100644
--- a/arch/x86/crypto/sm4_aesni_avx2_glue.c
+++ b/arch/x86/crypto/sm4_aesni_avx2_glue.c
@@ -8,11 +8,10 @@
* Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
*/
+#include <asm/fpu/api.h>
#include <linux/module.h>
#include <linux/crypto.h>
#include <linux/kernel.h>
-#include <asm/simd.h>
-#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <crypto/sm4.h>
#include "sm4-avx.h"
@@ -48,10 +47,9 @@ static int ctr_crypt(struct skcipher_request *req)
static struct skcipher_alg sm4_aesni_avx2_skciphers[] = {
{
.base = {
- .cra_name = "__ecb(sm4)",
- .cra_driver_name = "__ecb-sm4-aesni-avx2",
+ .cra_name = "ecb(sm4)",
+ .cra_driver_name = "ecb-sm4-aesni-avx2",
.cra_priority = 500,
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = SM4_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct sm4_ctx),
.cra_module = THIS_MODULE,
@@ -64,10 +62,9 @@ static struct skcipher_alg sm4_aesni_avx2_skciphers[] = {
.decrypt = sm4_avx_ecb_decrypt,
}, {
.base = {
- .cra_name = "__cbc(sm4)",
- .cra_driver_name = "__cbc-sm4-aesni-avx2",
+ .cra_name = "cbc(sm4)",
+ .cra_driver_name = "cbc-sm4-aesni-avx2",
.cra_priority = 500,
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = SM4_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct sm4_ctx),
.cra_module = THIS_MODULE,
@@ -81,10 +78,9 @@ static struct skcipher_alg sm4_aesni_avx2_skciphers[] = {
.decrypt = cbc_decrypt,
}, {
.base = {
- .cra_name = "__ctr(sm4)",
- .cra_driver_name = "__ctr-sm4-aesni-avx2",
+ .cra_name = "ctr(sm4)",
+ .cra_driver_name = "ctr-sm4-aesni-avx2",
.cra_priority = 500,
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = 1,
.cra_ctxsize = sizeof(struct sm4_ctx),
.cra_module = THIS_MODULE,
@@ -100,9 +96,6 @@ static struct skcipher_alg sm4_aesni_avx2_skciphers[] = {
}
};
-static struct simd_skcipher_alg *
-simd_sm4_aesni_avx2_skciphers[ARRAY_SIZE(sm4_aesni_avx2_skciphers)];
-
static int __init sm4_init(void)
{
const char *feature_name;
@@ -121,16 +114,14 @@ static int __init sm4_init(void)
return -ENODEV;
}
- return simd_register_skciphers_compat(sm4_aesni_avx2_skciphers,
- ARRAY_SIZE(sm4_aesni_avx2_skciphers),
- simd_sm4_aesni_avx2_skciphers);
+ return crypto_register_skciphers(sm4_aesni_avx2_skciphers,
+ ARRAY_SIZE(sm4_aesni_avx2_skciphers));
}
static void __exit sm4_exit(void)
{
- simd_unregister_skciphers(sm4_aesni_avx2_skciphers,
- ARRAY_SIZE(sm4_aesni_avx2_skciphers),
- simd_sm4_aesni_avx2_skciphers);
+ crypto_unregister_skciphers(sm4_aesni_avx2_skciphers,
+ ARRAY_SIZE(sm4_aesni_avx2_skciphers));
}
module_init(sm4_init);
diff --git a/arch/x86/crypto/sm4_aesni_avx_glue.c b/arch/x86/crypto/sm4_aesni_avx_glue.c
index 85b4ca78b47b..88caf418a06f 100644
--- a/arch/x86/crypto/sm4_aesni_avx_glue.c
+++ b/arch/x86/crypto/sm4_aesni_avx_glue.c
@@ -8,11 +8,11 @@
* Copyright (c) 2021 Tianjia Zhang <tianjia.zhang@linux.alibaba.com>
*/
+#include <asm/fpu/api.h>
#include <linux/module.h>
#include <linux/crypto.h>
+#include <linux/export.h>
#include <linux/kernel.h>
-#include <asm/simd.h>
-#include <crypto/internal/simd.h>
#include <crypto/internal/skcipher.h>
#include <crypto/sm4.h>
#include "sm4-avx.h"
@@ -263,10 +263,9 @@ static int ctr_crypt(struct skcipher_request *req)
static struct skcipher_alg sm4_aesni_avx_skciphers[] = {
{
.base = {
- .cra_name = "__ecb(sm4)",
- .cra_driver_name = "__ecb-sm4-aesni-avx",
+ .cra_name = "ecb(sm4)",
+ .cra_driver_name = "ecb-sm4-aesni-avx",
.cra_priority = 400,
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = SM4_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct sm4_ctx),
.cra_module = THIS_MODULE,
@@ -279,10 +278,9 @@ static struct skcipher_alg sm4_aesni_avx_skciphers[] = {
.decrypt = sm4_avx_ecb_decrypt,
}, {
.base = {
- .cra_name = "__cbc(sm4)",
- .cra_driver_name = "__cbc-sm4-aesni-avx",
+ .cra_name = "cbc(sm4)",
+ .cra_driver_name = "cbc-sm4-aesni-avx",
.cra_priority = 400,
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = SM4_BLOCK_SIZE,
.cra_ctxsize = sizeof(struct sm4_ctx),
.cra_module = THIS_MODULE,
@@ -296,10 +294,9 @@ static struct skcipher_alg sm4_aesni_avx_skciphers[] = {
.decrypt = cbc_decrypt,
}, {
.base = {
- .cra_name = "__ctr(sm4)",
- .cra_driver_name = "__ctr-sm4-aesni-avx",
+ .cra_name = "ctr(sm4)",
+ .cra_driver_name = "ctr-sm4-aesni-avx",
.cra_priority = 400,
- .cra_flags = CRYPTO_ALG_INTERNAL,
.cra_blocksize = 1,
.cra_ctxsize = sizeof(struct sm4_ctx),
.cra_module = THIS_MODULE,
@@ -315,9 +312,6 @@ static struct skcipher_alg sm4_aesni_avx_skciphers[] = {
}
};
-static struct simd_skcipher_alg *
-simd_sm4_aesni_avx_skciphers[ARRAY_SIZE(sm4_aesni_avx_skciphers)];
-
static int __init sm4_init(void)
{
const char *feature_name;
@@ -335,16 +329,14 @@ static int __init sm4_init(void)
return -ENODEV;
}
- return simd_register_skciphers_compat(sm4_aesni_avx_skciphers,
- ARRAY_SIZE(sm4_aesni_avx_skciphers),
- simd_sm4_aesni_avx_skciphers);
+ return crypto_register_skciphers(sm4_aesni_avx_skciphers,
+ ARRAY_SIZE(sm4_aesni_avx_skciphers));
}
static void __exit sm4_exit(void)
{
- simd_unregister_skciphers(sm4_aesni_avx_skciphers,
- ARRAY_SIZE(sm4_aesni_avx_skciphers),
- simd_sm4_aesni_avx_skciphers);
+ crypto_unregister_skciphers(sm4_aesni_avx_skciphers,
+ ARRAY_SIZE(sm4_aesni_avx_skciphers));
}
module_init(sm4_init);
diff --git a/arch/x86/crypto/twofish_avx_glue.c b/arch/x86/crypto/twofish_avx_glue.c
index 3eb3440b477a..9e20db013750 100644
--- a/arch/x86/crypto/twofish_avx_glue.c
+++ b/arch/x86/crypto/twofish_avx_glue.c
@@ -13,7 +13,6 @@
#include <linux/crypto.h>
#include <linux/err.h>
#include <crypto/algapi.h>
-#include <crypto/internal/simd.h>
#include <crypto/twofish.h>
#include "twofish.h"
@@ -74,10 +73,9 @@ static int cbc_decrypt(struct skcipher_request *req)
static struct skcipher_alg twofish_algs[] = {
{
- .base.cra_name = "__ecb(twofish)",
- .base.cra_driver_name = "__ecb-twofish-avx",
+ .base.cra_name = "ecb(twofish)",
+ .base.cra_driver_name = "ecb-twofish-avx",
.base.cra_priority = 400,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = TF_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct twofish_ctx),
.base.cra_module = THIS_MODULE,
@@ -87,10 +85,9 @@ static struct skcipher_alg twofish_algs[] = {
.encrypt = ecb_encrypt,
.decrypt = ecb_decrypt,
}, {
- .base.cra_name = "__cbc(twofish)",
- .base.cra_driver_name = "__cbc-twofish-avx",
+ .base.cra_name = "cbc(twofish)",
+ .base.cra_driver_name = "cbc-twofish-avx",
.base.cra_priority = 400,
- .base.cra_flags = CRYPTO_ALG_INTERNAL,
.base.cra_blocksize = TF_BLOCK_SIZE,
.base.cra_ctxsize = sizeof(struct twofish_ctx),
.base.cra_module = THIS_MODULE,
@@ -103,8 +100,6 @@ static struct skcipher_alg twofish_algs[] = {
},
};
-static struct simd_skcipher_alg *twofish_simd_algs[ARRAY_SIZE(twofish_algs)];
-
static int __init twofish_init(void)
{
const char *feature_name;
@@ -114,15 +109,13 @@ static int __init twofish_init(void)
return -ENODEV;
}
- return simd_register_skciphers_compat(twofish_algs,
- ARRAY_SIZE(twofish_algs),
- twofish_simd_algs);
+ return crypto_register_skciphers(twofish_algs,
+ ARRAY_SIZE(twofish_algs));
}
static void __exit twofish_exit(void)
{
- simd_unregister_skciphers(twofish_algs, ARRAY_SIZE(twofish_algs),
- twofish_simd_algs);
+ crypto_unregister_skciphers(twofish_algs, ARRAY_SIZE(twofish_algs));
}
module_init(twofish_init);
diff --git a/arch/x86/crypto/twofish_glue.c b/arch/x86/crypto/twofish_glue.c
index 4c67184dc573..8e9906d36902 100644
--- a/arch/x86/crypto/twofish_glue.c
+++ b/arch/x86/crypto/twofish_glue.c
@@ -40,6 +40,7 @@
#include <crypto/algapi.h>
#include <crypto/twofish.h>
+#include <linux/export.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/types.h>
diff --git a/arch/x86/crypto/twofish_glue_3way.c b/arch/x86/crypto/twofish_glue_3way.c
index 1a1ecfa7f72a..8ad77725bf60 100644
--- a/arch/x86/crypto/twofish_glue_3way.c
+++ b/arch/x86/crypto/twofish_glue_3way.c
@@ -9,6 +9,7 @@
#include <crypto/algapi.h>
#include <crypto/twofish.h>
#include <linux/crypto.h>
+#include <linux/export.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/types.h>
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index d83236b96f22..94519688b007 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -369,7 +369,7 @@ For 32-bit we have the following conventions - kernel is built with
.endm
.macro STACKLEAK_ERASE_NOCLOBBER
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
PUSH_AND_CLEAR_REGS
call stackleak_erase
POP_REGS
@@ -388,7 +388,7 @@ For 32-bit we have the following conventions - kernel is built with
#endif /* !CONFIG_X86_64 */
.macro STACKLEAK_ERASE
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
call stackleak_erase
#endif
.endm
diff --git a/arch/x86/entry/entry.S b/arch/x86/entry/entry.S
index 175958b02f2b..8e9a0cc20a4a 100644
--- a/arch/x86/entry/entry.S
+++ b/arch/x86/entry/entry.S
@@ -36,20 +36,20 @@ EXPORT_SYMBOL_GPL(write_ibpb);
/*
* Define the VERW operand that is disguised as entry code so that
- * it can be referenced with KPTI enabled. This ensure VERW can be
+ * it can be referenced with KPTI enabled. This ensures VERW can be
* used late in exit-to-user path after page tables are switched.
*/
.pushsection .entry.text, "ax"
.align L1_CACHE_BYTES, 0xcc
-SYM_CODE_START_NOALIGN(mds_verw_sel)
+SYM_CODE_START_NOALIGN(x86_verw_sel)
UNWIND_HINT_UNDEFINED
ANNOTATE_NOENDBR
.word __KERNEL_DS
.align L1_CACHE_BYTES, 0xcc
-SYM_CODE_END(mds_verw_sel);
+SYM_CODE_END(x86_verw_sel);
/* For KVM */
-EXPORT_SYMBOL_GPL(mds_verw_sel);
+EXPORT_SYMBOL_GPL(x86_verw_sel);
.popsection
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ac007ea00979..4877e16da69a 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -473,3 +473,5 @@
465 i386 listxattrat sys_listxattrat
466 i386 removexattrat sys_removexattrat
467 i386 open_tree_attr sys_open_tree_attr
+468 i386 file_getattr sys_file_getattr
+469 i386 file_setattr sys_file_setattr
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index cfb5ca41e30d..92cf0fe2291e 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -391,6 +391,8 @@
465 common listxattrat sys_listxattrat
466 common removexattrat sys_removexattrat
467 common open_tree_attr sys_open_tree_attr
+468 common file_getattr sys_file_getattr
+469 common file_setattr sys_file_setattr
#
# Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
index 54d3e9774d62..f247f5f5cb44 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -62,7 +62,7 @@ ifneq ($(RETPOLINE_VDSO_CFLAGS),)
endif
endif
-$(vobjs): KBUILD_CFLAGS := $(filter-out $(PADDING_CFLAGS) $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+$(vobjs): KBUILD_CFLAGS := $(filter-out $(PADDING_CFLAGS) $(CC_FLAGS_LTO) $(CC_FLAGS_CFI) $(RANDSTRUCT_CFLAGS) $(KSTACK_ERASE_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
$(vobjs): KBUILD_AFLAGS += -DBUILD_VDSO
#
@@ -123,6 +123,7 @@ KBUILD_CFLAGS_32 := $(filter-out -mcmodel=kernel,$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out -fno-pic,$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out -mfentry,$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out $(RANDSTRUCT_CFLAGS),$(KBUILD_CFLAGS_32))
+KBUILD_CFLAGS_32 := $(filter-out $(KSTACK_ERASE_CFLAGS),$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out $(GCC_PLUGINS_CFLAGS),$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out $(RETPOLINE_CFLAGS),$(KBUILD_CFLAGS_32))
KBUILD_CFLAGS_32 := $(filter-out $(CC_FLAGS_LTO),$(KBUILD_CFLAGS_32))
diff --git a/arch/x86/entry/vdso/vma.c b/arch/x86/entry/vdso/vma.c
index adb299d3b6a1..afe105b2f907 100644
--- a/arch/x86/entry/vdso/vma.c
+++ b/arch/x86/entry/vdso/vma.c
@@ -65,7 +65,6 @@ static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
static void vdso_fix_landing(const struct vdso_image *image,
struct vm_area_struct *new_vma)
{
-#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
if (in_ia32_syscall() && image == &vdso_image_32) {
struct pt_regs *regs = current_pt_regs();
unsigned long vdso_land = image->sym_int80_landing_pad;
@@ -76,7 +75,6 @@ static void vdso_fix_landing(const struct vdso_image *image,
if (regs->ip == old_land_addr)
regs->ip = new_vma->vm_start + vdso_land;
}
-#endif
}
static int vdso_mremap(const struct vm_special_mapping *sm,
@@ -227,7 +225,6 @@ int map_vdso_once(const struct vdso_image *image, unsigned long addr)
return map_vdso(image, addr);
}
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
static int load_vdso32(void)
{
if (vdso32_enabled != 1) /* Other values all mean "disabled" */
@@ -235,45 +232,38 @@ static int load_vdso32(void)
return map_vdso(&vdso_image_32, 0);
}
-#endif
-#ifdef CONFIG_X86_64
int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
{
- if (!vdso64_enabled)
- return 0;
+ if (IS_ENABLED(CONFIG_X86_64)) {
+ if (!vdso64_enabled)
+ return 0;
+
+ return map_vdso(&vdso_image_64, 0);
+ }
- return map_vdso(&vdso_image_64, 0);
+ return load_vdso32();
}
#ifdef CONFIG_COMPAT
int compat_arch_setup_additional_pages(struct linux_binprm *bprm,
int uses_interp, bool x32)
{
-#ifdef CONFIG_X86_X32_ABI
- if (x32) {
+ if (IS_ENABLED(CONFIG_X86_X32_ABI) && x32) {
if (!vdso64_enabled)
return 0;
return map_vdso(&vdso_image_x32, 0);
}
-#endif
-#ifdef CONFIG_IA32_EMULATION
- return load_vdso32();
-#else
+
+ if (IS_ENABLED(CONFIG_IA32_EMULATION))
+ return load_vdso32();
+
return 0;
-#endif
-}
-#endif
-#else
-int arch_setup_additional_pages(struct linux_binprm *bprm, int uses_interp)
-{
- return load_vdso32();
}
#endif
bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
{
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
const struct vdso_image *image = current->mm->context.vdso_image;
unsigned long vdso = (unsigned long) current->mm->context.vdso;
@@ -282,7 +272,6 @@ bool arch_syscall_is_vdso_sigreturn(struct pt_regs *regs)
regs->ip == vdso + image->sym_vdso32_rt_sigreturn_landing_pad)
return true;
}
-#endif
return false;
}
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
index 2fb7d53cf333..c9103a6fa06e 100644
--- a/arch/x86/entry/vsyscall/vsyscall_64.c
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -341,9 +341,7 @@ void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
p4d = p4d_offset(pgd, VSYSCALL_ADDR);
-#if CONFIG_PGTABLE_LEVELS >= 5
set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER));
-#endif
pud = pud_offset(p4d, VSYSCALL_ADDR);
set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
pmd = pmd_offset(pud, VSYSCALL_ADDR);
diff --git a/arch/x86/events/amd/brs.c b/arch/x86/events/amd/brs.c
index ec3427463382..06f35a6b58a5 100644
--- a/arch/x86/events/amd/brs.c
+++ b/arch/x86/events/amd/brs.c
@@ -44,12 +44,12 @@ static inline unsigned int brs_to(int idx)
static __always_inline void set_debug_extn_cfg(u64 val)
{
/* bits[4:3] must always be set to 11b */
- __wrmsr(MSR_AMD_DBG_EXTN_CFG, val | 3ULL << 3, val >> 32);
+ native_wrmsrq(MSR_AMD_DBG_EXTN_CFG, val | 3ULL << 3);
}
static __always_inline u64 get_debug_extn_cfg(void)
{
- return __rdmsr(MSR_AMD_DBG_EXTN_CFG);
+ return native_rdmsrq(MSR_AMD_DBG_EXTN_CFG);
}
static bool __init amd_brs_detect(void)
@@ -187,7 +187,7 @@ void amd_brs_reset(void)
/*
* Mark first entry as poisoned
*/
- wrmsrl(brs_to(0), BRS_POISON);
+ wrmsrq(brs_to(0), BRS_POISON);
}
int __init amd_brs_init(void)
@@ -325,7 +325,7 @@ void amd_brs_drain(void)
u32 brs_idx = tos - i;
u64 from, to;
- rdmsrl(brs_to(brs_idx), to);
+ rdmsrq(brs_to(brs_idx), to);
/* Entry does not belong to us (as marked by kernel) */
if (to == BRS_POISON)
@@ -341,7 +341,7 @@ void amd_brs_drain(void)
if (!amd_brs_match_plm(event, to))
continue;
- rdmsrl(brs_from(brs_idx), from);
+ rdmsrq(brs_from(brs_idx), from);
perf_clear_branch_entry_bitfields(br+nr);
@@ -371,7 +371,7 @@ static void amd_brs_poison_buffer(void)
idx = amd_brs_get_tos(&cfg);
/* Poison target of entry */
- wrmsrl(brs_to(idx), BRS_POISON);
+ wrmsrq(brs_to(idx), BRS_POISON);
}
/*
diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
index 30d6ceb4c8ad..b20661b8621d 100644
--- a/arch/x86/events/amd/core.c
+++ b/arch/x86/events/amd/core.c
@@ -9,6 +9,7 @@
#include <linux/jiffies.h>
#include <asm/apicdef.h>
#include <asm/apic.h>
+#include <asm/msr.h>
#include <asm/nmi.h>
#include "../perf_event.h"
@@ -563,13 +564,13 @@ static void amd_pmu_cpu_reset(int cpu)
return;
/* Clear enable bits i.e. PerfCntrGlobalCtl.PerfCntrEn */
- wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0);
+ wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, 0);
/*
* Clear freeze and overflow bits i.e. PerfCntrGLobalStatus.LbrFreeze
* and PerfCntrGLobalStatus.PerfCntrOvfl
*/
- wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR,
+ wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR,
GLOBAL_STATUS_LBRS_FROZEN | amd_pmu_global_cntr_mask);
}
@@ -651,7 +652,7 @@ static void amd_pmu_cpu_dead(int cpu)
static __always_inline void amd_pmu_set_global_ctl(u64 ctl)
{
- wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, ctl);
+ wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_CTL, ctl);
}
static inline u64 amd_pmu_get_global_status(void)
@@ -659,7 +660,7 @@ static inline u64 amd_pmu_get_global_status(void)
u64 status;
/* PerfCntrGlobalStatus is read-only */
- rdmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, status);
+ rdmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS, status);
return status;
}
@@ -672,14 +673,14 @@ static inline void amd_pmu_ack_global_status(u64 status)
* clears the same bit in PerfCntrGlobalStatus
*/
- wrmsrl(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, status);
+ wrmsrq(MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR, status);
}
static bool amd_pmu_test_overflow_topbit(int idx)
{
u64 counter;
- rdmsrl(x86_pmu_event_addr(idx), counter);
+ rdmsrq(x86_pmu_event_addr(idx), counter);
return !(counter & BIT_ULL(x86_pmu.cntval_bits - 1));
}
@@ -1003,8 +1004,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
- if (perf_event_overflow(event, &data, regs))
- x86_pmu_stop(event, 0);
+ perf_event_overflow(event, &data, regs);
}
/*
diff --git a/arch/x86/events/amd/ibs.c b/arch/x86/events/amd/ibs.c
index 0252b7ea8bca..112f43b23ebf 100644
--- a/arch/x86/events/amd/ibs.c
+++ b/arch/x86/events/amd/ibs.c
@@ -15,6 +15,7 @@
#include <linux/sched/clock.h>
#include <asm/apic.h>
+#include <asm/msr.h>
#include "../perf_event.h"
@@ -26,7 +27,7 @@ static u32 ibs_caps;
#include <linux/hardirq.h>
#include <asm/nmi.h>
-#include <asm/amd-ibs.h>
+#include <asm/amd/ibs.h>
/* attr.config2 */
#define IBS_SW_FILTER_MASK 1
@@ -424,7 +425,7 @@ perf_ibs_event_update(struct perf_ibs *perf_ibs, struct perf_event *event,
* prev count manually on overflow.
*/
while (!perf_event_try_update(event, count, 64)) {
- rdmsrl(event->hw.config_base, *config);
+ rdmsrq(event->hw.config_base, *config);
count = perf_ibs->get_count(*config);
}
}
@@ -435,9 +436,9 @@ static inline void perf_ibs_enable_event(struct perf_ibs *perf_ibs,
u64 tmp = hwc->config | config;
if (perf_ibs->fetch_count_reset_broken)
- wrmsrl(hwc->config_base, tmp & ~perf_ibs->enable_mask);
+ wrmsrq(hwc->config_base, tmp & ~perf_ibs->enable_mask);
- wrmsrl(hwc->config_base, tmp | perf_ibs->enable_mask);
+ wrmsrq(hwc->config_base, tmp | perf_ibs->enable_mask);
}
/*
@@ -452,9 +453,9 @@ static inline void perf_ibs_disable_event(struct perf_ibs *perf_ibs,
{
config &= ~perf_ibs->cnt_mask;
if (boot_cpu_data.x86 == 0x10)
- wrmsrl(hwc->config_base, config);
+ wrmsrq(hwc->config_base, config);
config &= ~perf_ibs->enable_mask;
- wrmsrl(hwc->config_base, config);
+ wrmsrq(hwc->config_base, config);
}
/*
@@ -513,7 +514,7 @@ static void perf_ibs_stop(struct perf_event *event, int flags)
if (!stopping && (hwc->state & PERF_HES_UPTODATE))
return;
- rdmsrl(hwc->config_base, config);
+ rdmsrq(hwc->config_base, config);
if (stopping) {
/*
@@ -1256,7 +1257,7 @@ fail:
hwc = &event->hw;
msr = hwc->config_base;
buf = ibs_data.regs;
- rdmsrl(msr, *buf);
+ rdmsrq(msr, *buf);
if (!(*buf++ & perf_ibs->valid_mask))
goto fail;
@@ -1274,7 +1275,7 @@ fail:
offset_max = perf_ibs_get_offset_max(perf_ibs, event, check_rip);
do {
- rdmsrl(msr + offset, *buf++);
+ rdmsrq(msr + offset, *buf++);
size++;
offset = find_next_bit(perf_ibs->offset_mask,
perf_ibs->offset_max,
@@ -1304,17 +1305,17 @@ fail:
if (event->attr.sample_type & PERF_SAMPLE_RAW) {
if (perf_ibs == &perf_ibs_op) {
if (ibs_caps & IBS_CAPS_BRNTRGT) {
- rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++);
+ rdmsrq(MSR_AMD64_IBSBRTARGET, *buf++);
br_target_idx = size;
size++;
}
if (ibs_caps & IBS_CAPS_OPDATA4) {
- rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++);
+ rdmsrq(MSR_AMD64_IBSOPDATA4, *buf++);
size++;
}
}
if (perf_ibs == &perf_ibs_fetch && (ibs_caps & IBS_CAPS_FETCHCTLEXTD)) {
- rdmsrl(MSR_AMD64_ICIBSEXTDCTL, *buf++);
+ rdmsrq(MSR_AMD64_ICIBSEXTDCTL, *buf++);
size++;
}
}
@@ -1373,9 +1374,7 @@ fail:
hwc->sample_period = perf_ibs->min_period;
out:
- if (throttle) {
- perf_ibs_stop(event, 0);
- } else {
+ if (!throttle) {
if (perf_ibs == &perf_ibs_op) {
if (ibs_caps & IBS_CAPS_OPCNTEXT) {
new_config = period & IBS_OP_MAX_CNT_EXT_MASK;
@@ -1565,7 +1564,7 @@ static inline int ibs_eilvt_valid(void)
preempt_disable();
- rdmsrl(MSR_AMD64_IBSCTL, val);
+ rdmsrq(MSR_AMD64_IBSCTL, val);
offset = val & IBSCTL_LVT_OFFSET_MASK;
if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
@@ -1680,7 +1679,7 @@ static inline int get_ibs_lvt_offset(void)
{
u64 val;
- rdmsrl(MSR_AMD64_IBSCTL, val);
+ rdmsrq(MSR_AMD64_IBSCTL, val);
if (!(val & IBSCTL_LVT_OFFSET_VALID))
return -EINVAL;
diff --git a/arch/x86/events/amd/iommu.c b/arch/x86/events/amd/iommu.c
index f8228d8243f7..a721da9987dd 100644
--- a/arch/x86/events/amd/iommu.c
+++ b/arch/x86/events/amd/iommu.c
@@ -16,6 +16,8 @@
#include <linux/slab.h>
#include <linux/amd-iommu.h>
+#include <asm/msr.h>
+
#include "../perf_event.h"
#include "iommu.h"
diff --git a/arch/x86/events/amd/lbr.c b/arch/x86/events/amd/lbr.c
index c06ccca96851..d24da377df77 100644
--- a/arch/x86/events/amd/lbr.c
+++ b/arch/x86/events/amd/lbr.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/perf_event.h>
+#include <asm/msr.h>
#include <asm/perf_event.h>
#include "../perf_event.h"
@@ -61,19 +62,19 @@ struct branch_entry {
static __always_inline void amd_pmu_lbr_set_from(unsigned int idx, u64 val)
{
- wrmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2, val);
+ wrmsrq(MSR_AMD_SAMP_BR_FROM + idx * 2, val);
}
static __always_inline void amd_pmu_lbr_set_to(unsigned int idx, u64 val)
{
- wrmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2 + 1, val);
+ wrmsrq(MSR_AMD_SAMP_BR_FROM + idx * 2 + 1, val);
}
static __always_inline u64 amd_pmu_lbr_get_from(unsigned int idx)
{
u64 val;
- rdmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2, val);
+ rdmsrq(MSR_AMD_SAMP_BR_FROM + idx * 2, val);
return val;
}
@@ -82,7 +83,7 @@ static __always_inline u64 amd_pmu_lbr_get_to(unsigned int idx)
{
u64 val;
- rdmsrl(MSR_AMD_SAMP_BR_FROM + idx * 2 + 1, val);
+ rdmsrq(MSR_AMD_SAMP_BR_FROM + idx * 2 + 1, val);
return val;
}
@@ -333,7 +334,7 @@ void amd_pmu_lbr_reset(void)
cpuc->last_task_ctx = NULL;
cpuc->last_log_id = 0;
- wrmsrl(MSR_AMD64_LBR_SELECT, 0);
+ wrmsrq(MSR_AMD64_LBR_SELECT, 0);
}
void amd_pmu_lbr_add(struct perf_event *event)
@@ -396,16 +397,16 @@ void amd_pmu_lbr_enable_all(void)
/* Set hardware branch filter */
if (cpuc->lbr_select) {
lbr_select = cpuc->lbr_sel->config & LBR_SELECT_MASK;
- wrmsrl(MSR_AMD64_LBR_SELECT, lbr_select);
+ wrmsrq(MSR_AMD64_LBR_SELECT, lbr_select);
}
if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
- rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
- wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+ rdmsrq(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+ wrmsrq(MSR_IA32_DEBUGCTLMSR, dbg_ctl | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
}
- rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
- wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN);
+ rdmsrq(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
+ wrmsrq(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg | DBG_EXTN_CFG_LBRV2EN);
}
void amd_pmu_lbr_disable_all(void)
diff --git a/arch/x86/events/amd/power.c b/arch/x86/events/amd/power.c
index 37d5b380516e..dad42790cf7d 100644
--- a/arch/x86/events/amd/power.c
+++ b/arch/x86/events/amd/power.c
@@ -11,6 +11,7 @@
#include <linux/slab.h>
#include <linux/perf_event.h>
#include <asm/cpu_device_id.h>
+#include <asm/msr.h>
#include "../perf_event.h"
/* Event code: LSB 8 bits, passed in attr->config any other bit is reserved. */
@@ -48,8 +49,8 @@ static void event_update(struct perf_event *event)
prev_pwr_acc = hwc->pwr_acc;
prev_ptsc = hwc->ptsc;
- rdmsrl(MSR_F15H_CU_PWR_ACCUMULATOR, new_pwr_acc);
- rdmsrl(MSR_F15H_PTSC, new_ptsc);
+ rdmsrq(MSR_F15H_CU_PWR_ACCUMULATOR, new_pwr_acc);
+ rdmsrq(MSR_F15H_PTSC, new_ptsc);
/*
* Calculate the CU power consumption over a time period, the unit of
@@ -75,8 +76,8 @@ static void __pmu_event_start(struct perf_event *event)
event->hw.state = 0;
- rdmsrl(MSR_F15H_PTSC, event->hw.ptsc);
- rdmsrl(MSR_F15H_CU_PWR_ACCUMULATOR, event->hw.pwr_acc);
+ rdmsrq(MSR_F15H_PTSC, event->hw.ptsc);
+ rdmsrq(MSR_F15H_CU_PWR_ACCUMULATOR, event->hw.pwr_acc);
}
static void pmu_event_start(struct perf_event *event, int mode)
@@ -272,7 +273,7 @@ static int __init amd_power_pmu_init(void)
cpu_pwr_sample_ratio = cpuid_ecx(0x80000007);
- if (rdmsrl_safe(MSR_F15H_CU_MAX_PWR_ACCUMULATOR, &max_cu_acc_power)) {
+ if (rdmsrq_safe(MSR_F15H_CU_MAX_PWR_ACCUMULATOR, &max_cu_acc_power)) {
pr_err("Failed to read max compute unit power accumulator MSR\n");
return -ENODEV;
}
diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
index 49c26ce2b115..e8b6af199c73 100644
--- a/arch/x86/events/amd/uncore.c
+++ b/arch/x86/events/amd/uncore.c
@@ -21,6 +21,7 @@
#define NUM_COUNTERS_NB 4
#define NUM_COUNTERS_L2 4
#define NUM_COUNTERS_L3 6
+#define NUM_COUNTERS_MAX 64
#define RDPMC_BASE_NB 6
#define RDPMC_BASE_LLC 10
@@ -38,7 +39,10 @@ struct amd_uncore_ctx {
int refcnt;
int cpu;
struct perf_event **events;
- struct hlist_node node;
+ unsigned long active_mask[BITS_TO_LONGS(NUM_COUNTERS_MAX)];
+ int nr_active;
+ struct hrtimer hrtimer;
+ u64 hrtimer_duration;
};
struct amd_uncore_pmu {
@@ -83,11 +87,51 @@ struct amd_uncore {
static struct amd_uncore uncores[UNCORE_TYPE_MAX];
+/* Interval for hrtimer, defaults to 60000 milliseconds */
+static unsigned int update_interval = 60 * MSEC_PER_SEC;
+module_param(update_interval, uint, 0444);
+
static struct amd_uncore_pmu *event_to_amd_uncore_pmu(struct perf_event *event)
{
return container_of(event->pmu, struct amd_uncore_pmu, pmu);
}
+static enum hrtimer_restart amd_uncore_hrtimer(struct hrtimer *hrtimer)
+{
+ struct amd_uncore_ctx *ctx;
+ struct perf_event *event;
+ int bit;
+
+ ctx = container_of(hrtimer, struct amd_uncore_ctx, hrtimer);
+
+ if (!ctx->nr_active || ctx->cpu != smp_processor_id())
+ return HRTIMER_NORESTART;
+
+ for_each_set_bit(bit, ctx->active_mask, NUM_COUNTERS_MAX) {
+ event = ctx->events[bit];
+ event->pmu->read(event);
+ }
+
+ hrtimer_forward_now(hrtimer, ns_to_ktime(ctx->hrtimer_duration));
+ return HRTIMER_RESTART;
+}
+
+static void amd_uncore_start_hrtimer(struct amd_uncore_ctx *ctx)
+{
+ hrtimer_start(&ctx->hrtimer, ns_to_ktime(ctx->hrtimer_duration),
+ HRTIMER_MODE_REL_PINNED_HARD);
+}
+
+static void amd_uncore_cancel_hrtimer(struct amd_uncore_ctx *ctx)
+{
+ hrtimer_cancel(&ctx->hrtimer);
+}
+
+static void amd_uncore_init_hrtimer(struct amd_uncore_ctx *ctx)
+{
+ hrtimer_setup(&ctx->hrtimer, amd_uncore_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
+}
+
static void amd_uncore_read(struct perf_event *event)
{
struct hw_perf_event *hwc = &event->hw;
@@ -106,9 +150,9 @@ static void amd_uncore_read(struct perf_event *event)
* read counts directly from the corresponding PERF_CTR.
*/
if (hwc->event_base_rdpmc < 0)
- rdmsrl(hwc->event_base, new);
+ rdmsrq(hwc->event_base, new);
else
- rdpmcl(hwc->event_base_rdpmc, new);
+ new = rdpmc(hwc->event_base_rdpmc);
local64_set(&hwc->prev_count, new);
delta = (new << COUNTER_SHIFT) - (prev << COUNTER_SHIFT);
@@ -118,27 +162,40 @@ static void amd_uncore_read(struct perf_event *event)
static void amd_uncore_start(struct perf_event *event, int flags)
{
+ struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+ struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
struct hw_perf_event *hwc = &event->hw;
+ if (!ctx->nr_active++)
+ amd_uncore_start_hrtimer(ctx);
+
if (flags & PERF_EF_RELOAD)
- wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
+ wrmsrq(hwc->event_base, (u64)local64_read(&hwc->prev_count));
hwc->state = 0;
- wrmsrl(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE));
+ __set_bit(hwc->idx, ctx->active_mask);
+ wrmsrq(hwc->config_base, (hwc->config | ARCH_PERFMON_EVENTSEL_ENABLE));
perf_event_update_userpage(event);
}
static void amd_uncore_stop(struct perf_event *event, int flags)
{
+ struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+ struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
struct hw_perf_event *hwc = &event->hw;
- wrmsrl(hwc->config_base, hwc->config);
+ wrmsrq(hwc->config_base, hwc->config);
hwc->state |= PERF_HES_STOPPED;
if ((flags & PERF_EF_UPDATE) && !(hwc->state & PERF_HES_UPTODATE)) {
event->pmu->read(event);
hwc->state |= PERF_HES_UPTODATE;
}
+
+ if (!--ctx->nr_active)
+ amd_uncore_cancel_hrtimer(ctx);
+
+ __clear_bit(hwc->idx, ctx->active_mask);
}
static int amd_uncore_add(struct perf_event *event, int flags)
@@ -491,6 +548,9 @@ static int amd_uncore_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
goto fail;
}
+ amd_uncore_init_hrtimer(curr);
+ curr->hrtimer_duration = (u64)update_interval * NSEC_PER_MSEC;
+
cpumask_set_cpu(cpu, &pmu->active_mask);
}
@@ -880,16 +940,55 @@ static int amd_uncore_umc_event_init(struct perf_event *event)
static void amd_uncore_umc_start(struct perf_event *event, int flags)
{
+ struct amd_uncore_pmu *pmu = event_to_amd_uncore_pmu(event);
+ struct amd_uncore_ctx *ctx = *per_cpu_ptr(pmu->ctx, event->cpu);
struct hw_perf_event *hwc = &event->hw;
+ if (!ctx->nr_active++)
+ amd_uncore_start_hrtimer(ctx);
+
if (flags & PERF_EF_RELOAD)
- wrmsrl(hwc->event_base, (u64)local64_read(&hwc->prev_count));
+ wrmsrq(hwc->event_base, (u64)local64_read(&hwc->prev_count));
hwc->state = 0;
- wrmsrl(hwc->config_base, (hwc->config | AMD64_PERFMON_V2_ENABLE_UMC));
+ __set_bit(hwc->idx, ctx->active_mask);
+ wrmsrq(hwc->config_base, (hwc->config | AMD64_PERFMON_V2_ENABLE_UMC));
perf_event_update_userpage(event);
}
+static void amd_uncore_umc_read(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+ u64 prev, new, shift;
+ s64 delta;
+
+ shift = COUNTER_SHIFT + 1;
+ prev = local64_read(&hwc->prev_count);
+
+ /*
+ * UMC counters do not have RDPMC assignments. Read counts directly
+ * from the corresponding PERF_CTR.
+ */
+ rdmsrl(hwc->event_base, new);
+
+ /*
+ * Unlike the other uncore counters, UMC counters saturate and set the
+ * Overflow bit (bit 48) on overflow. Since they do not roll over,
+ * proactively reset the corresponding PERF_CTR when bit 47 is set so
+ * that the counter never gets a chance to saturate.
+ */
+ if (new & BIT_ULL(63 - COUNTER_SHIFT)) {
+ wrmsrl(hwc->event_base, 0);
+ local64_set(&hwc->prev_count, 0);
+ } else {
+ local64_set(&hwc->prev_count, new);
+ }
+
+ delta = (new << shift) - (prev << shift);
+ delta >>= shift;
+ local64_add(delta, &event->count);
+}
+
static
void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
{
@@ -968,7 +1067,7 @@ int amd_uncore_umc_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
.del = amd_uncore_del,
.start = amd_uncore_umc_start,
.stop = amd_uncore_stop,
- .read = amd_uncore_read,
+ .read = amd_uncore_umc_read,
.capabilities = PERF_PMU_CAP_NO_EXCLUDE | PERF_PMU_CAP_NO_INTERRUPT,
.module = THIS_MODULE,
};
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index 139ad80d1df3..7610f26dfbd9 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -32,6 +32,7 @@
#include <asm/apic.h>
#include <asm/stacktrace.h>
+#include <asm/msr.h>
#include <asm/nmi.h>
#include <asm/smp.h>
#include <asm/alternative.h>
@@ -95,6 +96,11 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_filter, *x86_pmu.filter);
DEFINE_STATIC_CALL_NULL(x86_pmu_late_setup, *x86_pmu.late_setup);
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_enable, *x86_pmu.pebs_enable);
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_disable, *x86_pmu.pebs_disable);
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_enable_all, *x86_pmu.pebs_enable_all);
+DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_disable_all, *x86_pmu.pebs_disable_all);
+
/*
* This one is magic, it will get called even when PMU init fails (because
* there is no PMU), in which case it should simply return NULL.
@@ -134,7 +140,7 @@ u64 x86_perf_event_update(struct perf_event *event)
*/
prev_raw_count = local64_read(&hwc->prev_count);
do {
- rdpmcl(hwc->event_base_rdpmc, new_raw_count);
+ new_raw_count = rdpmc(hwc->event_base_rdpmc);
} while (!local64_try_cmpxchg(&hwc->prev_count,
&prev_raw_count, new_raw_count));
@@ -269,7 +275,7 @@ bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
*/
for_each_set_bit(i, cntr_mask, X86_PMC_IDX_MAX) {
reg = x86_pmu_config_addr(i);
- ret = rdmsrl_safe(reg, &val);
+ ret = rdmsrq_safe(reg, &val);
if (ret)
goto msr_fail;
if (val & ARCH_PERFMON_EVENTSEL_ENABLE) {
@@ -283,7 +289,7 @@ bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
if (*(u64 *)fixed_cntr_mask) {
reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
- ret = rdmsrl_safe(reg, &val);
+ ret = rdmsrq_safe(reg, &val);
if (ret)
goto msr_fail;
for_each_set_bit(i, fixed_cntr_mask, X86_PMC_IDX_MAX) {
@@ -314,11 +320,11 @@ bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
* (qemu/kvm) that don't trap on the MSR access and always return 0s.
*/
reg = x86_pmu_event_addr(reg_safe);
- if (rdmsrl_safe(reg, &val))
+ if (rdmsrq_safe(reg, &val))
goto msr_fail;
val ^= 0xffffUL;
- ret = wrmsrl_safe(reg, val);
- ret |= rdmsrl_safe(reg, &val_new);
+ ret = wrmsrq_safe(reg, val);
+ ret |= rdmsrq_safe(reg, &val_new);
if (ret || val != val_new)
goto msr_fail;
@@ -674,6 +680,7 @@ static int __x86_pmu_event_init(struct perf_event *event)
event->hw.idx = -1;
event->hw.last_cpu = -1;
event->hw.last_tag = ~0ULL;
+ event->hw.dyn_constraint = ~0ULL;
/* mark unused */
event->hw.extra_reg.idx = EXTRA_REG_NONE;
@@ -693,13 +700,13 @@ void x86_pmu_disable_all(void)
if (!test_bit(idx, cpuc->active_mask))
continue;
- rdmsrl(x86_pmu_config_addr(idx), val);
+ rdmsrq(x86_pmu_config_addr(idx), val);
if (!(val & ARCH_PERFMON_EVENTSEL_ENABLE))
continue;
val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
- wrmsrl(x86_pmu_config_addr(idx), val);
+ wrmsrq(x86_pmu_config_addr(idx), val);
if (is_counter_pair(hwc))
- wrmsrl(x86_pmu_config_addr(idx + 1), 0);
+ wrmsrq(x86_pmu_config_addr(idx + 1), 0);
}
}
@@ -756,15 +763,16 @@ void x86_pmu_enable_all(int added)
int is_x86_event(struct perf_event *event)
{
- int i;
-
- if (!is_hybrid())
- return event->pmu == &pmu;
-
- for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) {
- if (event->pmu == &x86_pmu.hybrid_pmu[i].pmu)
- return true;
- }
+ /*
+ * For a non-hybrid platforms, the type of X86 pmu is
+ * always PERF_TYPE_RAW.
+ * For a hybrid platform, the PERF_PMU_CAP_EXTENDED_HW_TYPE
+ * is a unique capability for the X86 PMU.
+ * Use them to detect a X86 event.
+ */
+ if (event->pmu->type == PERF_TYPE_RAW ||
+ event->pmu->capabilities & PERF_PMU_CAP_EXTENDED_HW_TYPE)
+ return true;
return false;
}
@@ -1420,14 +1428,14 @@ int x86_perf_event_set_period(struct perf_event *event)
*/
local64_set(&hwc->prev_count, (u64)-left);
- wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+ wrmsrq(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
/*
* Sign extend the Merge event counter's upper 16 bits since
* we currently declare a 48-bit counter width
*/
if (is_counter_pair(hwc))
- wrmsrl(x86_pmu_event_addr(idx + 1), 0xffff);
+ wrmsrq(x86_pmu_event_addr(idx + 1), 0xffff);
perf_event_update_userpage(event);
@@ -1550,10 +1558,10 @@ void perf_event_print_debug(void)
return;
if (x86_pmu.version >= 2) {
- rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
- rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
- rdmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow);
- rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed);
+ rdmsrq(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
+ rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, status);
+ rdmsrq(MSR_CORE_PERF_GLOBAL_OVF_CTRL, overflow);
+ rdmsrq(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, fixed);
pr_info("\n");
pr_info("CPU#%d: ctrl: %016llx\n", cpu, ctrl);
@@ -1561,19 +1569,19 @@ void perf_event_print_debug(void)
pr_info("CPU#%d: overflow: %016llx\n", cpu, overflow);
pr_info("CPU#%d: fixed: %016llx\n", cpu, fixed);
if (pebs_constraints) {
- rdmsrl(MSR_IA32_PEBS_ENABLE, pebs);
+ rdmsrq(MSR_IA32_PEBS_ENABLE, pebs);
pr_info("CPU#%d: pebs: %016llx\n", cpu, pebs);
}
if (x86_pmu.lbr_nr) {
- rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
pr_info("CPU#%d: debugctl: %016llx\n", cpu, debugctl);
}
}
pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask);
for_each_set_bit(idx, cntr_mask, X86_PMC_IDX_MAX) {
- rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
- rdmsrl(x86_pmu_event_addr(idx), pmc_count);
+ rdmsrq(x86_pmu_config_addr(idx), pmc_ctrl);
+ rdmsrq(x86_pmu_event_addr(idx), pmc_count);
prev_left = per_cpu(pmc_prev_left[idx], cpu);
@@ -1587,7 +1595,7 @@ void perf_event_print_debug(void)
for_each_set_bit(idx, fixed_cntr_mask, X86_PMC_IDX_MAX) {
if (fixed_counter_disabled(idx, cpuc->pmu))
continue;
- rdmsrl(x86_pmu_fixed_ctr_addr(idx), pmc_count);
+ rdmsrq(x86_pmu_fixed_ctr_addr(idx), pmc_count);
pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
cpu, idx, pmc_count);
@@ -1683,6 +1691,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
struct cpu_hw_events *cpuc;
struct perf_event *event;
int idx, handled = 0;
+ u64 last_period;
u64 val;
cpuc = this_cpu_ptr(&cpu_hw_events);
@@ -1702,6 +1711,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
continue;
event = cpuc->events[idx];
+ last_period = event->hw.last_period;
val = static_call(x86_pmu_update)(event);
if (val & (1ULL << (x86_pmu.cntval_bits - 1)))
@@ -1715,12 +1725,11 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
if (!static_call(x86_pmu_set_period)(event))
continue;
- perf_sample_data_init(&data, 0, event->hw.last_period);
+ perf_sample_data_init(&data, 0, last_period);
perf_sample_save_brstack(&data, event, &cpuc->lbr_stack, NULL);
- if (perf_event_overflow(event, &data, regs))
- x86_pmu_stop(event, 0);
+ perf_event_overflow(event, &data, regs);
}
if (handled)
@@ -2046,6 +2055,11 @@ static void x86_pmu_static_call_update(void)
static_call_update(x86_pmu_filter, x86_pmu.filter);
static_call_update(x86_pmu_late_setup, x86_pmu.late_setup);
+
+ static_call_update(x86_pmu_pebs_enable, x86_pmu.pebs_enable);
+ static_call_update(x86_pmu_pebs_disable, x86_pmu.pebs_disable);
+ static_call_update(x86_pmu_pebs_enable_all, x86_pmu.pebs_enable_all);
+ static_call_update(x86_pmu_pebs_disable_all, x86_pmu.pebs_disable_all);
}
static void _x86_pmu_read(struct perf_event *event)
@@ -2496,9 +2510,9 @@ void perf_clear_dirty_counters(void)
if (!test_bit(i - INTEL_PMC_IDX_FIXED, hybrid(cpuc->pmu, fixed_cntr_mask)))
continue;
- wrmsrl(x86_pmu_fixed_ctr_addr(i - INTEL_PMC_IDX_FIXED), 0);
+ wrmsrq(x86_pmu_fixed_ctr_addr(i - INTEL_PMC_IDX_FIXED), 0);
} else {
- wrmsrl(x86_pmu_event_addr(i), 0);
+ wrmsrq(x86_pmu_event_addr(i), 0);
}
}
@@ -2803,8 +2817,15 @@ static unsigned long get_segment_base(unsigned int segment)
#ifdef CONFIG_MODIFY_LDT_SYSCALL
struct ldt_struct *ldt;
+ /*
+ * If we're not in a valid context with a real (not just lazy)
+ * user mm, then don't even try.
+ */
+ if (!nmi_uaccess_okay())
+ return 0;
+
/* IRQs are off, so this synchronizes with smp_store_release */
- ldt = READ_ONCE(current->active_mm->context.ldt);
+ ldt = smp_load_acquire(&current->mm->context.ldt);
if (!ldt || idx >= ldt->nr_entries)
return 0;
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index a95e6c91c4d7..61da6b8a3d51 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -17,6 +17,7 @@
#include <linux/sizes.h>
#include <asm/perf_event.h>
+#include <asm/msr.h>
#include "../perf_event.h"
@@ -80,54 +81,54 @@ static void *
bts_buffer_setup_aux(struct perf_event *event, void **pages,
int nr_pages, bool overwrite)
{
- struct bts_buffer *buf;
+ struct bts_buffer *bb;
struct page *page;
int cpu = event->cpu;
int node = (cpu == -1) ? cpu : cpu_to_node(cpu);
unsigned long offset;
size_t size = nr_pages << PAGE_SHIFT;
- int pg, nbuf, pad;
+ int pg, nr_buf, pad;
/* count all the high order buffers */
- for (pg = 0, nbuf = 0; pg < nr_pages;) {
+ for (pg = 0, nr_buf = 0; pg < nr_pages;) {
page = virt_to_page(pages[pg]);
pg += buf_nr_pages(page);
- nbuf++;
+ nr_buf++;
}
/*
* to avoid interrupts in overwrite mode, only allow one physical
*/
- if (overwrite && nbuf > 1)
+ if (overwrite && nr_buf > 1)
return NULL;
- buf = kzalloc_node(offsetof(struct bts_buffer, buf[nbuf]), GFP_KERNEL, node);
- if (!buf)
+ bb = kzalloc_node(struct_size(bb, buf, nr_buf), GFP_KERNEL, node);
+ if (!bb)
return NULL;
- buf->nr_pages = nr_pages;
- buf->nr_bufs = nbuf;
- buf->snapshot = overwrite;
- buf->data_pages = pages;
- buf->real_size = size - size % BTS_RECORD_SIZE;
+ bb->nr_pages = nr_pages;
+ bb->nr_bufs = nr_buf;
+ bb->snapshot = overwrite;
+ bb->data_pages = pages;
+ bb->real_size = size - size % BTS_RECORD_SIZE;
- for (pg = 0, nbuf = 0, offset = 0, pad = 0; nbuf < buf->nr_bufs; nbuf++) {
+ for (pg = 0, nr_buf = 0, offset = 0, pad = 0; nr_buf < bb->nr_bufs; nr_buf++) {
unsigned int __nr_pages;
page = virt_to_page(pages[pg]);
__nr_pages = buf_nr_pages(page);
- buf->buf[nbuf].page = page;
- buf->buf[nbuf].offset = offset;
- buf->buf[nbuf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0);
- buf->buf[nbuf].size = buf_size(page) - buf->buf[nbuf].displacement;
- pad = buf->buf[nbuf].size % BTS_RECORD_SIZE;
- buf->buf[nbuf].size -= pad;
+ bb->buf[nr_buf].page = page;
+ bb->buf[nr_buf].offset = offset;
+ bb->buf[nr_buf].displacement = (pad ? BTS_RECORD_SIZE - pad : 0);
+ bb->buf[nr_buf].size = buf_size(page) - bb->buf[nr_buf].displacement;
+ pad = bb->buf[nr_buf].size % BTS_RECORD_SIZE;
+ bb->buf[nr_buf].size -= pad;
pg += __nr_pages;
offset += __nr_pages << PAGE_SHIFT;
}
- return buf;
+ return bb;
}
static void bts_buffer_free_aux(void *data)
@@ -135,25 +136,25 @@ static void bts_buffer_free_aux(void *data)
kfree(data);
}
-static unsigned long bts_buffer_offset(struct bts_buffer *buf, unsigned int idx)
+static unsigned long bts_buffer_offset(struct bts_buffer *bb, unsigned int idx)
{
- return buf->buf[idx].offset + buf->buf[idx].displacement;
+ return bb->buf[idx].offset + bb->buf[idx].displacement;
}
static void
-bts_config_buffer(struct bts_buffer *buf)
+bts_config_buffer(struct bts_buffer *bb)
{
int cpu = raw_smp_processor_id();
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
- struct bts_phys *phys = &buf->buf[buf->cur_buf];
+ struct bts_phys *phys = &bb->buf[bb->cur_buf];
unsigned long index, thresh = 0, end = phys->size;
struct page *page = phys->page;
- index = local_read(&buf->head);
+ index = local_read(&bb->head);
- if (!buf->snapshot) {
- if (buf->end < phys->offset + buf_size(page))
- end = buf->end - phys->offset - phys->displacement;
+ if (!bb->snapshot) {
+ if (bb->end < phys->offset + buf_size(page))
+ end = bb->end - phys->offset - phys->displacement;
index -= phys->offset + phys->displacement;
@@ -168,7 +169,7 @@ bts_config_buffer(struct bts_buffer *buf)
ds->bts_buffer_base = (u64)(long)page_address(page) + phys->displacement;
ds->bts_index = ds->bts_buffer_base + index;
ds->bts_absolute_maximum = ds->bts_buffer_base + end;
- ds->bts_interrupt_threshold = !buf->snapshot
+ ds->bts_interrupt_threshold = !bb->snapshot
? ds->bts_buffer_base + thresh
: ds->bts_absolute_maximum + BTS_RECORD_SIZE;
}
@@ -184,16 +185,16 @@ static void bts_update(struct bts_ctx *bts)
{
int cpu = raw_smp_processor_id();
struct debug_store *ds = per_cpu(cpu_hw_events, cpu).ds;
- struct bts_buffer *buf = perf_get_aux(&bts->handle);
+ struct bts_buffer *bb = perf_get_aux(&bts->handle);
unsigned long index = ds->bts_index - ds->bts_buffer_base, old, head;
- if (!buf)
+ if (!bb)
return;
- head = index + bts_buffer_offset(buf, buf->cur_buf);
- old = local_xchg(&buf->head, head);
+ head = index + bts_buffer_offset(bb, bb->cur_buf);
+ old = local_xchg(&bb->head, head);
- if (!buf->snapshot) {
+ if (!bb->snapshot) {
if (old == head)
return;
@@ -205,9 +206,9 @@ static void bts_update(struct bts_ctx *bts)
* old and head are always in the same physical buffer, so we
* can subtract them to get the data size.
*/
- local_add(head - old, &buf->data_size);
+ local_add(head - old, &bb->data_size);
} else {
- local_set(&buf->data_size, head);
+ local_set(&bb->data_size, head);
}
/*
@@ -218,7 +219,7 @@ static void bts_update(struct bts_ctx *bts)
}
static int
-bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
+bts_buffer_reset(struct bts_buffer *bb, struct perf_output_handle *handle);
/*
* Ordering PMU callbacks wrt themselves and the PMI is done by means
@@ -232,17 +233,17 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle);
static void __bts_event_start(struct perf_event *event)
{
struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
- struct bts_buffer *buf = perf_get_aux(&bts->handle);
+ struct bts_buffer *bb = perf_get_aux(&bts->handle);
u64 config = 0;
- if (!buf->snapshot)
+ if (!bb->snapshot)
config |= ARCH_PERFMON_EVENTSEL_INT;
if (!event->attr.exclude_kernel)
config |= ARCH_PERFMON_EVENTSEL_OS;
if (!event->attr.exclude_user)
config |= ARCH_PERFMON_EVENTSEL_USR;
- bts_config_buffer(buf);
+ bts_config_buffer(bb);
/*
* local barrier to make sure that ds configuration made it
@@ -261,13 +262,13 @@ static void bts_event_start(struct perf_event *event, int flags)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
- struct bts_buffer *buf;
+ struct bts_buffer *bb;
- buf = perf_aux_output_begin(&bts->handle, event);
- if (!buf)
+ bb = perf_aux_output_begin(&bts->handle, event);
+ if (!bb)
goto fail_stop;
- if (bts_buffer_reset(buf, &bts->handle))
+ if (bts_buffer_reset(bb, &bts->handle))
goto fail_end_stop;
bts->ds_back.bts_buffer_base = cpuc->ds->bts_buffer_base;
@@ -306,27 +307,27 @@ static void bts_event_stop(struct perf_event *event, int flags)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct bts_ctx *bts = this_cpu_ptr(bts_ctx);
- struct bts_buffer *buf = NULL;
+ struct bts_buffer *bb = NULL;
int state = READ_ONCE(bts->state);
if (state == BTS_STATE_ACTIVE)
__bts_event_stop(event, BTS_STATE_STOPPED);
if (state != BTS_STATE_STOPPED)
- buf = perf_get_aux(&bts->handle);
+ bb = perf_get_aux(&bts->handle);
event->hw.state |= PERF_HES_STOPPED;
if (flags & PERF_EF_UPDATE) {
bts_update(bts);
- if (buf) {
- if (buf->snapshot)
+ if (bb) {
+ if (bb->snapshot)
bts->handle.head =
- local_xchg(&buf->data_size,
- buf->nr_pages << PAGE_SHIFT);
+ local_xchg(&bb->data_size,
+ bb->nr_pages << PAGE_SHIFT);
perf_aux_output_end(&bts->handle,
- local_xchg(&buf->data_size, 0));
+ local_xchg(&bb->data_size, 0));
}
cpuc->ds->bts_index = bts->ds_back.bts_buffer_base;
@@ -382,19 +383,19 @@ void intel_bts_disable_local(void)
}
static int
-bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
+bts_buffer_reset(struct bts_buffer *bb, struct perf_output_handle *handle)
{
unsigned long head, space, next_space, pad, gap, skip, wakeup;
unsigned int next_buf;
struct bts_phys *phys, *next_phys;
int ret;
- if (buf->snapshot)
+ if (bb->snapshot)
return 0;
- head = handle->head & ((buf->nr_pages << PAGE_SHIFT) - 1);
+ head = handle->head & ((bb->nr_pages << PAGE_SHIFT) - 1);
- phys = &buf->buf[buf->cur_buf];
+ phys = &bb->buf[bb->cur_buf];
space = phys->offset + phys->displacement + phys->size - head;
pad = space;
if (space > handle->size) {
@@ -403,10 +404,10 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
}
if (space <= BTS_SAFETY_MARGIN) {
/* See if next phys buffer has more space */
- next_buf = buf->cur_buf + 1;
- if (next_buf >= buf->nr_bufs)
+ next_buf = bb->cur_buf + 1;
+ if (next_buf >= bb->nr_bufs)
next_buf = 0;
- next_phys = &buf->buf[next_buf];
+ next_phys = &bb->buf[next_buf];
gap = buf_size(phys->page) - phys->displacement - phys->size +
next_phys->displacement;
skip = pad + gap;
@@ -431,8 +432,8 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
* anymore, so we must not be racing with
* bts_update().
*/
- buf->cur_buf = next_buf;
- local_set(&buf->head, head);
+ bb->cur_buf = next_buf;
+ local_set(&bb->head, head);
}
}
}
@@ -445,7 +446,7 @@ bts_buffer_reset(struct bts_buffer *buf, struct perf_output_handle *handle)
space -= space % BTS_RECORD_SIZE;
}
- buf->end = head + space;
+ bb->end = head + space;
/*
* If we have no space, the lost notification would have been sent when
@@ -462,7 +463,7 @@ int intel_bts_interrupt(void)
struct debug_store *ds = this_cpu_ptr(&cpu_hw_events)->ds;
struct bts_ctx *bts;
struct perf_event *event;
- struct bts_buffer *buf;
+ struct bts_buffer *bb;
s64 old_head;
int err = -ENOSPC, handled = 0;
@@ -485,8 +486,8 @@ int intel_bts_interrupt(void)
if (READ_ONCE(bts->state) == BTS_STATE_STOPPED)
return handled;
- buf = perf_get_aux(&bts->handle);
- if (!buf)
+ bb = perf_get_aux(&bts->handle);
+ if (!bb)
return handled;
/*
@@ -494,26 +495,26 @@ int intel_bts_interrupt(void)
* there's no other way of telling, because the pointer will
* keep moving
*/
- if (buf->snapshot)
+ if (bb->snapshot)
return 0;
- old_head = local_read(&buf->head);
+ old_head = local_read(&bb->head);
bts_update(bts);
/* no new data */
- if (old_head == local_read(&buf->head))
+ if (old_head == local_read(&bb->head))
return handled;
- perf_aux_output_end(&bts->handle, local_xchg(&buf->data_size, 0));
+ perf_aux_output_end(&bts->handle, local_xchg(&bb->data_size, 0));
- buf = perf_aux_output_begin(&bts->handle, event);
- if (buf)
- err = bts_buffer_reset(buf, &bts->handle);
+ bb = perf_aux_output_begin(&bts->handle, event);
+ if (bb)
+ err = bts_buffer_reset(bb, &bts->handle);
if (err) {
WRITE_ONCE(bts->state, BTS_STATE_STOPPED);
- if (buf) {
+ if (bb) {
/*
* BTS_STATE_STOPPED should be visible before
* cleared handle::event
@@ -599,7 +600,11 @@ static void bts_event_read(struct perf_event *event)
static __init int bts_init(void)
{
- if (!boot_cpu_has(X86_FEATURE_DTES64) || !x86_pmu.bts)
+ if (!boot_cpu_has(X86_FEATURE_DTES64))
+ return -ENODEV;
+
+ x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS);
+ if (!x86_pmu.bts)
return -ENODEV;
if (boot_cpu_has(X86_FEATURE_PTI)) {
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index c5f385413392..c2fb729c270e 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -23,6 +23,7 @@
#include <asm/intel_pt.h>
#include <asm/apic.h>
#include <asm/cpu_device_id.h>
+#include <asm/msr.h>
#include "../perf_event.h"
@@ -2224,6 +2225,18 @@ static struct extra_reg intel_cmt_extra_regs[] __read_mostly = {
EVENT_EXTRA_END
};
+EVENT_ATTR_STR(topdown-fe-bound, td_fe_bound_skt, "event=0x9c,umask=0x01");
+EVENT_ATTR_STR(topdown-retiring, td_retiring_skt, "event=0xc2,umask=0x02");
+EVENT_ATTR_STR(topdown-be-bound, td_be_bound_skt, "event=0xa4,umask=0x02");
+
+static struct attribute *skt_events_attrs[] = {
+ EVENT_PTR(td_fe_bound_skt),
+ EVENT_PTR(td_retiring_skt),
+ EVENT_PTR(td_bad_spec_cmt),
+ EVENT_PTR(td_be_bound_skt),
+ NULL,
+};
+
#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */
#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */
#define KNL_MCDRAM_LOCAL BIT_ULL(21)
@@ -2285,7 +2298,7 @@ static __always_inline void __intel_pmu_disable_all(bool bts)
{
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
- wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+ wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, 0);
if (bts && test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask))
intel_pmu_disable_bts();
@@ -2294,7 +2307,7 @@ static __always_inline void __intel_pmu_disable_all(bool bts)
static __always_inline void intel_pmu_disable_all(void)
{
__intel_pmu_disable_all(true);
- intel_pmu_pebs_disable_all();
+ static_call_cond(x86_pmu_pebs_disable_all)();
intel_pmu_lbr_disable_all();
}
@@ -2306,11 +2319,11 @@ static void __intel_pmu_enable_all(int added, bool pmi)
intel_pmu_lbr_enable_all(pmi);
if (cpuc->fixed_ctrl_val != cpuc->active_fixed_ctrl_val) {
- wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, cpuc->fixed_ctrl_val);
+ wrmsrq(MSR_ARCH_PERFMON_FIXED_CTR_CTRL, cpuc->fixed_ctrl_val);
cpuc->active_fixed_ctrl_val = cpuc->fixed_ctrl_val;
}
- wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL,
+ wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL,
intel_ctrl & ~cpuc->intel_ctrl_guest_mask);
if (test_bit(INTEL_PMC_IDX_FIXED_BTS, cpuc->active_mask)) {
@@ -2326,7 +2339,7 @@ static void __intel_pmu_enable_all(int added, bool pmi)
static void intel_pmu_enable_all(int added)
{
- intel_pmu_pebs_enable_all();
+ static_call_cond(x86_pmu_pebs_enable_all)();
__intel_pmu_enable_all(added, false);
}
@@ -2426,12 +2439,12 @@ static void intel_pmu_nhm_workaround(void)
}
for (i = 0; i < 4; i++) {
- wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, nhm_magic[i]);
- wrmsrl(MSR_ARCH_PERFMON_PERFCTR0 + i, 0x0);
+ wrmsrq(MSR_ARCH_PERFMON_EVENTSEL0 + i, nhm_magic[i]);
+ wrmsrq(MSR_ARCH_PERFMON_PERFCTR0 + i, 0x0);
}
- wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0xf);
- wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
+ wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, 0xf);
+ wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, 0x0);
for (i = 0; i < 4; i++) {
event = cpuc->events[i];
@@ -2441,7 +2454,7 @@ static void intel_pmu_nhm_workaround(void)
__x86_pmu_enable_event(&event->hw,
ARCH_PERFMON_EVENTSEL_ENABLE);
} else
- wrmsrl(MSR_ARCH_PERFMON_EVENTSEL0 + i, 0x0);
+ wrmsrq(MSR_ARCH_PERFMON_EVENTSEL0 + i, 0x0);
}
}
@@ -2458,7 +2471,7 @@ static void intel_set_tfa(struct cpu_hw_events *cpuc, bool on)
if (cpuc->tfa_shadow != val) {
cpuc->tfa_shadow = val;
- wrmsrl(MSR_TSX_FORCE_ABORT, val);
+ wrmsrq(MSR_TSX_FORCE_ABORT, val);
}
}
@@ -2489,14 +2502,14 @@ static inline u64 intel_pmu_get_status(void)
{
u64 status;
- rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+ rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, status);
return status;
}
static inline void intel_pmu_ack_status(u64 ack)
{
- wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
+ wrmsrq(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
}
static inline bool event_is_checkpointed(struct perf_event *event)
@@ -2583,7 +2596,7 @@ static void intel_pmu_disable_event(struct perf_event *event)
* so we don't trigger the event without PEBS bit set.
*/
if (unlikely(event->attr.precise_ip))
- intel_pmu_pebs_disable(event);
+ static_call(x86_pmu_pebs_disable)(event);
}
static void intel_pmu_assign_event(struct perf_event *event, int idx)
@@ -2603,6 +2616,9 @@ static void intel_pmu_del_event(struct perf_event *event)
intel_pmu_lbr_del(event);
if (event->attr.precise_ip)
intel_pmu_pebs_del(event);
+ if (is_pebs_counter_event_group(event) ||
+ is_acr_event_group(event))
+ this_cpu_ptr(&cpu_hw_events)->n_late_setup--;
}
static int icl_set_topdown_event_period(struct perf_event *event)
@@ -2619,15 +2635,15 @@ static int icl_set_topdown_event_period(struct perf_event *event)
* Don't need to clear them again.
*/
if (left == x86_pmu.max_period) {
- wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
- wrmsrl(MSR_PERF_METRICS, 0);
+ wrmsrq(MSR_CORE_PERF_FIXED_CTR3, 0);
+ wrmsrq(MSR_PERF_METRICS, 0);
hwc->saved_slots = 0;
hwc->saved_metric = 0;
}
if ((hwc->saved_slots) && is_slots_event(event)) {
- wrmsrl(MSR_CORE_PERF_FIXED_CTR3, hwc->saved_slots);
- wrmsrl(MSR_PERF_METRICS, hwc->saved_metric);
+ wrmsrq(MSR_CORE_PERF_FIXED_CTR3, hwc->saved_slots);
+ wrmsrq(MSR_PERF_METRICS, hwc->saved_metric);
}
perf_event_update_userpage(event);
@@ -2724,12 +2740,12 @@ static u64 intel_update_topdown_event(struct perf_event *event, int metric_end,
if (!val) {
/* read Fixed counter 3 */
- rdpmcl((3 | INTEL_PMC_FIXED_RDPMC_BASE), slots);
+ slots = rdpmc(3 | INTEL_PMC_FIXED_RDPMC_BASE);
if (!slots)
return 0;
/* read PERF_METRICS */
- rdpmcl(INTEL_PMC_FIXED_RDPMC_METRICS, metrics);
+ metrics = rdpmc(INTEL_PMC_FIXED_RDPMC_METRICS);
} else {
slots = val[0];
metrics = val[1];
@@ -2773,8 +2789,8 @@ static u64 intel_update_topdown_event(struct perf_event *event, int metric_end,
if (reset) {
/* The fixed counter 3 has to be written before the PERF_METRICS. */
- wrmsrl(MSR_CORE_PERF_FIXED_CTR3, 0);
- wrmsrl(MSR_PERF_METRICS, 0);
+ wrmsrq(MSR_CORE_PERF_FIXED_CTR3, 0);
+ wrmsrq(MSR_PERF_METRICS, 0);
if (event)
update_saved_topdown_regs(event, 0, 0, metric_end);
}
@@ -2810,7 +2826,7 @@ static void intel_pmu_read_event(struct perf_event *event)
* If the PEBS counters snapshotting is enabled,
* the topdown event is available in PEBS records.
*/
- if (is_topdown_event(event) && !is_pebs_counter_event_group(event))
+ if (is_topdown_count(event) && !is_pebs_counter_event_group(event))
static_call(intel_pmu_update_topdown_event)(event, NULL);
else
intel_pmu_drain_pebs_buffer();
@@ -2880,6 +2896,54 @@ static void intel_pmu_enable_fixed(struct perf_event *event)
cpuc->fixed_ctrl_val |= bits;
}
+static void intel_pmu_config_acr(int idx, u64 mask, u32 reload)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int msr_b, msr_c;
+ int msr_offset;
+
+ if (!mask && !cpuc->acr_cfg_b[idx])
+ return;
+
+ if (idx < INTEL_PMC_IDX_FIXED) {
+ msr_b = MSR_IA32_PMC_V6_GP0_CFG_B;
+ msr_c = MSR_IA32_PMC_V6_GP0_CFG_C;
+ msr_offset = x86_pmu.addr_offset(idx, false);
+ } else {
+ msr_b = MSR_IA32_PMC_V6_FX0_CFG_B;
+ msr_c = MSR_IA32_PMC_V6_FX0_CFG_C;
+ msr_offset = x86_pmu.addr_offset(idx - INTEL_PMC_IDX_FIXED, false);
+ }
+
+ if (cpuc->acr_cfg_b[idx] != mask) {
+ wrmsrl(msr_b + msr_offset, mask);
+ cpuc->acr_cfg_b[idx] = mask;
+ }
+ /* Only need to update the reload value when there is a valid config value. */
+ if (mask && cpuc->acr_cfg_c[idx] != reload) {
+ wrmsrl(msr_c + msr_offset, reload);
+ cpuc->acr_cfg_c[idx] = reload;
+ }
+}
+
+static void intel_pmu_enable_acr(struct perf_event *event)
+{
+ struct hw_perf_event *hwc = &event->hw;
+
+ if (!is_acr_event_group(event) || !event->attr.config2) {
+ /*
+ * The disable doesn't clear the ACR CFG register.
+ * Check and clear the ACR CFG register.
+ */
+ intel_pmu_config_acr(hwc->idx, 0, 0);
+ return;
+ }
+
+ intel_pmu_config_acr(hwc->idx, hwc->config1, -hwc->sample_period);
+}
+
+DEFINE_STATIC_CALL_NULL(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
+
static void intel_pmu_enable_event(struct perf_event *event)
{
u64 enable_mask = ARCH_PERFMON_EVENTSEL_ENABLE;
@@ -2887,16 +2951,19 @@ static void intel_pmu_enable_event(struct perf_event *event)
int idx = hwc->idx;
if (unlikely(event->attr.precise_ip))
- intel_pmu_pebs_enable(event);
+ static_call(x86_pmu_pebs_enable)(event);
switch (idx) {
case 0 ... INTEL_PMC_IDX_FIXED - 1:
if (branch_sample_counters(event))
enable_mask |= ARCH_PERFMON_EVENTSEL_BR_CNTR;
intel_set_masks(event, idx);
+ static_call_cond(intel_pmu_enable_acr_event)(event);
__x86_pmu_enable_event(hwc, enable_mask);
break;
case INTEL_PMC_IDX_FIXED ... INTEL_PMC_IDX_FIXED_BTS - 1:
+ static_call_cond(intel_pmu_enable_acr_event)(event);
+ fallthrough;
case INTEL_PMC_IDX_METRIC_BASE ... INTEL_PMC_IDX_METRIC_END:
intel_pmu_enable_fixed(event);
break;
@@ -2914,12 +2981,51 @@ static void intel_pmu_enable_event(struct perf_event *event)
}
}
+static void intel_pmu_acr_late_setup(struct cpu_hw_events *cpuc)
+{
+ struct perf_event *event, *leader;
+ int i, j, idx;
+
+ for (i = 0; i < cpuc->n_events; i++) {
+ leader = cpuc->event_list[i];
+ if (!is_acr_event_group(leader))
+ continue;
+
+ /* The ACR events must be contiguous. */
+ for (j = i; j < cpuc->n_events; j++) {
+ event = cpuc->event_list[j];
+ if (event->group_leader != leader->group_leader)
+ break;
+ for_each_set_bit(idx, (unsigned long *)&event->attr.config2, X86_PMC_IDX_MAX) {
+ if (WARN_ON_ONCE(i + idx > cpuc->n_events))
+ return;
+ __set_bit(cpuc->assign[i + idx], (unsigned long *)&event->hw.config1);
+ }
+ }
+ i = j - 1;
+ }
+}
+
+void intel_pmu_late_setup(void)
+{
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+
+ if (!cpuc->n_late_setup)
+ return;
+
+ intel_pmu_pebs_late_setup(cpuc);
+ intel_pmu_acr_late_setup(cpuc);
+}
+
static void intel_pmu_add_event(struct perf_event *event)
{
if (event->attr.precise_ip)
intel_pmu_pebs_add(event);
if (intel_pmu_needs_branch_stack(event))
intel_pmu_lbr_add(event);
+ if (is_pebs_counter_event_group(event) ||
+ is_acr_event_group(event))
+ this_cpu_ptr(&cpu_hw_events)->n_late_setup++;
}
/*
@@ -2937,7 +3043,7 @@ int intel_pmu_save_and_restart(struct perf_event *event)
*/
if (unlikely(event_is_checkpointed(event))) {
/* No race with NMIs because the counter should not be armed */
- wrmsrl(event->hw.event_base, 0);
+ wrmsrq(event->hw.event_base, 0);
local64_set(&event->hw.prev_count, 0);
}
return static_call(x86_pmu_set_period)(event);
@@ -2976,13 +3082,13 @@ static void intel_pmu_reset(void)
pr_info("clearing PMU state on CPU#%d\n", smp_processor_id());
for_each_set_bit(idx, cntr_mask, INTEL_PMC_MAX_GENERIC) {
- wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
- wrmsrl_safe(x86_pmu_event_addr(idx), 0ull);
+ wrmsrq_safe(x86_pmu_config_addr(idx), 0ull);
+ wrmsrq_safe(x86_pmu_event_addr(idx), 0ull);
}
for_each_set_bit(idx, fixed_cntr_mask, INTEL_PMC_MAX_FIXED) {
if (fixed_counter_disabled(idx, cpuc->pmu))
continue;
- wrmsrl_safe(x86_pmu_fixed_ctr_addr(idx), 0ull);
+ wrmsrq_safe(x86_pmu_fixed_ctr_addr(idx), 0ull);
}
if (ds)
@@ -2991,7 +3097,7 @@ static void intel_pmu_reset(void)
/* Ack all overflows and disable fixed counters */
if (x86_pmu.version >= 2) {
intel_pmu_ack_status(intel_pmu_get_status());
- wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+ wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, 0);
}
/* Reset LBRs and LBR freezing */
@@ -3035,8 +3141,7 @@ static void x86_pmu_handle_guest_pebs(struct pt_regs *regs,
continue;
perf_sample_data_init(data, 0, event->hw.last_period);
- if (perf_event_overflow(event, data, regs))
- x86_pmu_stop(event, 0);
+ perf_event_overflow(event, data, regs);
/* Inject one fake event is enough. */
break;
@@ -3101,7 +3206,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
* Update the MSR if pebs_enabled is changed.
*/
if (pebs_enabled != cpuc->pebs_enabled)
- wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+ wrmsrq(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
/*
* Above PEBS handler (PEBS counters snapshotting) has updated fixed
@@ -3141,6 +3246,7 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[bit];
+ u64 last_period;
handled++;
@@ -3168,16 +3274,17 @@ static int handle_pmi_common(struct pt_regs *regs, u64 status)
if (is_pebs_counter_event_group(event))
x86_pmu.drain_pebs(regs, &data);
+ last_period = event->hw.last_period;
+
if (!intel_pmu_save_and_restart(event))
continue;
- perf_sample_data_init(&data, 0, event->hw.last_period);
+ perf_sample_data_init(&data, 0, last_period);
if (has_branch_stack(event))
intel_pmu_lbr_save_brstack(&data, cpuc, event);
- if (perf_event_overflow(event, &data, regs))
- x86_pmu_stop(event, 0);
+ perf_event_overflow(event, &data, regs);
}
return handled;
@@ -3739,10 +3846,9 @@ intel_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
if (cpuc->excl_cntrs)
return intel_get_excl_constraints(cpuc, event, idx, c2);
- /* Not all counters support the branch counter feature. */
- if (branch_sample_counters(event)) {
+ if (event->hw.dyn_constraint != ~0ULL) {
c2 = dyn_constraint(cpuc, c2, idx);
- c2->idxmsk64 &= x86_pmu.lbr_counters;
+ c2->idxmsk64 &= event->hw.dyn_constraint;
c2->weight = hweight64(c2->idxmsk64);
}
@@ -4083,6 +4189,39 @@ end:
return start;
}
+static inline bool intel_pmu_has_acr(struct pmu *pmu)
+{
+ return !!hybrid(pmu, acr_cause_mask64);
+}
+
+static bool intel_pmu_is_acr_group(struct perf_event *event)
+{
+ /* The group leader has the ACR flag set */
+ if (is_acr_event_group(event))
+ return true;
+
+ /* The acr_mask is set */
+ if (event->attr.config2)
+ return true;
+
+ return false;
+}
+
+static inline void intel_pmu_set_acr_cntr_constr(struct perf_event *event,
+ u64 *cause_mask, int *num)
+{
+ event->hw.dyn_constraint &= hybrid(event->pmu, acr_cntr_mask64);
+ *cause_mask |= event->attr.config2;
+ *num += 1;
+}
+
+static inline void intel_pmu_set_acr_caused_constr(struct perf_event *event,
+ int idx, u64 cause_mask)
+{
+ if (test_bit(idx, (unsigned long *)&cause_mask))
+ event->hw.dyn_constraint &= hybrid(event->pmu, acr_cause_mask64);
+}
+
static int intel_pmu_hw_config(struct perf_event *event)
{
int ret = x86_pmu_hw_config(event);
@@ -4144,15 +4283,19 @@ static int intel_pmu_hw_config(struct perf_event *event)
leader = event->group_leader;
if (branch_sample_call_stack(leader))
return -EINVAL;
- if (branch_sample_counters(leader))
+ if (branch_sample_counters(leader)) {
num++;
+ leader->hw.dyn_constraint &= x86_pmu.lbr_counters;
+ }
leader->hw.flags |= PERF_X86_EVENT_BRANCH_COUNTERS;
for_each_sibling_event(sibling, leader) {
if (branch_sample_call_stack(sibling))
return -EINVAL;
- if (branch_sample_counters(sibling))
+ if (branch_sample_counters(sibling)) {
num++;
+ sibling->hw.dyn_constraint &= x86_pmu.lbr_counters;
+ }
}
if (num > fls(x86_pmu.lbr_counters))
@@ -4207,6 +4350,94 @@ static int intel_pmu_hw_config(struct perf_event *event)
event->attr.precise_ip)
event->group_leader->hw.flags |= PERF_X86_EVENT_PEBS_CNTR;
+ if (intel_pmu_has_acr(event->pmu) && intel_pmu_is_acr_group(event)) {
+ struct perf_event *sibling, *leader = event->group_leader;
+ struct pmu *pmu = event->pmu;
+ bool has_sw_event = false;
+ int num = 0, idx = 0;
+ u64 cause_mask = 0;
+
+ /* Not support perf metrics */
+ if (is_metric_event(event))
+ return -EINVAL;
+
+ /* Not support freq mode */
+ if (event->attr.freq)
+ return -EINVAL;
+
+ /* PDist is not supported */
+ if (event->attr.config2 && event->attr.precise_ip > 2)
+ return -EINVAL;
+
+ /* The reload value cannot exceeds the max period */
+ if (event->attr.sample_period > x86_pmu.max_period)
+ return -EINVAL;
+ /*
+ * The counter-constraints of each event cannot be finalized
+ * unless the whole group is scanned. However, it's hard
+ * to know whether the event is the last one of the group.
+ * Recalculate the counter-constraints for each event when
+ * adding a new event.
+ *
+ * The group is traversed twice, which may be optimized later.
+ * In the first round,
+ * - Find all events which do reload when other events
+ * overflow and set the corresponding counter-constraints
+ * - Add all events, which can cause other events reload,
+ * in the cause_mask
+ * - Error out if the number of events exceeds the HW limit
+ * - The ACR events must be contiguous.
+ * Error out if there are non-X86 events between ACR events.
+ * This is not a HW limit, but a SW limit.
+ * With the assumption, the intel_pmu_acr_late_setup() can
+ * easily convert the event idx to counter idx without
+ * traversing the whole event list.
+ */
+ if (!is_x86_event(leader))
+ return -EINVAL;
+
+ if (leader->attr.config2)
+ intel_pmu_set_acr_cntr_constr(leader, &cause_mask, &num);
+
+ if (leader->nr_siblings) {
+ for_each_sibling_event(sibling, leader) {
+ if (!is_x86_event(sibling)) {
+ has_sw_event = true;
+ continue;
+ }
+ if (!sibling->attr.config2)
+ continue;
+ if (has_sw_event)
+ return -EINVAL;
+ intel_pmu_set_acr_cntr_constr(sibling, &cause_mask, &num);
+ }
+ }
+ if (leader != event && event->attr.config2) {
+ if (has_sw_event)
+ return -EINVAL;
+ intel_pmu_set_acr_cntr_constr(event, &cause_mask, &num);
+ }
+
+ if (hweight64(cause_mask) > hweight64(hybrid(pmu, acr_cause_mask64)) ||
+ num > hweight64(hybrid(event->pmu, acr_cntr_mask64)))
+ return -EINVAL;
+ /*
+ * In the second round, apply the counter-constraints for
+ * the events which can cause other events reload.
+ */
+ intel_pmu_set_acr_caused_constr(leader, idx++, cause_mask);
+
+ if (leader->nr_siblings) {
+ for_each_sibling_event(sibling, leader)
+ intel_pmu_set_acr_caused_constr(sibling, idx++, cause_mask);
+ }
+
+ if (leader != event)
+ intel_pmu_set_acr_caused_constr(event, idx, cause_mask);
+
+ leader->hw.flags |= PERF_X86_EVENT_ACR;
+ }
+
if ((event->attr.type == PERF_TYPE_HARDWARE) ||
(event->attr.type == PERF_TYPE_HW_CACHE))
return 0;
@@ -4354,7 +4585,7 @@ static struct perf_guest_switch_msr *intel_guest_get_msrs(int *nr, void *data)
.guest = intel_ctrl & ~cpuc->intel_ctrl_host_mask & ~pebs_mask,
};
- if (!x86_pmu.pebs)
+ if (!x86_pmu.ds_pebs)
return arr;
/*
@@ -4952,7 +5183,7 @@ int intel_cpuc_prepare(struct cpu_hw_events *cpuc, int cpu)
goto err;
}
- if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_BR_CNTR)) {
+ if (x86_pmu.flags & (PMU_FL_EXCL_CNTRS | PMU_FL_TFA | PMU_FL_DYN_CONSTRAINT)) {
size_t sz = X86_PMC_IDX_MAX * sizeof(struct event_constraint);
cpuc->constraint_list = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
@@ -5041,7 +5272,7 @@ static inline bool intel_pmu_broken_perf_cap(void)
return false;
}
-static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
+static void update_pmu_cap(struct pmu *pmu)
{
unsigned int cntr, fixed_cntr, ecx, edx;
union cpuid35_eax eax;
@@ -5050,20 +5281,30 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
cpuid(ARCH_PERFMON_EXT_LEAF, &eax.full, &ebx.full, &ecx, &edx);
if (ebx.split.umask2)
- pmu->config_mask |= ARCH_PERFMON_EVENTSEL_UMASK2;
+ hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_UMASK2;
if (ebx.split.eq)
- pmu->config_mask |= ARCH_PERFMON_EVENTSEL_EQ;
+ hybrid(pmu, config_mask) |= ARCH_PERFMON_EVENTSEL_EQ;
if (eax.split.cntr_subleaf) {
cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
&cntr, &fixed_cntr, &ecx, &edx);
- pmu->cntr_mask64 = cntr;
- pmu->fixed_cntr_mask64 = fixed_cntr;
+ hybrid(pmu, cntr_mask64) = cntr;
+ hybrid(pmu, fixed_cntr_mask64) = fixed_cntr;
+ }
+
+ if (eax.split.acr_subleaf) {
+ cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_ACR_LEAF,
+ &cntr, &fixed_cntr, &ecx, &edx);
+ /* The mask of the counters which can be reloaded */
+ hybrid(pmu, acr_cntr_mask64) = cntr | ((u64)fixed_cntr << INTEL_PMC_IDX_FIXED);
+
+ /* The mask of the counters which can cause a reload of reloadable counters */
+ hybrid(pmu, acr_cause_mask64) = ecx | ((u64)edx << INTEL_PMC_IDX_FIXED);
}
if (!intel_pmu_broken_perf_cap()) {
/* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
- rdmsrl(MSR_IA32_PERF_CAPABILITIES, pmu->intel_cap.capabilities);
+ rdmsrq(MSR_IA32_PERF_CAPABILITIES, hybrid(pmu, intel_cap).capabilities);
}
}
@@ -5150,7 +5391,7 @@ static bool init_hybrid_pmu(int cpu)
goto end;
if (this_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
- update_pmu_cap(pmu);
+ update_pmu_cap(&pmu->pmu);
intel_pmu_check_hybrid_pmus(pmu);
@@ -5211,7 +5452,7 @@ static void intel_pmu_cpu_starting(int cpu)
if (!is_hybrid() && x86_pmu.intel_cap.perf_metrics) {
union perf_capabilities perf_cap;
- rdmsrl(MSR_IA32_PERF_CAPABILITIES, perf_cap.capabilities);
+ rdmsrq(MSR_IA32_PERF_CAPABILITIES, perf_cap.capabilities);
if (!perf_cap.perf_metrics) {
x86_pmu.intel_cap.perf_metrics = 0;
x86_pmu.intel_ctrl &= ~(1ULL << GLOBAL_CTRL_EN_PERF_METRICS);
@@ -5524,7 +5765,7 @@ static __init void intel_clovertown_quirk(void)
* these chips.
*/
pr_warn("PEBS disabled due to CPU errata\n");
- x86_pmu.pebs = 0;
+ x86_pmu.ds_pebs = 0;
x86_pmu.pebs_constraints = NULL;
}
@@ -5619,24 +5860,24 @@ static bool check_msr(unsigned long msr, u64 mask)
* matches, this is needed to detect certain hardware emulators
* (qemu/kvm) that don't trap on the MSR access and always return 0s.
*/
- if (rdmsrl_safe(msr, &val_old))
+ if (rdmsrq_safe(msr, &val_old))
return false;
/*
- * Only change the bits which can be updated by wrmsrl.
+ * Only change the bits which can be updated by wrmsrq.
*/
val_tmp = val_old ^ mask;
if (is_lbr_from(msr))
val_tmp = lbr_from_signext_quirk_wr(val_tmp);
- if (wrmsrl_safe(msr, val_tmp) ||
- rdmsrl_safe(msr, &val_new))
+ if (wrmsrq_safe(msr, val_tmp) ||
+ rdmsrq_safe(msr, &val_new))
return false;
/*
- * Quirk only affects validation in wrmsr(), so wrmsrl()'s value
- * should equal rdmsrl()'s even with the quirk.
+ * Quirk only affects validation in wrmsr(), so wrmsrq()'s value
+ * should equal rdmsrq()'s even with the quirk.
*/
if (val_new != val_tmp)
return false;
@@ -5647,7 +5888,7 @@ static bool check_msr(unsigned long msr, u64 mask)
/* Here it's sure that the MSR can be safely accessed.
* Restore the old value and return.
*/
- wrmsrl(msr, val_old);
+ wrmsrq(msr, val_old);
return true;
}
@@ -6012,7 +6253,7 @@ tsx_is_visible(struct kobject *kobj, struct attribute *attr, int i)
static umode_t
pebs_is_visible(struct kobject *kobj, struct attribute *attr, int i)
{
- return x86_pmu.pebs ? attr->mode : 0;
+ return x86_pmu.ds_pebs ? attr->mode : 0;
}
static umode_t
@@ -6043,6 +6284,21 @@ td_is_visible(struct kobject *kobj, struct attribute *attr, int i)
return attr->mode;
}
+PMU_FORMAT_ATTR(acr_mask, "config2:0-63");
+
+static struct attribute *format_acr_attrs[] = {
+ &format_attr_acr_mask.attr,
+ NULL
+};
+
+static umode_t
+acr_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+ struct device *dev = kobj_to_dev(kobj);
+
+ return intel_pmu_has_acr(dev_get_drvdata(dev)) ? attr->mode : 0;
+}
+
static struct attribute_group group_events_td = {
.name = "events",
.is_visible = td_is_visible,
@@ -6085,6 +6341,12 @@ static struct attribute_group group_format_evtsel_ext = {
.is_visible = evtsel_ext_is_visible,
};
+static struct attribute_group group_format_acr = {
+ .name = "format",
+ .attrs = format_acr_attrs,
+ .is_visible = acr_is_visible,
+};
+
static struct attribute_group group_default = {
.attrs = intel_pmu_attrs,
.is_visible = default_is_visible,
@@ -6099,6 +6361,7 @@ static const struct attribute_group *attr_update[] = {
&group_format_extra,
&group_format_extra_skl,
&group_format_evtsel_ext,
+ &group_format_acr,
&group_default,
NULL,
};
@@ -6383,6 +6646,7 @@ static const struct attribute_group *hybrid_attr_update[] = {
&group_caps_lbr,
&hybrid_group_format_extra,
&group_format_evtsel_ext,
+ &group_format_acr,
&group_default,
&hybrid_group_cpus,
NULL,
@@ -6575,6 +6839,7 @@ static __always_inline void intel_pmu_init_skt(struct pmu *pmu)
intel_pmu_init_grt(pmu);
hybrid(pmu, event_constraints) = intel_skt_event_constraints;
hybrid(pmu, extra_regs) = intel_cmt_extra_regs;
+ static_call_update(intel_pmu_enable_acr_event, intel_pmu_enable_acr);
}
__init int intel_pmu_init(void)
@@ -6635,6 +6900,7 @@ __init int intel_pmu_init(void)
x86_pmu.pebs_events_mask = intel_pmu_pebs_mask(x86_pmu.cntr_mask64);
x86_pmu.pebs_capable = PEBS_COUNTER_MASK;
+ x86_pmu.config_mask = X86_RAW_EVENT_MASK;
/*
* Quirk: v2 perfmon does not report fixed-purpose events, so
@@ -6651,7 +6917,7 @@ __init int intel_pmu_init(void)
if (boot_cpu_has(X86_FEATURE_PDCM)) {
u64 capabilities;
- rdmsrl(MSR_IA32_PERF_CAPABILITIES, capabilities);
+ rdmsrq(MSR_IA32_PERF_CAPABILITIES, capabilities);
x86_pmu.intel_cap.capabilities = capabilities;
}
@@ -6663,7 +6929,7 @@ __init int intel_pmu_init(void)
if (boot_cpu_has(X86_FEATURE_ARCH_LBR))
intel_pmu_arch_lbr_init();
- intel_ds_init();
+ intel_pebs_init();
x86_add_quirk(intel_arch_events_quirk); /* Install first, so it runs last */
@@ -6674,6 +6940,12 @@ __init int intel_pmu_init(void)
}
/*
+ * Many features on and after V6 require dynamic constraint,
+ * e.g., Arch PEBS, ACR.
+ */
+ if (version >= 6)
+ x86_pmu.flags |= PMU_FL_DYN_CONSTRAINT;
+ /*
* Install the hw-cache-events table:
*/
switch (boot_cpu_data.x86_vfm) {
@@ -6884,6 +7156,18 @@ __init int intel_pmu_init(void)
name = "crestmont";
break;
+ case INTEL_ATOM_DARKMONT_X:
+ intel_pmu_init_skt(NULL);
+ intel_pmu_pebs_data_source_cmt();
+ x86_pmu.pebs_latency_data = cmt_latency_data;
+ x86_pmu.get_event_constraints = cmt_get_event_constraints;
+ td_attr = skt_events_attrs;
+ mem_attr = grt_mem_attrs;
+ extra_attr = cmt_format_attr;
+ pr_cont("Darkmont events, ");
+ name = "darkmont";
+ break;
+
case INTEL_WESTMERE:
case INTEL_WESTMERE_EP:
case INTEL_WESTMERE_EX:
@@ -7433,6 +7717,18 @@ __init int intel_pmu_init(void)
x86_pmu.attr_update = hybrid_attr_update;
}
+ /*
+ * The archPerfmonExt (0x23) includes an enhanced enumeration of
+ * PMU architectural features with a per-core view. For non-hybrid,
+ * each core has the same PMU capabilities. It's good enough to
+ * update the x86_pmu from the booting CPU. For hybrid, the x86_pmu
+ * is used to keep the common capabilities. Still keep the values
+ * from the leaf 0xa. The core specific update will be done later
+ * when a new type is online.
+ */
+ if (!is_hybrid() && boot_cpu_has(X86_FEATURE_ARCH_PERFMON_EXT))
+ update_pmu_cap(NULL);
+
intel_pmu_check_counters_mask(&x86_pmu.cntr_mask64,
&x86_pmu.fixed_cntr_mask64,
&x86_pmu.intel_ctrl);
diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
index ae4ec16156bb..ec753e39b007 100644
--- a/arch/x86/events/intel/cstate.c
+++ b/arch/x86/events/intel/cstate.c
@@ -111,6 +111,7 @@
#include <linux/nospec.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
+#include <asm/msr.h>
#include "../perf_event.h"
#include "../probe.h"
@@ -320,7 +321,7 @@ static inline u64 cstate_pmu_read_counter(struct perf_event *event)
{
u64 val;
- rdmsrl(event->hw.event_base, val);
+ rdmsrq(event->hw.event_base, val);
return val;
}
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
index 8d86e91bd5e5..c0b7ac1c7594 100644
--- a/arch/x86/events/intel/ds.c
+++ b/arch/x86/events/intel/ds.c
@@ -10,6 +10,7 @@
#include <asm/tlbflush.h>
#include <asm/insn.h>
#include <asm/io.h>
+#include <asm/msr.h>
#include <asm/timer.h>
#include "../perf_event.h"
@@ -624,7 +625,7 @@ static int alloc_pebs_buffer(int cpu)
int max, node = cpu_to_node(cpu);
void *buffer, *insn_buff, *cea;
- if (!x86_pmu.pebs)
+ if (!x86_pmu.ds_pebs)
return 0;
buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu);
@@ -659,7 +660,7 @@ static void release_pebs_buffer(int cpu)
struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu);
void *cea;
- if (!x86_pmu.pebs)
+ if (!x86_pmu.ds_pebs)
return;
kfree(per_cpu(insn_buffer, cpu));
@@ -734,7 +735,7 @@ void release_ds_buffers(void)
{
int cpu;
- if (!x86_pmu.bts && !x86_pmu.pebs)
+ if (!x86_pmu.bts && !x86_pmu.ds_pebs)
return;
for_each_possible_cpu(cpu)
@@ -750,7 +751,8 @@ void release_ds_buffers(void)
}
for_each_possible_cpu(cpu) {
- release_pebs_buffer(cpu);
+ if (x86_pmu.ds_pebs)
+ release_pebs_buffer(cpu);
release_bts_buffer(cpu);
}
}
@@ -761,15 +763,17 @@ void reserve_ds_buffers(void)
int cpu;
x86_pmu.bts_active = 0;
- x86_pmu.pebs_active = 0;
- if (!x86_pmu.bts && !x86_pmu.pebs)
+ if (x86_pmu.ds_pebs)
+ x86_pmu.pebs_active = 0;
+
+ if (!x86_pmu.bts && !x86_pmu.ds_pebs)
return;
if (!x86_pmu.bts)
bts_err = 1;
- if (!x86_pmu.pebs)
+ if (!x86_pmu.ds_pebs)
pebs_err = 1;
for_each_possible_cpu(cpu) {
@@ -781,7 +785,8 @@ void reserve_ds_buffers(void)
if (!bts_err && alloc_bts_buffer(cpu))
bts_err = 1;
- if (!pebs_err && alloc_pebs_buffer(cpu))
+ if (x86_pmu.ds_pebs && !pebs_err &&
+ alloc_pebs_buffer(cpu))
pebs_err = 1;
if (bts_err && pebs_err)
@@ -793,7 +798,7 @@ void reserve_ds_buffers(void)
release_bts_buffer(cpu);
}
- if (pebs_err) {
+ if (x86_pmu.ds_pebs && pebs_err) {
for_each_possible_cpu(cpu)
release_pebs_buffer(cpu);
}
@@ -805,7 +810,7 @@ void reserve_ds_buffers(void)
if (x86_pmu.bts && !bts_err)
x86_pmu.bts_active = 1;
- if (x86_pmu.pebs && !pebs_err)
+ if (x86_pmu.ds_pebs && !pebs_err)
x86_pmu.pebs_active = 1;
for_each_possible_cpu(cpu) {
@@ -1355,9 +1360,8 @@ static void __intel_pmu_pebs_update_cfg(struct perf_event *event,
}
-static void intel_pmu_late_setup(void)
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc)
{
- struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
struct perf_event *event;
u64 pebs_data_cfg = 0;
int i;
@@ -1517,7 +1521,7 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event)
else
value = ds->pebs_event_reset[MAX_PEBS_EVENTS + idx];
}
- wrmsrl(base + idx, value);
+ wrmsrq(base + idx, value);
}
static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc)
@@ -1554,7 +1558,7 @@ void intel_pmu_pebs_enable(struct perf_event *event)
*/
intel_pmu_drain_pebs_buffer();
adaptive_pebs_record_size_update();
- wrmsrl(MSR_PEBS_DATA_CFG, pebs_data_cfg);
+ wrmsrq(MSR_PEBS_DATA_CFG, pebs_data_cfg);
cpuc->active_pebs_data_cfg = pebs_data_cfg;
}
}
@@ -1617,7 +1621,7 @@ void intel_pmu_pebs_disable(struct perf_event *event)
intel_pmu_pebs_via_pt_disable(event);
if (cpuc->enabled)
- wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+ wrmsrq(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
hwc->config |= ARCH_PERFMON_EVENTSEL_INT;
}
@@ -1627,7 +1631,7 @@ void intel_pmu_pebs_enable_all(void)
struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
if (cpuc->pebs_enabled)
- wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
+ wrmsrq(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled);
}
void intel_pmu_pebs_disable_all(void)
@@ -1828,8 +1832,6 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event,
perf_sample_data_init(data, 0, event->hw.last_period);
- data->period = event->hw.last_period;
-
/*
* Use latency for weight (only avail with PEBS-LL)
*/
@@ -2082,7 +2084,6 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
sample_type = event->attr.sample_type;
format_group = basic->format_group;
perf_sample_data_init(data, 0, event->hw.last_period);
- data->period = event->hw.last_period;
setup_pebs_time(event, data, basic->tsc);
@@ -2276,7 +2277,7 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count)
WARN_ON(this_cpu_read(cpu_hw_events.enabled));
prev_raw_count = local64_read(&hwc->prev_count);
- rdpmcl(hwc->event_base_rdpmc, new_raw_count);
+ new_raw_count = rdpmc(hwc->event_base_rdpmc);
local64_set(&hwc->prev_count, new_raw_count);
/*
@@ -2359,8 +2360,7 @@ __intel_pmu_pebs_last_event(struct perf_event *event,
* All but the last records are processed.
* The last one is left to be able to call the overflow handler.
*/
- if (perf_event_overflow(event, data, regs))
- x86_pmu_stop(event, 0);
+ perf_event_overflow(event, data, regs);
}
if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) {
@@ -2589,8 +2589,8 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
if (error[bit]) {
perf_log_lost_samples(event, error[bit]);
- if (iregs && perf_event_account_interrupt(event))
- x86_pmu_stop(event, 0);
+ if (iregs)
+ perf_event_account_interrupt(event);
}
if (counts[bit]) {
@@ -2670,10 +2670,10 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
}
/*
- * BTS, PEBS probe and setup
+ * PEBS probe and setup
*/
-void __init intel_ds_init(void)
+void __init intel_pebs_init(void)
{
/*
* No support for 32bit formats
@@ -2681,13 +2681,12 @@ void __init intel_ds_init(void)
if (!boot_cpu_has(X86_FEATURE_DTES64))
return;
- x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS);
- x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS);
+ x86_pmu.ds_pebs = boot_cpu_has(X86_FEATURE_PEBS);
x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE;
if (x86_pmu.version <= 4)
x86_pmu.pebs_no_isolation = 1;
- if (x86_pmu.pebs) {
+ if (x86_pmu.ds_pebs) {
char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-';
char *pebs_qual = "";
int format = x86_pmu.intel_cap.pebs_format;
@@ -2695,6 +2694,11 @@ void __init intel_ds_init(void)
if (format < 4)
x86_pmu.intel_cap.pebs_baseline = 0;
+ x86_pmu.pebs_enable = intel_pmu_pebs_enable;
+ x86_pmu.pebs_disable = intel_pmu_pebs_disable;
+ x86_pmu.pebs_enable_all = intel_pmu_pebs_enable_all;
+ x86_pmu.pebs_disable_all = intel_pmu_pebs_disable_all;
+
switch (format) {
case 0:
pr_cont("PEBS fmt0%c, ", pebs_type);
@@ -2779,7 +2783,7 @@ void __init intel_ds_init(void)
default:
pr_cont("no PEBS fmt%d%c, ", format, pebs_type);
- x86_pmu.pebs = 0;
+ x86_pmu.ds_pebs = 0;
}
}
}
@@ -2788,8 +2792,8 @@ void perf_restore_debug_store(void)
{
struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
- if (!x86_pmu.bts && !x86_pmu.pebs)
+ if (!x86_pmu.bts && !x86_pmu.ds_pebs)
return;
- wrmsrl(MSR_IA32_DS_AREA, (unsigned long)ds);
+ wrmsrq(MSR_IA32_DS_AREA, (unsigned long)ds);
}
diff --git a/arch/x86/events/intel/knc.c b/arch/x86/events/intel/knc.c
index 034a1f6a457c..e614baf42926 100644
--- a/arch/x86/events/intel/knc.c
+++ b/arch/x86/events/intel/knc.c
@@ -5,6 +5,7 @@
#include <linux/types.h>
#include <asm/hardirq.h>
+#include <asm/msr.h>
#include "../perf_event.h"
@@ -159,18 +160,18 @@ static void knc_pmu_disable_all(void)
{
u64 val;
- rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+ rdmsrq(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
val &= ~(KNC_ENABLE_COUNTER0|KNC_ENABLE_COUNTER1);
- wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+ wrmsrq(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
}
static void knc_pmu_enable_all(int added)
{
u64 val;
- rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+ rdmsrq(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
val |= (KNC_ENABLE_COUNTER0|KNC_ENABLE_COUNTER1);
- wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
+ wrmsrq(MSR_KNC_IA32_PERF_GLOBAL_CTRL, val);
}
static inline void
@@ -182,7 +183,7 @@ knc_pmu_disable_event(struct perf_event *event)
val = hwc->config;
val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
+ (void)wrmsrq_safe(hwc->config_base + hwc->idx, val);
}
static void knc_pmu_enable_event(struct perf_event *event)
@@ -193,21 +194,21 @@ static void knc_pmu_enable_event(struct perf_event *event)
val = hwc->config;
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- (void)wrmsrl_safe(hwc->config_base + hwc->idx, val);
+ (void)wrmsrq_safe(hwc->config_base + hwc->idx, val);
}
static inline u64 knc_pmu_get_status(void)
{
u64 status;
- rdmsrl(MSR_KNC_IA32_PERF_GLOBAL_STATUS, status);
+ rdmsrq(MSR_KNC_IA32_PERF_GLOBAL_STATUS, status);
return status;
}
static inline void knc_pmu_ack_status(u64 ack)
{
- wrmsrl(MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL, ack);
+ wrmsrq(MSR_KNC_IA32_PERF_GLOBAL_OVF_CONTROL, ack);
}
static int knc_pmu_handle_irq(struct pt_regs *regs)
@@ -241,19 +242,20 @@ again:
for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
struct perf_event *event = cpuc->events[bit];
+ u64 last_period;
handled++;
if (!test_bit(bit, cpuc->active_mask))
continue;
+ last_period = event->hw.last_period;
if (!intel_pmu_save_and_restart(event))
continue;
- perf_sample_data_init(&data, 0, event->hw.last_period);
+ perf_sample_data_init(&data, 0, last_period);
- if (perf_event_overflow(event, &data, regs))
- x86_pmu_stop(event, 0);
+ perf_event_overflow(event, &data, regs);
}
/*
diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c
index f44c3d866f24..7aa59966e7c3 100644
--- a/arch/x86/events/intel/lbr.c
+++ b/arch/x86/events/intel/lbr.c
@@ -137,9 +137,9 @@ static void __intel_pmu_lbr_enable(bool pmi)
if (cpuc->lbr_sel)
lbr_select = cpuc->lbr_sel->config & x86_pmu.lbr_sel_mask;
if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && !pmi && cpuc->lbr_sel)
- wrmsrl(MSR_LBR_SELECT, lbr_select);
+ wrmsrq(MSR_LBR_SELECT, lbr_select);
- rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
orig_debugctl = debugctl;
if (!static_cpu_has(X86_FEATURE_ARCH_LBR))
@@ -155,10 +155,10 @@ static void __intel_pmu_lbr_enable(bool pmi)
debugctl |= DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
if (orig_debugctl != debugctl)
- wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
if (static_cpu_has(X86_FEATURE_ARCH_LBR))
- wrmsrl(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN);
+ wrmsrq(MSR_ARCH_LBR_CTL, lbr_select | ARCH_LBR_CTL_LBREN);
}
void intel_pmu_lbr_reset_32(void)
@@ -166,7 +166,7 @@ void intel_pmu_lbr_reset_32(void)
int i;
for (i = 0; i < x86_pmu.lbr_nr; i++)
- wrmsrl(x86_pmu.lbr_from + i, 0);
+ wrmsrq(x86_pmu.lbr_from + i, 0);
}
void intel_pmu_lbr_reset_64(void)
@@ -174,17 +174,17 @@ void intel_pmu_lbr_reset_64(void)
int i;
for (i = 0; i < x86_pmu.lbr_nr; i++) {
- wrmsrl(x86_pmu.lbr_from + i, 0);
- wrmsrl(x86_pmu.lbr_to + i, 0);
+ wrmsrq(x86_pmu.lbr_from + i, 0);
+ wrmsrq(x86_pmu.lbr_to + i, 0);
if (x86_pmu.lbr_has_info)
- wrmsrl(x86_pmu.lbr_info + i, 0);
+ wrmsrq(x86_pmu.lbr_info + i, 0);
}
}
static void intel_pmu_arch_lbr_reset(void)
{
/* Write to ARCH_LBR_DEPTH MSR, all LBR entries are reset to 0 */
- wrmsrl(MSR_ARCH_LBR_DEPTH, x86_pmu.lbr_nr);
+ wrmsrq(MSR_ARCH_LBR_DEPTH, x86_pmu.lbr_nr);
}
void intel_pmu_lbr_reset(void)
@@ -199,7 +199,7 @@ void intel_pmu_lbr_reset(void)
cpuc->last_task_ctx = NULL;
cpuc->last_log_id = 0;
if (!static_cpu_has(X86_FEATURE_ARCH_LBR) && cpuc->lbr_select)
- wrmsrl(MSR_LBR_SELECT, 0);
+ wrmsrq(MSR_LBR_SELECT, 0);
}
/*
@@ -209,7 +209,7 @@ static inline u64 intel_pmu_lbr_tos(void)
{
u64 tos;
- rdmsrl(x86_pmu.lbr_tos, tos);
+ rdmsrq(x86_pmu.lbr_tos, tos);
return tos;
}
@@ -282,17 +282,17 @@ static u64 lbr_from_signext_quirk_rd(u64 val)
static __always_inline void wrlbr_from(unsigned int idx, u64 val)
{
val = lbr_from_signext_quirk_wr(val);
- wrmsrl(x86_pmu.lbr_from + idx, val);
+ wrmsrq(x86_pmu.lbr_from + idx, val);
}
static __always_inline void wrlbr_to(unsigned int idx, u64 val)
{
- wrmsrl(x86_pmu.lbr_to + idx, val);
+ wrmsrq(x86_pmu.lbr_to + idx, val);
}
static __always_inline void wrlbr_info(unsigned int idx, u64 val)
{
- wrmsrl(x86_pmu.lbr_info + idx, val);
+ wrmsrq(x86_pmu.lbr_info + idx, val);
}
static __always_inline u64 rdlbr_from(unsigned int idx, struct lbr_entry *lbr)
@@ -302,7 +302,7 @@ static __always_inline u64 rdlbr_from(unsigned int idx, struct lbr_entry *lbr)
if (lbr)
return lbr->from;
- rdmsrl(x86_pmu.lbr_from + idx, val);
+ rdmsrq(x86_pmu.lbr_from + idx, val);
return lbr_from_signext_quirk_rd(val);
}
@@ -314,7 +314,7 @@ static __always_inline u64 rdlbr_to(unsigned int idx, struct lbr_entry *lbr)
if (lbr)
return lbr->to;
- rdmsrl(x86_pmu.lbr_to + idx, val);
+ rdmsrq(x86_pmu.lbr_to + idx, val);
return val;
}
@@ -326,7 +326,7 @@ static __always_inline u64 rdlbr_info(unsigned int idx, struct lbr_entry *lbr)
if (lbr)
return lbr->info;
- rdmsrl(x86_pmu.lbr_info + idx, val);
+ rdmsrq(x86_pmu.lbr_info + idx, val);
return val;
}
@@ -380,10 +380,10 @@ void intel_pmu_lbr_restore(void *ctx)
wrlbr_info(lbr_idx, 0);
}
- wrmsrl(x86_pmu.lbr_tos, tos);
+ wrmsrq(x86_pmu.lbr_tos, tos);
if (cpuc->lbr_select)
- wrmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
+ wrmsrq(MSR_LBR_SELECT, task_ctx->lbr_sel);
}
static void intel_pmu_arch_lbr_restore(void *ctx)
@@ -475,7 +475,7 @@ void intel_pmu_lbr_save(void *ctx)
task_ctx->tos = tos;
if (cpuc->lbr_select)
- rdmsrl(MSR_LBR_SELECT, task_ctx->lbr_sel);
+ rdmsrq(MSR_LBR_SELECT, task_ctx->lbr_sel);
}
static void intel_pmu_arch_lbr_save(void *ctx)
@@ -752,7 +752,7 @@ void intel_pmu_lbr_read_32(struct cpu_hw_events *cpuc)
u64 lbr;
} msr_lastbranch;
- rdmsrl(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
+ rdmsrq(x86_pmu.lbr_from + lbr_idx, msr_lastbranch.lbr);
perf_clear_branch_entry_bitfields(br);
@@ -1602,7 +1602,7 @@ void __init intel_pmu_arch_lbr_init(void)
goto clear_arch_lbr;
/* Apply the max depth of Arch LBR */
- if (wrmsrl_safe(MSR_ARCH_LBR_DEPTH, lbr_nr))
+ if (wrmsrq_safe(MSR_ARCH_LBR_DEPTH, lbr_nr))
goto clear_arch_lbr;
x86_pmu.lbr_depth_mask = eax.split.lbr_depth_mask;
@@ -1618,7 +1618,7 @@ void __init intel_pmu_arch_lbr_init(void)
x86_pmu.lbr_nr = lbr_nr;
if (!!x86_pmu.lbr_counters)
- x86_pmu.flags |= PMU_FL_BR_CNTR;
+ x86_pmu.flags |= PMU_FL_BR_CNTR | PMU_FL_DYN_CONSTRAINT;
if (x86_pmu.lbr_mispred)
static_branch_enable(&x86_lbr_mispred);
diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
index c85a9fc44355..e5fd7367e45d 100644
--- a/arch/x86/events/intel/p4.c
+++ b/arch/x86/events/intel/p4.c
@@ -13,6 +13,7 @@
#include <asm/cpu_device_id.h>
#include <asm/hardirq.h>
#include <asm/apic.h>
+#include <asm/msr.h>
#include "../perf_event.h"
@@ -859,9 +860,9 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
u64 v;
/* an official way for overflow indication */
- rdmsrl(hwc->config_base, v);
+ rdmsrq(hwc->config_base, v);
if (v & P4_CCCR_OVF) {
- wrmsrl(hwc->config_base, v & ~P4_CCCR_OVF);
+ wrmsrq(hwc->config_base, v & ~P4_CCCR_OVF);
return 1;
}
@@ -872,7 +873,7 @@ static inline int p4_pmu_clear_cccr_ovf(struct hw_perf_event *hwc)
* the counter has reached zero value and continued counting before
* real NMI signal was received:
*/
- rdmsrl(hwc->event_base, v);
+ rdmsrq(hwc->event_base, v);
if (!(v & ARCH_P4_UNFLAGGED_BIT))
return 1;
@@ -897,8 +898,8 @@ static void p4_pmu_disable_pebs(void)
* So at moment let leave metrics turned on forever -- it's
* ok for now but need to be revisited!
*
- * (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, 0);
- * (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, 0);
+ * (void)wrmsrq_safe(MSR_IA32_PEBS_ENABLE, 0);
+ * (void)wrmsrq_safe(MSR_P4_PEBS_MATRIX_VERT, 0);
*/
}
@@ -911,7 +912,7 @@ static inline void p4_pmu_disable_event(struct perf_event *event)
* state we need to clear P4_CCCR_OVF, otherwise interrupt get
* asserted again and again
*/
- (void)wrmsrl_safe(hwc->config_base,
+ (void)wrmsrq_safe(hwc->config_base,
p4_config_unpack_cccr(hwc->config) & ~P4_CCCR_ENABLE & ~P4_CCCR_OVF & ~P4_CCCR_RESERVED);
}
@@ -944,8 +945,8 @@ static void p4_pmu_enable_pebs(u64 config)
bind = &p4_pebs_bind_map[idx];
- (void)wrmsrl_safe(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs);
- (void)wrmsrl_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert);
+ (void)wrmsrq_safe(MSR_IA32_PEBS_ENABLE, (u64)bind->metric_pebs);
+ (void)wrmsrq_safe(MSR_P4_PEBS_MATRIX_VERT, (u64)bind->metric_vert);
}
static void __p4_pmu_enable_event(struct perf_event *event)
@@ -979,8 +980,8 @@ static void __p4_pmu_enable_event(struct perf_event *event)
*/
p4_pmu_enable_pebs(hwc->config);
- (void)wrmsrl_safe(escr_addr, escr_conf);
- (void)wrmsrl_safe(hwc->config_base,
+ (void)wrmsrq_safe(escr_addr, escr_conf);
+ (void)wrmsrq_safe(hwc->config_base,
(cccr & ~P4_CCCR_RESERVED) | P4_CCCR_ENABLE);
}
@@ -1024,7 +1025,7 @@ static int p4_pmu_set_period(struct perf_event *event)
*
* the former idea is taken from OProfile code
*/
- wrmsrl(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
+ wrmsrq(hwc->event_base, (u64)(-left) & x86_pmu.cntval_mask);
}
return ret;
@@ -1072,8 +1073,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
continue;
- if (perf_event_overflow(event, &data, regs))
- x86_pmu_stop(event, 0);
+ perf_event_overflow(event, &data, regs);
}
if (handled)
@@ -1398,7 +1398,7 @@ __init int p4_pmu_init(void)
*/
for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
reg = x86_pmu_config_addr(i);
- wrmsrl_safe(reg, 0ULL);
+ wrmsrq_safe(reg, 0ULL);
}
return 0;
diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c
index 65b45e9d7016..6e41de355bd8 100644
--- a/arch/x86/events/intel/p6.c
+++ b/arch/x86/events/intel/p6.c
@@ -3,6 +3,7 @@
#include <linux/types.h>
#include <asm/cpu_device_id.h>
+#include <asm/msr.h>
#include "../perf_event.h"
@@ -142,9 +143,9 @@ static void p6_pmu_disable_all(void)
u64 val;
/* p6 only has one enable register */
- rdmsrl(MSR_P6_EVNTSEL0, val);
+ rdmsrq(MSR_P6_EVNTSEL0, val);
val &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
- wrmsrl(MSR_P6_EVNTSEL0, val);
+ wrmsrq(MSR_P6_EVNTSEL0, val);
}
static void p6_pmu_enable_all(int added)
@@ -152,9 +153,9 @@ static void p6_pmu_enable_all(int added)
unsigned long val;
/* p6 only has one enable register */
- rdmsrl(MSR_P6_EVNTSEL0, val);
+ rdmsrq(MSR_P6_EVNTSEL0, val);
val |= ARCH_PERFMON_EVENTSEL_ENABLE;
- wrmsrl(MSR_P6_EVNTSEL0, val);
+ wrmsrq(MSR_P6_EVNTSEL0, val);
}
static inline void
@@ -163,7 +164,7 @@ p6_pmu_disable_event(struct perf_event *event)
struct hw_perf_event *hwc = &event->hw;
u64 val = P6_NOP_EVENT;
- (void)wrmsrl_safe(hwc->config_base, val);
+ (void)wrmsrq_safe(hwc->config_base, val);
}
static void p6_pmu_enable_event(struct perf_event *event)
@@ -180,7 +181,7 @@ static void p6_pmu_enable_event(struct perf_event *event)
* to actually enable the events.
*/
- (void)wrmsrl_safe(hwc->config_base, val);
+ (void)wrmsrq_safe(hwc->config_base, val);
}
PMU_FORMAT_ATTR(event, "config:0-7" );
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index fa37565f6418..e8cf29d2b10c 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -18,12 +18,13 @@
#include <linux/slab.h>
#include <linux/device.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/perf_event.h>
#include <asm/insn.h>
#include <asm/io.h>
#include <asm/intel_pt.h>
#include <asm/cpu_device_id.h>
+#include <asm/msr.h>
#include "../perf_event.h"
#include "pt.h"
@@ -194,7 +195,7 @@ static int __init pt_pmu_hw_init(void)
int ret;
long i;
- rdmsrl(MSR_PLATFORM_INFO, reg);
+ rdmsrq(MSR_PLATFORM_INFO, reg);
pt_pmu.max_nonturbo_ratio = (reg & 0xff00) >> 8;
/*
@@ -230,7 +231,7 @@ static int __init pt_pmu_hw_init(void)
* "IA32_VMX_MISC[bit 14]" being 1 means PT can trace
* post-VMXON.
*/
- rdmsrl(MSR_IA32_VMX_MISC, reg);
+ rdmsrq(MSR_IA32_VMX_MISC, reg);
if (reg & BIT(14))
pt_pmu.vmx = true;
}
@@ -426,7 +427,7 @@ static void pt_config_start(struct perf_event *event)
if (READ_ONCE(pt->vmx_on))
perf_aux_output_flag(&pt->handle, PERF_AUX_FLAG_PARTIAL);
else
- wrmsrl(MSR_IA32_RTIT_CTL, ctl);
+ wrmsrq(MSR_IA32_RTIT_CTL, ctl);
WRITE_ONCE(event->hw.aux_config, ctl);
}
@@ -485,12 +486,12 @@ static u64 pt_config_filters(struct perf_event *event)
/* avoid redundant msr writes */
if (pt->filters.filter[range].msr_a != filter->msr_a) {
- wrmsrl(pt_address_ranges[range].msr_a, filter->msr_a);
+ wrmsrq(pt_address_ranges[range].msr_a, filter->msr_a);
pt->filters.filter[range].msr_a = filter->msr_a;
}
if (pt->filters.filter[range].msr_b != filter->msr_b) {
- wrmsrl(pt_address_ranges[range].msr_b, filter->msr_b);
+ wrmsrq(pt_address_ranges[range].msr_b, filter->msr_b);
pt->filters.filter[range].msr_b = filter->msr_b;
}
@@ -509,7 +510,7 @@ static void pt_config(struct perf_event *event)
/* First round: clear STATUS, in particular the PSB byte counter. */
if (!event->hw.aux_config) {
perf_event_itrace_started(event);
- wrmsrl(MSR_IA32_RTIT_STATUS, 0);
+ wrmsrq(MSR_IA32_RTIT_STATUS, 0);
}
reg = pt_config_filters(event);
@@ -569,7 +570,7 @@ static void pt_config_stop(struct perf_event *event)
ctl &= ~RTIT_CTL_TRACEEN;
if (!READ_ONCE(pt->vmx_on))
- wrmsrl(MSR_IA32_RTIT_CTL, ctl);
+ wrmsrq(MSR_IA32_RTIT_CTL, ctl);
WRITE_ONCE(event->hw.aux_config, ctl);
@@ -658,13 +659,13 @@ static void pt_config_buffer(struct pt_buffer *buf)
reg = virt_to_phys(base);
if (pt->output_base != reg) {
pt->output_base = reg;
- wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, reg);
+ wrmsrq(MSR_IA32_RTIT_OUTPUT_BASE, reg);
}
reg = 0x7f | (mask << 7) | ((u64)buf->output_off << 32);
if (pt->output_mask != reg) {
pt->output_mask = reg;
- wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, reg);
+ wrmsrq(MSR_IA32_RTIT_OUTPUT_MASK, reg);
}
}
@@ -926,7 +927,7 @@ static void pt_handle_status(struct pt *pt)
int advance = 0;
u64 status;
- rdmsrl(MSR_IA32_RTIT_STATUS, status);
+ rdmsrq(MSR_IA32_RTIT_STATUS, status);
if (status & RTIT_STATUS_ERROR) {
pr_err_ratelimited("ToPA ERROR encountered, trying to recover\n");
@@ -970,7 +971,7 @@ static void pt_handle_status(struct pt *pt)
if (advance)
pt_buffer_advance(buf);
- wrmsrl(MSR_IA32_RTIT_STATUS, status);
+ wrmsrq(MSR_IA32_RTIT_STATUS, status);
}
/**
@@ -985,12 +986,12 @@ static void pt_read_offset(struct pt_buffer *buf)
struct topa_page *tp;
if (!buf->single) {
- rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, pt->output_base);
+ rdmsrq(MSR_IA32_RTIT_OUTPUT_BASE, pt->output_base);
tp = phys_to_virt(pt->output_base);
buf->cur = &tp->topa;
}
- rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, pt->output_mask);
+ rdmsrq(MSR_IA32_RTIT_OUTPUT_MASK, pt->output_mask);
/* offset within current output region */
buf->output_off = pt->output_mask >> 32;
/* index of current output region within this table */
@@ -1585,7 +1586,7 @@ void intel_pt_handle_vmx(int on)
/* Turn PTs back on */
if (!on && event)
- wrmsrl(MSR_IA32_RTIT_CTL, event->hw.aux_config);
+ wrmsrq(MSR_IA32_RTIT_CTL, event->hw.aux_config);
local_irq_restore(flags);
}
@@ -1611,7 +1612,7 @@ static void pt_event_start(struct perf_event *event, int mode)
* PMI might have just cleared these, so resume_allowed
* must be checked again also.
*/
- rdmsrl(MSR_IA32_RTIT_STATUS, status);
+ rdmsrq(MSR_IA32_RTIT_STATUS, status);
if (!(status & (RTIT_STATUS_TRIGGEREN |
RTIT_STATUS_ERROR |
RTIT_STATUS_STOPPED)) &&
@@ -1839,7 +1840,7 @@ static __init int pt_init(void)
for_each_online_cpu(cpu) {
u64 ctl;
- ret = rdmsrl_safe_on_cpu(cpu, MSR_IA32_RTIT_CTL, &ctl);
+ ret = rdmsrq_safe_on_cpu(cpu, MSR_IA32_RTIT_CTL, &ctl);
if (!ret && (ctl & RTIT_CTL_TRACEEN))
prior_warn++;
}
@@ -1863,6 +1864,8 @@ static __init int pt_init(void)
if (!intel_pt_validate_hw_cap(PT_CAP_topa_multiple_entries))
pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_NO_SG;
+ else
+ pt_pmu.pmu.capabilities = PERF_PMU_CAP_AUX_PREFER_LARGE;
pt_pmu.pmu.capabilities |= PERF_PMU_CAP_EXCLUSIVE |
PERF_PMU_CAP_ITRACE |
diff --git a/arch/x86/events/intel/uncore.c b/arch/x86/events/intel/uncore.c
index a34e50fc4a8f..a762f7f5b161 100644
--- a/arch/x86/events/intel/uncore.c
+++ b/arch/x86/events/intel/uncore.c
@@ -3,6 +3,7 @@
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
+#include <asm/msr.h>
#include "uncore.h"
#include "uncore_discovery.h"
@@ -150,7 +151,7 @@ u64 uncore_msr_read_counter(struct intel_uncore_box *box, struct perf_event *eve
{
u64 count;
- rdmsrl(event->hw.event_base, count);
+ rdmsrq(event->hw.event_base, count);
return count;
}
@@ -305,17 +306,11 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
{
struct intel_uncore_box *box;
struct perf_event *event;
- unsigned long flags;
int bit;
box = container_of(hrtimer, struct intel_uncore_box, hrtimer);
if (!box->n_active || box->cpu != smp_processor_id())
return HRTIMER_NORESTART;
- /*
- * disable local interrupt to prevent uncore_pmu_event_start/stop
- * to interrupt the update process
- */
- local_irq_save(flags);
/*
* handle boxes with an active event list as opposed to active
@@ -328,8 +323,6 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
for_each_set_bit(bit, box->active_mask, UNCORE_PMC_IDX_MAX)
uncore_perf_event_update(box, box->events[bit]);
- local_irq_restore(flags);
-
hrtimer_forward_now(hrtimer, ns_to_ktime(box->hrtimer_duration));
return HRTIMER_RESTART;
}
@@ -337,7 +330,7 @@ static enum hrtimer_restart uncore_pmu_hrtimer(struct hrtimer *hrtimer)
void uncore_pmu_start_hrtimer(struct intel_uncore_box *box)
{
hrtimer_start(&box->hrtimer, ns_to_ktime(box->hrtimer_duration),
- HRTIMER_MODE_REL_PINNED);
+ HRTIMER_MODE_REL_PINNED_HARD);
}
void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
@@ -347,7 +340,7 @@ void uncore_pmu_cancel_hrtimer(struct intel_uncore_box *box)
static void uncore_pmu_init_hrtimer(struct intel_uncore_box *box)
{
- hrtimer_setup(&box->hrtimer, uncore_pmu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
+ hrtimer_setup(&box->hrtimer, uncore_pmu_hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
}
static struct intel_uncore_box *uncore_alloc_box(struct intel_uncore_type *type,
@@ -1814,6 +1807,12 @@ static const struct intel_uncore_init_fun lnl_uncore_init __initconst = {
.mmio_init = lnl_uncore_mmio_init,
};
+static const struct intel_uncore_init_fun ptl_uncore_init __initconst = {
+ .cpu_init = ptl_uncore_cpu_init,
+ .mmio_init = ptl_uncore_mmio_init,
+ .use_discovery = true,
+};
+
static const struct intel_uncore_init_fun icx_uncore_init __initconst = {
.cpu_init = icx_uncore_cpu_init,
.pci_init = icx_uncore_pci_init,
@@ -1895,6 +1894,7 @@ static const struct x86_cpu_id intel_uncore_match[] __initconst = {
X86_MATCH_VFM(INTEL_ARROWLAKE_U, &mtl_uncore_init),
X86_MATCH_VFM(INTEL_ARROWLAKE_H, &mtl_uncore_init),
X86_MATCH_VFM(INTEL_LUNARLAKE_M, &lnl_uncore_init),
+ X86_MATCH_VFM(INTEL_PANTHERLAKE_L, &ptl_uncore_init),
X86_MATCH_VFM(INTEL_SAPPHIRERAPIDS_X, &spr_uncore_init),
X86_MATCH_VFM(INTEL_EMERALDRAPIDS_X, &spr_uncore_init),
X86_MATCH_VFM(INTEL_GRANITERAPIDS_X, &gnr_uncore_init),
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 3dcb88c0ecfa..d8815fff7588 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -612,10 +612,12 @@ void tgl_uncore_cpu_init(void);
void adl_uncore_cpu_init(void);
void lnl_uncore_cpu_init(void);
void mtl_uncore_cpu_init(void);
+void ptl_uncore_cpu_init(void);
void tgl_uncore_mmio_init(void);
void tgl_l_uncore_mmio_init(void);
void adl_uncore_mmio_init(void);
void lnl_uncore_mmio_init(void);
+void ptl_uncore_mmio_init(void);
int snb_pci2phy_map_init(int devid);
/* uncore_snbep.c */
diff --git a/arch/x86/events/intel/uncore_discovery.c b/arch/x86/events/intel/uncore_discovery.c
index 571e44b49691..7d57ce706feb 100644
--- a/arch/x86/events/intel/uncore_discovery.c
+++ b/arch/x86/events/intel/uncore_discovery.c
@@ -5,6 +5,7 @@
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <asm/msr.h>
#include "uncore.h"
#include "uncore_discovery.h"
@@ -273,32 +274,15 @@ uncore_ignore_unit(struct uncore_unit_discovery *unit, int *ignore)
return false;
}
-static int parse_discovery_table(struct pci_dev *dev, int die,
- u32 bar_offset, bool *parsed,
- int *ignore)
+static int __parse_discovery_table(resource_size_t addr, int die,
+ bool *parsed, int *ignore)
{
struct uncore_global_discovery global;
struct uncore_unit_discovery unit;
void __iomem *io_addr;
- resource_size_t addr;
unsigned long size;
- u32 val;
int i;
- pci_read_config_dword(dev, bar_offset, &val);
-
- if (val & ~PCI_BASE_ADDRESS_MEM_MASK & ~PCI_BASE_ADDRESS_MEM_TYPE_64)
- return -EINVAL;
-
- addr = (resource_size_t)(val & PCI_BASE_ADDRESS_MEM_MASK);
-#ifdef CONFIG_PHYS_ADDR_T_64BIT
- if ((val & PCI_BASE_ADDRESS_MEM_TYPE_MASK) == PCI_BASE_ADDRESS_MEM_TYPE_64) {
- u32 val2;
-
- pci_read_config_dword(dev, bar_offset + 4, &val2);
- addr |= ((resource_size_t)val2) << 32;
- }
-#endif
size = UNCORE_DISCOVERY_GLOBAL_MAP_SIZE;
io_addr = ioremap(addr, size);
if (!io_addr)
@@ -341,7 +325,32 @@ static int parse_discovery_table(struct pci_dev *dev, int die,
return 0;
}
-bool intel_uncore_has_discovery_tables(int *ignore)
+static int parse_discovery_table(struct pci_dev *dev, int die,
+ u32 bar_offset, bool *parsed,
+ int *ignore)
+{
+ resource_size_t addr;
+ u32 val;
+
+ pci_read_config_dword(dev, bar_offset, &val);
+
+ if (val & ~PCI_BASE_ADDRESS_MEM_MASK & ~PCI_BASE_ADDRESS_MEM_TYPE_64)
+ return -EINVAL;
+
+ addr = (resource_size_t)(val & PCI_BASE_ADDRESS_MEM_MASK);
+#ifdef CONFIG_PHYS_ADDR_T_64BIT
+ if ((val & PCI_BASE_ADDRESS_MEM_TYPE_MASK) == PCI_BASE_ADDRESS_MEM_TYPE_64) {
+ u32 val2;
+
+ pci_read_config_dword(dev, bar_offset + 4, &val2);
+ addr |= ((resource_size_t)val2) << 32;
+ }
+#endif
+
+ return __parse_discovery_table(addr, die, parsed, ignore);
+}
+
+static bool intel_uncore_has_discovery_tables_pci(int *ignore)
{
u32 device, val, entry_id, bar_offset;
int die, dvsec = 0, ret = true;
@@ -390,6 +399,45 @@ err:
return ret;
}
+static bool intel_uncore_has_discovery_tables_msr(int *ignore)
+{
+ unsigned long *die_mask;
+ bool parsed = false;
+ int cpu, die;
+ u64 base;
+
+ die_mask = kcalloc(BITS_TO_LONGS(uncore_max_dies()),
+ sizeof(unsigned long), GFP_KERNEL);
+ if (!die_mask)
+ return false;
+
+ cpus_read_lock();
+ for_each_online_cpu(cpu) {
+ die = topology_logical_die_id(cpu);
+ if (__test_and_set_bit(die, die_mask))
+ continue;
+
+ if (rdmsrq_safe_on_cpu(cpu, UNCORE_DISCOVERY_MSR, &base))
+ continue;
+
+ if (!base)
+ continue;
+
+ __parse_discovery_table(base, die, &parsed, ignore);
+ }
+
+ cpus_read_unlock();
+
+ kfree(die_mask);
+ return parsed;
+}
+
+bool intel_uncore_has_discovery_tables(int *ignore)
+{
+ return intel_uncore_has_discovery_tables_msr(ignore) ||
+ intel_uncore_has_discovery_tables_pci(ignore);
+}
+
void intel_uncore_clear_discovery_tables(void)
{
struct intel_uncore_discovery_type *type, *next;
@@ -441,17 +489,17 @@ static u64 intel_generic_uncore_box_ctl(struct intel_uncore_box *box)
void intel_generic_uncore_msr_init_box(struct intel_uncore_box *box)
{
- wrmsrl(intel_generic_uncore_box_ctl(box), GENERIC_PMON_BOX_CTL_INT);
+ wrmsrq(intel_generic_uncore_box_ctl(box), GENERIC_PMON_BOX_CTL_INT);
}
void intel_generic_uncore_msr_disable_box(struct intel_uncore_box *box)
{
- wrmsrl(intel_generic_uncore_box_ctl(box), GENERIC_PMON_BOX_CTL_FRZ);
+ wrmsrq(intel_generic_uncore_box_ctl(box), GENERIC_PMON_BOX_CTL_FRZ);
}
void intel_generic_uncore_msr_enable_box(struct intel_uncore_box *box)
{
- wrmsrl(intel_generic_uncore_box_ctl(box), 0);
+ wrmsrq(intel_generic_uncore_box_ctl(box), 0);
}
static void intel_generic_uncore_msr_enable_event(struct intel_uncore_box *box,
@@ -459,7 +507,7 @@ static void intel_generic_uncore_msr_enable_event(struct intel_uncore_box *box,
{
struct hw_perf_event *hwc = &event->hw;
- wrmsrl(hwc->config_base, hwc->config);
+ wrmsrq(hwc->config_base, hwc->config);
}
static void intel_generic_uncore_msr_disable_event(struct intel_uncore_box *box,
@@ -467,7 +515,7 @@ static void intel_generic_uncore_msr_disable_event(struct intel_uncore_box *box,
{
struct hw_perf_event *hwc = &event->hw;
- wrmsrl(hwc->config_base, 0);
+ wrmsrq(hwc->config_base, 0);
}
static struct intel_uncore_ops generic_uncore_msr_ops = {
@@ -603,7 +651,7 @@ void intel_generic_uncore_mmio_init_box(struct intel_uncore_box *box)
}
addr = unit->addr;
- box->io_addr = ioremap(addr, UNCORE_GENERIC_MMIO_SIZE);
+ box->io_addr = ioremap(addr, type->mmio_map_size);
if (!box->io_addr) {
pr_warn("Uncore type %d box %d: ioremap error for 0x%llx.\n",
type->type_id, unit->id, (unsigned long long)addr);
diff --git a/arch/x86/events/intel/uncore_discovery.h b/arch/x86/events/intel/uncore_discovery.h
index 0e94aa7db8e7..dff75c98e22f 100644
--- a/arch/x86/events/intel/uncore_discovery.h
+++ b/arch/x86/events/intel/uncore_discovery.h
@@ -1,5 +1,8 @@
/* SPDX-License-Identifier: GPL-2.0-only */
+/* Store the full address of the global discovery table */
+#define UNCORE_DISCOVERY_MSR 0x201e
+
/* Generic device ID of a discovery table device */
#define UNCORE_DISCOVERY_TABLE_DEVICE 0x09a7
/* Capability ID for a discovery table device */
@@ -168,3 +171,7 @@ bool intel_generic_uncore_assign_hw_event(struct perf_event *event,
struct intel_uncore_box *box);
void uncore_find_add_unit(struct intel_uncore_discovery_unit *node,
struct rb_root *root, u16 *num_units);
+struct intel_uncore_type **
+uncore_get_uncores(enum uncore_access_type type_id, int num_extra,
+ struct intel_uncore_type **extra, int max_num_types,
+ struct intel_uncore_type **uncores);
diff --git a/arch/x86/events/intel/uncore_nhmex.c b/arch/x86/events/intel/uncore_nhmex.c
index 466833478e81..8962e7cb21e3 100644
--- a/arch/x86/events/intel/uncore_nhmex.c
+++ b/arch/x86/events/intel/uncore_nhmex.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* Nehalem-EX/Westmere-EX uncore support */
#include <asm/cpu_device_id.h>
+#include <asm/msr.h>
#include "uncore.h"
/* NHM-EX event control */
@@ -200,12 +201,12 @@ DEFINE_UNCORE_FORMAT_ATTR(mask, mask, "config2:0-63");
static void nhmex_uncore_msr_init_box(struct intel_uncore_box *box)
{
- wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
+ wrmsrq(NHMEX_U_MSR_PMON_GLOBAL_CTL, NHMEX_U_PMON_GLOBAL_EN_ALL);
}
static void nhmex_uncore_msr_exit_box(struct intel_uncore_box *box)
{
- wrmsrl(NHMEX_U_MSR_PMON_GLOBAL_CTL, 0);
+ wrmsrq(NHMEX_U_MSR_PMON_GLOBAL_CTL, 0);
}
static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
@@ -214,12 +215,12 @@ static void nhmex_uncore_msr_disable_box(struct intel_uncore_box *box)
u64 config;
if (msr) {
- rdmsrl(msr, config);
+ rdmsrq(msr, config);
config &= ~((1ULL << uncore_num_counters(box)) - 1);
/* WBox has a fixed counter */
if (uncore_msr_fixed_ctl(box))
config &= ~NHMEX_W_PMON_GLOBAL_FIXED_EN;
- wrmsrl(msr, config);
+ wrmsrq(msr, config);
}
}
@@ -229,18 +230,18 @@ static void nhmex_uncore_msr_enable_box(struct intel_uncore_box *box)
u64 config;
if (msr) {
- rdmsrl(msr, config);
+ rdmsrq(msr, config);
config |= (1ULL << uncore_num_counters(box)) - 1;
/* WBox has a fixed counter */
if (uncore_msr_fixed_ctl(box))
config |= NHMEX_W_PMON_GLOBAL_FIXED_EN;
- wrmsrl(msr, config);
+ wrmsrq(msr, config);
}
}
static void nhmex_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
{
- wrmsrl(event->hw.config_base, 0);
+ wrmsrq(event->hw.config_base, 0);
}
static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
@@ -248,11 +249,11 @@ static void nhmex_uncore_msr_enable_event(struct intel_uncore_box *box, struct p
struct hw_perf_event *hwc = &event->hw;
if (hwc->idx == UNCORE_PMC_IDX_FIXED)
- wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
+ wrmsrq(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0);
else if (box->pmu->type->event_mask & NHMEX_PMON_CTL_EN_BIT0)
- wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+ wrmsrq(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
else
- wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+ wrmsrq(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
}
#define NHMEX_UNCORE_OPS_COMMON_INIT() \
@@ -382,10 +383,10 @@ static void nhmex_bbox_msr_enable_event(struct intel_uncore_box *box, struct per
struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
if (reg1->idx != EXTRA_REG_NONE) {
- wrmsrl(reg1->reg, reg1->config);
- wrmsrl(reg1->reg + 1, reg2->config);
+ wrmsrq(reg1->reg, reg1->config);
+ wrmsrq(reg1->reg + 1, reg2->config);
}
- wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+ wrmsrq(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
(hwc->config & NHMEX_B_PMON_CTL_EV_SEL_MASK));
}
@@ -467,12 +468,12 @@ static void nhmex_sbox_msr_enable_event(struct intel_uncore_box *box, struct per
struct hw_perf_event_extra *reg2 = &hwc->branch_reg;
if (reg1->idx != EXTRA_REG_NONE) {
- wrmsrl(reg1->reg, 0);
- wrmsrl(reg1->reg + 1, reg1->config);
- wrmsrl(reg1->reg + 2, reg2->config);
- wrmsrl(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
+ wrmsrq(reg1->reg, 0);
+ wrmsrq(reg1->reg + 1, reg1->config);
+ wrmsrq(reg1->reg + 2, reg2->config);
+ wrmsrq(reg1->reg, NHMEX_S_PMON_MM_CFG_EN);
}
- wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
+ wrmsrq(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT22);
}
static struct attribute *nhmex_uncore_sbox_formats_attr[] = {
@@ -842,25 +843,25 @@ static void nhmex_mbox_msr_enable_event(struct intel_uncore_box *box, struct per
idx = __BITS_VALUE(reg1->idx, 0, 8);
if (idx != 0xff)
- wrmsrl(__BITS_VALUE(reg1->reg, 0, 16),
+ wrmsrq(__BITS_VALUE(reg1->reg, 0, 16),
nhmex_mbox_shared_reg_config(box, idx));
idx = __BITS_VALUE(reg1->idx, 1, 8);
if (idx != 0xff)
- wrmsrl(__BITS_VALUE(reg1->reg, 1, 16),
+ wrmsrq(__BITS_VALUE(reg1->reg, 1, 16),
nhmex_mbox_shared_reg_config(box, idx));
if (reg2->idx != EXTRA_REG_NONE) {
- wrmsrl(reg2->reg, 0);
+ wrmsrq(reg2->reg, 0);
if (reg2->config != ~0ULL) {
- wrmsrl(reg2->reg + 1,
+ wrmsrq(reg2->reg + 1,
reg2->config & NHMEX_M_PMON_ADDR_MATCH_MASK);
- wrmsrl(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
+ wrmsrq(reg2->reg + 2, NHMEX_M_PMON_ADDR_MASK_MASK &
(reg2->config >> NHMEX_M_PMON_ADDR_MASK_SHIFT));
- wrmsrl(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
+ wrmsrq(reg2->reg, NHMEX_M_PMON_MM_CFG_EN);
}
}
- wrmsrl(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
+ wrmsrq(hwc->config_base, hwc->config | NHMEX_PMON_CTL_EN_BIT0);
}
DEFINE_UNCORE_FORMAT_ATTR(count_mode, count_mode, "config:2-3");
@@ -1121,31 +1122,31 @@ static void nhmex_rbox_msr_enable_event(struct intel_uncore_box *box, struct per
switch (idx % 6) {
case 0:
- wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
+ wrmsrq(NHMEX_R_MSR_PORTN_IPERF_CFG0(port), reg1->config);
break;
case 1:
- wrmsrl(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
+ wrmsrq(NHMEX_R_MSR_PORTN_IPERF_CFG1(port), reg1->config);
break;
case 2:
case 3:
- wrmsrl(NHMEX_R_MSR_PORTN_QLX_CFG(port),
+ wrmsrq(NHMEX_R_MSR_PORTN_QLX_CFG(port),
uncore_shared_reg_config(box, 2 + (idx / 6) * 5));
break;
case 4:
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
+ wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET1_MM_CFG(port),
hwc->config >> 32);
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
+ wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET1_MATCH(port), reg1->config);
+ wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET1_MASK(port), reg2->config);
break;
case 5:
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
+ wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET2_MM_CFG(port),
hwc->config >> 32);
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
- wrmsrl(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
+ wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET2_MATCH(port), reg1->config);
+ wrmsrq(NHMEX_R_MSR_PORTN_XBR_SET2_MASK(port), reg2->config);
break;
}
- wrmsrl(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
+ wrmsrq(hwc->config_base, NHMEX_PMON_CTL_EN_BIT0 |
(hwc->config & NHMEX_R_PMON_CTL_EV_SEL_MASK));
}
diff --git a/arch/x86/events/intel/uncore_snb.c b/arch/x86/events/intel/uncore_snb.c
index edb7fd50efe0..807e582b8f17 100644
--- a/arch/x86/events/intel/uncore_snb.c
+++ b/arch/x86/events/intel/uncore_snb.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
/* Nehalem/SandBridge/Haswell/Broadwell/Skylake uncore support */
+#include <asm/msr.h>
#include "uncore.h"
#include "uncore_discovery.h"
@@ -260,34 +261,34 @@ static void snb_uncore_msr_enable_event(struct intel_uncore_box *box, struct per
struct hw_perf_event *hwc = &event->hw;
if (hwc->idx < UNCORE_PMC_IDX_FIXED)
- wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+ wrmsrq(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
else
- wrmsrl(hwc->config_base, SNB_UNC_CTL_EN);
+ wrmsrq(hwc->config_base, SNB_UNC_CTL_EN);
}
static void snb_uncore_msr_disable_event(struct intel_uncore_box *box, struct perf_event *event)
{
- wrmsrl(event->hw.config_base, 0);
+ wrmsrq(event->hw.config_base, 0);
}
static void snb_uncore_msr_init_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0) {
- wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+ wrmsrq(SNB_UNC_PERF_GLOBAL_CTL,
SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
}
}
static void snb_uncore_msr_enable_box(struct intel_uncore_box *box)
{
- wrmsrl(SNB_UNC_PERF_GLOBAL_CTL,
+ wrmsrq(SNB_UNC_PERF_GLOBAL_CTL,
SNB_UNC_GLOBAL_CTL_EN | SNB_UNC_GLOBAL_CTL_CORE_ALL);
}
static void snb_uncore_msr_exit_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0)
- wrmsrl(SNB_UNC_PERF_GLOBAL_CTL, 0);
+ wrmsrq(SNB_UNC_PERF_GLOBAL_CTL, 0);
}
static struct uncore_event_desc snb_uncore_events[] = {
@@ -372,7 +373,7 @@ void snb_uncore_cpu_init(void)
static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0) {
- wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
+ wrmsrq(SKL_UNC_PERF_GLOBAL_CTL,
SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
}
@@ -383,14 +384,14 @@ static void skl_uncore_msr_init_box(struct intel_uncore_box *box)
static void skl_uncore_msr_enable_box(struct intel_uncore_box *box)
{
- wrmsrl(SKL_UNC_PERF_GLOBAL_CTL,
+ wrmsrq(SKL_UNC_PERF_GLOBAL_CTL,
SNB_UNC_GLOBAL_CTL_EN | SKL_UNC_GLOBAL_CTL_CORE_ALL);
}
static void skl_uncore_msr_exit_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0)
- wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, 0);
+ wrmsrq(SKL_UNC_PERF_GLOBAL_CTL, 0);
}
static struct intel_uncore_ops skl_uncore_msr_ops = {
@@ -504,7 +505,7 @@ static int icl_get_cbox_num(void)
{
u64 num_boxes;
- rdmsrl(ICL_UNC_CBO_CONFIG, num_boxes);
+ rdmsrq(ICL_UNC_CBO_CONFIG, num_boxes);
return num_boxes & ICL_UNC_NUM_CBO_MASK;
}
@@ -525,7 +526,7 @@ static struct intel_uncore_type *tgl_msr_uncores[] = {
static void rkl_uncore_msr_init_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0)
- wrmsrl(SKL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
+ wrmsrq(SKL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
}
void tgl_uncore_cpu_init(void)
@@ -541,24 +542,24 @@ void tgl_uncore_cpu_init(void)
static void adl_uncore_msr_init_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0)
- wrmsrl(ADL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
+ wrmsrq(ADL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
}
static void adl_uncore_msr_enable_box(struct intel_uncore_box *box)
{
- wrmsrl(ADL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
+ wrmsrq(ADL_UNC_PERF_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
}
static void adl_uncore_msr_disable_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0)
- wrmsrl(ADL_UNC_PERF_GLOBAL_CTL, 0);
+ wrmsrq(ADL_UNC_PERF_GLOBAL_CTL, 0);
}
static void adl_uncore_msr_exit_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0)
- wrmsrl(ADL_UNC_PERF_GLOBAL_CTL, 0);
+ wrmsrq(ADL_UNC_PERF_GLOBAL_CTL, 0);
}
static struct intel_uncore_ops adl_uncore_msr_ops = {
@@ -691,7 +692,7 @@ static struct intel_uncore_type mtl_uncore_hac_cbox = {
static void mtl_uncore_msr_init_box(struct intel_uncore_box *box)
{
- wrmsrl(uncore_msr_box_ctl(box), SNB_UNC_GLOBAL_CTL_EN);
+ wrmsrq(uncore_msr_box_ctl(box), SNB_UNC_GLOBAL_CTL_EN);
}
static struct intel_uncore_ops mtl_uncore_msr_ops = {
@@ -758,7 +759,7 @@ static struct intel_uncore_type *lnl_msr_uncores[] = {
static void lnl_uncore_msr_init_box(struct intel_uncore_box *box)
{
if (box->pmu->pmu_idx == 0)
- wrmsrl(LNL_UNC_MSR_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
+ wrmsrq(LNL_UNC_MSR_GLOBAL_CTL, SNB_UNC_GLOBAL_CTL_EN);
}
static struct intel_uncore_ops lnl_uncore_msr_ops = {
@@ -1306,12 +1307,12 @@ int skl_uncore_pci_init(void)
/* Nehalem uncore support */
static void nhm_uncore_msr_disable_box(struct intel_uncore_box *box)
{
- wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, 0);
+ wrmsrq(NHM_UNC_PERF_GLOBAL_CTL, 0);
}
static void nhm_uncore_msr_enable_box(struct intel_uncore_box *box)
{
- wrmsrl(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
+ wrmsrq(NHM_UNC_PERF_GLOBAL_CTL, NHM_UNC_GLOBAL_CTL_EN_PC_ALL | NHM_UNC_GLOBAL_CTL_EN_FC);
}
static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct perf_event *event)
@@ -1319,9 +1320,9 @@ static void nhm_uncore_msr_enable_event(struct intel_uncore_box *box, struct per
struct hw_perf_event *hwc = &event->hw;
if (hwc->idx < UNCORE_PMC_IDX_FIXED)
- wrmsrl(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
+ wrmsrq(hwc->config_base, hwc->config | SNB_UNC_CTL_EN);
else
- wrmsrl(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
+ wrmsrq(hwc->config_base, NHM_UNC_FIXED_CTR_CTL_EN);
}
static struct attribute *nhm_uncore_formats_attr[] = {
@@ -1854,3 +1855,82 @@ void lnl_uncore_mmio_init(void)
}
/* end of Lunar Lake MMIO uncore support */
+
+/* Panther Lake uncore support */
+
+#define UNCORE_PTL_MAX_NUM_UNCORE_TYPES 42
+#define UNCORE_PTL_TYPE_IMC 6
+#define UNCORE_PTL_TYPE_SNCU 34
+#define UNCORE_PTL_TYPE_HBO 41
+
+#define PTL_UNCORE_GLOBAL_CTL_OFFSET 0x380
+
+static struct intel_uncore_type ptl_uncore_imc = {
+ .name = "imc",
+ .mmio_map_size = 0xf00,
+};
+
+static void ptl_uncore_sncu_init_box(struct intel_uncore_box *box)
+{
+ intel_generic_uncore_mmio_init_box(box);
+
+ /* Clear the global freeze bit */
+ if (box->io_addr)
+ writel(0, box->io_addr + PTL_UNCORE_GLOBAL_CTL_OFFSET);
+}
+
+static struct intel_uncore_ops ptl_uncore_sncu_ops = {
+ .init_box = ptl_uncore_sncu_init_box,
+ .exit_box = uncore_mmio_exit_box,
+ .disable_box = intel_generic_uncore_mmio_disable_box,
+ .enable_box = intel_generic_uncore_mmio_enable_box,
+ .disable_event = intel_generic_uncore_mmio_disable_event,
+ .enable_event = intel_generic_uncore_mmio_enable_event,
+ .read_counter = uncore_mmio_read_counter,
+};
+
+static struct intel_uncore_type ptl_uncore_sncu = {
+ .name = "sncu",
+ .ops = &ptl_uncore_sncu_ops,
+ .mmio_map_size = 0xf00,
+};
+
+static struct intel_uncore_type ptl_uncore_hbo = {
+ .name = "hbo",
+ .mmio_map_size = 0xf00,
+};
+
+static struct intel_uncore_type *ptl_uncores[UNCORE_PTL_MAX_NUM_UNCORE_TYPES] = {
+ [UNCORE_PTL_TYPE_IMC] = &ptl_uncore_imc,
+ [UNCORE_PTL_TYPE_SNCU] = &ptl_uncore_sncu,
+ [UNCORE_PTL_TYPE_HBO] = &ptl_uncore_hbo,
+};
+
+#define UNCORE_PTL_MMIO_EXTRA_UNCORES 1
+
+static struct intel_uncore_type *ptl_mmio_extra_uncores[UNCORE_PTL_MMIO_EXTRA_UNCORES] = {
+ &adl_uncore_imc_free_running,
+};
+
+void ptl_uncore_mmio_init(void)
+{
+ uncore_mmio_uncores = uncore_get_uncores(UNCORE_ACCESS_MMIO,
+ UNCORE_PTL_MMIO_EXTRA_UNCORES,
+ ptl_mmio_extra_uncores,
+ UNCORE_PTL_MAX_NUM_UNCORE_TYPES,
+ ptl_uncores);
+}
+
+static struct intel_uncore_type *ptl_msr_uncores[] = {
+ &mtl_uncore_cbox,
+ NULL
+};
+
+void ptl_uncore_cpu_init(void)
+{
+ mtl_uncore_cbox.num_boxes = 6;
+ mtl_uncore_cbox.ops = &lnl_uncore_msr_ops;
+ uncore_msr_uncores = ptl_msr_uncores;
+}
+
+/* end of Panther Lake uncore support */
diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index 76d96df1475a..e1f370b8d065 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
/* SandyBridge-EP/IvyTown uncore support */
#include <asm/cpu_device_id.h>
+#include <asm/msr.h>
#include "uncore.h"
#include "uncore_discovery.h"
@@ -618,9 +619,9 @@ static void snbep_uncore_msr_disable_box(struct intel_uncore_box *box)
msr = uncore_msr_box_ctl(box);
if (msr) {
- rdmsrl(msr, config);
+ rdmsrq(msr, config);
config |= SNBEP_PMON_BOX_CTL_FRZ;
- wrmsrl(msr, config);
+ wrmsrq(msr, config);
}
}
@@ -631,9 +632,9 @@ static void snbep_uncore_msr_enable_box(struct intel_uncore_box *box)
msr = uncore_msr_box_ctl(box);
if (msr) {
- rdmsrl(msr, config);
+ rdmsrq(msr, config);
config &= ~SNBEP_PMON_BOX_CTL_FRZ;
- wrmsrl(msr, config);
+ wrmsrq(msr, config);
}
}
@@ -643,9 +644,9 @@ static void snbep_uncore_msr_enable_event(struct intel_uncore_box *box, struct p
struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
if (reg1->idx != EXTRA_REG_NONE)
- wrmsrl(reg1->reg, uncore_shared_reg_config(box, 0));
+ wrmsrq(reg1->reg, uncore_shared_reg_config(box, 0));
- wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+ wrmsrq(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
}
static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
@@ -653,7 +654,7 @@ static void snbep_uncore_msr_disable_event(struct intel_uncore_box *box,
{
struct hw_perf_event *hwc = &event->hw;
- wrmsrl(hwc->config_base, hwc->config);
+ wrmsrq(hwc->config_base, hwc->config);
}
static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
@@ -661,7 +662,7 @@ static void snbep_uncore_msr_init_box(struct intel_uncore_box *box)
unsigned msr = uncore_msr_box_ctl(box);
if (msr)
- wrmsrl(msr, SNBEP_PMON_BOX_CTL_INT);
+ wrmsrq(msr, SNBEP_PMON_BOX_CTL_INT);
}
static struct attribute *snbep_uncore_formats_attr[] = {
@@ -1532,7 +1533,7 @@ static void ivbep_uncore_msr_init_box(struct intel_uncore_box *box)
{
unsigned msr = uncore_msr_box_ctl(box);
if (msr)
- wrmsrl(msr, IVBEP_PMON_BOX_CTL_INT);
+ wrmsrq(msr, IVBEP_PMON_BOX_CTL_INT);
}
static void ivbep_uncore_pci_init_box(struct intel_uncore_box *box)
@@ -1783,11 +1784,11 @@ static void ivbep_cbox_enable_event(struct intel_uncore_box *box, struct perf_ev
if (reg1->idx != EXTRA_REG_NONE) {
u64 filter = uncore_shared_reg_config(box, 0);
- wrmsrl(reg1->reg, filter & 0xffffffff);
- wrmsrl(reg1->reg + 6, filter >> 32);
+ wrmsrq(reg1->reg, filter & 0xffffffff);
+ wrmsrq(reg1->reg + 6, filter >> 32);
}
- wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+ wrmsrq(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
}
static struct intel_uncore_ops ivbep_uncore_cbox_ops = {
@@ -2767,11 +2768,11 @@ static void hswep_cbox_enable_event(struct intel_uncore_box *box,
if (reg1->idx != EXTRA_REG_NONE) {
u64 filter = uncore_shared_reg_config(box, 0);
- wrmsrl(reg1->reg, filter & 0xffffffff);
- wrmsrl(reg1->reg + 1, filter >> 32);
+ wrmsrq(reg1->reg, filter & 0xffffffff);
+ wrmsrq(reg1->reg + 1, filter >> 32);
}
- wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+ wrmsrq(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
}
static struct intel_uncore_ops hswep_uncore_cbox_ops = {
@@ -2816,7 +2817,7 @@ static void hswep_uncore_sbox_msr_init_box(struct intel_uncore_box *box)
for_each_set_bit(i, (unsigned long *)&init, 64) {
flags |= (1ULL << i);
- wrmsrl(msr, flags);
+ wrmsrq(msr, flags);
}
}
}
@@ -3708,7 +3709,7 @@ static void skx_iio_enable_event(struct intel_uncore_box *box,
{
struct hw_perf_event *hwc = &event->hw;
- wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+ wrmsrq(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
}
static struct intel_uncore_ops skx_uncore_iio_ops = {
@@ -3765,7 +3766,7 @@ static int skx_msr_cpu_bus_read(int cpu, u64 *topology)
{
u64 msr_value;
- if (rdmsrl_on_cpu(cpu, SKX_MSR_CPU_BUS_NUMBER, &msr_value) ||
+ if (rdmsrq_on_cpu(cpu, SKX_MSR_CPU_BUS_NUMBER, &msr_value) ||
!(msr_value & SKX_MSR_CPU_BUS_VALID_BIT))
return -ENXIO;
@@ -4655,9 +4656,9 @@ static void snr_cha_enable_event(struct intel_uncore_box *box,
struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
if (reg1->idx != EXTRA_REG_NONE)
- wrmsrl(reg1->reg, reg1->config);
+ wrmsrq(reg1->reg, reg1->config);
- wrmsrl(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
+ wrmsrq(hwc->config_base, hwc->config | SNBEP_PMON_CTL_EN);
}
static struct intel_uncore_ops snr_uncore_chabox_ops = {
@@ -5882,9 +5883,9 @@ static void spr_uncore_msr_enable_event(struct intel_uncore_box *box,
struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
if (reg1->idx != EXTRA_REG_NONE)
- wrmsrl(reg1->reg, reg1->config);
+ wrmsrq(reg1->reg, reg1->config);
- wrmsrl(hwc->config_base, hwc->config);
+ wrmsrq(hwc->config_base, hwc->config);
}
static void spr_uncore_msr_disable_event(struct intel_uncore_box *box,
@@ -5894,9 +5895,9 @@ static void spr_uncore_msr_disable_event(struct intel_uncore_box *box,
struct hw_perf_event_extra *reg1 = &hwc->extra_reg;
if (reg1->idx != EXTRA_REG_NONE)
- wrmsrl(reg1->reg, 0);
+ wrmsrq(reg1->reg, 0);
- wrmsrl(hwc->config_base, 0);
+ wrmsrq(hwc->config_base, 0);
}
static int spr_cha_hw_config(struct intel_uncore_box *box, struct perf_event *event)
@@ -6408,9 +6409,11 @@ static void uncore_type_customized_copy(struct intel_uncore_type *to_type,
to_type->get_topology = from_type->get_topology;
if (from_type->cleanup_mapping)
to_type->cleanup_mapping = from_type->cleanup_mapping;
+ if (from_type->mmio_map_size)
+ to_type->mmio_map_size = from_type->mmio_map_size;
}
-static struct intel_uncore_type **
+struct intel_uncore_type **
uncore_get_uncores(enum uncore_access_type type_id, int num_extra,
struct intel_uncore_type **extra, int max_num_types,
struct intel_uncore_type **uncores)
@@ -6485,7 +6488,7 @@ void spr_uncore_cpu_init(void)
* of UNCORE_SPR_CHA) is incorrect on some SPR variants because of a
* firmware bug. Using the value from SPR_MSR_UNC_CBO_CONFIG to replace it.
*/
- rdmsrl(SPR_MSR_UNC_CBO_CONFIG, num_cbo);
+ rdmsrq(SPR_MSR_UNC_CBO_CONFIG, num_cbo);
/*
* The MSR doesn't work on the EMR XCC, but the firmware bug doesn't impact
* the EMR XCC. Don't let the value from the MSR replace the existing value.
diff --git a/arch/x86/events/msr.c b/arch/x86/events/msr.c
index 45b1866ff051..7f5007a4752a 100644
--- a/arch/x86/events/msr.c
+++ b/arch/x86/events/msr.c
@@ -3,6 +3,8 @@
#include <linux/sysfs.h>
#include <linux/nospec.h>
#include <asm/cpu_device_id.h>
+#include <asm/msr.h>
+
#include "probe.h"
enum perf_msr_id {
@@ -231,7 +233,7 @@ static inline u64 msr_read_counter(struct perf_event *event)
u64 now;
if (event->hw.event_base)
- rdmsrl(event->hw.event_base, now);
+ rdmsrq(event->hw.event_base, now);
else
now = rdtsc_ordered();
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index 46d120597bab..2b969386dcdd 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -17,6 +17,7 @@
#include <asm/fpu/xstate.h>
#include <asm/intel_ds.h>
#include <asm/cpu.h>
+#include <asm/msr.h>
/* To enable MSR tracing please use the generic trace points. */
@@ -127,6 +128,11 @@ static inline bool is_pebs_counter_event_group(struct perf_event *event)
return check_leader_group(event->group_leader, PERF_X86_EVENT_PEBS_CNTR);
}
+static inline bool is_acr_event_group(struct perf_event *event)
+{
+ return check_leader_group(event->group_leader, PERF_X86_EVENT_ACR);
+}
+
struct amd_nb {
int nb_id; /* NorthBridge id */
int refcnt; /* reference count */
@@ -268,6 +274,7 @@ struct cpu_hw_events {
struct event_constraint *event_constraint[X86_PMC_IDX_MAX];
int n_excl; /* the number of exclusive events */
+ int n_late_setup; /* the num of events needs late setup */
unsigned int txn_flags;
int is_fake;
@@ -293,6 +300,10 @@ struct cpu_hw_events {
u64 fixed_ctrl_val;
u64 active_fixed_ctrl_val;
+ /* Intel ACR configuration */
+ u64 acr_cfg_b[X86_PMC_IDX_MAX];
+ u64 acr_cfg_c[X86_PMC_IDX_MAX];
+
/*
* Intel LBR bits
*/
@@ -714,6 +725,15 @@ struct x86_hybrid_pmu {
u64 fixed_cntr_mask64;
unsigned long fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
};
+
+ union {
+ u64 acr_cntr_mask64;
+ unsigned long acr_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
+ union {
+ u64 acr_cause_mask64;
+ unsigned long acr_cause_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
struct event_constraint unconstrained;
u64 hw_cache_event_ids
@@ -796,6 +816,10 @@ struct x86_pmu {
int (*hw_config)(struct perf_event *event);
int (*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
void (*late_setup)(void);
+ void (*pebs_enable)(struct perf_event *event);
+ void (*pebs_disable)(struct perf_event *event);
+ void (*pebs_enable_all)(void);
+ void (*pebs_disable_all)(void);
unsigned eventsel;
unsigned perfctr;
unsigned fixedctr;
@@ -812,6 +836,14 @@ struct x86_pmu {
u64 fixed_cntr_mask64;
unsigned long fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
};
+ union {
+ u64 acr_cntr_mask64;
+ unsigned long acr_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
+ union {
+ u64 acr_cause_mask64;
+ unsigned long acr_cause_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
+ };
int cntval_bits;
u64 cntval_mask;
union {
@@ -878,7 +910,7 @@ struct x86_pmu {
*/
unsigned int bts :1,
bts_active :1,
- pebs :1,
+ ds_pebs :1,
pebs_active :1,
pebs_broken :1,
pebs_prec_dist :1,
@@ -1049,6 +1081,7 @@ do { \
#define PMU_FL_MEM_LOADS_AUX 0x100 /* Require an auxiliary event for the complete memory info */
#define PMU_FL_RETIRE_LATENCY 0x200 /* Support Retire Latency in PEBS */
#define PMU_FL_BR_CNTR 0x400 /* Support branch counter logging */
+#define PMU_FL_DYN_CONSTRAINT 0x800 /* Needs dynamic constraint */
#define EVENT_VAR(_id) event_attr_##_id
#define EVENT_PTR(_id) &event_attr_##_id.attr.attr
@@ -1091,6 +1124,7 @@ static struct perf_pmu_format_hybrid_attr format_attr_hybrid_##_name = {\
.pmu_type = _pmu, \
}
+int is_x86_event(struct perf_event *event);
struct pmu *x86_get_pmu(unsigned int cpu);
extern struct x86_pmu x86_pmu __read_mostly;
@@ -1098,6 +1132,10 @@ DECLARE_STATIC_CALL(x86_pmu_set_period, *x86_pmu.set_period);
DECLARE_STATIC_CALL(x86_pmu_update, *x86_pmu.update);
DECLARE_STATIC_CALL(x86_pmu_drain_pebs, *x86_pmu.drain_pebs);
DECLARE_STATIC_CALL(x86_pmu_late_setup, *x86_pmu.late_setup);
+DECLARE_STATIC_CALL(x86_pmu_pebs_enable, *x86_pmu.pebs_enable);
+DECLARE_STATIC_CALL(x86_pmu_pebs_disable, *x86_pmu.pebs_disable);
+DECLARE_STATIC_CALL(x86_pmu_pebs_enable_all, *x86_pmu.pebs_enable_all);
+DECLARE_STATIC_CALL(x86_pmu_pebs_disable_all, *x86_pmu.pebs_disable_all);
static __always_inline struct x86_perf_task_context_opt *task_context_opt(void *ctx)
{
@@ -1205,16 +1243,16 @@ static inline void __x86_pmu_enable_event(struct hw_perf_event *hwc,
u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
if (hwc->extra_reg.reg)
- wrmsrl(hwc->extra_reg.reg, hwc->extra_reg.config);
+ wrmsrq(hwc->extra_reg.reg, hwc->extra_reg.config);
/*
* Add enabled Merge event on next counter
* if large increment event being enabled on this counter
*/
if (is_counter_pair(hwc))
- wrmsrl(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en);
+ wrmsrq(x86_pmu_config_addr(hwc->idx + 1), x86_pmu.perf_ctr_pair_en);
- wrmsrl(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
+ wrmsrq(hwc->config_base, (hwc->config | enable_mask) & ~disable_mask);
}
void x86_pmu_enable_all(int added);
@@ -1230,10 +1268,10 @@ static inline void x86_pmu_disable_event(struct perf_event *event)
u64 disable_mask = __this_cpu_read(cpu_hw_events.perf_ctr_virt_mask);
struct hw_perf_event *hwc = &event->hw;
- wrmsrl(hwc->config_base, hwc->config & ~disable_mask);
+ wrmsrq(hwc->config_base, hwc->config & ~disable_mask);
if (is_counter_pair(hwc))
- wrmsrl(x86_pmu_config_addr(hwc->idx + 1), 0);
+ wrmsrq(x86_pmu_config_addr(hwc->idx + 1), 0);
}
void x86_pmu_enable_event(struct perf_event *event);
@@ -1401,12 +1439,12 @@ static __always_inline void __amd_pmu_lbr_disable(void)
{
u64 dbg_ctl, dbg_extn_cfg;
- rdmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
- wrmsrl(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN);
+ rdmsrq(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg);
+ wrmsrq(MSR_AMD_DBG_EXTN_CFG, dbg_extn_cfg & ~DBG_EXTN_CFG_LBRV2EN);
if (cpu_feature_enabled(X86_FEATURE_AMD_LBR_PMC_FREEZE)) {
- rdmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
- wrmsrl(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
+ rdmsrq(MSR_IA32_DEBUGCTLMSR, dbg_ctl);
+ wrmsrq(MSR_IA32_DEBUGCTLMSR, dbg_ctl & ~DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
}
}
@@ -1538,21 +1576,21 @@ static inline bool intel_pmu_has_bts(struct perf_event *event)
static __always_inline void __intel_pmu_pebs_disable_all(void)
{
- wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+ wrmsrq(MSR_IA32_PEBS_ENABLE, 0);
}
static __always_inline void __intel_pmu_arch_lbr_disable(void)
{
- wrmsrl(MSR_ARCH_LBR_CTL, 0);
+ wrmsrq(MSR_ARCH_LBR_CTL, 0);
}
static __always_inline void __intel_pmu_lbr_disable(void)
{
u64 debugctl;
- rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
debugctl &= ~(DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI);
- wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
}
int intel_pmu_save_and_restart(struct perf_event *event);
@@ -1587,6 +1625,8 @@ void intel_pmu_disable_bts(void);
int intel_pmu_drain_bts_buffer(void);
+void intel_pmu_late_setup(void);
+
u64 grt_latency_data(struct perf_event *event, u64 status);
u64 cmt_latency_data(struct perf_event *event, u64 status);
@@ -1643,11 +1683,13 @@ void intel_pmu_pebs_disable_all(void);
void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in);
+void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc);
+
void intel_pmu_drain_pebs_buffer(void);
void intel_pmu_store_pebs_lbrs(struct lbr_entry *lbr);
-void intel_ds_init(void);
+void intel_pebs_init(void);
void intel_pmu_lbr_save_brstack(struct perf_sample_data *data,
struct cpu_hw_events *cpuc,
diff --git a/arch/x86/events/perf_event_flags.h b/arch/x86/events/perf_event_flags.h
index 1d9e385649b5..70078334e4a3 100644
--- a/arch/x86/events/perf_event_flags.h
+++ b/arch/x86/events/perf_event_flags.h
@@ -2,23 +2,24 @@
/*
* struct hw_perf_event.flags flags
*/
-PERF_ARCH(PEBS_LDLAT, 0x00001) /* ld+ldlat data address sampling */
-PERF_ARCH(PEBS_ST, 0x00002) /* st data address sampling */
-PERF_ARCH(PEBS_ST_HSW, 0x00004) /* haswell style datala, store */
-PERF_ARCH(PEBS_LD_HSW, 0x00008) /* haswell style datala, load */
-PERF_ARCH(PEBS_NA_HSW, 0x00010) /* haswell style datala, unknown */
-PERF_ARCH(EXCL, 0x00020) /* HT exclusivity on counter */
-PERF_ARCH(DYNAMIC, 0x00040) /* dynamic alloc'd constraint */
-PERF_ARCH(PEBS_CNTR, 0x00080) /* PEBS counters snapshot */
-PERF_ARCH(EXCL_ACCT, 0x00100) /* accounted EXCL event */
-PERF_ARCH(AUTO_RELOAD, 0x00200) /* use PEBS auto-reload */
-PERF_ARCH(LARGE_PEBS, 0x00400) /* use large PEBS */
-PERF_ARCH(PEBS_VIA_PT, 0x00800) /* use PT buffer for PEBS */
-PERF_ARCH(PAIR, 0x01000) /* Large Increment per Cycle */
-PERF_ARCH(LBR_SELECT, 0x02000) /* Save/Restore MSR_LBR_SELECT */
-PERF_ARCH(TOPDOWN, 0x04000) /* Count Topdown slots/metrics events */
-PERF_ARCH(PEBS_STLAT, 0x08000) /* st+stlat data address sampling */
-PERF_ARCH(AMD_BRS, 0x10000) /* AMD Branch Sampling */
-PERF_ARCH(PEBS_LAT_HYBRID, 0x20000) /* ld and st lat for hybrid */
-PERF_ARCH(NEEDS_BRANCH_STACK, 0x40000) /* require branch stack setup */
-PERF_ARCH(BRANCH_COUNTERS, 0x80000) /* logs the counters in the extra space of each branch */
+PERF_ARCH(PEBS_LDLAT, 0x0000001) /* ld+ldlat data address sampling */
+PERF_ARCH(PEBS_ST, 0x0000002) /* st data address sampling */
+PERF_ARCH(PEBS_ST_HSW, 0x0000004) /* haswell style datala, store */
+PERF_ARCH(PEBS_LD_HSW, 0x0000008) /* haswell style datala, load */
+PERF_ARCH(PEBS_NA_HSW, 0x0000010) /* haswell style datala, unknown */
+PERF_ARCH(EXCL, 0x0000020) /* HT exclusivity on counter */
+PERF_ARCH(DYNAMIC, 0x0000040) /* dynamic alloc'd constraint */
+PERF_ARCH(PEBS_CNTR, 0x0000080) /* PEBS counters snapshot */
+PERF_ARCH(EXCL_ACCT, 0x0000100) /* accounted EXCL event */
+PERF_ARCH(AUTO_RELOAD, 0x0000200) /* use PEBS auto-reload */
+PERF_ARCH(LARGE_PEBS, 0x0000400) /* use large PEBS */
+PERF_ARCH(PEBS_VIA_PT, 0x0000800) /* use PT buffer for PEBS */
+PERF_ARCH(PAIR, 0x0001000) /* Large Increment per Cycle */
+PERF_ARCH(LBR_SELECT, 0x0002000) /* Save/Restore MSR_LBR_SELECT */
+PERF_ARCH(TOPDOWN, 0x0004000) /* Count Topdown slots/metrics events */
+PERF_ARCH(PEBS_STLAT, 0x0008000) /* st+stlat data address sampling */
+PERF_ARCH(AMD_BRS, 0x0010000) /* AMD Branch Sampling */
+PERF_ARCH(PEBS_LAT_HYBRID, 0x0020000) /* ld and st lat for hybrid */
+PERF_ARCH(NEEDS_BRANCH_STACK, 0x0040000) /* require branch stack setup */
+PERF_ARCH(BRANCH_COUNTERS, 0x0080000) /* logs the counters in the extra space of each branch */
+PERF_ARCH(ACR, 0x0100000) /* Auto counter reload */
diff --git a/arch/x86/events/probe.c b/arch/x86/events/probe.c
index 600bf8d15c0c..bb719d0d3f0b 100644
--- a/arch/x86/events/probe.c
+++ b/arch/x86/events/probe.c
@@ -2,6 +2,8 @@
#include <linux/export.h>
#include <linux/types.h>
#include <linux/bits.h>
+
+#include <asm/msr.h>
#include "probe.h"
static umode_t
@@ -43,7 +45,7 @@ perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data)
if (msr[bit].test && !msr[bit].test(bit, data))
continue;
/* Virt sucks; you cannot tell if a R/O MSR is present :/ */
- if (rdmsrl_safe(msr[bit].msr, &val))
+ if (rdmsrq_safe(msr[bit].msr, &val))
continue;
mask = msr[bit].mask;
diff --git a/arch/x86/events/rapl.c b/arch/x86/events/rapl.c
index 8ddace8cea96..defd86137f12 100644
--- a/arch/x86/events/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -65,6 +65,7 @@
#include <linux/nospec.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
+#include <asm/msr.h>
#include "perf_event.h"
#include "probe.h"
@@ -192,7 +193,7 @@ static inline unsigned int get_rapl_pmu_idx(int cpu, int scope)
static inline u64 rapl_read_counter(struct perf_event *event)
{
u64 raw;
- rdmsrl(event->hw.event_base, raw);
+ rdmsrq(event->hw.event_base, raw);
return raw;
}
@@ -221,7 +222,7 @@ static u64 rapl_event_update(struct perf_event *event)
prev_raw_count = local64_read(&hwc->prev_count);
do {
- rdmsrl(event->hw.event_base, new_raw_count);
+ rdmsrq(event->hw.event_base, new_raw_count);
} while (!local64_try_cmpxchg(&hwc->prev_count,
&prev_raw_count, new_raw_count));
@@ -610,8 +611,8 @@ static int rapl_check_hw_unit(void)
u64 msr_rapl_power_unit_bits;
int i;
- /* protect rdmsrl() to handle virtualization */
- if (rdmsrl_safe(rapl_model->msr_power_unit, &msr_rapl_power_unit_bits))
+ /* protect rdmsrq() to handle virtualization */
+ if (rdmsrq_safe(rapl_model->msr_power_unit, &msr_rapl_power_unit_bits))
return -1;
for (i = 0; i < NR_RAPL_PKG_DOMAINS; i++)
rapl_pkg_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
diff --git a/arch/x86/events/utils.c b/arch/x86/events/utils.c
index dab4ed199227..77fd00b3305e 100644
--- a/arch/x86/events/utils.c
+++ b/arch/x86/events/utils.c
@@ -2,6 +2,7 @@
#include <asm/insn.h>
#include <linux/mm.h>
+#include <asm/msr.h>
#include "perf_event.h"
static int decode_branch_type(struct insn *insn)
diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
index 2fd9b0cf9a5e..4bdfcf091200 100644
--- a/arch/x86/events/zhaoxin/core.c
+++ b/arch/x86/events/zhaoxin/core.c
@@ -15,6 +15,7 @@
#include <asm/cpufeature.h>
#include <asm/hardirq.h>
#include <asm/apic.h>
+#include <asm/msr.h>
#include "../perf_event.h"
@@ -254,26 +255,26 @@ static __initconst const u64 zxe_hw_cache_event_ids
static void zhaoxin_pmu_disable_all(void)
{
- wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+ wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, 0);
}
static void zhaoxin_pmu_enable_all(int added)
{
- wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+ wrmsrq(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
}
static inline u64 zhaoxin_pmu_get_status(void)
{
u64 status;
- rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+ rdmsrq(MSR_CORE_PERF_GLOBAL_STATUS, status);
return status;
}
static inline void zhaoxin_pmu_ack_status(u64 ack)
{
- wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
+ wrmsrq(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
}
static inline void zxc_pmu_ack_status(u64 ack)
@@ -293,9 +294,9 @@ static void zhaoxin_pmu_disable_fixed(struct hw_perf_event *hwc)
mask = 0xfULL << (idx * 4);
- rdmsrl(hwc->config_base, ctrl_val);
+ rdmsrq(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
- wrmsrl(hwc->config_base, ctrl_val);
+ wrmsrq(hwc->config_base, ctrl_val);
}
static void zhaoxin_pmu_disable_event(struct perf_event *event)
@@ -329,10 +330,10 @@ static void zhaoxin_pmu_enable_fixed(struct hw_perf_event *hwc)
bits <<= (idx * 4);
mask = 0xfULL << (idx * 4);
- rdmsrl(hwc->config_base, ctrl_val);
+ rdmsrq(hwc->config_base, ctrl_val);
ctrl_val &= ~mask;
ctrl_val |= bits;
- wrmsrl(hwc->config_base, ctrl_val);
+ wrmsrq(hwc->config_base, ctrl_val);
}
static void zhaoxin_pmu_enable_event(struct perf_event *event)
@@ -397,8 +398,7 @@ again:
if (!x86_perf_event_set_period(event))
continue;
- if (perf_event_overflow(event, &data, regs))
- x86_pmu_stop(event, 0);
+ perf_event_overflow(event, &data, regs);
}
/*
diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c
index 6d91ac5f9836..bfde0a3498b9 100644
--- a/arch/x86/hyperv/hv_apic.c
+++ b/arch/x86/hyperv/hv_apic.c
@@ -28,6 +28,7 @@
#include <asm/hypervisor.h>
#include <asm/mshyperv.h>
#include <asm/apic.h>
+#include <asm/msr.h>
#include <asm/trace/hyperv.h>
@@ -37,7 +38,7 @@ static u64 hv_apic_icr_read(void)
{
u64 reg_val;
- rdmsrl(HV_X64_MSR_ICR, reg_val);
+ rdmsrq(HV_X64_MSR_ICR, reg_val);
return reg_val;
}
@@ -49,7 +50,7 @@ static void hv_apic_icr_write(u32 low, u32 id)
reg_val = reg_val << 32;
reg_val |= low;
- wrmsrl(HV_X64_MSR_ICR, reg_val);
+ wrmsrq(HV_X64_MSR_ICR, reg_val);
}
static u32 hv_apic_read(u32 reg)
@@ -75,10 +76,10 @@ static void hv_apic_write(u32 reg, u32 val)
{
switch (reg) {
case APIC_EOI:
- wrmsr(HV_X64_MSR_EOI, val, 0);
+ wrmsrq(HV_X64_MSR_EOI, val);
break;
case APIC_TASKPRI:
- wrmsr(HV_X64_MSR_TPR, val, 0);
+ wrmsrq(HV_X64_MSR_TPR, val);
break;
default:
native_apic_mem_write(reg, val);
@@ -92,7 +93,7 @@ static void hv_apic_eoi_write(void)
if (hvp && (xchg(&hvp->apic_assist, 0) & 0x1))
return;
- wrmsr(HV_X64_MSR_EOI, APIC_EOI_ACK, 0);
+ wrmsrq(HV_X64_MSR_EOI, APIC_EOI_ACK);
}
static bool cpu_is_self(int cpu)
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index ddeb40930bc8..afdbda2dd7b7 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -21,6 +21,7 @@
#include <asm/hypervisor.h>
#include <hyperv/hvhdk.h>
#include <asm/mshyperv.h>
+#include <asm/msr.h>
#include <asm/idtentry.h>
#include <asm/set_memory.h>
#include <linux/kexec.h>
@@ -33,6 +34,7 @@
#include <linux/syscore_ops.h>
#include <clocksource/hyperv_timer.h>
#include <linux/highmem.h>
+#include <linux/export.h>
void *hv_hypercall_pg;
EXPORT_SYMBOL_GPL(hv_hypercall_pg);
@@ -62,7 +64,7 @@ static int hyperv_init_ghcb(void)
* returned by MSR_AMD64_SEV_ES_GHCB is above shared
* memory boundary and map it here.
*/
- rdmsrl(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);
+ rdmsrq(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);
/* Mask out vTOM bit. ioremap_cache() maps decrypted */
ghcb_gpa &= ~ms_hyperv.shared_gpa_boundary;
@@ -95,7 +97,7 @@ static int hv_cpu_init(unsigned int cpu)
* For root partition we get the hypervisor provided VP assist
* page, instead of allocating a new page.
*/
- rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+ rdmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
*hvp = memremap(msr.pfn << HV_X64_MSR_VP_ASSIST_PAGE_ADDRESS_SHIFT,
PAGE_SIZE, MEMREMAP_WB);
} else {
@@ -128,7 +130,7 @@ static int hv_cpu_init(unsigned int cpu)
}
if (!WARN_ON(!(*hvp))) {
msr.enable = 1;
- wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+ wrmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
}
return hyperv_init_ghcb();
@@ -140,7 +142,7 @@ static void hv_reenlightenment_notify(struct work_struct *dummy)
{
struct hv_tsc_emulation_status emu_status;
- rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+ rdmsrq(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
/* Don't issue the callback if TSC accesses are not emulated */
if (hv_reenlightenment_cb && emu_status.inprogress)
@@ -153,11 +155,11 @@ void hyperv_stop_tsc_emulation(void)
u64 freq;
struct hv_tsc_emulation_status emu_status;
- rdmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+ rdmsrq(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
emu_status.inprogress = 0;
- wrmsrl(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
+ wrmsrq(HV_X64_MSR_TSC_EMULATION_STATUS, *(u64 *)&emu_status);
- rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
+ rdmsrq(HV_X64_MSR_TSC_FREQUENCY, freq);
tsc_khz = div64_u64(freq, 1000);
}
EXPORT_SYMBOL_GPL(hyperv_stop_tsc_emulation);
@@ -203,8 +205,8 @@ void set_hv_tscchange_cb(void (*cb)(void))
re_ctrl.target_vp = hv_vp_index[get_cpu()];
- wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
- wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
+ wrmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+ wrmsrq(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
put_cpu();
}
@@ -217,9 +219,9 @@ void clear_hv_tscchange_cb(void)
if (!hv_reenlightenment_available())
return;
- rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
+ rdmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
re_ctrl.enabled = 0;
- wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
+ wrmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *(u64 *)&re_ctrl);
hv_reenlightenment_cb = NULL;
}
@@ -251,16 +253,16 @@ static int hv_cpu_die(unsigned int cpu)
*/
memunmap(hv_vp_assist_page[cpu]);
hv_vp_assist_page[cpu] = NULL;
- rdmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+ rdmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
msr.enable = 0;
}
- wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
+ wrmsrq(HV_X64_MSR_VP_ASSIST_PAGE, msr.as_uint64);
}
if (hv_reenlightenment_cb == NULL)
return 0;
- rdmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+ rdmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
if (re_ctrl.target_vp == hv_vp_index[cpu]) {
/*
* Reassign reenlightenment notifications to some other online
@@ -274,7 +276,7 @@ static int hv_cpu_die(unsigned int cpu)
else
re_ctrl.enabled = 0;
- wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
+ wrmsrq(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
}
return 0;
@@ -331,9 +333,9 @@ static int hv_suspend(void)
hv_hypercall_pg = NULL;
/* Disable the hypercall page in the hypervisor */
- rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hypercall_msr.enable = 0;
- wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
ret = hv_cpu_die(0);
return ret;
@@ -348,11 +350,11 @@ static void hv_resume(void)
WARN_ON(ret);
/* Re-enable the hypercall page */
- rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hypercall_msr.enable = 1;
hypercall_msr.guest_physical_address =
vmalloc_to_pfn(hv_hypercall_pg_saved);
- wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hv_hypercall_pg = hv_hypercall_pg_saved;
hv_hypercall_pg_saved = NULL;
@@ -390,40 +392,6 @@ static void __init hv_stimer_setup_percpu_clockev(void)
old_setup_percpu_clockev();
}
-#if IS_ENABLED(CONFIG_HYPERV_VTL_MODE)
-static u8 __init get_vtl(void)
-{
- u64 control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_REGISTERS;
- struct hv_input_get_vp_registers *input;
- struct hv_output_get_vp_registers *output;
- unsigned long flags;
- u64 ret;
-
- local_irq_save(flags);
- input = *this_cpu_ptr(hyperv_pcpu_input_arg);
- output = *this_cpu_ptr(hyperv_pcpu_output_arg);
-
- memset(input, 0, struct_size(input, names, 1));
- input->partition_id = HV_PARTITION_ID_SELF;
- input->vp_index = HV_VP_INDEX_SELF;
- input->input_vtl.as_uint8 = 0;
- input->names[0] = HV_REGISTER_VSM_VP_STATUS;
-
- ret = hv_do_hypercall(control, input, output);
- if (hv_result_success(ret)) {
- ret = output->values[0].reg8 & HV_X64_VTL_MASK;
- } else {
- pr_err("Failed to get VTL(error: %lld) exiting...\n", ret);
- BUG();
- }
-
- local_irq_restore(flags);
- return ret;
-}
-#else
-static inline u8 get_vtl(void) { return 0; }
-#endif
-
/*
* This function is to be invoked early in the boot sequence after the
* hypervisor has been detected.
@@ -499,7 +467,7 @@ void __init hyperv_init(void)
* in such a VM and is only used in such a VM.
*/
guest_id = hv_generate_guest_id(LINUX_VERSION_CODE);
- wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
+ wrmsrq(HV_X64_MSR_GUEST_OS_ID, guest_id);
/* With the paravisor, the VM must also write the ID via GHCB/GHCI */
hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id);
@@ -515,7 +483,7 @@ void __init hyperv_init(void)
if (hv_hypercall_pg == NULL)
goto clean_guest_os_id;
- rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
hypercall_msr.enable = 1;
if (hv_root_partition()) {
@@ -532,7 +500,7 @@ void __init hyperv_init(void)
* so it is populated with code, then copy the code to an
* executable page.
*/
- wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
pg = vmalloc_to_page(hv_hypercall_pg);
src = memremap(hypercall_msr.guest_physical_address << PAGE_SHIFT, PAGE_SIZE,
@@ -544,7 +512,7 @@ void __init hyperv_init(void)
hv_remap_tsc_clocksource();
} else {
hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
- wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ wrmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
}
skip_hypercall_pg_init:
@@ -608,7 +576,7 @@ skip_hypercall_pg_init:
return;
clean_guest_os_id:
- wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
+ wrmsrq(HV_X64_MSR_GUEST_OS_ID, 0);
hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE);
free_ghcb_page:
@@ -629,7 +597,7 @@ void hyperv_cleanup(void)
union hv_reference_tsc_msr tsc_msr;
/* Reset our OS id */
- wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
+ wrmsrq(HV_X64_MSR_GUEST_OS_ID, 0);
hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
/*
@@ -667,18 +635,18 @@ void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die)
return;
panic_reported = true;
- rdmsrl(HV_X64_MSR_GUEST_OS_ID, guest_id);
+ rdmsrq(HV_X64_MSR_GUEST_OS_ID, guest_id);
- wrmsrl(HV_X64_MSR_CRASH_P0, err);
- wrmsrl(HV_X64_MSR_CRASH_P1, guest_id);
- wrmsrl(HV_X64_MSR_CRASH_P2, regs->ip);
- wrmsrl(HV_X64_MSR_CRASH_P3, regs->ax);
- wrmsrl(HV_X64_MSR_CRASH_P4, regs->sp);
+ wrmsrq(HV_X64_MSR_CRASH_P0, err);
+ wrmsrq(HV_X64_MSR_CRASH_P1, guest_id);
+ wrmsrq(HV_X64_MSR_CRASH_P2, regs->ip);
+ wrmsrq(HV_X64_MSR_CRASH_P3, regs->ax);
+ wrmsrq(HV_X64_MSR_CRASH_P4, regs->sp);
/*
* Let Hyper-V know there is crash data available
*/
- wrmsrl(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
+ wrmsrq(HV_X64_MSR_CRASH_CTL, HV_CRASH_CTL_CRASH_NOTIFY);
}
EXPORT_SYMBOL_GPL(hyperv_report_panic);
@@ -701,8 +669,41 @@ bool hv_is_hyperv_initialized(void)
* that the hypercall page is setup
*/
hypercall_msr.as_uint64 = 0;
- rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+ rdmsrq(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
return hypercall_msr.enable;
}
EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
+
+int hv_apicid_to_vp_index(u32 apic_id)
+{
+ u64 control;
+ u64 status;
+ unsigned long irq_flags;
+ struct hv_get_vp_from_apic_id_in *input;
+ u32 *output, ret;
+
+ local_irq_save(irq_flags);
+
+ input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+ memset(input, 0, sizeof(*input));
+ input->partition_id = HV_PARTITION_ID_SELF;
+ input->apic_ids[0] = apic_id;
+
+ output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+ control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_INDEX_FROM_APIC_ID;
+ status = hv_do_hypercall(control, input, output);
+ ret = output[0];
+
+ local_irq_restore(irq_flags);
+
+ if (!hv_result_success(status)) {
+ pr_err("failed to get vp index from apic id %d, status %#llx\n",
+ apic_id, status);
+ return -EINVAL;
+ }
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(hv_apicid_to_vp_index);
diff --git a/arch/x86/hyperv/hv_spinlock.c b/arch/x86/hyperv/hv_spinlock.c
index 151e851bef09..81b006601370 100644
--- a/arch/x86/hyperv/hv_spinlock.c
+++ b/arch/x86/hyperv/hv_spinlock.c
@@ -15,6 +15,7 @@
#include <asm/mshyperv.h>
#include <asm/paravirt.h>
#include <asm/apic.h>
+#include <asm/msr.h>
static bool hv_pvspin __initdata = true;
@@ -39,18 +40,18 @@ static void hv_qlock_wait(u8 *byte, u8 val)
* To prevent a race against the unlock path it is required to
* disable interrupts before accessing the HV_X64_MSR_GUEST_IDLE
* MSR. Otherwise, if the IPI from hv_qlock_kick() arrives between
- * the lock value check and the rdmsrl() then the vCPU might be put
+ * the lock value check and the rdmsrq() then the vCPU might be put
* into 'idle' state by the hypervisor and kept in that state for
* an unspecified amount of time.
*/
local_irq_save(flags);
/*
- * Only issue the rdmsrl() when the lock state has not changed.
+ * Only issue the rdmsrq() when the lock state has not changed.
*/
if (READ_ONCE(*byte) == val) {
unsigned long msr_val;
- rdmsrl(HV_X64_MSR_GUEST_IDLE, msr_val);
+ rdmsrq(HV_X64_MSR_GUEST_IDLE, msr_val);
(void)msr_val;
}
diff --git a/arch/x86/hyperv/hv_vtl.c b/arch/x86/hyperv/hv_vtl.c
index 13242ed8ff16..042e8712d8de 100644
--- a/arch/x86/hyperv/hv_vtl.c
+++ b/arch/x86/hyperv/hv_vtl.c
@@ -11,6 +11,7 @@
#include <asm/desc.h>
#include <asm/i8259.h>
#include <asm/mshyperv.h>
+#include <asm/msr.h>
#include <asm/realmode.h>
#include <asm/reboot.h>
#include <../kernel/smpboot.h>
@@ -55,7 +56,12 @@ static void __noreturn hv_vtl_restart(char __maybe_unused *cmd)
void __init hv_vtl_init_platform(void)
{
- pr_info("Linux runs in Hyper-V Virtual Trust Level\n");
+ /*
+ * This function is a no-op if the VTL mode is not enabled.
+ * If it is, this function runs if and only the kernel boots in
+ * VTL2 which the x86 hv initialization path makes sure of.
+ */
+ pr_info("Linux runs in Hyper-V Virtual Trust Level %d\n", ms_hyperv.vtl);
x86_platform.realmode_reserve = x86_init_noop;
x86_platform.realmode_init = x86_init_noop;
@@ -149,11 +155,11 @@ static int hv_vtl_bringup_vcpu(u32 target_vp_index, int cpu, u64 eip_ignored)
input->vp_context.rip = rip;
input->vp_context.rsp = rsp;
input->vp_context.rflags = 0x0000000000000002;
- input->vp_context.efer = __rdmsr(MSR_EFER);
+ input->vp_context.efer = native_rdmsrq(MSR_EFER);
input->vp_context.cr0 = native_read_cr0();
input->vp_context.cr3 = __native_read_cr3();
input->vp_context.cr4 = native_read_cr4();
- input->vp_context.msr_cr_pat = __rdmsr(MSR_IA32_CR_PAT);
+ input->vp_context.msr_cr_pat = native_rdmsrq(MSR_IA32_CR_PAT);
input->vp_context.idtr.limit = idt_ptr.size;
input->vp_context.idtr.base = idt_ptr.address;
input->vp_context.gdtr.limit = gdt_ptr.size;
@@ -206,63 +212,23 @@ free_lock:
return ret;
}
-static int hv_vtl_apicid_to_vp_id(u32 apic_id)
-{
- u64 control;
- u64 status;
- unsigned long irq_flags;
- struct hv_get_vp_from_apic_id_in *input;
- u32 *output, ret;
-
- local_irq_save(irq_flags);
-
- input = *this_cpu_ptr(hyperv_pcpu_input_arg);
- memset(input, 0, sizeof(*input));
- input->partition_id = HV_PARTITION_ID_SELF;
- input->apic_ids[0] = apic_id;
-
- output = *this_cpu_ptr(hyperv_pcpu_output_arg);
-
- control = HV_HYPERCALL_REP_COMP_1 | HVCALL_GET_VP_ID_FROM_APIC_ID;
- status = hv_do_hypercall(control, input, output);
- ret = output[0];
-
- local_irq_restore(irq_flags);
-
- if (!hv_result_success(status)) {
- pr_err("failed to get vp id from apic id %d, status %#llx\n",
- apic_id, status);
- return -EINVAL;
- }
-
- return ret;
-}
-
-static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip)
+static int hv_vtl_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip, unsigned int cpu)
{
- int vp_id, cpu;
-
- /* Find the logical CPU for the APIC ID */
- for_each_present_cpu(cpu) {
- if (arch_match_cpu_phys_id(cpu, apicid))
- break;
- }
- if (cpu >= nr_cpu_ids)
- return -EINVAL;
+ int vp_index;
pr_debug("Bringing up CPU with APIC ID %d in VTL2...\n", apicid);
- vp_id = hv_vtl_apicid_to_vp_id(apicid);
+ vp_index = hv_apicid_to_vp_index(apicid);
- if (vp_id < 0) {
+ if (vp_index < 0) {
pr_err("Couldn't find CPU with APIC ID %d\n", apicid);
return -EINVAL;
}
- if (vp_id > ms_hyperv.max_vp_index) {
- pr_err("Invalid CPU id %d for APIC ID %d\n", vp_id, apicid);
+ if (vp_index > ms_hyperv.max_vp_index) {
+ pr_err("Invalid CPU id %d for APIC ID %d\n", vp_index, apicid);
return -EINVAL;
}
- return hv_vtl_bringup_vcpu(vp_id, cpu, start_eip);
+ return hv_vtl_bringup_vcpu(vp_index, cpu, start_eip);
}
int __init hv_vtl_early_init(void)
diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
index 31f0d29cbc5e..090f5ac9f492 100644
--- a/arch/x86/hyperv/irqdomain.c
+++ b/arch/x86/hyperv/irqdomain.c
@@ -10,6 +10,7 @@
#include <linux/pci.h>
#include <linux/irq.h>
+#include <linux/export.h>
#include <asm/mshyperv.h>
static int hv_map_interrupt(union hv_device_id device_id, bool level,
@@ -46,7 +47,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
if (nr_bank < 0) {
local_irq_restore(flags);
pr_err("%s: unable to generate VP set\n", __func__);
- return EINVAL;
+ return -EINVAL;
}
intr_desc->target.flags = HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
@@ -66,7 +67,7 @@ static int hv_map_interrupt(union hv_device_id device_id, bool level,
if (!hv_result_success(status))
hv_status_err(status, "\n");
- return hv_result(status);
+ return hv_result_to_errno(status);
}
static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry)
@@ -88,7 +89,10 @@ static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry)
status = hv_do_hypercall(HVCALL_UNMAP_DEVICE_INTERRUPT, input, NULL);
local_irq_restore(flags);
- return hv_result(status);
+ if (!hv_result_success(status))
+ hv_status_err(status, "\n");
+
+ return hv_result_to_errno(status);
}
#ifdef CONFIG_PCI_MSI
@@ -169,13 +173,34 @@ static union hv_device_id hv_build_pci_dev_id(struct pci_dev *dev)
return dev_id;
}
-static int hv_map_msi_interrupt(struct pci_dev *dev, int cpu, int vector,
- struct hv_interrupt_entry *entry)
+/**
+ * hv_map_msi_interrupt() - "Map" the MSI IRQ in the hypervisor.
+ * @data: Describes the IRQ
+ * @out_entry: Hypervisor (MSI) interrupt entry (can be NULL)
+ *
+ * Map the IRQ in the hypervisor by issuing a MAP_DEVICE_INTERRUPT hypercall.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_map_msi_interrupt(struct irq_data *data,
+ struct hv_interrupt_entry *out_entry)
{
- union hv_device_id device_id = hv_build_pci_dev_id(dev);
+ struct irq_cfg *cfg = irqd_cfg(data);
+ struct hv_interrupt_entry dummy;
+ union hv_device_id device_id;
+ struct msi_desc *msidesc;
+ struct pci_dev *dev;
+ int cpu;
- return hv_map_interrupt(device_id, false, cpu, vector, entry);
+ msidesc = irq_data_get_msi_desc(data);
+ dev = msi_desc_to_pci_dev(msidesc);
+ device_id = hv_build_pci_dev_id(dev);
+ cpu = cpumask_first(irq_data_get_effective_affinity_mask(data));
+
+ return hv_map_interrupt(device_id, false, cpu, cfg->vector,
+ out_entry ? out_entry : &dummy);
}
+EXPORT_SYMBOL_GPL(hv_map_msi_interrupt);
static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi_msg *msg)
{
@@ -188,13 +213,11 @@ static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi
static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry);
static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
{
+ struct hv_interrupt_entry *stored_entry;
+ struct irq_cfg *cfg = irqd_cfg(data);
struct msi_desc *msidesc;
struct pci_dev *dev;
- struct hv_interrupt_entry out_entry, *stored_entry;
- struct irq_cfg *cfg = irqd_cfg(data);
- const cpumask_t *affinity;
- int cpu;
- u64 status;
+ int ret;
msidesc = irq_data_get_msi_desc(data);
dev = msi_desc_to_pci_dev(msidesc);
@@ -204,9 +227,6 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
return;
}
- affinity = irq_data_get_effective_affinity_mask(data);
- cpu = cpumask_first_and(affinity, cpu_online_mask);
-
if (data->chip_data) {
/*
* This interrupt is already mapped. Let's unmap first.
@@ -219,14 +239,12 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
stored_entry = data->chip_data;
data->chip_data = NULL;
- status = hv_unmap_msi_interrupt(dev, stored_entry);
+ ret = hv_unmap_msi_interrupt(dev, stored_entry);
kfree(stored_entry);
- if (status != HV_STATUS_SUCCESS) {
- hv_status_debug(status, "failed to unmap\n");
+ if (ret)
return;
- }
}
stored_entry = kzalloc(sizeof(*stored_entry), GFP_ATOMIC);
@@ -235,15 +253,14 @@ static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
return;
}
- status = hv_map_msi_interrupt(dev, cpu, cfg->vector, &out_entry);
- if (status != HV_STATUS_SUCCESS) {
+ ret = hv_map_msi_interrupt(data, stored_entry);
+ if (ret) {
kfree(stored_entry);
return;
}
- *stored_entry = out_entry;
data->chip_data = stored_entry;
- entry_to_msi_msg(&out_entry, msg);
+ entry_to_msi_msg(data->chip_data, msg);
return;
}
@@ -257,7 +274,6 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
{
struct hv_interrupt_entry old_entry;
struct msi_msg msg;
- u64 status;
if (!irqd->chip_data) {
pr_debug("%s: no chip data\n!", __func__);
@@ -270,10 +286,7 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
kfree(irqd->chip_data);
irqd->chip_data = NULL;
- status = hv_unmap_msi_interrupt(dev, &old_entry);
-
- if (status != HV_STATUS_SUCCESS)
- hv_status_err(status, "\n");
+ (void)hv_unmap_msi_interrupt(dev, &old_entry);
}
static void hv_msi_free_irq(struct irq_domain *domain,
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index 77bf05f06b9e..ade6c665c97e 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -9,6 +9,8 @@
#include <linux/bitfield.h>
#include <linux/types.h>
#include <linux/slab.h>
+#include <linux/cpu.h>
+#include <linux/export.h>
#include <asm/svm.h>
#include <asm/sev.h>
#include <asm/io.h>
@@ -22,6 +24,7 @@
#include <asm/realmode.h>
#include <asm/e820/api.h>
#include <asm/desc.h>
+#include <asm/msr.h>
#include <uapi/asm/vmx.h>
#ifdef CONFIG_AMD_MEM_ENCRYPT
@@ -110,12 +113,12 @@ u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size)
static inline u64 rd_ghcb_msr(void)
{
- return __rdmsr(MSR_AMD64_SEV_ES_GHCB);
+ return native_rdmsrq(MSR_AMD64_SEV_ES_GHCB);
}
static inline void wr_ghcb_msr(u64 val)
{
- native_wrmsrl(MSR_AMD64_SEV_ES_GHCB, val);
+ native_wrmsrq(MSR_AMD64_SEV_ES_GHCB, val);
}
static enum es_result hv_ghcb_hv_call(struct ghcb *ghcb, u64 exit_code,
@@ -288,7 +291,7 @@ static void snp_cleanup_vmsa(struct sev_es_save_area *vmsa)
free_page((unsigned long)vmsa);
}
-int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
+int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip, unsigned int cpu)
{
struct sev_es_save_area *vmsa = (struct sev_es_save_area *)
__get_free_page(GFP_KERNEL | __GFP_ZERO);
@@ -297,10 +300,16 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
u64 ret, retry = 5;
struct hv_enable_vp_vtl *start_vp_input;
unsigned long flags;
+ int vp_index;
if (!vmsa)
return -ENOMEM;
+ /* Find the Hyper-V VP index which might be not the same as APIC ID */
+ vp_index = hv_apicid_to_vp_index(apic_id);
+ if (vp_index < 0 || vp_index > ms_hyperv.max_vp_index)
+ return -EINVAL;
+
native_store_gdt(&gdtr);
vmsa->gdtr.base = gdtr.address;
@@ -348,7 +357,7 @@ int hv_snp_boot_ap(u32 cpu, unsigned long start_ip)
start_vp_input = (struct hv_enable_vp_vtl *)ap_start_input_arg;
memset(start_vp_input, 0, sizeof(*start_vp_input));
start_vp_input->partition_id = -1;
- start_vp_input->vp_index = cpu;
+ start_vp_input->vp_index = vp_index;
start_vp_input->target_vtl.target_vtl = ms_hyperv.vtl;
*(u64 *)&start_vp_input->vp_context = __pa(vmsa) | 1;
diff --git a/arch/x86/hyperv/nested.c b/arch/x86/hyperv/nested.c
index 1083dc8646f9..8ccbb7c4fc27 100644
--- a/arch/x86/hyperv/nested.c
+++ b/arch/x86/hyperv/nested.c
@@ -11,6 +11,7 @@
#include <linux/types.h>
+#include <linux/export.h>
#include <hyperv/hvhdk.h>
#include <asm/mshyperv.h>
#include <asm/tlbflush.h>
diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 5ab1a4598d00..a03aa6f999d1 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -158,13 +158,13 @@ static inline bool acpi_has_cpu_in_madt(void)
}
#define ACPI_HAVE_ARCH_SET_ROOT_POINTER
-static inline void acpi_arch_set_root_pointer(u64 addr)
+static __always_inline void acpi_arch_set_root_pointer(u64 addr)
{
x86_init.acpi.set_root_pointer(addr);
}
#define ACPI_HAVE_ARCH_GET_ROOT_POINTER
-static inline u64 acpi_arch_get_root_pointer(void)
+static __always_inline u64 acpi_arch_get_root_pointer(void)
{
return x86_init.acpi.get_root_pointer();
}
diff --git a/arch/x86/include/asm/acrn.h b/arch/x86/include/asm/acrn.h
index 1dd14381bcb6..fab11192c60a 100644
--- a/arch/x86/include/asm/acrn.h
+++ b/arch/x86/include/asm/acrn.h
@@ -25,7 +25,7 @@ void acrn_remove_intr_handler(void);
static inline u32 acrn_cpuid_base(void)
{
if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
- return hypervisor_cpuid_base("ACRNACRNACRN", 0);
+ return cpuid_base_hypervisor("ACRNACRNACRN", 0);
return 0;
}
diff --git a/arch/x86/include/asm/alternative.h b/arch/x86/include/asm/alternative.h
index f2294784babc..15bc07a5ebb3 100644
--- a/arch/x86/include/asm/alternative.h
+++ b/arch/x86/include/asm/alternative.h
@@ -83,6 +83,12 @@ struct alt_instr {
extern struct alt_instr __alt_instructions[], __alt_instructions_end[];
+extern s32 __retpoline_sites[], __retpoline_sites_end[];
+extern s32 __return_sites[], __return_sites_end[];
+extern s32 __cfi_sites[], __cfi_sites_end[];
+extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[];
+extern s32 __smp_locks[], __smp_locks_end[];
+
/*
* Debug flag that can be tested to see whether alternative
* instructions were patched in already:
@@ -367,11 +373,6 @@ void nop_func(void);
__ALTERNATIVE(\oldinstr, \newinstr, \ft_flags)
.endm
-#define old_len 141b-140b
-#define new_len1 144f-143f
-#define new_len2 145f-144f
-#define new_len3 146f-145f
-
/*
* Same as ALTERNATIVE macro above but for two alternatives. If CPU
* has @feature1, it replaces @oldinstr with @newinstr1. If CPU has
diff --git a/arch/x86/include/asm/amd_hsmp.h b/arch/x86/include/asm/amd/hsmp.h
index 03c2ce3edaf5..2137f62853ed 100644
--- a/arch/x86/include/asm/amd_hsmp.h
+++ b/arch/x86/include/asm/amd/hsmp.h
@@ -1,5 +1,4 @@
/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-
#ifndef _ASM_X86_AMD_HSMP_H_
#define _ASM_X86_AMD_HSMP_H_
@@ -13,4 +12,5 @@ static inline int hsmp_send_message(struct hsmp_message *msg)
return -ENODEV;
}
#endif
+
#endif /*_ASM_X86_AMD_HSMP_H_*/
diff --git a/arch/x86/include/asm/amd-ibs.h b/arch/x86/include/asm/amd/ibs.h
index 77f3a589a99a..3ee5903982c2 100644
--- a/arch/x86/include/asm/amd-ibs.h
+++ b/arch/x86/include/asm/amd/ibs.h
@@ -1,4 +1,7 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_AMD_IBS_H
+#define _ASM_X86_AMD_IBS_H
+
/*
* From PPR Vol 1 for AMD Family 19h Model 01h B1
* 55898 Rev 0.35 - Feb 5, 2021
@@ -151,3 +154,5 @@ struct perf_ibs_data {
};
u64 regs[MSR_AMD64_IBS_REG_COUNT_MAX];
};
+
+#endif /* _ASM_X86_AMD_IBS_H */
diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd/nb.h
index adfa0854cf2d..ddb5108cf46c 100644
--- a/arch/x86/include/asm/amd_nb.h
+++ b/arch/x86/include/asm/amd/nb.h
@@ -4,7 +4,7 @@
#include <linux/ioport.h>
#include <linux/pci.h>
-#include <asm/amd_node.h>
+#include <asm/amd/node.h>
struct amd_nb_bus_dev_range {
u8 bus;
diff --git a/arch/x86/include/asm/amd_node.h b/arch/x86/include/asm/amd/node.h
index 23fe617898a8..23fe617898a8 100644
--- a/arch/x86/include/asm/amd_node.h
+++ b/arch/x86/include/asm/amd/node.h
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index c903d358405d..07ba4935e873 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -120,7 +120,7 @@ static inline bool apic_is_x2apic_enabled(void)
{
u64 msr;
- if (rdmsrl_safe(MSR_IA32_APICBASE, &msr))
+ if (rdmsrq_safe(MSR_IA32_APICBASE, &msr))
return false;
return msr & X2APIC_ENABLE;
}
@@ -209,12 +209,12 @@ static inline void native_apic_msr_write(u32 reg, u32 v)
reg == APIC_LVR)
return;
- wrmsr(APIC_BASE_MSR + (reg >> 4), v, 0);
+ wrmsrq(APIC_BASE_MSR + (reg >> 4), v);
}
static inline void native_apic_msr_eoi(void)
{
- __wrmsr(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK, 0);
+ native_wrmsrq(APIC_BASE_MSR + (APIC_EOI >> 4), APIC_EOI_ACK);
}
static inline u32 native_apic_msr_read(u32 reg)
@@ -224,20 +224,20 @@ static inline u32 native_apic_msr_read(u32 reg)
if (reg == APIC_DFR)
return -1;
- rdmsrl(APIC_BASE_MSR + (reg >> 4), msr);
+ rdmsrq(APIC_BASE_MSR + (reg >> 4), msr);
return (u32)msr;
}
static inline void native_x2apic_icr_write(u32 low, u32 id)
{
- wrmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
+ wrmsrq(APIC_BASE_MSR + (APIC_ICR >> 4), ((__u64) id) << 32 | low);
}
static inline u64 native_x2apic_icr_read(void)
{
unsigned long val;
- rdmsrl(APIC_BASE_MSR + (APIC_ICR >> 4), val);
+ rdmsrq(APIC_BASE_MSR + (APIC_ICR >> 4), val);
return val;
}
@@ -313,9 +313,9 @@ struct apic {
u32 (*get_apic_id)(u32 id);
/* wakeup_secondary_cpu */
- int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip, unsigned int cpu);
/* wakeup secondary CPU using 64-bit wakeup point */
- int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip, unsigned int cpu);
char *name;
};
@@ -333,8 +333,8 @@ struct apic_override {
void (*send_IPI_self)(int vector);
u64 (*icr_read)(void);
void (*icr_write)(u32 low, u32 high);
- int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip);
- int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip);
+ int (*wakeup_secondary_cpu)(u32 apicid, unsigned long start_eip, unsigned int cpu);
+ int (*wakeup_secondary_cpu_64)(u32 apicid, unsigned long start_eip, unsigned int cpu);
};
/*
@@ -488,11 +488,14 @@ static inline void apic_setup_apic_calls(void) { }
extern void apic_ack_irq(struct irq_data *data);
+#define APIC_VECTOR_TO_BIT_NUMBER(v) ((unsigned int)(v) % 32)
+#define APIC_VECTOR_TO_REG_OFFSET(v) ((unsigned int)(v) / 32 * 0x10)
+
static inline bool lapic_vector_set_in_irr(unsigned int vector)
{
- u32 irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
+ u32 irr = apic_read(APIC_IRR + APIC_VECTOR_TO_REG_OFFSET(vector));
- return !!(irr & (1U << (vector % 32)));
+ return !!(irr & (1U << APIC_VECTOR_TO_BIT_NUMBER(vector)));
}
static inline bool is_vector_pending(unsigned int vector)
@@ -500,6 +503,65 @@ static inline bool is_vector_pending(unsigned int vector)
return lapic_vector_set_in_irr(vector) || pi_pending_this_cpu(vector);
}
+#define MAX_APIC_VECTOR 256
+#define APIC_VECTORS_PER_REG 32
+
+/*
+ * Vector states are maintained by APIC in 32-bit registers that are
+ * 16 bytes aligned. The status of each vector is kept in a single
+ * bit.
+ */
+static inline int apic_find_highest_vector(void *bitmap)
+{
+ int vec;
+ u32 *reg;
+
+ for (vec = MAX_APIC_VECTOR - APIC_VECTORS_PER_REG; vec >= 0; vec -= APIC_VECTORS_PER_REG) {
+ reg = bitmap + APIC_VECTOR_TO_REG_OFFSET(vec);
+ if (*reg)
+ return __fls(*reg) + vec;
+ }
+
+ return -1;
+}
+
+static inline u32 apic_get_reg(void *regs, int reg)
+{
+ return *((u32 *) (regs + reg));
+}
+
+static inline void apic_set_reg(void *regs, int reg, u32 val)
+{
+ *((u32 *) (regs + reg)) = val;
+}
+
+static __always_inline u64 apic_get_reg64(void *regs, int reg)
+{
+ BUILD_BUG_ON(reg != APIC_ICR);
+ return *((u64 *) (regs + reg));
+}
+
+static __always_inline void apic_set_reg64(void *regs, int reg, u64 val)
+{
+ BUILD_BUG_ON(reg != APIC_ICR);
+ *((u64 *) (regs + reg)) = val;
+}
+
+static inline void apic_clear_vector(int vec, void *bitmap)
+{
+ clear_bit(APIC_VECTOR_TO_BIT_NUMBER(vec), bitmap + APIC_VECTOR_TO_REG_OFFSET(vec));
+}
+
+static inline void apic_set_vector(int vec, void *bitmap)
+{
+ set_bit(APIC_VECTOR_TO_BIT_NUMBER(vec), bitmap + APIC_VECTOR_TO_REG_OFFSET(vec));
+}
+
+static inline int apic_test_vector(int vec, void *bitmap)
+{
+ return test_bit(APIC_VECTOR_TO_BIT_NUMBER(vec), bitmap + APIC_VECTOR_TO_REG_OFFSET(vec));
+}
+
/*
* Warm reset vector position:
*/
diff --git a/arch/x86/include/asm/arch_hweight.h b/arch/x86/include/asm/arch_hweight.h
index cbc6157f0b4b..b5982b94bdba 100644
--- a/arch/x86/include/asm/arch_hweight.h
+++ b/arch/x86/include/asm/arch_hweight.h
@@ -16,8 +16,7 @@ static __always_inline unsigned int __arch_hweight32(unsigned int w)
{
unsigned int res;
- asm_inline (ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE
- "call __sw_hweight32",
+ asm_inline (ALTERNATIVE("call __sw_hweight32",
"popcntl %[val], %[cnt]", X86_FEATURE_POPCNT)
: [cnt] "=" REG_OUT (res), ASM_CALL_CONSTRAINT
: [val] REG_IN (w));
@@ -46,8 +45,7 @@ static __always_inline unsigned long __arch_hweight64(__u64 w)
{
unsigned long res;
- asm_inline (ALTERNATIVE(ANNOTATE_IGNORE_ALTERNATIVE
- "call __sw_hweight64",
+ asm_inline (ALTERNATIVE("call __sw_hweight64",
"popcntq %[val], %[cnt]", X86_FEATURE_POPCNT)
: [cnt] "=" REG_OUT (res), ASM_CALL_CONSTRAINT
: [val] REG_IN (w));
diff --git a/arch/x86/include/asm/asm.h b/arch/x86/include/asm/asm.h
index cc2881576c2c..f963848024a5 100644
--- a/arch/x86/include/asm/asm.h
+++ b/arch/x86/include/asm/asm.h
@@ -114,17 +114,12 @@
#endif
#ifndef __ASSEMBLER__
-#ifndef __pic__
static __always_inline __pure void *rip_rel_ptr(void *p)
{
asm("leaq %c1(%%rip), %0" : "=r"(p) : "i"(p));
return p;
}
-#define RIP_REL_REF(var) (*(typeof(&(var)))rip_rel_ptr(&(var)))
-#else
-#define RIP_REL_REF(var) (var)
-#endif
#endif
/*
@@ -243,5 +238,24 @@ register unsigned long current_stack_pointer asm(_ASM_SP);
#define _ASM_EXTABLE_FAULT(from, to) \
_ASM_EXTABLE_TYPE(from, to, EX_TYPE_FAULT)
+/*
+ * Both i386 and x86_64 returns 64-bit values in edx:eax for certain
+ * instructions, but GCC's "A" constraint has different meanings.
+ * For i386, "A" means exactly edx:eax, while for x86_64 it
+ * means rax *or* rdx.
+ *
+ * These helpers wrapping these semantic differences save one instruction
+ * clearing the high half of 'low':
+ */
+#ifdef CONFIG_X86_64
+# define EAX_EDX_DECLARE_ARGS(val, low, high) unsigned long low, high
+# define EAX_EDX_VAL(val, low, high) ((low) | (high) << 32)
+# define EAX_EDX_RET(val, low, high) "=a" (low), "=d" (high)
+#else
+# define EAX_EDX_DECLARE_ARGS(val, low, high) u64 val
+# define EAX_EDX_VAL(val, low, high) (val)
+# define EAX_EDX_RET(val, low, high) "=A" (val)
+#endif
+
#endif /* __KERNEL__ */
#endif /* _ASM_X86_ASM_H */
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index 100413aff640..eebbc8889e70 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -248,7 +248,7 @@ arch_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr)
static __always_inline unsigned long variable__ffs(unsigned long word)
{
- asm("rep; bsf %1,%0"
+ asm("tzcnt %1,%0"
: "=r" (word)
: ASM_INPUT_RM (word));
return word;
@@ -267,10 +267,7 @@ static __always_inline unsigned long variable__ffs(unsigned long word)
static __always_inline unsigned long variable_ffz(unsigned long word)
{
- asm("rep; bsf %1,%0"
- : "=r" (word)
- : "r" (~word));
- return word;
+ return variable__ffs(~word);
}
/**
diff --git a/arch/x86/include/asm/boot.h b/arch/x86/include/asm/boot.h
index 3f02ff6d333d..02b23aa78955 100644
--- a/arch/x86/include/asm/boot.h
+++ b/arch/x86/include/asm/boot.h
@@ -74,6 +74,11 @@
# define BOOT_STACK_SIZE 0x1000
#endif
+#define TRAMPOLINE_32BIT_SIZE (2 * PAGE_SIZE)
+
+#define TRAMPOLINE_32BIT_CODE_OFFSET PAGE_SIZE
+#define TRAMPOLINE_32BIT_CODE_SIZE 0xA0
+
#ifndef __ASSEMBLER__
extern unsigned int output_len;
extern const unsigned long kernel_text_size;
@@ -83,6 +88,11 @@ unsigned long decompress_kernel(unsigned char *outbuf, unsigned long virt_addr,
void (*error)(char *x));
extern struct boot_params *boot_params_ptr;
+extern unsigned long *trampoline_32bit;
+extern const u16 trampoline_ljmp_imm_offset;
+
+void trampoline_32bit_src(void *trampoline, bool enable_5lvl);
+
#endif
#endif /* _ASM_X86_BOOT_H */
diff --git a/arch/x86/include/asm/bug.h b/arch/x86/include/asm/bug.h
index f0e9acf72547..20fcb8507ad1 100644
--- a/arch/x86/include/asm/bug.h
+++ b/arch/x86/include/asm/bug.h
@@ -32,45 +32,42 @@
#ifdef CONFIG_GENERIC_BUG
#ifdef CONFIG_X86_32
-# define __BUG_REL(val) ".long " __stringify(val)
+# define __BUG_REL(val) ".long " val
#else
-# define __BUG_REL(val) ".long " __stringify(val) " - ."
+# define __BUG_REL(val) ".long " val " - ."
#endif
#ifdef CONFIG_DEBUG_BUGVERBOSE
+#define __BUG_ENTRY(file, line, flags) \
+ "2:\t" __BUG_REL("1b") "\t# bug_entry::bug_addr\n" \
+ "\t" __BUG_REL(file) "\t# bug_entry::file\n" \
+ "\t.word " line "\t# bug_entry::line\n" \
+ "\t.word " flags "\t# bug_entry::flags\n"
+#else
+#define __BUG_ENTRY(file, line, flags) \
+ "2:\t" __BUG_REL("1b") "\t# bug_entry::bug_addr\n" \
+ "\t.word " flags "\t# bug_entry::flags\n"
+#endif
+
+#define _BUG_FLAGS_ASM(ins, file, line, flags, size, extra) \
+ "1:\t" ins "\n" \
+ ".pushsection __bug_table,\"aw\"\n" \
+ __BUG_ENTRY(file, line, flags) \
+ "\t.org 2b + " size "\n" \
+ ".popsection\n" \
+ extra
#define _BUG_FLAGS(ins, flags, extra) \
do { \
- asm_inline volatile("1:\t" ins "\n" \
- ".pushsection __bug_table,\"aw\"\n" \
- "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \
- "\t" __BUG_REL(%c0) "\t# bug_entry::file\n" \
- "\t.word %c1" "\t# bug_entry::line\n" \
- "\t.word %c2" "\t# bug_entry::flags\n" \
- "\t.org 2b+%c3\n" \
- ".popsection\n" \
- extra \
+ asm_inline volatile(_BUG_FLAGS_ASM(ins, "%c0", \
+ "%c1", "%c2", "%c3", extra) \
: : "i" (__FILE__), "i" (__LINE__), \
"i" (flags), \
"i" (sizeof(struct bug_entry))); \
} while (0)
-#else /* !CONFIG_DEBUG_BUGVERBOSE */
-
-#define _BUG_FLAGS(ins, flags, extra) \
-do { \
- asm_inline volatile("1:\t" ins "\n" \
- ".pushsection __bug_table,\"aw\"\n" \
- "2:\t" __BUG_REL(1b) "\t# bug_entry::bug_addr\n" \
- "\t.word %c0" "\t# bug_entry::flags\n" \
- "\t.org 2b+%c1\n" \
- ".popsection\n" \
- extra \
- : : "i" (flags), \
- "i" (sizeof(struct bug_entry))); \
-} while (0)
-
-#endif /* CONFIG_DEBUG_BUGVERBOSE */
+#define ARCH_WARN_ASM(file, line, flags, size) \
+ _BUG_FLAGS_ASM(ASM_UD2, file, line, flags, size, "")
#else
@@ -92,11 +89,14 @@ do { \
* were to trigger, we'd rather wreck the machine in an attempt to get the
* message out than not know about it.
*/
+
+#define ARCH_WARN_REACHABLE ANNOTATE_REACHABLE(1b)
+
#define __WARN_FLAGS(flags) \
do { \
__auto_type __flags = BUGFLAG_WARNING|(flags); \
instrumentation_begin(); \
- _BUG_FLAGS(ASM_UD2, __flags, ANNOTATE_REACHABLE(1b)); \
+ _BUG_FLAGS(ASM_UD2, __flags, ARCH_WARN_REACHABLE); \
instrumentation_end(); \
} while (0)
diff --git a/arch/x86/include/asm/ce4100.h b/arch/x86/include/asm/ce4100.h
index 2930f560d7f3..e1f965bb1e31 100644
--- a/arch/x86/include/asm/ce4100.h
+++ b/arch/x86/include/asm/ce4100.h
@@ -4,4 +4,10 @@
int ce4100_pci_init(void);
+#ifdef CONFIG_SERIAL_8250
+void __init sdv_serial_fixup(void);
+#else
+static inline void sdv_serial_fixup(void) {};
+#endif
+
#endif
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 3e51ba459154..1751f1eb95ef 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -116,8 +116,6 @@ struct pt_regs;
#ifdef CONFIG_CFI_CLANG
enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
#define __bpfcall
-extern u32 cfi_bpf_hash;
-extern u32 cfi_bpf_subprog_hash;
static inline int cfi_get_offset(void)
{
@@ -135,6 +133,8 @@ static inline int cfi_get_offset(void)
#define cfi_get_offset cfi_get_offset
extern u32 cfi_get_func_hash(void *func);
+#define cfi_get_func_hash cfi_get_func_hash
+
extern int cfi_get_func_arity(void *func);
#ifdef CONFIG_FINEIBT
@@ -153,12 +153,6 @@ static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
{
return BUG_TRAP_TYPE_NONE;
}
-#define cfi_bpf_hash 0U
-#define cfi_bpf_subprog_hash 0U
-static inline u32 cfi_get_func_hash(void *func)
-{
- return 0;
-}
static inline int cfi_get_func_arity(void *func)
{
return 0;
diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h
index e7225452963f..e1dbf8df1b69 100644
--- a/arch/x86/include/asm/coco.h
+++ b/arch/x86/include/asm/coco.h
@@ -22,7 +22,7 @@ static inline u64 cc_get_mask(void)
static inline void cc_set_mask(u64 mask)
{
- RIP_REL_REF(cc_mask) = mask;
+ cc_mask = mask;
}
u64 cc_mkenc(u64 val);
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 30144ef9ef02..06fc0479a23f 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -218,6 +218,7 @@
#define X86_FEATURE_FLEXPRIORITY ( 8*32+ 1) /* "flexpriority" Intel FlexPriority */
#define X86_FEATURE_EPT ( 8*32+ 2) /* "ept" Intel Extended Page Table */
#define X86_FEATURE_VPID ( 8*32+ 3) /* "vpid" Intel Virtual Processor ID */
+#define X86_FEATURE_COHERENCY_SFW_NO ( 8*32+ 4) /* SNP cache coherency software work around not needed */
#define X86_FEATURE_VMMCALL ( 8*32+15) /* "vmmcall" Prefer VMMCALL to VMCALL */
#define X86_FEATURE_XENPV ( 8*32+16) /* Xen paravirtual guest */
@@ -336,6 +337,7 @@
#define X86_FEATURE_AMD_IBRS (13*32+14) /* Indirect Branch Restricted Speculation */
#define X86_FEATURE_AMD_STIBP (13*32+15) /* Single Thread Indirect Branch Predictors */
#define X86_FEATURE_AMD_STIBP_ALWAYS_ON (13*32+17) /* Single Thread Indirect Branch Predictors always-on preferred */
+#define X86_FEATURE_AMD_IBRS_SAME_MODE (13*32+19) /* Indirect Branch Restricted Speculation same mode protection*/
#define X86_FEATURE_AMD_PPIN (13*32+23) /* "amd_ppin" Protected Processor Inventory Number */
#define X86_FEATURE_AMD_SSBD (13*32+24) /* Speculative Store Bypass Disable */
#define X86_FEATURE_VIRT_SSBD (13*32+25) /* "virt_ssbd" Virtualized Speculative Store Bypass Disable */
@@ -378,6 +380,7 @@
#define X86_FEATURE_V_SPEC_CTRL (15*32+20) /* "v_spec_ctrl" Virtual SPEC_CTRL */
#define X86_FEATURE_VNMI (15*32+25) /* "vnmi" Virtual NMI */
#define X86_FEATURE_SVME_ADDR_CHK (15*32+28) /* SVME addr check */
+#define X86_FEATURE_BUS_LOCK_THRESHOLD (15*32+29) /* Bus lock threshold */
#define X86_FEATURE_IDLE_HLT (15*32+30) /* IDLE HLT intercept */
/* Intel-defined CPU features, CPUID level 0x00000007:0 (ECX), word 16 */
@@ -446,6 +449,7 @@
#define X86_FEATURE_DEBUG_SWAP (19*32+14) /* "debug_swap" SEV-ES full debug state swap support */
#define X86_FEATURE_RMPREAD (19*32+21) /* RMPREAD instruction */
#define X86_FEATURE_SEGMENTED_RMP (19*32+23) /* Segmented RMP support */
+#define X86_FEATURE_ALLOWED_SEV_FEATURES (19*32+27) /* Allowed SEV Features */
#define X86_FEATURE_SVSM (19*32+28) /* "svsm" SVSM present */
#define X86_FEATURE_HV_INUSE_WR_ALLOWED (19*32+30) /* Allow Write to in-use hypervisor-owned pages */
@@ -453,10 +457,15 @@
#define X86_FEATURE_NO_NESTED_DATA_BP (20*32+ 0) /* No Nested Data Breakpoints */
#define X86_FEATURE_WRMSR_XX_BASE_NS (20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
#define X86_FEATURE_LFENCE_RDTSC (20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_VERW_CLEAR (20*32+ 5) /* The memory form of VERW mitigates TSA */
#define X86_FEATURE_NULL_SEL_CLR_BASE (20*32+ 6) /* Null Selector Clears Base */
+
#define X86_FEATURE_AUTOIBRS (20*32+ 8) /* Automatic IBRS */
#define X86_FEATURE_NO_SMM_CTL_MSR (20*32+ 9) /* SMM_CTL MSR is not present */
+#define X86_FEATURE_GP_ON_USER_CPUID (20*32+17) /* User CPUID faulting */
+
+#define X86_FEATURE_PREFETCHI (20*32+20) /* Prefetch Data/Instruction to Cache Level */
#define X86_FEATURE_SBPB (20*32+27) /* Selective Branch Prediction Barrier */
#define X86_FEATURE_IBPB_BRTYPE (20*32+28) /* MSR_PRED_CMD[IBPB] flushes all branch type predictions */
#define X86_FEATURE_SRSO_NO (20*32+29) /* CPU is not affected by SRSO */
@@ -476,12 +485,16 @@
#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* Clear branch history at syscall entry using SW loop */
#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* BHI_DIS_S HW control available */
#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* BHI_DIS_S HW control enabled */
-#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */
-#define X86_FEATURE_AMD_FAST_CPPC (21*32 + 5) /* Fast CPPC */
-#define X86_FEATURE_AMD_HETEROGENEOUS_CORES (21*32 + 6) /* Heterogeneous Core Topology */
-#define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32 + 7) /* Workload Classification */
-#define X86_FEATURE_PREFER_YMM (21*32 + 8) /* Avoid ZMM registers due to downclocking */
-#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32 + 9) /* Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_CLEAR_BHB_VMEXIT (21*32+ 4) /* Clear branch history at vmexit using SW loop */
+#define X86_FEATURE_AMD_FAST_CPPC (21*32+ 5) /* Fast CPPC */
+#define X86_FEATURE_AMD_HTR_CORES (21*32+ 6) /* Heterogeneous Core Topology */
+#define X86_FEATURE_AMD_WORKLOAD_CLASS (21*32+ 7) /* Workload Classification */
+#define X86_FEATURE_PREFER_YMM (21*32+ 8) /* Avoid ZMM registers due to downclocking */
+#define X86_FEATURE_APX (21*32+ 9) /* Advanced Performance Extensions */
+#define X86_FEATURE_INDIRECT_THUNK_ITS (21*32+10) /* Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_TSA_SQ_NO (21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
+#define X86_FEATURE_TSA_L1_NO (21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
+#define X86_FEATURE_CLEAR_CPU_BUF_VM (21*32+13) /* Clear CPU buffers using VERW before VMRUN */
/*
* BUG word(s)
@@ -520,7 +533,7 @@
#define X86_BUG_ITLB_MULTIHIT X86_BUG(23) /* "itlb_multihit" CPU may incur MCE during certain page attribute changes */
#define X86_BUG_SRBDS X86_BUG(24) /* "srbds" CPU may leak RNG bits if not mitigated */
#define X86_BUG_MMIO_STALE_DATA X86_BUG(25) /* "mmio_stale_data" CPU is affected by Processor MMIO Stale Data vulnerabilities */
-#define X86_BUG_MMIO_UNKNOWN X86_BUG(26) /* "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */
+/* unused, was #define X86_BUG_MMIO_UNKNOWN X86_BUG(26) "mmio_unknown" CPU is too old and its MMIO Stale Data status is unknown */
#define X86_BUG_RETBLEED X86_BUG(27) /* "retbleed" CPU is affected by RETBleed */
#define X86_BUG_EIBRS_PBRSB X86_BUG(28) /* "eibrs_pbrsb" EIBRS is vulnerable to Post Barrier RSB Predictions */
#define X86_BUG_SMT_RSB X86_BUG(29) /* "smt_rsb" CPU is vulnerable to Cross-Thread Return Address Predictions */
@@ -528,12 +541,14 @@
#define X86_BUG_TDX_PW_MCE X86_BUG(31) /* "tdx_pw_mce" CPU may incur #MC if non-TD software does partial write to TDX private memory */
/* BUG word 2 */
-#define X86_BUG_SRSO X86_BUG(1*32 + 0) /* "srso" AMD SRSO bug */
-#define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* "div0" AMD DIV0 speculation bug */
-#define X86_BUG_RFDS X86_BUG(1*32 + 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
-#define X86_BUG_BHI X86_BUG(1*32 + 3) /* "bhi" CPU is affected by Branch History Injection */
-#define X86_BUG_IBPB_NO_RET X86_BUG(1*32 + 4) /* "ibpb_no_ret" IBPB omits return target predictions */
-#define X86_BUG_SPECTRE_V2_USER X86_BUG(1*32 + 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
-#define X86_BUG_ITS X86_BUG(1*32 + 6) /* "its" CPU is affected by Indirect Target Selection */
-#define X86_BUG_ITS_NATIVE_ONLY X86_BUG(1*32 + 7) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
+#define X86_BUG_SRSO X86_BUG( 1*32+ 0) /* "srso" AMD SRSO bug */
+#define X86_BUG_DIV0 X86_BUG( 1*32+ 1) /* "div0" AMD DIV0 speculation bug */
+#define X86_BUG_RFDS X86_BUG( 1*32+ 2) /* "rfds" CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI X86_BUG( 1*32+ 3) /* "bhi" CPU is affected by Branch History Injection */
+#define X86_BUG_IBPB_NO_RET X86_BUG( 1*32+ 4) /* "ibpb_no_ret" IBPB omits return target predictions */
+#define X86_BUG_SPECTRE_V2_USER X86_BUG( 1*32+ 5) /* "spectre_v2_user" CPU is affected by Spectre variant 2 attack between user processes */
+#define X86_BUG_OLD_MICROCODE X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
+#define X86_BUG_ITS X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
+#define X86_BUG_ITS_NATIVE_ONLY X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
+#define X86_BUG_TSA X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
#endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/cpuid/api.h b/arch/x86/include/asm/cpuid/api.h
index 9c180c9cc58e..44fa82e1267c 100644
--- a/arch/x86/include/asm/cpuid/api.h
+++ b/arch/x86/include/asm/cpuid/api.h
@@ -14,9 +14,9 @@
*/
#ifdef CONFIG_X86_32
-bool have_cpuid_p(void);
+bool cpuid_feature(void);
#else
-static inline bool have_cpuid_p(void)
+static inline bool cpuid_feature(void)
{
return true;
}
@@ -36,9 +36,9 @@ static inline void native_cpuid(u32 *eax, u32 *ebx,
}
#define NATIVE_CPUID_REG(reg) \
-static inline u32 native_cpuid_##reg(u32 op) \
+static inline u32 native_cpuid_##reg(u32 op) \
{ \
- u32 eax = op, ebx, ecx = 0, edx; \
+ u32 eax = op, ebx, ecx = 0, edx; \
\
native_cpuid(&eax, &ebx, &ecx, &edx); \
\
@@ -160,6 +160,10 @@ static inline void __cpuid_read_reg(u32 leaf, u32 subleaf,
__cpuid_read_reg(leaf, 0, regidx, (u32 *)(reg)); \
}
+/*
+ * Hypervisor-related APIs:
+ */
+
static __always_inline bool cpuid_function_is_indexed(u32 function)
{
switch (function) {
@@ -184,14 +188,14 @@ static __always_inline bool cpuid_function_is_indexed(u32 function)
return false;
}
-#define for_each_possible_hypervisor_cpuid_base(function) \
+#define for_each_possible_cpuid_base_hypervisor(function) \
for (function = 0x40000000; function < 0x40010000; function += 0x100)
-static inline u32 hypervisor_cpuid_base(const char *sig, u32 leaves)
+static inline u32 cpuid_base_hypervisor(const char *sig, u32 leaves)
{
u32 base, eax, signature[3];
- for_each_possible_hypervisor_cpuid_base(base) {
+ for_each_possible_cpuid_base_hypervisor(base) {
cpuid(base, &eax, &signature[0], &signature[1], &signature[2]);
/*
@@ -207,4 +211,82 @@ static inline u32 hypervisor_cpuid_base(const char *sig, u32 leaves)
return 0;
}
+/*
+ * CPUID(0x2) parsing:
+ */
+
+/**
+ * cpuid_leaf_0x2() - Return sanitized CPUID(0x2) register output
+ * @regs: Output parameter
+ *
+ * Query CPUID(0x2) and store its output in @regs. Force set any
+ * invalid 1-byte descriptor returned by the hardware to zero (the NULL
+ * cache/TLB descriptor) before returning it to the caller.
+ *
+ * Use for_each_cpuid_0x2_desc() to iterate over the register output in
+ * parsed form.
+ */
+static inline void cpuid_leaf_0x2(union leaf_0x2_regs *regs)
+{
+ cpuid_leaf(0x2, regs);
+
+ /*
+ * All Intel CPUs must report an iteration count of 1. In case
+ * of bogus hardware, treat all returned descriptors as NULL.
+ */
+ if (regs->desc[0] != 0x01) {
+ for (int i = 0; i < 4; i++)
+ regs->regv[i] = 0;
+ return;
+ }
+
+ /*
+ * The most significant bit (MSB) of each register must be clear.
+ * If a register is invalid, replace its descriptors with NULL.
+ */
+ for (int i = 0; i < 4; i++) {
+ if (regs->reg[i].invalid)
+ regs->regv[i] = 0;
+ }
+}
+
+/**
+ * for_each_cpuid_0x2_desc() - Iterator for parsed CPUID(0x2) descriptors
+ * @_regs: CPUID(0x2) register output, as returned by cpuid_leaf_0x2()
+ * @_ptr: u8 pointer, for macro internal use only
+ * @_desc: Pointer to the parsed CPUID(0x2) descriptor at each iteration
+ *
+ * Loop over the 1-byte descriptors in the passed CPUID(0x2) output registers
+ * @_regs. Provide the parsed information for each descriptor through @_desc.
+ *
+ * To handle cache-specific descriptors, switch on @_desc->c_type. For TLB
+ * descriptors, switch on @_desc->t_type.
+ *
+ * Example usage for cache descriptors::
+ *
+ * const struct leaf_0x2_table *desc;
+ * union leaf_0x2_regs regs;
+ * u8 *ptr;
+ *
+ * cpuid_leaf_0x2(&regs);
+ * for_each_cpuid_0x2_desc(regs, ptr, desc) {
+ * switch (desc->c_type) {
+ * ...
+ * }
+ * }
+ */
+#define for_each_cpuid_0x2_desc(_regs, _ptr, _desc) \
+ for (_ptr = &(_regs).desc[1]; \
+ _ptr < &(_regs).desc[16] && (_desc = &cpuid_0x2_table[*_ptr]); \
+ _ptr++)
+
+/*
+ * CPUID(0x80000006) parsing:
+ */
+
+static inline bool cpuid_amd_hygon_has_l3_cache(void)
+{
+ return cpuid_edx(0x80000006);
+}
+
#endif /* _ASM_X86_CPUID_API_H */
diff --git a/arch/x86/include/asm/cpuid/types.h b/arch/x86/include/asm/cpuid/types.h
index 8582e27e836d..8a00364b79de 100644
--- a/arch/x86/include/asm/cpuid/types.h
+++ b/arch/x86/include/asm/cpuid/types.h
@@ -2,6 +2,7 @@
#ifndef _ASM_X86_CPUID_TYPES_H
#define _ASM_X86_CPUID_TYPES_H
+#include <linux/build_bug.h>
#include <linux/types.h>
/*
@@ -29,4 +30,98 @@ enum cpuid_regs_idx {
#define CPUID_LEAF_FREQ 0x16
#define CPUID_LEAF_TILE 0x1d
+/*
+ * Types for CPUID(0x2) parsing:
+ */
+
+struct leaf_0x2_reg {
+ u32 : 31,
+ invalid : 1;
+};
+
+union leaf_0x2_regs {
+ struct leaf_0x2_reg reg[4];
+ u32 regv[4];
+ u8 desc[16];
+};
+
+/*
+ * Leaf 0x2 1-byte descriptors' cache types
+ * To be used for their mappings at cpuid_0x2_table[]
+ *
+ * Start at 1 since type 0 is reserved for HW byte descriptors which are
+ * not recognized by the kernel; i.e., those without an explicit mapping.
+ */
+enum _cache_table_type {
+ CACHE_L1_INST = 1,
+ CACHE_L1_DATA,
+ CACHE_L2,
+ CACHE_L3
+ /* Adjust __TLB_TABLE_TYPE_BEGIN before adding more types */
+} __packed;
+#ifndef __CHECKER__
+static_assert(sizeof(enum _cache_table_type) == 1);
+#endif
+
+/*
+ * Ensure that leaf 0x2 cache and TLB type values do not intersect,
+ * since they share the same type field at struct cpuid_0x2_table.
+ */
+#define __TLB_TABLE_TYPE_BEGIN (CACHE_L3 + 1)
+
+/*
+ * Leaf 0x2 1-byte descriptors' TLB types
+ * To be used for their mappings at cpuid_0x2_table[]
+ */
+enum _tlb_table_type {
+ TLB_INST_4K = __TLB_TABLE_TYPE_BEGIN,
+ TLB_INST_4M,
+ TLB_INST_2M_4M,
+ TLB_INST_ALL,
+
+ TLB_DATA_4K,
+ TLB_DATA_4M,
+ TLB_DATA_2M_4M,
+ TLB_DATA_4K_4M,
+ TLB_DATA_1G,
+ TLB_DATA_1G_2M_4M,
+
+ TLB_DATA0_4K,
+ TLB_DATA0_4M,
+ TLB_DATA0_2M_4M,
+
+ STLB_4K,
+ STLB_4K_2M,
+} __packed;
+#ifndef __CHECKER__
+static_assert(sizeof(enum _tlb_table_type) == 1);
+#endif
+
+/*
+ * Combined parsing table for leaf 0x2 cache and TLB descriptors.
+ */
+
+struct leaf_0x2_table {
+ union {
+ enum _cache_table_type c_type;
+ enum _tlb_table_type t_type;
+ };
+ union {
+ short c_size;
+ short entries;
+ };
+};
+
+extern const struct leaf_0x2_table cpuid_0x2_table[256];
+
+/*
+ * All of leaf 0x2's one-byte TLB descriptors implies the same number of entries
+ * for their respective TLB types. TLB descriptor 0x63 is an exception: it
+ * implies 4 dTLB entries for 1GB pages and 32 dTLB entries for 2MB or 4MB pages.
+ *
+ * Encode that descriptor's dTLB entry count for 2MB/4MB pages here, as the entry
+ * count for dTLB 1GB pages is already encoded at the cpuid_0x2_table[]'s mapping.
+ */
+#define TLB_0x63_2M_4M_ENTRIES 32
+
#endif /* _ASM_X86_CPUID_TYPES_H */
diff --git a/arch/x86/include/asm/debugreg.h b/arch/x86/include/asm/debugreg.h
index fdbbbfec745a..a2c1f2d24b64 100644
--- a/arch/x86/include/asm/debugreg.h
+++ b/arch/x86/include/asm/debugreg.h
@@ -9,6 +9,14 @@
#include <asm/cpufeature.h>
#include <asm/msr.h>
+/*
+ * Define bits that are always set to 1 in DR7, only bit 10 is
+ * architecturally reserved to '1'.
+ *
+ * This is also the init/reset value for DR7.
+ */
+#define DR7_FIXED_1 0x00000400
+
DECLARE_PER_CPU(unsigned long, cpu_dr7);
#ifndef CONFIG_PARAVIRT_XXL
@@ -23,7 +31,7 @@ DECLARE_PER_CPU(unsigned long, cpu_dr7);
static __always_inline unsigned long native_get_debugreg(int regno)
{
- unsigned long val = 0; /* Damn you, gcc! */
+ unsigned long val;
switch (regno) {
case 0:
@@ -43,7 +51,7 @@ static __always_inline unsigned long native_get_debugreg(int regno)
break;
case 7:
/*
- * Apply __FORCE_ORDER to DR7 reads to forbid re-ordering them
+ * Use "asm volatile" for DR7 reads to forbid re-ordering them
* with other code.
*
* This is needed because a DR7 access can cause a #VC exception
@@ -55,7 +63,7 @@ static __always_inline unsigned long native_get_debugreg(int regno)
* re-ordered to happen before the call to sev_es_ist_enter(),
* causing stack recursion.
*/
- asm volatile("mov %%db7, %0" : "=r" (val) : __FORCE_ORDER);
+ asm volatile("mov %%db7, %0" : "=r" (val));
break;
default:
BUG();
@@ -83,15 +91,15 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value)
break;
case 7:
/*
- * Apply __FORCE_ORDER to DR7 writes to forbid re-ordering them
+ * Use "asm volatile" for DR7 writes to forbid re-ordering them
* with other code.
*
* While is didn't happen with a DR7 write (see the DR7 read
* comment above which explains where it happened), add the
- * __FORCE_ORDER here too to avoid similar problems in the
+ * "asm volatile" here too to avoid similar problems in the
* future.
*/
- asm volatile("mov %0, %%db7" ::"r" (value), __FORCE_ORDER);
+ asm volatile("mov %0, %%db7" ::"r" (value));
break;
default:
BUG();
@@ -100,8 +108,8 @@ static __always_inline void native_set_debugreg(int regno, unsigned long value)
static inline void hw_breakpoint_disable(void)
{
- /* Zero the control register for HW Breakpoint */
- set_debugreg(0UL, 7);
+ /* Reset the control register for HW Breakpoint */
+ set_debugreg(DR7_FIXED_1, 7);
/* Zero-out the individual HW breakpoint address registers */
set_debugreg(0UL, 0);
@@ -125,9 +133,12 @@ static __always_inline unsigned long local_db_save(void)
return 0;
get_debugreg(dr7, 7);
- dr7 &= ~0x400; /* architecturally set bit */
+
+ /* Architecturally set bit */
+ dr7 &= ~DR7_FIXED_1;
if (dr7)
- set_debugreg(0, 7);
+ set_debugreg(DR7_FIXED_1, 7);
+
/*
* Ensure the compiler doesn't lower the above statements into
* the critical section; disabling breakpoints late would not
@@ -169,7 +180,7 @@ static inline unsigned long get_debugctlmsr(void)
if (boot_cpu_data.x86 < 6)
return 0;
#endif
- rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+ rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
return debugctlmsr;
}
@@ -180,7 +191,7 @@ static inline void update_debugctlmsr(unsigned long debugctlmsr)
if (boot_cpu_data.x86 < 6)
return;
#endif
- wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
+ wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctlmsr);
}
#endif /* _ASM_X86_DEBUGREG_H */
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 128602612eca..6c8fdc96be7e 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -76,12 +76,8 @@ typedef struct user_i387_struct elf_fpregset_t;
#include <asm/vdso.h>
-#ifdef CONFIG_X86_64
extern unsigned int vdso64_enabled;
-#endif
-#if defined(CONFIG_X86_32) || defined(CONFIG_IA32_EMULATION)
extern unsigned int vdso32_enabled;
-#endif
/*
* This is used to ensure we don't load something for the wrong architecture.
diff --git a/arch/x86/include/asm/entry-common.h b/arch/x86/include/asm/entry-common.h
index 77d20555e04d..d535a97c7284 100644
--- a/arch/x86/include/asm/entry-common.h
+++ b/arch/x86/include/asm/entry-common.h
@@ -53,7 +53,6 @@ static inline void arch_exit_work(unsigned long ti_work)
if (unlikely(ti_work & _TIF_IO_BITMAP))
tss_update_io_bitmap();
- fpregs_assert_state_consistent();
if (unlikely(ti_work & _TIF_NEED_FPU_LOAD))
switch_fpu_return();
}
@@ -61,7 +60,9 @@ static inline void arch_exit_work(unsigned long ti_work)
static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
unsigned long ti_work)
{
- if (IS_ENABLED(CONFIG_X86_DEBUG_FPU) || unlikely(ti_work))
+ fpregs_assert_state_consistent();
+
+ if (unlikely(ti_work))
arch_exit_work(ti_work);
fred_update_rsp0();
diff --git a/arch/x86/include/asm/fpu/api.h b/arch/x86/include/asm/fpu/api.h
index f42de5f05e7e..cd6f194a912b 100644
--- a/arch/x86/include/asm/fpu/api.h
+++ b/arch/x86/include/asm/fpu/api.h
@@ -126,6 +126,7 @@ static inline void fpstate_init_soft(struct swregs_state *soft) {}
#endif
/* State tracking */
+DECLARE_PER_CPU(bool, kernel_fpu_allowed);
DECLARE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
/* Process cleanup */
@@ -136,7 +137,7 @@ static inline void fpstate_free(struct fpu *fpu) { }
#endif
/* fpstate-related functions which are exported to KVM */
-extern void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature);
+extern void fpstate_clear_xstate_component(struct fpstate *fpstate, unsigned int xfeature);
extern u64 xstate_get_guest_group_perm(void);
diff --git a/arch/x86/include/asm/fpu/sched.h b/arch/x86/include/asm/fpu/sched.h
index c485f1944c5f..c060549c6c94 100644
--- a/arch/x86/include/asm/fpu/sched.h
+++ b/arch/x86/include/asm/fpu/sched.h
@@ -10,7 +10,7 @@
#include <asm/trace/fpu.h>
extern void save_fpregs_to_fpstate(struct fpu *fpu);
-extern void fpu__drop(struct fpu *fpu);
+extern void fpu__drop(struct task_struct *tsk);
extern int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
unsigned long shstk_addr);
extern void fpu_flush_thread(void);
@@ -18,31 +18,25 @@ extern void fpu_flush_thread(void);
/*
* FPU state switching for scheduling.
*
- * This is a two-stage process:
+ * switch_fpu() saves the old state and sets TIF_NEED_FPU_LOAD if
+ * TIF_NEED_FPU_LOAD is not set. This is done within the context
+ * of the old process.
*
- * - switch_fpu_prepare() saves the old state.
- * This is done within the context of the old process.
- *
- * - switch_fpu_finish() sets TIF_NEED_FPU_LOAD; the floating point state
- * will get loaded on return to userspace, or when the kernel needs it.
- *
- * If TIF_NEED_FPU_LOAD is cleared then the CPU's FPU registers
- * are saved in the current thread's FPU register state.
- *
- * If TIF_NEED_FPU_LOAD is set then CPU's FPU registers may not
- * hold current()'s FPU registers. It is required to load the
+ * Once TIF_NEED_FPU_LOAD is set, it is required to load the
* registers before returning to userland or using the content
* otherwise.
*
* The FPU context is only stored/restored for a user task and
* PF_KTHREAD is used to distinguish between kernel and user threads.
*/
-static inline void switch_fpu_prepare(struct task_struct *old, int cpu)
+static inline void switch_fpu(struct task_struct *old, int cpu)
{
- if (cpu_feature_enabled(X86_FEATURE_FPU) &&
+ if (!test_tsk_thread_flag(old, TIF_NEED_FPU_LOAD) &&
+ cpu_feature_enabled(X86_FEATURE_FPU) &&
!(old->flags & (PF_KTHREAD | PF_USER_WORKER))) {
- struct fpu *old_fpu = &old->thread.fpu;
+ struct fpu *old_fpu = x86_task_fpu(old);
+ set_tsk_thread_flag(old, TIF_NEED_FPU_LOAD);
save_fpregs_to_fpstate(old_fpu);
/*
* The save operation preserved register state, so the
@@ -50,7 +44,7 @@ static inline void switch_fpu_prepare(struct task_struct *old, int cpu)
* current CPU number in @old_fpu, so the next return
* to user space can avoid the FPU register restore
* when is returns on the same CPU and still owns the
- * context.
+ * context. See fpregs_restore_userregs().
*/
old_fpu->last_cpu = cpu;
@@ -58,14 +52,4 @@ static inline void switch_fpu_prepare(struct task_struct *old, int cpu)
}
}
-/*
- * Delay loading of the complete FPU state until the return to userland.
- * PKRU is handled separately.
- */
-static inline void switch_fpu_finish(struct task_struct *new)
-{
- if (cpu_feature_enabled(X86_FEATURE_FPU))
- set_tsk_thread_flag(new, TIF_NEED_FPU_LOAD);
-}
-
#endif /* _ASM_X86_FPU_SCHED_H */
diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
index de16862bf230..93e99d2583d6 100644
--- a/arch/x86/include/asm/fpu/types.h
+++ b/arch/x86/include/asm/fpu/types.h
@@ -118,13 +118,14 @@ enum xfeature {
XFEATURE_PKRU,
XFEATURE_PASID,
XFEATURE_CET_USER,
- XFEATURE_CET_KERNEL_UNUSED,
+ XFEATURE_CET_KERNEL,
XFEATURE_RSRVD_COMP_13,
XFEATURE_RSRVD_COMP_14,
XFEATURE_LBR,
XFEATURE_RSRVD_COMP_16,
XFEATURE_XTILE_CFG,
XFEATURE_XTILE_DATA,
+ XFEATURE_APX,
XFEATURE_MAX,
};
@@ -141,10 +142,11 @@ enum xfeature {
#define XFEATURE_MASK_PKRU (1 << XFEATURE_PKRU)
#define XFEATURE_MASK_PASID (1 << XFEATURE_PASID)
#define XFEATURE_MASK_CET_USER (1 << XFEATURE_CET_USER)
-#define XFEATURE_MASK_CET_KERNEL (1 << XFEATURE_CET_KERNEL_UNUSED)
+#define XFEATURE_MASK_CET_KERNEL (1 << XFEATURE_CET_KERNEL)
#define XFEATURE_MASK_LBR (1 << XFEATURE_LBR)
#define XFEATURE_MASK_XTILE_CFG (1 << XFEATURE_XTILE_CFG)
#define XFEATURE_MASK_XTILE_DATA (1 << XFEATURE_XTILE_DATA)
+#define XFEATURE_MASK_APX (1 << XFEATURE_APX)
#define XFEATURE_MASK_FPSSE (XFEATURE_MASK_FP | XFEATURE_MASK_SSE)
#define XFEATURE_MASK_AVX512 (XFEATURE_MASK_OPMASK \
@@ -267,6 +269,16 @@ struct cet_user_state {
};
/*
+ * State component 12 is Control-flow Enforcement supervisor states.
+ * This state includes SSP pointers for privilege levels 0 through 2.
+ */
+struct cet_supervisor_state {
+ u64 pl0_ssp;
+ u64 pl1_ssp;
+ u64 pl2_ssp;
+} __packed;
+
+/*
* State component 15: Architectural LBR configuration state.
* The size of Arch LBR state depends on the number of LBRs (lbr_depth).
*/
@@ -304,6 +316,13 @@ struct xtile_data {
} __packed;
/*
+ * State component 19: 8B extended general purpose register.
+ */
+struct apx_state {
+ u64 egpr[16];
+} __packed;
+
+/*
* State component 10 is supervisor state used for context-switching the
* PASID state.
*/
@@ -407,9 +426,11 @@ struct fpu_state_perm {
/*
* @__state_perm:
*
- * This bitmap indicates the permission for state components, which
- * are available to a thread group. The permission prctl() sets the
- * enabled state bits in thread_group_leader()->thread.fpu.
+ * This bitmap indicates the permission for state components
+ * available to a thread group, including both user and supervisor
+ * components and software-defined bits like FPU_GUEST_PERM_LOCKED.
+ * The permission prctl() sets the enabled state bits in
+ * thread_group_leader()->thread.fpu.
*
* All run time operations use the per thread information in the
* currently active fpu.fpstate which contains the xfeature masks
@@ -525,13 +546,6 @@ struct fpu_guest {
u64 xfeatures;
/*
- * @perm: xfeature bitmap of features which are
- * permitted to be enabled for the guest
- * vCPU.
- */
- u64 perm;
-
- /*
* @xfd_err: Save the guest value.
*/
u64 xfd_err;
@@ -548,6 +562,31 @@ struct fpu_guest {
};
/*
+ * FPU state configuration data for fpu_guest.
+ * Initialized at boot time. Read only after init.
+ */
+struct vcpu_fpu_config {
+ /*
+ * @size:
+ *
+ * The default size of the register state buffer in guest FPUs.
+ * Includes all supported features except independent managed
+ * features and features which have to be requested by user space
+ * before usage.
+ */
+ unsigned int size;
+
+ /*
+ * @features:
+ *
+ * The default supported features bitmap in guest FPUs. Does not
+ * include independent managed features and features which have to
+ * be requested by user space before usage.
+ */
+ u64 features;
+};
+
+/*
* FPU state configuration data. Initialized at boot time. Read only after init.
*/
struct fpu_state_config {
@@ -563,8 +602,9 @@ struct fpu_state_config {
* @default_size:
*
* The default size of the register state buffer. Includes all
- * supported features except independent managed features and
- * features which have to be requested by user space before usage.
+ * supported features except independent managed features,
+ * guest-only features and features which have to be requested by
+ * user space before usage.
*/
unsigned int default_size;
@@ -580,8 +620,8 @@ struct fpu_state_config {
* @default_features:
*
* The default supported features bitmap. Does not include
- * independent managed features and features which have to
- * be requested by user space before usage.
+ * independent managed features, guest-only features and features
+ * which have to be requested by user space before usage.
*/
u64 default_features;
/*
@@ -602,5 +642,6 @@ struct fpu_state_config {
/* FPU state configuration information */
extern struct fpu_state_config fpu_kernel_cfg, fpu_user_cfg;
+extern struct vcpu_fpu_config guest_default_cfg;
#endif /* _ASM_X86_FPU_TYPES_H */
diff --git a/arch/x86/include/asm/fpu/xstate.h b/arch/x86/include/asm/fpu/xstate.h
index 7f39fe7980c5..7a7dc9d56027 100644
--- a/arch/x86/include/asm/fpu/xstate.h
+++ b/arch/x86/include/asm/fpu/xstate.h
@@ -32,7 +32,8 @@
XFEATURE_MASK_PKRU | \
XFEATURE_MASK_BNDREGS | \
XFEATURE_MASK_BNDCSR | \
- XFEATURE_MASK_XTILE)
+ XFEATURE_MASK_XTILE | \
+ XFEATURE_MASK_APX)
/*
* Features which are restored when returning to user space.
@@ -45,9 +46,13 @@
/* Features which are dynamically enabled for a process on request */
#define XFEATURE_MASK_USER_DYNAMIC XFEATURE_MASK_XTILE_DATA
+/* Supervisor features which are enabled only in guest FPUs */
+#define XFEATURE_MASK_GUEST_SUPERVISOR XFEATURE_MASK_CET_KERNEL
+
/* All currently supported supervisor features */
#define XFEATURE_MASK_SUPERVISOR_SUPPORTED (XFEATURE_MASK_PASID | \
- XFEATURE_MASK_CET_USER)
+ XFEATURE_MASK_CET_USER | \
+ XFEATURE_MASK_GUEST_SUPERVISOR)
/*
* A supervisor state component may not always contain valuable information,
@@ -74,8 +79,7 @@
* Unsupported supervisor features. When a supervisor feature in this mask is
* supported in the future, move it to the supported supervisor feature mask.
*/
-#define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT | \
- XFEATURE_MASK_CET_KERNEL)
+#define XFEATURE_MASK_SUPERVISOR_UNSUPPORTED (XFEATURE_MASK_PT)
/* All supervisor states including supported and unsupported states. */
#define XFEATURE_MASK_SUPERVISOR_ALL (XFEATURE_MASK_SUPERVISOR_SUPPORTED | \
diff --git a/arch/x86/include/asm/fred.h b/arch/x86/include/asm/fred.h
index 2a29e5216881..12b34d5b2953 100644
--- a/arch/x86/include/asm/fred.h
+++ b/arch/x86/include/asm/fred.h
@@ -9,6 +9,7 @@
#include <linux/const.h>
#include <asm/asm.h>
+#include <asm/msr.h>
#include <asm/trapnr.h>
/*
diff --git a/arch/x86/include/asm/fsgsbase.h b/arch/x86/include/asm/fsgsbase.h
index 02f239569b93..ab2547f97c2c 100644
--- a/arch/x86/include/asm/fsgsbase.h
+++ b/arch/x86/include/asm/fsgsbase.h
@@ -60,7 +60,7 @@ static inline unsigned long x86_fsbase_read_cpu(void)
if (boot_cpu_has(X86_FEATURE_FSGSBASE))
fsbase = rdfsbase();
else
- rdmsrl(MSR_FS_BASE, fsbase);
+ rdmsrq(MSR_FS_BASE, fsbase);
return fsbase;
}
@@ -70,7 +70,7 @@ static inline void x86_fsbase_write_cpu(unsigned long fsbase)
if (boot_cpu_has(X86_FEATURE_FSGSBASE))
wrfsbase(fsbase);
else
- wrmsrl(MSR_FS_BASE, fsbase);
+ wrmsrq(MSR_FS_BASE, fsbase);
}
extern unsigned long x86_gsbase_read_cpu_inactive(void);
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 162ebd73a698..cbe19e669080 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -92,8 +92,6 @@ struct irq_cfg {
extern struct irq_cfg *irq_cfg(unsigned int irq);
extern struct irq_cfg *irqd_cfg(struct irq_data *irq_data);
-extern void lock_vector_lock(void);
-extern void unlock_vector_lock(void);
#ifdef CONFIG_SMP
extern void vector_schedule_cleanup(struct irq_cfg *);
extern void irq_complete_move(struct irq_cfg *cfg);
@@ -101,12 +99,16 @@ extern void irq_complete_move(struct irq_cfg *cfg);
static inline void vector_schedule_cleanup(struct irq_cfg *c) { }
static inline void irq_complete_move(struct irq_cfg *c) { }
#endif
-
extern void apic_ack_edge(struct irq_data *data);
-#else /* CONFIG_IRQ_DOMAIN_HIERARCHY */
+#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */
+
+#ifdef CONFIG_X86_LOCAL_APIC
+extern void lock_vector_lock(void);
+extern void unlock_vector_lock(void);
+#else
static inline void lock_vector_lock(void) {}
static inline void unlock_vector_lock(void) {}
-#endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */
+#endif
/* Statistics */
extern atomic_t irq_err_count;
diff --git a/arch/x86/include/asm/inat.h b/arch/x86/include/asm/inat.h
index 53e4015242b4..97f341777db5 100644
--- a/arch/x86/include/asm/inat.h
+++ b/arch/x86/include/asm/inat.h
@@ -82,6 +82,7 @@
#define INAT_NO_REX2 (1 << (INAT_FLAG_OFFS + 8))
#define INAT_REX2_VARIANT (1 << (INAT_FLAG_OFFS + 9))
#define INAT_EVEX_SCALABLE (1 << (INAT_FLAG_OFFS + 10))
+#define INAT_INV64 (1 << (INAT_FLAG_OFFS + 11))
/* Attribute making macros for attribute tables */
#define INAT_MAKE_PREFIX(pfx) (pfx << INAT_PFX_OFFS)
#define INAT_MAKE_ESCAPE(esc) (esc << INAT_ESC_OFFS)
@@ -242,4 +243,9 @@ static inline int inat_evex_scalable(insn_attr_t attr)
{
return attr & INAT_EVEX_SCALABLE;
}
+
+static inline int inat_is_invalid64(insn_attr_t attr)
+{
+ return attr & INAT_INV64;
+}
#endif
diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 8b1b1abcef15..5a68e9db6518 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -5,7 +5,7 @@
#if defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 170000
#define __head __section(".head.text") __no_sanitize_undefined __no_stack_protector
#else
-#define __head __section(".head.text") __no_sanitize_undefined
+#define __head __section(".head.text") __no_sanitize_undefined __no_kstack_erase
#endif
struct x86_mapping_info {
diff --git a/arch/x86/include/asm/intel-family.h b/arch/x86/include/asm/intel-family.h
index be10c188614f..e345dbdf933e 100644
--- a/arch/x86/include/asm/intel-family.h
+++ b/arch/x86/include/asm/intel-family.h
@@ -150,6 +150,11 @@
#define INTEL_PANTHERLAKE_L IFM(6, 0xCC) /* Cougar Cove / Crestmont */
+#define INTEL_WILDCATLAKE_L IFM(6, 0xD5)
+
+#define INTEL_NOVALAKE IFM(18, 0x01)
+#define INTEL_NOVALAKE_L IFM(18, 0x03)
+
/* "Small Core" Processors (Atom/E-Core) */
#define INTEL_ATOM_BONNELL IFM(6, 0x1C) /* Diamondville, Pineview */
diff --git a/arch/x86/include/asm/intel_telemetry.h b/arch/x86/include/asm/intel_telemetry.h
index 43b7657febca..944637a4e6de 100644
--- a/arch/x86/include/asm/intel_telemetry.h
+++ b/arch/x86/include/asm/intel_telemetry.h
@@ -59,18 +59,6 @@ struct telemetry_plt_config {
};
struct telemetry_core_ops {
- int (*get_sampling_period)(u8 *pss_min_period, u8 *pss_max_period,
- u8 *ioss_min_period, u8 *ioss_max_period);
-
- int (*get_eventconfig)(struct telemetry_evtconfig *pss_evtconfig,
- struct telemetry_evtconfig *ioss_evtconfig,
- int pss_len, int ioss_len);
-
- int (*update_events)(struct telemetry_evtconfig pss_evtconfig,
- struct telemetry_evtconfig ioss_evtconfig);
-
- int (*set_sampling_period)(u8 pss_period, u8 ioss_period);
-
int (*get_trace_verbosity)(enum telemetry_unit telem_unit,
u32 *verbosity);
@@ -84,11 +72,6 @@ struct telemetry_core_ops {
int (*read_eventlog)(enum telemetry_unit telem_unit,
struct telemetry_evtlog *evtlog,
int len, int log_all_evts);
-
- int (*add_events)(u8 num_pss_evts, u8 num_ioss_evts,
- u32 *pss_evtmap, u32 *ioss_evtmap);
-
- int (*reset_events)(void);
};
int telemetry_set_pltdata(const struct telemetry_core_ops *ops,
@@ -101,35 +84,15 @@ struct telemetry_plt_config *telemetry_get_pltdata(void);
int telemetry_get_evtname(enum telemetry_unit telem_unit,
const char **name, int len);
-int telemetry_update_events(struct telemetry_evtconfig pss_evtconfig,
- struct telemetry_evtconfig ioss_evtconfig);
-
-int telemetry_add_events(u8 num_pss_evts, u8 num_ioss_evts,
- u32 *pss_evtmap, u32 *ioss_evtmap);
-
-int telemetry_reset_events(void);
-
-int telemetry_get_eventconfig(struct telemetry_evtconfig *pss_config,
- struct telemetry_evtconfig *ioss_config,
- int pss_len, int ioss_len);
-
int telemetry_read_events(enum telemetry_unit telem_unit,
struct telemetry_evtlog *evtlog, int len);
-int telemetry_raw_read_events(enum telemetry_unit telem_unit,
- struct telemetry_evtlog *evtlog, int len);
-
int telemetry_read_eventlog(enum telemetry_unit telem_unit,
struct telemetry_evtlog *evtlog, int len);
int telemetry_raw_read_eventlog(enum telemetry_unit telem_unit,
struct telemetry_evtlog *evtlog, int len);
-int telemetry_get_sampling_period(u8 *pss_min_period, u8 *pss_max_period,
- u8 *ioss_min_period, u8 *ioss_max_period);
-
-int telemetry_set_sampling_period(u8 pss_period, u8 ioss_period);
-
int telemetry_set_trace_verbosity(enum telemetry_unit telem_unit,
u32 verbosity);
diff --git a/arch/x86/include/asm/io.h b/arch/x86/include/asm/io.h
index e889c3bab5a2..ca309a3227c7 100644
--- a/arch/x86/include/asm/io.h
+++ b/arch/x86/include/asm/io.h
@@ -217,7 +217,7 @@ void memset_io(volatile void __iomem *, int, size_t);
static inline void __iowrite32_copy(void __iomem *to, const void *from,
size_t count)
{
- asm volatile("rep ; movsl"
+ asm volatile("rep movsl"
: "=&c"(count), "=&D"(to), "=&S"(from)
: "0"(count), "1"(to), "2"(from)
: "memory");
@@ -282,7 +282,7 @@ static inline void outs##bwl(u16 port, const void *addr, unsigned long count) \
count--; \
} \
} else { \
- asm volatile("rep; outs" #bwl \
+ asm volatile("rep outs" #bwl \
: "+S"(addr), "+c"(count) \
: "d"(port) : "memory"); \
} \
@@ -298,7 +298,7 @@ static inline void ins##bwl(u16 port, void *addr, unsigned long count) \
count--; \
} \
} else { \
- asm volatile("rep; ins" #bwl \
+ asm volatile("rep ins" #bwl \
: "+D"(addr), "+c"(count) \
: "d"(port) : "memory"); \
} \
diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 5036f13ab69f..5a0d42464d44 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -26,7 +26,22 @@ enum {
IRQ_REMAP_X2APIC_MODE,
};
-struct vcpu_data {
+/*
+ * This is mainly used to communicate information back-and-forth
+ * between SVM and IOMMU for setting up and tearing down posted
+ * interrupt
+ */
+struct amd_iommu_pi_data {
+ u64 vapic_addr; /* Physical address of the vCPU's vAPIC. */
+ u32 ga_tag;
+ u32 vector; /* Guest vector of the interrupt */
+ int cpu;
+ bool ga_log_intr;
+ bool is_guest_mode;
+ void *ir_data;
+};
+
+struct intel_iommu_pi_data {
u64 pi_desc_addr; /* Physical address of PI Descriptor */
u32 vector; /* Guest vector of the interrupt */
};
diff --git a/arch/x86/include/asm/irqflags.h b/arch/x86/include/asm/irqflags.h
index 9a9b21b78905..b30e5474c18e 100644
--- a/arch/x86/include/asm/irqflags.h
+++ b/arch/x86/include/asm/irqflags.h
@@ -44,13 +44,13 @@ static __always_inline void native_irq_enable(void)
static __always_inline void native_safe_halt(void)
{
- mds_idle_clear_cpu_buffers();
+ x86_idle_clear_cpu_buffers();
asm volatile("sti; hlt": : :"memory");
}
static __always_inline void native_halt(void)
{
- mds_idle_clear_cpu_buffers();
+ x86_idle_clear_cpu_buffers();
asm volatile("hlt": : :"memory");
}
diff --git a/arch/x86/include/asm/kexec.h b/arch/x86/include/asm/kexec.h
index 5432457d2338..f2ad77929d6e 100644
--- a/arch/x86/include/asm/kexec.h
+++ b/arch/x86/include/asm/kexec.h
@@ -8,6 +8,9 @@
# define PA_PGD 2
# define PA_SWAP_PAGE 3
# define PAGES_NR 4
+#else
+/* Size of each exception handler referenced by the IDT */
+# define KEXEC_DEBUG_EXC_HANDLER_SIZE 6 /* PUSHI, PUSHI, 2-byte JMP */
#endif
# define KEXEC_CONTROL_PAGE_SIZE 4096
@@ -59,6 +62,10 @@ struct kimage;
extern unsigned long kexec_va_control_page;
extern unsigned long kexec_pa_table_page;
extern unsigned long kexec_pa_swap_page;
+extern gate_desc kexec_debug_idt[];
+extern unsigned char kexec_debug_exc_vectors[];
+extern uint16_t kexec_debug_8250_port;
+extern unsigned long kexec_debug_8250_mmio32;
#endif
/*
diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
index 823c0434bbad..18a5c3119e1a 100644
--- a/arch/x86/include/asm/kvm-x86-ops.h
+++ b/arch/x86/include/asm/kvm-x86-ops.h
@@ -21,6 +21,7 @@ KVM_X86_OP(has_emulated_msr)
KVM_X86_OP(vcpu_after_set_cpuid)
KVM_X86_OP(vm_init)
KVM_X86_OP_OPTIONAL(vm_destroy)
+KVM_X86_OP_OPTIONAL(vm_pre_destroy)
KVM_X86_OP_OPTIONAL_RET0(vcpu_precreate)
KVM_X86_OP(vcpu_create)
KVM_X86_OP(vcpu_free)
@@ -48,7 +49,6 @@ KVM_X86_OP(set_idt)
KVM_X86_OP(get_gdt)
KVM_X86_OP(set_gdt)
KVM_X86_OP(sync_dirty_debug_regs)
-KVM_X86_OP(set_dr6)
KVM_X86_OP(set_dr7)
KVM_X86_OP(cache_reg)
KVM_X86_OP(get_rflags)
@@ -111,10 +111,11 @@ KVM_X86_OP_OPTIONAL(update_cpu_dirty_logging)
KVM_X86_OP_OPTIONAL(vcpu_blocking)
KVM_X86_OP_OPTIONAL(vcpu_unblocking)
KVM_X86_OP_OPTIONAL(pi_update_irte)
-KVM_X86_OP_OPTIONAL(pi_start_assignment)
+KVM_X86_OP_OPTIONAL(pi_start_bypass)
KVM_X86_OP_OPTIONAL(apicv_pre_state_restore)
KVM_X86_OP_OPTIONAL(apicv_post_state_restore)
KVM_X86_OP_OPTIONAL_RET0(dy_apicv_has_pending_interrupt)
+KVM_X86_OP_OPTIONAL(protected_apic_has_interrupt)
KVM_X86_OP_OPTIONAL(set_hv_timer)
KVM_X86_OP_OPTIONAL(cancel_hv_timer)
KVM_X86_OP(setup_mce)
@@ -126,6 +127,7 @@ KVM_X86_OP(enable_smi_window)
#endif
KVM_X86_OP_OPTIONAL(dev_get_attr)
KVM_X86_OP_OPTIONAL(mem_enc_ioctl)
+KVM_X86_OP_OPTIONAL(vcpu_mem_enc_ioctl)
KVM_X86_OP_OPTIONAL(mem_enc_register_region)
KVM_X86_OP_OPTIONAL(mem_enc_unregister_region)
KVM_X86_OP_OPTIONAL(vm_copy_enc_context_from)
@@ -136,7 +138,7 @@ KVM_X86_OP(check_emulate_instruction)
KVM_X86_OP(apic_init_signal_blocked)
KVM_X86_OP_OPTIONAL(enable_l2_tlb_flush)
KVM_X86_OP_OPTIONAL(migrate_timers)
-KVM_X86_OP(msr_filter_changed)
+KVM_X86_OP(recalc_msr_intercepts)
KVM_X86_OP(complete_emulated_msr)
KVM_X86_OP(vcpu_deliver_sipi_vector)
KVM_X86_OP_OPTIONAL_RET0(vcpu_get_apicv_inhibit_reasons);
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7bc174a1f1cb..f19a76d3ca0e 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -31,9 +31,11 @@
#include <asm/apic.h>
#include <asm/pvclock-abi.h>
+#include <asm/debugreg.h>
#include <asm/desc.h>
#include <asm/mtrr.h>
#include <asm/msr-index.h>
+#include <asm/msr.h>
#include <asm/asm.h>
#include <asm/irq_remapping.h>
#include <asm/kvm_page_track.h>
@@ -125,7 +127,8 @@
KVM_ARCH_REQ_FLAGS(31, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
#define KVM_REQ_HV_TLB_FLUSH \
KVM_ARCH_REQ_FLAGS(32, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
-#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE KVM_ARCH_REQ(34)
+#define KVM_REQ_UPDATE_PROTECTED_GUEST_STATE \
+ KVM_ARCH_REQ_FLAGS(34, KVM_REQUEST_WAIT)
#define CR0_RESERVED_BITS \
(~(unsigned long)(X86_CR0_PE | X86_CR0_MP | X86_CR0_EM | X86_CR0_TS \
@@ -247,7 +250,6 @@ enum x86_intercept_stage;
#define DR7_BP_EN_MASK 0x000000ff
#define DR7_GE (1 << 9)
#define DR7_GD (1 << 13)
-#define DR7_FIXED_1 0x00000400
#define DR7_VOLATILE 0xffff2bff
#define KVM_GUESTDBG_VALID_MASK \
@@ -295,6 +297,7 @@ enum x86_intercept_stage;
*/
#define KVM_APIC_PV_EOI_PENDING 1
+struct kvm_kernel_irqfd;
struct kvm_kernel_irq_routing_entry;
/*
@@ -411,7 +414,6 @@ struct kvm_rmap_head {
};
struct kvm_pio_request {
- unsigned long linear_rip;
unsigned long count;
int in;
int port;
@@ -608,8 +610,15 @@ struct kvm_pmu {
struct kvm_pmu_ops;
enum {
- KVM_DEBUGREG_BP_ENABLED = 1,
- KVM_DEBUGREG_WONT_EXIT = 2,
+ KVM_DEBUGREG_BP_ENABLED = BIT(0),
+ KVM_DEBUGREG_WONT_EXIT = BIT(1),
+ /*
+ * Guest debug registers (DR0-3, DR6 and DR7) are saved/restored by
+ * hardware on exit from or enter to guest. KVM needn't switch them.
+ * DR0-3, DR6 and DR7 are set to their architectural INIT value on VM
+ * exit, host values need to be restored.
+ */
+ KVM_DEBUGREG_AUTO_SWITCH = BIT(2),
};
struct kvm_mtrr {
@@ -692,8 +701,13 @@ struct kvm_vcpu_hv {
struct kvm_vcpu_hv_tlb_flush_fifo tlb_flush_fifo[HV_NR_TLB_FLUSH_FIFOS];
- /* Preallocated buffer for handling hypercalls passing sparse vCPU set */
+ /*
+ * Preallocated buffers for handling hypercalls that pass sparse vCPU
+ * sets (for high vCPU counts, they're too large to comfortably fit on
+ * the stack).
+ */
u64 sparse_banks[HV_MAX_SPARSE_VCPU_BANKS];
+ DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
struct hv_vp_assist_page vp_assist_page;
@@ -756,6 +770,7 @@ enum kvm_only_cpuid_leafs {
CPUID_8000_0022_EAX,
CPUID_7_2_EDX,
CPUID_24_0_EBX,
+ CPUID_8000_0021_ECX,
NR_KVM_CPU_CAPS,
NKVMCAPINTS = NR_KVM_CPU_CAPS - NCAPINTS,
@@ -910,6 +925,7 @@ struct kvm_vcpu_arch {
bool emulate_regs_need_sync_to_vcpu;
bool emulate_regs_need_sync_from_vcpu;
int (*complete_userspace_io)(struct kvm_vcpu *vcpu);
+ unsigned long cui_linear_rip;
gpa_t time;
s8 pvclock_tsc_shift;
@@ -1027,6 +1043,7 @@ struct kvm_vcpu_arch {
int pending_ioapic_eoi;
int pending_external_vector;
+ int highest_stale_pending_ioapic_eoi;
/* be preempted when it's in kernel-mode(cpl=0) */
bool preempted_in_kernel;
@@ -1304,6 +1321,12 @@ enum kvm_apicv_inhibit {
*/
APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED,
+ /*
+ * AVIC is disabled because the vCPU's APIC ID is beyond the max
+ * supported by AVIC/x2AVIC, i.e. the vCPU is unaddressable.
+ */
+ APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG,
+
NR_APICV_INHIBIT_REASONS,
};
@@ -1322,7 +1345,8 @@ enum kvm_apicv_inhibit {
__APICV_INHIBIT_REASON(IRQWIN), \
__APICV_INHIBIT_REASON(PIT_REINJ), \
__APICV_INHIBIT_REASON(SEV), \
- __APICV_INHIBIT_REASON(LOGICAL_ID_ALIASED)
+ __APICV_INHIBIT_REASON(LOGICAL_ID_ALIASED), \
+ __APICV_INHIBIT_REASON(PHYSICAL_ID_TOO_BIG)
struct kvm_arch {
unsigned long n_used_mmu_pages;
@@ -1334,7 +1358,7 @@ struct kvm_arch {
bool has_private_mem;
bool has_protected_state;
bool pre_fault_allowed;
- struct hlist_head mmu_page_hash[KVM_NUM_MMU_PAGES];
+ struct hlist_head *mmu_page_hash;
struct list_head active_mmu_pages;
/*
* A list of kvm_mmu_page structs that, if zapped, could possibly be
@@ -1363,11 +1387,13 @@ struct kvm_arch {
#define __KVM_HAVE_ARCH_NONCOHERENT_DMA
atomic_t noncoherent_dma_count;
-#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE
- atomic_t assigned_device_count;
+ unsigned long nr_possible_bypass_irqs;
+
+#ifdef CONFIG_KVM_IOAPIC
struct kvm_pic *vpic;
struct kvm_ioapic *vioapic;
struct kvm_pit *vpit;
+#endif
atomic_t vapics_in_nmi_mode;
struct mutex apic_map_lock;
struct kvm_apic_map __rcu *apic_map;
@@ -1382,12 +1408,8 @@ struct kvm_arch {
gpa_t wall_clock;
- bool mwait_in_guest;
- bool hlt_in_guest;
- bool pause_in_guest;
- bool cstate_in_guest;
+ u64 disabled_exits;
- unsigned long irq_sources_bitmap;
s64 kvmclock_offset;
/*
@@ -1416,9 +1438,6 @@ struct kvm_arch {
struct delayed_work kvmclock_update_work;
struct delayed_work kvmclock_sync_work;
- /* reads protected by irq_srcu, writes by irq_lock */
- struct hlist_head mask_notifier_list;
-
#ifdef CONFIG_KVM_HYPERV
struct kvm_hv hyperv;
#endif
@@ -1441,6 +1460,7 @@ struct kvm_arch {
bool x2apic_format;
bool x2apic_broadcast_quirk_disabled;
+ bool has_mapped_host_mmio;
bool guest_can_read_msr_platform_info;
bool exception_payload_enabled;
@@ -1570,6 +1590,13 @@ struct kvm_arch {
struct kvm_mmu_memory_cache split_desc_cache;
gfn_t gfn_direct_bits;
+
+ /*
+ * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A Zero
+ * value indicates CPU dirty logging is unsupported or disabled in
+ * current VM.
+ */
+ int cpu_dirty_log_size;
};
struct kvm_vm_stat {
@@ -1657,6 +1684,12 @@ static inline u16 kvm_lapic_irq_dest_mode(bool dest_mode_logical)
return dest_mode_logical ? APIC_DEST_LOGICAL : APIC_DEST_PHYSICAL;
}
+enum kvm_x86_run_flags {
+ KVM_RUN_FORCE_IMMEDIATE_EXIT = BIT(0),
+ KVM_RUN_LOAD_GUEST_DR6 = BIT(1),
+ KVM_RUN_LOAD_DEBUGCTL = BIT(2),
+};
+
struct kvm_x86_ops {
const char *name;
@@ -1673,6 +1706,7 @@ struct kvm_x86_ops {
unsigned int vm_size;
int (*vm_init)(struct kvm *kvm);
void (*vm_destroy)(struct kvm *kvm);
+ void (*vm_pre_destroy)(struct kvm *kvm);
/* Create, but do not attach this VCPU */
int (*vcpu_precreate)(struct kvm *kvm);
@@ -1684,6 +1718,12 @@ struct kvm_x86_ops {
void (*vcpu_load)(struct kvm_vcpu *vcpu, int cpu);
void (*vcpu_put)(struct kvm_vcpu *vcpu);
+ /*
+ * Mask of DEBUGCTL bits that are owned by the host, i.e. that need to
+ * match the host's value even while the guest is active.
+ */
+ const u64 HOST_OWNED_DEBUGCTL;
+
void (*update_exception_bitmap)(struct kvm_vcpu *vcpu);
int (*get_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
int (*set_msr)(struct kvm_vcpu *vcpu, struct msr_data *msr);
@@ -1706,7 +1746,6 @@ struct kvm_x86_ops {
void (*get_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
void (*set_gdt)(struct kvm_vcpu *vcpu, struct desc_ptr *dt);
void (*sync_dirty_debug_regs)(struct kvm_vcpu *vcpu);
- void (*set_dr6)(struct kvm_vcpu *vcpu, unsigned long value);
void (*set_dr7)(struct kvm_vcpu *vcpu, unsigned long value);
void (*cache_reg)(struct kvm_vcpu *vcpu, enum kvm_reg reg);
unsigned long (*get_rflags)(struct kvm_vcpu *vcpu);
@@ -1737,7 +1776,7 @@ struct kvm_x86_ops {
int (*vcpu_pre_run)(struct kvm_vcpu *vcpu);
enum exit_fastpath_completion (*vcpu_run)(struct kvm_vcpu *vcpu,
- bool force_immediate_exit);
+ u64 run_flags);
int (*handle_exit)(struct kvm_vcpu *vcpu,
enum exit_fastpath_completion exit_fastpath);
int (*skip_emulated_instruction)(struct kvm_vcpu *vcpu);
@@ -1822,11 +1861,6 @@ struct kvm_x86_ops {
struct x86_exception *exception);
void (*handle_exit_irqoff)(struct kvm_vcpu *vcpu);
- /*
- * Size of the CPU's dirty log buffer, i.e. VMX's PML buffer. A zero
- * value indicates CPU dirty logging is unsupported or disabled.
- */
- int cpu_dirty_log_size;
void (*update_cpu_dirty_logging)(struct kvm_vcpu *vcpu);
const struct kvm_x86_nested_ops *nested_ops;
@@ -1834,12 +1868,14 @@ struct kvm_x86_ops {
void (*vcpu_blocking)(struct kvm_vcpu *vcpu);
void (*vcpu_unblocking)(struct kvm_vcpu *vcpu);
- int (*pi_update_irte)(struct kvm *kvm, unsigned int host_irq,
- uint32_t guest_irq, bool set);
- void (*pi_start_assignment)(struct kvm *kvm);
+ int (*pi_update_irte)(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+ unsigned int host_irq, uint32_t guest_irq,
+ struct kvm_vcpu *vcpu, u32 vector);
+ void (*pi_start_bypass)(struct kvm *kvm);
void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu);
void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
bool (*dy_apicv_has_pending_interrupt)(struct kvm_vcpu *vcpu);
+ bool (*protected_apic_has_interrupt)(struct kvm_vcpu *vcpu);
int (*set_hv_timer)(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
bool *expired);
@@ -1856,6 +1892,7 @@ struct kvm_x86_ops {
int (*dev_get_attr)(u32 group, u64 attr, u64 *val);
int (*mem_enc_ioctl)(struct kvm *kvm, void __user *argp);
+ int (*vcpu_mem_enc_ioctl)(struct kvm_vcpu *vcpu, void __user *argp);
int (*mem_enc_register_region)(struct kvm *kvm, struct kvm_enc_region *argp);
int (*mem_enc_unregister_region)(struct kvm *kvm, struct kvm_enc_region *argp);
int (*vm_copy_enc_context_from)(struct kvm *kvm, unsigned int source_fd);
@@ -1871,7 +1908,7 @@ struct kvm_x86_ops {
int (*enable_l2_tlb_flush)(struct kvm_vcpu *vcpu);
void (*migrate_timers)(struct kvm_vcpu *vcpu);
- void (*msr_filter_changed)(struct kvm_vcpu *vcpu);
+ void (*recalc_msr_intercepts)(struct kvm_vcpu *vcpu);
int (*complete_emulated_msr)(struct kvm_vcpu *vcpu, int err);
void (*vcpu_deliver_sipi_vector)(struct kvm_vcpu *vcpu, u8 vector);
@@ -1929,6 +1966,8 @@ struct kvm_arch_async_pf {
extern u32 __read_mostly kvm_nr_uret_msrs;
extern bool __read_mostly allow_smaller_maxphyaddr;
extern bool __read_mostly enable_apicv;
+extern bool __read_mostly enable_ipiv;
+extern bool __read_mostly enable_device_posted_irqs;
extern struct kvm_x86_ops kvm_x86_ops;
#define kvm_x86_call(func) static_call(kvm_x86_##func)
@@ -1946,7 +1985,7 @@ void kvm_x86_vendor_exit(void);
#define __KVM_HAVE_ARCH_VM_ALLOC
static inline struct kvm *kvm_arch_alloc_vm(void)
{
- return __vmalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
+ return kvzalloc(kvm_x86_ops.vm_size, GFP_KERNEL_ACCOUNT);
}
#define __KVM_HAVE_ARCH_VM_FREE
@@ -1991,7 +2030,7 @@ void kvm_mmu_vendor_module_exit(void);
void kvm_mmu_destroy(struct kvm_vcpu *vcpu);
int kvm_mmu_create(struct kvm_vcpu *vcpu);
-void kvm_mmu_init_vm(struct kvm *kvm);
+int kvm_mmu_init_vm(struct kvm *kvm);
void kvm_mmu_uninit_vm(struct kvm *kvm);
void kvm_mmu_init_memslot_memory_attributes(struct kvm *kvm,
@@ -2022,19 +2061,6 @@ int load_pdptrs(struct kvm_vcpu *vcpu, unsigned long cr3);
int emulator_write_phys(struct kvm_vcpu *vcpu, gpa_t gpa,
const void *val, int bytes);
-struct kvm_irq_mask_notifier {
- void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
- int irq;
- struct hlist_node link;
-};
-
-void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
- struct kvm_irq_mask_notifier *kimn);
-void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
- struct kvm_irq_mask_notifier *kimn);
-void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
- bool mask);
-
extern bool tdp_enabled;
u64 vcpu_tsc_khz(struct kvm_vcpu *vcpu);
@@ -2193,9 +2219,6 @@ static inline int __kvm_irq_line_state(unsigned long *irq_state,
return !!(*irq_state);
}
-int kvm_pic_set_irq(struct kvm_pic *pic, int irq, int irq_source_id, int level);
-void kvm_pic_clear_all(struct kvm_pic *pic, int irq_source_id);
-
void kvm_inject_nmi(struct kvm_vcpu *vcpu);
int kvm_get_nr_pending_nmis(struct kvm_vcpu *vcpu);
@@ -2278,7 +2301,7 @@ static inline unsigned long read_msr(unsigned long msr)
{
u64 value;
- rdmsrl(msr, value);
+ rdmsrq(msr, value);
return value;
}
#endif
@@ -2332,6 +2355,7 @@ int kvm_pv_send_ipi(struct kvm *kvm, unsigned long ipi_bitmap_low,
int kvm_add_user_return_msr(u32 msr);
int kvm_find_user_return_msr(u32 msr);
int kvm_set_user_return_msr(unsigned index, u64 val, u64 mask);
+void kvm_user_return_msr_update_cache(unsigned int index, u64 val);
static inline bool kvm_is_supported_user_return_msr(u32 msr)
{
@@ -2371,9 +2395,6 @@ bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu);
bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
struct kvm_vcpu **dest_vcpu);
-void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
- struct kvm_lapic_irq *irq);
-
static inline bool kvm_irq_is_postable(struct kvm_lapic_irq *irq)
{
/* We can only post Fixed and LowPrio IRQs */
@@ -2415,7 +2436,12 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
KVM_X86_QUIRK_FIX_HYPERCALL_INSN | \
KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS | \
KVM_X86_QUIRK_SLOT_ZAP_ALL | \
- KVM_X86_QUIRK_STUFF_FEATURE_MSRS)
+ KVM_X86_QUIRK_STUFF_FEATURE_MSRS | \
+ KVM_X86_QUIRK_IGNORE_GUEST_PAT)
+
+#define KVM_X86_CONDITIONAL_QUIRKS \
+ (KVM_X86_QUIRK_CD_NW_CLEARED | \
+ KVM_X86_QUIRK_IGNORE_GUEST_PAT)
/*
* KVM previously used a u32 field in kvm_run to indicate the hypercall was
@@ -2426,7 +2452,7 @@ int memslot_rmap_alloc(struct kvm_memory_slot *slot, unsigned long npages);
static inline bool kvm_arch_has_irq_bypass(void)
{
- return enable_apicv && irq_remapping_cap(IRQ_POSTING_CAP);
+ return enable_device_posted_irqs;
}
#endif /* _ASM_X86_KVM_HOST_H */
diff --git a/arch/x86/include/asm/linkage.h b/arch/x86/include/asm/linkage.h
index b51d8a4673f5..9d38ae744a2e 100644
--- a/arch/x86/include/asm/linkage.h
+++ b/arch/x86/include/asm/linkage.h
@@ -141,5 +141,15 @@
#define SYM_FUNC_START_WEAK_NOALIGN(name) \
SYM_START(name, SYM_L_WEAK, SYM_A_NONE)
+/*
+ * Expose 'sym' to the startup code in arch/x86/boot/startup/, by emitting an
+ * alias prefixed with __pi_
+ */
+#ifdef __ASSEMBLER__
+#define SYM_PIC_ALIAS(sym) SYM_ALIAS(__pi_ ## sym, sym, SYM_L_GLOBAL)
+#else
+#define SYM_PIC_ALIAS(sym) extern typeof(sym) __PASTE(__pi_, sym) __alias(sym)
+#endif
+
#endif /* _ASM_X86_LINKAGE_H */
diff --git a/arch/x86/include/asm/mem_encrypt.h b/arch/x86/include/asm/mem_encrypt.h
index 1530ee301dfe..ea6494628cb0 100644
--- a/arch/x86/include/asm/mem_encrypt.h
+++ b/arch/x86/include/asm/mem_encrypt.h
@@ -61,7 +61,7 @@ void __init sev_es_init_vc_handling(void);
static inline u64 sme_get_me_mask(void)
{
- return RIP_REL_REF(sme_me_mask);
+ return sme_me_mask;
}
#define __bss_decrypted __section(".bss..decrypted")
diff --git a/arch/x86/include/asm/microcode.h b/arch/x86/include/asm/microcode.h
index be7cddc414e4..8b41f26f003b 100644
--- a/arch/x86/include/asm/microcode.h
+++ b/arch/x86/include/asm/microcode.h
@@ -2,6 +2,8 @@
#ifndef _ASM_X86_MICROCODE_H
#define _ASM_X86_MICROCODE_H
+#include <asm/msr.h>
+
struct cpu_signature {
unsigned int sig;
unsigned int pf;
@@ -63,7 +65,7 @@ static inline u32 intel_get_microcode_revision(void)
{
u32 rev, dummy;
- native_wrmsrl(MSR_IA32_UCODE_REV, 0);
+ native_wrmsrq(MSR_IA32_UCODE_REV, 0);
/* As documented in the SDM: Do a CPUID 1 here */
native_cpuid_eax(1);
diff --git a/arch/x86/include/asm/mmu.h b/arch/x86/include/asm/mmu.h
index 8b8055a8eb9e..0fe9c569d171 100644
--- a/arch/x86/include/asm/mmu.h
+++ b/arch/x86/include/asm/mmu.h
@@ -16,6 +16,8 @@
#define MM_CONTEXT_LOCK_LAM 2
/* Allow LAM and SVA coexisting */
#define MM_CONTEXT_FORCE_TAGGED_SVA 3
+/* Tracks mm_cpumask */
+#define MM_CONTEXT_NOTRACK 4
/*
* x86 has arch-specific MMU state beyond what lives in mm_struct.
@@ -44,9 +46,7 @@ typedef struct {
struct ldt_struct *ldt;
#endif
-#ifdef CONFIG_X86_64
unsigned long flags;
-#endif
#ifdef CONFIG_ADDRESS_MASKING
/* Active LAM mode: X86_CR3_LAM_U48 or X86_CR3_LAM_U57 or 0 (disabled) */
diff --git a/arch/x86/include/asm/mmu_context.h b/arch/x86/include/asm/mmu_context.h
index 2398058b6e83..73bf3b1b44e8 100644
--- a/arch/x86/include/asm/mmu_context.h
+++ b/arch/x86/include/asm/mmu_context.h
@@ -190,7 +190,7 @@ extern void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
#define activate_mm(prev, next) \
do { \
paravirt_enter_mmap(next); \
- switch_mm((prev), (next), NULL); \
+ switch_mm_irqs_off((prev), (next), NULL); \
} while (0);
#ifdef CONFIG_X86_32
@@ -247,6 +247,16 @@ static inline bool is_64bit_mm(struct mm_struct *mm)
}
#endif
+static inline bool is_notrack_mm(struct mm_struct *mm)
+{
+ return test_bit(MM_CONTEXT_NOTRACK, &mm->context.flags);
+}
+
+static inline void set_notrack_mm(struct mm_struct *mm)
+{
+ set_bit(MM_CONTEXT_NOTRACK, &mm->context.flags);
+}
+
/*
* We only want to enforce protection keys on the current process
* because we effectively have no access to PKRU for other
@@ -272,4 +282,7 @@ unsigned long __get_current_cr3_fast(void);
#include <asm-generic/mmu_context.h>
+extern struct mm_struct *use_temporary_mm(struct mm_struct *temp_mm);
+extern void unuse_temporary_mm(struct mm_struct *prev_mm);
+
#endif /* _ASM_X86_MMU_CONTEXT_H */
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index e988bac0a4a1..3c2de4ce3b10 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -5,12 +5,20 @@
#include <asm-generic/module.h>
#include <asm/orc_types.h>
+struct its_array {
+#ifdef CONFIG_MITIGATION_ITS
+ void **pages;
+ int num;
+#endif
+};
+
struct mod_arch_specific {
#ifdef CONFIG_UNWINDER_ORC
unsigned int num_orcs;
int *orc_unwind_ip;
struct orc_entry *orc_unwind;
#endif
+ struct its_array its_pages;
};
#endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
index bab5ccfc60a7..abc4659f5809 100644
--- a/arch/x86/include/asm/mshyperv.h
+++ b/arch/x86/include/asm/mshyperv.h
@@ -8,6 +8,7 @@
#include <linux/io.h>
#include <asm/nospec-branch.h>
#include <asm/paravirt.h>
+#include <asm/msr.h>
#include <hyperv/hvhdk.h>
/*
@@ -111,12 +112,6 @@ static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
return hv_status;
}
-/* Hypercall to the L0 hypervisor */
-static inline u64 hv_do_nested_hypercall(u64 control, void *input, void *output)
-{
- return hv_do_hypercall(control | HV_HYPERCALL_NESTED, input, output);
-}
-
/* Fast hypercall with 8 bytes of input and no output */
static inline u64 _hv_do_fast_hypercall8(u64 control, u64 input1)
{
@@ -164,13 +159,6 @@ static inline u64 hv_do_fast_hypercall8(u16 code, u64 input1)
return _hv_do_fast_hypercall8(control, input1);
}
-static inline u64 hv_do_fast_nested_hypercall8(u16 code, u64 input1)
-{
- u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
-
- return _hv_do_fast_hypercall8(control, input1);
-}
-
/* Fast hypercall with 16 bytes of input */
static inline u64 _hv_do_fast_hypercall16(u64 control, u64 input1, u64 input2)
{
@@ -222,13 +210,6 @@ static inline u64 hv_do_fast_hypercall16(u16 code, u64 input1, u64 input2)
return _hv_do_fast_hypercall16(control, input1, input2);
}
-static inline u64 hv_do_fast_nested_hypercall16(u16 code, u64 input1, u64 input2)
-{
- u64 control = (u64)code | HV_HYPERCALL_FAST_BIT | HV_HYPERCALL_NESTED;
-
- return _hv_do_fast_hypercall16(control, input1, input2);
-}
-
extern struct hv_vp_assist_page **hv_vp_assist_page;
static inline struct hv_vp_assist_page *hv_get_vp_assist_page(unsigned int cpu)
@@ -261,6 +242,8 @@ static inline void hv_apic_init(void) {}
struct irq_domain *hv_create_pci_msi_domain(void);
+int hv_map_msi_interrupt(struct irq_data *data,
+ struct hv_interrupt_entry *out_entry);
int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector,
struct hv_interrupt_entry *entry);
int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
@@ -268,11 +251,12 @@ int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
#ifdef CONFIG_AMD_MEM_ENCRYPT
bool hv_ghcb_negotiate_protocol(void);
void __noreturn hv_ghcb_terminate(unsigned int set, unsigned int reason);
-int hv_snp_boot_ap(u32 cpu, unsigned long start_ip);
+int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip, unsigned int cpu);
#else
static inline bool hv_ghcb_negotiate_protocol(void) { return false; }
static inline void hv_ghcb_terminate(unsigned int set, unsigned int reason) {}
-static inline int hv_snp_boot_ap(u32 cpu, unsigned long start_ip) { return 0; }
+static inline int hv_snp_boot_ap(u32 apic_id, unsigned long start_ip,
+ unsigned int cpu) { return 0; }
#endif
#if defined(CONFIG_AMD_MEM_ENCRYPT) || defined(CONFIG_INTEL_TDX_GUEST)
@@ -304,8 +288,9 @@ void hv_set_non_nested_msr(unsigned int reg, u64 value);
static __always_inline u64 hv_raw_get_msr(unsigned int reg)
{
- return __rdmsr(reg);
+ return native_rdmsrq(reg);
}
+int hv_apicid_to_vp_index(u32 apic_id);
#else /* CONFIG_HYPERV */
static inline void hyperv_init(void) {}
@@ -327,6 +312,7 @@ static inline void hv_set_msr(unsigned int reg, u64 value) { }
static inline u64 hv_get_msr(unsigned int reg) { return 0; }
static inline void hv_set_non_nested_msr(unsigned int reg, u64 value) { }
static inline u64 hv_get_non_nested_msr(unsigned int reg) { return 0; }
+static inline int hv_apicid_to_vp_index(u32 apic_id) { return -EINVAL; }
#endif /* CONFIG_HYPERV */
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index e7d2f460fcc6..b65c3ba5fa14 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -419,6 +419,7 @@
#define DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI (1UL << 12)
#define DEBUGCTLMSR_FREEZE_IN_SMM_BIT 14
#define DEBUGCTLMSR_FREEZE_IN_SMM (1UL << DEBUGCTLMSR_FREEZE_IN_SMM_BIT)
+#define DEBUGCTLMSR_RTM_DEBUG BIT(15)
#define MSR_PEBS_FRONTEND 0x000003f7
@@ -533,7 +534,7 @@
#define MSR_HWP_CAPABILITIES 0x00000771
#define MSR_HWP_REQUEST_PKG 0x00000772
#define MSR_HWP_INTERRUPT 0x00000773
-#define MSR_HWP_REQUEST 0x00000774
+#define MSR_HWP_REQUEST 0x00000774
#define MSR_HWP_STATUS 0x00000777
/* CPUID.6.EAX */
@@ -550,16 +551,16 @@
#define HWP_LOWEST_PERF(x) (((x) >> 24) & 0xff)
/* IA32_HWP_REQUEST */
-#define HWP_MIN_PERF(x) (x & 0xff)
-#define HWP_MAX_PERF(x) ((x & 0xff) << 8)
+#define HWP_MIN_PERF(x) (x & 0xff)
+#define HWP_MAX_PERF(x) ((x & 0xff) << 8)
#define HWP_DESIRED_PERF(x) ((x & 0xff) << 16)
-#define HWP_ENERGY_PERF_PREFERENCE(x) (((unsigned long long) x & 0xff) << 24)
+#define HWP_ENERGY_PERF_PREFERENCE(x) (((u64)x & 0xff) << 24)
#define HWP_EPP_PERFORMANCE 0x00
#define HWP_EPP_BALANCE_PERFORMANCE 0x80
#define HWP_EPP_BALANCE_POWERSAVE 0xC0
#define HWP_EPP_POWERSAVE 0xFF
-#define HWP_ACTIVITY_WINDOW(x) ((unsigned long long)(x & 0xff3) << 32)
-#define HWP_PACKAGE_CONTROL(x) ((unsigned long long)(x & 0x1) << 42)
+#define HWP_ACTIVITY_WINDOW(x) ((u64)(x & 0xff3) << 32)
+#define HWP_PACKAGE_CONTROL(x) ((u64)(x & 0x1) << 42)
/* IA32_HWP_STATUS */
#define HWP_GUARANTEED_CHANGE(x) (x & 0x1)
@@ -602,7 +603,11 @@
/* V6 PMON MSR range */
#define MSR_IA32_PMC_V6_GP0_CTR 0x1900
#define MSR_IA32_PMC_V6_GP0_CFG_A 0x1901
+#define MSR_IA32_PMC_V6_GP0_CFG_B 0x1902
+#define MSR_IA32_PMC_V6_GP0_CFG_C 0x1903
#define MSR_IA32_PMC_V6_FX0_CTR 0x1980
+#define MSR_IA32_PMC_V6_FX0_CFG_B 0x1982
+#define MSR_IA32_PMC_V6_FX0_CFG_C 0x1983
#define MSR_IA32_PMC_V6_STEP 4
/* KeyID partitioning between MKTME and TDX */
@@ -624,6 +629,7 @@
#define MSR_AMD64_OSVW_STATUS 0xc0010141
#define MSR_AMD_PPIN_CTL 0xc00102f0
#define MSR_AMD_PPIN 0xc00102f1
+#define MSR_AMD64_CPUID_FN_7 0xc0011002
#define MSR_AMD64_CPUID_FN_1 0xc0011004
#define MSR_AMD64_LS_CFG 0xc0011020
#define MSR_AMD64_DC_CFG 0xc0011022
@@ -728,6 +734,11 @@
#define MSR_AMD64_PERF_CNTR_GLOBAL_CTL 0xc0000301
#define MSR_AMD64_PERF_CNTR_GLOBAL_STATUS_CLR 0xc0000302
+/* AMD Hardware Feedback Support MSRs */
+#define MSR_AMD_WORKLOAD_CLASS_CONFIG 0xc0000500
+#define MSR_AMD_WORKLOAD_CLASS_ID 0xc0000501
+#define MSR_AMD_WORKLOAD_HRST 0xc0000502
+
/* AMD Last Branch Record MSRs */
#define MSR_AMD64_LBR_SELECT 0xc000010e
@@ -826,6 +837,7 @@
#define MSR_K7_HWCR_SMMLOCK BIT_ULL(MSR_K7_HWCR_SMMLOCK_BIT)
#define MSR_K7_HWCR_IRPERF_EN_BIT 30
#define MSR_K7_HWCR_IRPERF_EN BIT_ULL(MSR_K7_HWCR_IRPERF_EN_BIT)
+#define MSR_K7_HWCR_CPUID_USER_DIS_BIT 35
#define MSR_K7_FID_VID_CTL 0xc0010041
#define MSR_K7_FID_VID_STATUS 0xc0010042
#define MSR_K7_HWCR_CPB_DIS_BIT 25
diff --git a/arch/x86/include/asm/msr.h b/arch/x86/include/asm/msr.h
index 9397a319d165..9c2ea29e12a9 100644
--- a/arch/x86/include/asm/msr.h
+++ b/arch/x86/include/asm/msr.h
@@ -12,6 +12,7 @@
#include <uapi/asm/msr.h>
#include <asm/shared/msr.h>
+#include <linux/types.h>
#include <linux/percpu.h>
struct msr_info {
@@ -37,23 +38,6 @@ struct saved_msrs {
};
/*
- * both i386 and x86_64 returns 64-bit value in edx:eax, but gcc's "A"
- * constraint has different meanings. For i386, "A" means exactly
- * edx:eax, while for x86_64 it doesn't mean rdx:rax or edx:eax. Instead,
- * it means rax *or* rdx.
- */
-#ifdef CONFIG_X86_64
-/* Using 64-bit values saves one instruction clearing the high half of low */
-#define DECLARE_ARGS(val, low, high) unsigned long low, high
-#define EAX_EDX_VAL(val, low, high) ((low) | (high) << 32)
-#define EAX_EDX_RET(val, low, high) "=a" (low), "=d" (high)
-#else
-#define DECLARE_ARGS(val, low, high) unsigned long long val
-#define EAX_EDX_VAL(val, low, high) (val)
-#define EAX_EDX_RET(val, low, high) "=A" (val)
-#endif
-
-/*
* Be very careful with includes. This header is prone to include loops.
*/
#include <asm/atomic.h>
@@ -63,13 +47,13 @@ struct saved_msrs {
DECLARE_TRACEPOINT(read_msr);
DECLARE_TRACEPOINT(write_msr);
DECLARE_TRACEPOINT(rdpmc);
-extern void do_trace_write_msr(unsigned int msr, u64 val, int failed);
-extern void do_trace_read_msr(unsigned int msr, u64 val, int failed);
-extern void do_trace_rdpmc(unsigned int msr, u64 val, int failed);
+extern void do_trace_write_msr(u32 msr, u64 val, int failed);
+extern void do_trace_read_msr(u32 msr, u64 val, int failed);
+extern void do_trace_rdpmc(u32 msr, u64 val, int failed);
#else
-static inline void do_trace_write_msr(unsigned int msr, u64 val, int failed) {}
-static inline void do_trace_read_msr(unsigned int msr, u64 val, int failed) {}
-static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
+static inline void do_trace_write_msr(u32 msr, u64 val, int failed) {}
+static inline void do_trace_read_msr(u32 msr, u64 val, int failed) {}
+static inline void do_trace_rdpmc(u32 msr, u64 val, int failed) {}
#endif
/*
@@ -79,9 +63,9 @@ static inline void do_trace_rdpmc(unsigned int msr, u64 val, int failed) {}
* think of extending them - you will be slapped with a stinking trout or a frozen
* shark will reach you, wherever you are! You've been warned.
*/
-static __always_inline unsigned long long __rdmsr(unsigned int msr)
+static __always_inline u64 __rdmsr(u32 msr)
{
- DECLARE_ARGS(val, low, high);
+ EAX_EDX_DECLARE_ARGS(val, low, high);
asm volatile("1: rdmsr\n"
"2:\n"
@@ -91,12 +75,12 @@ static __always_inline unsigned long long __rdmsr(unsigned int msr)
return EAX_EDX_VAL(val, low, high);
}
-static __always_inline void __wrmsr(unsigned int msr, u32 low, u32 high)
+static __always_inline void __wrmsrq(u32 msr, u64 val)
{
asm volatile("1: wrmsr\n"
"2:\n"
_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR)
- : : "c" (msr), "a"(low), "d" (high) : "memory");
+ : : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)) : "memory");
}
#define native_rdmsr(msr, val1, val2) \
@@ -106,16 +90,20 @@ do { \
(void)((val2) = (u32)(__val >> 32)); \
} while (0)
+static __always_inline u64 native_rdmsrq(u32 msr)
+{
+ return __rdmsr(msr);
+}
+
#define native_wrmsr(msr, low, high) \
- __wrmsr(msr, low, high)
+ __wrmsrq((msr), (u64)(high) << 32 | (low))
-#define native_wrmsrl(msr, val) \
- __wrmsr((msr), (u32)((u64)(val)), \
- (u32)((u64)(val) >> 32))
+#define native_wrmsrq(msr, val) \
+ __wrmsrq((msr), (val))
-static inline unsigned long long native_read_msr(unsigned int msr)
+static inline u64 native_read_msr(u32 msr)
{
- unsigned long long val;
+ u64 val;
val = __rdmsr(msr);
@@ -125,34 +113,35 @@ static inline unsigned long long native_read_msr(unsigned int msr)
return val;
}
-static inline unsigned long long native_read_msr_safe(unsigned int msr,
- int *err)
+static inline int native_read_msr_safe(u32 msr, u64 *p)
{
- DECLARE_ARGS(val, low, high);
+ int err;
+ EAX_EDX_DECLARE_ARGS(val, low, high);
asm volatile("1: rdmsr ; xor %[err],%[err]\n"
"2:\n\t"
_ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_RDMSR_SAFE, %[err])
- : [err] "=r" (*err), EAX_EDX_RET(val, low, high)
+ : [err] "=r" (err), EAX_EDX_RET(val, low, high)
: "c" (msr));
if (tracepoint_enabled(read_msr))
- do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), *err);
- return EAX_EDX_VAL(val, low, high);
+ do_trace_read_msr(msr, EAX_EDX_VAL(val, low, high), err);
+
+ *p = EAX_EDX_VAL(val, low, high);
+
+ return err;
}
/* Can be uninlined because referenced by paravirt */
-static inline void notrace
-native_write_msr(unsigned int msr, u32 low, u32 high)
+static inline void notrace native_write_msr(u32 msr, u64 val)
{
- __wrmsr(msr, low, high);
+ native_wrmsrq(msr, val);
if (tracepoint_enabled(write_msr))
- do_trace_write_msr(msr, ((u64)high << 32 | low), 0);
+ do_trace_write_msr(msr, val, 0);
}
/* Can be uninlined because referenced by paravirt */
-static inline int notrace
-native_write_msr_safe(unsigned int msr, u32 low, u32 high)
+static inline int notrace native_write_msr_safe(u32 msr, u64 val)
{
int err;
@@ -160,73 +149,19 @@ native_write_msr_safe(unsigned int msr, u32 low, u32 high)
"2:\n\t"
_ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_WRMSR_SAFE, %[err])
: [err] "=a" (err)
- : "c" (msr), "0" (low), "d" (high)
+ : "c" (msr), "0" ((u32)val), "d" ((u32)(val >> 32))
: "memory");
if (tracepoint_enabled(write_msr))
- do_trace_write_msr(msr, ((u64)high << 32 | low), err);
+ do_trace_write_msr(msr, val, err);
return err;
}
extern int rdmsr_safe_regs(u32 regs[8]);
extern int wrmsr_safe_regs(u32 regs[8]);
-/**
- * rdtsc() - returns the current TSC without ordering constraints
- *
- * rdtsc() returns the result of RDTSC as a 64-bit integer. The
- * only ordering constraint it supplies is the ordering implied by
- * "asm volatile": it will put the RDTSC in the place you expect. The
- * CPU can and will speculatively execute that RDTSC, though, so the
- * results can be non-monotonic if compared on different CPUs.
- */
-static __always_inline unsigned long long rdtsc(void)
+static inline u64 native_read_pmc(int counter)
{
- DECLARE_ARGS(val, low, high);
-
- asm volatile("rdtsc" : EAX_EDX_RET(val, low, high));
-
- return EAX_EDX_VAL(val, low, high);
-}
-
-/**
- * rdtsc_ordered() - read the current TSC in program order
- *
- * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer.
- * It is ordered like a load to a global in-memory counter. It should
- * be impossible to observe non-monotonic rdtsc_unordered() behavior
- * across multiple CPUs as long as the TSC is synced.
- */
-static __always_inline unsigned long long rdtsc_ordered(void)
-{
- DECLARE_ARGS(val, low, high);
-
- /*
- * The RDTSC instruction is not ordered relative to memory
- * access. The Intel SDM and the AMD APM are both vague on this
- * point, but empirically an RDTSC instruction can be
- * speculatively executed before prior loads. An RDTSC
- * immediately after an appropriate barrier appears to be
- * ordered as a normal load, that is, it provides the same
- * ordering guarantees as reading from a global memory location
- * that some other imaginary CPU is updating continuously with a
- * time stamp.
- *
- * Thus, use the preferred barrier on the respective CPU, aiming for
- * RDTSCP as the default.
- */
- asm volatile(ALTERNATIVE_2("rdtsc",
- "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC,
- "rdtscp", X86_FEATURE_RDTSCP)
- : EAX_EDX_RET(val, low, high)
- /* RDTSCP clobbers ECX with MSR_TSC_AUX. */
- :: "ecx");
-
- return EAX_EDX_VAL(val, low, high);
-}
-
-static inline unsigned long long native_read_pmc(int counter)
-{
- DECLARE_ARGS(val, low, high);
+ EAX_EDX_DECLARE_ARGS(val, low, high);
asm volatile("rdpmc" : EAX_EDX_RET(val, low, high) : "c" (counter));
if (tracepoint_enabled(rdpmc))
@@ -251,56 +186,49 @@ do { \
(void)((high) = (u32)(__val >> 32)); \
} while (0)
-static inline void wrmsr(unsigned int msr, u32 low, u32 high)
+static inline void wrmsr(u32 msr, u32 low, u32 high)
{
- native_write_msr(msr, low, high);
+ native_write_msr(msr, (u64)high << 32 | low);
}
-#define rdmsrl(msr, val) \
+#define rdmsrq(msr, val) \
((val) = native_read_msr((msr)))
-static inline void wrmsrl(unsigned int msr, u64 val)
+static inline void wrmsrq(u32 msr, u64 val)
{
- native_write_msr(msr, (u32)(val & 0xffffffffULL), (u32)(val >> 32));
+ native_write_msr(msr, val);
}
/* wrmsr with exception handling */
-static inline int wrmsr_safe(unsigned int msr, u32 low, u32 high)
+static inline int wrmsrq_safe(u32 msr, u64 val)
{
- return native_write_msr_safe(msr, low, high);
+ return native_write_msr_safe(msr, val);
}
/* rdmsr with exception handling */
#define rdmsr_safe(msr, low, high) \
({ \
- int __err; \
- u64 __val = native_read_msr_safe((msr), &__err); \
+ u64 __val; \
+ int __err = native_read_msr_safe((msr), &__val); \
(*low) = (u32)__val; \
(*high) = (u32)(__val >> 32); \
__err; \
})
-static inline int rdmsrl_safe(unsigned int msr, unsigned long long *p)
+static inline int rdmsrq_safe(u32 msr, u64 *p)
{
- int err;
-
- *p = native_read_msr_safe(msr, &err);
- return err;
+ return native_read_msr_safe(msr, p);
}
-#define rdpmc(counter, low, high) \
-do { \
- u64 _l = native_read_pmc((counter)); \
- (low) = (u32)_l; \
- (high) = (u32)(_l >> 32); \
-} while (0)
-
-#define rdpmcl(counter, val) ((val) = native_read_pmc(counter))
+static __always_inline u64 rdpmc(int counter)
+{
+ return native_read_pmc(counter);
+}
#endif /* !CONFIG_PARAVIRT_XXL */
/* Instruction opcode for WRMSRNS supported in binutils >= 2.40 */
-#define WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6)
+#define ASM_WRMSRNS _ASM_BYTES(0x0f,0x01,0xc6)
/* Non-serializing WRMSR, when available. Falls back to a serializing WRMSR. */
static __always_inline void wrmsrns(u32 msr, u64 val)
@@ -309,17 +237,17 @@ static __always_inline void wrmsrns(u32 msr, u64 val)
* WRMSR is 2 bytes. WRMSRNS is 3 bytes. Pad WRMSR with a redundant
* DS prefix to avoid a trailing NOP.
*/
- asm volatile("1: " ALTERNATIVE("ds wrmsr", WRMSRNS, X86_FEATURE_WRMSRNS)
+ asm volatile("1: " ALTERNATIVE("ds wrmsr", ASM_WRMSRNS, X86_FEATURE_WRMSRNS)
"2: " _ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR)
: : "c" (msr), "a" ((u32)val), "d" ((u32)(val >> 32)));
}
/*
- * 64-bit version of wrmsr_safe():
+ * Dual u32 version of wrmsrq_safe():
*/
-static inline int wrmsrl_safe(u32 msr, u64 val)
+static inline int wrmsr_safe(u32 msr, u32 low, u32 high)
{
- return wrmsr_safe(msr, (u32)val, (u32)(val >> 32));
+ return wrmsrq_safe(msr, (u64)high << 32 | low);
}
struct msr __percpu *msrs_alloc(void);
@@ -330,14 +258,14 @@ int msr_clear_bit(u32 msr, u8 bit);
#ifdef CONFIG_SMP
int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
-int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
-int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
+int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
+int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
void rdmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs);
void wrmsr_on_cpus(const struct cpumask *mask, u32 msr_no, struct msr __percpu *msrs);
int rdmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h);
int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h);
-int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
-int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
+int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q);
+int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q);
int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8]);
#else /* CONFIG_SMP */
@@ -351,14 +279,14 @@ static inline int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
wrmsr(msr_no, l, h);
return 0;
}
-static inline int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+static inline int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
{
- rdmsrl(msr_no, *q);
+ rdmsrq(msr_no, *q);
return 0;
}
-static inline int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+static inline int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
{
- wrmsrl(msr_no, q);
+ wrmsrq(msr_no, q);
return 0;
}
static inline void rdmsr_on_cpus(const struct cpumask *m, u32 msr_no,
@@ -380,13 +308,13 @@ static inline int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
{
return wrmsr_safe(msr_no, l, h);
}
-static inline int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+static inline int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
{
- return rdmsrl_safe(msr_no, q);
+ return rdmsrq_safe(msr_no, q);
}
-static inline int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+static inline int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
{
- return wrmsrl_safe(msr_no, q);
+ return wrmsrq_safe(msr_no, q);
}
static inline int rdmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
{
@@ -397,5 +325,11 @@ static inline int wrmsr_safe_regs_on_cpu(unsigned int cpu, u32 regs[8])
return wrmsr_safe_regs(regs);
}
#endif /* CONFIG_SMP */
+
+/* Compatibility wrappers: */
+#define rdmsrl(msr, val) rdmsrq(msr, val)
+#define wrmsrl(msr, val) wrmsrq(msr, val)
+#define rdmsrl_on_cpu(cpu, msr, q) rdmsrq_on_cpu(cpu, msr, q)
+
#endif /* __ASSEMBLER__ */
#endif /* _ASM_X86_MSR_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index ce857ef54cf1..6ca6516c7492 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -25,29 +25,29 @@
#define TPAUSE_C01_STATE 1
#define TPAUSE_C02_STATE 0
-static __always_inline void __monitor(const void *eax, unsigned long ecx,
- unsigned long edx)
+static __always_inline void __monitor(const void *eax, u32 ecx, u32 edx)
{
- /* "monitor %eax, %ecx, %edx;" */
- asm volatile(".byte 0x0f, 0x01, 0xc8;"
- :: "a" (eax), "c" (ecx), "d"(edx));
+ /*
+ * Use the instruction mnemonic with implicit operands, as the LLVM
+ * assembler fails to assemble the mnemonic with explicit operands:
+ */
+ asm volatile("monitor" :: "a" (eax), "c" (ecx), "d" (edx));
}
-static __always_inline void __monitorx(const void *eax, unsigned long ecx,
- unsigned long edx)
+static __always_inline void __monitorx(const void *eax, u32 ecx, u32 edx)
{
- /* "monitorx %eax, %ecx, %edx;" */
- asm volatile(".byte 0x0f, 0x01, 0xfa;"
+ /* "monitorx %eax, %ecx, %edx" */
+ asm volatile(".byte 0x0f, 0x01, 0xfa"
:: "a" (eax), "c" (ecx), "d"(edx));
}
-static __always_inline void __mwait(unsigned long eax, unsigned long ecx)
+static __always_inline void __mwait(u32 eax, u32 ecx)
{
- mds_idle_clear_cpu_buffers();
-
- /* "mwait %eax, %ecx;" */
- asm volatile(".byte 0x0f, 0x01, 0xc9;"
- :: "a" (eax), "c" (ecx));
+ /*
+ * Use the instruction mnemonic with implicit operands, as the LLVM
+ * assembler fails to assemble the mnemonic with explicit operands:
+ */
+ asm volatile("mwait" :: "a" (eax), "c" (ecx));
}
/*
@@ -76,13 +76,12 @@ static __always_inline void __mwait(unsigned long eax, unsigned long ecx)
* EAX (logical) address to monitor
* ECX #GP if not zero
*/
-static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
- unsigned long ecx)
+static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
{
- /* No MDS buffer clear as this is AMD/HYGON only */
+ /* No need for TSA buffer clearing on AMD */
- /* "mwaitx %eax, %ebx, %ecx;" */
- asm volatile(".byte 0x0f, 0x01, 0xfb;"
+ /* "mwaitx %eax, %ebx, %ecx" */
+ asm volatile(".byte 0x0f, 0x01, 0xfb"
:: "a" (eax), "b" (ebx), "c" (ecx));
}
@@ -95,12 +94,10 @@ static __always_inline void __mwaitx(unsigned long eax, unsigned long ebx,
* executing mwait, it would otherwise go unnoticed and the next tick
* would not be reprogrammed accordingly before mwait ever wakes up.
*/
-static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
+static __always_inline void __sti_mwait(u32 eax, u32 ecx)
{
- mds_idle_clear_cpu_buffers();
- /* "mwait %eax, %ecx;" */
- asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"
- :: "a" (eax), "c" (ecx));
+
+ asm volatile("sti; mwait" :: "a" (eax), "c" (ecx));
}
/*
@@ -113,26 +110,31 @@ static __always_inline void __sti_mwait(unsigned long eax, unsigned long ecx)
* New with Core Duo processors, MWAIT can take some hints based on CPU
* capability.
*/
-static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned long ecx)
+static __always_inline void mwait_idle_with_hints(u32 eax, u32 ecx)
{
+ if (need_resched())
+ return;
+
+ x86_idle_clear_cpu_buffers();
+
if (static_cpu_has_bug(X86_BUG_MONITOR) || !current_set_polling_and_test()) {
- if (static_cpu_has_bug(X86_BUG_CLFLUSH_MONITOR)) {
- mb();
- clflush((void *)&current_thread_info()->flags);
- mb();
- }
+ const void *addr = &current_thread_info()->flags;
- __monitor((void *)&current_thread_info()->flags, 0, 0);
+ alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
+ __monitor(addr, 0, 0);
- if (!need_resched()) {
- if (ecx & 1) {
- __mwait(eax, ecx);
- } else {
- __sti_mwait(eax, ecx);
- raw_local_irq_disable();
- }
+ if (need_resched())
+ goto out;
+
+ if (ecx & 1) {
+ __mwait(eax, ecx);
+ } else {
+ __sti_mwait(eax, ecx);
+ raw_local_irq_disable();
}
}
+
+out:
current_clr_polling();
}
@@ -144,16 +146,9 @@ static __always_inline void mwait_idle_with_hints(unsigned long eax, unsigned lo
*/
static inline void __tpause(u32 ecx, u32 edx, u32 eax)
{
- /* "tpause %ecx, %edx, %eax;" */
- #ifdef CONFIG_AS_TPAUSE
- asm volatile("tpause %%ecx\n"
- :
- : "c"(ecx), "d"(edx), "a"(eax));
- #else
- asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1\t\n"
- :
- : "c"(ecx), "d"(edx), "a"(eax));
- #endif
+ /* "tpause %ecx" */
+ asm volatile(".byte 0x66, 0x0f, 0xae, 0xf1"
+ :: "c" (ecx), "d" (edx), "a" (eax));
}
#endif /* _ASM_X86_MWAIT_H */
diff --git a/arch/x86/include/asm/nmi.h b/arch/x86/include/asm/nmi.h
index f677382093f3..79d88d12c8fb 100644
--- a/arch/x86/include/asm/nmi.h
+++ b/arch/x86/include/asm/nmi.h
@@ -14,12 +14,26 @@ extern void release_perfctr_nmi(unsigned int);
extern int reserve_evntsel_nmi(unsigned int);
extern void release_evntsel_nmi(unsigned int);
-extern int unknown_nmi_panic;
-
#endif /* CONFIG_X86_LOCAL_APIC */
+extern int unknown_nmi_panic;
+extern int panic_on_unrecovered_nmi;
+extern int panic_on_io_nmi;
+
+/* NMI handler flags */
#define NMI_FLAG_FIRST 1
+/**
+ * enum - NMI types.
+ * @NMI_LOCAL: Local NMI, CPU-specific NMI generated by the Local APIC.
+ * @NMI_UNKNOWN: Unknown NMI, the source of the NMI may not be identified.
+ * @NMI_SERR: System Error NMI, typically triggered by PCI errors.
+ * @NMI_IO_CHECK: I/O Check NMI, related to I/O errors.
+ * @NMI_MAX: Maximum value for NMI types.
+ *
+ * NMI types are used to categorize NMIs and to dispatch them to the
+ * appropriate handler.
+ */
enum {
NMI_LOCAL=0,
NMI_UNKNOWN,
@@ -28,6 +42,7 @@ enum {
NMI_MAX
};
+/* NMI handler return values */
#define NMI_DONE 0
#define NMI_HANDLED 1
@@ -41,6 +56,25 @@ struct nmiaction {
const char *name;
};
+/**
+ * register_nmi_handler - Register a handler for a specific NMI type
+ * @t: NMI type (e.g. NMI_LOCAL)
+ * @fn: The NMI handler
+ * @fg: Flags associated with the NMI handler
+ * @n: Name of the NMI handler
+ * @init: Optional __init* attributes for struct nmiaction
+ *
+ * Adds the provided handler to the list of handlers for the specified
+ * NMI type. Handlers flagged with NMI_FLAG_FIRST would be executed first.
+ *
+ * Sometimes the source of an NMI can't be reliably determined which
+ * results in an NMI being tagged as "unknown". Register an additional
+ * handler using the NMI type - NMI_UNKNOWN to handle such cases. The
+ * caller would get one last chance to assume responsibility for the
+ * NMI.
+ *
+ * Return: 0 on success, or an error code on failure.
+ */
#define register_nmi_handler(t, fn, fg, n, init...) \
({ \
static struct nmiaction init fn##_na = { \
@@ -54,7 +88,16 @@ struct nmiaction {
int __register_nmi_handler(unsigned int, struct nmiaction *);
-void unregister_nmi_handler(unsigned int, const char *);
+/**
+ * unregister_nmi_handler - Unregister a handler for a specific NMI type
+ * @type: NMI type (e.g. NMI_LOCAL)
+ * @name: Name of the NMI handler used during registration
+ *
+ * Removes the handler associated with the specified NMI type from the
+ * NMI handler list. The "name" is used as a lookup key to identify the
+ * handler.
+ */
+void unregister_nmi_handler(unsigned int type, const char *name);
void set_emergency_nmi_handler(unsigned int type, nmi_handler_t handler);
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 7d04ade33541..10f261678749 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -302,32 +302,38 @@
.endm
/*
- * Macro to execute VERW instruction that mitigate transient data sampling
- * attacks such as MDS. On affected systems a microcode update overloaded VERW
- * instruction to also clear the CPU buffers. VERW clobbers CFLAGS.ZF.
- *
+ * Macro to execute VERW insns that mitigate transient data sampling
+ * attacks such as MDS or TSA. On affected systems a microcode update
+ * overloaded VERW insns to also clear the CPU buffers. VERW clobbers
+ * CFLAGS.ZF.
* Note: Only the memory operand variant of VERW clears the CPU buffers.
*/
-.macro CLEAR_CPU_BUFFERS
+.macro __CLEAR_CPU_BUFFERS feature
#ifdef CONFIG_X86_64
- ALTERNATIVE "", "verw mds_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF
+ ALTERNATIVE "", "verw x86_verw_sel(%rip)", \feature
#else
/*
* In 32bit mode, the memory operand must be a %cs reference. The data
* segments may not be usable (vm86 mode), and the stack segment may not
* be flat (ESPFIX32).
*/
- ALTERNATIVE "", "verw %cs:mds_verw_sel", X86_FEATURE_CLEAR_CPU_BUF
+ ALTERNATIVE "", "verw %cs:x86_verw_sel", \feature
#endif
.endm
+#define CLEAR_CPU_BUFFERS \
+ __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF
+
+#define VM_CLEAR_CPU_BUFFERS \
+ __CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF_VM
+
#ifdef CONFIG_X86_64
.macro CLEAR_BRANCH_HISTORY
ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
.endm
.macro CLEAR_BRANCH_HISTORY_VMEXIT
- ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT
+ ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_VMEXIT
.endm
#else
#define CLEAR_BRANCH_HISTORY
@@ -567,24 +573,24 @@ DECLARE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
DECLARE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
-DECLARE_STATIC_KEY_FALSE(mds_idle_clear);
+DECLARE_STATIC_KEY_FALSE(cpu_buf_idle_clear);
DECLARE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
-DECLARE_STATIC_KEY_FALSE(mmio_stale_data_clear);
+DECLARE_STATIC_KEY_FALSE(cpu_buf_vm_clear);
-extern u16 mds_verw_sel;
+extern u16 x86_verw_sel;
#include <asm/segment.h>
/**
- * mds_clear_cpu_buffers - Mitigation for MDS and TAA vulnerability
+ * x86_clear_cpu_buffers - Buffer clearing support for different x86 CPU vulns
*
* This uses the otherwise unused and obsolete VERW instruction in
* combination with microcode which triggers a CPU buffer flush when the
* instruction is executed.
*/
-static __always_inline void mds_clear_cpu_buffers(void)
+static __always_inline void x86_clear_cpu_buffers(void)
{
static const u16 ds = __KERNEL_DS;
@@ -601,14 +607,15 @@ static __always_inline void mds_clear_cpu_buffers(void)
}
/**
- * mds_idle_clear_cpu_buffers - Mitigation for MDS vulnerability
+ * x86_idle_clear_cpu_buffers - Buffer clearing support in idle for the MDS
+ * and TSA vulnerabilities.
*
* Clear CPU buffers if the corresponding static key is enabled
*/
-static __always_inline void mds_idle_clear_cpu_buffers(void)
+static __always_inline void x86_idle_clear_cpu_buffers(void)
{
- if (static_branch_likely(&mds_idle_clear))
- mds_clear_cpu_buffers();
+ if (static_branch_likely(&cpu_buf_idle_clear))
+ x86_clear_cpu_buffers();
}
#endif /* __ASSEMBLER__ */
diff --git a/arch/x86/include/asm/page_32_types.h b/arch/x86/include/asm/page_32_types.h
index a9b62e0e6f79..623f1e9f493e 100644
--- a/arch/x86/include/asm/page_32_types.h
+++ b/arch/x86/include/asm/page_32_types.h
@@ -73,7 +73,6 @@ extern unsigned int __VMALLOC_RESERVE;
extern int sysctl_legacy_va_layout;
extern void find_low_pfn_range(void);
-extern void setup_bootmem_allocator(void);
#endif /* !__ASSEMBLER__ */
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index d3aab6f4e59a..015d23f3e01f 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -62,7 +62,6 @@ static inline void clear_page(void *page)
void copy_page(void *to, void *from);
KCFI_REFERENCE(copy_page);
-#ifdef CONFIG_X86_5LEVEL
/*
* User space process size. This is the first address outside the user range.
* There are a few constraints that determine this:
@@ -93,7 +92,6 @@ static __always_inline unsigned long task_size_max(void)
return ret;
}
-#endif /* CONFIG_X86_5LEVEL */
#endif /* !__ASSEMBLER__ */
diff --git a/arch/x86/include/asm/page_64_types.h b/arch/x86/include/asm/page_64_types.h
index 1faa8f88850a..7400dab373fe 100644
--- a/arch/x86/include/asm/page_64_types.h
+++ b/arch/x86/include/asm/page_64_types.h
@@ -41,25 +41,14 @@
#define __PAGE_OFFSET_BASE_L5 _AC(0xff11000000000000, UL)
#define __PAGE_OFFSET_BASE_L4 _AC(0xffff888000000000, UL)
-#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
#define __PAGE_OFFSET page_offset_base
-#else
-#define __PAGE_OFFSET __PAGE_OFFSET_BASE_L4
-#endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
#define __START_KERNEL_map _AC(0xffffffff80000000, UL)
/* See Documentation/arch/x86/x86_64/mm.rst for a description of the memory map. */
#define __PHYSICAL_MASK_SHIFT 52
-
-#ifdef CONFIG_X86_5LEVEL
#define __VIRTUAL_MASK_SHIFT (pgtable_l5_enabled() ? 56 : 47)
-/* See task_size_max() in <asm/page_64.h> */
-#else
-#define __VIRTUAL_MASK_SHIFT 47
-#define task_size_max() ((_AC(1,UL) << __VIRTUAL_MASK_SHIFT) - PAGE_SIZE)
-#endif
#define TASK_SIZE_MAX task_size_max()
#define DEFAULT_MAP_WINDOW ((1UL << 47) - PAGE_SIZE)
diff --git a/arch/x86/include/asm/page_types.h b/arch/x86/include/asm/page_types.h
index 9f77bf03d747..018a8d906ca3 100644
--- a/arch/x86/include/asm/page_types.h
+++ b/arch/x86/include/asm/page_types.h
@@ -29,9 +29,7 @@
#define VM_DATA_DEFAULT_FLAGS VM_DATA_FLAGS_TSK_EXEC
/* Physical address where kernel should be loaded. */
-#define LOAD_PHYSICAL_ADDR ((CONFIG_PHYSICAL_START \
- + (CONFIG_PHYSICAL_ALIGN - 1)) \
- & ~(CONFIG_PHYSICAL_ALIGN - 1))
+#define LOAD_PHYSICAL_ADDR __ALIGN_KERNEL_MASK(CONFIG_PHYSICAL_START, CONFIG_PHYSICAL_ALIGN - 1)
#define __START_KERNEL (__START_KERNEL_map + LOAD_PHYSICAL_ADDR)
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index c4c23190925c..b5e59a7ba0d0 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -175,26 +175,24 @@ static inline void __write_cr4(unsigned long x)
PVOP_VCALL1(cpu.write_cr4, x);
}
-static inline u64 paravirt_read_msr(unsigned msr)
+static inline u64 paravirt_read_msr(u32 msr)
{
return PVOP_CALL1(u64, cpu.read_msr, msr);
}
-static inline void paravirt_write_msr(unsigned msr,
- unsigned low, unsigned high)
+static inline void paravirt_write_msr(u32 msr, u64 val)
{
- PVOP_VCALL3(cpu.write_msr, msr, low, high);
+ PVOP_VCALL2(cpu.write_msr, msr, val);
}
-static inline u64 paravirt_read_msr_safe(unsigned msr, int *err)
+static inline int paravirt_read_msr_safe(u32 msr, u64 *val)
{
- return PVOP_CALL2(u64, cpu.read_msr_safe, msr, err);
+ return PVOP_CALL2(int, cpu.read_msr_safe, msr, val);
}
-static inline int paravirt_write_msr_safe(unsigned msr,
- unsigned low, unsigned high)
+static inline int paravirt_write_msr_safe(u32 msr, u64 val)
{
- return PVOP_CALL3(int, cpu.write_msr_safe, msr, low, high);
+ return PVOP_CALL2(int, cpu.write_msr_safe, msr, val);
}
#define rdmsr(msr, val1, val2) \
@@ -204,55 +202,46 @@ do { \
val2 = _l >> 32; \
} while (0)
-#define wrmsr(msr, val1, val2) \
-do { \
- paravirt_write_msr(msr, val1, val2); \
-} while (0)
+static __always_inline void wrmsr(u32 msr, u32 low, u32 high)
+{
+ paravirt_write_msr(msr, (u64)high << 32 | low);
+}
-#define rdmsrl(msr, val) \
+#define rdmsrq(msr, val) \
do { \
val = paravirt_read_msr(msr); \
} while (0)
-static inline void wrmsrl(unsigned msr, u64 val)
+static inline void wrmsrq(u32 msr, u64 val)
{
- wrmsr(msr, (u32)val, (u32)(val>>32));
+ paravirt_write_msr(msr, val);
}
-#define wrmsr_safe(msr, a, b) paravirt_write_msr_safe(msr, a, b)
+static inline int wrmsrq_safe(u32 msr, u64 val)
+{
+ return paravirt_write_msr_safe(msr, val);
+}
/* rdmsr with exception handling */
#define rdmsr_safe(msr, a, b) \
({ \
- int _err; \
- u64 _l = paravirt_read_msr_safe(msr, &_err); \
+ u64 _l; \
+ int _err = paravirt_read_msr_safe((msr), &_l); \
(*a) = (u32)_l; \
- (*b) = _l >> 32; \
+ (*b) = (u32)(_l >> 32); \
_err; \
})
-static inline int rdmsrl_safe(unsigned msr, unsigned long long *p)
+static __always_inline int rdmsrq_safe(u32 msr, u64 *p)
{
- int err;
-
- *p = paravirt_read_msr_safe(msr, &err);
- return err;
+ return paravirt_read_msr_safe(msr, p);
}
-static inline unsigned long long paravirt_read_pmc(int counter)
+static __always_inline u64 rdpmc(int counter)
{
return PVOP_CALL1(u64, cpu.read_pmc, counter);
}
-#define rdpmc(counter, low, high) \
-do { \
- u64 _l = paravirt_read_pmc(counter); \
- low = (u32)_l; \
- high = _l >> 32; \
-} while (0)
-
-#define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter))
-
static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries)
{
PVOP_VCALL2(cpu.alloc_ldt, ldt, entries);
@@ -474,8 +463,6 @@ static inline void set_p4d(p4d_t *p4dp, p4d_t p4d)
PVOP_VCALL2(mmu.set_p4d, p4dp, val);
}
-#if CONFIG_PGTABLE_LEVELS >= 5
-
static inline p4d_t __p4d(p4dval_t val)
{
p4dval_t ret = PVOP_ALT_CALLEE1(p4dval_t, mmu.make_p4d, val,
@@ -507,8 +494,6 @@ static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd)
set_pgd(pgdp, native_make_pgd(0)); \
} while (0)
-#endif /* CONFIG_PGTABLE_LEVELS == 5 */
-
static inline void p4d_clear(p4d_t *p4dp)
{
set_p4d(p4dp, native_make_p4d(0));
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 631c306ce1ff..37a8627d8277 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -91,15 +91,15 @@ struct pv_cpu_ops {
unsigned int *ecx, unsigned int *edx);
/* Unsafe MSR operations. These will warn or panic on failure. */
- u64 (*read_msr)(unsigned int msr);
- void (*write_msr)(unsigned int msr, unsigned low, unsigned high);
+ u64 (*read_msr)(u32 msr);
+ void (*write_msr)(u32 msr, u64 val);
/*
* Safe MSR operations.
- * read sets err to 0 or -EIO. write returns 0 or -EIO.
+ * Returns 0 or -EIO.
*/
- u64 (*read_msr_safe)(unsigned int msr, int *err);
- int (*write_msr_safe)(unsigned int msr, unsigned low, unsigned high);
+ int (*read_msr_safe)(u32 msr, u64 *val);
+ int (*write_msr_safe)(u32 msr, u64 val);
u64 (*read_pmc)(int counter);
@@ -189,12 +189,10 @@ struct pv_mmu_ops {
void (*set_p4d)(p4d_t *p4dp, p4d_t p4dval);
-#if CONFIG_PGTABLE_LEVELS >= 5
struct paravirt_callee_save p4d_val;
struct paravirt_callee_save make_p4d;
void (*set_pgd)(pgd_t *pgdp, pgd_t pgdval);
-#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
struct pv_lazy_ops lazy_mode;
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index 5fe314a2e73e..b0d03b6c279b 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -29,6 +29,8 @@
#ifdef CONFIG_SMP
+#define __force_percpu_prefix "%%"__stringify(__percpu_seg)":"
+
#ifdef CONFIG_CC_HAS_NAMED_AS
#ifdef __CHECKER__
@@ -36,23 +38,23 @@
# define __seg_fs __attribute__((address_space(__seg_fs)))
#endif
+#define __percpu_prefix
#define __percpu_seg_override CONCATENATE(__seg_, __percpu_seg)
-#define __percpu_prefix ""
#else /* !CONFIG_CC_HAS_NAMED_AS: */
+#define __percpu_prefix __force_percpu_prefix
#define __percpu_seg_override
-#define __percpu_prefix "%%"__stringify(__percpu_seg)":"
#endif /* CONFIG_CC_HAS_NAMED_AS */
-#define __force_percpu_prefix "%%"__stringify(__percpu_seg)":"
-#define __my_cpu_offset this_cpu_read(this_cpu_off)
-
/*
* Compared to the generic __my_cpu_offset version, the following
* saves one instruction and avoids clobbering a temp register.
- *
+ */
+#define __my_cpu_offset this_cpu_read(this_cpu_off)
+
+/*
* arch_raw_cpu_ptr should not be used in 32-bit VDSO for a 64-bit
* kernel, because games are played with CONFIG_X86_64 there and
* sizeof(this_cpu_off) becames 4.
@@ -77,9 +79,9 @@
#else /* !CONFIG_SMP: */
+#define __force_percpu_prefix
+#define __percpu_prefix
#define __percpu_seg_override
-#define __percpu_prefix ""
-#define __force_percpu_prefix ""
#define PER_CPU_VAR(var) (var)__percpu_rel
@@ -97,8 +99,8 @@
# define __my_cpu_var(var) (*__my_cpu_ptr(&(var)))
#endif
-#define __percpu_arg(x) __percpu_prefix "%" #x
#define __force_percpu_arg(x) __force_percpu_prefix "%" #x
+#define __percpu_arg(x) __percpu_prefix "%" #x
/*
* For arch-specific code, we can use direct single-insn ops (they
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 812dac3f79f0..70d1d94aca7e 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -195,6 +195,7 @@ union cpuid10_edx {
*/
#define ARCH_PERFMON_EXT_LEAF 0x00000023
#define ARCH_PERFMON_NUM_COUNTER_LEAF 0x1
+#define ARCH_PERFMON_ACR_LEAF 0x2
union cpuid35_eax {
struct {
diff --git a/arch/x86/include/asm/pgtable-2level_types.h b/arch/x86/include/asm/pgtable-2level_types.h
index 66425424ce91..54690bd4ddbe 100644
--- a/arch/x86/include/asm/pgtable-2level_types.h
+++ b/arch/x86/include/asm/pgtable-2level_types.h
@@ -18,8 +18,6 @@ typedef union {
} pte_t;
#endif /* !__ASSEMBLER__ */
-#define SHARED_KERNEL_PMD 0
-
#define ARCH_PAGE_TABLE_SYNC_MASK PGTBL_PMD_MODIFIED
/*
diff --git a/arch/x86/include/asm/pgtable-3level_types.h b/arch/x86/include/asm/pgtable-3level_types.h
index 9d5b257d44e3..580b09bf6a45 100644
--- a/arch/x86/include/asm/pgtable-3level_types.h
+++ b/arch/x86/include/asm/pgtable-3level_types.h
@@ -27,9 +27,7 @@ typedef union {
} pmd_t;
#endif /* !__ASSEMBLER__ */
-#define SHARED_KERNEL_PMD (!static_cpu_has(X86_FEATURE_PTI))
-
-#define ARCH_PAGE_TABLE_SYNC_MASK (SHARED_KERNEL_PMD ? 0 : PGTBL_PMD_MODIFIED)
+#define ARCH_PAGE_TABLE_SYNC_MASK PGTBL_PMD_MODIFIED
/*
* PGDIR_SHIFT determines what a top-level page table entry can map
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 7bd6bd6df4a1..e33df3da6980 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -292,13 +292,6 @@ static inline unsigned long pgd_pfn(pgd_t pgd)
return (pgd_val(pgd) & PTE_PFN_MASK) >> PAGE_SHIFT;
}
-#define p4d_leaf p4d_leaf
-static inline bool p4d_leaf(p4d_t p4d)
-{
- /* No 512 GiB pages yet */
- return 0;
-}
-
#define pte_page(pte) pfn_to_page(pte_pfn(pte))
#define pmd_leaf pmd_leaf
@@ -308,16 +301,15 @@ static inline bool pmd_leaf(pmd_t pte)
}
#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_leaf */
static inline int pmd_trans_huge(pmd_t pmd)
{
- return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
+ return (pmd_val(pmd) & _PAGE_PSE) == _PAGE_PSE;
}
#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
static inline int pud_trans_huge(pud_t pud)
{
- return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
+ return (pud_val(pud) & _PAGE_PSE) == _PAGE_PSE;
}
#endif
@@ -327,24 +319,6 @@ static inline int has_transparent_hugepage(void)
return boot_cpu_has(X86_FEATURE_PSE);
}
-#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
-static inline int pmd_devmap(pmd_t pmd)
-{
- return !!(pmd_val(pmd) & _PAGE_DEVMAP);
-}
-
-#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-static inline int pud_devmap(pud_t pud)
-{
- return !!(pud_val(pud) & _PAGE_DEVMAP);
-}
-#else
-static inline int pud_devmap(pud_t pud)
-{
- return 0;
-}
-#endif
-
#ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
static inline bool pmd_special(pmd_t pmd)
{
@@ -368,12 +342,6 @@ static inline pud_t pud_mkspecial(pud_t pud)
return pud_set_flags(pud, _PAGE_SPECIAL);
}
#endif /* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */
-
-static inline int pgd_devmap(pgd_t pgd)
-{
- return 0;
-}
-#endif
#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
static inline pte_t pte_set_flags(pte_t pte, pteval_t set)
@@ -534,11 +502,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
return pte_set_flags(pte, _PAGE_SPECIAL);
}
-static inline pte_t pte_mkdevmap(pte_t pte)
-{
- return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP);
-}
-
/* See comments above mksaveddirty_shift() */
static inline pmd_t pmd_mksaveddirty(pmd_t pmd)
{
@@ -610,11 +573,6 @@ static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd)
return pmd_set_flags(pmd, _PAGE_DIRTY);
}
-static inline pmd_t pmd_mkdevmap(pmd_t pmd)
-{
- return pmd_set_flags(pmd, _PAGE_DEVMAP);
-}
-
static inline pmd_t pmd_mkhuge(pmd_t pmd)
{
return pmd_set_flags(pmd, _PAGE_PSE);
@@ -680,11 +638,6 @@ static inline pud_t pud_mkdirty(pud_t pud)
return pud_mksaveddirty(pud);
}
-static inline pud_t pud_mkdevmap(pud_t pud)
-{
- return pud_set_flags(pud, _PAGE_DEVMAP);
-}
-
static inline pud_t pud_mkhuge(pud_t pud)
{
return pud_set_flags(pud, _PAGE_PSE);
@@ -784,6 +737,9 @@ static inline pgprotval_t check_pgprot(pgprot_t pgprot)
static inline pte_t pfn_pte(unsigned long page_nr, pgprot_t pgprot)
{
phys_addr_t pfn = (phys_addr_t)page_nr << PAGE_SHIFT;
+ /* This bit combination is used to mark shadow stacks */
+ WARN_ON_ONCE((pgprot_val(pgprot) & (_PAGE_DIRTY | _PAGE_RW)) ==
+ _PAGE_DIRTY);
pfn ^= protnone_mask(pgprot_val(pgprot));
pfn &= PTE_PFN_MASK;
return __pte(pfn | check_pgprot(pgprot));
@@ -1012,13 +968,6 @@ static inline int pte_present(pte_t a)
return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
}
-#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
-static inline int pte_devmap(pte_t a)
-{
- return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP;
-}
-#endif
-
#define pte_accessible pte_accessible
static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
{
@@ -1080,22 +1029,6 @@ static inline unsigned long pmd_page_vaddr(pmd_t pmd)
*/
#define pmd_page(pmd) pfn_to_page(pmd_pfn(pmd))
-/*
- * Conversion functions: convert a page and protection to a page entry,
- * and a page entry and page directory to the page they refer to.
- *
- * (Currently stuck as a macro because of indirect forward reference
- * to linux/mm.h:page_to_nid())
- */
-#define mk_pte(page, pgprot) \
-({ \
- pgprot_t __pgprot = pgprot; \
- \
- WARN_ON_ONCE((pgprot_val(__pgprot) & (_PAGE_DIRTY | _PAGE_RW)) == \
- _PAGE_DIRTY); \
- pfn_pte(page_to_pfn(page), __pgprot); \
-})
-
static inline int pmd_bad(pmd_t pmd)
{
return (pmd_flags(pmd) & ~(_PAGE_USER | _PAGE_ACCESSED)) !=
@@ -1360,8 +1293,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm,
#define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0)
-#define mk_pmd(page, pgprot) pfn_pmd(page_to_pfn(page), (pgprot))
-
#define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS
extern int pmdp_set_access_flags(struct vm_area_struct *vma,
unsigned long address, pmd_t *pmdp,
@@ -1472,9 +1403,6 @@ static inline bool pgdp_maps_userspace(void *__ptr)
return (((ptr & ~PAGE_MASK) / sizeof(pgd_t)) < PGD_KERNEL_START);
}
-#define pgd_leaf pgd_leaf
-static inline bool pgd_leaf(pgd_t pgd) { return false; }
-
#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
/*
* All top-level MITIGATION_PAGE_TABLE_ISOLATION page tables are order-1 pages
@@ -1586,7 +1514,7 @@ static inline pte_t pte_swp_mkexclusive(pte_t pte)
return pte_set_flags(pte, _PAGE_SWP_EXCLUSIVE);
}
-static inline int pte_swp_exclusive(pte_t pte)
+static inline bool pte_swp_exclusive(pte_t pte)
{
return pte_flags(pte) & _PAGE_SWP_EXCLUSIVE;
}
diff --git a/arch/x86/include/asm/pgtable_64.h b/arch/x86/include/asm/pgtable_64.h
index b89f8f1194a9..f06e5d6a2747 100644
--- a/arch/x86/include/asm/pgtable_64.h
+++ b/arch/x86/include/asm/pgtable_64.h
@@ -41,11 +41,9 @@ static inline void sync_initial_page_table(void) { }
pr_err("%s:%d: bad pud %p(%016lx)\n", \
__FILE__, __LINE__, &(e), pud_val(e))
-#if CONFIG_PGTABLE_LEVELS >= 5
#define p4d_ERROR(e) \
pr_err("%s:%d: bad p4d %p(%016lx)\n", \
__FILE__, __LINE__, &(e), p4d_val(e))
-#endif
#define pgd_ERROR(e) \
pr_err("%s:%d: bad pgd %p(%016lx)\n", \
diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 5bb782d856f2..4604f924d8b8 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -23,7 +23,6 @@ typedef struct { pmdval_t pmd; } pmd_t;
extern unsigned int __pgtable_l5_enabled;
-#ifdef CONFIG_X86_5LEVEL
#ifdef USE_EARLY_PGTABLE_L5
/*
* cpu_feature_enabled() is not available in early boot code.
@@ -37,19 +36,11 @@ static inline bool pgtable_l5_enabled(void)
#define pgtable_l5_enabled() cpu_feature_enabled(X86_FEATURE_LA57)
#endif /* USE_EARLY_PGTABLE_L5 */
-#else
-#define pgtable_l5_enabled() 0
-#endif /* CONFIG_X86_5LEVEL */
-
extern unsigned int pgdir_shift;
extern unsigned int ptrs_per_p4d;
#endif /* !__ASSEMBLER__ */
-#define SHARED_KERNEL_PMD 0
-
-#ifdef CONFIG_X86_5LEVEL
-
/*
* PGDIR_SHIFT determines what a top-level page table entry can map
*/
@@ -67,17 +58,6 @@ extern unsigned int ptrs_per_p4d;
#define MAX_POSSIBLE_PHYSMEM_BITS 52
-#else /* CONFIG_X86_5LEVEL */
-
-/*
- * PGDIR_SHIFT determines what a top-level page table entry can map
- */
-#define PGDIR_SHIFT 39
-#define PTRS_PER_PGD 512
-#define MAX_PTRS_PER_P4D 1
-
-#endif /* CONFIG_X86_5LEVEL */
-
/*
* 3rd level page
*/
@@ -130,15 +110,9 @@ extern unsigned int ptrs_per_p4d;
#define __VMEMMAP_BASE_L4 0xffffea0000000000UL
#define __VMEMMAP_BASE_L5 0xffd4000000000000UL
-#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
# define VMALLOC_START vmalloc_base
# define VMALLOC_SIZE_TB (pgtable_l5_enabled() ? VMALLOC_SIZE_TB_L5 : VMALLOC_SIZE_TB_L4)
# define VMEMMAP_START vmemmap_base
-#else
-# define VMALLOC_START __VMALLOC_BASE_L4
-# define VMALLOC_SIZE_TB VMALLOC_SIZE_TB_L4
-# define VMEMMAP_START __VMEMMAP_BASE_L4
-#endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
#ifdef CONFIG_RANDOMIZE_MEMORY
# define DIRECT_MAP_PHYSMEM_END direct_map_physmem_end
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b74ec5c3643b..2ec250ba467e 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -34,7 +34,6 @@
#define _PAGE_BIT_UFFD_WP _PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */
#define _PAGE_BIT_SOFT_DIRTY _PAGE_BIT_SOFTW3 /* software dirty tracking */
#define _PAGE_BIT_KERNEL_4K _PAGE_BIT_SOFTW3 /* page must not be converted to large */
-#define _PAGE_BIT_DEVMAP _PAGE_BIT_SOFTW4
#ifdef CONFIG_X86_64
#define _PAGE_BIT_SAVED_DIRTY _PAGE_BIT_SOFTW5 /* Saved Dirty bit (leaf) */
@@ -121,11 +120,9 @@
#if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
#define _PAGE_NX (_AT(pteval_t, 1) << _PAGE_BIT_NX)
-#define _PAGE_DEVMAP (_AT(u64, 1) << _PAGE_BIT_DEVMAP)
#define _PAGE_SOFTW4 (_AT(pteval_t, 1) << _PAGE_BIT_SOFTW4)
#else
#define _PAGE_NX (_AT(pteval_t, 0))
-#define _PAGE_DEVMAP (_AT(pteval_t, 0))
#define _PAGE_SOFTW4 (_AT(pteval_t, 0))
#endif
@@ -154,7 +151,7 @@
#define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \
_PAGE_SPECIAL | _PAGE_ACCESSED | \
_PAGE_DIRTY_BITS | _PAGE_SOFT_DIRTY | \
- _PAGE_DEVMAP | _PAGE_CC | _PAGE_UFFD_WP)
+ _PAGE_CC | _PAGE_UFFD_WP)
#define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT)
#define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE)
@@ -214,9 +211,6 @@ enum page_cache_mode {
#define PAGE_READONLY __pg(__PP| 0|_USR|___A|__NX| 0| 0| 0)
#define PAGE_READONLY_EXEC __pg(__PP| 0|_USR|___A| 0| 0| 0| 0)
-#define __PAGE_KERNEL (__PP|__RW| 0|___A|__NX|___D| 0|___G)
-#define __PAGE_KERNEL_EXEC (__PP|__RW| 0|___A| 0|___D| 0|___G)
-
/*
* Page tables needs to have Write=1 in order for any lower PTEs to be
* writable. This includes shadow stack memory (Write=0, Dirty=1)
diff --git a/arch/x86/include/asm/posted_intr.h b/arch/x86/include/asm/posted_intr.h
index de788b400fba..a5f761fbf45b 100644
--- a/arch/x86/include/asm/posted_intr.h
+++ b/arch/x86/include/asm/posted_intr.h
@@ -1,19 +1,24 @@
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef _X86_POSTED_INTR_H
#define _X86_POSTED_INTR_H
+
+#include <asm/cmpxchg.h>
+#include <asm/rwonce.h>
#include <asm/irq_vectors.h>
+#include <linux/bitmap.h>
+
#define POSTED_INTR_ON 0
#define POSTED_INTR_SN 1
#define PID_TABLE_ENTRY_VALID 1
+#define NR_PIR_VECTORS 256
+#define NR_PIR_WORDS (NR_PIR_VECTORS / BITS_PER_LONG)
+
/* Posted-Interrupt Descriptor */
struct pi_desc {
- union {
- u32 pir[8]; /* Posted interrupt requested */
- u64 pir64[4];
- };
+ unsigned long pir[NR_PIR_WORDS]; /* Posted interrupt requested */
union {
struct {
u16 notifications; /* Suppress and outstanding bits */
@@ -26,6 +31,65 @@ struct pi_desc {
u32 rsvd[6];
} __aligned(64);
+/*
+ * De-multiplexing posted interrupts is on the performance path, the code
+ * below is written to optimize the cache performance based on the following
+ * considerations:
+ * 1.Posted interrupt descriptor (PID) fits in a cache line that is frequently
+ * accessed by both CPU and IOMMU.
+ * 2.During software processing of posted interrupts, the CPU needs to do
+ * natural width read and xchg for checking and clearing posted interrupt
+ * request (PIR), a 256 bit field within the PID.
+ * 3.On the other side, the IOMMU does atomic swaps of the entire PID cache
+ * line when posting interrupts and setting control bits.
+ * 4.The CPU can access the cache line a magnitude faster than the IOMMU.
+ * 5.Each time the IOMMU does interrupt posting to the PIR will evict the PID
+ * cache line. The cache line states after each operation are as follows,
+ * assuming a 64-bit kernel:
+ * CPU IOMMU PID Cache line state
+ * ---------------------------------------------------------------
+ *...read64 exclusive
+ *...lock xchg64 modified
+ *... post/atomic swap invalid
+ *...-------------------------------------------------------------
+ *
+ * To reduce L1 data cache miss, it is important to avoid contention with
+ * IOMMU's interrupt posting/atomic swap. Therefore, a copy of PIR is used
+ * when processing posted interrupts in software, e.g. to dispatch interrupt
+ * handlers for posted MSIs, or to move interrupts from the PIR to the vIRR
+ * in KVM.
+ *
+ * In addition, the code is trying to keep the cache line state consistent
+ * as much as possible. e.g. when making a copy and clearing the PIR
+ * (assuming non-zero PIR bits are present in the entire PIR), it does:
+ * read, read, read, read, xchg, xchg, xchg, xchg
+ * instead of:
+ * read, xchg, read, xchg, read, xchg, read, xchg
+ */
+static __always_inline bool pi_harvest_pir(unsigned long *pir,
+ unsigned long *pir_vals)
+{
+ unsigned long pending = 0;
+ int i;
+
+ for (i = 0; i < NR_PIR_WORDS; i++) {
+ pir_vals[i] = READ_ONCE(pir[i]);
+ pending |= pir_vals[i];
+ }
+
+ if (!pending)
+ return false;
+
+ for (i = 0; i < NR_PIR_WORDS; i++) {
+ if (!pir_vals[i])
+ continue;
+
+ pir_vals[i] = arch_xchg(&pir[i], 0);
+ }
+
+ return true;
+}
+
static inline bool pi_test_and_set_on(struct pi_desc *pi_desc)
{
return test_and_set_bit(POSTED_INTR_ON, (unsigned long *)&pi_desc->control);
@@ -43,12 +107,12 @@ static inline bool pi_test_and_clear_sn(struct pi_desc *pi_desc)
static inline bool pi_test_and_set_pir(int vector, struct pi_desc *pi_desc)
{
- return test_and_set_bit(vector, (unsigned long *)pi_desc->pir);
+ return test_and_set_bit(vector, pi_desc->pir);
}
static inline bool pi_is_pir_empty(struct pi_desc *pi_desc)
{
- return bitmap_empty((unsigned long *)pi_desc->pir, NR_VECTORS);
+ return bitmap_empty(pi_desc->pir, NR_VECTORS);
}
static inline void pi_set_sn(struct pi_desc *pi_desc)
@@ -81,6 +145,11 @@ static inline bool pi_test_sn(struct pi_desc *pi_desc)
return test_bit(POSTED_INTR_SN, (unsigned long *)&pi_desc->control);
}
+static inline bool pi_test_pir(int vector, struct pi_desc *pi_desc)
+{
+ return test_bit(vector, (unsigned long *)pi_desc->pir);
+}
+
/* Non-atomic helpers */
static inline void __pi_set_sn(struct pi_desc *pi_desc)
{
@@ -105,7 +174,7 @@ static inline bool pi_pending_this_cpu(unsigned int vector)
if (WARN_ON_ONCE(vector > NR_VECTORS || vector < FIRST_EXTERNAL_VECTOR))
return false;
- return test_bit(vector, (unsigned long *)pid->pir);
+ return test_bit(vector, pid->pir);
}
extern void intel_posted_msi_init(void);
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 5d2f7e5aff26..bde58f6510ac 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -16,7 +16,7 @@ struct vm86;
#include <uapi/asm/sigcontext.h>
#include <asm/current.h>
#include <asm/cpufeatures.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/page.h>
#include <asm/pgtable_types.h>
#include <asm/percpu.h>
@@ -514,15 +514,14 @@ struct thread_struct {
struct thread_shstk shstk;
#endif
-
- /* Floating point and extended processor state */
- struct fpu fpu;
- /*
- * WARNING: 'fpu' is dynamically-sized. It *MUST* be at
- * the end.
- */
};
+#ifdef CONFIG_X86_DEBUG_FPU
+extern struct fpu *x86_task_fpu(struct task_struct *task);
+#else
+# define x86_task_fpu(task) ((struct fpu *)((void *)(task) + sizeof(*(task))))
+#endif
+
extern void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size);
static inline void arch_thread_struct_whitelist(unsigned long *offset,
@@ -734,6 +733,7 @@ void store_cpu_caps(struct cpuinfo_x86 *info);
enum l1tf_mitigations {
L1TF_MITIGATION_OFF,
+ L1TF_MITIGATION_AUTO,
L1TF_MITIGATION_FLUSH_NOWARN,
L1TF_MITIGATION_FLUSH,
L1TF_MITIGATION_FLUSH_NOSMT,
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index f607081a022a..e406a1e92c63 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -78,7 +78,7 @@ extern unsigned char secondary_startup_64[];
extern unsigned char secondary_startup_64_no_verify[];
#endif
-static inline size_t real_mode_size_needed(void)
+static __always_inline size_t real_mode_size_needed(void)
{
if (real_mode_header)
return 0; /* already allocated. */
diff --git a/arch/x86/include/asm/resctrl.h b/arch/x86/include/asm/resctrl.h
index 011bf67a1866..feb93b50e990 100644
--- a/arch/x86/include/asm/resctrl.h
+++ b/arch/x86/include/asm/resctrl.h
@@ -9,6 +9,8 @@
#include <linux/resctrl_types.h>
#include <linux/sched.h>
+#include <asm/msr.h>
+
/*
* This value can never be a valid CLOSID, and is used when mapping a
* (closid, rmid) pair to an index and back. On x86 only the RMID is
@@ -175,7 +177,7 @@ static inline bool resctrl_arch_match_rmid(struct task_struct *tsk, u32 ignored,
return READ_ONCE(tsk->rmid) == rmid;
}
-static inline void resctrl_sched_in(struct task_struct *tsk)
+static inline void resctrl_arch_sched_in(struct task_struct *tsk)
{
if (static_branch_likely(&rdt_enable_key))
__resctrl_sched_in(tsk);
@@ -194,25 +196,22 @@ static inline u32 resctrl_arch_rmid_idx_encode(u32 ignored, u32 rmid)
/* x86 can always read an rmid, nothing needs allocating */
struct rdt_resource;
-static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r, int evtid)
+static inline void *resctrl_arch_mon_ctx_alloc(struct rdt_resource *r,
+ enum resctrl_event_id evtid)
{
might_sleep();
return NULL;
-};
+}
-static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r, int evtid,
- void *ctx) { };
+static inline void resctrl_arch_mon_ctx_free(struct rdt_resource *r,
+ enum resctrl_event_id evtid,
+ void *ctx) { }
-u64 resctrl_arch_get_prefetch_disable_bits(void);
-int resctrl_arch_pseudo_lock_fn(void *_plr);
-int resctrl_arch_measure_cycles_lat_fn(void *_plr);
-int resctrl_arch_measure_l2_residency(void *_plr);
-int resctrl_arch_measure_l3_residency(void *_plr);
void resctrl_cpu_detect(struct cpuinfo_x86 *c);
#else
-static inline void resctrl_sched_in(struct task_struct *tsk) {}
+static inline void resctrl_arch_sched_in(struct task_struct *tsk) {}
static inline void resctrl_cpu_detect(struct cpuinfo_x86 *c) {}
#endif /* CONFIG_X86_CPU_RESCTRL */
diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
index 8d9f1c9aaa4c..61f56cdaccb5 100644
--- a/arch/x86/include/asm/set_memory.h
+++ b/arch/x86/include/asm/set_memory.h
@@ -4,6 +4,7 @@
#include <asm/page.h>
#include <asm-generic/set_memory.h>
+#include <asm/pgtable.h>
#define set_memory_rox set_memory_rox
int set_memory_rox(unsigned long addr, int numpages);
@@ -37,6 +38,7 @@ int set_memory_rox(unsigned long addr, int numpages);
* The caller is required to take care of these.
*/
+int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot);
int _set_memory_uc(unsigned long addr, int numpages);
int _set_memory_wc(unsigned long addr, int numpages);
int _set_memory_wt(unsigned long addr, int numpages);
diff --git a/arch/x86/include/asm/setup.h b/arch/x86/include/asm/setup.h
index ad9212df0ec0..692af46603a1 100644
--- a/arch/x86/include/asm/setup.h
+++ b/arch/x86/include/asm/setup.h
@@ -52,6 +52,7 @@ extern void reserve_standard_io_resources(void);
extern void i386_reserve_resources(void);
extern unsigned long __startup_64(unsigned long p2v_offset, struct boot_params *bp);
extern void startup_64_setup_gdt_idt(void);
+extern void startup_64_load_idt(void *vc_handler);
extern void early_setup_idt(void);
extern void __init do_early_exception(struct pt_regs *regs, int trapnr);
@@ -67,6 +68,8 @@ extern void x86_ce4100_early_setup(void);
static inline void x86_ce4100_early_setup(void) { }
#endif
+#include <linux/kexec_handover.h>
+
#ifndef _SETUP
#include <asm/espfix.h>
diff --git a/arch/x86/include/asm/sev-internal.h b/arch/x86/include/asm/sev-internal.h
new file mode 100644
index 000000000000..3dfd306d1c9e
--- /dev/null
+++ b/arch/x86/include/asm/sev-internal.h
@@ -0,0 +1,105 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#define DR7_RESET_VALUE 0x400
+
+extern struct ghcb boot_ghcb_page;
+extern u64 sev_hv_features;
+extern u64 sev_secrets_pa;
+
+/* #VC handler runtime per-CPU data */
+struct sev_es_runtime_data {
+ struct ghcb ghcb_page;
+
+ /*
+ * Reserve one page per CPU as backup storage for the unencrypted GHCB.
+ * It is needed when an NMI happens while the #VC handler uses the real
+ * GHCB, and the NMI handler itself is causing another #VC exception. In
+ * that case the GHCB content of the first handler needs to be backed up
+ * and restored.
+ */
+ struct ghcb backup_ghcb;
+
+ /*
+ * Mark the per-cpu GHCBs as in-use to detect nested #VC exceptions.
+ * There is no need for it to be atomic, because nothing is written to
+ * the GHCB between the read and the write of ghcb_active. So it is safe
+ * to use it when a nested #VC exception happens before the write.
+ *
+ * This is necessary for example in the #VC->NMI->#VC case when the NMI
+ * happens while the first #VC handler uses the GHCB. When the NMI code
+ * raises a second #VC handler it might overwrite the contents of the
+ * GHCB written by the first handler. To avoid this the content of the
+ * GHCB is saved and restored when the GHCB is detected to be in use
+ * already.
+ */
+ bool ghcb_active;
+ bool backup_ghcb_active;
+
+ /*
+ * Cached DR7 value - write it on DR7 writes and return it on reads.
+ * That value will never make it to the real hardware DR7 as debugging
+ * is currently unsupported in SEV-ES guests.
+ */
+ unsigned long dr7;
+};
+
+struct ghcb_state {
+ struct ghcb *ghcb;
+};
+
+extern struct svsm_ca boot_svsm_ca_page;
+
+struct ghcb *__sev_get_ghcb(struct ghcb_state *state);
+void __sev_put_ghcb(struct ghcb_state *state);
+
+DECLARE_PER_CPU(struct sev_es_runtime_data*, runtime_data);
+DECLARE_PER_CPU(struct sev_es_save_area *, sev_vmsa);
+
+void early_set_pages_state(unsigned long vaddr, unsigned long paddr,
+ unsigned long npages, enum psc_op op);
+
+DECLARE_PER_CPU(struct svsm_ca *, svsm_caa);
+DECLARE_PER_CPU(u64, svsm_caa_pa);
+
+extern struct svsm_ca *boot_svsm_caa;
+extern u64 boot_svsm_caa_pa;
+
+static __always_inline struct svsm_ca *svsm_get_caa(void)
+{
+ if (sev_cfg.use_cas)
+ return this_cpu_read(svsm_caa);
+ else
+ return boot_svsm_caa;
+}
+
+static __always_inline u64 svsm_get_caa_pa(void)
+{
+ if (sev_cfg.use_cas)
+ return this_cpu_read(svsm_caa_pa);
+ else
+ return boot_svsm_caa_pa;
+}
+
+int svsm_perform_call_protocol(struct svsm_call *call);
+
+static inline u64 sev_es_rd_ghcb_msr(void)
+{
+ return native_rdmsrq(MSR_AMD64_SEV_ES_GHCB);
+}
+
+static __always_inline void sev_es_wr_ghcb_msr(u64 val)
+{
+ u32 low, high;
+
+ low = (u32)(val);
+ high = (u32)(val >> 32);
+
+ native_wrmsr(MSR_AMD64_SEV_ES_GHCB, low, high);
+}
+
+void snp_register_ghcb_early(unsigned long paddr);
+bool sev_es_negotiate_protocol(void);
+bool sev_es_check_cpu_features(void);
+u64 get_hv_features(void);
+
+const struct snp_cpuid_table *snp_cpuid_get_table(void);
diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h
index ba7999f66abe..02236962fdb1 100644
--- a/arch/x86/include/asm/sev.h
+++ b/arch/x86/include/asm/sev.h
@@ -15,6 +15,7 @@
#include <asm/sev-common.h>
#include <asm/coco.h>
#include <asm/set_memory.h>
+#include <asm/svm.h>
#define GHCB_PROTOCOL_MIN 1ULL
#define GHCB_PROTOCOL_MAX 2ULL
@@ -83,6 +84,36 @@ extern void vc_no_ghcb(void);
extern void vc_boot_ghcb(void);
extern bool handle_vc_boot_ghcb(struct pt_regs *regs);
+/*
+ * Individual entries of the SNP CPUID table, as defined by the SNP
+ * Firmware ABI, Revision 0.9, Section 7.1, Table 14.
+ */
+struct snp_cpuid_fn {
+ u32 eax_in;
+ u32 ecx_in;
+ u64 xcr0_in;
+ u64 xss_in;
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 edx;
+ u64 __reserved;
+} __packed;
+
+/*
+ * SNP CPUID table, as defined by the SNP Firmware ABI, Revision 0.9,
+ * Section 8.14.2.6. Also noted there is the SNP firmware-enforced limit
+ * of 64 entries per CPUID table.
+ */
+#define SNP_CPUID_COUNT_MAX 64
+
+struct snp_cpuid_table {
+ u32 count;
+ u32 __reserved1;
+ u64 __reserved2;
+ struct snp_cpuid_fn fn[SNP_CPUID_COUNT_MAX];
+} __packed;
+
/* PVALIDATE return codes */
#define PVALIDATE_FAIL_SIZEMISMATCH 6
@@ -192,6 +223,18 @@ struct snp_tsc_info_resp {
u8 rsvd2[100];
} __packed;
+/*
+ * Obtain the mean TSC frequency by decreasing the nominal TSC frequency with
+ * TSC_FACTOR as documented in the SNP Firmware ABI specification:
+ *
+ * GUEST_TSC_FREQ * (1 - (TSC_FACTOR * 0.00001))
+ *
+ * which is equivalent to:
+ *
+ * GUEST_TSC_FREQ -= (GUEST_TSC_FREQ * TSC_FACTOR) / 100000;
+ */
+#define SNP_SCALE_TSC_FREQ(freq, factor) ((freq) - (freq) * (factor) / 100000)
+
struct snp_guest_req {
void *req_buf;
size_t req_sz;
@@ -200,6 +243,7 @@ struct snp_guest_req {
size_t resp_sz;
u64 exit_code;
+ u64 exitinfo2;
unsigned int vmpck_id;
u8 msg_version;
u8 msg_type;
@@ -251,8 +295,11 @@ struct snp_secrets_page {
u8 svsm_guest_vmpl;
u8 rsvd3[3];
+ /* The percentage decrease from nominal to mean TSC frequency. */
+ u32 tsc_factor;
+
/* Remainder of page */
- u8 rsvd4[3744];
+ u8 rsvd4[3740];
} __packed;
struct snp_msg_desc {
@@ -384,6 +431,10 @@ struct svsm_call {
#define SVSM_ATTEST_SERVICES 0
#define SVSM_ATTEST_SINGLE_SERVICE 1
+#define SVSM_VTPM_CALL(x) ((2ULL << 32) | (x))
+#define SVSM_VTPM_QUERY 0
+#define SVSM_VTPM_CMD 1
+
#ifdef CONFIG_AMD_MEM_ENCRYPT
extern u8 snp_vmpl;
@@ -410,7 +461,7 @@ static __always_inline void sev_es_nmi_complete(void)
cc_platform_has(CC_ATTR_GUEST_STATE_ENCRYPT))
__sev_es_nmi_complete();
}
-extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd);
+extern int __init sev_es_efi_map_ghcbs_cas(pgd_t *pgd);
extern void sev_enable(struct boot_params *bp);
/*
@@ -451,8 +502,6 @@ static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate)
return rc;
}
-struct snp_guest_request_ioctl;
-
void setup_ghcb(void);
void early_snp_set_memory_private(unsigned long vaddr, unsigned long paddr,
unsigned long npages);
@@ -478,12 +527,41 @@ void snp_kexec_begin(void);
int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id);
struct snp_msg_desc *snp_msg_alloc(void);
void snp_msg_free(struct snp_msg_desc *mdesc);
-int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req,
- struct snp_guest_request_ioctl *rio);
+int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req);
+
+int snp_svsm_vtpm_send_command(u8 *buffer);
void __init snp_secure_tsc_prepare(void);
void __init snp_secure_tsc_init(void);
+static __always_inline void vc_ghcb_invalidate(struct ghcb *ghcb)
+{
+ ghcb->save.sw_exit_code = 0;
+ __builtin_memset(ghcb->save.valid_bitmap, 0, sizeof(ghcb->save.valid_bitmap));
+}
+
+void vc_forward_exception(struct es_em_ctxt *ctxt);
+
+/* I/O parameters for CPUID-related helpers */
+struct cpuid_leaf {
+ u32 fn;
+ u32 subfn;
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 edx;
+};
+
+int snp_cpuid(struct ghcb *ghcb, struct es_em_ctxt *ctxt, struct cpuid_leaf *leaf);
+
+void __noreturn sev_es_terminate(unsigned int set, unsigned int reason);
+enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
+ struct es_em_ctxt *ctxt,
+ u64 exit_code, u64 exit_info_1,
+ u64 exit_info_2);
+
+extern struct ghcb *boot_ghcb;
+
#else /* !CONFIG_AMD_MEM_ENCRYPT */
#define snp_vmpl 0
@@ -491,7 +569,7 @@ static inline void sev_es_ist_enter(struct pt_regs *regs) { }
static inline void sev_es_ist_exit(void) { }
static inline int sev_es_setup_ap_jump_table(struct real_mode_header *rmh) { return 0; }
static inline void sev_es_nmi_complete(void) { }
-static inline int sev_es_efi_map_ghcbs(pgd_t *pgd) { return 0; }
+static inline int sev_es_efi_map_ghcbs_cas(pgd_t *pgd) { return 0; }
static inline void sev_enable(struct boot_params *bp) { }
static inline int pvalidate(unsigned long vaddr, bool rmp_psize, bool validate) { return 0; }
static inline int rmpadjust(unsigned long vaddr, bool rmp_psize, unsigned long attrs) { return 0; }
@@ -522,8 +600,9 @@ static inline void snp_kexec_begin(void) { }
static inline int snp_msg_init(struct snp_msg_desc *mdesc, int vmpck_id) { return -1; }
static inline struct snp_msg_desc *snp_msg_alloc(void) { return NULL; }
static inline void snp_msg_free(struct snp_msg_desc *mdesc) { }
-static inline int snp_send_guest_request(struct snp_msg_desc *mdesc, struct snp_guest_req *req,
- struct snp_guest_request_ioctl *rio) { return -ENODEV; }
+static inline int snp_send_guest_request(struct snp_msg_desc *mdesc,
+ struct snp_guest_req *req) { return -ENODEV; }
+static inline int snp_svsm_vtpm_send_command(u8 *buffer) { return -ENODEV; }
static inline void __init snp_secure_tsc_prepare(void) { }
static inline void __init snp_secure_tsc_init(void) { }
@@ -540,6 +619,24 @@ int rmp_make_shared(u64 pfn, enum pg_level level);
void snp_leak_pages(u64 pfn, unsigned int npages);
void kdump_sev_callback(void);
void snp_fixup_e820_tables(void);
+
+static inline void sev_evict_cache(void *va, int npages)
+{
+ volatile u8 val __always_unused;
+ u8 *bytes = va;
+ int page_idx;
+
+ /*
+ * For SEV guests, a read from the first/last cache-lines of a 4K page
+ * using the guest key is sufficient to cause a flush of all cache-lines
+ * associated with that 4K page without incurring all the overhead of a
+ * full CLFLUSH sequence.
+ */
+ for (page_idx = 0; page_idx < npages; page_idx++) {
+ val = bytes[page_idx * PAGE_SIZE];
+ val = bytes[page_idx * PAGE_SIZE + PAGE_SIZE - 1];
+ }
+}
#else
static inline bool snp_probe_rmptable_info(void) { return false; }
static inline int snp_rmptable_init(void) { return -ENOSYS; }
@@ -555,6 +652,7 @@ static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV
static inline void snp_leak_pages(u64 pfn, unsigned int npages) {}
static inline void kdump_sev_callback(void) { }
static inline void snp_fixup_e820_tables(void) {}
+static inline void sev_evict_cache(void *va, int npages) {}
#endif
#endif
diff --git a/arch/x86/include/asm/shared/tdx.h b/arch/x86/include/asm/shared/tdx.h
index a28ff6b14145..8bc074c8d7c6 100644
--- a/arch/x86/include/asm/shared/tdx.h
+++ b/arch/x86/include/asm/shared/tdx.h
@@ -13,6 +13,7 @@
/* TDX module Call Leaf IDs */
#define TDG_VP_VMCALL 0
#define TDG_VP_INFO 1
+#define TDG_MR_RTMR_EXTEND 2
#define TDG_VP_VEINFO_GET 3
#define TDG_MR_REPORT 4
#define TDG_MEM_PAGE_ACCEPT 6
@@ -67,11 +68,20 @@
#define TD_CTLS_LOCK BIT_ULL(TD_CTLS_LOCK_BIT)
/* TDX hypercall Leaf IDs */
+#define TDVMCALL_GET_TD_VM_CALL_INFO 0x10000
#define TDVMCALL_MAP_GPA 0x10001
#define TDVMCALL_GET_QUOTE 0x10002
#define TDVMCALL_REPORT_FATAL_ERROR 0x10003
+#define TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT 0x10004ULL
-#define TDVMCALL_STATUS_RETRY 1
+/*
+ * TDG.VP.VMCALL Status Codes (returned in R10)
+ */
+#define TDVMCALL_STATUS_SUCCESS 0x0000000000000000ULL
+#define TDVMCALL_STATUS_RETRY 0x0000000000000001ULL
+#define TDVMCALL_STATUS_INVALID_OPERAND 0x8000000000000000ULL
+#define TDVMCALL_STATUS_ALIGN_ERROR 0x8000000000000002ULL
+#define TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED 0x8000000000000003ULL
/*
* Bitmasks of exposed registers (with VMM).
diff --git a/arch/x86/include/asm/sighandling.h b/arch/x86/include/asm/sighandling.h
index e770c4fc47f4..8727c7e21dd1 100644
--- a/arch/x86/include/asm/sighandling.h
+++ b/arch/x86/include/asm/sighandling.h
@@ -24,4 +24,26 @@ int ia32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
int x64_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
int x32_setup_rt_frame(struct ksignal *ksig, struct pt_regs *regs);
+/*
+ * To prevent immediate repeat of single step trap on return from SIGTRAP
+ * handler if the trap flag (TF) is set without an external debugger attached,
+ * clear the software event flag in the augmented SS, ensuring no single-step
+ * trap is pending upon ERETU completion.
+ *
+ * Note, this function should be called in sigreturn() before the original
+ * state is restored to make sure the TF is read from the entry frame.
+ */
+static __always_inline void prevent_single_step_upon_eretu(struct pt_regs *regs)
+{
+ /*
+ * If the trap flag (TF) is set, i.e., the sigreturn() SYSCALL instruction
+ * is being single-stepped, do not clear the software event flag in the
+ * augmented SS, thus a debugger won't skip over the following instruction.
+ */
+#ifdef CONFIG_X86_FRED
+ if (!(regs->flags & X86_EFLAGS_TF))
+ regs->fred_ss.swevent = 0;
+#endif
+}
+
#endif /* _ASM_X86_SIGHANDLING_H */
diff --git a/arch/x86/include/asm/simd.h b/arch/x86/include/asm/simd.h
index a341c878e977..b8027b63cd7a 100644
--- a/arch/x86/include/asm/simd.h
+++ b/arch/x86/include/asm/simd.h
@@ -1,6 +1,10 @@
/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_SIMD_H
+#define _ASM_SIMD_H
#include <asm/fpu/api.h>
+#include <linux/compiler_attributes.h>
+#include <linux/types.h>
/*
* may_use_simd - whether it is allowable at this time to issue SIMD
@@ -10,3 +14,5 @@ static __must_check inline bool may_use_simd(void)
{
return irq_fpu_usable();
}
+
+#endif /* _ASM_SIMD_H */
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 0c1c68039d6f..22bfebe6776d 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -112,7 +112,10 @@ void __noreturn hlt_play_dead(void);
void native_play_dead(void);
void play_dead_common(void);
void wbinvd_on_cpu(int cpu);
-int wbinvd_on_all_cpus(void);
+void wbinvd_on_all_cpus(void);
+void wbinvd_on_cpus_mask(struct cpumask *cpus);
+void wbnoinvd_on_all_cpus(void);
+void wbnoinvd_on_cpus_mask(struct cpumask *cpus);
void smp_kick_mwait_play_dead(void);
void __noreturn mwait_play_dead(unsigned int eax_hint);
@@ -148,10 +151,24 @@ static inline struct cpumask *cpu_l2c_shared_mask(int cpu)
#else /* !CONFIG_SMP */
#define wbinvd_on_cpu(cpu) wbinvd()
-static inline int wbinvd_on_all_cpus(void)
+static inline void wbinvd_on_all_cpus(void)
{
wbinvd();
- return 0;
+}
+
+static inline void wbinvd_on_cpus_mask(struct cpumask *cpus)
+{
+ wbinvd();
+}
+
+static inline void wbnoinvd_on_all_cpus(void)
+{
+ wbnoinvd();
+}
+
+static inline void wbnoinvd_on_cpus_mask(struct cpumask *cpus)
+{
+ wbnoinvd();
}
static inline struct cpumask *cpu_llc_shared_mask(int cpu)
diff --git a/arch/x86/include/asm/spec-ctrl.h b/arch/x86/include/asm/spec-ctrl.h
index 658b690b2ccb..00b7e0398210 100644
--- a/arch/x86/include/asm/spec-ctrl.h
+++ b/arch/x86/include/asm/spec-ctrl.h
@@ -84,7 +84,7 @@ static inline u64 ssbd_tif_to_amd_ls_cfg(u64 tifn)
static __always_inline void __update_spec_ctrl(u64 val)
{
__this_cpu_write(x86_spec_ctrl_current, val);
- native_wrmsrl(MSR_IA32_SPEC_CTRL, val);
+ native_wrmsrq(MSR_IA32_SPEC_CTRL, val);
}
#ifdef CONFIG_SMP
diff --git a/arch/x86/include/asm/special_insns.h b/arch/x86/include/asm/special_insns.h
index 6266d6b9e0b8..fde2bd7af19e 100644
--- a/arch/x86/include/asm/special_insns.h
+++ b/arch/x86/include/asm/special_insns.h
@@ -10,30 +10,19 @@
#include <linux/irqflags.h>
#include <linux/jump_label.h>
-/*
- * The compiler should not reorder volatile asm statements with respect to each
- * other: they should execute in program order. However GCC 4.9.x and 5.x have
- * a bug (which was fixed in 8.1, 7.3 and 6.5) where they might reorder
- * volatile asm. The write functions are not affected since they have memory
- * clobbers preventing reordering. To prevent reads from being reordered with
- * respect to writes, use a dummy memory operand.
- */
-
-#define __FORCE_ORDER "m"(*(unsigned int *)0x1000UL)
-
void native_write_cr0(unsigned long val);
static inline unsigned long native_read_cr0(void)
{
unsigned long val;
- asm volatile("mov %%cr0,%0\n\t" : "=r" (val) : __FORCE_ORDER);
+ asm volatile("mov %%cr0,%0" : "=r" (val));
return val;
}
static __always_inline unsigned long native_read_cr2(void)
{
unsigned long val;
- asm volatile("mov %%cr2,%0\n\t" : "=r" (val) : __FORCE_ORDER);
+ asm volatile("mov %%cr2,%0" : "=r" (val));
return val;
}
@@ -45,7 +34,7 @@ static __always_inline void native_write_cr2(unsigned long val)
static __always_inline unsigned long __native_read_cr3(void)
{
unsigned long val;
- asm volatile("mov %%cr3,%0\n\t" : "=r" (val) : __FORCE_ORDER);
+ asm volatile("mov %%cr3,%0" : "=r" (val));
return val;
}
@@ -66,10 +55,10 @@ static inline unsigned long native_read_cr4(void)
asm volatile("1: mov %%cr4, %0\n"
"2:\n"
_ASM_EXTABLE(1b, 2b)
- : "=r" (val) : "0" (0), __FORCE_ORDER);
+ : "=r" (val) : "0" (0));
#else
/* CR4 always exists on x86_64. */
- asm volatile("mov %%cr4,%0\n\t" : "=r" (val) : __FORCE_ORDER);
+ asm volatile("mov %%cr4,%0" : "=r" (val));
#endif
return val;
}
@@ -115,9 +104,36 @@ static inline void wrpkru(u32 pkru)
}
#endif
+/*
+ * Write back all modified lines in all levels of cache associated with this
+ * logical processor to main memory, and then invalidate all caches. Depending
+ * on the micro-architecture, WBINVD (and WBNOINVD below) may or may not affect
+ * lower level caches associated with another logical processor that shares any
+ * level of this processor's cache hierarchy.
+ */
static __always_inline void wbinvd(void)
{
- asm volatile("wbinvd": : :"memory");
+ asm volatile("wbinvd" : : : "memory");
+}
+
+/* Instruction encoding provided for binutils backwards compatibility. */
+#define ASM_WBNOINVD _ASM_BYTES(0xf3,0x0f,0x09)
+
+/*
+ * Write back all modified lines in all levels of cache associated with this
+ * logical processor to main memory, but do NOT explicitly invalidate caches,
+ * i.e. leave all/most cache lines in the hierarchy in non-modified state.
+ */
+static __always_inline void wbnoinvd(void)
+{
+ /*
+ * Explicitly encode WBINVD if X86_FEATURE_WBNOINVD is unavailable even
+ * though WBNOINVD is backwards compatible (it's simply WBINVD with an
+ * ignored REP prefix), to guarantee that WBNOINVD isn't used if it
+ * needs to be avoided for any reason. For all supported usage in the
+ * kernel, WBINVD is functionally a superset of WBNOINVD.
+ */
+ alternative("wbinvd", ASM_WBNOINVD, X86_FEATURE_WBNOINVD);
}
static inline unsigned long __read_cr4(void)
diff --git a/arch/x86/include/asm/string_32.h b/arch/x86/include/asm/string_32.h
index 32c0d981a82a..e9cce169bb4c 100644
--- a/arch/x86/include/asm/string_32.h
+++ b/arch/x86/include/asm/string_32.h
@@ -33,11 +33,11 @@ extern size_t strlen(const char *s);
static __always_inline void *__memcpy(void *to, const void *from, size_t n)
{
int d0, d1, d2;
- asm volatile("rep ; movsl\n\t"
+ asm volatile("rep movsl\n\t"
"movl %4,%%ecx\n\t"
"andl $3,%%ecx\n\t"
"jz 1f\n\t"
- "rep ; movsb\n\t"
+ "rep movsb\n\t"
"1:"
: "=&c" (d0), "=&D" (d1), "=&S" (d2)
: "0" (n / 4), "g" (n), "1" ((long)to), "2" ((long)from)
@@ -89,7 +89,7 @@ static __always_inline void *__constant_memcpy(void *to, const void *from,
if (n >= 5 * 4) {
/* large block: use rep prefix */
int ecx;
- asm volatile("rep ; movsl"
+ asm volatile("rep movsl"
: "=&c" (ecx), "=&D" (edi), "=&S" (esi)
: "0" (n / 4), "1" (edi), "2" (esi)
: "memory"
@@ -165,8 +165,7 @@ extern void *memchr(const void *cs, int c, size_t count);
static inline void *__memset_generic(void *s, char c, size_t count)
{
int d0, d1;
- asm volatile("rep\n\t"
- "stosb"
+ asm volatile("rep stosb"
: "=&c" (d0), "=&D" (d1)
: "a" (c), "1" (s), "0" (count)
: "memory");
@@ -199,8 +198,7 @@ extern void *memset(void *, int, size_t);
static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
{
int d0, d1;
- asm volatile("rep\n\t"
- "stosw"
+ asm volatile("rep stosw"
: "=&c" (d0), "=&D" (d1)
: "a" (v), "1" (s), "0" (n)
: "memory");
@@ -211,8 +209,7 @@ static inline void *memset16(uint16_t *s, uint16_t v, size_t n)
static inline void *memset32(uint32_t *s, uint32_t v, size_t n)
{
int d0, d1;
- asm volatile("rep\n\t"
- "stosl"
+ asm volatile("rep stosl"
: "=&c" (d0), "=&D" (d1)
: "a" (v), "1" (s), "0" (n)
: "memory");
diff --git a/arch/x86/include/asm/suspend_32.h b/arch/x86/include/asm/suspend_32.h
index d8416b3bf832..e8e5aab06255 100644
--- a/arch/x86/include/asm/suspend_32.h
+++ b/arch/x86/include/asm/suspend_32.h
@@ -9,6 +9,7 @@
#include <asm/desc.h>
#include <asm/fpu/api.h>
+#include <asm/msr.h>
/* image of the saved processor state */
struct saved_context {
diff --git a/arch/x86/include/asm/suspend_64.h b/arch/x86/include/asm/suspend_64.h
index 54df06687d83..b512f9665f78 100644
--- a/arch/x86/include/asm/suspend_64.h
+++ b/arch/x86/include/asm/suspend_64.h
@@ -9,6 +9,7 @@
#include <asm/desc.h>
#include <asm/fpu/api.h>
+#include <asm/msr.h>
/*
* Image of the saved processor state, used by the low level ACPI suspend to
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index 9b7fa99ae951..ffc27f676243 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -116,6 +116,7 @@ enum {
INTERCEPT_INVPCID,
INTERCEPT_MCOMMIT,
INTERCEPT_TLBSYNC,
+ INTERCEPT_BUSLOCK,
INTERCEPT_IDLE_HLT = 166,
};
@@ -159,7 +160,12 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
u64 avic_physical_id; /* Offset 0xf8 */
u8 reserved_7[8];
u64 vmsa_pa; /* Used for an SEV-ES guest */
- u8 reserved_8[720];
+ u8 reserved_8[16];
+ u16 bus_lock_counter; /* Offset 0x120 */
+ u8 reserved_9[22];
+ u64 allowed_sev_features; /* Offset 0x138 */
+ u64 guest_sev_features; /* Offset 0x140 */
+ u8 reserved_10[664];
/*
* Offset 0x3e0, 32 bytes reserved
* for use by hypervisor/software.
@@ -246,16 +252,21 @@ struct __attribute__ ((__packed__)) vmcb_control_area {
#define AVIC_LOGICAL_ID_ENTRY_VALID_BIT 31
#define AVIC_LOGICAL_ID_ENTRY_VALID_MASK (1 << 31)
+/*
+ * GA_LOG_INTR is a synthetic flag that's never propagated to hardware-visible
+ * tables. GA_LOG_INTR is set if the vCPU needs device posted IRQs to generate
+ * GA log interrupts to wake the vCPU (because it's blocking or about to block).
+ */
+#define AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR BIT_ULL(61)
+
#define AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK GENMASK_ULL(11, 0)
-#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK (0xFFFFFFFFFFULL << 12)
+#define AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK GENMASK_ULL(51, 12)
#define AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK (1ULL << 62)
#define AVIC_PHYSICAL_ID_ENTRY_VALID_MASK (1ULL << 63)
#define AVIC_PHYSICAL_ID_TABLE_SIZE_MASK (0xFFULL)
#define AVIC_DOORBELL_PHYSICAL_ID_MASK GENMASK_ULL(11, 0)
-#define VMCB_AVIC_APIC_BAR_MASK 0xFFFFFFFFFF000ULL
-
#define AVIC_UNACCEL_ACCESS_WRITE_MASK 1
#define AVIC_UNACCEL_ACCESS_OFFSET_MASK 0xFF0
#define AVIC_UNACCEL_ACCESS_VECTOR_MASK 0xFFFFFFFF
@@ -284,13 +295,13 @@ enum avic_ipi_failure_cause {
static_assert((AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == AVIC_MAX_PHYSICAL_ID);
static_assert((X2AVIC_MAX_PHYSICAL_ID & AVIC_PHYSICAL_MAX_INDEX_MASK) == X2AVIC_MAX_PHYSICAL_ID);
-#define AVIC_HPA_MASK ~((0xFFFULL << 52) | 0xFFF)
-
#define SVM_SEV_FEAT_SNP_ACTIVE BIT(0)
#define SVM_SEV_FEAT_RESTRICTED_INJECTION BIT(3)
#define SVM_SEV_FEAT_ALTERNATE_INJECTION BIT(4)
#define SVM_SEV_FEAT_DEBUG_SWAP BIT(5)
+#define VMCB_ALLOWED_SEV_FEATURES_VALID BIT_ULL(63)
+
struct vmcb_seg {
u16 selector;
u16 attrib;
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 75248546403d..499b1c15cc8b 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -52,6 +52,8 @@ do { \
} while (0)
#ifdef CONFIG_X86_32
+#include <asm/msr.h>
+
static inline void refresh_sysenter_cs(struct thread_struct *thread)
{
/* Only happens when SEP is enabled, no need to test "SEP"arately: */
@@ -59,7 +61,7 @@ static inline void refresh_sysenter_cs(struct thread_struct *thread)
return;
this_cpu_write(cpu_tss_rw.x86_tss.ss1, thread->sysenter_cs);
- wrmsr(MSR_IA32_SYSENTER_CS, thread->sysenter_cs, 0);
+ wrmsrq(MSR_IA32_SYSENTER_CS, thread->sysenter_cs);
}
#endif
diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h
index 7c488ff0c764..c10dbb74cd00 100644
--- a/arch/x86/include/asm/syscall.h
+++ b/arch/x86/include/asm/syscall.h
@@ -38,6 +38,13 @@ static inline int syscall_get_nr(struct task_struct *task, struct pt_regs *regs)
return regs->orig_ax;
}
+static inline void syscall_set_nr(struct task_struct *task,
+ struct pt_regs *regs,
+ int nr)
+{
+ regs->orig_ax = nr;
+}
+
static inline void syscall_rollback(struct task_struct *task,
struct pt_regs *regs)
{
@@ -90,6 +97,18 @@ static inline void syscall_get_arguments(struct task_struct *task,
args[5] = regs->bp;
}
+static inline void syscall_set_arguments(struct task_struct *task,
+ struct pt_regs *regs,
+ const unsigned long *args)
+{
+ regs->bx = args[0];
+ regs->cx = args[1];
+ regs->dx = args[2];
+ regs->si = args[3];
+ regs->di = args[4];
+ regs->bp = args[5];
+}
+
static inline int syscall_get_arch(struct task_struct *task)
{
return AUDIT_ARCH_I386;
@@ -121,6 +140,30 @@ static inline void syscall_get_arguments(struct task_struct *task,
}
}
+static inline void syscall_set_arguments(struct task_struct *task,
+ struct pt_regs *regs,
+ const unsigned long *args)
+{
+# ifdef CONFIG_IA32_EMULATION
+ if (task->thread_info.status & TS_COMPAT) {
+ regs->bx = *args++;
+ regs->cx = *args++;
+ regs->dx = *args++;
+ regs->si = *args++;
+ regs->di = *args++;
+ regs->bp = *args;
+ } else
+# endif
+ {
+ regs->di = *args++;
+ regs->si = *args++;
+ regs->dx = *args++;
+ regs->r10 = *args++;
+ regs->r8 = *args++;
+ regs->r9 = *args;
+ }
+}
+
static inline int syscall_get_arch(struct task_struct *task)
{
/* x32 tasks should be considered AUDIT_ARCH_X86_64. */
diff --git a/arch/x86/include/asm/tdx.h b/arch/x86/include/asm/tdx.h
index 4a1922ec80cf..7ddef3a69866 100644
--- a/arch/x86/include/asm/tdx.h
+++ b/arch/x86/include/asm/tdx.h
@@ -5,6 +5,7 @@
#include <linux/init.h>
#include <linux/bits.h>
+#include <linux/mmzone.h>
#include <asm/errno.h>
#include <asm/ptrace.h>
@@ -18,6 +19,7 @@
* TDX module.
*/
#define TDX_ERROR _BITUL(63)
+#define TDX_NON_RECOVERABLE _BITUL(62)
#define TDX_SW_ERROR (TDX_ERROR | GENMASK_ULL(47, 40))
#define TDX_SEAMCALL_VMFAILINVALID (TDX_SW_ERROR | _UL(0xFFFF0000))
@@ -33,6 +35,8 @@
#ifndef __ASSEMBLER__
#include <uapi/asm/mce.h>
+#include <asm/tdx_global_metadata.h>
+#include <linux/pgtable.h>
/*
* Used by the #VE exception handler to gather the #VE exception
@@ -64,6 +68,8 @@ bool tdx_early_handle_ve(struct pt_regs *regs);
int tdx_mcall_get_report0(u8 *reportdata, u8 *tdreport);
+int tdx_mcall_extend_rtmr(u8 index, u8 *data);
+
u64 tdx_hcall_get_quote(u8 *buf, size_t size);
void __init tdx_dump_attributes(u64 td_attr);
@@ -100,7 +106,7 @@ void tdx_init(void);
typedef u64 (*sc_func_t)(u64 fn, struct tdx_module_args *args);
-static inline u64 sc_retry(sc_func_t func, u64 fn,
+static __always_inline u64 sc_retry(sc_func_t func, u64 fn,
struct tdx_module_args *args)
{
int retry = RDRAND_RETRY_LOOPS;
@@ -119,11 +125,82 @@ static inline u64 sc_retry(sc_func_t func, u64 fn,
int tdx_cpu_enable(void);
int tdx_enable(void);
const char *tdx_dump_mce_info(struct mce *m);
+const struct tdx_sys_info *tdx_get_sysinfo(void);
+
+int tdx_guest_keyid_alloc(void);
+u32 tdx_get_nr_guest_keyids(void);
+void tdx_guest_keyid_free(unsigned int keyid);
+
+struct tdx_td {
+ /* TD root structure: */
+ struct page *tdr_page;
+
+ int tdcs_nr_pages;
+ /* TD control structure: */
+ struct page **tdcs_pages;
+
+ /* Size of `tdcx_pages` in struct tdx_vp */
+ int tdcx_nr_pages;
+};
+
+struct tdx_vp {
+ /* TDVP root page */
+ struct page *tdvpr_page;
+
+ /* TD vCPU control structure: */
+ struct page **tdcx_pages;
+};
+
+static inline u64 mk_keyed_paddr(u16 hkid, struct page *page)
+{
+ u64 ret;
+
+ ret = page_to_phys(page);
+ /* KeyID bits are just above the physical address bits: */
+ ret |= (u64)hkid << boot_cpu_data.x86_phys_bits;
+
+ return ret;
+}
+
+static inline int pg_level_to_tdx_sept_level(enum pg_level level)
+{
+ WARN_ON_ONCE(level == PG_LEVEL_NONE);
+ return level - 1;
+}
+
+u64 tdh_vp_enter(struct tdx_vp *vp, struct tdx_module_args *args);
+u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page);
+u64 tdh_mem_page_add(struct tdx_td *td, u64 gpa, struct page *page, struct page *source, u64 *ext_err1, u64 *ext_err2);
+u64 tdh_mem_sept_add(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2);
+u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page);
+u64 tdh_mem_page_aug(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2);
+u64 tdh_mem_range_block(struct tdx_td *td, u64 gpa, int level, u64 *ext_err1, u64 *ext_err2);
+u64 tdh_mng_key_config(struct tdx_td *td);
+u64 tdh_mng_create(struct tdx_td *td, u16 hkid);
+u64 tdh_vp_create(struct tdx_td *td, struct tdx_vp *vp);
+u64 tdh_mng_rd(struct tdx_td *td, u64 field, u64 *data);
+u64 tdh_mr_extend(struct tdx_td *td, u64 gpa, u64 *ext_err1, u64 *ext_err2);
+u64 tdh_mr_finalize(struct tdx_td *td);
+u64 tdh_vp_flush(struct tdx_vp *vp);
+u64 tdh_mng_vpflushdone(struct tdx_td *td);
+u64 tdh_mng_key_freeid(struct tdx_td *td);
+u64 tdh_mng_init(struct tdx_td *td, u64 td_params, u64 *extended_err);
+u64 tdh_vp_init(struct tdx_vp *vp, u64 initial_rcx, u32 x2apicid);
+u64 tdh_vp_rd(struct tdx_vp *vp, u64 field, u64 *data);
+u64 tdh_vp_wr(struct tdx_vp *vp, u64 field, u64 data, u64 mask);
+u64 tdh_phymem_page_reclaim(struct page *page, u64 *tdx_pt, u64 *tdx_owner, u64 *tdx_size);
+u64 tdh_mem_track(struct tdx_td *tdr);
+u64 tdh_mem_page_remove(struct tdx_td *td, u64 gpa, u64 level, u64 *ext_err1, u64 *ext_err2);
+u64 tdh_phymem_cache_wb(bool resume);
+u64 tdh_phymem_page_wbinvd_tdr(struct tdx_td *td);
+u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page);
#else
static inline void tdx_init(void) { }
static inline int tdx_cpu_enable(void) { return -ENODEV; }
static inline int tdx_enable(void) { return -ENODEV; }
+static inline u32 tdx_get_nr_guest_keyids(void) { return 0; }
static inline const char *tdx_dump_mce_info(struct mce *m) { return NULL; }
+static inline const struct tdx_sys_info *tdx_get_sysinfo(void) { return NULL; }
#endif /* CONFIG_INTEL_TDX_HOST */
#endif /* !__ASSEMBLER__ */
diff --git a/arch/x86/virt/vmx/tdx/tdx_global_metadata.h b/arch/x86/include/asm/tdx_global_metadata.h
index 6dd3c9695f59..060a2ad744bf 100644
--- a/arch/x86/virt/vmx/tdx/tdx_global_metadata.h
+++ b/arch/x86/include/asm/tdx_global_metadata.h
@@ -17,9 +17,28 @@ struct tdx_sys_info_tdmr {
u16 pamt_1g_entry_size;
};
+struct tdx_sys_info_td_ctrl {
+ u16 tdr_base_size;
+ u16 tdcs_base_size;
+ u16 tdvps_base_size;
+};
+
+struct tdx_sys_info_td_conf {
+ u64 attributes_fixed0;
+ u64 attributes_fixed1;
+ u64 xfam_fixed0;
+ u64 xfam_fixed1;
+ u16 num_cpuid_config;
+ u16 max_vcpus_per_td;
+ u64 cpuid_config_leaves[128];
+ u64 cpuid_config_values[128][2];
+};
+
struct tdx_sys_info {
struct tdx_sys_info_features features;
struct tdx_sys_info_tdmr tdmr;
+ struct tdx_sys_info_td_ctrl td_ctrl;
+ struct tdx_sys_info_td_conf td_conf;
};
#endif
diff --git a/arch/x86/include/asm/text-patching.h b/arch/x86/include/asm/text-patching.h
index ab9e143ec9fe..5337f1be18f6 100644
--- a/arch/x86/include/asm/text-patching.h
+++ b/arch/x86/include/asm/text-patching.h
@@ -11,11 +11,11 @@
* JUMP_LABEL_NOP_SIZE/RELATIVEJUMP_SIZE, which are 5.
* Raise it if needed.
*/
-#define POKE_MAX_OPCODE_SIZE 5
+#define TEXT_POKE_MAX_OPCODE_SIZE 5
extern void text_poke_early(void *addr, const void *opcode, size_t len);
-extern void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len);
+extern void text_poke_apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len);
/*
* Clear and restore the kernel write-protection flag on the local CPU.
@@ -32,17 +32,17 @@ extern void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u
* an inconsistent instruction while you patch.
*/
extern void *text_poke(void *addr, const void *opcode, size_t len);
-extern void text_poke_sync(void);
+extern void smp_text_poke_sync_each_cpu(void);
extern void *text_poke_kgdb(void *addr, const void *opcode, size_t len);
extern void *text_poke_copy(void *addr, const void *opcode, size_t len);
#define text_poke_copy text_poke_copy
extern void *text_poke_copy_locked(void *addr, const void *opcode, size_t len, bool core_ok);
extern void *text_poke_set(void *addr, int c, size_t len);
-extern int poke_int3_handler(struct pt_regs *regs);
-extern void text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate);
+extern int smp_text_poke_int3_handler(struct pt_regs *regs);
+extern void smp_text_poke_single(void *addr, const void *opcode, size_t len, const void *emulate);
-extern void text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate);
-extern void text_poke_finish(void);
+extern void smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, const void *emulate);
+extern void smp_text_poke_batch_finish(void);
#define INT3_INSN_SIZE 1
#define INT3_INSN_OPCODE 0xCC
@@ -82,7 +82,7 @@ static __always_inline int text_opcode_size(u8 opcode)
}
union text_poke_insn {
- u8 text[POKE_MAX_OPCODE_SIZE];
+ u8 text[TEXT_POKE_MAX_OPCODE_SIZE];
struct {
u8 opcode;
s32 disp;
@@ -128,8 +128,8 @@ void *text_gen_insn(u8 opcode, const void *addr, const void *dest)
}
extern int after_bootmem;
-extern __ro_after_init struct mm_struct *poking_mm;
-extern __ro_after_init unsigned long poking_addr;
+extern __ro_after_init struct mm_struct *text_poke_mm;
+extern __ro_after_init unsigned long text_poke_mm_addr;
#ifndef CONFIG_UML_X86
static __always_inline
@@ -142,13 +142,14 @@ static __always_inline
void int3_emulate_push(struct pt_regs *regs, unsigned long val)
{
/*
- * The int3 handler in entry_64.S adds a gap between the
+ * The INT3 handler in entry_64.S adds a gap between the
* stack where the break point happened, and the saving of
* pt_regs. We can extend the original stack because of
- * this gap. See the idtentry macro's create_gap option.
+ * this gap. See the idtentry macro's X86_TRAP_BP logic.
*
- * Similarly entry_32.S will have a gap on the stack for (any) hardware
- * exception and pt_regs; see FIXUP_FRAME.
+ * Similarly, entry_32.S will have a gap on the stack for
+ * (any) hardware exception and pt_regs; see the
+ * FIXUP_FRAME macro.
*/
regs->sp -= sizeof(unsigned long);
*(unsigned long *)regs->sp = val;
diff --git a/arch/x86/include/asm/tlbflush.h b/arch/x86/include/asm/tlbflush.h
index e9b81876ebe4..00daedfefc1b 100644
--- a/arch/x86/include/asm/tlbflush.h
+++ b/arch/x86/include/asm/tlbflush.h
@@ -356,11 +356,6 @@ static inline void arch_tlbbatch_add_pending(struct arch_tlbflush_unmap_batch *b
mmu_notifier_arch_invalidate_secondary_tlbs(mm, 0, -1UL);
}
-static inline void arch_flush_tlb_batched_pending(struct mm_struct *mm)
-{
- flush_tlb_mm(mm);
-}
-
extern void arch_tlbbatch_flush(struct arch_tlbflush_unmap_batch *batch);
static inline bool pte_flags_need_flush(unsigned long oldflags,
diff --git a/arch/x86/include/asm/trace/common.h b/arch/x86/include/asm/trace/common.h
deleted file mode 100644
index f0f9bcdb74d9..000000000000
--- a/arch/x86/include/asm/trace/common.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_TRACE_COMMON_H
-#define _ASM_TRACE_COMMON_H
-
-#ifdef CONFIG_TRACING
-DECLARE_STATIC_KEY_FALSE(trace_pagefault_key);
-#define trace_pagefault_enabled() \
- static_branch_unlikely(&trace_pagefault_key)
-#else
-static inline bool trace_pagefault_enabled(void) { return false; }
-#endif
-
-#endif
diff --git a/arch/x86/include/asm/trace/exceptions.h b/arch/x86/include/asm/trace/exceptions.h
deleted file mode 100644
index 6b1e87194809..000000000000
--- a/arch/x86/include/asm/trace/exceptions.h
+++ /dev/null
@@ -1,54 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#undef TRACE_SYSTEM
-#define TRACE_SYSTEM exceptions
-
-#if !defined(_TRACE_PAGE_FAULT_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_PAGE_FAULT_H
-
-#include <linux/tracepoint.h>
-#include <asm/trace/common.h>
-
-extern int trace_pagefault_reg(void);
-extern void trace_pagefault_unreg(void);
-
-DECLARE_EVENT_CLASS(x86_exceptions,
-
- TP_PROTO(unsigned long address, struct pt_regs *regs,
- unsigned long error_code),
-
- TP_ARGS(address, regs, error_code),
-
- TP_STRUCT__entry(
- __field( unsigned long, address )
- __field( unsigned long, ip )
- __field( unsigned long, error_code )
- ),
-
- TP_fast_assign(
- __entry->address = address;
- __entry->ip = regs->ip;
- __entry->error_code = error_code;
- ),
-
- TP_printk("address=%ps ip=%ps error_code=0x%lx",
- (void *)__entry->address, (void *)__entry->ip,
- __entry->error_code) );
-
-#define DEFINE_PAGE_FAULT_EVENT(name) \
-DEFINE_EVENT_FN(x86_exceptions, name, \
- TP_PROTO(unsigned long address, struct pt_regs *regs, \
- unsigned long error_code), \
- TP_ARGS(address, regs, error_code), \
- trace_pagefault_reg, trace_pagefault_unreg);
-
-DEFINE_PAGE_FAULT_EVENT(page_fault_user);
-DEFINE_PAGE_FAULT_EVENT(page_fault_kernel);
-
-#undef TRACE_INCLUDE_PATH
-#undef TRACE_INCLUDE_FILE
-#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE exceptions
-#endif /* _TRACE_PAGE_FAULT_H */
-
-/* This part must be outside protection */
-#include <trace/define_trace.h>
diff --git a/arch/x86/include/asm/trace/fpu.h b/arch/x86/include/asm/trace/fpu.h
index 4645a6334063..721b408d9a67 100644
--- a/arch/x86/include/asm/trace/fpu.h
+++ b/arch/x86/include/asm/trace/fpu.h
@@ -44,16 +44,6 @@ DEFINE_EVENT(x86_fpu, x86_fpu_after_save,
TP_ARGS(fpu)
);
-DEFINE_EVENT(x86_fpu, x86_fpu_before_restore,
- TP_PROTO(struct fpu *fpu),
- TP_ARGS(fpu)
-);
-
-DEFINE_EVENT(x86_fpu, x86_fpu_after_restore,
- TP_PROTO(struct fpu *fpu),
- TP_ARGS(fpu)
-);
-
DEFINE_EVENT(x86_fpu, x86_fpu_regs_activated,
TP_PROTO(struct fpu *fpu),
TP_ARGS(fpu)
@@ -64,21 +54,11 @@ DEFINE_EVENT(x86_fpu, x86_fpu_regs_deactivated,
TP_ARGS(fpu)
);
-DEFINE_EVENT(x86_fpu, x86_fpu_init_state,
- TP_PROTO(struct fpu *fpu),
- TP_ARGS(fpu)
-);
-
DEFINE_EVENT(x86_fpu, x86_fpu_dropped,
TP_PROTO(struct fpu *fpu),
TP_ARGS(fpu)
);
-DEFINE_EVENT(x86_fpu, x86_fpu_copy_src,
- TP_PROTO(struct fpu *fpu),
- TP_ARGS(fpu)
-);
-
DEFINE_EVENT(x86_fpu, x86_fpu_copy_dst,
TP_PROTO(struct fpu *fpu),
TP_ARGS(fpu)
diff --git a/arch/x86/include/asm/trace/irq_vectors.h b/arch/x86/include/asm/trace/irq_vectors.h
index 88e7f0f3bf62..7408bebdfde0 100644
--- a/arch/x86/include/asm/trace/irq_vectors.h
+++ b/arch/x86/include/asm/trace/irq_vectors.h
@@ -6,7 +6,6 @@
#define _TRACE_IRQ_VECTORS_H
#include <linux/tracepoint.h>
-#include <asm/trace/common.h>
#ifdef CONFIG_X86_LOCAL_APIC
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index 94408a784c8e..4f7f09f50552 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -5,10 +5,65 @@
#ifndef _ASM_X86_TSC_H
#define _ASM_X86_TSC_H
+#include <asm/asm.h>
#include <asm/cpufeature.h>
#include <asm/processor.h>
#include <asm/msr.h>
+/**
+ * rdtsc() - returns the current TSC without ordering constraints
+ *
+ * rdtsc() returns the result of RDTSC as a 64-bit integer. The
+ * only ordering constraint it supplies is the ordering implied by
+ * "asm volatile": it will put the RDTSC in the place you expect. The
+ * CPU can and will speculatively execute that RDTSC, though, so the
+ * results can be non-monotonic if compared on different CPUs.
+ */
+static __always_inline u64 rdtsc(void)
+{
+ EAX_EDX_DECLARE_ARGS(val, low, high);
+
+ asm volatile("rdtsc" : EAX_EDX_RET(val, low, high));
+
+ return EAX_EDX_VAL(val, low, high);
+}
+
+/**
+ * rdtsc_ordered() - read the current TSC in program order
+ *
+ * rdtsc_ordered() returns the result of RDTSC as a 64-bit integer.
+ * It is ordered like a load to a global in-memory counter. It should
+ * be impossible to observe non-monotonic rdtsc_unordered() behavior
+ * across multiple CPUs as long as the TSC is synced.
+ */
+static __always_inline u64 rdtsc_ordered(void)
+{
+ EAX_EDX_DECLARE_ARGS(val, low, high);
+
+ /*
+ * The RDTSC instruction is not ordered relative to memory
+ * access. The Intel SDM and the AMD APM are both vague on this
+ * point, but empirically an RDTSC instruction can be
+ * speculatively executed before prior loads. An RDTSC
+ * immediately after an appropriate barrier appears to be
+ * ordered as a normal load, that is, it provides the same
+ * ordering guarantees as reading from a global memory location
+ * that some other imaginary CPU is updating continuously with a
+ * time stamp.
+ *
+ * Thus, use the preferred barrier on the respective CPU, aiming for
+ * RDTSCP as the default.
+ */
+ asm volatile(ALTERNATIVE_2("rdtsc",
+ "lfence; rdtsc", X86_FEATURE_LFENCE_RDTSC,
+ "rdtscp", X86_FEATURE_RDTSCP)
+ : EAX_EDX_RET(val, low, high)
+ /* RDTSCP clobbers ECX with MSR_TSC_AUX. */
+ :: "ecx");
+
+ return EAX_EDX_VAL(val, low, high);
+}
+
/*
* Standard way to access the cycle counter.
*/
diff --git a/arch/x86/include/asm/uaccess_64.h b/arch/x86/include/asm/uaccess_64.h
index c52f0133425b..c8a5ae35c871 100644
--- a/arch/x86/include/asm/uaccess_64.h
+++ b/arch/x86/include/asm/uaccess_64.h
@@ -26,8 +26,8 @@ extern unsigned long USER_PTR_MAX;
*/
static inline unsigned long __untagged_addr(unsigned long addr)
{
- asm (ALTERNATIVE("",
- "and " __percpu_arg([mask]) ", %[addr]", X86_FEATURE_LAM)
+ asm_inline (ALTERNATIVE("", "and " __percpu_arg([mask]) ", %[addr]",
+ X86_FEATURE_LAM)
: [addr] "+r" (addr)
: [mask] "m" (__my_cpu_var(tlbstate_untag_mask)));
@@ -54,7 +54,7 @@ static inline unsigned long __untagged_addr_remote(struct mm_struct *mm,
#endif
#define valid_user_address(x) \
- ((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX))
+ likely((__force unsigned long)(x) <= runtime_const_ptr(USER_PTR_MAX))
/*
* Masking the user address is an alternative to a conditional
diff --git a/arch/x86/include/asm/vdso.h b/arch/x86/include/asm/vdso.h
index 80be0da733df..b7253ef3205a 100644
--- a/arch/x86/include/asm/vdso.h
+++ b/arch/x86/include/asm/vdso.h
@@ -27,17 +27,9 @@ struct vdso_image {
long sym_vdso32_rt_sigreturn_landing_pad;
};
-#ifdef CONFIG_X86_64
extern const struct vdso_image vdso_image_64;
-#endif
-
-#ifdef CONFIG_X86_X32_ABI
extern const struct vdso_image vdso_image_x32;
-#endif
-
-#if defined CONFIG_X86_32 || defined CONFIG_COMPAT
extern const struct vdso_image vdso_image_32;
-#endif
extern int __init init_vdso_image(const struct vdso_image *image);
diff --git a/arch/x86/include/asm/vdso/processor.h b/arch/x86/include/asm/vdso/processor.h
index c9b2ba7a9ec4..7000aeb59aa2 100644
--- a/arch/x86/include/asm/vdso/processor.h
+++ b/arch/x86/include/asm/vdso/processor.h
@@ -7,15 +7,15 @@
#ifndef __ASSEMBLER__
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static __always_inline void rep_nop(void)
+/* PAUSE is a good thing to insert into busy-wait loops. */
+static __always_inline void native_pause(void)
{
- asm volatile("rep; nop" ::: "memory");
+ asm volatile("pause" ::: "memory");
}
static __always_inline void cpu_relax(void)
{
- rep_nop();
+ native_pause();
}
struct getcpu_cache;
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 8707361b24da..cca7d6641287 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -256,6 +256,7 @@ enum vmcs_field {
TSC_MULTIPLIER_HIGH = 0x00002033,
TERTIARY_VM_EXEC_CONTROL = 0x00002034,
TERTIARY_VM_EXEC_CONTROL_HIGH = 0x00002035,
+ SHARED_EPT_POINTER = 0x0000203C,
PID_POINTER_TABLE = 0x00002042,
PID_POINTER_TABLE_HIGH = 0x00002043,
GUEST_PHYSICAL_ADDRESS = 0x00002400,
@@ -586,6 +587,7 @@ enum vm_entry_failure_code {
#define EPT_VIOLATION_PROT_READ BIT(3)
#define EPT_VIOLATION_PROT_WRITE BIT(4)
#define EPT_VIOLATION_PROT_EXEC BIT(5)
+#define EPT_VIOLATION_EXEC_FOR_RING3_LIN BIT(6)
#define EPT_VIOLATION_PROT_MASK (EPT_VIOLATION_PROT_READ | \
EPT_VIOLATION_PROT_WRITE | \
EPT_VIOLATION_PROT_EXEC)
diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
index 213cf5379a5a..36698cc9fb44 100644
--- a/arch/x86/include/asm/x86_init.h
+++ b/arch/x86/include/asm/x86_init.h
@@ -292,6 +292,7 @@ struct x86_hyper_runtime {
* @set_wallclock: set time back to HW clock
* @is_untracked_pat_range exclude from PAT logic
* @nmi_init enable NMI on cpus
+ * @get_nmi_reason get the reason an NMI was received
* @save_sched_clock_state: save state for sched_clock() on suspend
* @restore_sched_clock_state: restore state for sched_clock() on resume
* @apic_post_init: adjust apic if needed
diff --git a/arch/x86/include/asm/xen/hypervisor.h b/arch/x86/include/asm/xen/hypervisor.h
index bd0fc69a10a7..c2fc7869b996 100644
--- a/arch/x86/include/asm/xen/hypervisor.h
+++ b/arch/x86/include/asm/xen/hypervisor.h
@@ -43,7 +43,7 @@ extern struct start_info *xen_start_info;
static inline uint32_t xen_cpuid_base(void)
{
- return hypervisor_cpuid_base(XEN_SIGNATURE, 2);
+ return cpuid_base_hypervisor(XEN_SIGNATURE, 2);
}
struct pci_dev;
diff --git a/arch/x86/include/uapi/asm/debugreg.h b/arch/x86/include/uapi/asm/debugreg.h
index 0007ba077c0c..41da492dfb01 100644
--- a/arch/x86/include/uapi/asm/debugreg.h
+++ b/arch/x86/include/uapi/asm/debugreg.h
@@ -15,7 +15,26 @@
which debugging register was responsible for the trap. The other bits
are either reserved or not of interest to us. */
-/* Define reserved bits in DR6 which are always set to 1 */
+/*
+ * Define bits in DR6 which are set to 1 by default.
+ *
+ * This is also the DR6 architectural value following Power-up, Reset or INIT.
+ *
+ * Note, with the introduction of Bus Lock Detection (BLD) and Restricted
+ * Transactional Memory (RTM), the DR6 register has been modified:
+ *
+ * 1) BLD flag (bit 11) is no longer reserved to 1 if the CPU supports
+ * Bus Lock Detection. The assertion of a bus lock could clear it.
+ *
+ * 2) RTM flag (bit 16) is no longer reserved to 1 if the CPU supports
+ * restricted transactional memory. #DB occurred inside an RTM region
+ * could clear it.
+ *
+ * Apparently, DR6.BLD and DR6.RTM are active low bits.
+ *
+ * As a result, DR6_RESERVED is an incorrect name now, but it is kept for
+ * compatibility.
+ */
#define DR6_RESERVED (0xFFFF0FF0)
#define DR_TRAP0 (0x1) /* db0 */
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 460306b35a4b..0f15d683817d 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -441,6 +441,7 @@ struct kvm_sync_regs {
#define KVM_X86_QUIRK_MWAIT_NEVER_UD_FAULTS (1 << 6)
#define KVM_X86_QUIRK_SLOT_ZAP_ALL (1 << 7)
#define KVM_X86_QUIRK_STUFF_FEATURE_MSRS (1 << 8)
+#define KVM_X86_QUIRK_IGNORE_GUEST_PAT (1 << 9)
#define KVM_STATE_NESTED_FORMAT_VMX 0
#define KVM_STATE_NESTED_FORMAT_SVM 1
@@ -844,6 +845,7 @@ struct kvm_sev_snp_launch_start {
};
/* Kept in sync with firmware values for simplicity. */
+#define KVM_SEV_PAGE_TYPE_INVALID 0x0
#define KVM_SEV_SNP_PAGE_TYPE_NORMAL 0x1
#define KVM_SEV_SNP_PAGE_TYPE_ZERO 0x3
#define KVM_SEV_SNP_PAGE_TYPE_UNMEASURED 0x4
@@ -930,4 +932,80 @@ struct kvm_hyperv_eventfd {
#define KVM_X86_SNP_VM 4
#define KVM_X86_TDX_VM 5
+/* Trust Domain eXtension sub-ioctl() commands. */
+enum kvm_tdx_cmd_id {
+ KVM_TDX_CAPABILITIES = 0,
+ KVM_TDX_INIT_VM,
+ KVM_TDX_INIT_VCPU,
+ KVM_TDX_INIT_MEM_REGION,
+ KVM_TDX_FINALIZE_VM,
+ KVM_TDX_GET_CPUID,
+
+ KVM_TDX_CMD_NR_MAX,
+};
+
+struct kvm_tdx_cmd {
+ /* enum kvm_tdx_cmd_id */
+ __u32 id;
+ /* flags for sub-commend. If sub-command doesn't use this, set zero. */
+ __u32 flags;
+ /*
+ * data for each sub-command. An immediate or a pointer to the actual
+ * data in process virtual address. If sub-command doesn't use it,
+ * set zero.
+ */
+ __u64 data;
+ /*
+ * Auxiliary error code. The sub-command may return TDX SEAMCALL
+ * status code in addition to -Exxx.
+ */
+ __u64 hw_error;
+};
+
+struct kvm_tdx_capabilities {
+ __u64 supported_attrs;
+ __u64 supported_xfam;
+
+ __u64 kernel_tdvmcallinfo_1_r11;
+ __u64 user_tdvmcallinfo_1_r11;
+ __u64 kernel_tdvmcallinfo_1_r12;
+ __u64 user_tdvmcallinfo_1_r12;
+
+ __u64 reserved[250];
+
+ /* Configurable CPUID bits for userspace */
+ struct kvm_cpuid2 cpuid;
+};
+
+struct kvm_tdx_init_vm {
+ __u64 attributes;
+ __u64 xfam;
+ __u64 mrconfigid[6]; /* sha384 digest */
+ __u64 mrowner[6]; /* sha384 digest */
+ __u64 mrownerconfig[6]; /* sha384 digest */
+
+ /* The total space for TD_PARAMS before the CPUIDs is 256 bytes */
+ __u64 reserved[12];
+
+ /*
+ * Call KVM_TDX_INIT_VM before vcpu creation, thus before
+ * KVM_SET_CPUID2.
+ * This configuration supersedes KVM_SET_CPUID2s for VCPUs because the
+ * TDX module directly virtualizes those CPUIDs without VMM. The user
+ * space VMM, e.g. qemu, should make KVM_SET_CPUID2 consistent with
+ * those values. If it doesn't, KVM may have wrong idea of vCPUIDs of
+ * the guest, and KVM may wrongly emulate CPUIDs or MSRs that the TDX
+ * module doesn't virtualize.
+ */
+ struct kvm_cpuid2 cpuid;
+};
+
+#define KVM_TDX_MEASURE_MEMORY_REGION _BITULL(0)
+
+struct kvm_tdx_init_mem_region {
+ __u64 source_addr;
+ __u64 gpa;
+ __u64 nr_pages;
+};
+
#endif /* _ASM_X86_KVM_H */
diff --git a/arch/x86/include/uapi/asm/setup_data.h b/arch/x86/include/uapi/asm/setup_data.h
index 50c45ead4e7c..2671c4e1b3a0 100644
--- a/arch/x86/include/uapi/asm/setup_data.h
+++ b/arch/x86/include/uapi/asm/setup_data.h
@@ -13,7 +13,8 @@
#define SETUP_CC_BLOB 7
#define SETUP_IMA 8
#define SETUP_RNG_SEED 9
-#define SETUP_ENUM_MAX SETUP_RNG_SEED
+#define SETUP_KEXEC_KHO 10
+#define SETUP_ENUM_MAX SETUP_KEXEC_KHO
#define SETUP_INDIRECT (1<<31)
#define SETUP_TYPE_MAX (SETUP_ENUM_MAX | SETUP_INDIRECT)
@@ -78,6 +79,16 @@ struct ima_setup_data {
__u64 size;
} __attribute__((packed));
+/*
+ * Locations of kexec handover metadata
+ */
+struct kho_data {
+ __u64 fdt_addr;
+ __u64 fdt_size;
+ __u64 scratch_addr;
+ __u64 scratch_size;
+} __attribute__((packed));
+
#endif /* __ASSEMBLER__ */
#endif /* _UAPI_ASM_X86_SETUP_DATA_H */
diff --git a/arch/x86/include/uapi/asm/svm.h b/arch/x86/include/uapi/asm/svm.h
index ec1321248dac..9c640a521a67 100644
--- a/arch/x86/include/uapi/asm/svm.h
+++ b/arch/x86/include/uapi/asm/svm.h
@@ -95,6 +95,7 @@
#define SVM_EXIT_CR14_WRITE_TRAP 0x09e
#define SVM_EXIT_CR15_WRITE_TRAP 0x09f
#define SVM_EXIT_INVPCID 0x0a2
+#define SVM_EXIT_BUS_LOCK 0x0a5
#define SVM_EXIT_IDLE_HLT 0x0a6
#define SVM_EXIT_NPF 0x400
#define SVM_EXIT_AVIC_INCOMPLETE_IPI 0x401
@@ -225,6 +226,7 @@
{ SVM_EXIT_CR4_WRITE_TRAP, "write_cr4_trap" }, \
{ SVM_EXIT_CR8_WRITE_TRAP, "write_cr8_trap" }, \
{ SVM_EXIT_INVPCID, "invpcid" }, \
+ { SVM_EXIT_BUS_LOCK, "buslock" }, \
{ SVM_EXIT_IDLE_HLT, "idle-halt" }, \
{ SVM_EXIT_NPF, "npf" }, \
{ SVM_EXIT_AVIC_INCOMPLETE_IPI, "avic_incomplete_ipi" }, \
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index a5faf6d88f1b..f0f4a4cf84a7 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -34,6 +34,7 @@
#define EXIT_REASON_TRIPLE_FAULT 2
#define EXIT_REASON_INIT_SIGNAL 3
#define EXIT_REASON_SIPI_SIGNAL 4
+#define EXIT_REASON_OTHER_SMI 6
#define EXIT_REASON_INTERRUPT_WINDOW 7
#define EXIT_REASON_NMI_WINDOW 8
@@ -92,6 +93,7 @@
#define EXIT_REASON_TPAUSE 68
#define EXIT_REASON_BUS_LOCK 74
#define EXIT_REASON_NOTIFY 75
+#define EXIT_REASON_TDCALL 77
#define VMX_EXIT_REASONS \
{ EXIT_REASON_EXCEPTION_NMI, "EXCEPTION_NMI" }, \
@@ -155,7 +157,8 @@
{ EXIT_REASON_UMWAIT, "UMWAIT" }, \
{ EXIT_REASON_TPAUSE, "TPAUSE" }, \
{ EXIT_REASON_BUS_LOCK, "BUS_LOCK" }, \
- { EXIT_REASON_NOTIFY, "NOTIFY" }
+ { EXIT_REASON_NOTIFY, "NOTIFY" }, \
+ { EXIT_REASON_TDCALL, "TDCALL" }
#define VMX_EXIT_REASON_FLAGS \
{ VMX_EXIT_REASONS_FAILED_VMENTRY, "FAILED_VMENTRY" }
diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 84cfa179802c..0d2a6d953be9 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -3,7 +3,7 @@
# Makefile for the linux kernel.
#
-extra-y += vmlinux.lds
+always-$(KBUILD_BUILTIN) += vmlinux.lds
CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
@@ -141,7 +141,6 @@ obj-$(CONFIG_OF) += devicetree.o
obj-$(CONFIG_UPROBES) += uprobes.o
obj-$(CONFIG_PERF_EVENTS) += perf_regs.o
-obj-$(CONFIG_TRACING) += tracepoint.o
obj-$(CONFIG_SCHED_MC_PRIO) += itmt.o
obj-$(CONFIG_X86_UMIP) += umip.o
diff --git a/arch/x86/kernel/acpi/cppc.c b/arch/x86/kernel/acpi/cppc.c
index 77bfb846490c..7047124490f6 100644
--- a/arch/x86/kernel/acpi/cppc.c
+++ b/arch/x86/kernel/acpi/cppc.c
@@ -49,7 +49,7 @@ int cpc_read_ffh(int cpunum, struct cpc_reg *reg, u64 *val)
{
int err;
- err = rdmsrl_safe_on_cpu(cpunum, reg->address, val);
+ err = rdmsrq_safe_on_cpu(cpunum, reg->address, val);
if (!err) {
u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1,
reg->bit_offset);
@@ -65,7 +65,7 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
u64 rd_val;
int err;
- err = rdmsrl_safe_on_cpu(cpunum, reg->address, &rd_val);
+ err = rdmsrq_safe_on_cpu(cpunum, reg->address, &rd_val);
if (!err) {
u64 mask = GENMASK_ULL(reg->bit_offset + reg->bit_width - 1,
reg->bit_offset);
@@ -74,7 +74,7 @@ int cpc_write_ffh(int cpunum, struct cpc_reg *reg, u64 val)
val &= mask;
rd_val &= ~mask;
rd_val |= val;
- err = wrmsrl_safe_on_cpu(cpunum, reg->address, rd_val);
+ err = wrmsrq_safe_on_cpu(cpunum, reg->address, rd_val);
}
return err;
}
@@ -147,7 +147,7 @@ int amd_get_highest_perf(unsigned int cpu, u32 *highest_perf)
int ret;
if (cpu_feature_enabled(X86_FEATURE_CPPC)) {
- ret = rdmsrl_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &val);
+ ret = rdmsrq_safe_on_cpu(cpu, MSR_AMD_CPPC_CAP1, &val);
if (ret)
goto out;
@@ -272,7 +272,7 @@ int amd_get_boost_ratio_numerator(unsigned int cpu, u64 *numerator)
}
/* detect if running on heterogeneous design */
- if (cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES)) {
+ if (cpu_feature_enabled(X86_FEATURE_AMD_HTR_CORES)) {
switch (core_type) {
case TOPO_CPU_TYPE_UNKNOWN:
pr_warn("Undefined core type found for cpu %d\n", cpu);
diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index d5ac34186555..8698d66563ed 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -14,7 +14,7 @@
#include <acpi/processor.h>
#include <asm/cpu_device_id.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/mwait.h>
#include <asm/special_insns.h>
#include <asm/smp.h>
diff --git a/arch/x86/kernel/acpi/madt_wakeup.c b/arch/x86/kernel/acpi/madt_wakeup.c
index f36f28405dcc..6d7603511f52 100644
--- a/arch/x86/kernel/acpi/madt_wakeup.c
+++ b/arch/x86/kernel/acpi/madt_wakeup.c
@@ -126,7 +126,7 @@ static int __init acpi_mp_setup_reset(u64 reset_vector)
return 0;
}
-static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip)
+static int acpi_wakeup_cpu(u32 apicid, unsigned long start_ip, unsigned int cpu)
{
if (!acpi_mp_wake_mailbox_paddr) {
pr_warn_once("No MADT mailbox: cannot bringup secondary CPUs. Booting with kexec?\n");
diff --git a/arch/x86/kernel/acpi/sleep.c b/arch/x86/kernel/acpi/sleep.c
index 6dfecb27b846..91fa262f0e30 100644
--- a/arch/x86/kernel/acpi/sleep.c
+++ b/arch/x86/kernel/acpi/sleep.c
@@ -16,6 +16,7 @@
#include <asm/cacheflush.h>
#include <asm/realmode.h>
#include <asm/hypervisor.h>
+#include <asm/msr.h>
#include <asm/smp.h>
#include <linux/ftrace.h>
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 45bcff181cba..7bde68247b5f 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -1,39 +1,17 @@
// SPDX-License-Identifier: GPL-2.0-only
#define pr_fmt(fmt) "SMP alternatives: " fmt
-#include <linux/module.h>
-#include <linux/sched.h>
+#include <linux/mmu_context.h>
#include <linux/perf_event.h>
-#include <linux/mutex.h>
-#include <linux/list.h>
-#include <linux/stringify.h>
-#include <linux/highmem.h>
-#include <linux/mm.h>
#include <linux/vmalloc.h>
#include <linux/memory.h>
-#include <linux/stop_machine.h>
-#include <linux/slab.h>
-#include <linux/kdebug.h>
-#include <linux/kprobes.h>
-#include <linux/mmu_context.h>
-#include <linux/bsearch.h>
-#include <linux/sync_core.h>
#include <linux/execmem.h>
+
#include <asm/text-patching.h>
-#include <asm/alternative.h>
-#include <asm/sections.h>
-#include <asm/mce.h>
-#include <asm/nmi.h>
-#include <asm/cacheflush.h>
-#include <asm/tlbflush.h>
#include <asm/insn.h>
-#include <asm/io.h>
-#include <asm/fixmap.h>
-#include <asm/paravirt.h>
-#include <asm/asm-prototypes.h>
-#include <asm/cfi.h>
#include <asm/ibt.h>
#include <asm/set_memory.h>
+#include <asm/nmi.h>
int __read_mostly alternatives_patched;
@@ -138,6 +116,24 @@ static struct module *its_mod;
#endif
static void *its_page;
static unsigned int its_offset;
+struct its_array its_pages;
+
+static void *__its_alloc(struct its_array *pages)
+{
+ void *page __free(execmem) = execmem_alloc_rw(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+ if (!page)
+ return NULL;
+
+ void *tmp = krealloc(pages->pages, (pages->num+1) * sizeof(void *),
+ GFP_KERNEL);
+ if (!tmp)
+ return NULL;
+
+ pages->pages = tmp;
+ pages->pages[pages->num++] = page;
+
+ return no_free_ptr(page);
+}
/* Initialize a thunk with the "jmp *reg; int3" instructions. */
static void *its_init_thunk(void *thunk, int reg)
@@ -173,6 +169,21 @@ static void *its_init_thunk(void *thunk, int reg)
return thunk + offset;
}
+static void its_pages_protect(struct its_array *pages)
+{
+ for (int i = 0; i < pages->num; i++) {
+ void *page = pages->pages[i];
+ execmem_restore_rox(page, PAGE_SIZE);
+ }
+}
+
+static void its_fini_core(void)
+{
+ if (IS_ENABLED(CONFIG_STRICT_KERNEL_RWX))
+ its_pages_protect(&its_pages);
+ kfree(its_pages.pages);
+}
+
#ifdef CONFIG_MODULES
void its_init_mod(struct module *mod)
{
@@ -195,10 +206,8 @@ void its_fini_mod(struct module *mod)
its_page = NULL;
mutex_unlock(&text_mutex);
- for (int i = 0; i < mod->its_num_pages; i++) {
- void *page = mod->its_page_array[i];
- execmem_restore_rox(page, PAGE_SIZE);
- }
+ if (IS_ENABLED(CONFIG_STRICT_MODULE_RWX))
+ its_pages_protect(&mod->arch.its_pages);
}
void its_free_mod(struct module *mod)
@@ -206,37 +215,32 @@ void its_free_mod(struct module *mod)
if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
return;
- for (int i = 0; i < mod->its_num_pages; i++) {
- void *page = mod->its_page_array[i];
+ for (int i = 0; i < mod->arch.its_pages.num; i++) {
+ void *page = mod->arch.its_pages.pages[i];
execmem_free(page);
}
- kfree(mod->its_page_array);
+ kfree(mod->arch.its_pages.pages);
}
#endif /* CONFIG_MODULES */
static void *its_alloc(void)
{
- void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
-
- if (!page)
- return NULL;
+ struct its_array *pages = &its_pages;
+ void *page;
#ifdef CONFIG_MODULES
- if (its_mod) {
- void *tmp = krealloc(its_mod->its_page_array,
- (its_mod->its_num_pages+1) * sizeof(void *),
- GFP_KERNEL);
- if (!tmp)
- return NULL;
+ if (its_mod)
+ pages = &its_mod->arch.its_pages;
+#endif
- its_mod->its_page_array = tmp;
- its_mod->its_page_array[its_mod->its_num_pages++] = page;
+ page = __its_alloc(pages);
+ if (!page)
+ return NULL;
- execmem_make_temp_rw(page, PAGE_SIZE);
- }
-#endif /* CONFIG_MODULES */
+ if (pages == &its_pages)
+ set_memory_x((unsigned long)page, 1);
- return no_free_ptr(page);
+ return page;
}
static void *its_allocate_thunk(int reg)
@@ -290,7 +294,9 @@ u8 *its_static_thunk(int reg)
return thunk;
}
-#endif
+#else
+static inline void its_fini_core(void) {}
+#endif /* CONFIG_MITIGATION_ITS */
/*
* Nomenclature for variable names to simplify and clarify this code and ease
@@ -339,13 +345,6 @@ static void add_nop(u8 *buf, unsigned int len)
*buf = INT3_INSN_OPCODE;
}
-extern s32 __retpoline_sites[], __retpoline_sites_end[];
-extern s32 __return_sites[], __return_sites_end[];
-extern s32 __cfi_sites[], __cfi_sites_end[];
-extern s32 __ibt_endbr_seal[], __ibt_endbr_seal_end[];
-extern s32 __smp_locks[], __smp_locks_end[];
-void text_poke_early(void *addr, const void *opcode, size_t len);
-
/*
* Matches NOP and NOPL, not any of the other possible NOPs.
*/
@@ -537,7 +536,7 @@ static void __apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen,
}
}
-void apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len)
+void text_poke_apply_relocation(u8 *buf, const u8 * const instr, size_t instrlen, u8 *repl, size_t repl_len)
{
__apply_relocation(buf, instr, instrlen, repl, repl_len);
optimize_nops(instr, buf, instrlen);
@@ -625,7 +624,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
DPRINTK(ALT, "alt table %px, -> %px", start, end);
/*
- * In the case CONFIG_X86_5LEVEL=y, KASAN_SHADOW_START is defined using
+ * KASAN_SHADOW_START is defined using
* cpu_feature_enabled(X86_FEATURE_LA57) and is therefore patched here.
* During the process, KASAN becomes confused seeing partial LA57
* conversion and triggers a false-positive out-of-bound report.
@@ -693,7 +692,7 @@ void __init_or_module noinline apply_alternatives(struct alt_instr *start,
for (; insn_buff_sz < a->instrlen; insn_buff_sz++)
insn_buff[insn_buff_sz] = 0x90;
- apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen);
+ text_poke_apply_relocation(insn_buff, instr, a->instrlen, replacement, a->replacementlen);
DUMP_BYTES(ALT, instr, a->instrlen, "%px: old_insn: ", instr);
DUMP_BYTES(ALT, replacement, a->replacementlen, "%px: rpl_insn: ", replacement);
@@ -1184,43 +1183,6 @@ bool cfi_bhi __ro_after_init = false;
#endif
#ifdef CONFIG_CFI_CLANG
-struct bpf_insn;
-
-/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */
-extern unsigned int __bpf_prog_runX(const void *ctx,
- const struct bpf_insn *insn);
-
-KCFI_REFERENCE(__bpf_prog_runX);
-
-/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */
-asm (
-" .pushsection .data..ro_after_init,\"aw\",@progbits \n"
-" .type cfi_bpf_hash,@object \n"
-" .globl cfi_bpf_hash \n"
-" .p2align 2, 0x0 \n"
-"cfi_bpf_hash: \n"
-" .long __kcfi_typeid___bpf_prog_runX \n"
-" .size cfi_bpf_hash, 4 \n"
-" .popsection \n"
-);
-
-/* Must match bpf_callback_t */
-extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
-
-KCFI_REFERENCE(__bpf_callback_fn);
-
-/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */
-asm (
-" .pushsection .data..ro_after_init,\"aw\",@progbits \n"
-" .type cfi_bpf_subprog_hash,@object \n"
-" .globl cfi_bpf_subprog_hash \n"
-" .p2align 2, 0x0 \n"
-"cfi_bpf_subprog_hash: \n"
-" .long __kcfi_typeid___bpf_callback_fn \n"
-" .size cfi_bpf_subprog_hash, 4 \n"
-" .popsection \n"
-);
-
u32 cfi_get_func_hash(void *func)
{
u32 hash;
@@ -2305,7 +2267,7 @@ __visible noinline void __init __alt_reloc_selftest(void *arg)
static noinline void __init alt_reloc_selftest(void)
{
/*
- * Tests apply_relocation().
+ * Tests text_poke_apply_relocation().
*
* This has a relative immediate (CALL) in a place other than the first
* instruction and additionally on x86_64 we get a RIP-relative LEA:
@@ -2367,6 +2329,8 @@ void __init alternative_instructions(void)
apply_retpolines(__retpoline_sites, __retpoline_sites_end);
apply_returns(__return_sites, __return_sites_end);
+ its_fini_core();
+
/*
* Adjust all CALL instructions to point to func()-10, including
* those in .altinstr_replacement.
@@ -2442,76 +2406,8 @@ void __init_or_module text_poke_early(void *addr, const void *opcode,
}
}
-typedef struct {
- struct mm_struct *mm;
-} temp_mm_state_t;
-
-/*
- * Using a temporary mm allows to set temporary mappings that are not accessible
- * by other CPUs. Such mappings are needed to perform sensitive memory writes
- * that override the kernel memory protections (e.g., W^X), without exposing the
- * temporary page-table mappings that are required for these write operations to
- * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
- * mapping is torn down.
- *
- * Context: The temporary mm needs to be used exclusively by a single core. To
- * harden security IRQs must be disabled while the temporary mm is
- * loaded, thereby preventing interrupt handler bugs from overriding
- * the kernel memory protection.
- */
-static inline temp_mm_state_t use_temporary_mm(struct mm_struct *mm)
-{
- temp_mm_state_t temp_state;
-
- lockdep_assert_irqs_disabled();
-
- /*
- * Make sure not to be in TLB lazy mode, as otherwise we'll end up
- * with a stale address space WITHOUT being in lazy mode after
- * restoring the previous mm.
- */
- if (this_cpu_read(cpu_tlbstate_shared.is_lazy))
- leave_mm();
-
- temp_state.mm = this_cpu_read(cpu_tlbstate.loaded_mm);
- switch_mm_irqs_off(NULL, mm, current);
-
- /*
- * If breakpoints are enabled, disable them while the temporary mm is
- * used. Userspace might set up watchpoints on addresses that are used
- * in the temporary mm, which would lead to wrong signals being sent or
- * crashes.
- *
- * Note that breakpoints are not disabled selectively, which also causes
- * kernel breakpoints (e.g., perf's) to be disabled. This might be
- * undesirable, but still seems reasonable as the code that runs in the
- * temporary mm should be short.
- */
- if (hw_breakpoint_active())
- hw_breakpoint_disable();
-
- return temp_state;
-}
-
-__ro_after_init struct mm_struct *poking_mm;
-__ro_after_init unsigned long poking_addr;
-
-static inline void unuse_temporary_mm(temp_mm_state_t prev_state)
-{
- lockdep_assert_irqs_disabled();
-
- switch_mm_irqs_off(NULL, prev_state.mm, current);
-
- /* Clear the cpumask, to indicate no TLB flushing is needed anywhere */
- cpumask_clear_cpu(raw_smp_processor_id(), mm_cpumask(poking_mm));
-
- /*
- * Restore the breakpoints if they were disabled before the temporary mm
- * was loaded.
- */
- if (hw_breakpoint_active())
- hw_breakpoint_restore();
-}
+__ro_after_init struct mm_struct *text_poke_mm;
+__ro_after_init unsigned long text_poke_mm_addr;
static void text_poke_memcpy(void *dst, const void *src, size_t len)
{
@@ -2531,7 +2427,7 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l
{
bool cross_page_boundary = offset_in_page(addr) + len > PAGE_SIZE;
struct page *pages[2] = {NULL};
- temp_mm_state_t prev;
+ struct mm_struct *prev_mm;
unsigned long flags;
pte_t pte, *ptep;
spinlock_t *ptl;
@@ -2568,7 +2464,7 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l
/*
* The lock is not really needed, but this allows to avoid open-coding.
*/
- ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+ ptep = get_locked_pte(text_poke_mm, text_poke_mm_addr, &ptl);
/*
* This must not fail; preallocated in poking_init().
@@ -2578,21 +2474,21 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l
local_irq_save(flags);
pte = mk_pte(pages[0], pgprot);
- set_pte_at(poking_mm, poking_addr, ptep, pte);
+ set_pte_at(text_poke_mm, text_poke_mm_addr, ptep, pte);
if (cross_page_boundary) {
pte = mk_pte(pages[1], pgprot);
- set_pte_at(poking_mm, poking_addr + PAGE_SIZE, ptep + 1, pte);
+ set_pte_at(text_poke_mm, text_poke_mm_addr + PAGE_SIZE, ptep + 1, pte);
}
/*
* Loading the temporary mm behaves as a compiler barrier, which
* guarantees that the PTE will be set at the time memcpy() is done.
*/
- prev = use_temporary_mm(poking_mm);
+ prev_mm = use_temporary_mm(text_poke_mm);
kasan_disable_current();
- func((u8 *)poking_addr + offset_in_page(addr), src, len);
+ func((u8 *)text_poke_mm_addr + offset_in_page(addr), src, len);
kasan_enable_current();
/*
@@ -2601,22 +2497,22 @@ static void *__text_poke(text_poke_f func, void *addr, const void *src, size_t l
*/
barrier();
- pte_clear(poking_mm, poking_addr, ptep);
+ pte_clear(text_poke_mm, text_poke_mm_addr, ptep);
if (cross_page_boundary)
- pte_clear(poking_mm, poking_addr + PAGE_SIZE, ptep + 1);
+ pte_clear(text_poke_mm, text_poke_mm_addr + PAGE_SIZE, ptep + 1);
/*
* Loading the previous page-table hierarchy requires a serializing
* instruction that already allows the core to see the updated version.
* Xen-PV is assumed to serialize execution in a similar manner.
*/
- unuse_temporary_mm(prev);
+ unuse_temporary_mm(prev_mm);
/*
* Flushing the TLB might involve IPIs, which would require enabled
* IRQs, but not if the mm is not used, as it is in this point.
*/
- flush_tlb_mm_range(poking_mm, poking_addr, poking_addr +
+ flush_tlb_mm_range(text_poke_mm, text_poke_mm_addr, text_poke_mm_addr +
(cross_page_boundary ? 2 : 1) * PAGE_SIZE,
PAGE_SHIFT, false);
@@ -2752,7 +2648,7 @@ static void do_sync_core(void *info)
sync_core();
}
-void text_poke_sync(void)
+void smp_text_poke_sync_each_cpu(void)
{
on_each_cpu(do_sync_core, NULL, 1);
}
@@ -2762,64 +2658,66 @@ void text_poke_sync(void)
* this thing. When len == 6 everything is prefixed with 0x0f and we map
* opcode to Jcc.d8, using len to distinguish.
*/
-struct text_poke_loc {
+struct smp_text_poke_loc {
/* addr := _stext + rel_addr */
s32 rel_addr;
s32 disp;
u8 len;
u8 opcode;
- const u8 text[POKE_MAX_OPCODE_SIZE];
- /* see text_poke_bp_batch() */
+ const u8 text[TEXT_POKE_MAX_OPCODE_SIZE];
+ /* see smp_text_poke_batch_finish() */
u8 old;
};
-struct bp_patching_desc {
- struct text_poke_loc *vec;
+#define TEXT_POKE_ARRAY_MAX (PAGE_SIZE / sizeof(struct smp_text_poke_loc))
+
+static struct smp_text_poke_array {
+ struct smp_text_poke_loc vec[TEXT_POKE_ARRAY_MAX];
int nr_entries;
- atomic_t refs;
-};
+} text_poke_array;
-static struct bp_patching_desc bp_desc;
+static DEFINE_PER_CPU(atomic_t, text_poke_array_refs);
-static __always_inline
-struct bp_patching_desc *try_get_desc(void)
+/*
+ * These four __always_inline annotations imply noinstr, necessary
+ * due to smp_text_poke_int3_handler() being noinstr:
+ */
+
+static __always_inline bool try_get_text_poke_array(void)
{
- struct bp_patching_desc *desc = &bp_desc;
+ atomic_t *refs = this_cpu_ptr(&text_poke_array_refs);
- if (!raw_atomic_inc_not_zero(&desc->refs))
- return NULL;
+ if (!raw_atomic_inc_not_zero(refs))
+ return false;
- return desc;
+ return true;
}
-static __always_inline void put_desc(void)
+static __always_inline void put_text_poke_array(void)
{
- struct bp_patching_desc *desc = &bp_desc;
+ atomic_t *refs = this_cpu_ptr(&text_poke_array_refs);
smp_mb__before_atomic();
- raw_atomic_dec(&desc->refs);
+ raw_atomic_dec(refs);
}
-static __always_inline void *text_poke_addr(struct text_poke_loc *tp)
+static __always_inline void *text_poke_addr(const struct smp_text_poke_loc *tpl)
{
- return _stext + tp->rel_addr;
+ return _stext + tpl->rel_addr;
}
-static __always_inline int patch_cmp(const void *key, const void *elt)
+static __always_inline int patch_cmp(const void *tpl_a, const void *tpl_b)
{
- struct text_poke_loc *tp = (struct text_poke_loc *) elt;
-
- if (key < text_poke_addr(tp))
+ if (tpl_a < text_poke_addr(tpl_b))
return -1;
- if (key > text_poke_addr(tp))
+ if (tpl_a > text_poke_addr(tpl_b))
return 1;
return 0;
}
-noinstr int poke_int3_handler(struct pt_regs *regs)
+noinstr int smp_text_poke_int3_handler(struct pt_regs *regs)
{
- struct bp_patching_desc *desc;
- struct text_poke_loc *tp;
+ struct smp_text_poke_loc *tpl;
int ret = 0;
void *ip;
@@ -2828,41 +2726,40 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
/*
* Having observed our INT3 instruction, we now must observe
- * bp_desc with non-zero refcount:
+ * text_poke_array with non-zero refcount:
*
- * bp_desc.refs = 1 INT3
- * WMB RMB
- * write INT3 if (bp_desc.refs != 0)
+ * text_poke_array_refs = 1 INT3
+ * WMB RMB
+ * write INT3 if (text_poke_array_refs != 0)
*/
smp_rmb();
- desc = try_get_desc();
- if (!desc)
+ if (!try_get_text_poke_array())
return 0;
/*
- * Discount the INT3. See text_poke_bp_batch().
+ * Discount the INT3. See smp_text_poke_batch_finish().
*/
ip = (void *) regs->ip - INT3_INSN_SIZE;
/*
* Skip the binary search if there is a single member in the vector.
*/
- if (unlikely(desc->nr_entries > 1)) {
- tp = __inline_bsearch(ip, desc->vec, desc->nr_entries,
- sizeof(struct text_poke_loc),
+ if (unlikely(text_poke_array.nr_entries > 1)) {
+ tpl = __inline_bsearch(ip, text_poke_array.vec, text_poke_array.nr_entries,
+ sizeof(struct smp_text_poke_loc),
patch_cmp);
- if (!tp)
+ if (!tpl)
goto out_put;
} else {
- tp = desc->vec;
- if (text_poke_addr(tp) != ip)
+ tpl = text_poke_array.vec;
+ if (text_poke_addr(tpl) != ip)
goto out_put;
}
- ip += tp->len;
+ ip += tpl->len;
- switch (tp->opcode) {
+ switch (tpl->opcode) {
case INT3_INSN_OPCODE:
/*
* Someone poked an explicit INT3, they'll want to handle it,
@@ -2875,16 +2772,16 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
break;
case CALL_INSN_OPCODE:
- int3_emulate_call(regs, (long)ip + tp->disp);
+ int3_emulate_call(regs, (long)ip + tpl->disp);
break;
case JMP32_INSN_OPCODE:
case JMP8_INSN_OPCODE:
- int3_emulate_jmp(regs, (long)ip + tp->disp);
+ int3_emulate_jmp(regs, (long)ip + tpl->disp);
break;
case 0x70 ... 0x7f: /* Jcc */
- int3_emulate_jcc(regs, tp->opcode & 0xf, (long)ip, tp->disp);
+ int3_emulate_jcc(regs, tpl->opcode & 0xf, (long)ip, tpl->disp);
break;
default:
@@ -2894,51 +2791,50 @@ noinstr int poke_int3_handler(struct pt_regs *regs)
ret = 1;
out_put:
- put_desc();
+ put_text_poke_array();
return ret;
}
-#define TP_VEC_MAX (PAGE_SIZE / sizeof(struct text_poke_loc))
-static struct text_poke_loc tp_vec[TP_VEC_MAX];
-static int tp_vec_nr;
-
/**
- * text_poke_bp_batch() -- update instructions on live kernel on SMP
- * @tp: vector of instructions to patch
- * @nr_entries: number of entries in the vector
+ * smp_text_poke_batch_finish() -- update instructions on live kernel on SMP
*
- * Modify multi-byte instruction by using int3 breakpoint on SMP.
- * We completely avoid stop_machine() here, and achieve the
- * synchronization using int3 breakpoint.
+ * Input state:
+ * text_poke_array.vec: vector of instructions to patch
+ * text_poke_array.nr_entries: number of entries in the vector
+ *
+ * Modify multi-byte instructions by using INT3 breakpoints on SMP.
+ * We completely avoid using stop_machine() here, and achieve the
+ * synchronization using INT3 breakpoints and SMP cross-calls.
*
* The way it is done:
* - For each entry in the vector:
- * - add a int3 trap to the address that will be patched
- * - sync cores
+ * - add an INT3 trap to the address that will be patched
+ * - SMP sync all CPUs
* - For each entry in the vector:
* - update all but the first byte of the patched range
- * - sync cores
+ * - SMP sync all CPUs
* - For each entry in the vector:
- * - replace the first byte (int3) by the first byte of
+ * - replace the first byte (INT3) by the first byte of the
* replacing opcode
- * - sync cores
+ * - SMP sync all CPUs
*/
-static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries)
+void smp_text_poke_batch_finish(void)
{
unsigned char int3 = INT3_INSN_OPCODE;
unsigned int i;
int do_sync;
- lockdep_assert_held(&text_mutex);
+ if (!text_poke_array.nr_entries)
+ return;
- bp_desc.vec = tp;
- bp_desc.nr_entries = nr_entries;
+ lockdep_assert_held(&text_mutex);
/*
- * Corresponds to the implicit memory barrier in try_get_desc() to
- * ensure reading a non-zero refcount provides up to date bp_desc data.
+ * Corresponds to the implicit memory barrier in try_get_text_poke_array() to
+ * ensure reading a non-zero refcount provides up to date text_poke_array data.
*/
- atomic_set_release(&bp_desc.refs, 1);
+ for_each_possible_cpu(i)
+ atomic_set_release(per_cpu_ptr(&text_poke_array_refs, i), 1);
/*
* Function tracing can enable thousands of places that need to be
@@ -2951,33 +2847,33 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
cond_resched();
/*
- * Corresponding read barrier in int3 notifier for making sure the
- * nr_entries and handler are correctly ordered wrt. patching.
+ * Corresponding read barrier in INT3 notifier for making sure the
+ * text_poke_array.nr_entries and handler are correctly ordered wrt. patching.
*/
smp_wmb();
/*
- * First step: add a int3 trap to the address that will be patched.
+ * First step: add a INT3 trap to the address that will be patched.
*/
- for (i = 0; i < nr_entries; i++) {
- tp[i].old = *(u8 *)text_poke_addr(&tp[i]);
- text_poke(text_poke_addr(&tp[i]), &int3, INT3_INSN_SIZE);
+ for (i = 0; i < text_poke_array.nr_entries; i++) {
+ text_poke_array.vec[i].old = *(u8 *)text_poke_addr(&text_poke_array.vec[i]);
+ text_poke(text_poke_addr(&text_poke_array.vec[i]), &int3, INT3_INSN_SIZE);
}
- text_poke_sync();
+ smp_text_poke_sync_each_cpu();
/*
* Second step: update all but the first byte of the patched range.
*/
- for (do_sync = 0, i = 0; i < nr_entries; i++) {
- u8 old[POKE_MAX_OPCODE_SIZE+1] = { tp[i].old, };
- u8 _new[POKE_MAX_OPCODE_SIZE+1];
- const u8 *new = tp[i].text;
- int len = tp[i].len;
+ for (do_sync = 0, i = 0; i < text_poke_array.nr_entries; i++) {
+ u8 old[TEXT_POKE_MAX_OPCODE_SIZE+1] = { text_poke_array.vec[i].old, };
+ u8 _new[TEXT_POKE_MAX_OPCODE_SIZE+1];
+ const u8 *new = text_poke_array.vec[i].text;
+ int len = text_poke_array.vec[i].len;
if (len - INT3_INSN_SIZE > 0) {
memcpy(old + INT3_INSN_SIZE,
- text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+ text_poke_addr(&text_poke_array.vec[i]) + INT3_INSN_SIZE,
len - INT3_INSN_SIZE);
if (len == 6) {
@@ -2986,7 +2882,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
new = _new;
}
- text_poke(text_poke_addr(&tp[i]) + INT3_INSN_SIZE,
+ text_poke(text_poke_addr(&text_poke_array.vec[i]) + INT3_INSN_SIZE,
new + INT3_INSN_SIZE,
len - INT3_INSN_SIZE);
@@ -3017,7 +2913,7 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
* The old instruction is recorded so that the event can be
* processed forwards or backwards.
*/
- perf_event_text_poke(text_poke_addr(&tp[i]), old, len, new, len);
+ perf_event_text_poke(text_poke_addr(&text_poke_array.vec[i]), old, len, new, len);
}
if (do_sync) {
@@ -3026,63 +2922,79 @@ static void text_poke_bp_batch(struct text_poke_loc *tp, unsigned int nr_entries
* not necessary and we'd be safe even without it. But
* better safe than sorry (plus there's not only Intel).
*/
- text_poke_sync();
+ smp_text_poke_sync_each_cpu();
}
/*
- * Third step: replace the first byte (int3) by the first byte of
+ * Third step: replace the first byte (INT3) by the first byte of the
* replacing opcode.
*/
- for (do_sync = 0, i = 0; i < nr_entries; i++) {
- u8 byte = tp[i].text[0];
+ for (do_sync = 0, i = 0; i < text_poke_array.nr_entries; i++) {
+ u8 byte = text_poke_array.vec[i].text[0];
- if (tp[i].len == 6)
+ if (text_poke_array.vec[i].len == 6)
byte = 0x0f;
if (byte == INT3_INSN_OPCODE)
continue;
- text_poke(text_poke_addr(&tp[i]), &byte, INT3_INSN_SIZE);
+ text_poke(text_poke_addr(&text_poke_array.vec[i]), &byte, INT3_INSN_SIZE);
do_sync++;
}
if (do_sync)
- text_poke_sync();
+ smp_text_poke_sync_each_cpu();
/*
* Remove and wait for refs to be zero.
+ *
+ * Notably, if after step-3 above the INT3 got removed, then the
+ * smp_text_poke_sync_each_cpu() will have serialized against any running INT3
+ * handlers and the below spin-wait will not happen.
+ *
+ * IOW. unless the replacement instruction is INT3, this case goes
+ * unused.
*/
- if (!atomic_dec_and_test(&bp_desc.refs))
- atomic_cond_read_acquire(&bp_desc.refs, !VAL);
+ for_each_possible_cpu(i) {
+ atomic_t *refs = per_cpu_ptr(&text_poke_array_refs, i);
+
+ if (unlikely(!atomic_dec_and_test(refs)))
+ atomic_cond_read_acquire(refs, !VAL);
+ }
+
+ /* They are all completed: */
+ text_poke_array.nr_entries = 0;
}
-static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
- const void *opcode, size_t len, const void *emulate)
+static void __smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, const void *emulate)
{
+ struct smp_text_poke_loc *tpl;
struct insn insn;
int ret, i = 0;
+ tpl = &text_poke_array.vec[text_poke_array.nr_entries++];
+
if (len == 6)
i = 1;
- memcpy((void *)tp->text, opcode+i, len-i);
+ memcpy((void *)tpl->text, opcode+i, len-i);
if (!emulate)
emulate = opcode;
ret = insn_decode_kernel(&insn, emulate);
BUG_ON(ret < 0);
- tp->rel_addr = addr - (void *)_stext;
- tp->len = len;
- tp->opcode = insn.opcode.bytes[0];
+ tpl->rel_addr = addr - (void *)_stext;
+ tpl->len = len;
+ tpl->opcode = insn.opcode.bytes[0];
if (is_jcc32(&insn)) {
/*
* Map Jcc.d32 onto Jcc.d8 and use len to distinguish.
*/
- tp->opcode = insn.opcode.bytes[1] - 0x10;
+ tpl->opcode = insn.opcode.bytes[1] - 0x10;
}
- switch (tp->opcode) {
+ switch (tpl->opcode) {
case RET_INSN_OPCODE:
case JMP32_INSN_OPCODE:
case JMP8_INSN_OPCODE:
@@ -3091,14 +3003,14 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
* next instruction can be padded with INT3.
*/
for (i = insn.length; i < len; i++)
- BUG_ON(tp->text[i] != INT3_INSN_OPCODE);
+ BUG_ON(tpl->text[i] != INT3_INSN_OPCODE);
break;
default:
BUG_ON(len != insn.length);
}
- switch (tp->opcode) {
+ switch (tpl->opcode) {
case INT3_INSN_OPCODE:
case RET_INSN_OPCODE:
break;
@@ -3107,21 +3019,21 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
case JMP32_INSN_OPCODE:
case JMP8_INSN_OPCODE:
case 0x70 ... 0x7f: /* Jcc */
- tp->disp = insn.immediate.value;
+ tpl->disp = insn.immediate.value;
break;
default: /* assume NOP */
switch (len) {
case 2: /* NOP2 -- emulate as JMP8+0 */
BUG_ON(memcmp(emulate, x86_nops[len], len));
- tp->opcode = JMP8_INSN_OPCODE;
- tp->disp = 0;
+ tpl->opcode = JMP8_INSN_OPCODE;
+ tpl->disp = 0;
break;
case 5: /* NOP5 -- emulate as JMP32+0 */
BUG_ON(memcmp(emulate, x86_nops[len], len));
- tp->opcode = JMP32_INSN_OPCODE;
- tp->disp = 0;
+ tpl->opcode = JMP32_INSN_OPCODE;
+ tpl->disp = 0;
break;
default: /* unknown instruction */
@@ -3132,51 +3044,50 @@ static void text_poke_loc_init(struct text_poke_loc *tp, void *addr,
}
/*
- * We hard rely on the tp_vec being ordered; ensure this is so by flushing
+ * We hard rely on the text_poke_array.vec being ordered; ensure this is so by flushing
* early if needed.
*/
-static bool tp_order_fail(void *addr)
+static bool text_poke_addr_ordered(void *addr)
{
- struct text_poke_loc *tp;
-
- if (!tp_vec_nr)
- return false;
+ WARN_ON_ONCE(!addr);
- if (!addr) /* force */
+ if (!text_poke_array.nr_entries)
return true;
- tp = &tp_vec[tp_vec_nr - 1];
- if ((unsigned long)text_poke_addr(tp) > (unsigned long)addr)
- return true;
-
- return false;
-}
-
-static void text_poke_flush(void *addr)
-{
- if (tp_vec_nr == TP_VEC_MAX || tp_order_fail(addr)) {
- text_poke_bp_batch(tp_vec, tp_vec_nr);
- tp_vec_nr = 0;
- }
-}
+ /*
+ * If the last current entry's address is higher than the
+ * new entry's address we'd like to add, then ordering
+ * is violated and we must first flush all pending patching
+ * requests:
+ */
+ if (text_poke_addr(text_poke_array.vec + text_poke_array.nr_entries-1) > addr)
+ return false;
-void text_poke_finish(void)
-{
- text_poke_flush(NULL);
+ return true;
}
-void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const void *emulate)
+/**
+ * smp_text_poke_batch_add() -- update instruction on live kernel on SMP, batched
+ * @addr: address to patch
+ * @opcode: opcode of new instruction
+ * @len: length to copy
+ * @emulate: instruction to be emulated
+ *
+ * Add a new instruction to the current queue of to-be-patched instructions
+ * the kernel maintains. The patching request will not be executed immediately,
+ * but becomes part of an array of patching requests, optimized for batched
+ * execution. All pending patching requests will be executed on the next
+ * smp_text_poke_batch_finish() call.
+ */
+void __ref smp_text_poke_batch_add(void *addr, const void *opcode, size_t len, const void *emulate)
{
- struct text_poke_loc *tp;
-
- text_poke_flush(addr);
-
- tp = &tp_vec[tp_vec_nr++];
- text_poke_loc_init(tp, addr, opcode, len, emulate);
+ if (text_poke_array.nr_entries == TEXT_POKE_ARRAY_MAX || !text_poke_addr_ordered(addr))
+ smp_text_poke_batch_finish();
+ __smp_text_poke_batch_add(addr, opcode, len, emulate);
}
/**
- * text_poke_bp() -- update instructions on live kernel on SMP
+ * smp_text_poke_single() -- update instruction on live kernel on SMP immediately
* @addr: address to patch
* @opcode: opcode of new instruction
* @len: length to copy
@@ -3184,12 +3095,11 @@ void __ref text_poke_queue(void *addr, const void *opcode, size_t len, const voi
*
* Update a single instruction with the vector in the stack, avoiding
* dynamically allocated memory. This function should be used when it is
- * not possible to allocate memory.
+ * not possible to allocate memory for a vector. The single instruction
+ * is patched in immediately.
*/
-void __ref text_poke_bp(void *addr, const void *opcode, size_t len, const void *emulate)
+void __ref smp_text_poke_single(void *addr, const void *opcode, size_t len, const void *emulate)
{
- struct text_poke_loc tp;
-
- text_poke_loc_init(&tp, addr, opcode, len, emulate);
- text_poke_bp_batch(&tp, 1);
+ smp_text_poke_batch_add(addr, opcode, len, emulate);
+ smp_text_poke_batch_finish();
}
diff --git a/arch/x86/kernel/amd_gart_64.c b/arch/x86/kernel/amd_gart_64.c
index c884deca839b..3485d419c2f5 100644
--- a/arch/x86/kernel/amd_gart_64.c
+++ b/arch/x86/kernel/amd_gart_64.c
@@ -39,7 +39,7 @@
#include <asm/gart.h>
#include <asm/set_memory.h>
#include <asm/dma.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
#include <asm/x86_init.h>
static unsigned long iommu_bus_base; /* GART remapping area (physical) */
diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c
index 6d12a9b69432..c1acead6227a 100644
--- a/arch/x86/kernel/amd_nb.c
+++ b/arch/x86/kernel/amd_nb.c
@@ -13,7 +13,9 @@
#include <linux/export.h>
#include <linux/spinlock.h>
#include <linux/pci_ids.h>
-#include <asm/amd_nb.h>
+
+#include <asm/amd/nb.h>
+#include <asm/cpuid/api.h>
static u32 *flush_words;
@@ -91,10 +93,7 @@ static int amd_cache_northbridges(void)
if (amd_gart_present())
amd_northbridges.flags |= AMD_NB_GART;
- /*
- * Check for L3 cache presence.
- */
- if (!cpuid_edx(0x80000006))
+ if (!cpuid_amd_hygon_has_l3_cache())
return 0;
/*
@@ -151,7 +150,7 @@ struct resource *amd_get_mmconfig_range(struct resource *res)
/* Assume CPUs from Fam10h have mmconfig, although not all VMs do */
if (boot_cpu_data.x86 < 0x10 ||
- rdmsrl_safe(MSR_FAM10H_MMIO_CONF_BASE, &msr))
+ rdmsrq_safe(MSR_FAM10H_MMIO_CONF_BASE, &msr))
return NULL;
/* mmconfig is not enabled */
diff --git a/arch/x86/kernel/amd_node.c b/arch/x86/kernel/amd_node.c
index b670fa85c61b..a40176b62eb5 100644
--- a/arch/x86/kernel/amd_node.c
+++ b/arch/x86/kernel/amd_node.c
@@ -9,7 +9,7 @@
*/
#include <linux/debugfs.h>
-#include <asm/amd_node.h>
+#include <asm/amd/node.h>
/*
* AMD Nodes are a physical collection of I/O devices within an SoC. There can be one
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 89c0c8a3fc7e..769321185a08 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -29,7 +29,7 @@
#include <asm/gart.h>
#include <asm/pci-direct.h>
#include <asm/dma.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
#include <asm/x86_init.h>
#include <linux/crash_dump.h>
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 62584a347931..d73ba5a7b623 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -59,6 +59,7 @@
#include <asm/time.h>
#include <asm/smp.h>
#include <asm/mce.h>
+#include <asm/msr.h>
#include <asm/tsc.h>
#include <asm/hypervisor.h>
#include <asm/cpu_device_id.h>
@@ -425,7 +426,7 @@ static int lapic_next_deadline(unsigned long delta,
weak_wrmsr_fence();
tsc = rdtsc();
- wrmsrl(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR));
+ wrmsrq(MSR_IA32_TSC_DEADLINE, tsc + (((u64) delta) * TSC_DIVISOR));
return 0;
}
@@ -449,7 +450,7 @@ static int lapic_timer_shutdown(struct clock_event_device *evt)
* the timer _and_ zero the counter registers:
*/
if (v & APIC_LVT_TIMER_TSCDEADLINE)
- wrmsrl(MSR_IA32_TSC_DEADLINE, 0);
+ wrmsrq(MSR_IA32_TSC_DEADLINE, 0);
else
apic_write(APIC_TMICT, 0);
@@ -1694,7 +1695,7 @@ static bool x2apic_hw_locked(void)
x86_arch_cap_msr = x86_read_arch_cap_msr();
if (x86_arch_cap_msr & ARCH_CAP_XAPIC_DISABLE) {
- rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr);
+ rdmsrq(MSR_IA32_XAPIC_DISABLE_STATUS, msr);
return (msr & LEGACY_XAPIC_DISABLED);
}
return false;
@@ -1707,12 +1708,12 @@ static void __x2apic_disable(void)
if (!boot_cpu_has(X86_FEATURE_APIC))
return;
- rdmsrl(MSR_IA32_APICBASE, msr);
+ rdmsrq(MSR_IA32_APICBASE, msr);
if (!(msr & X2APIC_ENABLE))
return;
/* Disable xapic and x2apic first and then reenable xapic mode */
- wrmsrl(MSR_IA32_APICBASE, msr & ~(X2APIC_ENABLE | XAPIC_ENABLE));
- wrmsrl(MSR_IA32_APICBASE, msr & ~X2APIC_ENABLE);
+ wrmsrq(MSR_IA32_APICBASE, msr & ~(X2APIC_ENABLE | XAPIC_ENABLE));
+ wrmsrq(MSR_IA32_APICBASE, msr & ~X2APIC_ENABLE);
printk_once(KERN_INFO "x2apic disabled\n");
}
@@ -1720,10 +1721,10 @@ static void __x2apic_enable(void)
{
u64 msr;
- rdmsrl(MSR_IA32_APICBASE, msr);
+ rdmsrq(MSR_IA32_APICBASE, msr);
if (msr & X2APIC_ENABLE)
return;
- wrmsrl(MSR_IA32_APICBASE, msr | X2APIC_ENABLE);
+ wrmsrq(MSR_IA32_APICBASE, msr | X2APIC_ENABLE);
printk_once(KERN_INFO "x2apic enabled\n");
}
diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c
index b5bb7a2e8340..58abb941c45b 100644
--- a/arch/x86/kernel/apic/apic_noop.c
+++ b/arch/x86/kernel/apic/apic_noop.c
@@ -27,7 +27,13 @@ static void noop_send_IPI_allbutself(int vector) { }
static void noop_send_IPI_all(int vector) { }
static void noop_send_IPI_self(int vector) { }
static void noop_apic_icr_write(u32 low, u32 id) { }
-static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip) { return -1; }
+
+static int noop_wakeup_secondary_cpu(u32 apicid, unsigned long start_eip,
+ unsigned int cpu)
+{
+ return -1;
+}
+
static u64 noop_apic_icr_read(void) { return 0; }
static u32 noop_get_apic_id(u32 apicid) { return 0; }
static void noop_apic_eoi(void) { }
diff --git a/arch/x86/kernel/apic/apic_numachip.c b/arch/x86/kernel/apic/apic_numachip.c
index 16410f087b7a..5c5be2d58242 100644
--- a/arch/x86/kernel/apic/apic_numachip.c
+++ b/arch/x86/kernel/apic/apic_numachip.c
@@ -14,6 +14,7 @@
#include <linux/init.h>
#include <linux/pgtable.h>
+#include <asm/msr.h>
#include <asm/numachip/numachip.h>
#include <asm/numachip/numachip_csr.h>
@@ -31,7 +32,7 @@ static u32 numachip1_get_apic_id(u32 x)
unsigned int id = (x >> 24) & 0xff;
if (static_cpu_has(X86_FEATURE_NODEID_MSR)) {
- rdmsrl(MSR_FAM10H_NODE_ID, value);
+ rdmsrq(MSR_FAM10H_NODE_ID, value);
id |= (value << 2) & 0xff00;
}
@@ -42,7 +43,7 @@ static u32 numachip2_get_apic_id(u32 x)
{
u64 mcfg;
- rdmsrl(MSR_FAM10H_MMIO_CONF_BASE, mcfg);
+ rdmsrq(MSR_FAM10H_MMIO_CONF_BASE, mcfg);
return ((mcfg >> (28 - 8)) & 0xfff00) | (x >> 24);
}
@@ -56,7 +57,7 @@ static void numachip2_apic_icr_write(int apicid, unsigned int val)
numachip2_write32_lcsr(NUMACHIP2_APIC_ICR, (apicid << 12) | val);
}
-static int numachip_wakeup_secondary(u32 phys_apicid, unsigned long start_rip)
+static int numachip_wakeup_secondary(u32 phys_apicid, unsigned long start_rip, unsigned int cpu)
{
numachip_apic_icr_write(phys_apicid, APIC_DM_INIT);
numachip_apic_icr_write(phys_apicid, APIC_DM_STARTUP |
@@ -150,7 +151,7 @@ static void fixup_cpu_id(struct cpuinfo_x86 *c, int node)
/* Account for nodes per socket in multi-core-module processors */
if (boot_cpu_has(X86_FEATURE_NODEID_MSR)) {
- rdmsrl(MSR_FAM10H_NODE_ID, val);
+ rdmsrq(MSR_FAM10H_NODE_ID, val);
nodes = ((val >> 3) & 7) + 1;
}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index eebc360ed1bb..5ba2feb2c04c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -1486,7 +1486,7 @@ static void __init delay_with_tsc(void)
* 1 GHz == 40 jiffies
*/
do {
- rep_nop();
+ native_pause();
now = rdtsc();
} while ((now - start) < 40000000000ULL / HZ && time_before_eq(jiffies, end));
}
@@ -2225,7 +2225,7 @@ static int mp_irqdomain_create(int ioapic)
/* Handle device tree enumerated APICs proper */
if (cfg->dev) {
- fn = of_node_to_fwnode(cfg->dev);
+ fn = of_fwnode_handle(cfg->dev);
} else {
fn = irq_domain_alloc_named_id_fwnode("IO-APIC", mpc_ioapic_id(ioapic));
if (!fn)
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index fee42a73d64a..a947b46a8b64 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -183,6 +183,7 @@ setnew:
apicd->cpu = newcpu;
BUG_ON(!IS_ERR_OR_NULL(per_cpu(vector_irq, newcpu)[newvec]));
per_cpu(vector_irq, newcpu)[newvec] = desc;
+ apic_update_irq_cfg(irqd, newvec, newcpu);
}
static void vector_assign_managed_shutdown(struct irq_data *irqd)
@@ -261,7 +262,6 @@ assign_vector_locked(struct irq_data *irqd, const struct cpumask *dest)
if (vector < 0)
return vector;
apic_update_vector(irqd, vector, cpu);
- apic_update_irq_cfg(irqd, vector, cpu);
return 0;
}
@@ -338,7 +338,7 @@ assign_managed_vector(struct irq_data *irqd, const struct cpumask *dest)
if (vector < 0)
return vector;
apic_update_vector(irqd, vector, cpu);
- apic_update_irq_cfg(irqd, vector, cpu);
+
return 0;
}
@@ -864,7 +864,7 @@ void lapic_offline(void)
__vector_cleanup(cl, false);
irq_matrix_offline(vector_matrix);
- WARN_ON_ONCE(try_to_del_timer_sync(&cl->timer) < 0);
+ WARN_ON_ONCE(timer_delete_sync_try(&cl->timer) < 0);
WARN_ON_ONCE(!hlist_empty(&cl->head));
unlock_vector_lock();
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 7fef504ca508..15209f220e1f 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -667,7 +667,7 @@ static __init void build_uv_gr_table(void)
}
}
-static int uv_wakeup_secondary(u32 phys_apicid, unsigned long start_rip)
+static int uv_wakeup_secondary(u32 phys_apicid, unsigned long start_rip, unsigned int cpu)
{
unsigned long val;
int pnode;
diff --git a/arch/x86/kernel/asm-offsets.c b/arch/x86/kernel/asm-offsets.c
index ad4ea6fb3b6c..6259b474073b 100644
--- a/arch/x86/kernel/asm-offsets.c
+++ b/arch/x86/kernel/asm-offsets.c
@@ -33,6 +33,14 @@
static void __used common(void)
{
+ OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
+ OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
+ OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
+ OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping);
+ OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level);
+ OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability);
+ OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
+
BLANK();
OFFSET(TASK_threadsp, task_struct, thread.sp);
#ifdef CONFIG_STACKPROTECTOR
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 2b411cd00a4e..e0a292db97b2 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -12,15 +12,6 @@ void foo(void);
void foo(void)
{
- OFFSET(CPUINFO_x86, cpuinfo_x86, x86);
- OFFSET(CPUINFO_x86_vendor, cpuinfo_x86, x86_vendor);
- OFFSET(CPUINFO_x86_model, cpuinfo_x86, x86_model);
- OFFSET(CPUINFO_x86_stepping, cpuinfo_x86, x86_stepping);
- OFFSET(CPUINFO_cpuid_level, cpuinfo_x86, cpuid_level);
- OFFSET(CPUINFO_x86_capability, cpuinfo_x86, x86_capability);
- OFFSET(CPUINFO_x86_vendor_id, cpuinfo_x86, x86_vendor_id);
- BLANK();
-
OFFSET(PT_EBX, pt_regs, bx);
OFFSET(PT_ECX, pt_regs, cx);
OFFSET(PT_EDX, pt_regs, dx);
diff --git a/arch/x86/kernel/callthunks.c b/arch/x86/kernel/callthunks.c
index d86d7d6e750c..a951333c5995 100644
--- a/arch/x86/kernel/callthunks.c
+++ b/arch/x86/kernel/callthunks.c
@@ -185,7 +185,7 @@ static void *patch_dest(void *dest, bool direct)
u8 *pad = dest - tsize;
memcpy(insn_buff, skl_call_thunk_template, tsize);
- apply_relocation(insn_buff, pad, tsize, skl_call_thunk_template, tsize);
+ text_poke_apply_relocation(insn_buff, pad, tsize, skl_call_thunk_template, tsize);
/* Already patched? */
if (!bcmp(pad, insn_buff, tsize))
@@ -294,7 +294,7 @@ static bool is_callthunk(void *addr)
pad = (void *)(dest - tmpl_size);
memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
- apply_relocation(insn_buff, pad, tmpl_size, skl_call_thunk_template, tmpl_size);
+ text_poke_apply_relocation(insn_buff, pad, tmpl_size, skl_call_thunk_template, tmpl_size);
return !bcmp(pad, insn_buff, tmpl_size);
}
@@ -312,7 +312,7 @@ int x86_call_depth_emit_accounting(u8 **pprog, void *func, void *ip)
return 0;
memcpy(insn_buff, skl_call_thunk_template, tmpl_size);
- apply_relocation(insn_buff, ip, tmpl_size, skl_call_thunk_template, tmpl_size);
+ text_poke_apply_relocation(insn_buff, ip, tmpl_size, skl_call_thunk_template, tmpl_size);
memcpy(*pprog, insn_buff, tmpl_size);
*pprog += tmpl_size;
diff --git a/arch/x86/kernel/cet.c b/arch/x86/kernel/cet.c
index 303bf74d175b..99444409c026 100644
--- a/arch/x86/kernel/cet.c
+++ b/arch/x86/kernel/cet.c
@@ -2,6 +2,7 @@
#include <linux/ptrace.h>
#include <asm/bugs.h>
+#include <asm/msr.h>
#include <asm/traps.h>
enum cp_error_code {
@@ -55,7 +56,7 @@ static void do_user_cp_fault(struct pt_regs *regs, unsigned long error_code)
* will be whatever is live in userspace. So read the SSP before enabling
* interrupts so locking the fpregs to do it later is not required.
*/
- rdmsrl(MSR_IA32_PL3_SSP, ssp);
+ rdmsrq(MSR_IA32_PL3_SSP, ssp);
cond_local_irq_enable(regs);
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 4efdf5c2efc8..1e26179ff18c 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -24,7 +24,7 @@ obj-y += rdrand.o
obj-y += match.o
obj-y += bugs.o
obj-y += aperfmperf.o
-obj-y += cpuid-deps.o
+obj-y += cpuid-deps.o cpuid_0x2_table.o
obj-y += umwait.o
obj-y += capflags.o powerflags.o
@@ -38,6 +38,9 @@ obj-y += intel.o tsx.o
obj-$(CONFIG_PM) += intel_epb.o
endif
obj-$(CONFIG_CPU_SUP_AMD) += amd.o
+ifeq ($(CONFIG_AMD_NB)$(CONFIG_SYSFS),yy)
+obj-y += amd_cache_disable.o
+endif
obj-$(CONFIG_CPU_SUP_HYGON) += hygon.o
obj-$(CONFIG_CPU_SUP_CYRIX_32) += cyrix.o
obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 4e06baab40bb..a5ece6ebe8a7 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,6 +9,7 @@
#include <linux/sched/clock.h>
#include <linux/random.h>
#include <linux/topology.h>
+#include <linux/platform_data/x86/amd-fch.h>
#include <asm/processor.h>
#include <asm/apic.h>
#include <asm/cacheinfo.h>
@@ -21,6 +22,7 @@
#include <asm/delay.h>
#include <asm/debugreg.h>
#include <asm/resctrl.h>
+#include <asm/msr.h>
#include <asm/sev.h>
#ifdef CONFIG_X86_64
@@ -29,9 +31,9 @@
#include "cpu.h"
-u16 invlpgb_count_max __ro_after_init;
+u16 invlpgb_count_max __ro_after_init = 1;
-static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
+static inline int rdmsrq_amd_safe(unsigned msr, u64 *p)
{
u32 gprs[8] = { 0 };
int err;
@@ -49,7 +51,7 @@ static inline int rdmsrl_amd_safe(unsigned msr, unsigned long long *p)
return err;
}
-static inline int wrmsrl_amd_safe(unsigned msr, unsigned long long val)
+static inline int wrmsrq_amd_safe(unsigned msr, u64 val)
{
u32 gprs[8] = { 0 };
@@ -375,6 +377,47 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c)
#endif
}
+#define ZEN_MODEL_STEP_UCODE(fam, model, step, ucode) \
+ X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, fam, model), \
+ step, step, ucode)
+
+static const struct x86_cpu_id amd_tsa_microcode[] = {
+ ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x1, 0x0a0011d7),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x2, 0x0a00123b),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x08, 0x2, 0x0a00820d),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x1, 0x0a10114c),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x2, 0x0a10124c),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x18, 0x1, 0x0a108109),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x0, 0x0a20102e),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x2, 0x0a201211),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x44, 0x1, 0x0a404108),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x50, 0x0, 0x0a500012),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x61, 0x2, 0x0a60120a),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x74, 0x1, 0x0a704108),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x75, 0x2, 0x0a705208),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x78, 0x0, 0x0a708008),
+ ZEN_MODEL_STEP_UCODE(0x19, 0x7c, 0x0, 0x0a70c008),
+ ZEN_MODEL_STEP_UCODE(0x19, 0xa0, 0x2, 0x0aa00216),
+ {},
+};
+
+static void tsa_init(struct cpuinfo_x86 *c)
+{
+ if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+ return;
+
+ if (cpu_has(c, X86_FEATURE_ZEN3) ||
+ cpu_has(c, X86_FEATURE_ZEN4)) {
+ if (x86_match_min_microcode_rev(amd_tsa_microcode))
+ setup_force_cpu_cap(X86_FEATURE_VERW_CLEAR);
+ else
+ pr_debug("%s: current revision: 0x%x\n", __func__, c->microcode);
+ } else {
+ setup_force_cpu_cap(X86_FEATURE_TSA_SQ_NO);
+ setup_force_cpu_cap(X86_FEATURE_TSA_L1_NO);
+ }
+}
+
static void bsp_init_amd(struct cpuinfo_x86 *c)
{
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
@@ -383,7 +426,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
(c->x86 == 0x10 && c->x86_model >= 0x2)) {
u64 val;
- rdmsrl(MSR_K7_HWCR, val);
+ rdmsrq(MSR_K7_HWCR, val);
if (!(val & BIT(24)))
pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n");
}
@@ -422,7 +465,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
* Try to cache the base value so further operations can
* avoid RMW. If that faults, do not enable SSBD.
*/
- if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+ if (!rdmsrq_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
setup_force_cpu_cap(X86_FEATURE_SSBD);
x86_amd_ls_cfg_ssbd_mask = 1ULL << bit;
@@ -487,6 +530,11 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
}
bsp_determine_snp(c);
+ tsa_init(c);
+
+ if (cpu_has(c, X86_FEATURE_GP_ON_USER_CPUID))
+ setup_force_cpu_cap(X86_FEATURE_CPUID_FAULT);
+
return;
warn:
@@ -513,7 +561,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
*/
if (cpu_has(c, X86_FEATURE_SME) || cpu_has(c, X86_FEATURE_SEV)) {
/* Check if memory encryption is enabled */
- rdmsrl(MSR_AMD64_SYSCFG, msr);
+ rdmsrq(MSR_AMD64_SYSCFG, msr);
if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
goto clear_all;
@@ -530,7 +578,7 @@ static void early_detect_mem_encrypt(struct cpuinfo_x86 *c)
if (!sme_me_mask)
setup_clear_cpu_cap(X86_FEATURE_SME);
- rdmsrl(MSR_K7_HWCR, msr);
+ rdmsrq(MSR_K7_HWCR, msr);
if (!(msr & MSR_K7_HWCR_SMMLOCK))
goto clear_sev;
@@ -617,7 +665,7 @@ static void early_init_amd(struct cpuinfo_x86 *c)
if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) {
if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB))
setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
- else if (c->x86 >= 0x19 && !wrmsrl_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
+ else if (c->x86 >= 0x19 && !wrmsrq_safe(MSR_IA32_PRED_CMD, PRED_CMD_SBPB)) {
setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE);
setup_force_cpu_cap(X86_FEATURE_SBPB);
}
@@ -641,14 +689,14 @@ static void init_amd_k8(struct cpuinfo_x86 *c)
*/
if (c->x86_model < 0x14 && cpu_has(c, X86_FEATURE_LAHF_LM) && !cpu_has(c, X86_FEATURE_HYPERVISOR)) {
clear_cpu_cap(c, X86_FEATURE_LAHF_LM);
- if (!rdmsrl_amd_safe(0xc001100d, &value)) {
+ if (!rdmsrq_amd_safe(0xc001100d, &value)) {
value &= ~BIT_64(32);
- wrmsrl_amd_safe(0xc001100d, value);
+ wrmsrq_amd_safe(0xc001100d, value);
}
}
if (!c->x86_model_id[0])
- strcpy(c->x86_model_id, "Hammer");
+ strscpy(c->x86_model_id, "Hammer");
#ifdef CONFIG_SMP
/*
@@ -793,9 +841,9 @@ static void init_amd_bd(struct cpuinfo_x86 *c)
* Disable it on the affected CPUs.
*/
if ((c->x86_model >= 0x02) && (c->x86_model < 0x20)) {
- if (!rdmsrl_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) {
+ if (!rdmsrq_safe(MSR_F15H_IC_CFG, &value) && !(value & 0x1E)) {
value |= 0x1E;
- wrmsrl_safe(MSR_F15H_IC_CFG, value);
+ wrmsrq_safe(MSR_F15H_IC_CFG, value);
}
}
@@ -844,9 +892,9 @@ void init_spectral_chicken(struct cpuinfo_x86 *c)
* suppresses non-branch predictions.
*/
if (!cpu_has(c, X86_FEATURE_HYPERVISOR)) {
- if (!rdmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
+ if (!rdmsrq_safe(MSR_ZEN2_SPECTRAL_CHICKEN, &value)) {
value |= MSR_ZEN2_SPECTRAL_CHICKEN_BIT;
- wrmsrl_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
+ wrmsrq_safe(MSR_ZEN2_SPECTRAL_CHICKEN, value);
}
}
#endif
@@ -928,6 +976,16 @@ static void init_amd_zen2(struct cpuinfo_x86 *c)
init_spectral_chicken(c);
fix_erratum_1386(c);
zen2_zenbleed_check(c);
+
+ /* Disable RDSEED on AMD Cyan Skillfish because of an error. */
+ if (c->x86_model == 0x47 && c->x86_stepping == 0x0) {
+ clear_cpu_cap(c, X86_FEATURE_RDSEED);
+ msr_clear_bit(MSR_AMD64_CPUID_FN_7, 18);
+ pr_emerg("RDSEED is not reliable on this platform; disabling.\n");
+ }
+
+ /* Correct misconfigured CPUID on some clients. */
+ clear_cpu_cap(c, X86_FEATURE_INVLPGB);
}
static void init_amd_zen3(struct cpuinfo_x86 *c)
@@ -1030,7 +1088,7 @@ static void init_amd(struct cpuinfo_x86 *c)
init_amd_cacheinfo(c);
if (cpu_has(c, X86_FEATURE_SVM)) {
- rdmsrl(MSR_VM_CR, vm_cr);
+ rdmsrq(MSR_VM_CR, vm_cr);
if (vm_cr & SVM_VM_CR_SVM_DIS_MASK) {
pr_notice_once("SVM disabled (by BIOS) in MSR_VM_CR\n");
clear_cpu_cap(c, X86_FEATURE_SVM);
@@ -1211,7 +1269,7 @@ void amd_set_dr_addr_mask(unsigned long mask, unsigned int dr)
if (per_cpu(amd_dr_addr_mask, cpu)[dr] == mask)
return;
- wrmsr(amd_msr_dr_addr_masks[dr], mask, 0);
+ wrmsrq(amd_msr_dr_addr_masks[dr], mask);
per_cpu(amd_dr_addr_mask, cpu)[dr] = mask;
}
@@ -1242,3 +1300,56 @@ void amd_check_microcode(void)
if (cpu_feature_enabled(X86_FEATURE_ZEN2))
on_each_cpu(zenbleed_check_cpu, NULL, 1);
}
+
+static const char * const s5_reset_reason_txt[] = {
+ [0] = "thermal pin BP_THERMTRIP_L was tripped",
+ [1] = "power button was pressed for 4 seconds",
+ [2] = "shutdown pin was tripped",
+ [4] = "remote ASF power off command was received",
+ [9] = "internal CPU thermal limit was tripped",
+ [16] = "system reset pin BP_SYS_RST_L was tripped",
+ [17] = "software issued PCI reset",
+ [18] = "software wrote 0x4 to reset control register 0xCF9",
+ [19] = "software wrote 0x6 to reset control register 0xCF9",
+ [20] = "software wrote 0xE to reset control register 0xCF9",
+ [21] = "ACPI power state transition occurred",
+ [22] = "keyboard reset pin KB_RST_L was tripped",
+ [23] = "internal CPU shutdown event occurred",
+ [24] = "system failed to boot before failed boot timer expired",
+ [25] = "hardware watchdog timer expired",
+ [26] = "remote ASF reset command was received",
+ [27] = "an uncorrected error caused a data fabric sync flood event",
+ [29] = "FCH and MP1 failed warm reset handshake",
+ [30] = "a parity error occurred",
+ [31] = "a software sync flood event occurred",
+};
+
+static __init int print_s5_reset_status_mmio(void)
+{
+ unsigned long value;
+ void __iomem *addr;
+ int i;
+
+ if (!cpu_feature_enabled(X86_FEATURE_ZEN))
+ return 0;
+
+ addr = ioremap(FCH_PM_BASE + FCH_PM_S5_RESET_STATUS, sizeof(value));
+ if (!addr)
+ return 0;
+
+ value = ioread32(addr);
+ iounmap(addr);
+
+ for (i = 0; i < ARRAY_SIZE(s5_reset_reason_txt); i++) {
+ if (!(value & BIT(i)))
+ continue;
+
+ if (s5_reset_reason_txt[i]) {
+ pr_info("x86/amd: Previous system reset reason [0x%08lx]: %s\n",
+ value, s5_reset_reason_txt[i]);
+ }
+ }
+
+ return 0;
+}
+late_initcall(print_s5_reset_status_mmio);
diff --git a/arch/x86/kernel/cpu/amd_cache_disable.c b/arch/x86/kernel/cpu/amd_cache_disable.c
new file mode 100644
index 000000000000..8843b9557aea
--- /dev/null
+++ b/arch/x86/kernel/cpu/amd_cache_disable.c
@@ -0,0 +1,301 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * AMD L3 cache_disable_{0,1} sysfs handling
+ * Documentation/ABI/testing/sysfs-devices-system-cpu
+ */
+
+#include <linux/cacheinfo.h>
+#include <linux/capability.h>
+#include <linux/pci.h>
+#include <linux/sysfs.h>
+
+#include <asm/amd/nb.h>
+
+#include "cpu.h"
+
+/*
+ * L3 cache descriptors
+ */
+static void amd_calc_l3_indices(struct amd_northbridge *nb)
+{
+ struct amd_l3_cache *l3 = &nb->l3_cache;
+ unsigned int sc0, sc1, sc2, sc3;
+ u32 val = 0;
+
+ pci_read_config_dword(nb->misc, 0x1C4, &val);
+
+ /* calculate subcache sizes */
+ l3->subcaches[0] = sc0 = !(val & BIT(0));
+ l3->subcaches[1] = sc1 = !(val & BIT(4));
+
+ if (boot_cpu_data.x86 == 0x15) {
+ l3->subcaches[0] = sc0 += !(val & BIT(1));
+ l3->subcaches[1] = sc1 += !(val & BIT(5));
+ }
+
+ l3->subcaches[2] = sc2 = !(val & BIT(8)) + !(val & BIT(9));
+ l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
+
+ l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
+}
+
+/*
+ * check whether a slot used for disabling an L3 index is occupied.
+ * @l3: L3 cache descriptor
+ * @slot: slot number (0..1)
+ *
+ * @returns: the disabled index if used or negative value if slot free.
+ */
+static int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned int slot)
+{
+ unsigned int reg = 0;
+
+ pci_read_config_dword(nb->misc, 0x1BC + slot * 4, &reg);
+
+ /* check whether this slot is activated already */
+ if (reg & (3UL << 30))
+ return reg & 0xfff;
+
+ return -1;
+}
+
+static ssize_t show_cache_disable(struct cacheinfo *ci, char *buf, unsigned int slot)
+{
+ int index;
+ struct amd_northbridge *nb = ci->priv;
+
+ index = amd_get_l3_disable_slot(nb, slot);
+ if (index >= 0)
+ return sysfs_emit(buf, "%d\n", index);
+
+ return sysfs_emit(buf, "FREE\n");
+}
+
+#define SHOW_CACHE_DISABLE(slot) \
+static ssize_t \
+cache_disable_##slot##_show(struct device *dev, \
+ struct device_attribute *attr, char *buf) \
+{ \
+ struct cacheinfo *ci = dev_get_drvdata(dev); \
+ return show_cache_disable(ci, buf, slot); \
+}
+
+SHOW_CACHE_DISABLE(0)
+SHOW_CACHE_DISABLE(1)
+
+static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu,
+ unsigned int slot, unsigned long idx)
+{
+ int i;
+
+ idx |= BIT(30);
+
+ /*
+ * disable index in all 4 subcaches
+ */
+ for (i = 0; i < 4; i++) {
+ u32 reg = idx | (i << 20);
+
+ if (!nb->l3_cache.subcaches[i])
+ continue;
+
+ pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
+
+ /*
+ * We need to WBINVD on a core on the node containing the L3
+ * cache which indices we disable therefore a simple wbinvd()
+ * is not sufficient.
+ */
+ wbinvd_on_cpu(cpu);
+
+ reg |= BIT(31);
+ pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
+ }
+}
+
+/*
+ * disable a L3 cache index by using a disable-slot
+ *
+ * @l3: L3 cache descriptor
+ * @cpu: A CPU on the node containing the L3 cache
+ * @slot: slot number (0..1)
+ * @index: index to disable
+ *
+ * @return: 0 on success, error status on failure
+ */
+static int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu,
+ unsigned int slot, unsigned long index)
+{
+ int ret = 0;
+
+ /* check if @slot is already used or the index is already disabled */
+ ret = amd_get_l3_disable_slot(nb, slot);
+ if (ret >= 0)
+ return -EEXIST;
+
+ if (index > nb->l3_cache.indices)
+ return -EINVAL;
+
+ /* check whether the other slot has disabled the same index already */
+ if (index == amd_get_l3_disable_slot(nb, !slot))
+ return -EEXIST;
+
+ amd_l3_disable_index(nb, cpu, slot, index);
+
+ return 0;
+}
+
+static ssize_t store_cache_disable(struct cacheinfo *ci, const char *buf,
+ size_t count, unsigned int slot)
+{
+ struct amd_northbridge *nb = ci->priv;
+ unsigned long val = 0;
+ int cpu, err = 0;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ cpu = cpumask_first(&ci->shared_cpu_map);
+
+ if (kstrtoul(buf, 10, &val) < 0)
+ return -EINVAL;
+
+ err = amd_set_l3_disable_slot(nb, cpu, slot, val);
+ if (err) {
+ if (err == -EEXIST)
+ pr_warn("L3 slot %d in use/index already disabled!\n",
+ slot);
+ return err;
+ }
+ return count;
+}
+
+#define STORE_CACHE_DISABLE(slot) \
+static ssize_t \
+cache_disable_##slot##_store(struct device *dev, \
+ struct device_attribute *attr, \
+ const char *buf, size_t count) \
+{ \
+ struct cacheinfo *ci = dev_get_drvdata(dev); \
+ return store_cache_disable(ci, buf, count, slot); \
+}
+
+STORE_CACHE_DISABLE(0)
+STORE_CACHE_DISABLE(1)
+
+static ssize_t subcaches_show(struct device *dev, struct device_attribute *attr,
+ char *buf)
+{
+ struct cacheinfo *ci = dev_get_drvdata(dev);
+ int cpu = cpumask_first(&ci->shared_cpu_map);
+
+ return sysfs_emit(buf, "%x\n", amd_get_subcaches(cpu));
+}
+
+static ssize_t subcaches_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct cacheinfo *ci = dev_get_drvdata(dev);
+ int cpu = cpumask_first(&ci->shared_cpu_map);
+ unsigned long val;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (kstrtoul(buf, 16, &val) < 0)
+ return -EINVAL;
+
+ if (amd_set_subcaches(cpu, val))
+ return -EINVAL;
+
+ return count;
+}
+
+static DEVICE_ATTR_RW(cache_disable_0);
+static DEVICE_ATTR_RW(cache_disable_1);
+static DEVICE_ATTR_RW(subcaches);
+
+static umode_t cache_private_attrs_is_visible(struct kobject *kobj,
+ struct attribute *attr, int unused)
+{
+ struct device *dev = kobj_to_dev(kobj);
+ struct cacheinfo *ci = dev_get_drvdata(dev);
+ umode_t mode = attr->mode;
+
+ if (!ci->priv)
+ return 0;
+
+ if ((attr == &dev_attr_subcaches.attr) &&
+ amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ return mode;
+
+ if ((attr == &dev_attr_cache_disable_0.attr ||
+ attr == &dev_attr_cache_disable_1.attr) &&
+ amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+ return mode;
+
+ return 0;
+}
+
+static struct attribute_group cache_private_group = {
+ .is_visible = cache_private_attrs_is_visible,
+};
+
+static void init_amd_l3_attrs(void)
+{
+ static struct attribute **amd_l3_attrs;
+ int n = 1;
+
+ if (amd_l3_attrs) /* already initialized */
+ return;
+
+ if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
+ n += 2;
+ if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ n += 1;
+
+ amd_l3_attrs = kcalloc(n, sizeof(*amd_l3_attrs), GFP_KERNEL);
+ if (!amd_l3_attrs)
+ return;
+
+ n = 0;
+ if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) {
+ amd_l3_attrs[n++] = &dev_attr_cache_disable_0.attr;
+ amd_l3_attrs[n++] = &dev_attr_cache_disable_1.attr;
+ }
+ if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
+ amd_l3_attrs[n++] = &dev_attr_subcaches.attr;
+
+ cache_private_group.attrs = amd_l3_attrs;
+}
+
+const struct attribute_group *cache_get_priv_group(struct cacheinfo *ci)
+{
+ struct amd_northbridge *nb = ci->priv;
+
+ if (ci->level < 3 || !nb)
+ return NULL;
+
+ if (nb && nb->l3_cache.indices)
+ init_amd_l3_attrs();
+
+ return &cache_private_group;
+}
+
+struct amd_northbridge *amd_init_l3_cache(int index)
+{
+ struct amd_northbridge *nb;
+ int node;
+
+ /* only for L3, and not in virtualized environments */
+ if (index < 3)
+ return NULL;
+
+ node = topology_amd_node_id(smp_processor_id());
+ nb = node_to_amd_nb(node);
+ if (nb && !nb->l3_cache.indices)
+ amd_calc_l3_indices(nb);
+
+ return nb;
+}
diff --git a/arch/x86/kernel/cpu/aperfmperf.c b/arch/x86/kernel/cpu/aperfmperf.c
index 6cf31a1649c4..a315b0627dfb 100644
--- a/arch/x86/kernel/cpu/aperfmperf.c
+++ b/arch/x86/kernel/cpu/aperfmperf.c
@@ -20,6 +20,7 @@
#include <asm/cpu.h>
#include <asm/cpu_device_id.h>
#include <asm/intel-family.h>
+#include <asm/msr.h>
#include "cpu.h"
@@ -40,8 +41,8 @@ static void init_counter_refs(void)
{
u64 aperf, mperf;
- rdmsrl(MSR_IA32_APERF, aperf);
- rdmsrl(MSR_IA32_MPERF, mperf);
+ rdmsrq(MSR_IA32_APERF, aperf);
+ rdmsrq(MSR_IA32_MPERF, mperf);
this_cpu_write(cpu_samples.aperf, aperf);
this_cpu_write(cpu_samples.mperf, mperf);
@@ -99,7 +100,7 @@ static bool __init turbo_disabled(void)
u64 misc_en;
int err;
- err = rdmsrl_safe(MSR_IA32_MISC_ENABLE, &misc_en);
+ err = rdmsrq_safe(MSR_IA32_MISC_ENABLE, &misc_en);
if (err)
return false;
@@ -110,11 +111,11 @@ static bool __init slv_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
{
int err;
- err = rdmsrl_safe(MSR_ATOM_CORE_RATIOS, base_freq);
+ err = rdmsrq_safe(MSR_ATOM_CORE_RATIOS, base_freq);
if (err)
return false;
- err = rdmsrl_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq);
+ err = rdmsrq_safe(MSR_ATOM_CORE_TURBO_RATIOS, turbo_freq);
if (err)
return false;
@@ -152,13 +153,13 @@ static bool __init knl_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq,
int err, i;
u64 msr;
- err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+ err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq);
if (err)
return false;
*base_freq = (*base_freq >> 8) & 0xFF; /* max P state */
- err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
+ err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &msr);
if (err)
return false;
@@ -190,17 +191,17 @@ static bool __init skx_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq, int s
u32 group_size;
int err, i;
- err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+ err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq);
if (err)
return false;
*base_freq = (*base_freq >> 8) & 0xFF; /* max P state */
- err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &ratios);
+ err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &ratios);
if (err)
return false;
- err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT1, &counts);
+ err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT1, &counts);
if (err)
return false;
@@ -220,11 +221,11 @@ static bool __init core_set_max_freq_ratio(u64 *base_freq, u64 *turbo_freq)
u64 msr;
int err;
- err = rdmsrl_safe(MSR_PLATFORM_INFO, base_freq);
+ err = rdmsrq_safe(MSR_PLATFORM_INFO, base_freq);
if (err)
return false;
- err = rdmsrl_safe(MSR_TURBO_RATIO_LIMIT, &msr);
+ err = rdmsrq_safe(MSR_TURBO_RATIO_LIMIT, &msr);
if (err)
return false;
@@ -474,8 +475,8 @@ void arch_scale_freq_tick(void)
if (!cpu_feature_enabled(X86_FEATURE_APERFMPERF))
return;
- rdmsrl(MSR_IA32_APERF, aperf);
- rdmsrl(MSR_IA32_MPERF, mperf);
+ rdmsrq(MSR_IA32_APERF, aperf);
+ rdmsrq(MSR_IA32_MPERF, mperf);
acnt = aperf - s->aperf;
mcnt = mperf - s->mperf;
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 8596ce85026c..b74bf937cd9f 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -34,22 +34,68 @@
#include "cpu.h"
+/*
+ * Speculation Vulnerability Handling
+ *
+ * Each vulnerability is handled with the following functions:
+ * <vuln>_select_mitigation() -- Selects a mitigation to use. This should
+ * take into account all relevant command line
+ * options.
+ * <vuln>_update_mitigation() -- This is called after all vulnerabilities have
+ * selected a mitigation, in case the selection
+ * may want to change based on other choices
+ * made. This function is optional.
+ * <vuln>_apply_mitigation() -- Enable the selected mitigation.
+ *
+ * The compile-time mitigation in all cases should be AUTO. An explicit
+ * command-line option can override AUTO. If no such option is
+ * provided, <vuln>_select_mitigation() will override AUTO to the best
+ * mitigation option.
+ */
+
static void __init spectre_v1_select_mitigation(void);
+static void __init spectre_v1_apply_mitigation(void);
static void __init spectre_v2_select_mitigation(void);
+static void __init spectre_v2_update_mitigation(void);
+static void __init spectre_v2_apply_mitigation(void);
static void __init retbleed_select_mitigation(void);
+static void __init retbleed_update_mitigation(void);
+static void __init retbleed_apply_mitigation(void);
static void __init spectre_v2_user_select_mitigation(void);
+static void __init spectre_v2_user_update_mitigation(void);
+static void __init spectre_v2_user_apply_mitigation(void);
static void __init ssb_select_mitigation(void);
+static void __init ssb_apply_mitigation(void);
static void __init l1tf_select_mitigation(void);
+static void __init l1tf_apply_mitigation(void);
static void __init mds_select_mitigation(void);
-static void __init md_clear_update_mitigation(void);
-static void __init md_clear_select_mitigation(void);
+static void __init mds_update_mitigation(void);
+static void __init mds_apply_mitigation(void);
static void __init taa_select_mitigation(void);
+static void __init taa_update_mitigation(void);
+static void __init taa_apply_mitigation(void);
static void __init mmio_select_mitigation(void);
+static void __init mmio_update_mitigation(void);
+static void __init mmio_apply_mitigation(void);
+static void __init rfds_select_mitigation(void);
+static void __init rfds_update_mitigation(void);
+static void __init rfds_apply_mitigation(void);
static void __init srbds_select_mitigation(void);
+static void __init srbds_apply_mitigation(void);
static void __init l1d_flush_select_mitigation(void);
static void __init srso_select_mitigation(void);
+static void __init srso_update_mitigation(void);
+static void __init srso_apply_mitigation(void);
static void __init gds_select_mitigation(void);
+static void __init gds_apply_mitigation(void);
+static void __init bhi_select_mitigation(void);
+static void __init bhi_update_mitigation(void);
+static void __init bhi_apply_mitigation(void);
static void __init its_select_mitigation(void);
+static void __init its_update_mitigation(void);
+static void __init its_apply_mitigation(void);
+static void __init tsa_select_mitigation(void);
+static void __init tsa_apply_mitigation(void);
/* The base value of the SPEC_CTRL MSR without task-specific bits set */
u64 x86_spec_ctrl_base;
@@ -69,17 +115,16 @@ void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk;
static void __init set_return_thunk(void *thunk)
{
- if (x86_return_thunk != __x86_return_thunk)
- pr_warn("x86/bugs: return thunk changed\n");
-
x86_return_thunk = thunk;
+
+ pr_info("active return thunk: %ps\n", thunk);
}
/* Update SPEC_CTRL MSR and its cached copy unconditionally */
static void update_spec_ctrl(u64 val)
{
this_cpu_write(x86_spec_ctrl_current, val);
- wrmsrl(MSR_IA32_SPEC_CTRL, val);
+ wrmsrq(MSR_IA32_SPEC_CTRL, val);
}
/*
@@ -98,7 +143,7 @@ void update_spec_ctrl_cond(u64 val)
* forced the update can be delayed until that time.
*/
if (!cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS))
- wrmsrl(MSR_IA32_SPEC_CTRL, val);
+ wrmsrq(MSR_IA32_SPEC_CTRL, val);
}
noinstr u64 spec_ctrl_current(void)
@@ -125,9 +170,9 @@ DEFINE_STATIC_KEY_FALSE(switch_mm_always_ibpb);
DEFINE_STATIC_KEY_FALSE(switch_vcpu_ibpb);
EXPORT_SYMBOL_GPL(switch_vcpu_ibpb);
-/* Control MDS CPU buffer clear before idling (halt, mwait) */
-DEFINE_STATIC_KEY_FALSE(mds_idle_clear);
-EXPORT_SYMBOL_GPL(mds_idle_clear);
+/* Control CPU buffer clear before idling (halt, mwait) */
+DEFINE_STATIC_KEY_FALSE(cpu_buf_idle_clear);
+EXPORT_SYMBOL_GPL(cpu_buf_idle_clear);
/*
* Controls whether l1d flush based mitigations are enabled,
@@ -136,9 +181,46 @@ EXPORT_SYMBOL_GPL(mds_idle_clear);
*/
DEFINE_STATIC_KEY_FALSE(switch_mm_cond_l1d_flush);
-/* Controls CPU Fill buffer clear before KVM guest MMIO accesses */
-DEFINE_STATIC_KEY_FALSE(mmio_stale_data_clear);
-EXPORT_SYMBOL_GPL(mmio_stale_data_clear);
+/*
+ * Controls CPU Fill buffer clear before VMenter. This is a subset of
+ * X86_FEATURE_CLEAR_CPU_BUF, and should only be enabled when KVM-only
+ * mitigation is required.
+ */
+DEFINE_STATIC_KEY_FALSE(cpu_buf_vm_clear);
+EXPORT_SYMBOL_GPL(cpu_buf_vm_clear);
+
+#undef pr_fmt
+#define pr_fmt(fmt) "mitigations: " fmt
+
+static void __init cpu_print_attack_vectors(void)
+{
+ pr_info("Enabled attack vectors: ");
+
+ if (cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL))
+ pr_cont("user_kernel, ");
+
+ if (cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER))
+ pr_cont("user_user, ");
+
+ if (cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_HOST))
+ pr_cont("guest_host, ");
+
+ if (cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_GUEST))
+ pr_cont("guest_guest, ");
+
+ pr_cont("SMT mitigations: ");
+
+ switch (smt_mitigations) {
+ case SMT_MITIGATIONS_OFF:
+ pr_cont("off\n");
+ break;
+ case SMT_MITIGATIONS_AUTO:
+ pr_cont("auto\n");
+ break;
+ case SMT_MITIGATIONS_ON:
+ pr_cont("on\n");
+ }
+}
void __init cpu_select_mitigations(void)
{
@@ -148,7 +230,7 @@ void __init cpu_select_mitigations(void)
* init code as it is not enumerated and depends on the family.
*/
if (cpu_feature_enabled(X86_FEATURE_MSR_SPEC_CTRL)) {
- rdmsrl(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
+ rdmsrq(MSR_IA32_SPEC_CTRL, x86_spec_ctrl_base);
/*
* Previously running kernel (kexec), may have some controls
@@ -160,34 +242,74 @@ void __init cpu_select_mitigations(void)
x86_arch_cap_msr = x86_read_arch_cap_msr();
+ cpu_print_attack_vectors();
+
/* Select the proper CPU mitigations before patching alternatives: */
spectre_v1_select_mitigation();
spectre_v2_select_mitigation();
- /*
- * retbleed_select_mitigation() relies on the state set by
- * spectre_v2_select_mitigation(); specifically it wants to know about
- * spectre_v2=ibrs.
- */
retbleed_select_mitigation();
- /*
- * spectre_v2_user_select_mitigation() relies on the state set by
- * retbleed_select_mitigation(); specifically the STIBP selection is
- * forced for UNRET or IBPB.
- */
spectre_v2_user_select_mitigation();
ssb_select_mitigation();
l1tf_select_mitigation();
- md_clear_select_mitigation();
+ mds_select_mitigation();
+ taa_select_mitigation();
+ mmio_select_mitigation();
+ rfds_select_mitigation();
srbds_select_mitigation();
l1d_flush_select_mitigation();
-
- /*
- * srso_select_mitigation() depends and must run after
- * retbleed_select_mitigation().
- */
srso_select_mitigation();
gds_select_mitigation();
its_select_mitigation();
+ bhi_select_mitigation();
+ tsa_select_mitigation();
+
+ /*
+ * After mitigations are selected, some may need to update their
+ * choices.
+ */
+ spectre_v2_update_mitigation();
+ /*
+ * retbleed_update_mitigation() relies on the state set by
+ * spectre_v2_update_mitigation(); specifically it wants to know about
+ * spectre_v2=ibrs.
+ */
+ retbleed_update_mitigation();
+ /*
+ * its_update_mitigation() depends on spectre_v2_update_mitigation()
+ * and retbleed_update_mitigation().
+ */
+ its_update_mitigation();
+
+ /*
+ * spectre_v2_user_update_mitigation() depends on
+ * retbleed_update_mitigation(), specifically the STIBP
+ * selection is forced for UNRET or IBPB.
+ */
+ spectre_v2_user_update_mitigation();
+ mds_update_mitigation();
+ taa_update_mitigation();
+ mmio_update_mitigation();
+ rfds_update_mitigation();
+ bhi_update_mitigation();
+ /* srso_update_mitigation() depends on retbleed_update_mitigation(). */
+ srso_update_mitigation();
+
+ spectre_v1_apply_mitigation();
+ spectre_v2_apply_mitigation();
+ retbleed_apply_mitigation();
+ spectre_v2_user_apply_mitigation();
+ ssb_apply_mitigation();
+ l1tf_apply_mitigation();
+ mds_apply_mitigation();
+ taa_apply_mitigation();
+ mmio_apply_mitigation();
+ rfds_apply_mitigation();
+ srbds_apply_mitigation();
+ srso_apply_mitigation();
+ gds_apply_mitigation();
+ its_apply_mitigation();
+ bhi_apply_mitigation();
+ tsa_apply_mitigation();
}
/*
@@ -237,14 +359,70 @@ static void x86_amd_ssb_disable(void)
u64 msrval = x86_amd_ls_cfg_base | x86_amd_ls_cfg_ssbd_mask;
if (boot_cpu_has(X86_FEATURE_VIRT_SSBD))
- wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
+ wrmsrq(MSR_AMD64_VIRT_SPEC_CTRL, SPEC_CTRL_SSBD);
else if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD))
- wrmsrl(MSR_AMD64_LS_CFG, msrval);
+ wrmsrq(MSR_AMD64_LS_CFG, msrval);
}
#undef pr_fmt
#define pr_fmt(fmt) "MDS: " fmt
+/*
+ * Returns true if vulnerability should be mitigated based on the
+ * selected attack vector controls.
+ *
+ * See Documentation/admin-guide/hw-vuln/attack_vector_controls.rst
+ */
+static bool __init should_mitigate_vuln(unsigned int bug)
+{
+ switch (bug) {
+ /*
+ * The only runtime-selected spectre_v1 mitigations in the kernel are
+ * related to SWAPGS protection on kernel entry. Therefore, protection
+ * is only required for the user->kernel attack vector.
+ */
+ case X86_BUG_SPECTRE_V1:
+ return cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL);
+
+ case X86_BUG_SPECTRE_V2:
+ case X86_BUG_RETBLEED:
+ case X86_BUG_SRSO:
+ case X86_BUG_L1TF:
+ case X86_BUG_ITS:
+ return cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL) ||
+ cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_HOST);
+
+ case X86_BUG_SPECTRE_V2_USER:
+ return cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER) ||
+ cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_GUEST);
+
+ /*
+ * All the vulnerabilities below allow potentially leaking data
+ * across address spaces. Therefore, mitigation is required for
+ * any of these 4 attack vectors.
+ */
+ case X86_BUG_MDS:
+ case X86_BUG_TAA:
+ case X86_BUG_MMIO_STALE_DATA:
+ case X86_BUG_RFDS:
+ case X86_BUG_SRBDS:
+ return cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL) ||
+ cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_HOST) ||
+ cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER) ||
+ cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_GUEST);
+
+ case X86_BUG_GDS:
+ return cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL) ||
+ cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_HOST) ||
+ cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER) ||
+ cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_GUEST) ||
+ (smt_mitigations != SMT_MITIGATIONS_OFF);
+ default:
+ WARN(1, "Unknown bug %x\n", bug);
+ return false;
+ }
+}
+
/* Default mitigation for MDS-affected CPUs */
static enum mds_mitigations mds_mitigation __ro_after_init =
IS_ENABLED(CONFIG_MITIGATION_MDS) ? MDS_MITIGATION_AUTO : MDS_MITIGATION_OFF;
@@ -290,24 +468,56 @@ enum rfds_mitigations {
static enum rfds_mitigations rfds_mitigation __ro_after_init =
IS_ENABLED(CONFIG_MITIGATION_RFDS) ? RFDS_MITIGATION_AUTO : RFDS_MITIGATION_OFF;
+/*
+ * Set if any of MDS/TAA/MMIO/RFDS are going to enable VERW clearing
+ * through X86_FEATURE_CLEAR_CPU_BUF on kernel and guest entry.
+ */
+static bool verw_clear_cpu_buf_mitigation_selected __ro_after_init;
+
static void __init mds_select_mitigation(void)
{
- if (!boot_cpu_has_bug(X86_BUG_MDS) || cpu_mitigations_off()) {
+ if (!boot_cpu_has_bug(X86_BUG_MDS)) {
mds_mitigation = MDS_MITIGATION_OFF;
return;
}
- if (mds_mitigation == MDS_MITIGATION_AUTO)
+ if (mds_mitigation == MDS_MITIGATION_AUTO) {
+ if (should_mitigate_vuln(X86_BUG_MDS))
+ mds_mitigation = MDS_MITIGATION_FULL;
+ else
+ mds_mitigation = MDS_MITIGATION_OFF;
+ }
+
+ if (mds_mitigation == MDS_MITIGATION_OFF)
+ return;
+
+ verw_clear_cpu_buf_mitigation_selected = true;
+}
+
+static void __init mds_update_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_MDS))
+ return;
+
+ /* If TAA, MMIO, or RFDS are being mitigated, MDS gets mitigated too. */
+ if (verw_clear_cpu_buf_mitigation_selected)
mds_mitigation = MDS_MITIGATION_FULL;
if (mds_mitigation == MDS_MITIGATION_FULL) {
if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
mds_mitigation = MDS_MITIGATION_VMWERV;
+ }
- setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+ pr_info("%s\n", mds_strings[mds_mitigation]);
+}
+static void __init mds_apply_mitigation(void)
+{
+ if (mds_mitigation == MDS_MITIGATION_FULL ||
+ mds_mitigation == MDS_MITIGATION_VMWERV) {
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
if (!boot_cpu_has(X86_BUG_MSBDS_ONLY) &&
- (mds_nosmt || cpu_mitigations_auto_nosmt()))
+ (mds_nosmt || smt_mitigations == SMT_MITIGATIONS_ON))
cpu_smt_disable(false);
}
}
@@ -345,6 +555,11 @@ static const char * const taa_strings[] = {
[TAA_MITIGATION_TSX_DISABLED] = "Mitigation: TSX disabled",
};
+static bool __init taa_vulnerable(void)
+{
+ return boot_cpu_has_bug(X86_BUG_TAA) && boot_cpu_has(X86_FEATURE_RTM);
+}
+
static void __init taa_select_mitigation(void)
{
if (!boot_cpu_has_bug(X86_BUG_TAA)) {
@@ -358,48 +573,64 @@ static void __init taa_select_mitigation(void)
return;
}
- if (cpu_mitigations_off()) {
- taa_mitigation = TAA_MITIGATION_OFF;
- return;
+ /* Microcode will be checked in taa_update_mitigation(). */
+ if (taa_mitigation == TAA_MITIGATION_AUTO) {
+ if (should_mitigate_vuln(X86_BUG_TAA))
+ taa_mitigation = TAA_MITIGATION_VERW;
+ else
+ taa_mitigation = TAA_MITIGATION_OFF;
}
- /*
- * TAA mitigation via VERW is turned off if both
- * tsx_async_abort=off and mds=off are specified.
- */
- if (taa_mitigation == TAA_MITIGATION_OFF &&
- mds_mitigation == MDS_MITIGATION_OFF)
+ if (taa_mitigation != TAA_MITIGATION_OFF)
+ verw_clear_cpu_buf_mitigation_selected = true;
+}
+
+static void __init taa_update_mitigation(void)
+{
+ if (!taa_vulnerable())
return;
- if (boot_cpu_has(X86_FEATURE_MD_CLEAR))
+ if (verw_clear_cpu_buf_mitigation_selected)
taa_mitigation = TAA_MITIGATION_VERW;
- else
- taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
- /*
- * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1.
- * A microcode update fixes this behavior to clear CPU buffers. It also
- * adds support for MSR_IA32_TSX_CTRL which is enumerated by the
- * ARCH_CAP_TSX_CTRL_MSR bit.
- *
- * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode
- * update is required.
- */
- if ( (x86_arch_cap_msr & ARCH_CAP_MDS_NO) &&
- !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))
- taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
+ if (taa_mitigation == TAA_MITIGATION_VERW) {
+ /* Check if the requisite ucode is available. */
+ if (!boot_cpu_has(X86_FEATURE_MD_CLEAR))
+ taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
- /*
- * TSX is enabled, select alternate mitigation for TAA which is
- * the same as MDS. Enable MDS static branch to clear CPU buffers.
- *
- * For guests that can't determine whether the correct microcode is
- * present on host, enable the mitigation for UCODE_NEEDED as well.
- */
- setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+ /*
+ * VERW doesn't clear the CPU buffers when MD_CLEAR=1 and MDS_NO=1.
+ * A microcode update fixes this behavior to clear CPU buffers. It also
+ * adds support for MSR_IA32_TSX_CTRL which is enumerated by the
+ * ARCH_CAP_TSX_CTRL_MSR bit.
+ *
+ * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode
+ * update is required.
+ */
+ if ((x86_arch_cap_msr & ARCH_CAP_MDS_NO) &&
+ !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))
+ taa_mitigation = TAA_MITIGATION_UCODE_NEEDED;
+ }
- if (taa_nosmt || cpu_mitigations_auto_nosmt())
- cpu_smt_disable(false);
+ pr_info("%s\n", taa_strings[taa_mitigation]);
+}
+
+static void __init taa_apply_mitigation(void)
+{
+ if (taa_mitigation == TAA_MITIGATION_VERW ||
+ taa_mitigation == TAA_MITIGATION_UCODE_NEEDED) {
+ /*
+ * TSX is enabled, select alternate mitigation for TAA which is
+ * the same as MDS. Enable MDS static branch to clear CPU buffers.
+ *
+ * For guests that can't determine whether the correct microcode is
+ * present on host, enable the mitigation for UCODE_NEEDED as well.
+ */
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+
+ if (taa_nosmt || smt_mitigations == SMT_MITIGATIONS_ON)
+ cpu_smt_disable(false);
+ }
}
static int __init tsx_async_abort_parse_cmdline(char *str)
@@ -437,31 +668,71 @@ static const char * const mmio_strings[] = {
static void __init mmio_select_mitigation(void)
{
if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) ||
- boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) ||
cpu_mitigations_off()) {
mmio_mitigation = MMIO_MITIGATION_OFF;
return;
}
+ /* Microcode will be checked in mmio_update_mitigation(). */
+ if (mmio_mitigation == MMIO_MITIGATION_AUTO) {
+ if (should_mitigate_vuln(X86_BUG_MMIO_STALE_DATA))
+ mmio_mitigation = MMIO_MITIGATION_VERW;
+ else
+ mmio_mitigation = MMIO_MITIGATION_OFF;
+ }
+
if (mmio_mitigation == MMIO_MITIGATION_OFF)
return;
/*
* Enable CPU buffer clear mitigation for host and VMM, if also affected
- * by MDS or TAA. Otherwise, enable mitigation for VMM only.
+ * by MDS or TAA.
*/
- if (boot_cpu_has_bug(X86_BUG_MDS) || (boot_cpu_has_bug(X86_BUG_TAA) &&
- boot_cpu_has(X86_FEATURE_RTM)))
- setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+ if (boot_cpu_has_bug(X86_BUG_MDS) || taa_vulnerable())
+ verw_clear_cpu_buf_mitigation_selected = true;
+}
+
+static void __init mmio_update_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
+ return;
+
+ if (verw_clear_cpu_buf_mitigation_selected)
+ mmio_mitigation = MMIO_MITIGATION_VERW;
+
+ if (mmio_mitigation == MMIO_MITIGATION_VERW) {
+ /*
+ * Check if the system has the right microcode.
+ *
+ * CPU Fill buffer clear mitigation is enumerated by either an explicit
+ * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS
+ * affected systems.
+ */
+ if (!((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) ||
+ (boot_cpu_has(X86_FEATURE_MD_CLEAR) &&
+ boot_cpu_has(X86_FEATURE_FLUSH_L1D) &&
+ !(x86_arch_cap_msr & ARCH_CAP_MDS_NO))))
+ mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED;
+ }
+
+ pr_info("%s\n", mmio_strings[mmio_mitigation]);
+}
+
+static void __init mmio_apply_mitigation(void)
+{
+ if (mmio_mitigation == MMIO_MITIGATION_OFF)
+ return;
/*
- * X86_FEATURE_CLEAR_CPU_BUF could be enabled by other VERW based
- * mitigations, disable KVM-only mitigation in that case.
+ * Only enable the VMM mitigation if the CPU buffer clear mitigation is
+ * not being used.
*/
- if (boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF))
- static_branch_disable(&mmio_stale_data_clear);
- else
- static_branch_enable(&mmio_stale_data_clear);
+ if (verw_clear_cpu_buf_mitigation_selected) {
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+ static_branch_disable(&cpu_buf_vm_clear);
+ } else {
+ static_branch_enable(&cpu_buf_vm_clear);
+ }
/*
* If Processor-MMIO-Stale-Data bug is present and Fill Buffer data can
@@ -469,24 +740,9 @@ static void __init mmio_select_mitigation(void)
* is required irrespective of SMT state.
*/
if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO))
- static_branch_enable(&mds_idle_clear);
+ static_branch_enable(&cpu_buf_idle_clear);
- /*
- * Check if the system has the right microcode.
- *
- * CPU Fill buffer clear mitigation is enumerated by either an explicit
- * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS
- * affected systems.
- */
- if ((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) ||
- (boot_cpu_has(X86_FEATURE_MD_CLEAR) &&
- boot_cpu_has(X86_FEATURE_FLUSH_L1D) &&
- !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)))
- mmio_mitigation = MMIO_MITIGATION_VERW;
- else
- mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED;
-
- if (mmio_nosmt || cpu_mitigations_auto_nosmt())
+ if (mmio_nosmt || smt_mitigations == SMT_MITIGATIONS_ON)
cpu_smt_disable(false);
}
@@ -520,22 +776,52 @@ static const char * const rfds_strings[] = {
[RFDS_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode",
};
+static inline bool __init verw_clears_cpu_reg_file(void)
+{
+ return (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR);
+}
+
static void __init rfds_select_mitigation(void)
{
- if (!boot_cpu_has_bug(X86_BUG_RFDS) || cpu_mitigations_off()) {
+ if (!boot_cpu_has_bug(X86_BUG_RFDS)) {
rfds_mitigation = RFDS_MITIGATION_OFF;
return;
}
+
+ if (rfds_mitigation == RFDS_MITIGATION_AUTO) {
+ if (should_mitigate_vuln(X86_BUG_RFDS))
+ rfds_mitigation = RFDS_MITIGATION_VERW;
+ else
+ rfds_mitigation = RFDS_MITIGATION_OFF;
+ }
+
if (rfds_mitigation == RFDS_MITIGATION_OFF)
return;
- if (rfds_mitigation == RFDS_MITIGATION_AUTO)
+ if (verw_clears_cpu_reg_file())
+ verw_clear_cpu_buf_mitigation_selected = true;
+}
+
+static void __init rfds_update_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_RFDS))
+ return;
+
+ if (verw_clear_cpu_buf_mitigation_selected)
rfds_mitigation = RFDS_MITIGATION_VERW;
- if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR)
+ if (rfds_mitigation == RFDS_MITIGATION_VERW) {
+ if (!verw_clears_cpu_reg_file())
+ rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED;
+ }
+
+ pr_info("%s\n", rfds_strings[rfds_mitigation]);
+}
+
+static void __init rfds_apply_mitigation(void)
+{
+ if (rfds_mitigation == RFDS_MITIGATION_VERW)
setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
- else
- rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED;
}
static __init int rfds_parse_cmdline(char *str)
@@ -556,76 +842,11 @@ static __init int rfds_parse_cmdline(char *str)
early_param("reg_file_data_sampling", rfds_parse_cmdline);
#undef pr_fmt
-#define pr_fmt(fmt) "" fmt
-
-static void __init md_clear_update_mitigation(void)
-{
- if (cpu_mitigations_off())
- return;
-
- if (!boot_cpu_has(X86_FEATURE_CLEAR_CPU_BUF))
- goto out;
-
- /*
- * X86_FEATURE_CLEAR_CPU_BUF is now enabled. Update MDS, TAA and MMIO
- * Stale Data mitigation, if necessary.
- */
- if (mds_mitigation == MDS_MITIGATION_OFF &&
- boot_cpu_has_bug(X86_BUG_MDS)) {
- mds_mitigation = MDS_MITIGATION_FULL;
- mds_select_mitigation();
- }
- if (taa_mitigation == TAA_MITIGATION_OFF &&
- boot_cpu_has_bug(X86_BUG_TAA)) {
- taa_mitigation = TAA_MITIGATION_VERW;
- taa_select_mitigation();
- }
- /*
- * MMIO_MITIGATION_OFF is not checked here so that mmio_stale_data_clear
- * gets updated correctly as per X86_FEATURE_CLEAR_CPU_BUF state.
- */
- if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) {
- mmio_mitigation = MMIO_MITIGATION_VERW;
- mmio_select_mitigation();
- }
- if (rfds_mitigation == RFDS_MITIGATION_OFF &&
- boot_cpu_has_bug(X86_BUG_RFDS)) {
- rfds_mitigation = RFDS_MITIGATION_VERW;
- rfds_select_mitigation();
- }
-out:
- if (boot_cpu_has_bug(X86_BUG_MDS))
- pr_info("MDS: %s\n", mds_strings[mds_mitigation]);
- if (boot_cpu_has_bug(X86_BUG_TAA))
- pr_info("TAA: %s\n", taa_strings[taa_mitigation]);
- if (boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA))
- pr_info("MMIO Stale Data: %s\n", mmio_strings[mmio_mitigation]);
- else if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
- pr_info("MMIO Stale Data: Unknown: No mitigations\n");
- if (boot_cpu_has_bug(X86_BUG_RFDS))
- pr_info("Register File Data Sampling: %s\n", rfds_strings[rfds_mitigation]);
-}
-
-static void __init md_clear_select_mitigation(void)
-{
- mds_select_mitigation();
- taa_select_mitigation();
- mmio_select_mitigation();
- rfds_select_mitigation();
-
- /*
- * As these mitigations are inter-related and rely on VERW instruction
- * to clear the microarchitural buffers, update and print their status
- * after mitigation selection is done for each of these vulnerabilities.
- */
- md_clear_update_mitigation();
-}
-
-#undef pr_fmt
#define pr_fmt(fmt) "SRBDS: " fmt
enum srbds_mitigations {
SRBDS_MITIGATION_OFF,
+ SRBDS_MITIGATION_AUTO,
SRBDS_MITIGATION_UCODE_NEEDED,
SRBDS_MITIGATION_FULL,
SRBDS_MITIGATION_TSX_OFF,
@@ -633,7 +854,7 @@ enum srbds_mitigations {
};
static enum srbds_mitigations srbds_mitigation __ro_after_init =
- IS_ENABLED(CONFIG_MITIGATION_SRBDS) ? SRBDS_MITIGATION_FULL : SRBDS_MITIGATION_OFF;
+ IS_ENABLED(CONFIG_MITIGATION_SRBDS) ? SRBDS_MITIGATION_AUTO : SRBDS_MITIGATION_OFF;
static const char * const srbds_strings[] = {
[SRBDS_MITIGATION_OFF] = "Vulnerable",
@@ -665,7 +886,7 @@ void update_srbds_msr(void)
if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL))
return;
- rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+ rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
switch (srbds_mitigation) {
case SRBDS_MITIGATION_OFF:
@@ -679,13 +900,24 @@ void update_srbds_msr(void)
break;
}
- wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+ wrmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
}
static void __init srbds_select_mitigation(void)
{
- if (!boot_cpu_has_bug(X86_BUG_SRBDS))
+ if (!boot_cpu_has_bug(X86_BUG_SRBDS)) {
+ srbds_mitigation = SRBDS_MITIGATION_OFF;
return;
+ }
+
+ if (srbds_mitigation == SRBDS_MITIGATION_AUTO) {
+ if (should_mitigate_vuln(X86_BUG_SRBDS))
+ srbds_mitigation = SRBDS_MITIGATION_FULL;
+ else {
+ srbds_mitigation = SRBDS_MITIGATION_OFF;
+ return;
+ }
+ }
/*
* Check to see if this is one of the MDS_NO systems supporting TSX that
@@ -699,13 +931,17 @@ static void __init srbds_select_mitigation(void)
srbds_mitigation = SRBDS_MITIGATION_HYPERVISOR;
else if (!boot_cpu_has(X86_FEATURE_SRBDS_CTRL))
srbds_mitigation = SRBDS_MITIGATION_UCODE_NEEDED;
- else if (cpu_mitigations_off() || srbds_off)
+ else if (srbds_off)
srbds_mitigation = SRBDS_MITIGATION_OFF;
- update_srbds_msr();
pr_info("%s\n", srbds_strings[srbds_mitigation]);
}
+static void __init srbds_apply_mitigation(void)
+{
+ update_srbds_msr();
+}
+
static int __init srbds_parse_cmdline(char *str)
{
if (!str)
@@ -752,6 +988,7 @@ early_param("l1d_flush", l1d_flush_parse_cmdline);
enum gds_mitigations {
GDS_MITIGATION_OFF,
+ GDS_MITIGATION_AUTO,
GDS_MITIGATION_UCODE_NEEDED,
GDS_MITIGATION_FORCE,
GDS_MITIGATION_FULL,
@@ -760,7 +997,7 @@ enum gds_mitigations {
};
static enum gds_mitigations gds_mitigation __ro_after_init =
- IS_ENABLED(CONFIG_MITIGATION_GDS) ? GDS_MITIGATION_FULL : GDS_MITIGATION_OFF;
+ IS_ENABLED(CONFIG_MITIGATION_GDS) ? GDS_MITIGATION_AUTO : GDS_MITIGATION_OFF;
static const char * const gds_strings[] = {
[GDS_MITIGATION_OFF] = "Vulnerable",
@@ -785,7 +1022,7 @@ void update_gds_msr(void)
switch (gds_mitigation) {
case GDS_MITIGATION_OFF:
- rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+ rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
mcu_ctrl |= GDS_MITG_DIS;
break;
case GDS_MITIGATION_FULL_LOCKED:
@@ -795,23 +1032,24 @@ void update_gds_msr(void)
* CPUs.
*/
case GDS_MITIGATION_FULL:
- rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+ rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
mcu_ctrl &= ~GDS_MITG_DIS;
break;
case GDS_MITIGATION_FORCE:
case GDS_MITIGATION_UCODE_NEEDED:
case GDS_MITIGATION_HYPERVISOR:
+ case GDS_MITIGATION_AUTO:
return;
}
- wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+ wrmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
/*
* Check to make sure that the WRMSR value was not ignored. Writes to
* GDS_MITG_DIS will be ignored if this processor is locked but the boot
* processor was not.
*/
- rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after);
+ rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl_after);
WARN_ON_ONCE(mcu_ctrl != mcu_ctrl_after);
}
@@ -824,33 +1062,31 @@ static void __init gds_select_mitigation(void)
if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
gds_mitigation = GDS_MITIGATION_HYPERVISOR;
- goto out;
+ return;
}
- if (cpu_mitigations_off())
- gds_mitigation = GDS_MITIGATION_OFF;
/* Will verify below that mitigation _can_ be disabled */
+ if (gds_mitigation == GDS_MITIGATION_AUTO) {
+ if (should_mitigate_vuln(X86_BUG_GDS))
+ gds_mitigation = GDS_MITIGATION_FULL;
+ else {
+ gds_mitigation = GDS_MITIGATION_OFF;
+ return;
+ }
+ }
/* No microcode */
if (!(x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)) {
- if (gds_mitigation == GDS_MITIGATION_FORCE) {
- /*
- * This only needs to be done on the boot CPU so do it
- * here rather than in update_gds_msr()
- */
- setup_clear_cpu_cap(X86_FEATURE_AVX);
- pr_warn("Microcode update needed! Disabling AVX as mitigation.\n");
- } else {
+ if (gds_mitigation != GDS_MITIGATION_FORCE)
gds_mitigation = GDS_MITIGATION_UCODE_NEEDED;
- }
- goto out;
+ return;
}
/* Microcode has mitigation, use it */
if (gds_mitigation == GDS_MITIGATION_FORCE)
gds_mitigation = GDS_MITIGATION_FULL;
- rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
+ rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_ctrl);
if (mcu_ctrl & GDS_MITG_LOCKED) {
if (gds_mitigation == GDS_MITIGATION_OFF)
pr_warn("Mitigation locked. Disable failed.\n");
@@ -864,9 +1100,25 @@ static void __init gds_select_mitigation(void)
*/
gds_mitigation = GDS_MITIGATION_FULL_LOCKED;
}
+}
+
+static void __init gds_apply_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_GDS))
+ return;
+
+ /* Microcode is present */
+ if (x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)
+ update_gds_msr();
+ else if (gds_mitigation == GDS_MITIGATION_FORCE) {
+ /*
+ * This only needs to be done on the boot CPU so do it
+ * here rather than in update_gds_msr()
+ */
+ setup_clear_cpu_cap(X86_FEATURE_AVX);
+ pr_warn("Microcode update needed! Disabling AVX as mitigation.\n");
+ }
- update_gds_msr();
-out:
pr_info("%s\n", gds_strings[gds_mitigation]);
}
@@ -927,10 +1179,17 @@ static bool smap_works_speculatively(void)
static void __init spectre_v1_select_mitigation(void)
{
- if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1) || cpu_mitigations_off()) {
+ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
+ spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE;
+
+ if (!should_mitigate_vuln(X86_BUG_SPECTRE_V1))
spectre_v1_mitigation = SPECTRE_V1_MITIGATION_NONE;
+}
+
+static void __init spectre_v1_apply_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V1))
return;
- }
if (spectre_v1_mitigation == SPECTRE_V1_MITIGATION_AUTO) {
/*
@@ -980,11 +1239,37 @@ early_param("nospectre_v1", nospectre_v1_cmdline);
enum spectre_v2_mitigation spectre_v2_enabled __ro_after_init = SPECTRE_V2_NONE;
+/* Depends on spectre_v2 mitigation selected already */
+static inline bool cdt_possible(enum spectre_v2_mitigation mode)
+{
+ if (!IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) ||
+ !IS_ENABLED(CONFIG_MITIGATION_RETPOLINE))
+ return false;
+
+ if (mode == SPECTRE_V2_RETPOLINE ||
+ mode == SPECTRE_V2_EIBRS_RETPOLINE)
+ return true;
+
+ return false;
+}
+
#undef pr_fmt
#define pr_fmt(fmt) "RETBleed: " fmt
+enum its_mitigation {
+ ITS_MITIGATION_OFF,
+ ITS_MITIGATION_AUTO,
+ ITS_MITIGATION_VMEXIT_ONLY,
+ ITS_MITIGATION_ALIGNED_THUNKS,
+ ITS_MITIGATION_RETPOLINE_STUFF,
+};
+
+static enum its_mitigation its_mitigation __ro_after_init =
+ IS_ENABLED(CONFIG_MITIGATION_ITS) ? ITS_MITIGATION_AUTO : ITS_MITIGATION_OFF;
+
enum retbleed_mitigation {
RETBLEED_MITIGATION_NONE,
+ RETBLEED_MITIGATION_AUTO,
RETBLEED_MITIGATION_UNRET,
RETBLEED_MITIGATION_IBPB,
RETBLEED_MITIGATION_IBRS,
@@ -992,14 +1277,6 @@ enum retbleed_mitigation {
RETBLEED_MITIGATION_STUFF,
};
-enum retbleed_mitigation_cmd {
- RETBLEED_CMD_OFF,
- RETBLEED_CMD_AUTO,
- RETBLEED_CMD_UNRET,
- RETBLEED_CMD_IBPB,
- RETBLEED_CMD_STUFF,
-};
-
static const char * const retbleed_strings[] = {
[RETBLEED_MITIGATION_NONE] = "Vulnerable",
[RETBLEED_MITIGATION_UNRET] = "Mitigation: untrained return thunk",
@@ -1010,12 +1287,25 @@ static const char * const retbleed_strings[] = {
};
static enum retbleed_mitigation retbleed_mitigation __ro_after_init =
- RETBLEED_MITIGATION_NONE;
-static enum retbleed_mitigation_cmd retbleed_cmd __ro_after_init =
- IS_ENABLED(CONFIG_MITIGATION_RETBLEED) ? RETBLEED_CMD_AUTO : RETBLEED_CMD_OFF;
+ IS_ENABLED(CONFIG_MITIGATION_RETBLEED) ? RETBLEED_MITIGATION_AUTO : RETBLEED_MITIGATION_NONE;
static int __ro_after_init retbleed_nosmt = false;
+enum srso_mitigation {
+ SRSO_MITIGATION_NONE,
+ SRSO_MITIGATION_AUTO,
+ SRSO_MITIGATION_UCODE_NEEDED,
+ SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED,
+ SRSO_MITIGATION_MICROCODE,
+ SRSO_MITIGATION_NOSMT,
+ SRSO_MITIGATION_SAFE_RET,
+ SRSO_MITIGATION_IBPB,
+ SRSO_MITIGATION_IBPB_ON_VMEXIT,
+ SRSO_MITIGATION_BP_SPEC_REDUCE,
+};
+
+static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_AUTO;
+
static int __init retbleed_parse_cmdline(char *str)
{
if (!str)
@@ -1029,15 +1319,15 @@ static int __init retbleed_parse_cmdline(char *str)
}
if (!strcmp(str, "off")) {
- retbleed_cmd = RETBLEED_CMD_OFF;
+ retbleed_mitigation = RETBLEED_MITIGATION_NONE;
} else if (!strcmp(str, "auto")) {
- retbleed_cmd = RETBLEED_CMD_AUTO;
+ retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
} else if (!strcmp(str, "unret")) {
- retbleed_cmd = RETBLEED_CMD_UNRET;
+ retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
} else if (!strcmp(str, "ibpb")) {
- retbleed_cmd = RETBLEED_CMD_IBPB;
+ retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
} else if (!strcmp(str, "stuff")) {
- retbleed_cmd = RETBLEED_CMD_STUFF;
+ retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
} else if (!strcmp(str, "nosmt")) {
retbleed_nosmt = true;
} else if (!strcmp(str, "force")) {
@@ -1058,72 +1348,119 @@ early_param("retbleed", retbleed_parse_cmdline);
static void __init retbleed_select_mitigation(void)
{
- bool mitigate_smt = false;
-
- if (!boot_cpu_has_bug(X86_BUG_RETBLEED) || cpu_mitigations_off())
- return;
-
- switch (retbleed_cmd) {
- case RETBLEED_CMD_OFF:
+ if (!boot_cpu_has_bug(X86_BUG_RETBLEED)) {
+ retbleed_mitigation = RETBLEED_MITIGATION_NONE;
return;
+ }
- case RETBLEED_CMD_UNRET:
- if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) {
- retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
- } else {
+ switch (retbleed_mitigation) {
+ case RETBLEED_MITIGATION_UNRET:
+ if (!IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY)) {
+ retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
pr_err("WARNING: kernel not compiled with MITIGATION_UNRET_ENTRY.\n");
- goto do_cmd_auto;
}
break;
-
- case RETBLEED_CMD_IBPB:
+ case RETBLEED_MITIGATION_IBPB:
if (!boot_cpu_has(X86_FEATURE_IBPB)) {
pr_err("WARNING: CPU does not support IBPB.\n");
- goto do_cmd_auto;
- } else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
- retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
- } else {
+ retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
+ } else if (!IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
- goto do_cmd_auto;
+ retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
+ }
+ break;
+ case RETBLEED_MITIGATION_STUFF:
+ if (!IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING)) {
+ pr_err("WARNING: kernel not compiled with MITIGATION_CALL_DEPTH_TRACKING.\n");
+ retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
+ } else if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL) {
+ pr_err("WARNING: retbleed=stuff only supported for Intel CPUs.\n");
+ retbleed_mitigation = RETBLEED_MITIGATION_AUTO;
}
break;
+ default:
+ break;
+ }
- case RETBLEED_CMD_STUFF:
- if (IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) &&
- spectre_v2_enabled == SPECTRE_V2_RETPOLINE) {
- retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
+ if (retbleed_mitigation != RETBLEED_MITIGATION_AUTO)
+ return;
- } else {
- if (IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING))
- pr_err("WARNING: retbleed=stuff depends on spectre_v2=retpoline\n");
- else
- pr_err("WARNING: kernel not compiled with MITIGATION_CALL_DEPTH_TRACKING.\n");
+ if (!should_mitigate_vuln(X86_BUG_RETBLEED)) {
+ retbleed_mitigation = RETBLEED_MITIGATION_NONE;
+ return;
+ }
- goto do_cmd_auto;
- }
- break;
+ /* Intel mitigation selected in retbleed_update_mitigation() */
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
+ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
+ if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY))
+ retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
+ else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY) &&
+ boot_cpu_has(X86_FEATURE_IBPB))
+ retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
+ else
+ retbleed_mitigation = RETBLEED_MITIGATION_NONE;
+ } else if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+ /* Final mitigation depends on spectre-v2 selection */
+ if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED))
+ retbleed_mitigation = RETBLEED_MITIGATION_EIBRS;
+ else if (boot_cpu_has(X86_FEATURE_IBRS))
+ retbleed_mitigation = RETBLEED_MITIGATION_IBRS;
+ else
+ retbleed_mitigation = RETBLEED_MITIGATION_NONE;
+ }
+}
-do_cmd_auto:
- case RETBLEED_CMD_AUTO:
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
- boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
- if (IS_ENABLED(CONFIG_MITIGATION_UNRET_ENTRY))
- retbleed_mitigation = RETBLEED_MITIGATION_UNRET;
- else if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY) &&
- boot_cpu_has(X86_FEATURE_IBPB))
- retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
- }
+static void __init retbleed_update_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_RETBLEED))
+ return;
- /*
- * The Intel mitigation (IBRS or eIBRS) was already selected in
- * spectre_v2_select_mitigation(). 'retbleed_mitigation' will
- * be set accordingly below.
- */
+ /* ITS can also enable stuffing */
+ if (its_mitigation == ITS_MITIGATION_RETPOLINE_STUFF)
+ retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
- break;
+ /* If SRSO is using IBPB, that works for retbleed too */
+ if (srso_mitigation == SRSO_MITIGATION_IBPB)
+ retbleed_mitigation = RETBLEED_MITIGATION_IBPB;
+
+ if (retbleed_mitigation == RETBLEED_MITIGATION_STUFF &&
+ !cdt_possible(spectre_v2_enabled)) {
+ pr_err("WARNING: retbleed=stuff depends on retpoline\n");
+ retbleed_mitigation = RETBLEED_MITIGATION_NONE;
+ }
+
+ /*
+ * Let IBRS trump all on Intel without affecting the effects of the
+ * retbleed= cmdline option except for call depth based stuffing
+ */
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+ switch (spectre_v2_enabled) {
+ case SPECTRE_V2_IBRS:
+ retbleed_mitigation = RETBLEED_MITIGATION_IBRS;
+ break;
+ case SPECTRE_V2_EIBRS:
+ case SPECTRE_V2_EIBRS_RETPOLINE:
+ case SPECTRE_V2_EIBRS_LFENCE:
+ retbleed_mitigation = RETBLEED_MITIGATION_EIBRS;
+ break;
+ default:
+ if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF)
+ pr_err(RETBLEED_INTEL_MSG);
+ }
}
+ pr_info("%s\n", retbleed_strings[retbleed_mitigation]);
+}
+
+static void __init retbleed_apply_mitigation(void)
+{
+ bool mitigate_smt = false;
+
switch (retbleed_mitigation) {
+ case RETBLEED_MITIGATION_NONE:
+ return;
+
case RETBLEED_MITIGATION_UNRET:
setup_force_cpu_cap(X86_FEATURE_RETHUNK);
setup_force_cpu_cap(X86_FEATURE_UNRET);
@@ -1171,49 +1508,13 @@ do_cmd_auto:
}
if (mitigate_smt && !boot_cpu_has(X86_FEATURE_STIBP) &&
- (retbleed_nosmt || cpu_mitigations_auto_nosmt()))
+ (retbleed_nosmt || smt_mitigations == SMT_MITIGATIONS_ON))
cpu_smt_disable(false);
-
- /*
- * Let IBRS trump all on Intel without affecting the effects of the
- * retbleed= cmdline option except for call depth based stuffing
- */
- if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
- switch (spectre_v2_enabled) {
- case SPECTRE_V2_IBRS:
- retbleed_mitigation = RETBLEED_MITIGATION_IBRS;
- break;
- case SPECTRE_V2_EIBRS:
- case SPECTRE_V2_EIBRS_RETPOLINE:
- case SPECTRE_V2_EIBRS_LFENCE:
- retbleed_mitigation = RETBLEED_MITIGATION_EIBRS;
- break;
- default:
- if (retbleed_mitigation != RETBLEED_MITIGATION_STUFF)
- pr_err(RETBLEED_INTEL_MSG);
- }
- }
-
- pr_info("%s\n", retbleed_strings[retbleed_mitigation]);
}
#undef pr_fmt
#define pr_fmt(fmt) "ITS: " fmt
-enum its_mitigation_cmd {
- ITS_CMD_OFF,
- ITS_CMD_ON,
- ITS_CMD_VMEXIT,
- ITS_CMD_RSB_STUFF,
-};
-
-enum its_mitigation {
- ITS_MITIGATION_OFF,
- ITS_MITIGATION_VMEXIT_ONLY,
- ITS_MITIGATION_ALIGNED_THUNKS,
- ITS_MITIGATION_RETPOLINE_STUFF,
-};
-
static const char * const its_strings[] = {
[ITS_MITIGATION_OFF] = "Vulnerable",
[ITS_MITIGATION_VMEXIT_ONLY] = "Mitigation: Vulnerable, KVM: Not affected",
@@ -1221,11 +1522,6 @@ static const char * const its_strings[] = {
[ITS_MITIGATION_RETPOLINE_STUFF] = "Mitigation: Retpolines, Stuffing RSB",
};
-static enum its_mitigation its_mitigation __ro_after_init = ITS_MITIGATION_ALIGNED_THUNKS;
-
-static enum its_mitigation_cmd its_cmd __ro_after_init =
- IS_ENABLED(CONFIG_MITIGATION_ITS) ? ITS_CMD_ON : ITS_CMD_OFF;
-
static int __init its_parse_cmdline(char *str)
{
if (!str)
@@ -1237,16 +1533,16 @@ static int __init its_parse_cmdline(char *str)
}
if (!strcmp(str, "off")) {
- its_cmd = ITS_CMD_OFF;
+ its_mitigation = ITS_MITIGATION_OFF;
} else if (!strcmp(str, "on")) {
- its_cmd = ITS_CMD_ON;
+ its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
} else if (!strcmp(str, "force")) {
- its_cmd = ITS_CMD_ON;
+ its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
setup_force_cpu_bug(X86_BUG_ITS);
} else if (!strcmp(str, "vmexit")) {
- its_cmd = ITS_CMD_VMEXIT;
+ its_mitigation = ITS_MITIGATION_VMEXIT_ONLY;
} else if (!strcmp(str, "stuff")) {
- its_cmd = ITS_CMD_RSB_STUFF;
+ its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
} else {
pr_err("Ignoring unknown indirect_target_selection option (%s).", str);
}
@@ -1257,83 +1553,201 @@ early_param("indirect_target_selection", its_parse_cmdline);
static void __init its_select_mitigation(void)
{
- enum its_mitigation_cmd cmd = its_cmd;
-
- if (!boot_cpu_has_bug(X86_BUG_ITS) || cpu_mitigations_off()) {
+ if (!boot_cpu_has_bug(X86_BUG_ITS)) {
its_mitigation = ITS_MITIGATION_OFF;
return;
}
- /* Retpoline+CDT mitigates ITS, bail out */
- if (boot_cpu_has(X86_FEATURE_RETPOLINE) &&
- boot_cpu_has(X86_FEATURE_CALL_DEPTH)) {
- its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
- goto out;
+ if (its_mitigation == ITS_MITIGATION_AUTO) {
+ if (should_mitigate_vuln(X86_BUG_ITS))
+ its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
+ else
+ its_mitigation = ITS_MITIGATION_OFF;
}
- /* Exit early to avoid irrelevant warnings */
- if (cmd == ITS_CMD_OFF) {
- its_mitigation = ITS_MITIGATION_OFF;
- goto out;
- }
- if (spectre_v2_enabled == SPECTRE_V2_NONE) {
- pr_err("WARNING: Spectre-v2 mitigation is off, disabling ITS\n");
- its_mitigation = ITS_MITIGATION_OFF;
- goto out;
- }
+ if (its_mitigation == ITS_MITIGATION_OFF)
+ return;
+
if (!IS_ENABLED(CONFIG_MITIGATION_RETPOLINE) ||
!IS_ENABLED(CONFIG_MITIGATION_RETHUNK)) {
pr_err("WARNING: ITS mitigation depends on retpoline and rethunk support\n");
its_mitigation = ITS_MITIGATION_OFF;
- goto out;
+ return;
}
+
if (IS_ENABLED(CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B)) {
pr_err("WARNING: ITS mitigation is not compatible with CONFIG_DEBUG_FORCE_FUNCTION_ALIGN_64B\n");
its_mitigation = ITS_MITIGATION_OFF;
- goto out;
- }
- if (boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) {
- pr_err("WARNING: ITS mitigation is not compatible with lfence mitigation\n");
- its_mitigation = ITS_MITIGATION_OFF;
- goto out;
+ return;
}
- if (cmd == ITS_CMD_RSB_STUFF &&
- (!boot_cpu_has(X86_FEATURE_RETPOLINE) || !IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING))) {
+ if (its_mitigation == ITS_MITIGATION_RETPOLINE_STUFF &&
+ !IS_ENABLED(CONFIG_MITIGATION_CALL_DEPTH_TRACKING)) {
pr_err("RSB stuff mitigation not supported, using default\n");
- cmd = ITS_CMD_ON;
+ its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
}
- switch (cmd) {
- case ITS_CMD_OFF:
+ if (its_mitigation == ITS_MITIGATION_VMEXIT_ONLY &&
+ !boot_cpu_has_bug(X86_BUG_ITS_NATIVE_ONLY))
+ its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
+}
+
+static void __init its_update_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_ITS))
+ return;
+
+ switch (spectre_v2_enabled) {
+ case SPECTRE_V2_NONE:
+ if (its_mitigation != ITS_MITIGATION_OFF)
+ pr_err("WARNING: Spectre-v2 mitigation is off, disabling ITS\n");
its_mitigation = ITS_MITIGATION_OFF;
break;
- case ITS_CMD_VMEXIT:
- if (boot_cpu_has_bug(X86_BUG_ITS_NATIVE_ONLY)) {
- its_mitigation = ITS_MITIGATION_VMEXIT_ONLY;
- goto out;
- }
- fallthrough;
- case ITS_CMD_ON:
+ case SPECTRE_V2_RETPOLINE:
+ case SPECTRE_V2_EIBRS_RETPOLINE:
+ /* Retpoline+CDT mitigates ITS */
+ if (retbleed_mitigation == RETBLEED_MITIGATION_STUFF)
+ its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
+ break;
+ case SPECTRE_V2_LFENCE:
+ case SPECTRE_V2_EIBRS_LFENCE:
+ pr_err("WARNING: ITS mitigation is not compatible with lfence mitigation\n");
+ its_mitigation = ITS_MITIGATION_OFF;
+ break;
+ default:
+ break;
+ }
+
+ if (its_mitigation == ITS_MITIGATION_RETPOLINE_STUFF &&
+ !cdt_possible(spectre_v2_enabled))
its_mitigation = ITS_MITIGATION_ALIGNED_THUNKS;
+
+ pr_info("%s\n", its_strings[its_mitigation]);
+}
+
+static void __init its_apply_mitigation(void)
+{
+ switch (its_mitigation) {
+ case ITS_MITIGATION_OFF:
+ case ITS_MITIGATION_AUTO:
+ case ITS_MITIGATION_VMEXIT_ONLY:
+ break;
+ case ITS_MITIGATION_ALIGNED_THUNKS:
if (!boot_cpu_has(X86_FEATURE_RETPOLINE))
setup_force_cpu_cap(X86_FEATURE_INDIRECT_THUNK_ITS);
+
setup_force_cpu_cap(X86_FEATURE_RETHUNK);
set_return_thunk(its_return_thunk);
break;
- case ITS_CMD_RSB_STUFF:
- its_mitigation = ITS_MITIGATION_RETPOLINE_STUFF;
+ case ITS_MITIGATION_RETPOLINE_STUFF:
setup_force_cpu_cap(X86_FEATURE_RETHUNK);
setup_force_cpu_cap(X86_FEATURE_CALL_DEPTH);
set_return_thunk(call_depth_return_thunk);
- if (retbleed_mitigation == RETBLEED_MITIGATION_NONE) {
- retbleed_mitigation = RETBLEED_MITIGATION_STUFF;
- pr_info("Retbleed mitigation updated to stuffing\n");
+ break;
+ }
+}
+
+#undef pr_fmt
+#define pr_fmt(fmt) "Transient Scheduler Attacks: " fmt
+
+enum tsa_mitigations {
+ TSA_MITIGATION_NONE,
+ TSA_MITIGATION_AUTO,
+ TSA_MITIGATION_UCODE_NEEDED,
+ TSA_MITIGATION_USER_KERNEL,
+ TSA_MITIGATION_VM,
+ TSA_MITIGATION_FULL,
+};
+
+static const char * const tsa_strings[] = {
+ [TSA_MITIGATION_NONE] = "Vulnerable",
+ [TSA_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode",
+ [TSA_MITIGATION_USER_KERNEL] = "Mitigation: Clear CPU buffers: user/kernel boundary",
+ [TSA_MITIGATION_VM] = "Mitigation: Clear CPU buffers: VM",
+ [TSA_MITIGATION_FULL] = "Mitigation: Clear CPU buffers",
+};
+
+static enum tsa_mitigations tsa_mitigation __ro_after_init =
+ IS_ENABLED(CONFIG_MITIGATION_TSA) ? TSA_MITIGATION_AUTO : TSA_MITIGATION_NONE;
+
+static int __init tsa_parse_cmdline(char *str)
+{
+ if (!str)
+ return -EINVAL;
+
+ if (!strcmp(str, "off"))
+ tsa_mitigation = TSA_MITIGATION_NONE;
+ else if (!strcmp(str, "on"))
+ tsa_mitigation = TSA_MITIGATION_FULL;
+ else if (!strcmp(str, "user"))
+ tsa_mitigation = TSA_MITIGATION_USER_KERNEL;
+ else if (!strcmp(str, "vm"))
+ tsa_mitigation = TSA_MITIGATION_VM;
+ else
+ pr_err("Ignoring unknown tsa=%s option.\n", str);
+
+ return 0;
+}
+early_param("tsa", tsa_parse_cmdline);
+
+static void __init tsa_select_mitigation(void)
+{
+ if (!boot_cpu_has_bug(X86_BUG_TSA)) {
+ tsa_mitigation = TSA_MITIGATION_NONE;
+ return;
+ }
+
+ if (tsa_mitigation == TSA_MITIGATION_AUTO) {
+ bool vm = false, uk = false;
+
+ tsa_mitigation = TSA_MITIGATION_NONE;
+
+ if (cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL) ||
+ cpu_attack_vector_mitigated(CPU_MITIGATE_USER_USER)) {
+ tsa_mitigation = TSA_MITIGATION_USER_KERNEL;
+ uk = true;
+ }
+
+ if (cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_HOST) ||
+ cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_GUEST)) {
+ tsa_mitigation = TSA_MITIGATION_VM;
+ vm = true;
}
+
+ if (uk && vm)
+ tsa_mitigation = TSA_MITIGATION_FULL;
+ }
+
+ if (tsa_mitigation == TSA_MITIGATION_NONE)
+ return;
+
+ if (!boot_cpu_has(X86_FEATURE_VERW_CLEAR))
+ tsa_mitigation = TSA_MITIGATION_UCODE_NEEDED;
+
+ /*
+ * No need to set verw_clear_cpu_buf_mitigation_selected - it
+ * doesn't fit all cases here and it is not needed because this
+ * is the only VERW-based mitigation on AMD.
+ */
+ pr_info("%s\n", tsa_strings[tsa_mitigation]);
+}
+
+static void __init tsa_apply_mitigation(void)
+{
+ switch (tsa_mitigation) {
+ case TSA_MITIGATION_USER_KERNEL:
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+ break;
+ case TSA_MITIGATION_VM:
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+ break;
+ case TSA_MITIGATION_FULL:
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+ break;
+ default:
break;
}
-out:
- pr_info("%s\n", its_strings[its_mitigation]);
}
#undef pr_fmt
@@ -1413,6 +1827,8 @@ enum spectre_v2_mitigation_cmd {
SPECTRE_V2_CMD_IBRS,
};
+static enum spectre_v2_mitigation_cmd spectre_v2_cmd __ro_after_init = SPECTRE_V2_CMD_AUTO;
+
enum spectre_v2_user_cmd {
SPECTRE_V2_USER_CMD_NONE,
SPECTRE_V2_USER_CMD_AUTO,
@@ -1451,31 +1867,18 @@ static void __init spec_v2_user_print_cond(const char *reason, bool secure)
pr_info("spectre_v2_user=%s forced on command line.\n", reason);
}
-static __ro_after_init enum spectre_v2_mitigation_cmd spectre_v2_cmd;
-
-static enum spectre_v2_user_cmd __init
-spectre_v2_parse_user_cmdline(void)
+static enum spectre_v2_user_cmd __init spectre_v2_parse_user_cmdline(void)
{
- enum spectre_v2_user_cmd mode;
char arg[20];
int ret, i;
- mode = IS_ENABLED(CONFIG_MITIGATION_SPECTRE_V2) ?
- SPECTRE_V2_USER_CMD_AUTO : SPECTRE_V2_USER_CMD_NONE;
-
- switch (spectre_v2_cmd) {
- case SPECTRE_V2_CMD_NONE:
+ if (!IS_ENABLED(CONFIG_MITIGATION_SPECTRE_V2))
return SPECTRE_V2_USER_CMD_NONE;
- case SPECTRE_V2_CMD_FORCE:
- return SPECTRE_V2_USER_CMD_FORCE;
- default:
- break;
- }
ret = cmdline_find_option(boot_command_line, "spectre_v2_user",
arg, sizeof(arg));
if (ret < 0)
- return mode;
+ return SPECTRE_V2_USER_CMD_AUTO;
for (i = 0; i < ARRAY_SIZE(v2_user_options); i++) {
if (match_option(arg, ret, v2_user_options[i].option)) {
@@ -1486,7 +1889,7 @@ spectre_v2_parse_user_cmdline(void)
}
pr_err("Unknown user space protection option (%s). Switching to default\n", arg);
- return mode;
+ return SPECTRE_V2_USER_CMD_AUTO;
}
static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode)
@@ -1494,60 +1897,79 @@ static inline bool spectre_v2_in_ibrs_mode(enum spectre_v2_mitigation mode)
return spectre_v2_in_eibrs_mode(mode) || mode == SPECTRE_V2_IBRS;
}
-static void __init
-spectre_v2_user_select_mitigation(void)
+static void __init spectre_v2_user_select_mitigation(void)
{
- enum spectre_v2_user_mitigation mode = SPECTRE_V2_USER_NONE;
- enum spectre_v2_user_cmd cmd;
-
if (!boot_cpu_has(X86_FEATURE_IBPB) && !boot_cpu_has(X86_FEATURE_STIBP))
return;
- cmd = spectre_v2_parse_user_cmdline();
- switch (cmd) {
+ switch (spectre_v2_parse_user_cmdline()) {
case SPECTRE_V2_USER_CMD_NONE:
- goto set_mode;
+ return;
case SPECTRE_V2_USER_CMD_FORCE:
- mode = SPECTRE_V2_USER_STRICT;
+ spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT;
+ spectre_v2_user_stibp = SPECTRE_V2_USER_STRICT;
break;
case SPECTRE_V2_USER_CMD_AUTO:
+ if (!should_mitigate_vuln(X86_BUG_SPECTRE_V2_USER))
+ break;
+ spectre_v2_user_ibpb = SPECTRE_V2_USER_PRCTL;
+ if (smt_mitigations == SMT_MITIGATIONS_OFF)
+ break;
+ spectre_v2_user_stibp = SPECTRE_V2_USER_PRCTL;
+ break;
case SPECTRE_V2_USER_CMD_PRCTL:
+ spectre_v2_user_ibpb = SPECTRE_V2_USER_PRCTL;
+ spectre_v2_user_stibp = SPECTRE_V2_USER_PRCTL;
+ break;
case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
- mode = SPECTRE_V2_USER_PRCTL;
+ spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT;
+ spectre_v2_user_stibp = SPECTRE_V2_USER_PRCTL;
break;
case SPECTRE_V2_USER_CMD_SECCOMP:
+ if (IS_ENABLED(CONFIG_SECCOMP))
+ spectre_v2_user_ibpb = SPECTRE_V2_USER_SECCOMP;
+ else
+ spectre_v2_user_ibpb = SPECTRE_V2_USER_PRCTL;
+ spectre_v2_user_stibp = spectre_v2_user_ibpb;
+ break;
case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
+ spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT;
if (IS_ENABLED(CONFIG_SECCOMP))
- mode = SPECTRE_V2_USER_SECCOMP;
+ spectre_v2_user_stibp = SPECTRE_V2_USER_SECCOMP;
else
- mode = SPECTRE_V2_USER_PRCTL;
+ spectre_v2_user_stibp = SPECTRE_V2_USER_PRCTL;
break;
}
- /* Initialize Indirect Branch Prediction Barrier */
- if (boot_cpu_has(X86_FEATURE_IBPB)) {
- static_branch_enable(&switch_vcpu_ibpb);
+ /*
+ * At this point, an STIBP mode other than "off" has been set.
+ * If STIBP support is not being forced, check if STIBP always-on
+ * is preferred.
+ */
+ if ((spectre_v2_user_stibp == SPECTRE_V2_USER_PRCTL ||
+ spectre_v2_user_stibp == SPECTRE_V2_USER_SECCOMP) &&
+ boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
+ spectre_v2_user_stibp = SPECTRE_V2_USER_STRICT_PREFERRED;
- spectre_v2_user_ibpb = mode;
- switch (cmd) {
- case SPECTRE_V2_USER_CMD_NONE:
- break;
- case SPECTRE_V2_USER_CMD_FORCE:
- case SPECTRE_V2_USER_CMD_PRCTL_IBPB:
- case SPECTRE_V2_USER_CMD_SECCOMP_IBPB:
- static_branch_enable(&switch_mm_always_ibpb);
- spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT;
- break;
- case SPECTRE_V2_USER_CMD_PRCTL:
- case SPECTRE_V2_USER_CMD_AUTO:
- case SPECTRE_V2_USER_CMD_SECCOMP:
- static_branch_enable(&switch_mm_cond_ibpb);
- break;
- }
+ if (!boot_cpu_has(X86_FEATURE_IBPB))
+ spectre_v2_user_ibpb = SPECTRE_V2_USER_NONE;
- pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
- static_key_enabled(&switch_mm_always_ibpb) ?
- "always-on" : "conditional");
+ if (!boot_cpu_has(X86_FEATURE_STIBP))
+ spectre_v2_user_stibp = SPECTRE_V2_USER_NONE;
+}
+
+static void __init spectre_v2_user_update_mitigation(void)
+{
+ if (!boot_cpu_has(X86_FEATURE_IBPB) && !boot_cpu_has(X86_FEATURE_STIBP))
+ return;
+
+ /* The spectre_v2 cmd line can override spectre_v2_user options */
+ if (spectre_v2_cmd == SPECTRE_V2_CMD_NONE) {
+ spectre_v2_user_ibpb = SPECTRE_V2_USER_NONE;
+ spectre_v2_user_stibp = SPECTRE_V2_USER_NONE;
+ } else if (spectre_v2_cmd == SPECTRE_V2_CMD_FORCE) {
+ spectre_v2_user_ibpb = SPECTRE_V2_USER_STRICT;
+ spectre_v2_user_stibp = SPECTRE_V2_USER_STRICT;
}
/*
@@ -1565,30 +1987,44 @@ spectre_v2_user_select_mitigation(void)
if (!boot_cpu_has(X86_FEATURE_STIBP) ||
!cpu_smt_possible() ||
(spectre_v2_in_eibrs_mode(spectre_v2_enabled) &&
- !boot_cpu_has(X86_FEATURE_AUTOIBRS)))
+ !boot_cpu_has(X86_FEATURE_AUTOIBRS))) {
+ spectre_v2_user_stibp = SPECTRE_V2_USER_NONE;
return;
+ }
- /*
- * At this point, an STIBP mode other than "off" has been set.
- * If STIBP support is not being forced, check if STIBP always-on
- * is preferred.
- */
- if (mode != SPECTRE_V2_USER_STRICT &&
- boot_cpu_has(X86_FEATURE_AMD_STIBP_ALWAYS_ON))
- mode = SPECTRE_V2_USER_STRICT_PREFERRED;
-
- if (retbleed_mitigation == RETBLEED_MITIGATION_UNRET ||
- retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
- if (mode != SPECTRE_V2_USER_STRICT &&
- mode != SPECTRE_V2_USER_STRICT_PREFERRED)
+ if (spectre_v2_user_stibp != SPECTRE_V2_USER_NONE &&
+ (retbleed_mitigation == RETBLEED_MITIGATION_UNRET ||
+ retbleed_mitigation == RETBLEED_MITIGATION_IBPB)) {
+ if (spectre_v2_user_stibp != SPECTRE_V2_USER_STRICT &&
+ spectre_v2_user_stibp != SPECTRE_V2_USER_STRICT_PREFERRED)
pr_info("Selecting STIBP always-on mode to complement retbleed mitigation\n");
- mode = SPECTRE_V2_USER_STRICT_PREFERRED;
+ spectre_v2_user_stibp = SPECTRE_V2_USER_STRICT_PREFERRED;
}
+ pr_info("%s\n", spectre_v2_user_strings[spectre_v2_user_stibp]);
+}
+
+static void __init spectre_v2_user_apply_mitigation(void)
+{
+ /* Initialize Indirect Branch Prediction Barrier */
+ if (spectre_v2_user_ibpb != SPECTRE_V2_USER_NONE) {
+ static_branch_enable(&switch_vcpu_ibpb);
- spectre_v2_user_stibp = mode;
+ switch (spectre_v2_user_ibpb) {
+ case SPECTRE_V2_USER_STRICT:
+ static_branch_enable(&switch_mm_always_ibpb);
+ break;
+ case SPECTRE_V2_USER_PRCTL:
+ case SPECTRE_V2_USER_SECCOMP:
+ static_branch_enable(&switch_mm_cond_ibpb);
+ break;
+ default:
+ break;
+ }
-set_mode:
- pr_info("%s\n", spectre_v2_user_strings[mode]);
+ pr_info("mitigation: Enabling %s Indirect Branch Prediction Barrier\n",
+ static_key_enabled(&switch_mm_always_ibpb) ?
+ "always-on" : "conditional");
+ }
}
static const char * const spectre_v2_strings[] = {
@@ -1632,8 +2068,7 @@ static enum spectre_v2_mitigation_cmd __init spectre_v2_parse_cmdline(void)
int ret, i;
cmd = IS_ENABLED(CONFIG_MITIGATION_SPECTRE_V2) ? SPECTRE_V2_CMD_AUTO : SPECTRE_V2_CMD_NONE;
- if (cmdline_find_option_bool(boot_command_line, "nospectre_v2") ||
- cpu_mitigations_off())
+ if (cmdline_find_option_bool(boot_command_line, "nospectre_v2"))
return SPECTRE_V2_CMD_NONE;
ret = cmdline_find_option(boot_command_line, "spectre_v2", arg, sizeof(arg));
@@ -1808,12 +2243,13 @@ static bool __init spec_ctrl_bhi_dis(void)
enum bhi_mitigations {
BHI_MITIGATION_OFF,
+ BHI_MITIGATION_AUTO,
BHI_MITIGATION_ON,
BHI_MITIGATION_VMEXIT_ONLY,
};
static enum bhi_mitigations bhi_mitigation __ro_after_init =
- IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_ON : BHI_MITIGATION_OFF;
+ IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_AUTO : BHI_MITIGATION_OFF;
static int __init spectre_bhi_parse_cmdline(char *str)
{
@@ -1835,6 +2271,34 @@ early_param("spectre_bhi", spectre_bhi_parse_cmdline);
static void __init bhi_select_mitigation(void)
{
+ if (!boot_cpu_has(X86_BUG_BHI))
+ bhi_mitigation = BHI_MITIGATION_OFF;
+
+ if (bhi_mitigation != BHI_MITIGATION_AUTO)
+ return;
+
+ if (cpu_attack_vector_mitigated(CPU_MITIGATE_GUEST_HOST)) {
+ if (cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL))
+ bhi_mitigation = BHI_MITIGATION_ON;
+ else
+ bhi_mitigation = BHI_MITIGATION_VMEXIT_ONLY;
+ } else {
+ bhi_mitigation = BHI_MITIGATION_OFF;
+ }
+}
+
+static void __init bhi_update_mitigation(void)
+{
+ if (spectre_v2_cmd == SPECTRE_V2_CMD_NONE)
+ bhi_mitigation = BHI_MITIGATION_OFF;
+
+ if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) &&
+ spectre_v2_cmd == SPECTRE_V2_CMD_AUTO)
+ bhi_mitigation = BHI_MITIGATION_OFF;
+}
+
+static void __init bhi_apply_mitigation(void)
+{
if (bhi_mitigation == BHI_MITIGATION_OFF)
return;
@@ -1855,86 +2319,95 @@ static void __init bhi_select_mitigation(void)
if (bhi_mitigation == BHI_MITIGATION_VMEXIT_ONLY) {
pr_info("Spectre BHI mitigation: SW BHB clearing on VM exit only\n");
- setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_VMEXIT);
return;
}
pr_info("Spectre BHI mitigation: SW BHB clearing on syscall and VM exit\n");
setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP);
- setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT);
+ setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_VMEXIT);
}
static void __init spectre_v2_select_mitigation(void)
{
- enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline();
- enum spectre_v2_mitigation mode = SPECTRE_V2_NONE;
+ spectre_v2_cmd = spectre_v2_parse_cmdline();
- /*
- * If the CPU is not affected and the command line mode is NONE or AUTO
- * then nothing to do.
- */
if (!boot_cpu_has_bug(X86_BUG_SPECTRE_V2) &&
- (cmd == SPECTRE_V2_CMD_NONE || cmd == SPECTRE_V2_CMD_AUTO))
+ (spectre_v2_cmd == SPECTRE_V2_CMD_NONE || spectre_v2_cmd == SPECTRE_V2_CMD_AUTO))
return;
- switch (cmd) {
+ switch (spectre_v2_cmd) {
case SPECTRE_V2_CMD_NONE:
return;
- case SPECTRE_V2_CMD_FORCE:
case SPECTRE_V2_CMD_AUTO:
- if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
- mode = SPECTRE_V2_EIBRS;
+ if (!should_mitigate_vuln(X86_BUG_SPECTRE_V2))
break;
- }
-
- if (IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY) &&
- boot_cpu_has_bug(X86_BUG_RETBLEED) &&
- retbleed_cmd != RETBLEED_CMD_OFF &&
- retbleed_cmd != RETBLEED_CMD_STUFF &&
- boot_cpu_has(X86_FEATURE_IBRS) &&
- boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
- mode = SPECTRE_V2_IBRS;
+ fallthrough;
+ case SPECTRE_V2_CMD_FORCE:
+ if (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED)) {
+ spectre_v2_enabled = SPECTRE_V2_EIBRS;
break;
}
- mode = spectre_v2_select_retpoline();
+ spectre_v2_enabled = spectre_v2_select_retpoline();
break;
case SPECTRE_V2_CMD_RETPOLINE_LFENCE:
pr_err(SPECTRE_V2_LFENCE_MSG);
- mode = SPECTRE_V2_LFENCE;
+ spectre_v2_enabled = SPECTRE_V2_LFENCE;
break;
case SPECTRE_V2_CMD_RETPOLINE_GENERIC:
- mode = SPECTRE_V2_RETPOLINE;
+ spectre_v2_enabled = SPECTRE_V2_RETPOLINE;
break;
case SPECTRE_V2_CMD_RETPOLINE:
- mode = spectre_v2_select_retpoline();
+ spectre_v2_enabled = spectre_v2_select_retpoline();
break;
case SPECTRE_V2_CMD_IBRS:
- mode = SPECTRE_V2_IBRS;
+ spectre_v2_enabled = SPECTRE_V2_IBRS;
break;
case SPECTRE_V2_CMD_EIBRS:
- mode = SPECTRE_V2_EIBRS;
+ spectre_v2_enabled = SPECTRE_V2_EIBRS;
break;
case SPECTRE_V2_CMD_EIBRS_LFENCE:
- mode = SPECTRE_V2_EIBRS_LFENCE;
+ spectre_v2_enabled = SPECTRE_V2_EIBRS_LFENCE;
break;
case SPECTRE_V2_CMD_EIBRS_RETPOLINE:
- mode = SPECTRE_V2_EIBRS_RETPOLINE;
+ spectre_v2_enabled = SPECTRE_V2_EIBRS_RETPOLINE;
break;
}
+}
+
+static void __init spectre_v2_update_mitigation(void)
+{
+ if (spectre_v2_cmd == SPECTRE_V2_CMD_AUTO &&
+ !spectre_v2_in_eibrs_mode(spectre_v2_enabled)) {
+ if (IS_ENABLED(CONFIG_MITIGATION_IBRS_ENTRY) &&
+ boot_cpu_has_bug(X86_BUG_RETBLEED) &&
+ retbleed_mitigation != RETBLEED_MITIGATION_NONE &&
+ retbleed_mitigation != RETBLEED_MITIGATION_STUFF &&
+ boot_cpu_has(X86_FEATURE_IBRS) &&
+ boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+ spectre_v2_enabled = SPECTRE_V2_IBRS;
+ }
+ }
+
+ if (boot_cpu_has_bug(X86_BUG_SPECTRE_V2))
+ pr_info("%s\n", spectre_v2_strings[spectre_v2_enabled]);
+}
- if (mode == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled())
+static void __init spectre_v2_apply_mitigation(void)
+{
+ if (spectre_v2_enabled == SPECTRE_V2_EIBRS && unprivileged_ebpf_enabled())
pr_err(SPECTRE_V2_EIBRS_EBPF_MSG);
- if (spectre_v2_in_ibrs_mode(mode)) {
+ if (spectre_v2_in_ibrs_mode(spectre_v2_enabled)) {
if (boot_cpu_has(X86_FEATURE_AUTOIBRS)) {
msr_set_bit(MSR_EFER, _EFER_AUTOIBRS);
} else {
@@ -1943,8 +2416,10 @@ static void __init spectre_v2_select_mitigation(void)
}
}
- switch (mode) {
+ switch (spectre_v2_enabled) {
case SPECTRE_V2_NONE:
+ return;
+
case SPECTRE_V2_EIBRS:
break;
@@ -1970,18 +2445,12 @@ static void __init spectre_v2_select_mitigation(void)
* JMPs gets protection against BHI and Intramode-BTI, but RET
* prediction from a non-RSB predictor is still a risk.
*/
- if (mode == SPECTRE_V2_EIBRS_LFENCE ||
- mode == SPECTRE_V2_EIBRS_RETPOLINE ||
- mode == SPECTRE_V2_RETPOLINE)
+ if (spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE ||
+ spectre_v2_enabled == SPECTRE_V2_EIBRS_RETPOLINE ||
+ spectre_v2_enabled == SPECTRE_V2_RETPOLINE)
spec_ctrl_disable_kernel_rrsba();
- if (boot_cpu_has(X86_BUG_BHI))
- bhi_select_mitigation();
-
- spectre_v2_enabled = mode;
- pr_info("%s\n", spectre_v2_strings[mode]);
-
- spectre_v2_select_rsb_mitigation(mode);
+ spectre_v2_select_rsb_mitigation(spectre_v2_enabled);
/*
* Retpoline protects the kernel, but doesn't protect firmware. IBRS
@@ -1989,28 +2458,26 @@ static void __init spectre_v2_select_mitigation(void)
* firmware calls only when IBRS / Enhanced / Automatic IBRS aren't
* otherwise enabled.
*
- * Use "mode" to check Enhanced IBRS instead of boot_cpu_has(), because
- * the user might select retpoline on the kernel command line and if
- * the CPU supports Enhanced IBRS, kernel might un-intentionally not
- * enable IBRS around firmware calls.
+ * Use "spectre_v2_enabled" to check Enhanced IBRS instead of
+ * boot_cpu_has(), because the user might select retpoline on the kernel
+ * command line and if the CPU supports Enhanced IBRS, kernel might
+ * un-intentionally not enable IBRS around firmware calls.
*/
if (boot_cpu_has_bug(X86_BUG_RETBLEED) &&
boot_cpu_has(X86_FEATURE_IBPB) &&
(boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||
boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)) {
- if (retbleed_cmd != RETBLEED_CMD_IBPB) {
+ if (retbleed_mitigation != RETBLEED_MITIGATION_IBPB) {
setup_force_cpu_cap(X86_FEATURE_USE_IBPB_FW);
pr_info("Enabling Speculation Barrier for firmware calls\n");
}
- } else if (boot_cpu_has(X86_FEATURE_IBRS) && !spectre_v2_in_ibrs_mode(mode)) {
+ } else if (boot_cpu_has(X86_FEATURE_IBRS) &&
+ !spectre_v2_in_ibrs_mode(spectre_v2_enabled)) {
setup_force_cpu_cap(X86_FEATURE_USE_IBRS_FW);
pr_info("Enabling Restricted Speculation for firmware calls\n");
}
-
- /* Set up IBPB and STIBP depending on the general spectre V2 command */
- spectre_v2_cmd = cmd;
}
static void update_stibp_msr(void * __unused)
@@ -2063,10 +2530,10 @@ static void update_mds_branch_idle(void)
return;
if (sched_smt_active()) {
- static_branch_enable(&mds_idle_clear);
+ static_branch_enable(&cpu_buf_idle_clear);
} else if (mmio_mitigation == MMIO_MITIGATION_OFF ||
(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) {
- static_branch_disable(&mds_idle_clear);
+ static_branch_disable(&cpu_buf_idle_clear);
}
}
@@ -2130,6 +2597,25 @@ void cpu_bugs_smt_update(void)
break;
}
+ switch (tsa_mitigation) {
+ case TSA_MITIGATION_USER_KERNEL:
+ case TSA_MITIGATION_VM:
+ case TSA_MITIGATION_AUTO:
+ case TSA_MITIGATION_FULL:
+ /*
+ * TSA-SQ can potentially lead to info leakage between
+ * SMT threads.
+ */
+ if (sched_smt_active())
+ static_branch_enable(&cpu_buf_idle_clear);
+ else
+ static_branch_disable(&cpu_buf_idle_clear);
+ break;
+ case TSA_MITIGATION_NONE:
+ case TSA_MITIGATION_UCODE_NEEDED:
+ break;
+ }
+
mutex_unlock(&spec_ctrl_mutex);
}
@@ -2199,19 +2685,18 @@ static enum ssb_mitigation_cmd __init ssb_parse_cmdline(void)
return cmd;
}
-static enum ssb_mitigation __init __ssb_select_mitigation(void)
+static void __init ssb_select_mitigation(void)
{
- enum ssb_mitigation mode = SPEC_STORE_BYPASS_NONE;
enum ssb_mitigation_cmd cmd;
if (!boot_cpu_has(X86_FEATURE_SSBD))
- return mode;
+ goto out;
cmd = ssb_parse_cmdline();
if (!boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS) &&
(cmd == SPEC_STORE_BYPASS_CMD_NONE ||
cmd == SPEC_STORE_BYPASS_CMD_AUTO))
- return mode;
+ return;
switch (cmd) {
case SPEC_STORE_BYPASS_CMD_SECCOMP:
@@ -2220,28 +2705,35 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
* enabled.
*/
if (IS_ENABLED(CONFIG_SECCOMP))
- mode = SPEC_STORE_BYPASS_SECCOMP;
+ ssb_mode = SPEC_STORE_BYPASS_SECCOMP;
else
- mode = SPEC_STORE_BYPASS_PRCTL;
+ ssb_mode = SPEC_STORE_BYPASS_PRCTL;
break;
case SPEC_STORE_BYPASS_CMD_ON:
- mode = SPEC_STORE_BYPASS_DISABLE;
+ ssb_mode = SPEC_STORE_BYPASS_DISABLE;
break;
case SPEC_STORE_BYPASS_CMD_AUTO:
case SPEC_STORE_BYPASS_CMD_PRCTL:
- mode = SPEC_STORE_BYPASS_PRCTL;
+ ssb_mode = SPEC_STORE_BYPASS_PRCTL;
break;
case SPEC_STORE_BYPASS_CMD_NONE:
break;
}
+out:
+ if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
+ pr_info("%s\n", ssb_strings[ssb_mode]);
+}
+
+static void __init ssb_apply_mitigation(void)
+{
/*
* We have three CPU feature flags that are in play here:
* - X86_BUG_SPEC_STORE_BYPASS - CPU is susceptible.
* - X86_FEATURE_SSBD - CPU is able to turn off speculative store bypass
* - X86_FEATURE_SPEC_STORE_BYPASS_DISABLE - engage the mitigation
*/
- if (mode == SPEC_STORE_BYPASS_DISABLE) {
+ if (ssb_mode == SPEC_STORE_BYPASS_DISABLE) {
setup_force_cpu_cap(X86_FEATURE_SPEC_STORE_BYPASS_DISABLE);
/*
* Intel uses the SPEC CTRL MSR Bit(2) for this, while AMD may
@@ -2255,16 +2747,6 @@ static enum ssb_mitigation __init __ssb_select_mitigation(void)
update_spec_ctrl(x86_spec_ctrl_base);
}
}
-
- return mode;
-}
-
-static void ssb_select_mitigation(void)
-{
- ssb_mode = __ssb_select_mitigation();
-
- if (boot_cpu_has_bug(X86_BUG_SPEC_STORE_BYPASS))
- pr_info("%s\n", ssb_strings[ssb_mode]);
}
#undef pr_fmt
@@ -2520,7 +3002,7 @@ EXPORT_SYMBOL_GPL(itlb_multihit_kvm_mitigation);
/* Default mitigation for L1TF-affected CPUs */
enum l1tf_mitigations l1tf_mitigation __ro_after_init =
- IS_ENABLED(CONFIG_MITIGATION_L1TF) ? L1TF_MITIGATION_FLUSH : L1TF_MITIGATION_OFF;
+ IS_ENABLED(CONFIG_MITIGATION_L1TF) ? L1TF_MITIGATION_AUTO : L1TF_MITIGATION_OFF;
#if IS_ENABLED(CONFIG_KVM_INTEL)
EXPORT_SYMBOL_GPL(l1tf_mitigation);
#endif
@@ -2568,15 +3050,31 @@ static void override_cache_bits(struct cpuinfo_x86 *c)
static void __init l1tf_select_mitigation(void)
{
- u64 half_pa;
+ if (!boot_cpu_has_bug(X86_BUG_L1TF)) {
+ l1tf_mitigation = L1TF_MITIGATION_OFF;
+ return;
+ }
- if (!boot_cpu_has_bug(X86_BUG_L1TF))
+ if (l1tf_mitigation != L1TF_MITIGATION_AUTO)
return;
- if (cpu_mitigations_off())
+ if (!should_mitigate_vuln(X86_BUG_L1TF)) {
l1tf_mitigation = L1TF_MITIGATION_OFF;
- else if (cpu_mitigations_auto_nosmt())
+ return;
+ }
+
+ if (smt_mitigations == SMT_MITIGATIONS_ON)
l1tf_mitigation = L1TF_MITIGATION_FLUSH_NOSMT;
+ else
+ l1tf_mitigation = L1TF_MITIGATION_FLUSH;
+}
+
+static void __init l1tf_apply_mitigation(void)
+{
+ u64 half_pa;
+
+ if (!boot_cpu_has_bug(X86_BUG_L1TF))
+ return;
override_cache_bits(&boot_cpu_data);
@@ -2584,6 +3082,7 @@ static void __init l1tf_select_mitigation(void)
case L1TF_MITIGATION_OFF:
case L1TF_MITIGATION_FLUSH_NOWARN:
case L1TF_MITIGATION_FLUSH:
+ case L1TF_MITIGATION_AUTO:
break;
case L1TF_MITIGATION_FLUSH_NOSMT:
case L1TF_MITIGATION_FULL:
@@ -2641,54 +3140,33 @@ early_param("l1tf", l1tf_cmdline);
#undef pr_fmt
#define pr_fmt(fmt) "Speculative Return Stack Overflow: " fmt
-enum srso_mitigation {
- SRSO_MITIGATION_NONE,
- SRSO_MITIGATION_UCODE_NEEDED,
- SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED,
- SRSO_MITIGATION_MICROCODE,
- SRSO_MITIGATION_SAFE_RET,
- SRSO_MITIGATION_IBPB,
- SRSO_MITIGATION_IBPB_ON_VMEXIT,
- SRSO_MITIGATION_BP_SPEC_REDUCE,
-};
-
-enum srso_mitigation_cmd {
- SRSO_CMD_OFF,
- SRSO_CMD_MICROCODE,
- SRSO_CMD_SAFE_RET,
- SRSO_CMD_IBPB,
- SRSO_CMD_IBPB_ON_VMEXIT,
-};
-
static const char * const srso_strings[] = {
[SRSO_MITIGATION_NONE] = "Vulnerable",
[SRSO_MITIGATION_UCODE_NEEDED] = "Vulnerable: No microcode",
[SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED] = "Vulnerable: Safe RET, no microcode",
[SRSO_MITIGATION_MICROCODE] = "Vulnerable: Microcode, no safe RET",
+ [SRSO_MITIGATION_NOSMT] = "Mitigation: SMT disabled",
[SRSO_MITIGATION_SAFE_RET] = "Mitigation: Safe RET",
[SRSO_MITIGATION_IBPB] = "Mitigation: IBPB",
[SRSO_MITIGATION_IBPB_ON_VMEXIT] = "Mitigation: IBPB on VMEXIT only",
[SRSO_MITIGATION_BP_SPEC_REDUCE] = "Mitigation: Reduced Speculation"
};
-static enum srso_mitigation srso_mitigation __ro_after_init = SRSO_MITIGATION_NONE;
-static enum srso_mitigation_cmd srso_cmd __ro_after_init = SRSO_CMD_SAFE_RET;
-
static int __init srso_parse_cmdline(char *str)
{
if (!str)
return -EINVAL;
if (!strcmp(str, "off"))
- srso_cmd = SRSO_CMD_OFF;
+ srso_mitigation = SRSO_MITIGATION_NONE;
else if (!strcmp(str, "microcode"))
- srso_cmd = SRSO_CMD_MICROCODE;
+ srso_mitigation = SRSO_MITIGATION_MICROCODE;
else if (!strcmp(str, "safe-ret"))
- srso_cmd = SRSO_CMD_SAFE_RET;
+ srso_mitigation = SRSO_MITIGATION_SAFE_RET;
else if (!strcmp(str, "ibpb"))
- srso_cmd = SRSO_CMD_IBPB;
+ srso_mitigation = SRSO_MITIGATION_IBPB;
else if (!strcmp(str, "ibpb-vmexit"))
- srso_cmd = SRSO_CMD_IBPB_ON_VMEXIT;
+ srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
else
pr_err("Ignoring unknown SRSO option (%s).", str);
@@ -2700,132 +3178,87 @@ early_param("spec_rstack_overflow", srso_parse_cmdline);
static void __init srso_select_mitigation(void)
{
- bool has_microcode = boot_cpu_has(X86_FEATURE_IBPB_BRTYPE);
-
- if (!boot_cpu_has_bug(X86_BUG_SRSO) ||
- cpu_mitigations_off() ||
- srso_cmd == SRSO_CMD_OFF) {
- if (boot_cpu_has(X86_FEATURE_SBPB))
- x86_pred_cmd = PRED_CMD_SBPB;
- goto out;
+ if (!boot_cpu_has_bug(X86_BUG_SRSO)) {
+ srso_mitigation = SRSO_MITIGATION_NONE;
+ return;
}
- if (has_microcode) {
- /*
- * Zen1/2 with SMT off aren't vulnerable after the right
- * IBPB microcode has been applied.
- *
- * Zen1/2 don't have SBPB, no need to try to enable it here.
- */
- if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) {
- setup_force_cpu_cap(X86_FEATURE_SRSO_NO);
- goto out;
+ if (srso_mitigation == SRSO_MITIGATION_AUTO) {
+ if (should_mitigate_vuln(X86_BUG_SRSO)) {
+ srso_mitigation = SRSO_MITIGATION_SAFE_RET;
+ } else {
+ srso_mitigation = SRSO_MITIGATION_NONE;
+ return;
}
+ }
- if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB) {
- srso_mitigation = SRSO_MITIGATION_IBPB;
- goto out;
- }
- } else {
+ /* Zen1/2 with SMT off aren't vulnerable to SRSO. */
+ if (boot_cpu_data.x86 < 0x19 && !cpu_smt_possible()) {
+ srso_mitigation = SRSO_MITIGATION_NOSMT;
+ return;
+ }
+
+ if (!boot_cpu_has(X86_FEATURE_IBPB_BRTYPE)) {
pr_warn("IBPB-extending microcode not applied!\n");
pr_warn(SRSO_NOTICE);
- /* may be overwritten by SRSO_CMD_SAFE_RET below */
- srso_mitigation = SRSO_MITIGATION_UCODE_NEEDED;
+ /*
+ * Safe-RET provides partial mitigation without microcode, but
+ * other mitigations require microcode to provide any
+ * mitigations.
+ */
+ if (srso_mitigation == SRSO_MITIGATION_SAFE_RET)
+ srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED;
+ else
+ srso_mitigation = SRSO_MITIGATION_UCODE_NEEDED;
}
- switch (srso_cmd) {
- case SRSO_CMD_MICROCODE:
- if (has_microcode) {
- srso_mitigation = SRSO_MITIGATION_MICROCODE;
- pr_warn(SRSO_NOTICE);
- }
- break;
-
- case SRSO_CMD_SAFE_RET:
- if (boot_cpu_has(X86_FEATURE_SRSO_USER_KERNEL_NO))
+ switch (srso_mitigation) {
+ case SRSO_MITIGATION_SAFE_RET:
+ case SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED:
+ if (boot_cpu_has(X86_FEATURE_SRSO_USER_KERNEL_NO)) {
+ srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
goto ibpb_on_vmexit;
-
- if (IS_ENABLED(CONFIG_MITIGATION_SRSO)) {
- /*
- * Enable the return thunk for generated code
- * like ftrace, static_call, etc.
- */
- setup_force_cpu_cap(X86_FEATURE_RETHUNK);
- setup_force_cpu_cap(X86_FEATURE_UNRET);
-
- if (boot_cpu_data.x86 == 0x19) {
- setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS);
- set_return_thunk(srso_alias_return_thunk);
- } else {
- setup_force_cpu_cap(X86_FEATURE_SRSO);
- set_return_thunk(srso_return_thunk);
- }
- if (has_microcode)
- srso_mitigation = SRSO_MITIGATION_SAFE_RET;
- else
- srso_mitigation = SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED;
- } else {
- pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n");
}
- break;
- case SRSO_CMD_IBPB:
- if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
- if (has_microcode) {
- setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
- setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
- srso_mitigation = SRSO_MITIGATION_IBPB;
-
- /*
- * IBPB on entry already obviates the need for
- * software-based untraining so clear those in case some
- * other mitigation like Retbleed has selected them.
- */
- setup_clear_cpu_cap(X86_FEATURE_UNRET);
- setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
-
- /*
- * There is no need for RSB filling: write_ibpb() ensures
- * all predictions, including the RSB, are invalidated,
- * regardless of IBPB implementation.
- */
- setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
- }
- } else {
- pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
+ if (!IS_ENABLED(CONFIG_MITIGATION_SRSO)) {
+ pr_err("WARNING: kernel not compiled with MITIGATION_SRSO.\n");
+ srso_mitigation = SRSO_MITIGATION_NONE;
}
break;
-
ibpb_on_vmexit:
- case SRSO_CMD_IBPB_ON_VMEXIT:
+ case SRSO_MITIGATION_IBPB_ON_VMEXIT:
if (boot_cpu_has(X86_FEATURE_SRSO_BP_SPEC_REDUCE)) {
pr_notice("Reducing speculation to address VM/HV SRSO attack vector.\n");
srso_mitigation = SRSO_MITIGATION_BP_SPEC_REDUCE;
break;
}
-
- if (IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
- if (has_microcode) {
- setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
- srso_mitigation = SRSO_MITIGATION_IBPB_ON_VMEXIT;
-
- /*
- * There is no need for RSB filling: write_ibpb() ensures
- * all predictions, including the RSB, are invalidated,
- * regardless of IBPB implementation.
- */
- setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
- }
- } else {
+ fallthrough;
+ case SRSO_MITIGATION_IBPB:
+ if (!IS_ENABLED(CONFIG_MITIGATION_IBPB_ENTRY)) {
pr_err("WARNING: kernel not compiled with MITIGATION_IBPB_ENTRY.\n");
+ srso_mitigation = SRSO_MITIGATION_NONE;
}
break;
default:
break;
}
+}
-out:
+static void __init srso_update_mitigation(void)
+{
+ /* If retbleed is using IBPB, that works for SRSO as well */
+ if (retbleed_mitigation == RETBLEED_MITIGATION_IBPB &&
+ boot_cpu_has(X86_FEATURE_IBPB_BRTYPE))
+ srso_mitigation = SRSO_MITIGATION_IBPB;
+
+ if (boot_cpu_has_bug(X86_BUG_SRSO) &&
+ !cpu_mitigations_off())
+ pr_info("%s\n", srso_strings[srso_mitigation]);
+}
+
+static void __init srso_apply_mitigation(void)
+{
/*
* Clear the feature flag if this mitigation is not selected as that
* feature flag controls the BpSpecReduce MSR bit toggling in KVM.
@@ -2833,8 +3266,52 @@ out:
if (srso_mitigation != SRSO_MITIGATION_BP_SPEC_REDUCE)
setup_clear_cpu_cap(X86_FEATURE_SRSO_BP_SPEC_REDUCE);
- if (srso_mitigation != SRSO_MITIGATION_NONE)
- pr_info("%s\n", srso_strings[srso_mitigation]);
+ if (srso_mitigation == SRSO_MITIGATION_NONE) {
+ if (boot_cpu_has(X86_FEATURE_SBPB))
+ x86_pred_cmd = PRED_CMD_SBPB;
+ return;
+ }
+
+ switch (srso_mitigation) {
+ case SRSO_MITIGATION_SAFE_RET:
+ case SRSO_MITIGATION_SAFE_RET_UCODE_NEEDED:
+ /*
+ * Enable the return thunk for generated code
+ * like ftrace, static_call, etc.
+ */
+ setup_force_cpu_cap(X86_FEATURE_RETHUNK);
+ setup_force_cpu_cap(X86_FEATURE_UNRET);
+
+ if (boot_cpu_data.x86 == 0x19) {
+ setup_force_cpu_cap(X86_FEATURE_SRSO_ALIAS);
+ set_return_thunk(srso_alias_return_thunk);
+ } else {
+ setup_force_cpu_cap(X86_FEATURE_SRSO);
+ set_return_thunk(srso_return_thunk);
+ }
+ break;
+ case SRSO_MITIGATION_IBPB:
+ setup_force_cpu_cap(X86_FEATURE_ENTRY_IBPB);
+ /*
+ * IBPB on entry already obviates the need for
+ * software-based untraining so clear those in case some
+ * other mitigation like Retbleed has selected them.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_UNRET);
+ setup_clear_cpu_cap(X86_FEATURE_RETHUNK);
+ fallthrough;
+ case SRSO_MITIGATION_IBPB_ON_VMEXIT:
+ setup_force_cpu_cap(X86_FEATURE_IBPB_ON_VMEXIT);
+ /*
+ * There is no need for RSB filling: entry_ibpb() ensures
+ * all predictions, including the RSB, are invalidated,
+ * regardless of IBPB implementation.
+ */
+ setup_clear_cpu_cap(X86_FEATURE_RSB_VMEXIT);
+ break;
+ default:
+ break;
+ }
}
#undef pr_fmt
@@ -2929,9 +3406,6 @@ static ssize_t tsx_async_abort_show_state(char *buf)
static ssize_t mmio_stale_data_show_state(char *buf)
{
- if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
- return sysfs_emit(buf, "Unknown: No mitigations\n");
-
if (mmio_mitigation == MMIO_MITIGATION_OFF)
return sysfs_emit(buf, "%s\n", mmio_strings[mmio_mitigation]);
@@ -2949,6 +3423,14 @@ static ssize_t rfds_show_state(char *buf)
return sysfs_emit(buf, "%s\n", rfds_strings[rfds_mitigation]);
}
+static ssize_t old_microcode_show_state(char *buf)
+{
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ return sysfs_emit(buf, "Unknown: running under hypervisor");
+
+ return sysfs_emit(buf, "Vulnerable\n");
+}
+
static ssize_t its_show_state(char *buf)
{
return sysfs_emit(buf, "%s\n", its_strings[its_mitigation]);
@@ -3012,7 +3494,7 @@ static const char *spectre_bhi_state(void)
!boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) &&
rrsba_disabled)
return "; BHI: Retpoline";
- else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT))
+ else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_VMEXIT))
return "; BHI: Vulnerable, KVM: SW loop";
return "; BHI: Vulnerable";
@@ -3067,9 +3549,6 @@ static ssize_t retbleed_show_state(char *buf)
static ssize_t srso_show_state(char *buf)
{
- if (boot_cpu_has(X86_FEATURE_SRSO_NO))
- return sysfs_emit(buf, "Mitigation: SMT disabled\n");
-
return sysfs_emit(buf, "%s\n", srso_strings[srso_mitigation]);
}
@@ -3078,6 +3557,11 @@ static ssize_t gds_show_state(char *buf)
return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]);
}
+static ssize_t tsa_show_state(char *buf)
+{
+ return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]);
+}
+
static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
char *buf, unsigned int bug)
{
@@ -3121,7 +3605,6 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
return srbds_show_state(buf);
case X86_BUG_MMIO_STALE_DATA:
- case X86_BUG_MMIO_UNKNOWN:
return mmio_stale_data_show_state(buf);
case X86_BUG_RETBLEED:
@@ -3136,9 +3619,15 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
case X86_BUG_RFDS:
return rfds_show_state(buf);
+ case X86_BUG_OLD_MICROCODE:
+ return old_microcode_show_state(buf);
+
case X86_BUG_ITS:
return its_show_state(buf);
+ case X86_BUG_TSA:
+ return tsa_show_state(buf);
+
default:
break;
}
@@ -3193,10 +3682,7 @@ ssize_t cpu_show_srbds(struct device *dev, struct device_attribute *attr, char *
ssize_t cpu_show_mmio_stale_data(struct device *dev, struct device_attribute *attr, char *buf)
{
- if (boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN))
- return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_UNKNOWN);
- else
- return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
+ return cpu_show_common(dev, attr, buf, X86_BUG_MMIO_STALE_DATA);
}
ssize_t cpu_show_retbleed(struct device *dev, struct device_attribute *attr, char *buf)
@@ -3219,10 +3705,20 @@ ssize_t cpu_show_reg_file_data_sampling(struct device *dev, struct device_attrib
return cpu_show_common(dev, attr, buf, X86_BUG_RFDS);
}
+ssize_t cpu_show_old_microcode(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_OLD_MICROCODE);
+}
+
ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_attribute *attr, char *buf)
{
return cpu_show_common(dev, attr, buf, X86_BUG_ITS);
}
+
+ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf)
+{
+ return cpu_show_common(dev, attr, buf, X86_BUG_TSA);
+}
#endif
void __warn_thunk(void)
diff --git a/arch/x86/kernel/cpu/bus_lock.c b/arch/x86/kernel/cpu/bus_lock.c
index 237faf7e700c..981f8b1f0792 100644
--- a/arch/x86/kernel/cpu/bus_lock.c
+++ b/arch/x86/kernel/cpu/bus_lock.c
@@ -10,6 +10,7 @@
#include <asm/cmdline.h>
#include <asm/traps.h>
#include <asm/cpu.h>
+#include <asm/msr.h>
enum split_lock_detect_state {
sld_off = 0,
@@ -95,15 +96,15 @@ static bool split_lock_verify_msr(bool on)
{
u64 ctrl, tmp;
- if (rdmsrl_safe(MSR_TEST_CTRL, &ctrl))
+ if (rdmsrq_safe(MSR_TEST_CTRL, &ctrl))
return false;
if (on)
ctrl |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
else
ctrl &= ~MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
- if (wrmsrl_safe(MSR_TEST_CTRL, ctrl))
+ if (wrmsrq_safe(MSR_TEST_CTRL, ctrl))
return false;
- rdmsrl(MSR_TEST_CTRL, tmp);
+ rdmsrq(MSR_TEST_CTRL, tmp);
return ctrl == tmp;
}
@@ -137,7 +138,7 @@ static void __init __split_lock_setup(void)
return;
}
- rdmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache);
+ rdmsrq(MSR_TEST_CTRL, msr_test_ctrl_cache);
if (!split_lock_verify_msr(true)) {
pr_info("MSR access failed: Disabled\n");
@@ -145,7 +146,7 @@ static void __init __split_lock_setup(void)
}
/* Restore the MSR to its cached value. */
- wrmsrl(MSR_TEST_CTRL, msr_test_ctrl_cache);
+ wrmsrq(MSR_TEST_CTRL, msr_test_ctrl_cache);
setup_force_cpu_cap(X86_FEATURE_SPLIT_LOCK_DETECT);
}
@@ -162,7 +163,7 @@ static void sld_update_msr(bool on)
if (on)
test_ctrl_val |= MSR_TEST_CTRL_SPLIT_LOCK_DETECT;
- wrmsrl(MSR_TEST_CTRL, test_ctrl_val);
+ wrmsrq(MSR_TEST_CTRL, test_ctrl_val);
}
void split_lock_init(void)
@@ -297,7 +298,7 @@ void bus_lock_init(void)
if (!boot_cpu_has(X86_FEATURE_BUS_LOCK_DETECT))
return;
- rdmsrl(MSR_IA32_DEBUGCTLMSR, val);
+ rdmsrq(MSR_IA32_DEBUGCTLMSR, val);
if ((boot_cpu_has(X86_FEATURE_SPLIT_LOCK_DETECT) &&
(sld_state == sld_warn || sld_state == sld_fatal)) ||
@@ -311,7 +312,7 @@ void bus_lock_init(void)
val |= DEBUGCTLMSR_BUS_LOCK_DETECT;
}
- wrmsrl(MSR_IA32_DEBUGCTLMSR, val);
+ wrmsrq(MSR_IA32_DEBUGCTLMSR, val);
}
bool handle_user_split_lock(struct pt_regs *regs, long error_code)
@@ -375,7 +376,7 @@ static void __init split_lock_setup(struct cpuinfo_x86 *c)
* MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT is. All CPUs that set
* it have split lock detection.
*/
- rdmsrl(MSR_IA32_CORE_CAPS, ia32_core_caps);
+ rdmsrq(MSR_IA32_CORE_CAPS, ia32_core_caps);
if (ia32_core_caps & MSR_IA32_CORE_CAPS_SPLIT_LOCK_DETECT)
goto supported;
diff --git a/arch/x86/kernel/cpu/cacheinfo.c b/arch/x86/kernel/cpu/cacheinfo.c
index b3a520959b51..adfa7e8bb865 100644
--- a/arch/x86/kernel/cpu/cacheinfo.c
+++ b/arch/x86/kernel/cpu/cacheinfo.c
@@ -1,35 +1,28 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * Routines to identify caches on Intel CPU.
+ * x86 CPU caches detection and configuration
*
- * Changes:
- * Venkatesh Pallipadi : Adding cache identification through cpuid(4)
- * Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure.
- * Andi Kleen / Andreas Herrmann : CPUID4 emulation on AMD.
+ * Previous changes
+ * - Venkatesh Pallipadi: Cache identification through CPUID(0x4)
+ * - Ashok Raj <ashok.raj@intel.com>: Work with CPU hotplug infrastructure
+ * - Andi Kleen / Andreas Herrmann: CPUID(0x4) emulation on AMD
*/
#include <linux/cacheinfo.h>
-#include <linux/capability.h>
#include <linux/cpu.h>
#include <linux/cpuhotplug.h>
-#include <linux/pci.h>
#include <linux/stop_machine.h>
-#include <linux/sysfs.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
#include <asm/cacheinfo.h>
#include <asm/cpufeature.h>
+#include <asm/cpuid/api.h>
#include <asm/mtrr.h>
#include <asm/smp.h>
#include <asm/tlbflush.h>
#include "cpu.h"
-#define LVL_1_INST 1
-#define LVL_1_DATA 2
-#define LVL_2 3
-#define LVL_3 4
-
/* Shared last level cache maps */
DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
@@ -41,208 +34,127 @@ static cpumask_var_t cpu_cacheinfo_mask;
/* Kernel controls MTRR and/or PAT MSRs. */
unsigned int memory_caching_control __ro_after_init;
-struct _cache_table {
- unsigned char descriptor;
- char cache_type;
- short size;
-};
-
-#define MB(x) ((x) * 1024)
-
-/* All the cache descriptor types we care about (no TLB or
- trace cache entries) */
-
-static const struct _cache_table cache_table[] =
-{
- { 0x06, LVL_1_INST, 8 }, /* 4-way set assoc, 32 byte line size */
- { 0x08, LVL_1_INST, 16 }, /* 4-way set assoc, 32 byte line size */
- { 0x09, LVL_1_INST, 32 }, /* 4-way set assoc, 64 byte line size */
- { 0x0a, LVL_1_DATA, 8 }, /* 2 way set assoc, 32 byte line size */
- { 0x0c, LVL_1_DATA, 16 }, /* 4-way set assoc, 32 byte line size */
- { 0x0d, LVL_1_DATA, 16 }, /* 4-way set assoc, 64 byte line size */
- { 0x0e, LVL_1_DATA, 24 }, /* 6-way set assoc, 64 byte line size */
- { 0x21, LVL_2, 256 }, /* 8-way set assoc, 64 byte line size */
- { 0x22, LVL_3, 512 }, /* 4-way set assoc, sectored cache, 64 byte line size */
- { 0x23, LVL_3, MB(1) }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x25, LVL_3, MB(2) }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x29, LVL_3, MB(4) }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x2c, LVL_1_DATA, 32 }, /* 8-way set assoc, 64 byte line size */
- { 0x30, LVL_1_INST, 32 }, /* 8-way set assoc, 64 byte line size */
- { 0x39, LVL_2, 128 }, /* 4-way set assoc, sectored cache, 64 byte line size */
- { 0x3a, LVL_2, 192 }, /* 6-way set assoc, sectored cache, 64 byte line size */
- { 0x3b, LVL_2, 128 }, /* 2-way set assoc, sectored cache, 64 byte line size */
- { 0x3c, LVL_2, 256 }, /* 4-way set assoc, sectored cache, 64 byte line size */
- { 0x3d, LVL_2, 384 }, /* 6-way set assoc, sectored cache, 64 byte line size */
- { 0x3e, LVL_2, 512 }, /* 4-way set assoc, sectored cache, 64 byte line size */
- { 0x3f, LVL_2, 256 }, /* 2-way set assoc, 64 byte line size */
- { 0x41, LVL_2, 128 }, /* 4-way set assoc, 32 byte line size */
- { 0x42, LVL_2, 256 }, /* 4-way set assoc, 32 byte line size */
- { 0x43, LVL_2, 512 }, /* 4-way set assoc, 32 byte line size */
- { 0x44, LVL_2, MB(1) }, /* 4-way set assoc, 32 byte line size */
- { 0x45, LVL_2, MB(2) }, /* 4-way set assoc, 32 byte line size */
- { 0x46, LVL_3, MB(4) }, /* 4-way set assoc, 64 byte line size */
- { 0x47, LVL_3, MB(8) }, /* 8-way set assoc, 64 byte line size */
- { 0x48, LVL_2, MB(3) }, /* 12-way set assoc, 64 byte line size */
- { 0x49, LVL_3, MB(4) }, /* 16-way set assoc, 64 byte line size */
- { 0x4a, LVL_3, MB(6) }, /* 12-way set assoc, 64 byte line size */
- { 0x4b, LVL_3, MB(8) }, /* 16-way set assoc, 64 byte line size */
- { 0x4c, LVL_3, MB(12) }, /* 12-way set assoc, 64 byte line size */
- { 0x4d, LVL_3, MB(16) }, /* 16-way set assoc, 64 byte line size */
- { 0x4e, LVL_2, MB(6) }, /* 24-way set assoc, 64 byte line size */
- { 0x60, LVL_1_DATA, 16 }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x66, LVL_1_DATA, 8 }, /* 4-way set assoc, sectored cache, 64 byte line size */
- { 0x67, LVL_1_DATA, 16 }, /* 4-way set assoc, sectored cache, 64 byte line size */
- { 0x68, LVL_1_DATA, 32 }, /* 4-way set assoc, sectored cache, 64 byte line size */
- { 0x78, LVL_2, MB(1) }, /* 4-way set assoc, 64 byte line size */
- { 0x79, LVL_2, 128 }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x7a, LVL_2, 256 }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x7b, LVL_2, 512 }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x7c, LVL_2, MB(1) }, /* 8-way set assoc, sectored cache, 64 byte line size */
- { 0x7d, LVL_2, MB(2) }, /* 8-way set assoc, 64 byte line size */
- { 0x7f, LVL_2, 512 }, /* 2-way set assoc, 64 byte line size */
- { 0x80, LVL_2, 512 }, /* 8-way set assoc, 64 byte line size */
- { 0x82, LVL_2, 256 }, /* 8-way set assoc, 32 byte line size */
- { 0x83, LVL_2, 512 }, /* 8-way set assoc, 32 byte line size */
- { 0x84, LVL_2, MB(1) }, /* 8-way set assoc, 32 byte line size */
- { 0x85, LVL_2, MB(2) }, /* 8-way set assoc, 32 byte line size */
- { 0x86, LVL_2, 512 }, /* 4-way set assoc, 64 byte line size */
- { 0x87, LVL_2, MB(1) }, /* 8-way set assoc, 64 byte line size */
- { 0xd0, LVL_3, 512 }, /* 4-way set assoc, 64 byte line size */
- { 0xd1, LVL_3, MB(1) }, /* 4-way set assoc, 64 byte line size */
- { 0xd2, LVL_3, MB(2) }, /* 4-way set assoc, 64 byte line size */
- { 0xd6, LVL_3, MB(1) }, /* 8-way set assoc, 64 byte line size */
- { 0xd7, LVL_3, MB(2) }, /* 8-way set assoc, 64 byte line size */
- { 0xd8, LVL_3, MB(4) }, /* 12-way set assoc, 64 byte line size */
- { 0xdc, LVL_3, MB(2) }, /* 12-way set assoc, 64 byte line size */
- { 0xdd, LVL_3, MB(4) }, /* 12-way set assoc, 64 byte line size */
- { 0xde, LVL_3, MB(8) }, /* 12-way set assoc, 64 byte line size */
- { 0xe2, LVL_3, MB(2) }, /* 16-way set assoc, 64 byte line size */
- { 0xe3, LVL_3, MB(4) }, /* 16-way set assoc, 64 byte line size */
- { 0xe4, LVL_3, MB(8) }, /* 16-way set assoc, 64 byte line size */
- { 0xea, LVL_3, MB(12) }, /* 24-way set assoc, 64 byte line size */
- { 0xeb, LVL_3, MB(18) }, /* 24-way set assoc, 64 byte line size */
- { 0xec, LVL_3, MB(24) }, /* 24-way set assoc, 64 byte line size */
- { 0x00, 0, 0}
-};
-
-
enum _cache_type {
- CTYPE_NULL = 0,
- CTYPE_DATA = 1,
- CTYPE_INST = 2,
- CTYPE_UNIFIED = 3
+ CTYPE_NULL = 0,
+ CTYPE_DATA = 1,
+ CTYPE_INST = 2,
+ CTYPE_UNIFIED = 3
};
union _cpuid4_leaf_eax {
struct {
- enum _cache_type type:5;
- unsigned int level:3;
- unsigned int is_self_initializing:1;
- unsigned int is_fully_associative:1;
- unsigned int reserved:4;
- unsigned int num_threads_sharing:12;
- unsigned int num_cores_on_die:6;
+ enum _cache_type type :5;
+ unsigned int level :3;
+ unsigned int is_self_initializing :1;
+ unsigned int is_fully_associative :1;
+ unsigned int reserved :4;
+ unsigned int num_threads_sharing :12;
+ unsigned int num_cores_on_die :6;
} split;
u32 full;
};
union _cpuid4_leaf_ebx {
struct {
- unsigned int coherency_line_size:12;
- unsigned int physical_line_partition:10;
- unsigned int ways_of_associativity:10;
+ unsigned int coherency_line_size :12;
+ unsigned int physical_line_partition :10;
+ unsigned int ways_of_associativity :10;
} split;
u32 full;
};
union _cpuid4_leaf_ecx {
struct {
- unsigned int number_of_sets:32;
+ unsigned int number_of_sets :32;
} split;
u32 full;
};
-struct _cpuid4_info_regs {
+struct _cpuid4_info {
union _cpuid4_leaf_eax eax;
union _cpuid4_leaf_ebx ebx;
union _cpuid4_leaf_ecx ecx;
unsigned int id;
unsigned long size;
- struct amd_northbridge *nb;
};
-/* AMD doesn't have CPUID4. Emulate it here to report the same
- information to the user. This makes some assumptions about the machine:
- L2 not shared, no SMT etc. that is currently true on AMD CPUs.
+/* Map CPUID(0x4) EAX.cache_type to <linux/cacheinfo.h> types */
+static const enum cache_type cache_type_map[] = {
+ [CTYPE_NULL] = CACHE_TYPE_NOCACHE,
+ [CTYPE_DATA] = CACHE_TYPE_DATA,
+ [CTYPE_INST] = CACHE_TYPE_INST,
+ [CTYPE_UNIFIED] = CACHE_TYPE_UNIFIED,
+};
+
+/*
+ * Fallback AMD CPUID(0x4) emulation
+ * AMD CPUs with TOPOEXT can just use CPUID(0x8000001d)
+ *
+ * @AMD_L2_L3_INVALID_ASSOC: cache info for the respective L2/L3 cache should
+ * be determined from CPUID(0x8000001d) instead of CPUID(0x80000006).
+ */
+
+#define AMD_CPUID4_FULLY_ASSOCIATIVE 0xffff
+#define AMD_L2_L3_INVALID_ASSOC 0x9
- In theory the TLBs could be reported as fake type (they are in "dummy").
- Maybe later */
union l1_cache {
struct {
- unsigned line_size:8;
- unsigned lines_per_tag:8;
- unsigned assoc:8;
- unsigned size_in_kb:8;
+ unsigned line_size :8;
+ unsigned lines_per_tag :8;
+ unsigned assoc :8;
+ unsigned size_in_kb :8;
};
- unsigned val;
+ unsigned int val;
};
union l2_cache {
struct {
- unsigned line_size:8;
- unsigned lines_per_tag:4;
- unsigned assoc:4;
- unsigned size_in_kb:16;
+ unsigned line_size :8;
+ unsigned lines_per_tag :4;
+ unsigned assoc :4;
+ unsigned size_in_kb :16;
};
- unsigned val;
+ unsigned int val;
};
union l3_cache {
struct {
- unsigned line_size:8;
- unsigned lines_per_tag:4;
- unsigned assoc:4;
- unsigned res:2;
- unsigned size_encoded:14;
+ unsigned line_size :8;
+ unsigned lines_per_tag :4;
+ unsigned assoc :4;
+ unsigned res :2;
+ unsigned size_encoded :14;
};
- unsigned val;
+ unsigned int val;
};
+/* L2/L3 associativity mapping */
static const unsigned short assocs[] = {
- [1] = 1,
- [2] = 2,
- [4] = 4,
- [6] = 8,
- [8] = 16,
- [0xa] = 32,
- [0xb] = 48,
- [0xc] = 64,
- [0xd] = 96,
- [0xe] = 128,
- [0xf] = 0xffff /* fully associative - no way to show this currently */
+ [1] = 1,
+ [2] = 2,
+ [3] = 3,
+ [4] = 4,
+ [5] = 6,
+ [6] = 8,
+ [8] = 16,
+ [0xa] = 32,
+ [0xb] = 48,
+ [0xc] = 64,
+ [0xd] = 96,
+ [0xe] = 128,
+ [0xf] = AMD_CPUID4_FULLY_ASSOCIATIVE
};
static const unsigned char levels[] = { 1, 1, 2, 3 };
-static const unsigned char types[] = { 1, 2, 3, 3 };
+static const unsigned char types[] = { 1, 2, 3, 3 };
-static const enum cache_type cache_type_map[] = {
- [CTYPE_NULL] = CACHE_TYPE_NOCACHE,
- [CTYPE_DATA] = CACHE_TYPE_DATA,
- [CTYPE_INST] = CACHE_TYPE_INST,
- [CTYPE_UNIFIED] = CACHE_TYPE_UNIFIED,
-};
-
-static void
-amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
- union _cpuid4_leaf_ebx *ebx,
- union _cpuid4_leaf_ecx *ecx)
+static void legacy_amd_cpuid4(int index, union _cpuid4_leaf_eax *eax,
+ union _cpuid4_leaf_ebx *ebx, union _cpuid4_leaf_ecx *ecx)
{
- unsigned dummy;
- unsigned line_size, lines_per_tag, assoc, size_in_kb;
- union l1_cache l1i, l1d;
+ unsigned int dummy, line_size, lines_per_tag, assoc, size_in_kb;
+ union l1_cache l1i, l1d, *l1;
union l2_cache l2;
union l3_cache l3;
- union l1_cache *l1 = &l1d;
eax->full = 0;
ebx->full = 0;
@@ -251,430 +163,155 @@ amd_cpuid4(int leaf, union _cpuid4_leaf_eax *eax,
cpuid(0x80000005, &dummy, &dummy, &l1d.val, &l1i.val);
cpuid(0x80000006, &dummy, &dummy, &l2.val, &l3.val);
- switch (leaf) {
+ l1 = &l1d;
+ switch (index) {
case 1:
l1 = &l1i;
fallthrough;
case 0:
if (!l1->val)
return;
- assoc = assocs[l1->assoc];
- line_size = l1->line_size;
- lines_per_tag = l1->lines_per_tag;
- size_in_kb = l1->size_in_kb;
+
+ assoc = (l1->assoc == 0xff) ? AMD_CPUID4_FULLY_ASSOCIATIVE : l1->assoc;
+ line_size = l1->line_size;
+ lines_per_tag = l1->lines_per_tag;
+ size_in_kb = l1->size_in_kb;
break;
case 2:
- if (!l2.val)
+ if (!l2.assoc || l2.assoc == AMD_L2_L3_INVALID_ASSOC)
return;
- assoc = assocs[l2.assoc];
- line_size = l2.line_size;
- lines_per_tag = l2.lines_per_tag;
- /* cpu_data has errata corrections for K7 applied */
- size_in_kb = __this_cpu_read(cpu_info.x86_cache_size);
+
+ /* Use x86_cache_size as it might have K7 errata fixes */
+ assoc = assocs[l2.assoc];
+ line_size = l2.line_size;
+ lines_per_tag = l2.lines_per_tag;
+ size_in_kb = __this_cpu_read(cpu_info.x86_cache_size);
break;
case 3:
- if (!l3.val)
+ if (!l3.assoc || l3.assoc == AMD_L2_L3_INVALID_ASSOC)
return;
- assoc = assocs[l3.assoc];
- line_size = l3.line_size;
- lines_per_tag = l3.lines_per_tag;
- size_in_kb = l3.size_encoded * 512;
+
+ assoc = assocs[l3.assoc];
+ line_size = l3.line_size;
+ lines_per_tag = l3.lines_per_tag;
+ size_in_kb = l3.size_encoded * 512;
if (boot_cpu_has(X86_FEATURE_AMD_DCM)) {
- size_in_kb = size_in_kb >> 1;
- assoc = assoc >> 1;
+ size_in_kb = size_in_kb >> 1;
+ assoc = assoc >> 1;
}
break;
default:
return;
}
- eax->split.is_self_initializing = 1;
- eax->split.type = types[leaf];
- eax->split.level = levels[leaf];
- eax->split.num_threads_sharing = 0;
- eax->split.num_cores_on_die = topology_num_cores_per_package();
+ eax->split.is_self_initializing = 1;
+ eax->split.type = types[index];
+ eax->split.level = levels[index];
+ eax->split.num_threads_sharing = 0;
+ eax->split.num_cores_on_die = topology_num_cores_per_package();
-
- if (assoc == 0xffff)
+ if (assoc == AMD_CPUID4_FULLY_ASSOCIATIVE)
eax->split.is_fully_associative = 1;
- ebx->split.coherency_line_size = line_size - 1;
- ebx->split.ways_of_associativity = assoc - 1;
- ebx->split.physical_line_partition = lines_per_tag - 1;
- ecx->split.number_of_sets = (size_in_kb * 1024) / line_size /
- (ebx->split.ways_of_associativity + 1) - 1;
-}
-
-#if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS)
-
-/*
- * L3 cache descriptors
- */
-static void amd_calc_l3_indices(struct amd_northbridge *nb)
-{
- struct amd_l3_cache *l3 = &nb->l3_cache;
- unsigned int sc0, sc1, sc2, sc3;
- u32 val = 0;
-
- pci_read_config_dword(nb->misc, 0x1C4, &val);
-
- /* calculate subcache sizes */
- l3->subcaches[0] = sc0 = !(val & BIT(0));
- l3->subcaches[1] = sc1 = !(val & BIT(4));
-
- if (boot_cpu_data.x86 == 0x15) {
- l3->subcaches[0] = sc0 += !(val & BIT(1));
- l3->subcaches[1] = sc1 += !(val & BIT(5));
- }
-
- l3->subcaches[2] = sc2 = !(val & BIT(8)) + !(val & BIT(9));
- l3->subcaches[3] = sc3 = !(val & BIT(12)) + !(val & BIT(13));
-
- l3->indices = (max(max3(sc0, sc1, sc2), sc3) << 10) - 1;
-}
-
-/*
- * check whether a slot used for disabling an L3 index is occupied.
- * @l3: L3 cache descriptor
- * @slot: slot number (0..1)
- *
- * @returns: the disabled index if used or negative value if slot free.
- */
-static int amd_get_l3_disable_slot(struct amd_northbridge *nb, unsigned slot)
-{
- unsigned int reg = 0;
-
- pci_read_config_dword(nb->misc, 0x1BC + slot * 4, &reg);
-
- /* check whether this slot is activated already */
- if (reg & (3UL << 30))
- return reg & 0xfff;
-
- return -1;
-}
-
-static ssize_t show_cache_disable(struct cacheinfo *this_leaf, char *buf,
- unsigned int slot)
-{
- int index;
- struct amd_northbridge *nb = this_leaf->priv;
-
- index = amd_get_l3_disable_slot(nb, slot);
- if (index >= 0)
- return sprintf(buf, "%d\n", index);
-
- return sprintf(buf, "FREE\n");
-}
-
-#define SHOW_CACHE_DISABLE(slot) \
-static ssize_t \
-cache_disable_##slot##_show(struct device *dev, \
- struct device_attribute *attr, char *buf) \
-{ \
- struct cacheinfo *this_leaf = dev_get_drvdata(dev); \
- return show_cache_disable(this_leaf, buf, slot); \
-}
-SHOW_CACHE_DISABLE(0)
-SHOW_CACHE_DISABLE(1)
-
-static void amd_l3_disable_index(struct amd_northbridge *nb, int cpu,
- unsigned slot, unsigned long idx)
-{
- int i;
- idx |= BIT(30);
-
- /*
- * disable index in all 4 subcaches
- */
- for (i = 0; i < 4; i++) {
- u32 reg = idx | (i << 20);
-
- if (!nb->l3_cache.subcaches[i])
- continue;
-
- pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
-
- /*
- * We need to WBINVD on a core on the node containing the L3
- * cache which indices we disable therefore a simple wbinvd()
- * is not sufficient.
- */
- wbinvd_on_cpu(cpu);
-
- reg |= BIT(31);
- pci_write_config_dword(nb->misc, 0x1BC + slot * 4, reg);
- }
-}
-
-/*
- * disable a L3 cache index by using a disable-slot
- *
- * @l3: L3 cache descriptor
- * @cpu: A CPU on the node containing the L3 cache
- * @slot: slot number (0..1)
- * @index: index to disable
- *
- * @return: 0 on success, error status on failure
- */
-static int amd_set_l3_disable_slot(struct amd_northbridge *nb, int cpu,
- unsigned slot, unsigned long index)
-{
- int ret = 0;
-
- /* check if @slot is already used or the index is already disabled */
- ret = amd_get_l3_disable_slot(nb, slot);
- if (ret >= 0)
- return -EEXIST;
-
- if (index > nb->l3_cache.indices)
- return -EINVAL;
-
- /* check whether the other slot has disabled the same index already */
- if (index == amd_get_l3_disable_slot(nb, !slot))
- return -EEXIST;
-
- amd_l3_disable_index(nb, cpu, slot, index);
-
- return 0;
-}
-
-static ssize_t store_cache_disable(struct cacheinfo *this_leaf,
- const char *buf, size_t count,
- unsigned int slot)
-{
- unsigned long val = 0;
- int cpu, err = 0;
- struct amd_northbridge *nb = this_leaf->priv;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- cpu = cpumask_first(&this_leaf->shared_cpu_map);
-
- if (kstrtoul(buf, 10, &val) < 0)
- return -EINVAL;
-
- err = amd_set_l3_disable_slot(nb, cpu, slot, val);
- if (err) {
- if (err == -EEXIST)
- pr_warn("L3 slot %d in use/index already disabled!\n",
- slot);
- return err;
- }
- return count;
-}
-
-#define STORE_CACHE_DISABLE(slot) \
-static ssize_t \
-cache_disable_##slot##_store(struct device *dev, \
- struct device_attribute *attr, \
- const char *buf, size_t count) \
-{ \
- struct cacheinfo *this_leaf = dev_get_drvdata(dev); \
- return store_cache_disable(this_leaf, buf, count, slot); \
-}
-STORE_CACHE_DISABLE(0)
-STORE_CACHE_DISABLE(1)
-
-static ssize_t subcaches_show(struct device *dev,
- struct device_attribute *attr, char *buf)
-{
- struct cacheinfo *this_leaf = dev_get_drvdata(dev);
- int cpu = cpumask_first(&this_leaf->shared_cpu_map);
-
- return sprintf(buf, "%x\n", amd_get_subcaches(cpu));
-}
-
-static ssize_t subcaches_store(struct device *dev,
- struct device_attribute *attr,
- const char *buf, size_t count)
-{
- struct cacheinfo *this_leaf = dev_get_drvdata(dev);
- int cpu = cpumask_first(&this_leaf->shared_cpu_map);
- unsigned long val;
-
- if (!capable(CAP_SYS_ADMIN))
- return -EPERM;
-
- if (kstrtoul(buf, 16, &val) < 0)
- return -EINVAL;
-
- if (amd_set_subcaches(cpu, val))
- return -EINVAL;
-
- return count;
+ ebx->split.coherency_line_size = line_size - 1;
+ ebx->split.ways_of_associativity = assoc - 1;
+ ebx->split.physical_line_partition = lines_per_tag - 1;
+ ecx->split.number_of_sets = (size_in_kb * 1024) / line_size /
+ (ebx->split.ways_of_associativity + 1) - 1;
}
-static DEVICE_ATTR_RW(cache_disable_0);
-static DEVICE_ATTR_RW(cache_disable_1);
-static DEVICE_ATTR_RW(subcaches);
-
-static umode_t
-cache_private_attrs_is_visible(struct kobject *kobj,
- struct attribute *attr, int unused)
+static int cpuid4_info_fill_done(struct _cpuid4_info *id4, union _cpuid4_leaf_eax eax,
+ union _cpuid4_leaf_ebx ebx, union _cpuid4_leaf_ecx ecx)
{
- struct device *dev = kobj_to_dev(kobj);
- struct cacheinfo *this_leaf = dev_get_drvdata(dev);
- umode_t mode = attr->mode;
-
- if (!this_leaf->priv)
- return 0;
-
- if ((attr == &dev_attr_subcaches.attr) &&
- amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
- return mode;
+ if (eax.split.type == CTYPE_NULL)
+ return -EIO;
- if ((attr == &dev_attr_cache_disable_0.attr ||
- attr == &dev_attr_cache_disable_1.attr) &&
- amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
- return mode;
+ id4->eax = eax;
+ id4->ebx = ebx;
+ id4->ecx = ecx;
+ id4->size = (ecx.split.number_of_sets + 1) *
+ (ebx.split.coherency_line_size + 1) *
+ (ebx.split.physical_line_partition + 1) *
+ (ebx.split.ways_of_associativity + 1);
return 0;
}
-static struct attribute_group cache_private_group = {
- .is_visible = cache_private_attrs_is_visible,
-};
-
-static void init_amd_l3_attrs(void)
-{
- int n = 1;
- static struct attribute **amd_l3_attrs;
-
- if (amd_l3_attrs) /* already initialized */
- return;
-
- if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE))
- n += 2;
- if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
- n += 1;
-
- amd_l3_attrs = kcalloc(n, sizeof(*amd_l3_attrs), GFP_KERNEL);
- if (!amd_l3_attrs)
- return;
-
- n = 0;
- if (amd_nb_has_feature(AMD_NB_L3_INDEX_DISABLE)) {
- amd_l3_attrs[n++] = &dev_attr_cache_disable_0.attr;
- amd_l3_attrs[n++] = &dev_attr_cache_disable_1.attr;
- }
- if (amd_nb_has_feature(AMD_NB_L3_PARTITIONING))
- amd_l3_attrs[n++] = &dev_attr_subcaches.attr;
-
- cache_private_group.attrs = amd_l3_attrs;
-}
-
-const struct attribute_group *
-cache_get_priv_group(struct cacheinfo *this_leaf)
+static int amd_fill_cpuid4_info(int index, struct _cpuid4_info *id4)
{
- struct amd_northbridge *nb = this_leaf->priv;
-
- if (this_leaf->level < 3 || !nb)
- return NULL;
+ union _cpuid4_leaf_eax eax;
+ union _cpuid4_leaf_ebx ebx;
+ union _cpuid4_leaf_ecx ecx;
+ u32 ignored;
- if (nb && nb->l3_cache.indices)
- init_amd_l3_attrs();
+ if (boot_cpu_has(X86_FEATURE_TOPOEXT) || boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+ cpuid_count(0x8000001d, index, &eax.full, &ebx.full, &ecx.full, &ignored);
+ else
+ legacy_amd_cpuid4(index, &eax, &ebx, &ecx);
- return &cache_private_group;
+ return cpuid4_info_fill_done(id4, eax, ebx, ecx);
}
-static void amd_init_l3_cache(struct _cpuid4_info_regs *this_leaf, int index)
+static int intel_fill_cpuid4_info(int index, struct _cpuid4_info *id4)
{
- int node;
+ union _cpuid4_leaf_eax eax;
+ union _cpuid4_leaf_ebx ebx;
+ union _cpuid4_leaf_ecx ecx;
+ u32 ignored;
- /* only for L3, and not in virtualized environments */
- if (index < 3)
- return;
+ cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &ignored);
- node = topology_amd_node_id(smp_processor_id());
- this_leaf->nb = node_to_amd_nb(node);
- if (this_leaf->nb && !this_leaf->nb->l3_cache.indices)
- amd_calc_l3_indices(this_leaf->nb);
+ return cpuid4_info_fill_done(id4, eax, ebx, ecx);
}
-#else
-#define amd_init_l3_cache(x, y)
-#endif /* CONFIG_AMD_NB && CONFIG_SYSFS */
-static int
-cpuid4_cache_lookup_regs(int index, struct _cpuid4_info_regs *this_leaf)
+static int fill_cpuid4_info(int index, struct _cpuid4_info *id4)
{
- union _cpuid4_leaf_eax eax;
- union _cpuid4_leaf_ebx ebx;
- union _cpuid4_leaf_ecx ecx;
- unsigned edx;
-
- if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
- if (boot_cpu_has(X86_FEATURE_TOPOEXT))
- cpuid_count(0x8000001d, index, &eax.full,
- &ebx.full, &ecx.full, &edx);
- else
- amd_cpuid4(index, &eax, &ebx, &ecx);
- amd_init_l3_cache(this_leaf, index);
- } else if (boot_cpu_data.x86_vendor == X86_VENDOR_HYGON) {
- cpuid_count(0x8000001d, index, &eax.full,
- &ebx.full, &ecx.full, &edx);
- amd_init_l3_cache(this_leaf, index);
- } else {
- cpuid_count(4, index, &eax.full, &ebx.full, &ecx.full, &edx);
- }
+ u8 cpu_vendor = boot_cpu_data.x86_vendor;
- if (eax.split.type == CTYPE_NULL)
- return -EIO; /* better error ? */
-
- this_leaf->eax = eax;
- this_leaf->ebx = ebx;
- this_leaf->ecx = ecx;
- this_leaf->size = (ecx.split.number_of_sets + 1) *
- (ebx.split.coherency_line_size + 1) *
- (ebx.split.physical_line_partition + 1) *
- (ebx.split.ways_of_associativity + 1);
- return 0;
+ return (cpu_vendor == X86_VENDOR_AMD || cpu_vendor == X86_VENDOR_HYGON) ?
+ amd_fill_cpuid4_info(index, id4) :
+ intel_fill_cpuid4_info(index, id4);
}
static int find_num_cache_leaves(struct cpuinfo_x86 *c)
{
- unsigned int eax, ebx, ecx, edx, op;
- union _cpuid4_leaf_eax cache_eax;
- int i = -1;
-
- if (c->x86_vendor == X86_VENDOR_AMD ||
- c->x86_vendor == X86_VENDOR_HYGON)
- op = 0x8000001d;
- else
- op = 4;
+ unsigned int eax, ebx, ecx, edx, op;
+ union _cpuid4_leaf_eax cache_eax;
+ int i = -1;
+ /* Do a CPUID(op) loop to calculate num_cache_leaves */
+ op = (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) ? 0x8000001d : 4;
do {
++i;
- /* Do cpuid(op) loop to find out num_cache_leaves */
cpuid_count(op, i, &eax, &ebx, &ecx, &edx);
cache_eax.full = eax;
} while (cache_eax.split.type != CTYPE_NULL);
return i;
}
+/*
+ * AMD/Hygon CPUs may have multiple LLCs if L3 caches exist.
+ */
+
void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id)
{
- /*
- * We may have multiple LLCs if L3 caches exist, so check if we
- * have an L3 cache by looking at the L3 cache CPUID leaf.
- */
- if (!cpuid_edx(0x80000006))
+ if (!cpuid_amd_hygon_has_l3_cache())
return;
if (c->x86 < 0x17) {
- /* LLC is at the node level. */
+ /* Pre-Zen: LLC is at the node level */
c->topo.llc_id = die_id;
} else if (c->x86 == 0x17 && c->x86_model <= 0x1F) {
/*
- * LLC is at the core complex level.
- * Core complex ID is ApicId[3] for these processors.
+ * Family 17h up to 1F models: LLC is at the core
+ * complex level. Core complex ID is ApicId[3].
*/
c->topo.llc_id = c->topo.apicid >> 3;
} else {
/*
- * LLC ID is calculated from the number of threads sharing the
- * cache.
- * */
+ * Newer families: LLC ID is calculated from the number
+ * of threads sharing the L3 cache.
+ */
u32 eax, ebx, ecx, edx, num_sharing_cache = 0;
u32 llc_index = find_num_cache_leaves(c) - 1;
@@ -683,25 +320,21 @@ void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id)
num_sharing_cache = ((eax >> 14) & 0xfff) + 1;
if (num_sharing_cache) {
- int bits = get_count_order(num_sharing_cache);
+ int index_msb = get_count_order(num_sharing_cache);
- c->topo.llc_id = c->topo.apicid >> bits;
+ c->topo.llc_id = c->topo.apicid >> index_msb;
}
}
}
void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c)
{
- /*
- * We may have multiple LLCs if L3 caches exist, so check if we
- * have an L3 cache by looking at the L3 cache CPUID leaf.
- */
- if (!cpuid_edx(0x80000006))
+ if (!cpuid_amd_hygon_has_l3_cache())
return;
/*
- * LLC is at the core complex level.
- * Core complex ID is ApicId[3] for these processors.
+ * Hygons are similar to AMD Family 17h up to 1F models: LLC is
+ * at the core complex level. Core complex ID is ApicId[3].
*/
c->topo.llc_id = c->topo.apicid >> 3;
}
@@ -710,14 +343,10 @@ void init_amd_cacheinfo(struct cpuinfo_x86 *c)
{
struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
- if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
+ if (boot_cpu_has(X86_FEATURE_TOPOEXT))
ci->num_leaves = find_num_cache_leaves(c);
- } else if (c->extended_cpuid_level >= 0x80000006) {
- if (cpuid_edx(0x80000006) & 0xf000)
- ci->num_leaves = 4;
- else
- ci->num_leaves = 3;
- }
+ else if (c->extended_cpuid_level >= 0x80000006)
+ ci->num_leaves = (cpuid_edx(0x80000006) & 0xf000) ? 4 : 3;
}
void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
@@ -727,148 +356,131 @@ void init_hygon_cacheinfo(struct cpuinfo_x86 *c)
ci->num_leaves = find_num_cache_leaves(c);
}
-void init_intel_cacheinfo(struct cpuinfo_x86 *c)
+static void intel_cacheinfo_done(struct cpuinfo_x86 *c, unsigned int l3,
+ unsigned int l2, unsigned int l1i, unsigned int l1d)
{
- /* Cache sizes */
- unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0;
- unsigned int new_l1d = 0, new_l1i = 0; /* Cache sizes from cpuid(4) */
- unsigned int new_l2 = 0, new_l3 = 0, i; /* Cache sizes from cpuid(4) */
- unsigned int l2_id = 0, l3_id = 0, num_threads_sharing, index_msb;
- struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
+ /*
+ * If llc_id is still unset, then cpuid_level < 4, which implies
+ * that the only possibility left is SMT. Since CPUID(0x2) doesn't
+ * specify any shared caches and SMT shares all caches, we can
+ * unconditionally set LLC ID to the package ID so that all
+ * threads share it.
+ */
+ if (c->topo.llc_id == BAD_APICID)
+ c->topo.llc_id = c->topo.pkg_id;
- if (c->cpuid_level > 3) {
- /*
- * There should be at least one leaf. A non-zero value means
- * that the number of leaves has been initialized.
- */
- if (!ci->num_leaves)
- ci->num_leaves = find_num_cache_leaves(c);
+ c->x86_cache_size = l3 ? l3 : (l2 ? l2 : l1i + l1d);
- /*
- * Whenever possible use cpuid(4), deterministic cache
- * parameters cpuid leaf to find the cache details
- */
- for (i = 0; i < ci->num_leaves; i++) {
- struct _cpuid4_info_regs this_leaf = {};
- int retval;
+ if (!l2)
+ cpu_detect_cache_sizes(c);
+}
- retval = cpuid4_cache_lookup_regs(i, &this_leaf);
- if (retval < 0)
- continue;
+/*
+ * Legacy Intel CPUID(0x2) path if CPUID(0x4) is not available.
+ */
+static void intel_cacheinfo_0x2(struct cpuinfo_x86 *c)
+{
+ unsigned int l1i = 0, l1d = 0, l2 = 0, l3 = 0;
+ const struct leaf_0x2_table *desc;
+ union leaf_0x2_regs regs;
+ u8 *ptr;
- switch (this_leaf.eax.split.level) {
- case 1:
- if (this_leaf.eax.split.type == CTYPE_DATA)
- new_l1d = this_leaf.size/1024;
- else if (this_leaf.eax.split.type == CTYPE_INST)
- new_l1i = this_leaf.size/1024;
- break;
- case 2:
- new_l2 = this_leaf.size/1024;
- num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
- index_msb = get_count_order(num_threads_sharing);
- l2_id = c->topo.apicid & ~((1 << index_msb) - 1);
- break;
- case 3:
- new_l3 = this_leaf.size/1024;
- num_threads_sharing = 1 + this_leaf.eax.split.num_threads_sharing;
- index_msb = get_count_order(num_threads_sharing);
- l3_id = c->topo.apicid & ~((1 << index_msb) - 1);
- break;
- default:
- break;
- }
- }
- }
+ if (c->cpuid_level < 2)
+ return;
- /* Don't use CPUID(2) if CPUID(4) is supported. */
- if (!ci->num_leaves && c->cpuid_level > 1) {
- /* supports eax=2 call */
- int j, n;
- unsigned int regs[4];
- unsigned char *dp = (unsigned char *)regs;
-
- /* Number of times to iterate */
- n = cpuid_eax(2) & 0xFF;
-
- for (i = 0 ; i < n ; i++) {
- cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
-
- /* If bit 31 is set, this is an unknown format */
- for (j = 0 ; j < 4 ; j++)
- if (regs[j] & (1 << 31))
- regs[j] = 0;
-
- /* Byte 0 is level count, not a descriptor */
- for (j = 1 ; j < 16 ; j++) {
- unsigned char des = dp[j];
- unsigned char k = 0;
-
- /* look up this descriptor in the table */
- while (cache_table[k].descriptor != 0) {
- if (cache_table[k].descriptor == des) {
- switch (cache_table[k].cache_type) {
- case LVL_1_INST:
- l1i += cache_table[k].size;
- break;
- case LVL_1_DATA:
- l1d += cache_table[k].size;
- break;
- case LVL_2:
- l2 += cache_table[k].size;
- break;
- case LVL_3:
- l3 += cache_table[k].size;
- break;
- }
-
- break;
- }
-
- k++;
- }
- }
+ cpuid_leaf_0x2(&regs);
+ for_each_cpuid_0x2_desc(regs, ptr, desc) {
+ switch (desc->c_type) {
+ case CACHE_L1_INST: l1i += desc->c_size; break;
+ case CACHE_L1_DATA: l1d += desc->c_size; break;
+ case CACHE_L2: l2 += desc->c_size; break;
+ case CACHE_L3: l3 += desc->c_size; break;
}
}
- if (new_l1d)
- l1d = new_l1d;
+ intel_cacheinfo_done(c, l3, l2, l1i, l1d);
+}
- if (new_l1i)
- l1i = new_l1i;
+static unsigned int calc_cache_topo_id(struct cpuinfo_x86 *c, const struct _cpuid4_info *id4)
+{
+ unsigned int num_threads_sharing;
+ int index_msb;
- if (new_l2) {
- l2 = new_l2;
- c->topo.llc_id = l2_id;
- c->topo.l2c_id = l2_id;
- }
+ num_threads_sharing = 1 + id4->eax.split.num_threads_sharing;
+ index_msb = get_count_order(num_threads_sharing);
+ return c->topo.apicid & ~((1 << index_msb) - 1);
+}
- if (new_l3) {
- l3 = new_l3;
- c->topo.llc_id = l3_id;
- }
+static bool intel_cacheinfo_0x4(struct cpuinfo_x86 *c)
+{
+ struct cpu_cacheinfo *ci = get_cpu_cacheinfo(c->cpu_index);
+ unsigned int l2_id = BAD_APICID, l3_id = BAD_APICID;
+ unsigned int l1d = 0, l1i = 0, l2 = 0, l3 = 0;
+
+ if (c->cpuid_level < 4)
+ return false;
/*
- * If llc_id is not yet set, this means cpuid_level < 4 which in
- * turns means that the only possibility is SMT (as indicated in
- * cpuid1). Since cpuid2 doesn't specify shared caches, and we know
- * that SMT shares all caches, we can unconditionally set cpu_llc_id to
- * c->topo.pkg_id.
+ * There should be at least one leaf. A non-zero value means
+ * that the number of leaves has been previously initialized.
*/
- if (c->topo.llc_id == BAD_APICID)
- c->topo.llc_id = c->topo.pkg_id;
+ if (!ci->num_leaves)
+ ci->num_leaves = find_num_cache_leaves(c);
+
+ if (!ci->num_leaves)
+ return false;
- c->x86_cache_size = l3 ? l3 : (l2 ? l2 : (l1i+l1d));
+ for (int i = 0; i < ci->num_leaves; i++) {
+ struct _cpuid4_info id4 = {};
+ int ret;
- if (!l2)
- cpu_detect_cache_sizes(c);
+ ret = intel_fill_cpuid4_info(i, &id4);
+ if (ret < 0)
+ continue;
+
+ switch (id4.eax.split.level) {
+ case 1:
+ if (id4.eax.split.type == CTYPE_DATA)
+ l1d = id4.size / 1024;
+ else if (id4.eax.split.type == CTYPE_INST)
+ l1i = id4.size / 1024;
+ break;
+ case 2:
+ l2 = id4.size / 1024;
+ l2_id = calc_cache_topo_id(c, &id4);
+ break;
+ case 3:
+ l3 = id4.size / 1024;
+ l3_id = calc_cache_topo_id(c, &id4);
+ break;
+ default:
+ break;
+ }
+ }
+
+ c->topo.l2c_id = l2_id;
+ c->topo.llc_id = (l3_id == BAD_APICID) ? l2_id : l3_id;
+ intel_cacheinfo_done(c, l3, l2, l1i, l1d);
+ return true;
+}
+
+void init_intel_cacheinfo(struct cpuinfo_x86 *c)
+{
+ /* Don't use CPUID(0x2) if CPUID(0x4) is supported. */
+ if (intel_cacheinfo_0x4(c))
+ return;
+
+ intel_cacheinfo_0x2(c);
}
+/*
+ * <linux/cacheinfo.h> shared_cpu_map setup, AMD/Hygon
+ */
static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
- struct _cpuid4_info_regs *base)
+ const struct _cpuid4_info *id4)
{
struct cpu_cacheinfo *this_cpu_ci;
- struct cacheinfo *this_leaf;
+ struct cacheinfo *ci;
int i, sibling;
/*
@@ -880,18 +492,18 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
this_cpu_ci = get_cpu_cacheinfo(i);
if (!this_cpu_ci->info_list)
continue;
- this_leaf = this_cpu_ci->info_list + index;
+
+ ci = this_cpu_ci->info_list + index;
for_each_cpu(sibling, cpu_llc_shared_mask(cpu)) {
if (!cpu_online(sibling))
continue;
- cpumask_set_cpu(sibling,
- &this_leaf->shared_cpu_map);
+ cpumask_set_cpu(sibling, &ci->shared_cpu_map);
}
}
} else if (boot_cpu_has(X86_FEATURE_TOPOEXT)) {
unsigned int apicid, nshared, first, last;
- nshared = base->eax.split.num_threads_sharing + 1;
+ nshared = id4->eax.split.num_threads_sharing + 1;
apicid = cpu_data(cpu).topo.apicid;
first = apicid - (apicid % nshared);
last = first + nshared - 1;
@@ -905,14 +517,13 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
if ((apicid < first) || (apicid > last))
continue;
- this_leaf = this_cpu_ci->info_list + index;
+ ci = this_cpu_ci->info_list + index;
for_each_online_cpu(sibling) {
apicid = cpu_data(sibling).topo.apicid;
if ((apicid < first) || (apicid > last))
continue;
- cpumask_set_cpu(sibling,
- &this_leaf->shared_cpu_map);
+ cpumask_set_cpu(sibling, &ci->shared_cpu_map);
}
}
} else
@@ -921,25 +532,27 @@ static int __cache_amd_cpumap_setup(unsigned int cpu, int index,
return 1;
}
+/*
+ * <linux/cacheinfo.h> shared_cpu_map setup, Intel + fallback AMD/Hygon
+ */
static void __cache_cpumap_setup(unsigned int cpu, int index,
- struct _cpuid4_info_regs *base)
+ const struct _cpuid4_info *id4)
{
struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
- struct cacheinfo *this_leaf, *sibling_leaf;
+ struct cpuinfo_x86 *c = &cpu_data(cpu);
+ struct cacheinfo *ci, *sibling_ci;
unsigned long num_threads_sharing;
int index_msb, i;
- struct cpuinfo_x86 *c = &cpu_data(cpu);
- if (c->x86_vendor == X86_VENDOR_AMD ||
- c->x86_vendor == X86_VENDOR_HYGON) {
- if (__cache_amd_cpumap_setup(cpu, index, base))
+ if (c->x86_vendor == X86_VENDOR_AMD || c->x86_vendor == X86_VENDOR_HYGON) {
+ if (__cache_amd_cpumap_setup(cpu, index, id4))
return;
}
- this_leaf = this_cpu_ci->info_list + index;
- num_threads_sharing = 1 + base->eax.split.num_threads_sharing;
+ ci = this_cpu_ci->info_list + index;
+ num_threads_sharing = 1 + id4->eax.split.num_threads_sharing;
- cpumask_set_cpu(cpu, &this_leaf->shared_cpu_map);
+ cpumask_set_cpu(cpu, &ci->shared_cpu_map);
if (num_threads_sharing == 1)
return;
@@ -949,30 +562,29 @@ static void __cache_cpumap_setup(unsigned int cpu, int index,
if (cpu_data(i).topo.apicid >> index_msb == c->topo.apicid >> index_msb) {
struct cpu_cacheinfo *sib_cpu_ci = get_cpu_cacheinfo(i);
+ /* Skip if itself or no cacheinfo */
if (i == cpu || !sib_cpu_ci->info_list)
- continue;/* skip if itself or no cacheinfo */
- sibling_leaf = sib_cpu_ci->info_list + index;
- cpumask_set_cpu(i, &this_leaf->shared_cpu_map);
- cpumask_set_cpu(cpu, &sibling_leaf->shared_cpu_map);
+ continue;
+
+ sibling_ci = sib_cpu_ci->info_list + index;
+ cpumask_set_cpu(i, &ci->shared_cpu_map);
+ cpumask_set_cpu(cpu, &sibling_ci->shared_cpu_map);
}
}
-static void ci_leaf_init(struct cacheinfo *this_leaf,
- struct _cpuid4_info_regs *base)
+static void ci_info_init(struct cacheinfo *ci, const struct _cpuid4_info *id4,
+ struct amd_northbridge *nb)
{
- this_leaf->id = base->id;
- this_leaf->attributes = CACHE_ID;
- this_leaf->level = base->eax.split.level;
- this_leaf->type = cache_type_map[base->eax.split.type];
- this_leaf->coherency_line_size =
- base->ebx.split.coherency_line_size + 1;
- this_leaf->ways_of_associativity =
- base->ebx.split.ways_of_associativity + 1;
- this_leaf->size = base->size;
- this_leaf->number_of_sets = base->ecx.split.number_of_sets + 1;
- this_leaf->physical_line_partition =
- base->ebx.split.physical_line_partition + 1;
- this_leaf->priv = base->nb;
+ ci->id = id4->id;
+ ci->attributes = CACHE_ID;
+ ci->level = id4->eax.split.level;
+ ci->type = cache_type_map[id4->eax.split.type];
+ ci->coherency_line_size = id4->ebx.split.coherency_line_size + 1;
+ ci->ways_of_associativity = id4->ebx.split.ways_of_associativity + 1;
+ ci->size = id4->size;
+ ci->number_of_sets = id4->ecx.split.number_of_sets + 1;
+ ci->physical_line_partition = id4->ebx.split.physical_line_partition + 1;
+ ci->priv = nb;
}
int init_cache_level(unsigned int cpu)
@@ -987,38 +599,45 @@ int init_cache_level(unsigned int cpu)
}
/*
- * The max shared threads number comes from CPUID.4:EAX[25-14] with input
+ * The max shared threads number comes from CPUID(0x4) EAX[25-14] with input
* ECX as cache index. Then right shift apicid by the number's order to get
* cache id for this cache node.
*/
-static void get_cache_id(int cpu, struct _cpuid4_info_regs *id4_regs)
+static void get_cache_id(int cpu, struct _cpuid4_info *id4)
{
struct cpuinfo_x86 *c = &cpu_data(cpu);
unsigned long num_threads_sharing;
int index_msb;
- num_threads_sharing = 1 + id4_regs->eax.split.num_threads_sharing;
+ num_threads_sharing = 1 + id4->eax.split.num_threads_sharing;
index_msb = get_count_order(num_threads_sharing);
- id4_regs->id = c->topo.apicid >> index_msb;
+ id4->id = c->topo.apicid >> index_msb;
}
int populate_cache_leaves(unsigned int cpu)
{
- unsigned int idx, ret;
struct cpu_cacheinfo *this_cpu_ci = get_cpu_cacheinfo(cpu);
- struct cacheinfo *this_leaf = this_cpu_ci->info_list;
- struct _cpuid4_info_regs id4_regs = {};
+ struct cacheinfo *ci = this_cpu_ci->info_list;
+ u8 cpu_vendor = boot_cpu_data.x86_vendor;
+ struct amd_northbridge *nb = NULL;
+ struct _cpuid4_info id4 = {};
+ int idx, ret;
for (idx = 0; idx < this_cpu_ci->num_leaves; idx++) {
- ret = cpuid4_cache_lookup_regs(idx, &id4_regs);
+ ret = fill_cpuid4_info(idx, &id4);
if (ret)
return ret;
- get_cache_id(cpu, &id4_regs);
- ci_leaf_init(this_leaf++, &id4_regs);
- __cache_cpumap_setup(cpu, idx, &id4_regs);
+
+ get_cache_id(cpu, &id4);
+
+ if (cpu_vendor == X86_VENDOR_AMD || cpu_vendor == X86_VENDOR_HYGON)
+ nb = amd_init_l3_cache(idx);
+
+ ci_info_init(ci++, &id4, nb);
+ __cache_cpumap_setup(cpu, idx, &id4);
}
- this_cpu_ci->cpu_map_populated = true;
+ this_cpu_ci->cpu_map_populated = true;
return 0;
}
@@ -1034,31 +653,33 @@ int populate_cache_leaves(unsigned int cpu)
static unsigned long saved_cr4;
static DEFINE_RAW_SPINLOCK(cache_disable_lock);
+/*
+ * Cache flushing is the most time-consuming step when programming the
+ * MTRRs. On many Intel CPUs without known erratas, it can be skipped
+ * if the CPU declares cache self-snooping support.
+ */
+static void maybe_flush_caches(void)
+{
+ if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+ wbinvd();
+}
+
void cache_disable(void) __acquires(cache_disable_lock)
{
unsigned long cr0;
/*
- * Note that this is not ideal
- * since the cache is only flushed/disabled for this CPU while the
- * MTRRs are changed, but changing this requires more invasive
- * changes to the way the kernel boots
+ * This is not ideal since the cache is only flushed/disabled
+ * for this CPU while the MTRRs are changed, but changing this
+ * requires more invasive changes to the way the kernel boots.
*/
-
raw_spin_lock(&cache_disable_lock);
/* Enter the no-fill (CD=1, NW=0) cache mode and flush caches. */
cr0 = read_cr0() | X86_CR0_CD;
write_cr0(cr0);
- /*
- * Cache flushing is the most time-consuming step when programming
- * the MTRRs. Fortunately, as per the Intel Software Development
- * Manual, we can skip it if the processor supports cache self-
- * snooping.
- */
- if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
- wbinvd();
+ maybe_flush_caches();
/* Save value of CR4 and clear Page Global Enable (bit 7) */
if (cpu_feature_enabled(X86_FEATURE_PGE)) {
@@ -1073,9 +694,7 @@ void cache_disable(void) __acquires(cache_disable_lock)
if (cpu_feature_enabled(X86_FEATURE_MTRR))
mtrr_disable();
- /* Again, only flush caches if we have to. */
- if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
- wbinvd();
+ maybe_flush_caches();
}
void cache_enable(void) __releases(cache_disable_lock)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 0ff057ff11ce..34a054181c4d 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -26,10 +26,11 @@
#include <linux/pgtable.h>
#include <linux/stackprotector.h>
#include <linux/utsname.h>
+#include <linux/efi.h>
#include <asm/alternative.h>
#include <asm/cmdline.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/perf_event.h>
#include <asm/mmu_context.h>
#include <asm/doublefault.h>
@@ -148,7 +149,7 @@ static void ppin_init(struct cpuinfo_x86 *c)
*/
info = (struct ppin_info *)id->driver_data;
- if (rdmsrl_safe(info->msr_ppin_ctl, &val))
+ if (rdmsrq_safe(info->msr_ppin_ctl, &val))
goto clear_ppin;
if ((val & 3UL) == 1UL) {
@@ -158,13 +159,13 @@ static void ppin_init(struct cpuinfo_x86 *c)
/* If PPIN is disabled, try to enable */
if (!(val & 2UL)) {
- wrmsrl_safe(info->msr_ppin_ctl, val | 2UL);
- rdmsrl_safe(info->msr_ppin_ctl, &val);
+ wrmsrq_safe(info->msr_ppin_ctl, val | 2UL);
+ rdmsrq_safe(info->msr_ppin_ctl, &val);
}
/* Is the enable bit set? */
if (val & 2UL) {
- c->ppin = __rdmsr(info->msr_ppin);
+ c->ppin = native_rdmsrq(info->msr_ppin);
set_cpu_cap(c, info->feature);
return;
}
@@ -242,6 +243,7 @@ DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
#endif
} };
EXPORT_PER_CPU_SYMBOL_GPL(gdt_page);
+SYM_PIC_ALIAS(gdt_page);
#ifdef CONFIG_X86_64
static int __init x86_nopcid_setup(char *s)
@@ -321,7 +323,7 @@ static int __init cachesize_setup(char *str)
__setup("cachesize=", cachesize_setup);
/* Probe for the CPUID instruction */
-bool have_cpuid_p(void)
+bool cpuid_feature(void)
{
return flag_is_changeable_p(X86_EFLAGS_ID);
}
@@ -562,9 +564,9 @@ __noendbr u64 ibt_save(bool disable)
u64 msr = 0;
if (cpu_feature_enabled(X86_FEATURE_IBT)) {
- rdmsrl(MSR_IA32_S_CET, msr);
+ rdmsrq(MSR_IA32_S_CET, msr);
if (disable)
- wrmsrl(MSR_IA32_S_CET, msr & ~CET_ENDBR_EN);
+ wrmsrq(MSR_IA32_S_CET, msr & ~CET_ENDBR_EN);
}
return msr;
@@ -575,10 +577,10 @@ __noendbr void ibt_restore(u64 save)
u64 msr;
if (cpu_feature_enabled(X86_FEATURE_IBT)) {
- rdmsrl(MSR_IA32_S_CET, msr);
+ rdmsrq(MSR_IA32_S_CET, msr);
msr &= ~CET_ENDBR_EN;
msr |= (save & CET_ENDBR_EN);
- wrmsrl(MSR_IA32_S_CET, msr);
+ wrmsrq(MSR_IA32_S_CET, msr);
}
}
@@ -602,15 +604,15 @@ static __always_inline void setup_cet(struct cpuinfo_x86 *c)
set_cpu_cap(c, X86_FEATURE_USER_SHSTK);
if (kernel_ibt)
- wrmsrl(MSR_IA32_S_CET, CET_ENDBR_EN);
+ wrmsrq(MSR_IA32_S_CET, CET_ENDBR_EN);
else
- wrmsrl(MSR_IA32_S_CET, 0);
+ wrmsrq(MSR_IA32_S_CET, 0);
cr4_set_bits(X86_CR4_CET);
if (kernel_ibt && ibt_selftest()) {
pr_err("IBT selftest: Failed!\n");
- wrmsrl(MSR_IA32_S_CET, 0);
+ wrmsrq(MSR_IA32_S_CET, 0);
setup_clear_cpu_cap(X86_FEATURE_IBT);
}
}
@@ -621,8 +623,8 @@ __noendbr void cet_disable(void)
cpu_feature_enabled(X86_FEATURE_SHSTK)))
return;
- wrmsrl(MSR_IA32_S_CET, 0);
- wrmsrl(MSR_IA32_U_CET, 0);
+ wrmsrq(MSR_IA32_S_CET, 0);
+ wrmsrq(MSR_IA32_U_CET, 0);
}
/*
@@ -751,9 +753,9 @@ void __init switch_gdt_and_percpu_base(int cpu)
* No need to load %gs. It is already correct.
*
* Writing %gs on 64bit would zero GSBASE which would make any per
- * CPU operation up to the point of the wrmsrl() fault.
+ * CPU operation up to the point of the wrmsrq() fault.
*
- * Set GSBASE to the new offset. Until the wrmsrl() happens the
+ * Set GSBASE to the new offset. Until the wrmsrq() happens the
* early mapping is still valid. That means the GSBASE update will
* lose any prior per CPU data which was not copied over in
* setup_per_cpu_areas().
@@ -761,7 +763,7 @@ void __init switch_gdt_and_percpu_base(int cpu)
* This works even with stackprotector enabled because the
* per CPU stack canary is 0 in both per CPU areas.
*/
- wrmsrl(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
+ wrmsrq(MSR_GS_BASE, cpu_kernelmode_gs_base(cpu));
#else
/*
* %fs is already set to __KERNEL_PERCPU, but after switching GDT
@@ -1005,17 +1007,18 @@ void get_cpu_cap(struct cpuinfo_x86 *c)
c->x86_capability[CPUID_D_1_EAX] = eax;
}
- /* AMD-defined flags: level 0x80000001 */
+ /*
+ * Check if extended CPUID leaves are implemented: Max extended
+ * CPUID leaf must be in the 0x80000001-0x8000ffff range.
+ */
eax = cpuid_eax(0x80000000);
- c->extended_cpuid_level = eax;
+ c->extended_cpuid_level = ((eax & 0xffff0000) == 0x80000000) ? eax : 0;
- if ((eax & 0xffff0000) == 0x80000000) {
- if (eax >= 0x80000001) {
- cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
+ if (c->extended_cpuid_level >= 0x80000001) {
+ cpuid(0x80000001, &eax, &ebx, &ecx, &edx);
- c->x86_capability[CPUID_8000_0001_ECX] = ecx;
- c->x86_capability[CPUID_8000_0001_EDX] = edx;
- }
+ c->x86_capability[CPUID_8000_0001_ECX] = ecx;
+ c->x86_capability[CPUID_8000_0001_EDX] = edx;
}
if (c->extended_cpuid_level >= 0x80000007) {
@@ -1231,6 +1234,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
#define ITS BIT(8)
/* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */
#define ITS_NATIVE_ONLY BIT(9)
+/* CPU is affected by Transient Scheduler Attacks */
+#define TSA BIT(10)
static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE, X86_STEP_MAX, SRBDS),
@@ -1278,7 +1283,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
VULNBL_AMD(0x16, RETBLEED),
VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
- VULNBL_AMD(0x19, SRSO),
+ VULNBL_AMD(0x19, SRSO | TSA),
VULNBL_AMD(0x1a, SRSO),
{}
};
@@ -1295,7 +1300,7 @@ u64 x86_read_arch_cap_msr(void)
u64 x86_arch_cap_msr = 0;
if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
- rdmsrl(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr);
+ rdmsrq(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr);
return x86_arch_cap_msr;
}
@@ -1351,10 +1356,52 @@ static bool __init vulnerable_to_its(u64 x86_arch_cap_msr)
return false;
}
+static struct x86_cpu_id cpu_latest_microcode[] = {
+#include "microcode/intel-ucode-defs.h"
+ {}
+};
+
+static bool __init cpu_has_old_microcode(void)
+{
+ const struct x86_cpu_id *m = x86_match_cpu(cpu_latest_microcode);
+
+ /* Give unknown CPUs a pass: */
+ if (!m) {
+ /* Intel CPUs should be in the list. Warn if not: */
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL)
+ pr_info("x86/CPU: Model not found in latest microcode list\n");
+ return false;
+ }
+
+ /*
+ * Hosts usually lie to guests with a super high microcode
+ * version. Just ignore what hosts tell guests:
+ */
+ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
+ return false;
+
+ /* Consider all debug microcode to be old: */
+ if (boot_cpu_data.microcode & BIT(31))
+ return true;
+
+ /* Give new microcode a pass: */
+ if (boot_cpu_data.microcode >= m->driver_data)
+ return false;
+
+ /* Uh oh, too old: */
+ return true;
+}
+
static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
{
u64 x86_arch_cap_msr = x86_read_arch_cap_msr();
+ if (cpu_has_old_microcode()) {
+ pr_warn("x86/CPU: Running old microcode\n");
+ setup_force_cpu_bug(X86_BUG_OLD_MICROCODE);
+ add_taint(TAINT_CPU_OUT_OF_SPEC, LOCKDEP_STILL_OK);
+ }
+
/* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */
if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) &&
!(x86_arch_cap_msr & ARCH_CAP_PSCHANGE_MC_NO))
@@ -1435,15 +1482,10 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
* Affected CPU list is generally enough to enumerate the vulnerability,
* but for virtualization case check for ARCH_CAP MSR bits also, VMM may
* not want the guest to enumerate the bug.
- *
- * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist,
- * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits.
*/
if (!arch_cap_mmio_immune(x86_arch_cap_msr)) {
if (cpu_matches(cpu_vuln_blacklist, MMIO))
setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA);
- else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO))
- setup_force_cpu_bug(X86_BUG_MMIO_UNKNOWN);
}
if (!cpu_has(c, X86_FEATURE_BTC_NO)) {
@@ -1491,6 +1533,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY);
}
+ if (c->x86_vendor == X86_VENDOR_AMD) {
+ if (!cpu_has(c, X86_FEATURE_TSA_SQ_NO) ||
+ !cpu_has(c, X86_FEATURE_TSA_L1_NO)) {
+ if (cpu_matches(cpu_vuln_blacklist, TSA) ||
+ /* Enable bug on Zen guests to allow for live migration. */
+ (cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_ZEN)))
+ setup_force_cpu_bug(X86_BUG_TSA);
+ }
+ }
+
if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
return;
@@ -1672,11 +1724,11 @@ static void __init early_identify_cpu(struct cpuinfo_x86 *c)
memset(&c->x86_capability, 0, sizeof(c->x86_capability));
c->extended_cpuid_level = 0;
- if (!have_cpuid_p())
+ if (!cpuid_feature())
identify_cpu_without_cpuid(c);
/* cyrix could have cpuid enabled via c_identify()*/
- if (have_cpuid_p()) {
+ if (cpuid_feature()) {
cpu_detect(c);
get_cpu_vendor(c);
intel_unlock_cpuid_leafs(c);
@@ -1791,11 +1843,11 @@ static bool detect_null_seg_behavior(void)
*/
unsigned long old_base, tmp;
- rdmsrl(MSR_FS_BASE, old_base);
- wrmsrl(MSR_FS_BASE, 1);
+ rdmsrq(MSR_FS_BASE, old_base);
+ wrmsrq(MSR_FS_BASE, 1);
loadsegment(fs, 0);
- rdmsrl(MSR_FS_BASE, tmp);
- wrmsrl(MSR_FS_BASE, old_base);
+ rdmsrq(MSR_FS_BASE, tmp);
+ wrmsrq(MSR_FS_BASE, old_base);
return tmp == 0;
}
@@ -1836,11 +1888,11 @@ static void generic_identify(struct cpuinfo_x86 *c)
{
c->extended_cpuid_level = 0;
- if (!have_cpuid_p())
+ if (!cpuid_feature())
identify_cpu_without_cpuid(c);
/* cyrix could have cpuid enabled via c_identify()*/
- if (!have_cpuid_p())
+ if (!cpuid_feature())
return;
cpu_detect(c);
@@ -2024,9 +2076,9 @@ void enable_sep_cpu(void)
*/
tss->x86_tss.ss1 = __KERNEL_CS;
- wrmsr(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1, 0);
- wrmsr(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1), 0);
- wrmsr(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32, 0);
+ wrmsrq(MSR_IA32_SYSENTER_CS, tss->x86_tss.ss1);
+ wrmsrq(MSR_IA32_SYSENTER_ESP, (unsigned long)(cpu_entry_stack(cpu) + 1));
+ wrmsrq(MSR_IA32_SYSENTER_EIP, (unsigned long)entry_SYSENTER_32);
put_cpu();
}
@@ -2133,7 +2185,7 @@ DEFINE_PER_CPU_CACHE_HOT(unsigned long, cpu_current_top_of_stack) = TOP_OF_INIT_
DEFINE_PER_CPU_CACHE_HOT(u64, __x86_call_depth);
EXPORT_PER_CPU_SYMBOL(__x86_call_depth);
-static void wrmsrl_cstar(unsigned long val)
+static void wrmsrq_cstar(unsigned long val)
{
/*
* Intel CPUs do not support 32-bit SYSCALL. Writing to MSR_CSTAR
@@ -2141,37 +2193,37 @@ static void wrmsrl_cstar(unsigned long val)
* guest. Avoid the pointless write on all Intel CPUs.
*/
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
- wrmsrl(MSR_CSTAR, val);
+ wrmsrq(MSR_CSTAR, val);
}
static inline void idt_syscall_init(void)
{
- wrmsrl(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
+ wrmsrq(MSR_LSTAR, (unsigned long)entry_SYSCALL_64);
if (ia32_enabled()) {
- wrmsrl_cstar((unsigned long)entry_SYSCALL_compat);
+ wrmsrq_cstar((unsigned long)entry_SYSCALL_compat);
/*
* This only works on Intel CPUs.
* On AMD CPUs these MSRs are 32-bit, CPU truncates MSR_IA32_SYSENTER_EIP.
* This does not cause SYSENTER to jump to the wrong location, because
* AMD doesn't allow SYSENTER in long mode (either 32- or 64-bit).
*/
- wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP,
+ wrmsrq_safe(MSR_IA32_SYSENTER_CS, (u64)__KERNEL_CS);
+ wrmsrq_safe(MSR_IA32_SYSENTER_ESP,
(unsigned long)(cpu_entry_stack(smp_processor_id()) + 1));
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
+ wrmsrq_safe(MSR_IA32_SYSENTER_EIP, (u64)entry_SYSENTER_compat);
} else {
- wrmsrl_cstar((unsigned long)entry_SYSCALL32_ignore);
- wrmsrl_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
- wrmsrl_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
- wrmsrl_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
+ wrmsrq_cstar((unsigned long)entry_SYSCALL32_ignore);
+ wrmsrq_safe(MSR_IA32_SYSENTER_CS, (u64)GDT_ENTRY_INVALID_SEG);
+ wrmsrq_safe(MSR_IA32_SYSENTER_ESP, 0ULL);
+ wrmsrq_safe(MSR_IA32_SYSENTER_EIP, 0ULL);
}
/*
* Flags to clear on syscall; clear as much as possible
* to minimize user space-kernel interference.
*/
- wrmsrl(MSR_SYSCALL_MASK,
+ wrmsrq(MSR_SYSCALL_MASK,
X86_EFLAGS_CF|X86_EFLAGS_PF|X86_EFLAGS_AF|
X86_EFLAGS_ZF|X86_EFLAGS_SF|X86_EFLAGS_TF|
X86_EFLAGS_IF|X86_EFLAGS_DF|X86_EFLAGS_OF|
@@ -2204,20 +2256,16 @@ EXPORT_PER_CPU_SYMBOL(__stack_chk_guard);
#endif
#endif
-/*
- * Clear all 6 debug registers:
- */
-static void clear_all_debug_regs(void)
+static void initialize_debug_regs(void)
{
- int i;
-
- for (i = 0; i < 8; i++) {
- /* Ignore db4, db5 */
- if ((i == 4) || (i == 5))
- continue;
-
- set_debugreg(0, i);
- }
+ /* Control register first -- to make sure everything is disabled. */
+ set_debugreg(DR7_FIXED_1, 7);
+ set_debugreg(DR6_RESERVED, 6);
+ /* dr5 and dr4 don't exist */
+ set_debugreg(0, 3);
+ set_debugreg(0, 2);
+ set_debugreg(0, 1);
+ set_debugreg(0, 0);
}
#ifdef CONFIG_KGDB
@@ -2240,7 +2288,7 @@ static inline void setup_getcpu(int cpu)
struct desc_struct d = { };
if (boot_cpu_has(X86_FEATURE_RDTSCP) || boot_cpu_has(X86_FEATURE_RDPID))
- wrmsr(MSR_TSC_AUX, cpudata, 0);
+ wrmsrq(MSR_TSC_AUX, cpudata);
/* Store CPU and node number in limit. */
d.limit0 = cpudata;
@@ -2355,8 +2403,8 @@ void cpu_init(void)
memset(cur->thread.tls_array, 0, GDT_ENTRY_TLS_ENTRIES * 8);
syscall_init();
- wrmsrl(MSR_FS_BASE, 0);
- wrmsrl(MSR_KERNEL_GS_BASE, 0);
+ wrmsrq(MSR_FS_BASE, 0);
+ wrmsrq(MSR_KERNEL_GS_BASE, 0);
barrier();
x2apic_setup();
@@ -2378,7 +2426,7 @@ void cpu_init(void)
load_mm_ldt(&init_mm);
- clear_all_debug_regs();
+ initialize_debug_regs();
dbg_restore_debug_regs();
doublefault_init_cpu_tss();
@@ -2491,6 +2539,12 @@ void __init arch_cpu_finalize_init(void)
fpu__init_cpu();
/*
+ * This needs to follow the FPU initializtion, since EFI depends on it.
+ */
+ if (efi_enabled(EFI_RUNTIME_SERVICES))
+ efi_enter_virtual_mode();
+
+ /*
* Ensure that access to the per CPU representation has the initial
* boot CPU configuration.
*/
diff --git a/arch/x86/kernel/cpu/cpu.h b/arch/x86/kernel/cpu/cpu.h
index 51deb60a9d26..bc38b2d56f26 100644
--- a/arch/x86/kernel/cpu/cpu.h
+++ b/arch/x86/kernel/cpu/cpu.h
@@ -75,6 +75,15 @@ extern void check_null_seg_clears_base(struct cpuinfo_x86 *c);
void cacheinfo_amd_init_llc_id(struct cpuinfo_x86 *c, u16 die_id);
void cacheinfo_hygon_init_llc_id(struct cpuinfo_x86 *c);
+#if defined(CONFIG_AMD_NB) && defined(CONFIG_SYSFS)
+struct amd_northbridge *amd_init_l3_cache(int index);
+#else
+static inline struct amd_northbridge *amd_init_l3_cache(int index)
+{
+ return NULL;
+}
+#endif
+
unsigned int aperfmperf_get_khz(int cpu);
void cpu_select_mitigations(void);
diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c
index a2fbea0be535..46efcbd6afa4 100644
--- a/arch/x86/kernel/cpu/cpuid-deps.c
+++ b/arch/x86/kernel/cpu/cpuid-deps.c
@@ -28,6 +28,7 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_PKU, X86_FEATURE_XSAVE },
{ X86_FEATURE_MPX, X86_FEATURE_XSAVE },
{ X86_FEATURE_XGETBV1, X86_FEATURE_XSAVE },
+ { X86_FEATURE_APX, X86_FEATURE_XSAVE },
{ X86_FEATURE_CMOV, X86_FEATURE_FXSR },
{ X86_FEATURE_MMX, X86_FEATURE_FXSR },
{ X86_FEATURE_MMXEXT, X86_FEATURE_MMX },
@@ -82,8 +83,12 @@ static const struct cpuid_dep cpuid_deps[] = {
{ X86_FEATURE_XFD, X86_FEATURE_XSAVES },
{ X86_FEATURE_XFD, X86_FEATURE_XGETBV1 },
{ X86_FEATURE_AMX_TILE, X86_FEATURE_XFD },
+ { X86_FEATURE_AMX_FP16, X86_FEATURE_AMX_TILE },
+ { X86_FEATURE_AMX_BF16, X86_FEATURE_AMX_TILE },
+ { X86_FEATURE_AMX_INT8, X86_FEATURE_AMX_TILE },
{ X86_FEATURE_SHSTK, X86_FEATURE_XSAVES },
{ X86_FEATURE_FRED, X86_FEATURE_LKGS },
+ { X86_FEATURE_SPEC_CTRL_SSBD, X86_FEATURE_SPEC_CTRL },
{}
};
diff --git a/arch/x86/kernel/cpu/cpuid_0x2_table.c b/arch/x86/kernel/cpu/cpuid_0x2_table.c
new file mode 100644
index 000000000000..89bc8db5e9c6
--- /dev/null
+++ b/arch/x86/kernel/cpu/cpuid_0x2_table.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/sizes.h>
+
+#include <asm/cpuid/types.h>
+
+#include "cpu.h"
+
+#define CACHE_ENTRY(_desc, _type, _size) \
+ [_desc] = { \
+ .c_type = (_type), \
+ .c_size = (_size) / SZ_1K, \
+ }
+
+#define TLB_ENTRY(_desc, _type, _entries) \
+ [_desc] = { \
+ .t_type = (_type), \
+ .entries = (_entries), \
+ }
+
+const struct leaf_0x2_table cpuid_0x2_table[256] = {
+ CACHE_ENTRY(0x06, CACHE_L1_INST, SZ_8K ), /* 4-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x08, CACHE_L1_INST, SZ_16K ), /* 4-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x09, CACHE_L1_INST, SZ_32K ), /* 4-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x0a, CACHE_L1_DATA, SZ_8K ), /* 2 way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x0c, CACHE_L1_DATA, SZ_16K ), /* 4-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x0d, CACHE_L1_DATA, SZ_16K ), /* 4-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x0e, CACHE_L1_DATA, SZ_24K ), /* 6-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x21, CACHE_L2, SZ_256K ), /* 8-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x22, CACHE_L3, SZ_512K ), /* 4-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x23, CACHE_L3, SZ_1M ), /* 8-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x25, CACHE_L3, SZ_2M ), /* 8-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x29, CACHE_L3, SZ_4M ), /* 8-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x2c, CACHE_L1_DATA, SZ_32K ), /* 8-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x30, CACHE_L1_INST, SZ_32K ), /* 8-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x39, CACHE_L2, SZ_128K ), /* 4-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x3a, CACHE_L2, SZ_192K ), /* 6-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x3b, CACHE_L2, SZ_128K ), /* 2-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x3c, CACHE_L2, SZ_256K ), /* 4-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x3d, CACHE_L2, SZ_384K ), /* 6-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x3e, CACHE_L2, SZ_512K ), /* 4-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x3f, CACHE_L2, SZ_256K ), /* 2-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x41, CACHE_L2, SZ_128K ), /* 4-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x42, CACHE_L2, SZ_256K ), /* 4-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x43, CACHE_L2, SZ_512K ), /* 4-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x44, CACHE_L2, SZ_1M ), /* 4-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x45, CACHE_L2, SZ_2M ), /* 4-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x46, CACHE_L3, SZ_4M ), /* 4-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x47, CACHE_L3, SZ_8M ), /* 8-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x48, CACHE_L2, SZ_3M ), /* 12-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x49, CACHE_L3, SZ_4M ), /* 16-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x4a, CACHE_L3, SZ_6M ), /* 12-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x4b, CACHE_L3, SZ_8M ), /* 16-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x4c, CACHE_L3, SZ_12M ), /* 12-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x4d, CACHE_L3, SZ_16M ), /* 16-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x4e, CACHE_L2, SZ_6M ), /* 24-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x60, CACHE_L1_DATA, SZ_16K ), /* 8-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x66, CACHE_L1_DATA, SZ_8K ), /* 4-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x67, CACHE_L1_DATA, SZ_16K ), /* 4-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x68, CACHE_L1_DATA, SZ_32K ), /* 4-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x78, CACHE_L2, SZ_1M ), /* 4-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x79, CACHE_L2, SZ_128K ), /* 8-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x7a, CACHE_L2, SZ_256K ), /* 8-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x7b, CACHE_L2, SZ_512K ), /* 8-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x7c, CACHE_L2, SZ_1M ), /* 8-way set assoc, sectored cache, 64 byte line size */
+ CACHE_ENTRY(0x7d, CACHE_L2, SZ_2M ), /* 8-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x7f, CACHE_L2, SZ_512K ), /* 2-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x80, CACHE_L2, SZ_512K ), /* 8-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x82, CACHE_L2, SZ_256K ), /* 8-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x83, CACHE_L2, SZ_512K ), /* 8-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x84, CACHE_L2, SZ_1M ), /* 8-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x85, CACHE_L2, SZ_2M ), /* 8-way set assoc, 32 byte line size */
+ CACHE_ENTRY(0x86, CACHE_L2, SZ_512K ), /* 4-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0x87, CACHE_L2, SZ_1M ), /* 8-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xd0, CACHE_L3, SZ_512K ), /* 4-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xd1, CACHE_L3, SZ_1M ), /* 4-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xd2, CACHE_L3, SZ_2M ), /* 4-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xd6, CACHE_L3, SZ_1M ), /* 8-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xd7, CACHE_L3, SZ_2M ), /* 8-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xd8, CACHE_L3, SZ_4M ), /* 12-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xdc, CACHE_L3, SZ_2M ), /* 12-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xdd, CACHE_L3, SZ_4M ), /* 12-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xde, CACHE_L3, SZ_8M ), /* 12-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xe2, CACHE_L3, SZ_2M ), /* 16-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xe3, CACHE_L3, SZ_4M ), /* 16-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xe4, CACHE_L3, SZ_8M ), /* 16-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xea, CACHE_L3, SZ_12M ), /* 24-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xeb, CACHE_L3, SZ_18M ), /* 24-way set assoc, 64 byte line size */
+ CACHE_ENTRY(0xec, CACHE_L3, SZ_24M ), /* 24-way set assoc, 64 byte line size */
+
+ TLB_ENTRY( 0x01, TLB_INST_4K, 32 ), /* TLB_INST 4 KByte pages, 4-way set associative */
+ TLB_ENTRY( 0x02, TLB_INST_4M, 2 ), /* TLB_INST 4 MByte pages, full associative */
+ TLB_ENTRY( 0x03, TLB_DATA_4K, 64 ), /* TLB_DATA 4 KByte pages, 4-way set associative */
+ TLB_ENTRY( 0x04, TLB_DATA_4M, 8 ), /* TLB_DATA 4 MByte pages, 4-way set associative */
+ TLB_ENTRY( 0x05, TLB_DATA_4M, 32 ), /* TLB_DATA 4 MByte pages, 4-way set associative */
+ TLB_ENTRY( 0x0b, TLB_INST_4M, 4 ), /* TLB_INST 4 MByte pages, 4-way set associative */
+ TLB_ENTRY( 0x4f, TLB_INST_4K, 32 ), /* TLB_INST 4 KByte pages */
+ TLB_ENTRY( 0x50, TLB_INST_ALL, 64 ), /* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+ TLB_ENTRY( 0x51, TLB_INST_ALL, 128 ), /* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+ TLB_ENTRY( 0x52, TLB_INST_ALL, 256 ), /* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
+ TLB_ENTRY( 0x55, TLB_INST_2M_4M, 7 ), /* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+ TLB_ENTRY( 0x56, TLB_DATA0_4M, 16 ), /* TLB_DATA0 4 MByte pages, 4-way set associative */
+ TLB_ENTRY( 0x57, TLB_DATA0_4K, 16 ), /* TLB_DATA0 4 KByte pages, 4-way associative */
+ TLB_ENTRY( 0x59, TLB_DATA0_4K, 16 ), /* TLB_DATA0 4 KByte pages, fully associative */
+ TLB_ENTRY( 0x5a, TLB_DATA0_2M_4M, 32 ), /* TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative */
+ TLB_ENTRY( 0x5b, TLB_DATA_4K_4M, 64 ), /* TLB_DATA 4 KByte and 4 MByte pages */
+ TLB_ENTRY( 0x5c, TLB_DATA_4K_4M, 128 ), /* TLB_DATA 4 KByte and 4 MByte pages */
+ TLB_ENTRY( 0x5d, TLB_DATA_4K_4M, 256 ), /* TLB_DATA 4 KByte and 4 MByte pages */
+ TLB_ENTRY( 0x61, TLB_INST_4K, 48 ), /* TLB_INST 4 KByte pages, full associative */
+ TLB_ENTRY( 0x63, TLB_DATA_1G_2M_4M, 4 ), /* TLB_DATA 1 GByte pages, 4-way set associative
+ * (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here) */
+ TLB_ENTRY( 0x6b, TLB_DATA_4K, 256 ), /* TLB_DATA 4 KByte pages, 8-way associative */
+ TLB_ENTRY( 0x6c, TLB_DATA_2M_4M, 128 ), /* TLB_DATA 2 MByte or 4 MByte pages, 8-way associative */
+ TLB_ENTRY( 0x6d, TLB_DATA_1G, 16 ), /* TLB_DATA 1 GByte pages, fully associative */
+ TLB_ENTRY( 0x76, TLB_INST_2M_4M, 8 ), /* TLB_INST 2-MByte or 4-MByte pages, fully associative */
+ TLB_ENTRY( 0xb0, TLB_INST_4K, 128 ), /* TLB_INST 4 KByte pages, 4-way set associative */
+ TLB_ENTRY( 0xb1, TLB_INST_2M_4M, 4 ), /* TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries */
+ TLB_ENTRY( 0xb2, TLB_INST_4K, 64 ), /* TLB_INST 4KByte pages, 4-way set associative */
+ TLB_ENTRY( 0xb3, TLB_DATA_4K, 128 ), /* TLB_DATA 4 KByte pages, 4-way set associative */
+ TLB_ENTRY( 0xb4, TLB_DATA_4K, 256 ), /* TLB_DATA 4 KByte pages, 4-way associative */
+ TLB_ENTRY( 0xb5, TLB_INST_4K, 64 ), /* TLB_INST 4 KByte pages, 8-way set associative */
+ TLB_ENTRY( 0xb6, TLB_INST_4K, 128 ), /* TLB_INST 4 KByte pages, 8-way set associative */
+ TLB_ENTRY( 0xba, TLB_DATA_4K, 64 ), /* TLB_DATA 4 KByte pages, 4-way associative */
+ TLB_ENTRY( 0xc0, TLB_DATA_4K_4M, 8 ), /* TLB_DATA 4 KByte and 4 MByte pages, 4-way associative */
+ TLB_ENTRY( 0xc1, STLB_4K_2M, 1024 ), /* STLB 4 KByte and 2 MByte pages, 8-way associative */
+ TLB_ENTRY( 0xc2, TLB_DATA_2M_4M, 16 ), /* TLB_DATA 2 MByte/4MByte pages, 4-way associative */
+ TLB_ENTRY( 0xca, STLB_4K, 512 ), /* STLB 4 KByte pages, 4-way associative */
+};
diff --git a/arch/x86/kernel/cpu/feat_ctl.c b/arch/x86/kernel/cpu/feat_ctl.c
index 4a4118784c13..d69757246bde 100644
--- a/arch/x86/kernel/cpu/feat_ctl.c
+++ b/arch/x86/kernel/cpu/feat_ctl.c
@@ -4,6 +4,7 @@
#include <asm/cpu.h>
#include <asm/cpufeature.h>
#include <asm/msr-index.h>
+#include <asm/msr.h>
#include <asm/processor.h>
#include <asm/vmx.h>
@@ -118,7 +119,7 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
bool enable_vmx;
u64 msr;
- if (rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr)) {
+ if (rdmsrq_safe(MSR_IA32_FEAT_CTL, &msr)) {
clear_cpu_cap(c, X86_FEATURE_VMX);
clear_cpu_cap(c, X86_FEATURE_SGX);
return;
@@ -165,7 +166,7 @@ void init_ia32_feat_ctl(struct cpuinfo_x86 *c)
msr |= FEAT_CTL_SGX_LC_ENABLED;
}
- wrmsrl(MSR_IA32_FEAT_CTL, msr);
+ wrmsrq(MSR_IA32_FEAT_CTL, msr);
update_caps:
set_cpu_cap(c, X86_FEATURE_MSR_IA32_FEAT_CTL);
diff --git a/arch/x86/kernel/cpu/hygon.c b/arch/x86/kernel/cpu/hygon.c
index 6af4a4a90a52..2154f12766fb 100644
--- a/arch/x86/kernel/cpu/hygon.c
+++ b/arch/x86/kernel/cpu/hygon.c
@@ -15,6 +15,7 @@
#include <asm/cacheinfo.h>
#include <asm/spec-ctrl.h>
#include <asm/delay.h>
+#include <asm/msr.h>
#include "cpu.h"
@@ -96,7 +97,7 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c)
if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
u64 val;
- rdmsrl(MSR_K7_HWCR, val);
+ rdmsrq(MSR_K7_HWCR, val);
if (!(val & BIT(24)))
pr_warn(FW_BUG "TSC doesn't count with P0 frequency!\n");
}
@@ -110,7 +111,7 @@ static void bsp_init_hygon(struct cpuinfo_x86 *c)
* Try to cache the base value so further operations can
* avoid RMW. If that faults, do not enable SSBD.
*/
- if (!rdmsrl_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
+ if (!rdmsrq_safe(MSR_AMD64_LS_CFG, &x86_amd_ls_cfg_base)) {
setup_force_cpu_cap(X86_FEATURE_LS_CFG_SSBD);
setup_force_cpu_cap(X86_FEATURE_SSBD);
x86_amd_ls_cfg_ssbd_mask = 1ULL << 10;
@@ -194,7 +195,7 @@ static void init_hygon(struct cpuinfo_x86 *c)
init_hygon_cacheinfo(c);
if (cpu_has(c, X86_FEATURE_SVM)) {
- rdmsrl(MSR_VM_CR, vm_cr);
+ rdmsrq(MSR_VM_CR, vm_cr);
if (vm_cr & SVM_VM_CR_SVM_DIS_MASK) {
pr_notice_once("SVM disabled (by BIOS) in MSR_VM_CR\n");
clear_cpu_cap(c, X86_FEATURE_SVM);
diff --git a/arch/x86/kernel/cpu/intel.c b/arch/x86/kernel/cpu/intel.c
index cdc9813871ef..076eaa41b8c8 100644
--- a/arch/x86/kernel/cpu/intel.c
+++ b/arch/x86/kernel/cpu/intel.c
@@ -6,6 +6,7 @@
#include <linux/minmax.h>
#include <linux/smp.h>
#include <linux/string.h>
+#include <linux/types.h>
#ifdef CONFIG_X86_64
#include <linux/topology.h>
@@ -15,6 +16,7 @@
#include <asm/cpu_device_id.h>
#include <asm/cpufeature.h>
#include <asm/cpu.h>
+#include <asm/cpuid/api.h>
#include <asm/hwcap2.h>
#include <asm/intel-family.h>
#include <asm/microcode.h>
@@ -157,7 +159,7 @@ static void detect_tme_early(struct cpuinfo_x86 *c)
u64 tme_activate;
int keyid_bits;
- rdmsrl(MSR_IA32_TME_ACTIVATE, tme_activate);
+ rdmsrq(MSR_IA32_TME_ACTIVATE, tme_activate);
if (!TME_ACTIVATE_LOCKED(tme_activate) || !TME_ACTIVATE_ENABLED(tme_activate)) {
pr_info_once("x86/tme: not enabled by BIOS\n");
@@ -299,7 +301,7 @@ static void early_init_intel(struct cpuinfo_x86 *c)
* string flag and enhanced fast string capabilities accordingly.
*/
if (c->x86_vfm >= INTEL_PENTIUM_M_DOTHAN) {
- rdmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
+ rdmsrq(MSR_IA32_MISC_ENABLE, misc_enable);
if (misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING) {
/* X86_FEATURE_ERMS is set based on CPUID */
set_cpu_cap(c, X86_FEATURE_REP_GOOD);
@@ -488,7 +490,7 @@ static void init_cpuid_fault(struct cpuinfo_x86 *c)
{
u64 msr;
- if (!rdmsrl_safe(MSR_PLATFORM_INFO, &msr)) {
+ if (!rdmsrq_safe(MSR_PLATFORM_INFO, &msr)) {
if (msr & MSR_PLATFORM_INFO_CPUID_FAULT)
set_cpu_cap(c, X86_FEATURE_CPUID_FAULT);
}
@@ -498,7 +500,7 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
{
u64 msr;
- if (rdmsrl_safe(MSR_MISC_FEATURES_ENABLES, &msr))
+ if (rdmsrq_safe(MSR_MISC_FEATURES_ENABLES, &msr))
return;
/* Clear all MISC features */
@@ -509,7 +511,7 @@ static void init_intel_misc_features(struct cpuinfo_x86 *c)
probe_xeon_phi_r3mwait(c);
msr = this_cpu_read(msr_misc_features_shadow);
- wrmsrl(MSR_MISC_FEATURES_ENABLES, msr);
+ wrmsrq(MSR_MISC_FEATURES_ENABLES, msr);
}
/*
@@ -646,103 +648,11 @@ static unsigned int intel_size_cache(struct cpuinfo_x86 *c, unsigned int size)
}
#endif
-#define TLB_INST_4K 0x01
-#define TLB_INST_4M 0x02
-#define TLB_INST_2M_4M 0x03
-
-#define TLB_INST_ALL 0x05
-#define TLB_INST_1G 0x06
-
-#define TLB_DATA_4K 0x11
-#define TLB_DATA_4M 0x12
-#define TLB_DATA_2M_4M 0x13
-#define TLB_DATA_4K_4M 0x14
-
-#define TLB_DATA_1G 0x16
-#define TLB_DATA_1G_2M_4M 0x17
-
-#define TLB_DATA0_4K 0x21
-#define TLB_DATA0_4M 0x22
-#define TLB_DATA0_2M_4M 0x23
-
-#define STLB_4K 0x41
-#define STLB_4K_2M 0x42
-
-/*
- * All of leaf 0x2's one-byte TLB descriptors implies the same number of
- * entries for their respective TLB types. The 0x63 descriptor is an
- * exception: it implies 4 dTLB entries for 1GB pages 32 dTLB entries
- * for 2MB or 4MB pages. Encode descriptor 0x63 dTLB entry count for
- * 2MB/4MB pages here, as its count for dTLB 1GB pages is already at the
- * intel_tlb_table[] mapping.
- */
-#define TLB_0x63_2M_4M_ENTRIES 32
-
-struct _tlb_table {
- unsigned char descriptor;
- char tlb_type;
- unsigned int entries;
-};
-
-static const struct _tlb_table intel_tlb_table[] = {
- { 0x01, TLB_INST_4K, 32}, /* TLB_INST 4 KByte pages, 4-way set associative */
- { 0x02, TLB_INST_4M, 2}, /* TLB_INST 4 MByte pages, full associative */
- { 0x03, TLB_DATA_4K, 64}, /* TLB_DATA 4 KByte pages, 4-way set associative */
- { 0x04, TLB_DATA_4M, 8}, /* TLB_DATA 4 MByte pages, 4-way set associative */
- { 0x05, TLB_DATA_4M, 32}, /* TLB_DATA 4 MByte pages, 4-way set associative */
- { 0x0b, TLB_INST_4M, 4}, /* TLB_INST 4 MByte pages, 4-way set associative */
- { 0x4f, TLB_INST_4K, 32}, /* TLB_INST 4 KByte pages */
- { 0x50, TLB_INST_ALL, 64}, /* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
- { 0x51, TLB_INST_ALL, 128}, /* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
- { 0x52, TLB_INST_ALL, 256}, /* TLB_INST 4 KByte and 2-MByte or 4-MByte pages */
- { 0x55, TLB_INST_2M_4M, 7}, /* TLB_INST 2-MByte or 4-MByte pages, fully associative */
- { 0x56, TLB_DATA0_4M, 16}, /* TLB_DATA0 4 MByte pages, 4-way set associative */
- { 0x57, TLB_DATA0_4K, 16}, /* TLB_DATA0 4 KByte pages, 4-way associative */
- { 0x59, TLB_DATA0_4K, 16}, /* TLB_DATA0 4 KByte pages, fully associative */
- { 0x5a, TLB_DATA0_2M_4M, 32}, /* TLB_DATA0 2-MByte or 4 MByte pages, 4-way set associative */
- { 0x5b, TLB_DATA_4K_4M, 64}, /* TLB_DATA 4 KByte and 4 MByte pages */
- { 0x5c, TLB_DATA_4K_4M, 128}, /* TLB_DATA 4 KByte and 4 MByte pages */
- { 0x5d, TLB_DATA_4K_4M, 256}, /* TLB_DATA 4 KByte and 4 MByte pages */
- { 0x61, TLB_INST_4K, 48}, /* TLB_INST 4 KByte pages, full associative */
- { 0x63, TLB_DATA_1G_2M_4M, 4}, /* TLB_DATA 1 GByte pages, 4-way set associative
- * (plus 32 entries TLB_DATA 2 MByte or 4 MByte pages, not encoded here) */
- { 0x6b, TLB_DATA_4K, 256}, /* TLB_DATA 4 KByte pages, 8-way associative */
- { 0x6c, TLB_DATA_2M_4M, 128}, /* TLB_DATA 2 MByte or 4 MByte pages, 8-way associative */
- { 0x6d, TLB_DATA_1G, 16}, /* TLB_DATA 1 GByte pages, fully associative */
- { 0x76, TLB_INST_2M_4M, 8}, /* TLB_INST 2-MByte or 4-MByte pages, fully associative */
- { 0xb0, TLB_INST_4K, 128}, /* TLB_INST 4 KByte pages, 4-way set associative */
- { 0xb1, TLB_INST_2M_4M, 4}, /* TLB_INST 2M pages, 4-way, 8 entries or 4M pages, 4-way entries */
- { 0xb2, TLB_INST_4K, 64}, /* TLB_INST 4KByte pages, 4-way set associative */
- { 0xb3, TLB_DATA_4K, 128}, /* TLB_DATA 4 KByte pages, 4-way set associative */
- { 0xb4, TLB_DATA_4K, 256}, /* TLB_DATA 4 KByte pages, 4-way associative */
- { 0xb5, TLB_INST_4K, 64}, /* TLB_INST 4 KByte pages, 8-way set associative */
- { 0xb6, TLB_INST_4K, 128}, /* TLB_INST 4 KByte pages, 8-way set associative */
- { 0xba, TLB_DATA_4K, 64}, /* TLB_DATA 4 KByte pages, 4-way associative */
- { 0xc0, TLB_DATA_4K_4M, 8}, /* TLB_DATA 4 KByte and 4 MByte pages, 4-way associative */
- { 0xc1, STLB_4K_2M, 1024}, /* STLB 4 KByte and 2 MByte pages, 8-way associative */
- { 0xc2, TLB_DATA_2M_4M, 16}, /* TLB_DATA 2 MByte/4MByte pages, 4-way associative */
- { 0xca, STLB_4K, 512}, /* STLB 4 KByte pages, 4-way associative */
- { 0x00, 0, 0 }
-};
-
-static void intel_tlb_lookup(const unsigned char desc)
+static void intel_tlb_lookup(const struct leaf_0x2_table *desc)
{
- unsigned int entries;
- unsigned char k;
-
- if (desc == 0)
- return;
-
- /* look up this descriptor in the table */
- for (k = 0; intel_tlb_table[k].descriptor != desc &&
- intel_tlb_table[k].descriptor != 0; k++)
- ;
+ short entries = desc->entries;
- if (intel_tlb_table[k].tlb_type == 0)
- return;
-
- entries = intel_tlb_table[k].entries;
- switch (intel_tlb_table[k].tlb_type) {
+ switch (desc->t_type) {
case STLB_4K:
tlb_lli_4k = max(tlb_lli_4k, entries);
tlb_lld_4k = max(tlb_lld_4k, entries);
@@ -799,28 +709,16 @@ static void intel_tlb_lookup(const unsigned char desc)
static void intel_detect_tlb(struct cpuinfo_x86 *c)
{
- int i, j, n;
- unsigned int regs[4];
- unsigned char *desc = (unsigned char *)regs;
+ const struct leaf_0x2_table *desc;
+ union leaf_0x2_regs regs;
+ u8 *ptr;
if (c->cpuid_level < 2)
return;
- /* Number of times to iterate */
- n = cpuid_eax(2) & 0xFF;
-
- for (i = 0 ; i < n ; i++) {
- cpuid(2, &regs[0], &regs[1], &regs[2], &regs[3]);
-
- /* If bit 31 is set, this is an unknown format */
- for (j = 0 ; j < 4 ; j++)
- if (regs[j] & (1 << 31))
- regs[j] = 0;
-
- /* Byte 0 is level count, not a descriptor */
- for (j = 1 ; j < 16 ; j++)
- intel_tlb_lookup(desc[j]);
- }
+ cpuid_leaf_0x2(&regs);
+ for_each_cpuid_0x2_desc(regs, ptr, desc)
+ intel_tlb_lookup(desc);
}
static const struct cpu_dev intel_cpu_dev = {
diff --git a/arch/x86/kernel/cpu/intel_epb.c b/arch/x86/kernel/cpu/intel_epb.c
index 30b1d63b97f3..bc7671f920a7 100644
--- a/arch/x86/kernel/cpu/intel_epb.c
+++ b/arch/x86/kernel/cpu/intel_epb.c
@@ -79,7 +79,7 @@ static int intel_epb_save(void)
{
u64 epb;
- rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+ rdmsrq(MSR_IA32_ENERGY_PERF_BIAS, epb);
/*
* Ensure that saved_epb will always be nonzero after this write even if
* the EPB value read from the MSR is 0.
@@ -94,7 +94,7 @@ static void intel_epb_restore(void)
u64 val = this_cpu_read(saved_epb);
u64 epb;
- rdmsrl(MSR_IA32_ENERGY_PERF_BIAS, epb);
+ rdmsrq(MSR_IA32_ENERGY_PERF_BIAS, epb);
if (val) {
val &= EPB_MASK;
} else {
@@ -111,7 +111,7 @@ static void intel_epb_restore(void)
pr_warn_once("ENERGY_PERF_BIAS: Set to 'normal', was 'performance'\n");
}
}
- wrmsrl(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~EPB_MASK) | val);
+ wrmsrq(MSR_IA32_ENERGY_PERF_BIAS, (epb & ~EPB_MASK) | val);
}
static struct syscore_ops intel_epb_syscore_ops = {
@@ -135,7 +135,7 @@ static ssize_t energy_perf_bias_show(struct device *dev,
u64 epb;
int ret;
- ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+ ret = rdmsrq_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
if (ret < 0)
return ret;
@@ -157,11 +157,11 @@ static ssize_t energy_perf_bias_store(struct device *dev,
else if (kstrtou64(buf, 0, &val) || val > MAX_EPB)
return -EINVAL;
- ret = rdmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
+ ret = rdmsrq_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS, &epb);
if (ret < 0)
return ret;
- ret = wrmsrl_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS,
+ ret = wrmsrq_on_cpu(cpu, MSR_IA32_ENERGY_PERF_BIAS,
(epb & ~EPB_MASK) | val);
if (ret < 0)
return ret;
diff --git a/arch/x86/kernel/cpu/mce/amd.c b/arch/x86/kernel/cpu/mce/amd.c
index 1075a90141da..5c4eb28c3ac9 100644
--- a/arch/x86/kernel/cpu/mce/amd.c
+++ b/arch/x86/kernel/cpu/mce/amd.c
@@ -350,7 +350,6 @@ static void smca_configure(unsigned int bank, unsigned int cpu)
struct thresh_restart {
struct threshold_block *b;
- int reset;
int set_lvt_off;
int lvt_off;
u16 old_limit;
@@ -432,13 +431,13 @@ static void threshold_restart_bank(void *_tr)
rdmsr(tr->b->address, lo, hi);
- if (tr->b->threshold_limit < (hi & THRESHOLD_MAX))
- tr->reset = 1; /* limit cannot be lower than err count */
-
- if (tr->reset) { /* reset err count and overflow bit */
- hi =
- (hi & ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI)) |
- (THRESHOLD_MAX - tr->b->threshold_limit);
+ /*
+ * Reset error count and overflow bit.
+ * This is done during init or after handling an interrupt.
+ */
+ if (hi & MASK_OVERFLOW_HI || tr->set_lvt_off) {
+ hi &= ~(MASK_ERR_COUNT_HI | MASK_OVERFLOW_HI);
+ hi |= THRESHOLD_MAX - tr->b->threshold_limit;
} else if (tr->old_limit) { /* change limit w/o reset */
int new_count = (hi & THRESHOLD_MAX) +
(tr->old_limit - tr->b->threshold_limit);
@@ -662,12 +661,12 @@ static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
return;
}
- rdmsrl(MSR_K7_HWCR, hwcr);
+ rdmsrq(MSR_K7_HWCR, hwcr);
/* McStatusWrEn has to be set */
need_toggle = !(hwcr & BIT(18));
if (need_toggle)
- wrmsrl(MSR_K7_HWCR, hwcr | BIT(18));
+ wrmsrq(MSR_K7_HWCR, hwcr | BIT(18));
/* Clear CntP bit safely */
for (i = 0; i < num_msrs; i++)
@@ -675,7 +674,7 @@ static void disable_err_thresholding(struct cpuinfo_x86 *c, unsigned int bank)
/* restore old settings */
if (need_toggle)
- wrmsrl(MSR_K7_HWCR, hwcr);
+ wrmsrq(MSR_K7_HWCR, hwcr);
}
/* cpu init entry point, called from mce.c with preempt off */
@@ -805,12 +804,12 @@ static void __log_error(unsigned int bank, u64 status, u64 addr, u64 misc)
}
if (mce_flags.smca) {
- rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), m->ipid);
+ rdmsrq(MSR_AMD64_SMCA_MCx_IPID(bank), m->ipid);
if (m->status & MCI_STATUS_SYNDV) {
- rdmsrl(MSR_AMD64_SMCA_MCx_SYND(bank), m->synd);
- rdmsrl(MSR_AMD64_SMCA_MCx_SYND1(bank), err.vendor.amd.synd1);
- rdmsrl(MSR_AMD64_SMCA_MCx_SYND2(bank), err.vendor.amd.synd2);
+ rdmsrq(MSR_AMD64_SMCA_MCx_SYND(bank), m->synd);
+ rdmsrq(MSR_AMD64_SMCA_MCx_SYND1(bank), err.vendor.amd.synd1);
+ rdmsrq(MSR_AMD64_SMCA_MCx_SYND2(bank), err.vendor.amd.synd2);
}
}
@@ -834,16 +833,16 @@ _log_error_bank(unsigned int bank, u32 msr_stat, u32 msr_addr, u64 misc)
{
u64 status, addr = 0;
- rdmsrl(msr_stat, status);
+ rdmsrq(msr_stat, status);
if (!(status & MCI_STATUS_VAL))
return false;
if (status & MCI_STATUS_ADDRV)
- rdmsrl(msr_addr, addr);
+ rdmsrq(msr_addr, addr);
__log_error(bank, status, addr, misc);
- wrmsrl(msr_stat, 0);
+ wrmsrq(msr_stat, 0);
return status & MCI_STATUS_DEFERRED;
}
@@ -862,7 +861,7 @@ static bool _log_error_deferred(unsigned int bank, u32 misc)
return true;
/* Clear MCA_DESTAT if the deferred error was logged from MCA_STATUS. */
- wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0);
+ wrmsrq(MSR_AMD64_SMCA_MCx_DESTAT(bank), 0);
return true;
}
@@ -1113,13 +1112,20 @@ static const char *get_name(unsigned int cpu, unsigned int bank, struct threshol
}
bank_type = smca_get_bank_type(cpu, bank);
- if (bank_type >= N_SMCA_BANK_TYPES)
- return NULL;
if (b && (bank_type == SMCA_UMC || bank_type == SMCA_UMC_V2)) {
if (b->block < ARRAY_SIZE(smca_umc_block_names))
return smca_umc_block_names[b->block];
- return NULL;
+ }
+
+ if (b && b->block) {
+ snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_block_%u", b->block);
+ return buf_mcatype;
+ }
+
+ if (bank_type >= N_SMCA_BANK_TYPES) {
+ snprintf(buf_mcatype, MAX_MCATYPE_NAME_LEN, "th_bank_%u", bank);
+ return buf_mcatype;
}
if (per_cpu(smca_bank_counts, cpu)[bank_type] == 1)
diff --git a/arch/x86/kernel/cpu/mce/core.c b/arch/x86/kernel/cpu/mce/core.c
index f6fd71b64b66..4da4eab56c81 100644
--- a/arch/x86/kernel/cpu/mce/core.c
+++ b/arch/x86/kernel/cpu/mce/core.c
@@ -121,7 +121,7 @@ void mce_prep_record_common(struct mce *m)
{
m->cpuid = cpuid_eax(1);
m->cpuvendor = boot_cpu_data.x86_vendor;
- m->mcgcap = __rdmsr(MSR_IA32_MCG_CAP);
+ m->mcgcap = native_rdmsrq(MSR_IA32_MCG_CAP);
/* need the internal __ version to avoid deadlocks */
m->time = __ktime_get_real_seconds();
}
@@ -388,9 +388,9 @@ void ex_handler_msr_mce(struct pt_regs *regs, bool wrmsr)
}
/* MSR access wrappers used for error injection */
-noinstr u64 mce_rdmsrl(u32 msr)
+noinstr u64 mce_rdmsrq(u32 msr)
{
- DECLARE_ARGS(val, low, high);
+ EAX_EDX_DECLARE_ARGS(val, low, high);
if (__this_cpu_read(injectm.finished)) {
int offset;
@@ -423,7 +423,7 @@ noinstr u64 mce_rdmsrl(u32 msr)
return EAX_EDX_VAL(val, low, high);
}
-static noinstr void mce_wrmsrl(u32 msr, u64 v)
+static noinstr void mce_wrmsrq(u32 msr, u64 v)
{
u32 low, high;
@@ -444,7 +444,7 @@ static noinstr void mce_wrmsrl(u32 msr, u64 v)
low = (u32)v;
high = (u32)(v >> 32);
- /* See comment in mce_rdmsrl() */
+ /* See comment in mce_rdmsrq() */
asm volatile("1: wrmsr\n"
"2:\n"
_ASM_EXTABLE_TYPE(1b, 2b, EX_TYPE_WRMSR_IN_MCE)
@@ -468,7 +468,7 @@ static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs
instrumentation_end();
m = &err->m;
- m->mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
+ m->mcgstatus = mce_rdmsrq(MSR_IA32_MCG_STATUS);
if (regs) {
/*
* Get the address of the instruction at the time of
@@ -488,7 +488,7 @@ static noinstr void mce_gather_info(struct mce_hw_err *err, struct pt_regs *regs
}
/* Use accurate RIP reporting if available. */
if (mca_cfg.rip_msr)
- m->ip = mce_rdmsrl(mca_cfg.rip_msr);
+ m->ip = mce_rdmsrq(mca_cfg.rip_msr);
}
}
@@ -684,10 +684,10 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
struct mce *m = &err->m;
if (m->status & MCI_STATUS_MISCV)
- m->misc = mce_rdmsrl(mca_msr_reg(i, MCA_MISC));
+ m->misc = mce_rdmsrq(mca_msr_reg(i, MCA_MISC));
if (m->status & MCI_STATUS_ADDRV) {
- m->addr = mce_rdmsrl(mca_msr_reg(i, MCA_ADDR));
+ m->addr = mce_rdmsrq(mca_msr_reg(i, MCA_ADDR));
/*
* Mask the reported address by the reported granularity.
@@ -702,12 +702,12 @@ static noinstr void mce_read_aux(struct mce_hw_err *err, int i)
}
if (mce_flags.smca) {
- m->ipid = mce_rdmsrl(MSR_AMD64_SMCA_MCx_IPID(i));
+ m->ipid = mce_rdmsrq(MSR_AMD64_SMCA_MCx_IPID(i));
if (m->status & MCI_STATUS_SYNDV) {
- m->synd = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND(i));
- err->vendor.amd.synd1 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND1(i));
- err->vendor.amd.synd2 = mce_rdmsrl(MSR_AMD64_SMCA_MCx_SYND2(i));
+ m->synd = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND(i));
+ err->vendor.amd.synd1 = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND1(i));
+ err->vendor.amd.synd2 = mce_rdmsrq(MSR_AMD64_SMCA_MCx_SYND2(i));
}
}
}
@@ -753,7 +753,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
m->bank = i;
barrier();
- m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+ m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
/*
* Update storm tracking here, before checking for the
@@ -829,7 +829,7 @@ clear_it:
/*
* Clear state for this bank.
*/
- mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+ mce_wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
}
/*
@@ -887,8 +887,8 @@ quirk_sandybridge_ifu(int bank, struct mce *m, struct pt_regs *regs)
*/
static noinstr bool quirk_skylake_repmov(void)
{
- u64 mcgstatus = mce_rdmsrl(MSR_IA32_MCG_STATUS);
- u64 misc_enable = mce_rdmsrl(MSR_IA32_MISC_ENABLE);
+ u64 mcgstatus = mce_rdmsrq(MSR_IA32_MCG_STATUS);
+ u64 misc_enable = mce_rdmsrq(MSR_IA32_MISC_ENABLE);
u64 mc1_status;
/*
@@ -899,7 +899,7 @@ static noinstr bool quirk_skylake_repmov(void)
!(misc_enable & MSR_IA32_MISC_ENABLE_FAST_STRING))
return false;
- mc1_status = mce_rdmsrl(MSR_IA32_MCx_STATUS(1));
+ mc1_status = mce_rdmsrq(MSR_IA32_MCx_STATUS(1));
/* Check for a software-recoverable data fetch error. */
if ((mc1_status &
@@ -910,8 +910,8 @@ static noinstr bool quirk_skylake_repmov(void)
MCI_STATUS_ADDRV | MCI_STATUS_MISCV |
MCI_STATUS_AR | MCI_STATUS_S)) {
misc_enable &= ~MSR_IA32_MISC_ENABLE_FAST_STRING;
- mce_wrmsrl(MSR_IA32_MISC_ENABLE, misc_enable);
- mce_wrmsrl(MSR_IA32_MCx_STATUS(1), 0);
+ mce_wrmsrq(MSR_IA32_MISC_ENABLE, misc_enable);
+ mce_wrmsrq(MSR_IA32_MCx_STATUS(1), 0);
instrumentation_begin();
pr_err_once("Erratum detected, disable fast string copy instructions.\n");
@@ -955,7 +955,7 @@ static __always_inline int mce_no_way_out(struct mce_hw_err *err, char **msg, un
int i;
for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
- m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+ m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
if (!(m->status & MCI_STATUS_VAL))
continue;
@@ -1274,7 +1274,7 @@ static __always_inline void mce_clear_state(unsigned long *toclear)
for (i = 0; i < this_cpu_read(mce_num_banks); i++) {
if (arch_test_bit(i, toclear))
- mce_wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+ mce_wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
}
}
@@ -1298,7 +1298,7 @@ static noinstr bool mce_check_crashing_cpu(void)
(crashing_cpu != -1 && crashing_cpu != cpu)) {
u64 mcgstatus;
- mcgstatus = __rdmsr(MSR_IA32_MCG_STATUS);
+ mcgstatus = native_rdmsrq(MSR_IA32_MCG_STATUS);
if (boot_cpu_data.x86_vendor == X86_VENDOR_ZHAOXIN) {
if (mcgstatus & MCG_STATUS_LMCES)
@@ -1306,7 +1306,7 @@ static noinstr bool mce_check_crashing_cpu(void)
}
if (mcgstatus & MCG_STATUS_RIPV) {
- __wrmsr(MSR_IA32_MCG_STATUS, 0, 0);
+ native_wrmsrq(MSR_IA32_MCG_STATUS, 0);
return true;
}
}
@@ -1335,7 +1335,7 @@ __mc_scan_banks(struct mce_hw_err *err, struct pt_regs *regs,
m->addr = 0;
m->bank = i;
- m->status = mce_rdmsrl(mca_msr_reg(i, MCA_STATUS));
+ m->status = mce_rdmsrq(mca_msr_reg(i, MCA_STATUS));
if (!(m->status & MCI_STATUS_VAL))
continue;
@@ -1693,7 +1693,7 @@ out:
instrumentation_end();
clear:
- mce_wrmsrl(MSR_IA32_MCG_STATUS, 0);
+ mce_wrmsrq(MSR_IA32_MCG_STATUS, 0);
}
EXPORT_SYMBOL_GPL(do_machine_check);
@@ -1740,6 +1740,11 @@ static void mc_poll_banks_default(void)
void (*mc_poll_banks)(void) = mc_poll_banks_default;
+static bool should_enable_timer(unsigned long iv)
+{
+ return !mca_cfg.ignore_ce && iv;
+}
+
static void mce_timer_fn(struct timer_list *t)
{
struct timer_list *cpu_t = this_cpu_ptr(&mce_timer);
@@ -1763,7 +1768,7 @@ static void mce_timer_fn(struct timer_list *t)
if (mce_get_storm_mode()) {
__start_timer(t, HZ);
- } else {
+ } else if (should_enable_timer(iv)) {
__this_cpu_write(mce_next_interval, iv);
__start_timer(t, iv);
}
@@ -1822,7 +1827,7 @@ static void __mcheck_cpu_cap_init(void)
u64 cap;
u8 b;
- rdmsrl(MSR_IA32_MCG_CAP, cap);
+ rdmsrq(MSR_IA32_MCG_CAP, cap);
b = cap & MCG_BANKCNT_MASK;
@@ -1863,7 +1868,7 @@ static void __mcheck_cpu_init_generic(void)
cr4_set_bits(X86_CR4_MCE);
- rdmsrl(MSR_IA32_MCG_CAP, cap);
+ rdmsrq(MSR_IA32_MCG_CAP, cap);
if (cap & MCG_CTL_P)
wrmsr(MSR_IA32_MCG_CTL, 0xffffffff, 0xffffffff);
}
@@ -1878,8 +1883,8 @@ static void __mcheck_cpu_init_clear_banks(void)
if (!b->init)
continue;
- wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
- wrmsrl(mca_msr_reg(i, MCA_STATUS), 0);
+ wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
+ wrmsrq(mca_msr_reg(i, MCA_STATUS), 0);
}
}
@@ -1905,7 +1910,7 @@ static void __mcheck_cpu_check_banks(void)
if (!b->init)
continue;
- rdmsrl(mca_msr_reg(i, MCA_CTL), msrval);
+ rdmsrq(mca_msr_reg(i, MCA_CTL), msrval);
b->init = !!msrval;
}
}
@@ -2156,11 +2161,10 @@ static void mce_start_timer(struct timer_list *t)
{
unsigned long iv = check_interval * HZ;
- if (mca_cfg.ignore_ce || !iv)
- return;
-
- this_cpu_write(mce_next_interval, iv);
- __start_timer(t, iv);
+ if (should_enable_timer(iv)) {
+ this_cpu_write(mce_next_interval, iv);
+ __start_timer(t, iv);
+ }
}
static void __mcheck_cpu_setup_timer(void)
@@ -2436,7 +2440,7 @@ static void mce_disable_error_reporting(void)
struct mce_bank *b = &mce_banks[i];
if (b->init)
- wrmsrl(mca_msr_reg(i, MCA_CTL), 0);
+ wrmsrq(mca_msr_reg(i, MCA_CTL), 0);
}
return;
}
@@ -2786,7 +2790,7 @@ static void mce_reenable_cpu(void)
struct mce_bank *b = &mce_banks[i];
if (b->init)
- wrmsrl(mca_msr_reg(i, MCA_CTL), b->ctl);
+ wrmsrq(mca_msr_reg(i, MCA_CTL), b->ctl);
}
}
@@ -2801,15 +2805,9 @@ static int mce_cpu_dead(unsigned int cpu)
static int mce_cpu_online(unsigned int cpu)
{
struct timer_list *t = this_cpu_ptr(&mce_timer);
- int ret;
mce_device_create(cpu);
-
- ret = mce_threshold_create_device(cpu);
- if (ret) {
- mce_device_remove(cpu);
- return ret;
- }
+ mce_threshold_create_device(cpu);
mce_reenable_cpu();
mce_start_timer(t);
return 0;
diff --git a/arch/x86/kernel/cpu/mce/inject.c b/arch/x86/kernel/cpu/mce/inject.c
index 06e3cf7229ce..d02c4f556cd0 100644
--- a/arch/x86/kernel/cpu/mce/inject.c
+++ b/arch/x86/kernel/cpu/mce/inject.c
@@ -24,10 +24,11 @@
#include <linux/pci.h>
#include <linux/uaccess.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
#include <asm/apic.h>
#include <asm/irq_vectors.h>
#include <asm/mce.h>
+#include <asm/msr.h>
#include <asm/nmi.h>
#include <asm/smp.h>
@@ -475,27 +476,27 @@ static void prepare_msrs(void *info)
struct mce m = *(struct mce *)info;
u8 b = m.bank;
- wrmsrl(MSR_IA32_MCG_STATUS, m.mcgstatus);
+ wrmsrq(MSR_IA32_MCG_STATUS, m.mcgstatus);
if (boot_cpu_has(X86_FEATURE_SMCA)) {
if (m.inject_flags == DFR_INT_INJ) {
- wrmsrl(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status);
- wrmsrl(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr);
+ wrmsrq(MSR_AMD64_SMCA_MCx_DESTAT(b), m.status);
+ wrmsrq(MSR_AMD64_SMCA_MCx_DEADDR(b), m.addr);
} else {
- wrmsrl(MSR_AMD64_SMCA_MCx_STATUS(b), m.status);
- wrmsrl(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr);
+ wrmsrq(MSR_AMD64_SMCA_MCx_STATUS(b), m.status);
+ wrmsrq(MSR_AMD64_SMCA_MCx_ADDR(b), m.addr);
}
- wrmsrl(MSR_AMD64_SMCA_MCx_SYND(b), m.synd);
+ wrmsrq(MSR_AMD64_SMCA_MCx_SYND(b), m.synd);
if (m.misc)
- wrmsrl(MSR_AMD64_SMCA_MCx_MISC(b), m.misc);
+ wrmsrq(MSR_AMD64_SMCA_MCx_MISC(b), m.misc);
} else {
- wrmsrl(MSR_IA32_MCx_STATUS(b), m.status);
- wrmsrl(MSR_IA32_MCx_ADDR(b), m.addr);
+ wrmsrq(MSR_IA32_MCx_STATUS(b), m.status);
+ wrmsrq(MSR_IA32_MCx_ADDR(b), m.addr);
if (m.misc)
- wrmsrl(MSR_IA32_MCx_MISC(b), m.misc);
+ wrmsrq(MSR_IA32_MCx_MISC(b), m.misc);
}
}
@@ -589,7 +590,7 @@ static int inj_bank_set(void *data, u64 val)
u64 cap;
/* Get bank count on target CPU so we can handle non-uniform values. */
- rdmsrl_on_cpu(m->extcpu, MSR_IA32_MCG_CAP, &cap);
+ rdmsrq_on_cpu(m->extcpu, MSR_IA32_MCG_CAP, &cap);
n_banks = cap & MCG_BANKCNT_MASK;
if (val >= n_banks) {
@@ -613,7 +614,7 @@ static int inj_bank_set(void *data, u64 val)
if (cpu_feature_enabled(X86_FEATURE_SMCA)) {
u64 ipid;
- if (rdmsrl_on_cpu(m->extcpu, MSR_AMD64_SMCA_MCx_IPID(val), &ipid)) {
+ if (rdmsrq_on_cpu(m->extcpu, MSR_AMD64_SMCA_MCx_IPID(val), &ipid)) {
pr_err("Error reading IPID on CPU%d\n", m->extcpu);
return -EINVAL;
}
@@ -741,15 +742,15 @@ static void check_hw_inj_possible(void)
u64 status = MCI_STATUS_VAL, ipid;
/* Check whether bank is populated */
- rdmsrl(MSR_AMD64_SMCA_MCx_IPID(bank), ipid);
+ rdmsrq(MSR_AMD64_SMCA_MCx_IPID(bank), ipid);
if (!ipid)
continue;
toggle_hw_mce_inject(cpu, true);
- wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), status);
- rdmsrl_safe(mca_msr_reg(bank, MCA_STATUS), &status);
- wrmsrl_safe(mca_msr_reg(bank, MCA_STATUS), 0);
+ wrmsrq_safe(mca_msr_reg(bank, MCA_STATUS), status);
+ rdmsrq_safe(mca_msr_reg(bank, MCA_STATUS), &status);
+ wrmsrq_safe(mca_msr_reg(bank, MCA_STATUS), 0);
if (!status) {
hw_injection_possible = false;
diff --git a/arch/x86/kernel/cpu/mce/intel.c b/arch/x86/kernel/cpu/mce/intel.c
index f863df0ff42c..9b149b9c4109 100644
--- a/arch/x86/kernel/cpu/mce/intel.c
+++ b/arch/x86/kernel/cpu/mce/intel.c
@@ -94,7 +94,7 @@ static bool cmci_supported(int *banks)
if (!boot_cpu_has(X86_FEATURE_APIC) || lapic_get_maxlvt() < 6)
return false;
- rdmsrl(MSR_IA32_MCG_CAP, cap);
+ rdmsrq(MSR_IA32_MCG_CAP, cap);
*banks = min_t(unsigned, MAX_NR_BANKS, cap & MCG_BANKCNT_MASK);
return !!(cap & MCG_CMCI_P);
}
@@ -106,7 +106,7 @@ static bool lmce_supported(void)
if (mca_cfg.lmce_disabled)
return false;
- rdmsrl(MSR_IA32_MCG_CAP, tmp);
+ rdmsrq(MSR_IA32_MCG_CAP, tmp);
/*
* LMCE depends on recovery support in the processor. Hence both
@@ -123,7 +123,7 @@ static bool lmce_supported(void)
* WARN if the MSR isn't locked as init_ia32_feat_ctl() unconditionally
* locks the MSR in the event that it wasn't already locked by BIOS.
*/
- rdmsrl(MSR_IA32_FEAT_CTL, tmp);
+ rdmsrq(MSR_IA32_FEAT_CTL, tmp);
if (WARN_ON_ONCE(!(tmp & FEAT_CTL_LOCKED)))
return false;
@@ -141,9 +141,9 @@ static void cmci_set_threshold(int bank, int thresh)
u64 val;
raw_spin_lock_irqsave(&cmci_discover_lock, flags);
- rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ rdmsrq(MSR_IA32_MCx_CTL2(bank), val);
val &= ~MCI_CTL2_CMCI_THRESHOLD_MASK;
- wrmsrl(MSR_IA32_MCx_CTL2(bank), val | thresh);
+ wrmsrq(MSR_IA32_MCx_CTL2(bank), val | thresh);
raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
}
@@ -184,7 +184,7 @@ static bool cmci_skip_bank(int bank, u64 *val)
if (test_bit(bank, mce_banks_ce_disabled))
return true;
- rdmsrl(MSR_IA32_MCx_CTL2(bank), *val);
+ rdmsrq(MSR_IA32_MCx_CTL2(bank), *val);
/* Already owned by someone else? */
if (*val & MCI_CTL2_CMCI_EN) {
@@ -232,8 +232,8 @@ static void cmci_claim_bank(int bank, u64 val, int bios_zero_thresh, int *bios_w
struct mca_storm_desc *storm = this_cpu_ptr(&storm_desc);
val |= MCI_CTL2_CMCI_EN;
- wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
- rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ wrmsrq(MSR_IA32_MCx_CTL2(bank), val);
+ rdmsrq(MSR_IA32_MCx_CTL2(bank), val);
/* If the enable bit did not stick, this bank should be polled. */
if (!(val & MCI_CTL2_CMCI_EN)) {
@@ -324,9 +324,9 @@ static void __cmci_disable_bank(int bank)
if (!test_bit(bank, this_cpu_ptr(mce_banks_owned)))
return;
- rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ rdmsrq(MSR_IA32_MCx_CTL2(bank), val);
val &= ~MCI_CTL2_CMCI_EN;
- wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+ wrmsrq(MSR_IA32_MCx_CTL2(bank), val);
__clear_bit(bank, this_cpu_ptr(mce_banks_owned));
if ((val & MCI_CTL2_CMCI_THRESHOLD_MASK) == CMCI_STORM_THRESHOLD)
@@ -430,10 +430,10 @@ void intel_init_lmce(void)
if (!lmce_supported())
return;
- rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+ rdmsrq(MSR_IA32_MCG_EXT_CTL, val);
if (!(val & MCG_EXT_CTL_LMCE_EN))
- wrmsrl(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
+ wrmsrq(MSR_IA32_MCG_EXT_CTL, val | MCG_EXT_CTL_LMCE_EN);
}
void intel_clear_lmce(void)
@@ -443,9 +443,9 @@ void intel_clear_lmce(void)
if (!lmce_supported())
return;
- rdmsrl(MSR_IA32_MCG_EXT_CTL, val);
+ rdmsrq(MSR_IA32_MCG_EXT_CTL, val);
val &= ~MCG_EXT_CTL_LMCE_EN;
- wrmsrl(MSR_IA32_MCG_EXT_CTL, val);
+ wrmsrq(MSR_IA32_MCG_EXT_CTL, val);
}
/*
@@ -460,10 +460,10 @@ static void intel_imc_init(struct cpuinfo_x86 *c)
case INTEL_SANDYBRIDGE_X:
case INTEL_IVYBRIDGE_X:
case INTEL_HASWELL_X:
- if (rdmsrl_safe(MSR_ERROR_CONTROL, &error_control))
+ if (rdmsrq_safe(MSR_ERROR_CONTROL, &error_control))
return;
error_control |= 2;
- wrmsrl_safe(MSR_ERROR_CONTROL, error_control);
+ wrmsrq_safe(MSR_ERROR_CONTROL, error_control);
break;
}
}
@@ -478,6 +478,7 @@ void mce_intel_feature_init(struct cpuinfo_x86 *c)
void mce_intel_feature_clear(struct cpuinfo_x86 *c)
{
intel_clear_lmce();
+ cmci_clear();
}
bool intel_filter_mce(struct mce *m)
diff --git a/arch/x86/kernel/cpu/mce/internal.h b/arch/x86/kernel/cpu/mce/internal.h
index 95a504ece43e..b5ba598e54cb 100644
--- a/arch/x86/kernel/cpu/mce/internal.h
+++ b/arch/x86/kernel/cpu/mce/internal.h
@@ -312,7 +312,7 @@ static __always_inline void pentium_machine_check(struct pt_regs *regs) {}
static __always_inline void winchip_machine_check(struct pt_regs *regs) {}
#endif
-noinstr u64 mce_rdmsrl(u32 msr);
+noinstr u64 mce_rdmsrq(u32 msr);
static __always_inline u32 mca_msr_reg(int bank, enum mca_msr reg)
{
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index 96cb992d50ef..097e39327942 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -217,7 +217,6 @@ static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsi
{
struct patch_digest *pd = NULL;
u8 digest[SHA256_DIGEST_SIZE];
- struct sha256_state s;
int i;
if (x86_family(bsp_cpuid_1_eax) < 0x17)
@@ -235,9 +234,7 @@ static bool verify_sha256_digest(u32 patch_id, u32 cur_rev, const u8 *data, unsi
return false;
}
- sha256_init(&s);
- sha256_update(&s, data, len);
- sha256_final(&s, digest);
+ sha256(data, len, digest);
if (memcmp(digest, pd->sha256, sizeof(digest))) {
pr_err("Patch 0x%x SHA256 digest mismatch!\n", patch_id);
@@ -607,7 +604,7 @@ static bool __apply_microcode_amd(struct microcode_amd *mc, u32 *cur_rev,
if (!verify_sha256_digest(mc->hdr.patch_id, *cur_rev, (const u8 *)p_addr, psize))
return false;
- native_wrmsrl(MSR_AMD64_PATCH_LOADER, p_addr);
+ native_wrmsrq(MSR_AMD64_PATCH_LOADER, p_addr);
if (x86_family(bsp_cpuid_1_eax) == 0x17) {
unsigned long p_addr_end = p_addr + psize - 1;
@@ -1178,11 +1175,18 @@ static void microcode_fini_cpu_amd(int cpu)
uci->mc = NULL;
}
+static void finalize_late_load_amd(int result)
+{
+ if (result)
+ cleanup();
+}
+
static struct microcode_ops microcode_amd_ops = {
.request_microcode_fw = request_microcode_amd,
.collect_cpu_info = collect_cpu_info_amd,
.apply_microcode = apply_microcode_amd,
.microcode_fini_cpu = microcode_fini_cpu_amd,
+ .finalize_late_load = finalize_late_load_amd,
.nmi_safe = true,
};
diff --git a/arch/x86/kernel/cpu/microcode/amd_shas.c b/arch/x86/kernel/cpu/microcode/amd_shas.c
index 2a1655b1fdd8..1fd349cfc802 100644
--- a/arch/x86/kernel/cpu/microcode/amd_shas.c
+++ b/arch/x86/kernel/cpu/microcode/amd_shas.c
@@ -231,6 +231,13 @@ static const struct patch_digest phashes[] = {
0x0d,0x5b,0x65,0x34,0x69,0xb2,0x62,0x21,
}
},
+ { 0xa0011d7, {
+ 0x35,0x07,0xcd,0x40,0x94,0xbc,0x81,0x6b,
+ 0xfc,0x61,0x56,0x1a,0xe2,0xdb,0x96,0x12,
+ 0x1c,0x1c,0x31,0xb1,0x02,0x6f,0xe5,0xd2,
+ 0xfe,0x1b,0x04,0x03,0x2c,0x8f,0x4c,0x36,
+ }
+ },
{ 0xa001223, {
0xfb,0x32,0x5f,0xc6,0x83,0x4f,0x8c,0xb8,
0xa4,0x05,0xf9,0x71,0x53,0x01,0x16,0xc4,
@@ -294,6 +301,13 @@ static const struct patch_digest phashes[] = {
0xc0,0xcd,0x33,0xf2,0x8d,0xf9,0xef,0x59,
}
},
+ { 0xa00123b, {
+ 0xef,0xa1,0x1e,0x71,0xf1,0xc3,0x2c,0xe2,
+ 0xc3,0xef,0x69,0x41,0x7a,0x54,0xca,0xc3,
+ 0x8f,0x62,0x84,0xee,0xc2,0x39,0xd9,0x28,
+ 0x95,0xa7,0x12,0x49,0x1e,0x30,0x71,0x72,
+ }
+ },
{ 0xa00820c, {
0xa8,0x0c,0x81,0xc0,0xa6,0x00,0xe7,0xf3,
0x5f,0x65,0xd3,0xb9,0x6f,0xea,0x93,0x63,
@@ -301,6 +315,13 @@ static const struct patch_digest phashes[] = {
0xe1,0x3b,0x8d,0xb2,0xf8,0x22,0x03,0xe2,
}
},
+ { 0xa00820d, {
+ 0xf9,0x2a,0xc0,0xf4,0x9e,0xa4,0x87,0xa4,
+ 0x7d,0x87,0x00,0xfd,0xab,0xda,0x19,0xca,
+ 0x26,0x51,0x32,0xc1,0x57,0x91,0xdf,0xc1,
+ 0x05,0xeb,0x01,0x7c,0x5a,0x95,0x21,0xb7,
+ }
+ },
{ 0xa10113e, {
0x05,0x3c,0x66,0xd7,0xa9,0x5a,0x33,0x10,
0x1b,0xf8,0x9c,0x8f,0xed,0xfc,0xa7,0xa0,
@@ -322,6 +343,13 @@ static const struct patch_digest phashes[] = {
0xf1,0x5e,0xb0,0xde,0xb4,0x98,0xae,0xc4,
}
},
+ { 0xa10114c, {
+ 0x9e,0xb6,0xa2,0xd9,0x87,0x38,0xc5,0x64,
+ 0xd8,0x88,0xfa,0x78,0x98,0xf9,0x6f,0x74,
+ 0x39,0x90,0x1b,0xa5,0xcf,0x5e,0xb4,0x2a,
+ 0x02,0xff,0xd4,0x8c,0x71,0x8b,0xe2,0xc0,
+ }
+ },
{ 0xa10123e, {
0x03,0xb9,0x2c,0x76,0x48,0x93,0xc9,0x18,
0xfb,0x56,0xfd,0xf7,0xe2,0x1d,0xca,0x4d,
@@ -343,6 +371,13 @@ static const struct patch_digest phashes[] = {
0x1b,0x7d,0x64,0x9d,0x4b,0x53,0x13,0x75,
}
},
+ { 0xa10124c, {
+ 0x29,0xea,0xf1,0x2c,0xb2,0xe4,0xef,0x90,
+ 0xa4,0xcd,0x1d,0x86,0x97,0x17,0x61,0x46,
+ 0xfc,0x22,0xcb,0x57,0x75,0x19,0xc8,0xcc,
+ 0x0c,0xf5,0xbc,0xac,0x81,0x9d,0x9a,0xd2,
+ }
+ },
{ 0xa108108, {
0xed,0xc2,0xec,0xa1,0x15,0xc6,0x65,0xe9,
0xd0,0xef,0x39,0xaa,0x7f,0x55,0x06,0xc6,
@@ -350,6 +385,13 @@ static const struct patch_digest phashes[] = {
0x28,0x1e,0x9c,0x59,0x69,0x99,0x4d,0x16,
}
},
+ { 0xa108109, {
+ 0x85,0xb4,0xbd,0x7c,0x49,0xa7,0xbd,0xfa,
+ 0x49,0x36,0x80,0x81,0xc5,0xb7,0x39,0x1b,
+ 0x9a,0xaa,0x50,0xde,0x9b,0xe9,0x32,0x35,
+ 0x42,0x7e,0x51,0x4f,0x52,0x2c,0x28,0x59,
+ }
+ },
{ 0xa20102d, {
0xf9,0x6e,0xf2,0x32,0xd3,0x0f,0x5f,0x11,
0x59,0xa1,0xfe,0xcc,0xcd,0x9b,0x42,0x89,
@@ -357,6 +399,13 @@ static const struct patch_digest phashes[] = {
0x8c,0xe9,0x19,0x3e,0xcc,0x3f,0x7b,0xb4,
}
},
+ { 0xa20102e, {
+ 0xbe,0x1f,0x32,0x04,0x0d,0x3c,0x9c,0xdd,
+ 0xe1,0xa4,0xbf,0x76,0x3a,0xec,0xc2,0xf6,
+ 0x11,0x00,0xa7,0xaf,0x0f,0xe5,0x02,0xc5,
+ 0x54,0x3a,0x1f,0x8c,0x16,0xb5,0xff,0xbe,
+ }
+ },
{ 0xa201210, {
0xe8,0x6d,0x51,0x6a,0x8e,0x72,0xf3,0xfe,
0x6e,0x16,0xbc,0x62,0x59,0x40,0x17,0xe9,
@@ -364,6 +413,13 @@ static const struct patch_digest phashes[] = {
0xf7,0x55,0xf0,0x13,0xbb,0x22,0xf6,0x41,
}
},
+ { 0xa201211, {
+ 0x69,0xa1,0x17,0xec,0xd0,0xf6,0x6c,0x95,
+ 0xe2,0x1e,0xc5,0x59,0x1a,0x52,0x0a,0x27,
+ 0xc4,0xed,0xd5,0x59,0x1f,0xbf,0x00,0xff,
+ 0x08,0x88,0xb5,0xe1,0x12,0xb6,0xcc,0x27,
+ }
+ },
{ 0xa404107, {
0xbb,0x04,0x4e,0x47,0xdd,0x5e,0x26,0x45,
0x1a,0xc9,0x56,0x24,0xa4,0x4c,0x82,0xb0,
@@ -371,6 +427,13 @@ static const struct patch_digest phashes[] = {
0x13,0xbc,0xc5,0x25,0xe4,0xc5,0xc3,0x99,
}
},
+ { 0xa404108, {
+ 0x69,0x67,0x43,0x06,0xf8,0x0c,0x62,0xdc,
+ 0xa4,0x21,0x30,0x4f,0x0f,0x21,0x2c,0xcb,
+ 0xcc,0x37,0xf1,0x1c,0xc3,0xf8,0x2f,0x19,
+ 0xdf,0x53,0x53,0x46,0xb1,0x15,0xea,0x00,
+ }
+ },
{ 0xa500011, {
0x23,0x3d,0x70,0x7d,0x03,0xc3,0xc4,0xf4,
0x2b,0x82,0xc6,0x05,0xda,0x80,0x0a,0xf1,
@@ -378,6 +441,13 @@ static const struct patch_digest phashes[] = {
0x11,0x5e,0x96,0x7e,0x71,0xe9,0xfc,0x74,
}
},
+ { 0xa500012, {
+ 0xeb,0x74,0x0d,0x47,0xa1,0x8e,0x09,0xe4,
+ 0x93,0x4c,0xad,0x03,0x32,0x4c,0x38,0x16,
+ 0x10,0x39,0xdd,0x06,0xaa,0xce,0xd6,0x0f,
+ 0x62,0x83,0x9d,0x8e,0x64,0x55,0xbe,0x63,
+ }
+ },
{ 0xa601209, {
0x66,0x48,0xd4,0x09,0x05,0xcb,0x29,0x32,
0x66,0xb7,0x9a,0x76,0xcd,0x11,0xf3,0x30,
@@ -385,6 +455,13 @@ static const struct patch_digest phashes[] = {
0xe8,0x73,0xe2,0xd6,0xdb,0xd2,0x77,0x1d,
}
},
+ { 0xa60120a, {
+ 0x0c,0x8b,0x3d,0xfd,0x52,0x52,0x85,0x7d,
+ 0x20,0x3a,0xe1,0x7e,0xa4,0x21,0x3b,0x7b,
+ 0x17,0x86,0xae,0xac,0x13,0xb8,0x63,0x9d,
+ 0x06,0x01,0xd0,0xa0,0x51,0x9a,0x91,0x2c,
+ }
+ },
{ 0xa704107, {
0xf3,0xc6,0x58,0x26,0xee,0xac,0x3f,0xd6,
0xce,0xa1,0x72,0x47,0x3b,0xba,0x2b,0x93,
@@ -392,6 +469,13 @@ static const struct patch_digest phashes[] = {
0x64,0x39,0x71,0x8c,0xce,0xe7,0x41,0x39,
}
},
+ { 0xa704108, {
+ 0xd7,0x55,0x15,0x2b,0xfe,0xc4,0xbc,0x93,
+ 0xec,0x91,0xa0,0xae,0x45,0xb7,0xc3,0x98,
+ 0x4e,0xff,0x61,0x77,0x88,0xc2,0x70,0x49,
+ 0xe0,0x3a,0x1d,0x84,0x38,0x52,0xbf,0x5a,
+ }
+ },
{ 0xa705206, {
0x8d,0xc0,0x76,0xbd,0x58,0x9f,0x8f,0xa4,
0x12,0x9d,0x21,0xfb,0x48,0x21,0xbc,0xe7,
@@ -399,6 +483,13 @@ static const struct patch_digest phashes[] = {
0x03,0x35,0xe9,0xbe,0xfb,0x06,0xdf,0xfc,
}
},
+ { 0xa705208, {
+ 0x30,0x1d,0x55,0x24,0xbc,0x6b,0x5a,0x19,
+ 0x0c,0x7d,0x1d,0x74,0xaa,0xd1,0xeb,0xd2,
+ 0x16,0x62,0xf7,0x5b,0xe1,0x1f,0x18,0x11,
+ 0x5c,0xf0,0x94,0x90,0x26,0xec,0x69,0xff,
+ }
+ },
{ 0xa708007, {
0x6b,0x76,0xcc,0x78,0xc5,0x8a,0xa3,0xe3,
0x32,0x2d,0x79,0xe4,0xc3,0x80,0xdb,0xb2,
@@ -406,6 +497,13 @@ static const struct patch_digest phashes[] = {
0xdf,0x92,0x73,0x84,0x87,0x3c,0x73,0x93,
}
},
+ { 0xa708008, {
+ 0x08,0x6e,0xf0,0x22,0x4b,0x8e,0xc4,0x46,
+ 0x58,0x34,0xe6,0x47,0xa2,0x28,0xfd,0xab,
+ 0x22,0x3d,0xdd,0xd8,0x52,0x9e,0x1d,0x16,
+ 0xfa,0x01,0x68,0x14,0x79,0x3e,0xe8,0x6b,
+ }
+ },
{ 0xa70c005, {
0x88,0x5d,0xfb,0x79,0x64,0xd8,0x46,0x3b,
0x4a,0x83,0x8e,0x77,0x7e,0xcf,0xb3,0x0f,
@@ -413,6 +511,13 @@ static const struct patch_digest phashes[] = {
0xee,0x49,0xac,0xe1,0x8b,0x13,0xc5,0x13,
}
},
+ { 0xa70c008, {
+ 0x0f,0xdb,0x37,0xa1,0x10,0xaf,0xd4,0x21,
+ 0x94,0x0d,0xa4,0xa2,0xe9,0x86,0x6c,0x0e,
+ 0x85,0x7c,0x36,0x30,0xa3,0x3a,0x78,0x66,
+ 0x18,0x10,0x60,0x0d,0x78,0x3d,0x44,0xd0,
+ }
+ },
{ 0xaa00116, {
0xe8,0x4c,0x2c,0x88,0xa1,0xac,0x24,0x63,
0x65,0xe5,0xaa,0x2d,0x16,0xa9,0xc3,0xf5,
@@ -441,4 +546,11 @@ static const struct patch_digest phashes[] = {
0x68,0x2f,0x46,0xee,0xfe,0xc6,0x6d,0xef,
}
},
+ { 0xaa00216, {
+ 0x79,0xfb,0x5b,0x9f,0xb6,0xe6,0xa8,0xf5,
+ 0x4e,0x7c,0x4f,0x8e,0x1d,0xad,0xd0,0x08,
+ 0xc2,0x43,0x7c,0x8b,0xe6,0xdb,0xd0,0xd2,
+ 0xe8,0x39,0x26,0xc1,0xe5,0x5a,0x48,0xf1,
+ }
+ },
};
diff --git a/arch/x86/kernel/cpu/microcode/core.c b/arch/x86/kernel/cpu/microcode/core.c
index 079f046ee26d..b92e09a87c69 100644
--- a/arch/x86/kernel/cpu/microcode/core.c
+++ b/arch/x86/kernel/cpu/microcode/core.c
@@ -17,8 +17,8 @@
#define pr_fmt(fmt) "microcode: " fmt
-#include <linux/platform_device.h>
#include <linux/stop_machine.h>
+#include <linux/device/faux.h>
#include <linux/syscore_ops.h>
#include <linux/miscdevice.h>
#include <linux/capability.h>
@@ -37,6 +37,7 @@
#include <asm/perf_event.h>
#include <asm/processor.h>
#include <asm/cmdline.h>
+#include <asm/msr.h>
#include <asm/setup.h>
#include "internal.h"
@@ -117,7 +118,7 @@ bool __init microcode_loader_disabled(void)
* 3) Certain AMD patch levels are not allowed to be
* overwritten.
*/
- if (!have_cpuid_p() ||
+ if (!cpuid_feature() ||
native_cpuid_ecx(1) & BIT(31) ||
amd_check_current_patch_level())
dis_ucode_ldr = true;
@@ -248,7 +249,7 @@ static void reload_early_microcode(unsigned int cpu)
}
/* fake device for request_firmware */
-static struct platform_device *microcode_pdev;
+static struct faux_device *microcode_fdev;
#ifdef CONFIG_MICROCODE_LATE_LOADING
/*
@@ -689,13 +690,15 @@ static int load_late_locked(void)
if (!setup_cpus())
return -EBUSY;
- switch (microcode_ops->request_microcode_fw(0, &microcode_pdev->dev)) {
+ switch (microcode_ops->request_microcode_fw(0, &microcode_fdev->dev)) {
case UCODE_NEW:
return load_late_stop_cpus(false);
case UCODE_NEW_SAFE:
return load_late_stop_cpus(true);
case UCODE_NFOUND:
return -ENOENT;
+ case UCODE_OK:
+ return 0;
default:
return -EBADFD;
}
@@ -838,9 +841,9 @@ static int __init microcode_init(void)
if (early_data.new_rev)
pr_info_once("Updated early from: 0x%08x\n", early_data.old_rev);
- microcode_pdev = platform_device_register_simple("microcode", -1, NULL, 0);
- if (IS_ERR(microcode_pdev))
- return PTR_ERR(microcode_pdev);
+ microcode_fdev = faux_device_create("microcode", NULL, NULL);
+ if (!microcode_fdev)
+ return -ENODEV;
dev_root = bus_get_dev_root(&cpu_subsys);
if (dev_root) {
@@ -859,7 +862,7 @@ static int __init microcode_init(void)
return 0;
out_pdev:
- platform_device_unregister(microcode_pdev);
+ faux_device_destroy(microcode_fdev);
return error;
}
diff --git a/arch/x86/kernel/cpu/microcode/intel-ucode-defs.h b/arch/x86/kernel/cpu/microcode/intel-ucode-defs.h
new file mode 100644
index 000000000000..cb6e601701ab
--- /dev/null
+++ b/arch/x86/kernel/cpu/microcode/intel-ucode-defs.h
@@ -0,0 +1,150 @@
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x03, .steppings = 0x0004, .driver_data = 0x2 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x05, .steppings = 0x0001, .driver_data = 0x45 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x05, .steppings = 0x0002, .driver_data = 0x40 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x05, .steppings = 0x0004, .driver_data = 0x2c },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x05, .steppings = 0x0008, .driver_data = 0x10 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x06, .steppings = 0x0001, .driver_data = 0xa },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x06, .steppings = 0x0020, .driver_data = 0x3 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x06, .steppings = 0x0400, .driver_data = 0xd },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x06, .steppings = 0x2000, .driver_data = 0x7 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x07, .steppings = 0x0002, .driver_data = 0x14 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x07, .steppings = 0x0004, .driver_data = 0x38 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x07, .steppings = 0x0008, .driver_data = 0x2e },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x08, .steppings = 0x0002, .driver_data = 0x11 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x08, .steppings = 0x0008, .driver_data = 0x8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x08, .steppings = 0x0040, .driver_data = 0xc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x08, .steppings = 0x0400, .driver_data = 0x5 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x09, .steppings = 0x0020, .driver_data = 0x47 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0a, .steppings = 0x0001, .driver_data = 0x3 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0a, .steppings = 0x0002, .driver_data = 0x1 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0b, .steppings = 0x0002, .driver_data = 0x1d },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0b, .steppings = 0x0010, .driver_data = 0x2 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0d, .steppings = 0x0040, .driver_data = 0x18 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0e, .steppings = 0x0100, .driver_data = 0x39 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0e, .steppings = 0x1000, .driver_data = 0x59 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0f, .steppings = 0x0004, .driver_data = 0x5d },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0f, .steppings = 0x0040, .driver_data = 0xd2 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0f, .steppings = 0x0080, .driver_data = 0x6b },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0f, .steppings = 0x0400, .driver_data = 0x95 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0f, .steppings = 0x0800, .driver_data = 0xbc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x0f, .steppings = 0x2000, .driver_data = 0xa4 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x16, .steppings = 0x0002, .driver_data = 0x44 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x17, .steppings = 0x0040, .driver_data = 0x60f },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x17, .steppings = 0x0080, .driver_data = 0x70a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x17, .steppings = 0x0400, .driver_data = 0xa0b },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x1a, .steppings = 0x0010, .driver_data = 0x12 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x1a, .steppings = 0x0020, .driver_data = 0x1d },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x1c, .steppings = 0x0004, .driver_data = 0x219 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x1c, .steppings = 0x0400, .driver_data = 0x107 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x1d, .steppings = 0x0002, .driver_data = 0x29 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x1e, .steppings = 0x0020, .driver_data = 0xa },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x25, .steppings = 0x0004, .driver_data = 0x11 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x25, .steppings = 0x0020, .driver_data = 0x7 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x26, .steppings = 0x0002, .driver_data = 0x105 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x2a, .steppings = 0x0080, .driver_data = 0x2f },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x2c, .steppings = 0x0004, .driver_data = 0x1f },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x2d, .steppings = 0x0040, .driver_data = 0x621 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x2d, .steppings = 0x0080, .driver_data = 0x71a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x2e, .steppings = 0x0040, .driver_data = 0xd },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x2f, .steppings = 0x0004, .driver_data = 0x3b },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x37, .steppings = 0x0100, .driver_data = 0x838 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x37, .steppings = 0x0200, .driver_data = 0x90d },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x3a, .steppings = 0x0200, .driver_data = 0x21 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x3c, .steppings = 0x0008, .driver_data = 0x28 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x3d, .steppings = 0x0010, .driver_data = 0x2f },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x3e, .steppings = 0x0010, .driver_data = 0x42e },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x3e, .steppings = 0x0040, .driver_data = 0x600 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x3e, .steppings = 0x0080, .driver_data = 0x715 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x3f, .steppings = 0x0004, .driver_data = 0x49 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x3f, .steppings = 0x0010, .driver_data = 0x1a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x45, .steppings = 0x0002, .driver_data = 0x26 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x46, .steppings = 0x0002, .driver_data = 0x1c },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x47, .steppings = 0x0002, .driver_data = 0x22 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x4c, .steppings = 0x0008, .driver_data = 0x368 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x4c, .steppings = 0x0010, .driver_data = 0x411 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x4d, .steppings = 0x0100, .driver_data = 0x12d },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x4e, .steppings = 0x0008, .driver_data = 0xf0 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x55, .steppings = 0x0008, .driver_data = 0x1000191 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x55, .steppings = 0x0010, .driver_data = 0x2007006 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x55, .steppings = 0x0020, .driver_data = 0x3000010 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x55, .steppings = 0x0040, .driver_data = 0x4003605 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x55, .steppings = 0x0080, .driver_data = 0x5003707 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x55, .steppings = 0x0800, .driver_data = 0x7002904 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x56, .steppings = 0x0004, .driver_data = 0x1c },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x56, .steppings = 0x0008, .driver_data = 0x700001c },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x56, .steppings = 0x0010, .driver_data = 0xf00001a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x56, .steppings = 0x0020, .driver_data = 0xe000015 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x5c, .steppings = 0x0004, .driver_data = 0x14 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x5c, .steppings = 0x0200, .driver_data = 0x48 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x5c, .steppings = 0x0400, .driver_data = 0x28 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x5e, .steppings = 0x0008, .driver_data = 0xf0 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x5f, .steppings = 0x0002, .driver_data = 0x3e },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x66, .steppings = 0x0008, .driver_data = 0x2a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x6a, .steppings = 0x0020, .driver_data = 0xc0002f0 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x6a, .steppings = 0x0040, .driver_data = 0xd0003e7 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x6c, .steppings = 0x0002, .driver_data = 0x10002b0 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x7a, .steppings = 0x0002, .driver_data = 0x42 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x7a, .steppings = 0x0100, .driver_data = 0x24 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x7e, .steppings = 0x0020, .driver_data = 0xc6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8a, .steppings = 0x0002, .driver_data = 0x33 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8c, .steppings = 0x0002, .driver_data = 0xb8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8c, .steppings = 0x0004, .driver_data = 0x38 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8d, .steppings = 0x0002, .driver_data = 0x52 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8e, .steppings = 0x0200, .driver_data = 0xf6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8e, .steppings = 0x0400, .driver_data = 0xf6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8e, .steppings = 0x0800, .driver_data = 0xf6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8e, .steppings = 0x1000, .driver_data = 0xfc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8f, .steppings = 0x0100, .driver_data = 0x2c000390 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8f, .steppings = 0x0080, .driver_data = 0x2b000603 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8f, .steppings = 0x0040, .driver_data = 0x2c000390 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8f, .steppings = 0x0020, .driver_data = 0x2c000390 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x8f, .steppings = 0x0010, .driver_data = 0x2c000390 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x96, .steppings = 0x0002, .driver_data = 0x1a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x97, .steppings = 0x0004, .driver_data = 0x37 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x97, .steppings = 0x0020, .driver_data = 0x37 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xbf, .steppings = 0x0004, .driver_data = 0x37 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xbf, .steppings = 0x0020, .driver_data = 0x37 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x9a, .steppings = 0x0008, .driver_data = 0x435 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x9a, .steppings = 0x0010, .driver_data = 0x435 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x9c, .steppings = 0x0001, .driver_data = 0x24000026 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x9e, .steppings = 0x0200, .driver_data = 0xf8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x9e, .steppings = 0x0400, .driver_data = 0xf8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x9e, .steppings = 0x0800, .driver_data = 0xf6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x9e, .steppings = 0x1000, .driver_data = 0xf8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0x9e, .steppings = 0x2000, .driver_data = 0x100 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xa5, .steppings = 0x0004, .driver_data = 0xfc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xa5, .steppings = 0x0008, .driver_data = 0xfc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xa5, .steppings = 0x0020, .driver_data = 0xfc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xa6, .steppings = 0x0001, .driver_data = 0xfe },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xa6, .steppings = 0x0002, .driver_data = 0xfc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xa7, .steppings = 0x0002, .driver_data = 0x62 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xaa, .steppings = 0x0010, .driver_data = 0x20 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xb7, .steppings = 0x0002, .driver_data = 0x12b },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xba, .steppings = 0x0004, .driver_data = 0x4123 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xba, .steppings = 0x0008, .driver_data = 0x4123 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xba, .steppings = 0x0100, .driver_data = 0x4123 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xbe, .steppings = 0x0001, .driver_data = 0x1a },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xcf, .steppings = 0x0004, .driver_data = 0x21000283 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0x6, .model = 0xcf, .steppings = 0x0002, .driver_data = 0x21000283 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x00, .steppings = 0x0080, .driver_data = 0x12 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x00, .steppings = 0x0400, .driver_data = 0x15 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x01, .steppings = 0x0004, .driver_data = 0x2e },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x02, .steppings = 0x0010, .driver_data = 0x21 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x02, .steppings = 0x0020, .driver_data = 0x2c },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x02, .steppings = 0x0040, .driver_data = 0x10 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x02, .steppings = 0x0080, .driver_data = 0x39 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x02, .steppings = 0x0200, .driver_data = 0x2f },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x03, .steppings = 0x0004, .driver_data = 0xa },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x03, .steppings = 0x0008, .driver_data = 0xc },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x03, .steppings = 0x0010, .driver_data = 0x17 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x04, .steppings = 0x0002, .driver_data = 0x17 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x04, .steppings = 0x0008, .driver_data = 0x5 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x04, .steppings = 0x0010, .driver_data = 0x6 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x04, .steppings = 0x0080, .driver_data = 0x3 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x04, .steppings = 0x0100, .driver_data = 0xe },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x04, .steppings = 0x0200, .driver_data = 0x3 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x04, .steppings = 0x0400, .driver_data = 0x4 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x06, .steppings = 0x0004, .driver_data = 0xf },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x06, .steppings = 0x0010, .driver_data = 0x4 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x06, .steppings = 0x0020, .driver_data = 0x8 },
+{ .flags = X86_CPU_ID_FLAG_ENTRY_VALID, .vendor = X86_VENDOR_INTEL, .family = 0xf, .model = 0x06, .steppings = 0x0100, .driver_data = 0x9 },
diff --git a/arch/x86/kernel/cpu/microcode/intel.c b/arch/x86/kernel/cpu/microcode/intel.c
index 2a397da43923..371ca6eac00e 100644
--- a/arch/x86/kernel/cpu/microcode/intel.c
+++ b/arch/x86/kernel/cpu/microcode/intel.c
@@ -320,7 +320,7 @@ static enum ucode_state __apply_microcode(struct ucode_cpu_info *uci,
}
/* write microcode via MSR 0x79 */
- native_wrmsrl(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
+ native_wrmsrq(MSR_IA32_UCODE_WRITE, (unsigned long)mc->bits);
rev = intel_get_microcode_revision();
if (rev != mc->hdr.rev)
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 3e2533954675..c78f860419d6 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -30,6 +30,7 @@
#include <asm/reboot.h>
#include <asm/nmi.h>
#include <clocksource/hyperv_timer.h>
+#include <asm/msr.h>
#include <asm/numa.h>
#include <asm/svm.h>
@@ -70,7 +71,7 @@ u64 hv_get_non_nested_msr(unsigned int reg)
if (hv_is_synic_msr(reg) && ms_hyperv.paravisor_present)
hv_ivm_msr_read(reg, &value);
else
- rdmsrl(reg, value);
+ rdmsrq(reg, value);
return value;
}
EXPORT_SYMBOL_GPL(hv_get_non_nested_msr);
@@ -82,9 +83,9 @@ void hv_set_non_nested_msr(unsigned int reg, u64 value)
/* Write proxy bit via wrmsl instruction */
if (hv_is_sint_msr(reg))
- wrmsrl(reg, value | 1 << 20);
+ wrmsrq(reg, value | 1 << 20);
} else {
- wrmsrl(reg, value);
+ wrmsrq(reg, value);
}
}
EXPORT_SYMBOL_GPL(hv_set_non_nested_msr);
@@ -345,7 +346,7 @@ static unsigned long hv_get_tsc_khz(void)
{
unsigned long freq;
- rdmsrl(HV_X64_MSR_TSC_FREQUENCY, freq);
+ rdmsrq(HV_X64_MSR_TSC_FREQUENCY, freq);
return freq / 1000;
}
@@ -541,7 +542,7 @@ static void __init ms_hyperv_init_platform(void)
*/
u64 hv_lapic_frequency;
- rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
+ rdmsrq(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
lapic_timer_period = hv_lapic_frequency;
pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n",
@@ -574,7 +575,7 @@ static void __init ms_hyperv_init_platform(void)
* setting of this MSR bit should happen before init_intel()
* is called.
*/
- wrmsrl(HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_EXPOSE_INVARIANT_TSC);
+ wrmsrq(HV_X64_MSR_TSC_INVARIANT_CONTROL, HV_EXPOSE_INVARIANT_TSC);
setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
}
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index e2c6b471d230..8c18327eb10b 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -593,7 +593,7 @@ static void get_fixed_ranges(mtrr_type *frs)
void mtrr_save_fixed_ranges(void *info)
{
- if (boot_cpu_has(X86_FEATURE_MTRR))
+ if (mtrr_state.have_fixed)
get_fixed_ranges(mtrr_state.fixed_ranges);
}
diff --git a/arch/x86/kernel/cpu/resctrl/Makefile b/arch/x86/kernel/cpu/resctrl/Makefile
index 0c13b0befd8a..d8a04b195da2 100644
--- a/arch/x86/kernel/cpu/resctrl/Makefile
+++ b/arch/x86/kernel/cpu/resctrl/Makefile
@@ -2,4 +2,6 @@
obj-$(CONFIG_X86_CPU_RESCTRL) += core.o rdtgroup.o monitor.o
obj-$(CONFIG_X86_CPU_RESCTRL) += ctrlmondata.o
obj-$(CONFIG_RESCTRL_FS_PSEUDO_LOCK) += pseudo_lock.o
+
+# To allow define_trace.h's recursive include:
CFLAGS_pseudo_lock.o = -I$(src)
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index cf29681d01e0..187d527ef73b 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -22,6 +22,7 @@
#include <linux/cpuhotplug.h>
#include <asm/cpu_device_id.h>
+#include <asm/msr.h>
#include <asm/resctrl.h>
#include "internal.h"
@@ -60,7 +61,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
[RDT_RESOURCE_L3] =
{
.r_resctrl = {
- .rid = RDT_RESOURCE_L3,
.name = "L3",
.ctrl_scope = RESCTRL_L3_CACHE,
.mon_scope = RESCTRL_L3_CACHE,
@@ -74,7 +74,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
[RDT_RESOURCE_L2] =
{
.r_resctrl = {
- .rid = RDT_RESOURCE_L2,
.name = "L2",
.ctrl_scope = RESCTRL_L2_CACHE,
.ctrl_domains = ctrl_domain_init(RDT_RESOURCE_L2),
@@ -86,7 +85,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
[RDT_RESOURCE_MBA] =
{
.r_resctrl = {
- .rid = RDT_RESOURCE_MBA,
.name = "MB",
.ctrl_scope = RESCTRL_L3_CACHE,
.ctrl_domains = ctrl_domain_init(RDT_RESOURCE_MBA),
@@ -96,7 +94,6 @@ struct rdt_hw_resource rdt_resources_all[RDT_NUM_RESOURCES] = {
[RDT_RESOURCE_SMBA] =
{
.r_resctrl = {
- .rid = RDT_RESOURCE_SMBA,
.name = "SMBA",
.ctrl_scope = RESCTRL_L3_CACHE,
.ctrl_domains = ctrl_domain_init(RDT_RESOURCE_SMBA),
@@ -145,10 +142,10 @@ static inline void cache_alloc_hsw_probe(void)
struct rdt_resource *r = &hw_res->r_resctrl;
u64 max_cbm = BIT_ULL_MASK(20) - 1, l3_cbm_0;
- if (wrmsrl_safe(MSR_IA32_L3_CBM_BASE, max_cbm))
+ if (wrmsrq_safe(MSR_IA32_L3_CBM_BASE, max_cbm))
return;
- rdmsrl(MSR_IA32_L3_CBM_BASE, l3_cbm_0);
+ rdmsrq(MSR_IA32_L3_CBM_BASE, l3_cbm_0);
/* If all the bits were set in MSR, return success */
if (l3_cbm_0 != max_cbm)
@@ -164,21 +161,6 @@ static inline void cache_alloc_hsw_probe(void)
rdt_alloc_capable = true;
}
-bool is_mba_sc(struct rdt_resource *r)
-{
- if (!r)
- r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
-
- /*
- * The software controller support is only applicable to MBA resource.
- * Make sure to check for resource type.
- */
- if (r->rid != RDT_RESOURCE_MBA)
- return false;
-
- return r->membw.mba_sc;
-}
-
/*
* rdt_get_mb_table() - get a mapping of bandwidth(b/w) percentage values
* exposed to user interface and the h/w understandable delay values.
@@ -309,7 +291,7 @@ static void mba_wrmsr_amd(struct msr_param *m)
unsigned int i;
for (i = m->low; i < m->high; i++)
- wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
+ wrmsrq(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
}
/*
@@ -334,7 +316,7 @@ static void mba_wrmsr_intel(struct msr_param *m)
/* Write the delay values for mba. */
for (i = m->low; i < m->high; i++)
- wrmsrl(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], m->res));
+ wrmsrq(hw_res->msr_base + i, delay_bw_map(hw_dom->ctrl_val[i], m->res));
}
static void cat_wrmsr(struct msr_param *m)
@@ -344,7 +326,7 @@ static void cat_wrmsr(struct msr_param *m)
unsigned int i;
for (i = m->low; i < m->high; i++)
- wrmsrl(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
+ wrmsrq(hw_res->msr_base + i, hw_dom->ctrl_val[i]);
}
u32 resctrl_arch_get_num_closid(struct rdt_resource *r)
@@ -516,6 +498,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
struct rdt_hw_mon_domain *hw_dom;
struct rdt_domain_hdr *hdr;
struct rdt_mon_domain *d;
+ struct cacheinfo *ci;
int err;
lockdep_assert_held(&domain_list_lock);
@@ -543,12 +526,13 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
d = &hw_dom->d_resctrl;
d->hdr.id = id;
d->hdr.type = RESCTRL_MON_DOMAIN;
- d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
- if (!d->ci) {
+ ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+ if (!ci) {
pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
mon_domain_free(hw_dom);
return;
}
+ d->ci_id = ci->id;
cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
arch_mon_domain_online(r, d);
@@ -737,7 +721,7 @@ struct rdt_options {
bool force_off, force_on;
};
-static struct rdt_options rdt_options[] __initdata = {
+static struct rdt_options rdt_options[] __ro_after_init = {
RDT_OPT(RDT_FLAG_CMT, "cmt", X86_FEATURE_CQM_OCCUP_LLC),
RDT_OPT(RDT_FLAG_MBM_TOTAL, "mbmtotal", X86_FEATURE_CQM_MBM_TOTAL),
RDT_OPT(RDT_FLAG_MBM_LOCAL, "mbmlocal", X86_FEATURE_CQM_MBM_LOCAL),
@@ -777,7 +761,7 @@ static int __init set_rdt_options(char *str)
}
__setup("rdt", set_rdt_options);
-bool __init rdt_cpu_has(int flag)
+bool rdt_cpu_has(int flag)
{
bool ret = boot_cpu_has(flag);
struct rdt_options *o;
@@ -797,7 +781,7 @@ bool __init rdt_cpu_has(int flag)
return ret;
}
-__init bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt)
+bool resctrl_arch_is_evt_configurable(enum resctrl_event_id evt)
{
if (!rdt_cpu_has(X86_FEATURE_BMEC))
return false;
@@ -1011,7 +995,11 @@ void resctrl_cpu_detect(struct cpuinfo_x86 *c)
static int __init resctrl_arch_late_init(void)
{
struct rdt_resource *r;
- int state, ret;
+ int state, ret, i;
+
+ /* for_each_rdt_resource() requires all rid to be initialised. */
+ for (i = 0; i < RDT_NUM_RESOURCES; i++)
+ rdt_resources_all[i].r_resctrl.rid = i;
/*
* Initialize functions(or definitions) that are different
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 0a0ac5f6112e..1189c0df4ad7 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -16,277 +16,9 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/cpu.h>
-#include <linux/kernfs.h>
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-#include <linux/tick.h>
#include "internal.h"
-struct rdt_parse_data {
- struct rdtgroup *rdtgrp;
- char *buf;
-};
-
-typedef int (ctrlval_parser_t)(struct rdt_parse_data *data,
- struct resctrl_schema *s,
- struct rdt_ctrl_domain *d);
-
-/*
- * Check whether MBA bandwidth percentage value is correct. The value is
- * checked against the minimum and max bandwidth values specified by the
- * hardware. The allocated bandwidth percentage is rounded to the next
- * control step available on the hardware.
- */
-static bool bw_validate(char *buf, u32 *data, struct rdt_resource *r)
-{
- int ret;
- u32 bw;
-
- /*
- * Only linear delay values is supported for current Intel SKUs.
- */
- if (!r->membw.delay_linear && r->membw.arch_needs_linear) {
- rdt_last_cmd_puts("No support for non-linear MB domains\n");
- return false;
- }
-
- ret = kstrtou32(buf, 10, &bw);
- if (ret) {
- rdt_last_cmd_printf("Invalid MB value %s\n", buf);
- return false;
- }
-
- /* Nothing else to do if software controller is enabled. */
- if (is_mba_sc(r)) {
- *data = bw;
- return true;
- }
-
- if (bw < r->membw.min_bw || bw > r->membw.max_bw) {
- rdt_last_cmd_printf("MB value %u out of range [%d,%d]\n",
- bw, r->membw.min_bw, r->membw.max_bw);
- return false;
- }
-
- *data = roundup(bw, (unsigned long)r->membw.bw_gran);
- return true;
-}
-
-static int parse_bw(struct rdt_parse_data *data, struct resctrl_schema *s,
- struct rdt_ctrl_domain *d)
-{
- struct resctrl_staged_config *cfg;
- u32 closid = data->rdtgrp->closid;
- struct rdt_resource *r = s->res;
- u32 bw_val;
-
- cfg = &d->staged_config[s->conf_type];
- if (cfg->have_new_ctrl) {
- rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
- return -EINVAL;
- }
-
- if (!bw_validate(data->buf, &bw_val, r))
- return -EINVAL;
-
- if (is_mba_sc(r)) {
- d->mbps_val[closid] = bw_val;
- return 0;
- }
-
- cfg->new_ctrl = bw_val;
- cfg->have_new_ctrl = true;
-
- return 0;
-}
-
-/*
- * Check whether a cache bit mask is valid.
- * On Intel CPUs, non-contiguous 1s value support is indicated by CPUID:
- * - CPUID.0x10.1:ECX[3]: L3 non-contiguous 1s value supported if 1
- * - CPUID.0x10.2:ECX[3]: L2 non-contiguous 1s value supported if 1
- *
- * Haswell does not support a non-contiguous 1s value and additionally
- * requires at least two bits set.
- * AMD allows non-contiguous bitmasks.
- */
-static bool cbm_validate(char *buf, u32 *data, struct rdt_resource *r)
-{
- u32 supported_bits = BIT_MASK(r->cache.cbm_len) - 1;
- unsigned int cbm_len = r->cache.cbm_len;
- unsigned long first_bit, zero_bit, val;
- int ret;
-
- ret = kstrtoul(buf, 16, &val);
- if (ret) {
- rdt_last_cmd_printf("Non-hex character in the mask %s\n", buf);
- return false;
- }
-
- if ((r->cache.min_cbm_bits > 0 && val == 0) || val > supported_bits) {
- rdt_last_cmd_puts("Mask out of range\n");
- return false;
- }
-
- first_bit = find_first_bit(&val, cbm_len);
- zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
-
- /* Are non-contiguous bitmasks allowed? */
- if (!r->cache.arch_has_sparse_bitmasks &&
- (find_next_bit(&val, cbm_len, zero_bit) < cbm_len)) {
- rdt_last_cmd_printf("The mask %lx has non-consecutive 1-bits\n", val);
- return false;
- }
-
- if ((zero_bit - first_bit) < r->cache.min_cbm_bits) {
- rdt_last_cmd_printf("Need at least %d bits in the mask\n",
- r->cache.min_cbm_bits);
- return false;
- }
-
- *data = val;
- return true;
-}
-
-/*
- * Read one cache bit mask (hex). Check that it is valid for the current
- * resource type.
- */
-static int parse_cbm(struct rdt_parse_data *data, struct resctrl_schema *s,
- struct rdt_ctrl_domain *d)
-{
- struct rdtgroup *rdtgrp = data->rdtgrp;
- struct resctrl_staged_config *cfg;
- struct rdt_resource *r = s->res;
- u32 cbm_val;
-
- cfg = &d->staged_config[s->conf_type];
- if (cfg->have_new_ctrl) {
- rdt_last_cmd_printf("Duplicate domain %d\n", d->hdr.id);
- return -EINVAL;
- }
-
- /*
- * Cannot set up more than one pseudo-locked region in a cache
- * hierarchy.
- */
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
- rdtgroup_pseudo_locked_in_hierarchy(d)) {
- rdt_last_cmd_puts("Pseudo-locked region in hierarchy\n");
- return -EINVAL;
- }
-
- if (!cbm_validate(data->buf, &cbm_val, r))
- return -EINVAL;
-
- if ((rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
- rdtgrp->mode == RDT_MODE_SHAREABLE) &&
- rdtgroup_cbm_overlaps_pseudo_locked(d, cbm_val)) {
- rdt_last_cmd_puts("CBM overlaps with pseudo-locked region\n");
- return -EINVAL;
- }
-
- /*
- * The CBM may not overlap with the CBM of another closid if
- * either is exclusive.
- */
- if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, true)) {
- rdt_last_cmd_puts("Overlaps with exclusive group\n");
- return -EINVAL;
- }
-
- if (rdtgroup_cbm_overlaps(s, d, cbm_val, rdtgrp->closid, false)) {
- if (rdtgrp->mode == RDT_MODE_EXCLUSIVE ||
- rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
- rdt_last_cmd_puts("Overlaps with other group\n");
- return -EINVAL;
- }
- }
-
- cfg->new_ctrl = cbm_val;
- cfg->have_new_ctrl = true;
-
- return 0;
-}
-
-/*
- * For each domain in this resource we expect to find a series of:
- * id=mask
- * separated by ";". The "id" is in decimal, and must match one of
- * the "id"s for this resource.
- */
-static int parse_line(char *line, struct resctrl_schema *s,
- struct rdtgroup *rdtgrp)
-{
- enum resctrl_conf_type t = s->conf_type;
- ctrlval_parser_t *parse_ctrlval = NULL;
- struct resctrl_staged_config *cfg;
- struct rdt_resource *r = s->res;
- struct rdt_parse_data data;
- struct rdt_ctrl_domain *d;
- char *dom = NULL, *id;
- unsigned long dom_id;
-
- /* Walking r->domains, ensure it can't race with cpuhp */
- lockdep_assert_cpus_held();
-
- switch (r->schema_fmt) {
- case RESCTRL_SCHEMA_BITMAP:
- parse_ctrlval = &parse_cbm;
- break;
- case RESCTRL_SCHEMA_RANGE:
- parse_ctrlval = &parse_bw;
- break;
- }
-
- if (WARN_ON_ONCE(!parse_ctrlval))
- return -EINVAL;
-
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP &&
- (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)) {
- rdt_last_cmd_puts("Cannot pseudo-lock MBA resource\n");
- return -EINVAL;
- }
-
-next:
- if (!line || line[0] == '\0')
- return 0;
- dom = strsep(&line, ";");
- id = strsep(&dom, "=");
- if (!dom || kstrtoul(id, 10, &dom_id)) {
- rdt_last_cmd_puts("Missing '=' or non-numeric domain\n");
- return -EINVAL;
- }
- dom = strim(dom);
- list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
- if (d->hdr.id == dom_id) {
- data.buf = dom;
- data.rdtgrp = rdtgrp;
- if (parse_ctrlval(&data, s, d))
- return -EINVAL;
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
- cfg = &d->staged_config[t];
- /*
- * In pseudo-locking setup mode and just
- * parsed a valid CBM that should be
- * pseudo-locked. Only one locked region per
- * resource group and domain so just do
- * the required initialization for single
- * region and return.
- */
- rdtgrp->plr->s = s;
- rdtgrp->plr->d = d;
- rdtgrp->plr->cbm = cfg->new_ctrl;
- d->plr = rdtgrp->plr;
- return 0;
- }
- goto next;
- }
- }
- return -EINVAL;
-}
-
int resctrl_arch_update_one(struct rdt_resource *r, struct rdt_ctrl_domain *d,
u32 closid, enum resctrl_conf_type t, u32 cfg_val)
{
@@ -351,100 +83,6 @@ int resctrl_arch_update_domains(struct rdt_resource *r, u32 closid)
return 0;
}
-static int rdtgroup_parse_resource(char *resname, char *tok,
- struct rdtgroup *rdtgrp)
-{
- struct resctrl_schema *s;
-
- list_for_each_entry(s, &resctrl_schema_all, list) {
- if (!strcmp(resname, s->name) && rdtgrp->closid < s->num_closid)
- return parse_line(tok, s, rdtgrp);
- }
- rdt_last_cmd_printf("Unknown or unsupported resource name '%s'\n", resname);
- return -EINVAL;
-}
-
-ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
-{
- struct resctrl_schema *s;
- struct rdtgroup *rdtgrp;
- struct rdt_resource *r;
- char *tok, *resname;
- int ret = 0;
-
- /* Valid input requires a trailing newline */
- if (nbytes == 0 || buf[nbytes - 1] != '\n')
- return -EINVAL;
- buf[nbytes - 1] = '\0';
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (!rdtgrp) {
- rdtgroup_kn_unlock(of->kn);
- return -ENOENT;
- }
- rdt_last_cmd_clear();
-
- /*
- * No changes to pseudo-locked region allowed. It has to be removed
- * and re-created instead.
- */
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
- ret = -EINVAL;
- rdt_last_cmd_puts("Resource group is pseudo-locked\n");
- goto out;
- }
-
- rdt_staged_configs_clear();
-
- while ((tok = strsep(&buf, "\n")) != NULL) {
- resname = strim(strsep(&tok, ":"));
- if (!tok) {
- rdt_last_cmd_puts("Missing ':'\n");
- ret = -EINVAL;
- goto out;
- }
- if (tok[0] == '\0') {
- rdt_last_cmd_printf("Missing '%s' value\n", resname);
- ret = -EINVAL;
- goto out;
- }
- ret = rdtgroup_parse_resource(resname, tok, rdtgrp);
- if (ret)
- goto out;
- }
-
- list_for_each_entry(s, &resctrl_schema_all, list) {
- r = s->res;
-
- /*
- * Writes to mba_sc resources update the software controller,
- * not the control MSR.
- */
- if (is_mba_sc(r))
- continue;
-
- ret = resctrl_arch_update_domains(r, rdtgrp->closid);
- if (ret)
- goto out;
- }
-
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
- /*
- * If pseudo-locking fails we keep the resource group in
- * mode RDT_MODE_PSEUDO_LOCKSETUP with its class of service
- * active and updated for just the domain the pseudo-locked
- * region was requested for.
- */
- ret = rdtgroup_pseudo_lock_create(rdtgrp);
- }
-
-out:
- rdt_staged_configs_clear();
- rdtgroup_kn_unlock(of->kn);
- return ret ?: nbytes;
-}
-
u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d,
u32 closid, enum resctrl_conf_type type)
{
@@ -453,276 +91,3 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_ctrl_domain *d,
return hw_dom->ctrl_val[idx];
}
-
-static void show_doms(struct seq_file *s, struct resctrl_schema *schema, int closid)
-{
- struct rdt_resource *r = schema->res;
- struct rdt_ctrl_domain *dom;
- bool sep = false;
- u32 ctrl_val;
-
- /* Walking r->domains, ensure it can't race with cpuhp */
- lockdep_assert_cpus_held();
-
- seq_printf(s, "%*s:", max_name_width, schema->name);
- list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
- if (sep)
- seq_puts(s, ";");
-
- if (is_mba_sc(r))
- ctrl_val = dom->mbps_val[closid];
- else
- ctrl_val = resctrl_arch_get_config(r, dom, closid,
- schema->conf_type);
-
- seq_printf(s, schema->fmt_str, dom->hdr.id, ctrl_val);
- sep = true;
- }
- seq_puts(s, "\n");
-}
-
-int rdtgroup_schemata_show(struct kernfs_open_file *of,
- struct seq_file *s, void *v)
-{
- struct resctrl_schema *schema;
- struct rdtgroup *rdtgrp;
- int ret = 0;
- u32 closid;
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (rdtgrp) {
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
- list_for_each_entry(schema, &resctrl_schema_all, list) {
- seq_printf(s, "%s:uninitialized\n", schema->name);
- }
- } else if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
- if (!rdtgrp->plr->d) {
- rdt_last_cmd_clear();
- rdt_last_cmd_puts("Cache domain offline\n");
- ret = -ENODEV;
- } else {
- seq_printf(s, "%s:%d=%x\n",
- rdtgrp->plr->s->res->name,
- rdtgrp->plr->d->hdr.id,
- rdtgrp->plr->cbm);
- }
- } else {
- closid = rdtgrp->closid;
- list_for_each_entry(schema, &resctrl_schema_all, list) {
- if (closid < schema->num_closid)
- show_doms(s, schema, closid);
- }
- }
- } else {
- ret = -ENOENT;
- }
- rdtgroup_kn_unlock(of->kn);
- return ret;
-}
-
-static int smp_mon_event_count(void *arg)
-{
- mon_event_count(arg);
-
- return 0;
-}
-
-ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
-{
- struct rdtgroup *rdtgrp;
- int ret = 0;
-
- /* Valid input requires a trailing newline */
- if (nbytes == 0 || buf[nbytes - 1] != '\n')
- return -EINVAL;
- buf[nbytes - 1] = '\0';
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (!rdtgrp) {
- rdtgroup_kn_unlock(of->kn);
- return -ENOENT;
- }
- rdt_last_cmd_clear();
-
- if (!strcmp(buf, "mbm_local_bytes")) {
- if (resctrl_arch_is_mbm_local_enabled())
- rdtgrp->mba_mbps_event = QOS_L3_MBM_LOCAL_EVENT_ID;
- else
- ret = -EINVAL;
- } else if (!strcmp(buf, "mbm_total_bytes")) {
- if (resctrl_arch_is_mbm_total_enabled())
- rdtgrp->mba_mbps_event = QOS_L3_MBM_TOTAL_EVENT_ID;
- else
- ret = -EINVAL;
- } else {
- ret = -EINVAL;
- }
-
- if (ret)
- rdt_last_cmd_printf("Unsupported event id '%s'\n", buf);
-
- rdtgroup_kn_unlock(of->kn);
-
- return ret ?: nbytes;
-}
-
-int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
- struct seq_file *s, void *v)
-{
- struct rdtgroup *rdtgrp;
- int ret = 0;
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
-
- if (rdtgrp) {
- switch (rdtgrp->mba_mbps_event) {
- case QOS_L3_MBM_LOCAL_EVENT_ID:
- seq_puts(s, "mbm_local_bytes\n");
- break;
- case QOS_L3_MBM_TOTAL_EVENT_ID:
- seq_puts(s, "mbm_total_bytes\n");
- break;
- default:
- pr_warn_once("Bad event %d\n", rdtgrp->mba_mbps_event);
- ret = -EINVAL;
- break;
- }
- } else {
- ret = -ENOENT;
- }
-
- rdtgroup_kn_unlock(of->kn);
-
- return ret;
-}
-
-struct rdt_domain_hdr *resctrl_find_domain(struct list_head *h, int id,
- struct list_head **pos)
-{
- struct rdt_domain_hdr *d;
- struct list_head *l;
-
- list_for_each(l, h) {
- d = list_entry(l, struct rdt_domain_hdr, list);
- /* When id is found, return its domain. */
- if (id == d->id)
- return d;
- /* Stop searching when finding id's position in sorted list. */
- if (id < d->id)
- break;
- }
-
- if (pos)
- *pos = l;
-
- return NULL;
-}
-
-void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
- struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
- cpumask_t *cpumask, int evtid, int first)
-{
- int cpu;
-
- /* When picking a CPU from cpu_mask, ensure it can't race with cpuhp */
- lockdep_assert_cpus_held();
-
- /*
- * Setup the parameters to pass to mon_event_count() to read the data.
- */
- rr->rgrp = rdtgrp;
- rr->evtid = evtid;
- rr->r = r;
- rr->d = d;
- rr->first = first;
- rr->arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, evtid);
- if (IS_ERR(rr->arch_mon_ctx)) {
- rr->err = -EINVAL;
- return;
- }
-
- cpu = cpumask_any_housekeeping(cpumask, RESCTRL_PICK_ANY_CPU);
-
- /*
- * cpumask_any_housekeeping() prefers housekeeping CPUs, but
- * are all the CPUs nohz_full? If yes, pick a CPU to IPI.
- * MPAM's resctrl_arch_rmid_read() is unable to read the
- * counters on some platforms if its called in IRQ context.
- */
- if (tick_nohz_full_cpu(cpu))
- smp_call_function_any(cpumask, mon_event_count, rr, 1);
- else
- smp_call_on_cpu(cpu, smp_mon_event_count, rr, false);
-
- resctrl_arch_mon_ctx_free(r, evtid, rr->arch_mon_ctx);
-}
-
-int rdtgroup_mondata_show(struct seq_file *m, void *arg)
-{
- struct kernfs_open_file *of = m->private;
- struct rdt_domain_hdr *hdr;
- struct rmid_read rr = {0};
- struct rdt_mon_domain *d;
- u32 resid, evtid, domid;
- struct rdtgroup *rdtgrp;
- struct rdt_resource *r;
- union mon_data_bits md;
- int ret = 0;
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (!rdtgrp) {
- ret = -ENOENT;
- goto out;
- }
-
- md.priv = of->kn->priv;
- resid = md.u.rid;
- domid = md.u.domid;
- evtid = md.u.evtid;
- r = resctrl_arch_get_resource(resid);
-
- if (md.u.sum) {
- /*
- * This file requires summing across all domains that share
- * the L3 cache id that was provided in the "domid" field of the
- * mon_data_bits union. Search all domains in the resource for
- * one that matches this cache id.
- */
- list_for_each_entry(d, &r->mon_domains, hdr.list) {
- if (d->ci->id == domid) {
- rr.ci = d->ci;
- mon_event_read(&rr, r, NULL, rdtgrp,
- &d->ci->shared_cpu_map, evtid, false);
- goto checkresult;
- }
- }
- ret = -ENOENT;
- goto out;
- } else {
- /*
- * This file provides data from a single domain. Search
- * the resource to find the domain with "domid".
- */
- hdr = resctrl_find_domain(&r->mon_domains, domid, NULL);
- if (!hdr || WARN_ON_ONCE(hdr->type != RESCTRL_MON_DOMAIN)) {
- ret = -ENOENT;
- goto out;
- }
- d = container_of(hdr, struct rdt_mon_domain, hdr);
- mon_event_read(&rr, r, d, rdtgrp, &d->hdr.cpu_mask, evtid, false);
- }
-
-checkresult:
-
- if (rr.err == -EIO)
- seq_puts(m, "Error\n");
- else if (rr.err == -EINVAL)
- seq_puts(m, "Unavailable\n");
- else
- seq_printf(m, "%llu\n", rr.val);
-
-out:
- rdtgroup_kn_unlock(of->kn);
- return ret;
-}
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index eaae99602b61..5e3c41b36437 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -3,28 +3,21 @@
#define _ASM_X86_RESCTRL_INTERNAL_H
#include <linux/resctrl.h>
-#include <linux/sched.h>
-#include <linux/kernfs.h>
-#include <linux/fs_context.h>
-#include <linux/jump_label.h>
-#include <linux/tick.h>
-
-#include <asm/resctrl.h>
#define L3_QOS_CDP_ENABLE 0x01ULL
#define L2_QOS_CDP_ENABLE 0x01ULL
-#define CQM_LIMBOCHECK_INTERVAL 1000
-
#define MBM_CNTR_WIDTH_BASE 24
-#define MBM_OVERFLOW_INTERVAL 1000
-#define MAX_MBA_BW 100u
+
#define MBA_IS_LINEAR 0x4
+
#define MBM_CNTR_WIDTH_OFFSET_AMD 20
#define RMID_VAL_ERROR BIT_ULL(63)
+
#define RMID_VAL_UNAVAIL BIT_ULL(62)
+
/*
* With the above fields in use 62 bits remain in MSR_IA32_QM_CTR for
* data to be returned. The counter width is discovered from the hardware
@@ -33,278 +26,6 @@
#define MBM_CNTR_WIDTH_OFFSET_MAX (62 - MBM_CNTR_WIDTH_BASE)
/**
- * cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that
- * aren't marked nohz_full
- * @mask: The mask to pick a CPU from.
- * @exclude_cpu:The CPU to avoid picking.
- *
- * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping
- * CPUs that don't use nohz_full, these are preferred. Pass
- * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs.
- *
- * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available.
- */
-static inline unsigned int
-cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
-{
- unsigned int cpu, hk_cpu;
-
- if (exclude_cpu == RESCTRL_PICK_ANY_CPU)
- cpu = cpumask_any(mask);
- else
- cpu = cpumask_any_but(mask, exclude_cpu);
-
- /* Only continue if tick_nohz_full_mask has been initialized. */
- if (!tick_nohz_full_enabled())
- return cpu;
-
- /* If the CPU picked isn't marked nohz_full nothing more needs doing. */
- if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu))
- return cpu;
-
- /* Try to find a CPU that isn't nohz_full to use in preference */
- hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
- if (hk_cpu == exclude_cpu)
- hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask);
-
- if (hk_cpu < nr_cpu_ids)
- cpu = hk_cpu;
-
- return cpu;
-}
-
-struct rdt_fs_context {
- struct kernfs_fs_context kfc;
- bool enable_cdpl2;
- bool enable_cdpl3;
- bool enable_mba_mbps;
- bool enable_debug;
-};
-
-static inline struct rdt_fs_context *rdt_fc2context(struct fs_context *fc)
-{
- struct kernfs_fs_context *kfc = fc->fs_private;
-
- return container_of(kfc, struct rdt_fs_context, kfc);
-}
-
-/**
- * struct mon_evt - Entry in the event list of a resource
- * @evtid: event id
- * @name: name of the event
- * @configurable: true if the event is configurable
- * @list: entry in &rdt_resource->evt_list
- */
-struct mon_evt {
- enum resctrl_event_id evtid;
- char *name;
- bool configurable;
- struct list_head list;
-};
-
-/**
- * union mon_data_bits - Monitoring details for each event file.
- * @priv: Used to store monitoring event data in @u
- * as kernfs private data.
- * @u.rid: Resource id associated with the event file.
- * @u.evtid: Event id associated with the event file.
- * @u.sum: Set when event must be summed across multiple
- * domains.
- * @u.domid: When @u.sum is zero this is the domain to which
- * the event file belongs. When @sum is one this
- * is the id of the L3 cache that all domains to be
- * summed share.
- * @u: Name of the bit fields struct.
- */
-union mon_data_bits {
- void *priv;
- struct {
- unsigned int rid : 10;
- enum resctrl_event_id evtid : 7;
- unsigned int sum : 1;
- unsigned int domid : 14;
- } u;
-};
-
-/**
- * struct rmid_read - Data passed across smp_call*() to read event count.
- * @rgrp: Resource group for which the counter is being read. If it is a parent
- * resource group then its event count is summed with the count from all
- * its child resource groups.
- * @r: Resource describing the properties of the event being read.
- * @d: Domain that the counter should be read from. If NULL then sum all
- * domains in @r sharing L3 @ci.id
- * @evtid: Which monitor event to read.
- * @first: Initialize MBM counter when true.
- * @ci: Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
- * @err: Error encountered when reading counter.
- * @val: Returned value of event counter. If @rgrp is a parent resource group,
- * @val includes the sum of event counts from its child resource groups.
- * If @d is NULL, @val includes the sum of all domains in @r sharing @ci.id,
- * (summed across child resource groups if @rgrp is a parent resource group).
- * @arch_mon_ctx: Hardware monitor allocated for this read request (MPAM only).
- */
-struct rmid_read {
- struct rdtgroup *rgrp;
- struct rdt_resource *r;
- struct rdt_mon_domain *d;
- enum resctrl_event_id evtid;
- bool first;
- struct cacheinfo *ci;
- int err;
- u64 val;
- void *arch_mon_ctx;
-};
-
-extern struct list_head resctrl_schema_all;
-extern bool resctrl_mounted;
-
-enum rdt_group_type {
- RDTCTRL_GROUP = 0,
- RDTMON_GROUP,
- RDT_NUM_GROUP,
-};
-
-/**
- * enum rdtgrp_mode - Mode of a RDT resource group
- * @RDT_MODE_SHAREABLE: This resource group allows sharing of its allocations
- * @RDT_MODE_EXCLUSIVE: No sharing of this resource group's allocations allowed
- * @RDT_MODE_PSEUDO_LOCKSETUP: Resource group will be used for Pseudo-Locking
- * @RDT_MODE_PSEUDO_LOCKED: No sharing of this resource group's allocations
- * allowed AND the allocations are Cache Pseudo-Locked
- * @RDT_NUM_MODES: Total number of modes
- *
- * The mode of a resource group enables control over the allowed overlap
- * between allocations associated with different resource groups (classes
- * of service). User is able to modify the mode of a resource group by
- * writing to the "mode" resctrl file associated with the resource group.
- *
- * The "shareable", "exclusive", and "pseudo-locksetup" modes are set by
- * writing the appropriate text to the "mode" file. A resource group enters
- * "pseudo-locked" mode after the schemata is written while the resource
- * group is in "pseudo-locksetup" mode.
- */
-enum rdtgrp_mode {
- RDT_MODE_SHAREABLE = 0,
- RDT_MODE_EXCLUSIVE,
- RDT_MODE_PSEUDO_LOCKSETUP,
- RDT_MODE_PSEUDO_LOCKED,
-
- /* Must be last */
- RDT_NUM_MODES,
-};
-
-/**
- * struct mongroup - store mon group's data in resctrl fs.
- * @mon_data_kn: kernfs node for the mon_data directory
- * @parent: parent rdtgrp
- * @crdtgrp_list: child rdtgroup node list
- * @rmid: rmid for this rdtgroup
- */
-struct mongroup {
- struct kernfs_node *mon_data_kn;
- struct rdtgroup *parent;
- struct list_head crdtgrp_list;
- u32 rmid;
-};
-
-/**
- * struct rdtgroup - store rdtgroup's data in resctrl file system.
- * @kn: kernfs node
- * @rdtgroup_list: linked list for all rdtgroups
- * @closid: closid for this rdtgroup
- * @cpu_mask: CPUs assigned to this rdtgroup
- * @flags: status bits
- * @waitcount: how many cpus expect to find this
- * group when they acquire rdtgroup_mutex
- * @type: indicates type of this rdtgroup - either
- * monitor only or ctrl_mon group
- * @mon: mongroup related data
- * @mode: mode of resource group
- * @mba_mbps_event: input monitoring event id when mba_sc is enabled
- * @plr: pseudo-locked region
- */
-struct rdtgroup {
- struct kernfs_node *kn;
- struct list_head rdtgroup_list;
- u32 closid;
- struct cpumask cpu_mask;
- int flags;
- atomic_t waitcount;
- enum rdt_group_type type;
- struct mongroup mon;
- enum rdtgrp_mode mode;
- enum resctrl_event_id mba_mbps_event;
- struct pseudo_lock_region *plr;
-};
-
-/* rdtgroup.flags */
-#define RDT_DELETED 1
-
-/* rftype.flags */
-#define RFTYPE_FLAGS_CPUS_LIST 1
-
-/*
- * Define the file type flags for base and info directories.
- */
-#define RFTYPE_INFO BIT(0)
-#define RFTYPE_BASE BIT(1)
-#define RFTYPE_CTRL BIT(4)
-#define RFTYPE_MON BIT(5)
-#define RFTYPE_TOP BIT(6)
-#define RFTYPE_RES_CACHE BIT(8)
-#define RFTYPE_RES_MB BIT(9)
-#define RFTYPE_DEBUG BIT(10)
-#define RFTYPE_CTRL_INFO (RFTYPE_INFO | RFTYPE_CTRL)
-#define RFTYPE_MON_INFO (RFTYPE_INFO | RFTYPE_MON)
-#define RFTYPE_TOP_INFO (RFTYPE_INFO | RFTYPE_TOP)
-#define RFTYPE_CTRL_BASE (RFTYPE_BASE | RFTYPE_CTRL)
-#define RFTYPE_MON_BASE (RFTYPE_BASE | RFTYPE_MON)
-
-/* List of all resource groups */
-extern struct list_head rdt_all_groups;
-
-extern int max_name_width;
-
-/**
- * struct rftype - describe each file in the resctrl file system
- * @name: File name
- * @mode: Access mode
- * @kf_ops: File operations
- * @flags: File specific RFTYPE_FLAGS_* flags
- * @fflags: File specific RFTYPE_* flags
- * @seq_show: Show content of the file
- * @write: Write to the file
- */
-struct rftype {
- char *name;
- umode_t mode;
- const struct kernfs_ops *kf_ops;
- unsigned long flags;
- unsigned long fflags;
-
- int (*seq_show)(struct kernfs_open_file *of,
- struct seq_file *sf, void *v);
- /*
- * write() is the generic write callback which maps directly to
- * kernfs write operation and overrides all other operations.
- * Maximum write size is determined by ->max_write_len.
- */
- ssize_t (*write)(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off);
-};
-
-/**
- * struct mbm_state - status for each MBM counter in each domain
- * @prev_bw_bytes: Previous bytes value read for bandwidth calculation
- * @prev_bw: The most recent bandwidth in MBps
- */
-struct mbm_state {
- u64 prev_bw_bytes;
- u32 prev_bw;
-};
-
-/**
* struct arch_mbm_state - values used to compute resctrl_arch_rmid_read()s
* return value.
* @chunks: Total data moved (multiply by rdt_group.mon_scale to get bytes)
@@ -401,24 +122,7 @@ static inline struct rdt_hw_resource *resctrl_to_arch_res(struct rdt_resource *r
return container_of(r, struct rdt_hw_resource, r_resctrl);
}
-extern struct mutex rdtgroup_mutex;
-
-static inline const char *rdt_kn_name(const struct kernfs_node *kn)
-{
- return rcu_dereference_check(kn->name, lockdep_is_held(&rdtgroup_mutex));
-}
-
extern struct rdt_hw_resource rdt_resources_all[];
-extern struct rdtgroup rdtgroup_default;
-extern struct dentry *debugfs_resctrl;
-extern enum resctrl_event_id mba_mbps_default_event;
-
-static inline bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
-{
- return rdt_resources_all[l].cdp_enabled;
-}
-
-int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable);
void arch_mon_domain_online(struct rdt_resource *r, struct rdt_mon_domain *d);
@@ -455,99 +159,14 @@ union cpuid_0x10_x_edx {
unsigned int full;
};
-void rdt_last_cmd_clear(void);
-void rdt_last_cmd_puts(const char *s);
-__printf(1, 2)
-void rdt_last_cmd_printf(const char *fmt, ...);
-
void rdt_ctrl_update(void *arg);
-struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn);
-void rdtgroup_kn_unlock(struct kernfs_node *kn);
-int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name);
-int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
- umode_t mask);
-ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off);
-int rdtgroup_schemata_show(struct kernfs_open_file *of,
- struct seq_file *s, void *v);
-ssize_t rdtgroup_mba_mbps_event_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off);
-int rdtgroup_mba_mbps_event_show(struct kernfs_open_file *of,
- struct seq_file *s, void *v);
-bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
- unsigned long cbm, int closid, bool exclusive);
-unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r, struct rdt_ctrl_domain *d,
- unsigned long cbm);
-enum rdtgrp_mode rdtgroup_mode_by_closid(int closid);
-int rdtgroup_tasks_assigned(struct rdtgroup *r);
-int closids_supported(void);
-void closid_free(int closid);
-int alloc_rmid(u32 closid);
-void free_rmid(u32 closid, u32 rmid);
-int rdt_get_mon_l3_config(struct rdt_resource *r);
-void resctrl_mon_resource_exit(void);
-bool __init rdt_cpu_has(int flag);
-void mon_event_count(void *info);
-int rdtgroup_mondata_show(struct seq_file *m, void *arg);
-void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
- struct rdt_mon_domain *d, struct rdtgroup *rdtgrp,
- cpumask_t *cpumask, int evtid, int first);
-int __init resctrl_mon_resource_init(void);
-void mbm_setup_overflow_handler(struct rdt_mon_domain *dom,
- unsigned long delay_ms,
- int exclude_cpu);
-void mbm_handle_overflow(struct work_struct *work);
-void __init intel_rdt_mbm_apply_quirk(void);
-bool is_mba_sc(struct rdt_resource *r);
-void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
- int exclude_cpu);
-void cqm_handle_limbo(struct work_struct *work);
-bool has_busy_rmid(struct rdt_mon_domain *d);
-void __check_limbo(struct rdt_mon_domain *d, bool force_free);
-void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
-void resctrl_file_fflags_init(const char *config, unsigned long fflags);
-void rdt_staged_configs_clear(void);
-bool closid_allocated(unsigned int closid);
-int resctrl_find_cleanest_closid(void);
-
-#ifdef CONFIG_RESCTRL_FS_PSEUDO_LOCK
-int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp);
-int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp);
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm);
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d);
-int rdt_pseudo_lock_init(void);
-void rdt_pseudo_lock_release(void);
-int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp);
-void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp);
-#else
-static inline int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
-{
- return -EOPNOTSUPP;
-}
-static inline int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
-{
- return -EOPNOTSUPP;
-}
-
-static inline bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
-{
- return false;
-}
+int rdt_get_mon_l3_config(struct rdt_resource *r);
-static inline bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
-{
- return false;
-}
+bool rdt_cpu_has(int flag);
-static inline int rdt_pseudo_lock_init(void) { return 0; }
-static inline void rdt_pseudo_lock_release(void) { }
-static inline int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
-{
- return -EOPNOTSUPP;
-}
+void __init intel_rdt_mbm_apply_quirk(void);
-static inline void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp) { }
-#endif /* CONFIG_RESCTRL_FS_PSEUDO_LOCK */
+void rdt_domain_reconfigure_cdp(struct rdt_resource *r);
#endif /* _ASM_X86_RESCTRL_INTERNAL_H */
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index a93ed7d2a160..c261558276cd 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -18,62 +18,12 @@
#define pr_fmt(fmt) "resctrl: " fmt
#include <linux/cpu.h>
-#include <linux/module.h>
-#include <linux/sizes.h>
-#include <linux/slab.h>
+#include <linux/resctrl.h>
#include <asm/cpu_device_id.h>
-#include <asm/resctrl.h>
+#include <asm/msr.h>
#include "internal.h"
-#include "trace.h"
-
-/**
- * struct rmid_entry - dirty tracking for all RMID.
- * @closid: The CLOSID for this entry.
- * @rmid: The RMID for this entry.
- * @busy: The number of domains with cached data using this RMID.
- * @list: Member of the rmid_free_lru list when busy == 0.
- *
- * Depending on the architecture the correct monitor is accessed using
- * both @closid and @rmid, or @rmid only.
- *
- * Take the rdtgroup_mutex when accessing.
- */
-struct rmid_entry {
- u32 closid;
- u32 rmid;
- int busy;
- struct list_head list;
-};
-
-/*
- * @rmid_free_lru - A least recently used list of free RMIDs
- * These RMIDs are guaranteed to have an occupancy less than the
- * threshold occupancy
- */
-static LIST_HEAD(rmid_free_lru);
-
-/*
- * @closid_num_dirty_rmid The number of dirty RMID each CLOSID has.
- * Only allocated when CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID is defined.
- * Indexed by CLOSID. Protected by rdtgroup_mutex.
- */
-static u32 *closid_num_dirty_rmid;
-
-/*
- * @rmid_limbo_count - count of currently unused but (potentially)
- * dirty RMIDs.
- * This counts RMIDs that no one is currently using but that
- * may have a occupancy value > resctrl_rmid_realloc_threshold. User can
- * change the threshold occupancy value.
- */
-static unsigned int rmid_limbo_count;
-
-/*
- * @rmid_entry - The entry in the limbo and free lists.
- */
-static struct rmid_entry *rmid_ptrs;
/*
* Global boolean for rdt_monitor which is true if any
@@ -86,23 +36,12 @@ bool rdt_mon_capable;
*/
unsigned int rdt_mon_features;
-/*
- * This is the threshold cache occupancy in bytes at which we will consider an
- * RMID available for re-allocation.
- */
-unsigned int resctrl_rmid_realloc_threshold;
-
-/*
- * This is the maximum value for the reallocation threshold, in bytes.
- */
-unsigned int resctrl_rmid_realloc_limit;
-
#define CF(cf) ((unsigned long)(1048576 * (cf) + 0.5))
static int snc_nodes_per_l3_cache = 1;
/*
- * The correction factor table is documented in Documentation/arch/x86/resctrl.rst.
+ * The correction factor table is documented in Documentation/filesystems/resctrl.rst.
* If rmid > rmid threshold, MBM total and local values should be multiplied
* by the correction factor.
*
@@ -151,6 +90,7 @@ static const struct mbm_correction_factor_table {
};
static u32 mbm_cf_rmidthreshold __read_mostly = UINT_MAX;
+
static u64 mbm_cf __read_mostly;
static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
@@ -163,33 +103,6 @@ static inline u64 get_corrected_mbm_count(u32 rmid, unsigned long val)
}
/*
- * x86 and arm64 differ in their handling of monitoring.
- * x86's RMID are independent numbers, there is only one source of traffic
- * with an RMID value of '1'.
- * arm64's PMG extends the PARTID/CLOSID space, there are multiple sources of
- * traffic with a PMG value of '1', one for each CLOSID, meaning the RMID
- * value is no longer unique.
- * To account for this, resctrl uses an index. On x86 this is just the RMID,
- * on arm64 it encodes the CLOSID and RMID. This gives a unique number.
- *
- * The domain's rmid_busy_llc and rmid_ptrs[] are sized by index. The arch code
- * must accept an attempt to read every index.
- */
-static inline struct rmid_entry *__rmid_entry(u32 idx)
-{
- struct rmid_entry *entry;
- u32 closid, rmid;
-
- entry = &rmid_ptrs[idx];
- resctrl_arch_rmid_idx_decode(idx, &closid, &rmid);
-
- WARN_ON_ONCE(entry->closid != closid);
- WARN_ON_ONCE(entry->rmid != rmid);
-
- return entry;
-}
-
-/*
* When Sub-NUMA Cluster (SNC) mode is not enabled (as indicated by
* "snc_nodes_per_l3_cache == 1") no translation of the RMID value is
* needed. The physical RMID is the same as the logical RMID.
@@ -238,7 +151,7 @@ static int __rmid_read_phys(u32 prmid, enum resctrl_event_id eventid, u64 *val)
* are error bits.
*/
wrmsr(MSR_IA32_QM_EVTSEL, eventid, prmid);
- rdmsrl(MSR_IA32_QM_CTR, msr_val);
+ rdmsrq(MSR_IA32_QM_CTR, msr_val);
if (msr_val & RMID_VAL_ERROR)
return -EIO;
@@ -260,12 +173,11 @@ static struct arch_mbm_state *get_arch_mbm_state(struct rdt_hw_mon_domain *hw_do
return &hw_dom->arch_mbm_total[rmid];
case QOS_L3_MBM_LOCAL_EVENT_ID:
return &hw_dom->arch_mbm_local[rmid];
+ default:
+ /* Never expect to get here */
+ WARN_ON_ONCE(1);
+ return NULL;
}
-
- /* Never expect to get here */
- WARN_ON_ONCE(1);
-
- return NULL;
}
void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_mon_domain *d,
@@ -346,769 +258,6 @@ int resctrl_arch_rmid_read(struct rdt_resource *r, struct rdt_mon_domain *d,
return 0;
}
-static void limbo_release_entry(struct rmid_entry *entry)
-{
- lockdep_assert_held(&rdtgroup_mutex);
-
- rmid_limbo_count--;
- list_add_tail(&entry->list, &rmid_free_lru);
-
- if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
- closid_num_dirty_rmid[entry->closid]--;
-}
-
-/*
- * Check the RMIDs that are marked as busy for this domain. If the
- * reported LLC occupancy is below the threshold clear the busy bit and
- * decrement the count. If the busy count gets to zero on an RMID, we
- * free the RMID
- */
-void __check_limbo(struct rdt_mon_domain *d, bool force_free)
-{
- struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
- u32 idx_limit = resctrl_arch_system_num_rmid_idx();
- struct rmid_entry *entry;
- u32 idx, cur_idx = 1;
- void *arch_mon_ctx;
- bool rmid_dirty;
- u64 val = 0;
-
- arch_mon_ctx = resctrl_arch_mon_ctx_alloc(r, QOS_L3_OCCUP_EVENT_ID);
- if (IS_ERR(arch_mon_ctx)) {
- pr_warn_ratelimited("Failed to allocate monitor context: %ld",
- PTR_ERR(arch_mon_ctx));
- return;
- }
-
- /*
- * Skip RMID 0 and start from RMID 1 and check all the RMIDs that
- * are marked as busy for occupancy < threshold. If the occupancy
- * is less than the threshold decrement the busy counter of the
- * RMID and move it to the free list when the counter reaches 0.
- */
- for (;;) {
- idx = find_next_bit(d->rmid_busy_llc, idx_limit, cur_idx);
- if (idx >= idx_limit)
- break;
-
- entry = __rmid_entry(idx);
- if (resctrl_arch_rmid_read(r, d, entry->closid, entry->rmid,
- QOS_L3_OCCUP_EVENT_ID, &val,
- arch_mon_ctx)) {
- rmid_dirty = true;
- } else {
- rmid_dirty = (val >= resctrl_rmid_realloc_threshold);
-
- /*
- * x86's CLOSID and RMID are independent numbers, so the entry's
- * CLOSID is an empty CLOSID (X86_RESCTRL_EMPTY_CLOSID). On Arm the
- * RMID (PMG) extends the CLOSID (PARTID) space with bits that aren't
- * used to select the configuration. It is thus necessary to track both
- * CLOSID and RMID because there may be dependencies between them
- * on some architectures.
- */
- trace_mon_llc_occupancy_limbo(entry->closid, entry->rmid, d->hdr.id, val);
- }
-
- if (force_free || !rmid_dirty) {
- clear_bit(idx, d->rmid_busy_llc);
- if (!--entry->busy)
- limbo_release_entry(entry);
- }
- cur_idx = idx + 1;
- }
-
- resctrl_arch_mon_ctx_free(r, QOS_L3_OCCUP_EVENT_ID, arch_mon_ctx);
-}
-
-bool has_busy_rmid(struct rdt_mon_domain *d)
-{
- u32 idx_limit = resctrl_arch_system_num_rmid_idx();
-
- return find_first_bit(d->rmid_busy_llc, idx_limit) != idx_limit;
-}
-
-static struct rmid_entry *resctrl_find_free_rmid(u32 closid)
-{
- struct rmid_entry *itr;
- u32 itr_idx, cmp_idx;
-
- if (list_empty(&rmid_free_lru))
- return rmid_limbo_count ? ERR_PTR(-EBUSY) : ERR_PTR(-ENOSPC);
-
- list_for_each_entry(itr, &rmid_free_lru, list) {
- /*
- * Get the index of this free RMID, and the index it would need
- * to be if it were used with this CLOSID.
- * If the CLOSID is irrelevant on this architecture, the two
- * index values are always the same on every entry and thus the
- * very first entry will be returned.
- */
- itr_idx = resctrl_arch_rmid_idx_encode(itr->closid, itr->rmid);
- cmp_idx = resctrl_arch_rmid_idx_encode(closid, itr->rmid);
-
- if (itr_idx == cmp_idx)
- return itr;
- }
-
- return ERR_PTR(-ENOSPC);
-}
-
-/**
- * resctrl_find_cleanest_closid() - Find a CLOSID where all the associated
- * RMID are clean, or the CLOSID that has
- * the most clean RMID.
- *
- * MPAM's equivalent of RMID are per-CLOSID, meaning a freshly allocated CLOSID
- * may not be able to allocate clean RMID. To avoid this the allocator will
- * choose the CLOSID with the most clean RMID.
- *
- * When the CLOSID and RMID are independent numbers, the first free CLOSID will
- * be returned.
- */
-int resctrl_find_cleanest_closid(void)
-{
- u32 cleanest_closid = ~0;
- int i = 0;
-
- lockdep_assert_held(&rdtgroup_mutex);
-
- if (!IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
- return -EIO;
-
- for (i = 0; i < closids_supported(); i++) {
- int num_dirty;
-
- if (closid_allocated(i))
- continue;
-
- num_dirty = closid_num_dirty_rmid[i];
- if (num_dirty == 0)
- return i;
-
- if (cleanest_closid == ~0)
- cleanest_closid = i;
-
- if (num_dirty < closid_num_dirty_rmid[cleanest_closid])
- cleanest_closid = i;
- }
-
- if (cleanest_closid == ~0)
- return -ENOSPC;
-
- return cleanest_closid;
-}
-
-/*
- * For MPAM the RMID value is not unique, and has to be considered with
- * the CLOSID. The (CLOSID, RMID) pair is allocated on all domains, which
- * allows all domains to be managed by a single free list.
- * Each domain also has a rmid_busy_llc to reduce the work of the limbo handler.
- */
-int alloc_rmid(u32 closid)
-{
- struct rmid_entry *entry;
-
- lockdep_assert_held(&rdtgroup_mutex);
-
- entry = resctrl_find_free_rmid(closid);
- if (IS_ERR(entry))
- return PTR_ERR(entry);
-
- list_del(&entry->list);
- return entry->rmid;
-}
-
-static void add_rmid_to_limbo(struct rmid_entry *entry)
-{
- struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
- struct rdt_mon_domain *d;
- u32 idx;
-
- lockdep_assert_held(&rdtgroup_mutex);
-
- /* Walking r->domains, ensure it can't race with cpuhp */
- lockdep_assert_cpus_held();
-
- idx = resctrl_arch_rmid_idx_encode(entry->closid, entry->rmid);
-
- entry->busy = 0;
- list_for_each_entry(d, &r->mon_domains, hdr.list) {
- /*
- * For the first limbo RMID in the domain,
- * setup up the limbo worker.
- */
- if (!has_busy_rmid(d))
- cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL,
- RESCTRL_PICK_ANY_CPU);
- set_bit(idx, d->rmid_busy_llc);
- entry->busy++;
- }
-
- rmid_limbo_count++;
- if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID))
- closid_num_dirty_rmid[entry->closid]++;
-}
-
-void free_rmid(u32 closid, u32 rmid)
-{
- u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
- struct rmid_entry *entry;
-
- lockdep_assert_held(&rdtgroup_mutex);
-
- /*
- * Do not allow the default rmid to be free'd. Comparing by index
- * allows architectures that ignore the closid parameter to avoid an
- * unnecessary check.
- */
- if (!resctrl_arch_mon_capable() ||
- idx == resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
- RESCTRL_RESERVED_RMID))
- return;
-
- entry = __rmid_entry(idx);
-
- if (resctrl_arch_is_llc_occupancy_enabled())
- add_rmid_to_limbo(entry);
- else
- list_add_tail(&entry->list, &rmid_free_lru);
-}
-
-static struct mbm_state *get_mbm_state(struct rdt_mon_domain *d, u32 closid,
- u32 rmid, enum resctrl_event_id evtid)
-{
- u32 idx = resctrl_arch_rmid_idx_encode(closid, rmid);
-
- switch (evtid) {
- case QOS_L3_MBM_TOTAL_EVENT_ID:
- return &d->mbm_total[idx];
- case QOS_L3_MBM_LOCAL_EVENT_ID:
- return &d->mbm_local[idx];
- default:
- return NULL;
- }
-}
-
-static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
-{
- int cpu = smp_processor_id();
- struct rdt_mon_domain *d;
- struct mbm_state *m;
- int err, ret;
- u64 tval = 0;
-
- if (rr->first) {
- resctrl_arch_reset_rmid(rr->r, rr->d, closid, rmid, rr->evtid);
- m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
- if (m)
- memset(m, 0, sizeof(struct mbm_state));
- return 0;
- }
-
- if (rr->d) {
- /* Reading a single domain, must be on a CPU in that domain. */
- if (!cpumask_test_cpu(cpu, &rr->d->hdr.cpu_mask))
- return -EINVAL;
- rr->err = resctrl_arch_rmid_read(rr->r, rr->d, closid, rmid,
- rr->evtid, &tval, rr->arch_mon_ctx);
- if (rr->err)
- return rr->err;
-
- rr->val += tval;
-
- return 0;
- }
-
- /* Summing domains that share a cache, must be on a CPU for that cache. */
- if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
- return -EINVAL;
-
- /*
- * Legacy files must report the sum of an event across all
- * domains that share the same L3 cache instance.
- * Report success if a read from any domain succeeds, -EINVAL
- * (translated to "Unavailable" for user space) if reading from
- * all domains fail for any reason.
- */
- ret = -EINVAL;
- list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
- if (d->ci->id != rr->ci->id)
- continue;
- err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
- rr->evtid, &tval, rr->arch_mon_ctx);
- if (!err) {
- rr->val += tval;
- ret = 0;
- }
- }
-
- if (ret)
- rr->err = ret;
-
- return ret;
-}
-
-/*
- * mbm_bw_count() - Update bw count from values previously read by
- * __mon_event_count().
- * @closid: The closid used to identify the cached mbm_state.
- * @rmid: The rmid used to identify the cached mbm_state.
- * @rr: The struct rmid_read populated by __mon_event_count().
- *
- * Supporting function to calculate the memory bandwidth
- * and delta bandwidth in MBps. The chunks value previously read by
- * __mon_event_count() is compared with the chunks value from the previous
- * invocation. This must be called once per second to maintain values in MBps.
- */
-static void mbm_bw_count(u32 closid, u32 rmid, struct rmid_read *rr)
-{
- u64 cur_bw, bytes, cur_bytes;
- struct mbm_state *m;
-
- m = get_mbm_state(rr->d, closid, rmid, rr->evtid);
- if (WARN_ON_ONCE(!m))
- return;
-
- cur_bytes = rr->val;
- bytes = cur_bytes - m->prev_bw_bytes;
- m->prev_bw_bytes = cur_bytes;
-
- cur_bw = bytes / SZ_1M;
-
- m->prev_bw = cur_bw;
-}
-
-/*
- * This is scheduled by mon_event_read() to read the CQM/MBM counters
- * on a domain.
- */
-void mon_event_count(void *info)
-{
- struct rdtgroup *rdtgrp, *entry;
- struct rmid_read *rr = info;
- struct list_head *head;
- int ret;
-
- rdtgrp = rr->rgrp;
-
- ret = __mon_event_count(rdtgrp->closid, rdtgrp->mon.rmid, rr);
-
- /*
- * For Ctrl groups read data from child monitor groups and
- * add them together. Count events which are read successfully.
- * Discard the rmid_read's reporting errors.
- */
- head = &rdtgrp->mon.crdtgrp_list;
-
- if (rdtgrp->type == RDTCTRL_GROUP) {
- list_for_each_entry(entry, head, mon.crdtgrp_list) {
- if (__mon_event_count(entry->closid, entry->mon.rmid,
- rr) == 0)
- ret = 0;
- }
- }
-
- /*
- * __mon_event_count() calls for newly created monitor groups may
- * report -EINVAL/Unavailable if the monitor hasn't seen any traffic.
- * Discard error if any of the monitor event reads succeeded.
- */
- if (ret == 0)
- rr->err = 0;
-}
-
-static struct rdt_ctrl_domain *get_ctrl_domain_from_cpu(int cpu,
- struct rdt_resource *r)
-{
- struct rdt_ctrl_domain *d;
-
- lockdep_assert_cpus_held();
-
- list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
- /* Find the domain that contains this CPU */
- if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
- return d;
- }
-
- return NULL;
-}
-
-/*
- * Feedback loop for MBA software controller (mba_sc)
- *
- * mba_sc is a feedback loop where we periodically read MBM counters and
- * adjust the bandwidth percentage values via the IA32_MBA_THRTL_MSRs so
- * that:
- *
- * current bandwidth(cur_bw) < user specified bandwidth(user_bw)
- *
- * This uses the MBM counters to measure the bandwidth and MBA throttle
- * MSRs to control the bandwidth for a particular rdtgrp. It builds on the
- * fact that resctrl rdtgroups have both monitoring and control.
- *
- * The frequency of the checks is 1s and we just tag along the MBM overflow
- * timer. Having 1s interval makes the calculation of bandwidth simpler.
- *
- * Although MBA's goal is to restrict the bandwidth to a maximum, there may
- * be a need to increase the bandwidth to avoid unnecessarily restricting
- * the L2 <-> L3 traffic.
- *
- * Since MBA controls the L2 external bandwidth where as MBM measures the
- * L3 external bandwidth the following sequence could lead to such a
- * situation.
- *
- * Consider an rdtgroup which had high L3 <-> memory traffic in initial
- * phases -> mba_sc kicks in and reduced bandwidth percentage values -> but
- * after some time rdtgroup has mostly L2 <-> L3 traffic.
- *
- * In this case we may restrict the rdtgroup's L2 <-> L3 traffic as its
- * throttle MSRs already have low percentage values. To avoid
- * unnecessarily restricting such rdtgroups, we also increase the bandwidth.
- */
-static void update_mba_bw(struct rdtgroup *rgrp, struct rdt_mon_domain *dom_mbm)
-{
- u32 closid, rmid, cur_msr_val, new_msr_val;
- struct mbm_state *pmbm_data, *cmbm_data;
- struct rdt_ctrl_domain *dom_mba;
- enum resctrl_event_id evt_id;
- struct rdt_resource *r_mba;
- struct list_head *head;
- struct rdtgroup *entry;
- u32 cur_bw, user_bw;
-
- r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
- evt_id = rgrp->mba_mbps_event;
-
- closid = rgrp->closid;
- rmid = rgrp->mon.rmid;
- pmbm_data = get_mbm_state(dom_mbm, closid, rmid, evt_id);
- if (WARN_ON_ONCE(!pmbm_data))
- return;
-
- dom_mba = get_ctrl_domain_from_cpu(smp_processor_id(), r_mba);
- if (!dom_mba) {
- pr_warn_once("Failure to get domain for MBA update\n");
- return;
- }
-
- cur_bw = pmbm_data->prev_bw;
- user_bw = dom_mba->mbps_val[closid];
-
- /* MBA resource doesn't support CDP */
- cur_msr_val = resctrl_arch_get_config(r_mba, dom_mba, closid, CDP_NONE);
-
- /*
- * For Ctrl groups read data from child monitor groups.
- */
- head = &rgrp->mon.crdtgrp_list;
- list_for_each_entry(entry, head, mon.crdtgrp_list) {
- cmbm_data = get_mbm_state(dom_mbm, entry->closid, entry->mon.rmid, evt_id);
- if (WARN_ON_ONCE(!cmbm_data))
- return;
- cur_bw += cmbm_data->prev_bw;
- }
-
- /*
- * Scale up/down the bandwidth linearly for the ctrl group. The
- * bandwidth step is the bandwidth granularity specified by the
- * hardware.
- * Always increase throttling if current bandwidth is above the
- * target set by user.
- * But avoid thrashing up and down on every poll by checking
- * whether a decrease in throttling is likely to push the group
- * back over target. E.g. if currently throttling to 30% of bandwidth
- * on a system with 10% granularity steps, check whether moving to
- * 40% would go past the limit by multiplying current bandwidth by
- * "(30 + 10) / 30".
- */
- if (cur_msr_val > r_mba->membw.min_bw && user_bw < cur_bw) {
- new_msr_val = cur_msr_val - r_mba->membw.bw_gran;
- } else if (cur_msr_val < MAX_MBA_BW &&
- (user_bw > (cur_bw * (cur_msr_val + r_mba->membw.min_bw) / cur_msr_val))) {
- new_msr_val = cur_msr_val + r_mba->membw.bw_gran;
- } else {
- return;
- }
-
- resctrl_arch_update_one(r_mba, dom_mba, closid, CDP_NONE, new_msr_val);
-}
-
-static void mbm_update_one_event(struct rdt_resource *r, struct rdt_mon_domain *d,
- u32 closid, u32 rmid, enum resctrl_event_id evtid)
-{
- struct rmid_read rr = {0};
-
- rr.r = r;
- rr.d = d;
- rr.evtid = evtid;
- rr.arch_mon_ctx = resctrl_arch_mon_ctx_alloc(rr.r, rr.evtid);
- if (IS_ERR(rr.arch_mon_ctx)) {
- pr_warn_ratelimited("Failed to allocate monitor context: %ld",
- PTR_ERR(rr.arch_mon_ctx));
- return;
- }
-
- __mon_event_count(closid, rmid, &rr);
-
- /*
- * If the software controller is enabled, compute the
- * bandwidth for this event id.
- */
- if (is_mba_sc(NULL))
- mbm_bw_count(closid, rmid, &rr);
-
- resctrl_arch_mon_ctx_free(rr.r, rr.evtid, rr.arch_mon_ctx);
-}
-
-static void mbm_update(struct rdt_resource *r, struct rdt_mon_domain *d,
- u32 closid, u32 rmid)
-{
- /*
- * This is protected from concurrent reads from user as both
- * the user and overflow handler hold the global mutex.
- */
- if (resctrl_arch_is_mbm_total_enabled())
- mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_TOTAL_EVENT_ID);
-
- if (resctrl_arch_is_mbm_local_enabled())
- mbm_update_one_event(r, d, closid, rmid, QOS_L3_MBM_LOCAL_EVENT_ID);
-}
-
-/*
- * Handler to scan the limbo list and move the RMIDs
- * to free list whose occupancy < threshold_occupancy.
- */
-void cqm_handle_limbo(struct work_struct *work)
-{
- unsigned long delay = msecs_to_jiffies(CQM_LIMBOCHECK_INTERVAL);
- struct rdt_mon_domain *d;
-
- cpus_read_lock();
- mutex_lock(&rdtgroup_mutex);
-
- d = container_of(work, struct rdt_mon_domain, cqm_limbo.work);
-
- __check_limbo(d, false);
-
- if (has_busy_rmid(d)) {
- d->cqm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
- RESCTRL_PICK_ANY_CPU);
- schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo,
- delay);
- }
-
- mutex_unlock(&rdtgroup_mutex);
- cpus_read_unlock();
-}
-
-/**
- * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this
- * domain.
- * @dom: The domain the limbo handler should run for.
- * @delay_ms: How far in the future the handler should run.
- * @exclude_cpu: Which CPU the handler should not run on,
- * RESCTRL_PICK_ANY_CPU to pick any CPU.
- */
-void cqm_setup_limbo_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
- int exclude_cpu)
-{
- unsigned long delay = msecs_to_jiffies(delay_ms);
- int cpu;
-
- cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
- dom->cqm_work_cpu = cpu;
-
- if (cpu < nr_cpu_ids)
- schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
-}
-
-void mbm_handle_overflow(struct work_struct *work)
-{
- unsigned long delay = msecs_to_jiffies(MBM_OVERFLOW_INTERVAL);
- struct rdtgroup *prgrp, *crgrp;
- struct rdt_mon_domain *d;
- struct list_head *head;
- struct rdt_resource *r;
-
- cpus_read_lock();
- mutex_lock(&rdtgroup_mutex);
-
- /*
- * If the filesystem has been unmounted this work no longer needs to
- * run.
- */
- if (!resctrl_mounted || !resctrl_arch_mon_capable())
- goto out_unlock;
-
- r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
- d = container_of(work, struct rdt_mon_domain, mbm_over.work);
-
- list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
- mbm_update(r, d, prgrp->closid, prgrp->mon.rmid);
-
- head = &prgrp->mon.crdtgrp_list;
- list_for_each_entry(crgrp, head, mon.crdtgrp_list)
- mbm_update(r, d, crgrp->closid, crgrp->mon.rmid);
-
- if (is_mba_sc(NULL))
- update_mba_bw(prgrp, d);
- }
-
- /*
- * Re-check for housekeeping CPUs. This allows the overflow handler to
- * move off a nohz_full CPU quickly.
- */
- d->mbm_work_cpu = cpumask_any_housekeeping(&d->hdr.cpu_mask,
- RESCTRL_PICK_ANY_CPU);
- schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay);
-
-out_unlock:
- mutex_unlock(&rdtgroup_mutex);
- cpus_read_unlock();
-}
-
-/**
- * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this
- * domain.
- * @dom: The domain the overflow handler should run for.
- * @delay_ms: How far in the future the handler should run.
- * @exclude_cpu: Which CPU the handler should not run on,
- * RESCTRL_PICK_ANY_CPU to pick any CPU.
- */
-void mbm_setup_overflow_handler(struct rdt_mon_domain *dom, unsigned long delay_ms,
- int exclude_cpu)
-{
- unsigned long delay = msecs_to_jiffies(delay_ms);
- int cpu;
-
- /*
- * When a domain comes online there is no guarantee the filesystem is
- * mounted. If not, there is no need to catch counter overflow.
- */
- if (!resctrl_mounted || !resctrl_arch_mon_capable())
- return;
- cpu = cpumask_any_housekeeping(&dom->hdr.cpu_mask, exclude_cpu);
- dom->mbm_work_cpu = cpu;
-
- if (cpu < nr_cpu_ids)
- schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
-}
-
-static int dom_data_init(struct rdt_resource *r)
-{
- u32 idx_limit = resctrl_arch_system_num_rmid_idx();
- u32 num_closid = resctrl_arch_get_num_closid(r);
- struct rmid_entry *entry = NULL;
- int err = 0, i;
- u32 idx;
-
- mutex_lock(&rdtgroup_mutex);
- if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
- u32 *tmp;
-
- /*
- * If the architecture hasn't provided a sanitised value here,
- * this may result in larger arrays than necessary. Resctrl will
- * use a smaller system wide value based on the resources in
- * use.
- */
- tmp = kcalloc(num_closid, sizeof(*tmp), GFP_KERNEL);
- if (!tmp) {
- err = -ENOMEM;
- goto out_unlock;
- }
-
- closid_num_dirty_rmid = tmp;
- }
-
- rmid_ptrs = kcalloc(idx_limit, sizeof(struct rmid_entry), GFP_KERNEL);
- if (!rmid_ptrs) {
- if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
- kfree(closid_num_dirty_rmid);
- closid_num_dirty_rmid = NULL;
- }
- err = -ENOMEM;
- goto out_unlock;
- }
-
- for (i = 0; i < idx_limit; i++) {
- entry = &rmid_ptrs[i];
- INIT_LIST_HEAD(&entry->list);
-
- resctrl_arch_rmid_idx_decode(i, &entry->closid, &entry->rmid);
- list_add_tail(&entry->list, &rmid_free_lru);
- }
-
- /*
- * RESCTRL_RESERVED_CLOSID and RESCTRL_RESERVED_RMID are special and
- * are always allocated. These are used for the rdtgroup_default
- * control group, which will be setup later in resctrl_init().
- */
- idx = resctrl_arch_rmid_idx_encode(RESCTRL_RESERVED_CLOSID,
- RESCTRL_RESERVED_RMID);
- entry = __rmid_entry(idx);
- list_del(&entry->list);
-
-out_unlock:
- mutex_unlock(&rdtgroup_mutex);
-
- return err;
-}
-
-static void dom_data_exit(struct rdt_resource *r)
-{
- mutex_lock(&rdtgroup_mutex);
-
- if (!r->mon_capable)
- goto out_unlock;
-
- if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID)) {
- kfree(closid_num_dirty_rmid);
- closid_num_dirty_rmid = NULL;
- }
-
- kfree(rmid_ptrs);
- rmid_ptrs = NULL;
-
-out_unlock:
- mutex_unlock(&rdtgroup_mutex);
-}
-
-static struct mon_evt llc_occupancy_event = {
- .name = "llc_occupancy",
- .evtid = QOS_L3_OCCUP_EVENT_ID,
-};
-
-static struct mon_evt mbm_total_event = {
- .name = "mbm_total_bytes",
- .evtid = QOS_L3_MBM_TOTAL_EVENT_ID,
-};
-
-static struct mon_evt mbm_local_event = {
- .name = "mbm_local_bytes",
- .evtid = QOS_L3_MBM_LOCAL_EVENT_ID,
-};
-
-/*
- * Initialize the event list for the resource.
- *
- * Note that MBM events are also part of RDT_RESOURCE_L3 resource
- * because as per the SDM the total and local memory bandwidth
- * are enumerated as part of L3 monitoring.
- */
-static void l3_mon_evt_init(struct rdt_resource *r)
-{
- INIT_LIST_HEAD(&r->evt_list);
-
- if (resctrl_arch_is_llc_occupancy_enabled())
- list_add_tail(&llc_occupancy_event.list, &r->evt_list);
- if (resctrl_arch_is_mbm_total_enabled())
- list_add_tail(&mbm_total_event.list, &r->evt_list);
- if (resctrl_arch_is_mbm_local_enabled())
- list_add_tail(&mbm_local_event.list, &r->evt_list);
-}
-
/*
* The power-on reset value of MSR_RMID_SNC_CONFIG is 0x1
* which indicates that RMIDs are configured in legacy mode.
@@ -1192,51 +341,6 @@ static __init int snc_get_config(void)
return ret;
}
-/**
- * resctrl_mon_resource_init() - Initialise global monitoring structures.
- *
- * Allocate and initialise global monitor resources that do not belong to a
- * specific domain. i.e. the rmid_ptrs[] used for the limbo and free lists.
- * Called once during boot after the struct rdt_resource's have been configured
- * but before the filesystem is mounted.
- * Resctrl's cpuhp callbacks may be called before this point to bring a domain
- * online.
- *
- * Returns 0 for success, or -ENOMEM.
- */
-int __init resctrl_mon_resource_init(void)
-{
- struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
- int ret;
-
- if (!r->mon_capable)
- return 0;
-
- ret = dom_data_init(r);
- if (ret)
- return ret;
-
- l3_mon_evt_init(r);
-
- if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_TOTAL_EVENT_ID)) {
- mbm_total_event.configurable = true;
- resctrl_file_fflags_init("mbm_total_bytes_config",
- RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
- }
- if (resctrl_arch_is_evt_configurable(QOS_L3_MBM_LOCAL_EVENT_ID)) {
- mbm_local_event.configurable = true;
- resctrl_file_fflags_init("mbm_local_bytes_config",
- RFTYPE_MON_INFO | RFTYPE_RES_CACHE);
- }
-
- if (resctrl_arch_is_mbm_local_enabled())
- mba_mbps_default_event = QOS_L3_MBM_LOCAL_EVENT_ID;
- else if (resctrl_arch_is_mbm_total_enabled())
- mba_mbps_default_event = QOS_L3_MBM_TOTAL_EVENT_ID;
-
- return 0;
-}
-
int __init rdt_get_mon_l3_config(struct rdt_resource *r)
{
unsigned int mbm_offset = boot_cpu_data.x86_cache_mbm_width_offset;
@@ -1284,13 +388,6 @@ int __init rdt_get_mon_l3_config(struct rdt_resource *r)
return 0;
}
-void resctrl_mon_resource_exit(void)
-{
- struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
-
- dom_data_exit(r);
-}
-
void __init intel_rdt_mbm_apply_quirk(void)
{
int cf_index;
diff --git a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
index 92ea1472bde9..de580eca3363 100644
--- a/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock.c
@@ -11,26 +11,22 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <linux/cacheflush.h>
#include <linux/cpu.h>
-#include <linux/cpumask.h>
-#include <linux/debugfs.h>
-#include <linux/kthread.h>
-#include <linux/mman.h>
#include <linux/perf_event.h>
#include <linux/pm_qos.h>
-#include <linux/slab.h>
-#include <linux/uaccess.h>
+#include <linux/resctrl.h>
-#include <asm/cacheflush.h>
#include <asm/cpu_device_id.h>
-#include <asm/resctrl.h>
#include <asm/perf_event.h>
+#include <asm/msr.h>
#include "../../events/perf_event.h" /* For X86_CONFIG() */
#include "internal.h"
#define CREATE_TRACE_POINTS
-#include "trace.h"
+
+#include "pseudo_lock_trace.h"
/*
* The bits needed to disable hardware prefetching varies based on the
@@ -38,29 +34,6 @@
*/
static u64 prefetch_disable_bits;
-/*
- * Major number assigned to and shared by all devices exposing
- * pseudo-locked regions.
- */
-static unsigned int pseudo_lock_major;
-static unsigned long pseudo_lock_minor_avail = GENMASK(MINORBITS, 0);
-
-static char *pseudo_lock_devnode(const struct device *dev, umode_t *mode)
-{
- const struct rdtgroup *rdtgrp;
-
- rdtgrp = dev_get_drvdata(dev);
- if (mode)
- *mode = 0600;
- guard(mutex)(&rdtgroup_mutex);
- return kasprintf(GFP_KERNEL, "pseudo_lock/%s", rdt_kn_name(rdtgrp->kn));
-}
-
-static const struct class pseudo_lock_class = {
- .name = "pseudo_lock",
- .devnode = pseudo_lock_devnode,
-};
-
/**
* resctrl_arch_get_prefetch_disable_bits - prefetch disable bits of supported
* platforms
@@ -122,298 +95,6 @@ u64 resctrl_arch_get_prefetch_disable_bits(void)
}
/**
- * pseudo_lock_minor_get - Obtain available minor number
- * @minor: Pointer to where new minor number will be stored
- *
- * A bitmask is used to track available minor numbers. Here the next free
- * minor number is marked as unavailable and returned.
- *
- * Return: 0 on success, <0 on failure.
- */
-static int pseudo_lock_minor_get(unsigned int *minor)
-{
- unsigned long first_bit;
-
- first_bit = find_first_bit(&pseudo_lock_minor_avail, MINORBITS);
-
- if (first_bit == MINORBITS)
- return -ENOSPC;
-
- __clear_bit(first_bit, &pseudo_lock_minor_avail);
- *minor = first_bit;
-
- return 0;
-}
-
-/**
- * pseudo_lock_minor_release - Return minor number to available
- * @minor: The minor number made available
- */
-static void pseudo_lock_minor_release(unsigned int minor)
-{
- __set_bit(minor, &pseudo_lock_minor_avail);
-}
-
-/**
- * region_find_by_minor - Locate a pseudo-lock region by inode minor number
- * @minor: The minor number of the device representing pseudo-locked region
- *
- * When the character device is accessed we need to determine which
- * pseudo-locked region it belongs to. This is done by matching the minor
- * number of the device to the pseudo-locked region it belongs.
- *
- * Minor numbers are assigned at the time a pseudo-locked region is associated
- * with a cache instance.
- *
- * Return: On success return pointer to resource group owning the pseudo-locked
- * region, NULL on failure.
- */
-static struct rdtgroup *region_find_by_minor(unsigned int minor)
-{
- struct rdtgroup *rdtgrp, *rdtgrp_match = NULL;
-
- list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
- if (rdtgrp->plr && rdtgrp->plr->minor == minor) {
- rdtgrp_match = rdtgrp;
- break;
- }
- }
- return rdtgrp_match;
-}
-
-/**
- * struct pseudo_lock_pm_req - A power management QoS request list entry
- * @list: Entry within the @pm_reqs list for a pseudo-locked region
- * @req: PM QoS request
- */
-struct pseudo_lock_pm_req {
- struct list_head list;
- struct dev_pm_qos_request req;
-};
-
-static void pseudo_lock_cstates_relax(struct pseudo_lock_region *plr)
-{
- struct pseudo_lock_pm_req *pm_req, *next;
-
- list_for_each_entry_safe(pm_req, next, &plr->pm_reqs, list) {
- dev_pm_qos_remove_request(&pm_req->req);
- list_del(&pm_req->list);
- kfree(pm_req);
- }
-}
-
-/**
- * pseudo_lock_cstates_constrain - Restrict cores from entering C6
- * @plr: Pseudo-locked region
- *
- * To prevent the cache from being affected by power management entering
- * C6 has to be avoided. This is accomplished by requesting a latency
- * requirement lower than lowest C6 exit latency of all supported
- * platforms as found in the cpuidle state tables in the intel_idle driver.
- * At this time it is possible to do so with a single latency requirement
- * for all supported platforms.
- *
- * Since Goldmont is supported, which is affected by X86_BUG_MONITOR,
- * the ACPI latencies need to be considered while keeping in mind that C2
- * may be set to map to deeper sleep states. In this case the latency
- * requirement needs to prevent entering C2 also.
- *
- * Return: 0 on success, <0 on failure
- */
-static int pseudo_lock_cstates_constrain(struct pseudo_lock_region *plr)
-{
- struct pseudo_lock_pm_req *pm_req;
- int cpu;
- int ret;
-
- for_each_cpu(cpu, &plr->d->hdr.cpu_mask) {
- pm_req = kzalloc(sizeof(*pm_req), GFP_KERNEL);
- if (!pm_req) {
- rdt_last_cmd_puts("Failure to allocate memory for PM QoS\n");
- ret = -ENOMEM;
- goto out_err;
- }
- ret = dev_pm_qos_add_request(get_cpu_device(cpu),
- &pm_req->req,
- DEV_PM_QOS_RESUME_LATENCY,
- 30);
- if (ret < 0) {
- rdt_last_cmd_printf("Failed to add latency req CPU%d\n",
- cpu);
- kfree(pm_req);
- ret = -1;
- goto out_err;
- }
- list_add(&pm_req->list, &plr->pm_reqs);
- }
-
- return 0;
-
-out_err:
- pseudo_lock_cstates_relax(plr);
- return ret;
-}
-
-/**
- * pseudo_lock_region_clear - Reset pseudo-lock region data
- * @plr: pseudo-lock region
- *
- * All content of the pseudo-locked region is reset - any memory allocated
- * freed.
- *
- * Return: void
- */
-static void pseudo_lock_region_clear(struct pseudo_lock_region *plr)
-{
- plr->size = 0;
- plr->line_size = 0;
- kfree(plr->kmem);
- plr->kmem = NULL;
- plr->s = NULL;
- if (plr->d)
- plr->d->plr = NULL;
- plr->d = NULL;
- plr->cbm = 0;
- plr->debugfs_dir = NULL;
-}
-
-/**
- * pseudo_lock_region_init - Initialize pseudo-lock region information
- * @plr: pseudo-lock region
- *
- * Called after user provided a schemata to be pseudo-locked. From the
- * schemata the &struct pseudo_lock_region is on entry already initialized
- * with the resource, domain, and capacity bitmask. Here the information
- * required for pseudo-locking is deduced from this data and &struct
- * pseudo_lock_region initialized further. This information includes:
- * - size in bytes of the region to be pseudo-locked
- * - cache line size to know the stride with which data needs to be accessed
- * to be pseudo-locked
- * - a cpu associated with the cache instance on which the pseudo-locking
- * flow can be executed
- *
- * Return: 0 on success, <0 on failure. Descriptive error will be written
- * to last_cmd_status buffer.
- */
-static int pseudo_lock_region_init(struct pseudo_lock_region *plr)
-{
- enum resctrl_scope scope = plr->s->res->ctrl_scope;
- struct cacheinfo *ci;
- int ret;
-
- if (WARN_ON_ONCE(scope != RESCTRL_L2_CACHE && scope != RESCTRL_L3_CACHE))
- return -ENODEV;
-
- /* Pick the first cpu we find that is associated with the cache. */
- plr->cpu = cpumask_first(&plr->d->hdr.cpu_mask);
-
- if (!cpu_online(plr->cpu)) {
- rdt_last_cmd_printf("CPU %u associated with cache not online\n",
- plr->cpu);
- ret = -ENODEV;
- goto out_region;
- }
-
- ci = get_cpu_cacheinfo_level(plr->cpu, scope);
- if (ci) {
- plr->line_size = ci->coherency_line_size;
- plr->size = rdtgroup_cbm_to_size(plr->s->res, plr->d, plr->cbm);
- return 0;
- }
-
- ret = -1;
- rdt_last_cmd_puts("Unable to determine cache line size\n");
-out_region:
- pseudo_lock_region_clear(plr);
- return ret;
-}
-
-/**
- * pseudo_lock_init - Initialize a pseudo-lock region
- * @rdtgrp: resource group to which new pseudo-locked region will belong
- *
- * A pseudo-locked region is associated with a resource group. When this
- * association is created the pseudo-locked region is initialized. The
- * details of the pseudo-locked region are not known at this time so only
- * allocation is done and association established.
- *
- * Return: 0 on success, <0 on failure
- */
-static int pseudo_lock_init(struct rdtgroup *rdtgrp)
-{
- struct pseudo_lock_region *plr;
-
- plr = kzalloc(sizeof(*plr), GFP_KERNEL);
- if (!plr)
- return -ENOMEM;
-
- init_waitqueue_head(&plr->lock_thread_wq);
- INIT_LIST_HEAD(&plr->pm_reqs);
- rdtgrp->plr = plr;
- return 0;
-}
-
-/**
- * pseudo_lock_region_alloc - Allocate kernel memory that will be pseudo-locked
- * @plr: pseudo-lock region
- *
- * Initialize the details required to set up the pseudo-locked region and
- * allocate the contiguous memory that will be pseudo-locked to the cache.
- *
- * Return: 0 on success, <0 on failure. Descriptive error will be written
- * to last_cmd_status buffer.
- */
-static int pseudo_lock_region_alloc(struct pseudo_lock_region *plr)
-{
- int ret;
-
- ret = pseudo_lock_region_init(plr);
- if (ret < 0)
- return ret;
-
- /*
- * We do not yet support contiguous regions larger than
- * KMALLOC_MAX_SIZE.
- */
- if (plr->size > KMALLOC_MAX_SIZE) {
- rdt_last_cmd_puts("Requested region exceeds maximum size\n");
- ret = -E2BIG;
- goto out_region;
- }
-
- plr->kmem = kzalloc(plr->size, GFP_KERNEL);
- if (!plr->kmem) {
- rdt_last_cmd_puts("Unable to allocate memory\n");
- ret = -ENOMEM;
- goto out_region;
- }
-
- ret = 0;
- goto out;
-out_region:
- pseudo_lock_region_clear(plr);
-out:
- return ret;
-}
-
-/**
- * pseudo_lock_free - Free a pseudo-locked region
- * @rdtgrp: resource group to which pseudo-locked region belonged
- *
- * The pseudo-locked region's resources have already been released, or not
- * yet created at this point. Now it can be freed and disassociated from the
- * resource group.
- *
- * Return: void
- */
-static void pseudo_lock_free(struct rdtgroup *rdtgrp)
-{
- pseudo_lock_region_clear(rdtgrp->plr);
- kfree(rdtgrp->plr);
- rdtgrp->plr = NULL;
-}
-
-/**
* resctrl_arch_pseudo_lock_fn - Load kernel memory into cache
* @_plr: the pseudo-lock region descriptor
*
@@ -481,8 +162,8 @@ int resctrl_arch_pseudo_lock_fn(void *_plr)
* the buffer and evict pseudo-locked memory read earlier from the
* cache.
*/
- saved_msr = __rdmsr(MSR_MISC_FEATURE_CONTROL);
- __wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+ saved_msr = native_rdmsrq(MSR_MISC_FEATURE_CONTROL);
+ native_wrmsrq(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits);
closid_p = this_cpu_read(pqr_state.cur_closid);
rmid_p = this_cpu_read(pqr_state.cur_rmid);
mem_r = plr->kmem;
@@ -494,7 +175,7 @@ int resctrl_arch_pseudo_lock_fn(void *_plr)
* pseudo-locked followed by reading of kernel memory to load it
* into the cache.
*/
- __wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, plr->closid);
+ native_wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, plr->closid);
/*
* Cache was flushed earlier. Now access kernel memory to read it
@@ -531,10 +212,10 @@ int resctrl_arch_pseudo_lock_fn(void *_plr)
* Critical section end: restore closid with capacity bitmask that
* does not overlap with pseudo-locked region.
*/
- __wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, closid_p);
+ native_wrmsr(MSR_IA32_PQR_ASSOC, rmid_p, closid_p);
/* Re-enable the hardware prefetcher(s) */
- wrmsrl(MSR_MISC_FEATURE_CONTROL, saved_msr);
+ wrmsrq(MSR_MISC_FEATURE_CONTROL, saved_msr);
local_irq_enable();
plr->thread_done = 1;
@@ -543,340 +224,6 @@ int resctrl_arch_pseudo_lock_fn(void *_plr)
}
/**
- * rdtgroup_monitor_in_progress - Test if monitoring in progress
- * @rdtgrp: resource group being queried
- *
- * Return: 1 if monitor groups have been created for this resource
- * group, 0 otherwise.
- */
-static int rdtgroup_monitor_in_progress(struct rdtgroup *rdtgrp)
-{
- return !list_empty(&rdtgrp->mon.crdtgrp_list);
-}
-
-/**
- * rdtgroup_locksetup_user_restrict - Restrict user access to group
- * @rdtgrp: resource group needing access restricted
- *
- * A resource group used for cache pseudo-locking cannot have cpus or tasks
- * assigned to it. This is communicated to the user by restricting access
- * to all the files that can be used to make such changes.
- *
- * Permissions restored with rdtgroup_locksetup_user_restore()
- *
- * Return: 0 on success, <0 on failure. If a failure occurs during the
- * restriction of access an attempt will be made to restore permissions but
- * the state of the mode of these files will be uncertain when a failure
- * occurs.
- */
-static int rdtgroup_locksetup_user_restrict(struct rdtgroup *rdtgrp)
-{
- int ret;
-
- ret = rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
- if (ret)
- return ret;
-
- ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
- if (ret)
- goto err_tasks;
-
- ret = rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
- if (ret)
- goto err_cpus;
-
- if (resctrl_arch_mon_capable()) {
- ret = rdtgroup_kn_mode_restrict(rdtgrp, "mon_groups");
- if (ret)
- goto err_cpus_list;
- }
-
- ret = 0;
- goto out;
-
-err_cpus_list:
- rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
-err_cpus:
- rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
-err_tasks:
- rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
-out:
- return ret;
-}
-
-/**
- * rdtgroup_locksetup_user_restore - Restore user access to group
- * @rdtgrp: resource group needing access restored
- *
- * Restore all file access previously removed using
- * rdtgroup_locksetup_user_restrict()
- *
- * Return: 0 on success, <0 on failure. If a failure occurs during the
- * restoration of access an attempt will be made to restrict permissions
- * again but the state of the mode of these files will be uncertain when
- * a failure occurs.
- */
-static int rdtgroup_locksetup_user_restore(struct rdtgroup *rdtgrp)
-{
- int ret;
-
- ret = rdtgroup_kn_mode_restore(rdtgrp, "tasks", 0777);
- if (ret)
- return ret;
-
- ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0777);
- if (ret)
- goto err_tasks;
-
- ret = rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0777);
- if (ret)
- goto err_cpus;
-
- if (resctrl_arch_mon_capable()) {
- ret = rdtgroup_kn_mode_restore(rdtgrp, "mon_groups", 0777);
- if (ret)
- goto err_cpus_list;
- }
-
- ret = 0;
- goto out;
-
-err_cpus_list:
- rdtgroup_kn_mode_restrict(rdtgrp, "cpus_list");
-err_cpus:
- rdtgroup_kn_mode_restrict(rdtgrp, "cpus");
-err_tasks:
- rdtgroup_kn_mode_restrict(rdtgrp, "tasks");
-out:
- return ret;
-}
-
-/**
- * rdtgroup_locksetup_enter - Resource group enters locksetup mode
- * @rdtgrp: resource group requested to enter locksetup mode
- *
- * A resource group enters locksetup mode to reflect that it would be used
- * to represent a pseudo-locked region and is in the process of being set
- * up to do so. A resource group used for a pseudo-locked region would
- * lose the closid associated with it so we cannot allow it to have any
- * tasks or cpus assigned nor permit tasks or cpus to be assigned in the
- * future. Monitoring of a pseudo-locked region is not allowed either.
- *
- * The above and more restrictions on a pseudo-locked region are checked
- * for and enforced before the resource group enters the locksetup mode.
- *
- * Returns: 0 if the resource group successfully entered locksetup mode, <0
- * on failure. On failure the last_cmd_status buffer is updated with text to
- * communicate details of failure to the user.
- */
-int rdtgroup_locksetup_enter(struct rdtgroup *rdtgrp)
-{
- int ret;
-
- /*
- * The default resource group can neither be removed nor lose the
- * default closid associated with it.
- */
- if (rdtgrp == &rdtgroup_default) {
- rdt_last_cmd_puts("Cannot pseudo-lock default group\n");
- return -EINVAL;
- }
-
- /*
- * Cache Pseudo-locking not supported when CDP is enabled.
- *
- * Some things to consider if you would like to enable this
- * support (using L3 CDP as example):
- * - When CDP is enabled two separate resources are exposed,
- * L3DATA and L3CODE, but they are actually on the same cache.
- * The implication for pseudo-locking is that if a
- * pseudo-locked region is created on a domain of one
- * resource (eg. L3CODE), then a pseudo-locked region cannot
- * be created on that same domain of the other resource
- * (eg. L3DATA). This is because the creation of a
- * pseudo-locked region involves a call to wbinvd that will
- * affect all cache allocations on particular domain.
- * - Considering the previous, it may be possible to only
- * expose one of the CDP resources to pseudo-locking and
- * hide the other. For example, we could consider to only
- * expose L3DATA and since the L3 cache is unified it is
- * still possible to place instructions there are execute it.
- * - If only one region is exposed to pseudo-locking we should
- * still keep in mind that availability of a portion of cache
- * for pseudo-locking should take into account both resources.
- * Similarly, if a pseudo-locked region is created in one
- * resource, the portion of cache used by it should be made
- * unavailable to all future allocations from both resources.
- */
- if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3) ||
- resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2)) {
- rdt_last_cmd_puts("CDP enabled\n");
- return -EINVAL;
- }
-
- /*
- * Not knowing the bits to disable prefetching implies that this
- * platform does not support Cache Pseudo-Locking.
- */
- if (resctrl_arch_get_prefetch_disable_bits() == 0) {
- rdt_last_cmd_puts("Pseudo-locking not supported\n");
- return -EINVAL;
- }
-
- if (rdtgroup_monitor_in_progress(rdtgrp)) {
- rdt_last_cmd_puts("Monitoring in progress\n");
- return -EINVAL;
- }
-
- if (rdtgroup_tasks_assigned(rdtgrp)) {
- rdt_last_cmd_puts("Tasks assigned to resource group\n");
- return -EINVAL;
- }
-
- if (!cpumask_empty(&rdtgrp->cpu_mask)) {
- rdt_last_cmd_puts("CPUs assigned to resource group\n");
- return -EINVAL;
- }
-
- if (rdtgroup_locksetup_user_restrict(rdtgrp)) {
- rdt_last_cmd_puts("Unable to modify resctrl permissions\n");
- return -EIO;
- }
-
- ret = pseudo_lock_init(rdtgrp);
- if (ret) {
- rdt_last_cmd_puts("Unable to init pseudo-lock region\n");
- goto out_release;
- }
-
- /*
- * If this system is capable of monitoring a rmid would have been
- * allocated when the control group was created. This is not needed
- * anymore when this group would be used for pseudo-locking. This
- * is safe to call on platforms not capable of monitoring.
- */
- free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-
- ret = 0;
- goto out;
-
-out_release:
- rdtgroup_locksetup_user_restore(rdtgrp);
-out:
- return ret;
-}
-
-/**
- * rdtgroup_locksetup_exit - resource group exist locksetup mode
- * @rdtgrp: resource group
- *
- * When a resource group exits locksetup mode the earlier restrictions are
- * lifted.
- *
- * Return: 0 on success, <0 on failure
- */
-int rdtgroup_locksetup_exit(struct rdtgroup *rdtgrp)
-{
- int ret;
-
- if (resctrl_arch_mon_capable()) {
- ret = alloc_rmid(rdtgrp->closid);
- if (ret < 0) {
- rdt_last_cmd_puts("Out of RMIDs\n");
- return ret;
- }
- rdtgrp->mon.rmid = ret;
- }
-
- ret = rdtgroup_locksetup_user_restore(rdtgrp);
- if (ret) {
- free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
- return ret;
- }
-
- pseudo_lock_free(rdtgrp);
- return 0;
-}
-
-/**
- * rdtgroup_cbm_overlaps_pseudo_locked - Test if CBM or portion is pseudo-locked
- * @d: RDT domain
- * @cbm: CBM to test
- *
- * @d represents a cache instance and @cbm a capacity bitmask that is
- * considered for it. Determine if @cbm overlaps with any existing
- * pseudo-locked region on @d.
- *
- * @cbm is unsigned long, even if only 32 bits are used, to make the
- * bitmap functions work correctly.
- *
- * Return: true if @cbm overlaps with pseudo-locked region on @d, false
- * otherwise.
- */
-bool rdtgroup_cbm_overlaps_pseudo_locked(struct rdt_ctrl_domain *d, unsigned long cbm)
-{
- unsigned int cbm_len;
- unsigned long cbm_b;
-
- if (d->plr) {
- cbm_len = d->plr->s->res->cache.cbm_len;
- cbm_b = d->plr->cbm;
- if (bitmap_intersects(&cbm, &cbm_b, cbm_len))
- return true;
- }
- return false;
-}
-
-/**
- * rdtgroup_pseudo_locked_in_hierarchy - Pseudo-locked region in cache hierarchy
- * @d: RDT domain under test
- *
- * The setup of a pseudo-locked region affects all cache instances within
- * the hierarchy of the region. It is thus essential to know if any
- * pseudo-locked regions exist within a cache hierarchy to prevent any
- * attempts to create new pseudo-locked regions in the same hierarchy.
- *
- * Return: true if a pseudo-locked region exists in the hierarchy of @d or
- * if it is not possible to test due to memory allocation issue,
- * false otherwise.
- */
-bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_ctrl_domain *d)
-{
- struct rdt_ctrl_domain *d_i;
- cpumask_var_t cpu_with_psl;
- struct rdt_resource *r;
- bool ret = false;
-
- /* Walking r->domains, ensure it can't race with cpuhp */
- lockdep_assert_cpus_held();
-
- if (!zalloc_cpumask_var(&cpu_with_psl, GFP_KERNEL))
- return true;
-
- /*
- * First determine which cpus have pseudo-locked regions
- * associated with them.
- */
- for_each_alloc_capable_rdt_resource(r) {
- list_for_each_entry(d_i, &r->ctrl_domains, hdr.list) {
- if (d_i->plr)
- cpumask_or(cpu_with_psl, cpu_with_psl,
- &d_i->hdr.cpu_mask);
- }
- }
-
- /*
- * Next test if new pseudo-locked region would intersect with
- * existing region.
- */
- if (cpumask_intersects(&d->hdr.cpu_mask, cpu_with_psl))
- ret = true;
-
- free_cpumask_var(cpu_with_psl);
- return ret;
-}
-
-/**
* resctrl_arch_measure_cycles_lat_fn - Measure cycle latency to read
* pseudo-locked memory
* @_plr: pseudo-lock region to measure
@@ -904,7 +251,7 @@ int resctrl_arch_measure_cycles_lat_fn(void *_plr)
* Disable hardware prefetchers.
*/
rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
- wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+ wrmsrq(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits);
mem_r = READ_ONCE(plr->kmem);
/*
* Dummy execute of the time measurement to load the needed
@@ -1000,7 +347,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
* Disable hardware prefetchers.
*/
rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
- wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
+ wrmsrq(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits);
/* Initialize rest of local variables */
/*
@@ -1018,8 +365,8 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
* used in L1 cache, second to capture accurate value that does not
* include cache misses incurred because of instruction loads.
*/
- rdpmcl(hit_pmcnum, hits_before);
- rdpmcl(miss_pmcnum, miss_before);
+ hits_before = rdpmc(hit_pmcnum);
+ miss_before = rdpmc(miss_pmcnum);
/*
* From SDM: Performing back-to-back fast reads are not guaranteed
* to be monotonic.
@@ -1027,8 +374,8 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
* before proceeding.
*/
rmb();
- rdpmcl(hit_pmcnum, hits_before);
- rdpmcl(miss_pmcnum, miss_before);
+ hits_before = rdpmc(hit_pmcnum);
+ miss_before = rdpmc(miss_pmcnum);
/*
* Use LFENCE to ensure all previous instructions are retired
* before proceeding.
@@ -1050,8 +397,8 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
* before proceeding.
*/
rmb();
- rdpmcl(hit_pmcnum, hits_after);
- rdpmcl(miss_pmcnum, miss_after);
+ hits_after = rdpmc(hit_pmcnum);
+ miss_after = rdpmc(miss_pmcnum);
/*
* Use LFENCE to ensure all previous instructions are retired
* before proceeding.
@@ -1168,433 +515,3 @@ out:
wake_up_interruptible(&plr->lock_thread_wq);
return 0;
}
-
-/**
- * pseudo_lock_measure_cycles - Trigger latency measure to pseudo-locked region
- * @rdtgrp: Resource group to which the pseudo-locked region belongs.
- * @sel: Selector of which measurement to perform on a pseudo-locked region.
- *
- * The measurement of latency to access a pseudo-locked region should be
- * done from a cpu that is associated with that pseudo-locked region.
- * Determine which cpu is associated with this region and start a thread on
- * that cpu to perform the measurement, wait for that thread to complete.
- *
- * Return: 0 on success, <0 on failure
- */
-static int pseudo_lock_measure_cycles(struct rdtgroup *rdtgrp, int sel)
-{
- struct pseudo_lock_region *plr = rdtgrp->plr;
- struct task_struct *thread;
- unsigned int cpu;
- int ret = -1;
-
- cpus_read_lock();
- mutex_lock(&rdtgroup_mutex);
-
- if (rdtgrp->flags & RDT_DELETED) {
- ret = -ENODEV;
- goto out;
- }
-
- if (!plr->d) {
- ret = -ENODEV;
- goto out;
- }
-
- plr->thread_done = 0;
- cpu = cpumask_first(&plr->d->hdr.cpu_mask);
- if (!cpu_online(cpu)) {
- ret = -ENODEV;
- goto out;
- }
-
- plr->cpu = cpu;
-
- if (sel == 1)
- thread = kthread_run_on_cpu(resctrl_arch_measure_cycles_lat_fn,
- plr, cpu, "pseudo_lock_measure/%u");
- else if (sel == 2)
- thread = kthread_run_on_cpu(resctrl_arch_measure_l2_residency,
- plr, cpu, "pseudo_lock_measure/%u");
- else if (sel == 3)
- thread = kthread_run_on_cpu(resctrl_arch_measure_l3_residency,
- plr, cpu, "pseudo_lock_measure/%u");
- else
- goto out;
-
- if (IS_ERR(thread)) {
- ret = PTR_ERR(thread);
- goto out;
- }
-
- ret = wait_event_interruptible(plr->lock_thread_wq,
- plr->thread_done == 1);
- if (ret < 0)
- goto out;
-
- ret = 0;
-
-out:
- mutex_unlock(&rdtgroup_mutex);
- cpus_read_unlock();
- return ret;
-}
-
-static ssize_t pseudo_lock_measure_trigger(struct file *file,
- const char __user *user_buf,
- size_t count, loff_t *ppos)
-{
- struct rdtgroup *rdtgrp = file->private_data;
- size_t buf_size;
- char buf[32];
- int ret;
- int sel;
-
- buf_size = min(count, (sizeof(buf) - 1));
- if (copy_from_user(buf, user_buf, buf_size))
- return -EFAULT;
-
- buf[buf_size] = '\0';
- ret = kstrtoint(buf, 10, &sel);
- if (ret == 0) {
- if (sel != 1 && sel != 2 && sel != 3)
- return -EINVAL;
- ret = debugfs_file_get(file->f_path.dentry);
- if (ret)
- return ret;
- ret = pseudo_lock_measure_cycles(rdtgrp, sel);
- if (ret == 0)
- ret = count;
- debugfs_file_put(file->f_path.dentry);
- }
-
- return ret;
-}
-
-static const struct file_operations pseudo_measure_fops = {
- .write = pseudo_lock_measure_trigger,
- .open = simple_open,
- .llseek = default_llseek,
-};
-
-/**
- * rdtgroup_pseudo_lock_create - Create a pseudo-locked region
- * @rdtgrp: resource group to which pseudo-lock region belongs
- *
- * Called when a resource group in the pseudo-locksetup mode receives a
- * valid schemata that should be pseudo-locked. Since the resource group is
- * in pseudo-locksetup mode the &struct pseudo_lock_region has already been
- * allocated and initialized with the essential information. If a failure
- * occurs the resource group remains in the pseudo-locksetup mode with the
- * &struct pseudo_lock_region associated with it, but cleared from all
- * information and ready for the user to re-attempt pseudo-locking by
- * writing the schemata again.
- *
- * Return: 0 if the pseudo-locked region was successfully pseudo-locked, <0
- * on failure. Descriptive error will be written to last_cmd_status buffer.
- */
-int rdtgroup_pseudo_lock_create(struct rdtgroup *rdtgrp)
-{
- struct pseudo_lock_region *plr = rdtgrp->plr;
- struct task_struct *thread;
- unsigned int new_minor;
- struct device *dev;
- char *kn_name __free(kfree) = NULL;
- int ret;
-
- ret = pseudo_lock_region_alloc(plr);
- if (ret < 0)
- return ret;
-
- ret = pseudo_lock_cstates_constrain(plr);
- if (ret < 0) {
- ret = -EINVAL;
- goto out_region;
- }
- kn_name = kstrdup(rdt_kn_name(rdtgrp->kn), GFP_KERNEL);
- if (!kn_name) {
- ret = -ENOMEM;
- goto out_cstates;
- }
-
- plr->thread_done = 0;
-
- thread = kthread_run_on_cpu(resctrl_arch_pseudo_lock_fn, plr,
- plr->cpu, "pseudo_lock/%u");
- if (IS_ERR(thread)) {
- ret = PTR_ERR(thread);
- rdt_last_cmd_printf("Locking thread returned error %d\n", ret);
- goto out_cstates;
- }
-
- ret = wait_event_interruptible(plr->lock_thread_wq,
- plr->thread_done == 1);
- if (ret < 0) {
- /*
- * If the thread does not get on the CPU for whatever
- * reason and the process which sets up the region is
- * interrupted then this will leave the thread in runnable
- * state and once it gets on the CPU it will dereference
- * the cleared, but not freed, plr struct resulting in an
- * empty pseudo-locking loop.
- */
- rdt_last_cmd_puts("Locking thread interrupted\n");
- goto out_cstates;
- }
-
- ret = pseudo_lock_minor_get(&new_minor);
- if (ret < 0) {
- rdt_last_cmd_puts("Unable to obtain a new minor number\n");
- goto out_cstates;
- }
-
- /*
- * Unlock access but do not release the reference. The
- * pseudo-locked region will still be here on return.
- *
- * The mutex has to be released temporarily to avoid a potential
- * deadlock with the mm->mmap_lock which is obtained in the
- * device_create() and debugfs_create_dir() callpath below as well as
- * before the mmap() callback is called.
- */
- mutex_unlock(&rdtgroup_mutex);
-
- if (!IS_ERR_OR_NULL(debugfs_resctrl)) {
- plr->debugfs_dir = debugfs_create_dir(kn_name, debugfs_resctrl);
- if (!IS_ERR_OR_NULL(plr->debugfs_dir))
- debugfs_create_file("pseudo_lock_measure", 0200,
- plr->debugfs_dir, rdtgrp,
- &pseudo_measure_fops);
- }
-
- dev = device_create(&pseudo_lock_class, NULL,
- MKDEV(pseudo_lock_major, new_minor),
- rdtgrp, "%s", kn_name);
-
- mutex_lock(&rdtgroup_mutex);
-
- if (IS_ERR(dev)) {
- ret = PTR_ERR(dev);
- rdt_last_cmd_printf("Failed to create character device: %d\n",
- ret);
- goto out_debugfs;
- }
-
- /* We released the mutex - check if group was removed while we did so */
- if (rdtgrp->flags & RDT_DELETED) {
- ret = -ENODEV;
- goto out_device;
- }
-
- plr->minor = new_minor;
-
- rdtgrp->mode = RDT_MODE_PSEUDO_LOCKED;
- closid_free(rdtgrp->closid);
- rdtgroup_kn_mode_restore(rdtgrp, "cpus", 0444);
- rdtgroup_kn_mode_restore(rdtgrp, "cpus_list", 0444);
-
- ret = 0;
- goto out;
-
-out_device:
- device_destroy(&pseudo_lock_class, MKDEV(pseudo_lock_major, new_minor));
-out_debugfs:
- debugfs_remove_recursive(plr->debugfs_dir);
- pseudo_lock_minor_release(new_minor);
-out_cstates:
- pseudo_lock_cstates_relax(plr);
-out_region:
- pseudo_lock_region_clear(plr);
-out:
- return ret;
-}
-
-/**
- * rdtgroup_pseudo_lock_remove - Remove a pseudo-locked region
- * @rdtgrp: resource group to which the pseudo-locked region belongs
- *
- * The removal of a pseudo-locked region can be initiated when the resource
- * group is removed from user space via a "rmdir" from userspace or the
- * unmount of the resctrl filesystem. On removal the resource group does
- * not go back to pseudo-locksetup mode before it is removed, instead it is
- * removed directly. There is thus asymmetry with the creation where the
- * &struct pseudo_lock_region is removed here while it was not created in
- * rdtgroup_pseudo_lock_create().
- *
- * Return: void
- */
-void rdtgroup_pseudo_lock_remove(struct rdtgroup *rdtgrp)
-{
- struct pseudo_lock_region *plr = rdtgrp->plr;
-
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
- /*
- * Default group cannot be a pseudo-locked region so we can
- * free closid here.
- */
- closid_free(rdtgrp->closid);
- goto free;
- }
-
- pseudo_lock_cstates_relax(plr);
- debugfs_remove_recursive(rdtgrp->plr->debugfs_dir);
- device_destroy(&pseudo_lock_class, MKDEV(pseudo_lock_major, plr->minor));
- pseudo_lock_minor_release(plr->minor);
-
-free:
- pseudo_lock_free(rdtgrp);
-}
-
-static int pseudo_lock_dev_open(struct inode *inode, struct file *filp)
-{
- struct rdtgroup *rdtgrp;
-
- mutex_lock(&rdtgroup_mutex);
-
- rdtgrp = region_find_by_minor(iminor(inode));
- if (!rdtgrp) {
- mutex_unlock(&rdtgroup_mutex);
- return -ENODEV;
- }
-
- filp->private_data = rdtgrp;
- atomic_inc(&rdtgrp->waitcount);
- /* Perform a non-seekable open - llseek is not supported */
- filp->f_mode &= ~(FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE);
-
- mutex_unlock(&rdtgroup_mutex);
-
- return 0;
-}
-
-static int pseudo_lock_dev_release(struct inode *inode, struct file *filp)
-{
- struct rdtgroup *rdtgrp;
-
- mutex_lock(&rdtgroup_mutex);
- rdtgrp = filp->private_data;
- WARN_ON(!rdtgrp);
- if (!rdtgrp) {
- mutex_unlock(&rdtgroup_mutex);
- return -ENODEV;
- }
- filp->private_data = NULL;
- atomic_dec(&rdtgrp->waitcount);
- mutex_unlock(&rdtgroup_mutex);
- return 0;
-}
-
-static int pseudo_lock_dev_mremap(struct vm_area_struct *area)
-{
- /* Not supported */
- return -EINVAL;
-}
-
-static const struct vm_operations_struct pseudo_mmap_ops = {
- .mremap = pseudo_lock_dev_mremap,
-};
-
-static int pseudo_lock_dev_mmap(struct file *filp, struct vm_area_struct *vma)
-{
- unsigned long vsize = vma->vm_end - vma->vm_start;
- unsigned long off = vma->vm_pgoff << PAGE_SHIFT;
- struct pseudo_lock_region *plr;
- struct rdtgroup *rdtgrp;
- unsigned long physical;
- unsigned long psize;
-
- mutex_lock(&rdtgroup_mutex);
-
- rdtgrp = filp->private_data;
- WARN_ON(!rdtgrp);
- if (!rdtgrp) {
- mutex_unlock(&rdtgroup_mutex);
- return -ENODEV;
- }
-
- plr = rdtgrp->plr;
-
- if (!plr->d) {
- mutex_unlock(&rdtgroup_mutex);
- return -ENODEV;
- }
-
- /*
- * Task is required to run with affinity to the cpus associated
- * with the pseudo-locked region. If this is not the case the task
- * may be scheduled elsewhere and invalidate entries in the
- * pseudo-locked region.
- */
- if (!cpumask_subset(current->cpus_ptr, &plr->d->hdr.cpu_mask)) {
- mutex_unlock(&rdtgroup_mutex);
- return -EINVAL;
- }
-
- physical = __pa(plr->kmem) >> PAGE_SHIFT;
- psize = plr->size - off;
-
- if (off > plr->size) {
- mutex_unlock(&rdtgroup_mutex);
- return -ENOSPC;
- }
-
- /*
- * Ensure changes are carried directly to the memory being mapped,
- * do not allow copy-on-write mapping.
- */
- if (!(vma->vm_flags & VM_SHARED)) {
- mutex_unlock(&rdtgroup_mutex);
- return -EINVAL;
- }
-
- if (vsize > psize) {
- mutex_unlock(&rdtgroup_mutex);
- return -ENOSPC;
- }
-
- memset(plr->kmem + off, 0, vsize);
-
- if (remap_pfn_range(vma, vma->vm_start, physical + vma->vm_pgoff,
- vsize, vma->vm_page_prot)) {
- mutex_unlock(&rdtgroup_mutex);
- return -EAGAIN;
- }
- vma->vm_ops = &pseudo_mmap_ops;
- mutex_unlock(&rdtgroup_mutex);
- return 0;
-}
-
-static const struct file_operations pseudo_lock_dev_fops = {
- .owner = THIS_MODULE,
- .read = NULL,
- .write = NULL,
- .open = pseudo_lock_dev_open,
- .release = pseudo_lock_dev_release,
- .mmap = pseudo_lock_dev_mmap,
-};
-
-int rdt_pseudo_lock_init(void)
-{
- int ret;
-
- ret = register_chrdev(0, "pseudo_lock", &pseudo_lock_dev_fops);
- if (ret < 0)
- return ret;
-
- pseudo_lock_major = ret;
-
- ret = class_register(&pseudo_lock_class);
- if (ret) {
- unregister_chrdev(pseudo_lock_major, "pseudo_lock");
- return ret;
- }
-
- return 0;
-}
-
-void rdt_pseudo_lock_release(void)
-{
- class_unregister(&pseudo_lock_class);
- unregister_chrdev(pseudo_lock_major, "pseudo_lock");
- pseudo_lock_major = 0;
-}
diff --git a/arch/x86/kernel/cpu/resctrl/trace.h b/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h
index 2a506316b303..7c8aef08010f 100644
--- a/arch/x86/kernel/cpu/resctrl/trace.h
+++ b/arch/x86/kernel/cpu/resctrl/pseudo_lock_trace.h
@@ -2,8 +2,8 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM resctrl
-#if !defined(_TRACE_RESCTRL_H) || defined(TRACE_HEADER_MULTI_READ)
-#define _TRACE_RESCTRL_H
+#if !defined(_X86_RESCTRL_PSEUDO_LOCK_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define _X86_RESCTRL_PSEUDO_LOCK_TRACE_H
#include <linux/tracepoint.h>
@@ -35,25 +35,11 @@ TRACE_EVENT(pseudo_lock_l3,
TP_printk("hits=%llu miss=%llu",
__entry->l3_hits, __entry->l3_miss));
-TRACE_EVENT(mon_llc_occupancy_limbo,
- TP_PROTO(u32 ctrl_hw_id, u32 mon_hw_id, int domain_id, u64 llc_occupancy_bytes),
- TP_ARGS(ctrl_hw_id, mon_hw_id, domain_id, llc_occupancy_bytes),
- TP_STRUCT__entry(__field(u32, ctrl_hw_id)
- __field(u32, mon_hw_id)
- __field(int, domain_id)
- __field(u64, llc_occupancy_bytes)),
- TP_fast_assign(__entry->ctrl_hw_id = ctrl_hw_id;
- __entry->mon_hw_id = mon_hw_id;
- __entry->domain_id = domain_id;
- __entry->llc_occupancy_bytes = llc_occupancy_bytes;),
- TP_printk("ctrl_hw_id=%u mon_hw_id=%u domain_id=%d llc_occupancy_bytes=%llu",
- __entry->ctrl_hw_id, __entry->mon_hw_id, __entry->domain_id,
- __entry->llc_occupancy_bytes)
- );
-
-#endif /* _TRACE_RESCTRL_H */
+#endif /* _X86_RESCTRL_PSEUDO_LOCK_TRACE_H */
#undef TRACE_INCLUDE_PATH
#define TRACE_INCLUDE_PATH .
-#define TRACE_INCLUDE_FILE trace
+
+#define TRACE_INCLUDE_FILE pseudo_lock_trace
+
#include <trace/define_trace.h>
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index cc4a54145c83..885026468440 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -18,6 +18,7 @@
#include <linux/fs_parser.h>
#include <linux/sysfs.h>
#include <linux/kernfs.h>
+#include <linux/resctrl.h>
#include <linux/seq_buf.h>
#include <linux/seq_file.h>
#include <linux/sched/signal.h>
@@ -28,341 +29,17 @@
#include <uapi/linux/magic.h>
-#include <asm/resctrl.h>
+#include <asm/msr.h>
#include "internal.h"
DEFINE_STATIC_KEY_FALSE(rdt_enable_key);
-DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
-DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
-
-/* Mutex to protect rdtgroup access. */
-DEFINE_MUTEX(rdtgroup_mutex);
-
-static struct kernfs_root *rdt_root;
-struct rdtgroup rdtgroup_default;
-LIST_HEAD(rdt_all_groups);
-
-/* list of entries for the schemata file */
-LIST_HEAD(resctrl_schema_all);
-
-/* The filesystem can only be mounted once. */
-bool resctrl_mounted;
-
-/* Kernel fs node for "info" directory under root */
-static struct kernfs_node *kn_info;
-
-/* Kernel fs node for "mon_groups" directory under root */
-static struct kernfs_node *kn_mongrp;
-
-/* Kernel fs node for "mon_data" directory under root */
-static struct kernfs_node *kn_mondata;
-
-/*
- * Used to store the max resource name width to display the schemata names in
- * a tabular format.
- */
-int max_name_width;
-
-static struct seq_buf last_cmd_status;
-static char last_cmd_status_buf[512];
-
-static int rdtgroup_setup_root(struct rdt_fs_context *ctx);
-static void rdtgroup_destroy_root(void);
-
-struct dentry *debugfs_resctrl;
-
-/*
- * Memory bandwidth monitoring event to use for the default CTRL_MON group
- * and each new CTRL_MON group created by the user. Only relevant when
- * the filesystem is mounted with the "mba_MBps" option so it does not
- * matter that it remains uninitialized on systems that do not support
- * the "mba_MBps" option.
- */
-enum resctrl_event_id mba_mbps_default_event;
-
-static bool resctrl_debug;
-
-void rdt_last_cmd_clear(void)
-{
- lockdep_assert_held(&rdtgroup_mutex);
- seq_buf_clear(&last_cmd_status);
-}
-
-void rdt_last_cmd_puts(const char *s)
-{
- lockdep_assert_held(&rdtgroup_mutex);
- seq_buf_puts(&last_cmd_status, s);
-}
-
-void rdt_last_cmd_printf(const char *fmt, ...)
-{
- va_list ap;
-
- va_start(ap, fmt);
- lockdep_assert_held(&rdtgroup_mutex);
- seq_buf_vprintf(&last_cmd_status, fmt, ap);
- va_end(ap);
-}
-
-void rdt_staged_configs_clear(void)
-{
- struct rdt_ctrl_domain *dom;
- struct rdt_resource *r;
-
- lockdep_assert_held(&rdtgroup_mutex);
-
- for_each_alloc_capable_rdt_resource(r) {
- list_for_each_entry(dom, &r->ctrl_domains, hdr.list)
- memset(dom->staged_config, 0, sizeof(dom->staged_config));
- }
-}
-
-static bool resctrl_is_mbm_enabled(void)
-{
- return (resctrl_arch_is_mbm_total_enabled() ||
- resctrl_arch_is_mbm_local_enabled());
-}
-
-static bool resctrl_is_mbm_event(int e)
-{
- return (e >= QOS_L3_MBM_TOTAL_EVENT_ID &&
- e <= QOS_L3_MBM_LOCAL_EVENT_ID);
-}
-
-/*
- * Trivial allocator for CLOSIDs. Since h/w only supports a small number,
- * we can keep a bitmap of free CLOSIDs in a single integer.
- *
- * Using a global CLOSID across all resources has some advantages and
- * some drawbacks:
- * + We can simply set current's closid to assign a task to a resource
- * group.
- * + Context switch code can avoid extra memory references deciding which
- * CLOSID to load into the PQR_ASSOC MSR
- * - We give up some options in configuring resource groups across multi-socket
- * systems.
- * - Our choices on how to configure each resource become progressively more
- * limited as the number of resources grows.
- */
-static unsigned long closid_free_map;
-static int closid_free_map_len;
-
-int closids_supported(void)
-{
- return closid_free_map_len;
-}
-
-static void closid_init(void)
-{
- struct resctrl_schema *s;
- u32 rdt_min_closid = 32;
-
- /* Compute rdt_min_closid across all resources */
- list_for_each_entry(s, &resctrl_schema_all, list)
- rdt_min_closid = min(rdt_min_closid, s->num_closid);
-
- closid_free_map = BIT_MASK(rdt_min_closid) - 1;
-
- /* RESCTRL_RESERVED_CLOSID is always reserved for the default group */
- __clear_bit(RESCTRL_RESERVED_CLOSID, &closid_free_map);
- closid_free_map_len = rdt_min_closid;
-}
-
-static int closid_alloc(void)
-{
- int cleanest_closid;
- u32 closid;
-
- lockdep_assert_held(&rdtgroup_mutex);
-
- if (IS_ENABLED(CONFIG_RESCTRL_RMID_DEPENDS_ON_CLOSID) &&
- resctrl_arch_is_llc_occupancy_enabled()) {
- cleanest_closid = resctrl_find_cleanest_closid();
- if (cleanest_closid < 0)
- return cleanest_closid;
- closid = cleanest_closid;
- } else {
- closid = ffs(closid_free_map);
- if (closid == 0)
- return -ENOSPC;
- closid--;
- }
- __clear_bit(closid, &closid_free_map);
-
- return closid;
-}
-
-void closid_free(int closid)
-{
- lockdep_assert_held(&rdtgroup_mutex);
-
- __set_bit(closid, &closid_free_map);
-}
-
-/**
- * closid_allocated - test if provided closid is in use
- * @closid: closid to be tested
- *
- * Return: true if @closid is currently associated with a resource group,
- * false if @closid is free
- */
-bool closid_allocated(unsigned int closid)
-{
- lockdep_assert_held(&rdtgroup_mutex);
-
- return !test_bit(closid, &closid_free_map);
-}
-
-/**
- * rdtgroup_mode_by_closid - Return mode of resource group with closid
- * @closid: closid if the resource group
- *
- * Each resource group is associated with a @closid. Here the mode
- * of a resource group can be queried by searching for it using its closid.
- *
- * Return: mode as &enum rdtgrp_mode of resource group with closid @closid
- */
-enum rdtgrp_mode rdtgroup_mode_by_closid(int closid)
-{
- struct rdtgroup *rdtgrp;
-
- list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
- if (rdtgrp->closid == closid)
- return rdtgrp->mode;
- }
-
- return RDT_NUM_MODES;
-}
-
-static const char * const rdt_mode_str[] = {
- [RDT_MODE_SHAREABLE] = "shareable",
- [RDT_MODE_EXCLUSIVE] = "exclusive",
- [RDT_MODE_PSEUDO_LOCKSETUP] = "pseudo-locksetup",
- [RDT_MODE_PSEUDO_LOCKED] = "pseudo-locked",
-};
-
-/**
- * rdtgroup_mode_str - Return the string representation of mode
- * @mode: the resource group mode as &enum rdtgroup_mode
- *
- * Return: string representation of valid mode, "unknown" otherwise
- */
-static const char *rdtgroup_mode_str(enum rdtgrp_mode mode)
-{
- if (mode < RDT_MODE_SHAREABLE || mode >= RDT_NUM_MODES)
- return "unknown";
-
- return rdt_mode_str[mode];
-}
-/* set uid and gid of rdtgroup dirs and files to that of the creator */
-static int rdtgroup_kn_set_ugid(struct kernfs_node *kn)
-{
- struct iattr iattr = { .ia_valid = ATTR_UID | ATTR_GID,
- .ia_uid = current_fsuid(),
- .ia_gid = current_fsgid(), };
-
- if (uid_eq(iattr.ia_uid, GLOBAL_ROOT_UID) &&
- gid_eq(iattr.ia_gid, GLOBAL_ROOT_GID))
- return 0;
-
- return kernfs_setattr(kn, &iattr);
-}
-
-static int rdtgroup_add_file(struct kernfs_node *parent_kn, struct rftype *rft)
-{
- struct kernfs_node *kn;
- int ret;
-
- kn = __kernfs_create_file(parent_kn, rft->name, rft->mode,
- GLOBAL_ROOT_UID, GLOBAL_ROOT_GID,
- 0, rft->kf_ops, rft, NULL, NULL);
- if (IS_ERR(kn))
- return PTR_ERR(kn);
-
- ret = rdtgroup_kn_set_ugid(kn);
- if (ret) {
- kernfs_remove(kn);
- return ret;
- }
-
- return 0;
-}
-
-static int rdtgroup_seqfile_show(struct seq_file *m, void *arg)
-{
- struct kernfs_open_file *of = m->private;
- struct rftype *rft = of->kn->priv;
-
- if (rft->seq_show)
- return rft->seq_show(of, m, arg);
- return 0;
-}
-
-static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
- size_t nbytes, loff_t off)
-{
- struct rftype *rft = of->kn->priv;
-
- if (rft->write)
- return rft->write(of, buf, nbytes, off);
-
- return -EINVAL;
-}
-
-static const struct kernfs_ops rdtgroup_kf_single_ops = {
- .atomic_write_len = PAGE_SIZE,
- .write = rdtgroup_file_write,
- .seq_show = rdtgroup_seqfile_show,
-};
-
-static const struct kernfs_ops kf_mondata_ops = {
- .atomic_write_len = PAGE_SIZE,
- .seq_show = rdtgroup_mondata_show,
-};
-
-static bool is_cpu_list(struct kernfs_open_file *of)
-{
- struct rftype *rft = of->kn->priv;
-
- return rft->flags & RFTYPE_FLAGS_CPUS_LIST;
-}
-
-static int rdtgroup_cpus_show(struct kernfs_open_file *of,
- struct seq_file *s, void *v)
-{
- struct rdtgroup *rdtgrp;
- struct cpumask *mask;
- int ret = 0;
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
-
- if (rdtgrp) {
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
- if (!rdtgrp->plr->d) {
- rdt_last_cmd_clear();
- rdt_last_cmd_puts("Cache domain offline\n");
- ret = -ENODEV;
- } else {
- mask = &rdtgrp->plr->d->hdr.cpu_mask;
- seq_printf(s, is_cpu_list(of) ?
- "%*pbl\n" : "%*pb\n",
- cpumask_pr_args(mask));
- }
- } else {
- seq_printf(s, is_cpu_list(of) ? "%*pbl\n" : "%*pb\n",
- cpumask_pr_args(&rdtgrp->cpu_mask));
- }
- } else {
- ret = -ENOENT;
- }
- rdtgroup_kn_unlock(of->kn);
+DEFINE_STATIC_KEY_FALSE(rdt_mon_enable_key);
- return ret;
-}
+DEFINE_STATIC_KEY_FALSE(rdt_alloc_enable_key);
/*
- * This is safe against resctrl_sched_in() called from __switch_to()
+ * This is safe against resctrl_arch_sched_in() called from __switch_to()
* because __switch_to() is executed with interrupts disabled. A local call
* from update_closid_rmid() is protected against __switch_to() because
* preemption is disabled.
@@ -381,1223 +58,7 @@ void resctrl_arch_sync_cpu_closid_rmid(void *info)
* executing task might have its own closid selected. Just reuse
* the context switch code.
*/
- resctrl_sched_in(current);
-}
-
-/*
- * Update the PGR_ASSOC MSR on all cpus in @cpu_mask,
- *
- * Per task closids/rmids must have been set up before calling this function.
- * @r may be NULL.
- */
-static void
-update_closid_rmid(const struct cpumask *cpu_mask, struct rdtgroup *r)
-{
- struct resctrl_cpu_defaults defaults, *p = NULL;
-
- if (r) {
- defaults.closid = r->closid;
- defaults.rmid = r->mon.rmid;
- p = &defaults;
- }
-
- on_each_cpu_mask(cpu_mask, resctrl_arch_sync_cpu_closid_rmid, p, 1);
-}
-
-static int cpus_mon_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
- cpumask_var_t tmpmask)
-{
- struct rdtgroup *prgrp = rdtgrp->mon.parent, *crgrp;
- struct list_head *head;
-
- /* Check whether cpus belong to parent ctrl group */
- cpumask_andnot(tmpmask, newmask, &prgrp->cpu_mask);
- if (!cpumask_empty(tmpmask)) {
- rdt_last_cmd_puts("Can only add CPUs to mongroup that belong to parent\n");
- return -EINVAL;
- }
-
- /* Check whether cpus are dropped from this group */
- cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
- if (!cpumask_empty(tmpmask)) {
- /* Give any dropped cpus to parent rdtgroup */
- cpumask_or(&prgrp->cpu_mask, &prgrp->cpu_mask, tmpmask);
- update_closid_rmid(tmpmask, prgrp);
- }
-
- /*
- * If we added cpus, remove them from previous group that owned them
- * and update per-cpu rmid
- */
- cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
- if (!cpumask_empty(tmpmask)) {
- head = &prgrp->mon.crdtgrp_list;
- list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
- if (crgrp == rdtgrp)
- continue;
- cpumask_andnot(&crgrp->cpu_mask, &crgrp->cpu_mask,
- tmpmask);
- }
- update_closid_rmid(tmpmask, rdtgrp);
- }
-
- /* Done pushing/pulling - update this group with new mask */
- cpumask_copy(&rdtgrp->cpu_mask, newmask);
-
- return 0;
-}
-
-static void cpumask_rdtgrp_clear(struct rdtgroup *r, struct cpumask *m)
-{
- struct rdtgroup *crgrp;
-
- cpumask_andnot(&r->cpu_mask, &r->cpu_mask, m);
- /* update the child mon group masks as well*/
- list_for_each_entry(crgrp, &r->mon.crdtgrp_list, mon.crdtgrp_list)
- cpumask_and(&crgrp->cpu_mask, &r->cpu_mask, &crgrp->cpu_mask);
-}
-
-static int cpus_ctrl_write(struct rdtgroup *rdtgrp, cpumask_var_t newmask,
- cpumask_var_t tmpmask, cpumask_var_t tmpmask1)
-{
- struct rdtgroup *r, *crgrp;
- struct list_head *head;
-
- /* Check whether cpus are dropped from this group */
- cpumask_andnot(tmpmask, &rdtgrp->cpu_mask, newmask);
- if (!cpumask_empty(tmpmask)) {
- /* Can't drop from default group */
- if (rdtgrp == &rdtgroup_default) {
- rdt_last_cmd_puts("Can't drop CPUs from default group\n");
- return -EINVAL;
- }
-
- /* Give any dropped cpus to rdtgroup_default */
- cpumask_or(&rdtgroup_default.cpu_mask,
- &rdtgroup_default.cpu_mask, tmpmask);
- update_closid_rmid(tmpmask, &rdtgroup_default);
- }
-
- /*
- * If we added cpus, remove them from previous group and
- * the prev group's child groups that owned them
- * and update per-cpu closid/rmid.
- */
- cpumask_andnot(tmpmask, newmask, &rdtgrp->cpu_mask);
- if (!cpumask_empty(tmpmask)) {
- list_for_each_entry(r, &rdt_all_groups, rdtgroup_list) {
- if (r == rdtgrp)
- continue;
- cpumask_and(tmpmask1, &r->cpu_mask, tmpmask);
- if (!cpumask_empty(tmpmask1))
- cpumask_rdtgrp_clear(r, tmpmask1);
- }
- update_closid_rmid(tmpmask, rdtgrp);
- }
-
- /* Done pushing/pulling - update this group with new mask */
- cpumask_copy(&rdtgrp->cpu_mask, newmask);
-
- /*
- * Clear child mon group masks since there is a new parent mask
- * now and update the rmid for the cpus the child lost.
- */
- head = &rdtgrp->mon.crdtgrp_list;
- list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
- cpumask_and(tmpmask, &rdtgrp->cpu_mask, &crgrp->cpu_mask);
- update_closid_rmid(tmpmask, rdtgrp);
- cpumask_clear(&crgrp->cpu_mask);
- }
-
- return 0;
-}
-
-static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
-{
- cpumask_var_t tmpmask, newmask, tmpmask1;
- struct rdtgroup *rdtgrp;
- int ret;
-
- if (!buf)
- return -EINVAL;
-
- if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
- return -ENOMEM;
- if (!zalloc_cpumask_var(&newmask, GFP_KERNEL)) {
- free_cpumask_var(tmpmask);
- return -ENOMEM;
- }
- if (!zalloc_cpumask_var(&tmpmask1, GFP_KERNEL)) {
- free_cpumask_var(tmpmask);
- free_cpumask_var(newmask);
- return -ENOMEM;
- }
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (!rdtgrp) {
- ret = -ENOENT;
- goto unlock;
- }
-
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
- rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
- ret = -EINVAL;
- rdt_last_cmd_puts("Pseudo-locking in progress\n");
- goto unlock;
- }
-
- if (is_cpu_list(of))
- ret = cpulist_parse(buf, newmask);
- else
- ret = cpumask_parse(buf, newmask);
-
- if (ret) {
- rdt_last_cmd_puts("Bad CPU list/mask\n");
- goto unlock;
- }
-
- /* check that user didn't specify any offline cpus */
- cpumask_andnot(tmpmask, newmask, cpu_online_mask);
- if (!cpumask_empty(tmpmask)) {
- ret = -EINVAL;
- rdt_last_cmd_puts("Can only assign online CPUs\n");
- goto unlock;
- }
-
- if (rdtgrp->type == RDTCTRL_GROUP)
- ret = cpus_ctrl_write(rdtgrp, newmask, tmpmask, tmpmask1);
- else if (rdtgrp->type == RDTMON_GROUP)
- ret = cpus_mon_write(rdtgrp, newmask, tmpmask);
- else
- ret = -EINVAL;
-
-unlock:
- rdtgroup_kn_unlock(of->kn);
- free_cpumask_var(tmpmask);
- free_cpumask_var(newmask);
- free_cpumask_var(tmpmask1);
-
- return ret ?: nbytes;
-}
-
-/**
- * rdtgroup_remove - the helper to remove resource group safely
- * @rdtgrp: resource group to remove
- *
- * On resource group creation via a mkdir, an extra kernfs_node reference is
- * taken to ensure that the rdtgroup structure remains accessible for the
- * rdtgroup_kn_unlock() calls where it is removed.
- *
- * Drop the extra reference here, then free the rdtgroup structure.
- *
- * Return: void
- */
-static void rdtgroup_remove(struct rdtgroup *rdtgrp)
-{
- kernfs_put(rdtgrp->kn);
- kfree(rdtgrp);
-}
-
-static void _update_task_closid_rmid(void *task)
-{
- /*
- * If the task is still current on this CPU, update PQR_ASSOC MSR.
- * Otherwise, the MSR is updated when the task is scheduled in.
- */
- if (task == current)
- resctrl_sched_in(task);
-}
-
-static void update_task_closid_rmid(struct task_struct *t)
-{
- if (IS_ENABLED(CONFIG_SMP) && task_curr(t))
- smp_call_function_single(task_cpu(t), _update_task_closid_rmid, t, 1);
- else
- _update_task_closid_rmid(t);
-}
-
-static bool task_in_rdtgroup(struct task_struct *tsk, struct rdtgroup *rdtgrp)
-{
- u32 closid, rmid = rdtgrp->mon.rmid;
-
- if (rdtgrp->type == RDTCTRL_GROUP)
- closid = rdtgrp->closid;
- else if (rdtgrp->type == RDTMON_GROUP)
- closid = rdtgrp->mon.parent->closid;
- else
- return false;
-
- return resctrl_arch_match_closid(tsk, closid) &&
- resctrl_arch_match_rmid(tsk, closid, rmid);
-}
-
-static int __rdtgroup_move_task(struct task_struct *tsk,
- struct rdtgroup *rdtgrp)
-{
- /* If the task is already in rdtgrp, no need to move the task. */
- if (task_in_rdtgroup(tsk, rdtgrp))
- return 0;
-
- /*
- * Set the task's closid/rmid before the PQR_ASSOC MSR can be
- * updated by them.
- *
- * For ctrl_mon groups, move both closid and rmid.
- * For monitor groups, can move the tasks only from
- * their parent CTRL group.
- */
- if (rdtgrp->type == RDTMON_GROUP &&
- !resctrl_arch_match_closid(tsk, rdtgrp->mon.parent->closid)) {
- rdt_last_cmd_puts("Can't move task to different control group\n");
- return -EINVAL;
- }
-
- if (rdtgrp->type == RDTMON_GROUP)
- resctrl_arch_set_closid_rmid(tsk, rdtgrp->mon.parent->closid,
- rdtgrp->mon.rmid);
- else
- resctrl_arch_set_closid_rmid(tsk, rdtgrp->closid,
- rdtgrp->mon.rmid);
-
- /*
- * Ensure the task's closid and rmid are written before determining if
- * the task is current that will decide if it will be interrupted.
- * This pairs with the full barrier between the rq->curr update and
- * resctrl_sched_in() during context switch.
- */
- smp_mb();
-
- /*
- * By now, the task's closid and rmid are set. If the task is current
- * on a CPU, the PQR_ASSOC MSR needs to be updated to make the resource
- * group go into effect. If the task is not current, the MSR will be
- * updated when the task is scheduled in.
- */
- update_task_closid_rmid(tsk);
-
- return 0;
-}
-
-static bool is_closid_match(struct task_struct *t, struct rdtgroup *r)
-{
- return (resctrl_arch_alloc_capable() && (r->type == RDTCTRL_GROUP) &&
- resctrl_arch_match_closid(t, r->closid));
-}
-
-static bool is_rmid_match(struct task_struct *t, struct rdtgroup *r)
-{
- return (resctrl_arch_mon_capable() && (r->type == RDTMON_GROUP) &&
- resctrl_arch_match_rmid(t, r->mon.parent->closid,
- r->mon.rmid));
-}
-
-/**
- * rdtgroup_tasks_assigned - Test if tasks have been assigned to resource group
- * @r: Resource group
- *
- * Return: 1 if tasks have been assigned to @r, 0 otherwise
- */
-int rdtgroup_tasks_assigned(struct rdtgroup *r)
-{
- struct task_struct *p, *t;
- int ret = 0;
-
- lockdep_assert_held(&rdtgroup_mutex);
-
- rcu_read_lock();
- for_each_process_thread(p, t) {
- if (is_closid_match(t, r) || is_rmid_match(t, r)) {
- ret = 1;
- break;
- }
- }
- rcu_read_unlock();
-
- return ret;
-}
-
-static int rdtgroup_task_write_permission(struct task_struct *task,
- struct kernfs_open_file *of)
-{
- const struct cred *tcred = get_task_cred(task);
- const struct cred *cred = current_cred();
- int ret = 0;
-
- /*
- * Even if we're attaching all tasks in the thread group, we only
- * need to check permissions on one of them.
- */
- if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) &&
- !uid_eq(cred->euid, tcred->uid) &&
- !uid_eq(cred->euid, tcred->suid)) {
- rdt_last_cmd_printf("No permission to move task %d\n", task->pid);
- ret = -EPERM;
- }
-
- put_cred(tcred);
- return ret;
-}
-
-static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
- struct kernfs_open_file *of)
-{
- struct task_struct *tsk;
- int ret;
-
- rcu_read_lock();
- if (pid) {
- tsk = find_task_by_vpid(pid);
- if (!tsk) {
- rcu_read_unlock();
- rdt_last_cmd_printf("No task %d\n", pid);
- return -ESRCH;
- }
- } else {
- tsk = current;
- }
-
- get_task_struct(tsk);
- rcu_read_unlock();
-
- ret = rdtgroup_task_write_permission(tsk, of);
- if (!ret)
- ret = __rdtgroup_move_task(tsk, rdtgrp);
-
- put_task_struct(tsk);
- return ret;
-}
-
-static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
-{
- struct rdtgroup *rdtgrp;
- char *pid_str;
- int ret = 0;
- pid_t pid;
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (!rdtgrp) {
- rdtgroup_kn_unlock(of->kn);
- return -ENOENT;
- }
- rdt_last_cmd_clear();
-
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED ||
- rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
- ret = -EINVAL;
- rdt_last_cmd_puts("Pseudo-locking in progress\n");
- goto unlock;
- }
-
- while (buf && buf[0] != '\0' && buf[0] != '\n') {
- pid_str = strim(strsep(&buf, ","));
-
- if (kstrtoint(pid_str, 0, &pid)) {
- rdt_last_cmd_printf("Task list parsing error pid %s\n", pid_str);
- ret = -EINVAL;
- break;
- }
-
- if (pid < 0) {
- rdt_last_cmd_printf("Invalid pid %d\n", pid);
- ret = -EINVAL;
- break;
- }
-
- ret = rdtgroup_move_task(pid, rdtgrp, of);
- if (ret) {
- rdt_last_cmd_printf("Error while processing task %d\n", pid);
- break;
- }
- }
-
-unlock:
- rdtgroup_kn_unlock(of->kn);
-
- return ret ?: nbytes;
-}
-
-static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
-{
- struct task_struct *p, *t;
- pid_t pid;
-
- rcu_read_lock();
- for_each_process_thread(p, t) {
- if (is_closid_match(t, r) || is_rmid_match(t, r)) {
- pid = task_pid_vnr(t);
- if (pid)
- seq_printf(s, "%d\n", pid);
- }
- }
- rcu_read_unlock();
-}
-
-static int rdtgroup_tasks_show(struct kernfs_open_file *of,
- struct seq_file *s, void *v)
-{
- struct rdtgroup *rdtgrp;
- int ret = 0;
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (rdtgrp)
- show_rdt_tasks(rdtgrp, s);
- else
- ret = -ENOENT;
- rdtgroup_kn_unlock(of->kn);
-
- return ret;
-}
-
-static int rdtgroup_closid_show(struct kernfs_open_file *of,
- struct seq_file *s, void *v)
-{
- struct rdtgroup *rdtgrp;
- int ret = 0;
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (rdtgrp)
- seq_printf(s, "%u\n", rdtgrp->closid);
- else
- ret = -ENOENT;
- rdtgroup_kn_unlock(of->kn);
-
- return ret;
-}
-
-static int rdtgroup_rmid_show(struct kernfs_open_file *of,
- struct seq_file *s, void *v)
-{
- struct rdtgroup *rdtgrp;
- int ret = 0;
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (rdtgrp)
- seq_printf(s, "%u\n", rdtgrp->mon.rmid);
- else
- ret = -ENOENT;
- rdtgroup_kn_unlock(of->kn);
-
- return ret;
-}
-
-#ifdef CONFIG_PROC_CPU_RESCTRL
-
-/*
- * A task can only be part of one resctrl control group and of one monitor
- * group which is associated to that control group.
- *
- * 1) res:
- * mon:
- *
- * resctrl is not available.
- *
- * 2) res:/
- * mon:
- *
- * Task is part of the root resctrl control group, and it is not associated
- * to any monitor group.
- *
- * 3) res:/
- * mon:mon0
- *
- * Task is part of the root resctrl control group and monitor group mon0.
- *
- * 4) res:group0
- * mon:
- *
- * Task is part of resctrl control group group0, and it is not associated
- * to any monitor group.
- *
- * 5) res:group0
- * mon:mon1
- *
- * Task is part of resctrl control group group0 and monitor group mon1.
- */
-int proc_resctrl_show(struct seq_file *s, struct pid_namespace *ns,
- struct pid *pid, struct task_struct *tsk)
-{
- struct rdtgroup *rdtg;
- int ret = 0;
-
- mutex_lock(&rdtgroup_mutex);
-
- /* Return empty if resctrl has not been mounted. */
- if (!resctrl_mounted) {
- seq_puts(s, "res:\nmon:\n");
- goto unlock;
- }
-
- list_for_each_entry(rdtg, &rdt_all_groups, rdtgroup_list) {
- struct rdtgroup *crg;
-
- /*
- * Task information is only relevant for shareable
- * and exclusive groups.
- */
- if (rdtg->mode != RDT_MODE_SHAREABLE &&
- rdtg->mode != RDT_MODE_EXCLUSIVE)
- continue;
-
- if (!resctrl_arch_match_closid(tsk, rdtg->closid))
- continue;
-
- seq_printf(s, "res:%s%s\n", (rdtg == &rdtgroup_default) ? "/" : "",
- rdt_kn_name(rdtg->kn));
- seq_puts(s, "mon:");
- list_for_each_entry(crg, &rdtg->mon.crdtgrp_list,
- mon.crdtgrp_list) {
- if (!resctrl_arch_match_rmid(tsk, crg->mon.parent->closid,
- crg->mon.rmid))
- continue;
- seq_printf(s, "%s", rdt_kn_name(crg->kn));
- break;
- }
- seq_putc(s, '\n');
- goto unlock;
- }
- /*
- * The above search should succeed. Otherwise return
- * with an error.
- */
- ret = -ENOENT;
-unlock:
- mutex_unlock(&rdtgroup_mutex);
-
- return ret;
-}
-#endif
-
-static int rdt_last_cmd_status_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- int len;
-
- mutex_lock(&rdtgroup_mutex);
- len = seq_buf_used(&last_cmd_status);
- if (len)
- seq_printf(seq, "%.*s", len, last_cmd_status_buf);
- else
- seq_puts(seq, "ok\n");
- mutex_unlock(&rdtgroup_mutex);
- return 0;
-}
-
-static void *rdt_kn_parent_priv(struct kernfs_node *kn)
-{
- /*
- * The parent pointer is only valid within RCU section since it can be
- * replaced.
- */
- guard(rcu)();
- return rcu_dereference(kn->__parent)->priv;
-}
-
-static int rdt_num_closids_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
-
- seq_printf(seq, "%u\n", s->num_closid);
- return 0;
-}
-
-static int rdt_default_ctrl_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
- struct rdt_resource *r = s->res;
-
- seq_printf(seq, "%x\n", resctrl_get_default_ctrl(r));
- return 0;
-}
-
-static int rdt_min_cbm_bits_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
- struct rdt_resource *r = s->res;
-
- seq_printf(seq, "%u\n", r->cache.min_cbm_bits);
- return 0;
-}
-
-static int rdt_shareable_bits_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
- struct rdt_resource *r = s->res;
-
- seq_printf(seq, "%x\n", r->cache.shareable_bits);
- return 0;
-}
-
-/*
- * rdt_bit_usage_show - Display current usage of resources
- *
- * A domain is a shared resource that can now be allocated differently. Here
- * we display the current regions of the domain as an annotated bitmask.
- * For each domain of this resource its allocation bitmask
- * is annotated as below to indicate the current usage of the corresponding bit:
- * 0 - currently unused
- * X - currently available for sharing and used by software and hardware
- * H - currently used by hardware only but available for software use
- * S - currently used and shareable by software only
- * E - currently used exclusively by one resource group
- * P - currently pseudo-locked by one resource group
- */
-static int rdt_bit_usage_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
- /*
- * Use unsigned long even though only 32 bits are used to ensure
- * test_bit() is used safely.
- */
- unsigned long sw_shareable = 0, hw_shareable = 0;
- unsigned long exclusive = 0, pseudo_locked = 0;
- struct rdt_resource *r = s->res;
- struct rdt_ctrl_domain *dom;
- int i, hwb, swb, excl, psl;
- enum rdtgrp_mode mode;
- bool sep = false;
- u32 ctrl_val;
-
- cpus_read_lock();
- mutex_lock(&rdtgroup_mutex);
- hw_shareable = r->cache.shareable_bits;
- list_for_each_entry(dom, &r->ctrl_domains, hdr.list) {
- if (sep)
- seq_putc(seq, ';');
- sw_shareable = 0;
- exclusive = 0;
- seq_printf(seq, "%d=", dom->hdr.id);
- for (i = 0; i < closids_supported(); i++) {
- if (!closid_allocated(i))
- continue;
- ctrl_val = resctrl_arch_get_config(r, dom, i,
- s->conf_type);
- mode = rdtgroup_mode_by_closid(i);
- switch (mode) {
- case RDT_MODE_SHAREABLE:
- sw_shareable |= ctrl_val;
- break;
- case RDT_MODE_EXCLUSIVE:
- exclusive |= ctrl_val;
- break;
- case RDT_MODE_PSEUDO_LOCKSETUP:
- /*
- * RDT_MODE_PSEUDO_LOCKSETUP is possible
- * here but not included since the CBM
- * associated with this CLOSID in this mode
- * is not initialized and no task or cpu can be
- * assigned this CLOSID.
- */
- break;
- case RDT_MODE_PSEUDO_LOCKED:
- case RDT_NUM_MODES:
- WARN(1,
- "invalid mode for closid %d\n", i);
- break;
- }
- }
- for (i = r->cache.cbm_len - 1; i >= 0; i--) {
- pseudo_locked = dom->plr ? dom->plr->cbm : 0;
- hwb = test_bit(i, &hw_shareable);
- swb = test_bit(i, &sw_shareable);
- excl = test_bit(i, &exclusive);
- psl = test_bit(i, &pseudo_locked);
- if (hwb && swb)
- seq_putc(seq, 'X');
- else if (hwb && !swb)
- seq_putc(seq, 'H');
- else if (!hwb && swb)
- seq_putc(seq, 'S');
- else if (excl)
- seq_putc(seq, 'E');
- else if (psl)
- seq_putc(seq, 'P');
- else /* Unused bits remain */
- seq_putc(seq, '0');
- }
- sep = true;
- }
- seq_putc(seq, '\n');
- mutex_unlock(&rdtgroup_mutex);
- cpus_read_unlock();
- return 0;
-}
-
-static int rdt_min_bw_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
- struct rdt_resource *r = s->res;
-
- seq_printf(seq, "%u\n", r->membw.min_bw);
- return 0;
-}
-
-static int rdt_num_rmids_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
-
- seq_printf(seq, "%d\n", r->num_rmid);
-
- return 0;
-}
-
-static int rdt_mon_features_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
- struct mon_evt *mevt;
-
- list_for_each_entry(mevt, &r->evt_list, list) {
- seq_printf(seq, "%s\n", mevt->name);
- if (mevt->configurable)
- seq_printf(seq, "%s_config\n", mevt->name);
- }
-
- return 0;
-}
-
-static int rdt_bw_gran_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
- struct rdt_resource *r = s->res;
-
- seq_printf(seq, "%u\n", r->membw.bw_gran);
- return 0;
-}
-
-static int rdt_delay_linear_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
- struct rdt_resource *r = s->res;
-
- seq_printf(seq, "%u\n", r->membw.delay_linear);
- return 0;
-}
-
-static int max_threshold_occ_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- seq_printf(seq, "%u\n", resctrl_rmid_realloc_threshold);
-
- return 0;
-}
-
-static int rdt_thread_throttle_mode_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
- struct rdt_resource *r = s->res;
-
- switch (r->membw.throttle_mode) {
- case THREAD_THROTTLE_PER_THREAD:
- seq_puts(seq, "per-thread\n");
- return 0;
- case THREAD_THROTTLE_MAX:
- seq_puts(seq, "max\n");
- return 0;
- case THREAD_THROTTLE_UNDEFINED:
- seq_puts(seq, "undefined\n");
- return 0;
- }
-
- WARN_ON_ONCE(1);
-
- return 0;
-}
-
-static ssize_t max_threshold_occ_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
-{
- unsigned int bytes;
- int ret;
-
- ret = kstrtouint(buf, 0, &bytes);
- if (ret)
- return ret;
-
- if (bytes > resctrl_rmid_realloc_limit)
- return -EINVAL;
-
- resctrl_rmid_realloc_threshold = resctrl_arch_round_mon_val(bytes);
-
- return nbytes;
-}
-
-/*
- * rdtgroup_mode_show - Display mode of this resource group
- */
-static int rdtgroup_mode_show(struct kernfs_open_file *of,
- struct seq_file *s, void *v)
-{
- struct rdtgroup *rdtgrp;
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (!rdtgrp) {
- rdtgroup_kn_unlock(of->kn);
- return -ENOENT;
- }
-
- seq_printf(s, "%s\n", rdtgroup_mode_str(rdtgrp->mode));
-
- rdtgroup_kn_unlock(of->kn);
- return 0;
-}
-
-static enum resctrl_conf_type resctrl_peer_type(enum resctrl_conf_type my_type)
-{
- switch (my_type) {
- case CDP_CODE:
- return CDP_DATA;
- case CDP_DATA:
- return CDP_CODE;
- default:
- case CDP_NONE:
- return CDP_NONE;
- }
-}
-
-static int rdt_has_sparse_bitmasks_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct resctrl_schema *s = rdt_kn_parent_priv(of->kn);
- struct rdt_resource *r = s->res;
-
- seq_printf(seq, "%u\n", r->cache.arch_has_sparse_bitmasks);
-
- return 0;
-}
-
-/**
- * __rdtgroup_cbm_overlaps - Does CBM for intended closid overlap with other
- * @r: Resource to which domain instance @d belongs.
- * @d: The domain instance for which @closid is being tested.
- * @cbm: Capacity bitmask being tested.
- * @closid: Intended closid for @cbm.
- * @type: CDP type of @r.
- * @exclusive: Only check if overlaps with exclusive resource groups
- *
- * Checks if provided @cbm intended to be used for @closid on domain
- * @d overlaps with any other closids or other hardware usage associated
- * with this domain. If @exclusive is true then only overlaps with
- * resource groups in exclusive mode will be considered. If @exclusive
- * is false then overlaps with any resource group or hardware entities
- * will be considered.
- *
- * @cbm is unsigned long, even if only 32 bits are used, to make the
- * bitmap functions work correctly.
- *
- * Return: false if CBM does not overlap, true if it does.
- */
-static bool __rdtgroup_cbm_overlaps(struct rdt_resource *r, struct rdt_ctrl_domain *d,
- unsigned long cbm, int closid,
- enum resctrl_conf_type type, bool exclusive)
-{
- enum rdtgrp_mode mode;
- unsigned long ctrl_b;
- int i;
-
- /* Check for any overlap with regions used by hardware directly */
- if (!exclusive) {
- ctrl_b = r->cache.shareable_bits;
- if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len))
- return true;
- }
-
- /* Check for overlap with other resource groups */
- for (i = 0; i < closids_supported(); i++) {
- ctrl_b = resctrl_arch_get_config(r, d, i, type);
- mode = rdtgroup_mode_by_closid(i);
- if (closid_allocated(i) && i != closid &&
- mode != RDT_MODE_PSEUDO_LOCKSETUP) {
- if (bitmap_intersects(&cbm, &ctrl_b, r->cache.cbm_len)) {
- if (exclusive) {
- if (mode == RDT_MODE_EXCLUSIVE)
- return true;
- continue;
- }
- return true;
- }
- }
- }
-
- return false;
-}
-
-/**
- * rdtgroup_cbm_overlaps - Does CBM overlap with other use of hardware
- * @s: Schema for the resource to which domain instance @d belongs.
- * @d: The domain instance for which @closid is being tested.
- * @cbm: Capacity bitmask being tested.
- * @closid: Intended closid for @cbm.
- * @exclusive: Only check if overlaps with exclusive resource groups
- *
- * Resources that can be allocated using a CBM can use the CBM to control
- * the overlap of these allocations. rdtgroup_cmb_overlaps() is the test
- * for overlap. Overlap test is not limited to the specific resource for
- * which the CBM is intended though - when dealing with CDP resources that
- * share the underlying hardware the overlap check should be performed on
- * the CDP resource sharing the hardware also.
- *
- * Refer to description of __rdtgroup_cbm_overlaps() for the details of the
- * overlap test.
- *
- * Return: true if CBM overlap detected, false if there is no overlap
- */
-bool rdtgroup_cbm_overlaps(struct resctrl_schema *s, struct rdt_ctrl_domain *d,
- unsigned long cbm, int closid, bool exclusive)
-{
- enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
- struct rdt_resource *r = s->res;
-
- if (__rdtgroup_cbm_overlaps(r, d, cbm, closid, s->conf_type,
- exclusive))
- return true;
-
- if (!resctrl_arch_get_cdp_enabled(r->rid))
- return false;
- return __rdtgroup_cbm_overlaps(r, d, cbm, closid, peer_type, exclusive);
-}
-
-/**
- * rdtgroup_mode_test_exclusive - Test if this resource group can be exclusive
- * @rdtgrp: Resource group identified through its closid.
- *
- * An exclusive resource group implies that there should be no sharing of
- * its allocated resources. At the time this group is considered to be
- * exclusive this test can determine if its current schemata supports this
- * setting by testing for overlap with all other resource groups.
- *
- * Return: true if resource group can be exclusive, false if there is overlap
- * with allocations of other resource groups and thus this resource group
- * cannot be exclusive.
- */
-static bool rdtgroup_mode_test_exclusive(struct rdtgroup *rdtgrp)
-{
- int closid = rdtgrp->closid;
- struct rdt_ctrl_domain *d;
- struct resctrl_schema *s;
- struct rdt_resource *r;
- bool has_cache = false;
- u32 ctrl;
-
- /* Walking r->domains, ensure it can't race with cpuhp */
- lockdep_assert_cpus_held();
-
- list_for_each_entry(s, &resctrl_schema_all, list) {
- r = s->res;
- if (r->rid == RDT_RESOURCE_MBA || r->rid == RDT_RESOURCE_SMBA)
- continue;
- has_cache = true;
- list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
- ctrl = resctrl_arch_get_config(r, d, closid,
- s->conf_type);
- if (rdtgroup_cbm_overlaps(s, d, ctrl, closid, false)) {
- rdt_last_cmd_puts("Schemata overlaps\n");
- return false;
- }
- }
- }
-
- if (!has_cache) {
- rdt_last_cmd_puts("Cannot be exclusive without CAT/CDP\n");
- return false;
- }
-
- return true;
-}
-
-/*
- * rdtgroup_mode_write - Modify the resource group's mode
- */
-static ssize_t rdtgroup_mode_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes, loff_t off)
-{
- struct rdtgroup *rdtgrp;
- enum rdtgrp_mode mode;
- int ret = 0;
-
- /* Valid input requires a trailing newline */
- if (nbytes == 0 || buf[nbytes - 1] != '\n')
- return -EINVAL;
- buf[nbytes - 1] = '\0';
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (!rdtgrp) {
- rdtgroup_kn_unlock(of->kn);
- return -ENOENT;
- }
-
- rdt_last_cmd_clear();
-
- mode = rdtgrp->mode;
-
- if ((!strcmp(buf, "shareable") && mode == RDT_MODE_SHAREABLE) ||
- (!strcmp(buf, "exclusive") && mode == RDT_MODE_EXCLUSIVE) ||
- (!strcmp(buf, "pseudo-locksetup") &&
- mode == RDT_MODE_PSEUDO_LOCKSETUP) ||
- (!strcmp(buf, "pseudo-locked") && mode == RDT_MODE_PSEUDO_LOCKED))
- goto out;
-
- if (mode == RDT_MODE_PSEUDO_LOCKED) {
- rdt_last_cmd_puts("Cannot change pseudo-locked group\n");
- ret = -EINVAL;
- goto out;
- }
-
- if (!strcmp(buf, "shareable")) {
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
- ret = rdtgroup_locksetup_exit(rdtgrp);
- if (ret)
- goto out;
- }
- rdtgrp->mode = RDT_MODE_SHAREABLE;
- } else if (!strcmp(buf, "exclusive")) {
- if (!rdtgroup_mode_test_exclusive(rdtgrp)) {
- ret = -EINVAL;
- goto out;
- }
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
- ret = rdtgroup_locksetup_exit(rdtgrp);
- if (ret)
- goto out;
- }
- rdtgrp->mode = RDT_MODE_EXCLUSIVE;
- } else if (IS_ENABLED(CONFIG_RESCTRL_FS_PSEUDO_LOCK) &&
- !strcmp(buf, "pseudo-locksetup")) {
- ret = rdtgroup_locksetup_enter(rdtgrp);
- if (ret)
- goto out;
- rdtgrp->mode = RDT_MODE_PSEUDO_LOCKSETUP;
- } else {
- rdt_last_cmd_puts("Unknown or unsupported mode\n");
- ret = -EINVAL;
- }
-
-out:
- rdtgroup_kn_unlock(of->kn);
- return ret ?: nbytes;
-}
-
-/**
- * rdtgroup_cbm_to_size - Translate CBM to size in bytes
- * @r: RDT resource to which @d belongs.
- * @d: RDT domain instance.
- * @cbm: bitmask for which the size should be computed.
- *
- * The bitmask provided associated with the RDT domain instance @d will be
- * translated into how many bytes it represents. The size in bytes is
- * computed by first dividing the total cache size by the CBM length to
- * determine how many bytes each bit in the bitmask represents. The result
- * is multiplied with the number of bits set in the bitmask.
- *
- * @cbm is unsigned long, even if only 32 bits are used to make the
- * bitmap functions work correctly.
- */
-unsigned int rdtgroup_cbm_to_size(struct rdt_resource *r,
- struct rdt_ctrl_domain *d, unsigned long cbm)
-{
- unsigned int size = 0;
- struct cacheinfo *ci;
- int num_b;
-
- if (WARN_ON_ONCE(r->ctrl_scope != RESCTRL_L2_CACHE && r->ctrl_scope != RESCTRL_L3_CACHE))
- return size;
-
- num_b = bitmap_weight(&cbm, r->cache.cbm_len);
- ci = get_cpu_cacheinfo_level(cpumask_any(&d->hdr.cpu_mask), r->ctrl_scope);
- if (ci)
- size = ci->size / r->cache.cbm_len * num_b;
-
- return size;
-}
-
-/*
- * rdtgroup_size_show - Display size in bytes of allocated regions
- *
- * The "size" file mirrors the layout of the "schemata" file, printing the
- * size in bytes of each region instead of the capacity bitmask.
- */
-static int rdtgroup_size_show(struct kernfs_open_file *of,
- struct seq_file *s, void *v)
-{
- struct resctrl_schema *schema;
- enum resctrl_conf_type type;
- struct rdt_ctrl_domain *d;
- struct rdtgroup *rdtgrp;
- struct rdt_resource *r;
- unsigned int size;
- int ret = 0;
- u32 closid;
- bool sep;
- u32 ctrl;
-
- rdtgrp = rdtgroup_kn_lock_live(of->kn);
- if (!rdtgrp) {
- rdtgroup_kn_unlock(of->kn);
- return -ENOENT;
- }
-
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
- if (!rdtgrp->plr->d) {
- rdt_last_cmd_clear();
- rdt_last_cmd_puts("Cache domain offline\n");
- ret = -ENODEV;
- } else {
- seq_printf(s, "%*s:", max_name_width,
- rdtgrp->plr->s->name);
- size = rdtgroup_cbm_to_size(rdtgrp->plr->s->res,
- rdtgrp->plr->d,
- rdtgrp->plr->cbm);
- seq_printf(s, "%d=%u\n", rdtgrp->plr->d->hdr.id, size);
- }
- goto out;
- }
-
- closid = rdtgrp->closid;
-
- list_for_each_entry(schema, &resctrl_schema_all, list) {
- r = schema->res;
- type = schema->conf_type;
- sep = false;
- seq_printf(s, "%*s:", max_name_width, schema->name);
- list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
- if (sep)
- seq_putc(s, ';');
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP) {
- size = 0;
- } else {
- if (is_mba_sc(r))
- ctrl = d->mbps_val[closid];
- else
- ctrl = resctrl_arch_get_config(r, d,
- closid,
- type);
- if (r->rid == RDT_RESOURCE_MBA ||
- r->rid == RDT_RESOURCE_SMBA)
- size = ctrl;
- else
- size = rdtgroup_cbm_to_size(r, d, ctrl);
- }
- seq_printf(s, "%d=%u", d->hdr.id, size);
- sep = true;
- }
- seq_putc(s, '\n');
- }
-
-out:
- rdtgroup_kn_unlock(of->kn);
-
- return ret;
+ resctrl_arch_sched_in(current);
}
#define INVALID_CONFIG_INDEX UINT_MAX
@@ -1635,68 +96,12 @@ void resctrl_arch_mon_event_config_read(void *_config_info)
pr_warn_once("Invalid event id %d\n", config_info->evtid);
return;
}
- rdmsrl(MSR_IA32_EVT_CFG_BASE + index, msrval);
+ rdmsrq(MSR_IA32_EVT_CFG_BASE + index, msrval);
/* Report only the valid event configuration bits */
config_info->mon_config = msrval & MAX_EVT_CONFIG_BITS;
}
-static void mondata_config_read(struct resctrl_mon_config_info *mon_info)
-{
- smp_call_function_any(&mon_info->d->hdr.cpu_mask,
- resctrl_arch_mon_event_config_read, mon_info, 1);
-}
-
-static int mbm_config_show(struct seq_file *s, struct rdt_resource *r, u32 evtid)
-{
- struct resctrl_mon_config_info mon_info;
- struct rdt_mon_domain *dom;
- bool sep = false;
-
- cpus_read_lock();
- mutex_lock(&rdtgroup_mutex);
-
- list_for_each_entry(dom, &r->mon_domains, hdr.list) {
- if (sep)
- seq_puts(s, ";");
-
- memset(&mon_info, 0, sizeof(struct resctrl_mon_config_info));
- mon_info.r = r;
- mon_info.d = dom;
- mon_info.evtid = evtid;
- mondata_config_read(&mon_info);
-
- seq_printf(s, "%d=0x%02x", dom->hdr.id, mon_info.mon_config);
- sep = true;
- }
- seq_puts(s, "\n");
-
- mutex_unlock(&rdtgroup_mutex);
- cpus_read_unlock();
-
- return 0;
-}
-
-static int mbm_total_bytes_config_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
-
- mbm_config_show(seq, r, QOS_L3_MBM_TOTAL_EVENT_ID);
-
- return 0;
-}
-
-static int mbm_local_bytes_config_show(struct kernfs_open_file *of,
- struct seq_file *seq, void *v)
-{
- struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
-
- mbm_config_show(seq, r, QOS_L3_MBM_LOCAL_EVENT_ID);
-
- return 0;
-}
-
void resctrl_arch_mon_event_config_write(void *_config_info)
{
struct resctrl_mon_config_info *config_info = _config_info;
@@ -1707,638 +112,21 @@ void resctrl_arch_mon_event_config_write(void *_config_info)
pr_warn_once("Invalid event id %d\n", config_info->evtid);
return;
}
- wrmsr(MSR_IA32_EVT_CFG_BASE + index, config_info->mon_config, 0);
-}
-
-static void mbm_config_write_domain(struct rdt_resource *r,
- struct rdt_mon_domain *d, u32 evtid, u32 val)
-{
- struct resctrl_mon_config_info mon_info = {0};
-
- /*
- * Read the current config value first. If both are the same then
- * no need to write it again.
- */
- mon_info.r = r;
- mon_info.d = d;
- mon_info.evtid = evtid;
- mondata_config_read(&mon_info);
- if (mon_info.mon_config == val)
- return;
-
- mon_info.mon_config = val;
-
- /*
- * Update MSR_IA32_EVT_CFG_BASE MSR on one of the CPUs in the
- * domain. The MSRs offset from MSR MSR_IA32_EVT_CFG_BASE
- * are scoped at the domain level. Writing any of these MSRs
- * on one CPU is observed by all the CPUs in the domain.
- */
- smp_call_function_any(&d->hdr.cpu_mask, resctrl_arch_mon_event_config_write,
- &mon_info, 1);
-
- /*
- * When an Event Configuration is changed, the bandwidth counters
- * for all RMIDs and Events will be cleared by the hardware. The
- * hardware also sets MSR_IA32_QM_CTR.Unavailable (bit 62) for
- * every RMID on the next read to any event for every RMID.
- * Subsequent reads will have MSR_IA32_QM_CTR.Unavailable (bit 62)
- * cleared while it is tracked by the hardware. Clear the
- * mbm_local and mbm_total counts for all the RMIDs.
- */
- resctrl_arch_reset_rmid_all(r, d);
-}
-
-static int mon_config_write(struct rdt_resource *r, char *tok, u32 evtid)
-{
- char *dom_str = NULL, *id_str;
- unsigned long dom_id, val;
- struct rdt_mon_domain *d;
-
- /* Walking r->domains, ensure it can't race with cpuhp */
- lockdep_assert_cpus_held();
-
-next:
- if (!tok || tok[0] == '\0')
- return 0;
-
- /* Start processing the strings for each domain */
- dom_str = strim(strsep(&tok, ";"));
- id_str = strsep(&dom_str, "=");
-
- if (!id_str || kstrtoul(id_str, 10, &dom_id)) {
- rdt_last_cmd_puts("Missing '=' or non-numeric domain id\n");
- return -EINVAL;
- }
-
- if (!dom_str || kstrtoul(dom_str, 16, &val)) {
- rdt_last_cmd_puts("Non-numeric event configuration value\n");
- return -EINVAL;
- }
-
- /* Value from user cannot be more than the supported set of events */
- if ((val & r->mbm_cfg_mask) != val) {
- rdt_last_cmd_printf("Invalid event configuration: max valid mask is 0x%02x\n",
- r->mbm_cfg_mask);
- return -EINVAL;
- }
-
- list_for_each_entry(d, &r->mon_domains, hdr.list) {
- if (d->hdr.id == dom_id) {
- mbm_config_write_domain(r, d, evtid, val);
- goto next;
- }
- }
-
- return -EINVAL;
-}
-
-static ssize_t mbm_total_bytes_config_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes,
- loff_t off)
-{
- struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
- int ret;
-
- /* Valid input requires a trailing newline */
- if (nbytes == 0 || buf[nbytes - 1] != '\n')
- return -EINVAL;
-
- cpus_read_lock();
- mutex_lock(&rdtgroup_mutex);
-
- rdt_last_cmd_clear();
-
- buf[nbytes - 1] = '\0';
-
- ret = mon_config_write(r, buf, QOS_L3_MBM_TOTAL_EVENT_ID);
-
- mutex_unlock(&rdtgroup_mutex);
- cpus_read_unlock();
-
- return ret ?: nbytes;
-}
-
-static ssize_t mbm_local_bytes_config_write(struct kernfs_open_file *of,
- char *buf, size_t nbytes,
- loff_t off)
-{
- struct rdt_resource *r = rdt_kn_parent_priv(of->kn);
- int ret;
-
- /* Valid input requires a trailing newline */
- if (nbytes == 0 || buf[nbytes - 1] != '\n')
- return -EINVAL;
-
- cpus_read_lock();
- mutex_lock(&rdtgroup_mutex);
-
- rdt_last_cmd_clear();
-
- buf[nbytes - 1] = '\0';
-
- ret = mon_config_write(r, buf, QOS_L3_MBM_LOCAL_EVENT_ID);
-
- mutex_unlock(&rdtgroup_mutex);
- cpus_read_unlock();
-
- return ret ?: nbytes;
-}
-
-/* rdtgroup information files for one cache resource. */
-static struct rftype res_common_files[] = {
- {
- .name = "last_cmd_status",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_last_cmd_status_show,
- .fflags = RFTYPE_TOP_INFO,
- },
- {
- .name = "num_closids",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_num_closids_show,
- .fflags = RFTYPE_CTRL_INFO,
- },
- {
- .name = "mon_features",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_mon_features_show,
- .fflags = RFTYPE_MON_INFO,
- },
- {
- .name = "num_rmids",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_num_rmids_show,
- .fflags = RFTYPE_MON_INFO,
- },
- {
- .name = "cbm_mask",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_default_ctrl_show,
- .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
- },
- {
- .name = "min_cbm_bits",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_min_cbm_bits_show,
- .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
- },
- {
- .name = "shareable_bits",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_shareable_bits_show,
- .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
- },
- {
- .name = "bit_usage",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_bit_usage_show,
- .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
- },
- {
- .name = "min_bandwidth",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_min_bw_show,
- .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
- },
- {
- .name = "bandwidth_gran",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_bw_gran_show,
- .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
- },
- {
- .name = "delay_linear",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_delay_linear_show,
- .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_MB,
- },
- /*
- * Platform specific which (if any) capabilities are provided by
- * thread_throttle_mode. Defer "fflags" initialization to platform
- * discovery.
- */
- {
- .name = "thread_throttle_mode",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_thread_throttle_mode_show,
- },
- {
- .name = "max_threshold_occupancy",
- .mode = 0644,
- .kf_ops = &rdtgroup_kf_single_ops,
- .write = max_threshold_occ_write,
- .seq_show = max_threshold_occ_show,
- .fflags = RFTYPE_MON_INFO | RFTYPE_RES_CACHE,
- },
- {
- .name = "mbm_total_bytes_config",
- .mode = 0644,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = mbm_total_bytes_config_show,
- .write = mbm_total_bytes_config_write,
- },
- {
- .name = "mbm_local_bytes_config",
- .mode = 0644,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = mbm_local_bytes_config_show,
- .write = mbm_local_bytes_config_write,
- },
- {
- .name = "cpus",
- .mode = 0644,
- .kf_ops = &rdtgroup_kf_single_ops,
- .write = rdtgroup_cpus_write,
- .seq_show = rdtgroup_cpus_show,
- .fflags = RFTYPE_BASE,
- },
- {
- .name = "cpus_list",
- .mode = 0644,
- .kf_ops = &rdtgroup_kf_single_ops,
- .write = rdtgroup_cpus_write,
- .seq_show = rdtgroup_cpus_show,
- .flags = RFTYPE_FLAGS_CPUS_LIST,
- .fflags = RFTYPE_BASE,
- },
- {
- .name = "tasks",
- .mode = 0644,
- .kf_ops = &rdtgroup_kf_single_ops,
- .write = rdtgroup_tasks_write,
- .seq_show = rdtgroup_tasks_show,
- .fflags = RFTYPE_BASE,
- },
- {
- .name = "mon_hw_id",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdtgroup_rmid_show,
- .fflags = RFTYPE_MON_BASE | RFTYPE_DEBUG,
- },
- {
- .name = "schemata",
- .mode = 0644,
- .kf_ops = &rdtgroup_kf_single_ops,
- .write = rdtgroup_schemata_write,
- .seq_show = rdtgroup_schemata_show,
- .fflags = RFTYPE_CTRL_BASE,
- },
- {
- .name = "mba_MBps_event",
- .mode = 0644,
- .kf_ops = &rdtgroup_kf_single_ops,
- .write = rdtgroup_mba_mbps_event_write,
- .seq_show = rdtgroup_mba_mbps_event_show,
- },
- {
- .name = "mode",
- .mode = 0644,
- .kf_ops = &rdtgroup_kf_single_ops,
- .write = rdtgroup_mode_write,
- .seq_show = rdtgroup_mode_show,
- .fflags = RFTYPE_CTRL_BASE,
- },
- {
- .name = "size",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdtgroup_size_show,
- .fflags = RFTYPE_CTRL_BASE,
- },
- {
- .name = "sparse_masks",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdt_has_sparse_bitmasks_show,
- .fflags = RFTYPE_CTRL_INFO | RFTYPE_RES_CACHE,
- },
- {
- .name = "ctrl_hw_id",
- .mode = 0444,
- .kf_ops = &rdtgroup_kf_single_ops,
- .seq_show = rdtgroup_closid_show,
- .fflags = RFTYPE_CTRL_BASE | RFTYPE_DEBUG,
- },
-
-};
-
-static int rdtgroup_add_files(struct kernfs_node *kn, unsigned long fflags)
-{
- struct rftype *rfts, *rft;
- int ret, len;
-
- rfts = res_common_files;
- len = ARRAY_SIZE(res_common_files);
-
- lockdep_assert_held(&rdtgroup_mutex);
-
- if (resctrl_debug)
- fflags |= RFTYPE_DEBUG;
-
- for (rft = rfts; rft < rfts + len; rft++) {
- if (rft->fflags && ((fflags & rft->fflags) == rft->fflags)) {
- ret = rdtgroup_add_file(kn, rft);
- if (ret)
- goto error;
- }
- }
-
- return 0;
-error:
- pr_warn("Failed to add %s, err=%d\n", rft->name, ret);
- while (--rft >= rfts) {
- if ((fflags & rft->fflags) == rft->fflags)
- kernfs_remove_by_name(kn, rft->name);
- }
- return ret;
-}
-
-static struct rftype *rdtgroup_get_rftype_by_name(const char *name)
-{
- struct rftype *rfts, *rft;
- int len;
-
- rfts = res_common_files;
- len = ARRAY_SIZE(res_common_files);
-
- for (rft = rfts; rft < rfts + len; rft++) {
- if (!strcmp(rft->name, name))
- return rft;
- }
-
- return NULL;
-}
-
-static void thread_throttle_mode_init(void)
-{
- enum membw_throttle_mode throttle_mode = THREAD_THROTTLE_UNDEFINED;
- struct rdt_resource *r_mba, *r_smba;
-
- r_mba = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
- if (r_mba->alloc_capable &&
- r_mba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED)
- throttle_mode = r_mba->membw.throttle_mode;
-
- r_smba = resctrl_arch_get_resource(RDT_RESOURCE_SMBA);
- if (r_smba->alloc_capable &&
- r_smba->membw.throttle_mode != THREAD_THROTTLE_UNDEFINED)
- throttle_mode = r_smba->membw.throttle_mode;
-
- if (throttle_mode == THREAD_THROTTLE_UNDEFINED)
- return;
-
- resctrl_file_fflags_init("thread_throttle_mode",
- RFTYPE_CTRL_INFO | RFTYPE_RES_MB);
-}
-
-void resctrl_file_fflags_init(const char *config, unsigned long fflags)
-{
- struct rftype *rft;
-
- rft = rdtgroup_get_rftype_by_name(config);
- if (rft)
- rft->fflags = fflags;
-}
-
-/**
- * rdtgroup_kn_mode_restrict - Restrict user access to named resctrl file
- * @r: The resource group with which the file is associated.
- * @name: Name of the file
- *
- * The permissions of named resctrl file, directory, or link are modified
- * to not allow read, write, or execute by any user.
- *
- * WARNING: This function is intended to communicate to the user that the
- * resctrl file has been locked down - that it is not relevant to the
- * particular state the system finds itself in. It should not be relied
- * on to protect from user access because after the file's permissions
- * are restricted the user can still change the permissions using chmod
- * from the command line.
- *
- * Return: 0 on success, <0 on failure.
- */
-int rdtgroup_kn_mode_restrict(struct rdtgroup *r, const char *name)
-{
- struct iattr iattr = {.ia_valid = ATTR_MODE,};
- struct kernfs_node *kn;
- int ret = 0;
-
- kn = kernfs_find_and_get_ns(r->kn, name, NULL);
- if (!kn)
- return -ENOENT;
-
- switch (kernfs_type(kn)) {
- case KERNFS_DIR:
- iattr.ia_mode = S_IFDIR;
- break;
- case KERNFS_FILE:
- iattr.ia_mode = S_IFREG;
- break;
- case KERNFS_LINK:
- iattr.ia_mode = S_IFLNK;
- break;
- }
-
- ret = kernfs_setattr(kn, &iattr);
- kernfs_put(kn);
- return ret;
-}
-
-/**
- * rdtgroup_kn_mode_restore - Restore user access to named resctrl file
- * @r: The resource group with which the file is associated.
- * @name: Name of the file
- * @mask: Mask of permissions that should be restored
- *
- * Restore the permissions of the named file. If @name is a directory the
- * permissions of its parent will be used.
- *
- * Return: 0 on success, <0 on failure.
- */
-int rdtgroup_kn_mode_restore(struct rdtgroup *r, const char *name,
- umode_t mask)
-{
- struct iattr iattr = {.ia_valid = ATTR_MODE,};
- struct kernfs_node *kn, *parent;
- struct rftype *rfts, *rft;
- int ret, len;
-
- rfts = res_common_files;
- len = ARRAY_SIZE(res_common_files);
-
- for (rft = rfts; rft < rfts + len; rft++) {
- if (!strcmp(rft->name, name))
- iattr.ia_mode = rft->mode & mask;
- }
-
- kn = kernfs_find_and_get_ns(r->kn, name, NULL);
- if (!kn)
- return -ENOENT;
-
- switch (kernfs_type(kn)) {
- case KERNFS_DIR:
- parent = kernfs_get_parent(kn);
- if (parent) {
- iattr.ia_mode |= parent->mode;
- kernfs_put(parent);
- }
- iattr.ia_mode |= S_IFDIR;
- break;
- case KERNFS_FILE:
- iattr.ia_mode |= S_IFREG;
- break;
- case KERNFS_LINK:
- iattr.ia_mode |= S_IFLNK;
- break;
- }
-
- ret = kernfs_setattr(kn, &iattr);
- kernfs_put(kn);
- return ret;
-}
-
-static int rdtgroup_mkdir_info_resdir(void *priv, char *name,
- unsigned long fflags)
-{
- struct kernfs_node *kn_subdir;
- int ret;
-
- kn_subdir = kernfs_create_dir(kn_info, name,
- kn_info->mode, priv);
- if (IS_ERR(kn_subdir))
- return PTR_ERR(kn_subdir);
-
- ret = rdtgroup_kn_set_ugid(kn_subdir);
- if (ret)
- return ret;
-
- ret = rdtgroup_add_files(kn_subdir, fflags);
- if (!ret)
- kernfs_activate(kn_subdir);
-
- return ret;
-}
-
-static unsigned long fflags_from_resource(struct rdt_resource *r)
-{
- switch (r->rid) {
- case RDT_RESOURCE_L3:
- case RDT_RESOURCE_L2:
- return RFTYPE_RES_CACHE;
- case RDT_RESOURCE_MBA:
- case RDT_RESOURCE_SMBA:
- return RFTYPE_RES_MB;
- }
-
- return WARN_ON_ONCE(1);
-}
-
-static int rdtgroup_create_info_dir(struct kernfs_node *parent_kn)
-{
- struct resctrl_schema *s;
- struct rdt_resource *r;
- unsigned long fflags;
- char name[32];
- int ret;
-
- /* create the directory */
- kn_info = kernfs_create_dir(parent_kn, "info", parent_kn->mode, NULL);
- if (IS_ERR(kn_info))
- return PTR_ERR(kn_info);
-
- ret = rdtgroup_add_files(kn_info, RFTYPE_TOP_INFO);
- if (ret)
- goto out_destroy;
-
- /* loop over enabled controls, these are all alloc_capable */
- list_for_each_entry(s, &resctrl_schema_all, list) {
- r = s->res;
- fflags = fflags_from_resource(r) | RFTYPE_CTRL_INFO;
- ret = rdtgroup_mkdir_info_resdir(s, s->name, fflags);
- if (ret)
- goto out_destroy;
- }
-
- for_each_mon_capable_rdt_resource(r) {
- fflags = fflags_from_resource(r) | RFTYPE_MON_INFO;
- sprintf(name, "%s_MON", r->name);
- ret = rdtgroup_mkdir_info_resdir(r, name, fflags);
- if (ret)
- goto out_destroy;
- }
-
- ret = rdtgroup_kn_set_ugid(kn_info);
- if (ret)
- goto out_destroy;
-
- kernfs_activate(kn_info);
-
- return 0;
-
-out_destroy:
- kernfs_remove(kn_info);
- return ret;
-}
-
-static int
-mongroup_create_dir(struct kernfs_node *parent_kn, struct rdtgroup *prgrp,
- char *name, struct kernfs_node **dest_kn)
-{
- struct kernfs_node *kn;
- int ret;
-
- /* create the directory */
- kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
- if (IS_ERR(kn))
- return PTR_ERR(kn);
-
- if (dest_kn)
- *dest_kn = kn;
-
- ret = rdtgroup_kn_set_ugid(kn);
- if (ret)
- goto out_destroy;
-
- kernfs_activate(kn);
-
- return 0;
-
-out_destroy:
- kernfs_remove(kn);
- return ret;
+ wrmsrq(MSR_IA32_EVT_CFG_BASE + index, config_info->mon_config);
}
static void l3_qos_cfg_update(void *arg)
{
bool *enable = arg;
- wrmsrl(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
+ wrmsrq(MSR_IA32_L3_QOS_CFG, *enable ? L3_QOS_CDP_ENABLE : 0ULL);
}
static void l2_qos_cfg_update(void *arg)
{
bool *enable = arg;
- wrmsrl(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
-}
-
-static inline bool is_mba_linear(void)
-{
- return resctrl_arch_get_resource(RDT_RESOURCE_MBA)->membw.delay_linear;
+ wrmsrq(MSR_IA32_L2_QOS_CFG, *enable ? L2_QOS_CDP_ENABLE : 0ULL);
}
static int set_cache_qos_cfg(int level, bool enable)
@@ -2396,76 +184,6 @@ void rdt_domain_reconfigure_cdp(struct rdt_resource *r)
l3_qos_cfg_update(&hw_res->cdp_enabled);
}
-static int mba_sc_domain_allocate(struct rdt_resource *r, struct rdt_ctrl_domain *d)
-{
- u32 num_closid = resctrl_arch_get_num_closid(r);
- int cpu = cpumask_any(&d->hdr.cpu_mask);
- int i;
-
- d->mbps_val = kcalloc_node(num_closid, sizeof(*d->mbps_val),
- GFP_KERNEL, cpu_to_node(cpu));
- if (!d->mbps_val)
- return -ENOMEM;
-
- for (i = 0; i < num_closid; i++)
- d->mbps_val[i] = MBA_MAX_MBPS;
-
- return 0;
-}
-
-static void mba_sc_domain_destroy(struct rdt_resource *r,
- struct rdt_ctrl_domain *d)
-{
- kfree(d->mbps_val);
- d->mbps_val = NULL;
-}
-
-/*
- * MBA software controller is supported only if
- * MBM is supported and MBA is in linear scale,
- * and the MBM monitor scope is the same as MBA
- * control scope.
- */
-static bool supports_mba_mbps(void)
-{
- struct rdt_resource *rmbm = resctrl_arch_get_resource(RDT_RESOURCE_L3);
- struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
-
- return (resctrl_is_mbm_enabled() &&
- r->alloc_capable && is_mba_linear() &&
- r->ctrl_scope == rmbm->mon_scope);
-}
-
-/*
- * Enable or disable the MBA software controller
- * which helps user specify bandwidth in MBps.
- */
-static int set_mba_sc(bool mba_sc)
-{
- struct rdt_resource *r = resctrl_arch_get_resource(RDT_RESOURCE_MBA);
- u32 num_closid = resctrl_arch_get_num_closid(r);
- struct rdt_ctrl_domain *d;
- unsigned long fflags;
- int i;
-
- if (!supports_mba_mbps() || mba_sc == is_mba_sc(r))
- return -EINVAL;
-
- r->membw.mba_sc = mba_sc;
-
- rdtgroup_default.mba_mbps_event = mba_mbps_default_event;
-
- list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
- for (i = 0; i < num_closid; i++)
- d->mbps_val[i] = MBA_MAX_MBPS;
- }
-
- fflags = mba_sc ? RFTYPE_CTRL_BASE | RFTYPE_MON_BASE : 0;
- resctrl_file_fflags_init("mba_MBps_event", fflags);
-
- return 0;
-}
-
static int cdp_enable(int level)
{
struct rdt_resource *r_l = &rdt_resources_all[level].r_resctrl;
@@ -2506,419 +224,9 @@ int resctrl_arch_set_cdp_enabled(enum resctrl_res_level l, bool enable)
return 0;
}
-/*
- * We don't allow rdtgroup directories to be created anywhere
- * except the root directory. Thus when looking for the rdtgroup
- * structure for a kernfs node we are either looking at a directory,
- * in which case the rdtgroup structure is pointed at by the "priv"
- * field, otherwise we have a file, and need only look to the parent
- * to find the rdtgroup.
- */
-static struct rdtgroup *kernfs_to_rdtgroup(struct kernfs_node *kn)
-{
- if (kernfs_type(kn) == KERNFS_DIR) {
- /*
- * All the resource directories use "kn->priv"
- * to point to the "struct rdtgroup" for the
- * resource. "info" and its subdirectories don't
- * have rdtgroup structures, so return NULL here.
- */
- if (kn == kn_info ||
- rcu_access_pointer(kn->__parent) == kn_info)
- return NULL;
- else
- return kn->priv;
- } else {
- return rdt_kn_parent_priv(kn);
- }
-}
-
-static void rdtgroup_kn_get(struct rdtgroup *rdtgrp, struct kernfs_node *kn)
-{
- atomic_inc(&rdtgrp->waitcount);
- kernfs_break_active_protection(kn);
-}
-
-static void rdtgroup_kn_put(struct rdtgroup *rdtgrp, struct kernfs_node *kn)
-{
- if (atomic_dec_and_test(&rdtgrp->waitcount) &&
- (rdtgrp->flags & RDT_DELETED)) {
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
- rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
- rdtgroup_pseudo_lock_remove(rdtgrp);
- kernfs_unbreak_active_protection(kn);
- rdtgroup_remove(rdtgrp);
- } else {
- kernfs_unbreak_active_protection(kn);
- }
-}
-
-struct rdtgroup *rdtgroup_kn_lock_live(struct kernfs_node *kn)
-{
- struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
-
- if (!rdtgrp)
- return NULL;
-
- rdtgroup_kn_get(rdtgrp, kn);
-
- cpus_read_lock();
- mutex_lock(&rdtgroup_mutex);
-
- /* Was this group deleted while we waited? */
- if (rdtgrp->flags & RDT_DELETED)
- return NULL;
-
- return rdtgrp;
-}
-
-void rdtgroup_kn_unlock(struct kernfs_node *kn)
-{
- struct rdtgroup *rdtgrp = kernfs_to_rdtgroup(kn);
-
- if (!rdtgrp)
- return;
-
- mutex_unlock(&rdtgroup_mutex);
- cpus_read_unlock();
-
- rdtgroup_kn_put(rdtgrp, kn);
-}
-
-static int mkdir_mondata_all(struct kernfs_node *parent_kn,
- struct rdtgroup *prgrp,
- struct kernfs_node **mon_data_kn);
-
-static void rdt_disable_ctx(void)
-{
- resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
- resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
- set_mba_sc(false);
-
- resctrl_debug = false;
-}
-
-static int rdt_enable_ctx(struct rdt_fs_context *ctx)
-{
- int ret = 0;
-
- if (ctx->enable_cdpl2) {
- ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, true);
- if (ret)
- goto out_done;
- }
-
- if (ctx->enable_cdpl3) {
- ret = resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, true);
- if (ret)
- goto out_cdpl2;
- }
-
- if (ctx->enable_mba_mbps) {
- ret = set_mba_sc(true);
- if (ret)
- goto out_cdpl3;
- }
-
- if (ctx->enable_debug)
- resctrl_debug = true;
-
- return 0;
-
-out_cdpl3:
- resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L3, false);
-out_cdpl2:
- resctrl_arch_set_cdp_enabled(RDT_RESOURCE_L2, false);
-out_done:
- return ret;
-}
-
-static int schemata_list_add(struct rdt_resource *r, enum resctrl_conf_type type)
-{
- struct resctrl_schema *s;
- const char *suffix = "";
- int ret, cl;
-
- s = kzalloc(sizeof(*s), GFP_KERNEL);
- if (!s)
- return -ENOMEM;
-
- s->res = r;
- s->num_closid = resctrl_arch_get_num_closid(r);
- if (resctrl_arch_get_cdp_enabled(r->rid))
- s->num_closid /= 2;
-
- s->conf_type = type;
- switch (type) {
- case CDP_CODE:
- suffix = "CODE";
- break;
- case CDP_DATA:
- suffix = "DATA";
- break;
- case CDP_NONE:
- suffix = "";
- break;
- }
-
- ret = snprintf(s->name, sizeof(s->name), "%s%s", r->name, suffix);
- if (ret >= sizeof(s->name)) {
- kfree(s);
- return -EINVAL;
- }
-
- cl = strlen(s->name);
-
- /*
- * If CDP is supported by this resource, but not enabled,
- * include the suffix. This ensures the tabular format of the
- * schemata file does not change between mounts of the filesystem.
- */
- if (r->cdp_capable && !resctrl_arch_get_cdp_enabled(r->rid))
- cl += 4;
-
- if (cl > max_name_width)
- max_name_width = cl;
-
- switch (r->schema_fmt) {
- case RESCTRL_SCHEMA_BITMAP:
- s->fmt_str = "%d=%x";
- break;
- case RESCTRL_SCHEMA_RANGE:
- s->fmt_str = "%d=%u";
- break;
- }
-
- if (WARN_ON_ONCE(!s->fmt_str)) {
- kfree(s);
- return -EINVAL;
- }
-
- INIT_LIST_HEAD(&s->list);
- list_add(&s->list, &resctrl_schema_all);
-
- return 0;
-}
-
-static int schemata_list_create(void)
-{
- struct rdt_resource *r;
- int ret = 0;
-
- for_each_alloc_capable_rdt_resource(r) {
- if (resctrl_arch_get_cdp_enabled(r->rid)) {
- ret = schemata_list_add(r, CDP_CODE);
- if (ret)
- break;
-
- ret = schemata_list_add(r, CDP_DATA);
- } else {
- ret = schemata_list_add(r, CDP_NONE);
- }
-
- if (ret)
- break;
- }
-
- return ret;
-}
-
-static void schemata_list_destroy(void)
-{
- struct resctrl_schema *s, *tmp;
-
- list_for_each_entry_safe(s, tmp, &resctrl_schema_all, list) {
- list_del(&s->list);
- kfree(s);
- }
-}
-
-static int rdt_get_tree(struct fs_context *fc)
-{
- struct rdt_fs_context *ctx = rdt_fc2context(fc);
- unsigned long flags = RFTYPE_CTRL_BASE;
- struct rdt_mon_domain *dom;
- struct rdt_resource *r;
- int ret;
-
- cpus_read_lock();
- mutex_lock(&rdtgroup_mutex);
- /*
- * resctrl file system can only be mounted once.
- */
- if (resctrl_mounted) {
- ret = -EBUSY;
- goto out;
- }
-
- ret = rdtgroup_setup_root(ctx);
- if (ret)
- goto out;
-
- ret = rdt_enable_ctx(ctx);
- if (ret)
- goto out_root;
-
- ret = schemata_list_create();
- if (ret) {
- schemata_list_destroy();
- goto out_ctx;
- }
-
- closid_init();
-
- if (resctrl_arch_mon_capable())
- flags |= RFTYPE_MON;
-
- ret = rdtgroup_add_files(rdtgroup_default.kn, flags);
- if (ret)
- goto out_schemata_free;
-
- kernfs_activate(rdtgroup_default.kn);
-
- ret = rdtgroup_create_info_dir(rdtgroup_default.kn);
- if (ret < 0)
- goto out_schemata_free;
-
- if (resctrl_arch_mon_capable()) {
- ret = mongroup_create_dir(rdtgroup_default.kn,
- &rdtgroup_default, "mon_groups",
- &kn_mongrp);
- if (ret < 0)
- goto out_info;
-
- ret = mkdir_mondata_all(rdtgroup_default.kn,
- &rdtgroup_default, &kn_mondata);
- if (ret < 0)
- goto out_mongrp;
- rdtgroup_default.mon.mon_data_kn = kn_mondata;
- }
-
- ret = rdt_pseudo_lock_init();
- if (ret)
- goto out_mondata;
-
- ret = kernfs_get_tree(fc);
- if (ret < 0)
- goto out_psl;
-
- if (resctrl_arch_alloc_capable())
- resctrl_arch_enable_alloc();
- if (resctrl_arch_mon_capable())
- resctrl_arch_enable_mon();
-
- if (resctrl_arch_alloc_capable() || resctrl_arch_mon_capable())
- resctrl_mounted = true;
-
- if (resctrl_is_mbm_enabled()) {
- r = resctrl_arch_get_resource(RDT_RESOURCE_L3);
- list_for_each_entry(dom, &r->mon_domains, hdr.list)
- mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
- RESCTRL_PICK_ANY_CPU);
- }
-
- goto out;
-
-out_psl:
- rdt_pseudo_lock_release();
-out_mondata:
- if (resctrl_arch_mon_capable())
- kernfs_remove(kn_mondata);
-out_mongrp:
- if (resctrl_arch_mon_capable())
- kernfs_remove(kn_mongrp);
-out_info:
- kernfs_remove(kn_info);
-out_schemata_free:
- schemata_list_destroy();
-out_ctx:
- rdt_disable_ctx();
-out_root:
- rdtgroup_destroy_root();
-out:
- rdt_last_cmd_clear();
- mutex_unlock(&rdtgroup_mutex);
- cpus_read_unlock();
- return ret;
-}
-
-enum rdt_param {
- Opt_cdp,
- Opt_cdpl2,
- Opt_mba_mbps,
- Opt_debug,
- nr__rdt_params
-};
-
-static const struct fs_parameter_spec rdt_fs_parameters[] = {
- fsparam_flag("cdp", Opt_cdp),
- fsparam_flag("cdpl2", Opt_cdpl2),
- fsparam_flag("mba_MBps", Opt_mba_mbps),
- fsparam_flag("debug", Opt_debug),
- {}
-};
-
-static int rdt_parse_param(struct fs_context *fc, struct fs_parameter *param)
-{
- struct rdt_fs_context *ctx = rdt_fc2context(fc);
- struct fs_parse_result result;
- const char *msg;
- int opt;
-
- opt = fs_parse(fc, rdt_fs_parameters, param, &result);
- if (opt < 0)
- return opt;
-
- switch (opt) {
- case Opt_cdp:
- ctx->enable_cdpl3 = true;
- return 0;
- case Opt_cdpl2:
- ctx->enable_cdpl2 = true;
- return 0;
- case Opt_mba_mbps:
- msg = "mba_MBps requires MBM and linear scale MBA at L3 scope";
- if (!supports_mba_mbps())
- return invalfc(fc, msg);
- ctx->enable_mba_mbps = true;
- return 0;
- case Opt_debug:
- ctx->enable_debug = true;
- return 0;
- }
-
- return -EINVAL;
-}
-
-static void rdt_fs_context_free(struct fs_context *fc)
+bool resctrl_arch_get_cdp_enabled(enum resctrl_res_level l)
{
- struct rdt_fs_context *ctx = rdt_fc2context(fc);
-
- kernfs_free_fs_context(fc);
- kfree(ctx);
-}
-
-static const struct fs_context_operations rdt_fs_context_ops = {
- .free = rdt_fs_context_free,
- .parse_param = rdt_parse_param,
- .get_tree = rdt_get_tree,
-};
-
-static int rdt_init_fs_context(struct fs_context *fc)
-{
- struct rdt_fs_context *ctx;
-
- ctx = kzalloc(sizeof(struct rdt_fs_context), GFP_KERNEL);
- if (!ctx)
- return -ENOMEM;
-
- ctx->kfc.magic = RDTGROUP_SUPER_MAGIC;
- fc->fs_private = &ctx->kfc;
- fc->ops = &rdt_fs_context_ops;
- put_user_ns(fc->user_ns);
- fc->user_ns = get_user_ns(&init_user_ns);
- fc->global = true;
- return 0;
+ return rdt_resources_all[l].cdp_enabled;
}
void resctrl_arch_reset_all_ctrls(struct rdt_resource *r)
@@ -2952,1460 +260,3 @@ void resctrl_arch_reset_all_ctrls(struct rdt_resource *r)
return;
}
-
-/*
- * Move tasks from one to the other group. If @from is NULL, then all tasks
- * in the systems are moved unconditionally (used for teardown).
- *
- * If @mask is not NULL the cpus on which moved tasks are running are set
- * in that mask so the update smp function call is restricted to affected
- * cpus.
- */
-static void rdt_move_group_tasks(struct rdtgroup *from, struct rdtgroup *to,
- struct cpumask *mask)
-{
- struct task_struct *p, *t;
-
- read_lock(&tasklist_lock);
- for_each_process_thread(p, t) {
- if (!from || is_closid_match(t, from) ||
- is_rmid_match(t, from)) {
- resctrl_arch_set_closid_rmid(t, to->closid,
- to->mon.rmid);
-
- /*
- * Order the closid/rmid stores above before the loads
- * in task_curr(). This pairs with the full barrier
- * between the rq->curr update and resctrl_sched_in()
- * during context switch.
- */
- smp_mb();
-
- /*
- * If the task is on a CPU, set the CPU in the mask.
- * The detection is inaccurate as tasks might move or
- * schedule before the smp function call takes place.
- * In such a case the function call is pointless, but
- * there is no other side effect.
- */
- if (IS_ENABLED(CONFIG_SMP) && mask && task_curr(t))
- cpumask_set_cpu(task_cpu(t), mask);
- }
- }
- read_unlock(&tasklist_lock);
-}
-
-static void free_all_child_rdtgrp(struct rdtgroup *rdtgrp)
-{
- struct rdtgroup *sentry, *stmp;
- struct list_head *head;
-
- head = &rdtgrp->mon.crdtgrp_list;
- list_for_each_entry_safe(sentry, stmp, head, mon.crdtgrp_list) {
- free_rmid(sentry->closid, sentry->mon.rmid);
- list_del(&sentry->mon.crdtgrp_list);
-
- if (atomic_read(&sentry->waitcount) != 0)
- sentry->flags = RDT_DELETED;
- else
- rdtgroup_remove(sentry);
- }
-}
-
-/*
- * Forcibly remove all of subdirectories under root.
- */
-static void rmdir_all_sub(void)
-{
- struct rdtgroup *rdtgrp, *tmp;
-
- /* Move all tasks to the default resource group */
- rdt_move_group_tasks(NULL, &rdtgroup_default, NULL);
-
- list_for_each_entry_safe(rdtgrp, tmp, &rdt_all_groups, rdtgroup_list) {
- /* Free any child rmids */
- free_all_child_rdtgrp(rdtgrp);
-
- /* Remove each rdtgroup other than root */
- if (rdtgrp == &rdtgroup_default)
- continue;
-
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
- rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)
- rdtgroup_pseudo_lock_remove(rdtgrp);
-
- /*
- * Give any CPUs back to the default group. We cannot copy
- * cpu_online_mask because a CPU might have executed the
- * offline callback already, but is still marked online.
- */
- cpumask_or(&rdtgroup_default.cpu_mask,
- &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
-
- free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-
- kernfs_remove(rdtgrp->kn);
- list_del(&rdtgrp->rdtgroup_list);
-
- if (atomic_read(&rdtgrp->waitcount) != 0)
- rdtgrp->flags = RDT_DELETED;
- else
- rdtgroup_remove(rdtgrp);
- }
- /* Notify online CPUs to update per cpu storage and PQR_ASSOC MSR */
- update_closid_rmid(cpu_online_mask, &rdtgroup_default);
-
- kernfs_remove(kn_info);
- kernfs_remove(kn_mongrp);
- kernfs_remove(kn_mondata);
-}
-
-static void rdt_kill_sb(struct super_block *sb)
-{
- struct rdt_resource *r;
-
- cpus_read_lock();
- mutex_lock(&rdtgroup_mutex);
-
- rdt_disable_ctx();
-
- /* Put everything back to default values. */
- for_each_alloc_capable_rdt_resource(r)
- resctrl_arch_reset_all_ctrls(r);
-
- rmdir_all_sub();
- rdt_pseudo_lock_release();
- rdtgroup_default.mode = RDT_MODE_SHAREABLE;
- schemata_list_destroy();
- rdtgroup_destroy_root();
- if (resctrl_arch_alloc_capable())
- resctrl_arch_disable_alloc();
- if (resctrl_arch_mon_capable())
- resctrl_arch_disable_mon();
- resctrl_mounted = false;
- kernfs_kill_sb(sb);
- mutex_unlock(&rdtgroup_mutex);
- cpus_read_unlock();
-}
-
-static struct file_system_type rdt_fs_type = {
- .name = "resctrl",
- .init_fs_context = rdt_init_fs_context,
- .parameters = rdt_fs_parameters,
- .kill_sb = rdt_kill_sb,
-};
-
-static int mon_addfile(struct kernfs_node *parent_kn, const char *name,
- void *priv)
-{
- struct kernfs_node *kn;
- int ret = 0;
-
- kn = __kernfs_create_file(parent_kn, name, 0444,
- GLOBAL_ROOT_UID, GLOBAL_ROOT_GID, 0,
- &kf_mondata_ops, priv, NULL, NULL);
- if (IS_ERR(kn))
- return PTR_ERR(kn);
-
- ret = rdtgroup_kn_set_ugid(kn);
- if (ret) {
- kernfs_remove(kn);
- return ret;
- }
-
- return ret;
-}
-
-static void mon_rmdir_one_subdir(struct kernfs_node *pkn, char *name, char *subname)
-{
- struct kernfs_node *kn;
-
- kn = kernfs_find_and_get(pkn, name);
- if (!kn)
- return;
- kernfs_put(kn);
-
- if (kn->dir.subdirs <= 1)
- kernfs_remove(kn);
- else
- kernfs_remove_by_name(kn, subname);
-}
-
-/*
- * Remove all subdirectories of mon_data of ctrl_mon groups
- * and monitor groups for the given domain.
- * Remove files and directories containing "sum" of domain data
- * when last domain being summed is removed.
- */
-static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
- struct rdt_mon_domain *d)
-{
- struct rdtgroup *prgrp, *crgrp;
- char subname[32];
- bool snc_mode;
- char name[32];
-
- snc_mode = r->mon_scope == RESCTRL_L3_NODE;
- sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
- if (snc_mode)
- sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
-
- list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
- mon_rmdir_one_subdir(prgrp->mon.mon_data_kn, name, subname);
-
- list_for_each_entry(crgrp, &prgrp->mon.crdtgrp_list, mon.crdtgrp_list)
- mon_rmdir_one_subdir(crgrp->mon.mon_data_kn, name, subname);
- }
-}
-
-static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
- struct rdt_resource *r, struct rdtgroup *prgrp,
- bool do_sum)
-{
- struct rmid_read rr = {0};
- union mon_data_bits priv;
- struct mon_evt *mevt;
- int ret;
-
- if (WARN_ON(list_empty(&r->evt_list)))
- return -EPERM;
-
- priv.u.rid = r->rid;
- priv.u.domid = do_sum ? d->ci->id : d->hdr.id;
- priv.u.sum = do_sum;
- list_for_each_entry(mevt, &r->evt_list, list) {
- priv.u.evtid = mevt->evtid;
- ret = mon_addfile(kn, mevt->name, priv.priv);
- if (ret)
- return ret;
-
- if (!do_sum && resctrl_is_mbm_event(mevt->evtid))
- mon_event_read(&rr, r, d, prgrp, &d->hdr.cpu_mask, mevt->evtid, true);
- }
-
- return 0;
-}
-
-static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
- struct rdt_mon_domain *d,
- struct rdt_resource *r, struct rdtgroup *prgrp)
-{
- struct kernfs_node *kn, *ckn;
- char name[32];
- bool snc_mode;
- int ret = 0;
-
- lockdep_assert_held(&rdtgroup_mutex);
-
- snc_mode = r->mon_scope == RESCTRL_L3_NODE;
- sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
- kn = kernfs_find_and_get(parent_kn, name);
- if (kn) {
- /*
- * rdtgroup_mutex will prevent this directory from being
- * removed. No need to keep this hold.
- */
- kernfs_put(kn);
- } else {
- kn = kernfs_create_dir(parent_kn, name, parent_kn->mode, prgrp);
- if (IS_ERR(kn))
- return PTR_ERR(kn);
-
- ret = rdtgroup_kn_set_ugid(kn);
- if (ret)
- goto out_destroy;
- ret = mon_add_all_files(kn, d, r, prgrp, snc_mode);
- if (ret)
- goto out_destroy;
- }
-
- if (snc_mode) {
- sprintf(name, "mon_sub_%s_%02d", r->name, d->hdr.id);
- ckn = kernfs_create_dir(kn, name, parent_kn->mode, prgrp);
- if (IS_ERR(ckn)) {
- ret = -EINVAL;
- goto out_destroy;
- }
-
- ret = rdtgroup_kn_set_ugid(ckn);
- if (ret)
- goto out_destroy;
-
- ret = mon_add_all_files(ckn, d, r, prgrp, false);
- if (ret)
- goto out_destroy;
- }
-
- kernfs_activate(kn);
- return 0;
-
-out_destroy:
- kernfs_remove(kn);
- return ret;
-}
-
-/*
- * Add all subdirectories of mon_data for "ctrl_mon" groups
- * and "monitor" groups with given domain id.
- */
-static void mkdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
- struct rdt_mon_domain *d)
-{
- struct kernfs_node *parent_kn;
- struct rdtgroup *prgrp, *crgrp;
- struct list_head *head;
-
- list_for_each_entry(prgrp, &rdt_all_groups, rdtgroup_list) {
- parent_kn = prgrp->mon.mon_data_kn;
- mkdir_mondata_subdir(parent_kn, d, r, prgrp);
-
- head = &prgrp->mon.crdtgrp_list;
- list_for_each_entry(crgrp, head, mon.crdtgrp_list) {
- parent_kn = crgrp->mon.mon_data_kn;
- mkdir_mondata_subdir(parent_kn, d, r, crgrp);
- }
- }
-}
-
-static int mkdir_mondata_subdir_alldom(struct kernfs_node *parent_kn,
- struct rdt_resource *r,
- struct rdtgroup *prgrp)
-{
- struct rdt_mon_domain *dom;
- int ret;
-
- /* Walking r->domains, ensure it can't race with cpuhp */
- lockdep_assert_cpus_held();
-
- list_for_each_entry(dom, &r->mon_domains, hdr.list) {
- ret = mkdir_mondata_subdir(parent_kn, dom, r, prgrp);
- if (ret)
- return ret;
- }
-
- return 0;
-}
-
-/*
- * This creates a directory mon_data which contains the monitored data.
- *
- * mon_data has one directory for each domain which are named
- * in the format mon_<domain_name>_<domain_id>. For ex: A mon_data
- * with L3 domain looks as below:
- * ./mon_data:
- * mon_L3_00
- * mon_L3_01
- * mon_L3_02
- * ...
- *
- * Each domain directory has one file per event:
- * ./mon_L3_00/:
- * llc_occupancy
- *
- */
-static int mkdir_mondata_all(struct kernfs_node *parent_kn,
- struct rdtgroup *prgrp,
- struct kernfs_node **dest_kn)
-{
- struct rdt_resource *r;
- struct kernfs_node *kn;
- int ret;
-
- /*
- * Create the mon_data directory first.
- */
- ret = mongroup_create_dir(parent_kn, prgrp, "mon_data", &kn);
- if (ret)
- return ret;
-
- if (dest_kn)
- *dest_kn = kn;
-
- /*
- * Create the subdirectories for each domain. Note that all events
- * in a domain like L3 are grouped into a resource whose domain is L3
- */
- for_each_mon_capable_rdt_resource(r) {
- ret = mkdir_mondata_subdir_alldom(kn, r, prgrp);
- if (ret)
- goto out_destroy;
- }
-
- return 0;
-
-out_destroy:
- kernfs_remove(kn);
- return ret;
-}
-
-/**
- * cbm_ensure_valid - Enforce validity on provided CBM
- * @_val: Candidate CBM
- * @r: RDT resource to which the CBM belongs
- *
- * The provided CBM represents all cache portions available for use. This
- * may be represented by a bitmap that does not consist of contiguous ones
- * and thus be an invalid CBM.
- * Here the provided CBM is forced to be a valid CBM by only considering
- * the first set of contiguous bits as valid and clearing all bits.
- * The intention here is to provide a valid default CBM with which a new
- * resource group is initialized. The user can follow this with a
- * modification to the CBM if the default does not satisfy the
- * requirements.
- */
-static u32 cbm_ensure_valid(u32 _val, struct rdt_resource *r)
-{
- unsigned int cbm_len = r->cache.cbm_len;
- unsigned long first_bit, zero_bit;
- unsigned long val = _val;
-
- if (!val)
- return 0;
-
- first_bit = find_first_bit(&val, cbm_len);
- zero_bit = find_next_zero_bit(&val, cbm_len, first_bit);
-
- /* Clear any remaining bits to ensure contiguous region */
- bitmap_clear(&val, zero_bit, cbm_len - zero_bit);
- return (u32)val;
-}
-
-/*
- * Initialize cache resources per RDT domain
- *
- * Set the RDT domain up to start off with all usable allocations. That is,
- * all shareable and unused bits. All-zero CBM is invalid.
- */
-static int __init_one_rdt_domain(struct rdt_ctrl_domain *d, struct resctrl_schema *s,
- u32 closid)
-{
- enum resctrl_conf_type peer_type = resctrl_peer_type(s->conf_type);
- enum resctrl_conf_type t = s->conf_type;
- struct resctrl_staged_config *cfg;
- struct rdt_resource *r = s->res;
- u32 used_b = 0, unused_b = 0;
- unsigned long tmp_cbm;
- enum rdtgrp_mode mode;
- u32 peer_ctl, ctrl_val;
- int i;
-
- cfg = &d->staged_config[t];
- cfg->have_new_ctrl = false;
- cfg->new_ctrl = r->cache.shareable_bits;
- used_b = r->cache.shareable_bits;
- for (i = 0; i < closids_supported(); i++) {
- if (closid_allocated(i) && i != closid) {
- mode = rdtgroup_mode_by_closid(i);
- if (mode == RDT_MODE_PSEUDO_LOCKSETUP)
- /*
- * ctrl values for locksetup aren't relevant
- * until the schemata is written, and the mode
- * becomes RDT_MODE_PSEUDO_LOCKED.
- */
- continue;
- /*
- * If CDP is active include peer domain's
- * usage to ensure there is no overlap
- * with an exclusive group.
- */
- if (resctrl_arch_get_cdp_enabled(r->rid))
- peer_ctl = resctrl_arch_get_config(r, d, i,
- peer_type);
- else
- peer_ctl = 0;
- ctrl_val = resctrl_arch_get_config(r, d, i,
- s->conf_type);
- used_b |= ctrl_val | peer_ctl;
- if (mode == RDT_MODE_SHAREABLE)
- cfg->new_ctrl |= ctrl_val | peer_ctl;
- }
- }
- if (d->plr && d->plr->cbm > 0)
- used_b |= d->plr->cbm;
- unused_b = used_b ^ (BIT_MASK(r->cache.cbm_len) - 1);
- unused_b &= BIT_MASK(r->cache.cbm_len) - 1;
- cfg->new_ctrl |= unused_b;
- /*
- * Force the initial CBM to be valid, user can
- * modify the CBM based on system availability.
- */
- cfg->new_ctrl = cbm_ensure_valid(cfg->new_ctrl, r);
- /*
- * Assign the u32 CBM to an unsigned long to ensure that
- * bitmap_weight() does not access out-of-bound memory.
- */
- tmp_cbm = cfg->new_ctrl;
- if (bitmap_weight(&tmp_cbm, r->cache.cbm_len) < r->cache.min_cbm_bits) {
- rdt_last_cmd_printf("No space on %s:%d\n", s->name, d->hdr.id);
- return -ENOSPC;
- }
- cfg->have_new_ctrl = true;
-
- return 0;
-}
-
-/*
- * Initialize cache resources with default values.
- *
- * A new RDT group is being created on an allocation capable (CAT)
- * supporting system. Set this group up to start off with all usable
- * allocations.
- *
- * If there are no more shareable bits available on any domain then
- * the entire allocation will fail.
- */
-static int rdtgroup_init_cat(struct resctrl_schema *s, u32 closid)
-{
- struct rdt_ctrl_domain *d;
- int ret;
-
- list_for_each_entry(d, &s->res->ctrl_domains, hdr.list) {
- ret = __init_one_rdt_domain(d, s, closid);
- if (ret < 0)
- return ret;
- }
-
- return 0;
-}
-
-/* Initialize MBA resource with default values. */
-static void rdtgroup_init_mba(struct rdt_resource *r, u32 closid)
-{
- struct resctrl_staged_config *cfg;
- struct rdt_ctrl_domain *d;
-
- list_for_each_entry(d, &r->ctrl_domains, hdr.list) {
- if (is_mba_sc(r)) {
- d->mbps_val[closid] = MBA_MAX_MBPS;
- continue;
- }
-
- cfg = &d->staged_config[CDP_NONE];
- cfg->new_ctrl = resctrl_get_default_ctrl(r);
- cfg->have_new_ctrl = true;
- }
-}
-
-/* Initialize the RDT group's allocations. */
-static int rdtgroup_init_alloc(struct rdtgroup *rdtgrp)
-{
- struct resctrl_schema *s;
- struct rdt_resource *r;
- int ret = 0;
-
- rdt_staged_configs_clear();
-
- list_for_each_entry(s, &resctrl_schema_all, list) {
- r = s->res;
- if (r->rid == RDT_RESOURCE_MBA ||
- r->rid == RDT_RESOURCE_SMBA) {
- rdtgroup_init_mba(r, rdtgrp->closid);
- if (is_mba_sc(r))
- continue;
- } else {
- ret = rdtgroup_init_cat(s, rdtgrp->closid);
- if (ret < 0)
- goto out;
- }
-
- ret = resctrl_arch_update_domains(r, rdtgrp->closid);
- if (ret < 0) {
- rdt_last_cmd_puts("Failed to initialize allocations\n");
- goto out;
- }
-
- }
-
- rdtgrp->mode = RDT_MODE_SHAREABLE;
-
-out:
- rdt_staged_configs_clear();
- return ret;
-}
-
-static int mkdir_rdt_prepare_rmid_alloc(struct rdtgroup *rdtgrp)
-{
- int ret;
-
- if (!resctrl_arch_mon_capable())
- return 0;
-
- ret = alloc_rmid(rdtgrp->closid);
- if (ret < 0) {
- rdt_last_cmd_puts("Out of RMIDs\n");
- return ret;
- }
- rdtgrp->mon.rmid = ret;
-
- ret = mkdir_mondata_all(rdtgrp->kn, rdtgrp, &rdtgrp->mon.mon_data_kn);
- if (ret) {
- rdt_last_cmd_puts("kernfs subdir error\n");
- free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
- return ret;
- }
-
- return 0;
-}
-
-static void mkdir_rdt_prepare_rmid_free(struct rdtgroup *rgrp)
-{
- if (resctrl_arch_mon_capable())
- free_rmid(rgrp->closid, rgrp->mon.rmid);
-}
-
-/*
- * We allow creating mon groups only with in a directory called "mon_groups"
- * which is present in every ctrl_mon group. Check if this is a valid
- * "mon_groups" directory.
- *
- * 1. The directory should be named "mon_groups".
- * 2. The mon group itself should "not" be named "mon_groups".
- * This makes sure "mon_groups" directory always has a ctrl_mon group
- * as parent.
- */
-static bool is_mon_groups(struct kernfs_node *kn, const char *name)
-{
- return (!strcmp(rdt_kn_name(kn), "mon_groups") &&
- strcmp(name, "mon_groups"));
-}
-
-static int mkdir_rdt_prepare(struct kernfs_node *parent_kn,
- const char *name, umode_t mode,
- enum rdt_group_type rtype, struct rdtgroup **r)
-{
- struct rdtgroup *prdtgrp, *rdtgrp;
- unsigned long files = 0;
- struct kernfs_node *kn;
- int ret;
-
- prdtgrp = rdtgroup_kn_lock_live(parent_kn);
- if (!prdtgrp) {
- ret = -ENODEV;
- goto out_unlock;
- }
-
- /*
- * Check that the parent directory for a monitor group is a "mon_groups"
- * directory.
- */
- if (rtype == RDTMON_GROUP && !is_mon_groups(parent_kn, name)) {
- ret = -EPERM;
- goto out_unlock;
- }
-
- if (rtype == RDTMON_GROUP &&
- (prdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
- prdtgrp->mode == RDT_MODE_PSEUDO_LOCKED)) {
- ret = -EINVAL;
- rdt_last_cmd_puts("Pseudo-locking in progress\n");
- goto out_unlock;
- }
-
- /* allocate the rdtgroup. */
- rdtgrp = kzalloc(sizeof(*rdtgrp), GFP_KERNEL);
- if (!rdtgrp) {
- ret = -ENOSPC;
- rdt_last_cmd_puts("Kernel out of memory\n");
- goto out_unlock;
- }
- *r = rdtgrp;
- rdtgrp->mon.parent = prdtgrp;
- rdtgrp->type = rtype;
- INIT_LIST_HEAD(&rdtgrp->mon.crdtgrp_list);
-
- /* kernfs creates the directory for rdtgrp */
- kn = kernfs_create_dir(parent_kn, name, mode, rdtgrp);
- if (IS_ERR(kn)) {
- ret = PTR_ERR(kn);
- rdt_last_cmd_puts("kernfs create error\n");
- goto out_free_rgrp;
- }
- rdtgrp->kn = kn;
-
- /*
- * kernfs_remove() will drop the reference count on "kn" which
- * will free it. But we still need it to stick around for the
- * rdtgroup_kn_unlock(kn) call. Take one extra reference here,
- * which will be dropped by kernfs_put() in rdtgroup_remove().
- */
- kernfs_get(kn);
-
- ret = rdtgroup_kn_set_ugid(kn);
- if (ret) {
- rdt_last_cmd_puts("kernfs perm error\n");
- goto out_destroy;
- }
-
- if (rtype == RDTCTRL_GROUP) {
- files = RFTYPE_BASE | RFTYPE_CTRL;
- if (resctrl_arch_mon_capable())
- files |= RFTYPE_MON;
- } else {
- files = RFTYPE_BASE | RFTYPE_MON;
- }
-
- ret = rdtgroup_add_files(kn, files);
- if (ret) {
- rdt_last_cmd_puts("kernfs fill error\n");
- goto out_destroy;
- }
-
- /*
- * The caller unlocks the parent_kn upon success.
- */
- return 0;
-
-out_destroy:
- kernfs_put(rdtgrp->kn);
- kernfs_remove(rdtgrp->kn);
-out_free_rgrp:
- kfree(rdtgrp);
-out_unlock:
- rdtgroup_kn_unlock(parent_kn);
- return ret;
-}
-
-static void mkdir_rdt_prepare_clean(struct rdtgroup *rgrp)
-{
- kernfs_remove(rgrp->kn);
- rdtgroup_remove(rgrp);
-}
-
-/*
- * Create a monitor group under "mon_groups" directory of a control
- * and monitor group(ctrl_mon). This is a resource group
- * to monitor a subset of tasks and cpus in its parent ctrl_mon group.
- */
-static int rdtgroup_mkdir_mon(struct kernfs_node *parent_kn,
- const char *name, umode_t mode)
-{
- struct rdtgroup *rdtgrp, *prgrp;
- int ret;
-
- ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTMON_GROUP, &rdtgrp);
- if (ret)
- return ret;
-
- prgrp = rdtgrp->mon.parent;
- rdtgrp->closid = prgrp->closid;
-
- ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
- if (ret) {
- mkdir_rdt_prepare_clean(rdtgrp);
- goto out_unlock;
- }
-
- kernfs_activate(rdtgrp->kn);
-
- /*
- * Add the rdtgrp to the list of rdtgrps the parent
- * ctrl_mon group has to track.
- */
- list_add_tail(&rdtgrp->mon.crdtgrp_list, &prgrp->mon.crdtgrp_list);
-
-out_unlock:
- rdtgroup_kn_unlock(parent_kn);
- return ret;
-}
-
-/*
- * These are rdtgroups created under the root directory. Can be used
- * to allocate and monitor resources.
- */
-static int rdtgroup_mkdir_ctrl_mon(struct kernfs_node *parent_kn,
- const char *name, umode_t mode)
-{
- struct rdtgroup *rdtgrp;
- struct kernfs_node *kn;
- u32 closid;
- int ret;
-
- ret = mkdir_rdt_prepare(parent_kn, name, mode, RDTCTRL_GROUP, &rdtgrp);
- if (ret)
- return ret;
-
- kn = rdtgrp->kn;
- ret = closid_alloc();
- if (ret < 0) {
- rdt_last_cmd_puts("Out of CLOSIDs\n");
- goto out_common_fail;
- }
- closid = ret;
- ret = 0;
-
- rdtgrp->closid = closid;
-
- ret = mkdir_rdt_prepare_rmid_alloc(rdtgrp);
- if (ret)
- goto out_closid_free;
-
- kernfs_activate(rdtgrp->kn);
-
- ret = rdtgroup_init_alloc(rdtgrp);
- if (ret < 0)
- goto out_rmid_free;
-
- list_add(&rdtgrp->rdtgroup_list, &rdt_all_groups);
-
- if (resctrl_arch_mon_capable()) {
- /*
- * Create an empty mon_groups directory to hold the subset
- * of tasks and cpus to monitor.
- */
- ret = mongroup_create_dir(kn, rdtgrp, "mon_groups", NULL);
- if (ret) {
- rdt_last_cmd_puts("kernfs subdir error\n");
- goto out_del_list;
- }
- if (is_mba_sc(NULL))
- rdtgrp->mba_mbps_event = mba_mbps_default_event;
- }
-
- goto out_unlock;
-
-out_del_list:
- list_del(&rdtgrp->rdtgroup_list);
-out_rmid_free:
- mkdir_rdt_prepare_rmid_free(rdtgrp);
-out_closid_free:
- closid_free(closid);
-out_common_fail:
- mkdir_rdt_prepare_clean(rdtgrp);
-out_unlock:
- rdtgroup_kn_unlock(parent_kn);
- return ret;
-}
-
-static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
- umode_t mode)
-{
- /* Do not accept '\n' to avoid unparsable situation. */
- if (strchr(name, '\n'))
- return -EINVAL;
-
- /*
- * If the parent directory is the root directory and RDT
- * allocation is supported, add a control and monitoring
- * subdirectory
- */
- if (resctrl_arch_alloc_capable() && parent_kn == rdtgroup_default.kn)
- return rdtgroup_mkdir_ctrl_mon(parent_kn, name, mode);
-
- /* Else, attempt to add a monitoring subdirectory. */
- if (resctrl_arch_mon_capable())
- return rdtgroup_mkdir_mon(parent_kn, name, mode);
-
- return -EPERM;
-}
-
-static int rdtgroup_rmdir_mon(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
-{
- struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
- u32 closid, rmid;
- int cpu;
-
- /* Give any tasks back to the parent group */
- rdt_move_group_tasks(rdtgrp, prdtgrp, tmpmask);
-
- /*
- * Update per cpu closid/rmid of the moved CPUs first.
- * Note: the closid will not change, but the arch code still needs it.
- */
- closid = prdtgrp->closid;
- rmid = prdtgrp->mon.rmid;
- for_each_cpu(cpu, &rdtgrp->cpu_mask)
- resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid);
-
- /*
- * Update the MSR on moved CPUs and CPUs which have moved
- * task running on them.
- */
- cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
- update_closid_rmid(tmpmask, NULL);
-
- rdtgrp->flags = RDT_DELETED;
- free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
-
- /*
- * Remove the rdtgrp from the parent ctrl_mon group's list
- */
- WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
- list_del(&rdtgrp->mon.crdtgrp_list);
-
- kernfs_remove(rdtgrp->kn);
-
- return 0;
-}
-
-static int rdtgroup_ctrl_remove(struct rdtgroup *rdtgrp)
-{
- rdtgrp->flags = RDT_DELETED;
- list_del(&rdtgrp->rdtgroup_list);
-
- kernfs_remove(rdtgrp->kn);
- return 0;
-}
-
-static int rdtgroup_rmdir_ctrl(struct rdtgroup *rdtgrp, cpumask_var_t tmpmask)
-{
- u32 closid, rmid;
- int cpu;
-
- /* Give any tasks back to the default group */
- rdt_move_group_tasks(rdtgrp, &rdtgroup_default, tmpmask);
-
- /* Give any CPUs back to the default group */
- cpumask_or(&rdtgroup_default.cpu_mask,
- &rdtgroup_default.cpu_mask, &rdtgrp->cpu_mask);
-
- /* Update per cpu closid and rmid of the moved CPUs first */
- closid = rdtgroup_default.closid;
- rmid = rdtgroup_default.mon.rmid;
- for_each_cpu(cpu, &rdtgrp->cpu_mask)
- resctrl_arch_set_cpu_default_closid_rmid(cpu, closid, rmid);
-
- /*
- * Update the MSR on moved CPUs and CPUs which have moved
- * task running on them.
- */
- cpumask_or(tmpmask, tmpmask, &rdtgrp->cpu_mask);
- update_closid_rmid(tmpmask, NULL);
-
- free_rmid(rdtgrp->closid, rdtgrp->mon.rmid);
- closid_free(rdtgrp->closid);
-
- rdtgroup_ctrl_remove(rdtgrp);
-
- /*
- * Free all the child monitor group rmids.
- */
- free_all_child_rdtgrp(rdtgrp);
-
- return 0;
-}
-
-static struct kernfs_node *rdt_kn_parent(struct kernfs_node *kn)
-{
- /*
- * Valid within the RCU section it was obtained or while rdtgroup_mutex
- * is held.
- */
- return rcu_dereference_check(kn->__parent, lockdep_is_held(&rdtgroup_mutex));
-}
-
-static int rdtgroup_rmdir(struct kernfs_node *kn)
-{
- struct kernfs_node *parent_kn;
- struct rdtgroup *rdtgrp;
- cpumask_var_t tmpmask;
- int ret = 0;
-
- if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL))
- return -ENOMEM;
-
- rdtgrp = rdtgroup_kn_lock_live(kn);
- if (!rdtgrp) {
- ret = -EPERM;
- goto out;
- }
- parent_kn = rdt_kn_parent(kn);
-
- /*
- * If the rdtgroup is a ctrl_mon group and parent directory
- * is the root directory, remove the ctrl_mon group.
- *
- * If the rdtgroup is a mon group and parent directory
- * is a valid "mon_groups" directory, remove the mon group.
- */
- if (rdtgrp->type == RDTCTRL_GROUP && parent_kn == rdtgroup_default.kn &&
- rdtgrp != &rdtgroup_default) {
- if (rdtgrp->mode == RDT_MODE_PSEUDO_LOCKSETUP ||
- rdtgrp->mode == RDT_MODE_PSEUDO_LOCKED) {
- ret = rdtgroup_ctrl_remove(rdtgrp);
- } else {
- ret = rdtgroup_rmdir_ctrl(rdtgrp, tmpmask);
- }
- } else if (rdtgrp->type == RDTMON_GROUP &&
- is_mon_groups(parent_kn, rdt_kn_name(kn))) {
- ret = rdtgroup_rmdir_mon(rdtgrp, tmpmask);
- } else {
- ret = -EPERM;
- }
-
-out:
- rdtgroup_kn_unlock(kn);
- free_cpumask_var(tmpmask);
- return ret;
-}
-
-/**
- * mongrp_reparent() - replace parent CTRL_MON group of a MON group
- * @rdtgrp: the MON group whose parent should be replaced
- * @new_prdtgrp: replacement parent CTRL_MON group for @rdtgrp
- * @cpus: cpumask provided by the caller for use during this call
- *
- * Replaces the parent CTRL_MON group for a MON group, resulting in all member
- * tasks' CLOSID immediately changing to that of the new parent group.
- * Monitoring data for the group is unaffected by this operation.
- */
-static void mongrp_reparent(struct rdtgroup *rdtgrp,
- struct rdtgroup *new_prdtgrp,
- cpumask_var_t cpus)
-{
- struct rdtgroup *prdtgrp = rdtgrp->mon.parent;
-
- WARN_ON(rdtgrp->type != RDTMON_GROUP);
- WARN_ON(new_prdtgrp->type != RDTCTRL_GROUP);
-
- /* Nothing to do when simply renaming a MON group. */
- if (prdtgrp == new_prdtgrp)
- return;
-
- WARN_ON(list_empty(&prdtgrp->mon.crdtgrp_list));
- list_move_tail(&rdtgrp->mon.crdtgrp_list,
- &new_prdtgrp->mon.crdtgrp_list);
-
- rdtgrp->mon.parent = new_prdtgrp;
- rdtgrp->closid = new_prdtgrp->closid;
-
- /* Propagate updated closid to all tasks in this group. */
- rdt_move_group_tasks(rdtgrp, rdtgrp, cpus);
-
- update_closid_rmid(cpus, NULL);
-}
-
-static int rdtgroup_rename(struct kernfs_node *kn,
- struct kernfs_node *new_parent, const char *new_name)
-{
- struct kernfs_node *kn_parent;
- struct rdtgroup *new_prdtgrp;
- struct rdtgroup *rdtgrp;
- cpumask_var_t tmpmask;
- int ret;
-
- rdtgrp = kernfs_to_rdtgroup(kn);
- new_prdtgrp = kernfs_to_rdtgroup(new_parent);
- if (!rdtgrp || !new_prdtgrp)
- return -ENOENT;
-
- /* Release both kernfs active_refs before obtaining rdtgroup mutex. */
- rdtgroup_kn_get(rdtgrp, kn);
- rdtgroup_kn_get(new_prdtgrp, new_parent);
-
- mutex_lock(&rdtgroup_mutex);
-
- rdt_last_cmd_clear();
-
- /*
- * Don't allow kernfs_to_rdtgroup() to return a parent rdtgroup if
- * either kernfs_node is a file.
- */
- if (kernfs_type(kn) != KERNFS_DIR ||
- kernfs_type(new_parent) != KERNFS_DIR) {
- rdt_last_cmd_puts("Source and destination must be directories");
- ret = -EPERM;
- goto out;
- }
-
- if ((rdtgrp->flags & RDT_DELETED) || (new_prdtgrp->flags & RDT_DELETED)) {
- ret = -ENOENT;
- goto out;
- }
-
- kn_parent = rdt_kn_parent(kn);
- if (rdtgrp->type != RDTMON_GROUP || !kn_parent ||
- !is_mon_groups(kn_parent, rdt_kn_name(kn))) {
- rdt_last_cmd_puts("Source must be a MON group\n");
- ret = -EPERM;
- goto out;
- }
-
- if (!is_mon_groups(new_parent, new_name)) {
- rdt_last_cmd_puts("Destination must be a mon_groups subdirectory\n");
- ret = -EPERM;
- goto out;
- }
-
- /*
- * If the MON group is monitoring CPUs, the CPUs must be assigned to the
- * current parent CTRL_MON group and therefore cannot be assigned to
- * the new parent, making the move illegal.
- */
- if (!cpumask_empty(&rdtgrp->cpu_mask) &&
- rdtgrp->mon.parent != new_prdtgrp) {
- rdt_last_cmd_puts("Cannot move a MON group that monitors CPUs\n");
- ret = -EPERM;
- goto out;
- }
-
- /*
- * Allocate the cpumask for use in mongrp_reparent() to avoid the
- * possibility of failing to allocate it after kernfs_rename() has
- * succeeded.
- */
- if (!zalloc_cpumask_var(&tmpmask, GFP_KERNEL)) {
- ret = -ENOMEM;
- goto out;
- }
-
- /*
- * Perform all input validation and allocations needed to ensure
- * mongrp_reparent() will succeed before calling kernfs_rename(),
- * otherwise it would be necessary to revert this call if
- * mongrp_reparent() failed.
- */
- ret = kernfs_rename(kn, new_parent, new_name);
- if (!ret)
- mongrp_reparent(rdtgrp, new_prdtgrp, tmpmask);
-
- free_cpumask_var(tmpmask);
-
-out:
- mutex_unlock(&rdtgroup_mutex);
- rdtgroup_kn_put(rdtgrp, kn);
- rdtgroup_kn_put(new_prdtgrp, new_parent);
- return ret;
-}
-
-static int rdtgroup_show_options(struct seq_file *seq, struct kernfs_root *kf)
-{
- if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L3))
- seq_puts(seq, ",cdp");
-
- if (resctrl_arch_get_cdp_enabled(RDT_RESOURCE_L2))
- seq_puts(seq, ",cdpl2");
-
- if (is_mba_sc(resctrl_arch_get_resource(RDT_RESOURCE_MBA)))
- seq_puts(seq, ",mba_MBps");
-
- if (resctrl_debug)
- seq_puts(seq, ",debug");
-
- return 0;
-}
-
-static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
- .mkdir = rdtgroup_mkdir,
- .rmdir = rdtgroup_rmdir,
- .rename = rdtgroup_rename,
- .show_options = rdtgroup_show_options,
-};
-
-static int rdtgroup_setup_root(struct rdt_fs_context *ctx)
-{
- rdt_root = kernfs_create_root(&rdtgroup_kf_syscall_ops,
- KERNFS_ROOT_CREATE_DEACTIVATED |
- KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK,
- &rdtgroup_default);
- if (IS_ERR(rdt_root))
- return PTR_ERR(rdt_root);
-
- ctx->kfc.root = rdt_root;
- rdtgroup_default.kn = kernfs_root_to_node(rdt_root);
-
- return 0;
-}
-
-static void rdtgroup_destroy_root(void)
-{
- kernfs_destroy_root(rdt_root);
- rdtgroup_default.kn = NULL;
-}
-
-static void __init rdtgroup_setup_default(void)
-{
- mutex_lock(&rdtgroup_mutex);
-
- rdtgroup_default.closid = RESCTRL_RESERVED_CLOSID;
- rdtgroup_default.mon.rmid = RESCTRL_RESERVED_RMID;
- rdtgroup_default.type = RDTCTRL_GROUP;
- INIT_LIST_HEAD(&rdtgroup_default.mon.crdtgrp_list);
-
- list_add(&rdtgroup_default.rdtgroup_list, &rdt_all_groups);
-
- mutex_unlock(&rdtgroup_mutex);
-}
-
-static void domain_destroy_mon_state(struct rdt_mon_domain *d)
-{
- bitmap_free(d->rmid_busy_llc);
- kfree(d->mbm_total);
- kfree(d->mbm_local);
-}
-
-void resctrl_offline_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
-{
- mutex_lock(&rdtgroup_mutex);
-
- if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA)
- mba_sc_domain_destroy(r, d);
-
- mutex_unlock(&rdtgroup_mutex);
-}
-
-void resctrl_offline_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
-{
- mutex_lock(&rdtgroup_mutex);
-
- /*
- * If resctrl is mounted, remove all the
- * per domain monitor data directories.
- */
- if (resctrl_mounted && resctrl_arch_mon_capable())
- rmdir_mondata_subdir_allrdtgrp(r, d);
-
- if (resctrl_is_mbm_enabled())
- cancel_delayed_work(&d->mbm_over);
- if (resctrl_arch_is_llc_occupancy_enabled() && has_busy_rmid(d)) {
- /*
- * When a package is going down, forcefully
- * decrement rmid->ebusy. There is no way to know
- * that the L3 was flushed and hence may lead to
- * incorrect counts in rare scenarios, but leaving
- * the RMID as busy creates RMID leaks if the
- * package never comes back.
- */
- __check_limbo(d, true);
- cancel_delayed_work(&d->cqm_limbo);
- }
-
- domain_destroy_mon_state(d);
-
- mutex_unlock(&rdtgroup_mutex);
-}
-
-/**
- * domain_setup_mon_state() - Initialise domain monitoring structures.
- * @r: The resource for the newly online domain.
- * @d: The newly online domain.
- *
- * Allocate monitor resources that belong to this domain.
- * Called when the first CPU of a domain comes online, regardless of whether
- * the filesystem is mounted.
- * During boot this may be called before global allocations have been made by
- * resctrl_mon_resource_init().
- *
- * Returns 0 for success, or -ENOMEM.
- */
-static int domain_setup_mon_state(struct rdt_resource *r, struct rdt_mon_domain *d)
-{
- u32 idx_limit = resctrl_arch_system_num_rmid_idx();
- size_t tsize;
-
- if (resctrl_arch_is_llc_occupancy_enabled()) {
- d->rmid_busy_llc = bitmap_zalloc(idx_limit, GFP_KERNEL);
- if (!d->rmid_busy_llc)
- return -ENOMEM;
- }
- if (resctrl_arch_is_mbm_total_enabled()) {
- tsize = sizeof(*d->mbm_total);
- d->mbm_total = kcalloc(idx_limit, tsize, GFP_KERNEL);
- if (!d->mbm_total) {
- bitmap_free(d->rmid_busy_llc);
- return -ENOMEM;
- }
- }
- if (resctrl_arch_is_mbm_local_enabled()) {
- tsize = sizeof(*d->mbm_local);
- d->mbm_local = kcalloc(idx_limit, tsize, GFP_KERNEL);
- if (!d->mbm_local) {
- bitmap_free(d->rmid_busy_llc);
- kfree(d->mbm_total);
- return -ENOMEM;
- }
- }
-
- return 0;
-}
-
-int resctrl_online_ctrl_domain(struct rdt_resource *r, struct rdt_ctrl_domain *d)
-{
- int err = 0;
-
- mutex_lock(&rdtgroup_mutex);
-
- if (supports_mba_mbps() && r->rid == RDT_RESOURCE_MBA) {
- /* RDT_RESOURCE_MBA is never mon_capable */
- err = mba_sc_domain_allocate(r, d);
- }
-
- mutex_unlock(&rdtgroup_mutex);
-
- return err;
-}
-
-int resctrl_online_mon_domain(struct rdt_resource *r, struct rdt_mon_domain *d)
-{
- int err;
-
- mutex_lock(&rdtgroup_mutex);
-
- err = domain_setup_mon_state(r, d);
- if (err)
- goto out_unlock;
-
- if (resctrl_is_mbm_enabled()) {
- INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
- mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL,
- RESCTRL_PICK_ANY_CPU);
- }
-
- if (resctrl_arch_is_llc_occupancy_enabled())
- INIT_DELAYED_WORK(&d->cqm_limbo, cqm_handle_limbo);
-
- /*
- * If the filesystem is not mounted then only the default resource group
- * exists. Creation of its directories is deferred until mount time
- * by rdt_get_tree() calling mkdir_mondata_all().
- * If resctrl is mounted, add per domain monitor data directories.
- */
- if (resctrl_mounted && resctrl_arch_mon_capable())
- mkdir_mondata_subdir_allrdtgrp(r, d);
-
-out_unlock:
- mutex_unlock(&rdtgroup_mutex);
-
- return err;
-}
-
-void resctrl_online_cpu(unsigned int cpu)
-{
- mutex_lock(&rdtgroup_mutex);
- /* The CPU is set in default rdtgroup after online. */
- cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
- mutex_unlock(&rdtgroup_mutex);
-}
-
-static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
-{
- struct rdtgroup *cr;
-
- list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
- if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask))
- break;
- }
-}
-
-static struct rdt_mon_domain *get_mon_domain_from_cpu(int cpu,
- struct rdt_resource *r)
-{
- struct rdt_mon_domain *d;
-
- lockdep_assert_cpus_held();
-
- list_for_each_entry(d, &r->mon_domains, hdr.list) {
- /* Find the domain that contains this CPU */
- if (cpumask_test_cpu(cpu, &d->hdr.cpu_mask))
- return d;
- }
-
- return NULL;
-}
-
-void resctrl_offline_cpu(unsigned int cpu)
-{
- struct rdt_resource *l3 = resctrl_arch_get_resource(RDT_RESOURCE_L3);
- struct rdt_mon_domain *d;
- struct rdtgroup *rdtgrp;
-
- mutex_lock(&rdtgroup_mutex);
- list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
- if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
- clear_childcpus(rdtgrp, cpu);
- break;
- }
- }
-
- if (!l3->mon_capable)
- goto out_unlock;
-
- d = get_mon_domain_from_cpu(cpu, l3);
- if (d) {
- if (resctrl_is_mbm_enabled() && cpu == d->mbm_work_cpu) {
- cancel_delayed_work(&d->mbm_over);
- mbm_setup_overflow_handler(d, 0, cpu);
- }
- if (resctrl_arch_is_llc_occupancy_enabled() &&
- cpu == d->cqm_work_cpu && has_busy_rmid(d)) {
- cancel_delayed_work(&d->cqm_limbo);
- cqm_setup_limbo_handler(d, 0, cpu);
- }
- }
-
-out_unlock:
- mutex_unlock(&rdtgroup_mutex);
-}
-
-/*
- * resctrl_init - resctrl filesystem initialization
- *
- * Setup resctrl file system including set up root, create mount point,
- * register resctrl filesystem, and initialize files under root directory.
- *
- * Return: 0 on success or -errno
- */
-int __init resctrl_init(void)
-{
- int ret = 0;
-
- seq_buf_init(&last_cmd_status, last_cmd_status_buf,
- sizeof(last_cmd_status_buf));
-
- rdtgroup_setup_default();
-
- thread_throttle_mode_init();
-
- ret = resctrl_mon_resource_init();
- if (ret)
- return ret;
-
- ret = sysfs_create_mount_point(fs_kobj, "resctrl");
- if (ret) {
- resctrl_mon_resource_exit();
- return ret;
- }
-
- ret = register_filesystem(&rdt_fs_type);
- if (ret)
- goto cleanup_mountpoint;
-
- /*
- * Adding the resctrl debugfs directory here may not be ideal since
- * it would let the resctrl debugfs directory appear on the debugfs
- * filesystem before the resctrl filesystem is mounted.
- * It may also be ok since that would enable debugging of RDT before
- * resctrl is mounted.
- * The reason why the debugfs directory is created here and not in
- * rdt_get_tree() is because rdt_get_tree() takes rdtgroup_mutex and
- * during the debugfs directory creation also &sb->s_type->i_mutex_key
- * (the lockdep class of inode->i_rwsem). Other filesystem
- * interactions (eg. SyS_getdents) have the lock ordering:
- * &sb->s_type->i_mutex_key --> &mm->mmap_lock
- * During mmap(), called with &mm->mmap_lock, the rdtgroup_mutex
- * is taken, thus creating dependency:
- * &mm->mmap_lock --> rdtgroup_mutex for the latter that can cause
- * issues considering the other two lock dependencies.
- * By creating the debugfs directory here we avoid a dependency
- * that may cause deadlock (even though file operations cannot
- * occur until the filesystem is mounted, but I do not know how to
- * tell lockdep that).
- */
- debugfs_resctrl = debugfs_create_dir("resctrl", NULL);
-
- return 0;
-
-cleanup_mountpoint:
- sysfs_remove_mount_point(fs_kobj, "resctrl");
- resctrl_mon_resource_exit();
-
- return ret;
-}
-
-void __exit resctrl_exit(void)
-{
- debugfs_remove_recursive(debugfs_resctrl);
- unregister_filesystem(&rdt_fs_type);
- sysfs_remove_mount_point(fs_kobj, "resctrl");
-
- resctrl_mon_resource_exit();
-}
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index 16f3ca30626a..6b868afb26c3 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -27,6 +27,7 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_APERFMPERF, CPUID_ECX, 0, 0x00000006, 0 },
{ X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 },
{ X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 },
+ { X86_FEATURE_APX, CPUID_EDX, 21, 0x00000007, 1 },
{ X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 },
{ X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 },
{ X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 },
@@ -47,13 +48,16 @@ static const struct cpuid_bit cpuid_bits[] = {
{ X86_FEATURE_PROC_FEEDBACK, CPUID_EDX, 11, 0x80000007, 0 },
{ X86_FEATURE_AMD_FAST_CPPC, CPUID_EDX, 15, 0x80000007, 0 },
{ X86_FEATURE_MBA, CPUID_EBX, 6, 0x80000008, 0 },
+ { X86_FEATURE_COHERENCY_SFW_NO, CPUID_EBX, 31, 0x8000001f, 0 },
{ X86_FEATURE_SMBA, CPUID_EBX, 2, 0x80000020, 0 },
{ X86_FEATURE_BMEC, CPUID_EBX, 3, 0x80000020, 0 },
+ { X86_FEATURE_TSA_SQ_NO, CPUID_ECX, 1, 0x80000021, 0 },
+ { X86_FEATURE_TSA_L1_NO, CPUID_ECX, 2, 0x80000021, 0 },
{ X86_FEATURE_AMD_WORKLOAD_CLASS, CPUID_EAX, 22, 0x80000021, 0 },
{ X86_FEATURE_PERFMON_V2, CPUID_EAX, 0, 0x80000022, 0 },
{ X86_FEATURE_AMD_LBR_V2, CPUID_EAX, 1, 0x80000022, 0 },
{ X86_FEATURE_AMD_LBR_PMC_FREEZE, CPUID_EAX, 2, 0x80000022, 0 },
- { X86_FEATURE_AMD_HETEROGENEOUS_CORES, CPUID_EAX, 30, 0x80000026, 0 },
+ { X86_FEATURE_AMD_HTR_CORES, CPUID_EAX, 30, 0x80000026, 0 },
{ 0, 0, 0, 0, 0 }
};
diff --git a/arch/x86/kernel/cpu/sgx/driver.h b/arch/x86/kernel/cpu/sgx/driver.h
index 4eddb4d571ef..30f39f92c98f 100644
--- a/arch/x86/kernel/cpu/sgx/driver.h
+++ b/arch/x86/kernel/cpu/sgx/driver.h
@@ -2,7 +2,6 @@
#ifndef __ARCH_SGX_DRIVER_H__
#define __ARCH_SGX_DRIVER_H__
-#include <crypto/hash.h>
#include <linux/kref.h>
#include <linux/mmu_notifier.h>
#include <linux/radix-tree.h>
diff --git a/arch/x86/kernel/cpu/sgx/encl.c b/arch/x86/kernel/cpu/sgx/encl.c
index 279148e72459..308dbbae6c6e 100644
--- a/arch/x86/kernel/cpu/sgx/encl.c
+++ b/arch/x86/kernel/cpu/sgx/encl.c
@@ -279,7 +279,7 @@ static struct sgx_encl_page *__sgx_encl_load_page(struct sgx_encl *encl,
static struct sgx_encl_page *sgx_encl_load_page_in_vma(struct sgx_encl *encl,
unsigned long addr,
- unsigned long vm_flags)
+ vm_flags_t vm_flags)
{
unsigned long vm_prot_bits = vm_flags & VM_ACCESS_FLAGS;
struct sgx_encl_page *entry;
@@ -520,9 +520,9 @@ static void sgx_vma_open(struct vm_area_struct *vma)
* Return: 0 on success, -EACCES otherwise
*/
int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
- unsigned long end, unsigned long vm_flags)
+ unsigned long end, vm_flags_t vm_flags)
{
- unsigned long vm_prot_bits = vm_flags & VM_ACCESS_FLAGS;
+ vm_flags_t vm_prot_bits = vm_flags & VM_ACCESS_FLAGS;
struct sgx_encl_page *page;
unsigned long count = 0;
int ret = 0;
@@ -605,7 +605,7 @@ static int sgx_encl_debug_write(struct sgx_encl *encl, struct sgx_encl_page *pag
*/
static struct sgx_encl_page *sgx_encl_reserve_page(struct sgx_encl *encl,
unsigned long addr,
- unsigned long vm_flags)
+ vm_flags_t vm_flags)
{
struct sgx_encl_page *entry;
diff --git a/arch/x86/kernel/cpu/sgx/encl.h b/arch/x86/kernel/cpu/sgx/encl.h
index f94ff14c9486..8ff47f6652b9 100644
--- a/arch/x86/kernel/cpu/sgx/encl.h
+++ b/arch/x86/kernel/cpu/sgx/encl.h
@@ -101,7 +101,7 @@ static inline int sgx_encl_find(struct mm_struct *mm, unsigned long addr,
}
int sgx_encl_may_map(struct sgx_encl *encl, unsigned long start,
- unsigned long end, unsigned long vm_flags);
+ unsigned long end, vm_flags_t vm_flags);
bool current_is_ksgxd(void);
void sgx_encl_release(struct kref *ref);
diff --git a/arch/x86/kernel/cpu/sgx/ioctl.c b/arch/x86/kernel/cpu/sgx/ioctl.c
index 776a20172867..66f1efa16fbb 100644
--- a/arch/x86/kernel/cpu/sgx/ioctl.c
+++ b/arch/x86/kernel/cpu/sgx/ioctl.c
@@ -3,6 +3,7 @@
#include <asm/mman.h>
#include <asm/sgx.h>
+#include <crypto/sha2.h>
#include <linux/mman.h>
#include <linux/delay.h>
#include <linux/file.h>
@@ -463,31 +464,6 @@ static long sgx_ioc_enclave_add_pages(struct sgx_encl *encl, void __user *arg)
return ret;
}
-static int __sgx_get_key_hash(struct crypto_shash *tfm, const void *modulus,
- void *hash)
-{
- SHASH_DESC_ON_STACK(shash, tfm);
-
- shash->tfm = tfm;
-
- return crypto_shash_digest(shash, modulus, SGX_MODULUS_SIZE, hash);
-}
-
-static int sgx_get_key_hash(const void *modulus, void *hash)
-{
- struct crypto_shash *tfm;
- int ret;
-
- tfm = crypto_alloc_shash("sha256", 0, CRYPTO_ALG_ASYNC);
- if (IS_ERR(tfm))
- return PTR_ERR(tfm);
-
- ret = __sgx_get_key_hash(tfm, modulus, hash);
-
- crypto_free_shash(tfm);
- return ret;
-}
-
static int sgx_encl_init(struct sgx_encl *encl, struct sgx_sigstruct *sigstruct,
void *token)
{
@@ -523,9 +499,7 @@ static int sgx_encl_init(struct sgx_encl *encl, struct sgx_sigstruct *sigstruct,
sgx_xfrm_reserved_mask)
return -EINVAL;
- ret = sgx_get_key_hash(sigstruct->modulus, mrsigner);
- if (ret)
- return ret;
+ sha256(sigstruct->modulus, SGX_MODULUS_SIZE, (u8 *)mrsigner);
mutex_lock(&encl->lock);
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 8ce352fc72ac..2de01b379aa3 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -14,6 +14,7 @@
#include <linux/slab.h>
#include <linux/sysfs.h>
#include <linux/vmalloc.h>
+#include <asm/msr.h>
#include <asm/sgx.h>
#include "driver.h"
#include "encl.h"
@@ -719,6 +720,8 @@ int arch_memory_failure(unsigned long pfn, int flags)
goto out;
}
+ sgx_unmark_page_reclaimable(page);
+
/*
* TBD: Add additional plumbing to enable pre-emptive
* action for asynchronous poison notification. Until
@@ -871,7 +874,7 @@ void sgx_update_lepubkeyhash(u64 *lepubkeyhash)
WARN_ON_ONCE(preemptible());
for (i = 0; i < 4; i++)
- wrmsrl(MSR_IA32_SGXLEPUBKEYHASH0 + i, lepubkeyhash[i]);
+ wrmsrq(MSR_IA32_SGXLEPUBKEYHASH0 + i, lepubkeyhash[i]);
}
const struct file_operations sgx_provision_fops = {
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 01456236a6dd..e35ccdc84910 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -30,6 +30,7 @@
#include <asm/hypervisor.h>
#include <asm/io_apic.h>
#include <asm/mpspec.h>
+#include <asm/msr.h>
#include <asm/smp.h>
#include "cpu.h"
@@ -154,7 +155,7 @@ static __init bool check_for_real_bsp(u32 apic_id)
* kernel must rely on the firmware enumeration order.
*/
if (has_apic_base) {
- rdmsrl(MSR_IA32_APICBASE, msr);
+ rdmsrq(MSR_IA32_APICBASE, msr);
is_bsp = !!(msr & MSR_IA32_APICBASE_BSP);
}
diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c
index 03b3c9c3a45e..843b1655ab45 100644
--- a/arch/x86/kernel/cpu/topology_amd.c
+++ b/arch/x86/kernel/cpu/topology_amd.c
@@ -3,6 +3,7 @@
#include <asm/apic.h>
#include <asm/memtype.h>
+#include <asm/msr.h>
#include <asm/processor.h>
#include "cpu.h"
@@ -133,7 +134,7 @@ static void parse_fam10h_node_id(struct topo_scan *tscan)
if (!boot_cpu_has(X86_FEATURE_NODEID_MSR))
return;
- rdmsrl(MSR_FAM10H_NODE_ID, nid.msr);
+ rdmsrq(MSR_FAM10H_NODE_ID, nid.msr);
store_node(tscan, nid.nodes_per_pkg + 1, nid.node_id);
tscan->c->topo.llc_id = nid.node_id;
}
@@ -160,7 +161,7 @@ static void topoext_fixup(struct topo_scan *tscan)
if (msr_set_bit(0xc0011005, 54) <= 0)
return;
- rdmsrl(0xc0011005, msrval);
+ rdmsrq(0xc0011005, msrval);
if (msrval & BIT_64(54)) {
set_cpu_cap(c, X86_FEATURE_TOPOEXT);
pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n");
@@ -182,7 +183,7 @@ static void parse_topology_amd(struct topo_scan *tscan)
if (cpu_feature_enabled(X86_FEATURE_TOPOEXT))
has_topoext = cpu_parse_topology_ext(tscan);
- if (cpu_feature_enabled(X86_FEATURE_AMD_HETEROGENEOUS_CORES))
+ if (cpu_feature_enabled(X86_FEATURE_AMD_HTR_CORES))
tscan->c->topo.cpu_type = cpuid_ebx(0x80000026);
if (!has_topoext && !parse_8000_0008(tscan))
diff --git a/arch/x86/kernel/cpu/tsx.c b/arch/x86/kernel/cpu/tsx.c
index b31ee4f1657a..49782724a943 100644
--- a/arch/x86/kernel/cpu/tsx.c
+++ b/arch/x86/kernel/cpu/tsx.c
@@ -12,6 +12,7 @@
#include <asm/cmdline.h>
#include <asm/cpu.h>
+#include <asm/msr.h>
#include "cpu.h"
@@ -24,7 +25,7 @@ static void tsx_disable(void)
{
u64 tsx;
- rdmsrl(MSR_IA32_TSX_CTRL, tsx);
+ rdmsrq(MSR_IA32_TSX_CTRL, tsx);
/* Force all transactions to immediately abort */
tsx |= TSX_CTRL_RTM_DISABLE;
@@ -37,14 +38,14 @@ static void tsx_disable(void)
*/
tsx |= TSX_CTRL_CPUID_CLEAR;
- wrmsrl(MSR_IA32_TSX_CTRL, tsx);
+ wrmsrq(MSR_IA32_TSX_CTRL, tsx);
}
static void tsx_enable(void)
{
u64 tsx;
- rdmsrl(MSR_IA32_TSX_CTRL, tsx);
+ rdmsrq(MSR_IA32_TSX_CTRL, tsx);
/* Enable the RTM feature in the cpu */
tsx &= ~TSX_CTRL_RTM_DISABLE;
@@ -56,7 +57,7 @@ static void tsx_enable(void)
*/
tsx &= ~TSX_CTRL_CPUID_CLEAR;
- wrmsrl(MSR_IA32_TSX_CTRL, tsx);
+ wrmsrq(MSR_IA32_TSX_CTRL, tsx);
}
static enum tsx_ctrl_states x86_get_tsx_auto_mode(void)
@@ -115,13 +116,13 @@ static void tsx_clear_cpuid(void)
*/
if (boot_cpu_has(X86_FEATURE_RTM_ALWAYS_ABORT) &&
boot_cpu_has(X86_FEATURE_TSX_FORCE_ABORT)) {
- rdmsrl(MSR_TSX_FORCE_ABORT, msr);
+ rdmsrq(MSR_TSX_FORCE_ABORT, msr);
msr |= MSR_TFA_TSX_CPUID_CLEAR;
- wrmsrl(MSR_TSX_FORCE_ABORT, msr);
+ wrmsrq(MSR_TSX_FORCE_ABORT, msr);
} else if (cpu_feature_enabled(X86_FEATURE_MSR_TSX_CTRL)) {
- rdmsrl(MSR_IA32_TSX_CTRL, msr);
+ rdmsrq(MSR_IA32_TSX_CTRL, msr);
msr |= TSX_CTRL_CPUID_CLEAR;
- wrmsrl(MSR_IA32_TSX_CTRL, msr);
+ wrmsrq(MSR_IA32_TSX_CTRL, msr);
}
}
@@ -146,11 +147,11 @@ static void tsx_dev_mode_disable(void)
!cpu_feature_enabled(X86_FEATURE_SRBDS_CTRL))
return;
- rdmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
+ rdmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
if (mcu_opt_ctrl & RTM_ALLOW) {
mcu_opt_ctrl &= ~RTM_ALLOW;
- wrmsrl(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
+ wrmsrq(MSR_IA32_MCU_OPT_CTRL, mcu_opt_ctrl);
setup_force_cpu_cap(X86_FEATURE_RTM_ALWAYS_ABORT);
}
}
diff --git a/arch/x86/kernel/cpu/umwait.c b/arch/x86/kernel/cpu/umwait.c
index 2293efd6ffa6..933fcd7ff250 100644
--- a/arch/x86/kernel/cpu/umwait.c
+++ b/arch/x86/kernel/cpu/umwait.c
@@ -33,7 +33,7 @@ static DEFINE_MUTEX(umwait_lock);
static void umwait_update_control_msr(void * unused)
{
lockdep_assert_irqs_disabled();
- wrmsr(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached), 0);
+ wrmsrq(MSR_IA32_UMWAIT_CONTROL, READ_ONCE(umwait_control_cached));
}
/*
@@ -71,7 +71,7 @@ static int umwait_cpu_offline(unsigned int cpu)
* the original control MSR value in umwait_init(). So there
* is no race condition here.
*/
- wrmsr(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached, 0);
+ wrmsrq(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached);
return 0;
}
@@ -214,7 +214,7 @@ static int __init umwait_init(void)
* changed. This is the only place where orig_umwait_control_cached
* is modified.
*/
- rdmsrl(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached);
+ rdmsrq(MSR_IA32_UMWAIT_CONTROL, orig_umwait_control_cached);
ret = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "umwait:online",
umwait_cpu_online, umwait_cpu_offline);
diff --git a/arch/x86/kernel/cpu/zhaoxin.c b/arch/x86/kernel/cpu/zhaoxin.c
index 90eba7eb5335..89b1c8a70fe8 100644
--- a/arch/x86/kernel/cpu/zhaoxin.c
+++ b/arch/x86/kernel/cpu/zhaoxin.c
@@ -4,6 +4,7 @@
#include <asm/cpu.h>
#include <asm/cpufeature.h>
+#include <asm/msr.h>
#include "cpu.h"
diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
index 0be61c45400c..c6b12bed173d 100644
--- a/arch/x86/kernel/crash.c
+++ b/arch/x86/kernel/crash.c
@@ -163,10 +163,10 @@ static struct crash_mem *fill_up_crash_elf_data(void)
return NULL;
/*
- * Exclusion of crash region and/or crashk_low_res may cause
- * another range split. So add extra two slots here.
+ * Exclusion of crash region, crashk_low_res and/or crashk_cma_ranges
+ * may cause range splits. So add extra slots here.
*/
- nr_ranges += 2;
+ nr_ranges += 2 + crashk_cma_cnt;
cmem = vzalloc(struct_size(cmem, ranges, nr_ranges));
if (!cmem)
return NULL;
@@ -184,6 +184,7 @@ static struct crash_mem *fill_up_crash_elf_data(void)
static int elf_header_exclude_ranges(struct crash_mem *cmem)
{
int ret = 0;
+ int i;
/* Exclude the low 1M because it is always reserved */
ret = crash_exclude_mem_range(cmem, 0, SZ_1M - 1);
@@ -198,8 +199,17 @@ static int elf_header_exclude_ranges(struct crash_mem *cmem)
if (crashk_low_res.end)
ret = crash_exclude_mem_range(cmem, crashk_low_res.start,
crashk_low_res.end);
+ if (ret)
+ return ret;
- return ret;
+ for (i = 0; i < crashk_cma_cnt; ++i) {
+ ret = crash_exclude_mem_range(cmem, crashk_cma_ranges[i].start,
+ crashk_cma_ranges[i].end);
+ if (ret)
+ return ret;
+ }
+
+ return 0;
}
static int prepare_elf64_ram_headers_callback(struct resource *res, void *arg)
@@ -278,6 +288,7 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem,
unsigned long long mend)
{
unsigned long start, end;
+ int ret;
cmem->ranges[0].start = mstart;
cmem->ranges[0].end = mend;
@@ -286,22 +297,43 @@ static int memmap_exclude_ranges(struct kimage *image, struct crash_mem *cmem,
/* Exclude elf header region */
start = image->elf_load_addr;
end = start + image->elf_headers_sz - 1;
- return crash_exclude_mem_range(cmem, start, end);
+ ret = crash_exclude_mem_range(cmem, start, end);
+
+ if (ret)
+ return ret;
+
+ /* Exclude dm crypt keys region */
+ if (image->dm_crypt_keys_addr) {
+ start = image->dm_crypt_keys_addr;
+ end = start + image->dm_crypt_keys_sz - 1;
+ return crash_exclude_mem_range(cmem, start, end);
+ }
+
+ return ret;
}
/* Prepare memory map for crash dump kernel */
int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
{
+ unsigned int nr_ranges = 0;
int i, ret = 0;
unsigned long flags;
struct e820_entry ei;
struct crash_memmap_data cmd;
struct crash_mem *cmem;
- cmem = vzalloc(struct_size(cmem, ranges, 1));
+ /*
+ * Using random kexec_buf for passing dm crypt keys may cause a range
+ * split. So use two slots here.
+ */
+ nr_ranges = 2;
+ cmem = vzalloc(struct_size(cmem, ranges, nr_ranges));
if (!cmem)
return -ENOMEM;
+ cmem->max_nr_ranges = nr_ranges;
+ cmem->nr_ranges = 0;
+
memset(&cmd, 0, sizeof(struct crash_memmap_data));
cmd.params = params;
@@ -352,6 +384,14 @@ int crash_setup_memmap_entries(struct kimage *image, struct boot_params *params)
add_e820_entry(params, &ei);
}
+ for (i = 0; i < crashk_cma_cnt; ++i) {
+ ei.addr = crashk_cma_ranges[i].start;
+ ei.size = crashk_cma_ranges[i].end -
+ crashk_cma_ranges[i].start + 1;
+ ei.type = E820_TYPE_RAM;
+ add_e820_entry(params, &ei);
+ }
+
out:
vfree(cmem);
return ret;
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index c6fefd4585f8..71ee20102a8a 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -23,8 +23,6 @@
#include <asm/stacktrace.h>
#include <asm/unwind.h>
-int panic_on_unrecovered_nmi;
-int panic_on_io_nmi;
static int die_counter;
static struct pt_regs exec_summary_regs;
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 9920122018a0..c3acbd26408b 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -1300,6 +1300,24 @@ void __init e820__memblock_setup(void)
}
/*
+ * At this point memblock is only allowed to allocate from memory
+ * below 1M (aka ISA_END_ADDRESS) up until direct map is completely set
+ * up in init_mem_mapping().
+ *
+ * KHO kernels are special and use only scratch memory for memblock
+ * allocations, but memory below 1M is ignored by kernel after early
+ * boot and cannot be naturally marked as scratch.
+ *
+ * To allow allocation of the real-mode trampoline and a few (if any)
+ * other very early allocations from below 1M forcibly mark the memory
+ * below 1M as scratch.
+ *
+ * After real mode trampoline is allocated, we clear that scratch
+ * marking.
+ */
+ memblock_mark_kho_scratch(0, SZ_1M);
+
+ /*
* 32-bit systems are limited to 4BG of memory even with HIGHMEM and
* to even less without it.
* Discard memory after max_pfn - the actual limit detected at runtime.
diff --git a/arch/x86/kernel/early_printk.c b/arch/x86/kernel/early_printk.c
index 3aad78bfcb26..cba75306e5b6 100644
--- a/arch/x86/kernel/early_printk.c
+++ b/arch/x86/kernel/early_printk.c
@@ -1,6 +1,7 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/console.h>
#include <linux/kernel.h>
+#include <linux/kexec.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/screen_info.h>
@@ -144,6 +145,11 @@ static __init void early_serial_hw_init(unsigned divisor)
static_call(serial_out)(early_serial_base, DLL, divisor & 0xff);
static_call(serial_out)(early_serial_base, DLH, (divisor >> 8) & 0xff);
static_call(serial_out)(early_serial_base, LCR, c & ~DLAB);
+
+#if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_X86_64)
+ if (static_call_query(serial_in) == io_serial_in)
+ kexec_debug_8250_port = early_serial_base;
+#endif
}
#define DEFAULT_BAUD 9600
@@ -327,6 +333,9 @@ static __init void early_pci_serial_init(char *s)
/* WARNING! assuming the address is always in the first 4G */
early_serial_base =
(unsigned long)early_ioremap(bar0 & PCI_BASE_ADDRESS_MEM_MASK, 0x10);
+#if defined(CONFIG_KEXEC_CORE) && defined(CONFIG_X86_64)
+ kexec_debug_8250_mmio32 = bar0 & PCI_BASE_ADDRESS_MEM_MASK;
+#endif
write_pci_config(bus, slot, func, PCI_COMMAND,
cmdreg|PCI_COMMAND_MEMORY);
}
diff --git a/arch/x86/kernel/fpu/context.h b/arch/x86/kernel/fpu/context.h
index f6d856bd50bc..10d0a720659c 100644
--- a/arch/x86/kernel/fpu/context.h
+++ b/arch/x86/kernel/fpu/context.h
@@ -53,7 +53,7 @@ static inline void fpregs_activate(struct fpu *fpu)
/* Internal helper for switch_fpu_return() and signal frame setup */
static inline void fpregs_restore_userregs(void)
{
- struct fpu *fpu = &current->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current);
int cpu = smp_processor_id();
if (WARN_ON_ONCE(current->flags & (PF_KTHREAD | PF_USER_WORKER)))
@@ -67,7 +67,7 @@ static inline void fpregs_restore_userregs(void)
* If PKRU is enabled, then the PKRU value is already
* correct because it was either set in switch_to() or in
* flush_thread(). So it is excluded because it might be
- * not up to date in current->thread.fpu.xsave state.
+ * not up to date in current->thread.fpu->xsave state.
*
* XFD state is handled in restore_fpregs_from_fpstate().
*/
diff --git a/arch/x86/kernel/fpu/core.c b/arch/x86/kernel/fpu/core.c
index 91d6341f281f..aefd412a23dc 100644
--- a/arch/x86/kernel/fpu/core.c
+++ b/arch/x86/kernel/fpu/core.c
@@ -11,6 +11,7 @@
#include <asm/fpu/sched.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/types.h>
+#include <asm/msr.h>
#include <asm/traps.h>
#include <asm/irq_regs.h>
@@ -36,6 +37,7 @@ DEFINE_PER_CPU(u64, xfd_state);
/* The FPU state configuration data for kernel and user space */
struct fpu_state_config fpu_kernel_cfg __ro_after_init;
struct fpu_state_config fpu_user_cfg __ro_after_init;
+struct vcpu_fpu_config guest_default_cfg __ro_after_init;
/*
* Represents the initial FPU state. It's mostly (but not completely) zeroes,
@@ -43,14 +45,27 @@ struct fpu_state_config fpu_user_cfg __ro_after_init;
*/
struct fpstate init_fpstate __ro_after_init;
-/* Track in-kernel FPU usage */
-static DEFINE_PER_CPU(bool, in_kernel_fpu);
+/*
+ * Track FPU initialization and kernel-mode usage. 'true' means the FPU is
+ * initialized and is not currently being used by the kernel:
+ */
+DEFINE_PER_CPU(bool, kernel_fpu_allowed);
/*
* Track which context is using the FPU on the CPU:
*/
DEFINE_PER_CPU(struct fpu *, fpu_fpregs_owner_ctx);
+#ifdef CONFIG_X86_DEBUG_FPU
+struct fpu *x86_task_fpu(struct task_struct *task)
+{
+ if (WARN_ON_ONCE(task->flags & PF_KTHREAD))
+ return NULL;
+
+ return (void *)task + sizeof(*task);
+}
+#endif
+
/*
* Can we use the FPU in kernel mode with the
* whole "kernel_fpu_begin/end()" sequence?
@@ -61,15 +76,18 @@ bool irq_fpu_usable(void)
return false;
/*
- * In kernel FPU usage already active? This detects any explicitly
- * nested usage in task or softirq context, which is unsupported. It
- * also detects attempted usage in a hardirq that has interrupted a
- * kernel-mode FPU section.
+ * Return false in the following cases:
+ *
+ * - FPU is not yet initialized. This can happen only when the call is
+ * coming from CPU onlining, for example for microcode checksumming.
+ * - The kernel is already using the FPU, either because of explicit
+ * nesting (which should never be done), or because of implicit
+ * nesting when a hardirq interrupted a kernel-mode FPU section.
+ *
+ * The single boolean check below handles both cases:
*/
- if (this_cpu_read(in_kernel_fpu)) {
- WARN_ON_FPU(!in_hardirq());
+ if (!this_cpu_read(kernel_fpu_allowed))
return false;
- }
/*
* When not in NMI or hard interrupt context, FPU can be used in:
@@ -200,9 +218,9 @@ void fpu_reset_from_exception_fixup(void)
}
#if IS_ENABLED(CONFIG_KVM)
-static void __fpstate_reset(struct fpstate *fpstate, u64 xfd);
+static void __fpstate_reset(struct fpstate *fpstate);
-static void fpu_init_guest_permissions(struct fpu_guest *gfpu)
+static void fpu_lock_guest_permissions(void)
{
struct fpu_state_perm *fpuperm;
u64 perm;
@@ -211,15 +229,13 @@ static void fpu_init_guest_permissions(struct fpu_guest *gfpu)
return;
spin_lock_irq(&current->sighand->siglock);
- fpuperm = &current->group_leader->thread.fpu.guest_perm;
+ fpuperm = &x86_task_fpu(current->group_leader)->guest_perm;
perm = fpuperm->__state_perm;
/* First fpstate allocation locks down permissions. */
WRITE_ONCE(fpuperm->__state_perm, perm | FPU_GUEST_PERM_LOCKED);
spin_unlock_irq(&current->sighand->siglock);
-
- gfpu->perm = perm & ~FPU_GUEST_PERM_LOCKED;
}
bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
@@ -227,20 +243,21 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
struct fpstate *fpstate;
unsigned int size;
- size = fpu_kernel_cfg.default_size + ALIGN(offsetof(struct fpstate, regs), 64);
+ size = guest_default_cfg.size + ALIGN(offsetof(struct fpstate, regs), 64);
+
fpstate = vzalloc(size);
if (!fpstate)
return false;
- /* Leave xfd to 0 (the reset value defined by spec) */
- __fpstate_reset(fpstate, 0);
- fpstate_init_user(fpstate);
+ /* Initialize indicators to reflect properties of the fpstate */
fpstate->is_valloc = true;
fpstate->is_guest = true;
+ __fpstate_reset(fpstate);
+ fpstate_init_user(fpstate);
+
gfpu->fpstate = fpstate;
- gfpu->xfeatures = fpu_kernel_cfg.default_features;
- gfpu->perm = fpu_kernel_cfg.default_features;
+ gfpu->xfeatures = guest_default_cfg.features;
/*
* KVM sets the FP+SSE bits in the XSAVE header when copying FPU state
@@ -255,7 +272,7 @@ bool fpu_alloc_guest_fpstate(struct fpu_guest *gfpu)
if (WARN_ON_ONCE(fpu_user_cfg.default_size > gfpu->uabi_size))
gfpu->uabi_size = fpu_user_cfg.default_size;
- fpu_init_guest_permissions(gfpu);
+ fpu_lock_guest_permissions();
return true;
}
@@ -263,16 +280,16 @@ EXPORT_SYMBOL_GPL(fpu_alloc_guest_fpstate);
void fpu_free_guest_fpstate(struct fpu_guest *gfpu)
{
- struct fpstate *fps = gfpu->fpstate;
+ struct fpstate *fpstate = gfpu->fpstate;
- if (!fps)
+ if (!fpstate)
return;
- if (WARN_ON_ONCE(!fps->is_valloc || !fps->is_guest || fps->in_use))
+ if (WARN_ON_ONCE(!fpstate->is_valloc || !fpstate->is_guest || fpstate->in_use))
return;
gfpu->fpstate = NULL;
- vfree(fps);
+ vfree(fpstate);
}
EXPORT_SYMBOL_GPL(fpu_free_guest_fpstate);
@@ -323,12 +340,12 @@ EXPORT_SYMBOL_GPL(fpu_update_guest_xfd);
*/
void fpu_sync_guest_vmexit_xfd_state(void)
{
- struct fpstate *fps = current->thread.fpu.fpstate;
+ struct fpstate *fpstate = x86_task_fpu(current)->fpstate;
lockdep_assert_irqs_disabled();
if (fpu_state_size_dynamic()) {
- rdmsrl(MSR_IA32_XFD, fps->xfd);
- __this_cpu_write(xfd_state, fps->xfd);
+ rdmsrq(MSR_IA32_XFD, fpstate->xfd);
+ __this_cpu_write(xfd_state, fpstate->xfd);
}
}
EXPORT_SYMBOL_GPL(fpu_sync_guest_vmexit_xfd_state);
@@ -337,7 +354,7 @@ EXPORT_SYMBOL_GPL(fpu_sync_guest_vmexit_xfd_state);
int fpu_swap_kvm_fpstate(struct fpu_guest *guest_fpu, bool enter_guest)
{
struct fpstate *guest_fps = guest_fpu->fpstate;
- struct fpu *fpu = &current->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current);
struct fpstate *cur_fps = fpu->fpstate;
fpregs_lock();
@@ -431,14 +448,15 @@ void kernel_fpu_begin_mask(unsigned int kfpu_mask)
fpregs_lock();
WARN_ON_FPU(!irq_fpu_usable());
- WARN_ON_FPU(this_cpu_read(in_kernel_fpu));
- this_cpu_write(in_kernel_fpu, true);
+ /* Toggle kernel_fpu_allowed to false: */
+ WARN_ON_FPU(!this_cpu_read(kernel_fpu_allowed));
+ this_cpu_write(kernel_fpu_allowed, false);
if (!(current->flags & (PF_KTHREAD | PF_USER_WORKER)) &&
!test_thread_flag(TIF_NEED_FPU_LOAD)) {
set_thread_flag(TIF_NEED_FPU_LOAD);
- save_fpregs_to_fpstate(&current->thread.fpu);
+ save_fpregs_to_fpstate(x86_task_fpu(current));
}
__cpu_invalidate_fpregs_state();
@@ -453,9 +471,10 @@ EXPORT_SYMBOL_GPL(kernel_fpu_begin_mask);
void kernel_fpu_end(void)
{
- WARN_ON_FPU(!this_cpu_read(in_kernel_fpu));
+ /* Toggle kernel_fpu_allowed back to true: */
+ WARN_ON_FPU(this_cpu_read(kernel_fpu_allowed));
+ this_cpu_write(kernel_fpu_allowed, true);
- this_cpu_write(in_kernel_fpu, false);
if (!irqs_disabled())
fpregs_unlock();
}
@@ -467,7 +486,7 @@ EXPORT_SYMBOL_GPL(kernel_fpu_end);
*/
void fpu_sync_fpstate(struct fpu *fpu)
{
- WARN_ON_FPU(fpu != &current->thread.fpu);
+ WARN_ON_FPU(fpu != x86_task_fpu(current));
fpregs_lock();
trace_x86_fpu_before_save(fpu);
@@ -525,34 +544,56 @@ void fpstate_init_user(struct fpstate *fpstate)
fpstate_init_fstate(fpstate);
}
-static void __fpstate_reset(struct fpstate *fpstate, u64 xfd)
+static void __fpstate_reset(struct fpstate *fpstate)
{
- /* Initialize sizes and feature masks */
- fpstate->size = fpu_kernel_cfg.default_size;
+ /*
+ * Supervisor features (and thus sizes) may diverge between guest
+ * FPUs and host FPUs, as some supervisor features are supported
+ * for guests despite not being utilized by the host. User
+ * features and sizes are always identical, which allows for
+ * common guest and userspace ABI.
+ *
+ * For the host, set XFD to the kernel's desired initialization
+ * value. For guests, set XFD to its architectural RESET value.
+ */
+ if (fpstate->is_guest) {
+ fpstate->size = guest_default_cfg.size;
+ fpstate->xfeatures = guest_default_cfg.features;
+ fpstate->xfd = 0;
+ } else {
+ fpstate->size = fpu_kernel_cfg.default_size;
+ fpstate->xfeatures = fpu_kernel_cfg.default_features;
+ fpstate->xfd = init_fpstate.xfd;
+ }
+
fpstate->user_size = fpu_user_cfg.default_size;
- fpstate->xfeatures = fpu_kernel_cfg.default_features;
fpstate->user_xfeatures = fpu_user_cfg.default_features;
- fpstate->xfd = xfd;
}
void fpstate_reset(struct fpu *fpu)
{
/* Set the fpstate pointer to the default fpstate */
fpu->fpstate = &fpu->__fpstate;
- __fpstate_reset(fpu->fpstate, init_fpstate.xfd);
+ __fpstate_reset(fpu->fpstate);
/* Initialize the permission related info in fpu */
fpu->perm.__state_perm = fpu_kernel_cfg.default_features;
fpu->perm.__state_size = fpu_kernel_cfg.default_size;
fpu->perm.__user_state_size = fpu_user_cfg.default_size;
- /* Same defaults for guests */
- fpu->guest_perm = fpu->perm;
+
+ fpu->guest_perm.__state_perm = guest_default_cfg.features;
+ fpu->guest_perm.__state_size = guest_default_cfg.size;
+ /*
+ * User features and sizes are always identical between host and
+ * guest FPUs, which allows for common guest and userspace ABI.
+ */
+ fpu->guest_perm.__user_state_size = fpu_user_cfg.default_size;
}
static inline void fpu_inherit_perms(struct fpu *dst_fpu)
{
if (fpu_state_size_dynamic()) {
- struct fpu *src_fpu = &current->group_leader->thread.fpu;
+ struct fpu *src_fpu = x86_task_fpu(current->group_leader);
spin_lock_irq(&current->sighand->siglock);
/* Fork also inherits the permissions of the parent */
@@ -572,7 +613,7 @@ static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp)
if (!ssp)
return 0;
- xstate = get_xsave_addr(&dst->thread.fpu.fpstate->regs.xsave,
+ xstate = get_xsave_addr(&x86_task_fpu(dst)->fpstate->regs.xsave,
XFEATURE_CET_USER);
/*
@@ -593,8 +634,16 @@ static int update_fpu_shstk(struct task_struct *dst, unsigned long ssp)
int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
unsigned long ssp)
{
- struct fpu *src_fpu = &current->thread.fpu;
- struct fpu *dst_fpu = &dst->thread.fpu;
+ /*
+ * We allocate the new FPU structure right after the end of the task struct.
+ * task allocation size already took this into account.
+ *
+ * This is safe because task_struct size is a multiple of cacheline size,
+ * thus x86_task_fpu() will always be cacheline aligned as well.
+ */
+ struct fpu *dst_fpu = (void *)dst + sizeof(*dst);
+
+ BUILD_BUG_ON(sizeof(*dst) % SMP_CACHE_BYTES != 0);
/* The new task's FPU state cannot be valid in the hardware. */
dst_fpu->last_cpu = -1;
@@ -657,19 +706,22 @@ int fpu_clone(struct task_struct *dst, unsigned long clone_flags, bool minimal,
if (update_fpu_shstk(dst, ssp))
return 1;
- trace_x86_fpu_copy_src(src_fpu);
trace_x86_fpu_copy_dst(dst_fpu);
return 0;
}
/*
- * Whitelist the FPU register state embedded into task_struct for hardened
- * usercopy.
+ * While struct fpu is no longer part of struct thread_struct, it is still
+ * allocated after struct task_struct in the "task_struct" kmem cache. But
+ * since FPU is expected to be part of struct thread_struct, we have to
+ * adjust for it here.
*/
void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
{
- *offset = offsetof(struct thread_struct, fpu.__fpstate.regs);
+ /* The allocation follows struct task_struct. */
+ *offset = sizeof(struct task_struct) - offsetof(struct task_struct, thread);
+ *offset += offsetof(struct fpu, __fpstate.regs);
*size = fpu_kernel_cfg.default_size;
}
@@ -682,11 +734,18 @@ void fpu_thread_struct_whitelist(unsigned long *offset, unsigned long *size)
* a state-restore is coming: either an explicit one,
* or a reschedule.
*/
-void fpu__drop(struct fpu *fpu)
+void fpu__drop(struct task_struct *tsk)
{
+ struct fpu *fpu;
+
+ if (test_tsk_thread_flag(tsk, TIF_NEED_FPU_LOAD))
+ return;
+
+ fpu = x86_task_fpu(tsk);
+
preempt_disable();
- if (fpu == &current->thread.fpu) {
+ if (fpu == x86_task_fpu(current)) {
/* Ignore delayed exceptions from user space */
asm volatile("1: fwait\n"
"2:\n"
@@ -718,9 +777,9 @@ static inline void restore_fpregs_from_init_fpstate(u64 features_mask)
/*
* Reset current->fpu memory state to the init values.
*/
-static void fpu_reset_fpregs(void)
+static void fpu_reset_fpstate_regs(void)
{
- struct fpu *fpu = &current->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current);
fpregs_lock();
__fpu_invalidate_fpregs_state(fpu);
@@ -749,11 +808,11 @@ static void fpu_reset_fpregs(void)
*/
void fpu__clear_user_states(struct fpu *fpu)
{
- WARN_ON_FPU(fpu != &current->thread.fpu);
+ WARN_ON_FPU(fpu != x86_task_fpu(current));
fpregs_lock();
if (!cpu_feature_enabled(X86_FEATURE_FPU)) {
- fpu_reset_fpregs();
+ fpu_reset_fpstate_regs();
fpregs_unlock();
return;
}
@@ -782,8 +841,8 @@ void fpu__clear_user_states(struct fpu *fpu)
void fpu_flush_thread(void)
{
- fpstate_reset(&current->thread.fpu);
- fpu_reset_fpregs();
+ fpstate_reset(x86_task_fpu(current));
+ fpu_reset_fpstate_regs();
}
/*
* Load FPU context before returning to userspace.
@@ -823,7 +882,7 @@ void fpregs_lock_and_load(void)
*/
void fpregs_assert_state_consistent(void)
{
- struct fpu *fpu = &current->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current);
if (test_thread_flag(TIF_NEED_FPU_LOAD))
return;
@@ -835,7 +894,7 @@ EXPORT_SYMBOL_GPL(fpregs_assert_state_consistent);
void fpregs_mark_activate(void)
{
- struct fpu *fpu = &current->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current);
fpregs_activate(fpu);
fpu->last_cpu = smp_processor_id();
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 998a08f17e33..ff988b9ea39f 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -38,7 +38,7 @@ static void fpu__init_cpu_generic(void)
/* Flush out any pending x87 state: */
#ifdef CONFIG_MATH_EMULATION
if (!boot_cpu_has(X86_FEATURE_FPU))
- fpstate_init_soft(&current->thread.fpu.fpstate->regs.soft);
+ ;
else
#endif
asm volatile ("fninit");
@@ -51,6 +51,9 @@ void fpu__init_cpu(void)
{
fpu__init_cpu_generic();
fpu__init_cpu_xstate();
+
+ /* Start allowing kernel-mode FPU: */
+ this_cpu_write(kernel_fpu_allowed, true);
}
static bool __init fpu__probe_without_cpuid(void)
@@ -73,6 +76,8 @@ static bool __init fpu__probe_without_cpuid(void)
static void __init fpu__init_system_early_generic(void)
{
+ set_thread_flag(TIF_NEED_FPU_LOAD);
+
if (!boot_cpu_has(X86_FEATURE_CPUID) &&
!test_bit(X86_FEATURE_FPU, (unsigned long *)cpu_caps_cleared)) {
if (fpu__probe_without_cpuid())
@@ -94,7 +99,6 @@ static void __init fpu__init_system_early_generic(void)
* Boot time FPU feature detection code:
*/
unsigned int mxcsr_feature_mask __ro_after_init = 0xffffffffu;
-EXPORT_SYMBOL_GPL(mxcsr_feature_mask);
static void __init fpu__init_system_mxcsr(void)
{
@@ -150,11 +154,13 @@ static void __init fpu__init_task_struct_size(void)
{
int task_size = sizeof(struct task_struct);
+ task_size += sizeof(struct fpu);
+
/*
* Subtract off the static size of the register state.
* It potentially has a bunch of padding.
*/
- task_size -= sizeof(current->thread.fpu.__fpstate.regs);
+ task_size -= sizeof(union fpregs_state);
/*
* Add back the dynamically-calculated register state
@@ -164,14 +170,9 @@ static void __init fpu__init_task_struct_size(void)
/*
* We dynamically size 'struct fpu', so we require that
- * it be at the end of 'thread_struct' and that
- * 'thread_struct' be at the end of 'task_struct'. If
- * you hit a compile error here, check the structure to
- * see if something got added to the end.
+ * 'state' be at the end of 'it:
*/
CHECK_MEMBER_AT_END_OF(struct fpu, __fpstate);
- CHECK_MEMBER_AT_END_OF(struct thread_struct, fpu);
- CHECK_MEMBER_AT_END_OF(struct task_struct, thread);
arch_task_struct_size = task_size;
}
@@ -204,7 +205,7 @@ static void __init fpu__init_system_xstate_size_legacy(void)
fpu_kernel_cfg.default_size = size;
fpu_user_cfg.max_size = size;
fpu_user_cfg.default_size = size;
- fpstate_reset(&current->thread.fpu);
+ guest_default_cfg.size = size;
}
/*
@@ -213,7 +214,6 @@ static void __init fpu__init_system_xstate_size_legacy(void)
*/
void __init fpu__init_system(void)
{
- fpstate_reset(&current->thread.fpu);
fpu__init_system_early_generic();
/*
diff --git a/arch/x86/kernel/fpu/regset.c b/arch/x86/kernel/fpu/regset.c
index 887b0b8e21e3..0986c2200adc 100644
--- a/arch/x86/kernel/fpu/regset.c
+++ b/arch/x86/kernel/fpu/regset.c
@@ -45,7 +45,7 @@ int regset_xregset_fpregs_active(struct task_struct *target, const struct user_r
*/
static void sync_fpstate(struct fpu *fpu)
{
- if (fpu == &current->thread.fpu)
+ if (fpu == x86_task_fpu(current))
fpu_sync_fpstate(fpu);
}
@@ -63,7 +63,7 @@ static void fpu_force_restore(struct fpu *fpu)
* Only stopped child tasks can be used to modify the FPU
* state in the fpstate buffer:
*/
- WARN_ON_FPU(fpu == &current->thread.fpu);
+ WARN_ON_FPU(fpu == x86_task_fpu(current));
__fpu_invalidate_fpregs_state(fpu);
}
@@ -71,7 +71,7 @@ static void fpu_force_restore(struct fpu *fpu)
int xfpregs_get(struct task_struct *target, const struct user_regset *regset,
struct membuf to)
{
- struct fpu *fpu = &target->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(target);
if (!cpu_feature_enabled(X86_FEATURE_FXSR))
return -ENODEV;
@@ -91,7 +91,7 @@ int xfpregs_set(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct fpu *fpu = &target->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(target);
struct fxregs_state newstate;
int ret;
@@ -133,7 +133,7 @@ int xstateregs_get(struct task_struct *target, const struct user_regset *regset,
if (!cpu_feature_enabled(X86_FEATURE_XSAVE))
return -ENODEV;
- sync_fpstate(&target->thread.fpu);
+ sync_fpstate(x86_task_fpu(target));
copy_xstate_to_uabi_buf(to, target, XSTATE_COPY_XSAVE);
return 0;
@@ -143,7 +143,7 @@ int xstateregs_set(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct fpu *fpu = &target->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(target);
struct xregs_state *tmpbuf = NULL;
int ret;
@@ -187,7 +187,7 @@ int ssp_active(struct task_struct *target, const struct user_regset *regset)
int ssp_get(struct task_struct *target, const struct user_regset *regset,
struct membuf to)
{
- struct fpu *fpu = &target->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(target);
struct cet_user_state *cetregs;
if (!cpu_feature_enabled(X86_FEATURE_USER_SHSTK) ||
@@ -214,7 +214,7 @@ int ssp_set(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct fpu *fpu = &target->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(target);
struct xregs_state *xsave = &fpu->fpstate->regs.xsave;
struct cet_user_state *cetregs;
unsigned long user_ssp;
@@ -368,7 +368,7 @@ static void __convert_from_fxsr(struct user_i387_ia32_struct *env,
void
convert_from_fxsr(struct user_i387_ia32_struct *env, struct task_struct *tsk)
{
- __convert_from_fxsr(env, tsk, &tsk->thread.fpu.fpstate->regs.fxsave);
+ __convert_from_fxsr(env, tsk, &x86_task_fpu(tsk)->fpstate->regs.fxsave);
}
void convert_to_fxsr(struct fxregs_state *fxsave,
@@ -401,7 +401,7 @@ void convert_to_fxsr(struct fxregs_state *fxsave,
int fpregs_get(struct task_struct *target, const struct user_regset *regset,
struct membuf to)
{
- struct fpu *fpu = &target->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(target);
struct user_i387_ia32_struct env;
struct fxregs_state fxsave, *fx;
@@ -433,7 +433,7 @@ int fpregs_set(struct task_struct *target, const struct user_regset *regset,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct fpu *fpu = &target->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(target);
struct user_i387_ia32_struct env;
int ret;
diff --git a/arch/x86/kernel/fpu/signal.c b/arch/x86/kernel/fpu/signal.c
index 6c69cb28b298..c3ec2512f2bb 100644
--- a/arch/x86/kernel/fpu/signal.c
+++ b/arch/x86/kernel/fpu/signal.c
@@ -43,13 +43,13 @@ static inline bool check_xstate_in_sigframe(struct fxregs_state __user *fxbuf,
* fpstate layout with out copying the extended state information
* in the memory layout.
*/
- if (__get_user(magic2, (__u32 __user *)(fpstate + current->thread.fpu.fpstate->user_size)))
+ if (__get_user(magic2, (__u32 __user *)(fpstate + x86_task_fpu(current)->fpstate->user_size)))
return false;
if (likely(magic2 == FP_XSTATE_MAGIC2))
return true;
setfx:
- trace_x86_fpu_xstate_check_failed(&current->thread.fpu);
+ trace_x86_fpu_xstate_check_failed(x86_task_fpu(current));
/* Set the parameters for fx only state */
fx_sw->magic1 = 0;
@@ -64,13 +64,13 @@ setfx:
static inline bool save_fsave_header(struct task_struct *tsk, void __user *buf)
{
if (use_fxsr()) {
- struct xregs_state *xsave = &tsk->thread.fpu.fpstate->regs.xsave;
+ struct xregs_state *xsave = &x86_task_fpu(tsk)->fpstate->regs.xsave;
struct user_i387_ia32_struct env;
struct _fpstate_32 __user *fp = buf;
fpregs_lock();
if (!test_thread_flag(TIF_NEED_FPU_LOAD))
- fxsave(&tsk->thread.fpu.fpstate->regs.fxsave);
+ fxsave(&x86_task_fpu(tsk)->fpstate->regs.fxsave);
fpregs_unlock();
convert_from_fxsr(&env, tsk);
@@ -114,7 +114,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
{
struct xregs_state __user *x = buf;
struct _fpx_sw_bytes sw_bytes = {};
- u32 xfeatures;
int err;
/* Setup the bytes not touched by the [f]xsave and reserved for SW. */
@@ -128,12 +127,6 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
(__u32 __user *)(buf + fpstate->user_size));
/*
- * Read the xfeatures which we copied (directly from the cpu or
- * from the state in task struct) to the user buffers.
- */
- err |= __get_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
-
- /*
* For legacy compatible, we always set FP/SSE bits in the bit
* vector while saving the state to the user context. This will
* enable us capturing any changes(during sigreturn) to
@@ -144,9 +137,7 @@ static inline bool save_xstate_epilog(void __user *buf, int ia32_frame,
* header as well as change any contents in the memory layout.
* xrestore as part of sigreturn will capture all the changes.
*/
- xfeatures |= XFEATURE_MASK_FPSSE;
-
- err |= __put_user(xfeatures, (__u32 __user *)&x->header.xfeatures);
+ err |= set_xfeature_in_sigframe(x, XFEATURE_MASK_FPSSE);
return !err;
}
@@ -184,7 +175,7 @@ static inline int copy_fpregs_to_sigframe(struct xregs_state __user *buf, u32 pk
bool copy_fpstate_to_sigframe(void __user *buf, void __user *buf_fx, int size, u32 pkru)
{
struct task_struct *tsk = current;
- struct fpstate *fpstate = tsk->thread.fpu.fpstate;
+ struct fpstate *fpstate = x86_task_fpu(tsk)->fpstate;
bool ia32_fxstate = (buf != buf_fx);
int ret;
@@ -272,7 +263,7 @@ static int __restore_fpregs_from_user(void __user *buf, u64 ufeatures,
*/
static bool restore_fpregs_from_user(void __user *buf, u64 xrestore, bool fx_only)
{
- struct fpu *fpu = &current->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current);
int ret;
/* Restore enabled features only. */
@@ -332,7 +323,7 @@ static bool __fpu_restore_sig(void __user *buf, void __user *buf_fx,
bool ia32_fxstate)
{
struct task_struct *tsk = current;
- struct fpu *fpu = &tsk->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(tsk);
struct user_i387_ia32_struct env;
bool success, fx_only = false;
union fpregs_state *fpregs;
@@ -452,7 +443,7 @@ static inline unsigned int xstate_sigframe_size(struct fpstate *fpstate)
*/
bool fpu__restore_sig(void __user *buf, int ia32_frame)
{
- struct fpu *fpu = &current->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current);
void __user *buf_fx = buf;
bool ia32_fxstate = false;
bool success = false;
@@ -499,7 +490,7 @@ unsigned long
fpu__alloc_mathframe(unsigned long sp, int ia32_frame,
unsigned long *buf_fx, unsigned long *size)
{
- unsigned long frame_size = xstate_sigframe_size(current->thread.fpu.fpstate);
+ unsigned long frame_size = xstate_sigframe_size(x86_task_fpu(current)->fpstate);
*buf_fx = sp = round_down(sp - frame_size, 64);
if (ia32_frame && use_fxsr()) {
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index 6a41d1610d8b..12ed75c1b567 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -14,13 +14,15 @@
#include <linux/proc_fs.h>
#include <linux/vmalloc.h>
#include <linux/coredump.h>
+#include <linux/sort.h>
#include <asm/fpu/api.h>
#include <asm/fpu/regset.h>
#include <asm/fpu/signal.h>
#include <asm/fpu/xcr.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
+#include <asm/msr.h>
#include <asm/tlbflush.h>
#include <asm/prctl.h>
#include <asm/elf.h>
@@ -55,13 +57,14 @@ static const char *xfeature_names[] =
"Protection Keys User registers",
"PASID state",
"Control-flow User registers",
- "Control-flow Kernel registers (unused)",
+ "Control-flow Kernel registers (KVM only)",
"unknown xstate feature",
"unknown xstate feature",
"unknown xstate feature",
"unknown xstate feature",
"AMX Tile config",
"AMX Tile data",
+ "APX registers",
"unknown xstate feature",
};
@@ -78,8 +81,10 @@ static unsigned short xsave_cpuid_features[] __initdata = {
[XFEATURE_PKRU] = X86_FEATURE_OSPKE,
[XFEATURE_PASID] = X86_FEATURE_ENQCMD,
[XFEATURE_CET_USER] = X86_FEATURE_SHSTK,
+ [XFEATURE_CET_KERNEL] = X86_FEATURE_SHSTK,
[XFEATURE_XTILE_CFG] = X86_FEATURE_AMX_TILE,
[XFEATURE_XTILE_DATA] = X86_FEATURE_AMX_TILE,
+ [XFEATURE_APX] = X86_FEATURE_APX,
};
static unsigned int xstate_offsets[XFEATURE_MAX] __ro_after_init =
@@ -88,6 +93,31 @@ static unsigned int xstate_sizes[XFEATURE_MAX] __ro_after_init =
{ [ 0 ... XFEATURE_MAX - 1] = -1};
static unsigned int xstate_flags[XFEATURE_MAX] __ro_after_init;
+/*
+ * Ordering of xstate components in uncompacted format: The xfeature
+ * number does not necessarily indicate its position in the XSAVE buffer.
+ * This array defines the traversal order of xstate features.
+ */
+static unsigned int xfeature_uncompact_order[XFEATURE_MAX] __ro_after_init =
+ { [ 0 ... XFEATURE_MAX - 1] = -1};
+
+static inline unsigned int next_xfeature_order(unsigned int i, u64 mask)
+{
+ for (; xfeature_uncompact_order[i] != -1; i++) {
+ if (mask & BIT_ULL(xfeature_uncompact_order[i]))
+ break;
+ }
+
+ return i;
+}
+
+/* Iterate xstate features in uncompacted order: */
+#define for_each_extended_xfeature_in_order(i, mask) \
+ for (i = 0; \
+ i = next_xfeature_order(i, mask), \
+ xfeature_uncompact_order[i] != -1; \
+ i++)
+
#define XSTATE_FLAG_SUPERVISOR BIT(0)
#define XSTATE_FLAG_ALIGNED64 BIT(1)
@@ -199,7 +229,7 @@ void fpu__init_cpu_xstate(void)
* MSR_IA32_XSS sets supervisor states managed by XSAVES.
*/
if (boot_cpu_has(X86_FEATURE_XSAVES)) {
- wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+ wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() |
xfeatures_mask_independent());
}
}
@@ -209,16 +239,20 @@ static bool xfeature_enabled(enum xfeature xfeature)
return fpu_kernel_cfg.max_features & BIT_ULL(xfeature);
}
+static int compare_xstate_offsets(const void *xfeature1, const void *xfeature2)
+{
+ return xstate_offsets[*(unsigned int *)xfeature1] -
+ xstate_offsets[*(unsigned int *)xfeature2];
+}
+
/*
* Record the offsets and sizes of various xstates contained
- * in the XSAVE state memory layout.
+ * in the XSAVE state memory layout. Also, create an ordered
+ * list of xfeatures for handling out-of-order offsets.
*/
static void __init setup_xstate_cache(void)
{
- u32 eax, ebx, ecx, edx, i;
- /* start at the beginning of the "extended state" */
- unsigned int last_good_offset = offsetof(struct xregs_state,
- extended_state_area);
+ u32 eax, ebx, ecx, edx, xfeature, i = 0;
/*
* The FP xstates and SSE xstates are legacy states. They are always
* in the fixed offsets in the xsave area in either compacted form
@@ -232,31 +266,30 @@ static void __init setup_xstate_cache(void)
xstate_sizes[XFEATURE_SSE] = sizeof_field(struct fxregs_state,
xmm_space);
- for_each_extended_xfeature(i, fpu_kernel_cfg.max_features) {
- cpuid_count(CPUID_LEAF_XSTATE, i, &eax, &ebx, &ecx, &edx);
+ for_each_extended_xfeature(xfeature, fpu_kernel_cfg.max_features) {
+ cpuid_count(CPUID_LEAF_XSTATE, xfeature, &eax, &ebx, &ecx, &edx);
- xstate_sizes[i] = eax;
- xstate_flags[i] = ecx;
+ xstate_sizes[xfeature] = eax;
+ xstate_flags[xfeature] = ecx;
/*
* If an xfeature is supervisor state, the offset in EBX is
* invalid, leave it to -1.
*/
- if (xfeature_is_supervisor(i))
+ if (xfeature_is_supervisor(xfeature))
continue;
- xstate_offsets[i] = ebx;
+ xstate_offsets[xfeature] = ebx;
- /*
- * In our xstate size checks, we assume that the highest-numbered
- * xstate feature has the highest offset in the buffer. Ensure
- * it does.
- */
- WARN_ONCE(last_good_offset > xstate_offsets[i],
- "x86/fpu: misordered xstate at %d\n", last_good_offset);
-
- last_good_offset = xstate_offsets[i];
+ /* Populate the list of xfeatures before sorting */
+ xfeature_uncompact_order[i++] = xfeature;
}
+
+ /*
+ * Sort xfeatures by their offsets to support out-of-order
+ * offsets in the uncompacted format.
+ */
+ sort(xfeature_uncompact_order, i, sizeof(unsigned int), compare_xstate_offsets, NULL);
}
/*
@@ -340,7 +373,9 @@ static __init void os_xrstor_booting(struct xregs_state *xstate)
XFEATURE_MASK_BNDCSR | \
XFEATURE_MASK_PASID | \
XFEATURE_MASK_CET_USER | \
- XFEATURE_MASK_XTILE)
+ XFEATURE_MASK_CET_KERNEL | \
+ XFEATURE_MASK_XTILE | \
+ XFEATURE_MASK_APX)
/*
* setup the xstate image representing the init state
@@ -540,6 +575,8 @@ static bool __init check_xstate_against_struct(int nr)
case XFEATURE_PASID: return XCHECK_SZ(sz, nr, struct ia32_pasid_state);
case XFEATURE_XTILE_CFG: return XCHECK_SZ(sz, nr, struct xtile_cfg);
case XFEATURE_CET_USER: return XCHECK_SZ(sz, nr, struct cet_user_state);
+ case XFEATURE_CET_KERNEL: return XCHECK_SZ(sz, nr, struct cet_supervisor_state);
+ case XFEATURE_APX: return XCHECK_SZ(sz, nr, struct apx_state);
case XFEATURE_XTILE_DATA: check_xtile_data_against_struct(sz); return true;
default:
XSTATE_WARN_ON(1, "No structure for xstate: %d\n", nr);
@@ -552,13 +589,20 @@ static bool __init check_xstate_against_struct(int nr)
static unsigned int xstate_calculate_size(u64 xfeatures, bool compacted)
{
unsigned int topmost = fls64(xfeatures) - 1;
- unsigned int offset = xstate_offsets[topmost];
+ unsigned int offset, i;
if (topmost <= XFEATURE_SSE)
return sizeof(struct xregs_state);
- if (compacted)
+ if (compacted) {
offset = xfeature_get_offset(xfeatures, topmost);
+ } else {
+ /* Walk through the xfeature order to pick the last */
+ for_each_extended_xfeature_in_order(i, xfeatures)
+ topmost = xfeature_uncompact_order[i];
+ offset = xstate_offsets[topmost];
+ }
+
return offset + xstate_sizes[topmost];
}
@@ -639,7 +683,7 @@ static unsigned int __init get_xsave_compacted_size(void)
return get_compacted_size();
/* Disable independent features. */
- wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor());
+ wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor());
/*
* Ask the hardware what size is required of the buffer.
@@ -648,7 +692,7 @@ static unsigned int __init get_xsave_compacted_size(void)
size = get_compacted_size();
/* Re-enable independent features so XSAVES will work on them again. */
- wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
+ wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() | mask);
return size;
}
@@ -702,6 +746,9 @@ static int __init init_xstate_size(void)
fpu_user_cfg.default_size =
xstate_calculate_size(fpu_user_cfg.default_features, false);
+ guest_default_cfg.size =
+ xstate_calculate_size(guest_default_cfg.features, compacted);
+
return 0;
}
@@ -711,6 +758,8 @@ static int __init init_xstate_size(void)
*/
static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
{
+ pr_info("x86/fpu: XSAVE disabled\n");
+
fpu_kernel_cfg.max_features = 0;
cr4_clear_bits(X86_CR4_OSXSAVE);
setup_clear_cpu_cap(X86_FEATURE_XSAVE);
@@ -720,6 +769,7 @@ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
fpu_kernel_cfg.default_size = legacy_size;
fpu_user_cfg.max_size = legacy_size;
fpu_user_cfg.default_size = legacy_size;
+ guest_default_cfg.size = legacy_size;
/*
* Prevent enabling the static branch which enables writes to the
@@ -727,7 +777,25 @@ static void __init fpu__init_disable_system_xstate(unsigned int legacy_size)
*/
init_fpstate.xfd = 0;
- fpstate_reset(&current->thread.fpu);
+ fpstate_reset(x86_task_fpu(current));
+}
+
+static u64 __init host_default_mask(void)
+{
+ /*
+ * Exclude dynamic features (require userspace opt-in) and features
+ * that are supported only for KVM guests.
+ */
+ return ~((u64)XFEATURE_MASK_USER_DYNAMIC | XFEATURE_MASK_GUEST_SUPERVISOR);
+}
+
+static u64 __init guest_default_mask(void)
+{
+ /*
+ * Exclude dynamic features, which require userspace opt-in even
+ * for KVM guests.
+ */
+ return ~(u64)XFEATURE_MASK_USER_DYNAMIC;
}
/*
@@ -775,6 +843,17 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
goto out_disable;
}
+ if (fpu_kernel_cfg.max_features & XFEATURE_MASK_APX &&
+ fpu_kernel_cfg.max_features & (XFEATURE_MASK_BNDREGS | XFEATURE_MASK_BNDCSR)) {
+ /*
+ * This is a problematic CPU configuration where two
+ * conflicting state components are both enumerated.
+ */
+ pr_err("x86/fpu: Both APX/MPX present in the CPU's xstate features: 0x%llx.\n",
+ fpu_kernel_cfg.max_features);
+ goto out_disable;
+ }
+
fpu_kernel_cfg.independent_features = fpu_kernel_cfg.max_features &
XFEATURE_MASK_INDEPENDENT;
@@ -801,12 +880,13 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
fpu_user_cfg.max_features = fpu_kernel_cfg.max_features;
fpu_user_cfg.max_features &= XFEATURE_MASK_USER_SUPPORTED;
- /* Clean out dynamic features from default */
- fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features;
- fpu_kernel_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC;
-
- fpu_user_cfg.default_features = fpu_user_cfg.max_features;
- fpu_user_cfg.default_features &= ~XFEATURE_MASK_USER_DYNAMIC;
+ /*
+ * Now, given maximum feature set, determine default values by
+ * applying default masks.
+ */
+ fpu_kernel_cfg.default_features = fpu_kernel_cfg.max_features & host_default_mask();
+ fpu_user_cfg.default_features = fpu_user_cfg.max_features & host_default_mask();
+ guest_default_cfg.features = fpu_kernel_cfg.max_features & guest_default_mask();
/* Store it for paranoia check at the end */
xfeatures = fpu_kernel_cfg.max_features;
@@ -834,9 +914,6 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
if (err)
goto out_disable;
- /* Reset the state for the current task */
- fpstate_reset(&current->thread.fpu);
-
/*
* Update info used for ptrace frames; use standard-format size and no
* supervisor xstates:
@@ -852,7 +929,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
init_fpstate.xfeatures = fpu_kernel_cfg.default_features;
if (init_fpstate.size > sizeof(init_fpstate.regs)) {
- pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n",
+ pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d)\n",
sizeof(init_fpstate.regs), init_fpstate.size);
goto out_disable;
}
@@ -864,7 +941,7 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
* xfeatures mask.
*/
if (xfeatures != fpu_kernel_cfg.max_features) {
- pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init, disabling XSAVE\n",
+ pr_err("x86/fpu: xfeatures modified from 0x%016llx to 0x%016llx during init\n",
xfeatures, fpu_kernel_cfg.max_features);
goto out_disable;
}
@@ -904,12 +981,12 @@ void fpu__resume_cpu(void)
* of XSAVES and MSR_IA32_XSS.
*/
if (cpu_feature_enabled(X86_FEATURE_XSAVES)) {
- wrmsrl(MSR_IA32_XSS, xfeatures_mask_supervisor() |
+ wrmsrq(MSR_IA32_XSS, xfeatures_mask_supervisor() |
xfeatures_mask_independent());
}
if (fpu_state_size_dynamic())
- wrmsrl(MSR_IA32_XFD, current->thread.fpu.fpstate->xfd);
+ wrmsrq(MSR_IA32_XFD, x86_task_fpu(current)->fpstate->xfd);
}
/*
@@ -1071,10 +1148,9 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
const unsigned int off_mxcsr = offsetof(struct fxregs_state, mxcsr);
struct xregs_state *xinit = &init_fpstate.regs.xsave;
struct xregs_state *xsave = &fpstate->regs.xsave;
+ unsigned int zerofrom, i, xfeature;
struct xstate_header header;
- unsigned int zerofrom;
u64 mask;
- int i;
memset(&header, 0, sizeof(header));
header.xfeatures = xsave->header.xfeatures;
@@ -1143,15 +1219,16 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
*/
mask = header.xfeatures;
- for_each_extended_xfeature(i, mask) {
+ for_each_extended_xfeature_in_order(i, mask) {
+ xfeature = xfeature_uncompact_order[i];
/*
* If there was a feature or alignment gap, zero the space
* in the destination buffer.
*/
- if (zerofrom < xstate_offsets[i])
- membuf_zero(&to, xstate_offsets[i] - zerofrom);
+ if (zerofrom < xstate_offsets[xfeature])
+ membuf_zero(&to, xstate_offsets[xfeature] - zerofrom);
- if (i == XFEATURE_PKRU) {
+ if (xfeature == XFEATURE_PKRU) {
struct pkru_state pkru = {0};
/*
* PKRU is not necessarily up to date in the
@@ -1161,14 +1238,14 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
membuf_write(&to, &pkru, sizeof(pkru));
} else {
membuf_write(&to,
- __raw_xsave_addr(xsave, i),
- xstate_sizes[i]);
+ __raw_xsave_addr(xsave, xfeature),
+ xstate_sizes[xfeature]);
}
/*
* Keep track of the last copied state in the non-compacted
* target buffer for gap zeroing.
*/
- zerofrom = xstate_offsets[i] + xstate_sizes[i];
+ zerofrom = xstate_offsets[xfeature] + xstate_sizes[xfeature];
}
out:
@@ -1191,8 +1268,8 @@ out:
void copy_xstate_to_uabi_buf(struct membuf to, struct task_struct *tsk,
enum xstate_copy_mode copy_mode)
{
- __copy_xstate_to_uabi_buf(to, tsk->thread.fpu.fpstate,
- tsk->thread.fpu.fpstate->user_xfeatures,
+ __copy_xstate_to_uabi_buf(to, x86_task_fpu(tsk)->fpstate,
+ x86_task_fpu(tsk)->fpstate->user_xfeatures,
tsk->thread.pkru, copy_mode);
}
@@ -1332,7 +1409,7 @@ int copy_uabi_from_kernel_to_xstate(struct fpstate *fpstate, const void *kbuf, u
int copy_sigframe_from_user_to_xstate(struct task_struct *tsk,
const void __user *ubuf)
{
- return copy_uabi_to_xstate(tsk->thread.fpu.fpstate, NULL, ubuf, &tsk->thread.pkru);
+ return copy_uabi_to_xstate(x86_task_fpu(tsk)->fpstate, NULL, ubuf, &tsk->thread.pkru);
}
static bool validate_independent_components(u64 mask)
@@ -1398,9 +1475,9 @@ void xrstors(struct xregs_state *xstate, u64 mask)
}
#if IS_ENABLED(CONFIG_KVM)
-void fpstate_clear_xstate_component(struct fpstate *fps, unsigned int xfeature)
+void fpstate_clear_xstate_component(struct fpstate *fpstate, unsigned int xfeature)
{
- void *addr = get_xsave_addr(&fps->regs.xsave, xfeature);
+ void *addr = get_xsave_addr(&fpstate->regs.xsave, xfeature);
if (addr)
memset(addr, 0, xstate_sizes[xfeature]);
@@ -1426,7 +1503,7 @@ static bool xstate_op_valid(struct fpstate *fpstate, u64 mask, bool rstor)
* The XFD MSR does not match fpstate->xfd. That's invalid when
* the passed in fpstate is current's fpstate.
*/
- if (fpstate->xfd == current->thread.fpu.fpstate->xfd)
+ if (fpstate->xfd == x86_task_fpu(current)->fpstate->xfd)
return false;
/*
@@ -1503,7 +1580,7 @@ void fpstate_free(struct fpu *fpu)
static int fpstate_realloc(u64 xfeatures, unsigned int ksize,
unsigned int usize, struct fpu_guest *guest_fpu)
{
- struct fpu *fpu = &current->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current);
struct fpstate *curfps, *newfps = NULL;
unsigned int fpsize;
bool in_use;
@@ -1596,7 +1673,7 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
* AVX512.
*/
bool compacted = cpu_feature_enabled(X86_FEATURE_XCOMPACTED);
- struct fpu *fpu = &current->group_leader->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current->group_leader);
struct fpu_state_perm *perm;
unsigned int ksize, usize;
u64 mask;
@@ -1606,16 +1683,20 @@ static int __xstate_request_perm(u64 permitted, u64 requested, bool guest)
if ((permitted & requested) == requested)
return 0;
- /* Calculate the resulting kernel state size */
+ /*
+ * Calculate the resulting kernel state size. Note, @permitted also
+ * contains supervisor xfeatures even though supervisor are always
+ * permitted for kernel and guest FPUs, and never permitted for user
+ * FPUs.
+ */
mask = permitted | requested;
- /* Take supervisor states into account on the host */
- if (!guest)
- mask |= xfeatures_mask_supervisor();
ksize = xstate_calculate_size(mask, compacted);
- /* Calculate the resulting user state size */
- mask &= XFEATURE_MASK_USER_SUPPORTED;
- usize = xstate_calculate_size(mask, false);
+ /*
+ * Calculate the resulting user state size. Take care not to clobber
+ * the supervisor xfeatures in the new mask!
+ */
+ usize = xstate_calculate_size(mask & XFEATURE_MASK_USER_SUPPORTED, false);
if (!guest) {
ret = validate_sigaltstack(usize);
@@ -1699,7 +1780,7 @@ int __xfd_enable_feature(u64 xfd_err, struct fpu_guest *guest_fpu)
return -EPERM;
}
- fpu = &current->group_leader->thread.fpu;
+ fpu = x86_task_fpu(current->group_leader);
perm = guest_fpu ? &fpu->guest_perm : &fpu->perm;
ksize = perm->__state_size;
usize = perm->__user_state_size;
@@ -1804,7 +1885,7 @@ long fpu_xstate_prctl(int option, unsigned long arg2)
*/
static void avx512_status(struct seq_file *m, struct task_struct *task)
{
- unsigned long timestamp = READ_ONCE(task->thread.fpu.avx512_timestamp);
+ unsigned long timestamp = READ_ONCE(x86_task_fpu(task)->avx512_timestamp);
long delta;
if (!timestamp) {
diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
index 0fd34f53f025..52ce19289989 100644
--- a/arch/x86/kernel/fpu/xstate.h
+++ b/arch/x86/kernel/fpu/xstate.h
@@ -5,6 +5,7 @@
#include <asm/cpufeature.h>
#include <asm/fpu/xstate.h>
#include <asm/fpu/xcr.h>
+#include <asm/msr.h>
#ifdef CONFIG_X86_64
DECLARE_PER_CPU(u64, xfd_state);
@@ -22,7 +23,7 @@ static inline void xstate_init_xcomp_bv(struct xregs_state *xsave, u64 mask)
static inline u64 xstate_get_group_perm(bool guest)
{
- struct fpu *fpu = &current->group_leader->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current->group_leader);
struct fpu_state_perm *perm;
/* Pairs with WRITE_ONCE() in xstate_request_perm() */
@@ -69,21 +70,31 @@ static inline u64 xfeatures_mask_independent(void)
return fpu_kernel_cfg.independent_features;
}
+static inline int set_xfeature_in_sigframe(struct xregs_state __user *xbuf, u64 mask)
+{
+ u64 xfeatures;
+ int err;
+
+ /* Read the xfeatures value already saved in the user buffer */
+ err = __get_user(xfeatures, &xbuf->header.xfeatures);
+ xfeatures |= mask;
+ err |= __put_user(xfeatures, &xbuf->header.xfeatures);
+
+ return err;
+}
+
/*
* Update the value of PKRU register that was already pushed onto the signal frame.
*/
-static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u64 mask, u32 pkru)
+static inline int update_pkru_in_sigframe(struct xregs_state __user *buf, u32 pkru)
{
- u64 xstate_bv;
int err;
if (unlikely(!cpu_feature_enabled(X86_FEATURE_OSPKE)))
return 0;
/* Mark PKRU as in-use so that it is restored correctly. */
- xstate_bv = (mask & xfeatures_in_use()) | XFEATURE_MASK_PKRU;
-
- err = __put_user(xstate_bv, &buf->header.xfeatures);
+ err = set_xfeature_in_sigframe(buf, XFEATURE_MASK_PKRU);
if (err)
return err;
@@ -171,7 +182,7 @@ static inline void xfd_validate_state(struct fpstate *fpstate, u64 mask, bool rs
#ifdef CONFIG_X86_64
static inline void xfd_set_state(u64 xfd)
{
- wrmsrl(MSR_IA32_XFD, xfd);
+ wrmsrq(MSR_IA32_XFD, xfd);
__this_cpu_write(xfd_state, xfd);
}
@@ -288,7 +299,7 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkr
* internally, e.g. PKRU. That's user space ABI and also required
* to allow the signal handler to modify PKRU.
*/
- struct fpstate *fpstate = current->thread.fpu.fpstate;
+ struct fpstate *fpstate = x86_task_fpu(current)->fpstate;
u64 mask = fpstate->user_xfeatures;
u32 lmask;
u32 hmask;
@@ -307,7 +318,7 @@ static inline int xsave_to_user_sigframe(struct xregs_state __user *buf, u32 pkr
clac();
if (!err)
- err = update_pkru_in_sigframe(buf, mask, pkru);
+ err = update_pkru_in_sigframe(buf, pkru);
return err;
}
@@ -322,7 +333,7 @@ static inline int xrstor_from_user_sigframe(struct xregs_state __user *buf, u64
u32 hmask = mask >> 32;
int err;
- xfd_validate_state(current->thread.fpu.fpstate, mask, true);
+ xfd_validate_state(x86_task_fpu(current)->fpstate, mask, true);
stac();
XSTATE_OP(XRSTOR, xstate, lmask, hmask, err);
diff --git a/arch/x86/kernel/fred.c b/arch/x86/kernel/fred.c
index 5e2cd1004980..816187da3a47 100644
--- a/arch/x86/kernel/fred.c
+++ b/arch/x86/kernel/fred.c
@@ -3,6 +3,7 @@
#include <asm/desc.h>
#include <asm/fred.h>
+#include <asm/msr.h>
#include <asm/tlbflush.h>
#include <asm/traps.h>
@@ -43,23 +44,23 @@ void cpu_init_fred_exceptions(void)
*/
loadsegment(ss, __KERNEL_DS);
- wrmsrl(MSR_IA32_FRED_CONFIG,
+ wrmsrq(MSR_IA32_FRED_CONFIG,
/* Reserve for CALL emulation */
FRED_CONFIG_REDZONE |
FRED_CONFIG_INT_STKLVL(0) |
FRED_CONFIG_ENTRYPOINT(asm_fred_entrypoint_user));
- wrmsrl(MSR_IA32_FRED_STKLVLS, 0);
+ wrmsrq(MSR_IA32_FRED_STKLVLS, 0);
/*
* Ater a CPU offline/online cycle, the FRED RSP0 MSR should be
* resynchronized with its per-CPU cache.
*/
- wrmsrl(MSR_IA32_FRED_RSP0, __this_cpu_read(fred_rsp0));
+ wrmsrq(MSR_IA32_FRED_RSP0, __this_cpu_read(fred_rsp0));
- wrmsrl(MSR_IA32_FRED_RSP1, 0);
- wrmsrl(MSR_IA32_FRED_RSP2, 0);
- wrmsrl(MSR_IA32_FRED_RSP3, 0);
+ wrmsrq(MSR_IA32_FRED_RSP1, 0);
+ wrmsrq(MSR_IA32_FRED_RSP2, 0);
+ wrmsrq(MSR_IA32_FRED_RSP3, 0);
/* Enable FRED */
cr4_set_bits(X86_CR4_FRED);
@@ -79,14 +80,14 @@ void cpu_init_fred_rsps(void)
* (remember that user space faults are always taken on stack level 0)
* is to avoid overflowing the kernel stack.
*/
- wrmsrl(MSR_IA32_FRED_STKLVLS,
+ wrmsrq(MSR_IA32_FRED_STKLVLS,
FRED_STKLVL(X86_TRAP_DB, FRED_DB_STACK_LEVEL) |
FRED_STKLVL(X86_TRAP_NMI, FRED_NMI_STACK_LEVEL) |
FRED_STKLVL(X86_TRAP_MC, FRED_MC_STACK_LEVEL) |
FRED_STKLVL(X86_TRAP_DF, FRED_DF_STACK_LEVEL));
/* The FRED equivalents to IST stacks... */
- wrmsrl(MSR_IA32_FRED_RSP1, __this_cpu_ist_top_va(DB));
- wrmsrl(MSR_IA32_FRED_RSP2, __this_cpu_ist_top_va(NMI));
- wrmsrl(MSR_IA32_FRED_RSP3, __this_cpu_ist_top_va(DF));
+ wrmsrq(MSR_IA32_FRED_RSP1, __this_cpu_ist_top_va(DB));
+ wrmsrq(MSR_IA32_FRED_RSP2, __this_cpu_ist_top_va(NMI));
+ wrmsrq(MSR_IA32_FRED_RSP3, __this_cpu_ist_top_va(DF));
}
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index 5eb1514af559..4450acec9390 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -55,10 +55,10 @@ void ftrace_arch_code_modify_post_process(void)
{
/*
* ftrace_make_{call,nop}() may be called during
- * module load, and we need to finish the text_poke_queue()
+ * module load, and we need to finish the smp_text_poke_batch_add()
* that they do, here.
*/
- text_poke_finish();
+ smp_text_poke_batch_finish();
ftrace_poke_late = 0;
mutex_unlock(&text_mutex);
}
@@ -119,7 +119,7 @@ ftrace_modify_code_direct(unsigned long ip, const char *old_code,
/* replace the text with the new text */
if (ftrace_poke_late)
- text_poke_queue((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL);
+ smp_text_poke_batch_add((void *)ip, new_code, MCOUNT_INSN_SIZE, NULL);
else
text_poke_early((void *)ip, new_code, MCOUNT_INSN_SIZE);
return 0;
@@ -186,11 +186,11 @@ int ftrace_update_ftrace_func(ftrace_func_t func)
ip = (unsigned long)(&ftrace_call);
new = ftrace_call_replace(ip, (unsigned long)func);
- text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
+ smp_text_poke_single((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
ip = (unsigned long)(&ftrace_regs_call);
new = ftrace_call_replace(ip, (unsigned long)func);
- text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
+ smp_text_poke_single((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
return 0;
}
@@ -247,10 +247,10 @@ void ftrace_replace_code(int enable)
break;
}
- text_poke_queue((void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL);
+ smp_text_poke_batch_add((void *)rec->ip, new, MCOUNT_INSN_SIZE, NULL);
ftrace_update_record(rec, enable);
}
- text_poke_finish();
+ smp_text_poke_batch_finish();
}
void arch_ftrace_update_code(int command)
@@ -263,7 +263,7 @@ void arch_ftrace_update_code(int command)
static inline void *alloc_tramp(unsigned long size)
{
- return execmem_alloc(EXECMEM_FTRACE, size);
+ return execmem_alloc_rw(EXECMEM_FTRACE, size);
}
static inline void tramp_free(void *tramp)
{
@@ -492,7 +492,7 @@ void arch_ftrace_update_trampoline(struct ftrace_ops *ops)
mutex_lock(&text_mutex);
/* Do a safe modify in case the trampoline is executing */
new = ftrace_call_replace(ip, (unsigned long)func);
- text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
+ smp_text_poke_single((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
mutex_unlock(&text_mutex);
}
@@ -586,7 +586,7 @@ static int ftrace_mod_jmp(unsigned long ip, void *func)
const char *new;
new = ftrace_jmp_replace(ip, (unsigned long)func);
- text_poke_bp((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
+ smp_text_poke_single((void *)ip, new, MCOUNT_INSN_SIZE, NULL);
return 0;
}
diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
index fa9b6339975f..533fcf5636fc 100644
--- a/arch/x86/kernel/head64.c
+++ b/arch/x86/kernel/head64.c
@@ -47,234 +47,22 @@
* Manage page tables very early on.
*/
extern pmd_t early_dynamic_pgts[EARLY_DYNAMIC_PAGE_TABLES][PTRS_PER_PMD];
-static unsigned int __initdata next_early_pgt;
+unsigned int __initdata next_early_pgt;
+SYM_PIC_ALIAS(next_early_pgt);
pmdval_t early_pmd_flags = __PAGE_KERNEL_LARGE & ~(_PAGE_GLOBAL | _PAGE_NX);
-#ifdef CONFIG_X86_5LEVEL
unsigned int __pgtable_l5_enabled __ro_after_init;
unsigned int pgdir_shift __ro_after_init = 39;
EXPORT_SYMBOL(pgdir_shift);
unsigned int ptrs_per_p4d __ro_after_init = 1;
EXPORT_SYMBOL(ptrs_per_p4d);
-#endif
-#ifdef CONFIG_DYNAMIC_MEMORY_LAYOUT
unsigned long page_offset_base __ro_after_init = __PAGE_OFFSET_BASE_L4;
EXPORT_SYMBOL(page_offset_base);
unsigned long vmalloc_base __ro_after_init = __VMALLOC_BASE_L4;
EXPORT_SYMBOL(vmalloc_base);
unsigned long vmemmap_base __ro_after_init = __VMEMMAP_BASE_L4;
EXPORT_SYMBOL(vmemmap_base);
-#endif
-
-static inline bool check_la57_support(void)
-{
- if (!IS_ENABLED(CONFIG_X86_5LEVEL))
- return false;
-
- /*
- * 5-level paging is detected and enabled at kernel decompression
- * stage. Only check if it has been enabled there.
- */
- if (!(native_read_cr4() & X86_CR4_LA57))
- return false;
-
- RIP_REL_REF(__pgtable_l5_enabled) = 1;
- RIP_REL_REF(pgdir_shift) = 48;
- RIP_REL_REF(ptrs_per_p4d) = 512;
- RIP_REL_REF(page_offset_base) = __PAGE_OFFSET_BASE_L5;
- RIP_REL_REF(vmalloc_base) = __VMALLOC_BASE_L5;
- RIP_REL_REF(vmemmap_base) = __VMEMMAP_BASE_L5;
-
- return true;
-}
-
-static unsigned long __head sme_postprocess_startup(struct boot_params *bp,
- pmdval_t *pmd,
- unsigned long p2v_offset)
-{
- unsigned long paddr, paddr_end;
- int i;
-
- /* Encrypt the kernel and related (if SME is active) */
- sme_encrypt_kernel(bp);
-
- /*
- * Clear the memory encryption mask from the .bss..decrypted section.
- * The bss section will be memset to zero later in the initialization so
- * there is no need to zero it after changing the memory encryption
- * attribute.
- */
- if (sme_get_me_mask()) {
- paddr = (unsigned long)&RIP_REL_REF(__start_bss_decrypted);
- paddr_end = (unsigned long)&RIP_REL_REF(__end_bss_decrypted);
-
- for (; paddr < paddr_end; paddr += PMD_SIZE) {
- /*
- * On SNP, transition the page to shared in the RMP table so that
- * it is consistent with the page table attribute change.
- *
- * __start_bss_decrypted has a virtual address in the high range
- * mapping (kernel .text). PVALIDATE, by way of
- * early_snp_set_memory_shared(), requires a valid virtual
- * address but the kernel is currently running off of the identity
- * mapping so use the PA to get a *currently* valid virtual address.
- */
- early_snp_set_memory_shared(paddr, paddr, PTRS_PER_PMD);
-
- i = pmd_index(paddr - p2v_offset);
- pmd[i] -= sme_get_me_mask();
- }
- }
-
- /*
- * Return the SME encryption mask (if SME is active) to be used as a
- * modifier for the initial pgdir entry programmed into CR3.
- */
- return sme_get_me_mask();
-}
-
-/* Code in __startup_64() can be relocated during execution, but the compiler
- * doesn't have to generate PC-relative relocations when accessing globals from
- * that function. Clang actually does not generate them, which leads to
- * boot-time crashes. To work around this problem, every global pointer must
- * be accessed using RIP_REL_REF(). Kernel virtual addresses can be determined
- * by subtracting p2v_offset from the RIP-relative address.
- */
-unsigned long __head __startup_64(unsigned long p2v_offset,
- struct boot_params *bp)
-{
- pmd_t (*early_pgts)[PTRS_PER_PMD] = RIP_REL_REF(early_dynamic_pgts);
- unsigned long physaddr = (unsigned long)&RIP_REL_REF(_text);
- unsigned long va_text, va_end;
- unsigned long pgtable_flags;
- unsigned long load_delta;
- pgdval_t *pgd;
- p4dval_t *p4d;
- pudval_t *pud;
- pmdval_t *pmd, pmd_entry;
- bool la57;
- int i;
-
- la57 = check_la57_support();
-
- /* Is the address too large? */
- if (physaddr >> MAX_PHYSMEM_BITS)
- for (;;);
-
- /*
- * Compute the delta between the address I am compiled to run at
- * and the address I am actually running at.
- */
- load_delta = __START_KERNEL_map + p2v_offset;
- RIP_REL_REF(phys_base) = load_delta;
-
- /* Is the address not 2M aligned? */
- if (load_delta & ~PMD_MASK)
- for (;;);
-
- va_text = physaddr - p2v_offset;
- va_end = (unsigned long)&RIP_REL_REF(_end) - p2v_offset;
-
- /* Include the SME encryption mask in the fixup value */
- load_delta += sme_get_me_mask();
-
- /* Fixup the physical addresses in the page table */
-
- pgd = &RIP_REL_REF(early_top_pgt)->pgd;
- pgd[pgd_index(__START_KERNEL_map)] += load_delta;
-
- if (IS_ENABLED(CONFIG_X86_5LEVEL) && la57) {
- p4d = (p4dval_t *)&RIP_REL_REF(level4_kernel_pgt);
- p4d[MAX_PTRS_PER_P4D - 1] += load_delta;
-
- pgd[pgd_index(__START_KERNEL_map)] = (pgdval_t)p4d | _PAGE_TABLE;
- }
-
- RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 2].pud += load_delta;
- RIP_REL_REF(level3_kernel_pgt)[PTRS_PER_PUD - 1].pud += load_delta;
-
- for (i = FIXMAP_PMD_TOP; i > FIXMAP_PMD_TOP - FIXMAP_PMD_NUM; i--)
- RIP_REL_REF(level2_fixmap_pgt)[i].pmd += load_delta;
-
- /*
- * Set up the identity mapping for the switchover. These
- * entries should *NOT* have the global bit set! This also
- * creates a bunch of nonsense entries but that is fine --
- * it avoids problems around wraparound.
- */
-
- pud = &early_pgts[0]->pmd;
- pmd = &early_pgts[1]->pmd;
- RIP_REL_REF(next_early_pgt) = 2;
-
- pgtable_flags = _KERNPG_TABLE_NOENC + sme_get_me_mask();
-
- if (la57) {
- p4d = &early_pgts[RIP_REL_REF(next_early_pgt)++]->pmd;
-
- i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
- pgd[i + 0] = (pgdval_t)p4d + pgtable_flags;
- pgd[i + 1] = (pgdval_t)p4d + pgtable_flags;
-
- i = physaddr >> P4D_SHIFT;
- p4d[(i + 0) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
- p4d[(i + 1) % PTRS_PER_P4D] = (pgdval_t)pud + pgtable_flags;
- } else {
- i = (physaddr >> PGDIR_SHIFT) % PTRS_PER_PGD;
- pgd[i + 0] = (pgdval_t)pud + pgtable_flags;
- pgd[i + 1] = (pgdval_t)pud + pgtable_flags;
- }
-
- i = physaddr >> PUD_SHIFT;
- pud[(i + 0) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
- pud[(i + 1) % PTRS_PER_PUD] = (pudval_t)pmd + pgtable_flags;
-
- pmd_entry = __PAGE_KERNEL_LARGE_EXEC & ~_PAGE_GLOBAL;
- /* Filter out unsupported __PAGE_KERNEL_* bits: */
- pmd_entry &= RIP_REL_REF(__supported_pte_mask);
- pmd_entry += sme_get_me_mask();
- pmd_entry += physaddr;
-
- for (i = 0; i < DIV_ROUND_UP(va_end - va_text, PMD_SIZE); i++) {
- int idx = i + (physaddr >> PMD_SHIFT);
-
- pmd[idx % PTRS_PER_PMD] = pmd_entry + i * PMD_SIZE;
- }
-
- /*
- * Fixup the kernel text+data virtual addresses. Note that
- * we might write invalid pmds, when the kernel is relocated
- * cleanup_highmap() fixes this up along with the mappings
- * beyond _end.
- *
- * Only the region occupied by the kernel image has so far
- * been checked against the table of usable memory regions
- * provided by the firmware, so invalidate pages outside that
- * region. A page table entry that maps to a reserved area of
- * memory would allow processor speculation into that area,
- * and on some hardware (particularly the UV platform) even
- * speculative access to some reserved areas is caught as an
- * error, causing the BIOS to halt the system.
- */
-
- pmd = &RIP_REL_REF(level2_kernel_pgt)->pmd;
-
- /* invalidate pages before the kernel image */
- for (i = 0; i < pmd_index(va_text); i++)
- pmd[i] &= ~_PAGE_PRESENT;
-
- /* fixup pages that are part of the kernel image */
- for (; i <= pmd_index(va_end); i++)
- if (pmd[i] & _PAGE_PRESENT)
- pmd[i] += load_delta;
-
- /* invalidate pages after the kernel image */
- for (; i < PTRS_PER_PMD; i++)
- pmd[i] &= ~_PAGE_PRESENT;
-
- return sme_postprocess_startup(bp, pmd, p2v_offset);
-}
/* Wipe all early page tables except for the kernel symbol map */
static void __init reset_early_page_tables(void)
@@ -449,6 +237,12 @@ asmlinkage __visible void __init __noreturn x86_64_start_kernel(char * real_mode
/* Kill off the identity-map trampoline */
reset_early_page_tables();
+ if (pgtable_l5_enabled()) {
+ page_offset_base = __PAGE_OFFSET_BASE_L5;
+ vmalloc_base = __VMALLOC_BASE_L5;
+ vmemmap_base = __VMEMMAP_BASE_L5;
+ }
+
clear_bss();
/*
@@ -513,41 +307,6 @@ void __init __noreturn x86_64_start_reservations(char *real_mode_data)
start_kernel();
}
-/*
- * Data structures and code used for IDT setup in head_64.S. The bringup-IDT is
- * used until the idt_table takes over. On the boot CPU this happens in
- * x86_64_start_kernel(), on secondary CPUs in start_secondary(). In both cases
- * this happens in the functions called from head_64.S.
- *
- * The idt_table can't be used that early because all the code modifying it is
- * in idt.c and can be instrumented by tracing or KASAN, which both don't work
- * during early CPU bringup. Also the idt_table has the runtime vectors
- * configured which require certain CPU state to be setup already (like TSS),
- * which also hasn't happened yet in early CPU bringup.
- */
-static gate_desc bringup_idt_table[NUM_EXCEPTION_VECTORS] __page_aligned_data;
-
-/* This may run while still in the direct mapping */
-static void __head startup_64_load_idt(void *vc_handler)
-{
- struct desc_ptr desc = {
- .address = (unsigned long)&RIP_REL_REF(bringup_idt_table),
- .size = sizeof(bringup_idt_table) - 1,
- };
- struct idt_data data;
- gate_desc idt_desc;
-
- /* @vc_handler is set only for a VMM Communication Exception */
- if (vc_handler) {
- init_idt_data(&data, X86_TRAP_VC, vc_handler);
- idt_init_desc(&idt_desc, &data);
- native_write_idt_entry((gate_desc *)desc.address, X86_TRAP_VC, &idt_desc);
- }
-
- native_load_idt(&desc);
-}
-
-/* This is used when running on kernel addresses */
void early_setup_idt(void)
{
void *handler = NULL;
@@ -559,30 +318,3 @@ void early_setup_idt(void)
startup_64_load_idt(handler);
}
-
-/*
- * Setup boot CPU state needed before kernel switches to virtual addresses.
- */
-void __head startup_64_setup_gdt_idt(void)
-{
- struct desc_struct *gdt = (void *)(__force unsigned long)gdt_page.gdt;
- void *handler = NULL;
-
- struct desc_ptr startup_gdt_descr = {
- .address = (unsigned long)&RIP_REL_REF(*gdt),
- .size = GDT_SIZE - 1,
- };
-
- /* Load GDT */
- native_load_gdt(&startup_gdt_descr);
-
- /* New GDT is live - reload data segment registers */
- asm volatile("movl %%eax, %%ds\n"
- "movl %%eax, %%ss\n"
- "movl %%eax, %%es\n" : : "a"(__KERNEL_DS) : "memory");
-
- if (IS_ENABLED(CONFIG_AMD_MEM_ENCRYPT))
- handler = &RIP_REL_REF(vc_no_ghcb);
-
- startup_64_load_idt(handler);
-}
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 2e42056d2306..76743dfad6ab 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -86,7 +86,7 @@ SYM_CODE_START(startup_32)
movl $pa(__bss_stop),%ecx
subl %edi,%ecx
shrl $2,%ecx
- rep ; stosl
+ rep stosl
/*
* Copy bootup parameters out of the way.
* Note: %esi still has the pointer to the real-mode data.
@@ -98,15 +98,13 @@ SYM_CODE_START(startup_32)
movl $pa(boot_params),%edi
movl $(PARAM_SIZE/4),%ecx
cld
- rep
- movsl
+ rep movsl
movl pa(boot_params) + NEW_CL_POINTER,%esi
andl %esi,%esi
jz 1f # No command line
movl $pa(boot_command_line),%edi
movl $(COMMAND_LINE_SIZE/4),%ecx
- rep
- movsl
+ rep movsl
1:
#ifdef CONFIG_OLPC
diff --git a/arch/x86/kernel/head_64.S b/arch/x86/kernel/head_64.S
index fefe2a25cf02..3e9b3a3bd039 100644
--- a/arch/x86/kernel/head_64.S
+++ b/arch/x86/kernel/head_64.S
@@ -573,6 +573,7 @@ SYM_CODE_START_NOALIGN(vc_no_ghcb)
/* Pure iret required here - don't use INTERRUPT_RETURN */
iretq
SYM_CODE_END(vc_no_ghcb)
+SYM_PIC_ALIAS(vc_no_ghcb);
#endif
#ifdef CONFIG_MITIGATION_PAGE_TABLE_ISOLATION
@@ -604,10 +605,12 @@ SYM_DATA_START_PTI_ALIGNED(early_top_pgt)
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
.fill PTI_USER_PGD_FILL,8,0
SYM_DATA_END(early_top_pgt)
+SYM_PIC_ALIAS(early_top_pgt)
SYM_DATA_START_PAGE_ALIGNED(early_dynamic_pgts)
.fill 512*EARLY_DYNAMIC_PAGE_TABLES,8,0
SYM_DATA_END(early_dynamic_pgts)
+SYM_PIC_ALIAS(early_dynamic_pgts);
SYM_DATA(early_recursion_flag, .long 0)
@@ -646,12 +649,11 @@ SYM_DATA_START_PTI_ALIGNED(init_top_pgt)
SYM_DATA_END(init_top_pgt)
#endif
-#ifdef CONFIG_X86_5LEVEL
SYM_DATA_START_PAGE_ALIGNED(level4_kernel_pgt)
.fill 511,8,0
.quad level3_kernel_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
SYM_DATA_END(level4_kernel_pgt)
-#endif
+SYM_PIC_ALIAS(level4_kernel_pgt)
SYM_DATA_START_PAGE_ALIGNED(level3_kernel_pgt)
.fill L3_START_KERNEL,8,0
@@ -659,6 +661,7 @@ SYM_DATA_START_PAGE_ALIGNED(level3_kernel_pgt)
.quad level2_kernel_pgt - __START_KERNEL_map + _KERNPG_TABLE_NOENC
.quad level2_fixmap_pgt - __START_KERNEL_map + _PAGE_TABLE_NOENC
SYM_DATA_END(level3_kernel_pgt)
+SYM_PIC_ALIAS(level3_kernel_pgt)
SYM_DATA_START_PAGE_ALIGNED(level2_kernel_pgt)
/*
@@ -676,6 +679,7 @@ SYM_DATA_START_PAGE_ALIGNED(level2_kernel_pgt)
*/
PMDS(0, __PAGE_KERNEL_LARGE_EXEC, KERNEL_IMAGE_SIZE/PMD_SIZE)
SYM_DATA_END(level2_kernel_pgt)
+SYM_PIC_ALIAS(level2_kernel_pgt)
SYM_DATA_START_PAGE_ALIGNED(level2_fixmap_pgt)
.fill (512 - 4 - FIXMAP_PMD_NUM),8,0
@@ -688,6 +692,7 @@ SYM_DATA_START_PAGE_ALIGNED(level2_fixmap_pgt)
/* 6 MB reserved space + a 2MB hole */
.fill 4,8,0
SYM_DATA_END(level2_fixmap_pgt)
+SYM_PIC_ALIAS(level2_fixmap_pgt)
SYM_DATA_START_PAGE_ALIGNED(level1_fixmap_pgt)
.rept (FIXMAP_PMD_NUM)
@@ -703,6 +708,7 @@ SYM_DATA(smpboot_control, .long 0)
.align 16
/* This must match the first entry in level2_kernel_pgt */
SYM_DATA(phys_base, .quad 0x0)
+SYM_PIC_ALIAS(phys_base);
EXPORT_SYMBOL(phys_base)
#include "../xen/xen-head.S"
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 7f4b2966e15c..d6387dde3ff9 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -7,11 +7,12 @@
#include <linux/cpu.h>
#include <linux/irq.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/irq_remapping.h>
#include <asm/hpet.h>
#include <asm/time.h>
#include <asm/mwait.h>
+#include <asm/msr.h>
#undef pr_fmt
#define pr_fmt(fmt) "hpet: " fmt
@@ -970,7 +971,7 @@ static bool __init hpet_is_pc10_damaged(void)
return false;
/* Check whether PC10 is enabled in PKG C-state limit */
- rdmsrl(MSR_PKG_CST_CONFIG_CONTROL, pcfg);
+ rdmsrq(MSR_PKG_CST_CONFIG_CONTROL, pcfg);
if ((pcfg & 0xF) < 8)
return false;
diff --git a/arch/x86/kernel/ioport.c b/arch/x86/kernel/ioport.c
index 6290dd120f5e..ff40f09ad911 100644
--- a/arch/x86/kernel/ioport.c
+++ b/arch/x86/kernel/ioport.c
@@ -33,8 +33,9 @@ void io_bitmap_share(struct task_struct *tsk)
set_tsk_thread_flag(tsk, TIF_IO_BITMAP);
}
-static void task_update_io_bitmap(struct task_struct *tsk)
+static void task_update_io_bitmap(void)
{
+ struct task_struct *tsk = current;
struct thread_struct *t = &tsk->thread;
if (t->iopl_emul == 3 || t->io_bitmap) {
@@ -54,7 +55,12 @@ void io_bitmap_exit(struct task_struct *tsk)
struct io_bitmap *iobm = tsk->thread.io_bitmap;
tsk->thread.io_bitmap = NULL;
- task_update_io_bitmap(tsk);
+ /*
+ * Don't touch the TSS when invoked on a failed fork(). TSS
+ * reflects the state of @current and not the state of @tsk.
+ */
+ if (tsk == current)
+ task_update_io_bitmap();
if (iobm && refcount_dec_and_test(&iobm->refcnt))
kfree(iobm);
}
@@ -192,8 +198,7 @@ SYSCALL_DEFINE1(iopl, unsigned int, level)
}
t->iopl_emul = level;
- task_update_io_bitmap(current);
-
+ task_update_io_bitmap();
return 0;
}
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 81f9b78e0f7b..10721a125226 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -256,26 +256,59 @@ static __always_inline void handle_irq(struct irq_desc *desc,
__handle_irq(desc, regs);
}
-static __always_inline int call_irq_handler(int vector, struct pt_regs *regs)
+static struct irq_desc *reevaluate_vector(int vector)
{
- struct irq_desc *desc;
- int ret = 0;
+ struct irq_desc *desc = __this_cpu_read(vector_irq[vector]);
+
+ if (!IS_ERR_OR_NULL(desc))
+ return desc;
+
+ if (desc == VECTOR_UNUSED)
+ pr_emerg_ratelimited("No irq handler for %d.%u\n", smp_processor_id(), vector);
+ else
+ __this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
+ return NULL;
+}
+
+static __always_inline bool call_irq_handler(int vector, struct pt_regs *regs)
+{
+ struct irq_desc *desc = __this_cpu_read(vector_irq[vector]);
- desc = __this_cpu_read(vector_irq[vector]);
if (likely(!IS_ERR_OR_NULL(desc))) {
handle_irq(desc, regs);
- } else {
- ret = -EINVAL;
- if (desc == VECTOR_UNUSED) {
- pr_emerg_ratelimited("%s: %d.%u No irq handler for vector\n",
- __func__, smp_processor_id(),
- vector);
- } else {
- __this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
- }
+ return true;
}
- return ret;
+ /*
+ * Reevaluate with vector_lock held to prevent a race against
+ * request_irq() setting up the vector:
+ *
+ * CPU0 CPU1
+ * interrupt is raised in APIC IRR
+ * but not handled
+ * free_irq()
+ * per_cpu(vector_irq, CPU1)[vector] = VECTOR_SHUTDOWN;
+ *
+ * request_irq() common_interrupt()
+ * d = this_cpu_read(vector_irq[vector]);
+ *
+ * per_cpu(vector_irq, CPU1)[vector] = desc;
+ *
+ * if (d == VECTOR_SHUTDOWN)
+ * this_cpu_write(vector_irq[vector], VECTOR_UNUSED);
+ *
+ * This requires that the same vector on the same target CPU is
+ * handed out or that a spurious interrupt hits that CPU/vector.
+ */
+ lock_vector_lock();
+ desc = reevaluate_vector(vector);
+ unlock_vector_lock();
+
+ if (!desc)
+ return false;
+
+ handle_irq(desc, regs);
+ return true;
}
/*
@@ -289,7 +322,7 @@ DEFINE_IDTENTRY_IRQ(common_interrupt)
/* entry code tells RCU that we're not quiescent. Check it. */
RCU_LOCKDEP_WARN(!rcu_is_watching(), "IRQ failed to wake up RCU");
- if (unlikely(call_irq_handler(vector, regs)))
+ if (unlikely(!call_irq_handler(vector, regs)))
apic_eoi();
set_irq_regs(old_regs);
@@ -380,61 +413,18 @@ void intel_posted_msi_init(void)
this_cpu_write(posted_msi_pi_desc.ndst, destination);
}
-/*
- * De-multiplexing posted interrupts is on the performance path, the code
- * below is written to optimize the cache performance based on the following
- * considerations:
- * 1.Posted interrupt descriptor (PID) fits in a cache line that is frequently
- * accessed by both CPU and IOMMU.
- * 2.During posted MSI processing, the CPU needs to do 64-bit read and xchg
- * for checking and clearing posted interrupt request (PIR), a 256 bit field
- * within the PID.
- * 3.On the other side, the IOMMU does atomic swaps of the entire PID cache
- * line when posting interrupts and setting control bits.
- * 4.The CPU can access the cache line a magnitude faster than the IOMMU.
- * 5.Each time the IOMMU does interrupt posting to the PIR will evict the PID
- * cache line. The cache line states after each operation are as follows:
- * CPU IOMMU PID Cache line state
- * ---------------------------------------------------------------
- *...read64 exclusive
- *...lock xchg64 modified
- *... post/atomic swap invalid
- *...-------------------------------------------------------------
- *
- * To reduce L1 data cache miss, it is important to avoid contention with
- * IOMMU's interrupt posting/atomic swap. Therefore, a copy of PIR is used
- * to dispatch interrupt handlers.
- *
- * In addition, the code is trying to keep the cache line state consistent
- * as much as possible. e.g. when making a copy and clearing the PIR
- * (assuming non-zero PIR bits are present in the entire PIR), it does:
- * read, read, read, read, xchg, xchg, xchg, xchg
- * instead of:
- * read, xchg, read, xchg, read, xchg, read, xchg
- */
-static __always_inline bool handle_pending_pir(u64 *pir, struct pt_regs *regs)
+static __always_inline bool handle_pending_pir(unsigned long *pir, struct pt_regs *regs)
{
- int i, vec = FIRST_EXTERNAL_VECTOR;
- unsigned long pir_copy[4];
- bool handled = false;
-
- for (i = 0; i < 4; i++)
- pir_copy[i] = pir[i];
-
- for (i = 0; i < 4; i++) {
- if (!pir_copy[i])
- continue;
+ unsigned long pir_copy[NR_PIR_WORDS];
+ int vec = FIRST_EXTERNAL_VECTOR;
- pir_copy[i] = arch_xchg(&pir[i], 0);
- handled = true;
- }
+ if (!pi_harvest_pir(pir, pir_copy))
+ return false;
- if (handled) {
- for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR)
- call_irq_handler(vec, regs);
- }
+ for_each_set_bit_from(vec, pir_copy, FIRST_SYSTEM_VECTOR)
+ call_irq_handler(vec, regs);
- return handled;
+ return true;
}
/*
@@ -464,7 +454,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification)
* MAX_POSTED_MSI_COALESCING_LOOP - 1 loops are executed here.
*/
while (++i < MAX_POSTED_MSI_COALESCING_LOOP) {
- if (!handle_pending_pir(pid->pir64, regs))
+ if (!handle_pending_pir(pid->pir, regs))
break;
}
@@ -479,7 +469,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_posted_msi_notification)
* process PIR bits one last time such that handling the new interrupts
* are not delayed until the next IRQ.
*/
- handle_pending_pir(pid->pir64, regs);
+ handle_pending_pir(pid->pir, regs);
apic_eoi();
irq_exit();
diff --git a/arch/x86/kernel/itmt.c b/arch/x86/kernel/itmt.c
index 9cea1fc36c18..243a769fdd97 100644
--- a/arch/x86/kernel/itmt.c
+++ b/arch/x86/kernel/itmt.c
@@ -59,6 +59,18 @@ static ssize_t sched_itmt_enabled_write(struct file *filp,
return result;
}
+static int sched_core_priority_show(struct seq_file *s, void *unused)
+{
+ int cpu;
+
+ seq_puts(s, "CPU #\tPriority\n");
+ for_each_possible_cpu(cpu)
+ seq_printf(s, "%d\t%d\n", cpu, arch_asym_cpu_priority(cpu));
+
+ return 0;
+}
+DEFINE_SHOW_ATTRIBUTE(sched_core_priority);
+
static const struct file_operations dfs_sched_itmt_fops = {
.read = debugfs_read_file_bool,
.write = sched_itmt_enabled_write,
@@ -67,6 +79,7 @@ static const struct file_operations dfs_sched_itmt_fops = {
};
static struct dentry *dfs_sched_itmt;
+static struct dentry *dfs_sched_core_prio;
/**
* sched_set_itmt_support() - Indicate platform supports ITMT
@@ -102,6 +115,14 @@ int sched_set_itmt_support(void)
return -ENOMEM;
}
+ dfs_sched_core_prio = debugfs_create_file("sched_core_priority", 0644,
+ arch_debugfs_dir, NULL,
+ &sched_core_priority_fops);
+ if (IS_ERR_OR_NULL(dfs_sched_core_prio)) {
+ dfs_sched_core_prio = NULL;
+ return -ENOMEM;
+ }
+
sched_itmt_capable = true;
sysctl_sched_itmt_enabled = 1;
@@ -133,6 +154,8 @@ void sched_clear_itmt_support(void)
debugfs_remove(dfs_sched_itmt);
dfs_sched_itmt = NULL;
+ debugfs_remove(dfs_sched_core_prio);
+ dfs_sched_core_prio = NULL;
if (sysctl_sched_itmt_enabled) {
/* disable sched_itmt if we are no longer ITMT capable */
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index cd8ed1edbf9e..9e9a591a5fec 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -49,7 +49,7 @@ static uint32_t jailhouse_cpuid_base(void)
!boot_cpu_has(X86_FEATURE_HYPERVISOR))
return 0;
- return hypervisor_cpuid_base("Jailhouse\0\0\0", 0);
+ return cpuid_base_hypervisor("Jailhouse\0\0\0", 0);
}
static uint32_t __init jailhouse_detect(void)
diff --git a/arch/x86/kernel/jump_label.c b/arch/x86/kernel/jump_label.c
index f5b8ef02d172..a7949a54a0ff 100644
--- a/arch/x86/kernel/jump_label.c
+++ b/arch/x86/kernel/jump_label.c
@@ -102,7 +102,7 @@ __jump_label_transform(struct jump_entry *entry,
return;
}
- text_poke_bp((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL);
+ smp_text_poke_single((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL);
}
static void __ref jump_label_transform(struct jump_entry *entry,
@@ -135,7 +135,7 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
mutex_lock(&text_mutex);
jlp = __jump_label_patch(entry, type);
- text_poke_queue((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL);
+ smp_text_poke_batch_add((void *)jump_entry_code(entry), jlp.code, jlp.size, NULL);
mutex_unlock(&text_mutex);
return true;
}
@@ -143,6 +143,6 @@ bool arch_jump_label_transform_queue(struct jump_entry *entry,
void arch_jump_label_transform_apply(void)
{
mutex_lock(&text_mutex);
- text_poke_finish();
+ smp_text_poke_batch_finish();
mutex_unlock(&text_mutex);
}
diff --git a/arch/x86/kernel/kexec-bzimage64.c b/arch/x86/kernel/kexec-bzimage64.c
index 68530fad05f7..24a41f0e0cf1 100644
--- a/arch/x86/kernel/kexec-bzimage64.c
+++ b/arch/x86/kernel/kexec-bzimage64.c
@@ -27,6 +27,8 @@
#include <asm/kexec-bzimage64.h>
#define MAX_ELFCOREHDR_STR_LEN 30 /* elfcorehdr=0x<64bit-value> */
+#define MAX_DMCRYPTKEYS_STR_LEN 31 /* dmcryptkeys=0x<64bit-value> */
+
/*
* Defines lowest physical address for various segments. Not sure where
@@ -76,6 +78,10 @@ static int setup_cmdline(struct kimage *image, struct boot_params *params,
if (image->type == KEXEC_TYPE_CRASH) {
len = sprintf(cmdline_ptr,
"elfcorehdr=0x%lx ", image->elf_load_addr);
+
+ if (image->dm_crypt_keys_addr != 0)
+ len += sprintf(cmdline_ptr + len,
+ "dmcryptkeys=0x%lx ", image->dm_crypt_keys_addr);
}
memcpy(cmdline_ptr + len, cmdline, cmdline_len);
cmdline_len += len;
@@ -233,6 +239,32 @@ setup_ima_state(const struct kimage *image, struct boot_params *params,
#endif /* CONFIG_IMA_KEXEC */
}
+static void setup_kho(const struct kimage *image, struct boot_params *params,
+ unsigned long params_load_addr,
+ unsigned int setup_data_offset)
+{
+ struct setup_data *sd = (void *)params + setup_data_offset;
+ struct kho_data *kho = (void *)sd + sizeof(*sd);
+
+ if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER))
+ return;
+
+ sd->type = SETUP_KEXEC_KHO;
+ sd->len = sizeof(struct kho_data);
+
+ /* Only add if we have all KHO images in place */
+ if (!image->kho.fdt || !image->kho.scratch)
+ return;
+
+ /* Add setup data */
+ kho->fdt_addr = image->kho.fdt;
+ kho->fdt_size = PAGE_SIZE;
+ kho->scratch_addr = image->kho.scratch->mem;
+ kho->scratch_size = image->kho.scratch->bufsz;
+ sd->next = params->hdr.setup_data;
+ params->hdr.setup_data = params_load_addr + setup_data_offset;
+}
+
static int
setup_boot_parameters(struct kimage *image, struct boot_params *params,
unsigned long params_load_addr,
@@ -312,6 +344,13 @@ setup_boot_parameters(struct kimage *image, struct boot_params *params,
sizeof(struct ima_setup_data);
}
+ if (IS_ENABLED(CONFIG_KEXEC_HANDOVER)) {
+ /* Setup space to store preservation metadata */
+ setup_kho(image, params, params_load_addr, setup_data_offset);
+ setup_data_offset += sizeof(struct setup_data) +
+ sizeof(struct kho_data);
+ }
+
/* Setup RNG seed */
setup_rng_seed(params, params_load_addr, setup_data_offset);
@@ -441,6 +480,19 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
ret = crash_load_segments(image);
if (ret)
return ERR_PTR(ret);
+ ret = crash_load_dm_crypt_keys(image);
+ if (ret == -ENOENT) {
+ kexec_dprintk("No dm crypt key to load\n");
+ } else if (ret) {
+ pr_err("Failed to load dm crypt keys\n");
+ return ERR_PTR(ret);
+ }
+ if (image->dm_crypt_keys_addr &&
+ cmdline_len + MAX_ELFCOREHDR_STR_LEN + MAX_DMCRYPTKEYS_STR_LEN >
+ header->cmdline_size) {
+ pr_err("Appending dmcryptkeys=<addr> to command line exceeds maximum allowed length\n");
+ return ERR_PTR(-EINVAL);
+ }
}
#endif
@@ -468,6 +520,8 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
efi_map_sz = efi_get_runtime_map_size();
params_cmdline_sz = sizeof(struct boot_params) + cmdline_len +
MAX_ELFCOREHDR_STR_LEN;
+ if (image->dm_crypt_keys_addr)
+ params_cmdline_sz += MAX_DMCRYPTKEYS_STR_LEN;
params_cmdline_sz = ALIGN(params_cmdline_sz, 16);
kbuf.bufsz = params_cmdline_sz + ALIGN(efi_map_sz, 16) +
sizeof(struct setup_data) +
@@ -479,6 +533,10 @@ static void *bzImage64_load(struct kimage *image, char *kernel,
kbuf.bufsz += sizeof(struct setup_data) +
sizeof(struct ima_setup_data);
+ if (IS_ENABLED(CONFIG_KEXEC_HANDOVER))
+ kbuf.bufsz += sizeof(struct setup_data) +
+ sizeof(struct kho_data);
+
params = kzalloc(kbuf.bufsz, GFP_KERNEL);
if (!params)
return ERR_PTR(-ENOMEM);
diff --git a/arch/x86/kernel/kgdb.c b/arch/x86/kernel/kgdb.c
index 102641fd2172..8b1a9733d13e 100644
--- a/arch/x86/kernel/kgdb.c
+++ b/arch/x86/kernel/kgdb.c
@@ -385,7 +385,7 @@ static void kgdb_disable_hw_debug(struct pt_regs *regs)
struct perf_event *bp;
/* Disable hardware debugging while we are in kgdb: */
- set_debugreg(0UL, 7);
+ set_debugreg(DR7_FIXED_1, 7);
for (i = 0; i < HBP_NUM; i++) {
if (!breakinfo[i].enabled)
continue;
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 09608fd93687..6079d15dab8c 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -481,24 +481,6 @@ static int prepare_singlestep(kprobe_opcode_t *buf, struct kprobe *p,
return len;
}
-/* Make page to RO mode when allocate it */
-void *alloc_insn_page(void)
-{
- void *page;
-
- page = execmem_alloc(EXECMEM_KPROBES, PAGE_SIZE);
- if (!page)
- return NULL;
-
- /*
- * TODO: Once additional kernel code protection mechanisms are set, ensure
- * that the page was not maliciously altered and it is still zeroed.
- */
- set_memory_rox((unsigned long)page, 1);
-
- return page;
-}
-
/* Kprobe x86 instruction emulation - only regs->ip or IF flag modifiers */
static void kprobe_emulate_ifmodifiers(struct kprobe *p, struct pt_regs *regs)
@@ -808,7 +790,7 @@ void arch_arm_kprobe(struct kprobe *p)
u8 int3 = INT3_INSN_OPCODE;
text_poke(p->addr, &int3, 1);
- text_poke_sync();
+ smp_text_poke_sync_each_cpu();
perf_event_text_poke(p->addr, &p->opcode, 1, &int3, 1);
}
@@ -818,7 +800,7 @@ void arch_disarm_kprobe(struct kprobe *p)
perf_event_text_poke(p->addr, &int3, 1, &p->opcode, 1);
text_poke(p->addr, &p->opcode, 1);
- text_poke_sync();
+ smp_text_poke_sync_each_cpu();
}
void arch_remove_kprobe(struct kprobe *p)
diff --git a/arch/x86/kernel/kprobes/opt.c b/arch/x86/kernel/kprobes/opt.c
index 36d6809c6c9e..0aabd4c4e2c4 100644
--- a/arch/x86/kernel/kprobes/opt.c
+++ b/arch/x86/kernel/kprobes/opt.c
@@ -488,7 +488,7 @@ void arch_optimize_kprobes(struct list_head *oplist)
insn_buff[0] = JMP32_INSN_OPCODE;
*(s32 *)(&insn_buff[1]) = rel;
- text_poke_bp(op->kp.addr, insn_buff, JMP32_INSN_SIZE, NULL);
+ smp_text_poke_single(op->kp.addr, insn_buff, JMP32_INSN_SIZE, NULL);
list_del_init(&op->list);
}
@@ -513,11 +513,11 @@ void arch_unoptimize_kprobe(struct optimized_kprobe *op)
JMP32_INSN_SIZE - INT3_INSN_SIZE);
text_poke(addr, new, INT3_INSN_SIZE);
- text_poke_sync();
+ smp_text_poke_sync_each_cpu();
text_poke(addr + INT3_INSN_SIZE,
new + INT3_INSN_SIZE,
JMP32_INSN_SIZE - INT3_INSN_SIZE);
- text_poke_sync();
+ smp_text_poke_sync_each_cpu();
perf_event_text_poke(op->kp.addr, old, JMP32_INSN_SIZE, new, JMP32_INSN_SIZE);
}
diff --git a/arch/x86/kernel/ksysfs.c b/arch/x86/kernel/ksysfs.c
index b68d4be9464e..d547de9b3ed8 100644
--- a/arch/x86/kernel/ksysfs.c
+++ b/arch/x86/kernel/ksysfs.c
@@ -40,7 +40,7 @@ static const struct bin_attribute boot_params_data_attr = {
.name = "data",
.mode = S_IRUGO,
},
- .read_new = boot_params_data_read,
+ .read = boot_params_data_read,
.size = sizeof(boot_params),
};
@@ -56,7 +56,7 @@ static const struct bin_attribute *const boot_params_data_attrs[] = {
static const struct attribute_group boot_params_attr_group = {
.attrs = boot_params_version_attrs,
- .bin_attrs_new = boot_params_data_attrs,
+ .bin_attrs = boot_params_data_attrs,
};
static int kobj_to_setup_data_nr(struct kobject *kobj, int *nr)
@@ -250,7 +250,7 @@ static struct bin_attribute data_attr __ro_after_init = {
.name = "data",
.mode = S_IRUGO,
},
- .read_new = setup_data_data_read,
+ .read = setup_data_data_read,
};
static struct attribute *setup_data_type_attrs[] = {
@@ -265,7 +265,7 @@ static const struct bin_attribute *const setup_data_data_attrs[] = {
static const struct attribute_group setup_data_attr_group = {
.attrs = setup_data_type_attrs,
- .bin_attrs_new = setup_data_data_attrs,
+ .bin_attrs = setup_data_data_attrs,
};
static int __init create_setup_data_node(struct kobject *parent,
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 3be9b3342c67..8ae750cde0c6 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -40,6 +40,7 @@
#include <asm/mtrr.h>
#include <asm/tlb.h>
#include <asm/cpuidle_haltpoll.h>
+#include <asm/msr.h>
#include <asm/ptrace.h>
#include <asm/reboot.h>
#include <asm/svm.h>
@@ -301,7 +302,7 @@ DEFINE_IDTENTRY_SYSVEC(sysvec_kvm_asyncpf_interrupt)
token = __this_cpu_read(apf_reason.token);
kvm_async_pf_task_wake(token);
__this_cpu_write(apf_reason.token, 0);
- wrmsrl(MSR_KVM_ASYNC_PF_ACK, 1);
+ wrmsrq(MSR_KVM_ASYNC_PF_ACK, 1);
}
set_irq_regs(old_regs);
@@ -327,7 +328,7 @@ static void kvm_register_steal_time(void)
if (!has_steal_clock)
return;
- wrmsrl(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
+ wrmsrq(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
pr_debug("stealtime: cpu %d, msr %llx\n", cpu,
(unsigned long long) slow_virt_to_phys(st));
}
@@ -361,9 +362,9 @@ static void kvm_guest_cpu_init(void)
if (kvm_para_has_feature(KVM_FEATURE_ASYNC_PF_VMEXIT))
pa |= KVM_ASYNC_PF_DELIVERY_AS_PF_VMEXIT;
- wrmsrl(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR);
+ wrmsrq(MSR_KVM_ASYNC_PF_INT, HYPERVISOR_CALLBACK_VECTOR);
- wrmsrl(MSR_KVM_ASYNC_PF_EN, pa);
+ wrmsrq(MSR_KVM_ASYNC_PF_EN, pa);
__this_cpu_write(async_pf_enabled, true);
pr_debug("setup async PF for cpu %d\n", smp_processor_id());
}
@@ -376,7 +377,7 @@ static void kvm_guest_cpu_init(void)
__this_cpu_write(kvm_apic_eoi, 0);
pa = slow_virt_to_phys(this_cpu_ptr(&kvm_apic_eoi))
| KVM_MSR_ENABLED;
- wrmsrl(MSR_KVM_PV_EOI_EN, pa);
+ wrmsrq(MSR_KVM_PV_EOI_EN, pa);
}
if (has_steal_clock)
@@ -388,7 +389,7 @@ static void kvm_pv_disable_apf(void)
if (!__this_cpu_read(async_pf_enabled))
return;
- wrmsrl(MSR_KVM_ASYNC_PF_EN, 0);
+ wrmsrq(MSR_KVM_ASYNC_PF_EN, 0);
__this_cpu_write(async_pf_enabled, false);
pr_debug("disable async PF for cpu %d\n", smp_processor_id());
@@ -399,7 +400,7 @@ static void kvm_disable_steal_time(void)
if (!has_steal_clock)
return;
- wrmsr(MSR_KVM_STEAL_TIME, 0, 0);
+ wrmsrq(MSR_KVM_STEAL_TIME, 0);
}
static u64 kvm_steal_clock(int cpu)
@@ -419,7 +420,7 @@ static u64 kvm_steal_clock(int cpu)
return steal;
}
-static inline void __set_percpu_decrypted(void *ptr, unsigned long size)
+static inline __init void __set_percpu_decrypted(void *ptr, unsigned long size)
{
early_set_memory_decrypted((unsigned long) ptr, size);
}
@@ -451,9 +452,9 @@ static void kvm_guest_cpu_offline(bool shutdown)
{
kvm_disable_steal_time();
if (kvm_para_has_feature(KVM_FEATURE_PV_EOI))
- wrmsrl(MSR_KVM_PV_EOI_EN, 0);
+ wrmsrq(MSR_KVM_PV_EOI_EN, 0);
if (kvm_para_has_feature(KVM_FEATURE_MIGRATION_CONTROL))
- wrmsrl(MSR_KVM_MIGRATION_CONTROL, 0);
+ wrmsrq(MSR_KVM_MIGRATION_CONTROL, 0);
kvm_pv_disable_apf();
if (!shutdown)
apf_task_wake_all();
@@ -615,7 +616,7 @@ static int __init setup_efi_kvm_sev_migration(void)
}
pr_info("%s : live migration enabled in EFI\n", __func__);
- wrmsrl(MSR_KVM_MIGRATION_CONTROL, KVM_MIGRATION_READY);
+ wrmsrq(MSR_KVM_MIGRATION_CONTROL, KVM_MIGRATION_READY);
return 1;
}
@@ -728,7 +729,7 @@ static int kvm_suspend(void)
#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL))
- rdmsrl(MSR_KVM_POLL_CONTROL, val);
+ rdmsrq(MSR_KVM_POLL_CONTROL, val);
has_guest_poll = !(val & 1);
#endif
return 0;
@@ -740,7 +741,7 @@ static void kvm_resume(void)
#ifdef CONFIG_ARCH_CPUIDLE_HALTPOLL
if (kvm_para_has_feature(KVM_FEATURE_POLL_CONTROL) && has_guest_poll)
- wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+ wrmsrq(MSR_KVM_POLL_CONTROL, 0);
#endif
}
@@ -874,7 +875,7 @@ static noinline uint32_t __kvm_cpuid_base(void)
return 0; /* So we don't blow up on old processors */
if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
- return hypervisor_cpuid_base(KVM_SIGNATURE, 0);
+ return cpuid_base_hypervisor(KVM_SIGNATURE, 0);
return 0;
}
@@ -975,7 +976,7 @@ static void __init kvm_init_platform(void)
* If not booted using EFI, enable Live migration support.
*/
if (!efi_enabled(EFI_BOOT))
- wrmsrl(MSR_KVM_MIGRATION_CONTROL,
+ wrmsrq(MSR_KVM_MIGRATION_CONTROL,
KVM_MIGRATION_READY);
}
kvmclock_init();
@@ -1124,12 +1125,12 @@ out:
static void kvm_disable_host_haltpoll(void *i)
{
- wrmsrl(MSR_KVM_POLL_CONTROL, 0);
+ wrmsrq(MSR_KVM_POLL_CONTROL, 0);
}
static void kvm_enable_host_haltpoll(void *i)
{
- wrmsrl(MSR_KVM_POLL_CONTROL, 1);
+ wrmsrq(MSR_KVM_POLL_CONTROL, 1);
}
void arch_haltpoll_enable(unsigned int cpu)
diff --git a/arch/x86/kernel/kvmclock.c b/arch/x86/kernel/kvmclock.c
index 5b2c15214a6b..ca0a49eeac4a 100644
--- a/arch/x86/kernel/kvmclock.c
+++ b/arch/x86/kernel/kvmclock.c
@@ -60,7 +60,7 @@ EXPORT_PER_CPU_SYMBOL_GPL(hv_clock_per_cpu);
*/
static void kvm_get_wallclock(struct timespec64 *now)
{
- wrmsrl(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock));
+ wrmsrq(msr_kvm_wall_clock, slow_virt_to_phys(&wall_clock));
preempt_disable();
pvclock_read_wallclock(&wall_clock, this_cpu_pvti(), now);
preempt_enable();
@@ -173,7 +173,7 @@ static void kvm_register_clock(char *txt)
return;
pa = slow_virt_to_phys(&src->pvti) | 0x01ULL;
- wrmsrl(msr_kvm_system_time, pa);
+ wrmsrq(msr_kvm_system_time, pa);
pr_debug("kvm-clock: cpu %d, msr %llx, %s", smp_processor_id(), pa, txt);
}
@@ -196,7 +196,7 @@ static void kvm_setup_secondary_clock(void)
void kvmclock_disable(void)
{
if (msr_kvm_system_time)
- native_write_msr(msr_kvm_system_time, 0, 0);
+ native_write_msr(msr_kvm_system_time, 0);
}
static void __init kvmclock_init_mem(void)
diff --git a/arch/x86/kernel/machine_kexec_64.c b/arch/x86/kernel/machine_kexec_64.c
index a68f5a0a9f37..697fb99406e6 100644
--- a/arch/x86/kernel/machine_kexec_64.c
+++ b/arch/x86/kernel/machine_kexec_64.c
@@ -76,6 +76,19 @@ map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p)
static int map_acpi_tables(struct x86_mapping_info *info, pgd_t *level4p) { return 0; }
#endif
+static int map_mmio_serial(struct x86_mapping_info *info, pgd_t *level4p)
+{
+ unsigned long mstart, mend;
+
+ if (!kexec_debug_8250_mmio32)
+ return 0;
+
+ mstart = kexec_debug_8250_mmio32 & PAGE_MASK;
+ mend = (kexec_debug_8250_mmio32 + PAGE_SIZE + 23) & PAGE_MASK;
+ pr_info("Map PCI serial at %lx - %lx\n", mstart, mend);
+ return kernel_ident_mapping_init(info, level4p, mstart, mend);
+}
+
#ifdef CONFIG_KEXEC_FILE
const struct kexec_file_ops * const kexec_file_loaders[] = {
&kexec_bzImage64_ops,
@@ -285,6 +298,10 @@ static int init_pgtable(struct kimage *image, unsigned long control_page)
if (result)
return result;
+ result = map_mmio_serial(&info, image->arch.pgd);
+ if (result)
+ return result;
+
/*
* This must be last because the intermediate page table pages it
* allocates will not be control pages and may overlap the image.
@@ -304,6 +321,24 @@ static void load_segments(void)
);
}
+static void prepare_debug_idt(unsigned long control_page, unsigned long vec_ofs)
+{
+ gate_desc idtentry = { 0 };
+ int i;
+
+ idtentry.bits.p = 1;
+ idtentry.bits.type = GATE_TRAP;
+ idtentry.segment = __KERNEL_CS;
+ idtentry.offset_low = (control_page & 0xFFFF) + vec_ofs;
+ idtentry.offset_middle = (control_page >> 16) & 0xFFFF;
+ idtentry.offset_high = control_page >> 32;
+
+ for (i = 0; i < 16; i++) {
+ kexec_debug_idt[i] = idtentry;
+ idtentry.offset_low += KEXEC_DEBUG_EXC_HANDLER_SIZE;
+ }
+}
+
int machine_kexec_prepare(struct kimage *image)
{
void *control_page = page_address(image->control_code_page);
@@ -321,6 +356,9 @@ int machine_kexec_prepare(struct kimage *image)
if (image->type == KEXEC_TYPE_DEFAULT)
kexec_pa_swap_page = page_to_pfn(image->swap_page) << PAGE_SHIFT;
+ prepare_debug_idt((unsigned long)__pa(control_page),
+ (unsigned long)kexec_debug_exc_vectors - reloc_start);
+
__memcpy(control_page, __relocate_kernel_start, reloc_end - reloc_start);
set_memory_rox((unsigned long)control_page, 1);
@@ -396,16 +434,10 @@ void __nocfi machine_kexec(struct kimage *image)
* with from a table in memory. At no other time is the
* descriptor table in memory accessed.
*
- * I take advantage of this here by force loading the
- * segments, before I zap the gdt with an invalid value.
+ * Take advantage of this here by force loading the segments,
+ * before the GDT is zapped with an invalid value.
*/
load_segments();
- /*
- * The gdt & idt are now invalid.
- * If you want to load them you must set up your own idt & gdt.
- */
- native_idt_invalidate();
- native_gdt_invalidate();
/* now call it */
image->start = relocate_kernel_ptr((unsigned long)image->head,
@@ -598,13 +630,35 @@ static void kexec_mark_crashkres(bool protect)
kexec_mark_range(control, crashk_res.end, protect);
}
+/* make the memory storing dm crypt keys in/accessible */
+static void kexec_mark_dm_crypt_keys(bool protect)
+{
+ unsigned long start_paddr, end_paddr;
+ unsigned int nr_pages;
+
+ if (kexec_crash_image->dm_crypt_keys_addr) {
+ start_paddr = kexec_crash_image->dm_crypt_keys_addr;
+ end_paddr = start_paddr + kexec_crash_image->dm_crypt_keys_sz - 1;
+ nr_pages = (PAGE_ALIGN(end_paddr) - PAGE_ALIGN_DOWN(start_paddr))/PAGE_SIZE;
+ if (protect)
+ set_memory_np((unsigned long)phys_to_virt(start_paddr), nr_pages);
+ else
+ __set_memory_prot(
+ (unsigned long)phys_to_virt(start_paddr),
+ nr_pages,
+ __pgprot(_PAGE_PRESENT | _PAGE_NX | _PAGE_RW));
+ }
+}
+
void arch_kexec_protect_crashkres(void)
{
kexec_mark_crashkres(true);
+ kexec_mark_dm_crypt_keys(true);
}
void arch_kexec_unprotect_crashkres(void)
{
+ kexec_mark_dm_crypt_keys(false);
kexec_mark_crashkres(false);
}
#endif
diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
index 1f54eedc3015..ef6104e7cc72 100644
--- a/arch/x86/kernel/mmconf-fam10h_64.c
+++ b/arch/x86/kernel/mmconf-fam10h_64.c
@@ -97,7 +97,7 @@ static void get_fam10h_pci_mmconf_base(void)
/* SYS_CFG */
address = MSR_AMD64_SYSCFG;
- rdmsrl(address, val);
+ rdmsrq(address, val);
/* TOP_MEM2 is not enabled? */
if (!(val & (1<<21))) {
@@ -105,7 +105,7 @@ static void get_fam10h_pci_mmconf_base(void)
} else {
/* TOP_MEM2 */
address = MSR_K8_TOP_MEM2;
- rdmsrl(address, val);
+ rdmsrq(address, val);
tom2 = max(val & 0xffffff800000ULL, 1ULL << 32);
}
@@ -177,7 +177,7 @@ void fam10h_check_enable_mmcfg(void)
return;
address = MSR_FAM10H_MMIO_CONF_BASE;
- rdmsrl(address, val);
+ rdmsrq(address, val);
/* try to make sure that AP's setting is identical to BSP setting */
if (val & FAM10H_MMIO_CONF_ENABLE) {
@@ -212,7 +212,7 @@ void fam10h_check_enable_mmcfg(void)
(FAM10H_MMIO_CONF_BUSRANGE_MASK<<FAM10H_MMIO_CONF_BUSRANGE_SHIFT));
val |= fam10h_pci_mmconf_base | (8 << FAM10H_MMIO_CONF_BUSRANGE_SHIFT) |
FAM10H_MMIO_CONF_ENABLE;
- wrmsrl(address, val);
+ wrmsrq(address, val);
}
static int __init set_check_enable_amd_mmconf(const struct dmi_system_id *d)
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index ff07558b7ebc..0ffbae902e2f 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -206,7 +206,7 @@ static int write_relocate_add(Elf64_Shdr *sechdrs,
write, apply);
if (!early) {
- text_poke_sync();
+ smp_text_poke_sync_each_cpu();
mutex_unlock(&text_mutex);
}
diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 9a95d00f1423..be93ec7255bf 100644
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -49,27 +49,20 @@ struct nmi_desc {
struct list_head head;
};
-static struct nmi_desc nmi_desc[NMI_MAX] =
-{
- {
- .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[0].lock),
- .head = LIST_HEAD_INIT(nmi_desc[0].head),
- },
- {
- .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[1].lock),
- .head = LIST_HEAD_INIT(nmi_desc[1].head),
- },
- {
- .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[2].lock),
- .head = LIST_HEAD_INIT(nmi_desc[2].head),
- },
- {
- .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[3].lock),
- .head = LIST_HEAD_INIT(nmi_desc[3].head),
- },
+#define NMI_DESC_INIT(type) { \
+ .lock = __RAW_SPIN_LOCK_UNLOCKED(&nmi_desc[type].lock), \
+ .head = LIST_HEAD_INIT(nmi_desc[type].head), \
+}
+static struct nmi_desc nmi_desc[NMI_MAX] = {
+ NMI_DESC_INIT(NMI_LOCAL),
+ NMI_DESC_INIT(NMI_UNKNOWN),
+ NMI_DESC_INIT(NMI_SERR),
+ NMI_DESC_INIT(NMI_IO_CHECK),
};
+#define nmi_to_desc(type) (&nmi_desc[type])
+
struct nmi_stats {
unsigned int normal;
unsigned int unknown;
@@ -91,6 +84,9 @@ static DEFINE_PER_CPU(struct nmi_stats, nmi_stats);
static int ignore_nmis __read_mostly;
int unknown_nmi_panic;
+int panic_on_unrecovered_nmi;
+int panic_on_io_nmi;
+
/*
* Prevent NMI reason port (0x61) being accessed simultaneously, can
* only be used in NMI handler.
@@ -104,8 +100,6 @@ static int __init setup_unknown_nmi_panic(char *str)
}
__setup("unknown_nmi_panic", setup_unknown_nmi_panic);
-#define nmi_to_desc(type) (&nmi_desc[type])
-
static u64 nmi_longest_ns = 1 * NSEC_PER_MSEC;
static int __init nmi_warning_debugfs(void)
@@ -125,12 +119,12 @@ static void nmi_check_duration(struct nmiaction *action, u64 duration)
action->max_duration = duration;
- remainder_ns = do_div(duration, (1000 * 1000));
- decimal_msecs = remainder_ns / 1000;
+ /* Convert duration from nsec to msec */
+ remainder_ns = do_div(duration, NSEC_PER_MSEC);
+ decimal_msecs = remainder_ns / NSEC_PER_USEC;
- printk_ratelimited(KERN_INFO
- "INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
- action->handler, duration, decimal_msecs);
+ pr_info_ratelimited("INFO: NMI handler (%ps) took too long to run: %lld.%03d msecs\n",
+ action->handler, duration, decimal_msecs);
}
static int nmi_handle(unsigned int type, struct pt_regs *regs)
@@ -333,10 +327,9 @@ unknown_nmi_error(unsigned char reason, struct pt_regs *regs)
int handled;
/*
- * Use 'false' as back-to-back NMIs are dealt with one level up.
- * Of course this makes having multiple 'unknown' handlers useless
- * as only the first one is ever run (unless it can actually determine
- * if it caused the NMI)
+ * As a last resort, let the "unknown" handlers make a
+ * best-effort attempt to figure out if they can claim
+ * responsibility for this Unknown NMI.
*/
handled = nmi_handle(NMI_UNKNOWN, regs);
if (handled) {
@@ -366,17 +359,18 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
bool b2b = false;
/*
- * CPU-specific NMI must be processed before non-CPU-specific
- * NMI, otherwise we may lose it, because the CPU-specific
- * NMI can not be detected/processed on other CPUs.
- */
-
- /*
- * Back-to-back NMIs are interesting because they can either
- * be two NMI or more than two NMIs (any thing over two is dropped
- * due to NMI being edge-triggered). If this is the second half
- * of the back-to-back NMI, assume we dropped things and process
- * more handlers. Otherwise reset the 'swallow' NMI behaviour
+ * Back-to-back NMIs are detected by comparing the RIP of the
+ * current NMI with that of the previous NMI. If it is the same,
+ * it is assumed that the CPU did not have a chance to jump back
+ * into a non-NMI context and execute code in between the two
+ * NMIs.
+ *
+ * They are interesting because even if there are more than two,
+ * only a maximum of two can be detected (anything over two is
+ * dropped due to NMI being edge-triggered). If this is the
+ * second half of the back-to-back NMI, assume we dropped things
+ * and process more handlers. Otherwise, reset the 'swallow' NMI
+ * behavior.
*/
if (regs->ip == __this_cpu_read(last_nmi_rip))
b2b = true;
@@ -390,6 +384,11 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
if (microcode_nmi_handler_enabled() && microcode_nmi_handler())
goto out;
+ /*
+ * CPU-specific NMI must be processed before non-CPU-specific
+ * NMI, otherwise we may lose it, because the CPU-specific
+ * NMI can not be detected/processed on other CPUs.
+ */
handled = nmi_handle(NMI_LOCAL, regs);
__this_cpu_add(nmi_stats.normal, handled);
if (handled) {
@@ -426,13 +425,14 @@ static noinstr void default_do_nmi(struct pt_regs *regs)
pci_serr_error(reason, regs);
else if (reason & NMI_REASON_IOCHK)
io_check_error(reason, regs);
-#ifdef CONFIG_X86_32
+
/*
* Reassert NMI in case it became active
* meanwhile as it's edge-triggered:
*/
- reassert_nmi();
-#endif
+ if (IS_ENABLED(CONFIG_X86_32))
+ reassert_nmi();
+
__this_cpu_add(nmi_stats.external, 1);
raw_spin_unlock(&nmi_reason_lock);
goto out;
@@ -751,4 +751,3 @@ void local_touch_nmi(void)
{
__this_cpu_write(last_nmi_rip, 0);
}
-EXPORT_SYMBOL_GPL(local_touch_nmi);
diff --git a/arch/x86/kernel/nmi_selftest.c b/arch/x86/kernel/nmi_selftest.c
index e93a8545c74d..a010e9d062bf 100644
--- a/arch/x86/kernel/nmi_selftest.c
+++ b/arch/x86/kernel/nmi_selftest.c
@@ -1,7 +1,5 @@
// SPDX-License-Identifier: GPL-2.0
/*
- * arch/x86/kernel/nmi-selftest.c
- *
* Testsuite for NMI: IPIs
*
* Started by Don Zickus:
@@ -30,7 +28,6 @@ static DECLARE_BITMAP(nmi_ipi_mask, NR_CPUS) __initdata;
static int __initdata testcase_total;
static int __initdata testcase_successes;
-static int __initdata expected_testcase_failures;
static int __initdata unexpected_testcase_failures;
static int __initdata unexpected_testcase_unknowns;
@@ -120,26 +117,22 @@ static void __init dotest(void (*testcase_fn)(void), int expected)
unexpected_testcase_failures++;
if (nmi_fail == FAILURE)
- printk(KERN_CONT "FAILED |");
+ pr_cont("FAILED |");
else if (nmi_fail == TIMEOUT)
- printk(KERN_CONT "TIMEOUT|");
+ pr_cont("TIMEOUT|");
else
- printk(KERN_CONT "ERROR |");
+ pr_cont("ERROR |");
dump_stack();
} else {
testcase_successes++;
- printk(KERN_CONT " ok |");
+ pr_cont(" ok |");
}
- testcase_total++;
+ pr_cont("\n");
+ testcase_total++;
reset_nmi();
}
-static inline void __init print_testname(const char *testname)
-{
- printk("%12s:", testname);
-}
-
void __init nmi_selftest(void)
{
init_nmi_testsuite();
@@ -147,38 +140,25 @@ void __init nmi_selftest(void)
/*
* Run the testsuite:
*/
- printk("----------------\n");
- printk("| NMI testsuite:\n");
- printk("--------------------\n");
+ pr_info("----------------\n");
+ pr_info("| NMI testsuite:\n");
+ pr_info("--------------------\n");
- print_testname("remote IPI");
+ pr_info("%12s:", "remote IPI");
dotest(remote_ipi, SUCCESS);
- printk(KERN_CONT "\n");
- print_testname("local IPI");
+
+ pr_info("%12s:", "local IPI");
dotest(local_ipi, SUCCESS);
- printk(KERN_CONT "\n");
cleanup_nmi_testsuite();
+ pr_info("--------------------\n");
if (unexpected_testcase_failures) {
- printk("--------------------\n");
- printk("BUG: %3d unexpected failures (out of %3d) - debugging disabled! |\n",
+ pr_info("BUG: %3d unexpected failures (out of %3d) - debugging disabled! |\n",
unexpected_testcase_failures, testcase_total);
- printk("-----------------------------------------------------------------\n");
- } else if (expected_testcase_failures && testcase_successes) {
- printk("--------------------\n");
- printk("%3d out of %3d testcases failed, as expected. |\n",
- expected_testcase_failures, testcase_total);
- printk("----------------------------------------------------\n");
- } else if (expected_testcase_failures && !testcase_successes) {
- printk("--------------------\n");
- printk("All %3d testcases failed, as expected. |\n",
- expected_testcase_failures);
- printk("----------------------------------------\n");
} else {
- printk("--------------------\n");
- printk("Good, all %3d testcases passed! |\n",
+ pr_info("Good, all %3d testcases passed! |\n",
testcase_successes);
- printk("---------------------------------\n");
}
+ pr_info("-----------------------------------------------------------------\n");
}
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 1ccd05d8999f..ab3e172dcc69 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -33,6 +33,7 @@
#include <asm/tlb.h>
#include <asm/io_bitmap.h>
#include <asm/gsseg.h>
+#include <asm/msr.h>
/* stub always returning 0. */
DEFINE_ASM_FUNC(paravirt_ret0, "xor %eax,%eax", .entry.text);
@@ -210,12 +211,10 @@ struct paravirt_patch_template pv_ops = {
.mmu.set_p4d = native_set_p4d,
-#if CONFIG_PGTABLE_LEVELS >= 5
.mmu.p4d_val = PTE_IDENT,
.mmu.make_p4d = PTE_IDENT,
.mmu.set_pgd = native_set_pgd,
-#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
.mmu.pte_val = PTE_IDENT,
.mmu.pgd_val = PTE_IDENT,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 962c3ce39323..1b7960cf6eb0 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -30,7 +30,7 @@
#include <linux/hw_breakpoint.h>
#include <linux/entry-common.h>
#include <asm/cpu.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/apic.h>
#include <linux/uaccess.h>
#include <asm/mwait.h>
@@ -52,6 +52,7 @@
#include <asm/unwind.h>
#include <asm/tdx.h>
#include <asm/mmu_context.h>
+#include <asm/msr.h>
#include <asm/shstk.h>
#include "process.h"
@@ -93,17 +94,12 @@ EXPORT_PER_CPU_SYMBOL_GPL(__tss_limit_invalid);
*/
int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
{
- /* init_task is not dynamically sized (incomplete FPU state) */
- if (unlikely(src == &init_task))
- memcpy_and_pad(dst, arch_task_struct_size, src, sizeof(init_task), 0);
- else
- memcpy(dst, src, arch_task_struct_size);
+ /* fpu_clone() will initialize the "dst_fpu" memory */
+ memcpy_and_pad(dst, arch_task_struct_size, src, sizeof(*dst), 0);
#ifdef CONFIG_VM86
dst->thread.vm86 = NULL;
#endif
- /* Drop the copied pointer to current's fpstate */
- dst->thread.fpu.fpstate = NULL;
return 0;
}
@@ -111,8 +107,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
#ifdef CONFIG_X86_64
void arch_release_task_struct(struct task_struct *tsk)
{
- if (fpu_state_size_dynamic())
- fpstate_free(&tsk->thread.fpu);
+ if (fpu_state_size_dynamic() && !(tsk->flags & (PF_KTHREAD | PF_USER_WORKER)))
+ fpstate_free(x86_task_fpu(tsk));
}
#endif
@@ -122,7 +118,6 @@ void arch_release_task_struct(struct task_struct *tsk)
void exit_thread(struct task_struct *tsk)
{
struct thread_struct *t = &tsk->thread;
- struct fpu *fpu = &t->fpu;
if (test_thread_flag(TIF_IO_BITMAP))
io_bitmap_exit(tsk);
@@ -130,7 +125,7 @@ void exit_thread(struct task_struct *tsk)
free_vm86(t);
shstk_free(tsk);
- fpu__drop(fpu);
+ fpu__drop(tsk);
}
static int set_new_tls(struct task_struct *p, unsigned long tls)
@@ -181,6 +176,7 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
frame->ret_addr = (unsigned long) ret_from_fork_asm;
p->thread.sp = (unsigned long) fork_frame;
p->thread.io_bitmap = NULL;
+ clear_tsk_thread_flag(p, TIF_IO_BITMAP);
p->thread.iopl_warn = 0;
memset(p->thread.ptrace_bps, 0, sizeof(p->thread.ptrace_bps));
@@ -338,13 +334,21 @@ DEFINE_PER_CPU(u64, msr_misc_features_shadow);
static void set_cpuid_faulting(bool on)
{
- u64 msrval;
- msrval = this_cpu_read(msr_misc_features_shadow);
- msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT;
- msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT);
- this_cpu_write(msr_misc_features_shadow, msrval);
- wrmsrl(MSR_MISC_FEATURES_ENABLES, msrval);
+ if (boot_cpu_data.x86_vendor == X86_VENDOR_INTEL) {
+ u64 msrval;
+
+ msrval = this_cpu_read(msr_misc_features_shadow);
+ msrval &= ~MSR_MISC_FEATURES_ENABLES_CPUID_FAULT;
+ msrval |= (on << MSR_MISC_FEATURES_ENABLES_CPUID_FAULT_BIT);
+ this_cpu_write(msr_misc_features_shadow, msrval);
+ wrmsrq(MSR_MISC_FEATURES_ENABLES, msrval);
+ } else if (boot_cpu_data.x86_vendor == X86_VENDOR_AMD) {
+ if (on)
+ msr_set_bit(MSR_K7_HWCR, MSR_K7_HWCR_CPUID_USER_DIS_BIT);
+ else
+ msr_clear_bit(MSR_K7_HWCR, MSR_K7_HWCR_CPUID_USER_DIS_BIT);
+ }
}
static void disable_cpuid(void)
@@ -469,6 +473,11 @@ void native_tss_update_io_bitmap(void)
} else {
struct io_bitmap *iobm = t->io_bitmap;
+ if (WARN_ON_ONCE(!iobm)) {
+ clear_thread_flag(TIF_IO_BITMAP);
+ native_tss_invalidate_io_bitmap();
+ }
+
/*
* Only copy bitmap data when the sequence number differs. The
* update time is accounted to the incoming task.
@@ -561,7 +570,7 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
if (!static_cpu_has(X86_FEATURE_ZEN)) {
msr |= ssbd_tif_to_amd_ls_cfg(tifn);
- wrmsrl(MSR_AMD64_LS_CFG, msr);
+ wrmsrq(MSR_AMD64_LS_CFG, msr);
return;
}
@@ -578,7 +587,7 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
raw_spin_lock(&st->shared_state->lock);
/* First sibling enables SSBD: */
if (!st->shared_state->disable_state)
- wrmsrl(MSR_AMD64_LS_CFG, msr);
+ wrmsrq(MSR_AMD64_LS_CFG, msr);
st->shared_state->disable_state++;
raw_spin_unlock(&st->shared_state->lock);
} else {
@@ -588,7 +597,7 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
raw_spin_lock(&st->shared_state->lock);
st->shared_state->disable_state--;
if (!st->shared_state->disable_state)
- wrmsrl(MSR_AMD64_LS_CFG, msr);
+ wrmsrq(MSR_AMD64_LS_CFG, msr);
raw_spin_unlock(&st->shared_state->lock);
}
}
@@ -597,7 +606,7 @@ static __always_inline void amd_set_core_ssb_state(unsigned long tifn)
{
u64 msr = x86_amd_ls_cfg_base | ssbd_tif_to_amd_ls_cfg(tifn);
- wrmsrl(MSR_AMD64_LS_CFG, msr);
+ wrmsrq(MSR_AMD64_LS_CFG, msr);
}
#endif
@@ -607,7 +616,7 @@ static __always_inline void amd_set_ssb_virt_state(unsigned long tifn)
* SSBD has the same definition in SPEC_CTRL and VIRT_SPEC_CTRL,
* so ssbd_tif_to_spec_ctrl() just works.
*/
- wrmsrl(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn));
+ wrmsrq(MSR_AMD64_VIRT_SPEC_CTRL, ssbd_tif_to_spec_ctrl(tifn));
}
/*
@@ -710,11 +719,11 @@ void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p)
arch_has_block_step()) {
unsigned long debugctl, msk;
- rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
debugctl &= ~DEBUGCTLMSR_BTF;
msk = tifn & _TIF_BLOCKSTEP;
debugctl |= (msk >> TIF_BLOCKSTEP) << DEBUGCTLMSR_BTF_SHIFT;
- wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
}
if ((tifp ^ tifn) & _TIF_NOTSC)
@@ -906,19 +915,24 @@ static __init bool prefer_mwait_c1_over_halt(void)
*/
static __cpuidle void mwait_idle(void)
{
+ if (need_resched())
+ return;
+
+ x86_idle_clear_cpu_buffers();
+
if (!current_set_polling_and_test()) {
- if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
- mb(); /* quirk */
- clflush((void *)&current_thread_info()->flags);
- mb(); /* quirk */
- }
+ const void *addr = &current_thread_info()->flags;
- __monitor((void *)&current_thread_info()->flags, 0, 0);
- if (!need_resched()) {
- __sti_mwait(0, 0);
- raw_local_irq_disable();
- }
+ alternative_input("", "clflush (%[addr])", X86_BUG_CLFLUSH_MONITOR, [addr] "a" (addr));
+ __monitor(addr, 0, 0);
+ if (need_resched())
+ goto out;
+
+ __sti_mwait(0, 0);
+ raw_local_irq_disable();
}
+
+out:
__current_clr_polling();
}
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 4636ef359973..3ef15c2f152f 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -93,7 +93,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
/* Only print out debug registers if they are in their non-default state. */
if ((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
- (d6 == DR6_RESERVED) && (d7 == 0x400))
+ (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))
return;
printk("%sDR0: %08lx DR1: %08lx DR2: %08lx DR3: %08lx\n",
@@ -160,8 +160,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
/* never put a printk in __switch_to... printk() calls wake_up*() indirectly */
- if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
- switch_fpu_prepare(prev_p, cpu);
+ switch_fpu(prev_p, cpu);
/*
* Save away %gs. No need to save %fs, as it was saved on the
@@ -208,10 +207,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
raw_cpu_write(current_task, next_p);
- switch_fpu_finish(next_p);
-
/* Load the Intel cache allocation PQR MSR. */
- resctrl_sched_in(next_p);
+ resctrl_arch_sched_in(next_p);
return prev_p;
}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 7196ca7048be..52a5c03c353c 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -57,6 +57,7 @@
#include <asm/unistd.h>
#include <asm/fsgsbase.h>
#include <asm/fred.h>
+#include <asm/msr.h>
#ifdef CONFIG_IA32_EMULATION
/* Not included via unistd.h */
#include <asm/unistd_32_ia32.h>
@@ -95,8 +96,8 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
return;
if (mode == SHOW_REGS_USER) {
- rdmsrl(MSR_FS_BASE, fs);
- rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
+ rdmsrq(MSR_FS_BASE, fs);
+ rdmsrq(MSR_KERNEL_GS_BASE, shadowgs);
printk("%sFS: %016lx GS: %016lx\n",
log_lvl, fs, shadowgs);
return;
@@ -107,9 +108,9 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
asm("movl %%fs,%0" : "=r" (fsindex));
asm("movl %%gs,%0" : "=r" (gsindex));
- rdmsrl(MSR_FS_BASE, fs);
- rdmsrl(MSR_GS_BASE, gs);
- rdmsrl(MSR_KERNEL_GS_BASE, shadowgs);
+ rdmsrq(MSR_FS_BASE, fs);
+ rdmsrq(MSR_GS_BASE, gs);
+ rdmsrq(MSR_KERNEL_GS_BASE, shadowgs);
cr0 = read_cr0();
cr2 = read_cr2();
@@ -132,7 +133,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode,
/* Only print out debug registers if they are in their non-default state. */
if (!((d0 == 0) && (d1 == 0) && (d2 == 0) && (d3 == 0) &&
- (d6 == DR6_RESERVED) && (d7 == 0x400))) {
+ (d6 == DR6_RESERVED) && (d7 == DR7_FIXED_1))) {
printk("%sDR0: %016lx DR1: %016lx DR2: %016lx\n",
log_lvl, d0, d1, d2);
printk("%sDR3: %016lx DR6: %016lx DR7: %016lx\n",
@@ -195,7 +196,7 @@ static noinstr unsigned long __rdgsbase_inactive(void)
native_swapgs();
} else {
instrumentation_begin();
- rdmsrl(MSR_KERNEL_GS_BASE, gsbase);
+ rdmsrq(MSR_KERNEL_GS_BASE, gsbase);
instrumentation_end();
}
@@ -221,7 +222,7 @@ static noinstr void __wrgsbase_inactive(unsigned long gsbase)
native_swapgs();
} else {
instrumentation_begin();
- wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
+ wrmsrq(MSR_KERNEL_GS_BASE, gsbase);
instrumentation_end();
}
}
@@ -353,7 +354,7 @@ static __always_inline void load_seg_legacy(unsigned short prev_index,
} else {
if (prev_index != next_index)
loadseg(which, next_index);
- wrmsrl(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE,
+ wrmsrq(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE,
next_base);
}
} else {
@@ -463,7 +464,7 @@ unsigned long x86_gsbase_read_cpu_inactive(void)
gsbase = __rdgsbase_inactive();
local_irq_restore(flags);
} else {
- rdmsrl(MSR_KERNEL_GS_BASE, gsbase);
+ rdmsrq(MSR_KERNEL_GS_BASE, gsbase);
}
return gsbase;
@@ -478,7 +479,7 @@ void x86_gsbase_write_cpu_inactive(unsigned long gsbase)
__wrgsbase_inactive(gsbase);
local_irq_restore(flags);
} else {
- wrmsrl(MSR_KERNEL_GS_BASE, gsbase);
+ wrmsrq(MSR_KERNEL_GS_BASE, gsbase);
}
}
@@ -616,8 +617,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
this_cpu_read(hardirq_stack_inuse));
- if (!test_tsk_thread_flag(prev_p, TIF_NEED_FPU_LOAD))
- switch_fpu_prepare(prev_p, cpu);
+ switch_fpu(prev_p, cpu);
/* We must save %fs and %gs before load_TLS() because
* %fs and %gs may be cleared by load_TLS().
@@ -671,8 +671,6 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
raw_cpu_write(current_task, next_p);
raw_cpu_write(cpu_current_top_of_stack, task_top_of_stack(next_p));
- switch_fpu_finish(next_p);
-
/* Reload sp0. */
update_task_stack(next_p);
@@ -707,7 +705,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
}
/* Load the Intel cache allocation PQR MSR. */
- resctrl_sched_in(next_p);
+ resctrl_arch_sched_in(next_p);
+
+ /* Reset hw history on AMD CPUs */
+ if (cpu_feature_enabled(X86_FEATURE_AMD_WORKLOAD_CLASS))
+ wrmsrl(MSR_AMD_WORKLOAD_HRST, 0x1);
return prev_p;
}
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 095f04bdabdc..3dcadc13f09a 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1236,7 +1236,7 @@ long compat_arch_ptrace(struct task_struct *child, compat_long_t request,
static struct user_regset x86_64_regsets[] __ro_after_init = {
[REGSET64_GENERAL] = {
- .core_note_type = NT_PRSTATUS,
+ USER_REGSET_NOTE_TYPE(PRSTATUS),
.n = sizeof(struct user_regs_struct) / sizeof(long),
.size = sizeof(long),
.align = sizeof(long),
@@ -1244,7 +1244,7 @@ static struct user_regset x86_64_regsets[] __ro_after_init = {
.set = genregs_set
},
[REGSET64_FP] = {
- .core_note_type = NT_PRFPREG,
+ USER_REGSET_NOTE_TYPE(PRFPREG),
.n = sizeof(struct fxregs_state) / sizeof(long),
.size = sizeof(long),
.align = sizeof(long),
@@ -1253,7 +1253,7 @@ static struct user_regset x86_64_regsets[] __ro_after_init = {
.set = xfpregs_set
},
[REGSET64_XSTATE] = {
- .core_note_type = NT_X86_XSTATE,
+ USER_REGSET_NOTE_TYPE(X86_XSTATE),
.size = sizeof(u64),
.align = sizeof(u64),
.active = xstateregs_active,
@@ -1261,7 +1261,7 @@ static struct user_regset x86_64_regsets[] __ro_after_init = {
.set = xstateregs_set
},
[REGSET64_IOPERM] = {
- .core_note_type = NT_386_IOPERM,
+ USER_REGSET_NOTE_TYPE(386_IOPERM),
.n = IO_BITMAP_LONGS,
.size = sizeof(long),
.align = sizeof(long),
@@ -1270,7 +1270,7 @@ static struct user_regset x86_64_regsets[] __ro_after_init = {
},
#ifdef CONFIG_X86_USER_SHADOW_STACK
[REGSET64_SSP] = {
- .core_note_type = NT_X86_SHSTK,
+ USER_REGSET_NOTE_TYPE(X86_SHSTK),
.n = 1,
.size = sizeof(u64),
.align = sizeof(u64),
@@ -1297,7 +1297,7 @@ static const struct user_regset_view user_x86_64_view = {
#if defined CONFIG_X86_32 || defined CONFIG_IA32_EMULATION
static struct user_regset x86_32_regsets[] __ro_after_init = {
[REGSET32_GENERAL] = {
- .core_note_type = NT_PRSTATUS,
+ USER_REGSET_NOTE_TYPE(PRSTATUS),
.n = sizeof(struct user_regs_struct32) / sizeof(u32),
.size = sizeof(u32),
.align = sizeof(u32),
@@ -1305,7 +1305,7 @@ static struct user_regset x86_32_regsets[] __ro_after_init = {
.set = genregs32_set
},
[REGSET32_FP] = {
- .core_note_type = NT_PRFPREG,
+ USER_REGSET_NOTE_TYPE(PRFPREG),
.n = sizeof(struct user_i387_ia32_struct) / sizeof(u32),
.size = sizeof(u32),
.align = sizeof(u32),
@@ -1314,7 +1314,7 @@ static struct user_regset x86_32_regsets[] __ro_after_init = {
.set = fpregs_set
},
[REGSET32_XFP] = {
- .core_note_type = NT_PRXFPREG,
+ USER_REGSET_NOTE_TYPE(PRXFPREG),
.n = sizeof(struct fxregs_state) / sizeof(u32),
.size = sizeof(u32),
.align = sizeof(u32),
@@ -1323,7 +1323,7 @@ static struct user_regset x86_32_regsets[] __ro_after_init = {
.set = xfpregs_set
},
[REGSET32_XSTATE] = {
- .core_note_type = NT_X86_XSTATE,
+ USER_REGSET_NOTE_TYPE(X86_XSTATE),
.size = sizeof(u64),
.align = sizeof(u64),
.active = xstateregs_active,
@@ -1331,7 +1331,7 @@ static struct user_regset x86_32_regsets[] __ro_after_init = {
.set = xstateregs_set
},
[REGSET32_TLS] = {
- .core_note_type = NT_386_TLS,
+ USER_REGSET_NOTE_TYPE(386_TLS),
.n = GDT_ENTRY_TLS_ENTRIES,
.bias = GDT_ENTRY_TLS_MIN,
.size = sizeof(struct user_desc),
@@ -1341,7 +1341,7 @@ static struct user_regset x86_32_regsets[] __ro_after_init = {
.set = regset_tls_set
},
[REGSET32_IOPERM] = {
- .core_note_type = NT_386_IOPERM,
+ USER_REGSET_NOTE_TYPE(386_IOPERM),
.n = IO_BITMAP_BYTES / sizeof(u32),
.size = sizeof(u32),
.align = sizeof(u32),
diff --git a/arch/x86/kernel/reboot_fixups_32.c b/arch/x86/kernel/reboot_fixups_32.c
index b7c0f142d026..4679ac0a03eb 100644
--- a/arch/x86/kernel/reboot_fixups_32.c
+++ b/arch/x86/kernel/reboot_fixups_32.c
@@ -27,7 +27,7 @@ static void cs5530a_warm_reset(struct pci_dev *dev)
static void cs5536_warm_reset(struct pci_dev *dev)
{
/* writing 1 to the LSB of this MSR causes a hard reset */
- wrmsrl(MSR_DIVIL_SOFT_RESET, 1ULL);
+ wrmsrq(MSR_DIVIL_SOFT_RESET, 1ULL);
udelay(50); /* shouldn't get here but be safe and spin a while */
}
diff --git a/arch/x86/kernel/relocate_kernel_32.S b/arch/x86/kernel/relocate_kernel_32.S
index c7c4b1917336..57276f134d12 100644
--- a/arch/x86/kernel/relocate_kernel_32.S
+++ b/arch/x86/kernel/relocate_kernel_32.S
@@ -263,17 +263,17 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
movl %edx, %edi
movl $1024, %ecx
- rep ; movsl
+ rep movsl
movl %ebp, %edi
movl %eax, %esi
movl $1024, %ecx
- rep ; movsl
+ rep movsl
movl %eax, %edi
movl %edx, %esi
movl $1024, %ecx
- rep ; movsl
+ rep movsl
lea PAGE_SIZE(%ebp), %esi
jmp 0b
diff --git a/arch/x86/kernel/relocate_kernel_64.S b/arch/x86/kernel/relocate_kernel_64.S
index ac058971a382..ea604f4d0b52 100644
--- a/arch/x86/kernel/relocate_kernel_64.S
+++ b/arch/x86/kernel/relocate_kernel_64.S
@@ -39,6 +39,8 @@ SYM_DATA(kexec_va_control_page, .quad 0)
SYM_DATA(kexec_pa_table_page, .quad 0)
SYM_DATA(kexec_pa_swap_page, .quad 0)
SYM_DATA_LOCAL(pa_backup_pages_map, .quad 0)
+SYM_DATA(kexec_debug_8250_mmio32, .quad 0)
+SYM_DATA(kexec_debug_8250_port, .word 0)
.balign 16
SYM_DATA_START_LOCAL(kexec_debug_gdt)
@@ -50,6 +52,11 @@ SYM_DATA_START_LOCAL(kexec_debug_gdt)
.quad 0x00cf92000000ffff /* __KERNEL_DS */
SYM_DATA_END_LABEL(kexec_debug_gdt, SYM_L_LOCAL, kexec_debug_gdt_end)
+ .balign 8
+SYM_DATA_START(kexec_debug_idt)
+ .skip 0x100, 0x00
+SYM_DATA_END(kexec_debug_idt)
+
.section .text..relocate_kernel,"ax";
.code64
SYM_CODE_START_NOALIGN(relocate_kernel)
@@ -72,8 +79,13 @@ SYM_CODE_START_NOALIGN(relocate_kernel)
pushq %r15
pushf
- /* zero out flags, and disable interrupts */
- pushq $0
+ /* Invalidate GDT/IDT, zero out flags */
+ pushq $0
+ pushq $0
+
+ lidt (%rsp)
+ lgdt (%rsp)
+ addq $8, %rsp
popfq
/* Switch to the identity mapped page tables */
@@ -139,6 +151,15 @@ SYM_CODE_START_LOCAL_NOALIGN(identity_mapped)
movq %ds, %rax
movq %rax, %ds
+ /* Now an IDTR on the stack to load the IDT the kernel created */
+ leaq kexec_debug_idt(%rip), %rsi
+ pushq %rsi
+ pushw $0xff
+ lidt (%rsp)
+ addq $10, %rsp
+
+ //int3
+
/*
* Clear X86_CR4_CET (if it was set) such that we can clear CR0_WP
* below.
@@ -342,20 +363,20 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
/* copy source page to swap page */
movq kexec_pa_swap_page(%rip), %rdi
movl $512, %ecx
- rep ; movsq
+ rep movsq
/* copy destination page to source page */
movq %rax, %rdi
movq %rdx, %rsi
movl $512, %ecx
- rep ; movsq
+ rep movsq
/* copy swap page to destination page */
movq %rdx, %rdi
movq kexec_pa_swap_page(%rip), %rsi
.Lnoswap:
movl $512, %ecx
- rep ; movsq
+ rep movsq
lea PAGE_SIZE(%rax), %rsi
jmp .Lloop
@@ -364,3 +385,222 @@ SYM_CODE_START_LOCAL_NOALIGN(swap_pages)
ret
int3
SYM_CODE_END(swap_pages)
+
+/*
+ * Generic 'print character' routine
+ * - %al: Character to be printed (may clobber %rax)
+ * - %rdx: MMIO address or port.
+ */
+#define XMTRDY 0x20
+
+#define TXR 0 /* Transmit register (WRITE) */
+#define LSR 5 /* Line Status */
+
+SYM_CODE_START_LOCAL_NOALIGN(pr_char_8250)
+ UNWIND_HINT_FUNC
+ ANNOTATE_NOENDBR
+ addw $LSR, %dx
+ xchg %al, %ah
+.Lxmtrdy_loop:
+ inb %dx, %al
+ testb $XMTRDY, %al
+ jnz .Lready
+ pause
+ jmp .Lxmtrdy_loop
+
+.Lready:
+ subw $LSR, %dx
+ xchg %al, %ah
+ outb %al, %dx
+pr_char_null:
+ ANNOTATE_NOENDBR
+
+ ANNOTATE_UNRET_SAFE
+ ret
+SYM_CODE_END(pr_char_8250)
+
+SYM_CODE_START_LOCAL_NOALIGN(pr_char_8250_mmio32)
+ UNWIND_HINT_FUNC
+ ANNOTATE_NOENDBR
+.Lxmtrdy_loop_mmio:
+ movb (LSR*4)(%rdx), %ah
+ testb $XMTRDY, %ah
+ jnz .Lready_mmio
+ pause
+ jmp .Lxmtrdy_loop_mmio
+
+.Lready_mmio:
+ movb %al, (%rdx)
+ ANNOTATE_UNRET_SAFE
+ ret
+SYM_CODE_END(pr_char_8250_mmio32)
+
+/*
+ * Load pr_char function pointer into %rsi and load %rdx with whatever
+ * that function wants to see there (typically port/MMIO address).
+ */
+.macro pr_setup
+ leaq pr_char_8250(%rip), %rsi
+ movw kexec_debug_8250_port(%rip), %dx
+ testw %dx, %dx
+ jnz 1f
+
+ leaq pr_char_8250_mmio32(%rip), %rsi
+ movq kexec_debug_8250_mmio32(%rip), %rdx
+ testq %rdx, %rdx
+ jnz 1f
+
+ leaq pr_char_null(%rip), %rsi
+1:
+.endm
+
+/* Print the nybble in %bl, clobber %rax */
+SYM_CODE_START_LOCAL_NOALIGN(pr_nybble)
+ UNWIND_HINT_FUNC
+ movb %bl, %al
+ nop
+ andb $0x0f, %al
+ addb $0x30, %al
+ cmpb $0x3a, %al
+ jb 1f
+ addb $('a' - '0' - 10), %al
+ ANNOTATE_RETPOLINE_SAFE
+1: jmp *%rsi
+SYM_CODE_END(pr_nybble)
+
+SYM_CODE_START_LOCAL_NOALIGN(pr_qword)
+ UNWIND_HINT_FUNC
+ movq $16, %rcx
+1: rolq $4, %rbx
+ call pr_nybble
+ loop 1b
+ movb $'\n', %al
+ ANNOTATE_RETPOLINE_SAFE
+ jmp *%rsi
+SYM_CODE_END(pr_qword)
+
+.macro print_reg a, b, c, d, r
+ movb $\a, %al
+ ANNOTATE_RETPOLINE_SAFE
+ call *%rsi
+ movb $\b, %al
+ ANNOTATE_RETPOLINE_SAFE
+ call *%rsi
+ movb $\c, %al
+ ANNOTATE_RETPOLINE_SAFE
+ call *%rsi
+ movb $\d, %al
+ ANNOTATE_RETPOLINE_SAFE
+ call *%rsi
+ movq \r, %rbx
+ call pr_qword
+.endm
+
+SYM_CODE_START_NOALIGN(kexec_debug_exc_vectors)
+ /* Each of these is 6 bytes. */
+.macro vec_err exc
+ UNWIND_HINT_ENTRY
+ . = kexec_debug_exc_vectors + (\exc * KEXEC_DEBUG_EXC_HANDLER_SIZE)
+ nop
+ nop
+ pushq $\exc
+ jmp exc_handler
+.endm
+
+.macro vec_noerr exc
+ UNWIND_HINT_ENTRY
+ . = kexec_debug_exc_vectors + (\exc * KEXEC_DEBUG_EXC_HANDLER_SIZE)
+ pushq $0
+ pushq $\exc
+ jmp exc_handler
+.endm
+
+ ANNOTATE_NOENDBR
+ vec_noerr 0 // #DE
+ vec_noerr 1 // #DB
+ vec_noerr 2 // #NMI
+ vec_noerr 3 // #BP
+ vec_noerr 4 // #OF
+ vec_noerr 5 // #BR
+ vec_noerr 6 // #UD
+ vec_noerr 7 // #NM
+ vec_err 8 // #DF
+ vec_noerr 9
+ vec_err 10 // #TS
+ vec_err 11 // #NP
+ vec_err 12 // #SS
+ vec_err 13 // #GP
+ vec_err 14 // #PF
+ vec_noerr 15
+SYM_CODE_END(kexec_debug_exc_vectors)
+
+SYM_CODE_START_LOCAL_NOALIGN(exc_handler)
+ /* No need for RET mitigations during kexec */
+ VALIDATE_UNRET_END
+
+ pushq %rax
+ pushq %rbx
+ pushq %rcx
+ pushq %rdx
+ pushq %rsi
+
+ /* Stack frame */
+#define EXC_SS 0x58 /* Architectural... */
+#define EXC_RSP 0x50
+#define EXC_EFLAGS 0x48
+#define EXC_CS 0x40
+#define EXC_RIP 0x38
+#define EXC_ERRORCODE 0x30 /* Either architectural or zero pushed by handler */
+#define EXC_EXCEPTION 0x28 /* Pushed by handler entry point */
+#define EXC_RAX 0x20 /* Pushed just above in exc_handler */
+#define EXC_RBX 0x18
+#define EXC_RCX 0x10
+#define EXC_RDX 0x08
+#define EXC_RSI 0x00
+
+ /* Set up %rdx/%rsi for debug output */
+ pr_setup
+
+ /* rip and exception info */
+ print_reg 'E', 'x', 'c', ':', EXC_EXCEPTION(%rsp)
+ print_reg 'E', 'r', 'r', ':', EXC_ERRORCODE(%rsp)
+ print_reg 'r', 'i', 'p', ':', EXC_RIP(%rsp)
+ print_reg 'r', 's', 'p', ':', EXC_RSP(%rsp)
+
+ /* We spilled these to the stack */
+ print_reg 'r', 'a', 'x', ':', EXC_RAX(%rsp)
+ print_reg 'r', 'b', 'x', ':', EXC_RBX(%rsp)
+ print_reg 'r', 'c', 'x', ':', EXC_RCX(%rsp)
+ print_reg 'r', 'd', 'x', ':', EXC_RDX(%rsp)
+ print_reg 'r', 's', 'i', ':', EXC_RSI(%rsp)
+
+ /* Other registers untouched */
+ print_reg 'r', 'd', 'i', ':', %rdi
+ print_reg 'r', '8', ' ', ':', %r8
+ print_reg 'r', '9', ' ', ':', %r9
+ print_reg 'r', '1', '0', ':', %r10
+ print_reg 'r', '1', '1', ':', %r11
+ print_reg 'r', '1', '2', ':', %r12
+ print_reg 'r', '1', '3', ':', %r13
+ print_reg 'r', '1', '4', ':', %r14
+ print_reg 'r', '1', '5', ':', %r15
+ print_reg 'c', 'r', '2', ':', %cr2
+
+ /* Only return from INT3 */
+ cmpq $3, EXC_EXCEPTION(%rsp)
+ jne .Ldie
+
+ popq %rsi
+ popq %rdx
+ popq %rcx
+ popq %rbx
+ popq %rax
+
+ addq $16, %rsp
+ iretq
+
+.Ldie:
+ hlt
+ jmp .Ldie
+
+SYM_CODE_END(exc_handler)
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 9d2a13b37833..1b2edd07a3e1 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -11,6 +11,7 @@
#include <linux/crash_dump.h>
#include <linux/dma-map-ops.h>
#include <linux/efi.h>
+#include <linux/hugetlb.h>
#include <linux/ima.h>
#include <linux/init_ohci1394_dma.h>
#include <linux/initrd.h>
@@ -18,21 +19,19 @@
#include <linux/memblock.h>
#include <linux/panic_notifier.h>
#include <linux/pci.h>
+#include <linux/random.h>
#include <linux/root_dev.h>
-#include <linux/hugetlb.h>
-#include <linux/tboot.h>
-#include <linux/usb/xhci-dbgp.h>
#include <linux/static_call.h>
#include <linux/swiotlb.h>
-#include <linux/random.h>
+#include <linux/tboot.h>
+#include <linux/usb/xhci-dbgp.h>
+#include <linux/vmalloc.h>
#include <uapi/linux/mount.h>
#include <xen/xen.h>
#include <asm/apic.h>
-#include <asm/efi.h>
-#include <asm/numa.h>
#include <asm/bios_ebda.h>
#include <asm/bugs.h>
#include <asm/cacheinfo.h>
@@ -47,18 +46,16 @@
#include <asm/mce.h>
#include <asm/memtype.h>
#include <asm/mtrr.h>
-#include <asm/realmode.h>
+#include <asm/nmi.h>
+#include <asm/numa.h>
#include <asm/olpc_ofw.h>
#include <asm/pci-direct.h>
#include <asm/prom.h>
#include <asm/proto.h>
+#include <asm/realmode.h>
#include <asm/thermal.h>
#include <asm/unwind.h>
#include <asm/vsyscall.h>
-#include <linux/vmalloc.h>
-#if defined(CONFIG_X86_LOCAL_APIC)
-#include <asm/nmi.h>
-#endif
/*
* max_low_pfn_mapped: highest directly mapped pfn < 4 GB
@@ -134,6 +131,7 @@ struct ist_info ist_info;
struct cpuinfo_x86 boot_cpu_data __read_mostly;
EXPORT_SYMBOL(boot_cpu_data);
+SYM_PIC_ALIAS(boot_cpu_data);
#if !defined(CONFIG_X86_PAE) || defined(CONFIG_X86_64)
__visible unsigned long mmu_cr4_features __ro_after_init;
@@ -151,6 +149,13 @@ int bootloader_type, bootloader_version;
static const struct ctl_table x86_sysctl_table[] = {
{
+ .procname = "unknown_nmi_panic",
+ .data = &unknown_nmi_panic,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
.procname = "panic_on_unrecovered_nmi",
.data = &panic_on_unrecovered_nmi,
.maxlen = sizeof(int),
@@ -185,15 +190,6 @@ static const struct ctl_table x86_sysctl_table[] = {
.mode = 0644,
.proc_handler = proc_dointvec,
},
-#if defined(CONFIG_X86_LOCAL_APIC)
- {
- .procname = "unknown_nmi_panic",
- .data = &unknown_nmi_panic,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
-#endif
#if defined(CONFIG_ACPI_SLEEP)
{
.procname = "acpi_video_flags",
@@ -217,8 +213,10 @@ arch_initcall(init_x86_sysctl);
*/
struct screen_info screen_info;
EXPORT_SYMBOL(screen_info);
+#if defined(CONFIG_FIRMWARE_EDID)
struct edid_info edid_info;
EXPORT_SYMBOL_GPL(edid_info);
+#endif
extern int root_mountflags;
@@ -286,8 +284,8 @@ static void __init cleanup_highmap(void)
static void __init reserve_brk(void)
{
if (_brk_end > _brk_start)
- memblock_reserve(__pa_symbol(_brk_start),
- _brk_end - _brk_start);
+ memblock_reserve_kern(__pa_symbol(_brk_start),
+ _brk_end - _brk_start);
/* Mark brk area as locked down and no longer taking any
new allocations */
@@ -360,7 +358,7 @@ static void __init early_reserve_initrd(void)
!ramdisk_image || !ramdisk_size)
return; /* No initrd provided by bootloader */
- memblock_reserve(ramdisk_image, ramdisk_end - ramdisk_image);
+ memblock_reserve_kern(ramdisk_image, ramdisk_end - ramdisk_image);
}
static void __init reserve_initrd(void)
@@ -413,7 +411,7 @@ static void __init add_early_ima_buffer(u64 phys_addr)
}
if (data->size) {
- memblock_reserve(data->addr, data->size);
+ memblock_reserve_kern(data->addr, data->size);
ima_kexec_buffer_phys = data->addr;
ima_kexec_buffer_size = data->size;
}
@@ -451,6 +449,29 @@ int __init ima_get_kexec_buffer(void **addr, size_t *size)
}
#endif
+static void __init add_kho(u64 phys_addr, u32 data_len)
+{
+ struct kho_data *kho;
+ u64 addr = phys_addr + sizeof(struct setup_data);
+ u64 size = data_len - sizeof(struct setup_data);
+
+ if (!IS_ENABLED(CONFIG_KEXEC_HANDOVER)) {
+ pr_warn("Passed KHO data, but CONFIG_KEXEC_HANDOVER not set. Ignoring.\n");
+ return;
+ }
+
+ kho = early_memremap(addr, size);
+ if (!kho) {
+ pr_warn("setup: failed to memremap kho data (0x%llx, 0x%llx)\n",
+ addr, size);
+ return;
+ }
+
+ kho_populate(kho->fdt_addr, kho->fdt_size, kho->scratch_addr, kho->scratch_size);
+
+ early_memunmap(kho, size);
+}
+
static void __init parse_setup_data(void)
{
struct setup_data *data;
@@ -479,6 +500,9 @@ static void __init parse_setup_data(void)
case SETUP_IMA:
add_early_ima_buffer(pa_data);
break;
+ case SETUP_KEXEC_KHO:
+ add_kho(pa_data, data_len);
+ break;
case SETUP_RNG_SEED:
data = early_memremap(pa_data, data_len);
add_bootloader_randomness(data->data, data->len);
@@ -503,7 +527,9 @@ static void __init parse_boot_params(void)
{
ROOT_DEV = old_decode_dev(boot_params.hdr.root_dev);
screen_info = boot_params.screen_info;
+#if defined(CONFIG_FIRMWARE_EDID)
edid_info = boot_params.edid_info;
+#endif
#ifdef CONFIG_X86_32
apm_info.bios = boot_params.apm_bios_info;
ist_info = boot_params.ist_info;
@@ -553,7 +579,7 @@ static void __init memblock_x86_reserve_range_setup_data(void)
len = sizeof(*data);
pa_next = data->next;
- memblock_reserve(pa_data, sizeof(*data) + data->len);
+ memblock_reserve_kern(pa_data, sizeof(*data) + data->len);
if (data->type == SETUP_INDIRECT) {
len += data->len;
@@ -567,7 +593,7 @@ static void __init memblock_x86_reserve_range_setup_data(void)
indirect = (struct setup_indirect *)data->data;
if (indirect->type != SETUP_INDIRECT)
- memblock_reserve(indirect->addr, indirect->len);
+ memblock_reserve_kern(indirect->addr, indirect->len);
}
pa_data = pa_next;
@@ -577,7 +603,7 @@ static void __init memblock_x86_reserve_range_setup_data(void)
static void __init arch_reserve_crashkernel(void)
{
- unsigned long long crash_base, crash_size, low_size = 0;
+ unsigned long long crash_base, crash_size, low_size = 0, cma_size = 0;
bool high = false;
int ret;
@@ -586,7 +612,7 @@ static void __init arch_reserve_crashkernel(void)
ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
&crash_size, &crash_base,
- &low_size, &high);
+ &low_size, &cma_size, &high);
if (ret)
return;
@@ -596,6 +622,7 @@ static void __init arch_reserve_crashkernel(void)
}
reserve_crashkernel_generic(crash_size, crash_base, low_size, high);
+ reserve_crashkernel_cma(cma_size);
}
static struct resource standard_io_resources[] = {
@@ -770,8 +797,8 @@ static void __init early_reserve_memory(void)
* __end_of_kernel_reserve symbol must be explicitly reserved with a
* separate memblock_reserve() or they will be discarded.
*/
- memblock_reserve(__pa_symbol(_text),
- (unsigned long)__end_of_kernel_reserve - (unsigned long)_text);
+ memblock_reserve_kern(__pa_symbol(_text),
+ (unsigned long)__end_of_kernel_reserve - (unsigned long)_text);
/*
* The first 4Kb of memory is a BIOS owned area, but generally it is
diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
index 059685612362..2ddf23387c7e 100644
--- a/arch/x86/kernel/shstk.c
+++ b/arch/x86/kernel/shstk.c
@@ -173,8 +173,8 @@ static int shstk_setup(void)
return PTR_ERR((void *)addr);
fpregs_lock_and_load();
- wrmsrl(MSR_IA32_PL3_SSP, addr + size);
- wrmsrl(MSR_IA32_U_CET, CET_SHSTK_EN);
+ wrmsrq(MSR_IA32_PL3_SSP, addr + size);
+ wrmsrq(MSR_IA32_U_CET, CET_SHSTK_EN);
fpregs_unlock();
shstk->base = addr;
@@ -239,7 +239,7 @@ static unsigned long get_user_shstk_addr(void)
fpregs_lock_and_load();
- rdmsrl(MSR_IA32_PL3_SSP, ssp);
+ rdmsrq(MSR_IA32_PL3_SSP, ssp);
fpregs_unlock();
@@ -372,7 +372,7 @@ int setup_signal_shadow_stack(struct ksignal *ksig)
return -EFAULT;
fpregs_lock_and_load();
- wrmsrl(MSR_IA32_PL3_SSP, ssp);
+ wrmsrq(MSR_IA32_PL3_SSP, ssp);
fpregs_unlock();
return 0;
@@ -396,7 +396,7 @@ int restore_signal_shadow_stack(void)
return err;
fpregs_lock_and_load();
- wrmsrl(MSR_IA32_PL3_SSP, ssp);
+ wrmsrq(MSR_IA32_PL3_SSP, ssp);
fpregs_unlock();
return 0;
@@ -460,7 +460,7 @@ static int wrss_control(bool enable)
return 0;
fpregs_lock_and_load();
- rdmsrl(MSR_IA32_U_CET, msrval);
+ rdmsrq(MSR_IA32_U_CET, msrval);
if (enable) {
features_set(ARCH_SHSTK_WRSS);
@@ -473,7 +473,7 @@ static int wrss_control(bool enable)
msrval &= ~CET_WRSS_EN;
}
- wrmsrl(MSR_IA32_U_CET, msrval);
+ wrmsrq(MSR_IA32_U_CET, msrval);
unlock:
fpregs_unlock();
@@ -492,8 +492,8 @@ static int shstk_disable(void)
fpregs_lock_and_load();
/* Disable WRSS too when disabling shadow stack */
- wrmsrl(MSR_IA32_U_CET, 0);
- wrmsrl(MSR_IA32_PL3_SSP, 0);
+ wrmsrq(MSR_IA32_U_CET, 0);
+ wrmsrq(MSR_IA32_PL3_SSP, 0);
fpregs_unlock();
shstk_free(current);
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index 5f441039b572..2404233336ab 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -255,7 +255,7 @@ static void
handle_signal(struct ksignal *ksig, struct pt_regs *regs)
{
bool stepping, failed;
- struct fpu *fpu = &current->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(current);
if (v8086_mode(regs))
save_v86_state((struct kernel_vm86_regs *) regs, VM86_SIGNAL);
@@ -423,14 +423,14 @@ bool sigaltstack_size_valid(size_t ss_size)
if (!fpu_state_size_dynamic() && !strict_sigaltstack_size)
return true;
- fsize += current->group_leader->thread.fpu.perm.__user_state_size;
+ fsize += x86_task_fpu(current->group_leader)->perm.__user_state_size;
if (likely(ss_size > fsize))
return true;
if (strict_sigaltstack_size)
return ss_size > fsize;
- mask = current->group_leader->thread.fpu.perm.__state_perm;
+ mask = x86_task_fpu(current->group_leader)->perm.__state_perm;
if (mask & XFEATURE_MASK_USER_DYNAMIC)
return ss_size > fsize;
diff --git a/arch/x86/kernel/signal_32.c b/arch/x86/kernel/signal_32.c
index 98123ff10506..42bbc42bd350 100644
--- a/arch/x86/kernel/signal_32.c
+++ b/arch/x86/kernel/signal_32.c
@@ -152,6 +152,8 @@ SYSCALL32_DEFINE0(sigreturn)
struct sigframe_ia32 __user *frame = (struct sigframe_ia32 __user *)(regs->sp-8);
sigset_t set;
+ prevent_single_step_upon_eretu(regs);
+
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
if (__get_user(set.sig[0], &frame->sc.oldmask)
@@ -175,6 +177,8 @@ SYSCALL32_DEFINE0(rt_sigreturn)
struct rt_sigframe_ia32 __user *frame;
sigset_t set;
+ prevent_single_step_upon_eretu(regs);
+
frame = (struct rt_sigframe_ia32 __user *)(regs->sp - 4);
if (!access_ok(frame, sizeof(*frame)))
diff --git a/arch/x86/kernel/signal_64.c b/arch/x86/kernel/signal_64.c
index ee9453891901..d483b585c6c6 100644
--- a/arch/x86/kernel/signal_64.c
+++ b/arch/x86/kernel/signal_64.c
@@ -250,6 +250,8 @@ SYSCALL_DEFINE0(rt_sigreturn)
sigset_t set;
unsigned long uc_flags;
+ prevent_single_step_upon_eretu(regs);
+
frame = (struct rt_sigframe __user *)(regs->sp - sizeof(long));
if (!access_ok(frame, sizeof(*frame)))
goto badframe;
@@ -366,6 +368,8 @@ COMPAT_SYSCALL_DEFINE0(x32_rt_sigreturn)
sigset_t set;
unsigned long uc_flags;
+ prevent_single_step_upon_eretu(regs);
+
frame = (struct rt_sigframe_x32 __user *)(regs->sp - 8);
if (!access_ok(frame, sizeof(*frame)))
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 18266cc3d98c..b014e6d229f9 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -299,3 +299,27 @@ struct smp_ops smp_ops = {
.send_call_func_single_ipi = native_send_call_func_single_ipi,
};
EXPORT_SYMBOL_GPL(smp_ops);
+
+int arch_cpu_rescan_dead_smt_siblings(void)
+{
+ enum cpuhp_smt_control old = cpu_smt_control;
+ int ret;
+
+ /*
+ * If SMT has been disabled and SMT siblings are in HLT, bring them back
+ * online and offline them again so that they end up in MWAIT proper.
+ *
+ * Called with hotplug enabled.
+ */
+ if (old != CPU_SMT_DISABLED && old != CPU_SMT_FORCE_DISABLED)
+ return 0;
+
+ ret = cpuhp_smt_enable();
+ if (ret)
+ return ret;
+
+ ret = cpuhp_smt_disable(old);
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(arch_cpu_rescan_dead_smt_siblings);
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index d6cf1e23c2a3..33e166f6ab12 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -64,7 +64,7 @@
#include <asm/acpi.h>
#include <asm/cacheinfo.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/desc.h>
#include <asm/nmi.h>
#include <asm/irq.h>
@@ -478,44 +478,41 @@ static int x86_cluster_flags(void)
*/
static bool x86_has_numa_in_package;
-static struct sched_domain_topology_level x86_topology[6];
-
-static void __init build_sched_topology(void)
-{
- int i = 0;
-
-#ifdef CONFIG_SCHED_SMT
- x86_topology[i++] = (struct sched_domain_topology_level){
- cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT)
- };
-#endif
+static struct sched_domain_topology_level x86_topology[] = {
+ SDTL_INIT(cpu_smt_mask, cpu_smt_flags, SMT),
#ifdef CONFIG_SCHED_CLUSTER
- x86_topology[i++] = (struct sched_domain_topology_level){
- cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS)
- };
+ SDTL_INIT(cpu_clustergroup_mask, x86_cluster_flags, CLS),
#endif
#ifdef CONFIG_SCHED_MC
- x86_topology[i++] = (struct sched_domain_topology_level){
- cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC)
- };
+ SDTL_INIT(cpu_coregroup_mask, x86_core_flags, MC),
#endif
+ SDTL_INIT(cpu_cpu_mask, x86_sched_itmt_flags, PKG),
+ { NULL },
+};
+
+static void __init build_sched_topology(void)
+{
+ struct sched_domain_topology_level *topology = x86_topology;
+
/*
- * When there is NUMA topology inside the package skip the PKG domain
- * since the NUMA domains will auto-magically create the right spanning
- * domains based on the SLIT.
+ * When there is NUMA topology inside the package invalidate the
+ * PKG domain since the NUMA domains will auto-magically create the
+ * right spanning domains based on the SLIT.
*/
- if (!x86_has_numa_in_package) {
- x86_topology[i++] = (struct sched_domain_topology_level){
- cpu_cpu_mask, x86_sched_itmt_flags, SD_INIT_NAME(PKG)
- };
+ if (x86_has_numa_in_package) {
+ unsigned int pkgdom = ARRAY_SIZE(x86_topology) - 2;
+
+ memset(&x86_topology[pkgdom], 0, sizeof(x86_topology[pkgdom]));
}
/*
- * There must be one trailing NULL entry left.
+ * Drop the SMT domains if there is only one thread per-core
+ * since it'll get degenerated by the scheduler anyways.
*/
- BUG_ON(i >= ARRAY_SIZE(x86_topology)-1);
+ if (cpu_smt_num_threads <= 1)
+ ++topology;
- set_sched_topology(x86_topology);
+ set_sched_topology(topology);
}
void set_cpu_sibling_map(int cpu)
@@ -695,7 +692,7 @@ static void send_init_sequence(u32 phys_apicid)
/*
* Wake up AP by INIT, INIT, STARTUP sequence.
*/
-static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip)
+static int wakeup_secondary_cpu_via_init(u32 phys_apicid, unsigned long start_eip, unsigned int cpu)
{
unsigned long send_status = 0, accept_status = 0;
int num_starts, j, maxlvt;
@@ -842,7 +839,7 @@ int common_cpu_up(unsigned int cpu, struct task_struct *idle)
* Returns zero if startup was successfully sent, else error code from
* ->wakeup_secondary_cpu.
*/
-static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle)
+static int do_boot_cpu(u32 apicid, unsigned int cpu, struct task_struct *idle)
{
unsigned long start_ip = real_mode_header->trampoline_start;
int ret;
@@ -896,11 +893,11 @@ static int do_boot_cpu(u32 apicid, int cpu, struct task_struct *idle)
* - Use an INIT boot APIC message
*/
if (apic->wakeup_secondary_cpu_64)
- ret = apic->wakeup_secondary_cpu_64(apicid, start_ip);
+ ret = apic->wakeup_secondary_cpu_64(apicid, start_ip, cpu);
else if (apic->wakeup_secondary_cpu)
- ret = apic->wakeup_secondary_cpu(apicid, start_ip);
+ ret = apic->wakeup_secondary_cpu(apicid, start_ip, cpu);
else
- ret = wakeup_secondary_cpu_via_init(apicid, start_ip);
+ ret = wakeup_secondary_cpu_via_init(apicid, start_ip, cpu);
/* If the wakeup mechanism failed, cleanup the warm reset vector */
if (ret)
@@ -1188,6 +1185,12 @@ void cpu_disable_common(void)
remove_siblinginfo(cpu);
+ /*
+ * Stop allowing kernel-mode FPU. This is needed so that if the CPU is
+ * brought online again, the initial state is not allowed:
+ */
+ this_cpu_write(kernel_fpu_allowed, false);
+
/* It's now safe to remove this processor from the online map */
lock_vector_lock();
remove_cpu_from_maps(cpu);
diff --git a/arch/x86/kernel/static_call.c b/arch/x86/kernel/static_call.c
index c3d7ff44b29a..378c388d1b31 100644
--- a/arch/x86/kernel/static_call.c
+++ b/arch/x86/kernel/static_call.c
@@ -108,7 +108,7 @@ static void __ref __static_call_transform(void *insn, enum insn_type type,
if (system_state == SYSTEM_BOOTING || modinit)
return text_poke_early(insn, code, size);
- text_poke_bp(insn, code, size, emulate);
+ smp_text_poke_single(insn, code, size, emulate);
}
static void __static_call_validate(u8 *insn, bool tail, bool tramp)
diff --git a/arch/x86/kernel/trace_clock.c b/arch/x86/kernel/trace_clock.c
index b8e7abe00b06..708d61743d15 100644
--- a/arch/x86/kernel/trace_clock.c
+++ b/arch/x86/kernel/trace_clock.c
@@ -4,7 +4,7 @@
*/
#include <asm/trace_clock.h>
#include <asm/barrier.h>
-#include <asm/msr.h>
+#include <asm/tsc.h>
/*
* trace_clock_x86_tsc(): A clock that is just the cycle counter.
diff --git a/arch/x86/kernel/tracepoint.c b/arch/x86/kernel/tracepoint.c
deleted file mode 100644
index 03ae1caaa878..000000000000
--- a/arch/x86/kernel/tracepoint.c
+++ /dev/null
@@ -1,21 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2013 Seiji Aguchi <seiji.aguchi@hds.com>
- */
-#include <linux/jump_label.h>
-#include <linux/atomic.h>
-
-#include <asm/trace/exceptions.h>
-
-DEFINE_STATIC_KEY_FALSE(trace_pagefault_key);
-
-int trace_pagefault_reg(void)
-{
- static_branch_inc(&trace_pagefault_key);
- return 0;
-}
-
-void trace_pagefault_unreg(void)
-{
- static_branch_dec(&trace_pagefault_key);
-}
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index 9f88b8a78e50..36354b470590 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -68,6 +68,7 @@
#include <asm/vdso.h>
#include <asm/tdx.h>
#include <asm/cfi.h>
+#include <asm/msr.h>
#ifdef CONFIG_X86_64
#include <asm/x86_init.h>
@@ -351,7 +352,7 @@ static noinstr bool handle_bug(struct pt_regs *regs)
case BUG_UD1_UBSAN:
if (IS_ENABLED(CONFIG_UBSAN_TRAP)) {
pr_crit("%s at %pS\n",
- report_ubsan_failure(regs, ud_imm),
+ report_ubsan_failure(ud_imm),
(void *)regs->ip);
}
break;
@@ -749,7 +750,7 @@ static bool try_fixup_enqcmd_gp(void)
if (current->pasid_activated)
return false;
- wrmsrl(MSR_IA32_PASID, pasid | MSR_IA32_PASID_VALID);
+ wrmsrq(MSR_IA32_PASID, pasid | MSR_IA32_PASID_VALID);
current->pasid_activated = 1;
return true;
@@ -882,16 +883,16 @@ static void do_int3_user(struct pt_regs *regs)
DEFINE_IDTENTRY_RAW(exc_int3)
{
/*
- * poke_int3_handler() is completely self contained code; it does (and
+ * smp_text_poke_int3_handler() is completely self contained code; it does (and
* must) *NOT* call out to anything, lest it hits upon yet another
* INT3.
*/
- if (poke_int3_handler(regs))
+ if (smp_text_poke_int3_handler(regs))
return;
/*
* irqentry_enter_from_user_mode() uses static_branch_{,un}likely()
- * and therefore can trigger INT3, hence poke_int3_handler() must
+ * and therefore can trigger INT3, hence smp_text_poke_int3_handler() must
* be done before. If the entry came from kernel mode, then use
* nmi_enter() because the INT3 could have been hit in any context
* including NMI.
@@ -1021,24 +1022,32 @@ static bool is_sysenter_singlestep(struct pt_regs *regs)
#endif
}
-static __always_inline unsigned long debug_read_clear_dr6(void)
+static __always_inline unsigned long debug_read_reset_dr6(void)
{
unsigned long dr6;
+ get_debugreg(dr6, 6);
+ dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
+
/*
* The Intel SDM says:
*
- * Certain debug exceptions may clear bits 0-3. The remaining
- * contents of the DR6 register are never cleared by the
- * processor. To avoid confusion in identifying debug
- * exceptions, debug handlers should clear the register before
- * returning to the interrupted task.
+ * Certain debug exceptions may clear bits 0-3 of DR6.
+ *
+ * BLD induced #DB clears DR6.BLD and any other debug
+ * exception doesn't modify DR6.BLD.
*
- * Keep it simple: clear DR6 immediately.
+ * RTM induced #DB clears DR6.RTM and any other debug
+ * exception sets DR6.RTM.
+ *
+ * To avoid confusion in identifying debug exceptions,
+ * debug handlers should set DR6.BLD and DR6.RTM, and
+ * clear other DR6 bits before returning.
+ *
+ * Keep it simple: write DR6 with its architectural reset
+ * value 0xFFFF0FF0, defined as DR6_RESERVED, immediately.
*/
- get_debugreg(dr6, 6);
set_debugreg(DR6_RESERVED, 6);
- dr6 ^= DR6_RESERVED; /* Flip to positive polarity */
return dr6;
}
@@ -1120,9 +1129,9 @@ static noinstr void exc_debug_kernel(struct pt_regs *regs, unsigned long dr6)
*/
unsigned long debugctl;
- rdmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ rdmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
debugctl |= DEBUGCTLMSR_BTF;
- wrmsrl(MSR_IA32_DEBUGCTLMSR, debugctl);
+ wrmsrq(MSR_IA32_DEBUGCTLMSR, debugctl);
}
/*
@@ -1238,13 +1247,13 @@ out:
/* IST stack entry */
DEFINE_IDTENTRY_DEBUG(exc_debug)
{
- exc_debug_kernel(regs, debug_read_clear_dr6());
+ exc_debug_kernel(regs, debug_read_reset_dr6());
}
/* User entry, runs on regular task stack */
DEFINE_IDTENTRY_DEBUG_USER(exc_debug)
{
- exc_debug_user(regs, debug_read_clear_dr6());
+ exc_debug_user(regs, debug_read_reset_dr6());
}
#ifdef CONFIG_X86_FRED
@@ -1263,7 +1272,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug)
{
/*
* FRED #DB stores DR6 on the stack in the format which
- * debug_read_clear_dr6() returns for the IDT entry points.
+ * debug_read_reset_dr6() returns for the IDT entry points.
*/
unsigned long dr6 = fred_event_data(regs);
@@ -1278,7 +1287,7 @@ DEFINE_FREDENTRY_DEBUG(exc_debug)
/* 32 bit does not have separate entry points. */
DEFINE_IDTENTRY_RAW(exc_debug)
{
- unsigned long dr6 = debug_read_clear_dr6();
+ unsigned long dr6 = debug_read_reset_dr6();
if (user_mode(regs))
exc_debug_user(regs, dr6);
@@ -1295,7 +1304,7 @@ DEFINE_IDTENTRY_RAW(exc_debug)
static void math_error(struct pt_regs *regs, int trapnr)
{
struct task_struct *task = current;
- struct fpu *fpu = &task->thread.fpu;
+ struct fpu *fpu = x86_task_fpu(task);
int si_code;
char *str = (trapnr == X86_TRAP_MF) ? "fpu exception" :
"simd exception";
@@ -1386,11 +1395,11 @@ static bool handle_xfd_event(struct pt_regs *regs)
if (!IS_ENABLED(CONFIG_X86_64) || !cpu_feature_enabled(X86_FEATURE_XFD))
return false;
- rdmsrl(MSR_IA32_XFD_ERR, xfd_err);
+ rdmsrq(MSR_IA32_XFD_ERR, xfd_err);
if (!xfd_err)
return false;
- wrmsrl(MSR_IA32_XFD_ERR, 0);
+ wrmsrq(MSR_IA32_XFD_ERR, 0);
/* Die if that happens in kernel space */
if (WARN_ON(!user_mode(regs)))
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 88e5a4ed9db3..87e749106dda 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -16,7 +16,7 @@
#include <linux/static_key.h>
#include <linux/static_call.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/hpet.h>
#include <asm/timer.h>
#include <asm/vgtod.h>
@@ -29,6 +29,7 @@
#include <asm/apic.h>
#include <asm/cpu_device_id.h>
#include <asm/i8259.h>
+#include <asm/msr.h>
#include <asm/topology.h>
#include <asm/uv/uv.h>
#include <asm/sev.h>
@@ -1098,7 +1099,7 @@ static void __init detect_art(void)
if (art_base_clk.denominator < ART_MIN_DENOMINATOR)
return;
- rdmsrl(MSR_IA32_TSC_ADJUST, art_base_clk.offset);
+ rdmsrq(MSR_IA32_TSC_ADJUST, art_base_clk.offset);
/* Make this sticky over multiple CPU init calls */
setup_force_cpu_cap(X86_FEATURE_ART);
diff --git a/arch/x86/kernel/tsc_sync.c b/arch/x86/kernel/tsc_sync.c
index 4334033658ed..ec3aa340d351 100644
--- a/arch/x86/kernel/tsc_sync.c
+++ b/arch/x86/kernel/tsc_sync.c
@@ -21,6 +21,7 @@
#include <linux/kernel.h>
#include <linux/smp.h>
#include <linux/nmi.h>
+#include <asm/msr.h>
#include <asm/tsc.h>
struct tsc_adjust {
@@ -65,12 +66,12 @@ void tsc_verify_tsc_adjust(bool resume)
adj->nextcheck = jiffies + HZ;
- rdmsrl(MSR_IA32_TSC_ADJUST, curval);
+ rdmsrq(MSR_IA32_TSC_ADJUST, curval);
if (adj->adjusted == curval)
return;
/* Restore the original value */
- wrmsrl(MSR_IA32_TSC_ADJUST, adj->adjusted);
+ wrmsrq(MSR_IA32_TSC_ADJUST, adj->adjusted);
if (!adj->warned || resume) {
pr_warn(FW_BUG "TSC ADJUST differs: CPU%u %lld --> %lld. Restoring\n",
@@ -142,7 +143,7 @@ static void tsc_sanitize_first_cpu(struct tsc_adjust *cur, s64 bootval,
if (likely(!tsc_async_resets)) {
pr_warn(FW_BUG "TSC ADJUST: CPU%u: %lld force to 0\n",
cpu, bootval);
- wrmsrl(MSR_IA32_TSC_ADJUST, 0);
+ wrmsrq(MSR_IA32_TSC_ADJUST, 0);
bootval = 0;
} else {
pr_info("TSC ADJUST: CPU%u: %lld NOT forced to 0\n",
@@ -165,7 +166,7 @@ bool __init tsc_store_and_check_tsc_adjust(bool bootcpu)
if (check_tsc_unstable())
return false;
- rdmsrl(MSR_IA32_TSC_ADJUST, bootval);
+ rdmsrq(MSR_IA32_TSC_ADJUST, bootval);
cur->bootval = bootval;
cur->nextcheck = jiffies + HZ;
tsc_sanitize_first_cpu(cur, bootval, smp_processor_id(), bootcpu);
@@ -187,7 +188,7 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu)
if (!boot_cpu_has(X86_FEATURE_TSC_ADJUST))
return false;
- rdmsrl(MSR_IA32_TSC_ADJUST, bootval);
+ rdmsrq(MSR_IA32_TSC_ADJUST, bootval);
cur->bootval = bootval;
cur->nextcheck = jiffies + HZ;
cur->warned = false;
@@ -229,7 +230,7 @@ bool tsc_store_and_check_tsc_adjust(bool bootcpu)
*/
if (bootval != ref->adjusted) {
cur->adjusted = ref->adjusted;
- wrmsrl(MSR_IA32_TSC_ADJUST, ref->adjusted);
+ wrmsrq(MSR_IA32_TSC_ADJUST, ref->adjusted);
}
/*
* We have the TSCs forced to be in sync on this package. Skip sync
@@ -518,7 +519,7 @@ retry:
pr_warn("TSC ADJUST compensate: CPU%u observed %lld warp. Adjust: %lld\n",
cpu, cur_max_warp, cur->adjusted);
- wrmsrl(MSR_IA32_TSC_ADJUST, cur->adjusted);
+ wrmsrq(MSR_IA32_TSC_ADJUST, cur->adjusted);
goto retry;
}
diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
index 9194695662b2..6d383839e839 100644
--- a/arch/x86/kernel/uprobes.c
+++ b/arch/x86/kernel/uprobes.c
@@ -840,6 +840,11 @@ static int branch_setup_xol_ops(struct arch_uprobe *auprobe, struct insn *insn)
insn_byte_t p;
int i;
+ /* x86_nops[insn->length]; same as jmp with .offs = 0 */
+ if (insn->length <= ASM_NOP_MAX &&
+ !memcmp(insn->kaddr, x86_nops[insn->length], insn->length))
+ goto setup;
+
switch (opc1) {
case 0xeb: /* jmp 8 */
case 0xe9: /* jmp 32 */
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index cda5f8362e9d..4fa0be732af1 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -79,11 +79,13 @@ const_cpu_current_top_of_stack = cpu_current_top_of_stack;
#define BSS_DECRYPTED \
. = ALIGN(PMD_SIZE); \
__start_bss_decrypted = .; \
+ __pi___start_bss_decrypted = .; \
*(.bss..decrypted); \
. = ALIGN(PAGE_SIZE); \
__start_bss_decrypted_unused = .; \
. = ALIGN(PMD_SIZE); \
__end_bss_decrypted = .; \
+ __pi___end_bss_decrypted = .; \
#else
@@ -128,6 +130,7 @@ SECTIONS
/* Text and read-only data */
.text : AT(ADDR(.text) - LOAD_OFFSET) {
_text = .;
+ __pi__text = .;
_stext = .;
ALIGN_ENTRY_TEXT_BEGIN
*(.text..__x86.rethunk_untrain)
@@ -391,6 +394,7 @@ SECTIONS
. = ALIGN(PAGE_SIZE); /* keep VO_INIT_SIZE page aligned */
_end = .;
+ __pi__end = .;
#ifdef CONFIG_AMD_MEM_ENCRYPT
/*
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index fe8ea8c097de..2c86673155c9 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -95,6 +95,8 @@ config KVM_SW_PROTECTED_VM
config KVM_INTEL
tristate "KVM for Intel (and compatible) processors support"
depends on KVM && IA32_FEAT_CTL
+ select KVM_GENERIC_PRIVATE_MEM if INTEL_TDX_HOST
+ select KVM_GENERIC_MEMORY_ATTRIBUTES if INTEL_TDX_HOST
help
Provides support for KVM on processors equipped with Intel's VT
extensions, a.k.a. Virtual Machine Extensions (VMX).
@@ -129,6 +131,16 @@ config X86_SGX_KVM
If unsure, say N.
+config KVM_INTEL_TDX
+ bool "Intel Trust Domain Extensions (TDX) support"
+ default y
+ depends on INTEL_TDX_HOST
+ help
+ Provides support for launching Intel Trust Domain Extensions (TDX)
+ confidential VMs on Intel processors.
+
+ If unsure, say N.
+
config KVM_AMD
tristate "KVM for AMD processors support"
depends on KVM && (CPU_SUP_AMD || CPU_SUP_HYGON)
@@ -154,6 +166,16 @@ config KVM_AMD_SEV
Encrypted State (SEV-ES), and Secure Encrypted Virtualization with
Secure Nested Paging (SEV-SNP) technologies on AMD processors.
+config KVM_IOAPIC
+ bool "I/O APIC, PIC, and PIT emulation"
+ default y
+ depends on KVM
+ help
+ Provides support for KVM to emulate an I/O APIC, PIC, and PIT, i.e.
+ for full in-kernel APIC emulation.
+
+ If unsure, say Y.
+
config KVM_SMM
bool "System Management Mode emulation"
default y
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index f9dddb8cb466..c4b8950c7abe 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -5,12 +5,11 @@ ccflags-$(CONFIG_KVM_WERROR) += -Werror
include $(srctree)/virt/kvm/Makefile.kvm
-kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \
- i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
- debugfs.o mmu/mmu.o mmu/page_track.o \
- mmu/spte.o
+kvm-y += x86.o emulate.o irq.o lapic.o cpuid.o pmu.o mtrr.o \
+ debugfs.o mmu/mmu.o mmu/page_track.o mmu/spte.o
kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o
+kvm-$(CONFIG_KVM_IOAPIC) += i8259.o i8254.o ioapic.o
kvm-$(CONFIG_KVM_HYPERV) += hyperv.o
kvm-$(CONFIG_KVM_XEN) += xen.o
kvm-$(CONFIG_KVM_SMM) += smm.o
@@ -20,6 +19,7 @@ kvm-intel-y += vmx/vmx.o vmx/vmenter.o vmx/pmu_intel.o vmx/vmcs12.o \
kvm-intel-$(CONFIG_X86_SGX_KVM) += vmx/sgx.o
kvm-intel-$(CONFIG_KVM_HYPERV) += vmx/hyperv.o vmx/hyperv_evmcs.o
+kvm-intel-$(CONFIG_KVM_INTEL_TDX) += vmx/tdx.o
kvm-amd-y += svm/svm.o svm/vmenter.o svm/pmu.o svm/nested.o svm/avic.o
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 571c906ffcbf..e2836a255b16 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -21,7 +21,7 @@
#include <asm/user.h>
#include <asm/fpu/xstate.h>
#include <asm/sgx.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include "cpuid.h"
#include "lapic.h"
#include "mmu.h"
@@ -81,17 +81,8 @@ u32 xstate_required_size(u64 xstate_bv, bool compacted)
return ret;
}
-/*
- * Magic value used by KVM when querying userspace-provided CPUID entries and
- * doesn't care about the CPIUD index because the index of the function in
- * question is not significant. Note, this magic value must have at least one
- * bit set in bits[63:32] and must be consumed as a u64 by cpuid_entry2_find()
- * to avoid false positives when processing guest CPUID input.
- */
-#define KVM_CPUID_INDEX_NOT_SIGNIFICANT -1ull
-
-static struct kvm_cpuid_entry2 *cpuid_entry2_find(struct kvm_vcpu *vcpu,
- u32 function, u64 index)
+struct kvm_cpuid_entry2 *kvm_find_cpuid_entry2(
+ struct kvm_cpuid_entry2 *entries, int nent, u32 function, u64 index)
{
struct kvm_cpuid_entry2 *e;
int i;
@@ -108,8 +99,8 @@ static struct kvm_cpuid_entry2 *cpuid_entry2_find(struct kvm_vcpu *vcpu,
*/
lockdep_assert_irqs_enabled();
- for (i = 0; i < vcpu->arch.cpuid_nent; i++) {
- e = &vcpu->arch.cpuid_entries[i];
+ for (i = 0; i < nent; i++) {
+ e = &entries[i];
if (e->function != function)
continue;
@@ -140,26 +131,7 @@ static struct kvm_cpuid_entry2 *cpuid_entry2_find(struct kvm_vcpu *vcpu,
return NULL;
}
-
-struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu,
- u32 function, u32 index)
-{
- return cpuid_entry2_find(vcpu, function, index);
-}
-EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry_index);
-
-struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
- u32 function)
-{
- return cpuid_entry2_find(vcpu, function, KVM_CPUID_INDEX_NOT_SIGNIFICANT);
-}
-EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry);
-
-/*
- * cpuid_entry2_find() and KVM_CPUID_INDEX_NOT_SIGNIFICANT should never be used
- * directly outside of kvm_find_cpuid_entry() and kvm_find_cpuid_entry_index().
- */
-#undef KVM_CPUID_INDEX_NOT_SIGNIFICANT
+EXPORT_SYMBOL_GPL(kvm_find_cpuid_entry2);
static int kvm_check_cpuid(struct kvm_vcpu *vcpu)
{
@@ -236,7 +208,7 @@ static struct kvm_hypervisor_cpuid kvm_get_hypervisor_cpuid(struct kvm_vcpu *vcp
struct kvm_cpuid_entry2 *entry;
u32 base;
- for_each_possible_hypervisor_cpuid_base(base) {
+ for_each_possible_cpuid_base_hypervisor(base) {
entry = kvm_find_cpuid_entry(vcpu, base);
if (entry) {
@@ -492,6 +464,20 @@ not_found:
return 36;
}
+int cpuid_query_maxguestphyaddr(struct kvm_vcpu *vcpu)
+{
+ struct kvm_cpuid_entry2 *best;
+
+ best = kvm_find_cpuid_entry(vcpu, 0x80000000);
+ if (!best || best->eax < 0x80000008)
+ goto not_found;
+ best = kvm_find_cpuid_entry(vcpu, 0x80000008);
+ if (best)
+ return (best->eax >> 16) & 0xff;
+not_found:
+ return 0;
+}
+
/*
* This "raw" version returns the reserved GPA bits without any adjustments for
* encryption technologies that usurp bits. The raw mask should be used if and
@@ -992,6 +978,8 @@ void kvm_set_cpu_caps(void)
F(FZRM),
F(FSRS),
F(FSRC),
+ F(WRMSRNS),
+ X86_64_F(LKGS),
F(AMX_FP16),
F(AVX_IFMA),
F(LAM),
@@ -1107,6 +1095,7 @@ void kvm_set_cpu_caps(void)
F(AMD_SSB_NO),
F(AMD_STIBP),
F(AMD_STIBP_ALWAYS_ON),
+ F(AMD_IBRS_SAME_MODE),
F(AMD_PSFD),
F(AMD_IBPB_RET),
);
@@ -1164,6 +1153,7 @@ void kvm_set_cpu_caps(void)
kvm_cpu_cap_init(CPUID_8000_0021_EAX,
F(NO_NESTED_DATA_BP),
+ F(WRMSR_XX_BASE_NS),
/*
* Synthesize "LFENCE is serializing" into the AMD-defined entry
* in KVM's supported CPUID, i.e. if the feature is reported as
@@ -1176,17 +1166,27 @@ void kvm_set_cpu_caps(void)
*/
SYNTHESIZED_F(LFENCE_RDTSC),
/* SmmPgCfgLock */
+ /* 4: Resv */
+ SYNTHESIZED_F(VERW_CLEAR),
F(NULL_SEL_CLR_BASE),
+ /* UpperAddressIgnore */
F(AUTOIBRS),
+ F(PREFETCHI),
EMULATED_F(NO_SMM_CTL_MSR),
/* PrefetchCtlMsr */
- F(WRMSR_XX_BASE_NS),
+ /* GpOnUserCpuid */
+ /* EPSF */
SYNTHESIZED_F(SBPB),
SYNTHESIZED_F(IBPB_BRTYPE),
SYNTHESIZED_F(SRSO_NO),
F(SRSO_USER_KERNEL_NO),
);
+ kvm_cpu_cap_init(CPUID_8000_0021_ECX,
+ SYNTHESIZED_F(TSA_SQ_NO),
+ SYNTHESIZED_F(TSA_L1_NO),
+ );
+
kvm_cpu_cap_init(CPUID_8000_0022_EAX,
F(PERFMON_V2),
);
@@ -1756,8 +1756,9 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
entry->eax = entry->ebx = entry->ecx = entry->edx = 0;
break;
case 0x80000021:
- entry->ebx = entry->ecx = entry->edx = 0;
+ entry->ebx = entry->edx = 0;
cpuid_entry_override(entry, CPUID_8000_0021_EAX);
+ cpuid_entry_override(entry, CPUID_8000_0021_ECX);
break;
/* AMD Extended Performance Monitoring and Debug */
case 0x80000022: {
diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h
index d2884162a46a..d3f5ae15a7ca 100644
--- a/arch/x86/kvm/cpuid.h
+++ b/arch/x86/kvm/cpuid.h
@@ -11,10 +11,34 @@ extern u32 kvm_cpu_caps[NR_KVM_CPU_CAPS] __read_mostly;
void kvm_set_cpu_caps(void);
void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu);
-struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu,
- u32 function, u32 index);
-struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
- u32 function);
+struct kvm_cpuid_entry2 *kvm_find_cpuid_entry2(struct kvm_cpuid_entry2 *entries,
+ int nent, u32 function, u64 index);
+/*
+ * Magic value used by KVM when querying userspace-provided CPUID entries and
+ * doesn't care about the CPIUD index because the index of the function in
+ * question is not significant. Note, this magic value must have at least one
+ * bit set in bits[63:32] and must be consumed as a u64 by kvm_find_cpuid_entry2()
+ * to avoid false positives when processing guest CPUID input.
+ *
+ * KVM_CPUID_INDEX_NOT_SIGNIFICANT should never be used directly outside of
+ * kvm_find_cpuid_entry2() and kvm_find_cpuid_entry().
+ */
+#define KVM_CPUID_INDEX_NOT_SIGNIFICANT -1ull
+
+static inline struct kvm_cpuid_entry2 *kvm_find_cpuid_entry_index(struct kvm_vcpu *vcpu,
+ u32 function, u32 index)
+{
+ return kvm_find_cpuid_entry2(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent,
+ function, index);
+}
+
+static inline struct kvm_cpuid_entry2 *kvm_find_cpuid_entry(struct kvm_vcpu *vcpu,
+ u32 function)
+{
+ return kvm_find_cpuid_entry2(vcpu->arch.cpuid_entries, vcpu->arch.cpuid_nent,
+ function, KVM_CPUID_INDEX_NOT_SIGNIFICANT);
+}
+
int kvm_dev_ioctl_get_cpuid(struct kvm_cpuid2 *cpuid,
struct kvm_cpuid_entry2 __user *entries,
unsigned int type);
@@ -34,6 +58,7 @@ void __init kvm_init_xstate_sizes(void);
u32 xstate_required_size(u64 xstate_bv, bool compacted);
int cpuid_query_maxphyaddr(struct kvm_vcpu *vcpu);
+int cpuid_query_maxguestphyaddr(struct kvm_vcpu *vcpu);
u64 kvm_vcpu_reserved_gpa_bits_raw(struct kvm_vcpu *vcpu);
static inline int cpuid_maxphyaddr(struct kvm_vcpu *vcpu)
diff --git a/arch/x86/kvm/hyperv.c b/arch/x86/kvm/hyperv.c
index 24f0318c50d7..72b19a88a776 100644
--- a/arch/x86/kvm/hyperv.c
+++ b/arch/x86/kvm/hyperv.c
@@ -497,15 +497,19 @@ static int synic_set_irq(struct kvm_vcpu_hv_synic *synic, u32 sint)
return ret;
}
-int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vpidx, u32 sint)
+int kvm_hv_synic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+ int irq_source_id, int level, bool line_status)
{
struct kvm_vcpu_hv_synic *synic;
- synic = synic_get(kvm, vpidx);
+ if (!level)
+ return -1;
+
+ synic = synic_get(kvm, e->hv_sint.vcpu);
if (!synic)
return -EINVAL;
- return synic_set_irq(synic, sint);
+ return synic_set_irq(synic, e->hv_sint.sint);
}
void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector)
@@ -1979,6 +1983,9 @@ int kvm_hv_vcpu_flush_tlb(struct kvm_vcpu *vcpu)
if (entries[i] == KVM_HV_TLB_FLUSHALL_ENTRY)
goto out_flush_all;
+ if (is_noncanonical_invlpg_address(entries[i], vcpu))
+ continue;
+
/*
* Lower 12 bits of 'address' encode the number of additional
* pages to flush.
@@ -2001,11 +2008,11 @@ out_flush_all:
static u64 kvm_hv_flush_tlb(struct kvm_vcpu *vcpu, struct kvm_hv_hcall *hc)
{
struct kvm_vcpu_hv *hv_vcpu = to_hv_vcpu(vcpu);
+ unsigned long *vcpu_mask = hv_vcpu->vcpu_mask;
u64 *sparse_banks = hv_vcpu->sparse_banks;
struct kvm *kvm = vcpu->kvm;
struct hv_tlb_flush_ex flush_ex;
struct hv_tlb_flush flush;
- DECLARE_BITMAP(vcpu_mask, KVM_MAX_VCPUS);
struct kvm_vcpu_hv_tlb_flush_fifo *tlb_flush_fifo;
/*
* Normally, there can be no more than 'KVM_HV_TLB_FLUSH_FIFO_SIZE'
diff --git a/arch/x86/kvm/hyperv.h b/arch/x86/kvm/hyperv.h
index 913bfc96959c..6ce160ffa678 100644
--- a/arch/x86/kvm/hyperv.h
+++ b/arch/x86/kvm/hyperv.h
@@ -103,7 +103,8 @@ static inline bool kvm_hv_hypercall_enabled(struct kvm_vcpu *vcpu)
int kvm_hv_hypercall(struct kvm_vcpu *vcpu);
void kvm_hv_irq_routing_update(struct kvm *kvm);
-int kvm_hv_synic_set_irq(struct kvm *kvm, u32 vcpu_id, u32 sint);
+int kvm_hv_synic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+ int irq_source_id, int level, bool line_status);
void kvm_hv_synic_send_eoi(struct kvm_vcpu *vcpu, int vector);
int kvm_hv_activate_synic(struct kvm_vcpu *vcpu, bool dont_zero_synic_pages);
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 739aa6c0d0c3..850972deac8e 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -248,8 +248,8 @@ static void pit_do_work(struct kthread_work *work)
if (atomic_read(&ps->reinject) && !atomic_xchg(&ps->irq_ack, 0))
return;
- kvm_set_irq(kvm, pit->irq_source_id, 0, 1, false);
- kvm_set_irq(kvm, pit->irq_source_id, 0, 0, false);
+ kvm_set_irq(kvm, KVM_PIT_IRQ_SOURCE_ID, 0, 1, false);
+ kvm_set_irq(kvm, KVM_PIT_IRQ_SOURCE_ID, 0, 0, false);
/*
* Provides NMI watchdog support via Virtual Wire mode.
@@ -288,7 +288,7 @@ static inline void kvm_pit_reset_reinject(struct kvm_pit *pit)
atomic_set(&pit->pit_state.irq_ack, 1);
}
-void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject)
+static void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject)
{
struct kvm_kpit_state *ps = &pit->pit_state;
struct kvm *kvm = pit->kvm;
@@ -400,8 +400,8 @@ static void pit_load_count(struct kvm_pit *pit, int channel, u32 val)
}
}
-void kvm_pit_load_count(struct kvm_pit *pit, int channel, u32 val,
- int hpet_legacy_start)
+static void kvm_pit_load_count(struct kvm_pit *pit, int channel, u32 val,
+ int hpet_legacy_start)
{
u8 saved_mode;
@@ -641,7 +641,7 @@ static void kvm_pit_reset(struct kvm_pit *pit)
kvm_pit_reset_reinject(pit);
}
-static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
+static void pit_mask_notifier(struct kvm_irq_mask_notifier *kimn, bool mask)
{
struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier);
@@ -649,6 +649,79 @@ static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
kvm_pit_reset_reinject(pit);
}
+int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
+{
+ struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state;
+
+ BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels));
+
+ mutex_lock(&kps->lock);
+ memcpy(ps, &kps->channels, sizeof(*ps));
+ mutex_unlock(&kps->lock);
+ return 0;
+}
+
+int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
+{
+ int i;
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ mutex_lock(&pit->pit_state.lock);
+ memcpy(&pit->pit_state.channels, ps, sizeof(*ps));
+ for (i = 0; i < 3; i++)
+ kvm_pit_load_count(pit, i, ps->channels[i].count, 0);
+ mutex_unlock(&pit->pit_state.lock);
+ return 0;
+}
+
+int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
+{
+ mutex_lock(&kvm->arch.vpit->pit_state.lock);
+ memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels,
+ sizeof(ps->channels));
+ ps->flags = kvm->arch.vpit->pit_state.flags;
+ mutex_unlock(&kvm->arch.vpit->pit_state.lock);
+ memset(&ps->reserved, 0, sizeof(ps->reserved));
+ return 0;
+}
+
+int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
+{
+ int start = 0;
+ int i;
+ u32 prev_legacy, cur_legacy;
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ mutex_lock(&pit->pit_state.lock);
+ prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
+ cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY;
+ if (!prev_legacy && cur_legacy)
+ start = 1;
+ memcpy(&pit->pit_state.channels, &ps->channels,
+ sizeof(pit->pit_state.channels));
+ pit->pit_state.flags = ps->flags;
+ for (i = 0; i < 3; i++)
+ kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count,
+ start && i == 0);
+ mutex_unlock(&pit->pit_state.lock);
+ return 0;
+}
+
+int kvm_vm_ioctl_reinject(struct kvm *kvm, struct kvm_reinject_control *control)
+{
+ struct kvm_pit *pit = kvm->arch.vpit;
+
+ /* pit->pit_state.lock was overloaded to prevent userspace from getting
+ * an inconsistent state after running multiple KVM_REINJECT_CONTROL
+ * ioctls in parallel. Use a separate lock if that ioctl isn't rare.
+ */
+ mutex_lock(&pit->pit_state.lock);
+ kvm_pit_set_reinject(pit, control->pit_reinject);
+ mutex_unlock(&pit->pit_state.lock);
+
+ return 0;
+}
+
static const struct kvm_io_device_ops pit_dev_ops = {
.read = pit_ioport_read,
.write = pit_ioport_write,
@@ -671,10 +744,6 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
if (!pit)
return NULL;
- pit->irq_source_id = kvm_request_irq_source_id(kvm);
- if (pit->irq_source_id < 0)
- goto fail_request;
-
mutex_init(&pit->pit_state.lock);
pid = get_pid(task_tgid(current));
@@ -694,7 +763,7 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
pit_state->irq_ack_notifier.gsi = 0;
pit_state->irq_ack_notifier.irq_acked = kvm_pit_ack_irq;
- pit->mask_notifier.func = pit_mask_notifer;
+ pit->mask_notifier.func = pit_mask_notifier;
kvm_pit_reset(pit);
@@ -726,8 +795,6 @@ fail_register_pit:
kvm_pit_set_reinject(pit, false);
kthread_destroy_worker(pit->worker);
fail_kthread:
- kvm_free_irq_source_id(kvm, pit->irq_source_id);
-fail_request:
kfree(pit);
return NULL;
}
@@ -744,7 +811,6 @@ void kvm_free_pit(struct kvm *kvm)
kvm_pit_set_reinject(pit, false);
hrtimer_cancel(&pit->pit_state.timer);
kthread_destroy_worker(pit->worker);
- kvm_free_irq_source_id(kvm, pit->irq_source_id);
kfree(pit);
}
}
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index a768212ba821..60fa499d2f8a 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -6,6 +6,11 @@
#include <kvm/iodev.h>
+#include <uapi/asm/kvm.h>
+
+#include "ioapic.h"
+
+#ifdef CONFIG_KVM_IOAPIC
struct kvm_kpit_channel_state {
u32 count; /* can be 65536 */
u16 latched_count;
@@ -42,7 +47,6 @@ struct kvm_pit {
struct kvm_io_device speaker_dev;
struct kvm *kvm;
struct kvm_kpit_state pit_state;
- int irq_source_id;
struct kvm_irq_mask_notifier mask_notifier;
struct kthread_worker *worker;
struct kthread_work expired;
@@ -55,11 +59,14 @@ struct kvm_pit {
#define KVM_MAX_PIT_INTR_INTERVAL HZ / 100
#define KVM_PIT_CHANNEL_MASK 0x3
+int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps);
+int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps);
+int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps);
+int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps);
+int kvm_vm_ioctl_reinject(struct kvm *kvm, struct kvm_reinject_control *control);
+
struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags);
void kvm_free_pit(struct kvm *kvm);
-
-void kvm_pit_load_count(struct kvm_pit *pit, int channel, u32 val,
- int hpet_legacy_start);
-void kvm_pit_set_reinject(struct kvm_pit *pit, bool reinject);
+#endif /* CONFIG_KVM_IOAPIC */
#endif
diff --git a/arch/x86/kvm/i8259.c b/arch/x86/kvm/i8259.c
index a8fb19940975..2ac7f1678c46 100644
--- a/arch/x86/kvm/i8259.c
+++ b/arch/x86/kvm/i8259.c
@@ -31,6 +31,8 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/bitops.h>
+
+#include "ioapic.h"
#include "irq.h"
#include <linux/kvm_host.h>
@@ -185,8 +187,11 @@ void kvm_pic_update_irq(struct kvm_pic *s)
pic_unlock(s);
}
-int kvm_pic_set_irq(struct kvm_pic *s, int irq, int irq_source_id, int level)
+int kvm_pic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+ int irq_source_id, int level, bool line_status)
{
+ struct kvm_pic *s = kvm->arch.vpic;
+ int irq = e->irqchip.pin;
int ret, irq_level;
BUG_ON(irq < 0 || irq >= PIC_NUM_PINS);
@@ -203,16 +208,6 @@ int kvm_pic_set_irq(struct kvm_pic *s, int irq, int irq_source_id, int level)
return ret;
}
-void kvm_pic_clear_all(struct kvm_pic *s, int irq_source_id)
-{
- int i;
-
- pic_lock(s);
- for (i = 0; i < PIC_NUM_PINS; i++)
- __clear_bit(irq_source_id, &s->irq_states[i]);
- pic_unlock(s);
-}
-
/*
* acknowledge interrupt 'irq'
*/
diff --git a/arch/x86/kvm/ioapic.c b/arch/x86/kvm/ioapic.c
index 995eb5054360..2b5d389bca5f 100644
--- a/arch/x86/kvm/ioapic.c
+++ b/arch/x86/kvm/ioapic.c
@@ -41,11 +41,11 @@
#include <asm/processor.h>
#include <asm/page.h>
#include <asm/current.h>
-#include <trace/events/kvm.h>
#include "ioapic.h"
#include "lapic.h"
#include "irq.h"
+#include "trace.h"
static int ioapic_service(struct kvm_ioapic *vioapic, int irq,
bool line_status);
@@ -296,11 +296,8 @@ void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu, ulong *ioapic_handled_vectors)
index == RTC_GSI) {
u16 dm = kvm_lapic_irq_dest_mode(!!e->fields.dest_mode);
- if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
- e->fields.dest_id, dm) ||
- kvm_apic_pending_eoi(vcpu, e->fields.vector))
- __set_bit(e->fields.vector,
- ioapic_handled_vectors);
+ kvm_scan_ioapic_irq(vcpu, e->fields.dest_id, dm,
+ e->fields.vector, ioapic_handled_vectors);
}
}
spin_unlock(&ioapic->lock);
@@ -313,6 +310,42 @@ void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm)
kvm_make_scan_ioapic_request(kvm);
}
+void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn)
+{
+ struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+
+ mutex_lock(&kvm->irq_lock);
+ kimn->irq = irq;
+ hlist_add_head_rcu(&kimn->link, &ioapic->mask_notifier_list);
+ mutex_unlock(&kvm->irq_lock);
+}
+
+void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn)
+{
+ mutex_lock(&kvm->irq_lock);
+ hlist_del_rcu(&kimn->link);
+ mutex_unlock(&kvm->irq_lock);
+ synchronize_srcu(&kvm->irq_srcu);
+}
+
+void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
+ bool mask)
+{
+ struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+ struct kvm_irq_mask_notifier *kimn;
+ int idx, gsi;
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
+ if (gsi != -1)
+ hlist_for_each_entry_rcu(kimn, &ioapic->mask_notifier_list, link)
+ if (kimn->irq == gsi)
+ kimn->func(kimn, mask);
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
static void ioapic_write_indirect(struct kvm_ioapic *ioapic, u32 val)
{
unsigned index;
@@ -482,9 +515,11 @@ static int ioapic_service(struct kvm_ioapic *ioapic, int irq, bool line_status)
return ret;
}
-int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
- int level, bool line_status)
+int kvm_ioapic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+ int irq_source_id, int level, bool line_status)
{
+ struct kvm_ioapic *ioapic = kvm->arch.vioapic;
+ int irq = e->irqchip.pin;
int ret, irq_level;
BUG_ON(irq < 0 || irq >= IOAPIC_NUM_PINS);
@@ -499,16 +534,6 @@ int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
return ret;
}
-void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id)
-{
- int i;
-
- spin_lock(&ioapic->lock);
- for (i = 0; i < KVM_IOAPIC_NUM_PINS; i++)
- __clear_bit(irq_source_id, &ioapic->irq_states[i]);
- spin_unlock(&ioapic->lock);
-}
-
static void kvm_ioapic_eoi_inject_work(struct work_struct *work)
{
int i;
@@ -721,6 +746,7 @@ int kvm_ioapic_init(struct kvm *kvm)
return -ENOMEM;
spin_lock_init(&ioapic->lock);
INIT_DELAYED_WORK(&ioapic->eoi_inject, kvm_ioapic_eoi_inject_work);
+ INIT_HLIST_HEAD(&ioapic->mask_notifier_list);
kvm->arch.vioapic = ioapic;
kvm_ioapic_reset(ioapic);
kvm_iodevice_init(&ioapic->dev, &ioapic_mmio_ops);
diff --git a/arch/x86/kvm/ioapic.h b/arch/x86/kvm/ioapic.h
index 539333ac4b38..bf28dbc11ff6 100644
--- a/arch/x86/kvm/ioapic.h
+++ b/arch/x86/kvm/ioapic.h
@@ -86,8 +86,24 @@ struct kvm_ioapic {
struct delayed_work eoi_inject;
u32 irq_eoi[IOAPIC_NUM_PINS];
u32 irr_delivered;
+
+ /* reads protected by irq_srcu, writes by irq_lock */
+ struct hlist_head mask_notifier_list;
+};
+
+struct kvm_irq_mask_notifier {
+ void (*func)(struct kvm_irq_mask_notifier *kimn, bool masked);
+ int irq;
+ struct hlist_node link;
};
+void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn);
+void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
+ struct kvm_irq_mask_notifier *kimn);
+void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
+ bool mask);
+
#ifdef DEBUG
#define ASSERT(x) \
do { \
@@ -103,7 +119,7 @@ do { \
static inline int ioapic_in_kernel(struct kvm *kvm)
{
- return irqchip_kernel(kvm);
+ return irqchip_full(kvm);
}
void kvm_rtc_eoi_tracking_restore_one(struct kvm_vcpu *vcpu);
@@ -111,13 +127,15 @@ void kvm_ioapic_update_eoi(struct kvm_vcpu *vcpu, int vector,
int trigger_mode);
int kvm_ioapic_init(struct kvm *kvm);
void kvm_ioapic_destroy(struct kvm *kvm);
-int kvm_ioapic_set_irq(struct kvm_ioapic *ioapic, int irq, int irq_source_id,
- int level, bool line_status);
-void kvm_ioapic_clear_all(struct kvm_ioapic *ioapic, int irq_source_id);
+int kvm_ioapic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+ int irq_source_id, int level, bool line_status);
+
void kvm_get_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
void kvm_set_ioapic(struct kvm *kvm, struct kvm_ioapic_state *state);
void kvm_ioapic_scan_entry(struct kvm_vcpu *vcpu,
ulong *ioapic_handled_vectors);
void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
ulong *ioapic_handled_vectors);
+void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode,
+ u8 vector, unsigned long *ioapic_handled_vectors);
#endif
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index 63f66c51975a..16da89259011 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -11,9 +11,12 @@
#include <linux/export.h>
#include <linux/kvm_host.h>
+#include <linux/kvm_irqfd.h>
+#include "hyperv.h"
+#include "ioapic.h"
#include "irq.h"
-#include "i8254.h"
+#include "trace.h"
#include "x86.h"
#include "xen.h"
@@ -41,6 +44,14 @@ static int pending_userspace_extint(struct kvm_vcpu *v)
return v->arch.pending_external_vector != -1;
}
+static int get_userspace_extint(struct kvm_vcpu *vcpu)
+{
+ int vector = vcpu->arch.pending_external_vector;
+
+ vcpu->arch.pending_external_vector = -1;
+ return vector;
+}
+
/*
* check if there is pending interrupt from
* non-APIC source without intack.
@@ -67,10 +78,13 @@ int kvm_cpu_has_extint(struct kvm_vcpu *v)
if (!kvm_apic_accept_pic_intr(v))
return 0;
- if (irqchip_split(v->kvm))
- return pending_userspace_extint(v);
- else
+#ifdef CONFIG_KVM_IOAPIC
+ if (pic_in_kernel(v->kvm))
return v->kvm->arch.vpic->output;
+#endif
+
+ WARN_ON_ONCE(!irqchip_split(v->kvm));
+ return pending_userspace_extint(v);
}
/*
@@ -100,6 +114,9 @@ int kvm_cpu_has_interrupt(struct kvm_vcpu *v)
if (kvm_cpu_has_extint(v))
return 1;
+ if (lapic_in_kernel(v) && v->arch.apic->guest_apic_protected)
+ return kvm_x86_call(protected_apic_has_interrupt)(v);
+
return kvm_apic_has_interrupt(v) != -1; /* LAPIC */
}
EXPORT_SYMBOL_GPL(kvm_cpu_has_interrupt);
@@ -123,13 +140,13 @@ int kvm_cpu_get_extint(struct kvm_vcpu *v)
return v->kvm->arch.xen.upcall_vector;
#endif
- if (irqchip_split(v->kvm)) {
- int vector = v->arch.pending_external_vector;
-
- v->arch.pending_external_vector = -1;
- return vector;
- } else
+#ifdef CONFIG_KVM_IOAPIC
+ if (pic_in_kernel(v->kvm))
return kvm_pic_read_irq(v->kvm); /* PIC */
+#endif
+
+ WARN_ON_ONCE(!irqchip_split(v->kvm));
+ return get_userspace_extint(v);
}
EXPORT_SYMBOL_GPL(kvm_cpu_get_extint);
@@ -160,7 +177,9 @@ void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
{
__kvm_migrate_apic_timer(vcpu);
+#ifdef CONFIG_KVM_IOAPIC
__kvm_migrate_pit_timer(vcpu);
+#endif
kvm_x86_call(migrate_timers)(vcpu);
}
@@ -168,10 +187,532 @@ bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args)
{
bool resample = args->flags & KVM_IRQFD_FLAG_RESAMPLE;
- return resample ? irqchip_kernel(kvm) : irqchip_in_kernel(kvm);
+ return resample ? irqchip_full(kvm) : irqchip_in_kernel(kvm);
}
bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
{
return irqchip_in_kernel(kvm);
}
+
+int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
+ struct kvm_lapic_irq *irq, struct dest_map *dest_map)
+{
+ int r = -1;
+ struct kvm_vcpu *vcpu, *lowest = NULL;
+ unsigned long i, dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)];
+ unsigned int dest_vcpus = 0;
+
+ if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
+ return r;
+
+ if (irq->dest_mode == APIC_DEST_PHYSICAL &&
+ irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) {
+ pr_info("apic: phys broadcast and lowest prio\n");
+ irq->delivery_mode = APIC_DM_FIXED;
+ }
+
+ memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap));
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!kvm_apic_present(vcpu))
+ continue;
+
+ if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
+ irq->dest_id, irq->dest_mode))
+ continue;
+
+ if (!kvm_lowest_prio_delivery(irq)) {
+ if (r < 0)
+ r = 0;
+ r += kvm_apic_set_irq(vcpu, irq, dest_map);
+ } else if (kvm_apic_sw_enabled(vcpu->arch.apic)) {
+ if (!kvm_vector_hashing_enabled()) {
+ if (!lowest)
+ lowest = vcpu;
+ else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
+ lowest = vcpu;
+ } else {
+ __set_bit(i, dest_vcpu_bitmap);
+ dest_vcpus++;
+ }
+ }
+ }
+
+ if (dest_vcpus != 0) {
+ int idx = kvm_vector_to_index(irq->vector, dest_vcpus,
+ dest_vcpu_bitmap, KVM_MAX_VCPUS);
+
+ lowest = kvm_get_vcpu(kvm, idx);
+ }
+
+ if (lowest)
+ r = kvm_apic_set_irq(lowest, irq, dest_map);
+
+ return r;
+}
+
+static void kvm_msi_to_lapic_irq(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *e,
+ struct kvm_lapic_irq *irq)
+{
+ struct msi_msg msg = { .address_lo = e->msi.address_lo,
+ .address_hi = e->msi.address_hi,
+ .data = e->msi.data };
+
+ trace_kvm_msi_set_irq(msg.address_lo | (kvm->arch.x2apic_format ?
+ (u64)msg.address_hi << 32 : 0), msg.data);
+
+ irq->dest_id = x86_msi_msg_get_destid(&msg, kvm->arch.x2apic_format);
+ irq->vector = msg.arch_data.vector;
+ irq->dest_mode = kvm_lapic_irq_dest_mode(msg.arch_addr_lo.dest_mode_logical);
+ irq->trig_mode = msg.arch_data.is_level;
+ irq->delivery_mode = msg.arch_data.delivery_mode << 8;
+ irq->msi_redir_hint = msg.arch_addr_lo.redirect_hint;
+ irq->level = 1;
+ irq->shorthand = APIC_DEST_NOSHORT;
+}
+
+static inline bool kvm_msi_route_invalid(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *e)
+{
+ return kvm->arch.x2apic_format && (e->msi.address_hi & 0xff);
+}
+
+int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level, bool line_status)
+{
+ struct kvm_lapic_irq irq;
+
+ if (kvm_msi_route_invalid(kvm, e))
+ return -EINVAL;
+
+ if (!level)
+ return -1;
+
+ kvm_msi_to_lapic_irq(kvm, e, &irq);
+
+ return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
+}
+
+int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
+ struct kvm *kvm, int irq_source_id, int level,
+ bool line_status)
+{
+ struct kvm_lapic_irq irq;
+ int r;
+
+ switch (e->type) {
+#ifdef CONFIG_KVM_HYPERV
+ case KVM_IRQ_ROUTING_HV_SINT:
+ return kvm_hv_synic_set_irq(e, kvm, irq_source_id, level,
+ line_status);
+#endif
+
+ case KVM_IRQ_ROUTING_MSI:
+ if (kvm_msi_route_invalid(kvm, e))
+ return -EINVAL;
+
+ kvm_msi_to_lapic_irq(kvm, e, &irq);
+
+ if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
+ return r;
+ break;
+
+#ifdef CONFIG_KVM_XEN
+ case KVM_IRQ_ROUTING_XEN_EVTCHN:
+ if (!level)
+ return -1;
+
+ return kvm_xen_set_evtchn_fast(&e->xen_evtchn, kvm);
+#endif
+ default:
+ break;
+ }
+
+ return -EWOULDBLOCK;
+}
+
+int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
+ bool line_status)
+{
+ if (!irqchip_in_kernel(kvm))
+ return -ENXIO;
+
+ irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
+ irq_event->irq, irq_event->level,
+ line_status);
+ return 0;
+}
+
+bool kvm_arch_can_set_irq_routing(struct kvm *kvm)
+{
+ return irqchip_in_kernel(kvm);
+}
+
+int kvm_set_routing_entry(struct kvm *kvm,
+ struct kvm_kernel_irq_routing_entry *e,
+ const struct kvm_irq_routing_entry *ue)
+{
+ /* We can't check irqchip_in_kernel() here as some callers are
+ * currently initializing the irqchip. Other callers should therefore
+ * check kvm_arch_can_set_irq_routing() before calling this function.
+ */
+ switch (ue->type) {
+#ifdef CONFIG_KVM_IOAPIC
+ case KVM_IRQ_ROUTING_IRQCHIP:
+ if (irqchip_split(kvm))
+ return -EINVAL;
+ e->irqchip.pin = ue->u.irqchip.pin;
+ switch (ue->u.irqchip.irqchip) {
+ case KVM_IRQCHIP_PIC_SLAVE:
+ e->irqchip.pin += PIC_NUM_PINS / 2;
+ fallthrough;
+ case KVM_IRQCHIP_PIC_MASTER:
+ if (ue->u.irqchip.pin >= PIC_NUM_PINS / 2)
+ return -EINVAL;
+ e->set = kvm_pic_set_irq;
+ break;
+ case KVM_IRQCHIP_IOAPIC:
+ if (ue->u.irqchip.pin >= KVM_IOAPIC_NUM_PINS)
+ return -EINVAL;
+ e->set = kvm_ioapic_set_irq;
+ break;
+ default:
+ return -EINVAL;
+ }
+ e->irqchip.irqchip = ue->u.irqchip.irqchip;
+ break;
+#endif
+ case KVM_IRQ_ROUTING_MSI:
+ e->set = kvm_set_msi;
+ e->msi.address_lo = ue->u.msi.address_lo;
+ e->msi.address_hi = ue->u.msi.address_hi;
+ e->msi.data = ue->u.msi.data;
+
+ if (kvm_msi_route_invalid(kvm, e))
+ return -EINVAL;
+ break;
+#ifdef CONFIG_KVM_HYPERV
+ case KVM_IRQ_ROUTING_HV_SINT:
+ e->set = kvm_hv_synic_set_irq;
+ e->hv_sint.vcpu = ue->u.hv_sint.vcpu;
+ e->hv_sint.sint = ue->u.hv_sint.sint;
+ break;
+#endif
+#ifdef CONFIG_KVM_XEN
+ case KVM_IRQ_ROUTING_XEN_EVTCHN:
+ return kvm_xen_setup_evtchn(kvm, e, ue);
+#endif
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
+ struct kvm_vcpu **dest_vcpu)
+{
+ int r = 0;
+ unsigned long i;
+ struct kvm_vcpu *vcpu;
+
+ if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu))
+ return true;
+
+ kvm_for_each_vcpu(i, vcpu, kvm) {
+ if (!kvm_apic_present(vcpu))
+ continue;
+
+ if (!kvm_apic_match_dest(vcpu, NULL, irq->shorthand,
+ irq->dest_id, irq->dest_mode))
+ continue;
+
+ if (++r == 2)
+ return false;
+
+ *dest_vcpu = vcpu;
+ }
+
+ return r == 1;
+}
+EXPORT_SYMBOL_GPL(kvm_intr_is_single_vcpu);
+
+void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode,
+ u8 vector, unsigned long *ioapic_handled_vectors)
+{
+ /*
+ * Intercept EOI if the vCPU is the target of the new IRQ routing, or
+ * the vCPU has a pending IRQ from the old routing, i.e. if the vCPU
+ * may receive a level-triggered IRQ in the future, or already received
+ * level-triggered IRQ. The EOI needs to be intercepted and forwarded
+ * to I/O APIC emulation so that the IRQ can be de-asserted.
+ */
+ if (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT, dest_id, dest_mode)) {
+ __set_bit(vector, ioapic_handled_vectors);
+ } else if (kvm_apic_pending_eoi(vcpu, vector)) {
+ __set_bit(vector, ioapic_handled_vectors);
+
+ /*
+ * Track the highest pending EOI for which the vCPU is NOT the
+ * target in the new routing. Only the EOI for the IRQ that is
+ * in-flight (for the old routing) needs to be intercepted, any
+ * future IRQs that arrive on this vCPU will be coincidental to
+ * the level-triggered routing and don't need to be intercepted.
+ */
+ if ((int)vector > vcpu->arch.highest_stale_pending_ioapic_eoi)
+ vcpu->arch.highest_stale_pending_ioapic_eoi = vector;
+ }
+}
+
+void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
+ ulong *ioapic_handled_vectors)
+{
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_kernel_irq_routing_entry *entry;
+ struct kvm_irq_routing_table *table;
+ u32 i, nr_ioapic_pins;
+ int idx;
+
+ idx = srcu_read_lock(&kvm->irq_srcu);
+ table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
+ nr_ioapic_pins = min_t(u32, table->nr_rt_entries,
+ kvm->arch.nr_reserved_ioapic_pins);
+ for (i = 0; i < nr_ioapic_pins; ++i) {
+ hlist_for_each_entry(entry, &table->map[i], link) {
+ struct kvm_lapic_irq irq;
+
+ if (entry->type != KVM_IRQ_ROUTING_MSI)
+ continue;
+
+ kvm_msi_to_lapic_irq(vcpu->kvm, entry, &irq);
+
+ if (!irq.trig_mode)
+ continue;
+
+ kvm_scan_ioapic_irq(vcpu, irq.dest_id, irq.dest_mode,
+ irq.vector, ioapic_handled_vectors);
+ }
+ }
+ srcu_read_unlock(&kvm->irq_srcu, idx);
+}
+
+void kvm_arch_irq_routing_update(struct kvm *kvm)
+{
+#ifdef CONFIG_KVM_HYPERV
+ kvm_hv_irq_routing_update(kvm);
+#endif
+
+ if (irqchip_split(kvm))
+ kvm_make_scan_ioapic_request(kvm);
+}
+
+static int kvm_pi_update_irte(struct kvm_kernel_irqfd *irqfd,
+ struct kvm_kernel_irq_routing_entry *entry)
+{
+ unsigned int host_irq = irqfd->producer->irq;
+ struct kvm *kvm = irqfd->kvm;
+ struct kvm_vcpu *vcpu = NULL;
+ struct kvm_lapic_irq irq;
+ int r;
+
+ if (WARN_ON_ONCE(!irqchip_in_kernel(kvm) || !kvm_arch_has_irq_bypass()))
+ return -EINVAL;
+
+ if (entry && entry->type == KVM_IRQ_ROUTING_MSI) {
+ kvm_msi_to_lapic_irq(kvm, entry, &irq);
+
+ /*
+ * Force remapped mode if hardware doesn't support posting the
+ * virtual interrupt to a vCPU. Only IRQs are postable (NMIs,
+ * SMIs, etc. are not), and neither AMD nor Intel IOMMUs support
+ * posting multicast/broadcast IRQs. If the interrupt can't be
+ * posted, the device MSI needs to be routed to the host so that
+ * the guest's desired interrupt can be synthesized by KVM.
+ *
+ * This means that KVM can only post lowest-priority interrupts
+ * if they have a single CPU as the destination, e.g. only if
+ * the guest has affined the interrupt to a single vCPU.
+ */
+ if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
+ !kvm_irq_is_postable(&irq))
+ vcpu = NULL;
+ }
+
+ if (!irqfd->irq_bypass_vcpu && !vcpu)
+ return 0;
+
+ r = kvm_x86_call(pi_update_irte)(irqfd, irqfd->kvm, host_irq, irqfd->gsi,
+ vcpu, irq.vector);
+ if (r) {
+ WARN_ON_ONCE(irqfd->irq_bypass_vcpu && !vcpu);
+ irqfd->irq_bypass_vcpu = NULL;
+ return r;
+ }
+
+ irqfd->irq_bypass_vcpu = vcpu;
+
+ trace_kvm_pi_irte_update(host_irq, vcpu, irqfd->gsi, irq.vector, !!vcpu);
+ return 0;
+}
+
+int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
+ struct irq_bypass_producer *prod)
+{
+ struct kvm_kernel_irqfd *irqfd =
+ container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
+ int ret = 0;
+
+ spin_lock_irq(&kvm->irqfds.lock);
+ irqfd->producer = prod;
+
+ if (!kvm->arch.nr_possible_bypass_irqs++)
+ kvm_x86_call(pi_start_bypass)(kvm);
+
+ if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) {
+ ret = kvm_pi_update_irte(irqfd, &irqfd->irq_entry);
+ if (ret)
+ kvm->arch.nr_possible_bypass_irqs--;
+ }
+ spin_unlock_irq(&kvm->irqfds.lock);
+
+ return ret;
+}
+
+void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
+ struct irq_bypass_producer *prod)
+{
+ struct kvm_kernel_irqfd *irqfd =
+ container_of(cons, struct kvm_kernel_irqfd, consumer);
+ struct kvm *kvm = irqfd->kvm;
+ int ret;
+
+ WARN_ON(irqfd->producer != prod);
+
+ /*
+ * If the producer of an IRQ that is currently being posted to a vCPU
+ * is unregistered, change the associated IRTE back to remapped mode as
+ * the IRQ has been released (or repurposed) by the device driver, i.e.
+ * KVM must relinquish control of the IRTE.
+ */
+ spin_lock_irq(&kvm->irqfds.lock);
+
+ if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) {
+ ret = kvm_pi_update_irte(irqfd, NULL);
+ if (ret)
+ pr_info("irq bypass consumer (eventfd %p) unregistration fails: %d\n",
+ irqfd->consumer.eventfd, ret);
+ }
+ irqfd->producer = NULL;
+
+ kvm->arch.nr_possible_bypass_irqs--;
+
+ spin_unlock_irq(&kvm->irqfds.lock);
+}
+
+void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
+ struct kvm_kernel_irq_routing_entry *old,
+ struct kvm_kernel_irq_routing_entry *new)
+{
+ if (new->type != KVM_IRQ_ROUTING_MSI &&
+ old->type != KVM_IRQ_ROUTING_MSI)
+ return;
+
+ if (old->type == KVM_IRQ_ROUTING_MSI &&
+ new->type == KVM_IRQ_ROUTING_MSI &&
+ !memcmp(&old->msi, &new->msi, sizeof(new->msi)))
+ return;
+
+ kvm_pi_update_irte(irqfd, new);
+}
+
+#ifdef CONFIG_KVM_IOAPIC
+#define IOAPIC_ROUTING_ENTRY(irq) \
+ { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \
+ .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
+#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)
+
+#define PIC_ROUTING_ENTRY(irq) \
+ { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \
+ .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } }
+#define ROUTING_ENTRY2(irq) \
+ IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)
+
+static const struct kvm_irq_routing_entry default_routing[] = {
+ ROUTING_ENTRY2(0), ROUTING_ENTRY2(1),
+ ROUTING_ENTRY2(2), ROUTING_ENTRY2(3),
+ ROUTING_ENTRY2(4), ROUTING_ENTRY2(5),
+ ROUTING_ENTRY2(6), ROUTING_ENTRY2(7),
+ ROUTING_ENTRY2(8), ROUTING_ENTRY2(9),
+ ROUTING_ENTRY2(10), ROUTING_ENTRY2(11),
+ ROUTING_ENTRY2(12), ROUTING_ENTRY2(13),
+ ROUTING_ENTRY2(14), ROUTING_ENTRY2(15),
+ ROUTING_ENTRY1(16), ROUTING_ENTRY1(17),
+ ROUTING_ENTRY1(18), ROUTING_ENTRY1(19),
+ ROUTING_ENTRY1(20), ROUTING_ENTRY1(21),
+ ROUTING_ENTRY1(22), ROUTING_ENTRY1(23),
+};
+
+int kvm_setup_default_ioapic_and_pic_routing(struct kvm *kvm)
+{
+ return kvm_set_irq_routing(kvm, default_routing,
+ ARRAY_SIZE(default_routing), 0);
+}
+
+int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
+{
+ struct kvm_pic *pic = kvm->arch.vpic;
+ int r;
+
+ r = 0;
+ switch (chip->chip_id) {
+ case KVM_IRQCHIP_PIC_MASTER:
+ memcpy(&chip->chip.pic, &pic->pics[0],
+ sizeof(struct kvm_pic_state));
+ break;
+ case KVM_IRQCHIP_PIC_SLAVE:
+ memcpy(&chip->chip.pic, &pic->pics[1],
+ sizeof(struct kvm_pic_state));
+ break;
+ case KVM_IRQCHIP_IOAPIC:
+ kvm_get_ioapic(kvm, &chip->chip.ioapic);
+ break;
+ default:
+ r = -EINVAL;
+ break;
+ }
+ return r;
+}
+
+int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
+{
+ struct kvm_pic *pic = kvm->arch.vpic;
+ int r;
+
+ r = 0;
+ switch (chip->chip_id) {
+ case KVM_IRQCHIP_PIC_MASTER:
+ spin_lock(&pic->lock);
+ memcpy(&pic->pics[0], &chip->chip.pic,
+ sizeof(struct kvm_pic_state));
+ spin_unlock(&pic->lock);
+ break;
+ case KVM_IRQCHIP_PIC_SLAVE:
+ spin_lock(&pic->lock);
+ memcpy(&pic->pics[1], &chip->chip.pic,
+ sizeof(struct kvm_pic_state));
+ spin_unlock(&pic->lock);
+ break;
+ case KVM_IRQCHIP_IOAPIC:
+ kvm_set_ioapic(kvm, &chip->chip.ioapic);
+ break;
+ default:
+ r = -EINVAL;
+ break;
+ }
+ kvm_pic_update_irq(pic);
+ return r;
+}
+#endif
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 76d46b2f41dd..5e62c1f79ce6 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -18,6 +18,8 @@
#include <kvm/iodev.h>
#include "lapic.h"
+#ifdef CONFIG_KVM_IOAPIC
+
#define PIC_NUM_PINS 16
#define SELECT_PIC(irq) \
((irq) < 8 ? KVM_IRQCHIP_PIC_MASTER : KVM_IRQCHIP_PIC_SLAVE)
@@ -63,17 +65,15 @@ int kvm_pic_init(struct kvm *kvm);
void kvm_pic_destroy(struct kvm *kvm);
int kvm_pic_read_irq(struct kvm *kvm);
void kvm_pic_update_irq(struct kvm_pic *s);
+int kvm_pic_set_irq(struct kvm_kernel_irq_routing_entry *e, struct kvm *kvm,
+ int irq_source_id, int level, bool line_status);
-static inline int irqchip_split(struct kvm *kvm)
-{
- int mode = kvm->arch.irqchip_mode;
+int kvm_setup_default_ioapic_and_pic_routing(struct kvm *kvm);
- /* Matches smp_wmb() when setting irqchip_mode */
- smp_rmb();
- return mode == KVM_IRQCHIP_SPLIT;
-}
+int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip);
+int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip);
-static inline int irqchip_kernel(struct kvm *kvm)
+static inline int irqchip_full(struct kvm *kvm)
{
int mode = kvm->arch.irqchip_mode;
@@ -81,10 +81,26 @@ static inline int irqchip_kernel(struct kvm *kvm)
smp_rmb();
return mode == KVM_IRQCHIP_KERNEL;
}
+#else /* CONFIG_KVM_IOAPIC */
+static __always_inline int irqchip_full(struct kvm *kvm)
+{
+ return false;
+}
+#endif
static inline int pic_in_kernel(struct kvm *kvm)
{
- return irqchip_kernel(kvm);
+ return irqchip_full(kvm);
+}
+
+
+static inline int irqchip_split(struct kvm *kvm)
+{
+ int mode = kvm->arch.irqchip_mode;
+
+ /* Matches smp_wmb() when setting irqchip_mode */
+ smp_rmb();
+ return mode == KVM_IRQCHIP_SPLIT;
}
static inline int irqchip_in_kernel(struct kvm *kvm)
@@ -105,7 +121,6 @@ void __kvm_migrate_timers(struct kvm_vcpu *vcpu);
int apic_has_pending_timer(struct kvm_vcpu *vcpu);
-int kvm_setup_default_irq_routing(struct kvm *kvm);
int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
struct kvm_lapic_irq *irq,
struct dest_map *dest_map);
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
deleted file mode 100644
index 8136695f7b96..000000000000
--- a/arch/x86/kvm/irq_comm.c
+++ /dev/null
@@ -1,442 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * irq_comm.c: Common API for in kernel interrupt controller
- * Copyright (c) 2007, Intel Corporation.
- *
- * Authors:
- * Yaozu (Eddie) Dong <Eddie.dong@intel.com>
- *
- * Copyright 2010 Red Hat, Inc. and/or its affiliates.
- */
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/kvm_host.h>
-#include <linux/slab.h>
-#include <linux/export.h>
-#include <linux/rculist.h>
-
-#include <trace/events/kvm.h>
-
-#include "irq.h"
-
-#include "ioapic.h"
-
-#include "lapic.h"
-
-#include "hyperv.h"
-#include "x86.h"
-#include "xen.h"
-
-static int kvm_set_pic_irq(struct kvm_kernel_irq_routing_entry *e,
- struct kvm *kvm, int irq_source_id, int level,
- bool line_status)
-{
- struct kvm_pic *pic = kvm->arch.vpic;
- return kvm_pic_set_irq(pic, e->irqchip.pin, irq_source_id, level);
-}
-
-static int kvm_set_ioapic_irq(struct kvm_kernel_irq_routing_entry *e,
- struct kvm *kvm, int irq_source_id, int level,
- bool line_status)
-{
- struct kvm_ioapic *ioapic = kvm->arch.vioapic;
- return kvm_ioapic_set_irq(ioapic, e->irqchip.pin, irq_source_id, level,
- line_status);
-}
-
-int kvm_irq_delivery_to_apic(struct kvm *kvm, struct kvm_lapic *src,
- struct kvm_lapic_irq *irq, struct dest_map *dest_map)
-{
- int r = -1;
- struct kvm_vcpu *vcpu, *lowest = NULL;
- unsigned long i, dest_vcpu_bitmap[BITS_TO_LONGS(KVM_MAX_VCPUS)];
- unsigned int dest_vcpus = 0;
-
- if (kvm_irq_delivery_to_apic_fast(kvm, src, irq, &r, dest_map))
- return r;
-
- if (irq->dest_mode == APIC_DEST_PHYSICAL &&
- irq->dest_id == 0xff && kvm_lowest_prio_delivery(irq)) {
- pr_info("apic: phys broadcast and lowest prio\n");
- irq->delivery_mode = APIC_DM_FIXED;
- }
-
- memset(dest_vcpu_bitmap, 0, sizeof(dest_vcpu_bitmap));
-
- kvm_for_each_vcpu(i, vcpu, kvm) {
- if (!kvm_apic_present(vcpu))
- continue;
-
- if (!kvm_apic_match_dest(vcpu, src, irq->shorthand,
- irq->dest_id, irq->dest_mode))
- continue;
-
- if (!kvm_lowest_prio_delivery(irq)) {
- if (r < 0)
- r = 0;
- r += kvm_apic_set_irq(vcpu, irq, dest_map);
- } else if (kvm_apic_sw_enabled(vcpu->arch.apic)) {
- if (!kvm_vector_hashing_enabled()) {
- if (!lowest)
- lowest = vcpu;
- else if (kvm_apic_compare_prio(vcpu, lowest) < 0)
- lowest = vcpu;
- } else {
- __set_bit(i, dest_vcpu_bitmap);
- dest_vcpus++;
- }
- }
- }
-
- if (dest_vcpus != 0) {
- int idx = kvm_vector_to_index(irq->vector, dest_vcpus,
- dest_vcpu_bitmap, KVM_MAX_VCPUS);
-
- lowest = kvm_get_vcpu(kvm, idx);
- }
-
- if (lowest)
- r = kvm_apic_set_irq(lowest, irq, dest_map);
-
- return r;
-}
-
-void kvm_set_msi_irq(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
- struct kvm_lapic_irq *irq)
-{
- struct msi_msg msg = { .address_lo = e->msi.address_lo,
- .address_hi = e->msi.address_hi,
- .data = e->msi.data };
-
- trace_kvm_msi_set_irq(msg.address_lo | (kvm->arch.x2apic_format ?
- (u64)msg.address_hi << 32 : 0), msg.data);
-
- irq->dest_id = x86_msi_msg_get_destid(&msg, kvm->arch.x2apic_format);
- irq->vector = msg.arch_data.vector;
- irq->dest_mode = kvm_lapic_irq_dest_mode(msg.arch_addr_lo.dest_mode_logical);
- irq->trig_mode = msg.arch_data.is_level;
- irq->delivery_mode = msg.arch_data.delivery_mode << 8;
- irq->msi_redir_hint = msg.arch_addr_lo.redirect_hint;
- irq->level = 1;
- irq->shorthand = APIC_DEST_NOSHORT;
-}
-EXPORT_SYMBOL_GPL(kvm_set_msi_irq);
-
-static inline bool kvm_msi_route_invalid(struct kvm *kvm,
- struct kvm_kernel_irq_routing_entry *e)
-{
- return kvm->arch.x2apic_format && (e->msi.address_hi & 0xff);
-}
-
-int kvm_set_msi(struct kvm_kernel_irq_routing_entry *e,
- struct kvm *kvm, int irq_source_id, int level, bool line_status)
-{
- struct kvm_lapic_irq irq;
-
- if (kvm_msi_route_invalid(kvm, e))
- return -EINVAL;
-
- if (!level)
- return -1;
-
- kvm_set_msi_irq(kvm, e, &irq);
-
- return kvm_irq_delivery_to_apic(kvm, NULL, &irq, NULL);
-}
-
-#ifdef CONFIG_KVM_HYPERV
-static int kvm_hv_set_sint(struct kvm_kernel_irq_routing_entry *e,
- struct kvm *kvm, int irq_source_id, int level,
- bool line_status)
-{
- if (!level)
- return -1;
-
- return kvm_hv_synic_set_irq(kvm, e->hv_sint.vcpu, e->hv_sint.sint);
-}
-#endif
-
-int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
- struct kvm *kvm, int irq_source_id, int level,
- bool line_status)
-{
- struct kvm_lapic_irq irq;
- int r;
-
- switch (e->type) {
-#ifdef CONFIG_KVM_HYPERV
- case KVM_IRQ_ROUTING_HV_SINT:
- return kvm_hv_set_sint(e, kvm, irq_source_id, level,
- line_status);
-#endif
-
- case KVM_IRQ_ROUTING_MSI:
- if (kvm_msi_route_invalid(kvm, e))
- return -EINVAL;
-
- kvm_set_msi_irq(kvm, e, &irq);
-
- if (kvm_irq_delivery_to_apic_fast(kvm, NULL, &irq, &r, NULL))
- return r;
- break;
-
-#ifdef CONFIG_KVM_XEN
- case KVM_IRQ_ROUTING_XEN_EVTCHN:
- if (!level)
- return -1;
-
- return kvm_xen_set_evtchn_fast(&e->xen_evtchn, kvm);
-#endif
- default:
- break;
- }
-
- return -EWOULDBLOCK;
-}
-
-int kvm_request_irq_source_id(struct kvm *kvm)
-{
- unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
- int irq_source_id;
-
- mutex_lock(&kvm->irq_lock);
- irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);
-
- if (irq_source_id >= BITS_PER_LONG) {
- pr_warn("exhausted allocatable IRQ sources!\n");
- irq_source_id = -EFAULT;
- goto unlock;
- }
-
- ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
- ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
- set_bit(irq_source_id, bitmap);
-unlock:
- mutex_unlock(&kvm->irq_lock);
-
- return irq_source_id;
-}
-
-void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
-{
- ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
- ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
-
- mutex_lock(&kvm->irq_lock);
- if (irq_source_id < 0 ||
- irq_source_id >= BITS_PER_LONG) {
- pr_err("IRQ source ID out of range!\n");
- goto unlock;
- }
- clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
- if (!irqchip_kernel(kvm))
- goto unlock;
-
- kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
- kvm_pic_clear_all(kvm->arch.vpic, irq_source_id);
-unlock:
- mutex_unlock(&kvm->irq_lock);
-}
-
-void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
- struct kvm_irq_mask_notifier *kimn)
-{
- mutex_lock(&kvm->irq_lock);
- kimn->irq = irq;
- hlist_add_head_rcu(&kimn->link, &kvm->arch.mask_notifier_list);
- mutex_unlock(&kvm->irq_lock);
-}
-
-void kvm_unregister_irq_mask_notifier(struct kvm *kvm, int irq,
- struct kvm_irq_mask_notifier *kimn)
-{
- mutex_lock(&kvm->irq_lock);
- hlist_del_rcu(&kimn->link);
- mutex_unlock(&kvm->irq_lock);
- synchronize_srcu(&kvm->irq_srcu);
-}
-
-void kvm_fire_mask_notifiers(struct kvm *kvm, unsigned irqchip, unsigned pin,
- bool mask)
-{
- struct kvm_irq_mask_notifier *kimn;
- int idx, gsi;
-
- idx = srcu_read_lock(&kvm->irq_srcu);
- gsi = kvm_irq_map_chip_pin(kvm, irqchip, pin);
- if (gsi != -1)
- hlist_for_each_entry_rcu(kimn, &kvm->arch.mask_notifier_list, link)
- if (kimn->irq == gsi)
- kimn->func(kimn, mask);
- srcu_read_unlock(&kvm->irq_srcu, idx);
-}
-
-bool kvm_arch_can_set_irq_routing(struct kvm *kvm)
-{
- return irqchip_in_kernel(kvm);
-}
-
-int kvm_set_routing_entry(struct kvm *kvm,
- struct kvm_kernel_irq_routing_entry *e,
- const struct kvm_irq_routing_entry *ue)
-{
- /* We can't check irqchip_in_kernel() here as some callers are
- * currently initializing the irqchip. Other callers should therefore
- * check kvm_arch_can_set_irq_routing() before calling this function.
- */
- switch (ue->type) {
- case KVM_IRQ_ROUTING_IRQCHIP:
- if (irqchip_split(kvm))
- return -EINVAL;
- e->irqchip.pin = ue->u.irqchip.pin;
- switch (ue->u.irqchip.irqchip) {
- case KVM_IRQCHIP_PIC_SLAVE:
- e->irqchip.pin += PIC_NUM_PINS / 2;
- fallthrough;
- case KVM_IRQCHIP_PIC_MASTER:
- if (ue->u.irqchip.pin >= PIC_NUM_PINS / 2)
- return -EINVAL;
- e->set = kvm_set_pic_irq;
- break;
- case KVM_IRQCHIP_IOAPIC:
- if (ue->u.irqchip.pin >= KVM_IOAPIC_NUM_PINS)
- return -EINVAL;
- e->set = kvm_set_ioapic_irq;
- break;
- default:
- return -EINVAL;
- }
- e->irqchip.irqchip = ue->u.irqchip.irqchip;
- break;
- case KVM_IRQ_ROUTING_MSI:
- e->set = kvm_set_msi;
- e->msi.address_lo = ue->u.msi.address_lo;
- e->msi.address_hi = ue->u.msi.address_hi;
- e->msi.data = ue->u.msi.data;
-
- if (kvm_msi_route_invalid(kvm, e))
- return -EINVAL;
- break;
-#ifdef CONFIG_KVM_HYPERV
- case KVM_IRQ_ROUTING_HV_SINT:
- e->set = kvm_hv_set_sint;
- e->hv_sint.vcpu = ue->u.hv_sint.vcpu;
- e->hv_sint.sint = ue->u.hv_sint.sint;
- break;
-#endif
-#ifdef CONFIG_KVM_XEN
- case KVM_IRQ_ROUTING_XEN_EVTCHN:
- return kvm_xen_setup_evtchn(kvm, e, ue);
-#endif
- default:
- return -EINVAL;
- }
-
- return 0;
-}
-
-bool kvm_intr_is_single_vcpu(struct kvm *kvm, struct kvm_lapic_irq *irq,
- struct kvm_vcpu **dest_vcpu)
-{
- int r = 0;
- unsigned long i;
- struct kvm_vcpu *vcpu;
-
- if (kvm_intr_is_single_vcpu_fast(kvm, irq, dest_vcpu))
- return true;
-
- kvm_for_each_vcpu(i, vcpu, kvm) {
- if (!kvm_apic_present(vcpu))
- continue;
-
- if (!kvm_apic_match_dest(vcpu, NULL, irq->shorthand,
- irq->dest_id, irq->dest_mode))
- continue;
-
- if (++r == 2)
- return false;
-
- *dest_vcpu = vcpu;
- }
-
- return r == 1;
-}
-EXPORT_SYMBOL_GPL(kvm_intr_is_single_vcpu);
-
-#define IOAPIC_ROUTING_ENTRY(irq) \
- { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \
- .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
-#define ROUTING_ENTRY1(irq) IOAPIC_ROUTING_ENTRY(irq)
-
-#define PIC_ROUTING_ENTRY(irq) \
- { .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP, \
- .u.irqchip = { .irqchip = SELECT_PIC(irq), .pin = (irq) % 8 } }
-#define ROUTING_ENTRY2(irq) \
- IOAPIC_ROUTING_ENTRY(irq), PIC_ROUTING_ENTRY(irq)
-
-static const struct kvm_irq_routing_entry default_routing[] = {
- ROUTING_ENTRY2(0), ROUTING_ENTRY2(1),
- ROUTING_ENTRY2(2), ROUTING_ENTRY2(3),
- ROUTING_ENTRY2(4), ROUTING_ENTRY2(5),
- ROUTING_ENTRY2(6), ROUTING_ENTRY2(7),
- ROUTING_ENTRY2(8), ROUTING_ENTRY2(9),
- ROUTING_ENTRY2(10), ROUTING_ENTRY2(11),
- ROUTING_ENTRY2(12), ROUTING_ENTRY2(13),
- ROUTING_ENTRY2(14), ROUTING_ENTRY2(15),
- ROUTING_ENTRY1(16), ROUTING_ENTRY1(17),
- ROUTING_ENTRY1(18), ROUTING_ENTRY1(19),
- ROUTING_ENTRY1(20), ROUTING_ENTRY1(21),
- ROUTING_ENTRY1(22), ROUTING_ENTRY1(23),
-};
-
-int kvm_setup_default_irq_routing(struct kvm *kvm)
-{
- return kvm_set_irq_routing(kvm, default_routing,
- ARRAY_SIZE(default_routing), 0);
-}
-
-void kvm_arch_post_irq_routing_update(struct kvm *kvm)
-{
- if (!irqchip_split(kvm))
- return;
- kvm_make_scan_ioapic_request(kvm);
-}
-
-void kvm_scan_ioapic_routes(struct kvm_vcpu *vcpu,
- ulong *ioapic_handled_vectors)
-{
- struct kvm *kvm = vcpu->kvm;
- struct kvm_kernel_irq_routing_entry *entry;
- struct kvm_irq_routing_table *table;
- u32 i, nr_ioapic_pins;
- int idx;
-
- idx = srcu_read_lock(&kvm->irq_srcu);
- table = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
- nr_ioapic_pins = min_t(u32, table->nr_rt_entries,
- kvm->arch.nr_reserved_ioapic_pins);
- for (i = 0; i < nr_ioapic_pins; ++i) {
- hlist_for_each_entry(entry, &table->map[i], link) {
- struct kvm_lapic_irq irq;
-
- if (entry->type != KVM_IRQ_ROUTING_MSI)
- continue;
-
- kvm_set_msi_irq(vcpu->kvm, entry, &irq);
-
- if (irq.trig_mode &&
- (kvm_apic_match_dest(vcpu, NULL, APIC_DEST_NOSHORT,
- irq.dest_id, irq.dest_mode) ||
- kvm_apic_pending_eoi(vcpu, irq.vector)))
- __set_bit(irq.vector, ioapic_handled_vectors);
- }
- }
- srcu_read_unlock(&kvm->irq_srcu, idx);
-}
-
-void kvm_arch_irq_routing_update(struct kvm *kvm)
-{
-#ifdef CONFIG_KVM_HYPERV
- kvm_hv_irq_routing_update(kvm);
-#endif
-}
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 28e3317124fd..8172c2042dd6 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -27,6 +27,7 @@
#include <linux/export.h>
#include <linux/math64.h>
#include <linux/slab.h>
+#include <asm/apic.h>
#include <asm/processor.h>
#include <asm/mce.h>
#include <asm/msr.h>
@@ -55,9 +56,6 @@
/* 14 is the version for Xeon and Pentium 8.4.8*/
#define APIC_VERSION 0x14UL
#define LAPIC_MMIO_LENGTH (1 << 12)
-/* followed define is not in apicdef.h */
-#define MAX_APIC_VECTOR 256
-#define APIC_VECTORS_PER_REG 32
/*
* Enable local APIC timer advancement (tscdeadline mode only) with adaptive
@@ -79,42 +77,20 @@ module_param(lapic_timer_advance, bool, 0444);
static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data);
static int kvm_lapic_msr_write(struct kvm_lapic *apic, u32 reg, u64 data);
-static inline void __kvm_lapic_set_reg(char *regs, int reg_off, u32 val)
-{
- *((u32 *) (regs + reg_off)) = val;
-}
-
static inline void kvm_lapic_set_reg(struct kvm_lapic *apic, int reg_off, u32 val)
{
- __kvm_lapic_set_reg(apic->regs, reg_off, val);
-}
-
-static __always_inline u64 __kvm_lapic_get_reg64(char *regs, int reg)
-{
- BUILD_BUG_ON(reg != APIC_ICR);
- return *((u64 *) (regs + reg));
+ apic_set_reg(apic->regs, reg_off, val);
}
static __always_inline u64 kvm_lapic_get_reg64(struct kvm_lapic *apic, int reg)
{
- return __kvm_lapic_get_reg64(apic->regs, reg);
-}
-
-static __always_inline void __kvm_lapic_set_reg64(char *regs, int reg, u64 val)
-{
- BUILD_BUG_ON(reg != APIC_ICR);
- *((u64 *) (regs + reg)) = val;
+ return apic_get_reg64(apic->regs, reg);
}
static __always_inline void kvm_lapic_set_reg64(struct kvm_lapic *apic,
int reg, u64 val)
{
- __kvm_lapic_set_reg64(apic->regs, reg, val);
-}
-
-static inline int apic_test_vector(int vec, void *bitmap)
-{
- return test_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
+ apic_set_reg64(apic->regs, reg, val);
}
bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector)
@@ -125,16 +101,6 @@ bool kvm_apic_pending_eoi(struct kvm_vcpu *vcpu, int vector)
apic_test_vector(vector, apic->regs + APIC_IRR);
}
-static inline int __apic_test_and_set_vector(int vec, void *bitmap)
-{
- return __test_and_set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
-static inline int __apic_test_and_clear_vector(int vec, void *bitmap)
-{
- return __test_and_clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
__read_mostly DEFINE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu);
EXPORT_SYMBOL_GPL(kvm_has_noapic_vcpu);
@@ -626,21 +592,6 @@ static const unsigned int apic_lvt_mask[KVM_APIC_MAX_NR_LVT_ENTRIES] = {
[LVT_CMCI] = LVT_MASK | APIC_MODE_MASK
};
-static int find_highest_vector(void *bitmap)
-{
- int vec;
- u32 *reg;
-
- for (vec = MAX_APIC_VECTOR - APIC_VECTORS_PER_REG;
- vec >= 0; vec -= APIC_VECTORS_PER_REG) {
- reg = bitmap + REG_POS(vec);
- if (*reg)
- return __fls(*reg) + vec;
- }
-
- return -1;
-}
-
static u8 count_vectors(void *bitmap)
{
int vec;
@@ -648,34 +599,36 @@ static u8 count_vectors(void *bitmap)
u8 count = 0;
for (vec = 0; vec < MAX_APIC_VECTOR; vec += APIC_VECTORS_PER_REG) {
- reg = bitmap + REG_POS(vec);
+ reg = bitmap + APIC_VECTOR_TO_REG_OFFSET(vec);
count += hweight32(*reg);
}
return count;
}
-bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr)
+bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr)
{
+ unsigned long pir_vals[NR_PIR_WORDS];
+ u32 *__pir = (void *)pir_vals;
u32 i, vec;
- u32 pir_val, irr_val, prev_irr_val;
+ u32 irr_val, prev_irr_val;
int max_updated_irr;
max_updated_irr = -1;
*max_irr = -1;
+ if (!pi_harvest_pir(pir, pir_vals))
+ return false;
+
for (i = vec = 0; i <= 7; i++, vec += 32) {
u32 *p_irr = (u32 *)(regs + APIC_IRR + i * 0x10);
- irr_val = *p_irr;
- pir_val = READ_ONCE(pir[i]);
-
- if (pir_val) {
- pir_val = xchg(&pir[i], 0);
+ irr_val = READ_ONCE(*p_irr);
+ if (__pir[i]) {
prev_irr_val = irr_val;
do {
- irr_val = prev_irr_val | pir_val;
+ irr_val = prev_irr_val | __pir[i];
} while (prev_irr_val != irr_val &&
!try_cmpxchg(p_irr, &prev_irr_val, irr_val));
@@ -691,7 +644,7 @@ bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr)
}
EXPORT_SYMBOL_GPL(__kvm_apic_update_irr);
-bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr)
+bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, unsigned long *pir, int *max_irr)
{
struct kvm_lapic *apic = vcpu->arch.apic;
bool irr_updated = __kvm_apic_update_irr(pir, apic->regs, max_irr);
@@ -704,7 +657,7 @@ EXPORT_SYMBOL_GPL(kvm_apic_update_irr);
static inline int apic_search_irr(struct kvm_lapic *apic)
{
- return find_highest_vector(apic->regs + APIC_IRR);
+ return apic_find_highest_vector(apic->regs + APIC_IRR);
}
static inline int apic_find_highest_irr(struct kvm_lapic *apic)
@@ -727,10 +680,10 @@ static inline int apic_find_highest_irr(struct kvm_lapic *apic)
static inline void apic_clear_irr(int vec, struct kvm_lapic *apic)
{
if (unlikely(apic->apicv_active)) {
- kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
+ apic_clear_vector(vec, apic->regs + APIC_IRR);
} else {
apic->irr_pending = false;
- kvm_lapic_clear_vector(vec, apic->regs + APIC_IRR);
+ apic_clear_vector(vec, apic->regs + APIC_IRR);
if (apic_search_irr(apic) != -1)
apic->irr_pending = true;
}
@@ -742,9 +695,15 @@ void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec)
}
EXPORT_SYMBOL_GPL(kvm_apic_clear_irr);
+static void *apic_vector_to_isr(int vec, struct kvm_lapic *apic)
+{
+ return apic->regs + APIC_ISR + APIC_VECTOR_TO_REG_OFFSET(vec);
+}
+
static inline void apic_set_isr(int vec, struct kvm_lapic *apic)
{
- if (__apic_test_and_set_vector(vec, apic->regs + APIC_ISR))
+ if (__test_and_set_bit(APIC_VECTOR_TO_BIT_NUMBER(vec),
+ apic_vector_to_isr(vec, apic)))
return;
/*
@@ -779,7 +738,7 @@ static inline int apic_find_highest_isr(struct kvm_lapic *apic)
if (likely(apic->highest_isr_cache != -1))
return apic->highest_isr_cache;
- result = find_highest_vector(apic->regs + APIC_ISR);
+ result = apic_find_highest_vector(apic->regs + APIC_ISR);
ASSERT(result == -1 || result >= 16);
return result;
@@ -787,7 +746,8 @@ static inline int apic_find_highest_isr(struct kvm_lapic *apic)
static inline void apic_clear_isr(int vec, struct kvm_lapic *apic)
{
- if (!__apic_test_and_clear_vector(vec, apic->regs + APIC_ISR))
+ if (!__test_and_clear_bit(APIC_VECTOR_TO_BIT_NUMBER(vec),
+ apic_vector_to_isr(vec, apic)))
return;
/*
@@ -1330,11 +1290,9 @@ static int __apic_accept_irq(struct kvm_lapic *apic, int delivery_mode,
if (apic_test_vector(vector, apic->regs + APIC_TMR) != !!trig_mode) {
if (trig_mode)
- kvm_lapic_set_vector(vector,
- apic->regs + APIC_TMR);
+ apic_set_vector(vector, apic->regs + APIC_TMR);
else
- kvm_lapic_clear_vector(vector,
- apic->regs + APIC_TMR);
+ apic_clear_vector(vector, apic->regs + APIC_TMR);
}
kvm_x86_call(deliver_interrupt)(apic, delivery_mode,
@@ -1453,12 +1411,20 @@ static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector)
static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
{
- int trigger_mode;
+ int __maybe_unused trigger_mode;
/* Eoi the ioapic only if the ioapic doesn't own the vector. */
if (!kvm_ioapic_handles_vector(apic, vector))
return;
+ /*
+ * If the intercepted EOI is for an IRQ that was pending from previous
+ * routing, then re-scan the I/O APIC routes as EOIs for the IRQ likely
+ * no longer need to be intercepted.
+ */
+ if (apic->vcpu->arch.highest_stale_pending_ioapic_eoi == vector)
+ kvm_make_request(KVM_REQ_SCAN_IOAPIC, apic->vcpu);
+
/* Request a KVM exit to inform the userspace IOAPIC. */
if (irqchip_split(apic->vcpu->kvm)) {
apic->vcpu->arch.pending_ioapic_eoi = vector;
@@ -1466,12 +1432,14 @@ static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
return;
}
+#ifdef CONFIG_KVM_IOAPIC
if (apic_test_vector(vector, apic->regs + APIC_TMR))
trigger_mode = IOAPIC_LEVEL_TRIG;
else
trigger_mode = IOAPIC_EDGE_TRIG;
kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode);
+#endif
}
static int apic_set_eoi(struct kvm_lapic *apic)
@@ -1790,8 +1758,17 @@ static void apic_update_lvtt(struct kvm_lapic *apic)
static bool lapic_timer_int_injected(struct kvm_vcpu *vcpu)
{
struct kvm_lapic *apic = vcpu->arch.apic;
- u32 reg = kvm_lapic_get_reg(apic, APIC_LVTT);
+ u32 reg;
+ /*
+ * Assume a timer IRQ was "injected" if the APIC is protected. KVM's
+ * copy of the vIRR is bogus, it's the responsibility of the caller to
+ * precisely check whether or not a timer IRQ is pending.
+ */
+ if (apic->guest_apic_protected)
+ return true;
+
+ reg = kvm_lapic_get_reg(apic, APIC_LVTT);
if (kvm_apic_hw_enabled(apic)) {
int vec = reg & APIC_VECTOR_MASK;
void *bitmap = apic->regs + APIC_ISR;
@@ -2650,6 +2627,7 @@ int kvm_apic_set_base(struct kvm_vcpu *vcpu, u64 value, bool host_initiated)
kvm_recalculate_apic_map(vcpu->kvm);
return 0;
}
+EXPORT_SYMBOL_GPL(kvm_apic_set_base);
void kvm_apic_update_apicv(struct kvm_vcpu *vcpu)
{
@@ -2958,6 +2936,9 @@ int kvm_apic_has_interrupt(struct kvm_vcpu *vcpu)
if (!kvm_apic_present(vcpu))
return -1;
+ if (apic->guest_apic_protected)
+ return -1;
+
__apic_update_ppr(apic, &ppr);
return apic_has_interrupt_for_ppr(apic, ppr);
}
@@ -3061,12 +3042,12 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
if (!kvm_x86_ops.x2apic_icr_is_split) {
if (set) {
- icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) |
- (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32;
- __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr);
+ icr = apic_get_reg(s->regs, APIC_ICR) |
+ (u64)apic_get_reg(s->regs, APIC_ICR2) << 32;
+ apic_set_reg64(s->regs, APIC_ICR, icr);
} else {
- icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR);
- __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32);
+ icr = apic_get_reg64(s->regs, APIC_ICR);
+ apic_set_reg(s->regs, APIC_ICR2, icr >> 32);
}
}
}
@@ -3082,8 +3063,7 @@ int kvm_apic_get_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
* Get calculated timer current count for remaining timer period (if
* any) and store it in the returned register set.
*/
- __kvm_lapic_set_reg(s->regs, APIC_TMCCT,
- __apic_read(vcpu->arch.apic, APIC_TMCCT));
+ apic_set_reg(s->regs, APIC_TMCCT, __apic_read(vcpu->arch.apic, APIC_TMCCT));
return kvm_apic_state_fixup(vcpu, s, false);
}
@@ -3123,8 +3103,11 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
kvm_x86_call(hwapic_isr_update)(vcpu, apic_find_highest_isr(apic));
}
kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+#ifdef CONFIG_KVM_IOAPIC
if (ioapic_in_kernel(vcpu->kvm))
kvm_rtc_eoi_tracking_restore_one(vcpu);
+#endif
vcpu->arch.apic_arb_prio = 0;
diff --git a/arch/x86/kvm/lapic.h b/arch/x86/kvm/lapic.h
index 1a8553ebdb42..72de14527698 100644
--- a/arch/x86/kvm/lapic.h
+++ b/arch/x86/kvm/lapic.h
@@ -4,6 +4,8 @@
#include <kvm/iodev.h>
+#include <asm/apic.h>
+
#include <linux/kvm_host.h>
#include "hyperv.h"
@@ -21,6 +23,8 @@
#define APIC_BROADCAST 0xFF
#define X2APIC_BROADCAST 0xFFFFFFFFul
+#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
+
enum lapic_mode {
LAPIC_MODE_DISABLED = 0,
LAPIC_MODE_INVALID = X2APIC_ENABLE,
@@ -65,6 +69,8 @@ struct kvm_lapic {
bool sw_enabled;
bool irr_pending;
bool lvt0_in_nmi_mode;
+ /* Select registers in the vAPIC cannot be read/written. */
+ bool guest_apic_protected;
/* Number of bits set in ISR. */
s16 isr_count;
/* The highest vector set in ISR; if -1 - invalid, must scan ISR. */
@@ -101,8 +107,8 @@ bool kvm_apic_match_dest(struct kvm_vcpu *vcpu, struct kvm_lapic *source,
int shorthand, unsigned int dest, int dest_mode);
int kvm_apic_compare_prio(struct kvm_vcpu *vcpu1, struct kvm_vcpu *vcpu2);
void kvm_apic_clear_irr(struct kvm_vcpu *vcpu, int vec);
-bool __kvm_apic_update_irr(u32 *pir, void *regs, int *max_irr);
-bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, u32 *pir, int *max_irr);
+bool __kvm_apic_update_irr(unsigned long *pir, void *regs, int *max_irr);
+bool kvm_apic_update_irr(struct kvm_vcpu *vcpu, unsigned long *pir, int *max_irr);
void kvm_apic_update_ppr(struct kvm_vcpu *vcpu);
int kvm_apic_set_irq(struct kvm_vcpu *vcpu, struct kvm_lapic_irq *irq,
struct dest_map *dest_map);
@@ -143,22 +149,9 @@ void kvm_lapic_exit(void);
u64 kvm_lapic_readable_reg_mask(struct kvm_lapic *apic);
-#define VEC_POS(v) ((v) & (32 - 1))
-#define REG_POS(v) (((v) >> 5) << 4)
-
-static inline void kvm_lapic_clear_vector(int vec, void *bitmap)
-{
- clear_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
-static inline void kvm_lapic_set_vector(int vec, void *bitmap)
-{
- set_bit(VEC_POS(vec), (bitmap) + REG_POS(vec));
-}
-
static inline void kvm_lapic_set_irr(int vec, struct kvm_lapic *apic)
{
- kvm_lapic_set_vector(vec, apic->regs + APIC_IRR);
+ apic_set_vector(vec, apic->regs + APIC_IRR);
/*
* irr_pending must be true if any interrupt is pending; set it after
* APIC_IRR to avoid race with apic_clear_irr
@@ -166,14 +159,9 @@ static inline void kvm_lapic_set_irr(int vec, struct kvm_lapic *apic)
apic->irr_pending = true;
}
-static inline u32 __kvm_lapic_get_reg(char *regs, int reg_off)
-{
- return *((u32 *) (regs + reg_off));
-}
-
static inline u32 kvm_lapic_get_reg(struct kvm_lapic *apic, int reg_off)
{
- return __kvm_lapic_get_reg(apic->regs, reg_off);
+ return apic_get_reg(apic->regs, reg_off);
}
DECLARE_STATIC_KEY_FALSE(kvm_has_noapic_vcpu);
diff --git a/arch/x86/kvm/mmu.h b/arch/x86/kvm/mmu.h
index f2b36d32ef40..b4b6860ab971 100644
--- a/arch/x86/kvm/mmu.h
+++ b/arch/x86/kvm/mmu.h
@@ -79,6 +79,7 @@ static inline gfn_t kvm_mmu_max_gfn(void)
u8 kvm_mmu_get_max_tdp_level(void);
void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask);
+void kvm_mmu_set_mmio_spte_value(struct kvm *kvm, u64 mmio_value);
void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask);
void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only);
@@ -234,7 +235,7 @@ static inline u8 permission_fault(struct kvm_vcpu *vcpu, struct kvm_mmu *mmu,
return -(u32)fault & errcode;
}
-bool kvm_mmu_may_ignore_guest_pat(void);
+bool kvm_mmu_may_ignore_guest_pat(struct kvm *kvm);
int kvm_mmu_post_init_vm(struct kvm *kvm);
void kvm_mmu_pre_destroy_vm(struct kvm *kvm);
@@ -256,6 +257,9 @@ extern bool tdp_mmu_enabled;
#define tdp_mmu_enabled false
#endif
+bool kvm_tdp_mmu_gpa_is_mapped(struct kvm_vcpu *vcpu, u64 gpa);
+int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, u8 *level);
+
static inline bool kvm_memslots_have_rmaps(struct kvm *kvm)
{
return !tdp_mmu_enabled || kvm_shadow_root_allocated(kvm);
diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
index 8d1b632e33d2..6e838cb6c9e1 100644
--- a/arch/x86/kvm/mmu/mmu.c
+++ b/arch/x86/kvm/mmu/mmu.c
@@ -110,6 +110,7 @@ static bool __ro_after_init tdp_mmu_allowed;
#ifdef CONFIG_X86_64
bool __read_mostly tdp_mmu_enabled = true;
module_param_named(tdp_mmu, tdp_mmu_enabled, bool, 0444);
+EXPORT_SYMBOL_GPL(tdp_mmu_enabled);
#endif
static int max_huge_page_level __read_mostly;
@@ -1456,15 +1457,15 @@ void kvm_arch_mmu_enable_log_dirty_pt_masked(struct kvm *kvm,
* enabled but it chooses between clearing the Dirty bit and Writeable
* bit based on the context.
*/
- if (kvm_x86_ops.cpu_dirty_log_size)
+ if (kvm->arch.cpu_dirty_log_size)
kvm_mmu_clear_dirty_pt_masked(kvm, slot, gfn_offset, mask);
else
kvm_mmu_write_protect_pt_masked(kvm, slot, gfn_offset, mask);
}
-int kvm_cpu_dirty_log_size(void)
+int kvm_cpu_dirty_log_size(struct kvm *kvm)
{
- return kvm_x86_ops.cpu_dirty_log_size;
+ return kvm->arch.cpu_dirty_log_size;
}
bool kvm_mmu_slot_gfn_write_protect(struct kvm *kvm,
@@ -1982,14 +1983,35 @@ static bool sp_has_gptes(struct kvm_mmu_page *sp)
return true;
}
+static __ro_after_init HLIST_HEAD(empty_page_hash);
+
+static struct hlist_head *kvm_get_mmu_page_hash(struct kvm *kvm, gfn_t gfn)
+{
+ /*
+ * Ensure the load of the hash table pointer itself is ordered before
+ * loads to walk the table. The pointer is set at runtime outside of
+ * mmu_lock when the TDP MMU is enabled, i.e. when the hash table of
+ * shadow pages becomes necessary only when KVM needs to shadow L1's
+ * TDP for an L2 guest. Pairs with the smp_store_release() in
+ * kvm_mmu_alloc_page_hash().
+ */
+ struct hlist_head *page_hash = smp_load_acquire(&kvm->arch.mmu_page_hash);
+
+ lockdep_assert_held(&kvm->mmu_lock);
+
+ if (!page_hash)
+ return &empty_page_hash;
+
+ return &page_hash[kvm_page_table_hashfn(gfn)];
+}
+
#define for_each_valid_sp(_kvm, _sp, _list) \
hlist_for_each_entry(_sp, _list, hash_link) \
if (is_obsolete_sp((_kvm), (_sp))) { \
} else
#define for_each_gfn_valid_sp_with_gptes(_kvm, _sp, _gfn) \
- for_each_valid_sp(_kvm, _sp, \
- &(_kvm)->arch.mmu_page_hash[kvm_page_table_hashfn(_gfn)]) \
+ for_each_valid_sp(_kvm, _sp, kvm_get_mmu_page_hash(_kvm, _gfn)) \
if ((_sp)->gfn != (_gfn) || !sp_has_gptes(_sp)) {} else
static bool kvm_sync_page_check(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp)
@@ -2357,6 +2379,12 @@ static struct kvm_mmu_page *__kvm_mmu_get_shadow_page(struct kvm *kvm,
struct kvm_mmu_page *sp;
bool created = false;
+ /*
+ * No need for memory barriers, unlike in kvm_get_mmu_page_hash(), as
+ * mmu_page_hash must be set prior to creating the first shadow root,
+ * i.e. reaching this point is fully serialized by slots_arch_lock.
+ */
+ BUG_ON(!kvm->arch.mmu_page_hash);
sp_list = &kvm->arch.mmu_page_hash[kvm_page_table_hashfn(gfn)];
sp = kvm_mmu_find_shadow_page(kvm, vcpu, gfn, sp_list, role);
@@ -3019,7 +3047,8 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
}
if (is_shadow_present_pte(*sptep)) {
- if (prefetch)
+ if (prefetch && is_last_spte(*sptep, level) &&
+ pfn == spte_to_pfn(*sptep))
return RET_PF_SPURIOUS;
/*
@@ -3033,7 +3062,7 @@ static int mmu_set_spte(struct kvm_vcpu *vcpu, struct kvm_memory_slot *slot,
child = spte_to_child_sp(pte);
drop_parent_pte(vcpu->kvm, child, sptep);
flush = true;
- } else if (pfn != spte_to_pfn(*sptep)) {
+ } else if (WARN_ON_ONCE(pfn != spte_to_pfn(*sptep))) {
drop_spte(vcpu->kvm, sptep);
flush = true;
} else
@@ -3880,6 +3909,28 @@ out_unlock:
return r;
}
+static int kvm_mmu_alloc_page_hash(struct kvm *kvm)
+{
+ struct hlist_head *h;
+
+ if (kvm->arch.mmu_page_hash)
+ return 0;
+
+ h = kvcalloc(KVM_NUM_MMU_PAGES, sizeof(*h), GFP_KERNEL_ACCOUNT);
+ if (!h)
+ return -ENOMEM;
+
+ /*
+ * Ensure the hash table pointer is set only after all stores to zero
+ * the memory are retired. Pairs with the smp_load_acquire() in
+ * kvm_get_mmu_page_hash(). Note, mmu_lock must be held for write to
+ * add (or remove) shadow pages, and so readers are guaranteed to see
+ * an empty list for their current mmu_lock critical section.
+ */
+ smp_store_release(&kvm->arch.mmu_page_hash, h);
+ return 0;
+}
+
static int mmu_first_shadow_root_alloc(struct kvm *kvm)
{
struct kvm_memslots *slots;
@@ -3899,9 +3950,13 @@ static int mmu_first_shadow_root_alloc(struct kvm *kvm)
if (kvm_shadow_root_allocated(kvm))
goto out_unlock;
+ r = kvm_mmu_alloc_page_hash(kvm);
+ if (r)
+ goto out_unlock;
+
/*
- * Check if anything actually needs to be allocated, e.g. all metadata
- * will be allocated upfront if TDP is disabled.
+ * Check if memslot metadata actually needs to be allocated, e.g. all
+ * metadata will be allocated upfront if TDP is disabled.
*/
if (kvm_memslots_have_rmaps(kvm) &&
kvm_page_track_write_tracking_enabled(kvm))
@@ -4835,19 +4890,6 @@ out_unlock:
}
#endif
-bool kvm_mmu_may_ignore_guest_pat(void)
-{
- /*
- * When EPT is enabled (shadow_memtype_mask is non-zero), and the VM
- * has non-coherent DMA (DMA doesn't snoop CPU caches), KVM's ABI is to
- * honor the memtype from the guest's PAT so that guest accesses to
- * memory that is DMA'd aren't cached against the guest's wishes. As a
- * result, KVM _may_ ignore guest PAT, whereas without non-coherent DMA,
- * KVM _always_ ignores guest PAT (when EPT is enabled).
- */
- return shadow_memtype_mask;
-}
-
int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
{
#ifdef CONFIG_X86_64
@@ -4858,8 +4900,7 @@ int kvm_tdp_page_fault(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
return direct_page_fault(vcpu, fault);
}
-static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code,
- u8 *level)
+int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code, u8 *level)
{
int r;
@@ -4873,6 +4914,10 @@ static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code,
do {
if (signal_pending(current))
return -EINTR;
+
+ if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu))
+ return -EIO;
+
cond_resched();
r = kvm_mmu_do_page_fault(vcpu, gpa, error_code, true, NULL, level);
} while (r == RET_PF_RETRY);
@@ -4897,18 +4942,23 @@ static int kvm_tdp_map_page(struct kvm_vcpu *vcpu, gpa_t gpa, u64 error_code,
return -EIO;
}
}
+EXPORT_SYMBOL_GPL(kvm_tdp_map_page);
long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
struct kvm_pre_fault_memory *range)
{
u64 error_code = PFERR_GUEST_FINAL_MASK;
u8 level = PG_LEVEL_4K;
+ u64 direct_bits;
u64 end;
int r;
if (!vcpu->kvm->arch.pre_fault_allowed)
return -EOPNOTSUPP;
+ if (kvm_is_gfn_alias(vcpu->kvm, gpa_to_gfn(range->gpa)))
+ return -EINVAL;
+
/*
* reload is efficient when called repeatedly, so we can do it on
* every iteration.
@@ -4917,15 +4967,18 @@ long kvm_arch_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
if (r)
return r;
+ direct_bits = 0;
if (kvm_arch_has_private_mem(vcpu->kvm) &&
kvm_mem_is_private(vcpu->kvm, gpa_to_gfn(range->gpa)))
error_code |= PFERR_PRIVATE_ACCESS;
+ else
+ direct_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm));
/*
* Shadow paging uses GVA for kvm page fault, so restrict to
* two-dimensional paging.
*/
- r = kvm_tdp_map_page(vcpu, range->gpa, error_code, &level);
+ r = kvm_tdp_map_page(vcpu, range->gpa | direct_bits, error_code, &level);
if (r < 0)
return r;
@@ -5589,12 +5642,19 @@ void __kvm_mmu_refresh_passthrough_bits(struct kvm_vcpu *vcpu,
static inline int kvm_mmu_get_tdp_level(struct kvm_vcpu *vcpu)
{
+ int maxpa;
+
+ if (vcpu->kvm->arch.vm_type == KVM_X86_TDX_VM)
+ maxpa = cpuid_query_maxguestphyaddr(vcpu);
+ else
+ maxpa = cpuid_maxphyaddr(vcpu);
+
/* tdp_root_level is architecture forced level, use it if nonzero */
if (tdp_root_level)
return tdp_root_level;
/* Use 5-level TDP if and only if it's useful/necessary. */
- if (max_tdp_level == 5 && cpuid_maxphyaddr(vcpu) <= 48)
+ if (max_tdp_level == 5 && maxpa <= 48)
return 4;
return max_tdp_level;
@@ -5913,6 +5973,7 @@ int kvm_mmu_load(struct kvm_vcpu *vcpu)
out:
return r;
}
+EXPORT_SYMBOL_GPL(kvm_mmu_load);
void kvm_mmu_unload(struct kvm_vcpu *vcpu)
{
@@ -6674,15 +6735,22 @@ static void kvm_mmu_zap_all_fast(struct kvm *kvm)
kvm_tdp_mmu_zap_invalidated_roots(kvm, true);
}
-void kvm_mmu_init_vm(struct kvm *kvm)
+int kvm_mmu_init_vm(struct kvm *kvm)
{
+ int r;
+
kvm->arch.shadow_mmio_value = shadow_mmio_value;
INIT_LIST_HEAD(&kvm->arch.active_mmu_pages);
INIT_LIST_HEAD(&kvm->arch.possible_nx_huge_pages);
spin_lock_init(&kvm->arch.mmu_unsync_pages_lock);
- if (tdp_mmu_enabled)
+ if (tdp_mmu_enabled) {
kvm_mmu_init_tdp_mmu(kvm);
+ } else {
+ r = kvm_mmu_alloc_page_hash(kvm);
+ if (r)
+ return r;
+ }
kvm->arch.split_page_header_cache.kmem_cache = mmu_page_header_cache;
kvm->arch.split_page_header_cache.gfp_zero = __GFP_ZERO;
@@ -6691,6 +6759,7 @@ void kvm_mmu_init_vm(struct kvm *kvm)
kvm->arch.split_desc_cache.kmem_cache = pte_list_desc_cache;
kvm->arch.split_desc_cache.gfp_zero = __GFP_ZERO;
+ return 0;
}
static void mmu_free_vm_memory_caches(struct kvm *kvm)
@@ -6702,6 +6771,8 @@ static void mmu_free_vm_memory_caches(struct kvm *kvm)
void kvm_mmu_uninit_vm(struct kvm *kvm)
{
+ kvfree(kvm->arch.mmu_page_hash);
+
if (tdp_mmu_enabled)
kvm_mmu_uninit_tdp_mmu(kvm);
@@ -7239,6 +7310,7 @@ static void kvm_mmu_zap_memslot(struct kvm *kvm,
.start = slot->base_gfn,
.end = slot->base_gfn + slot->npages,
.may_block = true,
+ .attr_filter = KVM_FILTER_PRIVATE | KVM_FILTER_SHARED,
};
bool flush;
diff --git a/arch/x86/kvm/mmu/mmu_internal.h b/arch/x86/kvm/mmu/mmu_internal.h
index 75f00598289d..65f3c89d7c5d 100644
--- a/arch/x86/kvm/mmu/mmu_internal.h
+++ b/arch/x86/kvm/mmu/mmu_internal.h
@@ -103,6 +103,9 @@ struct kvm_mmu_page {
int root_count;
refcount_t tdp_mmu_root_count;
};
+
+ bool has_mapped_host_mmio;
+
union {
/* These two members aren't used for TDP MMU */
struct {
@@ -187,7 +190,8 @@ static inline gfn_t kvm_gfn_root_bits(const struct kvm *kvm, const struct kvm_mm
return kvm_gfn_direct_bits(kvm);
}
-static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp)
+static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm *kvm,
+ struct kvm_mmu_page *sp)
{
/*
* When using the EPT page-modification log, the GPAs in the CPU dirty
@@ -197,7 +201,7 @@ static inline bool kvm_mmu_page_ad_need_write_protect(struct kvm_mmu_page *sp)
* being enabled is mandatory as the bits used to denote WP-only SPTEs
* are reserved for PAE paging (32-bit KVM).
*/
- return kvm_x86_ops.cpu_dirty_log_size && sp->role.guest_mode;
+ return kvm->arch.cpu_dirty_log_size && sp->role.guest_mode;
}
static inline gfn_t gfn_round_for_level(gfn_t gfn, int level)
diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c
index 561c331fd6ec..1b17b12393a8 100644
--- a/arch/x86/kvm/mmu/page_track.c
+++ b/arch/x86/kvm/mmu/page_track.c
@@ -172,6 +172,9 @@ static int kvm_enable_external_write_tracking(struct kvm *kvm)
struct kvm_memory_slot *slot;
int r = 0, i, bkt;
+ if (kvm->arch.vm_type == KVM_X86_TDX_VM)
+ return -EOPNOTSUPP;
+
mutex_lock(&kvm->slots_arch_lock);
/*
diff --git a/arch/x86/kvm/mmu/paging_tmpl.h b/arch/x86/kvm/mmu/paging_tmpl.h
index 68e323568e95..ed762bb4b007 100644
--- a/arch/x86/kvm/mmu/paging_tmpl.h
+++ b/arch/x86/kvm/mmu/paging_tmpl.h
@@ -804,9 +804,12 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
if (r != RET_PF_CONTINUE)
return r;
+#if PTTYPE != PTTYPE_EPT
/*
- * Do not change pte_access if the pfn is a mmio page, otherwise
- * we will cache the incorrect access into mmio spte.
+ * Treat the guest PTE protections as writable, supervisor-only if this
+ * is a supervisor write fault and CR0.WP=0 (supervisor accesses ignore
+ * PTE.W if CR0.WP=0). Don't change the access type for emulated MMIO,
+ * otherwise KVM will cache incorrect access information in the SPTE.
*/
if (fault->write && !(walker.pte_access & ACC_WRITE_MASK) &&
!is_cr0_wp(vcpu->arch.mmu) && !fault->user && fault->slot) {
@@ -822,6 +825,7 @@ static int FNAME(page_fault)(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault
if (is_cr4_smep(vcpu->arch.mmu))
walker.pte_access &= ~ACC_EXEC_MASK;
}
+#endif
r = RET_PF_RETRY;
write_lock(&vcpu->kvm->mmu_lock);
diff --git a/arch/x86/kvm/mmu/spte.c b/arch/x86/kvm/mmu/spte.c
index 0f9f47b4ab0e..df31039b5d63 100644
--- a/arch/x86/kvm/mmu/spte.c
+++ b/arch/x86/kvm/mmu/spte.c
@@ -37,7 +37,6 @@ u64 __read_mostly shadow_mmio_value;
u64 __read_mostly shadow_mmio_mask;
u64 __read_mostly shadow_mmio_access_mask;
u64 __read_mostly shadow_present_mask;
-u64 __read_mostly shadow_memtype_mask;
u64 __read_mostly shadow_me_value;
u64 __read_mostly shadow_me_mask;
u64 __read_mostly shadow_acc_track_mask;
@@ -96,8 +95,6 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access)
u64 spte = generation_mmio_spte_mask(gen);
u64 gpa = gfn << PAGE_SHIFT;
- WARN_ON_ONCE(!vcpu->kvm->arch.shadow_mmio_value);
-
access &= shadow_mmio_access_mask;
spte |= vcpu->kvm->arch.shadow_mmio_value | access;
spte |= gpa | shadow_nonpresent_or_rsvd_mask;
@@ -107,7 +104,7 @@ u64 make_mmio_spte(struct kvm_vcpu *vcpu, u64 gfn, unsigned int access)
return spte;
}
-static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
+static bool __kvm_is_mmio_pfn(kvm_pfn_t pfn)
{
if (pfn_valid(pfn))
return !is_zero_pfn(pfn) && PageReserved(pfn_to_page(pfn)) &&
@@ -128,6 +125,35 @@ static bool kvm_is_mmio_pfn(kvm_pfn_t pfn)
E820_TYPE_RAM);
}
+static bool kvm_is_mmio_pfn(kvm_pfn_t pfn, int *is_host_mmio)
+{
+ /*
+ * Determining if a PFN is host MMIO is relative expensive. Cache the
+ * result locally (in the sole caller) to avoid doing the full query
+ * multiple times when creating a single SPTE.
+ */
+ if (*is_host_mmio < 0)
+ *is_host_mmio = __kvm_is_mmio_pfn(pfn);
+
+ return *is_host_mmio;
+}
+
+static void kvm_track_host_mmio_mapping(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa);
+
+ if (root)
+ WRITE_ONCE(root->has_mapped_host_mmio, true);
+ else
+ WRITE_ONCE(vcpu->kvm->arch.has_mapped_host_mmio, true);
+
+ /*
+ * Force vCPUs to exit and flush CPU buffers if the vCPU is using the
+ * affected root(s).
+ */
+ kvm_make_all_cpus_request(vcpu->kvm, KVM_REQ_OUTSIDE_GUEST_MODE);
+}
+
/*
* Returns true if the SPTE needs to be updated atomically due to having bits
* that may be changed without holding mmu_lock, and for which KVM must not
@@ -165,6 +191,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
{
int level = sp->role.level;
u64 spte = SPTE_MMU_PRESENT_MASK;
+ int is_host_mmio = -1;
bool wrprot = false;
/*
@@ -177,7 +204,7 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
if (sp->role.ad_disabled)
spte |= SPTE_TDP_AD_DISABLED;
- else if (kvm_mmu_page_ad_need_write_protect(sp))
+ else if (kvm_mmu_page_ad_need_write_protect(vcpu->kvm, sp))
spte |= SPTE_TDP_AD_WRPROT_ONLY;
spte |= shadow_present_mask;
@@ -212,15 +239,15 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
if (level > PG_LEVEL_4K)
spte |= PT_PAGE_SIZE_MASK;
- if (shadow_memtype_mask)
+ if (kvm_x86_ops.get_mt_mask)
spte |= kvm_x86_call(get_mt_mask)(vcpu, gfn,
- kvm_is_mmio_pfn(pfn));
+ kvm_is_mmio_pfn(pfn, &is_host_mmio));
if (host_writable)
spte |= shadow_host_writable_mask;
else
pte_access &= ~ACC_WRITE_MASK;
- if (shadow_me_value && !kvm_is_mmio_pfn(pfn))
+ if (shadow_me_value && !kvm_is_mmio_pfn(pfn, &is_host_mmio))
spte |= shadow_me_value;
spte |= (u64)pfn << PAGE_SHIFT;
@@ -265,6 +292,11 @@ bool make_spte(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
mark_page_dirty_in_slot(vcpu->kvm, slot, gfn);
}
+ if (static_branch_unlikely(&cpu_buf_vm_clear) &&
+ !kvm_vcpu_can_access_host_mmio(vcpu) &&
+ kvm_is_mmio_pfn(pfn, &is_host_mmio))
+ kvm_track_host_mmio_mapping(vcpu);
+
*new_spte = spte;
return wrprot;
}
@@ -440,6 +472,12 @@ void kvm_mmu_set_mmio_spte_mask(u64 mmio_value, u64 mmio_mask, u64 access_mask)
}
EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_mask);
+void kvm_mmu_set_mmio_spte_value(struct kvm *kvm, u64 mmio_value)
+{
+ kvm->arch.shadow_mmio_value = mmio_value;
+}
+EXPORT_SYMBOL_GPL(kvm_mmu_set_mmio_spte_value);
+
void kvm_mmu_set_me_spte_mask(u64 me_value, u64 me_mask)
{
/* shadow_me_value must be a subset of shadow_me_mask */
@@ -463,13 +501,7 @@ void kvm_mmu_set_ept_masks(bool has_ad_bits, bool has_exec_only)
/* VMX_EPT_SUPPRESS_VE_BIT is needed for W or X violation. */
shadow_present_mask =
(has_exec_only ? 0ull : VMX_EPT_READABLE_MASK) | VMX_EPT_SUPPRESS_VE_BIT;
- /*
- * EPT overrides the host MTRRs, and so KVM must program the desired
- * memtype directly into the SPTEs. Note, this mask is just the mask
- * of all bits that factor into the memtype, the actual memtype must be
- * dynamically calculated, e.g. to ensure host MMIO is mapped UC.
- */
- shadow_memtype_mask = VMX_EPT_MT_MASK | VMX_EPT_IPAT_BIT;
+
shadow_acc_track_mask = VMX_EPT_RWX_MASK;
shadow_host_writable_mask = EPT_SPTE_HOST_WRITABLE;
shadow_mmu_writable_mask = EPT_SPTE_MMU_WRITABLE;
@@ -521,12 +553,6 @@ void kvm_mmu_reset_all_pte_masks(void)
shadow_x_mask = 0;
shadow_present_mask = PT_PRESENT_MASK;
- /*
- * For shadow paging and NPT, KVM uses PAT entry '0' to encode WB
- * memtype in the SPTEs, i.e. relies on host MTRRs to provide the
- * correct memtype (WB is the "weakest" memtype).
- */
- shadow_memtype_mask = 0;
shadow_acc_track_mask = 0;
shadow_me_mask = 0;
shadow_me_value = 0;
diff --git a/arch/x86/kvm/mmu/spte.h b/arch/x86/kvm/mmu/spte.h
index 79cdceba9857..3133f066927e 100644
--- a/arch/x86/kvm/mmu/spte.h
+++ b/arch/x86/kvm/mmu/spte.h
@@ -187,7 +187,6 @@ extern u64 __read_mostly shadow_mmio_value;
extern u64 __read_mostly shadow_mmio_mask;
extern u64 __read_mostly shadow_mmio_access_mask;
extern u64 __read_mostly shadow_present_mask;
-extern u64 __read_mostly shadow_memtype_mask;
extern u64 __read_mostly shadow_me_value;
extern u64 __read_mostly shadow_me_mask;
@@ -281,6 +280,16 @@ static inline bool is_mirror_sptep(tdp_ptep_t sptep)
return is_mirror_sp(sptep_to_sp(rcu_dereference(sptep)));
}
+static inline bool kvm_vcpu_can_access_host_mmio(struct kvm_vcpu *vcpu)
+{
+ struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa);
+
+ if (root)
+ return READ_ONCE(root->has_mapped_host_mmio);
+
+ return READ_ONCE(vcpu->kvm->arch.has_mapped_host_mmio);
+}
+
static inline bool is_mmio_spte(struct kvm *kvm, u64 spte)
{
return (spte & shadow_mmio_mask) == kvm->arch.shadow_mmio_value &&
diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c
index 21a3b8166242..7f3d7229b2c1 100644
--- a/arch/x86/kvm/mmu/tdp_mmu.c
+++ b/arch/x86/kvm/mmu/tdp_mmu.c
@@ -378,7 +378,7 @@ static void remove_external_spte(struct kvm *kvm, gfn_t gfn, u64 old_spte,
/* Zapping leaf spte is allowed only when write lock is held. */
lockdep_assert_held_write(&kvm->mmu_lock);
/* Because write lock is held, operation should success. */
- ret = static_call(kvm_x86_remove_external_spte)(kvm, gfn, level, old_pfn);
+ ret = kvm_x86_call(remove_external_spte)(kvm, gfn, level, old_pfn);
KVM_BUG_ON(ret, kvm);
}
@@ -485,8 +485,8 @@ static void handle_removed_pt(struct kvm *kvm, tdp_ptep_t pt, bool shared)
}
if (is_mirror_sp(sp) &&
- WARN_ON(static_call(kvm_x86_free_external_spt)(kvm, base_gfn, sp->role.level,
- sp->external_spt))) {
+ WARN_ON(kvm_x86_call(free_external_spt)(kvm, base_gfn, sp->role.level,
+ sp->external_spt))) {
/*
* Failed to free page table page in mirror page table and
* there is nothing to do further.
@@ -538,12 +538,12 @@ static int __must_check set_external_spte_present(struct kvm *kvm, tdp_ptep_t sp
* external page table, or leaf.
*/
if (is_leaf) {
- ret = static_call(kvm_x86_set_external_spte)(kvm, gfn, level, new_pfn);
+ ret = kvm_x86_call(set_external_spte)(kvm, gfn, level, new_pfn);
} else {
void *external_spt = get_external_spt(gfn, new_spte, level);
KVM_BUG_ON(!external_spt, kvm);
- ret = static_call(kvm_x86_link_external_spt)(kvm, gfn, level, external_spt);
+ ret = kvm_x86_call(link_external_spt)(kvm, gfn, level, external_spt);
}
if (ret)
__kvm_tdp_mmu_write_spte(sptep, old_spte);
@@ -1153,13 +1153,12 @@ static int tdp_mmu_map_handle_target_level(struct kvm_vcpu *vcpu,
if (WARN_ON_ONCE(sp->role.level != fault->goal_level))
return RET_PF_RETRY;
- if (fault->prefetch && is_shadow_present_pte(iter->old_spte))
- return RET_PF_SPURIOUS;
-
if (is_shadow_present_pte(iter->old_spte) &&
- is_access_allowed(fault, iter->old_spte) &&
- is_last_spte(iter->old_spte, iter->level))
+ (fault->prefetch || is_access_allowed(fault, iter->old_spte)) &&
+ is_last_spte(iter->old_spte, iter->level)) {
+ WARN_ON_ONCE(fault->pfn != spte_to_pfn(iter->old_spte));
return RET_PF_SPURIOUS;
+ }
if (unlikely(!fault->slot))
new_spte = make_mmio_spte(vcpu, iter->gfn, ACC_ALL);
@@ -1630,21 +1629,21 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm,
}
}
-static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp)
+static bool tdp_mmu_need_write_protect(struct kvm *kvm, struct kvm_mmu_page *sp)
{
/*
* All TDP MMU shadow pages share the same role as their root, aside
* from level, so it is valid to key off any shadow page to determine if
* write protection is needed for an entire tree.
*/
- return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled;
+ return kvm_mmu_page_ad_need_write_protect(kvm, sp) || !kvm_ad_enabled;
}
static void clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root,
gfn_t start, gfn_t end)
{
- const u64 dbit = tdp_mmu_need_write_protect(root) ? PT_WRITABLE_MASK :
- shadow_dirty_mask;
+ const u64 dbit = tdp_mmu_need_write_protect(kvm, root) ?
+ PT_WRITABLE_MASK : shadow_dirty_mask;
struct tdp_iter iter;
rcu_read_lock();
@@ -1689,8 +1688,8 @@ void kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm,
static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root,
gfn_t gfn, unsigned long mask, bool wrprot)
{
- const u64 dbit = (wrprot || tdp_mmu_need_write_protect(root)) ? PT_WRITABLE_MASK :
- shadow_dirty_mask;
+ const u64 dbit = (wrprot || tdp_mmu_need_write_protect(kvm, root)) ?
+ PT_WRITABLE_MASK : shadow_dirty_mask;
struct tdp_iter iter;
lockdep_assert_held_write(&kvm->mmu_lock);
@@ -1911,16 +1910,13 @@ bool kvm_tdp_mmu_write_protect_gfn(struct kvm *kvm,
*
* Must be called between kvm_tdp_mmu_walk_lockless_{begin,end}.
*/
-int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
- int *root_level)
+static int __kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+ struct kvm_mmu_page *root)
{
- struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa);
struct tdp_iter iter;
gfn_t gfn = addr >> PAGE_SHIFT;
int leaf = -1;
- *root_level = vcpu->arch.mmu->root_role.level;
-
for_each_tdp_pte(iter, vcpu->kvm, root, gfn, gfn + 1) {
leaf = iter.level;
sptes[leaf] = iter.old_spte;
@@ -1929,6 +1925,36 @@ int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
return leaf;
}
+int kvm_tdp_mmu_get_walk(struct kvm_vcpu *vcpu, u64 addr, u64 *sptes,
+ int *root_level)
+{
+ struct kvm_mmu_page *root = root_to_sp(vcpu->arch.mmu->root.hpa);
+ *root_level = vcpu->arch.mmu->root_role.level;
+
+ return __kvm_tdp_mmu_get_walk(vcpu, addr, sptes, root);
+}
+
+bool kvm_tdp_mmu_gpa_is_mapped(struct kvm_vcpu *vcpu, u64 gpa)
+{
+ struct kvm *kvm = vcpu->kvm;
+ bool is_direct = kvm_is_addr_direct(kvm, gpa);
+ hpa_t root = is_direct ? vcpu->arch.mmu->root.hpa :
+ vcpu->arch.mmu->mirror_root_hpa;
+ u64 sptes[PT64_ROOT_MAX_LEVEL + 1], spte;
+ int leaf;
+
+ lockdep_assert_held(&kvm->mmu_lock);
+ rcu_read_lock();
+ leaf = __kvm_tdp_mmu_get_walk(vcpu, gpa, sptes, root_to_sp(root));
+ rcu_read_unlock();
+ if (leaf < 0)
+ return false;
+
+ spte = sptes[leaf];
+ return is_shadow_present_pte(spte) && is_last_spte(spte, leaf);
+}
+EXPORT_SYMBOL_GPL(kvm_tdp_mmu_gpa_is_mapped);
+
/*
* Returns the last level spte pointer of the shadow page walk for the given
* gpa, and sets *spte to the spte value. This spte may be non-preset. If no
diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h
index fde0ae986003..c53b92379e6e 100644
--- a/arch/x86/kvm/reverse_cpuid.h
+++ b/arch/x86/kvm/reverse_cpuid.h
@@ -52,6 +52,10 @@
/* CPUID level 0x80000022 (EAX) */
#define KVM_X86_FEATURE_PERFMON_V2 KVM_X86_FEATURE(CPUID_8000_0022_EAX, 0)
+/* CPUID level 0x80000021 (ECX) */
+#define KVM_X86_FEATURE_TSA_SQ_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 1)
+#define KVM_X86_FEATURE_TSA_L1_NO KVM_X86_FEATURE(CPUID_8000_0021_ECX, 2)
+
struct cpuid_reg {
u32 function;
u32 index;
@@ -82,6 +86,7 @@ static const struct cpuid_reg reverse_cpuid[] = {
[CPUID_8000_0022_EAX] = {0x80000022, 0, CPUID_EAX},
[CPUID_7_2_EDX] = { 7, 2, CPUID_EDX},
[CPUID_24_0_EBX] = { 0x24, 0, CPUID_EBX},
+ [CPUID_8000_0021_ECX] = {0x80000021, 0, CPUID_ECX},
};
/*
@@ -121,6 +126,8 @@ static __always_inline u32 __feature_translate(int x86_feature)
KVM_X86_TRANSLATE_FEATURE(PERFMON_V2);
KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL);
KVM_X86_TRANSLATE_FEATURE(BHI_CTRL);
+ KVM_X86_TRANSLATE_FEATURE(TSA_SQ_NO);
+ KVM_X86_TRANSLATE_FEATURE(TSA_L1_NO);
default:
return x86_feature;
}
diff --git a/arch/x86/kvm/smm.h b/arch/x86/kvm/smm.h
index a1cf2ac5bd78..551703fbe200 100644
--- a/arch/x86/kvm/smm.h
+++ b/arch/x86/kvm/smm.h
@@ -142,6 +142,9 @@ union kvm_smram {
static inline int kvm_inject_smi(struct kvm_vcpu *vcpu)
{
+ if (!kvm_x86_call(has_emulated_msr)(vcpu->kvm, MSR_IA32_SMBASE))
+ return -ENOTTY;
+
kvm_make_request(KVM_REQ_SMI, vcpu);
return 0;
}
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 7338879d1c0c..a34c5c3b164e 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -18,8 +18,10 @@
#include <linux/hashtable.h>
#include <linux/amd-iommu.h>
#include <linux/kvm_host.h>
+#include <linux/kvm_irqfd.h>
#include <asm/irq_remapping.h>
+#include <asm/msr.h>
#include "trace.h"
#include "lapic.h"
@@ -28,36 +30,39 @@
#include "svm.h"
/*
- * Encode the arbitrary VM ID and the vCPU's default APIC ID, i.e the vCPU ID,
- * into the GATag so that KVM can retrieve the correct vCPU from a GALog entry
- * if an interrupt can't be delivered, e.g. because the vCPU isn't running.
+ * Encode the arbitrary VM ID and the vCPU's _index_ into the GATag so that
+ * KVM can retrieve the correct vCPU from a GALog entry if an interrupt can't
+ * be delivered, e.g. because the vCPU isn't running. Use the vCPU's index
+ * instead of its ID (a.k.a. its default APIC ID), as KVM is guaranteed a fast
+ * lookup on the index, where as vCPUs whose index doesn't match their ID need
+ * to walk the entire xarray of vCPUs in the worst case scenario.
*
- * For the vCPU ID, use however many bits are currently allowed for the max
+ * For the vCPU index, use however many bits are currently allowed for the max
* guest physical APIC ID (limited by the size of the physical ID table), and
* use whatever bits remain to assign arbitrary AVIC IDs to VMs. Note, the
* size of the GATag is defined by hardware (32 bits), but is an opaque value
* as far as hardware is concerned.
*/
-#define AVIC_VCPU_ID_MASK AVIC_PHYSICAL_MAX_INDEX_MASK
+#define AVIC_VCPU_IDX_MASK AVIC_PHYSICAL_MAX_INDEX_MASK
#define AVIC_VM_ID_SHIFT HWEIGHT32(AVIC_PHYSICAL_MAX_INDEX_MASK)
#define AVIC_VM_ID_MASK (GENMASK(31, AVIC_VM_ID_SHIFT) >> AVIC_VM_ID_SHIFT)
#define AVIC_GATAG_TO_VMID(x) ((x >> AVIC_VM_ID_SHIFT) & AVIC_VM_ID_MASK)
-#define AVIC_GATAG_TO_VCPUID(x) (x & AVIC_VCPU_ID_MASK)
+#define AVIC_GATAG_TO_VCPUIDX(x) (x & AVIC_VCPU_IDX_MASK)
-#define __AVIC_GATAG(vm_id, vcpu_id) ((((vm_id) & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \
- ((vcpu_id) & AVIC_VCPU_ID_MASK))
-#define AVIC_GATAG(vm_id, vcpu_id) \
+#define __AVIC_GATAG(vm_id, vcpu_idx) ((((vm_id) & AVIC_VM_ID_MASK) << AVIC_VM_ID_SHIFT) | \
+ ((vcpu_idx) & AVIC_VCPU_IDX_MASK))
+#define AVIC_GATAG(vm_id, vcpu_idx) \
({ \
- u32 ga_tag = __AVIC_GATAG(vm_id, vcpu_id); \
+ u32 ga_tag = __AVIC_GATAG(vm_id, vcpu_idx); \
\
- WARN_ON_ONCE(AVIC_GATAG_TO_VCPUID(ga_tag) != (vcpu_id)); \
+ WARN_ON_ONCE(AVIC_GATAG_TO_VCPUIDX(ga_tag) != (vcpu_idx)); \
WARN_ON_ONCE(AVIC_GATAG_TO_VMID(ga_tag) != (vm_id)); \
ga_tag; \
})
-static_assert(__AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_ID_MASK) == -1u);
+static_assert(__AVIC_GATAG(AVIC_VM_ID_MASK, AVIC_VCPU_IDX_MASK) == -1u);
static bool force_avic;
module_param_unsafe(force_avic, bool, 0444);
@@ -74,14 +79,6 @@ static bool next_vm_id_wrapped = 0;
static DEFINE_SPINLOCK(svm_vm_data_hash_lock);
bool x2avic_enabled;
-/*
- * This is a wrapper of struct amd_iommu_ir_data.
- */
-struct amd_svm_iommu_ir {
- struct list_head node; /* Used by SVM for per-vcpu ir_list */
- void *data; /* Storing pointer to struct amd_ir_data */
-};
-
static void avic_activate_vmcb(struct vcpu_svm *svm)
{
struct vmcb *vmcb = svm->vmcb01.ptr;
@@ -146,16 +143,16 @@ int avic_ga_log_notifier(u32 ga_tag)
struct kvm_svm *kvm_svm;
struct kvm_vcpu *vcpu = NULL;
u32 vm_id = AVIC_GATAG_TO_VMID(ga_tag);
- u32 vcpu_id = AVIC_GATAG_TO_VCPUID(ga_tag);
+ u32 vcpu_idx = AVIC_GATAG_TO_VCPUIDX(ga_tag);
- pr_debug("SVM: %s: vm_id=%#x, vcpu_id=%#x\n", __func__, vm_id, vcpu_id);
- trace_kvm_avic_ga_log(vm_id, vcpu_id);
+ pr_debug("SVM: %s: vm_id=%#x, vcpu_idx=%#x\n", __func__, vm_id, vcpu_idx);
+ trace_kvm_avic_ga_log(vm_id, vcpu_idx);
spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
hash_for_each_possible(svm_vm_data_hash, kvm_svm, hnode, vm_id) {
if (kvm_svm->avic_vm_id != vm_id)
continue;
- vcpu = kvm_get_vcpu_by_id(&kvm_svm->kvm, vcpu_id);
+ vcpu = kvm_get_vcpu(&kvm_svm->kvm, vcpu_idx);
break;
}
spin_unlock_irqrestore(&svm_vm_data_hash_lock, flags);
@@ -179,10 +176,8 @@ void avic_vm_destroy(struct kvm *kvm)
if (!enable_apicv)
return;
- if (kvm_svm->avic_logical_id_table_page)
- __free_page(kvm_svm->avic_logical_id_table_page);
- if (kvm_svm->avic_physical_id_table_page)
- __free_page(kvm_svm->avic_physical_id_table_page);
+ free_page((unsigned long)kvm_svm->avic_logical_id_table);
+ free_page((unsigned long)kvm_svm->avic_physical_id_table);
spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
hash_del(&kvm_svm->hnode);
@@ -195,27 +190,19 @@ int avic_vm_init(struct kvm *kvm)
int err = -ENOMEM;
struct kvm_svm *kvm_svm = to_kvm_svm(kvm);
struct kvm_svm *k2;
- struct page *p_page;
- struct page *l_page;
u32 vm_id;
if (!enable_apicv)
return 0;
- /* Allocating physical APIC ID table (4KB) */
- p_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
- if (!p_page)
+ kvm_svm->avic_physical_id_table = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+ if (!kvm_svm->avic_physical_id_table)
goto free_avic;
- kvm_svm->avic_physical_id_table_page = p_page;
-
- /* Allocating logical APIC ID table (4KB) */
- l_page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO);
- if (!l_page)
+ kvm_svm->avic_logical_id_table = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
+ if (!kvm_svm->avic_logical_id_table)
goto free_avic;
- kvm_svm->avic_logical_id_table_page = l_page;
-
spin_lock_irqsave(&svm_vm_data_hash_lock, flags);
again:
vm_id = next_vm_id = (next_vm_id + 1) & AVIC_VM_ID_MASK;
@@ -241,17 +228,19 @@ free_avic:
return err;
}
+static phys_addr_t avic_get_backing_page_address(struct vcpu_svm *svm)
+{
+ return __sme_set(__pa(svm->vcpu.arch.apic->regs));
+}
+
void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb)
{
struct kvm_svm *kvm_svm = to_kvm_svm(svm->vcpu.kvm);
- phys_addr_t bpa = __sme_set(page_to_phys(svm->avic_backing_page));
- phys_addr_t lpa = __sme_set(page_to_phys(kvm_svm->avic_logical_id_table_page));
- phys_addr_t ppa = __sme_set(page_to_phys(kvm_svm->avic_physical_id_table_page));
- vmcb->control.avic_backing_page = bpa & AVIC_HPA_MASK;
- vmcb->control.avic_logical_id = lpa & AVIC_HPA_MASK;
- vmcb->control.avic_physical_id = ppa & AVIC_HPA_MASK;
- vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE & VMCB_AVIC_APIC_BAR_MASK;
+ vmcb->control.avic_backing_page = avic_get_backing_page_address(svm);
+ vmcb->control.avic_logical_id = __sme_set(__pa(kvm_svm->avic_logical_id_table));
+ vmcb->control.avic_physical_id = __sme_set(__pa(kvm_svm->avic_physical_id_table));
+ vmcb->control.avic_vapic_bar = APIC_DEFAULT_PHYS_BASE;
if (kvm_apicv_activated(svm->vcpu.kvm))
avic_activate_vmcb(svm);
@@ -259,32 +248,31 @@ void avic_init_vmcb(struct vcpu_svm *svm, struct vmcb *vmcb)
avic_deactivate_vmcb(svm);
}
-static u64 *avic_get_physical_id_entry(struct kvm_vcpu *vcpu,
- unsigned int index)
-{
- u64 *avic_physical_id_table;
- struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
-
- if ((!x2avic_enabled && index > AVIC_MAX_PHYSICAL_ID) ||
- (index > X2AVIC_MAX_PHYSICAL_ID))
- return NULL;
-
- avic_physical_id_table = page_address(kvm_svm->avic_physical_id_table_page);
-
- return &avic_physical_id_table[index];
-}
-
static int avic_init_backing_page(struct kvm_vcpu *vcpu)
{
- u64 *entry, new_entry;
- int id = vcpu->vcpu_id;
+ struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
struct vcpu_svm *svm = to_svm(vcpu);
+ u32 id = vcpu->vcpu_id;
+ u64 new_entry;
+ /*
+ * Inhibit AVIC if the vCPU ID is bigger than what is supported by AVIC
+ * hardware. Immediately clear apicv_active, i.e. don't wait until the
+ * KVM_REQ_APICV_UPDATE request is processed on the first KVM_RUN, as
+ * avic_vcpu_load() expects to be called if and only if the vCPU has
+ * fully initialized AVIC.
+ */
if ((!x2avic_enabled && id > AVIC_MAX_PHYSICAL_ID) ||
- (id > X2AVIC_MAX_PHYSICAL_ID))
- return -EINVAL;
+ (id > X2AVIC_MAX_PHYSICAL_ID)) {
+ kvm_set_apicv_inhibit(vcpu->kvm, APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG);
+ vcpu->arch.apic->apicv_active = false;
+ return 0;
+ }
+
+ BUILD_BUG_ON((AVIC_MAX_PHYSICAL_ID + 1) * sizeof(new_entry) > PAGE_SIZE ||
+ (X2AVIC_MAX_PHYSICAL_ID + 1) * sizeof(new_entry) > PAGE_SIZE);
- if (!vcpu->arch.apic->regs)
+ if (WARN_ON_ONCE(!vcpu->arch.apic->regs))
return -EINVAL;
if (kvm_apicv_activated(vcpu->kvm)) {
@@ -301,19 +289,21 @@ static int avic_init_backing_page(struct kvm_vcpu *vcpu)
return ret;
}
- svm->avic_backing_page = virt_to_page(vcpu->arch.apic->regs);
+ /* Note, fls64() returns the bit position, +1. */
+ BUILD_BUG_ON(__PHYSICAL_MASK_SHIFT >
+ fls64(AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK));
/* Setting AVIC backing page address in the phy APIC ID table */
- entry = avic_get_physical_id_entry(vcpu, id);
- if (!entry)
- return -EINVAL;
+ new_entry = avic_get_backing_page_address(svm) |
+ AVIC_PHYSICAL_ID_ENTRY_VALID_MASK;
+ svm->avic_physical_id_entry = new_entry;
- new_entry = __sme_set((page_to_phys(svm->avic_backing_page) &
- AVIC_PHYSICAL_ID_ENTRY_BACKING_PAGE_MASK) |
- AVIC_PHYSICAL_ID_ENTRY_VALID_MASK);
- WRITE_ONCE(*entry, new_entry);
-
- svm->avic_physical_id_cache = entry;
+ /*
+ * Initialize the real table, as vCPUs must have a valid entry in order
+ * for broadcast IPIs to function correctly (broadcast IPIs ignore
+ * invalid entries, i.e. aren't guaranteed to generate a VM-Exit).
+ */
+ WRITE_ONCE(kvm_svm->avic_physical_id_table[id], new_entry);
return 0;
}
@@ -330,7 +320,7 @@ void avic_ring_doorbell(struct kvm_vcpu *vcpu)
int cpu = READ_ONCE(vcpu->cpu);
if (cpu != get_cpu()) {
- wrmsrl(MSR_AMD64_SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu));
+ wrmsrq(MSR_AMD64_SVM_AVIC_DOORBELL, kvm_cpu_get_apicid(cpu));
trace_kvm_avic_doorbell(vcpu->vcpu_id, kvm_cpu_get_apicid(cpu));
}
put_cpu();
@@ -447,7 +437,7 @@ static int avic_kick_target_vcpus_fast(struct kvm *kvm, struct kvm_lapic *source
if (apic_x2apic_mode(source))
avic_logical_id_table = NULL;
else
- avic_logical_id_table = page_address(kvm_svm->avic_logical_id_table_page);
+ avic_logical_id_table = kvm_svm->avic_logical_id_table;
/*
* AVIC is inhibited if vCPUs aren't mapped 1:1 with logical
@@ -549,7 +539,6 @@ unsigned long avic_vcpu_get_apicv_inhibit_reasons(struct kvm_vcpu *vcpu)
static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat)
{
struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
- u32 *logical_apic_id_table;
u32 cluster, index;
ldr = GET_APIC_LOGICAL_ID(ldr);
@@ -570,9 +559,7 @@ static u32 *avic_get_logical_id_entry(struct kvm_vcpu *vcpu, u32 ldr, bool flat)
return NULL;
index += (cluster << 2);
- logical_apic_id_table = (u32 *) page_address(kvm_svm->avic_logical_id_table_page);
-
- return &logical_apic_id_table[index];
+ return &kvm_svm->avic_logical_id_table[index];
}
static void avic_ldr_write(struct kvm_vcpu *vcpu, u8 g_physical_id, u32 ldr)
@@ -721,6 +708,9 @@ int avic_init_vcpu(struct vcpu_svm *svm)
int ret;
struct kvm_vcpu *vcpu = &svm->vcpu;
+ INIT_LIST_HEAD(&svm->ir_list);
+ spin_lock_init(&svm->ir_list_lock);
+
if (!enable_apicv || !irqchip_in_kernel(vcpu->kvm))
return 0;
@@ -728,8 +718,6 @@ int avic_init_vcpu(struct vcpu_svm *svm)
if (ret)
return ret;
- INIT_LIST_HEAD(&svm->ir_list);
- spin_lock_init(&svm->ir_list_lock);
svm->dfr_reg = APIC_DFR_FLAT;
return ret;
@@ -741,316 +729,161 @@ void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu)
avic_handle_ldr_update(vcpu);
}
-static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
+static void svm_ir_list_del(struct kvm_kernel_irqfd *irqfd)
{
- int ret = 0;
+ struct kvm_vcpu *vcpu = irqfd->irq_bypass_vcpu;
unsigned long flags;
- struct amd_svm_iommu_ir *ir;
- struct vcpu_svm *svm = to_svm(vcpu);
-
- if (!kvm_arch_has_assigned_device(vcpu->kvm))
- return 0;
- /*
- * Here, we go through the per-vcpu ir_list to update all existing
- * interrupt remapping table entry targeting this vcpu.
- */
- spin_lock_irqsave(&svm->ir_list_lock, flags);
-
- if (list_empty(&svm->ir_list))
- goto out;
+ if (!vcpu)
+ return;
- list_for_each_entry(ir, &svm->ir_list, node) {
- if (activate)
- ret = amd_iommu_activate_guest_mode(ir->data);
- else
- ret = amd_iommu_deactivate_guest_mode(ir->data);
- if (ret)
- break;
- }
-out:
- spin_unlock_irqrestore(&svm->ir_list_lock, flags);
- return ret;
+ spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags);
+ list_del(&irqfd->vcpu_list);
+ spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags);
}
-static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
+int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+ unsigned int host_irq, uint32_t guest_irq,
+ struct kvm_vcpu *vcpu, u32 vector)
{
- unsigned long flags;
- struct amd_svm_iommu_ir *cur;
-
- spin_lock_irqsave(&svm->ir_list_lock, flags);
- list_for_each_entry(cur, &svm->ir_list, node) {
- if (cur->data != pi->ir_data)
- continue;
- list_del(&cur->node);
- kfree(cur);
- break;
- }
- spin_unlock_irqrestore(&svm->ir_list_lock, flags);
-}
-
-static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
-{
- int ret = 0;
- unsigned long flags;
- struct amd_svm_iommu_ir *ir;
- u64 entry;
-
- if (WARN_ON_ONCE(!pi->ir_data))
- return -EINVAL;
-
- /**
- * In some cases, the existing irte is updated and re-set,
- * so we need to check here if it's already been * added
- * to the ir_list.
- */
- if (pi->prev_ga_tag) {
- struct kvm *kvm = svm->vcpu.kvm;
- u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
- struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
- struct vcpu_svm *prev_svm;
-
- if (!prev_vcpu) {
- ret = -EINVAL;
- goto out;
- }
-
- prev_svm = to_svm(prev_vcpu);
- svm_ir_list_del(prev_svm, pi);
- }
-
- /**
- * Allocating new amd_iommu_pi_data, which will get
- * add to the per-vcpu ir_list.
- */
- ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT);
- if (!ir) {
- ret = -ENOMEM;
- goto out;
- }
- ir->data = pi->ir_data;
-
- spin_lock_irqsave(&svm->ir_list_lock, flags);
-
/*
- * Update the target pCPU for IOMMU doorbells if the vCPU is running.
- * If the vCPU is NOT running, i.e. is blocking or scheduled out, KVM
- * will update the pCPU info when the vCPU awkened and/or scheduled in.
- * See also avic_vcpu_load().
+ * If the IRQ was affined to a different vCPU, remove the IRTE metadata
+ * from the *previous* vCPU's list.
*/
- entry = READ_ONCE(*(svm->avic_physical_id_cache));
- if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
- amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK,
- true, pi->ir_data);
-
- list_add(&ir->node, &svm->ir_list);
- spin_unlock_irqrestore(&svm->ir_list_lock, flags);
-out:
- return ret;
-}
+ svm_ir_list_del(irqfd);
-/*
- * Note:
- * The HW cannot support posting multicast/broadcast
- * interrupts to a vCPU. So, we still use legacy interrupt
- * remapping for these kind of interrupts.
- *
- * For lowest-priority interrupts, we only support
- * those with single CPU as the destination, e.g. user
- * configures the interrupts via /proc/irq or uses
- * irqbalance to make the interrupts single-CPU.
- */
-static int
-get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
- struct vcpu_data *vcpu_info, struct vcpu_svm **svm)
-{
- struct kvm_lapic_irq irq;
- struct kvm_vcpu *vcpu = NULL;
-
- kvm_set_msi_irq(kvm, e, &irq);
-
- if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
- !kvm_irq_is_postable(&irq)) {
- pr_debug("SVM: %s: use legacy intr remap mode for irq %u\n",
- __func__, irq.vector);
- return -1;
- }
-
- pr_debug("SVM: %s: use GA mode for irq %u\n", __func__,
- irq.vector);
- *svm = to_svm(vcpu);
- vcpu_info->pi_desc_addr = __sme_set(page_to_phys((*svm)->avic_backing_page));
- vcpu_info->vector = irq.vector;
-
- return 0;
-}
-
-/*
- * avic_pi_update_irte - set IRTE for Posted-Interrupts
- *
- * @kvm: kvm
- * @host_irq: host irq of the interrupt
- * @guest_irq: gsi of the interrupt
- * @set: set or unset PI
- * returns 0 on success, < 0 on failure
- */
-int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
- uint32_t guest_irq, bool set)
-{
- struct kvm_kernel_irq_routing_entry *e;
- struct kvm_irq_routing_table *irq_rt;
- bool enable_remapped_mode = true;
- int idx, ret = 0;
-
- if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
- return 0;
-
- pr_debug("SVM: %s: host_irq=%#x, guest_irq=%#x, set=%#x\n",
- __func__, host_irq, guest_irq, set);
-
- idx = srcu_read_lock(&kvm->irq_srcu);
- irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
-
- if (guest_irq >= irq_rt->nr_rt_entries ||
- hlist_empty(&irq_rt->map[guest_irq])) {
- pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
- guest_irq, irq_rt->nr_rt_entries);
- goto out;
- }
-
- hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
- struct vcpu_data vcpu_info;
- struct vcpu_svm *svm = NULL;
+ if (vcpu) {
+ /*
+ * Try to enable guest_mode in IRTE, unless AVIC is inhibited,
+ * in which case configure the IRTE for legacy mode, but track
+ * the IRTE metadata so that it can be converted to guest mode
+ * if AVIC is enabled/uninhibited in the future.
+ */
+ struct amd_iommu_pi_data pi_data = {
+ .ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id,
+ vcpu->vcpu_idx),
+ .is_guest_mode = kvm_vcpu_apicv_active(vcpu),
+ .vapic_addr = avic_get_backing_page_address(to_svm(vcpu)),
+ .vector = vector,
+ };
+ struct vcpu_svm *svm = to_svm(vcpu);
+ u64 entry;
+ int ret;
- if (e->type != KVM_IRQ_ROUTING_MSI)
- continue;
+ /*
+ * Prevent the vCPU from being scheduled out or migrated until
+ * the IRTE is updated and its metadata has been added to the
+ * list of IRQs being posted to the vCPU, to ensure the IRTE
+ * isn't programmed with stale pCPU/IsRunning information.
+ */
+ guard(spinlock_irqsave)(&svm->ir_list_lock);
- /**
- * Here, we setup with legacy mode in the following cases:
- * 1. When cannot target interrupt to a specific vcpu.
- * 2. Unsetting posted interrupt.
- * 3. APIC virtualization is disabled for the vcpu.
- * 4. IRQ has incompatible delivery mode (SMI, INIT, etc)
+ /*
+ * Update the target pCPU for IOMMU doorbells if the vCPU is
+ * running. If the vCPU is NOT running, i.e. is blocking or
+ * scheduled out, KVM will update the pCPU info when the vCPU
+ * is awakened and/or scheduled in. See also avic_vcpu_load().
*/
- if (!get_pi_vcpu_info(kvm, e, &vcpu_info, &svm) && set &&
- kvm_vcpu_apicv_active(&svm->vcpu)) {
- struct amd_iommu_pi_data pi;
-
- enable_remapped_mode = false;
-
- /* Try to enable guest_mode in IRTE */
- pi.base = __sme_set(page_to_phys(svm->avic_backing_page) &
- AVIC_HPA_MASK);
- pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id,
- svm->vcpu.vcpu_id);
- pi.is_guest_mode = true;
- pi.vcpu_data = &vcpu_info;
- ret = irq_set_vcpu_affinity(host_irq, &pi);
-
- /**
- * Here, we successfully setting up vcpu affinity in
- * IOMMU guest mode. Now, we need to store the posted
- * interrupt information in a per-vcpu ir_list so that
- * we can reference to them directly when we update vcpu
- * scheduling information in IOMMU irte.
- */
- if (!ret && pi.is_guest_mode)
- svm_ir_list_add(svm, &pi);
+ entry = svm->avic_physical_id_entry;
+ if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) {
+ pi_data.cpu = entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
+ } else {
+ pi_data.cpu = -1;
+ pi_data.ga_log_intr = entry & AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR;
}
- if (!ret && svm) {
- trace_kvm_pi_irte_update(host_irq, svm->vcpu.vcpu_id,
- e->gsi, vcpu_info.vector,
- vcpu_info.pi_desc_addr, set);
- }
+ ret = irq_set_vcpu_affinity(host_irq, &pi_data);
+ if (ret)
+ return ret;
- if (ret < 0) {
- pr_err("%s: failed to update PI IRTE\n", __func__);
- goto out;
+ /*
+ * Revert to legacy mode if the IOMMU didn't provide metadata
+ * for the IRTE, which KVM needs to keep the IRTE up-to-date,
+ * e.g. if the vCPU is migrated or AVIC is disabled.
+ */
+ if (WARN_ON_ONCE(!pi_data.ir_data)) {
+ irq_set_vcpu_affinity(host_irq, NULL);
+ return -EIO;
}
- }
- ret = 0;
- if (enable_remapped_mode) {
- /* Use legacy mode in IRTE */
- struct amd_iommu_pi_data pi;
+ irqfd->irq_bypass_data = pi_data.ir_data;
+ list_add(&irqfd->vcpu_list, &svm->ir_list);
+ return 0;
+ }
+ return irq_set_vcpu_affinity(host_irq, NULL);
+}
- /**
- * Here, pi is used to:
- * - Tell IOMMU to use legacy mode for this interrupt.
- * - Retrieve ga_tag of prior interrupt remapping data.
- */
- pi.prev_ga_tag = 0;
- pi.is_guest_mode = false;
- ret = irq_set_vcpu_affinity(host_irq, &pi);
+enum avic_vcpu_action {
+ /*
+ * There is no need to differentiate between activate and deactivate,
+ * as KVM only refreshes AVIC state when the vCPU is scheduled in and
+ * isn't blocking, i.e. the pCPU must always be (in)valid when AVIC is
+ * being (de)activated.
+ */
+ AVIC_TOGGLE_ON_OFF = BIT(0),
+ AVIC_ACTIVATE = AVIC_TOGGLE_ON_OFF,
+ AVIC_DEACTIVATE = AVIC_TOGGLE_ON_OFF,
- /**
- * Check if the posted interrupt was previously
- * setup with the guest_mode by checking if the ga_tag
- * was cached. If so, we need to clean up the per-vcpu
- * ir_list.
- */
- if (!ret && pi.prev_ga_tag) {
- int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
- struct kvm_vcpu *vcpu;
+ /*
+ * No unique action is required to deal with a vCPU that stops/starts
+ * running. A vCPU that starts running by definition stops blocking as
+ * well, and a vCPU that stops running can't have been blocking, i.e.
+ * doesn't need to toggle GALogIntr.
+ */
+ AVIC_START_RUNNING = 0,
+ AVIC_STOP_RUNNING = 0,
- vcpu = kvm_get_vcpu_by_id(kvm, id);
- if (vcpu)
- svm_ir_list_del(to_svm(vcpu), &pi);
- }
- }
-out:
- srcu_read_unlock(&kvm->irq_srcu, idx);
- return ret;
-}
+ /*
+ * When a vCPU starts blocking, KVM needs to set the GALogIntr flag
+ * int all associated IRTEs so that KVM can wake the vCPU if an IRQ is
+ * sent to the vCPU.
+ */
+ AVIC_START_BLOCKING = BIT(1),
+};
-static inline int
-avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
+static void avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu,
+ enum avic_vcpu_action action)
{
- int ret = 0;
- struct amd_svm_iommu_ir *ir;
+ bool ga_log_intr = (action & AVIC_START_BLOCKING);
struct vcpu_svm *svm = to_svm(vcpu);
+ struct kvm_kernel_irqfd *irqfd;
lockdep_assert_held(&svm->ir_list_lock);
- if (!kvm_arch_has_assigned_device(vcpu->kvm))
- return 0;
-
/*
* Here, we go through the per-vcpu ir_list to update all existing
* interrupt remapping table entry targeting this vcpu.
*/
if (list_empty(&svm->ir_list))
- return 0;
+ return;
- list_for_each_entry(ir, &svm->ir_list, node) {
- ret = amd_iommu_update_ga(cpu, r, ir->data);
- if (ret)
- return ret;
+ list_for_each_entry(irqfd, &svm->ir_list, vcpu_list) {
+ void *data = irqfd->irq_bypass_data;
+
+ if (!(action & AVIC_TOGGLE_ON_OFF))
+ WARN_ON_ONCE(amd_iommu_update_ga(data, cpu, ga_log_intr));
+ else if (cpu >= 0)
+ WARN_ON_ONCE(amd_iommu_activate_guest_mode(data, cpu, ga_log_intr));
+ else
+ WARN_ON_ONCE(amd_iommu_deactivate_guest_mode(data));
}
- return 0;
}
-void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+static void __avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu,
+ enum avic_vcpu_action action)
{
- u64 entry;
+ struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
int h_physical_id = kvm_cpu_get_apicid(cpu);
struct vcpu_svm *svm = to_svm(vcpu);
unsigned long flags;
+ u64 entry;
lockdep_assert_preemption_disabled();
if (WARN_ON(h_physical_id & ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK))
return;
- /*
- * No need to update anything if the vCPU is blocking, i.e. if the vCPU
- * is being scheduled in after being preempted. The CPU entries in the
- * Physical APIC table and IRTE are consumed iff IsRun{ning} is '1'.
- * If the vCPU was migrated, its new CPU value will be stuffed when the
- * vCPU unblocks.
- */
- if (kvm_vcpu_is_blocking(vcpu))
+ if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >= PAGE_SIZE))
return;
/*
@@ -1062,38 +895,57 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
*/
spin_lock_irqsave(&svm->ir_list_lock, flags);
- entry = READ_ONCE(*(svm->avic_physical_id_cache));
+ entry = svm->avic_physical_id_entry;
WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK);
- entry &= ~AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
+ entry &= ~(AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK |
+ AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR);
entry |= (h_physical_id & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK);
entry |= AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
- WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
- avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
+ svm->avic_physical_id_entry = entry;
+
+ /*
+ * If IPI virtualization is disabled, clear IsRunning when updating the
+ * actual Physical ID table, so that the CPU never sees IsRunning=1.
+ * Keep the APIC ID up-to-date in the entry to minimize the chances of
+ * things going sideways if hardware peeks at the ID.
+ */
+ if (!enable_ipiv)
+ entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
+
+ WRITE_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id], entry);
+
+ avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, action);
spin_unlock_irqrestore(&svm->ir_list_lock, flags);
}
-void avic_vcpu_put(struct kvm_vcpu *vcpu)
+void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
- u64 entry;
+ /*
+ * No need to update anything if the vCPU is blocking, i.e. if the vCPU
+ * is being scheduled in after being preempted. The CPU entries in the
+ * Physical APIC table and IRTE are consumed iff IsRun{ning} is '1'.
+ * If the vCPU was migrated, its new CPU value will be stuffed when the
+ * vCPU unblocks.
+ */
+ if (kvm_vcpu_is_blocking(vcpu))
+ return;
+
+ __avic_vcpu_load(vcpu, cpu, AVIC_START_RUNNING);
+}
+
+static void __avic_vcpu_put(struct kvm_vcpu *vcpu, enum avic_vcpu_action action)
+{
+ struct kvm_svm *kvm_svm = to_kvm_svm(vcpu->kvm);
struct vcpu_svm *svm = to_svm(vcpu);
unsigned long flags;
+ u64 entry = svm->avic_physical_id_entry;
lockdep_assert_preemption_disabled();
- /*
- * Note, reading the Physical ID entry outside of ir_list_lock is safe
- * as only the pCPU that has loaded (or is loading) the vCPU is allowed
- * to modify the entry, and preemption is disabled. I.e. the vCPU
- * can't be scheduled out and thus avic_vcpu_{put,load}() can't run
- * recursively.
- */
- entry = READ_ONCE(*(svm->avic_physical_id_cache));
-
- /* Nothing to do if IsRunning == '0' due to vCPU blocking. */
- if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK))
+ if (WARN_ON_ONCE(vcpu->vcpu_id * sizeof(entry) >= PAGE_SIZE))
return;
/*
@@ -1106,13 +958,62 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
*/
spin_lock_irqsave(&svm->ir_list_lock, flags);
- avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
+ avic_update_iommu_vcpu_affinity(vcpu, -1, action);
+
+ WARN_ON_ONCE(entry & AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR);
+ /*
+ * Keep the previous APIC ID in the entry so that a rogue doorbell from
+ * hardware is at least restricted to a CPU associated with the vCPU.
+ */
entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
- WRITE_ONCE(*(svm->avic_physical_id_cache), entry);
+
+ if (enable_ipiv)
+ WRITE_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id], entry);
+
+ /*
+ * Note! Don't set AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR in the table as
+ * it's a synthetic flag that usurps an unused should-be-zero bit.
+ */
+ if (action & AVIC_START_BLOCKING)
+ entry |= AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR;
+
+ svm->avic_physical_id_entry = entry;
spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+}
+
+void avic_vcpu_put(struct kvm_vcpu *vcpu)
+{
+ /*
+ * Note, reading the Physical ID entry outside of ir_list_lock is safe
+ * as only the pCPU that has loaded (or is loading) the vCPU is allowed
+ * to modify the entry, and preemption is disabled. I.e. the vCPU
+ * can't be scheduled out and thus avic_vcpu_{put,load}() can't run
+ * recursively.
+ */
+ u64 entry = to_svm(vcpu)->avic_physical_id_entry;
+
+ /*
+ * Nothing to do if IsRunning == '0' due to vCPU blocking, i.e. if the
+ * vCPU is preempted while its in the process of blocking. WARN if the
+ * vCPU wasn't running and isn't blocking, KVM shouldn't attempt to put
+ * the AVIC if it wasn't previously loaded.
+ */
+ if (!(entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)) {
+ if (WARN_ON_ONCE(!kvm_vcpu_is_blocking(vcpu)))
+ return;
+ /*
+ * The vCPU was preempted while blocking, ensure its IRTEs are
+ * configured to generate GA Log Interrupts.
+ */
+ if (!(WARN_ON_ONCE(!(entry & AVIC_PHYSICAL_ID_ENTRY_GA_LOG_INTR))))
+ return;
+ }
+
+ __avic_vcpu_put(vcpu, kvm_vcpu_is_blocking(vcpu) ? AVIC_START_BLOCKING :
+ AVIC_STOP_RUNNING);
}
void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu)
@@ -1141,19 +1042,18 @@ void avic_refresh_virtual_apic_mode(struct kvm_vcpu *vcpu)
void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
{
- bool activated = kvm_vcpu_apicv_active(vcpu);
-
if (!enable_apicv)
return;
+ /* APICv should only be toggled on/off while the vCPU is running. */
+ WARN_ON_ONCE(kvm_vcpu_is_blocking(vcpu));
+
avic_refresh_virtual_apic_mode(vcpu);
- if (activated)
- avic_vcpu_load(vcpu, vcpu->cpu);
+ if (kvm_vcpu_apicv_active(vcpu))
+ __avic_vcpu_load(vcpu, vcpu->cpu, AVIC_ACTIVATE);
else
- avic_vcpu_put(vcpu);
-
- avic_set_pi_irte_mode(vcpu, activated);
+ __avic_vcpu_put(vcpu, AVIC_DEACTIVATE);
}
void avic_vcpu_blocking(struct kvm_vcpu *vcpu)
@@ -1161,20 +1061,25 @@ void avic_vcpu_blocking(struct kvm_vcpu *vcpu)
if (!kvm_vcpu_apicv_active(vcpu))
return;
- /*
- * Unload the AVIC when the vCPU is about to block, _before_
- * the vCPU actually blocks.
- *
- * Any IRQs that arrive before IsRunning=0 will not cause an
- * incomplete IPI vmexit on the source, therefore vIRR will also
- * be checked by kvm_vcpu_check_block() before blocking. The
- * memory barrier implicit in set_current_state orders writing
- * IsRunning=0 before reading the vIRR. The processor needs a
- * matching memory barrier on interrupt delivery between writing
- * IRR and reading IsRunning; the lack of this barrier might be
- * the cause of errata #1235).
- */
- avic_vcpu_put(vcpu);
+ /*
+ * Unload the AVIC when the vCPU is about to block, _before_ the vCPU
+ * actually blocks.
+ *
+ * Note, any IRQs that arrive before IsRunning=0 will not cause an
+ * incomplete IPI vmexit on the source; kvm_vcpu_check_block() handles
+ * this by checking vIRR one last time before blocking. The memory
+ * barrier implicit in set_current_state orders writing IsRunning=0
+ * before reading the vIRR. The processor needs a matching memory
+ * barrier on interrupt delivery between writing IRR and reading
+ * IsRunning; the lack of this barrier might be the cause of errata #1235).
+ *
+ * Clear IsRunning=0 even if guest IRQs are disabled, i.e. even if KVM
+ * doesn't need to detect events for scheduling purposes. The doorbell
+ * used to signal running vCPUs cannot be blocked, i.e. will perturb the
+ * CPU and cause noisy neighbor problems if the VM is sending interrupts
+ * to the vCPU while it's scheduled out.
+ */
+ __avic_vcpu_put(vcpu, AVIC_START_BLOCKING);
}
void avic_vcpu_unblocking(struct kvm_vcpu *vcpu)
@@ -1227,6 +1132,14 @@ bool avic_hardware_setup(void)
if (x2avic_enabled)
pr_info("x2AVIC enabled\n");
+ /*
+ * Disable IPI virtualization for AMD Family 17h CPUs (Zen1 and Zen2)
+ * due to erratum 1235, which results in missed VM-Exits on the sender
+ * and thus missed wake events for blocking vCPUs due to the CPU
+ * failing to see a software update to clear IsRunning.
+ */
+ enable_ipiv = enable_ipiv && boot_cpu_data.x86 != 0x17;
+
amd_iommu_register_ga_log_notifier(&avic_ga_log_notifier);
return true;
diff --git a/arch/x86/kvm/svm/nested.c b/arch/x86/kvm/svm/nested.c
index 834b67672d50..b7fd2e869998 100644
--- a/arch/x86/kvm/svm/nested.c
+++ b/arch/x86/kvm/svm/nested.c
@@ -185,12 +185,87 @@ void recalc_intercepts(struct vcpu_svm *svm)
}
/*
+ * This array (and its actual size) holds the set of offsets (indexing by chunk
+ * size) to process when merging vmcb12's MSRPM with vmcb01's MSRPM. Note, the
+ * set of MSRs for which interception is disabled in vmcb01 is per-vCPU, e.g.
+ * based on CPUID features. This array only tracks MSRs that *might* be passed
+ * through to the guest.
+ *
+ * Hardcode the capacity of the array based on the maximum number of _offsets_.
+ * MSRs are batched together, so there are fewer offsets than MSRs.
+ */
+static int nested_svm_msrpm_merge_offsets[7] __ro_after_init;
+static int nested_svm_nr_msrpm_merge_offsets __ro_after_init;
+typedef unsigned long nsvm_msrpm_merge_t;
+
+int __init nested_svm_init_msrpm_merge_offsets(void)
+{
+ static const u32 merge_msrs[] __initconst = {
+ MSR_STAR,
+ MSR_IA32_SYSENTER_CS,
+ MSR_IA32_SYSENTER_EIP,
+ MSR_IA32_SYSENTER_ESP,
+ #ifdef CONFIG_X86_64
+ MSR_GS_BASE,
+ MSR_FS_BASE,
+ MSR_KERNEL_GS_BASE,
+ MSR_LSTAR,
+ MSR_CSTAR,
+ MSR_SYSCALL_MASK,
+ #endif
+ MSR_IA32_SPEC_CTRL,
+ MSR_IA32_PRED_CMD,
+ MSR_IA32_FLUSH_CMD,
+ MSR_IA32_APERF,
+ MSR_IA32_MPERF,
+ MSR_IA32_LASTBRANCHFROMIP,
+ MSR_IA32_LASTBRANCHTOIP,
+ MSR_IA32_LASTINTFROMIP,
+ MSR_IA32_LASTINTTOIP,
+ };
+ int i, j;
+
+ for (i = 0; i < ARRAY_SIZE(merge_msrs); i++) {
+ int bit_nr = svm_msrpm_bit_nr(merge_msrs[i]);
+ u32 offset;
+
+ if (WARN_ON(bit_nr < 0))
+ return -EIO;
+
+ /*
+ * Merging is done in chunks to reduce the number of accesses
+ * to L1's bitmap.
+ */
+ offset = bit_nr / BITS_PER_BYTE / sizeof(nsvm_msrpm_merge_t);
+
+ for (j = 0; j < nested_svm_nr_msrpm_merge_offsets; j++) {
+ if (nested_svm_msrpm_merge_offsets[j] == offset)
+ break;
+ }
+
+ if (j < nested_svm_nr_msrpm_merge_offsets)
+ continue;
+
+ if (WARN_ON(j >= ARRAY_SIZE(nested_svm_msrpm_merge_offsets)))
+ return -EIO;
+
+ nested_svm_msrpm_merge_offsets[j] = offset;
+ nested_svm_nr_msrpm_merge_offsets++;
+ }
+
+ return 0;
+}
+
+/*
* Merge L0's (KVM) and L1's (Nested VMCB) MSR permission bitmaps. The function
* is optimized in that it only merges the parts where KVM MSR permission bitmap
* may contain zero bits.
*/
-static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
+static bool nested_svm_merge_msrpm(struct kvm_vcpu *vcpu)
{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ nsvm_msrpm_merge_t *msrpm02 = svm->nested.msrpm;
+ nsvm_msrpm_merge_t *msrpm01 = svm->msrpm;
int i;
/*
@@ -205,7 +280,7 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
if (!svm->nested.force_msr_bitmap_recalc) {
struct hv_vmcb_enlightenments *hve = &svm->nested.ctl.hv_enlightenments;
- if (kvm_hv_hypercall_enabled(&svm->vcpu) &&
+ if (kvm_hv_hypercall_enabled(vcpu) &&
hve->hv_enlightenments_control.msr_bitmap &&
(svm->nested.ctl.clean & BIT(HV_VMCB_NESTED_ENLIGHTENMENTS)))
goto set_msrpm_base_pa;
@@ -215,25 +290,17 @@ static bool nested_svm_vmrun_msrpm(struct vcpu_svm *svm)
if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
return true;
- for (i = 0; i < MSRPM_OFFSETS; i++) {
- u32 value, p;
- u64 offset;
-
- if (msrpm_offsets[i] == 0xffffffff)
- break;
-
- p = msrpm_offsets[i];
+ for (i = 0; i < nested_svm_nr_msrpm_merge_offsets; i++) {
+ const int p = nested_svm_msrpm_merge_offsets[i];
+ nsvm_msrpm_merge_t l1_val;
+ gpa_t gpa;
- /* x2apic msrs are intercepted always for the nested guest */
- if (is_x2apic_msrpm_offset(p))
- continue;
-
- offset = svm->nested.ctl.msrpm_base_pa + (p * 4);
+ gpa = svm->nested.ctl.msrpm_base_pa + (p * sizeof(l1_val));
- if (kvm_vcpu_read_guest(&svm->vcpu, offset, &value, 4))
+ if (kvm_vcpu_read_guest(vcpu, gpa, &l1_val, sizeof(l1_val)))
return false;
- svm->nested.msrpm[p] = svm->msrpm[p] | value;
+ msrpm02[p] = msrpm01[p] | l1_val;
}
svm->nested.force_msr_bitmap_recalc = false;
@@ -678,6 +745,33 @@ static void nested_vmcb02_prepare_control(struct vcpu_svm *svm,
vmcb02->control.iopm_base_pa = vmcb01->control.iopm_base_pa;
vmcb02->control.msrpm_base_pa = vmcb01->control.msrpm_base_pa;
+ /*
+ * Stash vmcb02's counter if the guest hasn't moved past the guilty
+ * instruction; otherwise, reset the counter to '0'.
+ *
+ * In order to detect if L2 has made forward progress or not, track the
+ * RIP at which a bus lock has occurred on a per-vmcb12 basis. If RIP
+ * is changed, guest has clearly made forward progress, bus_lock_counter
+ * still remained '1', so reset bus_lock_counter to '0'. Eg. In the
+ * scenario, where a buslock happened in L1 before VMRUN, the bus lock
+ * firmly happened on an instruction in the past. Even if vmcb01's
+ * counter is still '1', (because the guilty instruction got patched),
+ * the vCPU has clearly made forward progress and so KVM should reset
+ * vmcb02's counter to '0'.
+ *
+ * If the RIP hasn't changed, stash the bus lock counter at nested VMRUN
+ * to prevent the same guilty instruction from triggering a VM-Exit. Eg.
+ * if userspace rate-limits the vCPU, then it's entirely possible that
+ * L1's tick interrupt is pending by the time userspace re-runs the
+ * vCPU. If KVM unconditionally clears the counter on VMRUN, then when
+ * L1 re-enters L2, the same instruction will trigger a VM-Exit and the
+ * entire cycle start over.
+ */
+ if (vmcb02->save.rip && (svm->nested.ctl.bus_lock_rip == vmcb02->save.rip))
+ vmcb02->control.bus_lock_counter = 1;
+ else
+ vmcb02->control.bus_lock_counter = 0;
+
/* Done at vmrun: asid. */
/* Also overwritten later if necessary. */
@@ -910,7 +1004,7 @@ int nested_svm_vmrun(struct kvm_vcpu *vcpu)
if (enter_svm_guest_mode(vcpu, vmcb12_gpa, vmcb12, true))
goto out_exit_err;
- if (nested_svm_vmrun_msrpm(svm))
+ if (nested_svm_merge_msrpm(vcpu))
goto out;
out_exit_err:
@@ -1039,8 +1133,17 @@ int nested_svm_vmexit(struct vcpu_svm *svm)
}
+ /*
+ * Invalidate bus_lock_rip unless KVM is still waiting for the guest
+ * to make forward progress before re-enabling bus lock detection.
+ */
+ if (!vmcb02->control.bus_lock_counter)
+ svm->nested.ctl.bus_lock_rip = INVALID_GPA;
+
nested_svm_copy_common_state(svm->nested.vmcb02.ptr, svm->vmcb01.ptr);
+ kvm_nested_vmexit_handle_ibrs(vcpu);
+
svm_switch_vmcb(svm, &svm->vmcb01);
/*
@@ -1194,7 +1297,6 @@ int svm_allocate_nested(struct vcpu_svm *svm)
svm->nested.msrpm = svm_vcpu_alloc_msrpm();
if (!svm->nested.msrpm)
goto err_free_vmcb02;
- svm_vcpu_init_msrpm(&svm->vcpu, svm->nested.msrpm);
svm->nested.initialized = true;
return 0;
@@ -1254,26 +1356,26 @@ void svm_leave_nested(struct kvm_vcpu *vcpu)
static int nested_svm_exit_handled_msr(struct vcpu_svm *svm)
{
- u32 offset, msr, value;
- int write, mask;
+ gpa_t base = svm->nested.ctl.msrpm_base_pa;
+ int write, bit_nr;
+ u8 value, mask;
+ u32 msr;
if (!(vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_MSR_PROT)))
return NESTED_EXIT_HOST;
msr = svm->vcpu.arch.regs[VCPU_REGS_RCX];
- offset = svm_msrpm_offset(msr);
+ bit_nr = svm_msrpm_bit_nr(msr);
write = svm->vmcb->control.exit_info_1 & 1;
- mask = 1 << ((2 * (msr & 0xf)) + write);
- if (offset == MSR_INVALID)
+ if (bit_nr < 0)
return NESTED_EXIT_DONE;
- /* Offset is in 32 bit units but need in 8 bit units */
- offset *= 4;
-
- if (kvm_vcpu_read_guest(&svm->vcpu, svm->nested.ctl.msrpm_base_pa + offset, &value, 4))
+ if (kvm_vcpu_read_guest(&svm->vcpu, base + bit_nr / BITS_PER_BYTE,
+ &value, sizeof(value)))
return NESTED_EXIT_DONE;
+ mask = BIT(write) << (bit_nr & (BITS_PER_BYTE - 1));
return (value & mask) ? NESTED_EXIT_DONE : NESTED_EXIT_HOST;
}
@@ -1783,13 +1885,11 @@ out_free:
static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
{
- struct vcpu_svm *svm = to_svm(vcpu);
-
if (WARN_ON(!is_guest_mode(vcpu)))
return true;
if (!vcpu->arch.pdptrs_from_userspace &&
- !nested_npt_enabled(svm) && is_pae_paging(vcpu))
+ !nested_npt_enabled(to_svm(vcpu)) && is_pae_paging(vcpu))
/*
* Reload the guest's PDPTRs since after a migration
* the guest CR3 might be restored prior to setting the nested
@@ -1798,7 +1898,7 @@ static bool svm_get_nested_state_pages(struct kvm_vcpu *vcpu)
if (CC(!load_pdptrs(vcpu, vcpu->arch.cr3)))
return false;
- if (!nested_svm_vmrun_msrpm(svm)) {
+ if (!nested_svm_merge_msrpm(vcpu)) {
vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
vcpu->run->internal.suberror =
KVM_INTERNAL_ERROR_EMULATION;
diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c
index a7a7dc507336..2fbdebf79fbb 100644
--- a/arch/x86/kvm/svm/sev.c
+++ b/arch/x86/kvm/svm/sev.c
@@ -26,6 +26,7 @@
#include <asm/fpu/xcr.h>
#include <asm/fpu/xstate.h>
#include <asm/debugreg.h>
+#include <asm/msr.h>
#include <asm/sev.h>
#include "mmu.h"
@@ -116,6 +117,7 @@ static int sev_flush_asids(unsigned int min_asid, unsigned int max_asid)
*/
down_write(&sev_deactivate_lock);
+ /* SNP firmware requires use of WBINVD for ASID recycling. */
wbinvd_on_all_cpus();
if (sev_snp_enabled)
@@ -445,7 +447,12 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
init_args.probe = false;
ret = sev_platform_init(&init_args);
if (ret)
- goto e_free;
+ goto e_free_asid;
+
+ if (!zalloc_cpumask_var(&sev->have_run_cpus, GFP_KERNEL_ACCOUNT)) {
+ ret = -ENOMEM;
+ goto e_free_asid;
+ }
/* This needs to happen after SEV/SNP firmware initialization. */
if (vm_type == KVM_X86_SNP_VM) {
@@ -463,6 +470,8 @@ static int __sev_guest_init(struct kvm *kvm, struct kvm_sev_cmd *argp,
return 0;
e_free:
+ free_cpumask_var(sev->have_run_cpus);
+e_free_asid:
argp->error = init_args.error;
sev_asid_free(sev);
sev->asid = 0;
@@ -560,6 +569,8 @@ static int sev_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
if (copy_from_user(&params, u64_to_user_ptr(argp->data), sizeof(params)))
return -EFAULT;
+ sev->policy = params.policy;
+
memset(&start, 0, sizeof(start));
dh_blob = NULL;
@@ -705,6 +716,33 @@ static void sev_clflush_pages(struct page *pages[], unsigned long npages)
}
}
+static void sev_writeback_caches(struct kvm *kvm)
+{
+ /*
+ * Note, the caller is responsible for ensuring correctness if the mask
+ * can be modified, e.g. if a CPU could be doing VMRUN.
+ */
+ if (cpumask_empty(to_kvm_sev_info(kvm)->have_run_cpus))
+ return;
+
+ /*
+ * Ensure that all dirty guest tagged cache entries are written back
+ * before releasing the pages back to the system for use. CLFLUSH will
+ * not do this without SME_COHERENT, and flushing many cache lines
+ * individually is slower than blasting WBINVD for large VMs, so issue
+ * WBNOINVD (or WBINVD if the "no invalidate" variant is unsupported)
+ * on CPUs that have done VMRUN, i.e. may have dirtied data using the
+ * VM's ASID.
+ *
+ * For simplicity, never remove CPUs from the bitmap. Ideally, KVM
+ * would clear the mask when flushing caches, but doing so requires
+ * serializing multiple calls and having responding CPUs (to the IPI)
+ * mark themselves as still running if they are running (or about to
+ * run) a vCPU for the VM.
+ */
+ wbnoinvd_on_cpus_mask(to_kvm_sev_info(kvm)->have_run_cpus);
+}
+
static unsigned long get_num_contig_pages(unsigned long idx,
struct page **inpages, unsigned long npages)
{
@@ -1592,11 +1630,11 @@ static int sev_send_update_data(struct kvm *kvm, struct kvm_sev_cmd *argp)
/* allocate memory for header and transport buffer */
ret = -ENOMEM;
- hdr = kzalloc(params.hdr_len, GFP_KERNEL_ACCOUNT);
+ hdr = kzalloc(params.hdr_len, GFP_KERNEL);
if (!hdr)
goto e_unpin;
- trans_data = kzalloc(params.trans_len, GFP_KERNEL_ACCOUNT);
+ trans_data = kzalloc(params.trans_len, GFP_KERNEL);
if (!trans_data)
goto e_free_hdr;
@@ -1882,70 +1920,6 @@ static void sev_unlock_two_vms(struct kvm *dst_kvm, struct kvm *src_kvm)
atomic_set_release(&src_sev->migration_in_progress, 0);
}
-/* vCPU mutex subclasses. */
-enum sev_migration_role {
- SEV_MIGRATION_SOURCE = 0,
- SEV_MIGRATION_TARGET,
- SEV_NR_MIGRATION_ROLES,
-};
-
-static int sev_lock_vcpus_for_migration(struct kvm *kvm,
- enum sev_migration_role role)
-{
- struct kvm_vcpu *vcpu;
- unsigned long i, j;
-
- kvm_for_each_vcpu(i, vcpu, kvm) {
- if (mutex_lock_killable_nested(&vcpu->mutex, role))
- goto out_unlock;
-
-#ifdef CONFIG_PROVE_LOCKING
- if (!i)
- /*
- * Reset the role to one that avoids colliding with
- * the role used for the first vcpu mutex.
- */
- role = SEV_NR_MIGRATION_ROLES;
- else
- mutex_release(&vcpu->mutex.dep_map, _THIS_IP_);
-#endif
- }
-
- return 0;
-
-out_unlock:
-
- kvm_for_each_vcpu(j, vcpu, kvm) {
- if (i == j)
- break;
-
-#ifdef CONFIG_PROVE_LOCKING
- if (j)
- mutex_acquire(&vcpu->mutex.dep_map, role, 0, _THIS_IP_);
-#endif
-
- mutex_unlock(&vcpu->mutex);
- }
- return -EINTR;
-}
-
-static void sev_unlock_vcpus_for_migration(struct kvm *kvm)
-{
- struct kvm_vcpu *vcpu;
- unsigned long i;
- bool first = true;
-
- kvm_for_each_vcpu(i, vcpu, kvm) {
- if (first)
- first = false;
- else
- mutex_acquire(&vcpu->mutex.dep_map,
- SEV_NR_MIGRATION_ROLES, 0, _THIS_IP_);
-
- mutex_unlock(&vcpu->mutex);
- }
-}
-
static void sev_migrate_from(struct kvm *dst_kvm, struct kvm *src_kvm)
{
struct kvm_sev_info *dst = to_kvm_sev_info(dst_kvm);
@@ -2032,6 +2006,10 @@ static int sev_check_source_vcpus(struct kvm *dst, struct kvm *src)
struct kvm_vcpu *src_vcpu;
unsigned long i;
+ if (src->created_vcpus != atomic_read(&src->online_vcpus) ||
+ dst->created_vcpus != atomic_read(&dst->online_vcpus))
+ return -EBUSY;
+
if (!sev_es_guest(src))
return 0;
@@ -2083,10 +2061,10 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
charged = true;
}
- ret = sev_lock_vcpus_for_migration(kvm, SEV_MIGRATION_SOURCE);
+ ret = kvm_lock_all_vcpus(kvm);
if (ret)
goto out_dst_cgroup;
- ret = sev_lock_vcpus_for_migration(source_kvm, SEV_MIGRATION_TARGET);
+ ret = kvm_lock_all_vcpus(source_kvm);
if (ret)
goto out_dst_vcpu;
@@ -2094,15 +2072,26 @@ int sev_vm_move_enc_context_from(struct kvm *kvm, unsigned int source_fd)
if (ret)
goto out_source_vcpu;
+ /*
+ * Allocate a new have_run_cpus for the destination, i.e. don't copy
+ * the set of CPUs from the source. If a CPU was used to run a vCPU in
+ * the source VM but is never used for the destination VM, then the CPU
+ * can only have cached memory that was accessible to the source VM.
+ */
+ if (!zalloc_cpumask_var(&dst_sev->have_run_cpus, GFP_KERNEL_ACCOUNT)) {
+ ret = -ENOMEM;
+ goto out_source_vcpu;
+ }
+
sev_migrate_from(kvm, source_kvm);
kvm_vm_dead(source_kvm);
cg_cleanup_sev = src_sev;
ret = 0;
out_source_vcpu:
- sev_unlock_vcpus_for_migration(source_kvm);
+ kvm_unlock_all_vcpus(source_kvm);
out_dst_vcpu:
- sev_unlock_vcpus_for_migration(kvm);
+ kvm_unlock_all_vcpus(kvm);
out_dst_cgroup:
/* Operates on the source on success, on the destination on failure. */
if (charged)
@@ -2192,12 +2181,10 @@ static int snp_launch_start(struct kvm *kvm, struct kvm_sev_cmd *argp)
return -EINVAL;
/* Check for policy bits that must be set */
- if (!(params.policy & SNP_POLICY_MASK_RSVD_MBO) ||
- !(params.policy & SNP_POLICY_MASK_SMT))
+ if (!(params.policy & SNP_POLICY_MASK_RSVD_MBO))
return -EINVAL;
- if (params.policy & SNP_POLICY_MASK_SINGLE_SOCKET)
- return -EINVAL;
+ sev->policy = params.policy;
sev->snp_context = snp_context_create(kvm, argp);
if (!sev->snp_context)
@@ -2753,12 +2740,7 @@ int sev_mem_enc_unregister_region(struct kvm *kvm,
goto failed;
}
- /*
- * Ensure that all guest tagged cache entries are flushed before
- * releasing the pages back to the system for use. CLFLUSH will
- * not do this, so issue a WBINVD.
- */
- wbinvd_on_all_cpus();
+ sev_writeback_caches(kvm);
__unregister_enc_region_locked(kvm, region);
@@ -2800,13 +2782,18 @@ int sev_vm_copy_enc_context_from(struct kvm *kvm, unsigned int source_fd)
goto e_unlock;
}
+ mirror_sev = to_kvm_sev_info(kvm);
+ if (!zalloc_cpumask_var(&mirror_sev->have_run_cpus, GFP_KERNEL_ACCOUNT)) {
+ ret = -ENOMEM;
+ goto e_unlock;
+ }
+
/*
* The mirror kvm holds an enc_context_owner ref so its asid can't
* disappear until we're done with it
*/
source_sev = to_kvm_sev_info(source_kvm);
kvm_get_kvm(source_kvm);
- mirror_sev = to_kvm_sev_info(kvm);
list_add_tail(&mirror_sev->mirror_entry, &source_sev->mirror_vms);
/* Set enc_context_owner and copy its encryption context over */
@@ -2868,7 +2855,13 @@ void sev_vm_destroy(struct kvm *kvm)
WARN_ON(!list_empty(&sev->mirror_vms));
- /* If this is a mirror_kvm release the enc_context_owner and skip sev cleanup */
+ free_cpumask_var(sev->have_run_cpus);
+
+ /*
+ * If this is a mirror VM, remove it from the owner's list of a mirrors
+ * and skip ASID cleanup (the ASID is tied to the lifetime of the owner).
+ * Note, mirror VMs don't support registering encrypted regions.
+ */
if (is_mirroring_enc_context(kvm)) {
struct kvm *owner_kvm = sev->enc_context_owner;
@@ -2879,12 +2872,6 @@ void sev_vm_destroy(struct kvm *kvm)
return;
}
- /*
- * Ensure that all guest tagged cache entries are flushed before
- * releasing the pages back to the system for use. CLFLUSH will
- * not do this, so issue a WBINVD.
- */
- wbinvd_on_all_cpus();
/*
* if userspace was terminated before unregistering the memory regions
@@ -2930,9 +2917,37 @@ void __init sev_set_cpu_caps(void)
}
}
+static bool is_sev_snp_initialized(void)
+{
+ struct sev_user_data_snp_status *status;
+ struct sev_data_snp_addr buf;
+ bool initialized = false;
+ int ret, error = 0;
+
+ status = snp_alloc_firmware_page(GFP_KERNEL | __GFP_ZERO);
+ if (!status)
+ return false;
+
+ buf.address = __psp_pa(status);
+ ret = sev_do_cmd(SEV_CMD_SNP_PLATFORM_STATUS, &buf, &error);
+ if (ret) {
+ pr_err("SEV: SNP_PLATFORM_STATUS failed ret=%d, fw_error=%d (%#x)\n",
+ ret, error, error);
+ goto out;
+ }
+
+ initialized = !!status->state;
+
+out:
+ snp_free_firmware_page(status);
+
+ return initialized;
+}
+
void __init sev_hardware_setup(void)
{
unsigned int eax, ebx, ecx, edx, sev_asid_count, sev_es_asid_count;
+ struct sev_platform_init_args init_args = {0};
bool sev_snp_supported = false;
bool sev_es_supported = false;
bool sev_supported = false;
@@ -3033,6 +3048,14 @@ void __init sev_hardware_setup(void)
sev_snp_supported = sev_snp_enabled && cc_platform_has(CC_ATTR_HOST_SEV_SNP);
out:
+ if (sev_enabled) {
+ init_args.probe = true;
+ if (sev_platform_init(&init_args))
+ sev_supported = sev_es_supported = sev_snp_supported = false;
+ else if (sev_snp_supported)
+ sev_snp_supported = is_sev_snp_initialized();
+ }
+
if (boot_cpu_has(X86_FEATURE_SEV))
pr_info("SEV %s (ASIDs %u - %u)\n",
sev_supported ? min_sev_asid <= max_sev_asid ? "enabled" :
@@ -3074,6 +3097,8 @@ void sev_hardware_unsetup(void)
misc_cg_set_capacity(MISC_CG_RES_SEV, 0);
misc_cg_set_capacity(MISC_CG_RES_SEV_ES, 0);
+
+ sev_platform_shutdown();
}
int sev_cpu_init(struct svm_cpu_data *sd)
@@ -3116,30 +3141,29 @@ static void sev_flush_encrypted_page(struct kvm_vcpu *vcpu, void *va)
/*
* VM Page Flush takes a host virtual address and a guest ASID. Fall
- * back to WBINVD if this faults so as not to make any problems worse
- * by leaving stale encrypted data in the cache.
+ * back to full writeback of caches if this faults so as not to make
+ * any problems worse by leaving stale encrypted data in the cache.
*/
- if (WARN_ON_ONCE(wrmsrl_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid)))
- goto do_wbinvd;
+ if (WARN_ON_ONCE(wrmsrq_safe(MSR_AMD64_VM_PAGE_FLUSH, addr | asid)))
+ goto do_sev_writeback_caches;
return;
-do_wbinvd:
- wbinvd_on_all_cpus();
+do_sev_writeback_caches:
+ sev_writeback_caches(vcpu->kvm);
}
void sev_guest_memory_reclaimed(struct kvm *kvm)
{
/*
* With SNP+gmem, private/encrypted memory is unreachable via the
- * hva-based mmu notifiers, so these events are only actually
- * pertaining to shared pages where there is no need to perform
- * the WBINVD to flush associated caches.
+ * hva-based mmu notifiers, i.e. these events are explicitly scoped to
+ * shared pages, where there's no need to flush caches.
*/
if (!sev_guest(kvm) || sev_snp_guest(kvm))
return;
- wbinvd_on_all_cpus();
+ sev_writeback_caches(kvm);
}
void sev_free_vcpu(struct kvm_vcpu *vcpu)
@@ -3471,6 +3495,15 @@ int pre_sev_run(struct vcpu_svm *svm, int cpu)
if (sev_es_guest(kvm) && !VALID_PAGE(svm->vmcb->control.vmsa_pa))
return -EINVAL;
+ /*
+ * To optimize cache flushes when memory is reclaimed from an SEV VM,
+ * track physical CPUs that enter the guest for SEV VMs and thus can
+ * have encrypted, dirty data in the cache, and flush caches only for
+ * CPUs that have entered the guest.
+ */
+ if (!cpumask_test_cpu(cpu, to_kvm_sev_info(kvm)->have_run_cpus))
+ cpumask_set_cpu(cpu, to_kvm_sev_info(kvm)->have_run_cpus);
+
/* Assign the asid allocated with this SEV guest */
svm->asid = asid;
@@ -3903,9 +3936,9 @@ void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu)
* From this point forward, the VMSA will always be a guest-mapped page
* rather than the initial one allocated by KVM in svm->sev_es.vmsa. In
* theory, svm->sev_es.vmsa could be free'd and cleaned up here, but
- * that involves cleanups like wbinvd_on_all_cpus() which would ideally
- * be handled during teardown rather than guest boot. Deferring that
- * also allows the existing logic for SEV-ES VMSAs to be re-used with
+ * that involves cleanups like flushing caches, which would ideally be
+ * handled during teardown rather than guest boot. Deferring that also
+ * allows the existing logic for SEV-ES VMSAs to be re-used with
* minimal SNP-specific changes.
*/
svm->sev_es.snp_has_guest_vmsa = true;
@@ -3994,10 +4027,8 @@ static int sev_snp_ap_creation(struct vcpu_svm *svm)
* Unless Creation is deferred until INIT, signal the vCPU to update
* its state.
*/
- if (request != SVM_VMGEXIT_AP_CREATE_ON_INIT) {
- kvm_make_request(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
- kvm_vcpu_kick(target_vcpu);
- }
+ if (request != SVM_VMGEXIT_AP_CREATE_ON_INIT)
+ kvm_make_request_and_kick(KVM_REQ_UPDATE_PROTECTED_GUEST_STATE, target_vcpu);
return 0;
}
@@ -4409,16 +4440,17 @@ int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in)
count, in);
}
-static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
+void sev_es_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
{
- struct kvm_vcpu *vcpu = &svm->vcpu;
+ /* Clear intercepts on MSRs that are context switched by hardware. */
+ svm_disable_intercept_for_msr(vcpu, MSR_AMD64_SEV_ES_GHCB, MSR_TYPE_RW);
+ svm_disable_intercept_for_msr(vcpu, MSR_EFER, MSR_TYPE_RW);
+ svm_disable_intercept_for_msr(vcpu, MSR_IA32_CR_PAT, MSR_TYPE_RW);
- if (boot_cpu_has(X86_FEATURE_V_TSC_AUX)) {
- bool v_tsc_aux = guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) ||
- guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID);
-
- set_msr_interception(vcpu, svm->msrpm, MSR_TSC_AUX, v_tsc_aux, v_tsc_aux);
- }
+ if (boot_cpu_has(X86_FEATURE_V_TSC_AUX))
+ svm_set_intercept_for_msr(vcpu, MSR_TSC_AUX, MSR_TYPE_RW,
+ !guest_cpu_cap_has(vcpu, X86_FEATURE_RDTSCP) &&
+ !guest_cpu_cap_has(vcpu, X86_FEATURE_RDPID));
/*
* For SEV-ES, accesses to MSR_IA32_XSS should not be intercepted if
@@ -4432,11 +4464,9 @@ static void sev_es_vcpu_after_set_cpuid(struct vcpu_svm *svm)
* XSAVES being exposed to the guest so that KVM can at least honor
* guest CPUID for RDMSR and WRMSR.
*/
- if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) &&
- guest_cpuid_has(vcpu, X86_FEATURE_XSAVES))
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 1, 1);
- else
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_XSS, 0, 0);
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_XSS, MSR_TYPE_RW,
+ !guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) ||
+ !guest_cpuid_has(vcpu, X86_FEATURE_XSAVES));
}
void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
@@ -4448,15 +4478,12 @@ void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm)
best = kvm_find_cpuid_entry(vcpu, 0x8000001F);
if (best)
vcpu->arch.reserved_gpa_bits &= ~(1UL << (best->ebx & 0x3f));
-
- if (sev_es_guest(svm->vcpu.kvm))
- sev_es_vcpu_after_set_cpuid(svm);
}
static void sev_es_init_vmcb(struct vcpu_svm *svm)
{
+ struct kvm_sev_info *sev = to_kvm_sev_info(svm->vcpu.kvm);
struct vmcb *vmcb = svm->vmcb01.ptr;
- struct kvm_vcpu *vcpu = &svm->vcpu;
svm->vmcb->control.nested_ctl |= SVM_NESTED_CTL_SEV_ES_ENABLE;
@@ -4467,8 +4494,16 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
* the VMSA will be NULL if this vCPU is the destination for intrahost
* migration, and will be copied later.
*/
- if (svm->sev_es.vmsa && !svm->sev_es.snp_has_guest_vmsa)
- svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+ if (!svm->sev_es.snp_has_guest_vmsa) {
+ if (svm->sev_es.vmsa)
+ svm->vmcb->control.vmsa_pa = __pa(svm->sev_es.vmsa);
+ else
+ svm->vmcb->control.vmsa_pa = INVALID_PAGE;
+ }
+
+ if (cpu_feature_enabled(X86_FEATURE_ALLOWED_SEV_FEATURES))
+ svm->vmcb->control.allowed_sev_features = sev->vmsa_features |
+ VMCB_ALLOWED_SEV_FEATURES_VALID;
/* Can't intercept CR register access, HV can't modify CR registers */
svm_clr_intercept(svm, INTERCEPT_CR0_READ);
@@ -4506,10 +4541,6 @@ static void sev_es_init_vmcb(struct vcpu_svm *svm)
/* Can't intercept XSETBV, HV can't modify XCR0 directly */
svm_clr_intercept(svm, INTERCEPT_XSETBV);
-
- /* Clear intercepts on selected MSRs */
- set_msr_interception(vcpu, svm->msrpm, MSR_EFER, 1, 1);
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_CR_PAT, 1, 1);
}
void sev_init_vmcb(struct vcpu_svm *svm)
@@ -4898,7 +4929,7 @@ void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end)
/*
* SEV-ES avoids host/guest cache coherency issues through
- * WBINVD hooks issued via MMU notifiers during run-time, and
+ * WBNOINVD hooks issued via MMU notifiers during run-time, and
* KVM's VM destroy path at shutdown. Those MMU notifier events
* don't cover gmem since there is no requirement to map pages
* to a HVA in order to use them for a running guest. While the
@@ -4930,3 +4961,97 @@ int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
return level;
}
+
+struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+ struct vmcb_save_area *vmsa;
+ struct kvm_sev_info *sev;
+ int error = 0;
+ int ret;
+
+ if (!sev_es_guest(vcpu->kvm))
+ return NULL;
+
+ /*
+ * If the VMSA has not yet been encrypted, return a pointer to the
+ * current un-encrypted VMSA.
+ */
+ if (!vcpu->arch.guest_state_protected)
+ return (struct vmcb_save_area *)svm->sev_es.vmsa;
+
+ sev = to_kvm_sev_info(vcpu->kvm);
+
+ /* Check if the SEV policy allows debugging */
+ if (sev_snp_guest(vcpu->kvm)) {
+ if (!(sev->policy & SNP_POLICY_DEBUG))
+ return NULL;
+ } else {
+ if (sev->policy & SEV_POLICY_NODBG)
+ return NULL;
+ }
+
+ if (sev_snp_guest(vcpu->kvm)) {
+ struct sev_data_snp_dbg dbg = {0};
+
+ vmsa = snp_alloc_firmware_page(__GFP_ZERO);
+ if (!vmsa)
+ return NULL;
+
+ dbg.gctx_paddr = __psp_pa(sev->snp_context);
+ dbg.src_addr = svm->vmcb->control.vmsa_pa;
+ dbg.dst_addr = __psp_pa(vmsa);
+
+ ret = sev_do_cmd(SEV_CMD_SNP_DBG_DECRYPT, &dbg, &error);
+
+ /*
+ * Return the target page to a hypervisor page no matter what.
+ * If this fails, the page can't be used, so leak it and don't
+ * try to use it.
+ */
+ if (snp_page_reclaim(vcpu->kvm, PHYS_PFN(__pa(vmsa))))
+ return NULL;
+
+ if (ret) {
+ pr_err("SEV: SNP_DBG_DECRYPT failed ret=%d, fw_error=%d (%#x)\n",
+ ret, error, error);
+ free_page((unsigned long)vmsa);
+
+ return NULL;
+ }
+ } else {
+ struct sev_data_dbg dbg = {0};
+ struct page *vmsa_page;
+
+ vmsa_page = alloc_page(GFP_KERNEL);
+ if (!vmsa_page)
+ return NULL;
+
+ vmsa = page_address(vmsa_page);
+
+ dbg.handle = sev->handle;
+ dbg.src_addr = svm->vmcb->control.vmsa_pa;
+ dbg.dst_addr = __psp_pa(vmsa);
+ dbg.len = PAGE_SIZE;
+
+ ret = sev_do_cmd(SEV_CMD_DBG_DECRYPT, &dbg, &error);
+ if (ret) {
+ pr_err("SEV: SEV_CMD_DBG_DECRYPT failed ret=%d, fw_error=%d (0x%x)\n",
+ ret, error, error);
+ __free_page(vmsa_page);
+
+ return NULL;
+ }
+ }
+
+ return vmsa;
+}
+
+void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa)
+{
+ /* If the VMSA has not yet been encrypted, nothing was allocated */
+ if (!vcpu->arch.guest_state_protected || !vmsa)
+ return;
+
+ free_page((unsigned long)vmsa);
+}
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index a89c271a1951..d9931c6c4bc6 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -29,8 +29,10 @@
#include <linux/cc_platform.h>
#include <linux/smp.h>
#include <linux/string_choices.h>
+#include <linux/mutex.h>
#include <asm/apic.h>
+#include <asm/msr.h>
#include <asm/perf_event.h>
#include <asm/tlbflush.h>
#include <asm/desc.h>
@@ -70,8 +72,6 @@ MODULE_DEVICE_TABLE(x86cpu, svm_cpu_id);
static bool erratum_383_found __read_mostly;
-u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
-
/*
* Set osvw_len to higher value when updated Revision Guides
* are published and we know what the new status bits are
@@ -80,72 +80,6 @@ static uint64_t osvw_len = 4, osvw_status;
static DEFINE_PER_CPU(u64, current_tsc_ratio);
-#define X2APIC_MSR(x) (APIC_BASE_MSR + (x >> 4))
-
-static const struct svm_direct_access_msrs {
- u32 index; /* Index of the MSR */
- bool always; /* True if intercept is initially cleared */
-} direct_access_msrs[MAX_DIRECT_ACCESS_MSRS] = {
- { .index = MSR_STAR, .always = true },
- { .index = MSR_IA32_SYSENTER_CS, .always = true },
- { .index = MSR_IA32_SYSENTER_EIP, .always = false },
- { .index = MSR_IA32_SYSENTER_ESP, .always = false },
-#ifdef CONFIG_X86_64
- { .index = MSR_GS_BASE, .always = true },
- { .index = MSR_FS_BASE, .always = true },
- { .index = MSR_KERNEL_GS_BASE, .always = true },
- { .index = MSR_LSTAR, .always = true },
- { .index = MSR_CSTAR, .always = true },
- { .index = MSR_SYSCALL_MASK, .always = true },
-#endif
- { .index = MSR_IA32_SPEC_CTRL, .always = false },
- { .index = MSR_IA32_PRED_CMD, .always = false },
- { .index = MSR_IA32_FLUSH_CMD, .always = false },
- { .index = MSR_IA32_DEBUGCTLMSR, .always = false },
- { .index = MSR_IA32_LASTBRANCHFROMIP, .always = false },
- { .index = MSR_IA32_LASTBRANCHTOIP, .always = false },
- { .index = MSR_IA32_LASTINTFROMIP, .always = false },
- { .index = MSR_IA32_LASTINTTOIP, .always = false },
- { .index = MSR_IA32_XSS, .always = false },
- { .index = MSR_EFER, .always = false },
- { .index = MSR_IA32_CR_PAT, .always = false },
- { .index = MSR_AMD64_SEV_ES_GHCB, .always = true },
- { .index = MSR_TSC_AUX, .always = false },
- { .index = X2APIC_MSR(APIC_ID), .always = false },
- { .index = X2APIC_MSR(APIC_LVR), .always = false },
- { .index = X2APIC_MSR(APIC_TASKPRI), .always = false },
- { .index = X2APIC_MSR(APIC_ARBPRI), .always = false },
- { .index = X2APIC_MSR(APIC_PROCPRI), .always = false },
- { .index = X2APIC_MSR(APIC_EOI), .always = false },
- { .index = X2APIC_MSR(APIC_RRR), .always = false },
- { .index = X2APIC_MSR(APIC_LDR), .always = false },
- { .index = X2APIC_MSR(APIC_DFR), .always = false },
- { .index = X2APIC_MSR(APIC_SPIV), .always = false },
- { .index = X2APIC_MSR(APIC_ISR), .always = false },
- { .index = X2APIC_MSR(APIC_TMR), .always = false },
- { .index = X2APIC_MSR(APIC_IRR), .always = false },
- { .index = X2APIC_MSR(APIC_ESR), .always = false },
- { .index = X2APIC_MSR(APIC_ICR), .always = false },
- { .index = X2APIC_MSR(APIC_ICR2), .always = false },
-
- /*
- * Note:
- * AMD does not virtualize APIC TSC-deadline timer mode, but it is
- * emulated by KVM. When setting APIC LVTT (0x832) register bit 18,
- * the AVIC hardware would generate GP fault. Therefore, always
- * intercept the MSR 0x832, and do not setup direct_access_msr.
- */
- { .index = X2APIC_MSR(APIC_LVTTHMR), .always = false },
- { .index = X2APIC_MSR(APIC_LVTPC), .always = false },
- { .index = X2APIC_MSR(APIC_LVT0), .always = false },
- { .index = X2APIC_MSR(APIC_LVT1), .always = false },
- { .index = X2APIC_MSR(APIC_LVTERR), .always = false },
- { .index = X2APIC_MSR(APIC_TMICT), .always = false },
- { .index = X2APIC_MSR(APIC_TMCCT), .always = false },
- { .index = X2APIC_MSR(APIC_TDCR), .always = false },
- { .index = MSR_INVALID, .always = false },
-};
-
/*
* These 2 parameters are used to config the controls for Pause-Loop Exiting:
* pause_filter_count: On processors that support Pause filtering(indicated
@@ -230,6 +164,9 @@ module_param(tsc_scaling, int, 0444);
*/
static bool avic;
module_param(avic, bool, 0444);
+module_param(enable_ipiv, bool, 0444);
+
+module_param(enable_device_posted_irqs, bool, 0444);
bool __read_mostly dump_invalid_vmcb;
module_param(dump_invalid_vmcb, bool, 0644);
@@ -249,6 +186,8 @@ static unsigned long iopm_base;
DEFINE_PER_CPU(struct svm_cpu_data, svm_data);
+static DEFINE_MUTEX(vmcb_dump_mutex);
+
/*
* Only MSR_TSC_AUX is switched via the user return hook. EFER is switched via
* the VMCB, and the SYSCALL/SYSENTER MSRs are handled by VMLOAD/VMSAVE.
@@ -258,33 +197,6 @@ DEFINE_PER_CPU(struct svm_cpu_data, svm_data);
*/
static int tsc_aux_uret_slot __read_mostly = -1;
-static const u32 msrpm_ranges[] = {0, 0xc0000000, 0xc0010000};
-
-#define NUM_MSR_MAPS ARRAY_SIZE(msrpm_ranges)
-#define MSRS_RANGE_SIZE 2048
-#define MSRS_IN_RANGE (MSRS_RANGE_SIZE * 8 / 2)
-
-u32 svm_msrpm_offset(u32 msr)
-{
- u32 offset;
- int i;
-
- for (i = 0; i < NUM_MSR_MAPS; i++) {
- if (msr < msrpm_ranges[i] ||
- msr >= msrpm_ranges[i] + MSRS_IN_RANGE)
- continue;
-
- offset = (msr - msrpm_ranges[i]) / 4; /* 4 msrs per u8 */
- offset += (i * MSRS_RANGE_SIZE); /* add range offset */
-
- /* Now we have the u8 offset - but need the u32 offset */
- return offset / 4;
- }
-
- /* MSR not in any range */
- return MSR_INVALID;
-}
-
static int get_npt_level(void)
{
#ifdef CONFIG_X86_64
@@ -475,24 +387,18 @@ static void svm_inject_exception(struct kvm_vcpu *vcpu)
static void svm_init_erratum_383(void)
{
- u32 low, high;
- int err;
u64 val;
if (!static_cpu_has_bug(X86_BUG_AMD_TLB_MMATCH))
return;
/* Use _safe variants to not break nested virtualization */
- val = native_read_msr_safe(MSR_AMD64_DC_CFG, &err);
- if (err)
+ if (native_read_msr_safe(MSR_AMD64_DC_CFG, &val))
return;
val |= (1ULL << 47);
- low = lower_32_bits(val);
- high = upper_32_bits(val);
-
- native_write_msr_safe(MSR_AMD64_DC_CFG, low, high);
+ native_write_msr_safe(MSR_AMD64_DC_CFG, val);
erratum_383_found = true;
}
@@ -566,7 +472,7 @@ static void __svm_write_tsc_multiplier(u64 multiplier)
if (multiplier == __this_cpu_read(current_tsc_ratio))
return;
- wrmsrl(MSR_AMD64_TSC_RATIO, multiplier);
+ wrmsrq(MSR_AMD64_TSC_RATIO, multiplier);
__this_cpu_write(current_tsc_ratio, multiplier);
}
@@ -579,15 +485,15 @@ static inline void kvm_cpu_svm_disable(void)
{
uint64_t efer;
- wrmsrl(MSR_VM_HSAVE_PA, 0);
- rdmsrl(MSR_EFER, efer);
+ wrmsrq(MSR_VM_HSAVE_PA, 0);
+ rdmsrq(MSR_EFER, efer);
if (efer & EFER_SVME) {
/*
* Force GIF=1 prior to disabling SVM, e.g. to ensure INIT and
* NMI aren't blocked.
*/
stgi();
- wrmsrl(MSR_EFER, efer & ~EFER_SVME);
+ wrmsrq(MSR_EFER, efer & ~EFER_SVME);
}
}
@@ -616,7 +522,7 @@ static int svm_enable_virtualization_cpu(void)
uint64_t efer;
int me = raw_smp_processor_id();
- rdmsrl(MSR_EFER, efer);
+ rdmsrq(MSR_EFER, efer);
if (efer & EFER_SVME)
return -EBUSY;
@@ -626,9 +532,9 @@ static int svm_enable_virtualization_cpu(void)
sd->next_asid = sd->max_asid + 1;
sd->min_asid = max_sev_asid + 1;
- wrmsrl(MSR_EFER, efer | EFER_SVME);
+ wrmsrq(MSR_EFER, efer | EFER_SVME);
- wrmsrl(MSR_VM_HSAVE_PA, sd->save_area_pa);
+ wrmsrq(MSR_VM_HSAVE_PA, sd->save_area_pa);
if (static_cpu_has(X86_FEATURE_TSCRATEMSR)) {
/*
@@ -649,13 +555,12 @@ static int svm_enable_virtualization_cpu(void)
* erratum is present everywhere).
*/
if (cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) {
- uint64_t len, status = 0;
+ u64 len, status = 0;
int err;
- len = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &err);
+ err = native_read_msr_safe(MSR_AMD64_OSVW_ID_LENGTH, &len);
if (!err)
- status = native_read_msr_safe(MSR_AMD64_OSVW_STATUS,
- &err);
+ err = native_read_msr_safe(MSR_AMD64_OSVW_STATUS, &status);
if (err)
osvw_status = osvw_len = 0;
@@ -758,50 +663,8 @@ static void clr_dr_intercepts(struct vcpu_svm *svm)
recalc_intercepts(svm);
}
-static int direct_access_msr_slot(u32 msr)
-{
- u32 i;
-
- for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++)
- if (direct_access_msrs[i].index == msr)
- return i;
-
- return -ENOENT;
-}
-
-static void set_shadow_msr_intercept(struct kvm_vcpu *vcpu, u32 msr, int read,
- int write)
-{
- struct vcpu_svm *svm = to_svm(vcpu);
- int slot = direct_access_msr_slot(msr);
-
- if (slot == -ENOENT)
- return;
-
- /* Set the shadow bitmaps to the desired intercept states */
- if (read)
- set_bit(slot, svm->shadow_msr_intercept.read);
- else
- clear_bit(slot, svm->shadow_msr_intercept.read);
-
- if (write)
- set_bit(slot, svm->shadow_msr_intercept.write);
- else
- clear_bit(slot, svm->shadow_msr_intercept.write);
-}
-
-static bool valid_msr_intercept(u32 index)
-{
- return direct_access_msr_slot(index) != -ENOENT;
-}
-
static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
{
- u8 bit_write;
- unsigned long tmp;
- u32 offset;
- u32 *msrpm;
-
/*
* For non-nested case:
* If the L01 MSR bitmap does not intercept the MSR, then we need to
@@ -811,90 +674,102 @@ static bool msr_write_intercepted(struct kvm_vcpu *vcpu, u32 msr)
* If the L02 MSR bitmap does not intercept the MSR, then we need to
* save it.
*/
- msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm:
- to_svm(vcpu)->msrpm;
-
- offset = svm_msrpm_offset(msr);
- bit_write = 2 * (msr & 0x0f) + 1;
- tmp = msrpm[offset];
-
- BUG_ON(offset == MSR_INVALID);
+ void *msrpm = is_guest_mode(vcpu) ? to_svm(vcpu)->nested.msrpm :
+ to_svm(vcpu)->msrpm;
- return test_bit(bit_write, &tmp);
+ return svm_test_msr_bitmap_write(msrpm, msr);
}
-static void set_msr_interception_bitmap(struct kvm_vcpu *vcpu, u32 *msrpm,
- u32 msr, int read, int write)
+void svm_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set)
{
struct vcpu_svm *svm = to_svm(vcpu);
- u8 bit_read, bit_write;
- unsigned long tmp;
- u32 offset;
-
- /*
- * If this warning triggers extend the direct_access_msrs list at the
- * beginning of the file
- */
- WARN_ON(!valid_msr_intercept(msr));
+ void *msrpm = svm->msrpm;
- /* Enforce non allowed MSRs to trap */
- if (read && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ))
- read = 0;
-
- if (write && !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE))
- write = 0;
-
- offset = svm_msrpm_offset(msr);
- bit_read = 2 * (msr & 0x0f);
- bit_write = 2 * (msr & 0x0f) + 1;
- tmp = msrpm[offset];
-
- BUG_ON(offset == MSR_INVALID);
-
- read ? clear_bit(bit_read, &tmp) : set_bit(bit_read, &tmp);
- write ? clear_bit(bit_write, &tmp) : set_bit(bit_write, &tmp);
+ /* Don't disable interception for MSRs userspace wants to handle. */
+ if (type & MSR_TYPE_R) {
+ if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ))
+ svm_clear_msr_bitmap_read(msrpm, msr);
+ else
+ svm_set_msr_bitmap_read(msrpm, msr);
+ }
- msrpm[offset] = tmp;
+ if (type & MSR_TYPE_W) {
+ if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE))
+ svm_clear_msr_bitmap_write(msrpm, msr);
+ else
+ svm_set_msr_bitmap_write(msrpm, msr);
+ }
svm_hv_vmcb_dirty_nested_enlightenments(vcpu);
svm->nested.force_msr_bitmap_recalc = true;
}
-void set_msr_interception(struct kvm_vcpu *vcpu, u32 *msrpm, u32 msr,
- int read, int write)
-{
- set_shadow_msr_intercept(vcpu, msr, read, write);
- set_msr_interception_bitmap(vcpu, msrpm, msr, read, write);
-}
-
-u32 *svm_vcpu_alloc_msrpm(void)
+void *svm_alloc_permissions_map(unsigned long size, gfp_t gfp_mask)
{
- unsigned int order = get_order(MSRPM_SIZE);
- struct page *pages = alloc_pages(GFP_KERNEL_ACCOUNT, order);
- u32 *msrpm;
+ unsigned int order = get_order(size);
+ struct page *pages = alloc_pages(gfp_mask, order);
+ void *pm;
if (!pages)
return NULL;
- msrpm = page_address(pages);
- memset(msrpm, 0xff, PAGE_SIZE * (1 << order));
+ /*
+ * Set all bits in the permissions map so that all MSR and I/O accesses
+ * are intercepted by default.
+ */
+ pm = page_address(pages);
+ memset(pm, 0xff, PAGE_SIZE * (1 << order));
- return msrpm;
+ return pm;
}
-void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm)
+static void svm_recalc_lbr_msr_intercepts(struct kvm_vcpu *vcpu)
{
- int i;
+ bool intercept = !(to_svm(vcpu)->vmcb->control.virt_ext & LBR_CTL_ENABLE_MASK);
- for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
- if (!direct_access_msrs[i].always)
- continue;
- set_msr_interception(vcpu, msrpm, direct_access_msrs[i].index, 1, 1);
- }
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTBRANCHFROMIP, MSR_TYPE_RW, intercept);
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTBRANCHTOIP, MSR_TYPE_RW, intercept);
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTINTFROMIP, MSR_TYPE_RW, intercept);
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_LASTINTTOIP, MSR_TYPE_RW, intercept);
+
+ if (sev_es_guest(vcpu->kvm))
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_DEBUGCTLMSR, MSR_TYPE_RW, intercept);
}
void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept)
{
+ static const u32 x2avic_passthrough_msrs[] = {
+ X2APIC_MSR(APIC_ID),
+ X2APIC_MSR(APIC_LVR),
+ X2APIC_MSR(APIC_TASKPRI),
+ X2APIC_MSR(APIC_ARBPRI),
+ X2APIC_MSR(APIC_PROCPRI),
+ X2APIC_MSR(APIC_EOI),
+ X2APIC_MSR(APIC_RRR),
+ X2APIC_MSR(APIC_LDR),
+ X2APIC_MSR(APIC_DFR),
+ X2APIC_MSR(APIC_SPIV),
+ X2APIC_MSR(APIC_ISR),
+ X2APIC_MSR(APIC_TMR),
+ X2APIC_MSR(APIC_IRR),
+ X2APIC_MSR(APIC_ESR),
+ X2APIC_MSR(APIC_ICR),
+ X2APIC_MSR(APIC_ICR2),
+
+ /*
+ * Note! Always intercept LVTT, as TSC-deadline timer mode
+ * isn't virtualized by hardware, and the CPU will generate a
+ * #GP instead of a #VMEXIT.
+ */
+ X2APIC_MSR(APIC_LVTTHMR),
+ X2APIC_MSR(APIC_LVTPC),
+ X2APIC_MSR(APIC_LVT0),
+ X2APIC_MSR(APIC_LVT1),
+ X2APIC_MSR(APIC_LVTERR),
+ X2APIC_MSR(APIC_TMICT),
+ X2APIC_MSR(APIC_TMCCT),
+ X2APIC_MSR(APIC_TDCR),
+ };
int i;
if (intercept == svm->x2avic_msrs_intercepted)
@@ -903,84 +778,79 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool intercept)
if (!x2avic_enabled)
return;
- for (i = 0; i < MAX_DIRECT_ACCESS_MSRS; i++) {
- int index = direct_access_msrs[i].index;
-
- if ((index < APIC_BASE_MSR) ||
- (index > APIC_BASE_MSR + 0xff))
- continue;
- set_msr_interception(&svm->vcpu, svm->msrpm, index,
- !intercept, !intercept);
- }
+ for (i = 0; i < ARRAY_SIZE(x2avic_passthrough_msrs); i++)
+ svm_set_intercept_for_msr(&svm->vcpu, x2avic_passthrough_msrs[i],
+ MSR_TYPE_RW, intercept);
svm->x2avic_msrs_intercepted = intercept;
}
-void svm_vcpu_free_msrpm(u32 *msrpm)
+void svm_vcpu_free_msrpm(void *msrpm)
{
__free_pages(virt_to_page(msrpm), get_order(MSRPM_SIZE));
}
-static void svm_msr_filter_changed(struct kvm_vcpu *vcpu)
+static void svm_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- u32 i;
- /*
- * Set intercept permissions for all direct access MSRs again. They
- * will automatically get filtered through the MSR filter, so we are
- * back in sync after this.
- */
- for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
- u32 msr = direct_access_msrs[i].index;
- u32 read = test_bit(i, svm->shadow_msr_intercept.read);
- u32 write = test_bit(i, svm->shadow_msr_intercept.write);
+ svm_disable_intercept_for_msr(vcpu, MSR_STAR, MSR_TYPE_RW);
+ svm_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
- set_msr_interception_bitmap(vcpu, svm->msrpm, msr, read, write);
- }
-}
-
-static void add_msr_offset(u32 offset)
-{
- int i;
-
- for (i = 0; i < MSRPM_OFFSETS; ++i) {
-
- /* Offset already in list? */
- if (msrpm_offsets[i] == offset)
- return;
+#ifdef CONFIG_X86_64
+ svm_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW);
+ svm_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW);
+ svm_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+ svm_disable_intercept_for_msr(vcpu, MSR_LSTAR, MSR_TYPE_RW);
+ svm_disable_intercept_for_msr(vcpu, MSR_CSTAR, MSR_TYPE_RW);
+ svm_disable_intercept_for_msr(vcpu, MSR_SYSCALL_MASK, MSR_TYPE_RW);
+#endif
- /* Slot used by another offset? */
- if (msrpm_offsets[i] != MSR_INVALID)
- continue;
+ if (lbrv)
+ svm_recalc_lbr_msr_intercepts(vcpu);
- /* Add offset to list */
- msrpm_offsets[i] = offset;
+ if (cpu_feature_enabled(X86_FEATURE_IBPB))
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W,
+ !guest_has_pred_cmd_msr(vcpu));
- return;
- }
+ if (cpu_feature_enabled(X86_FEATURE_FLUSH_L1D))
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W,
+ !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D));
/*
- * If this BUG triggers the msrpm_offsets table has an overflow. Just
- * increase MSRPM_OFFSETS in this case.
+ * Disable interception of SPEC_CTRL if KVM doesn't need to manually
+ * context switch the MSR (SPEC_CTRL is virtualized by the CPU), or if
+ * the guest has a non-zero SPEC_CTRL value, i.e. is likely actively
+ * using SPEC_CTRL.
*/
- BUG();
-}
-
-static void init_msrpm_offsets(void)
-{
- int i;
-
- memset(msrpm_offsets, 0xff, sizeof(msrpm_offsets));
+ if (cpu_feature_enabled(X86_FEATURE_V_SPEC_CTRL))
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW,
+ !guest_has_spec_ctrl_msr(vcpu));
+ else
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW,
+ !svm->spec_ctrl);
- for (i = 0; direct_access_msrs[i].index != MSR_INVALID; i++) {
- u32 offset;
+ /*
+ * Intercept SYSENTER_EIP and SYSENTER_ESP when emulating an Intel CPU,
+ * as AMD hardware only store 32 bits, whereas Intel CPUs track 64 bits.
+ */
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW,
+ guest_cpuid_is_intel_compatible(vcpu));
+ svm_set_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW,
+ guest_cpuid_is_intel_compatible(vcpu));
+
+ if (kvm_aperfmperf_in_guest(vcpu->kvm)) {
+ svm_disable_intercept_for_msr(vcpu, MSR_IA32_APERF, MSR_TYPE_R);
+ svm_disable_intercept_for_msr(vcpu, MSR_IA32_MPERF, MSR_TYPE_R);
+ }
- offset = svm_msrpm_offset(direct_access_msrs[i].index);
- BUG_ON(offset == MSR_INVALID);
+ if (sev_es_guest(vcpu->kvm))
+ sev_es_recalc_msr_intercepts(vcpu);
- add_msr_offset(offset);
- }
+ /*
+ * x2APIC intercepts are modified on-demand and cannot be filtered by
+ * userspace.
+ */
}
void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb)
@@ -999,13 +869,7 @@ void svm_enable_lbrv(struct kvm_vcpu *vcpu)
struct vcpu_svm *svm = to_svm(vcpu);
svm->vmcb->control.virt_ext |= LBR_CTL_ENABLE_MASK;
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 1, 1);
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 1, 1);
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 1, 1);
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 1, 1);
-
- if (sev_es_guest(vcpu->kvm))
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_DEBUGCTLMSR, 1, 1);
+ svm_recalc_lbr_msr_intercepts(vcpu);
/* Move the LBR msrs to the vmcb02 so that the guest can see them. */
if (is_guest_mode(vcpu))
@@ -1017,12 +881,8 @@ static void svm_disable_lbrv(struct kvm_vcpu *vcpu)
struct vcpu_svm *svm = to_svm(vcpu);
KVM_BUG_ON(sev_es_guest(vcpu->kvm), vcpu->kvm);
-
svm->vmcb->control.virt_ext &= ~LBR_CTL_ENABLE_MASK;
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHFROMIP, 0, 0);
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTBRANCHTOIP, 0, 0);
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTFROMIP, 0, 0);
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_LASTINTTOIP, 0, 0);
+ svm_recalc_lbr_msr_intercepts(vcpu);
/*
* Move the LBR msrs back to the vmcb01 to avoid copying them
@@ -1177,9 +1037,10 @@ void svm_write_tsc_multiplier(struct kvm_vcpu *vcpu)
}
/* Evaluate instruction intercepts that depend on guest CPUID features. */
-static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
- struct vcpu_svm *svm)
+static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu)
{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
/*
* Intercept INVPCID if shadow paging is enabled to sync/free shadow
* roots, or if INVPCID is disabled in the guest to inject #UD.
@@ -1198,24 +1059,11 @@ static void svm_recalc_instruction_intercepts(struct kvm_vcpu *vcpu,
else
svm_set_intercept(svm, INTERCEPT_RDTSCP);
}
-}
-
-static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu)
-{
- struct vcpu_svm *svm = to_svm(vcpu);
if (guest_cpuid_is_intel_compatible(vcpu)) {
- /*
- * We must intercept SYSENTER_EIP and SYSENTER_ESP
- * accesses because the processor only stores 32 bits.
- * For the same reason we cannot use virtual VMLOAD/VMSAVE.
- */
svm_set_intercept(svm, INTERCEPT_VMLOAD);
svm_set_intercept(svm, INTERCEPT_VMSAVE);
svm->vmcb->control.virt_ext &= ~VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
-
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 0, 0);
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 0, 0);
} else {
/*
* If hardware supports Virtual VMLOAD VMSAVE then enable it
@@ -1226,12 +1074,15 @@ static inline void init_vmcb_after_set_cpuid(struct kvm_vcpu *vcpu)
svm_clr_intercept(svm, INTERCEPT_VMSAVE);
svm->vmcb->control.virt_ext |= VIRTUAL_VMLOAD_VMSAVE_ENABLE_MASK;
}
- /* No need to intercept these MSRs */
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_EIP, 1, 1);
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SYSENTER_ESP, 1, 1);
}
}
+static void svm_recalc_intercepts_after_set_cpuid(struct kvm_vcpu *vcpu)
+{
+ svm_recalc_instruction_intercepts(vcpu);
+ svm_recalc_msr_intercepts(vcpu);
+}
+
static void init_vmcb(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
@@ -1354,15 +1205,6 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
svm_clr_intercept(svm, INTERCEPT_PAUSE);
}
- svm_recalc_instruction_intercepts(vcpu, svm);
-
- /*
- * If the host supports V_SPEC_CTRL then disable the interception
- * of MSR_IA32_SPEC_CTRL.
- */
- if (boot_cpu_has(X86_FEATURE_V_SPEC_CTRL))
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
-
if (kvm_vcpu_apicv_active(vcpu))
avic_init_vmcb(svm, vmcb);
@@ -1375,11 +1217,15 @@ static void init_vmcb(struct kvm_vcpu *vcpu)
svm->vmcb->control.int_ctl |= V_GIF_ENABLE_MASK;
}
+ if (vcpu->kvm->arch.bus_lock_detection_enabled)
+ svm_set_intercept(svm, INTERCEPT_BUSLOCK);
+
if (sev_guest(vcpu->kvm))
sev_init_vmcb(svm);
svm_hv_init_vmcb(vmcb);
- init_vmcb_after_set_cpuid(vcpu);
+
+ svm_recalc_intercepts_after_set_cpuid(vcpu);
vmcb_mark_all_dirty(vmcb);
@@ -1390,8 +1236,6 @@ static void __svm_vcpu_reset(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- svm_vcpu_init_msrpm(vcpu, svm->msrpm);
-
svm_init_osvw(vcpu);
if (kvm_check_has_quirk(vcpu->kvm, KVM_X86_QUIRK_STUFF_FEATURE_MSRS))
@@ -1484,24 +1328,11 @@ out:
return err;
}
-static void svm_clear_current_vmcb(struct vmcb *vmcb)
-{
- int i;
-
- for_each_online_cpu(i)
- cmpxchg(per_cpu_ptr(&svm_data.current_vmcb, i), vmcb, NULL);
-}
-
static void svm_vcpu_free(struct kvm_vcpu *vcpu)
{
struct vcpu_svm *svm = to_svm(vcpu);
- /*
- * The vmcb page can be recycled, causing a false negative in
- * svm_vcpu_load(). So, ensure that no logical CPU has this
- * vmcb page recorded as its current vmcb.
- */
- svm_clear_current_vmcb(svm->vmcb);
+ WARN_ON_ONCE(!list_empty(&svm->ir_list));
svm_leave_nested(vcpu);
svm_free_nested(svm);
@@ -1509,7 +1340,7 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu)
sev_free_vcpu(vcpu);
__free_page(__sme_pa_to_page(svm->vmcb01.pa));
- __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE));
+ svm_vcpu_free_msrpm(svm->msrpm);
}
#ifdef CONFIG_CPU_MITIGATIONS
@@ -1616,19 +1447,9 @@ static void svm_prepare_host_switch(struct kvm_vcpu *vcpu)
static void svm_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
- struct vcpu_svm *svm = to_svm(vcpu);
- struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, cpu);
-
if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
shrink_ple_window(vcpu);
- if (sd->current_vmcb != svm->vmcb) {
- sd->current_vmcb = svm->vmcb;
-
- if (!cpu_feature_enabled(X86_FEATURE_IBPB_ON_VMEXIT) &&
- static_branch_likely(&switch_vcpu_ibpb))
- indirect_branch_prediction_barrier();
- }
if (kvm_vcpu_apicv_active(vcpu))
avic_vcpu_load(vcpu, cpu);
}
@@ -2205,14 +2026,13 @@ static int ac_interception(struct kvm_vcpu *vcpu)
static bool is_erratum_383(void)
{
- int err, i;
+ int i;
u64 value;
if (!erratum_383_found)
return false;
- value = native_read_msr_safe(MSR_IA32_MC0_STATUS, &err);
- if (err)
+ if (native_read_msr_safe(MSR_IA32_MC0_STATUS, &value))
return false;
/* Bit 62 may or may not be set for this mce */
@@ -2223,17 +2043,11 @@ static bool is_erratum_383(void)
/* Clear MCi_STATUS registers */
for (i = 0; i < 6; ++i)
- native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0, 0);
-
- value = native_read_msr_safe(MSR_IA32_MCG_STATUS, &err);
- if (!err) {
- u32 low, high;
+ native_write_msr_safe(MSR_IA32_MCx_STATUS(i), 0);
+ if (!native_read_msr_safe(MSR_IA32_MCG_STATUS, &value)) {
value &= ~(1ULL << 2);
- low = lower_32_bits(value);
- high = upper_32_bits(value);
-
- native_write_msr_safe(MSR_IA32_MCG_STATUS, low, high);
+ native_write_msr_safe(MSR_IA32_MCG_STATUS, value);
}
/* Flush tlb to evict multi-match entries */
@@ -2910,12 +2724,11 @@ static int svm_get_feature_msr(u32 msr, u64 *data)
return 0;
}
-static bool
-sev_es_prevent_msr_access(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+static bool sev_es_prevent_msr_access(struct kvm_vcpu *vcpu,
+ struct msr_data *msr_info)
{
return sev_es_guest(vcpu->kvm) &&
vcpu->arch.guest_state_protected &&
- svm_msrpm_offset(msr_info->index) != MSR_INVALID &&
!msr_write_intercepted(vcpu, msr_info->index);
}
@@ -3146,11 +2959,11 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
*
* For nested:
* The handling of the MSR bitmap for L2 guests is done in
- * nested_svm_vmrun_msrpm.
+ * nested_svm_merge_msrpm().
* We update the L1 MSR bit as well since it will end up
* touching the MSR anyway now.
*/
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_SPEC_CTRL, 1, 1);
+ svm_disable_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW);
break;
case MSR_AMD64_VIRT_SPEC_CTRL:
if (!msr->host_initiated &&
@@ -3216,8 +3029,7 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
/*
* TSC_AUX is usually changed only during boot and never read
- * directly. Intercept TSC_AUX instead of exposing it to the
- * guest via direct_access_msrs, and switch it via user return.
+ * directly. Intercept TSC_AUX and switch it via user return.
*/
preempt_disable();
ret = kvm_set_user_return_msr(tsc_aux_uret_slot, data, -1ull);
@@ -3234,17 +3046,6 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
}
/*
- * AMD changed the architectural behavior of bits 5:2. On CPUs
- * without BusLockTrap, bits 5:2 control "external pins", but
- * on CPUs that support BusLockDetect, bit 2 enables BusLockTrap
- * and bits 5:3 are reserved-to-zero. Sadly, old KVM allowed
- * the guest to set bits 5:2 despite not actually virtualizing
- * Performance-Monitoring/Breakpoint external pins. Drop bits
- * 5:2 for backwards compatibility.
- */
- data &= ~GENMASK(5, 2);
-
- /*
* Suppress BTF as KVM doesn't virtualize BTF, but there's no
* way to communicate lack of support to the guest.
*/
@@ -3374,6 +3175,37 @@ static int invpcid_interception(struct kvm_vcpu *vcpu)
return kvm_handle_invpcid(vcpu, type, gva);
}
+static inline int complete_userspace_buslock(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ /*
+ * If userspace has NOT changed RIP, then KVM's ABI is to let the guest
+ * execute the bus-locking instruction. Set the bus lock counter to '1'
+ * to effectively step past the bus lock.
+ */
+ if (kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))
+ svm->vmcb->control.bus_lock_counter = 1;
+
+ return 1;
+}
+
+static int bus_lock_exit(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_svm *svm = to_svm(vcpu);
+
+ vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
+ vcpu->run->flags |= KVM_RUN_X86_BUS_LOCK;
+
+ vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu);
+ vcpu->arch.complete_userspace_io = complete_userspace_buslock;
+
+ if (is_guest_mode(vcpu))
+ svm->nested.ctl.bus_lock_rip = vcpu->arch.cui_linear_rip;
+
+ return 0;
+}
+
static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[SVM_EXIT_READ_CR0] = cr_interception,
[SVM_EXIT_READ_CR3] = cr_interception,
@@ -3443,6 +3275,7 @@ static int (*const svm_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[SVM_EXIT_INVPCID] = invpcid_interception,
[SVM_EXIT_IDLE_HLT] = kvm_emulate_halt,
[SVM_EXIT_NPF] = npf_interception,
+ [SVM_EXIT_BUS_LOCK] = bus_lock_exit,
[SVM_EXIT_RSM] = rsm_interception,
[SVM_EXIT_AVIC_INCOMPLETE_IPI] = avic_incomplete_ipi_interception,
[SVM_EXIT_AVIC_UNACCELERATED_ACCESS] = avic_unaccelerated_access_interception,
@@ -3457,14 +3290,21 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
struct vmcb_control_area *control = &svm->vmcb->control;
struct vmcb_save_area *save = &svm->vmcb->save;
struct vmcb_save_area *save01 = &svm->vmcb01.ptr->save;
+ char *vm_type;
if (!dump_invalid_vmcb) {
pr_warn_ratelimited("set kvm_amd.dump_invalid_vmcb=1 to dump internal KVM state.\n");
return;
}
- pr_err("VMCB %p, last attempted VMRUN on CPU %d\n",
- svm->current_vmcb->ptr, vcpu->arch.last_vmentry_cpu);
+ guard(mutex)(&vmcb_dump_mutex);
+
+ vm_type = sev_snp_guest(vcpu->kvm) ? "SEV-SNP" :
+ sev_es_guest(vcpu->kvm) ? "SEV-ES" :
+ sev_guest(vcpu->kvm) ? "SEV" : "SVM";
+
+ pr_err("%s vCPU%u VMCB %p, last attempted VMRUN on CPU %d\n",
+ vm_type, vcpu->vcpu_id, svm->current_vmcb->ptr, vcpu->arch.last_vmentry_cpu);
pr_err("VMCB Control Area:\n");
pr_err("%-20s%04x\n", "cr_read:", control->intercepts[INTERCEPT_CR] & 0xffff);
pr_err("%-20s%04x\n", "cr_write:", control->intercepts[INTERCEPT_CR] >> 16);
@@ -3502,6 +3342,17 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
pr_err("%-20s%016llx\n", "avic_logical_id:", control->avic_logical_id);
pr_err("%-20s%016llx\n", "avic_physical_id:", control->avic_physical_id);
pr_err("%-20s%016llx\n", "vmsa_pa:", control->vmsa_pa);
+ pr_err("%-20s%016llx\n", "allowed_sev_features:", control->allowed_sev_features);
+ pr_err("%-20s%016llx\n", "guest_sev_features:", control->guest_sev_features);
+
+ if (sev_es_guest(vcpu->kvm)) {
+ save = sev_decrypt_vmsa(vcpu);
+ if (!save)
+ goto no_vmsa;
+
+ save01 = save;
+ }
+
pr_err("VMCB State Save Area:\n");
pr_err("%-5s s: %04x a: %04x l: %08x b: %016llx\n",
"es:",
@@ -3572,6 +3423,63 @@ static void dump_vmcb(struct kvm_vcpu *vcpu)
pr_err("%-15s %016llx %-13s %016llx\n",
"excp_from:", save->last_excp_from,
"excp_to:", save->last_excp_to);
+
+ if (sev_es_guest(vcpu->kvm)) {
+ struct sev_es_save_area *vmsa = (struct sev_es_save_area *)save;
+
+ pr_err("%-15s %016llx\n",
+ "sev_features", vmsa->sev_features);
+
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "rax:", vmsa->rax, "rbx:", vmsa->rbx);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "rcx:", vmsa->rcx, "rdx:", vmsa->rdx);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "rsi:", vmsa->rsi, "rdi:", vmsa->rdi);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "rbp:", vmsa->rbp, "rsp:", vmsa->rsp);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "r8:", vmsa->r8, "r9:", vmsa->r9);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "r10:", vmsa->r10, "r11:", vmsa->r11);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "r12:", vmsa->r12, "r13:", vmsa->r13);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "r14:", vmsa->r14, "r15:", vmsa->r15);
+ pr_err("%-15s %016llx %-13s %016llx\n",
+ "xcr0:", vmsa->xcr0, "xss:", vmsa->xss);
+ } else {
+ pr_err("%-15s %016llx %-13s %016lx\n",
+ "rax:", save->rax, "rbx:",
+ vcpu->arch.regs[VCPU_REGS_RBX]);
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "rcx:", vcpu->arch.regs[VCPU_REGS_RCX],
+ "rdx:", vcpu->arch.regs[VCPU_REGS_RDX]);
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "rsi:", vcpu->arch.regs[VCPU_REGS_RSI],
+ "rdi:", vcpu->arch.regs[VCPU_REGS_RDI]);
+ pr_err("%-15s %016lx %-13s %016llx\n",
+ "rbp:", vcpu->arch.regs[VCPU_REGS_RBP],
+ "rsp:", save->rsp);
+#ifdef CONFIG_X86_64
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "r8:", vcpu->arch.regs[VCPU_REGS_R8],
+ "r9:", vcpu->arch.regs[VCPU_REGS_R9]);
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "r10:", vcpu->arch.regs[VCPU_REGS_R10],
+ "r11:", vcpu->arch.regs[VCPU_REGS_R11]);
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "r12:", vcpu->arch.regs[VCPU_REGS_R12],
+ "r13:", vcpu->arch.regs[VCPU_REGS_R13]);
+ pr_err("%-15s %016lx %-13s %016lx\n",
+ "r14:", vcpu->arch.regs[VCPU_REGS_R14],
+ "r15:", vcpu->arch.regs[VCPU_REGS_R15]);
+#endif
+ }
+
+no_vmsa:
+ if (sev_es_guest(vcpu->kvm))
+ sev_free_decrypted_vmsa(vcpu, save);
}
static bool svm_check_exit_valid(u64 exit_code)
@@ -3608,6 +3516,10 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 exit_code)
return kvm_emulate_halt(vcpu);
else if (exit_code == SVM_EXIT_NPF)
return npf_interception(vcpu);
+#ifdef CONFIG_KVM_AMD_SEV
+ else if (exit_code == SVM_EXIT_VMGEXIT)
+ return sev_handle_vmgexit(vcpu);
+#endif
#endif
return svm_exit_handlers[exit_code](vcpu);
}
@@ -4319,9 +4231,9 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in
guest_state_exit_irqoff();
}
-static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
- bool force_immediate_exit)
+static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
{
+ bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
struct vcpu_svm *svm = to_svm(vcpu);
bool spec_ctrl_intercepted = msr_write_intercepted(vcpu, MSR_IA32_SPEC_CTRL);
@@ -4368,10 +4280,13 @@ static __no_kcsan fastpath_t svm_vcpu_run(struct kvm_vcpu *vcpu,
svm_hv_update_vp_id(svm->vmcb, vcpu);
/*
- * Run with all-zero DR6 unless needed, so that we can get the exact cause
- * of a #DB.
+ * Run with all-zero DR6 unless the guest can write DR6 freely, so that
+ * KVM can get the exact cause of a #DB. Note, loading guest DR6 from
+ * KVM's snapshot is only necessary when DR accesses won't exit.
*/
- if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)))
+ if (unlikely(run_flags & KVM_RUN_LOAD_GUEST_DR6))
+ svm_set_dr6(vcpu, vcpu->arch.dr6);
+ else if (likely(!(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)))
svm_set_dr6(vcpu, DR6_ACTIVE_LOW);
clgi();
@@ -4551,20 +4466,10 @@ static void svm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
if (guest_cpuid_is_intel_compatible(vcpu))
guest_cpu_cap_clear(vcpu, X86_FEATURE_V_VMSAVE_VMLOAD);
- svm_recalc_instruction_intercepts(vcpu, svm);
-
- if (boot_cpu_has(X86_FEATURE_IBPB))
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_PRED_CMD, 0,
- !!guest_has_pred_cmd_msr(vcpu));
-
- if (boot_cpu_has(X86_FEATURE_FLUSH_L1D))
- set_msr_interception(vcpu, svm->msrpm, MSR_IA32_FLUSH_CMD, 0,
- !!guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D));
-
if (sev_guest(vcpu->kvm))
sev_vcpu_after_set_cpuid(svm);
- init_vmcb_after_set_cpuid(vcpu);
+ svm_recalc_intercepts_after_set_cpuid(vcpu);
}
static bool svm_has_wbinvd_exit(void)
@@ -5115,7 +5020,7 @@ static int svm_vm_init(struct kvm *kvm)
}
if (!pause_filter_count || !pause_filter_thresh)
- kvm->arch.pause_in_guest = true;
+ kvm_disable_exits(kvm, KVM_X86_DISABLE_EXITS_PAUSE);
if (enable_apicv) {
int ret = avic_vm_init(kvm);
@@ -5182,7 +5087,6 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.set_idt = svm_set_idt,
.get_gdt = svm_get_gdt,
.set_gdt = svm_set_gdt,
- .set_dr6 = svm_set_dr6,
.set_dr7 = svm_set_dr7,
.sync_dirty_debug_regs = svm_sync_dirty_debug_regs,
.cache_reg = svm_cache_reg,
@@ -5267,7 +5171,7 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
.apic_init_signal_blocked = svm_apic_init_signal_blocked,
- .msr_filter_changed = svm_msr_filter_changed,
+ .recalc_msr_intercepts = svm_recalc_msr_intercepts,
.complete_emulated_msr = svm_complete_emulated_msr,
.vcpu_deliver_sipi_vector = svm_vcpu_deliver_sipi_vector,
@@ -5295,7 +5199,7 @@ static __init void svm_adjust_mmio_mask(void)
return;
/* If memory encryption is not enabled, use existing mask */
- rdmsrl(MSR_AMD64_SYSCFG, msr);
+ rdmsrq(MSR_AMD64_SYSCFG, msr);
if (!(msr & MSR_AMD64_SYSCFG_MEM_ENCRYPT))
return;
@@ -5369,6 +5273,9 @@ static __init void svm_set_cpu_caps(void)
kvm_cpu_cap_set(X86_FEATURE_SVME_ADDR_CHK);
}
+ if (cpu_feature_enabled(X86_FEATURE_BUS_LOCK_THRESHOLD))
+ kvm_caps.has_bus_lock_exit = true;
+
/* CPUID 0x80000008 */
if (boot_cpu_has(X86_FEATURE_LS_CFG_SSBD) ||
boot_cpu_has(X86_FEATURE_AMD_SSBD))
@@ -5400,11 +5307,8 @@ static __init void svm_set_cpu_caps(void)
static __init int svm_hardware_setup(void)
{
- int cpu;
- struct page *iopm_pages;
void *iopm_va;
- int r;
- unsigned int order = get_order(IOPM_SIZE);
+ int cpu, r;
/*
* NX is required for shadow paging and for NPT if the NX huge pages
@@ -5416,17 +5320,6 @@ static __init int svm_hardware_setup(void)
}
kvm_enable_efer_bits(EFER_NX);
- iopm_pages = alloc_pages(GFP_KERNEL, order);
-
- if (!iopm_pages)
- return -ENOMEM;
-
- iopm_va = page_address(iopm_pages);
- memset(iopm_va, 0xff, PAGE_SIZE * (1 << order));
- iopm_base = __sme_page_pa(iopm_pages);
-
- init_msrpm_offsets();
-
kvm_caps.supported_xcr0 &= ~(XFEATURE_MASK_BNDREGS |
XFEATURE_MASK_BNDCSR);
@@ -5460,6 +5353,10 @@ static __init int svm_hardware_setup(void)
if (nested) {
pr_info("Nested Virtualization enabled\n");
kvm_enable_efer_bits(EFER_SVME | EFER_LMSLE);
+
+ r = nested_svm_init_msrpm_merge_offsets();
+ if (r)
+ return r;
}
/*
@@ -5491,6 +5388,13 @@ static __init int svm_hardware_setup(void)
else
pr_info("LBR virtualization supported\n");
}
+
+ iopm_va = svm_alloc_permissions_map(IOPM_SIZE, GFP_KERNEL);
+ if (!iopm_va)
+ return -ENOMEM;
+
+ iopm_base = __sme_set(__pa(iopm_va));
+
/*
* Note, SEV setup consumes npt_enabled and enable_mmio_caching (which
* may be modified by svm_adjust_mmio_mask()), as well as nrips.
@@ -5508,6 +5412,7 @@ static __init int svm_hardware_setup(void)
enable_apicv = avic = avic && avic_hardware_setup();
if (!enable_apicv) {
+ enable_ipiv = false;
svm_x86_ops.vcpu_blocking = NULL;
svm_x86_ops.vcpu_unblocking = NULL;
svm_x86_ops.vcpu_get_apicv_inhibit_reasons = NULL;
@@ -5564,6 +5469,7 @@ static __init int svm_hardware_setup(void)
*/
allow_smaller_maxphyaddr = !npt_enabled;
+ kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_CD_NW_CLEARED;
return 0;
err:
@@ -5588,6 +5494,8 @@ static int __init svm_init(void)
{
int r;
+ KVM_SANITY_CHECK_VM_STRUCT_SIZE(kvm_svm);
+
__unused_size_checks();
if (!kvm_is_svm_supported())
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index f16b068c4228..58b9d168e0c8 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -44,9 +44,6 @@ static inline struct page *__sme_pa_to_page(unsigned long pa)
#define IOPM_SIZE PAGE_SIZE * 3
#define MSRPM_SIZE PAGE_SIZE * 2
-#define MAX_DIRECT_ACCESS_MSRS 48
-#define MSRPM_OFFSETS 32
-extern u32 msrpm_offsets[MSRPM_OFFSETS] __read_mostly;
extern bool npt_enabled;
extern int nrips;
extern int vgif;
@@ -98,6 +95,7 @@ struct kvm_sev_info {
unsigned int asid; /* ASID used for this guest */
unsigned int handle; /* SEV firmware handle */
int fd; /* SEV device fd */
+ unsigned long policy;
unsigned long pages_locked; /* Number of pages locked */
struct list_head regions_list; /* List of registered regions */
u64 ap_jump_table; /* SEV-ES AP Jump Table address */
@@ -112,15 +110,19 @@ struct kvm_sev_info {
void *guest_req_buf; /* Bounce buffer for SNP Guest Request input */
void *guest_resp_buf; /* Bounce buffer for SNP Guest Request output */
struct mutex guest_req_mutex; /* Must acquire before using bounce buffers */
+ cpumask_var_t have_run_cpus; /* CPUs that have done VMRUN for this VM. */
};
+#define SEV_POLICY_NODBG BIT_ULL(0)
+#define SNP_POLICY_DEBUG BIT_ULL(19)
+
struct kvm_svm {
struct kvm kvm;
/* Struct members for AVIC */
u32 avic_vm_id;
- struct page *avic_logical_id_table_page;
- struct page *avic_physical_id_table_page;
+ u32 *avic_logical_id_table;
+ u64 *avic_physical_id_table;
struct hlist_node hnode;
struct kvm_sev_info sev_info;
@@ -169,6 +171,7 @@ struct vmcb_ctrl_area_cached {
u64 nested_cr3;
u64 virt_ext;
u32 clean;
+ u64 bus_lock_rip;
union {
#if IS_ENABLED(CONFIG_HYPERV) || IS_ENABLED(CONFIG_KVM_HYPERV)
struct hv_vmcb_enlightenments hv_enlightenments;
@@ -184,8 +187,11 @@ struct svm_nested_state {
u64 vmcb12_gpa;
u64 last_vmcb12_gpa;
- /* These are the merged vectors */
- u32 *msrpm;
+ /*
+ * The MSR permissions map used for vmcb02, which is the merge result
+ * of vmcb01 and vmcb12
+ */
+ void *msrpm;
/* A VMRUN has started but has not yet been performed, so
* we cannot inject a nested vmexit yet. */
@@ -266,7 +272,7 @@ struct vcpu_svm {
*/
u64 virt_spec_ctrl;
- u32 *msrpm;
+ void *msrpm;
ulong nmi_iret_rip;
@@ -301,24 +307,26 @@ struct vcpu_svm {
u32 ldr_reg;
u32 dfr_reg;
- struct page *avic_backing_page;
- u64 *avic_physical_id_cache;
+
+ /* This is essentially a shadow of the vCPU's actual entry in the
+ * Physical ID table that is programmed into the VMCB, i.e. that is
+ * seen by the CPU. If IPI virtualization is disabled, IsRunning is
+ * only ever set in the shadow, i.e. is never propagated to the "real"
+ * table, so that hardware never sees IsRunning=1.
+ */
+ u64 avic_physical_id_entry;
/*
- * Per-vcpu list of struct amd_svm_iommu_ir:
- * This is used mainly to store interrupt remapping information used
- * when update the vcpu affinity. This avoids the need to scan for
- * IRTE and try to match ga_tag in the IOMMU driver.
+ * Per-vCPU list of irqfds that are eligible to post IRQs directly to
+ * the vCPU (a.k.a. device posted IRQs, a.k.a. IRQ bypass). The list
+ * is used to reconfigure IRTEs when the vCPU is loaded/put (to set the
+ * target pCPU), when AVIC is toggled on/off (to (de)activate bypass),
+ * and if the irqfd becomes ineligible for posting (to put the IRTE
+ * back into remapped mode).
*/
struct list_head ir_list;
spinlock_t ir_list_lock;
- /* Save desired MSR intercept (read: pass-through) state */
- struct {
- DECLARE_BITMAP(read, MAX_DIRECT_ACCESS_MSRS);
- DECLARE_BITMAP(write, MAX_DIRECT_ACCESS_MSRS);
- } shadow_msr_intercept;
-
struct vcpu_sev_es_state sev_es;
bool guest_state_loaded;
@@ -340,8 +348,6 @@ struct svm_cpu_data {
struct vmcb *save_area;
unsigned long save_area_pa;
- struct vmcb *current_vmcb;
-
/* index = sev_asid, value = vmcb pointer */
struct vmcb **sev_vmcbs;
};
@@ -610,17 +616,74 @@ static inline void svm_vmgexit_no_action(struct vcpu_svm *svm, u64 data)
svm_vmgexit_set_return_code(svm, GHCB_HV_RESP_NO_ACTION, data);
}
-/* svm.c */
-#define MSR_INVALID 0xffffffffU
+/*
+ * The MSRPM is 8KiB in size, divided into four 2KiB ranges (the fourth range
+ * is reserved). Each MSR within a range is covered by two bits, one each for
+ * read (bit 0) and write (bit 1), where a bit value of '1' means intercepted.
+ */
+#define SVM_MSRPM_BYTES_PER_RANGE 2048
+#define SVM_BITS_PER_MSR 2
+#define SVM_MSRS_PER_BYTE (BITS_PER_BYTE / SVM_BITS_PER_MSR)
+#define SVM_MSRS_PER_RANGE (SVM_MSRPM_BYTES_PER_RANGE * SVM_MSRS_PER_BYTE)
+static_assert(SVM_MSRS_PER_RANGE == 8192);
+#define SVM_MSRPM_OFFSET_MASK (SVM_MSRS_PER_RANGE - 1)
+
+static __always_inline int svm_msrpm_bit_nr(u32 msr)
+{
+ int range_nr;
+
+ switch (msr & ~SVM_MSRPM_OFFSET_MASK) {
+ case 0:
+ range_nr = 0;
+ break;
+ case 0xc0000000:
+ range_nr = 1;
+ break;
+ case 0xc0010000:
+ range_nr = 2;
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return range_nr * SVM_MSRPM_BYTES_PER_RANGE * BITS_PER_BYTE +
+ (msr & SVM_MSRPM_OFFSET_MASK) * SVM_BITS_PER_MSR;
+}
+
+#define __BUILD_SVM_MSR_BITMAP_HELPER(rtype, action, bitop, access, bit_rw) \
+static inline rtype svm_##action##_msr_bitmap_##access(unsigned long *bitmap, \
+ u32 msr) \
+{ \
+ int bit_nr; \
+ \
+ bit_nr = svm_msrpm_bit_nr(msr); \
+ if (bit_nr < 0) \
+ return (rtype)true; \
+ \
+ return bitop##_bit(bit_nr + bit_rw, bitmap); \
+}
+
+#define BUILD_SVM_MSR_BITMAP_HELPERS(ret_type, action, bitop) \
+ __BUILD_SVM_MSR_BITMAP_HELPER(ret_type, action, bitop, read, 0) \
+ __BUILD_SVM_MSR_BITMAP_HELPER(ret_type, action, bitop, write, 1)
+
+BUILD_SVM_MSR_BITMAP_HELPERS(bool, test, test)
+BUILD_SVM_MSR_BITMAP_HELPERS(void, clear, __clear)
+BUILD_SVM_MSR_BITMAP_HELPERS(void, set, __set)
#define DEBUGCTL_RESERVED_BITS (~DEBUGCTLMSR_LBR)
+/* svm.c */
extern bool dump_invalid_vmcb;
-u32 svm_msrpm_offset(u32 msr);
-u32 *svm_vcpu_alloc_msrpm(void);
-void svm_vcpu_init_msrpm(struct kvm_vcpu *vcpu, u32 *msrpm);
-void svm_vcpu_free_msrpm(u32 *msrpm);
+void *svm_alloc_permissions_map(unsigned long size, gfp_t gfp_mask);
+
+static inline void *svm_vcpu_alloc_msrpm(void)
+{
+ return svm_alloc_permissions_map(MSRPM_SIZE, GFP_KERNEL_ACCOUNT);
+}
+
+void svm_vcpu_free_msrpm(void *msrpm);
void svm_copy_lbrs(struct vmcb *to_vmcb, struct vmcb *from_vmcb);
void svm_enable_lbrv(struct kvm_vcpu *vcpu);
void svm_update_lbrv(struct kvm_vcpu *vcpu);
@@ -640,6 +703,20 @@ void svm_set_x2apic_msr_interception(struct vcpu_svm *svm, bool disable);
void svm_complete_interrupt_delivery(struct kvm_vcpu *vcpu, int delivery_mode,
int trig_mode, int vec);
+void svm_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set);
+
+static inline void svm_disable_intercept_for_msr(struct kvm_vcpu *vcpu,
+ u32 msr, int type)
+{
+ svm_set_intercept_for_msr(vcpu, msr, type, false);
+}
+
+static inline void svm_enable_intercept_for_msr(struct kvm_vcpu *vcpu,
+ u32 msr, int type)
+{
+ svm_set_intercept_for_msr(vcpu, msr, type, true);
+}
+
/* nested.c */
#define NESTED_EXIT_HOST 0 /* Exit handled on host level */
@@ -668,6 +745,8 @@ static inline bool nested_exit_on_nmi(struct vcpu_svm *svm)
return vmcb12_is_intercept(&svm->nested.ctl, INTERCEPT_NMI);
}
+int __init nested_svm_init_msrpm_merge_offsets(void);
+
int enter_svm_guest_mode(struct kvm_vcpu *vcpu,
u64 vmcb_gpa, struct vmcb *vmcb12, bool from_vmrun);
void svm_leave_nested(struct kvm_vcpu *vcpu);
@@ -718,7 +797,8 @@ extern struct kvm_x86_nested_ops svm_nested_ops;
BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_ALIASED) | \
BIT(APICV_INHIBIT_REASON_APIC_ID_MODIFIED) | \
BIT(APICV_INHIBIT_REASON_APIC_BASE_MODIFIED) | \
- BIT(APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED) \
+ BIT(APICV_INHIBIT_REASON_LOGICAL_ID_ALIASED) | \
+ BIT(APICV_INHIBIT_REASON_PHYSICAL_ID_TOO_BIG) \
)
bool avic_hardware_setup(void);
@@ -733,8 +813,9 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
void avic_vcpu_put(struct kvm_vcpu *vcpu);
void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu);
void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu);
-int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
- uint32_t guest_irq, bool set);
+int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+ unsigned int host_irq, uint32_t guest_irq,
+ struct kvm_vcpu *vcpu, u32 vector);
void avic_vcpu_blocking(struct kvm_vcpu *vcpu);
void avic_vcpu_unblocking(struct kvm_vcpu *vcpu);
void avic_ring_doorbell(struct kvm_vcpu *vcpu);
@@ -749,6 +830,7 @@ void sev_init_vmcb(struct vcpu_svm *svm);
void sev_vcpu_after_set_cpuid(struct vcpu_svm *svm);
int sev_es_string_io(struct vcpu_svm *svm, int size, unsigned int port, int in);
void sev_es_vcpu_reset(struct vcpu_svm *svm);
+void sev_es_recalc_msr_intercepts(struct kvm_vcpu *vcpu);
void sev_vcpu_deliver_sipi_vector(struct kvm_vcpu *vcpu, u8 vector);
void sev_es_prepare_switch_to_guest(struct vcpu_svm *svm, struct sev_es_save_area *hostsa);
void sev_es_unmap_ghcb(struct vcpu_svm *svm);
@@ -785,6 +867,8 @@ void sev_snp_init_protected_guest_state(struct kvm_vcpu *vcpu);
int sev_gmem_prepare(struct kvm *kvm, kvm_pfn_t pfn, gfn_t gfn, int max_order);
void sev_gmem_invalidate(kvm_pfn_t start, kvm_pfn_t end);
int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
+struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu);
+void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa);
#else
static inline struct page *snp_safe_alloc_page_node(int node, gfp_t gfp)
{
@@ -816,6 +900,11 @@ static inline int sev_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
return 0;
}
+static inline struct vmcb_save_area *sev_decrypt_vmsa(struct kvm_vcpu *vcpu)
+{
+ return NULL;
+}
+static inline void sev_free_decrypted_vmsa(struct kvm_vcpu *vcpu, struct vmcb_save_area *vmsa) {}
#endif
/* vmenter.S */
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 0c61153b275f..235c4af6b692 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -169,6 +169,9 @@ SYM_FUNC_START(__svm_vcpu_run)
#endif
mov VCPU_RDI(%_ASM_DI), %_ASM_DI
+ /* Clobbers EFLAGS.ZF */
+ VM_CLEAR_CPU_BUFFERS
+
/* Enter guest mode */
3: vmrun %_ASM_AX
4:
@@ -335,6 +338,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
mov SVM_current_vmcb(%rdi), %rax
mov KVM_VMCB_pa(%rax), %rax
+ /* Clobbers EFLAGS.ZF */
+ VM_CLEAR_CPU_BUFFERS
+
/* Enter guest mode */
1: vmrun %rax
2:
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index ba736cbb0587..57d79fd31df0 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -260,6 +260,86 @@ TRACE_EVENT(kvm_cpuid,
__entry->used_max_basic ? ", used max basic" : "")
);
+#define kvm_deliver_mode \
+ {0x0, "Fixed"}, \
+ {0x1, "LowPrio"}, \
+ {0x2, "SMI"}, \
+ {0x3, "Res3"}, \
+ {0x4, "NMI"}, \
+ {0x5, "INIT"}, \
+ {0x6, "SIPI"}, \
+ {0x7, "ExtINT"}
+
+#ifdef CONFIG_KVM_IOAPIC
+TRACE_EVENT(kvm_ioapic_set_irq,
+ TP_PROTO(__u64 e, int pin, bool coalesced),
+ TP_ARGS(e, pin, coalesced),
+
+ TP_STRUCT__entry(
+ __field( __u64, e )
+ __field( int, pin )
+ __field( bool, coalesced )
+ ),
+
+ TP_fast_assign(
+ __entry->e = e;
+ __entry->pin = pin;
+ __entry->coalesced = coalesced;
+ ),
+
+ TP_printk("pin %u dst %x vec %u (%s|%s|%s%s)%s",
+ __entry->pin, (u8)(__entry->e >> 56), (u8)__entry->e,
+ __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
+ (__entry->e & (1<<11)) ? "logical" : "physical",
+ (__entry->e & (1<<15)) ? "level" : "edge",
+ (__entry->e & (1<<16)) ? "|masked" : "",
+ __entry->coalesced ? " (coalesced)" : "")
+);
+
+TRACE_EVENT(kvm_ioapic_delayed_eoi_inj,
+ TP_PROTO(__u64 e),
+ TP_ARGS(e),
+
+ TP_STRUCT__entry(
+ __field( __u64, e )
+ ),
+
+ TP_fast_assign(
+ __entry->e = e;
+ ),
+
+ TP_printk("dst %x vec %u (%s|%s|%s%s)",
+ (u8)(__entry->e >> 56), (u8)__entry->e,
+ __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode),
+ (__entry->e & (1<<11)) ? "logical" : "physical",
+ (__entry->e & (1<<15)) ? "level" : "edge",
+ (__entry->e & (1<<16)) ? "|masked" : "")
+);
+#endif
+
+TRACE_EVENT(kvm_msi_set_irq,
+ TP_PROTO(__u64 address, __u64 data),
+ TP_ARGS(address, data),
+
+ TP_STRUCT__entry(
+ __field( __u64, address )
+ __field( __u64, data )
+ ),
+
+ TP_fast_assign(
+ __entry->address = address;
+ __entry->data = data;
+ ),
+
+ TP_printk("dst %llx vec %u (%s|%s|%s%s)",
+ (u8)(__entry->address >> 12) | ((__entry->address >> 32) & 0xffffff00),
+ (u8)__entry->data,
+ __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode),
+ (__entry->address & (1<<2)) ? "logical" : "physical",
+ (__entry->data & (1<<15)) ? "level" : "edge",
+ (__entry->address & (1<<3)) ? "|rh" : "")
+);
+
#define AREG(x) { APIC_##x, "APIC_" #x }
#define kvm_trace_symbol_apic \
@@ -1096,37 +1176,32 @@ TRACE_EVENT(kvm_smm_transition,
* Tracepoint for VT-d posted-interrupts and AMD-Vi Guest Virtual APIC.
*/
TRACE_EVENT(kvm_pi_irte_update,
- TP_PROTO(unsigned int host_irq, unsigned int vcpu_id,
- unsigned int gsi, unsigned int gvec,
- u64 pi_desc_addr, bool set),
- TP_ARGS(host_irq, vcpu_id, gsi, gvec, pi_desc_addr, set),
+ TP_PROTO(unsigned int host_irq, struct kvm_vcpu *vcpu,
+ unsigned int gsi, unsigned int gvec, bool set),
+ TP_ARGS(host_irq, vcpu, gsi, gvec, set),
TP_STRUCT__entry(
__field( unsigned int, host_irq )
- __field( unsigned int, vcpu_id )
+ __field( int, vcpu_id )
__field( unsigned int, gsi )
__field( unsigned int, gvec )
- __field( u64, pi_desc_addr )
__field( bool, set )
),
TP_fast_assign(
__entry->host_irq = host_irq;
- __entry->vcpu_id = vcpu_id;
+ __entry->vcpu_id = vcpu ? vcpu->vcpu_id : -1;
__entry->gsi = gsi;
__entry->gvec = gvec;
- __entry->pi_desc_addr = pi_desc_addr;
__entry->set = set;
),
- TP_printk("PI is %s for irq %u, vcpu %u, gsi: 0x%x, "
- "gvec: 0x%x, pi_desc_addr: 0x%llx",
+ TP_printk("PI is %s for irq %u, vcpu %d, gsi: 0x%x, gvec: 0x%x",
__entry->set ? "enabled and being updated" : "disabled",
__entry->host_irq,
__entry->vcpu_id,
__entry->gsi,
- __entry->gvec,
- __entry->pi_desc_addr)
+ __entry->gvec)
);
/*
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index cb6588238f46..5316c27f6099 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -15,7 +15,6 @@ extern bool __read_mostly enable_ept;
extern bool __read_mostly enable_unrestricted_guest;
extern bool __read_mostly enable_ept_ad_bits;
extern bool __read_mostly enable_pml;
-extern bool __read_mostly enable_ipiv;
extern int __read_mostly pt_mode;
#define PT_MODE_SYSTEM 0
diff --git a/arch/x86/kvm/vmx/common.h b/arch/x86/kvm/vmx/common.h
new file mode 100644
index 000000000000..bc5ece76533a
--- /dev/null
+++ b/arch/x86/kvm/vmx/common.h
@@ -0,0 +1,180 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef __KVM_X86_VMX_COMMON_H
+#define __KVM_X86_VMX_COMMON_H
+
+#include <linux/kvm_host.h>
+#include <asm/posted_intr.h>
+
+#include "mmu.h"
+
+union vmx_exit_reason {
+ struct {
+ u32 basic : 16;
+ u32 reserved16 : 1;
+ u32 reserved17 : 1;
+ u32 reserved18 : 1;
+ u32 reserved19 : 1;
+ u32 reserved20 : 1;
+ u32 reserved21 : 1;
+ u32 reserved22 : 1;
+ u32 reserved23 : 1;
+ u32 reserved24 : 1;
+ u32 reserved25 : 1;
+ u32 bus_lock_detected : 1;
+ u32 enclave_mode : 1;
+ u32 smi_pending_mtf : 1;
+ u32 smi_from_vmx_root : 1;
+ u32 reserved30 : 1;
+ u32 failed_vmentry : 1;
+ };
+ u32 full;
+};
+
+struct vcpu_vt {
+ /* Posted interrupt descriptor */
+ struct pi_desc pi_desc;
+
+ /* Used if this vCPU is waiting for PI notification wakeup. */
+ struct list_head pi_wakeup_list;
+
+ union vmx_exit_reason exit_reason;
+
+ unsigned long exit_qualification;
+ u32 exit_intr_info;
+
+ /*
+ * If true, guest state has been loaded into hardware, and host state
+ * saved into vcpu_{vt,vmx,tdx}. If false, host state is loaded into
+ * hardware.
+ */
+ bool guest_state_loaded;
+ bool emulation_required;
+
+#ifdef CONFIG_X86_64
+ u64 msr_host_kernel_gs_base;
+#endif
+};
+
+#ifdef CONFIG_KVM_INTEL_TDX
+
+static __always_inline bool is_td(struct kvm *kvm)
+{
+ return kvm->arch.vm_type == KVM_X86_TDX_VM;
+}
+
+static __always_inline bool is_td_vcpu(struct kvm_vcpu *vcpu)
+{
+ return is_td(vcpu->kvm);
+}
+
+#else
+
+static __always_inline bool is_td(struct kvm *kvm) { return false; }
+static __always_inline bool is_td_vcpu(struct kvm_vcpu *vcpu) { return false; }
+
+#endif
+
+static inline bool vt_is_tdx_private_gpa(struct kvm *kvm, gpa_t gpa)
+{
+ /* For TDX the direct mask is the shared mask. */
+ return !kvm_is_addr_direct(kvm, gpa);
+}
+
+static inline int __vmx_handle_ept_violation(struct kvm_vcpu *vcpu, gpa_t gpa,
+ unsigned long exit_qualification)
+{
+ u64 error_code;
+
+ /* Is it a read fault? */
+ error_code = (exit_qualification & EPT_VIOLATION_ACC_READ)
+ ? PFERR_USER_MASK : 0;
+ /* Is it a write fault? */
+ error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE)
+ ? PFERR_WRITE_MASK : 0;
+ /* Is it a fetch fault? */
+ error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR)
+ ? PFERR_FETCH_MASK : 0;
+ /* ept page table entry is present? */
+ error_code |= (exit_qualification & EPT_VIOLATION_PROT_MASK)
+ ? PFERR_PRESENT_MASK : 0;
+
+ if (error_code & EPT_VIOLATION_GVA_IS_VALID)
+ error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ?
+ PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
+
+ if (vt_is_tdx_private_gpa(vcpu->kvm, gpa))
+ error_code |= PFERR_PRIVATE_ACCESS;
+
+ return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
+}
+
+static inline void kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
+ int pi_vec)
+{
+#ifdef CONFIG_SMP
+ if (vcpu->mode == IN_GUEST_MODE) {
+ /*
+ * The vector of the virtual has already been set in the PIR.
+ * Send a notification event to deliver the virtual interrupt
+ * unless the vCPU is the currently running vCPU, i.e. the
+ * event is being sent from a fastpath VM-Exit handler, in
+ * which case the PIR will be synced to the vIRR before
+ * re-entering the guest.
+ *
+ * When the target is not the running vCPU, the following
+ * possibilities emerge:
+ *
+ * Case 1: vCPU stays in non-root mode. Sending a notification
+ * event posts the interrupt to the vCPU.
+ *
+ * Case 2: vCPU exits to root mode and is still runnable. The
+ * PIR will be synced to the vIRR before re-entering the guest.
+ * Sending a notification event is ok as the host IRQ handler
+ * will ignore the spurious event.
+ *
+ * Case 3: vCPU exits to root mode and is blocked. vcpu_block()
+ * has already synced PIR to vIRR and never blocks the vCPU if
+ * the vIRR is not empty. Therefore, a blocked vCPU here does
+ * not wait for any requested interrupts in PIR, and sending a
+ * notification event also results in a benign, spurious event.
+ */
+
+ if (vcpu != kvm_get_running_vcpu())
+ __apic_send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
+ return;
+ }
+#endif
+ /*
+ * The vCPU isn't in the guest; wake the vCPU in case it is blocking,
+ * otherwise do nothing as KVM will grab the highest priority pending
+ * IRQ via ->sync_pir_to_irr() in vcpu_enter_guest().
+ */
+ kvm_vcpu_wake_up(vcpu);
+}
+
+/*
+ * Post an interrupt to a vCPU's PIR and trigger the vCPU to process the
+ * interrupt if necessary.
+ */
+static inline void __vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu,
+ struct pi_desc *pi_desc, int vector)
+{
+ if (pi_test_and_set_pir(vector, pi_desc))
+ return;
+
+ /* If a previous notification has sent the IPI, nothing to do. */
+ if (pi_test_and_set_on(pi_desc))
+ return;
+
+ /*
+ * The implied barrier in pi_test_and_set_on() pairs with the smp_mb_*()
+ * after setting vcpu->mode in vcpu_enter_guest(), thus the vCPU is
+ * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a
+ * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE.
+ */
+ kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_VECTOR);
+}
+
+noinstr void vmx_handle_nmi(struct kvm_vcpu *vcpu);
+
+#endif /* __KVM_X86_VMX_COMMON_H */
diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
index 43ee9ed11291..dbab1c15b0cd 100644
--- a/arch/x86/kvm/vmx/main.c
+++ b/arch/x86/kvm/vmx/main.c
@@ -3,9 +3,848 @@
#include "x86_ops.h"
#include "vmx.h"
+#include "mmu.h"
#include "nested.h"
#include "pmu.h"
#include "posted_intr.h"
+#include "tdx.h"
+#include "tdx_arch.h"
+
+#ifdef CONFIG_KVM_INTEL_TDX
+static_assert(offsetof(struct vcpu_vmx, vt) == offsetof(struct vcpu_tdx, vt));
+
+static void vt_disable_virtualization_cpu(void)
+{
+ /* Note, TDX *and* VMX need to be disabled if TDX is enabled. */
+ if (enable_tdx)
+ tdx_disable_virtualization_cpu();
+ vmx_disable_virtualization_cpu();
+}
+
+static __init int vt_hardware_setup(void)
+{
+ int ret;
+
+ ret = vmx_hardware_setup();
+ if (ret)
+ return ret;
+
+ if (enable_tdx)
+ tdx_hardware_setup();
+
+ return 0;
+}
+
+static int vt_vm_init(struct kvm *kvm)
+{
+ if (is_td(kvm))
+ return tdx_vm_init(kvm);
+
+ return vmx_vm_init(kvm);
+}
+
+static void vt_vm_pre_destroy(struct kvm *kvm)
+{
+ if (is_td(kvm))
+ return tdx_mmu_release_hkid(kvm);
+}
+
+static void vt_vm_destroy(struct kvm *kvm)
+{
+ if (is_td(kvm))
+ return tdx_vm_destroy(kvm);
+
+ vmx_vm_destroy(kvm);
+}
+
+static int vt_vcpu_precreate(struct kvm *kvm)
+{
+ if (is_td(kvm))
+ return 0;
+
+ return vmx_vcpu_precreate(kvm);
+}
+
+static int vt_vcpu_create(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return tdx_vcpu_create(vcpu);
+
+ return vmx_vcpu_create(vcpu);
+}
+
+static void vt_vcpu_free(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu)) {
+ tdx_vcpu_free(vcpu);
+ return;
+ }
+
+ vmx_vcpu_free(vcpu);
+}
+
+static void vt_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
+{
+ if (is_td_vcpu(vcpu)) {
+ tdx_vcpu_reset(vcpu, init_event);
+ return;
+ }
+
+ vmx_vcpu_reset(vcpu, init_event);
+}
+
+static void vt_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+ if (is_td_vcpu(vcpu)) {
+ tdx_vcpu_load(vcpu, cpu);
+ return;
+ }
+
+ vmx_vcpu_load(vcpu, cpu);
+}
+
+static void vt_update_cpu_dirty_logging(struct kvm_vcpu *vcpu)
+{
+ /*
+ * Basic TDX does not support feature PML. KVM does not enable PML in
+ * TD's VMCS, nor does it allocate or flush PML buffer for TDX.
+ */
+ if (WARN_ON_ONCE(is_td_vcpu(vcpu)))
+ return;
+
+ vmx_update_cpu_dirty_logging(vcpu);
+}
+
+static void vt_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu)) {
+ tdx_prepare_switch_to_guest(vcpu);
+ return;
+ }
+
+ vmx_prepare_switch_to_guest(vcpu);
+}
+
+static void vt_vcpu_put(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu)) {
+ tdx_vcpu_put(vcpu);
+ return;
+ }
+
+ vmx_vcpu_put(vcpu);
+}
+
+static int vt_vcpu_pre_run(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return tdx_vcpu_pre_run(vcpu);
+
+ return vmx_vcpu_pre_run(vcpu);
+}
+
+static fastpath_t vt_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
+{
+ if (is_td_vcpu(vcpu))
+ return tdx_vcpu_run(vcpu, run_flags);
+
+ return vmx_vcpu_run(vcpu, run_flags);
+}
+
+static int vt_handle_exit(struct kvm_vcpu *vcpu,
+ enum exit_fastpath_completion fastpath)
+{
+ if (is_td_vcpu(vcpu))
+ return tdx_handle_exit(vcpu, fastpath);
+
+ return vmx_handle_exit(vcpu, fastpath);
+}
+
+static int vt_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+ if (unlikely(is_td_vcpu(vcpu)))
+ return tdx_set_msr(vcpu, msr_info);
+
+ return vmx_set_msr(vcpu, msr_info);
+}
+
+/*
+ * The kvm parameter can be NULL (module initialization, or invocation before
+ * VM creation). Be sure to check the kvm parameter before using it.
+ */
+static bool vt_has_emulated_msr(struct kvm *kvm, u32 index)
+{
+ if (kvm && is_td(kvm))
+ return tdx_has_emulated_msr(index);
+
+ return vmx_has_emulated_msr(kvm, index);
+}
+
+static int vt_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+{
+ if (unlikely(is_td_vcpu(vcpu)))
+ return tdx_get_msr(vcpu, msr_info);
+
+ return vmx_get_msr(vcpu, msr_info);
+}
+
+static void vt_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
+{
+ /*
+ * TDX doesn't allow VMM to configure interception of MSR accesses.
+ * TDX guest requests MSR accesses by calling TDVMCALL. The MSR
+ * filters will be applied when handling the TDVMCALL for RDMSR/WRMSR
+ * if the userspace has set any.
+ */
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_recalc_msr_intercepts(vcpu);
+}
+
+static int vt_complete_emulated_msr(struct kvm_vcpu *vcpu, int err)
+{
+ if (is_td_vcpu(vcpu))
+ return tdx_complete_emulated_msr(vcpu, err);
+
+ return vmx_complete_emulated_msr(vcpu, err);
+}
+
+#ifdef CONFIG_KVM_SMM
+static int vt_smi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
+{
+ if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm))
+ return 0;
+
+ return vmx_smi_allowed(vcpu, for_injection);
+}
+
+static int vt_enter_smm(struct kvm_vcpu *vcpu, union kvm_smram *smram)
+{
+ if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm))
+ return 0;
+
+ return vmx_enter_smm(vcpu, smram);
+}
+
+static int vt_leave_smm(struct kvm_vcpu *vcpu, const union kvm_smram *smram)
+{
+ if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm))
+ return 0;
+
+ return vmx_leave_smm(vcpu, smram);
+}
+
+static void vt_enable_smi_window(struct kvm_vcpu *vcpu)
+{
+ if (KVM_BUG_ON(is_td_vcpu(vcpu), vcpu->kvm))
+ return;
+
+ /* RSM will cause a vmexit anyway. */
+ vmx_enable_smi_window(vcpu);
+}
+#endif
+
+static int vt_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
+ void *insn, int insn_len)
+{
+ /*
+ * For TDX, this can only be triggered for MMIO emulation. Let the
+ * guest retry after installing the SPTE with suppress #VE bit cleared,
+ * so that the guest will receive #VE when retry. The guest is expected
+ * to call TDG.VP.VMCALL<MMIO> to request VMM to do MMIO emulation on
+ * #VE.
+ */
+ if (is_td_vcpu(vcpu))
+ return X86EMUL_RETRY_INSTR;
+
+ return vmx_check_emulate_instruction(vcpu, emul_type, insn, insn_len);
+}
+
+static bool vt_apic_init_signal_blocked(struct kvm_vcpu *vcpu)
+{
+ /*
+ * INIT and SIPI are always blocked for TDX, i.e., INIT handling and
+ * the OP vcpu_deliver_sipi_vector() won't be called.
+ */
+ if (is_td_vcpu(vcpu))
+ return true;
+
+ return vmx_apic_init_signal_blocked(vcpu);
+}
+
+static void vt_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
+{
+ /* Only x2APIC mode is supported for TD. */
+ if (is_td_vcpu(vcpu))
+ return;
+
+ return vmx_set_virtual_apic_mode(vcpu);
+}
+
+static void vt_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ return vmx_hwapic_isr_update(vcpu, max_isr);
+}
+
+static int vt_sync_pir_to_irr(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return -1;
+
+ return vmx_sync_pir_to_irr(vcpu);
+}
+
+static void vt_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
+ int trig_mode, int vector)
+{
+ if (is_td_vcpu(apic->vcpu)) {
+ tdx_deliver_interrupt(apic, delivery_mode, trig_mode,
+ vector);
+ return;
+ }
+
+ vmx_deliver_interrupt(apic, delivery_mode, trig_mode, vector);
+}
+
+static void vt_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_vcpu_after_set_cpuid(vcpu);
+}
+
+static void vt_update_exception_bitmap(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_update_exception_bitmap(vcpu);
+}
+
+static u64 vt_get_segment_base(struct kvm_vcpu *vcpu, int seg)
+{
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_get_segment_base(vcpu, seg);
+}
+
+static void vt_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var,
+ int seg)
+{
+ if (is_td_vcpu(vcpu)) {
+ memset(var, 0, sizeof(*var));
+ return;
+ }
+
+ vmx_get_segment(vcpu, var, seg);
+}
+
+static void vt_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var,
+ int seg)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_segment(vcpu, var, seg);
+}
+
+static int vt_get_cpl(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_get_cpl(vcpu);
+}
+
+static int vt_get_cpl_no_cache(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_get_cpl_no_cache(vcpu);
+}
+
+static void vt_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
+{
+ if (is_td_vcpu(vcpu)) {
+ *db = 0;
+ *l = 0;
+ return;
+ }
+
+ vmx_get_cs_db_l_bits(vcpu, db, l);
+}
+
+static bool vt_is_valid_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
+{
+ if (is_td_vcpu(vcpu))
+ return true;
+
+ return vmx_is_valid_cr0(vcpu, cr0);
+}
+
+static void vt_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_cr0(vcpu, cr0);
+}
+
+static bool vt_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+ if (is_td_vcpu(vcpu))
+ return true;
+
+ return vmx_is_valid_cr4(vcpu, cr4);
+}
+
+static void vt_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_cr4(vcpu, cr4);
+}
+
+static int vt_set_efer(struct kvm_vcpu *vcpu, u64 efer)
+{
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_set_efer(vcpu, efer);
+}
+
+static void vt_get_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+ if (is_td_vcpu(vcpu)) {
+ memset(dt, 0, sizeof(*dt));
+ return;
+ }
+
+ vmx_get_idt(vcpu, dt);
+}
+
+static void vt_set_idt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_idt(vcpu, dt);
+}
+
+static void vt_get_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+ if (is_td_vcpu(vcpu)) {
+ memset(dt, 0, sizeof(*dt));
+ return;
+ }
+
+ vmx_get_gdt(vcpu, dt);
+}
+
+static void vt_set_gdt(struct kvm_vcpu *vcpu, struct desc_ptr *dt)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_gdt(vcpu, dt);
+}
+
+static void vt_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_dr7(vcpu, val);
+}
+
+static void vt_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
+{
+ /*
+ * MOV-DR exiting is always cleared for TD guest, even in debug mode.
+ * Thus KVM_DEBUGREG_WONT_EXIT can never be set and it should never
+ * reach here for TD vcpu.
+ */
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_sync_dirty_debug_regs(vcpu);
+}
+
+static void vt_cache_reg(struct kvm_vcpu *vcpu, enum kvm_reg reg)
+{
+ if (WARN_ON_ONCE(is_td_vcpu(vcpu)))
+ return;
+
+ vmx_cache_reg(vcpu, reg);
+}
+
+static unsigned long vt_get_rflags(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_get_rflags(vcpu);
+}
+
+static void vt_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_rflags(vcpu, rflags);
+}
+
+static bool vt_get_if_flag(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return false;
+
+ return vmx_get_if_flag(vcpu);
+}
+
+static void vt_flush_tlb_all(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu)) {
+ tdx_flush_tlb_all(vcpu);
+ return;
+ }
+
+ vmx_flush_tlb_all(vcpu);
+}
+
+static void vt_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu)) {
+ tdx_flush_tlb_current(vcpu);
+ return;
+ }
+
+ vmx_flush_tlb_current(vcpu);
+}
+
+static void vt_flush_tlb_gva(struct kvm_vcpu *vcpu, gva_t addr)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_flush_tlb_gva(vcpu, addr);
+}
+
+static void vt_flush_tlb_guest(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_flush_tlb_guest(vcpu);
+}
+
+static void vt_inject_nmi(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu)) {
+ tdx_inject_nmi(vcpu);
+ return;
+ }
+
+ vmx_inject_nmi(vcpu);
+}
+
+static int vt_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
+{
+ /*
+ * The TDX module manages NMI windows and NMI reinjection, and hides NMI
+ * blocking, all KVM can do is throw an NMI over the wall.
+ */
+ if (is_td_vcpu(vcpu))
+ return true;
+
+ return vmx_nmi_allowed(vcpu, for_injection);
+}
+
+static bool vt_get_nmi_mask(struct kvm_vcpu *vcpu)
+{
+ /*
+ * KVM can't get NMI blocking status for TDX guest, assume NMIs are
+ * always unmasked.
+ */
+ if (is_td_vcpu(vcpu))
+ return false;
+
+ return vmx_get_nmi_mask(vcpu);
+}
+
+static void vt_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_nmi_mask(vcpu, masked);
+}
+
+static void vt_enable_nmi_window(struct kvm_vcpu *vcpu)
+{
+ /* Refer to the comments in tdx_inject_nmi(). */
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_enable_nmi_window(vcpu);
+}
+
+static void vt_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa,
+ int pgd_level)
+{
+ if (is_td_vcpu(vcpu)) {
+ tdx_load_mmu_pgd(vcpu, root_hpa, pgd_level);
+ return;
+ }
+
+ vmx_load_mmu_pgd(vcpu, root_hpa, pgd_level);
+}
+
+static void vt_set_interrupt_shadow(struct kvm_vcpu *vcpu, int mask)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_interrupt_shadow(vcpu, mask);
+}
+
+static u32 vt_get_interrupt_shadow(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_get_interrupt_shadow(vcpu);
+}
+
+static void vt_patch_hypercall(struct kvm_vcpu *vcpu,
+ unsigned char *hypercall)
+{
+ /*
+ * Because guest memory is protected, guest can't be patched. TD kernel
+ * is modified to use TDG.VP.VMCALL for hypercall.
+ */
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_patch_hypercall(vcpu, hypercall);
+}
+
+static void vt_inject_irq(struct kvm_vcpu *vcpu, bool reinjected)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_inject_irq(vcpu, reinjected);
+}
+
+static void vt_inject_exception(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_inject_exception(vcpu);
+}
+
+static void vt_cancel_injection(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_cancel_injection(vcpu);
+}
+
+static int vt_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
+{
+ if (is_td_vcpu(vcpu))
+ return tdx_interrupt_allowed(vcpu);
+
+ return vmx_interrupt_allowed(vcpu, for_injection);
+}
+
+static void vt_enable_irq_window(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_enable_irq_window(vcpu);
+}
+
+static void vt_get_entry_info(struct kvm_vcpu *vcpu, u32 *intr_info, u32 *error_code)
+{
+ *intr_info = 0;
+ *error_code = 0;
+
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_get_entry_info(vcpu, intr_info, error_code);
+}
+
+static void vt_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
+ u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code)
+{
+ if (is_td_vcpu(vcpu)) {
+ tdx_get_exit_info(vcpu, reason, info1, info2, intr_info,
+ error_code);
+ return;
+ }
+
+ vmx_get_exit_info(vcpu, reason, info1, info2, intr_info, error_code);
+}
+
+static void vt_update_cr8_intercept(struct kvm_vcpu *vcpu, int tpr, int irr)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_update_cr8_intercept(vcpu, tpr, irr);
+}
+
+static void vt_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_set_apic_access_page_addr(vcpu);
+}
+
+static void vt_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu)) {
+ KVM_BUG_ON(!kvm_vcpu_apicv_active(vcpu), vcpu->kvm);
+ return;
+ }
+
+ vmx_refresh_apicv_exec_ctrl(vcpu);
+}
+
+static void vt_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_load_eoi_exitmap(vcpu, eoi_exit_bitmap);
+}
+
+static int vt_set_tss_addr(struct kvm *kvm, unsigned int addr)
+{
+ if (is_td(kvm))
+ return 0;
+
+ return vmx_set_tss_addr(kvm, addr);
+}
+
+static int vt_set_identity_map_addr(struct kvm *kvm, u64 ident_addr)
+{
+ if (is_td(kvm))
+ return 0;
+
+ return vmx_set_identity_map_addr(kvm, ident_addr);
+}
+
+static u64 vt_get_l2_tsc_offset(struct kvm_vcpu *vcpu)
+{
+ /* TDX doesn't support L2 guest at the moment. */
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_get_l2_tsc_offset(vcpu);
+}
+
+static u64 vt_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu)
+{
+ /* TDX doesn't support L2 guest at the moment. */
+ if (is_td_vcpu(vcpu))
+ return 0;
+
+ return vmx_get_l2_tsc_multiplier(vcpu);
+}
+
+static void vt_write_tsc_offset(struct kvm_vcpu *vcpu)
+{
+ /* In TDX, tsc offset can't be changed. */
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_write_tsc_offset(vcpu);
+}
+
+static void vt_write_tsc_multiplier(struct kvm_vcpu *vcpu)
+{
+ /* In TDX, tsc multiplier can't be changed. */
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_write_tsc_multiplier(vcpu);
+}
+
+#ifdef CONFIG_X86_64
+static int vt_set_hv_timer(struct kvm_vcpu *vcpu, u64 guest_deadline_tsc,
+ bool *expired)
+{
+ /* VMX-preemption timer isn't available for TDX. */
+ if (is_td_vcpu(vcpu))
+ return -EINVAL;
+
+ return vmx_set_hv_timer(vcpu, guest_deadline_tsc, expired);
+}
+
+static void vt_cancel_hv_timer(struct kvm_vcpu *vcpu)
+{
+ /* VMX-preemption timer can't be set. See vt_set_hv_timer(). */
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_cancel_hv_timer(vcpu);
+}
+#endif
+
+static void vt_setup_mce(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return;
+
+ vmx_setup_mce(vcpu);
+}
+
+static int vt_mem_enc_ioctl(struct kvm *kvm, void __user *argp)
+{
+ if (!is_td(kvm))
+ return -ENOTTY;
+
+ return tdx_vm_ioctl(kvm, argp);
+}
+
+static int vt_vcpu_mem_enc_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
+{
+ if (!is_td_vcpu(vcpu))
+ return -EINVAL;
+
+ return tdx_vcpu_ioctl(vcpu, argp);
+}
+
+static int vt_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+{
+ if (is_td(kvm))
+ return tdx_gmem_private_max_mapping_level(kvm, pfn);
+
+ return 0;
+}
+
+#define vt_op(name) vt_##name
+#define vt_op_tdx_only(name) vt_##name
+#else /* CONFIG_KVM_INTEL_TDX */
+#define vt_op(name) vmx_##name
+#define vt_op_tdx_only(name) NULL
+#endif /* CONFIG_KVM_INTEL_TDX */
#define VMX_REQUIRED_APICV_INHIBITS \
(BIT(APICV_INHIBIT_REASON_DISABLED) | \
@@ -24,147 +863,210 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
.hardware_unsetup = vmx_hardware_unsetup,
.enable_virtualization_cpu = vmx_enable_virtualization_cpu,
- .disable_virtualization_cpu = vmx_disable_virtualization_cpu,
+ .disable_virtualization_cpu = vt_op(disable_virtualization_cpu),
.emergency_disable_virtualization_cpu = vmx_emergency_disable_virtualization_cpu,
- .has_emulated_msr = vmx_has_emulated_msr,
+ .has_emulated_msr = vt_op(has_emulated_msr),
.vm_size = sizeof(struct kvm_vmx),
- .vm_init = vmx_vm_init,
- .vm_destroy = vmx_vm_destroy,
- .vcpu_precreate = vmx_vcpu_precreate,
- .vcpu_create = vmx_vcpu_create,
- .vcpu_free = vmx_vcpu_free,
- .vcpu_reset = vmx_vcpu_reset,
+ .vm_init = vt_op(vm_init),
+ .vm_destroy = vt_op(vm_destroy),
+ .vm_pre_destroy = vt_op_tdx_only(vm_pre_destroy),
- .prepare_switch_to_guest = vmx_prepare_switch_to_guest,
- .vcpu_load = vmx_vcpu_load,
- .vcpu_put = vmx_vcpu_put,
+ .vcpu_precreate = vt_op(vcpu_precreate),
+ .vcpu_create = vt_op(vcpu_create),
+ .vcpu_free = vt_op(vcpu_free),
+ .vcpu_reset = vt_op(vcpu_reset),
- .update_exception_bitmap = vmx_update_exception_bitmap,
+ .prepare_switch_to_guest = vt_op(prepare_switch_to_guest),
+ .vcpu_load = vt_op(vcpu_load),
+ .vcpu_put = vt_op(vcpu_put),
+
+ .HOST_OWNED_DEBUGCTL = VMX_HOST_OWNED_DEBUGCTL_BITS,
+
+ .update_exception_bitmap = vt_op(update_exception_bitmap),
.get_feature_msr = vmx_get_feature_msr,
- .get_msr = vmx_get_msr,
- .set_msr = vmx_set_msr,
- .get_segment_base = vmx_get_segment_base,
- .get_segment = vmx_get_segment,
- .set_segment = vmx_set_segment,
- .get_cpl = vmx_get_cpl,
- .get_cpl_no_cache = vmx_get_cpl_no_cache,
- .get_cs_db_l_bits = vmx_get_cs_db_l_bits,
- .is_valid_cr0 = vmx_is_valid_cr0,
- .set_cr0 = vmx_set_cr0,
- .is_valid_cr4 = vmx_is_valid_cr4,
- .set_cr4 = vmx_set_cr4,
- .set_efer = vmx_set_efer,
- .get_idt = vmx_get_idt,
- .set_idt = vmx_set_idt,
- .get_gdt = vmx_get_gdt,
- .set_gdt = vmx_set_gdt,
- .set_dr6 = vmx_set_dr6,
- .set_dr7 = vmx_set_dr7,
- .sync_dirty_debug_regs = vmx_sync_dirty_debug_regs,
- .cache_reg = vmx_cache_reg,
- .get_rflags = vmx_get_rflags,
- .set_rflags = vmx_set_rflags,
- .get_if_flag = vmx_get_if_flag,
-
- .flush_tlb_all = vmx_flush_tlb_all,
- .flush_tlb_current = vmx_flush_tlb_current,
- .flush_tlb_gva = vmx_flush_tlb_gva,
- .flush_tlb_guest = vmx_flush_tlb_guest,
-
- .vcpu_pre_run = vmx_vcpu_pre_run,
- .vcpu_run = vmx_vcpu_run,
- .handle_exit = vmx_handle_exit,
+ .get_msr = vt_op(get_msr),
+ .set_msr = vt_op(set_msr),
+
+ .get_segment_base = vt_op(get_segment_base),
+ .get_segment = vt_op(get_segment),
+ .set_segment = vt_op(set_segment),
+ .get_cpl = vt_op(get_cpl),
+ .get_cpl_no_cache = vt_op(get_cpl_no_cache),
+ .get_cs_db_l_bits = vt_op(get_cs_db_l_bits),
+ .is_valid_cr0 = vt_op(is_valid_cr0),
+ .set_cr0 = vt_op(set_cr0),
+ .is_valid_cr4 = vt_op(is_valid_cr4),
+ .set_cr4 = vt_op(set_cr4),
+ .set_efer = vt_op(set_efer),
+ .get_idt = vt_op(get_idt),
+ .set_idt = vt_op(set_idt),
+ .get_gdt = vt_op(get_gdt),
+ .set_gdt = vt_op(set_gdt),
+ .set_dr7 = vt_op(set_dr7),
+ .sync_dirty_debug_regs = vt_op(sync_dirty_debug_regs),
+ .cache_reg = vt_op(cache_reg),
+ .get_rflags = vt_op(get_rflags),
+ .set_rflags = vt_op(set_rflags),
+ .get_if_flag = vt_op(get_if_flag),
+
+ .flush_tlb_all = vt_op(flush_tlb_all),
+ .flush_tlb_current = vt_op(flush_tlb_current),
+ .flush_tlb_gva = vt_op(flush_tlb_gva),
+ .flush_tlb_guest = vt_op(flush_tlb_guest),
+
+ .vcpu_pre_run = vt_op(vcpu_pre_run),
+ .vcpu_run = vt_op(vcpu_run),
+ .handle_exit = vt_op(handle_exit),
.skip_emulated_instruction = vmx_skip_emulated_instruction,
.update_emulated_instruction = vmx_update_emulated_instruction,
- .set_interrupt_shadow = vmx_set_interrupt_shadow,
- .get_interrupt_shadow = vmx_get_interrupt_shadow,
- .patch_hypercall = vmx_patch_hypercall,
- .inject_irq = vmx_inject_irq,
- .inject_nmi = vmx_inject_nmi,
- .inject_exception = vmx_inject_exception,
- .cancel_injection = vmx_cancel_injection,
- .interrupt_allowed = vmx_interrupt_allowed,
- .nmi_allowed = vmx_nmi_allowed,
- .get_nmi_mask = vmx_get_nmi_mask,
- .set_nmi_mask = vmx_set_nmi_mask,
- .enable_nmi_window = vmx_enable_nmi_window,
- .enable_irq_window = vmx_enable_irq_window,
- .update_cr8_intercept = vmx_update_cr8_intercept,
+ .set_interrupt_shadow = vt_op(set_interrupt_shadow),
+ .get_interrupt_shadow = vt_op(get_interrupt_shadow),
+ .patch_hypercall = vt_op(patch_hypercall),
+ .inject_irq = vt_op(inject_irq),
+ .inject_nmi = vt_op(inject_nmi),
+ .inject_exception = vt_op(inject_exception),
+ .cancel_injection = vt_op(cancel_injection),
+ .interrupt_allowed = vt_op(interrupt_allowed),
+ .nmi_allowed = vt_op(nmi_allowed),
+ .get_nmi_mask = vt_op(get_nmi_mask),
+ .set_nmi_mask = vt_op(set_nmi_mask),
+ .enable_nmi_window = vt_op(enable_nmi_window),
+ .enable_irq_window = vt_op(enable_irq_window),
+ .update_cr8_intercept = vt_op(update_cr8_intercept),
.x2apic_icr_is_split = false,
- .set_virtual_apic_mode = vmx_set_virtual_apic_mode,
- .set_apic_access_page_addr = vmx_set_apic_access_page_addr,
- .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
- .load_eoi_exitmap = vmx_load_eoi_exitmap,
- .apicv_pre_state_restore = vmx_apicv_pre_state_restore,
+ .set_virtual_apic_mode = vt_op(set_virtual_apic_mode),
+ .set_apic_access_page_addr = vt_op(set_apic_access_page_addr),
+ .refresh_apicv_exec_ctrl = vt_op(refresh_apicv_exec_ctrl),
+ .load_eoi_exitmap = vt_op(load_eoi_exitmap),
+ .apicv_pre_state_restore = pi_apicv_pre_state_restore,
.required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS,
- .hwapic_isr_update = vmx_hwapic_isr_update,
- .sync_pir_to_irr = vmx_sync_pir_to_irr,
- .deliver_interrupt = vmx_deliver_interrupt,
+ .hwapic_isr_update = vt_op(hwapic_isr_update),
+ .sync_pir_to_irr = vt_op(sync_pir_to_irr),
+ .deliver_interrupt = vt_op(deliver_interrupt),
.dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
- .set_tss_addr = vmx_set_tss_addr,
- .set_identity_map_addr = vmx_set_identity_map_addr,
+ .set_tss_addr = vt_op(set_tss_addr),
+ .set_identity_map_addr = vt_op(set_identity_map_addr),
.get_mt_mask = vmx_get_mt_mask,
- .get_exit_info = vmx_get_exit_info,
- .get_entry_info = vmx_get_entry_info,
+ .get_exit_info = vt_op(get_exit_info),
+ .get_entry_info = vt_op(get_entry_info),
- .vcpu_after_set_cpuid = vmx_vcpu_after_set_cpuid,
+ .vcpu_after_set_cpuid = vt_op(vcpu_after_set_cpuid),
.has_wbinvd_exit = cpu_has_vmx_wbinvd_exit,
- .get_l2_tsc_offset = vmx_get_l2_tsc_offset,
- .get_l2_tsc_multiplier = vmx_get_l2_tsc_multiplier,
- .write_tsc_offset = vmx_write_tsc_offset,
- .write_tsc_multiplier = vmx_write_tsc_multiplier,
+ .get_l2_tsc_offset = vt_op(get_l2_tsc_offset),
+ .get_l2_tsc_multiplier = vt_op(get_l2_tsc_multiplier),
+ .write_tsc_offset = vt_op(write_tsc_offset),
+ .write_tsc_multiplier = vt_op(write_tsc_multiplier),
- .load_mmu_pgd = vmx_load_mmu_pgd,
+ .load_mmu_pgd = vt_op(load_mmu_pgd),
.check_intercept = vmx_check_intercept,
.handle_exit_irqoff = vmx_handle_exit_irqoff,
- .cpu_dirty_log_size = PML_LOG_NR_ENTRIES,
- .update_cpu_dirty_logging = vmx_update_cpu_dirty_logging,
+ .update_cpu_dirty_logging = vt_op(update_cpu_dirty_logging),
.nested_ops = &vmx_nested_ops,
.pi_update_irte = vmx_pi_update_irte,
- .pi_start_assignment = vmx_pi_start_assignment,
+ .pi_start_bypass = vmx_pi_start_bypass,
#ifdef CONFIG_X86_64
- .set_hv_timer = vmx_set_hv_timer,
- .cancel_hv_timer = vmx_cancel_hv_timer,
+ .set_hv_timer = vt_op(set_hv_timer),
+ .cancel_hv_timer = vt_op(cancel_hv_timer),
#endif
- .setup_mce = vmx_setup_mce,
+ .setup_mce = vt_op(setup_mce),
#ifdef CONFIG_KVM_SMM
- .smi_allowed = vmx_smi_allowed,
- .enter_smm = vmx_enter_smm,
- .leave_smm = vmx_leave_smm,
- .enable_smi_window = vmx_enable_smi_window,
+ .smi_allowed = vt_op(smi_allowed),
+ .enter_smm = vt_op(enter_smm),
+ .leave_smm = vt_op(leave_smm),
+ .enable_smi_window = vt_op(enable_smi_window),
#endif
- .check_emulate_instruction = vmx_check_emulate_instruction,
- .apic_init_signal_blocked = vmx_apic_init_signal_blocked,
+ .check_emulate_instruction = vt_op(check_emulate_instruction),
+ .apic_init_signal_blocked = vt_op(apic_init_signal_blocked),
.migrate_timers = vmx_migrate_timers,
- .msr_filter_changed = vmx_msr_filter_changed,
- .complete_emulated_msr = kvm_complete_insn_gp,
+ .recalc_msr_intercepts = vt_op(recalc_msr_intercepts),
+ .complete_emulated_msr = vt_op(complete_emulated_msr),
.vcpu_deliver_sipi_vector = kvm_vcpu_deliver_sipi_vector,
.get_untagged_addr = vmx_get_untagged_addr,
+
+ .mem_enc_ioctl = vt_op_tdx_only(mem_enc_ioctl),
+ .vcpu_mem_enc_ioctl = vt_op_tdx_only(vcpu_mem_enc_ioctl),
+
+ .private_max_mapping_level = vt_op_tdx_only(gmem_private_max_mapping_level)
};
struct kvm_x86_init_ops vt_init_ops __initdata = {
- .hardware_setup = vmx_hardware_setup,
+ .hardware_setup = vt_op(hardware_setup),
.handle_intel_pt_intr = NULL,
.runtime_ops = &vt_x86_ops,
.pmu_ops = &intel_pmu_ops,
};
+
+static void __exit vt_exit(void)
+{
+ kvm_exit();
+ tdx_cleanup();
+ vmx_exit();
+}
+module_exit(vt_exit);
+
+static int __init vt_init(void)
+{
+ unsigned vcpu_size, vcpu_align;
+ int r;
+
+ r = vmx_init();
+ if (r)
+ return r;
+
+ /* tdx_init() has been taken */
+ r = tdx_bringup();
+ if (r)
+ goto err_tdx_bringup;
+
+ /*
+ * TDX and VMX have different vCPU structures. Calculate the
+ * maximum size/align so that kvm_init() can use the larger
+ * values to create the kmem_vcpu_cache.
+ */
+ vcpu_size = sizeof(struct vcpu_vmx);
+ vcpu_align = __alignof__(struct vcpu_vmx);
+ if (enable_tdx) {
+ vcpu_size = max_t(unsigned, vcpu_size,
+ sizeof(struct vcpu_tdx));
+ vcpu_align = max_t(unsigned, vcpu_align,
+ __alignof__(struct vcpu_tdx));
+ kvm_caps.supported_vm_types |= BIT(KVM_X86_TDX_VM);
+ }
+
+ /*
+ * Common KVM initialization _must_ come last, after this, /dev/kvm is
+ * exposed to userspace!
+ */
+ r = kvm_init(vcpu_size, vcpu_align, THIS_MODULE);
+ if (r)
+ goto err_kvm_init;
+
+ return 0;
+
+err_kvm_init:
+ tdx_cleanup();
+err_tdx_bringup:
+ vmx_exit();
+ return r;
+}
+module_init(vt_init);
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 5504d9e9fd32..b8ea1969113d 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6,6 +6,7 @@
#include <asm/debugreg.h>
#include <asm/mmu_context.h>
+#include <asm/msr.h>
#include "x86.h"
#include "cpuid.h"
@@ -275,7 +276,7 @@ static void vmx_sync_vmcs_host_state(struct vcpu_vmx *vmx,
{
struct vmcs_host_state *dest, *src;
- if (unlikely(!vmx->guest_state_loaded))
+ if (unlikely(!vmx->vt.guest_state_loaded))
return;
src = &prev->host_state;
@@ -301,7 +302,7 @@ static void vmx_switch_vmcs(struct kvm_vcpu *vcpu, struct loaded_vmcs *vmcs)
cpu = get_cpu();
prev = vmx->loaded_vmcs;
vmx->loaded_vmcs = vmcs;
- vmx_vcpu_load_vmcs(vcpu, cpu, prev);
+ vmx_vcpu_load_vmcs(vcpu, cpu);
vmx_sync_vmcs_host_state(vmx, prev);
put_cpu();
@@ -425,7 +426,7 @@ static void nested_ept_inject_page_fault(struct kvm_vcpu *vcpu,
* tables also changed, but KVM should not treat EPT Misconfig
* VM-Exits as writes.
*/
- WARN_ON_ONCE(vmx->exit_reason.basic != EXIT_REASON_EPT_VIOLATION);
+ WARN_ON_ONCE(vmx->vt.exit_reason.basic != EXIT_REASON_EPT_VIOLATION);
/*
* PML Full and EPT Violation VM-Exits both use bit 12 to report
@@ -714,6 +715,12 @@ static inline bool nested_vmx_prepare_msr_bitmap(struct kvm_vcpu *vcpu,
nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
MSR_IA32_FLUSH_CMD, MSR_TYPE_W);
+ nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+ MSR_IA32_APERF, MSR_TYPE_R);
+
+ nested_vmx_set_intercept_for_msr(vmx, msr_bitmap_l1, msr_bitmap_l0,
+ MSR_IA32_MPERF, MSR_TYPE_R);
+
kvm_vcpu_unmap(vcpu, &map);
vmx->nested.force_msr_bitmap_recalc = false;
@@ -824,12 +831,30 @@ static int nested_vmx_check_apicv_controls(struct kvm_vcpu *vcpu,
return 0;
}
+static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+ u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
+ vmx->nested.msrs.misc_high);
+
+ return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER;
+}
+
static int nested_vmx_check_msr_switch(struct kvm_vcpu *vcpu,
u32 count, u64 addr)
{
if (count == 0)
return 0;
+ /*
+ * Exceeding the limit results in architecturally _undefined_ behavior,
+ * i.e. KVM is allowed to do literally anything in response to a bad
+ * limit. Immediately generate a consistency check so that code that
+ * consumes the count doesn't need to worry about extreme edge cases.
+ */
+ if (count > nested_vmx_max_atomic_switch_msrs(vcpu))
+ return -EINVAL;
+
if (!kvm_vcpu_is_legal_aligned_gpa(vcpu, addr, 16) ||
!kvm_vcpu_is_legal_gpa(vcpu, (addr + count * sizeof(struct vmx_msr_entry) - 1)))
return -EINVAL;
@@ -940,15 +965,6 @@ static int nested_vmx_store_msr_check(struct kvm_vcpu *vcpu,
return 0;
}
-static u32 nested_vmx_max_atomic_switch_msrs(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- u64 vmx_misc = vmx_control_msr(vmx->nested.msrs.misc_low,
- vmx->nested.msrs.misc_high);
-
- return (vmx_misc_max_msr(vmx_misc) + 1) * VMX_MISC_MSR_LIST_MULTIPLIER;
-}
-
/*
* Load guest's/host's msr at nested entry/exit.
* return 0 for success, entry index for failure.
@@ -965,7 +981,7 @@ static u32 nested_vmx_load_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
for (i = 0; i < count; i++) {
- if (unlikely(i >= max_msr_list_size))
+ if (WARN_ON_ONCE(i >= max_msr_list_size))
goto fail;
if (kvm_vcpu_read_guest(vcpu, gpa + i * sizeof(e),
@@ -1053,7 +1069,7 @@ static int nested_vmx_store_msr(struct kvm_vcpu *vcpu, u64 gpa, u32 count)
u32 max_msr_list_size = nested_vmx_max_atomic_switch_msrs(vcpu);
for (i = 0; i < count; i++) {
- if (unlikely(i >= max_msr_list_size))
+ if (WARN_ON_ONCE(i >= max_msr_list_size))
return -EINVAL;
if (!read_and_check_msr_entry(vcpu, gpa, i, &e))
@@ -2653,10 +2669,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (vmx->nested.nested_run_pending &&
(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS)) {
kvm_set_dr(vcpu, 7, vmcs12->guest_dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmcs12->guest_ia32_debugctl);
+ vmx_guest_debugctl_write(vcpu, vmcs12->guest_ia32_debugctl &
+ vmx_get_supported_debugctl(vcpu, false));
} else {
kvm_set_dr(vcpu, 7, vcpu->arch.dr7);
- vmcs_write64(GUEST_IA32_DEBUGCTL, vmx->nested.pre_vmenter_debugctl);
+ vmx_guest_debugctl_write(vcpu, vmx->nested.pre_vmenter_debugctl);
}
if (kvm_mpx_supported() && (!vmx->nested.nested_run_pending ||
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -3146,7 +3163,8 @@ static int nested_vmx_check_guest_state(struct kvm_vcpu *vcpu,
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS) &&
- CC(!kvm_dr7_valid(vmcs12->guest_dr7)))
+ (CC(!kvm_dr7_valid(vmcs12->guest_dr7)) ||
+ CC(!vmx_is_valid_debugctl(vcpu, vmcs12->guest_ia32_debugctl, false))))
return -EINVAL;
if ((vmcs12->vm_entry_controls & VM_ENTRY_LOAD_IA32_PAT) &&
@@ -3520,7 +3538,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
if (!vmx->nested.nested_run_pending ||
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_DEBUG_CONTROLS))
- vmx->nested.pre_vmenter_debugctl = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ vmx->nested.pre_vmenter_debugctl = vmx_guest_debugctl_read();
if (kvm_mpx_supported() &&
(!vmx->nested.nested_run_pending ||
!(vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)))
@@ -4520,12 +4538,12 @@ static void copy_vmcs02_to_vmcs12_rare(struct kvm_vcpu *vcpu,
cpu = get_cpu();
vmx->loaded_vmcs = &vmx->nested.vmcs02;
- vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->vmcs01);
+ vmx_vcpu_load_vmcs(vcpu, cpu);
sync_vmcs02_to_vmcs12_rare(vcpu, vmcs12);
vmx->loaded_vmcs = &vmx->vmcs01;
- vmx_vcpu_load_vmcs(vcpu, cpu, &vmx->nested.vmcs02);
+ vmx_vcpu_load_vmcs(vcpu, cpu);
put_cpu();
}
@@ -4598,6 +4616,12 @@ static void sync_vmcs02_to_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12)
(vmcs12->vm_entry_controls & ~VM_ENTRY_IA32E_MODE) |
(vm_entry_controls_get(to_vmx(vcpu)) & VM_ENTRY_IA32E_MODE);
+ /*
+ * Note! Save DR7, but intentionally don't grab DEBUGCTL from vmcs02.
+ * Writes to DEBUGCTL that aren't intercepted by L1 are immediately
+ * propagated to vmcs12 (see vmx_set_msr()), as the value loaded into
+ * vmcs02 doesn't strictly track vmcs12.
+ */
if (vmcs12->vm_exit_controls & VM_EXIT_SAVE_DEBUG_CONTROLS)
vmcs12->guest_dr7 = vcpu->arch.dr7;
@@ -4622,7 +4646,7 @@ static void prepare_vmcs12(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
{
/* update exit information fields: */
vmcs12->vm_exit_reason = vm_exit_reason;
- if (to_vmx(vcpu)->exit_reason.enclave_mode)
+ if (vmx_get_exit_reason(vcpu).enclave_mode)
vmcs12->vm_exit_reason |= VMX_EXIT_REASONS_SGX_ENCLAVE_MODE;
vmcs12->exit_qualification = exit_qualification;
@@ -4788,13 +4812,13 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
__vmx_set_segment(vcpu, &seg, VCPU_SREG_LDTR);
kvm_set_dr(vcpu, 7, 0x400);
- vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+ vmx_guest_debugctl_write(vcpu, 0);
if (nested_vmx_load_msr(vcpu, vmcs12->vm_exit_msr_load_addr,
vmcs12->vm_exit_msr_load_count))
nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_MSR_FAIL);
- to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
+ to_vt(vcpu)->emulation_required = vmx_emulation_required(vcpu);
}
static inline u64 nested_vmx_get_vmcs01_guest_efer(struct vcpu_vmx *vmx)
@@ -4843,6 +4867,9 @@ static void nested_vmx_restore_host_state(struct kvm_vcpu *vcpu)
WARN_ON(kvm_set_dr(vcpu, 7, vmcs_readl(GUEST_DR7)));
}
+ /* Reload DEBUGCTL to ensure vmcs01 has a fresh FREEZE_IN_SMM value. */
+ vmx_reload_guest_debugctl(vcpu);
+
/*
* Note that calling vmx_set_{efer,cr0,cr4} is important as they
* handle a variety of side effects to KVM's software model.
@@ -5020,16 +5047,7 @@ void __nested_vmx_vmexit(struct kvm_vcpu *vcpu, u32 vm_exit_reason,
vmx_switch_vmcs(vcpu, &vmx->vmcs01);
- /*
- * If IBRS is advertised to the vCPU, KVM must flush the indirect
- * branch predictors when transitioning from L2 to L1, as L1 expects
- * hardware (KVM in this case) to provide separate predictor modes.
- * Bare metal isolates VMX root (host) from VMX non-root (guest), but
- * doesn't isolate different VMCSs, i.e. in this case, doesn't provide
- * separate modes for L2 vs L1.
- */
- if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL))
- indirect_branch_prediction_barrier();
+ kvm_nested_vmexit_handle_ibrs(vcpu);
/* Update any VMCS fields that might have changed while L2 ran */
vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.host.nr);
@@ -6127,7 +6145,7 @@ fail:
* nested VM-Exit. Pass the original exit reason, i.e. don't hardcode
* EXIT_REASON_VMFUNC as the exit reason.
*/
- nested_vmx_vmexit(vcpu, vmx->exit_reason.full,
+ nested_vmx_vmexit(vcpu, vmx->vt.exit_reason.full,
vmx_get_intr_info(vcpu),
vmx_get_exit_qual(vcpu));
return 1;
@@ -6572,7 +6590,7 @@ static bool nested_vmx_l1_wants_exit(struct kvm_vcpu *vcpu,
bool nested_vmx_reflect_vmexit(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- union vmx_exit_reason exit_reason = vmx->exit_reason;
+ union vmx_exit_reason exit_reason = vmx->vt.exit_reason;
unsigned long exit_qual;
u32 exit_intr_info;
@@ -7202,8 +7220,8 @@ static void nested_vmx_setup_cr_fixed(struct nested_vmx_msrs *msrs)
msrs->cr4_fixed0 = VMXON_CR4_ALWAYSON;
/* These MSRs specify bits which the guest must keep fixed off. */
- rdmsrl(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1);
- rdmsrl(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1);
+ rdmsrq(MSR_IA32_VMX_CR0_FIXED1, msrs->cr0_fixed1);
+ rdmsrq(MSR_IA32_VMX_CR4_FIXED1, msrs->cr4_fixed1);
if (vmx_umip_emulated())
msrs->cr4_fixed1 |= X86_CR4_UMIP;
diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c
index 77012b2eca0e..0b173602821b 100644
--- a/arch/x86/kvm/vmx/pmu_intel.c
+++ b/arch/x86/kvm/vmx/pmu_intel.c
@@ -13,12 +13,14 @@
#include <linux/types.h>
#include <linux/kvm_host.h>
#include <linux/perf_event.h>
+#include <asm/msr.h>
#include <asm/perf_event.h>
#include "x86.h"
#include "cpuid.h"
#include "lapic.h"
#include "nested.h"
#include "pmu.h"
+#include "tdx.h"
/*
* Perf's "BASE" is wildly misleading, architectural PMUs use bits 31:16 of ECX
@@ -34,6 +36,24 @@
#define MSR_PMC_FULL_WIDTH_BIT (MSR_IA32_PMC0 - MSR_IA32_PERFCTR0)
+static struct lbr_desc *vcpu_to_lbr_desc(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return NULL;
+
+ return &to_vmx(vcpu)->lbr_desc;
+}
+
+static struct x86_pmu_lbr *vcpu_to_lbr_records(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return NULL;
+
+ return &to_vmx(vcpu)->lbr_desc.records;
+}
+
+#pragma GCC poison to_vmx
+
static void reprogram_fixed_counters(struct kvm_pmu *pmu, u64 data)
{
struct kvm_pmc *pmc;
@@ -129,6 +149,22 @@ static inline struct kvm_pmc *get_fw_gp_pmc(struct kvm_pmu *pmu, u32 msr)
return get_gp_pmc(pmu, msr, MSR_IA32_PMC0);
}
+static bool intel_pmu_lbr_is_compatible(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return false;
+
+ return cpuid_model_is_consistent(vcpu);
+}
+
+bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu)
+{
+ if (is_td_vcpu(vcpu))
+ return false;
+
+ return !!vcpu_to_lbr_records(vcpu)->nr;
+}
+
static bool intel_pmu_is_valid_lbr_msr(struct kvm_vcpu *vcpu, u32 index)
{
struct x86_pmu_lbr *records = vcpu_to_lbr_records(vcpu);
@@ -194,6 +230,9 @@ static inline void intel_pmu_release_guest_lbr_event(struct kvm_vcpu *vcpu)
{
struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
+ if (!lbr_desc)
+ return;
+
if (lbr_desc->event) {
perf_event_release_kernel(lbr_desc->event);
lbr_desc->event = NULL;
@@ -235,6 +274,9 @@ int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu)
PERF_SAMPLE_BRANCH_USER,
};
+ if (WARN_ON_ONCE(!lbr_desc))
+ return 0;
+
if (unlikely(lbr_desc->event)) {
__set_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use);
return 0;
@@ -279,9 +321,9 @@ static bool intel_pmu_handle_lbr_msrs_access(struct kvm_vcpu *vcpu,
local_irq_disable();
if (lbr_desc->event->state == PERF_EVENT_STATE_ACTIVE) {
if (read)
- rdmsrl(index, msr_info->data);
+ rdmsrq(index, msr_info->data);
else
- wrmsrl(index, msr_info->data);
+ wrmsrq(index, msr_info->data);
__set_bit(INTEL_PMC_IDX_FIXED_VLBR, vcpu_to_pmu(vcpu)->pmc_in_use);
local_irq_enable();
return true;
@@ -466,6 +508,9 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
u64 perf_capabilities;
u64 counter_rsvd;
+ if (!lbr_desc)
+ return;
+
memset(&lbr_desc->records, 0, sizeof(lbr_desc->records));
/*
@@ -542,7 +587,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu)
INTEL_PMC_MAX_GENERIC, pmu->nr_arch_fixed_counters);
perf_capabilities = vcpu_get_perf_capabilities(vcpu);
- if (cpuid_model_is_consistent(vcpu) &&
+ if (intel_pmu_lbr_is_compatible(vcpu) &&
(perf_capabilities & PMU_CAP_LBR_FMT))
memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps));
else
@@ -570,6 +615,9 @@ static void intel_pmu_init(struct kvm_vcpu *vcpu)
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
+ if (!lbr_desc)
+ return;
+
for (i = 0; i < KVM_MAX_NR_INTEL_GP_COUNTERS; i++) {
pmu->gp_counters[i].type = KVM_PMC_GP;
pmu->gp_counters[i].vcpu = vcpu;
@@ -605,11 +653,11 @@ static void intel_pmu_reset(struct kvm_vcpu *vcpu)
*/
static void intel_pmu_legacy_freezing_lbrs_on_pmi(struct kvm_vcpu *vcpu)
{
- u64 data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ u64 data = vmx_guest_debugctl_read();
if (data & DEBUGCTLMSR_FREEZE_LBRS_ON_PMI) {
data &= ~DEBUGCTLMSR_LBR;
- vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+ vmx_guest_debugctl_write(vcpu, data);
}
}
@@ -677,9 +725,12 @@ void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu)
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
struct lbr_desc *lbr_desc = vcpu_to_lbr_desc(vcpu);
+ if (WARN_ON_ONCE(!lbr_desc))
+ return;
+
if (!lbr_desc->event) {
vmx_disable_lbr_msrs_passthrough(vcpu);
- if (vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR)
+ if (vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR)
goto warn;
if (test_bit(INTEL_PMC_IDX_FIXED_VLBR, pmu->pmc_in_use))
goto warn;
@@ -701,7 +752,7 @@ warn:
static void intel_pmu_cleanup(struct kvm_vcpu *vcpu)
{
- if (!(vmcs_read64(GUEST_IA32_DEBUGCTL) & DEBUGCTLMSR_LBR))
+ if (!(vmx_guest_debugctl_read() & DEBUGCTLMSR_LBR))
intel_pmu_release_guest_lbr_event(vcpu);
}
diff --git a/arch/x86/kvm/vmx/pmu_intel.h b/arch/x86/kvm/vmx/pmu_intel.h
new file mode 100644
index 000000000000..5620d0882cdc
--- /dev/null
+++ b/arch/x86/kvm/vmx/pmu_intel.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_PMU_INTEL_H
+#define __KVM_X86_VMX_PMU_INTEL_H
+
+#include <linux/kvm_host.h>
+
+bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu);
+int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu);
+
+struct lbr_desc {
+ /* Basic info about guest LBR records. */
+ struct x86_pmu_lbr records;
+
+ /*
+ * Emulate LBR feature via passthrough LBR registers when the
+ * per-vcpu guest LBR event is scheduled on the current pcpu.
+ *
+ * The records may be inaccurate if the host reclaims the LBR.
+ */
+ struct perf_event *event;
+
+ /* True if LBRs are marked as not intercepted in the MSR bitmap */
+ bool msr_passthrough;
+};
+
+extern struct x86_pmu_lbr vmx_lbr_caps;
+
+#endif /* __KVM_X86_VMX_PMU_INTEL_H */
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index d70e5b90087d..4a6d9a17da23 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -2,6 +2,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kvm_host.h>
+#include <linux/kvm_irqfd.h>
#include <asm/irq_remapping.h>
#include <asm/cpu.h>
@@ -11,6 +12,7 @@
#include "posted_intr.h"
#include "trace.h"
#include "vmx.h"
+#include "tdx.h"
/*
* Maintain a per-CPU list of vCPUs that need to be awakened by wakeup_handler()
@@ -33,9 +35,9 @@ static DEFINE_PER_CPU(raw_spinlock_t, wakeup_vcpus_on_cpu_lock);
#define PI_LOCK_SCHED_OUT SINGLE_DEPTH_NESTING
-static inline struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
+static struct pi_desc *vcpu_to_pi_desc(struct kvm_vcpu *vcpu)
{
- return &(to_vmx(vcpu)->pi_desc);
+ return &(to_vt(vcpu)->pi_desc);
}
static int pi_try_set_control(struct pi_desc *pi_desc, u64 *pold, u64 new)
@@ -55,7 +57,7 @@ static int pi_try_set_control(struct pi_desc *pi_desc, u64 *pold, u64 new)
void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
{
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vcpu_vt *vt = to_vt(vcpu);
struct pi_desc old, new;
unsigned long flags;
unsigned int dest;
@@ -71,13 +73,10 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
/*
* If the vCPU wasn't on the wakeup list and wasn't migrated, then the
* full update can be skipped as neither the vector nor the destination
- * needs to be changed.
+ * needs to be changed. Clear SN even if there is no assigned device,
+ * again for simplicity.
*/
if (pi_desc->nv != POSTED_INTR_WAKEUP_VECTOR && vcpu->cpu == cpu) {
- /*
- * Clear SN if it was set due to being preempted. Again, do
- * this even if there is no assigned device for simplicity.
- */
if (pi_test_and_clear_sn(pi_desc))
goto after_clear_sn;
return;
@@ -102,7 +101,7 @@ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu)
*/
raw_spin_lock(spinlock);
spin_acquire(&spinlock->dep_map, PI_LOCK_SCHED_OUT, 0, _RET_IP_);
- list_del(&vmx->pi_wakeup_list);
+ list_del(&vt->pi_wakeup_list);
spin_release(&spinlock->dep_map, _RET_IP_);
raw_spin_unlock(spinlock);
}
@@ -147,9 +146,13 @@ after_clear_sn:
static bool vmx_can_use_vtd_pi(struct kvm *kvm)
{
- return irqchip_in_kernel(kvm) && enable_apicv &&
- kvm_arch_has_assigned_device(kvm) &&
- irq_remapping_cap(IRQ_POSTING_CAP);
+ /*
+ * Note, reading the number of possible bypass IRQs can race with a
+ * bypass IRQ being attached to the VM. vmx_pi_start_bypass() ensures
+ * blockng vCPUs will see an elevated count or get KVM_REQ_UNBLOCK.
+ */
+ return irqchip_in_kernel(kvm) && kvm_arch_has_irq_bypass() &&
+ READ_ONCE(kvm->arch.nr_possible_bypass_irqs);
}
/*
@@ -159,7 +162,7 @@ static bool vmx_can_use_vtd_pi(struct kvm *kvm)
static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
{
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
- struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vcpu_vt *vt = to_vt(vcpu);
struct pi_desc old, new;
lockdep_assert_irqs_disabled();
@@ -178,7 +181,7 @@ static void pi_enable_wakeup_handler(struct kvm_vcpu *vcpu)
*/
raw_spin_lock_nested(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu),
PI_LOCK_SCHED_OUT);
- list_add_tail(&vmx->pi_wakeup_list,
+ list_add_tail(&vt->pi_wakeup_list,
&per_cpu(wakeup_vcpus_on_cpu, vcpu->cpu));
raw_spin_unlock(&per_cpu(wakeup_vcpus_on_cpu_lock, vcpu->cpu));
@@ -213,7 +216,8 @@ static bool vmx_needs_pi_wakeup(struct kvm_vcpu *vcpu)
* notification vector is switched to the one that calls
* back to the pi_wakeup_handler() function.
*/
- return vmx_can_use_ipiv(vcpu) || vmx_can_use_vtd_pi(vcpu->kvm);
+ return (vmx_can_use_ipiv(vcpu) && !is_td_vcpu(vcpu)) ||
+ vmx_can_use_vtd_pi(vcpu->kvm);
}
void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
@@ -223,15 +227,23 @@ void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu)
if (!vmx_needs_pi_wakeup(vcpu))
return;
- if (kvm_vcpu_is_blocking(vcpu) && !vmx_interrupt_blocked(vcpu))
- pi_enable_wakeup_handler(vcpu);
-
/*
- * Set SN when the vCPU is preempted. Note, the vCPU can both be seen
- * as blocking and preempted, e.g. if it's preempted between setting
- * its wait state and manually scheduling out.
+ * If the vCPU is blocking with IRQs enabled and ISN'T being preempted,
+ * enable the wakeup handler so that notification IRQ wakes the vCPU as
+ * expected. There is no need to enable the wakeup handler if the vCPU
+ * is preempted between setting its wait state and manually scheduling
+ * out, as the task is still runnable, i.e. doesn't need a wake event
+ * from KVM to be scheduled in.
+ *
+ * If the wakeup handler isn't being enabled, Suppress Notifications as
+ * the cost of propagating PIR.IRR to PID.ON is negligible compared to
+ * the cost of a spurious IRQ, and vCPU put/load is a slow path.
*/
- if (vcpu->preempted)
+ if (!vcpu->preempted && kvm_vcpu_is_blocking(vcpu) &&
+ ((is_td_vcpu(vcpu) && tdx_interrupt_allowed(vcpu)) ||
+ (!is_td_vcpu(vcpu) && !vmx_interrupt_blocked(vcpu))))
+ pi_enable_wakeup_handler(vcpu);
+ else
pi_set_sn(pi_desc);
}
@@ -243,13 +255,13 @@ void pi_wakeup_handler(void)
int cpu = smp_processor_id();
struct list_head *wakeup_list = &per_cpu(wakeup_vcpus_on_cpu, cpu);
raw_spinlock_t *spinlock = &per_cpu(wakeup_vcpus_on_cpu_lock, cpu);
- struct vcpu_vmx *vmx;
+ struct vcpu_vt *vt;
raw_spin_lock(spinlock);
- list_for_each_entry(vmx, wakeup_list, pi_wakeup_list) {
+ list_for_each_entry(vt, wakeup_list, pi_wakeup_list) {
- if (pi_test_on(&vmx->pi_desc))
- kvm_vcpu_wake_up(&vmx->vcpu);
+ if (pi_test_on(&vt->pi_desc))
+ kvm_vcpu_wake_up(vt_to_vcpu(vt));
}
raw_spin_unlock(spinlock);
}
@@ -260,6 +272,14 @@ void __init pi_init_cpu(int cpu)
raw_spin_lock_init(&per_cpu(wakeup_vcpus_on_cpu_lock, cpu));
}
+void pi_apicv_pre_state_restore(struct kvm_vcpu *vcpu)
+{
+ struct pi_desc *pi = vcpu_to_pi_desc(vcpu);
+
+ pi_clear_on(pi);
+ memset(pi->pir, 0, sizeof(pi->pir));
+}
+
bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
{
struct pi_desc *pi_desc = vcpu_to_pi_desc(vcpu);
@@ -270,99 +290,30 @@ bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu)
/*
- * Bail out of the block loop if the VM has an assigned
- * device, but the blocking vCPU didn't reconfigure the
- * PI.NV to the wakeup vector, i.e. the assigned device
- * came along after the initial check in vmx_vcpu_pi_put().
+ * Kick all vCPUs when the first possible bypass IRQ is attached to a VM, as
+ * blocking vCPUs may scheduled out without reconfiguring PID.NV to the wakeup
+ * vector, i.e. if the bypass IRQ came along after vmx_vcpu_pi_put().
*/
-void vmx_pi_start_assignment(struct kvm *kvm)
+void vmx_pi_start_bypass(struct kvm *kvm)
{
- if (!irq_remapping_cap(IRQ_POSTING_CAP))
+ if (WARN_ON_ONCE(!vmx_can_use_vtd_pi(kvm)))
return;
kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK);
}
-/*
- * vmx_pi_update_irte - set IRTE for Posted-Interrupts
- *
- * @kvm: kvm
- * @host_irq: host irq of the interrupt
- * @guest_irq: gsi of the interrupt
- * @set: set or unset PI
- * returns 0 on success, < 0 on failure
- */
-int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
- uint32_t guest_irq, bool set)
+int vmx_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+ unsigned int host_irq, uint32_t guest_irq,
+ struct kvm_vcpu *vcpu, u32 vector)
{
- struct kvm_kernel_irq_routing_entry *e;
- struct kvm_irq_routing_table *irq_rt;
- bool enable_remapped_mode = true;
- struct kvm_lapic_irq irq;
- struct kvm_vcpu *vcpu;
- struct vcpu_data vcpu_info;
- int idx, ret = 0;
-
- if (!vmx_can_use_vtd_pi(kvm))
- return 0;
-
- idx = srcu_read_lock(&kvm->irq_srcu);
- irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu);
- if (guest_irq >= irq_rt->nr_rt_entries ||
- hlist_empty(&irq_rt->map[guest_irq])) {
- pr_warn_once("no route for guest_irq %u/%u (broken user space?)\n",
- guest_irq, irq_rt->nr_rt_entries);
- goto out;
+ if (vcpu) {
+ struct intel_iommu_pi_data pi_data = {
+ .pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)),
+ .vector = vector,
+ };
+
+ return irq_set_vcpu_affinity(host_irq, &pi_data);
+ } else {
+ return irq_set_vcpu_affinity(host_irq, NULL);
}
-
- hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
- if (e->type != KVM_IRQ_ROUTING_MSI)
- continue;
- /*
- * VT-d PI cannot support posting multicast/broadcast
- * interrupts to a vCPU, we still use interrupt remapping
- * for these kind of interrupts.
- *
- * For lowest-priority interrupts, we only support
- * those with single CPU as the destination, e.g. user
- * configures the interrupts via /proc/irq or uses
- * irqbalance to make the interrupts single-CPU.
- *
- * We will support full lowest-priority interrupt later.
- *
- * In addition, we can only inject generic interrupts using
- * the PI mechanism, refuse to route others through it.
- */
-
- kvm_set_msi_irq(kvm, e, &irq);
- if (!kvm_intr_is_single_vcpu(kvm, &irq, &vcpu) ||
- !kvm_irq_is_postable(&irq))
- continue;
-
- vcpu_info.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu));
- vcpu_info.vector = irq.vector;
-
- trace_kvm_pi_irte_update(host_irq, vcpu->vcpu_id, e->gsi,
- vcpu_info.vector, vcpu_info.pi_desc_addr, set);
-
- if (!set)
- continue;
-
- enable_remapped_mode = false;
-
- ret = irq_set_vcpu_affinity(host_irq, &vcpu_info);
- if (ret < 0) {
- printk(KERN_INFO "%s: failed to update PI IRTE\n",
- __func__);
- goto out;
- }
- }
-
- if (enable_remapped_mode)
- ret = irq_set_vcpu_affinity(host_irq, NULL);
-
- ret = 0;
-out:
- srcu_read_unlock(&kvm->irq_srcu, idx);
- return ret;
}
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index ad9116a99bcc..a4af39948cf0 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -3,22 +3,27 @@
#define __KVM_X86_VMX_POSTED_INTR_H
#include <linux/bitmap.h>
+#include <linux/find.h>
+#include <linux/kvm_host.h>
+
#include <asm/posted_intr.h>
void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
void vmx_vcpu_pi_put(struct kvm_vcpu *vcpu);
void pi_wakeup_handler(void);
void __init pi_init_cpu(int cpu);
+void pi_apicv_pre_state_restore(struct kvm_vcpu *vcpu);
bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu);
-int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
- uint32_t guest_irq, bool set);
-void vmx_pi_start_assignment(struct kvm *kvm);
+int vmx_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+ unsigned int host_irq, uint32_t guest_irq,
+ struct kvm_vcpu *vcpu, u32 vector);
+void vmx_pi_start_bypass(struct kvm *kvm);
static inline int pi_find_highest_vector(struct pi_desc *pi_desc)
{
int vec;
- vec = find_last_bit((unsigned long *)pi_desc->pir, 256);
+ vec = find_last_bit(pi_desc->pir, 256);
return vec < 256 ? vec : -1;
}
diff --git a/arch/x86/kvm/vmx/run_flags.h b/arch/x86/kvm/vmx/run_flags.h
index 6a9bfdfbb6e5..2f20fb170def 100644
--- a/arch/x86/kvm/vmx/run_flags.h
+++ b/arch/x86/kvm/vmx/run_flags.h
@@ -2,10 +2,12 @@
#ifndef __KVM_X86_VMX_RUN_FLAGS_H
#define __KVM_X86_VMX_RUN_FLAGS_H
-#define VMX_RUN_VMRESUME_SHIFT 0
-#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1
+#define VMX_RUN_VMRESUME_SHIFT 0
+#define VMX_RUN_SAVE_SPEC_CTRL_SHIFT 1
+#define VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO_SHIFT 2
-#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT)
-#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT)
+#define VMX_RUN_VMRESUME BIT(VMX_RUN_VMRESUME_SHIFT)
+#define VMX_RUN_SAVE_SPEC_CTRL BIT(VMX_RUN_SAVE_SPEC_CTRL_SHIFT)
+#define VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO BIT(VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO_SHIFT)
#endif /* __KVM_X86_VMX_RUN_FLAGS_H */
diff --git a/arch/x86/kvm/vmx/sgx.c b/arch/x86/kvm/vmx/sgx.c
index 9961e07cf071..df1d0cf76947 100644
--- a/arch/x86/kvm/vmx/sgx.c
+++ b/arch/x86/kvm/vmx/sgx.c
@@ -2,6 +2,7 @@
/* Copyright(c) 2021 Intel Corporation. */
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#include <asm/msr.h>
#include <asm/sgx.h>
#include "x86.h"
@@ -411,16 +412,16 @@ void setup_default_sgx_lepubkeyhash(void)
* MSRs exist but are read-only (locked and not writable).
*/
if (!enable_sgx || boot_cpu_has(X86_FEATURE_SGX_LC) ||
- rdmsrl_safe(MSR_IA32_SGXLEPUBKEYHASH0, &sgx_pubkey_hash[0])) {
+ rdmsrq_safe(MSR_IA32_SGXLEPUBKEYHASH0, &sgx_pubkey_hash[0])) {
sgx_pubkey_hash[0] = 0xa6053e051270b7acULL;
sgx_pubkey_hash[1] = 0x6cfbe8ba8b3b413dULL;
sgx_pubkey_hash[2] = 0xc4916d99f2b3735dULL;
sgx_pubkey_hash[3] = 0xd4f8c05909f9bb3bULL;
} else {
/* MSR_IA32_SGXLEPUBKEYHASH0 is read above */
- rdmsrl(MSR_IA32_SGXLEPUBKEYHASH1, sgx_pubkey_hash[1]);
- rdmsrl(MSR_IA32_SGXLEPUBKEYHASH2, sgx_pubkey_hash[2]);
- rdmsrl(MSR_IA32_SGXLEPUBKEYHASH3, sgx_pubkey_hash[3]);
+ rdmsrq(MSR_IA32_SGXLEPUBKEYHASH1, sgx_pubkey_hash[1]);
+ rdmsrq(MSR_IA32_SGXLEPUBKEYHASH2, sgx_pubkey_hash[2]);
+ rdmsrq(MSR_IA32_SGXLEPUBKEYHASH3, sgx_pubkey_hash[3]);
}
}
diff --git a/arch/x86/kvm/vmx/tdx.c b/arch/x86/kvm/vmx/tdx.c
new file mode 100644
index 000000000000..66744f5768c8
--- /dev/null
+++ b/arch/x86/kvm/vmx/tdx.c
@@ -0,0 +1,3643 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/cleanup.h>
+#include <linux/cpu.h>
+#include <asm/cpufeature.h>
+#include <asm/fpu/xcr.h>
+#include <linux/misc_cgroup.h>
+#include <linux/mmu_context.h>
+#include <asm/tdx.h>
+#include "capabilities.h"
+#include "mmu.h"
+#include "x86_ops.h"
+#include "lapic.h"
+#include "tdx.h"
+#include "vmx.h"
+#include "mmu/spte.h"
+#include "common.h"
+#include "posted_intr.h"
+#include "irq.h"
+#include <trace/events/kvm.h>
+#include "trace.h"
+
+#pragma GCC poison to_vmx
+
+#undef pr_fmt
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#define pr_tdx_error(__fn, __err) \
+ pr_err_ratelimited("SEAMCALL %s failed: 0x%llx\n", #__fn, __err)
+
+#define __pr_tdx_error_N(__fn_str, __err, __fmt, ...) \
+ pr_err_ratelimited("SEAMCALL " __fn_str " failed: 0x%llx, " __fmt, __err, __VA_ARGS__)
+
+#define pr_tdx_error_1(__fn, __err, __rcx) \
+ __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx\n", __rcx)
+
+#define pr_tdx_error_2(__fn, __err, __rcx, __rdx) \
+ __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx, rdx 0x%llx\n", __rcx, __rdx)
+
+#define pr_tdx_error_3(__fn, __err, __rcx, __rdx, __r8) \
+ __pr_tdx_error_N(#__fn, __err, "rcx 0x%llx, rdx 0x%llx, r8 0x%llx\n", __rcx, __rdx, __r8)
+
+bool enable_tdx __ro_after_init;
+module_param_named(tdx, enable_tdx, bool, 0444);
+
+#define TDX_SHARED_BIT_PWL_5 gpa_to_gfn(BIT_ULL(51))
+#define TDX_SHARED_BIT_PWL_4 gpa_to_gfn(BIT_ULL(47))
+
+static enum cpuhp_state tdx_cpuhp_state;
+
+static const struct tdx_sys_info *tdx_sysinfo;
+
+void tdh_vp_rd_failed(struct vcpu_tdx *tdx, char *uclass, u32 field, u64 err)
+{
+ KVM_BUG_ON(1, tdx->vcpu.kvm);
+ pr_err("TDH_VP_RD[%s.0x%x] failed 0x%llx\n", uclass, field, err);
+}
+
+void tdh_vp_wr_failed(struct vcpu_tdx *tdx, char *uclass, char *op, u32 field,
+ u64 val, u64 err)
+{
+ KVM_BUG_ON(1, tdx->vcpu.kvm);
+ pr_err("TDH_VP_WR[%s.0x%x]%s0x%llx failed: 0x%llx\n", uclass, field, op, val, err);
+}
+
+#define KVM_SUPPORTED_TD_ATTRS (TDX_TD_ATTR_SEPT_VE_DISABLE)
+
+static __always_inline struct kvm_tdx *to_kvm_tdx(struct kvm *kvm)
+{
+ return container_of(kvm, struct kvm_tdx, kvm);
+}
+
+static __always_inline struct vcpu_tdx *to_tdx(struct kvm_vcpu *vcpu)
+{
+ return container_of(vcpu, struct vcpu_tdx, vcpu);
+}
+
+static u64 tdx_get_supported_attrs(const struct tdx_sys_info_td_conf *td_conf)
+{
+ u64 val = KVM_SUPPORTED_TD_ATTRS;
+
+ if ((val & td_conf->attributes_fixed1) != td_conf->attributes_fixed1)
+ return 0;
+
+ val &= td_conf->attributes_fixed0;
+
+ return val;
+}
+
+static u64 tdx_get_supported_xfam(const struct tdx_sys_info_td_conf *td_conf)
+{
+ u64 val = kvm_caps.supported_xcr0 | kvm_caps.supported_xss;
+
+ if ((val & td_conf->xfam_fixed1) != td_conf->xfam_fixed1)
+ return 0;
+
+ val &= td_conf->xfam_fixed0;
+
+ return val;
+}
+
+static int tdx_get_guest_phys_addr_bits(const u32 eax)
+{
+ return (eax & GENMASK(23, 16)) >> 16;
+}
+
+static u32 tdx_set_guest_phys_addr_bits(const u32 eax, int addr_bits)
+{
+ return (eax & ~GENMASK(23, 16)) | (addr_bits & 0xff) << 16;
+}
+
+#define TDX_FEATURE_TSX (__feature_bit(X86_FEATURE_HLE) | __feature_bit(X86_FEATURE_RTM))
+
+static bool has_tsx(const struct kvm_cpuid_entry2 *entry)
+{
+ return entry->function == 7 && entry->index == 0 &&
+ (entry->ebx & TDX_FEATURE_TSX);
+}
+
+static void clear_tsx(struct kvm_cpuid_entry2 *entry)
+{
+ entry->ebx &= ~TDX_FEATURE_TSX;
+}
+
+static bool has_waitpkg(const struct kvm_cpuid_entry2 *entry)
+{
+ return entry->function == 7 && entry->index == 0 &&
+ (entry->ecx & __feature_bit(X86_FEATURE_WAITPKG));
+}
+
+static void clear_waitpkg(struct kvm_cpuid_entry2 *entry)
+{
+ entry->ecx &= ~__feature_bit(X86_FEATURE_WAITPKG);
+}
+
+static void tdx_clear_unsupported_cpuid(struct kvm_cpuid_entry2 *entry)
+{
+ if (has_tsx(entry))
+ clear_tsx(entry);
+
+ if (has_waitpkg(entry))
+ clear_waitpkg(entry);
+}
+
+static bool tdx_unsupported_cpuid(const struct kvm_cpuid_entry2 *entry)
+{
+ return has_tsx(entry) || has_waitpkg(entry);
+}
+
+#define KVM_TDX_CPUID_NO_SUBLEAF ((__u32)-1)
+
+static void td_init_cpuid_entry2(struct kvm_cpuid_entry2 *entry, unsigned char idx)
+{
+ const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf;
+
+ entry->function = (u32)td_conf->cpuid_config_leaves[idx];
+ entry->index = td_conf->cpuid_config_leaves[idx] >> 32;
+ entry->eax = (u32)td_conf->cpuid_config_values[idx][0];
+ entry->ebx = td_conf->cpuid_config_values[idx][0] >> 32;
+ entry->ecx = (u32)td_conf->cpuid_config_values[idx][1];
+ entry->edx = td_conf->cpuid_config_values[idx][1] >> 32;
+
+ if (entry->index == KVM_TDX_CPUID_NO_SUBLEAF)
+ entry->index = 0;
+
+ /*
+ * The TDX module doesn't allow configuring the guest phys addr bits
+ * (EAX[23:16]). However, KVM uses it as an interface to the userspace
+ * to configure the GPAW. Report these bits as configurable.
+ */
+ if (entry->function == 0x80000008)
+ entry->eax = tdx_set_guest_phys_addr_bits(entry->eax, 0xff);
+
+ tdx_clear_unsupported_cpuid(entry);
+}
+
+#define TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT BIT(1)
+
+static int init_kvm_tdx_caps(const struct tdx_sys_info_td_conf *td_conf,
+ struct kvm_tdx_capabilities *caps)
+{
+ int i;
+
+ caps->supported_attrs = tdx_get_supported_attrs(td_conf);
+ if (!caps->supported_attrs)
+ return -EIO;
+
+ caps->supported_xfam = tdx_get_supported_xfam(td_conf);
+ if (!caps->supported_xfam)
+ return -EIO;
+
+ caps->cpuid.nent = td_conf->num_cpuid_config;
+
+ caps->user_tdvmcallinfo_1_r11 =
+ TDVMCALLINFO_SETUP_EVENT_NOTIFY_INTERRUPT;
+
+ for (i = 0; i < td_conf->num_cpuid_config; i++)
+ td_init_cpuid_entry2(&caps->cpuid.entries[i], i);
+
+ return 0;
+}
+
+/*
+ * Some SEAMCALLs acquire the TDX module globally, and can fail with
+ * TDX_OPERAND_BUSY. Use a global mutex to serialize these SEAMCALLs.
+ */
+static DEFINE_MUTEX(tdx_lock);
+
+static atomic_t nr_configured_hkid;
+
+static bool tdx_operand_busy(u64 err)
+{
+ return (err & TDX_SEAMCALL_STATUS_MASK) == TDX_OPERAND_BUSY;
+}
+
+
+/*
+ * A per-CPU list of TD vCPUs associated with a given CPU.
+ * Protected by interrupt mask. Only manipulated by the CPU owning this per-CPU
+ * list.
+ * - When a vCPU is loaded onto a CPU, it is removed from the per-CPU list of
+ * the old CPU during the IPI callback running on the old CPU, and then added
+ * to the per-CPU list of the new CPU.
+ * - When a TD is tearing down, all vCPUs are disassociated from their current
+ * running CPUs and removed from the per-CPU list during the IPI callback
+ * running on those CPUs.
+ * - When a CPU is brought down, traverse the per-CPU list to disassociate all
+ * associated TD vCPUs and remove them from the per-CPU list.
+ */
+static DEFINE_PER_CPU(struct list_head, associated_tdvcpus);
+
+static __always_inline unsigned long tdvmcall_exit_type(struct kvm_vcpu *vcpu)
+{
+ return to_tdx(vcpu)->vp_enter_args.r10;
+}
+
+static __always_inline unsigned long tdvmcall_leaf(struct kvm_vcpu *vcpu)
+{
+ return to_tdx(vcpu)->vp_enter_args.r11;
+}
+
+static __always_inline void tdvmcall_set_return_code(struct kvm_vcpu *vcpu,
+ long val)
+{
+ to_tdx(vcpu)->vp_enter_args.r10 = val;
+}
+
+static __always_inline void tdvmcall_set_return_val(struct kvm_vcpu *vcpu,
+ unsigned long val)
+{
+ to_tdx(vcpu)->vp_enter_args.r11 = val;
+}
+
+static inline void tdx_hkid_free(struct kvm_tdx *kvm_tdx)
+{
+ tdx_guest_keyid_free(kvm_tdx->hkid);
+ kvm_tdx->hkid = -1;
+ atomic_dec(&nr_configured_hkid);
+ misc_cg_uncharge(MISC_CG_RES_TDX, kvm_tdx->misc_cg, 1);
+ put_misc_cg(kvm_tdx->misc_cg);
+ kvm_tdx->misc_cg = NULL;
+}
+
+static inline bool is_hkid_assigned(struct kvm_tdx *kvm_tdx)
+{
+ return kvm_tdx->hkid > 0;
+}
+
+static inline void tdx_disassociate_vp(struct kvm_vcpu *vcpu)
+{
+ lockdep_assert_irqs_disabled();
+
+ list_del(&to_tdx(vcpu)->cpu_list);
+
+ /*
+ * Ensure tdx->cpu_list is updated before setting vcpu->cpu to -1,
+ * otherwise, a different CPU can see vcpu->cpu = -1 and add the vCPU
+ * to its list before it's deleted from this CPU's list.
+ */
+ smp_wmb();
+
+ vcpu->cpu = -1;
+}
+
+static void tdx_clear_page(struct page *page)
+{
+ const void *zero_page = (const void *) page_to_virt(ZERO_PAGE(0));
+ void *dest = page_to_virt(page);
+ unsigned long i;
+
+ /*
+ * The page could have been poisoned. MOVDIR64B also clears
+ * the poison bit so the kernel can safely use the page again.
+ */
+ for (i = 0; i < PAGE_SIZE; i += 64)
+ movdir64b(dest + i, zero_page);
+ /*
+ * MOVDIR64B store uses WC buffer. Prevent following memory reads
+ * from seeing potentially poisoned cache.
+ */
+ __mb();
+}
+
+static void tdx_no_vcpus_enter_start(struct kvm *kvm)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ WRITE_ONCE(kvm_tdx->wait_for_sept_zap, true);
+
+ kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE);
+}
+
+static void tdx_no_vcpus_enter_stop(struct kvm *kvm)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ WRITE_ONCE(kvm_tdx->wait_for_sept_zap, false);
+}
+
+/* TDH.PHYMEM.PAGE.RECLAIM is allowed only when destroying the TD. */
+static int __tdx_reclaim_page(struct page *page)
+{
+ u64 err, rcx, rdx, r8;
+
+ err = tdh_phymem_page_reclaim(page, &rcx, &rdx, &r8);
+
+ /*
+ * No need to check for TDX_OPERAND_BUSY; all TD pages are freed
+ * before the HKID is released and control pages have also been
+ * released at this point, so there is no possibility of contention.
+ */
+ if (WARN_ON_ONCE(err)) {
+ pr_tdx_error_3(TDH_PHYMEM_PAGE_RECLAIM, err, rcx, rdx, r8);
+ return -EIO;
+ }
+ return 0;
+}
+
+static int tdx_reclaim_page(struct page *page)
+{
+ int r;
+
+ r = __tdx_reclaim_page(page);
+ if (!r)
+ tdx_clear_page(page);
+ return r;
+}
+
+
+/*
+ * Reclaim the TD control page(s) which are crypto-protected by TDX guest's
+ * private KeyID. Assume the cache associated with the TDX private KeyID has
+ * been flushed.
+ */
+static void tdx_reclaim_control_page(struct page *ctrl_page)
+{
+ /*
+ * Leak the page if the kernel failed to reclaim the page.
+ * The kernel cannot use it safely anymore.
+ */
+ if (tdx_reclaim_page(ctrl_page))
+ return;
+
+ __free_page(ctrl_page);
+}
+
+struct tdx_flush_vp_arg {
+ struct kvm_vcpu *vcpu;
+ u64 err;
+};
+
+static void tdx_flush_vp(void *_arg)
+{
+ struct tdx_flush_vp_arg *arg = _arg;
+ struct kvm_vcpu *vcpu = arg->vcpu;
+ u64 err;
+
+ arg->err = 0;
+ lockdep_assert_irqs_disabled();
+
+ /* Task migration can race with CPU offlining. */
+ if (unlikely(vcpu->cpu != raw_smp_processor_id()))
+ return;
+
+ /*
+ * No need to do TDH_VP_FLUSH if the vCPU hasn't been initialized. The
+ * list tracking still needs to be updated so that it's correct if/when
+ * the vCPU does get initialized.
+ */
+ if (to_tdx(vcpu)->state != VCPU_TD_STATE_UNINITIALIZED) {
+ /*
+ * No need to retry. TDX Resources needed for TDH.VP.FLUSH are:
+ * TDVPR as exclusive, TDR as shared, and TDCS as shared. This
+ * vp flush function is called when destructing vCPU/TD or vCPU
+ * migration. No other thread uses TDVPR in those cases.
+ */
+ err = tdh_vp_flush(&to_tdx(vcpu)->vp);
+ if (unlikely(err && err != TDX_VCPU_NOT_ASSOCIATED)) {
+ /*
+ * This function is called in IPI context. Do not use
+ * printk to avoid console semaphore.
+ * The caller prints out the error message, instead.
+ */
+ if (err)
+ arg->err = err;
+ }
+ }
+
+ tdx_disassociate_vp(vcpu);
+}
+
+static void tdx_flush_vp_on_cpu(struct kvm_vcpu *vcpu)
+{
+ struct tdx_flush_vp_arg arg = {
+ .vcpu = vcpu,
+ };
+ int cpu = vcpu->cpu;
+
+ if (unlikely(cpu == -1))
+ return;
+
+ smp_call_function_single(cpu, tdx_flush_vp, &arg, 1);
+ if (KVM_BUG_ON(arg.err, vcpu->kvm))
+ pr_tdx_error(TDH_VP_FLUSH, arg.err);
+}
+
+void tdx_disable_virtualization_cpu(void)
+{
+ int cpu = raw_smp_processor_id();
+ struct list_head *tdvcpus = &per_cpu(associated_tdvcpus, cpu);
+ struct tdx_flush_vp_arg arg;
+ struct vcpu_tdx *tdx, *tmp;
+ unsigned long flags;
+
+ local_irq_save(flags);
+ /* Safe variant needed as tdx_disassociate_vp() deletes the entry. */
+ list_for_each_entry_safe(tdx, tmp, tdvcpus, cpu_list) {
+ arg.vcpu = &tdx->vcpu;
+ tdx_flush_vp(&arg);
+ }
+ local_irq_restore(flags);
+}
+
+#define TDX_SEAMCALL_RETRIES 10000
+
+static void smp_func_do_phymem_cache_wb(void *unused)
+{
+ u64 err = 0;
+ bool resume;
+ int i;
+
+ /*
+ * TDH.PHYMEM.CACHE.WB flushes caches associated with any TDX private
+ * KeyID on the package or core. The TDX module may not finish the
+ * cache flush but return TDX_INTERRUPTED_RESUMEABLE instead. The
+ * kernel should retry it until it returns success w/o rescheduling.
+ */
+ for (i = TDX_SEAMCALL_RETRIES; i > 0; i--) {
+ resume = !!err;
+ err = tdh_phymem_cache_wb(resume);
+ switch (err) {
+ case TDX_INTERRUPTED_RESUMABLE:
+ continue;
+ case TDX_NO_HKID_READY_TO_WBCACHE:
+ err = TDX_SUCCESS; /* Already done by other thread */
+ fallthrough;
+ default:
+ goto out;
+ }
+ }
+
+out:
+ if (WARN_ON_ONCE(err))
+ pr_tdx_error(TDH_PHYMEM_CACHE_WB, err);
+}
+
+void tdx_mmu_release_hkid(struct kvm *kvm)
+{
+ bool packages_allocated, targets_allocated;
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ cpumask_var_t packages, targets;
+ struct kvm_vcpu *vcpu;
+ unsigned long j;
+ int i;
+ u64 err;
+
+ if (!is_hkid_assigned(kvm_tdx))
+ return;
+
+ packages_allocated = zalloc_cpumask_var(&packages, GFP_KERNEL);
+ targets_allocated = zalloc_cpumask_var(&targets, GFP_KERNEL);
+ cpus_read_lock();
+
+ kvm_for_each_vcpu(j, vcpu, kvm)
+ tdx_flush_vp_on_cpu(vcpu);
+
+ /*
+ * TDH.PHYMEM.CACHE.WB tries to acquire the TDX module global lock
+ * and can fail with TDX_OPERAND_BUSY when it fails to get the lock.
+ * Multiple TDX guests can be destroyed simultaneously. Take the
+ * mutex to prevent it from getting error.
+ */
+ mutex_lock(&tdx_lock);
+
+ /*
+ * Releasing HKID is in vm_destroy().
+ * After the above flushing vps, there should be no more vCPU
+ * associations, as all vCPU fds have been released at this stage.
+ */
+ err = tdh_mng_vpflushdone(&kvm_tdx->td);
+ if (err == TDX_FLUSHVP_NOT_DONE)
+ goto out;
+ if (KVM_BUG_ON(err, kvm)) {
+ pr_tdx_error(TDH_MNG_VPFLUSHDONE, err);
+ pr_err("tdh_mng_vpflushdone() failed. HKID %d is leaked.\n",
+ kvm_tdx->hkid);
+ goto out;
+ }
+
+ for_each_online_cpu(i) {
+ if (packages_allocated &&
+ cpumask_test_and_set_cpu(topology_physical_package_id(i),
+ packages))
+ continue;
+ if (targets_allocated)
+ cpumask_set_cpu(i, targets);
+ }
+ if (targets_allocated)
+ on_each_cpu_mask(targets, smp_func_do_phymem_cache_wb, NULL, true);
+ else
+ on_each_cpu(smp_func_do_phymem_cache_wb, NULL, true);
+ /*
+ * In the case of error in smp_func_do_phymem_cache_wb(), the following
+ * tdh_mng_key_freeid() will fail.
+ */
+ err = tdh_mng_key_freeid(&kvm_tdx->td);
+ if (KVM_BUG_ON(err, kvm)) {
+ pr_tdx_error(TDH_MNG_KEY_FREEID, err);
+ pr_err("tdh_mng_key_freeid() failed. HKID %d is leaked.\n",
+ kvm_tdx->hkid);
+ } else {
+ tdx_hkid_free(kvm_tdx);
+ }
+
+out:
+ mutex_unlock(&tdx_lock);
+ cpus_read_unlock();
+ free_cpumask_var(targets);
+ free_cpumask_var(packages);
+}
+
+static void tdx_reclaim_td_control_pages(struct kvm *kvm)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ u64 err;
+ int i;
+
+ /*
+ * tdx_mmu_release_hkid() failed to reclaim HKID. Something went wrong
+ * heavily with TDX module. Give up freeing TD pages. As the function
+ * already warned, don't warn it again.
+ */
+ if (is_hkid_assigned(kvm_tdx))
+ return;
+
+ if (kvm_tdx->td.tdcs_pages) {
+ for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) {
+ if (!kvm_tdx->td.tdcs_pages[i])
+ continue;
+
+ tdx_reclaim_control_page(kvm_tdx->td.tdcs_pages[i]);
+ }
+ kfree(kvm_tdx->td.tdcs_pages);
+ kvm_tdx->td.tdcs_pages = NULL;
+ }
+
+ if (!kvm_tdx->td.tdr_page)
+ return;
+
+ if (__tdx_reclaim_page(kvm_tdx->td.tdr_page))
+ return;
+
+ /*
+ * Use a SEAMCALL to ask the TDX module to flush the cache based on the
+ * KeyID. TDX module may access TDR while operating on TD (Especially
+ * when it is reclaiming TDCS).
+ */
+ err = tdh_phymem_page_wbinvd_tdr(&kvm_tdx->td);
+ if (KVM_BUG_ON(err, kvm)) {
+ pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err);
+ return;
+ }
+ tdx_clear_page(kvm_tdx->td.tdr_page);
+
+ __free_page(kvm_tdx->td.tdr_page);
+ kvm_tdx->td.tdr_page = NULL;
+}
+
+void tdx_vm_destroy(struct kvm *kvm)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+ tdx_reclaim_td_control_pages(kvm);
+
+ kvm_tdx->state = TD_STATE_UNINITIALIZED;
+}
+
+static int tdx_do_tdh_mng_key_config(void *param)
+{
+ struct kvm_tdx *kvm_tdx = param;
+ u64 err;
+
+ /* TDX_RND_NO_ENTROPY related retries are handled by sc_retry() */
+ err = tdh_mng_key_config(&kvm_tdx->td);
+
+ if (KVM_BUG_ON(err, &kvm_tdx->kvm)) {
+ pr_tdx_error(TDH_MNG_KEY_CONFIG, err);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+int tdx_vm_init(struct kvm *kvm)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+ kvm->arch.has_protected_state = true;
+ kvm->arch.has_private_mem = true;
+ kvm->arch.disabled_quirks |= KVM_X86_QUIRK_IGNORE_GUEST_PAT;
+
+ /*
+ * Because guest TD is protected, VMM can't parse the instruction in TD.
+ * Instead, guest uses MMIO hypercall. For unmodified device driver,
+ * #VE needs to be injected for MMIO and #VE handler in TD converts MMIO
+ * instruction into MMIO hypercall.
+ *
+ * SPTE value for MMIO needs to be setup so that #VE is injected into
+ * TD instead of triggering EPT MISCONFIG.
+ * - RWX=0 so that EPT violation is triggered.
+ * - suppress #VE bit is cleared to inject #VE.
+ */
+ kvm_mmu_set_mmio_spte_value(kvm, 0);
+
+ /*
+ * TDX has its own limit of maximum vCPUs it can support for all
+ * TDX guests in addition to KVM_MAX_VCPUS. TDX module reports
+ * such limit via the MAX_VCPU_PER_TD global metadata. In
+ * practice, it reflects the number of logical CPUs that ALL
+ * platforms that the TDX module supports can possibly have.
+ *
+ * Limit TDX guest's maximum vCPUs to the number of logical CPUs
+ * the platform has. Simply forwarding the MAX_VCPU_PER_TD to
+ * userspace would result in an unpredictable ABI.
+ */
+ kvm->max_vcpus = min_t(int, kvm->max_vcpus, num_present_cpus());
+
+ kvm_tdx->state = TD_STATE_UNINITIALIZED;
+
+ return 0;
+}
+
+int tdx_vcpu_create(struct kvm_vcpu *vcpu)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+ if (kvm_tdx->state != TD_STATE_INITIALIZED)
+ return -EIO;
+
+ /*
+ * TDX module mandates APICv, which requires an in-kernel local APIC.
+ * Disallow an in-kernel I/O APIC, because level-triggered interrupts
+ * and thus the I/O APIC as a whole can't be faithfully emulated in KVM.
+ */
+ if (!irqchip_split(vcpu->kvm))
+ return -EINVAL;
+
+ fpstate_set_confidential(&vcpu->arch.guest_fpu);
+ vcpu->arch.apic->guest_apic_protected = true;
+ INIT_LIST_HEAD(&tdx->vt.pi_wakeup_list);
+
+ vcpu->arch.efer = EFER_SCE | EFER_LME | EFER_LMA | EFER_NX;
+
+ vcpu->arch.switch_db_regs = KVM_DEBUGREG_AUTO_SWITCH;
+ vcpu->arch.cr0_guest_owned_bits = -1ul;
+ vcpu->arch.cr4_guest_owned_bits = -1ul;
+
+ /* KVM can't change TSC offset/multiplier as TDX module manages them. */
+ vcpu->arch.guest_tsc_protected = true;
+ vcpu->arch.tsc_offset = kvm_tdx->tsc_offset;
+ vcpu->arch.l1_tsc_offset = vcpu->arch.tsc_offset;
+ vcpu->arch.tsc_scaling_ratio = kvm_tdx->tsc_multiplier;
+ vcpu->arch.l1_tsc_scaling_ratio = kvm_tdx->tsc_multiplier;
+
+ vcpu->arch.guest_state_protected =
+ !(to_kvm_tdx(vcpu->kvm)->attributes & TDX_TD_ATTR_DEBUG);
+
+ if ((kvm_tdx->xfam & XFEATURE_MASK_XTILE) == XFEATURE_MASK_XTILE)
+ vcpu->arch.xfd_no_write_intercept = true;
+
+ tdx->vt.pi_desc.nv = POSTED_INTR_VECTOR;
+ __pi_set_sn(&tdx->vt.pi_desc);
+
+ tdx->state = VCPU_TD_STATE_UNINITIALIZED;
+
+ return 0;
+}
+
+void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+ vmx_vcpu_pi_load(vcpu, cpu);
+ if (vcpu->cpu == cpu || !is_hkid_assigned(to_kvm_tdx(vcpu->kvm)))
+ return;
+
+ tdx_flush_vp_on_cpu(vcpu);
+
+ KVM_BUG_ON(cpu != raw_smp_processor_id(), vcpu->kvm);
+ local_irq_disable();
+ /*
+ * Pairs with the smp_wmb() in tdx_disassociate_vp() to ensure
+ * vcpu->cpu is read before tdx->cpu_list.
+ */
+ smp_rmb();
+
+ list_add(&tdx->cpu_list, &per_cpu(associated_tdvcpus, cpu));
+ local_irq_enable();
+}
+
+bool tdx_interrupt_allowed(struct kvm_vcpu *vcpu)
+{
+ /*
+ * KVM can't get the interrupt status of TDX guest and it assumes
+ * interrupt is always allowed unless TDX guest calls TDVMCALL with HLT,
+ * which passes the interrupt blocked flag.
+ */
+ return vmx_get_exit_reason(vcpu).basic != EXIT_REASON_HLT ||
+ !to_tdx(vcpu)->vp_enter_args.r12;
+}
+
+static bool tdx_protected_apic_has_interrupt(struct kvm_vcpu *vcpu)
+{
+ u64 vcpu_state_details;
+
+ if (pi_has_pending_interrupt(vcpu))
+ return true;
+
+ /*
+ * Only check RVI pending for HALTED case with IRQ enabled.
+ * For non-HLT cases, KVM doesn't care about STI/SS shadows. And if the
+ * interrupt was pending before TD exit, then it _must_ be blocked,
+ * otherwise the interrupt would have been serviced at the instruction
+ * boundary.
+ */
+ if (vmx_get_exit_reason(vcpu).basic != EXIT_REASON_HLT ||
+ to_tdx(vcpu)->vp_enter_args.r12)
+ return false;
+
+ vcpu_state_details =
+ td_state_non_arch_read64(to_tdx(vcpu), TD_VCPU_STATE_DETAILS_NON_ARCH);
+
+ return tdx_vcpu_state_details_intr_pending(vcpu_state_details);
+}
+
+/*
+ * Compared to vmx_prepare_switch_to_guest(), there is not much to do
+ * as SEAMCALL/SEAMRET calls take care of most of save and restore.
+ */
+void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vt *vt = to_vt(vcpu);
+
+ if (vt->guest_state_loaded)
+ return;
+
+ if (likely(is_64bit_mm(current->mm)))
+ vt->msr_host_kernel_gs_base = current->thread.gsbase;
+ else
+ vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
+
+ vt->guest_state_loaded = true;
+}
+
+struct tdx_uret_msr {
+ u32 msr;
+ unsigned int slot;
+ u64 defval;
+};
+
+static struct tdx_uret_msr tdx_uret_msrs[] = {
+ {.msr = MSR_SYSCALL_MASK, .defval = 0x20200 },
+ {.msr = MSR_STAR,},
+ {.msr = MSR_LSTAR,},
+ {.msr = MSR_TSC_AUX,},
+};
+
+static void tdx_user_return_msr_update_cache(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(tdx_uret_msrs); i++)
+ kvm_user_return_msr_update_cache(tdx_uret_msrs[i].slot,
+ tdx_uret_msrs[i].defval);
+}
+
+static void tdx_prepare_switch_to_host(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vt *vt = to_vt(vcpu);
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+ if (!vt->guest_state_loaded)
+ return;
+
+ ++vcpu->stat.host_state_reload;
+ wrmsrl(MSR_KERNEL_GS_BASE, vt->msr_host_kernel_gs_base);
+
+ if (tdx->guest_entered) {
+ tdx_user_return_msr_update_cache();
+ tdx->guest_entered = false;
+ }
+
+ vt->guest_state_loaded = false;
+}
+
+void tdx_vcpu_put(struct kvm_vcpu *vcpu)
+{
+ vmx_vcpu_pi_put(vcpu);
+ tdx_prepare_switch_to_host(vcpu);
+}
+
+void tdx_vcpu_free(struct kvm_vcpu *vcpu)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ int i;
+
+ /*
+ * It is not possible to reclaim pages while hkid is assigned. It might
+ * be assigned if:
+ * 1. the TD VM is being destroyed but freeing hkid failed, in which
+ * case the pages are leaked
+ * 2. TD VCPU creation failed and this on the error path, in which case
+ * there is nothing to do anyway
+ */
+ if (is_hkid_assigned(kvm_tdx))
+ return;
+
+ if (tdx->vp.tdcx_pages) {
+ for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) {
+ if (tdx->vp.tdcx_pages[i])
+ tdx_reclaim_control_page(tdx->vp.tdcx_pages[i]);
+ }
+ kfree(tdx->vp.tdcx_pages);
+ tdx->vp.tdcx_pages = NULL;
+ }
+ if (tdx->vp.tdvpr_page) {
+ tdx_reclaim_control_page(tdx->vp.tdvpr_page);
+ tdx->vp.tdvpr_page = 0;
+ }
+
+ tdx->state = VCPU_TD_STATE_UNINITIALIZED;
+}
+
+int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu)
+{
+ if (unlikely(to_tdx(vcpu)->state != VCPU_TD_STATE_INITIALIZED ||
+ to_kvm_tdx(vcpu->kvm)->state != TD_STATE_RUNNABLE))
+ return -EINVAL;
+
+ return 1;
+}
+
+static __always_inline u32 tdcall_to_vmx_exit_reason(struct kvm_vcpu *vcpu)
+{
+ switch (tdvmcall_leaf(vcpu)) {
+ case EXIT_REASON_CPUID:
+ case EXIT_REASON_HLT:
+ case EXIT_REASON_IO_INSTRUCTION:
+ case EXIT_REASON_MSR_READ:
+ case EXIT_REASON_MSR_WRITE:
+ return tdvmcall_leaf(vcpu);
+ case EXIT_REASON_EPT_VIOLATION:
+ return EXIT_REASON_EPT_MISCONFIG;
+ default:
+ break;
+ }
+
+ return EXIT_REASON_TDCALL;
+}
+
+static __always_inline u32 tdx_to_vmx_exit_reason(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ u32 exit_reason;
+
+ switch (tdx->vp_enter_ret & TDX_SEAMCALL_STATUS_MASK) {
+ case TDX_SUCCESS:
+ case TDX_NON_RECOVERABLE_VCPU:
+ case TDX_NON_RECOVERABLE_TD:
+ case TDX_NON_RECOVERABLE_TD_NON_ACCESSIBLE:
+ case TDX_NON_RECOVERABLE_TD_WRONG_APIC_MODE:
+ break;
+ default:
+ return -1u;
+ }
+
+ exit_reason = tdx->vp_enter_ret;
+
+ switch (exit_reason) {
+ case EXIT_REASON_TDCALL:
+ if (tdvmcall_exit_type(vcpu))
+ return EXIT_REASON_VMCALL;
+
+ return tdcall_to_vmx_exit_reason(vcpu);
+ case EXIT_REASON_EPT_MISCONFIG:
+ /*
+ * Defer KVM_BUG_ON() until tdx_handle_exit() because this is in
+ * non-instrumentable code with interrupts disabled.
+ */
+ return -1u;
+ default:
+ break;
+ }
+
+ return exit_reason;
+}
+
+static noinstr void tdx_vcpu_enter_exit(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ struct vcpu_vt *vt = to_vt(vcpu);
+
+ guest_state_enter_irqoff();
+
+ tdx->vp_enter_ret = tdh_vp_enter(&tdx->vp, &tdx->vp_enter_args);
+
+ vt->exit_reason.full = tdx_to_vmx_exit_reason(vcpu);
+
+ vt->exit_qualification = tdx->vp_enter_args.rcx;
+ tdx->ext_exit_qualification = tdx->vp_enter_args.rdx;
+ tdx->exit_gpa = tdx->vp_enter_args.r8;
+ vt->exit_intr_info = tdx->vp_enter_args.r9;
+
+ vmx_handle_nmi(vcpu);
+
+ guest_state_exit_irqoff();
+}
+
+static bool tdx_failed_vmentry(struct kvm_vcpu *vcpu)
+{
+ return vmx_get_exit_reason(vcpu).failed_vmentry &&
+ vmx_get_exit_reason(vcpu).full != -1u;
+}
+
+static fastpath_t tdx_exit_handlers_fastpath(struct kvm_vcpu *vcpu)
+{
+ u64 vp_enter_ret = to_tdx(vcpu)->vp_enter_ret;
+
+ /*
+ * TDX_OPERAND_BUSY could be returned for SEPT due to 0-step mitigation
+ * or for TD EPOCH due to contention with TDH.MEM.TRACK on TDH.VP.ENTER.
+ *
+ * When KVM requests KVM_REQ_OUTSIDE_GUEST_MODE, which has both
+ * KVM_REQUEST_WAIT and KVM_REQUEST_NO_ACTION set, it requires target
+ * vCPUs leaving fastpath so that interrupt can be enabled to ensure the
+ * IPIs can be delivered. Return EXIT_FASTPATH_EXIT_HANDLED instead of
+ * EXIT_FASTPATH_REENTER_GUEST to exit fastpath, otherwise, the
+ * requester may be blocked endlessly.
+ */
+ if (unlikely(tdx_operand_busy(vp_enter_ret)))
+ return EXIT_FASTPATH_EXIT_HANDLED;
+
+ return EXIT_FASTPATH_NONE;
+}
+
+#define TDX_REGS_AVAIL_SET (BIT_ULL(VCPU_EXREG_EXIT_INFO_1) | \
+ BIT_ULL(VCPU_EXREG_EXIT_INFO_2) | \
+ BIT_ULL(VCPU_REGS_RAX) | \
+ BIT_ULL(VCPU_REGS_RBX) | \
+ BIT_ULL(VCPU_REGS_RCX) | \
+ BIT_ULL(VCPU_REGS_RDX) | \
+ BIT_ULL(VCPU_REGS_RBP) | \
+ BIT_ULL(VCPU_REGS_RSI) | \
+ BIT_ULL(VCPU_REGS_RDI) | \
+ BIT_ULL(VCPU_REGS_R8) | \
+ BIT_ULL(VCPU_REGS_R9) | \
+ BIT_ULL(VCPU_REGS_R10) | \
+ BIT_ULL(VCPU_REGS_R11) | \
+ BIT_ULL(VCPU_REGS_R12) | \
+ BIT_ULL(VCPU_REGS_R13) | \
+ BIT_ULL(VCPU_REGS_R14) | \
+ BIT_ULL(VCPU_REGS_R15))
+
+static void tdx_load_host_xsave_state(struct kvm_vcpu *vcpu)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
+
+ /*
+ * All TDX hosts support PKRU; but even if they didn't,
+ * vcpu->arch.host_pkru would be 0 and the wrpkru would be
+ * skipped.
+ */
+ if (vcpu->arch.host_pkru != 0)
+ wrpkru(vcpu->arch.host_pkru);
+
+ if (kvm_host.xcr0 != (kvm_tdx->xfam & kvm_caps.supported_xcr0))
+ xsetbv(XCR_XFEATURE_ENABLED_MASK, kvm_host.xcr0);
+
+ /*
+ * Likewise, even if a TDX hosts didn't support XSS both arms of
+ * the comparison would be 0 and the wrmsrl would be skipped.
+ */
+ if (kvm_host.xss != (kvm_tdx->xfam & kvm_caps.supported_xss))
+ wrmsrl(MSR_IA32_XSS, kvm_host.xss);
+}
+
+#define TDX_DEBUGCTL_PRESERVED (DEBUGCTLMSR_BTF | \
+ DEBUGCTLMSR_FREEZE_PERFMON_ON_PMI | \
+ DEBUGCTLMSR_FREEZE_IN_SMM)
+
+fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ struct vcpu_vt *vt = to_vt(vcpu);
+
+ /*
+ * WARN if KVM wants to force an immediate exit, as the TDX module does
+ * not guarantee entry into the guest, i.e. it's possible for KVM to
+ * _think_ it completed entry to the guest and forced an immediate exit
+ * without actually having done so. Luckily, KVM never needs to force
+ * an immediate exit for TDX (KVM can't do direct event injection, so
+ * just WARN and continue on.
+ */
+ WARN_ON_ONCE(run_flags);
+
+ /*
+ * Wait until retry of SEPT-zap-related SEAMCALL completes before
+ * allowing vCPU entry to avoid contention with tdh_vp_enter() and
+ * TDCALLs.
+ */
+ if (unlikely(READ_ONCE(to_kvm_tdx(vcpu->kvm)->wait_for_sept_zap)))
+ return EXIT_FASTPATH_EXIT_HANDLED;
+
+ trace_kvm_entry(vcpu, run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT);
+
+ if (pi_test_on(&vt->pi_desc)) {
+ apic->send_IPI_self(POSTED_INTR_VECTOR);
+
+ if (pi_test_pir(kvm_lapic_get_reg(vcpu->arch.apic, APIC_LVTT) &
+ APIC_VECTOR_MASK, &vt->pi_desc))
+ kvm_wait_lapic_expire(vcpu);
+ }
+
+ tdx_vcpu_enter_exit(vcpu);
+
+ if (vcpu->arch.host_debugctl & ~TDX_DEBUGCTL_PRESERVED)
+ update_debugctlmsr(vcpu->arch.host_debugctl);
+
+ tdx_load_host_xsave_state(vcpu);
+ tdx->guest_entered = true;
+
+ vcpu->arch.regs_avail &= TDX_REGS_AVAIL_SET;
+
+ if (unlikely(tdx->vp_enter_ret == EXIT_REASON_EPT_MISCONFIG))
+ return EXIT_FASTPATH_NONE;
+
+ if (unlikely((tdx->vp_enter_ret & TDX_SW_ERROR) == TDX_SW_ERROR))
+ return EXIT_FASTPATH_NONE;
+
+ if (unlikely(vmx_get_exit_reason(vcpu).basic == EXIT_REASON_MCE_DURING_VMENTRY))
+ kvm_machine_check();
+
+ trace_kvm_exit(vcpu, KVM_ISA_VMX);
+
+ if (unlikely(tdx_failed_vmentry(vcpu)))
+ return EXIT_FASTPATH_NONE;
+
+ return tdx_exit_handlers_fastpath(vcpu);
+}
+
+void tdx_inject_nmi(struct kvm_vcpu *vcpu)
+{
+ ++vcpu->stat.nmi_injections;
+ td_management_write8(to_tdx(vcpu), TD_VCPU_PEND_NMI, 1);
+ /*
+ * From KVM's perspective, NMI injection is completed right after
+ * writing to PEND_NMI. KVM doesn't care whether an NMI is injected by
+ * the TDX module or not.
+ */
+ vcpu->arch.nmi_injected = false;
+ /*
+ * TDX doesn't support KVM to request NMI window exit. If there is
+ * still a pending vNMI, KVM is not able to inject it along with the
+ * one pending in TDX module in a back-to-back way. Since the previous
+ * vNMI is still pending in TDX module, i.e. it has not been delivered
+ * to TDX guest yet, it's OK to collapse the pending vNMI into the
+ * previous one. The guest is expected to handle all the NMI sources
+ * when handling the first vNMI.
+ */
+ vcpu->arch.nmi_pending = 0;
+}
+
+static int tdx_handle_exception_nmi(struct kvm_vcpu *vcpu)
+{
+ u32 intr_info = vmx_get_intr_info(vcpu);
+
+ /*
+ * Machine checks are handled by handle_exception_irqoff(), or by
+ * tdx_handle_exit() with TDX_NON_RECOVERABLE set if a #MC occurs on
+ * VM-Entry. NMIs are handled by tdx_vcpu_enter_exit().
+ */
+ if (is_nmi(intr_info) || is_machine_check(intr_info))
+ return 1;
+
+ vcpu->run->exit_reason = KVM_EXIT_EXCEPTION;
+ vcpu->run->ex.exception = intr_info & INTR_INFO_VECTOR_MASK;
+ vcpu->run->ex.error_code = 0;
+
+ return 0;
+}
+
+static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
+{
+ tdvmcall_set_return_code(vcpu, vcpu->run->hypercall.ret);
+ return 1;
+}
+
+static int tdx_emulate_vmcall(struct kvm_vcpu *vcpu)
+{
+ kvm_rax_write(vcpu, to_tdx(vcpu)->vp_enter_args.r10);
+ kvm_rbx_write(vcpu, to_tdx(vcpu)->vp_enter_args.r11);
+ kvm_rcx_write(vcpu, to_tdx(vcpu)->vp_enter_args.r12);
+ kvm_rdx_write(vcpu, to_tdx(vcpu)->vp_enter_args.r13);
+ kvm_rsi_write(vcpu, to_tdx(vcpu)->vp_enter_args.r14);
+
+ return __kvm_emulate_hypercall(vcpu, 0, complete_hypercall_exit);
+}
+
+/*
+ * Split into chunks and check interrupt pending between chunks. This allows
+ * for timely injection of interrupts to prevent issues with guest lockup
+ * detection.
+ */
+#define TDX_MAP_GPA_MAX_LEN (2 * 1024 * 1024)
+static void __tdx_map_gpa(struct vcpu_tdx *tdx);
+
+static int tdx_complete_vmcall_map_gpa(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+ if (vcpu->run->hypercall.ret) {
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ tdx->vp_enter_args.r11 = tdx->map_gpa_next;
+ return 1;
+ }
+
+ tdx->map_gpa_next += TDX_MAP_GPA_MAX_LEN;
+ if (tdx->map_gpa_next >= tdx->map_gpa_end)
+ return 1;
+
+ /*
+ * Stop processing the remaining part if there is a pending interrupt,
+ * which could be qualified to deliver. Skip checking pending RVI for
+ * TDVMCALL_MAP_GPA, see comments in tdx_protected_apic_has_interrupt().
+ */
+ if (kvm_vcpu_has_events(vcpu)) {
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_RETRY);
+ tdx->vp_enter_args.r11 = tdx->map_gpa_next;
+ return 1;
+ }
+
+ __tdx_map_gpa(tdx);
+ return 0;
+}
+
+static void __tdx_map_gpa(struct vcpu_tdx *tdx)
+{
+ u64 gpa = tdx->map_gpa_next;
+ u64 size = tdx->map_gpa_end - tdx->map_gpa_next;
+
+ if (size > TDX_MAP_GPA_MAX_LEN)
+ size = TDX_MAP_GPA_MAX_LEN;
+
+ tdx->vcpu.run->exit_reason = KVM_EXIT_HYPERCALL;
+ tdx->vcpu.run->hypercall.nr = KVM_HC_MAP_GPA_RANGE;
+ /*
+ * In principle this should have been -KVM_ENOSYS, but userspace (QEMU <=9.2)
+ * assumed that vcpu->run->hypercall.ret is never changed by KVM and thus that
+ * it was always zero on KVM_EXIT_HYPERCALL. Since KVM is now overwriting
+ * vcpu->run->hypercall.ret, ensuring that it is zero to not break QEMU.
+ */
+ tdx->vcpu.run->hypercall.ret = 0;
+ tdx->vcpu.run->hypercall.args[0] = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(tdx->vcpu.kvm));
+ tdx->vcpu.run->hypercall.args[1] = size / PAGE_SIZE;
+ tdx->vcpu.run->hypercall.args[2] = vt_is_tdx_private_gpa(tdx->vcpu.kvm, gpa) ?
+ KVM_MAP_GPA_RANGE_ENCRYPTED :
+ KVM_MAP_GPA_RANGE_DECRYPTED;
+ tdx->vcpu.run->hypercall.flags = KVM_EXIT_HYPERCALL_LONG_MODE;
+
+ tdx->vcpu.arch.complete_userspace_io = tdx_complete_vmcall_map_gpa;
+}
+
+static int tdx_map_gpa(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ u64 gpa = tdx->vp_enter_args.r12;
+ u64 size = tdx->vp_enter_args.r13;
+ u64 ret;
+
+ /*
+ * Converting TDVMCALL_MAP_GPA to KVM_HC_MAP_GPA_RANGE requires
+ * userspace to enable KVM_CAP_EXIT_HYPERCALL with KVM_HC_MAP_GPA_RANGE
+ * bit set. This is a base call so it should always be supported, but
+ * KVM has no way to ensure that userspace implements the GHCI correctly.
+ * So if KVM_HC_MAP_GPA_RANGE does not cause a VMEXIT, return an error
+ * to the guest.
+ */
+ if (!user_exit_on_hypercall(vcpu->kvm, KVM_HC_MAP_GPA_RANGE)) {
+ ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+ goto error;
+ }
+
+ if (gpa + size <= gpa || !kvm_vcpu_is_legal_gpa(vcpu, gpa) ||
+ !kvm_vcpu_is_legal_gpa(vcpu, gpa + size - 1) ||
+ (vt_is_tdx_private_gpa(vcpu->kvm, gpa) !=
+ vt_is_tdx_private_gpa(vcpu->kvm, gpa + size - 1))) {
+ ret = TDVMCALL_STATUS_INVALID_OPERAND;
+ goto error;
+ }
+
+ if (!PAGE_ALIGNED(gpa) || !PAGE_ALIGNED(size)) {
+ ret = TDVMCALL_STATUS_ALIGN_ERROR;
+ goto error;
+ }
+
+ tdx->map_gpa_end = gpa + size;
+ tdx->map_gpa_next = gpa;
+
+ __tdx_map_gpa(tdx);
+ return 0;
+
+error:
+ tdvmcall_set_return_code(vcpu, ret);
+ tdx->vp_enter_args.r11 = gpa;
+ return 1;
+}
+
+static int tdx_report_fatal_error(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ u64 *regs = vcpu->run->system_event.data;
+ u64 *module_regs = &tdx->vp_enter_args.r8;
+ int index = VCPU_REGS_RAX;
+
+ vcpu->run->exit_reason = KVM_EXIT_SYSTEM_EVENT;
+ vcpu->run->system_event.type = KVM_SYSTEM_EVENT_TDX_FATAL;
+ vcpu->run->system_event.ndata = 16;
+
+ /* Dump 16 general-purpose registers to userspace in ascending order. */
+ regs[index++] = tdx->vp_enter_ret;
+ regs[index++] = tdx->vp_enter_args.rcx;
+ regs[index++] = tdx->vp_enter_args.rdx;
+ regs[index++] = tdx->vp_enter_args.rbx;
+ regs[index++] = 0;
+ regs[index++] = 0;
+ regs[index++] = tdx->vp_enter_args.rsi;
+ regs[index] = tdx->vp_enter_args.rdi;
+ for (index = 0; index < 8; index++)
+ regs[VCPU_REGS_R8 + index] = module_regs[index];
+
+ return 0;
+}
+
+static int tdx_emulate_cpuid(struct kvm_vcpu *vcpu)
+{
+ u32 eax, ebx, ecx, edx;
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+ /* EAX and ECX for cpuid is stored in R12 and R13. */
+ eax = tdx->vp_enter_args.r12;
+ ecx = tdx->vp_enter_args.r13;
+
+ kvm_cpuid(vcpu, &eax, &ebx, &ecx, &edx, false);
+
+ tdx->vp_enter_args.r12 = eax;
+ tdx->vp_enter_args.r13 = ebx;
+ tdx->vp_enter_args.r14 = ecx;
+ tdx->vp_enter_args.r15 = edx;
+
+ return 1;
+}
+
+static int tdx_complete_pio_out(struct kvm_vcpu *vcpu)
+{
+ vcpu->arch.pio.count = 0;
+ return 1;
+}
+
+static int tdx_complete_pio_in(struct kvm_vcpu *vcpu)
+{
+ struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
+ unsigned long val = 0;
+ int ret;
+
+ ret = ctxt->ops->pio_in_emulated(ctxt, vcpu->arch.pio.size,
+ vcpu->arch.pio.port, &val, 1);
+
+ WARN_ON_ONCE(!ret);
+
+ tdvmcall_set_return_val(vcpu, val);
+
+ return 1;
+}
+
+static int tdx_emulate_io(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ struct x86_emulate_ctxt *ctxt = vcpu->arch.emulate_ctxt;
+ unsigned long val = 0;
+ unsigned int port;
+ u64 size, write;
+ int ret;
+
+ ++vcpu->stat.io_exits;
+
+ size = tdx->vp_enter_args.r12;
+ write = tdx->vp_enter_args.r13;
+ port = tdx->vp_enter_args.r14;
+
+ if ((write != 0 && write != 1) || (size != 1 && size != 2 && size != 4)) {
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
+ }
+
+ if (write) {
+ val = tdx->vp_enter_args.r15;
+ ret = ctxt->ops->pio_out_emulated(ctxt, size, port, &val, 1);
+ } else {
+ ret = ctxt->ops->pio_in_emulated(ctxt, size, port, &val, 1);
+ }
+
+ if (!ret)
+ vcpu->arch.complete_userspace_io = write ? tdx_complete_pio_out :
+ tdx_complete_pio_in;
+ else if (!write)
+ tdvmcall_set_return_val(vcpu, val);
+
+ return ret;
+}
+
+static int tdx_complete_mmio_read(struct kvm_vcpu *vcpu)
+{
+ unsigned long val = 0;
+ gpa_t gpa;
+ int size;
+
+ gpa = vcpu->mmio_fragments[0].gpa;
+ size = vcpu->mmio_fragments[0].len;
+
+ memcpy(&val, vcpu->run->mmio.data, size);
+ tdvmcall_set_return_val(vcpu, val);
+ trace_kvm_mmio(KVM_TRACE_MMIO_READ, size, gpa, &val);
+ return 1;
+}
+
+static inline int tdx_mmio_write(struct kvm_vcpu *vcpu, gpa_t gpa, int size,
+ unsigned long val)
+{
+ if (!kvm_io_bus_write(vcpu, KVM_FAST_MMIO_BUS, gpa, 0, NULL)) {
+ trace_kvm_fast_mmio(gpa);
+ return 0;
+ }
+
+ trace_kvm_mmio(KVM_TRACE_MMIO_WRITE, size, gpa, &val);
+ if (kvm_io_bus_write(vcpu, KVM_MMIO_BUS, gpa, size, &val))
+ return -EOPNOTSUPP;
+
+ return 0;
+}
+
+static inline int tdx_mmio_read(struct kvm_vcpu *vcpu, gpa_t gpa, int size)
+{
+ unsigned long val;
+
+ if (kvm_io_bus_read(vcpu, KVM_MMIO_BUS, gpa, size, &val))
+ return -EOPNOTSUPP;
+
+ tdvmcall_set_return_val(vcpu, val);
+ trace_kvm_mmio(KVM_TRACE_MMIO_READ, size, gpa, &val);
+ return 0;
+}
+
+static int tdx_emulate_mmio(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ int size, write, r;
+ unsigned long val;
+ gpa_t gpa;
+
+ size = tdx->vp_enter_args.r12;
+ write = tdx->vp_enter_args.r13;
+ gpa = tdx->vp_enter_args.r14;
+ val = write ? tdx->vp_enter_args.r15 : 0;
+
+ if (size != 1 && size != 2 && size != 4 && size != 8)
+ goto error;
+ if (write != 0 && write != 1)
+ goto error;
+
+ /*
+ * TDG.VP.VMCALL<MMIO> allows only shared GPA, it makes no sense to
+ * do MMIO emulation for private GPA.
+ */
+ if (vt_is_tdx_private_gpa(vcpu->kvm, gpa) ||
+ vt_is_tdx_private_gpa(vcpu->kvm, gpa + size - 1))
+ goto error;
+
+ gpa = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm));
+
+ if (write)
+ r = tdx_mmio_write(vcpu, gpa, size, val);
+ else
+ r = tdx_mmio_read(vcpu, gpa, size);
+ if (!r)
+ /* Kernel completed device emulation. */
+ return 1;
+
+ /* Request the device emulation to userspace device model. */
+ vcpu->mmio_is_write = write;
+ if (!write)
+ vcpu->arch.complete_userspace_io = tdx_complete_mmio_read;
+
+ vcpu->run->mmio.phys_addr = gpa;
+ vcpu->run->mmio.len = size;
+ vcpu->run->mmio.is_write = write;
+ vcpu->run->exit_reason = KVM_EXIT_MMIO;
+
+ if (write) {
+ memcpy(vcpu->run->mmio.data, &val, size);
+ } else {
+ vcpu->mmio_fragments[0].gpa = gpa;
+ vcpu->mmio_fragments[0].len = size;
+ trace_kvm_mmio(KVM_TRACE_MMIO_READ_UNSATISFIED, size, gpa, NULL);
+ }
+ return 0;
+
+error:
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
+}
+
+static int tdx_complete_get_td_vm_call_info(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+ tdvmcall_set_return_code(vcpu, vcpu->run->tdx.get_tdvmcall_info.ret);
+
+ /*
+ * For now, there is no TDVMCALL beyond GHCI base API supported by KVM
+ * directly without the support from userspace, just set the value
+ * returned from userspace.
+ */
+ tdx->vp_enter_args.r11 = vcpu->run->tdx.get_tdvmcall_info.r11;
+ tdx->vp_enter_args.r12 = vcpu->run->tdx.get_tdvmcall_info.r12;
+ tdx->vp_enter_args.r13 = vcpu->run->tdx.get_tdvmcall_info.r13;
+ tdx->vp_enter_args.r14 = vcpu->run->tdx.get_tdvmcall_info.r14;
+
+ return 1;
+}
+
+static int tdx_get_td_vm_call_info(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+ switch (tdx->vp_enter_args.r12) {
+ case 0:
+ tdx->vp_enter_args.r11 = 0;
+ tdx->vp_enter_args.r12 = 0;
+ tdx->vp_enter_args.r13 = 0;
+ tdx->vp_enter_args.r14 = 0;
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUCCESS);
+ return 1;
+ case 1:
+ vcpu->run->tdx.get_tdvmcall_info.leaf = tdx->vp_enter_args.r12;
+ vcpu->run->exit_reason = KVM_EXIT_TDX;
+ vcpu->run->tdx.flags = 0;
+ vcpu->run->tdx.nr = TDVMCALL_GET_TD_VM_CALL_INFO;
+ vcpu->run->tdx.get_tdvmcall_info.ret = TDVMCALL_STATUS_SUCCESS;
+ vcpu->run->tdx.get_tdvmcall_info.r11 = 0;
+ vcpu->run->tdx.get_tdvmcall_info.r12 = 0;
+ vcpu->run->tdx.get_tdvmcall_info.r13 = 0;
+ vcpu->run->tdx.get_tdvmcall_info.r14 = 0;
+ vcpu->arch.complete_userspace_io = tdx_complete_get_td_vm_call_info;
+ return 0;
+ default:
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
+ }
+}
+
+static int tdx_complete_simple(struct kvm_vcpu *vcpu)
+{
+ tdvmcall_set_return_code(vcpu, vcpu->run->tdx.unknown.ret);
+ return 1;
+}
+
+static int tdx_get_quote(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ u64 gpa = tdx->vp_enter_args.r12;
+ u64 size = tdx->vp_enter_args.r13;
+
+ /* The gpa of buffer must have shared bit set. */
+ if (vt_is_tdx_private_gpa(vcpu->kvm, gpa)) {
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
+ }
+
+ vcpu->run->exit_reason = KVM_EXIT_TDX;
+ vcpu->run->tdx.flags = 0;
+ vcpu->run->tdx.nr = TDVMCALL_GET_QUOTE;
+ vcpu->run->tdx.get_quote.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+ vcpu->run->tdx.get_quote.gpa = gpa & ~gfn_to_gpa(kvm_gfn_direct_bits(tdx->vcpu.kvm));
+ vcpu->run->tdx.get_quote.size = size;
+
+ vcpu->arch.complete_userspace_io = tdx_complete_simple;
+
+ return 0;
+}
+
+static int tdx_setup_event_notify_interrupt(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ u64 vector = tdx->vp_enter_args.r12;
+
+ if (vector < 32 || vector > 255) {
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
+ }
+
+ vcpu->run->exit_reason = KVM_EXIT_TDX;
+ vcpu->run->tdx.flags = 0;
+ vcpu->run->tdx.nr = TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT;
+ vcpu->run->tdx.setup_event_notify.ret = TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED;
+ vcpu->run->tdx.setup_event_notify.vector = vector;
+
+ vcpu->arch.complete_userspace_io = tdx_complete_simple;
+
+ return 0;
+}
+
+static int handle_tdvmcall(struct kvm_vcpu *vcpu)
+{
+ switch (tdvmcall_leaf(vcpu)) {
+ case TDVMCALL_MAP_GPA:
+ return tdx_map_gpa(vcpu);
+ case TDVMCALL_REPORT_FATAL_ERROR:
+ return tdx_report_fatal_error(vcpu);
+ case TDVMCALL_GET_TD_VM_CALL_INFO:
+ return tdx_get_td_vm_call_info(vcpu);
+ case TDVMCALL_GET_QUOTE:
+ return tdx_get_quote(vcpu);
+ case TDVMCALL_SETUP_EVENT_NOTIFY_INTERRUPT:
+ return tdx_setup_event_notify_interrupt(vcpu);
+ default:
+ break;
+ }
+
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_SUBFUNC_UNSUPPORTED);
+ return 1;
+}
+
+void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int pgd_level)
+{
+ u64 shared_bit = (pgd_level == 5) ? TDX_SHARED_BIT_PWL_5 :
+ TDX_SHARED_BIT_PWL_4;
+
+ if (KVM_BUG_ON(shared_bit != kvm_gfn_direct_bits(vcpu->kvm), vcpu->kvm))
+ return;
+
+ td_vmcs_write64(to_tdx(vcpu), SHARED_EPT_POINTER, root_hpa);
+}
+
+static void tdx_unpin(struct kvm *kvm, struct page *page)
+{
+ put_page(page);
+}
+
+static int tdx_mem_page_aug(struct kvm *kvm, gfn_t gfn,
+ enum pg_level level, struct page *page)
+{
+ int tdx_level = pg_level_to_tdx_sept_level(level);
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ gpa_t gpa = gfn_to_gpa(gfn);
+ u64 entry, level_state;
+ u64 err;
+
+ err = tdh_mem_page_aug(&kvm_tdx->td, gpa, tdx_level, page, &entry, &level_state);
+ if (unlikely(tdx_operand_busy(err))) {
+ tdx_unpin(kvm, page);
+ return -EBUSY;
+ }
+
+ if (KVM_BUG_ON(err, kvm)) {
+ pr_tdx_error_2(TDH_MEM_PAGE_AUG, err, entry, level_state);
+ tdx_unpin(kvm, page);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+/*
+ * KVM_TDX_INIT_MEM_REGION calls kvm_gmem_populate() to map guest pages; the
+ * callback tdx_gmem_post_populate() then maps pages into private memory.
+ * through the a seamcall TDH.MEM.PAGE.ADD(). The SEAMCALL also requires the
+ * private EPT structures for the page to have been built before, which is
+ * done via kvm_tdp_map_page(). nr_premapped counts the number of pages that
+ * were added to the EPT structures but not added with TDH.MEM.PAGE.ADD().
+ * The counter has to be zero on KVM_TDX_FINALIZE_VM, to ensure that there
+ * are no half-initialized shared EPT pages.
+ */
+static int tdx_mem_page_record_premap_cnt(struct kvm *kvm, gfn_t gfn,
+ enum pg_level level, kvm_pfn_t pfn)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+ if (KVM_BUG_ON(kvm->arch.pre_fault_allowed, kvm))
+ return -EINVAL;
+
+ /* nr_premapped will be decreased when tdh_mem_page_add() is called. */
+ atomic64_inc(&kvm_tdx->nr_premapped);
+ return 0;
+}
+
+static int tdx_sept_set_private_spte(struct kvm *kvm, gfn_t gfn,
+ enum pg_level level, kvm_pfn_t pfn)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ struct page *page = pfn_to_page(pfn);
+
+ /* TODO: handle large pages. */
+ if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
+ return -EINVAL;
+
+ /*
+ * Because guest_memfd doesn't support page migration with
+ * a_ops->migrate_folio (yet), no callback is triggered for KVM on page
+ * migration. Until guest_memfd supports page migration, prevent page
+ * migration.
+ * TODO: Once guest_memfd introduces callback on page migration,
+ * implement it and remove get_page/put_page().
+ */
+ get_page(page);
+
+ /*
+ * Read 'pre_fault_allowed' before 'kvm_tdx->state'; see matching
+ * barrier in tdx_td_finalize().
+ */
+ smp_rmb();
+ if (likely(kvm_tdx->state == TD_STATE_RUNNABLE))
+ return tdx_mem_page_aug(kvm, gfn, level, page);
+
+ return tdx_mem_page_record_premap_cnt(kvm, gfn, level, pfn);
+}
+
+static int tdx_sept_drop_private_spte(struct kvm *kvm, gfn_t gfn,
+ enum pg_level level, struct page *page)
+{
+ int tdx_level = pg_level_to_tdx_sept_level(level);
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ gpa_t gpa = gfn_to_gpa(gfn);
+ u64 err, entry, level_state;
+
+ /* TODO: handle large pages. */
+ if (KVM_BUG_ON(level != PG_LEVEL_4K, kvm))
+ return -EINVAL;
+
+ if (KVM_BUG_ON(!is_hkid_assigned(kvm_tdx), kvm))
+ return -EINVAL;
+
+ /*
+ * When zapping private page, write lock is held. So no race condition
+ * with other vcpu sept operation.
+ * Race with TDH.VP.ENTER due to (0-step mitigation) and Guest TDCALLs.
+ */
+ err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry,
+ &level_state);
+
+ if (unlikely(tdx_operand_busy(err))) {
+ /*
+ * The second retry is expected to succeed after kicking off all
+ * other vCPUs and prevent them from invoking TDH.VP.ENTER.
+ */
+ tdx_no_vcpus_enter_start(kvm);
+ err = tdh_mem_page_remove(&kvm_tdx->td, gpa, tdx_level, &entry,
+ &level_state);
+ tdx_no_vcpus_enter_stop(kvm);
+ }
+
+ if (KVM_BUG_ON(err, kvm)) {
+ pr_tdx_error_2(TDH_MEM_PAGE_REMOVE, err, entry, level_state);
+ return -EIO;
+ }
+
+ err = tdh_phymem_page_wbinvd_hkid((u16)kvm_tdx->hkid, page);
+
+ if (KVM_BUG_ON(err, kvm)) {
+ pr_tdx_error(TDH_PHYMEM_PAGE_WBINVD, err);
+ return -EIO;
+ }
+ tdx_clear_page(page);
+ tdx_unpin(kvm, page);
+ return 0;
+}
+
+static int tdx_sept_link_private_spt(struct kvm *kvm, gfn_t gfn,
+ enum pg_level level, void *private_spt)
+{
+ int tdx_level = pg_level_to_tdx_sept_level(level);
+ gpa_t gpa = gfn_to_gpa(gfn);
+ struct page *page = virt_to_page(private_spt);
+ u64 err, entry, level_state;
+
+ err = tdh_mem_sept_add(&to_kvm_tdx(kvm)->td, gpa, tdx_level, page, &entry,
+ &level_state);
+ if (unlikely(tdx_operand_busy(err)))
+ return -EBUSY;
+
+ if (KVM_BUG_ON(err, kvm)) {
+ pr_tdx_error_2(TDH_MEM_SEPT_ADD, err, entry, level_state);
+ return -EIO;
+ }
+
+ return 0;
+}
+
+/*
+ * Check if the error returned from a SEPT zap SEAMCALL is due to that a page is
+ * mapped by KVM_TDX_INIT_MEM_REGION without tdh_mem_page_add() being called
+ * successfully.
+ *
+ * Since tdh_mem_sept_add() must have been invoked successfully before a
+ * non-leaf entry present in the mirrored page table, the SEPT ZAP related
+ * SEAMCALLs should not encounter err TDX_EPT_WALK_FAILED. They should instead
+ * find TDX_EPT_ENTRY_STATE_INCORRECT due to an empty leaf entry found in the
+ * SEPT.
+ *
+ * Further check if the returned entry from SEPT walking is with RWX permissions
+ * to filter out anything unexpected.
+ *
+ * Note: @level is pg_level, not the tdx_level. The tdx_level extracted from
+ * level_state returned from a SEAMCALL error is the same as that passed into
+ * the SEAMCALL.
+ */
+static int tdx_is_sept_zap_err_due_to_premap(struct kvm_tdx *kvm_tdx, u64 err,
+ u64 entry, int level)
+{
+ if (!err || kvm_tdx->state == TD_STATE_RUNNABLE)
+ return false;
+
+ if (err != (TDX_EPT_ENTRY_STATE_INCORRECT | TDX_OPERAND_ID_RCX))
+ return false;
+
+ if ((is_last_spte(entry, level) && (entry & VMX_EPT_RWX_MASK)))
+ return false;
+
+ return true;
+}
+
+static int tdx_sept_zap_private_spte(struct kvm *kvm, gfn_t gfn,
+ enum pg_level level, struct page *page)
+{
+ int tdx_level = pg_level_to_tdx_sept_level(level);
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ gpa_t gpa = gfn_to_gpa(gfn) & KVM_HPAGE_MASK(level);
+ u64 err, entry, level_state;
+
+ /* For now large page isn't supported yet. */
+ WARN_ON_ONCE(level != PG_LEVEL_4K);
+
+ err = tdh_mem_range_block(&kvm_tdx->td, gpa, tdx_level, &entry, &level_state);
+
+ if (unlikely(tdx_operand_busy(err))) {
+ /* After no vCPUs enter, the second retry is expected to succeed */
+ tdx_no_vcpus_enter_start(kvm);
+ err = tdh_mem_range_block(&kvm_tdx->td, gpa, tdx_level, &entry, &level_state);
+ tdx_no_vcpus_enter_stop(kvm);
+ }
+ if (tdx_is_sept_zap_err_due_to_premap(kvm_tdx, err, entry, level) &&
+ !KVM_BUG_ON(!atomic64_read(&kvm_tdx->nr_premapped), kvm)) {
+ atomic64_dec(&kvm_tdx->nr_premapped);
+ tdx_unpin(kvm, page);
+ return 0;
+ }
+
+ if (KVM_BUG_ON(err, kvm)) {
+ pr_tdx_error_2(TDH_MEM_RANGE_BLOCK, err, entry, level_state);
+ return -EIO;
+ }
+ return 1;
+}
+
+/*
+ * Ensure shared and private EPTs to be flushed on all vCPUs.
+ * tdh_mem_track() is the only caller that increases TD epoch. An increase in
+ * the TD epoch (e.g., to value "N + 1") is successful only if no vCPUs are
+ * running in guest mode with the value "N - 1".
+ *
+ * A successful execution of tdh_mem_track() ensures that vCPUs can only run in
+ * guest mode with TD epoch value "N" if no TD exit occurs after the TD epoch
+ * being increased to "N + 1".
+ *
+ * Kicking off all vCPUs after that further results in no vCPUs can run in guest
+ * mode with TD epoch value "N", which unblocks the next tdh_mem_track() (e.g.
+ * to increase TD epoch to "N + 2").
+ *
+ * TDX module will flush EPT on the next TD enter and make vCPUs to run in
+ * guest mode with TD epoch value "N + 1".
+ *
+ * kvm_make_all_cpus_request() guarantees all vCPUs are out of guest mode by
+ * waiting empty IPI handler ack_kick().
+ *
+ * No action is required to the vCPUs being kicked off since the kicking off
+ * occurs certainly after TD epoch increment and before the next
+ * tdh_mem_track().
+ */
+static void tdx_track(struct kvm *kvm)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ u64 err;
+
+ /* If TD isn't finalized, it's before any vcpu running. */
+ if (unlikely(kvm_tdx->state != TD_STATE_RUNNABLE))
+ return;
+
+ lockdep_assert_held_write(&kvm->mmu_lock);
+
+ err = tdh_mem_track(&kvm_tdx->td);
+ if (unlikely(tdx_operand_busy(err))) {
+ /* After no vCPUs enter, the second retry is expected to succeed */
+ tdx_no_vcpus_enter_start(kvm);
+ err = tdh_mem_track(&kvm_tdx->td);
+ tdx_no_vcpus_enter_stop(kvm);
+ }
+
+ if (KVM_BUG_ON(err, kvm))
+ pr_tdx_error(TDH_MEM_TRACK, err);
+
+ kvm_make_all_cpus_request(kvm, KVM_REQ_OUTSIDE_GUEST_MODE);
+}
+
+static int tdx_sept_free_private_spt(struct kvm *kvm, gfn_t gfn,
+ enum pg_level level, void *private_spt)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+ /*
+ * free_external_spt() is only called after hkid is freed when TD is
+ * tearing down.
+ * KVM doesn't (yet) zap page table pages in mirror page table while
+ * TD is active, though guest pages mapped in mirror page table could be
+ * zapped during TD is active, e.g. for shared <-> private conversion
+ * and slot move/deletion.
+ */
+ if (KVM_BUG_ON(is_hkid_assigned(kvm_tdx), kvm))
+ return -EINVAL;
+
+ /*
+ * The HKID assigned to this TD was already freed and cache was
+ * already flushed. We don't have to flush again.
+ */
+ return tdx_reclaim_page(virt_to_page(private_spt));
+}
+
+static int tdx_sept_remove_private_spte(struct kvm *kvm, gfn_t gfn,
+ enum pg_level level, kvm_pfn_t pfn)
+{
+ struct page *page = pfn_to_page(pfn);
+ int ret;
+
+ /*
+ * HKID is released after all private pages have been removed, and set
+ * before any might be populated. Warn if zapping is attempted when
+ * there can't be anything populated in the private EPT.
+ */
+ if (KVM_BUG_ON(!is_hkid_assigned(to_kvm_tdx(kvm)), kvm))
+ return -EINVAL;
+
+ ret = tdx_sept_zap_private_spte(kvm, gfn, level, page);
+ if (ret <= 0)
+ return ret;
+
+ /*
+ * TDX requires TLB tracking before dropping private page. Do
+ * it here, although it is also done later.
+ */
+ tdx_track(kvm);
+
+ return tdx_sept_drop_private_spte(kvm, gfn, level, page);
+}
+
+void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
+ int trig_mode, int vector)
+{
+ struct kvm_vcpu *vcpu = apic->vcpu;
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+ /* TDX supports only posted interrupt. No lapic emulation. */
+ __vmx_deliver_posted_interrupt(vcpu, &tdx->vt.pi_desc, vector);
+
+ trace_kvm_apicv_accept_irq(vcpu->vcpu_id, delivery_mode, trig_mode, vector);
+}
+
+static inline bool tdx_is_sept_violation_unexpected_pending(struct kvm_vcpu *vcpu)
+{
+ u64 eeq_type = to_tdx(vcpu)->ext_exit_qualification & TDX_EXT_EXIT_QUAL_TYPE_MASK;
+ u64 eq = vmx_get_exit_qual(vcpu);
+
+ if (eeq_type != TDX_EXT_EXIT_QUAL_TYPE_PENDING_EPT_VIOLATION)
+ return false;
+
+ return !(eq & EPT_VIOLATION_PROT_MASK) && !(eq & EPT_VIOLATION_EXEC_FOR_RING3_LIN);
+}
+
+static int tdx_handle_ept_violation(struct kvm_vcpu *vcpu)
+{
+ unsigned long exit_qual;
+ gpa_t gpa = to_tdx(vcpu)->exit_gpa;
+ bool local_retry = false;
+ int ret;
+
+ if (vt_is_tdx_private_gpa(vcpu->kvm, gpa)) {
+ if (tdx_is_sept_violation_unexpected_pending(vcpu)) {
+ pr_warn("Guest access before accepting 0x%llx on vCPU %d\n",
+ gpa, vcpu->vcpu_id);
+ kvm_vm_dead(vcpu->kvm);
+ return -EIO;
+ }
+ /*
+ * Always treat SEPT violations as write faults. Ignore the
+ * EXIT_QUALIFICATION reported by TDX-SEAM for SEPT violations.
+ * TD private pages are always RWX in the SEPT tables,
+ * i.e. they're always mapped writable. Just as importantly,
+ * treating SEPT violations as write faults is necessary to
+ * avoid COW allocations, which will cause TDAUGPAGE failures
+ * due to aliasing a single HPA to multiple GPAs.
+ */
+ exit_qual = EPT_VIOLATION_ACC_WRITE;
+
+ /* Only private GPA triggers zero-step mitigation */
+ local_retry = true;
+ } else {
+ exit_qual = vmx_get_exit_qual(vcpu);
+ /*
+ * EPT violation due to instruction fetch should never be
+ * triggered from shared memory in TDX guest. If such EPT
+ * violation occurs, treat it as broken hardware.
+ */
+ if (KVM_BUG_ON(exit_qual & EPT_VIOLATION_ACC_INSTR, vcpu->kvm))
+ return -EIO;
+ }
+
+ trace_kvm_page_fault(vcpu, gpa, exit_qual);
+
+ /*
+ * To minimize TDH.VP.ENTER invocations, retry locally for private GPA
+ * mapping in TDX.
+ *
+ * KVM may return RET_PF_RETRY for private GPA due to
+ * - contentions when atomically updating SPTEs of the mirror page table
+ * - in-progress GFN invalidation or memslot removal.
+ * - TDX_OPERAND_BUSY error from TDH.MEM.PAGE.AUG or TDH.MEM.SEPT.ADD,
+ * caused by contentions with TDH.VP.ENTER (with zero-step mitigation)
+ * or certain TDCALLs.
+ *
+ * If TDH.VP.ENTER is invoked more times than the threshold set by the
+ * TDX module before KVM resolves the private GPA mapping, the TDX
+ * module will activate zero-step mitigation during TDH.VP.ENTER. This
+ * process acquires an SEPT tree lock in the TDX module, leading to
+ * further contentions with TDH.MEM.PAGE.AUG or TDH.MEM.SEPT.ADD
+ * operations on other vCPUs.
+ *
+ * Breaking out of local retries for kvm_vcpu_has_events() is for
+ * interrupt injection. kvm_vcpu_has_events() should not see pending
+ * events for TDX. Since KVM can't determine if IRQs (or NMIs) are
+ * blocked by TDs, false positives are inevitable i.e., KVM may re-enter
+ * the guest even if the IRQ/NMI can't be delivered.
+ *
+ * Note: even without breaking out of local retries, zero-step
+ * mitigation may still occur due to
+ * - invoking of TDH.VP.ENTER after KVM_EXIT_MEMORY_FAULT,
+ * - a single RIP causing EPT violations for more GFNs than the
+ * threshold count.
+ * This is safe, as triggering zero-step mitigation only introduces
+ * contentions to page installation SEAMCALLs on other vCPUs, which will
+ * handle retries locally in their EPT violation handlers.
+ */
+ while (1) {
+ ret = __vmx_handle_ept_violation(vcpu, gpa, exit_qual);
+
+ if (ret != RET_PF_RETRY || !local_retry)
+ break;
+
+ if (kvm_vcpu_has_events(vcpu) || signal_pending(current))
+ break;
+
+ if (kvm_check_request(KVM_REQ_VM_DEAD, vcpu)) {
+ ret = -EIO;
+ break;
+ }
+
+ cond_resched();
+ }
+ return ret;
+}
+
+int tdx_complete_emulated_msr(struct kvm_vcpu *vcpu, int err)
+{
+ if (err) {
+ tdvmcall_set_return_code(vcpu, TDVMCALL_STATUS_INVALID_OPERAND);
+ return 1;
+ }
+
+ if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_MSR_READ)
+ tdvmcall_set_return_val(vcpu, kvm_read_edx_eax(vcpu));
+
+ return 1;
+}
+
+
+int tdx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t fastpath)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ u64 vp_enter_ret = tdx->vp_enter_ret;
+ union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu);
+
+ if (fastpath != EXIT_FASTPATH_NONE)
+ return 1;
+
+ if (unlikely(vp_enter_ret == EXIT_REASON_EPT_MISCONFIG)) {
+ KVM_BUG_ON(1, vcpu->kvm);
+ return -EIO;
+ }
+
+ /*
+ * Handle TDX SW errors, including TDX_SEAMCALL_UD, TDX_SEAMCALL_GP and
+ * TDX_SEAMCALL_VMFAILINVALID.
+ */
+ if (unlikely((vp_enter_ret & TDX_SW_ERROR) == TDX_SW_ERROR)) {
+ KVM_BUG_ON(!kvm_rebooting, vcpu->kvm);
+ goto unhandled_exit;
+ }
+
+ if (unlikely(tdx_failed_vmentry(vcpu))) {
+ /*
+ * If the guest state is protected, that means off-TD debug is
+ * not enabled, TDX_NON_RECOVERABLE must be set.
+ */
+ WARN_ON_ONCE(vcpu->arch.guest_state_protected &&
+ !(vp_enter_ret & TDX_NON_RECOVERABLE));
+ vcpu->run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+ vcpu->run->fail_entry.hardware_entry_failure_reason = exit_reason.full;
+ vcpu->run->fail_entry.cpu = vcpu->arch.last_vmentry_cpu;
+ return 0;
+ }
+
+ if (unlikely(vp_enter_ret & (TDX_ERROR | TDX_NON_RECOVERABLE)) &&
+ exit_reason.basic != EXIT_REASON_TRIPLE_FAULT) {
+ kvm_pr_unimpl("TD vp_enter_ret 0x%llx\n", vp_enter_ret);
+ goto unhandled_exit;
+ }
+
+ WARN_ON_ONCE(exit_reason.basic != EXIT_REASON_TRIPLE_FAULT &&
+ (vp_enter_ret & TDX_SEAMCALL_STATUS_MASK) != TDX_SUCCESS);
+
+ switch (exit_reason.basic) {
+ case EXIT_REASON_TRIPLE_FAULT:
+ vcpu->run->exit_reason = KVM_EXIT_SHUTDOWN;
+ vcpu->mmio_needed = 0;
+ return 0;
+ case EXIT_REASON_EXCEPTION_NMI:
+ return tdx_handle_exception_nmi(vcpu);
+ case EXIT_REASON_EXTERNAL_INTERRUPT:
+ ++vcpu->stat.irq_exits;
+ return 1;
+ case EXIT_REASON_CPUID:
+ return tdx_emulate_cpuid(vcpu);
+ case EXIT_REASON_HLT:
+ return kvm_emulate_halt_noskip(vcpu);
+ case EXIT_REASON_TDCALL:
+ return handle_tdvmcall(vcpu);
+ case EXIT_REASON_VMCALL:
+ return tdx_emulate_vmcall(vcpu);
+ case EXIT_REASON_IO_INSTRUCTION:
+ return tdx_emulate_io(vcpu);
+ case EXIT_REASON_MSR_READ:
+ kvm_rcx_write(vcpu, tdx->vp_enter_args.r12);
+ return kvm_emulate_rdmsr(vcpu);
+ case EXIT_REASON_MSR_WRITE:
+ kvm_rcx_write(vcpu, tdx->vp_enter_args.r12);
+ kvm_rax_write(vcpu, tdx->vp_enter_args.r13 & -1u);
+ kvm_rdx_write(vcpu, tdx->vp_enter_args.r13 >> 32);
+ return kvm_emulate_wrmsr(vcpu);
+ case EXIT_REASON_EPT_MISCONFIG:
+ return tdx_emulate_mmio(vcpu);
+ case EXIT_REASON_EPT_VIOLATION:
+ return tdx_handle_ept_violation(vcpu);
+ case EXIT_REASON_OTHER_SMI:
+ /*
+ * Unlike VMX, SMI in SEAM non-root mode (i.e. when
+ * TD guest vCPU is running) will cause VM exit to TDX module,
+ * then SEAMRET to KVM. Once it exits to KVM, SMI is delivered
+ * and handled by kernel handler right away.
+ *
+ * The Other SMI exit can also be caused by the SEAM non-root
+ * machine check delivered via Machine Check System Management
+ * Interrupt (MSMI), but it has already been handled by the
+ * kernel machine check handler, i.e., the memory page has been
+ * marked as poisoned and it won't be freed to the free list
+ * when the TDX guest is terminated (the TDX module marks the
+ * guest as dead and prevent it from further running when
+ * machine check happens in SEAM non-root).
+ *
+ * - A MSMI will not reach here, it's handled as non_recoverable
+ * case above.
+ * - If it's not an MSMI, no need to do anything here.
+ */
+ return 1;
+ default:
+ break;
+ }
+
+unhandled_exit:
+ vcpu->run->exit_reason = KVM_EXIT_INTERNAL_ERROR;
+ vcpu->run->internal.suberror = KVM_INTERNAL_ERROR_UNEXPECTED_EXIT_REASON;
+ vcpu->run->internal.ndata = 2;
+ vcpu->run->internal.data[0] = vp_enter_ret;
+ vcpu->run->internal.data[1] = vcpu->arch.last_vmentry_cpu;
+ return 0;
+}
+
+void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
+ u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+
+ *reason = tdx->vt.exit_reason.full;
+ if (*reason != -1u) {
+ *info1 = vmx_get_exit_qual(vcpu);
+ *info2 = tdx->ext_exit_qualification;
+ *intr_info = vmx_get_intr_info(vcpu);
+ } else {
+ *info1 = 0;
+ *info2 = 0;
+ *intr_info = 0;
+ }
+
+ *error_code = 0;
+}
+
+bool tdx_has_emulated_msr(u32 index)
+{
+ switch (index) {
+ case MSR_IA32_UCODE_REV:
+ case MSR_IA32_ARCH_CAPABILITIES:
+ case MSR_IA32_POWER_CTL:
+ case MSR_IA32_CR_PAT:
+ case MSR_MTRRcap:
+ case MTRRphysBase_MSR(0) ... MSR_MTRRfix4K_F8000:
+ case MSR_MTRRdefType:
+ case MSR_IA32_TSC_DEADLINE:
+ case MSR_IA32_MISC_ENABLE:
+ case MSR_PLATFORM_INFO:
+ case MSR_MISC_FEATURES_ENABLES:
+ case MSR_IA32_APICBASE:
+ case MSR_EFER:
+ case MSR_IA32_FEAT_CTL:
+ case MSR_IA32_MCG_CAP:
+ case MSR_IA32_MCG_STATUS:
+ case MSR_IA32_MCG_CTL:
+ case MSR_IA32_MCG_EXT_CTL:
+ case MSR_IA32_MC0_CTL ... MSR_IA32_MCx_CTL(KVM_MAX_MCE_BANKS) - 1:
+ case MSR_IA32_MC0_CTL2 ... MSR_IA32_MCx_CTL2(KVM_MAX_MCE_BANKS) - 1:
+ /* MSR_IA32_MCx_{CTL, STATUS, ADDR, MISC, CTL2} */
+ case MSR_KVM_POLL_CONTROL:
+ return true;
+ case APIC_BASE_MSR ... APIC_BASE_MSR + 0xff:
+ /*
+ * x2APIC registers that are virtualized by the CPU can't be
+ * emulated, KVM doesn't have access to the virtual APIC page.
+ */
+ switch (index) {
+ case X2APIC_MSR(APIC_TASKPRI):
+ case X2APIC_MSR(APIC_PROCPRI):
+ case X2APIC_MSR(APIC_EOI):
+ case X2APIC_MSR(APIC_ISR) ... X2APIC_MSR(APIC_ISR + APIC_ISR_NR):
+ case X2APIC_MSR(APIC_TMR) ... X2APIC_MSR(APIC_TMR + APIC_ISR_NR):
+ case X2APIC_MSR(APIC_IRR) ... X2APIC_MSR(APIC_IRR + APIC_ISR_NR):
+ return false;
+ default:
+ return true;
+ }
+ default:
+ return false;
+ }
+}
+
+static bool tdx_is_read_only_msr(u32 index)
+{
+ return index == MSR_IA32_APICBASE || index == MSR_EFER ||
+ index == MSR_IA32_FEAT_CTL;
+}
+
+int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
+{
+ switch (msr->index) {
+ case MSR_IA32_FEAT_CTL:
+ /*
+ * MCE and MCA are advertised via cpuid. Guest kernel could
+ * check if LMCE is enabled or not.
+ */
+ msr->data = FEAT_CTL_LOCKED;
+ if (vcpu->arch.mcg_cap & MCG_LMCE_P)
+ msr->data |= FEAT_CTL_LMCE_ENABLED;
+ return 0;
+ case MSR_IA32_MCG_EXT_CTL:
+ if (!msr->host_initiated && !(vcpu->arch.mcg_cap & MCG_LMCE_P))
+ return 1;
+ msr->data = vcpu->arch.mcg_ext_ctl;
+ return 0;
+ default:
+ if (!tdx_has_emulated_msr(msr->index))
+ return 1;
+
+ return kvm_get_msr_common(vcpu, msr);
+ }
+}
+
+int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
+{
+ switch (msr->index) {
+ case MSR_IA32_MCG_EXT_CTL:
+ if ((!msr->host_initiated && !(vcpu->arch.mcg_cap & MCG_LMCE_P)) ||
+ (msr->data & ~MCG_EXT_CTL_LMCE_EN))
+ return 1;
+ vcpu->arch.mcg_ext_ctl = msr->data;
+ return 0;
+ default:
+ if (tdx_is_read_only_msr(msr->index))
+ return 1;
+
+ if (!tdx_has_emulated_msr(msr->index))
+ return 1;
+
+ return kvm_set_msr_common(vcpu, msr);
+ }
+}
+
+static int tdx_get_capabilities(struct kvm_tdx_cmd *cmd)
+{
+ const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf;
+ struct kvm_tdx_capabilities __user *user_caps;
+ struct kvm_tdx_capabilities *caps = NULL;
+ u32 nr_user_entries;
+ int ret = 0;
+
+ /* flags is reserved for future use */
+ if (cmd->flags)
+ return -EINVAL;
+
+ caps = kzalloc(sizeof(*caps) +
+ sizeof(struct kvm_cpuid_entry2) * td_conf->num_cpuid_config,
+ GFP_KERNEL);
+ if (!caps)
+ return -ENOMEM;
+
+ user_caps = u64_to_user_ptr(cmd->data);
+ if (get_user(nr_user_entries, &user_caps->cpuid.nent)) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ if (nr_user_entries < td_conf->num_cpuid_config) {
+ ret = -E2BIG;
+ goto out;
+ }
+
+ ret = init_kvm_tdx_caps(td_conf, caps);
+ if (ret)
+ goto out;
+
+ if (copy_to_user(user_caps, caps, sizeof(*caps))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ if (copy_to_user(user_caps->cpuid.entries, caps->cpuid.entries,
+ caps->cpuid.nent *
+ sizeof(caps->cpuid.entries[0])))
+ ret = -EFAULT;
+
+out:
+ /* kfree() accepts NULL. */
+ kfree(caps);
+ return ret;
+}
+
+/*
+ * KVM reports guest physical address in CPUID.0x800000008.EAX[23:16], which is
+ * similar to TDX's GPAW. Use this field as the interface for userspace to
+ * configure the GPAW and EPT level for TDs.
+ *
+ * Only values 48 and 52 are supported. Value 52 means GPAW-52 and EPT level
+ * 5, Value 48 means GPAW-48 and EPT level 4. For value 48, GPAW-48 is always
+ * supported. Value 52 is only supported when the platform supports 5 level
+ * EPT.
+ */
+static int setup_tdparams_eptp_controls(struct kvm_cpuid2 *cpuid,
+ struct td_params *td_params)
+{
+ const struct kvm_cpuid_entry2 *entry;
+ int guest_pa;
+
+ entry = kvm_find_cpuid_entry2(cpuid->entries, cpuid->nent, 0x80000008, 0);
+ if (!entry)
+ return -EINVAL;
+
+ guest_pa = tdx_get_guest_phys_addr_bits(entry->eax);
+
+ if (guest_pa != 48 && guest_pa != 52)
+ return -EINVAL;
+
+ if (guest_pa == 52 && !cpu_has_vmx_ept_5levels())
+ return -EINVAL;
+
+ td_params->eptp_controls = VMX_EPTP_MT_WB;
+ if (guest_pa == 52) {
+ td_params->eptp_controls |= VMX_EPTP_PWL_5;
+ td_params->config_flags |= TDX_CONFIG_FLAGS_MAX_GPAW;
+ } else {
+ td_params->eptp_controls |= VMX_EPTP_PWL_4;
+ }
+
+ return 0;
+}
+
+static int setup_tdparams_cpuids(struct kvm_cpuid2 *cpuid,
+ struct td_params *td_params)
+{
+ const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf;
+ const struct kvm_cpuid_entry2 *entry;
+ struct tdx_cpuid_value *value;
+ int i, copy_cnt = 0;
+
+ /*
+ * td_params.cpuid_values: The number and the order of cpuid_value must
+ * be same to the one of struct tdsysinfo.{num_cpuid_config, cpuid_configs}
+ * It's assumed that td_params was zeroed.
+ */
+ for (i = 0; i < td_conf->num_cpuid_config; i++) {
+ struct kvm_cpuid_entry2 tmp;
+
+ td_init_cpuid_entry2(&tmp, i);
+
+ entry = kvm_find_cpuid_entry2(cpuid->entries, cpuid->nent,
+ tmp.function, tmp.index);
+ if (!entry)
+ continue;
+
+ if (tdx_unsupported_cpuid(entry))
+ return -EINVAL;
+
+ copy_cnt++;
+
+ value = &td_params->cpuid_values[i];
+ value->eax = entry->eax;
+ value->ebx = entry->ebx;
+ value->ecx = entry->ecx;
+ value->edx = entry->edx;
+
+ /*
+ * TDX module does not accept nonzero bits 16..23 for the
+ * CPUID[0x80000008].EAX, see setup_tdparams_eptp_controls().
+ */
+ if (tmp.function == 0x80000008)
+ value->eax = tdx_set_guest_phys_addr_bits(value->eax, 0);
+ }
+
+ /*
+ * Rely on the TDX module to reject invalid configuration, but it can't
+ * check of leafs that don't have a proper slot in td_params->cpuid_values
+ * to stick then. So fail if there were entries that didn't get copied to
+ * td_params.
+ */
+ if (copy_cnt != cpuid->nent)
+ return -EINVAL;
+
+ return 0;
+}
+
+static int setup_tdparams(struct kvm *kvm, struct td_params *td_params,
+ struct kvm_tdx_init_vm *init_vm)
+{
+ const struct tdx_sys_info_td_conf *td_conf = &tdx_sysinfo->td_conf;
+ struct kvm_cpuid2 *cpuid = &init_vm->cpuid;
+ int ret;
+
+ if (kvm->created_vcpus)
+ return -EBUSY;
+
+ if (init_vm->attributes & ~tdx_get_supported_attrs(td_conf))
+ return -EINVAL;
+
+ if (init_vm->xfam & ~tdx_get_supported_xfam(td_conf))
+ return -EINVAL;
+
+ td_params->max_vcpus = kvm->max_vcpus;
+ td_params->attributes = init_vm->attributes | td_conf->attributes_fixed1;
+ td_params->xfam = init_vm->xfam | td_conf->xfam_fixed1;
+
+ td_params->config_flags = TDX_CONFIG_FLAGS_NO_RBP_MOD;
+ td_params->tsc_frequency = TDX_TSC_KHZ_TO_25MHZ(kvm->arch.default_tsc_khz);
+
+ ret = setup_tdparams_eptp_controls(cpuid, td_params);
+ if (ret)
+ return ret;
+
+ ret = setup_tdparams_cpuids(cpuid, td_params);
+ if (ret)
+ return ret;
+
+#define MEMCPY_SAME_SIZE(dst, src) \
+ do { \
+ BUILD_BUG_ON(sizeof(dst) != sizeof(src)); \
+ memcpy((dst), (src), sizeof(dst)); \
+ } while (0)
+
+ MEMCPY_SAME_SIZE(td_params->mrconfigid, init_vm->mrconfigid);
+ MEMCPY_SAME_SIZE(td_params->mrowner, init_vm->mrowner);
+ MEMCPY_SAME_SIZE(td_params->mrownerconfig, init_vm->mrownerconfig);
+
+ return 0;
+}
+
+static int __tdx_td_init(struct kvm *kvm, struct td_params *td_params,
+ u64 *seamcall_err)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ cpumask_var_t packages;
+ struct page **tdcs_pages = NULL;
+ struct page *tdr_page;
+ int ret, i;
+ u64 err, rcx;
+
+ *seamcall_err = 0;
+ ret = tdx_guest_keyid_alloc();
+ if (ret < 0)
+ return ret;
+ kvm_tdx->hkid = ret;
+ kvm_tdx->misc_cg = get_current_misc_cg();
+ ret = misc_cg_try_charge(MISC_CG_RES_TDX, kvm_tdx->misc_cg, 1);
+ if (ret)
+ goto free_hkid;
+
+ ret = -ENOMEM;
+
+ atomic_inc(&nr_configured_hkid);
+
+ tdr_page = alloc_page(GFP_KERNEL);
+ if (!tdr_page)
+ goto free_hkid;
+
+ kvm_tdx->td.tdcs_nr_pages = tdx_sysinfo->td_ctrl.tdcs_base_size / PAGE_SIZE;
+ /* TDVPS = TDVPR(4K page) + TDCX(multiple 4K pages), -1 for TDVPR. */
+ kvm_tdx->td.tdcx_nr_pages = tdx_sysinfo->td_ctrl.tdvps_base_size / PAGE_SIZE - 1;
+ tdcs_pages = kcalloc(kvm_tdx->td.tdcs_nr_pages, sizeof(*kvm_tdx->td.tdcs_pages),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!tdcs_pages)
+ goto free_tdr;
+
+ for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) {
+ tdcs_pages[i] = alloc_page(GFP_KERNEL);
+ if (!tdcs_pages[i])
+ goto free_tdcs;
+ }
+
+ if (!zalloc_cpumask_var(&packages, GFP_KERNEL))
+ goto free_tdcs;
+
+ cpus_read_lock();
+
+ /*
+ * Need at least one CPU of the package to be online in order to
+ * program all packages for host key id. Check it.
+ */
+ for_each_present_cpu(i)
+ cpumask_set_cpu(topology_physical_package_id(i), packages);
+ for_each_online_cpu(i)
+ cpumask_clear_cpu(topology_physical_package_id(i), packages);
+ if (!cpumask_empty(packages)) {
+ ret = -EIO;
+ /*
+ * Because it's hard for human operator to figure out the
+ * reason, warn it.
+ */
+#define MSG_ALLPKG "All packages need to have online CPU to create TD. Online CPU and retry.\n"
+ pr_warn_ratelimited(MSG_ALLPKG);
+ goto free_packages;
+ }
+
+ /*
+ * TDH.MNG.CREATE tries to grab the global TDX module and fails
+ * with TDX_OPERAND_BUSY when it fails to grab. Take the global
+ * lock to prevent it from failure.
+ */
+ mutex_lock(&tdx_lock);
+ kvm_tdx->td.tdr_page = tdr_page;
+ err = tdh_mng_create(&kvm_tdx->td, kvm_tdx->hkid);
+ mutex_unlock(&tdx_lock);
+
+ if (err == TDX_RND_NO_ENTROPY) {
+ ret = -EAGAIN;
+ goto free_packages;
+ }
+
+ if (WARN_ON_ONCE(err)) {
+ pr_tdx_error(TDH_MNG_CREATE, err);
+ ret = -EIO;
+ goto free_packages;
+ }
+
+ for_each_online_cpu(i) {
+ int pkg = topology_physical_package_id(i);
+
+ if (cpumask_test_and_set_cpu(pkg, packages))
+ continue;
+
+ /*
+ * Program the memory controller in the package with an
+ * encryption key associated to a TDX private host key id
+ * assigned to this TDR. Concurrent operations on same memory
+ * controller results in TDX_OPERAND_BUSY. No locking needed
+ * beyond the cpus_read_lock() above as it serializes against
+ * hotplug and the first online CPU of the package is always
+ * used. We never have two CPUs in the same socket trying to
+ * program the key.
+ */
+ ret = smp_call_on_cpu(i, tdx_do_tdh_mng_key_config,
+ kvm_tdx, true);
+ if (ret)
+ break;
+ }
+ cpus_read_unlock();
+ free_cpumask_var(packages);
+ if (ret) {
+ i = 0;
+ goto teardown;
+ }
+
+ kvm_tdx->td.tdcs_pages = tdcs_pages;
+ for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) {
+ err = tdh_mng_addcx(&kvm_tdx->td, tdcs_pages[i]);
+ if (err == TDX_RND_NO_ENTROPY) {
+ /* Here it's hard to allow userspace to retry. */
+ ret = -EAGAIN;
+ goto teardown;
+ }
+ if (WARN_ON_ONCE(err)) {
+ pr_tdx_error(TDH_MNG_ADDCX, err);
+ ret = -EIO;
+ goto teardown;
+ }
+ }
+
+ err = tdh_mng_init(&kvm_tdx->td, __pa(td_params), &rcx);
+ if ((err & TDX_SEAMCALL_STATUS_MASK) == TDX_OPERAND_INVALID) {
+ /*
+ * Because a user gives operands, don't warn.
+ * Return a hint to the user because it's sometimes hard for the
+ * user to figure out which operand is invalid. SEAMCALL status
+ * code includes which operand caused invalid operand error.
+ */
+ *seamcall_err = err;
+ ret = -EINVAL;
+ goto teardown;
+ } else if (WARN_ON_ONCE(err)) {
+ pr_tdx_error_1(TDH_MNG_INIT, err, rcx);
+ ret = -EIO;
+ goto teardown;
+ }
+
+ return 0;
+
+ /*
+ * The sequence for freeing resources from a partially initialized TD
+ * varies based on where in the initialization flow failure occurred.
+ * Simply use the full teardown and destroy, which naturally play nice
+ * with partial initialization.
+ */
+teardown:
+ /* Only free pages not yet added, so start at 'i' */
+ for (; i < kvm_tdx->td.tdcs_nr_pages; i++) {
+ if (tdcs_pages[i]) {
+ __free_page(tdcs_pages[i]);
+ tdcs_pages[i] = NULL;
+ }
+ }
+ if (!kvm_tdx->td.tdcs_pages)
+ kfree(tdcs_pages);
+
+ tdx_mmu_release_hkid(kvm);
+ tdx_reclaim_td_control_pages(kvm);
+
+ return ret;
+
+free_packages:
+ cpus_read_unlock();
+ free_cpumask_var(packages);
+
+free_tdcs:
+ for (i = 0; i < kvm_tdx->td.tdcs_nr_pages; i++) {
+ if (tdcs_pages[i])
+ __free_page(tdcs_pages[i]);
+ }
+ kfree(tdcs_pages);
+ kvm_tdx->td.tdcs_pages = NULL;
+
+free_tdr:
+ if (tdr_page)
+ __free_page(tdr_page);
+ kvm_tdx->td.tdr_page = 0;
+
+free_hkid:
+ tdx_hkid_free(kvm_tdx);
+
+ return ret;
+}
+
+static u64 tdx_td_metadata_field_read(struct kvm_tdx *tdx, u64 field_id,
+ u64 *data)
+{
+ u64 err;
+
+ err = tdh_mng_rd(&tdx->td, field_id, data);
+
+ return err;
+}
+
+#define TDX_MD_UNREADABLE_LEAF_MASK GENMASK(30, 7)
+#define TDX_MD_UNREADABLE_SUBLEAF_MASK GENMASK(31, 7)
+
+static int tdx_read_cpuid(struct kvm_vcpu *vcpu, u32 leaf, u32 sub_leaf,
+ bool sub_leaf_set, int *entry_index,
+ struct kvm_cpuid_entry2 *out)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
+ u64 field_id = TD_MD_FIELD_ID_CPUID_VALUES;
+ u64 ebx_eax, edx_ecx;
+ u64 err = 0;
+
+ if (sub_leaf > 0b1111111)
+ return -EINVAL;
+
+ if (*entry_index >= KVM_MAX_CPUID_ENTRIES)
+ return -EINVAL;
+
+ if (leaf & TDX_MD_UNREADABLE_LEAF_MASK ||
+ sub_leaf & TDX_MD_UNREADABLE_SUBLEAF_MASK)
+ return -EINVAL;
+
+ /*
+ * bit 23:17, REVSERVED: reserved, must be 0;
+ * bit 16, LEAF_31: leaf number bit 31;
+ * bit 15:9, LEAF_6_0: leaf number bits 6:0, leaf bits 30:7 are
+ * implicitly 0;
+ * bit 8, SUBLEAF_NA: sub-leaf not applicable flag;
+ * bit 7:1, SUBLEAF_6_0: sub-leaf number bits 6:0. If SUBLEAF_NA is 1,
+ * the SUBLEAF_6_0 is all-1.
+ * sub-leaf bits 31:7 are implicitly 0;
+ * bit 0, ELEMENT_I: Element index within field;
+ */
+ field_id |= ((leaf & 0x80000000) ? 1 : 0) << 16;
+ field_id |= (leaf & 0x7f) << 9;
+ if (sub_leaf_set)
+ field_id |= (sub_leaf & 0x7f) << 1;
+ else
+ field_id |= 0x1fe;
+
+ err = tdx_td_metadata_field_read(kvm_tdx, field_id, &ebx_eax);
+ if (err) //TODO check for specific errors
+ goto err_out;
+
+ out->eax = (u32) ebx_eax;
+ out->ebx = (u32) (ebx_eax >> 32);
+
+ field_id++;
+ err = tdx_td_metadata_field_read(kvm_tdx, field_id, &edx_ecx);
+ /*
+ * It's weird that reading edx_ecx fails while reading ebx_eax
+ * succeeded.
+ */
+ if (WARN_ON_ONCE(err))
+ goto err_out;
+
+ out->ecx = (u32) edx_ecx;
+ out->edx = (u32) (edx_ecx >> 32);
+
+ out->function = leaf;
+ out->index = sub_leaf;
+ out->flags |= sub_leaf_set ? KVM_CPUID_FLAG_SIGNIFCANT_INDEX : 0;
+
+ /*
+ * Work around missing support on old TDX modules, fetch
+ * guest maxpa from gfn_direct_bits.
+ */
+ if (leaf == 0x80000008) {
+ gpa_t gpa_bits = gfn_to_gpa(kvm_gfn_direct_bits(vcpu->kvm));
+ unsigned int g_maxpa = __ffs(gpa_bits) + 1;
+
+ out->eax = tdx_set_guest_phys_addr_bits(out->eax, g_maxpa);
+ }
+
+ (*entry_index)++;
+
+ return 0;
+
+err_out:
+ out->eax = 0;
+ out->ebx = 0;
+ out->ecx = 0;
+ out->edx = 0;
+
+ return -EIO;
+}
+
+static int tdx_td_init(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ struct kvm_tdx_init_vm *init_vm;
+ struct td_params *td_params = NULL;
+ int ret;
+
+ BUILD_BUG_ON(sizeof(*init_vm) != 256 + sizeof_field(struct kvm_tdx_init_vm, cpuid));
+ BUILD_BUG_ON(sizeof(struct td_params) != 1024);
+
+ if (kvm_tdx->state != TD_STATE_UNINITIALIZED)
+ return -EINVAL;
+
+ if (cmd->flags)
+ return -EINVAL;
+
+ init_vm = kmalloc(sizeof(*init_vm) +
+ sizeof(init_vm->cpuid.entries[0]) * KVM_MAX_CPUID_ENTRIES,
+ GFP_KERNEL);
+ if (!init_vm)
+ return -ENOMEM;
+
+ if (copy_from_user(init_vm, u64_to_user_ptr(cmd->data), sizeof(*init_vm))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ if (init_vm->cpuid.nent > KVM_MAX_CPUID_ENTRIES) {
+ ret = -E2BIG;
+ goto out;
+ }
+
+ if (copy_from_user(init_vm->cpuid.entries,
+ u64_to_user_ptr(cmd->data) + sizeof(*init_vm),
+ flex_array_size(init_vm, cpuid.entries, init_vm->cpuid.nent))) {
+ ret = -EFAULT;
+ goto out;
+ }
+
+ if (memchr_inv(init_vm->reserved, 0, sizeof(init_vm->reserved))) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ if (init_vm->cpuid.padding) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ td_params = kzalloc(sizeof(struct td_params), GFP_KERNEL);
+ if (!td_params) {
+ ret = -ENOMEM;
+ goto out;
+ }
+
+ ret = setup_tdparams(kvm, td_params, init_vm);
+ if (ret)
+ goto out;
+
+ ret = __tdx_td_init(kvm, td_params, &cmd->hw_error);
+ if (ret)
+ goto out;
+
+ kvm_tdx->tsc_offset = td_tdcs_exec_read64(kvm_tdx, TD_TDCS_EXEC_TSC_OFFSET);
+ kvm_tdx->tsc_multiplier = td_tdcs_exec_read64(kvm_tdx, TD_TDCS_EXEC_TSC_MULTIPLIER);
+ kvm_tdx->attributes = td_params->attributes;
+ kvm_tdx->xfam = td_params->xfam;
+
+ if (td_params->config_flags & TDX_CONFIG_FLAGS_MAX_GPAW)
+ kvm->arch.gfn_direct_bits = TDX_SHARED_BIT_PWL_5;
+ else
+ kvm->arch.gfn_direct_bits = TDX_SHARED_BIT_PWL_4;
+
+ kvm_tdx->state = TD_STATE_INITIALIZED;
+out:
+ /* kfree() accepts NULL. */
+ kfree(init_vm);
+ kfree(td_params);
+
+ return ret;
+}
+
+void tdx_flush_tlb_current(struct kvm_vcpu *vcpu)
+{
+ /*
+ * flush_tlb_current() is invoked when the first time for the vcpu to
+ * run or when root of shared EPT is invalidated.
+ * KVM only needs to flush shared EPT because the TDX module handles TLB
+ * invalidation for private EPT in tdh_vp_enter();
+ *
+ * A single context invalidation for shared EPT can be performed here.
+ * However, this single context invalidation requires the private EPTP
+ * rather than the shared EPTP to flush shared EPT, as shared EPT uses
+ * private EPTP as its ASID for TLB invalidation.
+ *
+ * To avoid reading back private EPTP, perform a global invalidation for
+ * shared EPT instead to keep this function simple.
+ */
+ ept_sync_global();
+}
+
+void tdx_flush_tlb_all(struct kvm_vcpu *vcpu)
+{
+ /*
+ * TDX has called tdx_track() in tdx_sept_remove_private_spte() to
+ * ensure that private EPT will be flushed on the next TD enter. No need
+ * to call tdx_track() here again even when this callback is a result of
+ * zapping private EPT.
+ *
+ * Due to the lack of the context to determine which EPT has been
+ * affected by zapping, invoke invept() directly here for both shared
+ * EPT and private EPT for simplicity, though it's not necessary for
+ * private EPT.
+ */
+ ept_sync_global();
+}
+
+static int tdx_td_finalize(struct kvm *kvm, struct kvm_tdx_cmd *cmd)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+
+ guard(mutex)(&kvm->slots_lock);
+
+ if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE)
+ return -EINVAL;
+ /*
+ * Pages are pending for KVM_TDX_INIT_MEM_REGION to issue
+ * TDH.MEM.PAGE.ADD().
+ */
+ if (atomic64_read(&kvm_tdx->nr_premapped))
+ return -EINVAL;
+
+ cmd->hw_error = tdh_mr_finalize(&kvm_tdx->td);
+ if (tdx_operand_busy(cmd->hw_error))
+ return -EBUSY;
+ if (KVM_BUG_ON(cmd->hw_error, kvm)) {
+ pr_tdx_error(TDH_MR_FINALIZE, cmd->hw_error);
+ return -EIO;
+ }
+
+ kvm_tdx->state = TD_STATE_RUNNABLE;
+ /* TD_STATE_RUNNABLE must be set before 'pre_fault_allowed' */
+ smp_wmb();
+ kvm->arch.pre_fault_allowed = true;
+ return 0;
+}
+
+int tdx_vm_ioctl(struct kvm *kvm, void __user *argp)
+{
+ struct kvm_tdx_cmd tdx_cmd;
+ int r;
+
+ if (copy_from_user(&tdx_cmd, argp, sizeof(struct kvm_tdx_cmd)))
+ return -EFAULT;
+
+ /*
+ * Userspace should never set hw_error. It is used to fill
+ * hardware-defined error by the kernel.
+ */
+ if (tdx_cmd.hw_error)
+ return -EINVAL;
+
+ mutex_lock(&kvm->lock);
+
+ switch (tdx_cmd.id) {
+ case KVM_TDX_CAPABILITIES:
+ r = tdx_get_capabilities(&tdx_cmd);
+ break;
+ case KVM_TDX_INIT_VM:
+ r = tdx_td_init(kvm, &tdx_cmd);
+ break;
+ case KVM_TDX_FINALIZE_VM:
+ r = tdx_td_finalize(kvm, &tdx_cmd);
+ break;
+ default:
+ r = -EINVAL;
+ goto out;
+ }
+
+ if (copy_to_user(argp, &tdx_cmd, sizeof(struct kvm_tdx_cmd)))
+ r = -EFAULT;
+
+out:
+ mutex_unlock(&kvm->lock);
+ return r;
+}
+
+/* VMM can pass one 64bit auxiliary data to vcpu via RCX for guest BIOS. */
+static int tdx_td_vcpu_init(struct kvm_vcpu *vcpu, u64 vcpu_rcx)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ struct page *page;
+ int ret, i;
+ u64 err;
+
+ page = alloc_page(GFP_KERNEL);
+ if (!page)
+ return -ENOMEM;
+ tdx->vp.tdvpr_page = page;
+
+ tdx->vp.tdcx_pages = kcalloc(kvm_tdx->td.tdcx_nr_pages, sizeof(*tdx->vp.tdcx_pages),
+ GFP_KERNEL);
+ if (!tdx->vp.tdcx_pages) {
+ ret = -ENOMEM;
+ goto free_tdvpr;
+ }
+
+ for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) {
+ page = alloc_page(GFP_KERNEL);
+ if (!page) {
+ ret = -ENOMEM;
+ goto free_tdcx;
+ }
+ tdx->vp.tdcx_pages[i] = page;
+ }
+
+ err = tdh_vp_create(&kvm_tdx->td, &tdx->vp);
+ if (KVM_BUG_ON(err, vcpu->kvm)) {
+ ret = -EIO;
+ pr_tdx_error(TDH_VP_CREATE, err);
+ goto free_tdcx;
+ }
+
+ for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) {
+ err = tdh_vp_addcx(&tdx->vp, tdx->vp.tdcx_pages[i]);
+ if (KVM_BUG_ON(err, vcpu->kvm)) {
+ pr_tdx_error(TDH_VP_ADDCX, err);
+ /*
+ * Pages already added are reclaimed by the vcpu_free
+ * method, but the rest are freed here.
+ */
+ for (; i < kvm_tdx->td.tdcx_nr_pages; i++) {
+ __free_page(tdx->vp.tdcx_pages[i]);
+ tdx->vp.tdcx_pages[i] = NULL;
+ }
+ return -EIO;
+ }
+ }
+
+ err = tdh_vp_init(&tdx->vp, vcpu_rcx, vcpu->vcpu_id);
+ if (KVM_BUG_ON(err, vcpu->kvm)) {
+ pr_tdx_error(TDH_VP_INIT, err);
+ return -EIO;
+ }
+
+ vcpu->arch.mp_state = KVM_MP_STATE_RUNNABLE;
+
+ return 0;
+
+free_tdcx:
+ for (i = 0; i < kvm_tdx->td.tdcx_nr_pages; i++) {
+ if (tdx->vp.tdcx_pages[i])
+ __free_page(tdx->vp.tdcx_pages[i]);
+ tdx->vp.tdcx_pages[i] = NULL;
+ }
+ kfree(tdx->vp.tdcx_pages);
+ tdx->vp.tdcx_pages = NULL;
+
+free_tdvpr:
+ if (tdx->vp.tdvpr_page)
+ __free_page(tdx->vp.tdvpr_page);
+ tdx->vp.tdvpr_page = 0;
+
+ return ret;
+}
+
+/* Sometimes reads multipple subleafs. Return how many enties were written. */
+static int tdx_vcpu_get_cpuid_leaf(struct kvm_vcpu *vcpu, u32 leaf, int *entry_index,
+ struct kvm_cpuid_entry2 *output_e)
+{
+ int sub_leaf = 0;
+ int ret;
+
+ /* First try without a subleaf */
+ ret = tdx_read_cpuid(vcpu, leaf, 0, false, entry_index, output_e);
+
+ /* If success, or invalid leaf, just give up */
+ if (ret != -EIO)
+ return ret;
+
+ /*
+ * If the try without a subleaf failed, try reading subleafs until
+ * failure. The TDX module only supports 6 bits of subleaf index.
+ */
+ while (1) {
+ /* Keep reading subleafs until there is a failure. */
+ if (tdx_read_cpuid(vcpu, leaf, sub_leaf, true, entry_index, output_e))
+ return !sub_leaf;
+
+ sub_leaf++;
+ output_e++;
+ }
+
+ return 0;
+}
+
+static int tdx_vcpu_get_cpuid(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd)
+{
+ struct kvm_cpuid2 __user *output, *td_cpuid;
+ int r = 0, i = 0, leaf;
+ u32 level;
+
+ output = u64_to_user_ptr(cmd->data);
+ td_cpuid = kzalloc(sizeof(*td_cpuid) +
+ sizeof(output->entries[0]) * KVM_MAX_CPUID_ENTRIES,
+ GFP_KERNEL);
+ if (!td_cpuid)
+ return -ENOMEM;
+
+ if (copy_from_user(td_cpuid, output, sizeof(*output))) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ /* Read max CPUID for normal range */
+ if (tdx_vcpu_get_cpuid_leaf(vcpu, 0, &i, &td_cpuid->entries[i])) {
+ r = -EIO;
+ goto out;
+ }
+ level = td_cpuid->entries[0].eax;
+
+ for (leaf = 1; leaf <= level; leaf++)
+ tdx_vcpu_get_cpuid_leaf(vcpu, leaf, &i, &td_cpuid->entries[i]);
+
+ /* Read max CPUID for extended range */
+ if (tdx_vcpu_get_cpuid_leaf(vcpu, 0x80000000, &i, &td_cpuid->entries[i])) {
+ r = -EIO;
+ goto out;
+ }
+ level = td_cpuid->entries[i - 1].eax;
+
+ for (leaf = 0x80000001; leaf <= level; leaf++)
+ tdx_vcpu_get_cpuid_leaf(vcpu, leaf, &i, &td_cpuid->entries[i]);
+
+ if (td_cpuid->nent < i)
+ r = -E2BIG;
+ td_cpuid->nent = i;
+
+ if (copy_to_user(output, td_cpuid, sizeof(*output))) {
+ r = -EFAULT;
+ goto out;
+ }
+
+ if (r == -E2BIG)
+ goto out;
+
+ if (copy_to_user(output->entries, td_cpuid->entries,
+ td_cpuid->nent * sizeof(struct kvm_cpuid_entry2)))
+ r = -EFAULT;
+
+out:
+ kfree(td_cpuid);
+
+ return r;
+}
+
+static int tdx_vcpu_init(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd)
+{
+ u64 apic_base;
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ int ret;
+
+ if (cmd->flags)
+ return -EINVAL;
+
+ if (tdx->state != VCPU_TD_STATE_UNINITIALIZED)
+ return -EINVAL;
+
+ /*
+ * TDX requires X2APIC, userspace is responsible for configuring guest
+ * CPUID accordingly.
+ */
+ apic_base = APIC_DEFAULT_PHYS_BASE | LAPIC_MODE_X2APIC |
+ (kvm_vcpu_is_reset_bsp(vcpu) ? MSR_IA32_APICBASE_BSP : 0);
+ if (kvm_apic_set_base(vcpu, apic_base, true))
+ return -EINVAL;
+
+ ret = tdx_td_vcpu_init(vcpu, (u64)cmd->data);
+ if (ret)
+ return ret;
+
+ td_vmcs_write16(tdx, POSTED_INTR_NV, POSTED_INTR_VECTOR);
+ td_vmcs_write64(tdx, POSTED_INTR_DESC_ADDR, __pa(&tdx->vt.pi_desc));
+ td_vmcs_setbit32(tdx, PIN_BASED_VM_EXEC_CONTROL, PIN_BASED_POSTED_INTR);
+
+ tdx->state = VCPU_TD_STATE_INITIALIZED;
+
+ return 0;
+}
+
+void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
+{
+ /*
+ * Yell on INIT, as TDX doesn't support INIT, i.e. KVM should drop all
+ * INIT events.
+ *
+ * Defer initializing vCPU for RESET state until KVM_TDX_INIT_VCPU, as
+ * userspace needs to define the vCPU model before KVM can initialize
+ * vCPU state, e.g. to enable x2APIC.
+ */
+ WARN_ON_ONCE(init_event);
+}
+
+struct tdx_gmem_post_populate_arg {
+ struct kvm_vcpu *vcpu;
+ __u32 flags;
+};
+
+static int tdx_gmem_post_populate(struct kvm *kvm, gfn_t gfn, kvm_pfn_t pfn,
+ void __user *src, int order, void *_arg)
+{
+ u64 error_code = PFERR_GUEST_FINAL_MASK | PFERR_PRIVATE_ACCESS;
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ struct tdx_gmem_post_populate_arg *arg = _arg;
+ struct kvm_vcpu *vcpu = arg->vcpu;
+ gpa_t gpa = gfn_to_gpa(gfn);
+ u8 level = PG_LEVEL_4K;
+ struct page *src_page;
+ int ret, i;
+ u64 err, entry, level_state;
+
+ /*
+ * Get the source page if it has been faulted in. Return failure if the
+ * source page has been swapped out or unmapped in primary memory.
+ */
+ ret = get_user_pages_fast((unsigned long)src, 1, 0, &src_page);
+ if (ret < 0)
+ return ret;
+ if (ret != 1)
+ return -ENOMEM;
+
+ ret = kvm_tdp_map_page(vcpu, gpa, error_code, &level);
+ if (ret < 0)
+ goto out;
+
+ /*
+ * The private mem cannot be zapped after kvm_tdp_map_page()
+ * because all paths are covered by slots_lock and the
+ * filemap invalidate lock. Check that they are indeed enough.
+ */
+ if (IS_ENABLED(CONFIG_KVM_PROVE_MMU)) {
+ scoped_guard(read_lock, &kvm->mmu_lock) {
+ if (KVM_BUG_ON(!kvm_tdp_mmu_gpa_is_mapped(vcpu, gpa), kvm)) {
+ ret = -EIO;
+ goto out;
+ }
+ }
+ }
+
+ ret = 0;
+ err = tdh_mem_page_add(&kvm_tdx->td, gpa, pfn_to_page(pfn),
+ src_page, &entry, &level_state);
+ if (err) {
+ ret = unlikely(tdx_operand_busy(err)) ? -EBUSY : -EIO;
+ goto out;
+ }
+
+ if (!KVM_BUG_ON(!atomic64_read(&kvm_tdx->nr_premapped), kvm))
+ atomic64_dec(&kvm_tdx->nr_premapped);
+
+ if (arg->flags & KVM_TDX_MEASURE_MEMORY_REGION) {
+ for (i = 0; i < PAGE_SIZE; i += TDX_EXTENDMR_CHUNKSIZE) {
+ err = tdh_mr_extend(&kvm_tdx->td, gpa + i, &entry,
+ &level_state);
+ if (err) {
+ ret = -EIO;
+ break;
+ }
+ }
+ }
+
+out:
+ put_page(src_page);
+ return ret;
+}
+
+static int tdx_vcpu_init_mem_region(struct kvm_vcpu *vcpu, struct kvm_tdx_cmd *cmd)
+{
+ struct vcpu_tdx *tdx = to_tdx(vcpu);
+ struct kvm *kvm = vcpu->kvm;
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(kvm);
+ struct kvm_tdx_init_mem_region region;
+ struct tdx_gmem_post_populate_arg arg;
+ long gmem_ret;
+ int ret;
+
+ if (tdx->state != VCPU_TD_STATE_INITIALIZED)
+ return -EINVAL;
+
+ guard(mutex)(&kvm->slots_lock);
+
+ /* Once TD is finalized, the initial guest memory is fixed. */
+ if (kvm_tdx->state == TD_STATE_RUNNABLE)
+ return -EINVAL;
+
+ if (cmd->flags & ~KVM_TDX_MEASURE_MEMORY_REGION)
+ return -EINVAL;
+
+ if (copy_from_user(&region, u64_to_user_ptr(cmd->data), sizeof(region)))
+ return -EFAULT;
+
+ if (!PAGE_ALIGNED(region.source_addr) || !PAGE_ALIGNED(region.gpa) ||
+ !region.nr_pages ||
+ region.gpa + (region.nr_pages << PAGE_SHIFT) <= region.gpa ||
+ !vt_is_tdx_private_gpa(kvm, region.gpa) ||
+ !vt_is_tdx_private_gpa(kvm, region.gpa + (region.nr_pages << PAGE_SHIFT) - 1))
+ return -EINVAL;
+
+ kvm_mmu_reload(vcpu);
+ ret = 0;
+ while (region.nr_pages) {
+ if (signal_pending(current)) {
+ ret = -EINTR;
+ break;
+ }
+
+ arg = (struct tdx_gmem_post_populate_arg) {
+ .vcpu = vcpu,
+ .flags = cmd->flags,
+ };
+ gmem_ret = kvm_gmem_populate(kvm, gpa_to_gfn(region.gpa),
+ u64_to_user_ptr(region.source_addr),
+ 1, tdx_gmem_post_populate, &arg);
+ if (gmem_ret < 0) {
+ ret = gmem_ret;
+ break;
+ }
+
+ if (gmem_ret != 1) {
+ ret = -EIO;
+ break;
+ }
+
+ region.source_addr += PAGE_SIZE;
+ region.gpa += PAGE_SIZE;
+ region.nr_pages--;
+
+ cond_resched();
+ }
+
+ if (copy_to_user(u64_to_user_ptr(cmd->data), &region, sizeof(region)))
+ ret = -EFAULT;
+ return ret;
+}
+
+int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp)
+{
+ struct kvm_tdx *kvm_tdx = to_kvm_tdx(vcpu->kvm);
+ struct kvm_tdx_cmd cmd;
+ int ret;
+
+ if (!is_hkid_assigned(kvm_tdx) || kvm_tdx->state == TD_STATE_RUNNABLE)
+ return -EINVAL;
+
+ if (copy_from_user(&cmd, argp, sizeof(cmd)))
+ return -EFAULT;
+
+ if (cmd.hw_error)
+ return -EINVAL;
+
+ switch (cmd.id) {
+ case KVM_TDX_INIT_VCPU:
+ ret = tdx_vcpu_init(vcpu, &cmd);
+ break;
+ case KVM_TDX_INIT_MEM_REGION:
+ ret = tdx_vcpu_init_mem_region(vcpu, &cmd);
+ break;
+ case KVM_TDX_GET_CPUID:
+ ret = tdx_vcpu_get_cpuid(vcpu, &cmd);
+ break;
+ default:
+ ret = -EINVAL;
+ break;
+ }
+
+ return ret;
+}
+
+int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn)
+{
+ return PG_LEVEL_4K;
+}
+
+static int tdx_online_cpu(unsigned int cpu)
+{
+ unsigned long flags;
+ int r;
+
+ /* Sanity check CPU is already in post-VMXON */
+ WARN_ON_ONCE(!(cr4_read_shadow() & X86_CR4_VMXE));
+
+ local_irq_save(flags);
+ r = tdx_cpu_enable();
+ local_irq_restore(flags);
+
+ return r;
+}
+
+static int tdx_offline_cpu(unsigned int cpu)
+{
+ int i;
+
+ /* No TD is running. Allow any cpu to be offline. */
+ if (!atomic_read(&nr_configured_hkid))
+ return 0;
+
+ /*
+ * In order to reclaim TDX HKID, (i.e. when deleting guest TD), need to
+ * call TDH.PHYMEM.PAGE.WBINVD on all packages to program all memory
+ * controller with pconfig. If we have active TDX HKID, refuse to
+ * offline the last online cpu.
+ */
+ for_each_online_cpu(i) {
+ /*
+ * Found another online cpu on the same package.
+ * Allow to offline.
+ */
+ if (i != cpu && topology_physical_package_id(i) ==
+ topology_physical_package_id(cpu))
+ return 0;
+ }
+
+ /*
+ * This is the last cpu of this package. Don't offline it.
+ *
+ * Because it's hard for human operator to understand the
+ * reason, warn it.
+ */
+#define MSG_ALLPKG_ONLINE \
+ "TDX requires all packages to have an online CPU. Delete all TDs in order to offline all CPUs of a package.\n"
+ pr_warn_ratelimited(MSG_ALLPKG_ONLINE);
+ return -EBUSY;
+}
+
+static void __do_tdx_cleanup(void)
+{
+ /*
+ * Once TDX module is initialized, it cannot be disabled and
+ * re-initialized again w/o runtime update (which isn't
+ * supported by kernel). Only need to remove the cpuhp here.
+ * The TDX host core code tracks TDX status and can handle
+ * 'multiple enabling' scenario.
+ */
+ WARN_ON_ONCE(!tdx_cpuhp_state);
+ cpuhp_remove_state_nocalls_cpuslocked(tdx_cpuhp_state);
+ tdx_cpuhp_state = 0;
+}
+
+static void __tdx_cleanup(void)
+{
+ cpus_read_lock();
+ __do_tdx_cleanup();
+ cpus_read_unlock();
+}
+
+static int __init __do_tdx_bringup(void)
+{
+ int r;
+
+ /*
+ * TDX-specific cpuhp callback to call tdx_cpu_enable() on all
+ * online CPUs before calling tdx_enable(), and on any new
+ * going-online CPU to make sure it is ready for TDX guest.
+ */
+ r = cpuhp_setup_state_cpuslocked(CPUHP_AP_ONLINE_DYN,
+ "kvm/cpu/tdx:online",
+ tdx_online_cpu, tdx_offline_cpu);
+ if (r < 0)
+ return r;
+
+ tdx_cpuhp_state = r;
+
+ r = tdx_enable();
+ if (r)
+ __do_tdx_cleanup();
+
+ return r;
+}
+
+static int __init __tdx_bringup(void)
+{
+ const struct tdx_sys_info_td_conf *td_conf;
+ int r, i;
+
+ for (i = 0; i < ARRAY_SIZE(tdx_uret_msrs); i++) {
+ /*
+ * Check if MSRs (tdx_uret_msrs) can be saved/restored
+ * before returning to user space.
+ *
+ * this_cpu_ptr(user_return_msrs)->registered isn't checked
+ * because the registration is done at vcpu runtime by
+ * tdx_user_return_msr_update_cache().
+ */
+ tdx_uret_msrs[i].slot = kvm_find_user_return_msr(tdx_uret_msrs[i].msr);
+ if (tdx_uret_msrs[i].slot == -1) {
+ /* If any MSR isn't supported, it is a KVM bug */
+ pr_err("MSR %x isn't included by kvm_find_user_return_msr\n",
+ tdx_uret_msrs[i].msr);
+ return -EIO;
+ }
+ }
+
+ /*
+ * Enabling TDX requires enabling hardware virtualization first,
+ * as making SEAMCALLs requires CPU being in post-VMXON state.
+ */
+ r = kvm_enable_virtualization();
+ if (r)
+ return r;
+
+ cpus_read_lock();
+ r = __do_tdx_bringup();
+ cpus_read_unlock();
+
+ if (r)
+ goto tdx_bringup_err;
+
+ /* Get TDX global information for later use */
+ tdx_sysinfo = tdx_get_sysinfo();
+ if (WARN_ON_ONCE(!tdx_sysinfo)) {
+ r = -EINVAL;
+ goto get_sysinfo_err;
+ }
+
+ /* Check TDX module and KVM capabilities */
+ if (!tdx_get_supported_attrs(&tdx_sysinfo->td_conf) ||
+ !tdx_get_supported_xfam(&tdx_sysinfo->td_conf))
+ goto get_sysinfo_err;
+
+ if (!(tdx_sysinfo->features.tdx_features0 & MD_FIELD_ID_FEATURES0_TOPOLOGY_ENUM))
+ goto get_sysinfo_err;
+
+ /*
+ * TDX has its own limit of maximum vCPUs it can support for all
+ * TDX guests in addition to KVM_MAX_VCPUS. Userspace needs to
+ * query TDX guest's maximum vCPUs by checking KVM_CAP_MAX_VCPU
+ * extension on per-VM basis.
+ *
+ * TDX module reports such limit via the MAX_VCPU_PER_TD global
+ * metadata. Different modules may report different values.
+ * Some old module may also not support this metadata (in which
+ * case this limit is U16_MAX).
+ *
+ * In practice, the reported value reflects the maximum logical
+ * CPUs that ALL the platforms that the module supports can
+ * possibly have.
+ *
+ * Simply forwarding the MAX_VCPU_PER_TD to userspace could
+ * result in an unpredictable ABI. KVM instead always advertise
+ * the number of logical CPUs the platform has as the maximum
+ * vCPUs for TDX guests.
+ *
+ * Make sure MAX_VCPU_PER_TD reported by TDX module is not
+ * smaller than the number of logical CPUs, otherwise KVM will
+ * report an unsupported value to userspace.
+ *
+ * Note, a platform with TDX enabled in the BIOS cannot support
+ * physical CPU hotplug, and TDX requires the BIOS has marked
+ * all logical CPUs in MADT table as enabled. Just use
+ * num_present_cpus() for the number of logical CPUs.
+ */
+ td_conf = &tdx_sysinfo->td_conf;
+ if (td_conf->max_vcpus_per_td < num_present_cpus()) {
+ pr_err("Disable TDX: MAX_VCPU_PER_TD (%u) smaller than number of logical CPUs (%u).\n",
+ td_conf->max_vcpus_per_td, num_present_cpus());
+ r = -EINVAL;
+ goto get_sysinfo_err;
+ }
+
+ if (misc_cg_set_capacity(MISC_CG_RES_TDX, tdx_get_nr_guest_keyids())) {
+ r = -EINVAL;
+ goto get_sysinfo_err;
+ }
+
+ /*
+ * Leave hardware virtualization enabled after TDX is enabled
+ * successfully. TDX CPU hotplug depends on this.
+ */
+ return 0;
+
+get_sysinfo_err:
+ __tdx_cleanup();
+tdx_bringup_err:
+ kvm_disable_virtualization();
+ return r;
+}
+
+void tdx_cleanup(void)
+{
+ if (enable_tdx) {
+ misc_cg_set_capacity(MISC_CG_RES_TDX, 0);
+ __tdx_cleanup();
+ kvm_disable_virtualization();
+ }
+}
+
+int __init tdx_bringup(void)
+{
+ int r, i;
+
+ /* tdx_disable_virtualization_cpu() uses associated_tdvcpus. */
+ for_each_possible_cpu(i)
+ INIT_LIST_HEAD(&per_cpu(associated_tdvcpus, i));
+
+ if (!enable_tdx)
+ return 0;
+
+ if (!enable_ept) {
+ pr_err("EPT is required for TDX\n");
+ goto success_disable_tdx;
+ }
+
+ if (!tdp_mmu_enabled || !enable_mmio_caching || !enable_ept_ad_bits) {
+ pr_err("TDP MMU and MMIO caching and EPT A/D bit is required for TDX\n");
+ goto success_disable_tdx;
+ }
+
+ if (!enable_apicv) {
+ pr_err("APICv is required for TDX\n");
+ goto success_disable_tdx;
+ }
+
+ if (!cpu_feature_enabled(X86_FEATURE_OSXSAVE)) {
+ pr_err("tdx: OSXSAVE is required for TDX\n");
+ goto success_disable_tdx;
+ }
+
+ if (!cpu_feature_enabled(X86_FEATURE_MOVDIR64B)) {
+ pr_err("tdx: MOVDIR64B is required for TDX\n");
+ goto success_disable_tdx;
+ }
+
+ if (!cpu_feature_enabled(X86_FEATURE_SELFSNOOP)) {
+ pr_err("Self-snoop is required for TDX\n");
+ goto success_disable_tdx;
+ }
+
+ if (!cpu_feature_enabled(X86_FEATURE_TDX_HOST_PLATFORM)) {
+ pr_err("tdx: no TDX private KeyIDs available\n");
+ goto success_disable_tdx;
+ }
+
+ if (!enable_virt_at_load) {
+ pr_err("tdx: tdx requires kvm.enable_virt_at_load=1\n");
+ goto success_disable_tdx;
+ }
+
+ /*
+ * Ideally KVM should probe whether TDX module has been loaded
+ * first and then try to bring it up. But TDX needs to use SEAMCALL
+ * to probe whether the module is loaded (there is no CPUID or MSR
+ * for that), and making SEAMCALL requires enabling virtualization
+ * first, just like the rest steps of bringing up TDX module.
+ *
+ * So, for simplicity do everything in __tdx_bringup(); the first
+ * SEAMCALL will return -ENODEV when the module is not loaded. The
+ * only complication is having to make sure that initialization
+ * SEAMCALLs don't return TDX_SEAMCALL_VMFAILINVALID in other
+ * cases.
+ */
+ r = __tdx_bringup();
+ if (r) {
+ /*
+ * Disable TDX only but don't fail to load module if the TDX
+ * module could not be loaded. No need to print message saying
+ * "module is not loaded" because it was printed when the first
+ * SEAMCALL failed. Don't bother unwinding the S-EPT hooks or
+ * vm_size, as kvm_x86_ops have already been finalized (and are
+ * intentionally not exported). The S-EPT code is unreachable,
+ * and allocating a few more bytes per VM in a should-be-rare
+ * failure scenario is a non-issue.
+ */
+ if (r == -ENODEV)
+ goto success_disable_tdx;
+
+ enable_tdx = 0;
+ }
+
+ return r;
+
+success_disable_tdx:
+ enable_tdx = 0;
+ return 0;
+}
+
+void __init tdx_hardware_setup(void)
+{
+ KVM_SANITY_CHECK_VM_STRUCT_SIZE(kvm_tdx);
+
+ /*
+ * Note, if the TDX module can't be loaded, KVM TDX support will be
+ * disabled but KVM will continue loading (see tdx_bringup()).
+ */
+ vt_x86_ops.vm_size = max_t(unsigned int, vt_x86_ops.vm_size, sizeof(struct kvm_tdx));
+
+ vt_x86_ops.link_external_spt = tdx_sept_link_private_spt;
+ vt_x86_ops.set_external_spte = tdx_sept_set_private_spte;
+ vt_x86_ops.free_external_spt = tdx_sept_free_private_spt;
+ vt_x86_ops.remove_external_spte = tdx_sept_remove_private_spte;
+ vt_x86_ops.protected_apic_has_interrupt = tdx_protected_apic_has_interrupt;
+}
diff --git a/arch/x86/kvm/vmx/tdx.h b/arch/x86/kvm/vmx/tdx.h
new file mode 100644
index 000000000000..ca39a9391db1
--- /dev/null
+++ b/arch/x86/kvm/vmx/tdx.h
@@ -0,0 +1,205 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __KVM_X86_VMX_TDX_H
+#define __KVM_X86_VMX_TDX_H
+
+#include "tdx_arch.h"
+#include "tdx_errno.h"
+
+#ifdef CONFIG_KVM_INTEL_TDX
+#include "common.h"
+
+void tdx_hardware_setup(void);
+int tdx_bringup(void);
+void tdx_cleanup(void);
+
+extern bool enable_tdx;
+
+/* TDX module hardware states. These follow the TDX module OP_STATEs. */
+enum kvm_tdx_state {
+ TD_STATE_UNINITIALIZED = 0,
+ TD_STATE_INITIALIZED,
+ TD_STATE_RUNNABLE,
+};
+
+struct kvm_tdx {
+ struct kvm kvm;
+
+ struct misc_cg *misc_cg;
+ int hkid;
+ enum kvm_tdx_state state;
+
+ u64 attributes;
+ u64 xfam;
+
+ u64 tsc_offset;
+ u64 tsc_multiplier;
+
+ struct tdx_td td;
+
+ /* For KVM_TDX_INIT_MEM_REGION. */
+ atomic64_t nr_premapped;
+
+ /*
+ * Prevent vCPUs from TD entry to ensure SEPT zap related SEAMCALLs do
+ * not contend with tdh_vp_enter() and TDCALLs.
+ * Set/unset is protected with kvm->mmu_lock.
+ */
+ bool wait_for_sept_zap;
+};
+
+/* TDX module vCPU states */
+enum vcpu_tdx_state {
+ VCPU_TD_STATE_UNINITIALIZED = 0,
+ VCPU_TD_STATE_INITIALIZED,
+};
+
+struct vcpu_tdx {
+ struct kvm_vcpu vcpu;
+ struct vcpu_vt vt;
+ u64 ext_exit_qualification;
+ gpa_t exit_gpa;
+ struct tdx_module_args vp_enter_args;
+
+ struct tdx_vp vp;
+
+ struct list_head cpu_list;
+
+ u64 vp_enter_ret;
+
+ enum vcpu_tdx_state state;
+ bool guest_entered;
+
+ u64 map_gpa_next;
+ u64 map_gpa_end;
+};
+
+void tdh_vp_rd_failed(struct vcpu_tdx *tdx, char *uclass, u32 field, u64 err);
+void tdh_vp_wr_failed(struct vcpu_tdx *tdx, char *uclass, char *op, u32 field,
+ u64 val, u64 err);
+
+static __always_inline u64 td_tdcs_exec_read64(struct kvm_tdx *kvm_tdx, u32 field)
+{
+ u64 err, data;
+
+ err = tdh_mng_rd(&kvm_tdx->td, TDCS_EXEC(field), &data);
+ if (unlikely(err)) {
+ pr_err("TDH_MNG_RD[EXEC.0x%x] failed: 0x%llx\n", field, err);
+ return 0;
+ }
+ return data;
+}
+
+static __always_inline void tdvps_vmcs_check(u32 field, u8 bits)
+{
+#define VMCS_ENC_ACCESS_TYPE_MASK 0x1UL
+#define VMCS_ENC_ACCESS_TYPE_FULL 0x0UL
+#define VMCS_ENC_ACCESS_TYPE_HIGH 0x1UL
+#define VMCS_ENC_ACCESS_TYPE(field) ((field) & VMCS_ENC_ACCESS_TYPE_MASK)
+
+ /* TDX is 64bit only. HIGH field isn't supported. */
+ BUILD_BUG_ON_MSG(__builtin_constant_p(field) &&
+ VMCS_ENC_ACCESS_TYPE(field) == VMCS_ENC_ACCESS_TYPE_HIGH,
+ "Read/Write to TD VMCS *_HIGH fields not supported");
+
+ BUILD_BUG_ON(bits != 16 && bits != 32 && bits != 64);
+
+#define VMCS_ENC_WIDTH_MASK GENMASK(14, 13)
+#define VMCS_ENC_WIDTH_16BIT (0UL << 13)
+#define VMCS_ENC_WIDTH_64BIT (1UL << 13)
+#define VMCS_ENC_WIDTH_32BIT (2UL << 13)
+#define VMCS_ENC_WIDTH_NATURAL (3UL << 13)
+#define VMCS_ENC_WIDTH(field) ((field) & VMCS_ENC_WIDTH_MASK)
+
+ /* TDX is 64bit only. i.e. natural width = 64bit. */
+ BUILD_BUG_ON_MSG(bits != 64 && __builtin_constant_p(field) &&
+ (VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_64BIT ||
+ VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_NATURAL),
+ "Invalid TD VMCS access for 64-bit field");
+ BUILD_BUG_ON_MSG(bits != 32 && __builtin_constant_p(field) &&
+ VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_32BIT,
+ "Invalid TD VMCS access for 32-bit field");
+ BUILD_BUG_ON_MSG(bits != 16 && __builtin_constant_p(field) &&
+ VMCS_ENC_WIDTH(field) == VMCS_ENC_WIDTH_16BIT,
+ "Invalid TD VMCS access for 16-bit field");
+}
+
+static __always_inline void tdvps_management_check(u64 field, u8 bits) {}
+static __always_inline void tdvps_state_non_arch_check(u64 field, u8 bits) {}
+
+#define TDX_BUILD_TDVPS_ACCESSORS(bits, uclass, lclass) \
+static __always_inline u##bits td_##lclass##_read##bits(struct vcpu_tdx *tdx, \
+ u32 field) \
+{ \
+ u64 err, data; \
+ \
+ tdvps_##lclass##_check(field, bits); \
+ err = tdh_vp_rd(&tdx->vp, TDVPS_##uclass(field), &data); \
+ if (unlikely(err)) { \
+ tdh_vp_rd_failed(tdx, #uclass, field, err); \
+ return 0; \
+ } \
+ return (u##bits)data; \
+} \
+static __always_inline void td_##lclass##_write##bits(struct vcpu_tdx *tdx, \
+ u32 field, u##bits val) \
+{ \
+ u64 err; \
+ \
+ tdvps_##lclass##_check(field, bits); \
+ err = tdh_vp_wr(&tdx->vp, TDVPS_##uclass(field), val, \
+ GENMASK_ULL(bits - 1, 0)); \
+ if (unlikely(err)) \
+ tdh_vp_wr_failed(tdx, #uclass, " = ", field, (u64)val, err); \
+} \
+static __always_inline void td_##lclass##_setbit##bits(struct vcpu_tdx *tdx, \
+ u32 field, u64 bit) \
+{ \
+ u64 err; \
+ \
+ tdvps_##lclass##_check(field, bits); \
+ err = tdh_vp_wr(&tdx->vp, TDVPS_##uclass(field), bit, bit); \
+ if (unlikely(err)) \
+ tdh_vp_wr_failed(tdx, #uclass, " |= ", field, bit, err); \
+} \
+static __always_inline void td_##lclass##_clearbit##bits(struct vcpu_tdx *tdx, \
+ u32 field, u64 bit) \
+{ \
+ u64 err; \
+ \
+ tdvps_##lclass##_check(field, bits); \
+ err = tdh_vp_wr(&tdx->vp, TDVPS_##uclass(field), 0, bit); \
+ if (unlikely(err)) \
+ tdh_vp_wr_failed(tdx, #uclass, " &= ~", field, bit, err);\
+}
+
+
+bool tdx_interrupt_allowed(struct kvm_vcpu *vcpu);
+int tdx_complete_emulated_msr(struct kvm_vcpu *vcpu, int err);
+
+TDX_BUILD_TDVPS_ACCESSORS(16, VMCS, vmcs);
+TDX_BUILD_TDVPS_ACCESSORS(32, VMCS, vmcs);
+TDX_BUILD_TDVPS_ACCESSORS(64, VMCS, vmcs);
+
+TDX_BUILD_TDVPS_ACCESSORS(8, MANAGEMENT, management);
+TDX_BUILD_TDVPS_ACCESSORS(64, STATE_NON_ARCH, state_non_arch);
+
+#else
+static inline int tdx_bringup(void) { return 0; }
+static inline void tdx_cleanup(void) {}
+
+#define enable_tdx 0
+
+struct kvm_tdx {
+ struct kvm kvm;
+};
+
+struct vcpu_tdx {
+ struct kvm_vcpu vcpu;
+};
+
+static inline bool tdx_interrupt_allowed(struct kvm_vcpu *vcpu) { return false; }
+static inline int tdx_complete_emulated_msr(struct kvm_vcpu *vcpu, int err) { return 0; }
+
+#endif
+
+#endif
diff --git a/arch/x86/kvm/vmx/tdx_arch.h b/arch/x86/kvm/vmx/tdx_arch.h
new file mode 100644
index 000000000000..a30e880849e3
--- /dev/null
+++ b/arch/x86/kvm/vmx/tdx_arch.h
@@ -0,0 +1,167 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* architectural constants/data definitions for TDX SEAMCALLs */
+
+#ifndef __KVM_X86_TDX_ARCH_H
+#define __KVM_X86_TDX_ARCH_H
+
+#include <linux/types.h>
+
+/* TDX control structure (TDR/TDCS/TDVPS) field access codes */
+#define TDX_NON_ARCH BIT_ULL(63)
+#define TDX_CLASS_SHIFT 56
+#define TDX_FIELD_MASK GENMASK_ULL(31, 0)
+
+#define __BUILD_TDX_FIELD(non_arch, class, field) \
+ (((non_arch) ? TDX_NON_ARCH : 0) | \
+ ((u64)(class) << TDX_CLASS_SHIFT) | \
+ ((u64)(field) & TDX_FIELD_MASK))
+
+#define BUILD_TDX_FIELD(class, field) \
+ __BUILD_TDX_FIELD(false, (class), (field))
+
+#define BUILD_TDX_FIELD_NON_ARCH(class, field) \
+ __BUILD_TDX_FIELD(true, (class), (field))
+
+
+/* Class code for TD */
+#define TD_CLASS_EXECUTION_CONTROLS 17ULL
+
+/* Class code for TDVPS */
+#define TDVPS_CLASS_VMCS 0ULL
+#define TDVPS_CLASS_GUEST_GPR 16ULL
+#define TDVPS_CLASS_OTHER_GUEST 17ULL
+#define TDVPS_CLASS_MANAGEMENT 32ULL
+
+enum tdx_tdcs_execution_control {
+ TD_TDCS_EXEC_TSC_OFFSET = 10,
+ TD_TDCS_EXEC_TSC_MULTIPLIER = 11,
+};
+
+enum tdx_vcpu_guest_other_state {
+ TD_VCPU_STATE_DETAILS_NON_ARCH = 0x100,
+};
+
+#define TDX_VCPU_STATE_DETAILS_INTR_PENDING BIT_ULL(0)
+
+static inline bool tdx_vcpu_state_details_intr_pending(u64 vcpu_state_details)
+{
+ return !!(vcpu_state_details & TDX_VCPU_STATE_DETAILS_INTR_PENDING);
+}
+
+/* @field is any of enum tdx_tdcs_execution_control */
+#define TDCS_EXEC(field) BUILD_TDX_FIELD(TD_CLASS_EXECUTION_CONTROLS, (field))
+
+/* @field is the VMCS field encoding */
+#define TDVPS_VMCS(field) BUILD_TDX_FIELD(TDVPS_CLASS_VMCS, (field))
+
+/* @field is any of enum tdx_guest_other_state */
+#define TDVPS_STATE(field) BUILD_TDX_FIELD(TDVPS_CLASS_OTHER_GUEST, (field))
+#define TDVPS_STATE_NON_ARCH(field) BUILD_TDX_FIELD_NON_ARCH(TDVPS_CLASS_OTHER_GUEST, (field))
+
+/* Management class fields */
+enum tdx_vcpu_guest_management {
+ TD_VCPU_PEND_NMI = 11,
+};
+
+/* @field is any of enum tdx_vcpu_guest_management */
+#define TDVPS_MANAGEMENT(field) BUILD_TDX_FIELD(TDVPS_CLASS_MANAGEMENT, (field))
+
+#define TDX_EXTENDMR_CHUNKSIZE 256
+
+struct tdx_cpuid_value {
+ u32 eax;
+ u32 ebx;
+ u32 ecx;
+ u32 edx;
+} __packed;
+
+#define TDX_TD_ATTR_DEBUG BIT_ULL(0)
+#define TDX_TD_ATTR_SEPT_VE_DISABLE BIT_ULL(28)
+#define TDX_TD_ATTR_PKS BIT_ULL(30)
+#define TDX_TD_ATTR_KL BIT_ULL(31)
+#define TDX_TD_ATTR_PERFMON BIT_ULL(63)
+
+#define TDX_EXT_EXIT_QUAL_TYPE_MASK GENMASK(3, 0)
+#define TDX_EXT_EXIT_QUAL_TYPE_PENDING_EPT_VIOLATION 6
+/*
+ * TD_PARAMS is provided as an input to TDH_MNG_INIT, the size of which is 1024B.
+ */
+struct td_params {
+ u64 attributes;
+ u64 xfam;
+ u16 max_vcpus;
+ u8 reserved0[6];
+
+ u64 eptp_controls;
+ u64 config_flags;
+ u16 tsc_frequency;
+ u8 reserved1[38];
+
+ u64 mrconfigid[6];
+ u64 mrowner[6];
+ u64 mrownerconfig[6];
+ u64 reserved2[4];
+
+ union {
+ DECLARE_FLEX_ARRAY(struct tdx_cpuid_value, cpuid_values);
+ u8 reserved3[768];
+ };
+} __packed __aligned(1024);
+
+/*
+ * Guest uses MAX_PA for GPAW when set.
+ * 0: GPA.SHARED bit is GPA[47]
+ * 1: GPA.SHARED bit is GPA[51]
+ */
+#define TDX_CONFIG_FLAGS_MAX_GPAW BIT_ULL(0)
+
+/*
+ * TDH.VP.ENTER, TDG.VP.VMCALL preserves RBP
+ * 0: RBP can be used for TDG.VP.VMCALL input. RBP is clobbered.
+ * 1: RBP can't be used for TDG.VP.VMCALL input. RBP is preserved.
+ */
+#define TDX_CONFIG_FLAGS_NO_RBP_MOD BIT_ULL(2)
+
+
+/*
+ * TDX requires the frequency to be defined in units of 25MHz, which is the
+ * frequency of the core crystal clock on TDX-capable platforms, i.e. the TDX
+ * module can only program frequencies that are multiples of 25MHz. The
+ * frequency must be between 100mhz and 10ghz (inclusive).
+ */
+#define TDX_TSC_KHZ_TO_25MHZ(tsc_in_khz) ((tsc_in_khz) / (25 * 1000))
+#define TDX_TSC_25MHZ_TO_KHZ(tsc_in_25mhz) ((tsc_in_25mhz) * (25 * 1000))
+#define TDX_MIN_TSC_FREQUENCY_KHZ (100 * 1000)
+#define TDX_MAX_TSC_FREQUENCY_KHZ (10 * 1000 * 1000)
+
+/* Additional Secure EPT entry information */
+#define TDX_SEPT_LEVEL_MASK GENMASK_ULL(2, 0)
+#define TDX_SEPT_STATE_MASK GENMASK_ULL(15, 8)
+#define TDX_SEPT_STATE_SHIFT 8
+
+enum tdx_sept_entry_state {
+ TDX_SEPT_FREE = 0,
+ TDX_SEPT_BLOCKED = 1,
+ TDX_SEPT_PENDING = 2,
+ TDX_SEPT_PENDING_BLOCKED = 3,
+ TDX_SEPT_PRESENT = 4,
+};
+
+static inline u8 tdx_get_sept_level(u64 sept_entry_info)
+{
+ return sept_entry_info & TDX_SEPT_LEVEL_MASK;
+}
+
+static inline u8 tdx_get_sept_state(u64 sept_entry_info)
+{
+ return (sept_entry_info & TDX_SEPT_STATE_MASK) >> TDX_SEPT_STATE_SHIFT;
+}
+
+#define MD_FIELD_ID_FEATURES0_TOPOLOGY_ENUM BIT_ULL(20)
+
+/*
+ * TD scope metadata field ID.
+ */
+#define TD_MD_FIELD_ID_CPUID_VALUES 0x9410000300000000ULL
+
+#endif /* __KVM_X86_TDX_ARCH_H */
diff --git a/arch/x86/kvm/vmx/tdx_errno.h b/arch/x86/kvm/vmx/tdx_errno.h
new file mode 100644
index 000000000000..6ff4672c4181
--- /dev/null
+++ b/arch/x86/kvm/vmx/tdx_errno.h
@@ -0,0 +1,40 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* architectural status code for SEAMCALL */
+
+#ifndef __KVM_X86_TDX_ERRNO_H
+#define __KVM_X86_TDX_ERRNO_H
+
+#define TDX_SEAMCALL_STATUS_MASK 0xFFFFFFFF00000000ULL
+
+/*
+ * TDX SEAMCALL Status Codes (returned in RAX)
+ */
+#define TDX_NON_RECOVERABLE_VCPU 0x4000000100000000ULL
+#define TDX_NON_RECOVERABLE_TD 0x4000000200000000ULL
+#define TDX_NON_RECOVERABLE_TD_NON_ACCESSIBLE 0x6000000500000000ULL
+#define TDX_NON_RECOVERABLE_TD_WRONG_APIC_MODE 0x6000000700000000ULL
+#define TDX_INTERRUPTED_RESUMABLE 0x8000000300000000ULL
+#define TDX_OPERAND_INVALID 0xC000010000000000ULL
+#define TDX_OPERAND_BUSY 0x8000020000000000ULL
+#define TDX_PREVIOUS_TLB_EPOCH_BUSY 0x8000020100000000ULL
+#define TDX_PAGE_METADATA_INCORRECT 0xC000030000000000ULL
+#define TDX_VCPU_NOT_ASSOCIATED 0x8000070200000000ULL
+#define TDX_KEY_GENERATION_FAILED 0x8000080000000000ULL
+#define TDX_KEY_STATE_INCORRECT 0xC000081100000000ULL
+#define TDX_KEY_CONFIGURED 0x0000081500000000ULL
+#define TDX_NO_HKID_READY_TO_WBCACHE 0x0000082100000000ULL
+#define TDX_FLUSHVP_NOT_DONE 0x8000082400000000ULL
+#define TDX_EPT_WALK_FAILED 0xC0000B0000000000ULL
+#define TDX_EPT_ENTRY_STATE_INCORRECT 0xC0000B0D00000000ULL
+#define TDX_METADATA_FIELD_NOT_READABLE 0xC0000C0200000000ULL
+
+/*
+ * TDX module operand ID, appears in 31:0 part of error code as
+ * detail information
+ */
+#define TDX_OPERAND_ID_RCX 0x01
+#define TDX_OPERAND_ID_TDR 0x80
+#define TDX_OPERAND_ID_SEPT 0x92
+#define TDX_OPERAND_ID_TD_EPOCH 0xa9
+
+#endif /* __KVM_X86_TDX_ERRNO_H */
diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S
index f6986dee6f8c..0a6cf5bff2aa 100644
--- a/arch/x86/kvm/vmx/vmenter.S
+++ b/arch/x86/kvm/vmx/vmenter.S
@@ -59,8 +59,7 @@
* without the explicit restore, thinks the stack is getting walloped.
* Using an unwind hint is problematic due to x86-64's dynamic alignment.
*/
- mov %_ASM_BP, %_ASM_SP
- pop %_ASM_BP
+ leave
RET
.endm
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 5c5766467a61..aa157fe5b7b3 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -46,6 +46,7 @@
#include <asm/perf_event.h>
#include <asm/mmu_context.h>
#include <asm/mshyperv.h>
+#include <asm/msr.h>
#include <asm/mwait.h>
#include <asm/spec-ctrl.h>
#include <asm/vmx.h>
@@ -53,6 +54,7 @@
#include <trace/events/ipi.h>
#include "capabilities.h"
+#include "common.h"
#include "cpuid.h"
#include "hyperv.h"
#include "kvm_onhyperv.h"
@@ -73,6 +75,8 @@
#include "vmx_onhyperv.h"
#include "posted_intr.h"
+#include "mmu/spte.h"
+
MODULE_AUTHOR("Qumranet");
MODULE_DESCRIPTION("KVM support for VMX (Intel VT-x) extensions");
MODULE_LICENSE("GPL");
@@ -111,10 +115,10 @@ static bool __read_mostly fasteoi = 1;
module_param(fasteoi, bool, 0444);
module_param(enable_apicv, bool, 0444);
-
-bool __read_mostly enable_ipiv = true;
module_param(enable_ipiv, bool, 0444);
+module_param(enable_device_posted_irqs, bool, 0444);
+
/*
* If nested=1, nested virtualization is supported, i.e., guests may use
* VMX and be a hypervisor for its own guests. If nested=0, guests may not
@@ -164,31 +168,6 @@ module_param(allow_smaller_maxphyaddr, bool, S_IRUGO);
RTIT_STATUS_BYTECNT))
/*
- * List of MSRs that can be directly passed to the guest.
- * In addition to these x2apic, PT and LBR MSRs are handled specially.
- */
-static u32 vmx_possible_passthrough_msrs[MAX_POSSIBLE_PASSTHROUGH_MSRS] = {
- MSR_IA32_SPEC_CTRL,
- MSR_IA32_PRED_CMD,
- MSR_IA32_FLUSH_CMD,
- MSR_IA32_TSC,
-#ifdef CONFIG_X86_64
- MSR_FS_BASE,
- MSR_GS_BASE,
- MSR_KERNEL_GS_BASE,
- MSR_IA32_XFD,
- MSR_IA32_XFD_ERR,
-#endif
- MSR_IA32_SYSENTER_CS,
- MSR_IA32_SYSENTER_ESP,
- MSR_IA32_SYSENTER_EIP,
- MSR_CORE_C1_RES,
- MSR_CORE_C3_RESIDENCY,
- MSR_CORE_C6_RESIDENCY,
- MSR_CORE_C7_RESIDENCY,
-};
-
-/*
* These 2 parameters are used to config the controls for Pause-Loop Exiting:
* ple_gap: upper bound on the amount of time between two successive
* executions of PAUSE in a loop. Also indicate if ple enabled.
@@ -273,6 +252,7 @@ static int vmx_setup_l1d_flush(enum vmx_l1d_flush_state l1tf)
case L1TF_MITIGATION_OFF:
l1tf = VMENTER_L1D_FLUSH_NEVER;
break;
+ case L1TF_MITIGATION_AUTO:
case L1TF_MITIGATION_FLUSH_NOWARN:
case L1TF_MITIGATION_FLUSH:
case L1TF_MITIGATION_FLUSH_NOSMT:
@@ -380,9 +360,9 @@ static __always_inline void vmx_disable_fb_clear(struct vcpu_vmx *vmx)
if (!vmx->disable_fb_clear)
return;
- msr = __rdmsr(MSR_IA32_MCU_OPT_CTRL);
+ msr = native_rdmsrq(MSR_IA32_MCU_OPT_CTRL);
msr |= FB_CLEAR_DIS;
- native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, msr);
+ native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, msr);
/* Cache the MSR value to avoid reading it later */
vmx->msr_ia32_mcu_opt_ctrl = msr;
}
@@ -393,7 +373,7 @@ static __always_inline void vmx_enable_fb_clear(struct vcpu_vmx *vmx)
return;
vmx->msr_ia32_mcu_opt_ctrl &= ~FB_CLEAR_DIS;
- native_wrmsrl(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl);
+ native_wrmsrq(MSR_IA32_MCU_OPT_CTRL, vmx->msr_ia32_mcu_opt_ctrl);
}
static void vmx_update_fb_clear_dis(struct kvm_vcpu *vcpu, struct vcpu_vmx *vmx)
@@ -669,40 +649,6 @@ static inline bool cpu_need_virtualize_apic_accesses(struct kvm_vcpu *vcpu)
return flexpriority_enabled && lapic_in_kernel(vcpu);
}
-static int vmx_get_passthrough_msr_slot(u32 msr)
-{
- int i;
-
- switch (msr) {
- case 0x800 ... 0x8ff:
- /* x2APIC MSRs. These are handled in vmx_update_msr_bitmap_x2apic() */
- return -ENOENT;
- case MSR_IA32_RTIT_STATUS:
- case MSR_IA32_RTIT_OUTPUT_BASE:
- case MSR_IA32_RTIT_OUTPUT_MASK:
- case MSR_IA32_RTIT_CR3_MATCH:
- case MSR_IA32_RTIT_ADDR0_A ... MSR_IA32_RTIT_ADDR3_B:
- /* PT MSRs. These are handled in pt_update_intercept_for_msr() */
- case MSR_LBR_SELECT:
- case MSR_LBR_TOS:
- case MSR_LBR_INFO_0 ... MSR_LBR_INFO_0 + 31:
- case MSR_LBR_NHM_FROM ... MSR_LBR_NHM_FROM + 31:
- case MSR_LBR_NHM_TO ... MSR_LBR_NHM_TO + 31:
- case MSR_LBR_CORE_FROM ... MSR_LBR_CORE_FROM + 8:
- case MSR_LBR_CORE_TO ... MSR_LBR_CORE_TO + 8:
- /* LBR MSRs. These are handled in vmx_update_intercept_for_lbr_msrs() */
- return -ENOENT;
- }
-
- for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) {
- if (vmx_possible_passthrough_msrs[i] == msr)
- return i;
- }
-
- WARN(1, "Invalid MSR %x, please adapt vmx_possible_passthrough_msrs[]", msr);
- return -ENOENT;
-}
-
struct vmx_uret_msr *vmx_find_uret_msr(struct vcpu_vmx *vmx, u32 msr)
{
int i;
@@ -769,8 +715,11 @@ void vmx_emergency_disable_virtualization_cpu(void)
return;
list_for_each_entry(v, &per_cpu(loaded_vmcss_on_cpu, cpu),
- loaded_vmcss_on_cpu_link)
+ loaded_vmcss_on_cpu_link) {
vmcs_clear(v->vmcs);
+ if (v->shadow_vmcs)
+ vmcs_clear(v->shadow_vmcs);
+ }
kvm_cpu_vmxoff();
}
@@ -955,6 +904,10 @@ unsigned int __vmx_vcpu_run_flags(struct vcpu_vmx *vmx)
if (!msr_write_intercepted(vmx, MSR_IA32_SPEC_CTRL))
flags |= VMX_RUN_SAVE_SPEC_CTRL;
+ if (static_branch_unlikely(&cpu_buf_vm_clear) &&
+ kvm_vcpu_can_access_host_mmio(&vmx->vcpu))
+ flags |= VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO;
+
return flags;
}
@@ -1063,7 +1016,7 @@ static void add_atomic_switch_msr(struct vcpu_vmx *vmx, unsigned msr,
* provide that period, so a CPU could write host's record into
* guest's memory.
*/
- wrmsrl(MSR_IA32_PEBS_ENABLE, 0);
+ wrmsrq(MSR_IA32_PEBS_ENABLE, 0);
}
i = vmx_find_loadstore_msr_slot(&m->guest, msr);
@@ -1192,13 +1145,13 @@ static inline void pt_load_msr(struct pt_ctx *ctx, u32 addr_range)
{
u32 i;
- wrmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
- wrmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
- wrmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
- wrmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
+ wrmsrq(MSR_IA32_RTIT_STATUS, ctx->status);
+ wrmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
+ wrmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
+ wrmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
for (i = 0; i < addr_range; i++) {
- wrmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
- wrmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
+ wrmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
+ wrmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
}
}
@@ -1206,13 +1159,13 @@ static inline void pt_save_msr(struct pt_ctx *ctx, u32 addr_range)
{
u32 i;
- rdmsrl(MSR_IA32_RTIT_STATUS, ctx->status);
- rdmsrl(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
- rdmsrl(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
- rdmsrl(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
+ rdmsrq(MSR_IA32_RTIT_STATUS, ctx->status);
+ rdmsrq(MSR_IA32_RTIT_OUTPUT_BASE, ctx->output_base);
+ rdmsrq(MSR_IA32_RTIT_OUTPUT_MASK, ctx->output_mask);
+ rdmsrq(MSR_IA32_RTIT_CR3_MATCH, ctx->cr3_match);
for (i = 0; i < addr_range; i++) {
- rdmsrl(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
- rdmsrl(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
+ rdmsrq(MSR_IA32_RTIT_ADDR0_A + i * 2, ctx->addr_a[i]);
+ rdmsrq(MSR_IA32_RTIT_ADDR0_B + i * 2, ctx->addr_b[i]);
}
}
@@ -1225,9 +1178,9 @@ static void pt_guest_enter(struct vcpu_vmx *vmx)
* GUEST_IA32_RTIT_CTL is already set in the VMCS.
* Save host state before VM entry.
*/
- rdmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+ rdmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
if (vmx->pt_desc.guest.ctl & RTIT_CTL_TRACEEN) {
- wrmsrl(MSR_IA32_RTIT_CTL, 0);
+ wrmsrq(MSR_IA32_RTIT_CTL, 0);
pt_save_msr(&vmx->pt_desc.host, vmx->pt_desc.num_address_ranges);
pt_load_msr(&vmx->pt_desc.guest, vmx->pt_desc.num_address_ranges);
}
@@ -1248,7 +1201,7 @@ static void pt_guest_exit(struct vcpu_vmx *vmx)
* i.e. RTIT_CTL is always cleared on VM-Exit. Restore it if necessary.
*/
if (vmx->pt_desc.host.ctl)
- wrmsrl(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
+ wrmsrq(MSR_IA32_RTIT_CTL, vmx->pt_desc.host.ctl);
}
void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
@@ -1281,6 +1234,7 @@ void vmx_set_host_fs_gs(struct vmcs_host_state *host, u16 fs_sel, u16 gs_sel,
void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vcpu_vt *vt = to_vt(vcpu);
struct vmcs_host_state *host_state;
#ifdef CONFIG_X86_64
int cpu = raw_smp_processor_id();
@@ -1309,7 +1263,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
if (vmx->nested.need_vmcs12_to_shadow_sync)
nested_sync_vmcs12_to_shadow(vcpu);
- if (vmx->guest_state_loaded)
+ if (vt->guest_state_loaded)
return;
host_state = &vmx->loaded_vmcs->host_state;
@@ -1330,15 +1284,15 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
fs_sel = current->thread.fsindex;
gs_sel = current->thread.gsindex;
fs_base = current->thread.fsbase;
- vmx->msr_host_kernel_gs_base = current->thread.gsbase;
+ vt->msr_host_kernel_gs_base = current->thread.gsbase;
} else {
savesegment(fs, fs_sel);
savesegment(gs, gs_sel);
fs_base = read_msr(MSR_FS_BASE);
- vmx->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
+ vt->msr_host_kernel_gs_base = read_msr(MSR_KERNEL_GS_BASE);
}
- wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+ wrmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#else
savesegment(fs, fs_sel);
savesegment(gs, gs_sel);
@@ -1347,14 +1301,14 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
#endif
vmx_set_host_fs_gs(host_state, fs_sel, gs_sel, fs_base, gs_base);
- vmx->guest_state_loaded = true;
+ vt->guest_state_loaded = true;
}
static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
{
struct vmcs_host_state *host_state;
- if (!vmx->guest_state_loaded)
+ if (!vmx->vt.guest_state_loaded)
return;
host_state = &vmx->loaded_vmcs->host_state;
@@ -1362,7 +1316,7 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
++vmx->vcpu.stat.host_state_reload;
#ifdef CONFIG_X86_64
- rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+ rdmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
#endif
if (host_state->ldt_sel || (host_state->gs_sel & 7)) {
kvm_load_ldt(host_state->ldt_sel);
@@ -1382,10 +1336,10 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
#endif
invalidate_tss_limit();
#ifdef CONFIG_X86_64
- wrmsrl(MSR_KERNEL_GS_BASE, vmx->msr_host_kernel_gs_base);
+ wrmsrq(MSR_KERNEL_GS_BASE, vmx->vt.msr_host_kernel_gs_base);
#endif
load_fixmap_gdt(raw_smp_processor_id());
- vmx->guest_state_loaded = false;
+ vmx->vt.guest_state_loaded = false;
vmx->guest_uret_msrs_loaded = false;
}
@@ -1393,8 +1347,8 @@ static void vmx_prepare_switch_to_host(struct vcpu_vmx *vmx)
static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
{
preempt_disable();
- if (vmx->guest_state_loaded)
- rdmsrl(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
+ if (vmx->vt.guest_state_loaded)
+ rdmsrq(MSR_KERNEL_GS_BASE, vmx->msr_guest_kernel_gs_base);
preempt_enable();
return vmx->msr_guest_kernel_gs_base;
}
@@ -1402,8 +1356,8 @@ static u64 vmx_read_guest_kernel_gs_base(struct vcpu_vmx *vmx)
static void vmx_write_guest_kernel_gs_base(struct vcpu_vmx *vmx, u64 data)
{
preempt_disable();
- if (vmx->guest_state_loaded)
- wrmsrl(MSR_KERNEL_GS_BASE, data);
+ if (vmx->vt.guest_state_loaded)
+ wrmsrq(MSR_KERNEL_GS_BASE, data);
preempt_enable();
vmx->msr_guest_kernel_gs_base = data;
}
@@ -1441,8 +1395,7 @@ static void shrink_ple_window(struct kvm_vcpu *vcpu)
}
}
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
- struct loaded_vmcs *buddy)
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
bool already_loaded = vmx->loaded_vmcs->cpu == cpu;
@@ -1469,17 +1422,6 @@ void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
if (prev != vmx->loaded_vmcs->vmcs) {
per_cpu(current_vmcs, cpu) = vmx->loaded_vmcs->vmcs;
vmcs_load(vmx->loaded_vmcs->vmcs);
-
- /*
- * No indirect branch prediction barrier needed when switching
- * the active VMCS within a vCPU, unless IBRS is advertised to
- * the vCPU. To minimize the number of IBPBs executed, KVM
- * performs IBPB on nested VM-Exit (a single nested transition
- * may switch the active VMCS multiple times).
- */
- if (static_branch_likely(&switch_vcpu_ibpb) &&
- (!buddy || WARN_ON_ONCE(buddy->vmcs != prev)))
- indirect_branch_prediction_barrier();
}
if (!already_loaded) {
@@ -1518,7 +1460,7 @@ void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (vcpu->scheduled_out && !kvm_pause_in_guest(vcpu->kvm))
shrink_ple_window(vcpu);
- vmx_vcpu_load_vmcs(vcpu, cpu, NULL);
+ vmx_vcpu_load_vmcs(vcpu, cpu);
vmx_vcpu_pi_load(vcpu, cpu);
}
@@ -1579,7 +1521,7 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
vmcs_writel(GUEST_RFLAGS, rflags);
if ((old_rflags ^ vmx->rflags) & X86_EFLAGS_VM)
- vmx->emulation_required = vmx_emulation_required(vcpu);
+ vmx->vt.emulation_required = vmx_emulation_required(vcpu);
}
bool vmx_get_if_flag(struct kvm_vcpu *vcpu)
@@ -1699,7 +1641,7 @@ int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
* so that guest userspace can't DoS the guest simply by triggering
* emulation (enclaves are CPL3 only).
*/
- if (to_vmx(vcpu)->exit_reason.enclave_mode) {
+ if (vmx_get_exit_reason(vcpu).enclave_mode) {
kvm_queue_exception(vcpu, UD_VECTOR);
return X86EMUL_PROPAGATE_FAULT;
}
@@ -1714,7 +1656,7 @@ int vmx_check_emulate_instruction(struct kvm_vcpu *vcpu, int emul_type,
static int skip_emulated_instruction(struct kvm_vcpu *vcpu)
{
- union vmx_exit_reason exit_reason = to_vmx(vcpu)->exit_reason;
+ union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu);
unsigned long rip, orig_rip;
u32 instr_len;
@@ -1861,7 +1803,7 @@ void vmx_inject_exception(struct kvm_vcpu *vcpu)
return;
}
- WARN_ON_ONCE(vmx->emulation_required);
+ WARN_ON_ONCE(vmx->vt.emulation_required);
if (kvm_exception_is_soft(ex->vector)) {
vmcs_write32(VM_ENTRY_INSTRUCTION_LEN,
@@ -2152,7 +2094,7 @@ int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
msr_info->data = vmx->pt_desc.guest.addr_a[index / 2];
break;
case MSR_IA32_DEBUGCTLMSR:
- msr_info->data = vmcs_read64(GUEST_IA32_DEBUGCTL);
+ msr_info->data = vmx_guest_debugctl_read();
break;
default:
find_uret_msr:
@@ -2177,7 +2119,7 @@ static u64 nested_vmx_truncate_sysenter_addr(struct kvm_vcpu *vcpu,
return (unsigned long)data;
}
-static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated)
{
u64 debugctl = 0;
@@ -2189,9 +2131,25 @@ static u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated
(host_initiated || intel_pmu_lbr_is_enabled(vcpu)))
debugctl |= DEBUGCTLMSR_LBR | DEBUGCTLMSR_FREEZE_LBRS_ON_PMI;
+ if (boot_cpu_has(X86_FEATURE_RTM) &&
+ (host_initiated || guest_cpu_cap_has(vcpu, X86_FEATURE_RTM)))
+ debugctl |= DEBUGCTLMSR_RTM_DEBUG;
+
return debugctl;
}
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated)
+{
+ u64 invalid;
+
+ invalid = data & ~vmx_get_supported_debugctl(vcpu, host_initiated);
+ if (invalid & (DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR)) {
+ kvm_pr_unimpl_wrmsr(vcpu, MSR_IA32_DEBUGCTLMSR, data);
+ invalid &= ~(DEBUGCTLMSR_BTF | DEBUGCTLMSR_LBR);
+ }
+ return !invalid;
+}
+
/*
* Writes msr value into the appropriate "register".
* Returns 0 on success, non-0 otherwise.
@@ -2260,29 +2218,22 @@ int vmx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
}
vmcs_writel(GUEST_SYSENTER_ESP, data);
break;
- case MSR_IA32_DEBUGCTLMSR: {
- u64 invalid;
-
- invalid = data & ~vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
- if (invalid & (DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR)) {
- kvm_pr_unimpl_wrmsr(vcpu, msr_index, data);
- data &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
- invalid &= ~(DEBUGCTLMSR_BTF|DEBUGCTLMSR_LBR);
- }
-
- if (invalid)
+ case MSR_IA32_DEBUGCTLMSR:
+ if (!vmx_is_valid_debugctl(vcpu, data, msr_info->host_initiated))
return 1;
+ data &= vmx_get_supported_debugctl(vcpu, msr_info->host_initiated);
+
if (is_guest_mode(vcpu) && get_vmcs12(vcpu)->vm_exit_controls &
VM_EXIT_SAVE_DEBUG_CONTROLS)
get_vmcs12(vcpu)->guest_ia32_debugctl = data;
- vmcs_write64(GUEST_IA32_DEBUGCTL, data);
+ vmx_guest_debugctl_write(vcpu, data);
+
if (intel_pmu_lbr_is_enabled(vcpu) && !to_vmx(vcpu)->lbr_desc.event &&
(data & DEBUGCTLMSR_LBR))
intel_pmu_create_guest_lbr_event(vcpu);
return 0;
- }
case MSR_IA32_BNDCFGS:
if (!kvm_mpx_supported() ||
(!msr_info->host_initiated &&
@@ -2574,7 +2525,7 @@ static u64 adjust_vmx_controls64(u64 ctl_opt, u32 msr)
{
u64 allowed;
- rdmsrl(msr, allowed);
+ rdmsrq(msr, allowed);
return ctl_opt & allowed;
}
@@ -2746,7 +2697,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
break;
}
- rdmsrl(MSR_IA32_VMX_BASIC, basic_msr);
+ rdmsrq(MSR_IA32_VMX_BASIC, basic_msr);
/* IA-32 SDM Vol 3B: VMCS size is never greater than 4kB. */
if (vmx_basic_vmcs_size(basic_msr) > PAGE_SIZE)
@@ -2766,7 +2717,7 @@ static int setup_vmcs_config(struct vmcs_config *vmcs_conf,
if (vmx_basic_vmcs_mem_type(basic_msr) != X86_MEMTYPE_WB)
return -EIO;
- rdmsrl(MSR_IA32_VMX_MISC, misc_msr);
+ rdmsrq(MSR_IA32_VMX_MISC, misc_msr);
vmcs_conf->basic = basic_msr;
vmcs_conf->pin_based_exec_ctrl = _pin_based_exec_control;
@@ -2850,7 +2801,7 @@ static int kvm_cpu_vmxon(u64 vmxon_pointer)
fault:
WARN_ONCE(1, "VMXON faulted, MSR_IA32_FEAT_CTL (0x3a) = 0x%llx\n",
- rdmsrl_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr);
+ rdmsrq_safe(MSR_IA32_FEAT_CTL, &msr) ? 0xdeadbeef : msr);
cr4_clear_bits(X86_CR4_VMXE);
return -EFAULT;
@@ -3404,7 +3355,7 @@ void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
}
/* depends on vcpu->arch.cr0 to be set to a new value */
- vmx->emulation_required = vmx_emulation_required(vcpu);
+ vmx->vt.emulation_required = vmx_emulation_required(vcpu);
}
static int vmx_get_max_ept_level(void)
@@ -3667,7 +3618,7 @@ void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg)
{
__vmx_set_segment(vcpu, var, seg);
- to_vmx(vcpu)->emulation_required = vmx_emulation_required(vcpu);
+ to_vmx(vcpu)->vt.emulation_required = vmx_emulation_required(vcpu);
}
void vmx_get_cs_db_l_bits(struct kvm_vcpu *vcpu, int *db, int *l)
@@ -4016,76 +3967,29 @@ static void vmx_msr_bitmap_l01_changed(struct vcpu_vmx *vmx)
vmx->nested.force_msr_bitmap_recalc = true;
}
-void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
+void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
- int idx;
if (!cpu_has_vmx_msr_bitmap())
return;
vmx_msr_bitmap_l01_changed(vmx);
- /*
- * Mark the desired intercept state in shadow bitmap, this is needed
- * for resync when the MSR filters change.
- */
- idx = vmx_get_passthrough_msr_slot(msr);
- if (idx >= 0) {
- if (type & MSR_TYPE_R)
- clear_bit(idx, vmx->shadow_msr_intercept.read);
- if (type & MSR_TYPE_W)
- clear_bit(idx, vmx->shadow_msr_intercept.write);
- }
-
- if ((type & MSR_TYPE_R) &&
- !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ)) {
- vmx_set_msr_bitmap_read(msr_bitmap, msr);
- type &= ~MSR_TYPE_R;
- }
-
- if ((type & MSR_TYPE_W) &&
- !kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE)) {
- vmx_set_msr_bitmap_write(msr_bitmap, msr);
- type &= ~MSR_TYPE_W;
+ if (type & MSR_TYPE_R) {
+ if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_READ))
+ vmx_clear_msr_bitmap_read(msr_bitmap, msr);
+ else
+ vmx_set_msr_bitmap_read(msr_bitmap, msr);
}
- if (type & MSR_TYPE_R)
- vmx_clear_msr_bitmap_read(msr_bitmap, msr);
-
- if (type & MSR_TYPE_W)
- vmx_clear_msr_bitmap_write(msr_bitmap, msr);
-}
-
-void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- unsigned long *msr_bitmap = vmx->vmcs01.msr_bitmap;
- int idx;
-
- if (!cpu_has_vmx_msr_bitmap())
- return;
-
- vmx_msr_bitmap_l01_changed(vmx);
-
- /*
- * Mark the desired intercept state in shadow bitmap, this is needed
- * for resync when the MSR filter changes.
- */
- idx = vmx_get_passthrough_msr_slot(msr);
- if (idx >= 0) {
- if (type & MSR_TYPE_R)
- set_bit(idx, vmx->shadow_msr_intercept.read);
- if (type & MSR_TYPE_W)
- set_bit(idx, vmx->shadow_msr_intercept.write);
+ if (type & MSR_TYPE_W) {
+ if (!set && kvm_msr_allowed(vcpu, msr, KVM_MSR_FILTER_WRITE))
+ vmx_clear_msr_bitmap_write(msr_bitmap, msr);
+ else
+ vmx_set_msr_bitmap_write(msr_bitmap, msr);
}
-
- if (type & MSR_TYPE_R)
- vmx_set_msr_bitmap_read(msr_bitmap, msr);
-
- if (type & MSR_TYPE_W)
- vmx_set_msr_bitmap_write(msr_bitmap, msr);
}
static void vmx_update_msr_bitmap_x2apic(struct kvm_vcpu *vcpu)
@@ -4164,79 +4068,57 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu)
}
}
-void vmx_msr_filter_changed(struct kvm_vcpu *vcpu)
+void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
- u32 i;
-
if (!cpu_has_vmx_msr_bitmap())
return;
- /*
- * Redo intercept permissions for MSRs that KVM is passing through to
- * the guest. Disabling interception will check the new MSR filter and
- * ensure that KVM enables interception if usersepace wants to filter
- * the MSR. MSRs that KVM is already intercepting don't need to be
- * refreshed since KVM is going to intercept them regardless of what
- * userspace wants.
- */
- for (i = 0; i < ARRAY_SIZE(vmx_possible_passthrough_msrs); i++) {
- u32 msr = vmx_possible_passthrough_msrs[i];
-
- if (!test_bit(i, vmx->shadow_msr_intercept.read))
- vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_R);
-
- if (!test_bit(i, vmx->shadow_msr_intercept.write))
- vmx_disable_intercept_for_msr(vcpu, msr, MSR_TYPE_W);
+ vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R);
+#ifdef CONFIG_X86_64
+ vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
+#endif
+ vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
+ vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
+ if (kvm_cstate_in_guest(vcpu->kvm)) {
+ vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R);
+ vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
+ vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
+ vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
+ }
+ if (kvm_aperfmperf_in_guest(vcpu->kvm)) {
+ vmx_disable_intercept_for_msr(vcpu, MSR_IA32_APERF, MSR_TYPE_R);
+ vmx_disable_intercept_for_msr(vcpu, MSR_IA32_MPERF, MSR_TYPE_R);
}
/* PT MSRs can be passed through iff PT is exposed to the guest. */
if (vmx_pt_mode_is_host_guest())
pt_update_intercept_for_msr(vcpu);
-}
-static inline void kvm_vcpu_trigger_posted_interrupt(struct kvm_vcpu *vcpu,
- int pi_vec)
-{
-#ifdef CONFIG_SMP
- if (vcpu->mode == IN_GUEST_MODE) {
- /*
- * The vector of the virtual has already been set in the PIR.
- * Send a notification event to deliver the virtual interrupt
- * unless the vCPU is the currently running vCPU, i.e. the
- * event is being sent from a fastpath VM-Exit handler, in
- * which case the PIR will be synced to the vIRR before
- * re-entering the guest.
- *
- * When the target is not the running vCPU, the following
- * possibilities emerge:
- *
- * Case 1: vCPU stays in non-root mode. Sending a notification
- * event posts the interrupt to the vCPU.
- *
- * Case 2: vCPU exits to root mode and is still runnable. The
- * PIR will be synced to the vIRR before re-entering the guest.
- * Sending a notification event is ok as the host IRQ handler
- * will ignore the spurious event.
- *
- * Case 3: vCPU exits to root mode and is blocked. vcpu_block()
- * has already synced PIR to vIRR and never blocks the vCPU if
- * the vIRR is not empty. Therefore, a blocked vCPU here does
- * not wait for any requested interrupts in PIR, and sending a
- * notification event also results in a benign, spurious event.
- */
+ if (vcpu->arch.xfd_no_write_intercept)
+ vmx_disable_intercept_for_msr(vcpu, MSR_IA32_XFD, MSR_TYPE_RW);
+
+ vmx_set_intercept_for_msr(vcpu, MSR_IA32_SPEC_CTRL, MSR_TYPE_RW,
+ !to_vmx(vcpu)->spec_ctrl);
+
+ if (kvm_cpu_cap_has(X86_FEATURE_XFD))
+ vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R,
+ !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD));
+
+ if (cpu_feature_enabled(X86_FEATURE_IBPB))
+ vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W,
+ !guest_has_pred_cmd_msr(vcpu));
+
+ if (cpu_feature_enabled(X86_FEATURE_FLUSH_L1D))
+ vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W,
+ !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D));
- if (vcpu != kvm_get_running_vcpu())
- __apic_send_IPI_mask(get_cpu_mask(vcpu->cpu), pi_vec);
- return;
- }
-#endif
/*
- * The vCPU isn't in the guest; wake the vCPU in case it is blocking,
- * otherwise do nothing as KVM will grab the highest priority pending
- * IRQ via ->sync_pir_to_irr() in vcpu_enter_guest().
+ * x2APIC and LBR MSR intercepts are modified on-demand and cannot be
+ * filtered by userspace.
*/
- kvm_vcpu_wake_up(vcpu);
}
static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
@@ -4287,7 +4169,7 @@ static int vmx_deliver_nested_posted_interrupt(struct kvm_vcpu *vcpu,
*/
static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vcpu_vt *vt = to_vt(vcpu);
int r;
r = vmx_deliver_nested_posted_interrupt(vcpu, vector);
@@ -4298,20 +4180,7 @@ static int vmx_deliver_posted_interrupt(struct kvm_vcpu *vcpu, int vector)
if (!vcpu->arch.apic->apicv_active)
return -1;
- if (pi_test_and_set_pir(vector, &vmx->pi_desc))
- return 0;
-
- /* If a previous notification has sent the IPI, nothing to do. */
- if (pi_test_and_set_on(&vmx->pi_desc))
- return 0;
-
- /*
- * The implied barrier in pi_test_and_set_on() pairs with the smp_mb_*()
- * after setting vcpu->mode in vcpu_enter_guest(), thus the vCPU is
- * guaranteed to see PID.ON=1 and sync the PIR to IRR if triggering a
- * posted interrupt "fails" because vcpu->mode != IN_GUEST_MODE.
- */
- kvm_vcpu_trigger_posted_interrupt(vcpu, POSTED_INTR_VECTOR);
+ __vmx_deliver_posted_interrupt(vcpu, &vt->pi_desc, vector);
return 0;
}
@@ -4391,7 +4260,7 @@ void vmx_set_constant_host_state(struct vcpu_vmx *vmx)
if (!IS_ENABLED(CONFIG_IA32_EMULATION) && !IS_ENABLED(CONFIG_X86_32))
vmcs_writel(HOST_IA32_SYSENTER_ESP, 0);
- rdmsrl(MSR_IA32_SYSENTER_EIP, tmpl);
+ rdmsrq(MSR_IA32_SYSENTER_EIP, tmpl);
vmcs_writel(HOST_IA32_SYSENTER_EIP, tmpl); /* 22.2.3 */
if (vmcs_config.vmexit_ctrl & VM_EXIT_LOAD_IA32_PAT) {
@@ -4778,7 +4647,7 @@ static void init_vmcs(struct vcpu_vmx *vmx)
vmcs_write16(GUEST_INTR_STATUS, 0);
vmcs_write16(POSTED_INTR_NV, POSTED_INTR_VECTOR);
- vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->pi_desc)));
+ vmcs_write64(POSTED_INTR_DESC_ADDR, __pa((&vmx->vt.pi_desc)));
}
if (vmx_can_use_ipiv(&vmx->vcpu)) {
@@ -4850,7 +4719,8 @@ static void init_vmcs(struct vcpu_vmx *vmx)
vmcs_write32(GUEST_SYSENTER_CS, 0);
vmcs_writel(GUEST_SYSENTER_ESP, 0);
vmcs_writel(GUEST_SYSENTER_EIP, 0);
- vmcs_write64(GUEST_IA32_DEBUGCTL, 0);
+
+ vmx_guest_debugctl_write(&vmx->vcpu, 0);
if (cpu_has_vmx_tpr_shadow()) {
vmcs_write64(VIRTUAL_APIC_PAGE_ADDR, 0);
@@ -4891,8 +4761,8 @@ static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu)
* Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
* or POSTED_INTR_WAKEUP_VECTOR.
*/
- vmx->pi_desc.nv = POSTED_INTR_VECTOR;
- __pi_set_sn(&vmx->pi_desc);
+ vmx->vt.pi_desc.nv = POSTED_INTR_VECTOR;
+ __pi_set_sn(&vmx->vt.pi_desc);
}
void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
@@ -5666,12 +5536,6 @@ void vmx_sync_dirty_debug_regs(struct kvm_vcpu *vcpu)
set_debugreg(DR6_RESERVED, 6);
}
-void vmx_set_dr6(struct kvm_vcpu *vcpu, unsigned long val)
-{
- lockdep_assert_irqs_disabled();
- set_debugreg(vcpu->arch.dr6, 6);
-}
-
void vmx_set_dr7(struct kvm_vcpu *vcpu, unsigned long val)
{
vmcs_writel(GUEST_DR7, val);
@@ -5809,11 +5673,8 @@ static int handle_task_switch(struct kvm_vcpu *vcpu)
static int handle_ept_violation(struct kvm_vcpu *vcpu)
{
- unsigned long exit_qualification;
+ unsigned long exit_qualification = vmx_get_exit_qual(vcpu);
gpa_t gpa;
- u64 error_code;
-
- exit_qualification = vmx_get_exit_qual(vcpu);
/*
* EPT violation happened while executing iret from NMI,
@@ -5829,23 +5690,6 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
gpa = vmcs_read64(GUEST_PHYSICAL_ADDRESS);
trace_kvm_page_fault(vcpu, gpa, exit_qualification);
- /* Is it a read fault? */
- error_code = (exit_qualification & EPT_VIOLATION_ACC_READ)
- ? PFERR_USER_MASK : 0;
- /* Is it a write fault? */
- error_code |= (exit_qualification & EPT_VIOLATION_ACC_WRITE)
- ? PFERR_WRITE_MASK : 0;
- /* Is it a fetch fault? */
- error_code |= (exit_qualification & EPT_VIOLATION_ACC_INSTR)
- ? PFERR_FETCH_MASK : 0;
- /* ept page table entry is present? */
- error_code |= (exit_qualification & EPT_VIOLATION_PROT_MASK)
- ? PFERR_PRESENT_MASK : 0;
-
- if (error_code & EPT_VIOLATION_GVA_IS_VALID)
- error_code |= (exit_qualification & EPT_VIOLATION_GVA_TRANSLATED) ?
- PFERR_GUEST_FINAL_MASK : PFERR_GUEST_PAGE_MASK;
-
/*
* Check that the GPA doesn't exceed physical memory limits, as that is
* a guest page fault. We have to emulate the instruction here, because
@@ -5857,7 +5701,7 @@ static int handle_ept_violation(struct kvm_vcpu *vcpu)
if (unlikely(allow_smaller_maxphyaddr && !kvm_vcpu_is_legal_gpa(vcpu, gpa)))
return kvm_emulate_instruction(vcpu, 0);
- return kvm_mmu_page_fault(vcpu, gpa, error_code, NULL, 0);
+ return __vmx_handle_ept_violation(vcpu, gpa, exit_qualification);
}
static int handle_ept_misconfig(struct kvm_vcpu *vcpu)
@@ -5902,7 +5746,7 @@ static bool vmx_unhandleable_emulation_required(struct kvm_vcpu *vcpu)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- if (!vmx->emulation_required)
+ if (!vmx->vt.emulation_required)
return false;
/*
@@ -5934,7 +5778,7 @@ static int handle_invalid_guest_state(struct kvm_vcpu *vcpu)
intr_window_requested = exec_controls_get(vmx) &
CPU_BASED_INTR_WINDOW_EXITING;
- while (vmx->emulation_required && count-- != 0) {
+ while (vmx->vt.emulation_required && count-- != 0) {
if (intr_window_requested && !vmx_interrupt_blocked(vcpu))
return handle_interrupt_window(&vmx->vcpu);
@@ -6129,7 +5973,7 @@ static int handle_bus_lock_vmexit(struct kvm_vcpu *vcpu)
* VM-Exits. Unconditionally set the flag here and leave the handling to
* vmx_handle_exit().
*/
- to_vmx(vcpu)->exit_reason.bus_lock_detected = true;
+ to_vt(vcpu)->exit_reason.bus_lock_detected = true;
return 1;
}
@@ -6227,9 +6071,9 @@ void vmx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- *reason = vmx->exit_reason.full;
+ *reason = vmx->vt.exit_reason.full;
*info1 = vmx_get_exit_qual(vcpu);
- if (!(vmx->exit_reason.failed_vmentry)) {
+ if (!(vmx->vt.exit_reason.failed_vmentry)) {
*info2 = vmx->idt_vectoring_info;
*intr_info = vmx_get_intr_info(vcpu);
if (is_exception_with_error_code(*intr_info))
@@ -6525,7 +6369,7 @@ void dump_vmcs(struct kvm_vcpu *vcpu)
static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
{
struct vcpu_vmx *vmx = to_vmx(vcpu);
- union vmx_exit_reason exit_reason = vmx->exit_reason;
+ union vmx_exit_reason exit_reason = vmx_get_exit_reason(vcpu);
u32 vectoring_info = vmx->idt_vectoring_info;
u16 exit_handler_index;
@@ -6581,7 +6425,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
* the least awful solution for the userspace case without
* risking false positives.
*/
- if (vmx->emulation_required) {
+ if (vmx->vt.emulation_required) {
nested_vmx_vmexit(vcpu, EXIT_REASON_TRIPLE_FAULT, 0, 0);
return 1;
}
@@ -6591,7 +6435,7 @@ static int __vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
}
/* If guest state is invalid, start emulating. L2 is handled above. */
- if (vmx->emulation_required)
+ if (vmx->vt.emulation_required)
return handle_invalid_guest_state(vcpu);
if (exit_reason.failed_vmentry) {
@@ -6691,7 +6535,7 @@ int vmx_handle_exit(struct kvm_vcpu *vcpu, fastpath_t exit_fastpath)
* Exit to user space when bus lock detected to inform that there is
* a bus lock in guest.
*/
- if (to_vmx(vcpu)->exit_reason.bus_lock_detected) {
+ if (vmx_get_exit_reason(vcpu).bus_lock_detected) {
if (ret > 0)
vcpu->run->exit_reason = KVM_EXIT_X86_BUS_LOCK;
@@ -6745,7 +6589,7 @@ static noinstr void vmx_l1d_flush(struct kvm_vcpu *vcpu)
vcpu->stat.l1d_flush++;
if (static_cpu_has(X86_FEATURE_FLUSH_L1D)) {
- native_wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+ native_wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
return;
}
@@ -6970,22 +6814,22 @@ static void vmx_set_rvi(int vector)
int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
+ struct vcpu_vt *vt = to_vt(vcpu);
int max_irr;
bool got_posted_interrupt;
if (KVM_BUG_ON(!enable_apicv, vcpu->kvm))
return -EIO;
- if (pi_test_on(&vmx->pi_desc)) {
- pi_clear_on(&vmx->pi_desc);
+ if (pi_test_on(&vt->pi_desc)) {
+ pi_clear_on(&vt->pi_desc);
/*
* IOMMU can write to PID.ON, so the barrier matters even on UP.
* But on x86 this is just a compiler barrier anyway.
*/
smp_mb__after_atomic();
got_posted_interrupt =
- kvm_apic_update_irr(vcpu, vmx->pi_desc.pir, &max_irr);
+ kvm_apic_update_irr(vcpu, vt->pi_desc.pir, &max_irr);
} else {
max_irr = kvm_lapic_find_highest_irr(vcpu);
got_posted_interrupt = false;
@@ -7025,14 +6869,6 @@ void vmx_load_eoi_exitmap(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap)
vmcs_write64(EOI_EXIT_BITMAP3, eoi_exit_bitmap[3]);
}
-void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
- pi_clear_on(&vmx->pi_desc);
- memset(vmx->pi_desc.pir, 0, sizeof(vmx->pi_desc.pir));
-}
-
void vmx_do_interrupt_irqoff(unsigned long entry);
void vmx_do_nmi_irqoff(void);
@@ -7052,7 +6888,7 @@ static void handle_nm_fault_irqoff(struct kvm_vcpu *vcpu)
* the #NM exception.
*/
if (is_xfd_nm_fault(vcpu))
- rdmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
+ rdmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
}
static void handle_exception_irqoff(struct kvm_vcpu *vcpu, u32 intr_info)
@@ -7089,14 +6925,12 @@ static void handle_external_interrupt_irqoff(struct kvm_vcpu *vcpu,
void vmx_handle_exit_irqoff(struct kvm_vcpu *vcpu)
{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
- if (vmx->emulation_required)
+ if (to_vt(vcpu)->emulation_required)
return;
- if (vmx->exit_reason.basic == EXIT_REASON_EXTERNAL_INTERRUPT)
+ if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_EXTERNAL_INTERRUPT)
handle_external_interrupt_irqoff(vcpu, vmx_get_intr_info(vcpu));
- else if (vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI)
+ else if (vmx_get_exit_reason(vcpu).basic == EXIT_REASON_EXCEPTION_NMI)
handle_exception_irqoff(vcpu, vmx_get_intr_info(vcpu));
}
@@ -7307,7 +7141,7 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx,
return;
if (flags & VMX_RUN_SAVE_SPEC_CTRL)
- vmx->spec_ctrl = __rdmsr(MSR_IA32_SPEC_CTRL);
+ vmx->spec_ctrl = native_rdmsrq(MSR_IA32_SPEC_CTRL);
/*
* If the guest/host SPEC_CTRL values differ, restore the host value.
@@ -7318,7 +7152,7 @@ void noinstr vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx,
*/
if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) ||
vmx->spec_ctrl != hostval)
- native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval);
+ native_wrmsrq(MSR_IA32_SPEC_CTRL, hostval);
barrier_nospec();
}
@@ -7331,10 +7165,10 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu,
* the fastpath even, all other exits must use the slow path.
*/
if (is_guest_mode(vcpu) &&
- to_vmx(vcpu)->exit_reason.basic != EXIT_REASON_PREEMPTION_TIMER)
+ vmx_get_exit_reason(vcpu).basic != EXIT_REASON_PREEMPTION_TIMER)
return EXIT_FASTPATH_NONE;
- switch (to_vmx(vcpu)->exit_reason.basic) {
+ switch (vmx_get_exit_reason(vcpu).basic) {
case EXIT_REASON_MSR_WRITE:
return handle_fastpath_set_msr_irqoff(vcpu);
case EXIT_REASON_PREEMPTION_TIMER:
@@ -7346,6 +7180,20 @@ static fastpath_t vmx_exit_handlers_fastpath(struct kvm_vcpu *vcpu,
}
}
+noinstr void vmx_handle_nmi(struct kvm_vcpu *vcpu)
+{
+ if ((u16)vmx_get_exit_reason(vcpu).basic != EXIT_REASON_EXCEPTION_NMI ||
+ !is_nmi(vmx_get_intr_info(vcpu)))
+ return;
+
+ kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
+ if (cpu_feature_enabled(X86_FEATURE_FRED))
+ fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR);
+ else
+ vmx_do_nmi_irqoff();
+ kvm_after_interrupt(vcpu);
+}
+
static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
unsigned int flags)
{
@@ -7358,12 +7206,16 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
* mitigation for MDS is done late in VMentry and is still
* executed in spite of L1D Flush. This is because an extra VERW
* should not matter much after the big hammer L1D Flush.
+ *
+ * cpu_buf_vm_clear is used when system is not vulnerable to MDS/TAA,
+ * and is affected by MMIO Stale Data. In such cases mitigation in only
+ * needed against an MMIO capable guest.
*/
if (static_branch_unlikely(&vmx_l1d_should_flush))
vmx_l1d_flush(vcpu);
- else if (static_branch_unlikely(&mmio_stale_data_clear) &&
- kvm_arch_has_assigned_device(vcpu->kvm))
- mds_clear_cpu_buffers();
+ else if (static_branch_unlikely(&cpu_buf_vm_clear) &&
+ (flags & VMX_RUN_CLEAR_CPU_BUFFERS_FOR_MMIO))
+ x86_clear_cpu_buffers();
vmx_disable_fb_clear(vmx);
@@ -7381,30 +7233,23 @@ static noinstr void vmx_vcpu_enter_exit(struct kvm_vcpu *vcpu,
vmx_enable_fb_clear(vmx);
if (unlikely(vmx->fail)) {
- vmx->exit_reason.full = 0xdead;
+ vmx->vt.exit_reason.full = 0xdead;
goto out;
}
- vmx->exit_reason.full = vmcs_read32(VM_EXIT_REASON);
- if (likely(!vmx->exit_reason.failed_vmentry))
+ vmx->vt.exit_reason.full = vmcs_read32(VM_EXIT_REASON);
+ if (likely(!vmx_get_exit_reason(vcpu).failed_vmentry))
vmx->idt_vectoring_info = vmcs_read32(IDT_VECTORING_INFO_FIELD);
- if ((u16)vmx->exit_reason.basic == EXIT_REASON_EXCEPTION_NMI &&
- is_nmi(vmx_get_intr_info(vcpu))) {
- kvm_before_interrupt(vcpu, KVM_HANDLING_NMI);
- if (cpu_feature_enabled(X86_FEATURE_FRED))
- fred_entry_from_kvm(EVENT_TYPE_NMI, NMI_VECTOR);
- else
- vmx_do_nmi_irqoff();
- kvm_after_interrupt(vcpu);
- }
+ vmx_handle_nmi(vcpu);
out:
guest_state_exit_irqoff();
}
-fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags)
{
+ bool force_immediate_exit = run_flags & KVM_RUN_FORCE_IMMEDIATE_EXIT;
struct vcpu_vmx *vmx = to_vmx(vcpu);
unsigned long cr3, cr4;
@@ -7418,15 +7263,15 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
* start emulation until we arrive back to a valid state. Synthesize a
* consistency check VM-Exit due to invalid guest state and bail.
*/
- if (unlikely(vmx->emulation_required)) {
+ if (unlikely(vmx->vt.emulation_required)) {
vmx->fail = 0;
- vmx->exit_reason.full = EXIT_REASON_INVALID_STATE;
- vmx->exit_reason.failed_vmentry = 1;
+ vmx->vt.exit_reason.full = EXIT_REASON_INVALID_STATE;
+ vmx->vt.exit_reason.failed_vmentry = 1;
kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1);
- vmx->exit_qualification = ENTRY_FAIL_DEFAULT;
+ vmx->vt.exit_qualification = ENTRY_FAIL_DEFAULT;
kvm_register_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2);
- vmx->exit_intr_info = 0;
+ vmx->vt.exit_intr_info = 0;
return EXIT_FASTPATH_NONE;
}
@@ -7449,6 +7294,12 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
vcpu->arch.regs_dirty = 0;
+ if (run_flags & KVM_RUN_LOAD_GUEST_DR6)
+ set_debugreg(vcpu->arch.dr6, 6);
+
+ if (run_flags & KVM_RUN_LOAD_DEBUGCTL)
+ vmx_reload_guest_debugctl(vcpu);
+
/*
* Refresh vmcs.HOST_CR3 if necessary. This must be done immediately
* prior to VM-Enter, as the kernel may load a new ASID (PCID) any time
@@ -7529,7 +7380,7 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
* checking.
*/
if (vmx->nested.nested_run_pending &&
- !vmx->exit_reason.failed_vmentry)
+ !vmx_get_exit_reason(vcpu).failed_vmentry)
++vcpu->stat.nested_run;
vmx->nested.nested_run_pending = 0;
@@ -7538,12 +7389,12 @@ fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit)
if (unlikely(vmx->fail))
return EXIT_FASTPATH_NONE;
- if (unlikely((u16)vmx->exit_reason.basic == EXIT_REASON_MCE_DURING_VMENTRY))
+ if (unlikely((u16)vmx_get_exit_reason(vcpu).basic == EXIT_REASON_MCE_DURING_VMENTRY))
kvm_machine_check();
trace_kvm_exit(vcpu, KVM_ISA_VMX);
- if (unlikely(vmx->exit_reason.failed_vmentry))
+ if (unlikely(vmx_get_exit_reason(vcpu).failed_vmentry))
return EXIT_FASTPATH_NONE;
vmx->loaded_vmcs->launched = 1;
@@ -7575,7 +7426,7 @@ int vmx_vcpu_create(struct kvm_vcpu *vcpu)
BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0);
vmx = to_vmx(vcpu);
- INIT_LIST_HEAD(&vmx->pi_wakeup_list);
+ INIT_LIST_HEAD(&vmx->vt.pi_wakeup_list);
err = -ENOMEM;
@@ -7623,26 +7474,6 @@ int vmx_vcpu_create(struct kvm_vcpu *vcpu)
evmcs->hv_enlightenments_control.msr_bitmap = 1;
}
- /* The MSR bitmap starts with all ones */
- bitmap_fill(vmx->shadow_msr_intercept.read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
- bitmap_fill(vmx->shadow_msr_intercept.write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
-
- vmx_disable_intercept_for_msr(vcpu, MSR_IA32_TSC, MSR_TYPE_R);
-#ifdef CONFIG_X86_64
- vmx_disable_intercept_for_msr(vcpu, MSR_FS_BASE, MSR_TYPE_RW);
- vmx_disable_intercept_for_msr(vcpu, MSR_GS_BASE, MSR_TYPE_RW);
- vmx_disable_intercept_for_msr(vcpu, MSR_KERNEL_GS_BASE, MSR_TYPE_RW);
-#endif
- vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_CS, MSR_TYPE_RW);
- vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_ESP, MSR_TYPE_RW);
- vmx_disable_intercept_for_msr(vcpu, MSR_IA32_SYSENTER_EIP, MSR_TYPE_RW);
- if (kvm_cstate_in_guest(vcpu->kvm)) {
- vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C1_RES, MSR_TYPE_R);
- vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C3_RESIDENCY, MSR_TYPE_R);
- vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C6_RESIDENCY, MSR_TYPE_R);
- vmx_disable_intercept_for_msr(vcpu, MSR_CORE_C7_RESIDENCY, MSR_TYPE_R);
- }
-
vmx->loaded_vmcs = &vmx->vmcs01;
if (cpu_need_virtualize_apic_accesses(vcpu)) {
@@ -7673,7 +7504,7 @@ int vmx_vcpu_create(struct kvm_vcpu *vcpu)
if (vmx_can_use_ipiv(vcpu))
WRITE_ONCE(to_kvm_vmx(vcpu->kvm)->pid_table[vcpu->vcpu_id],
- __pa(&vmx->pi_desc) | PID_TABLE_ENTRY_VALID);
+ __pa(&vmx->vt.pi_desc) | PID_TABLE_ENTRY_VALID);
return 0;
@@ -7692,7 +7523,7 @@ free_vpid:
int vmx_vm_init(struct kvm *kvm)
{
if (!ple_gap)
- kvm->arch.pause_in_guest = true;
+ kvm_disable_exits(kvm, KVM_X86_DISABLE_EXITS_PAUSE);
if (boot_cpu_has(X86_BUG_L1TF) && enable_ept) {
switch (l1tf_mitigation) {
@@ -7700,6 +7531,7 @@ int vmx_vm_init(struct kvm *kvm)
case L1TF_MITIGATION_FLUSH_NOWARN:
/* 'I explicitly don't care' is set */
break;
+ case L1TF_MITIGATION_AUTO:
case L1TF_MITIGATION_FLUSH:
case L1TF_MITIGATION_FLUSH_NOSMT:
case L1TF_MITIGATION_FULL:
@@ -7717,9 +7549,23 @@ int vmx_vm_init(struct kvm *kvm)
break;
}
}
+
+ if (enable_pml)
+ kvm->arch.cpu_dirty_log_size = PML_LOG_NR_ENTRIES;
return 0;
}
+static inline bool vmx_ignore_guest_pat(struct kvm *kvm)
+{
+ /*
+ * Non-coherent DMA devices need the guest to flush CPU properly.
+ * In that case it is not possible to map all guest RAM as WB, so
+ * always trust guest PAT.
+ */
+ return !kvm_arch_has_noncoherent_dma(kvm) &&
+ kvm_check_has_quirk(kvm, KVM_X86_QUIRK_IGNORE_GUEST_PAT);
+}
+
u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
{
/*
@@ -7729,13 +7575,8 @@ u8 vmx_get_mt_mask(struct kvm_vcpu *vcpu, gfn_t gfn, bool is_mmio)
if (is_mmio)
return MTRR_TYPE_UNCACHABLE << VMX_EPT_MT_EPTE_SHIFT;
- /*
- * Force WB and ignore guest PAT if the VM does NOT have a non-coherent
- * device attached. Letting the guest control memory types on Intel
- * CPUs may result in unexpected behavior, and so KVM's ABI is to trust
- * the guest to behave only as a last resort.
- */
- if (!kvm_arch_has_noncoherent_dma(vcpu->kvm))
+ /* Force WB if ignoring guest PAT */
+ if (vmx_ignore_guest_pat(vcpu->kvm))
return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT) | VMX_EPT_IPAT_BIT;
return (MTRR_TYPE_WRBACK << VMX_EPT_MT_EPTE_SHIFT);
@@ -7919,18 +7760,6 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
}
}
- if (kvm_cpu_cap_has(X86_FEATURE_XFD))
- vmx_set_intercept_for_msr(vcpu, MSR_IA32_XFD_ERR, MSR_TYPE_R,
- !guest_cpu_cap_has(vcpu, X86_FEATURE_XFD));
-
- if (boot_cpu_has(X86_FEATURE_IBPB))
- vmx_set_intercept_for_msr(vcpu, MSR_IA32_PRED_CMD, MSR_TYPE_W,
- !guest_has_pred_cmd_msr(vcpu));
-
- if (boot_cpu_has(X86_FEATURE_FLUSH_L1D))
- vmx_set_intercept_for_msr(vcpu, MSR_IA32_FLUSH_CMD, MSR_TYPE_W,
- !guest_cpu_cap_has(vcpu, X86_FEATURE_FLUSH_L1D));
-
set_cr4_guest_host_mask(vmx);
vmx_write_encls_bitmap(vcpu, NULL);
@@ -7946,6 +7775,9 @@ void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu)
vmx->msr_ia32_feature_control_valid_bits &=
~FEAT_CTL_SGX_LC_ENABLED;
+ /* Recalc MSR interception to account for feature changes. */
+ vmx_recalc_msr_intercepts(vcpu);
+
/* Refresh #PF interception to account for MAXPHYADDR changes. */
vmx_update_exception_bitmap(vcpu);
}
@@ -7959,7 +7791,7 @@ static __init u64 vmx_get_perf_capabilities(void)
return 0;
if (boot_cpu_has(X86_FEATURE_PDCM))
- rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
+ rdmsrq(MSR_IA32_PERF_CAPABILITIES, host_perf_cap);
if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) {
x86_perf_get_lbr(&vmx_lbr_caps);
@@ -8508,7 +8340,7 @@ __init int vmx_hardware_setup(void)
kvm_enable_efer_bits(EFER_NX);
if (boot_cpu_has(X86_FEATURE_MPX)) {
- rdmsrl(MSR_IA32_BNDCFGS, host_bndcfgs);
+ rdmsrq(MSR_IA32_BNDCFGS, host_bndcfgs);
WARN_ONCE(host_bndcfgs, "BNDCFGS in host will be lost");
}
@@ -8597,6 +8429,8 @@ __init int vmx_hardware_setup(void)
if (enable_ept)
kvm_mmu_set_ept_masks(enable_ept_ad_bits,
cpu_has_vmx_ept_execute_only());
+ else
+ vt_x86_ops.get_mt_mask = NULL;
/*
* Setup shadow_me_value/shadow_me_mask to include MKTME KeyID
@@ -8614,9 +8448,6 @@ __init int vmx_hardware_setup(void)
if (!enable_ept || !enable_ept_ad_bits || !cpu_has_vmx_pml())
enable_pml = 0;
- if (!enable_pml)
- vt_x86_ops.cpu_dirty_log_size = 0;
-
if (!cpu_has_vmx_preemption_timer())
enable_preemption_timer = false;
@@ -8674,6 +8505,27 @@ __init int vmx_hardware_setup(void)
kvm_set_posted_intr_wakeup_handler(pi_wakeup_handler);
+ /*
+ * On Intel CPUs that lack self-snoop feature, letting the guest control
+ * memory types may result in unexpected behavior. So always ignore guest
+ * PAT on those CPUs and map VM as writeback, not allowing userspace to
+ * disable the quirk.
+ *
+ * On certain Intel CPUs (e.g. SPR, ICX), though self-snoop feature is
+ * supported, UC is slow enough to cause issues with some older guests (e.g.
+ * an old version of bochs driver uses ioremap() instead of ioremap_wc() to
+ * map the video RAM, causing wayland desktop to fail to get started
+ * correctly). To avoid breaking those older guests that rely on KVM to force
+ * memory type to WB, provide KVM_X86_QUIRK_IGNORE_GUEST_PAT to preserve the
+ * safer (for performance) default behavior.
+ *
+ * On top of this, non-coherent DMA devices need the guest to flush CPU
+ * caches properly. This also requires honoring guest PAT, and is forced
+ * independent of the quirk in vmx_ignore_guest_pat().
+ */
+ if (!static_cpu_has(X86_FEATURE_SELFSNOOP))
+ kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT;
+ kvm_caps.inapplicable_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT;
return r;
}
@@ -8687,26 +8539,21 @@ static void vmx_cleanup_l1d_flush(void)
l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO;
}
-static void __vmx_exit(void)
+void vmx_exit(void)
{
allow_smaller_maxphyaddr = false;
vmx_cleanup_l1d_flush();
-}
-static void __exit vmx_exit(void)
-{
- kvm_exit();
- __vmx_exit();
kvm_x86_vendor_exit();
-
}
-module_exit(vmx_exit);
-static int __init vmx_init(void)
+int __init vmx_init(void)
{
int r, cpu;
+ KVM_SANITY_CHECK_VM_STRUCT_SIZE(kvm_vmx);
+
if (!kvm_is_vmx_supported())
return -EOPNOTSUPP;
@@ -8747,21 +8594,9 @@ static int __init vmx_init(void)
if (!enable_ept)
allow_smaller_maxphyaddr = true;
- /*
- * Common KVM initialization _must_ come last, after this, /dev/kvm is
- * exposed to userspace!
- */
- r = kvm_init(sizeof(struct vcpu_vmx), __alignof__(struct vcpu_vmx),
- THIS_MODULE);
- if (r)
- goto err_kvm_init;
-
return 0;
-err_kvm_init:
- __vmx_exit();
err_l1d_flush:
kvm_x86_vendor_exit();
return r;
}
-module_init(vmx_init);
diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
index 951e44dc9d0e..d3389baf3ab3 100644
--- a/arch/x86/kvm/vmx/vmx.h
+++ b/arch/x86/kvm/vmx/vmx.h
@@ -11,13 +11,13 @@
#include "capabilities.h"
#include "../kvm_cache_regs.h"
+#include "pmu_intel.h"
#include "vmcs.h"
#include "vmx_ops.h"
#include "../cpuid.h"
#include "run_flags.h"
#include "../mmu.h"
-
-#define X2APIC_MSR(r) (APIC_BASE_MSR + ((r) >> 4))
+#include "common.h"
#ifdef CONFIG_X86_64
#define MAX_NR_USER_RETURN_MSRS 7
@@ -67,47 +67,6 @@ struct pt_desc {
struct pt_ctx guest;
};
-union vmx_exit_reason {
- struct {
- u32 basic : 16;
- u32 reserved16 : 1;
- u32 reserved17 : 1;
- u32 reserved18 : 1;
- u32 reserved19 : 1;
- u32 reserved20 : 1;
- u32 reserved21 : 1;
- u32 reserved22 : 1;
- u32 reserved23 : 1;
- u32 reserved24 : 1;
- u32 reserved25 : 1;
- u32 bus_lock_detected : 1;
- u32 enclave_mode : 1;
- u32 smi_pending_mtf : 1;
- u32 smi_from_vmx_root : 1;
- u32 reserved30 : 1;
- u32 failed_vmentry : 1;
- };
- u32 full;
-};
-
-struct lbr_desc {
- /* Basic info about guest LBR records. */
- struct x86_pmu_lbr records;
-
- /*
- * Emulate LBR feature via passthrough LBR registers when the
- * per-vcpu guest LBR event is scheduled on the current pcpu.
- *
- * The records may be inaccurate if the host reclaims the LBR.
- */
- struct perf_event *event;
-
- /* True if LBRs are marked as not intercepted in the MSR bitmap */
- bool msr_passthrough;
-};
-
-extern struct x86_pmu_lbr vmx_lbr_caps;
-
/*
* The nested_vmx structure is part of vcpu_vmx, and holds information we need
* for correct emulation of VMX (i.e., nested VMX) on this vcpu.
@@ -248,20 +207,10 @@ struct nested_vmx {
struct vcpu_vmx {
struct kvm_vcpu vcpu;
+ struct vcpu_vt vt;
u8 fail;
u8 x2apic_msr_bitmap_mode;
- /*
- * If true, host state has been stored in vmx->loaded_vmcs for
- * the CPU registers that only need to be switched when transitioning
- * to/from the kernel, and the registers have been loaded with guest
- * values. If false, host state is loaded in the CPU registers
- * and vmx->loaded_vmcs->host_state is invalid.
- */
- bool guest_state_loaded;
-
- unsigned long exit_qualification;
- u32 exit_intr_info;
u32 idt_vectoring_info;
ulong rflags;
@@ -274,7 +223,6 @@ struct vcpu_vmx {
struct vmx_uret_msr guest_uret_msrs[MAX_NR_USER_RETURN_MSRS];
bool guest_uret_msrs_loaded;
#ifdef CONFIG_X86_64
- u64 msr_host_kernel_gs_base;
u64 msr_guest_kernel_gs_base;
#endif
@@ -313,15 +261,6 @@ struct vcpu_vmx {
} seg[8];
} segment_cache;
int vpid;
- bool emulation_required;
-
- union vmx_exit_reason exit_reason;
-
- /* Posted interrupt descriptor */
- struct pi_desc pi_desc;
-
- /* Used if this vCPU is waiting for PI notification wakeup. */
- struct list_head pi_wakeup_list;
/* Support for a guest hypervisor (nested VMX) */
struct nested_vmx nested;
@@ -355,13 +294,6 @@ struct vcpu_vmx {
struct pt_desc pt_desc;
struct lbr_desc lbr_desc;
- /* Save desired MSR intercept (read: pass-through) state */
-#define MAX_POSSIBLE_PASSTHROUGH_MSRS 16
- struct {
- DECLARE_BITMAP(read, MAX_POSSIBLE_PASSTHROUGH_MSRS);
- DECLARE_BITMAP(write, MAX_POSSIBLE_PASSTHROUGH_MSRS);
- } shadow_msr_intercept;
-
/* ve_info must be page aligned. */
struct vmx_ve_information *ve_info;
};
@@ -376,8 +308,44 @@ struct kvm_vmx {
u64 *pid_table;
};
-void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu,
- struct loaded_vmcs *buddy);
+static __always_inline struct vcpu_vt *to_vt(struct kvm_vcpu *vcpu)
+{
+ return &(container_of(vcpu, struct vcpu_vmx, vcpu)->vt);
+}
+
+static __always_inline struct kvm_vcpu *vt_to_vcpu(struct vcpu_vt *vt)
+{
+ return &(container_of(vt, struct vcpu_vmx, vt)->vcpu);
+}
+
+static __always_inline union vmx_exit_reason vmx_get_exit_reason(struct kvm_vcpu *vcpu)
+{
+ return to_vt(vcpu)->exit_reason;
+}
+
+static __always_inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vt *vt = to_vt(vcpu);
+
+ if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1) &&
+ !WARN_ON_ONCE(is_td_vcpu(vcpu)))
+ vt->exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
+
+ return vt->exit_qualification;
+}
+
+static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu)
+{
+ struct vcpu_vt *vt = to_vt(vcpu);
+
+ if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2) &&
+ !WARN_ON_ONCE(is_td_vcpu(vcpu)))
+ vt->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
+
+ return vt->exit_intr_info;
+}
+
+void vmx_vcpu_load_vmcs(struct kvm_vcpu *vcpu, int cpu);
int allocate_vpid(void);
void free_vpid(int vpid);
void vmx_set_constant_host_state(struct vcpu_vmx *vmx);
@@ -418,24 +386,54 @@ bool __vmx_vcpu_run(struct vcpu_vmx *vmx, unsigned long *regs,
int vmx_find_loadstore_msr_slot(struct vmx_msrs *m, u32 msr);
void vmx_ept_load_pdptrs(struct kvm_vcpu *vcpu);
-void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type);
-void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type);
+void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr, int type, bool set);
+
+static inline void vmx_disable_intercept_for_msr(struct kvm_vcpu *vcpu,
+ u32 msr, int type)
+{
+ vmx_set_intercept_for_msr(vcpu, msr, type, false);
+}
+
+static inline void vmx_enable_intercept_for_msr(struct kvm_vcpu *vcpu,
+ u32 msr, int type)
+{
+ vmx_set_intercept_for_msr(vcpu, msr, type, true);
+}
u64 vmx_get_l2_tsc_offset(struct kvm_vcpu *vcpu);
u64 vmx_get_l2_tsc_multiplier(struct kvm_vcpu *vcpu);
gva_t vmx_get_untagged_addr(struct kvm_vcpu *vcpu, gva_t gva, unsigned int flags);
-static inline void vmx_set_intercept_for_msr(struct kvm_vcpu *vcpu, u32 msr,
- int type, bool value)
+void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+
+u64 vmx_get_supported_debugctl(struct kvm_vcpu *vcpu, bool host_initiated);
+bool vmx_is_valid_debugctl(struct kvm_vcpu *vcpu, u64 data, bool host_initiated);
+
+#define VMX_HOST_OWNED_DEBUGCTL_BITS (DEBUGCTLMSR_FREEZE_IN_SMM)
+
+static inline void vmx_guest_debugctl_write(struct kvm_vcpu *vcpu, u64 val)
+{
+ WARN_ON_ONCE(val & VMX_HOST_OWNED_DEBUGCTL_BITS);
+
+ val |= vcpu->arch.host_debugctl & VMX_HOST_OWNED_DEBUGCTL_BITS;
+ vmcs_write64(GUEST_IA32_DEBUGCTL, val);
+}
+
+static inline u64 vmx_guest_debugctl_read(void)
{
- if (value)
- vmx_enable_intercept_for_msr(vcpu, msr, type);
- else
- vmx_disable_intercept_for_msr(vcpu, msr, type);
+ return vmcs_read64(GUEST_IA32_DEBUGCTL) & ~VMX_HOST_OWNED_DEBUGCTL_BITS;
}
-void vmx_update_cpu_dirty_logging(struct kvm_vcpu *vcpu);
+static inline void vmx_reload_guest_debugctl(struct kvm_vcpu *vcpu)
+{
+ u64 val = vmcs_read64(GUEST_IA32_DEBUGCTL);
+
+ if (!((val ^ vcpu->arch.host_debugctl) & VMX_HOST_OWNED_DEBUGCTL_BITS))
+ return;
+
+ vmx_guest_debugctl_write(vcpu, val & ~VMX_HOST_OWNED_DEBUGCTL_BITS);
+}
/*
* Note, early Intel manuals have the write-low and read-high bitmap offsets
@@ -662,45 +660,10 @@ static __always_inline struct vcpu_vmx *to_vmx(struct kvm_vcpu *vcpu)
return container_of(vcpu, struct vcpu_vmx, vcpu);
}
-static inline struct lbr_desc *vcpu_to_lbr_desc(struct kvm_vcpu *vcpu)
-{
- return &to_vmx(vcpu)->lbr_desc;
-}
-
-static inline struct x86_pmu_lbr *vcpu_to_lbr_records(struct kvm_vcpu *vcpu)
-{
- return &vcpu_to_lbr_desc(vcpu)->records;
-}
-
-static inline bool intel_pmu_lbr_is_enabled(struct kvm_vcpu *vcpu)
-{
- return !!vcpu_to_lbr_records(vcpu)->nr;
-}
-
void intel_pmu_cross_mapped_check(struct kvm_pmu *pmu);
int intel_pmu_create_guest_lbr_event(struct kvm_vcpu *vcpu);
void vmx_passthrough_lbr_msrs(struct kvm_vcpu *vcpu);
-static __always_inline unsigned long vmx_get_exit_qual(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
- if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_1))
- vmx->exit_qualification = vmcs_readl(EXIT_QUALIFICATION);
-
- return vmx->exit_qualification;
-}
-
-static __always_inline u32 vmx_get_intr_info(struct kvm_vcpu *vcpu)
-{
- struct vcpu_vmx *vmx = to_vmx(vcpu);
-
- if (!kvm_register_test_and_mark_available(vcpu, VCPU_EXREG_EXIT_INFO_2))
- vmx->exit_intr_info = vmcs_read32(VM_EXIT_INTR_INFO);
-
- return vmx->exit_intr_info;
-}
-
struct vmcs *alloc_vmcs_cpu(bool shadow, int cpu, gfp_t flags);
void free_vmcs(struct vmcs *vmcs);
int alloc_loaded_vmcs(struct loaded_vmcs *loaded_vmcs);
@@ -758,4 +721,7 @@ static inline void vmx_segment_cache_clear(struct vcpu_vmx *vmx)
vmx->segment_cache.bitmask = 0;
}
+int vmx_init(void);
+void vmx_exit(void);
+
#endif /* __KVM_X86_VMX_H */
diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
index 430773a5ef8e..2b3424f638db 100644
--- a/arch/x86/kvm/vmx/x86_ops.h
+++ b/arch/x86/kvm/vmx/x86_ops.h
@@ -21,7 +21,7 @@ void vmx_vm_destroy(struct kvm *kvm);
int vmx_vcpu_precreate(struct kvm *kvm);
int vmx_vcpu_create(struct kvm_vcpu *vcpu);
int vmx_vcpu_pre_run(struct kvm_vcpu *vcpu);
-fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, bool force_immediate_exit);
+fastpath_t vmx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags);
void vmx_vcpu_free(struct kvm_vcpu *vcpu);
void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
void vmx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
@@ -46,18 +46,18 @@ int vmx_check_intercept(struct kvm_vcpu *vcpu,
bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu);
void vmx_migrate_timers(struct kvm_vcpu *vcpu);
void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
-void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu);
void vmx_hwapic_isr_update(struct kvm_vcpu *vcpu, int max_isr);
int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu);
void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
int trig_mode, int vector);
void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu);
bool vmx_has_emulated_msr(struct kvm *kvm, u32 index);
-void vmx_msr_filter_changed(struct kvm_vcpu *vcpu);
+void vmx_recalc_msr_intercepts(struct kvm_vcpu *vcpu);
void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu);
int vmx_get_feature_msr(u32 msr, u64 *data);
int vmx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info);
+#define vmx_complete_emulated_msr kvm_complete_insn_gp
u64 vmx_get_segment_base(struct kvm_vcpu *vcpu, int seg);
void vmx_get_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
void vmx_set_segment(struct kvm_vcpu *vcpu, struct kvm_segment *var, int seg);
@@ -121,4 +121,39 @@ void vmx_cancel_hv_timer(struct kvm_vcpu *vcpu);
#endif
void vmx_setup_mce(struct kvm_vcpu *vcpu);
+#ifdef CONFIG_KVM_INTEL_TDX
+void tdx_disable_virtualization_cpu(void);
+int tdx_vm_init(struct kvm *kvm);
+void tdx_mmu_release_hkid(struct kvm *kvm);
+void tdx_vm_destroy(struct kvm *kvm);
+int tdx_vm_ioctl(struct kvm *kvm, void __user *argp);
+
+int tdx_vcpu_create(struct kvm_vcpu *vcpu);
+void tdx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event);
+void tdx_vcpu_free(struct kvm_vcpu *vcpu);
+void tdx_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
+int tdx_vcpu_pre_run(struct kvm_vcpu *vcpu);
+fastpath_t tdx_vcpu_run(struct kvm_vcpu *vcpu, u64 run_flags);
+void tdx_prepare_switch_to_guest(struct kvm_vcpu *vcpu);
+void tdx_vcpu_put(struct kvm_vcpu *vcpu);
+int tdx_handle_exit(struct kvm_vcpu *vcpu,
+ enum exit_fastpath_completion fastpath);
+
+void tdx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
+ int trig_mode, int vector);
+void tdx_inject_nmi(struct kvm_vcpu *vcpu);
+void tdx_get_exit_info(struct kvm_vcpu *vcpu, u32 *reason,
+ u64 *info1, u64 *info2, u32 *intr_info, u32 *error_code);
+bool tdx_has_emulated_msr(u32 index);
+int tdx_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
+int tdx_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr);
+
+int tdx_vcpu_ioctl(struct kvm_vcpu *vcpu, void __user *argp);
+
+void tdx_flush_tlb_current(struct kvm_vcpu *vcpu);
+void tdx_flush_tlb_all(struct kvm_vcpu *vcpu);
+void tdx_load_mmu_pgd(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
+int tdx_gmem_private_max_mapping_level(struct kvm *kvm, kvm_pfn_t pfn);
+#endif
+
#endif /* __KVM_X86_VMX_X86_OPS_H */
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index be7bb6d20129..a1c49bc681c4 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -90,7 +90,6 @@
#include "trace.h"
#define MAX_IO_MSRS 256
-#define KVM_MAX_MCE_BANKS 32
/*
* Note, kvm_caps fields should *never* have default values, all fields must be
@@ -227,6 +226,12 @@ EXPORT_SYMBOL_GPL(allow_smaller_maxphyaddr);
bool __read_mostly enable_apicv = true;
EXPORT_SYMBOL_GPL(enable_apicv);
+bool __read_mostly enable_ipiv = true;
+EXPORT_SYMBOL_GPL(enable_ipiv);
+
+bool __read_mostly enable_device_posted_irqs = true;
+EXPORT_SYMBOL_GPL(enable_device_posted_irqs);
+
const struct _kvm_stats_desc kvm_vm_stats_desc[] = {
KVM_GENERIC_VM_STATS(),
STATS_DESC_COUNTER(VM, mmu_shadow_zapped),
@@ -578,7 +583,7 @@ static void kvm_on_user_return(struct user_return_notifier *urn)
for (slot = 0; slot < kvm_nr_uret_msrs; ++slot) {
values = &msrs->values[slot];
if (values->host != values->curr) {
- wrmsrl(kvm_uret_msrs_list[slot], values->host);
+ wrmsrq(kvm_uret_msrs_list[slot], values->host);
values->curr = values->host;
}
}
@@ -590,10 +595,10 @@ static int kvm_probe_user_return_msr(u32 msr)
int ret;
preempt_disable();
- ret = rdmsrl_safe(msr, &val);
+ ret = rdmsrq_safe(msr, &val);
if (ret)
goto out;
- ret = wrmsrl_safe(msr, val);
+ ret = wrmsrq_safe(msr, val);
out:
preempt_enable();
return ret;
@@ -630,12 +635,21 @@ static void kvm_user_return_msr_cpu_online(void)
int i;
for (i = 0; i < kvm_nr_uret_msrs; ++i) {
- rdmsrl_safe(kvm_uret_msrs_list[i], &value);
+ rdmsrq_safe(kvm_uret_msrs_list[i], &value);
msrs->values[i].host = value;
msrs->values[i].curr = value;
}
}
+static void kvm_user_return_register_notifier(struct kvm_user_return_msrs *msrs)
+{
+ if (!msrs->registered) {
+ msrs->urn.on_user_return = kvm_on_user_return;
+ user_return_notifier_register(&msrs->urn);
+ msrs->registered = true;
+ }
+}
+
int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
{
struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
@@ -644,20 +658,25 @@ int kvm_set_user_return_msr(unsigned slot, u64 value, u64 mask)
value = (value & mask) | (msrs->values[slot].host & ~mask);
if (value == msrs->values[slot].curr)
return 0;
- err = wrmsrl_safe(kvm_uret_msrs_list[slot], value);
+ err = wrmsrq_safe(kvm_uret_msrs_list[slot], value);
if (err)
return 1;
msrs->values[slot].curr = value;
- if (!msrs->registered) {
- msrs->urn.on_user_return = kvm_on_user_return;
- user_return_notifier_register(&msrs->urn);
- msrs->registered = true;
- }
+ kvm_user_return_register_notifier(msrs);
return 0;
}
EXPORT_SYMBOL_GPL(kvm_set_user_return_msr);
+void kvm_user_return_msr_update_cache(unsigned int slot, u64 value)
+{
+ struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
+
+ msrs->values[slot].curr = value;
+ kvm_user_return_register_notifier(msrs);
+}
+EXPORT_SYMBOL_GPL(kvm_user_return_msr_update_cache);
+
static void drop_user_return_notifiers(void)
{
struct kvm_user_return_msrs *msrs = this_cpu_ptr(user_return_msrs);
@@ -1174,7 +1193,7 @@ void kvm_load_guest_xsave_state(struct kvm_vcpu *vcpu)
if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) &&
vcpu->arch.ia32_xss != kvm_host.xss)
- wrmsrl(MSR_IA32_XSS, vcpu->arch.ia32_xss);
+ wrmsrq(MSR_IA32_XSS, vcpu->arch.ia32_xss);
}
if (cpu_feature_enabled(X86_FEATURE_PKU) &&
@@ -1205,7 +1224,7 @@ void kvm_load_host_xsave_state(struct kvm_vcpu *vcpu)
if (guest_cpu_cap_has(vcpu, X86_FEATURE_XSAVES) &&
vcpu->arch.ia32_xss != kvm_host.xss)
- wrmsrl(MSR_IA32_XSS, kvm_host.xss);
+ wrmsrq(MSR_IA32_XSS, kvm_host.xss);
}
}
@@ -1662,7 +1681,7 @@ static int kvm_get_feature_msr(struct kvm_vcpu *vcpu, u32 index, u64 *data,
*data = MSR_PLATFORM_INFO_CPUID_FAULT;
break;
case MSR_IA32_UCODE_REV:
- rdmsrl_safe(index, data);
+ rdmsrq_safe(index, data);
break;
default:
return kvm_x86_call(get_feature_msr)(index, data);
@@ -3242,9 +3261,11 @@ int kvm_guest_time_update(struct kvm_vcpu *v)
/* With all the info we got, fill in the values */
- if (kvm_caps.has_tsc_control)
+ if (kvm_caps.has_tsc_control) {
tgt_tsc_khz = kvm_scale_tsc(tgt_tsc_khz,
v->arch.l1_tsc_scaling_ratio);
+ tgt_tsc_khz = tgt_tsc_khz ? : 1;
+ }
if (unlikely(vcpu->hw_tsc_khz != tgt_tsc_khz)) {
kvm_get_time_scale(NSEC_PER_SEC, tgt_tsc_khz * 1000LL,
@@ -3829,7 +3850,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (!data)
break;
- wrmsrl(MSR_IA32_PRED_CMD, data);
+ wrmsrq(MSR_IA32_PRED_CMD, data);
break;
}
case MSR_IA32_FLUSH_CMD:
@@ -3842,7 +3863,7 @@ int kvm_set_msr_common(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
if (!data)
break;
- wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+ wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
break;
case MSR_EFER:
return set_efer(vcpu, msr_info);
@@ -4561,6 +4582,9 @@ static u64 kvm_get_allowed_disable_exits(void)
{
u64 r = KVM_X86_DISABLE_EXITS_PAUSE;
+ if (boot_cpu_has(X86_FEATURE_APERFMPERF))
+ r |= KVM_X86_DISABLE_EXITS_APERFMPERF;
+
if (!mitigate_smt_rsb) {
r |= KVM_X86_DISABLE_EXITS_HLT |
KVM_X86_DISABLE_EXITS_CSTATE;
@@ -4616,17 +4640,20 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
case KVM_CAP_EXT_CPUID:
case KVM_CAP_EXT_EMUL_CPUID:
case KVM_CAP_CLOCKSOURCE:
+#ifdef CONFIG_KVM_IOAPIC
case KVM_CAP_PIT:
+ case KVM_CAP_PIT2:
+ case KVM_CAP_PIT_STATE2:
+ case KVM_CAP_REINJECT_CONTROL:
+#endif
case KVM_CAP_NOP_IO_DELAY:
case KVM_CAP_MP_STATE:
case KVM_CAP_SYNC_MMU:
case KVM_CAP_USER_NMI:
- case KVM_CAP_REINJECT_CONTROL:
case KVM_CAP_IRQ_INJECT_STATUS:
case KVM_CAP_IOEVENTFD:
case KVM_CAP_IOEVENTFD_NO_LENGTH:
- case KVM_CAP_PIT2:
- case KVM_CAP_PIT_STATE2:
+
case KVM_CAP_SET_IDENTITY_MAP_ADDR:
case KVM_CAP_VCPU_EVENTS:
#ifdef CONFIG_KVM_HYPERV
@@ -4739,6 +4766,8 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
break;
case KVM_CAP_MAX_VCPUS:
r = KVM_MAX_VCPUS;
+ if (kvm)
+ r = kvm->max_vcpus;
break;
case KVM_CAP_MAX_VCPU_ID:
r = KVM_MAX_VCPU_IDS;
@@ -4794,7 +4823,7 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
r = enable_pmu ? KVM_CAP_PMU_VALID_MASK : 0;
break;
case KVM_CAP_DISABLE_QUIRKS2:
- r = KVM_X86_VALID_QUIRKS;
+ r = kvm_caps.supported_quirks;
break;
case KVM_CAP_X86_NOTIFY_VMEXIT:
r = kvm_caps.has_notify_vmexit;
@@ -4965,16 +4994,13 @@ out:
return r;
}
-static void wbinvd_ipi(void *garbage)
-{
- wbinvd();
-}
-
static bool need_emulate_wbinvd(struct kvm_vcpu *vcpu)
{
return kvm_arch_has_noncoherent_dma(vcpu->kvm);
}
+static DEFINE_PER_CPU(struct kvm_vcpu *, last_vcpu);
+
void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
{
struct kvm_pmu *pmu = vcpu_to_pmu(vcpu);
@@ -4991,12 +5017,24 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
if (kvm_x86_call(has_wbinvd_exit)())
cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
else if (vcpu->cpu != -1 && vcpu->cpu != cpu)
- smp_call_function_single(vcpu->cpu,
- wbinvd_ipi, NULL, 1);
+ wbinvd_on_cpu(vcpu->cpu);
}
kvm_x86_call(vcpu_load)(vcpu, cpu);
+ if (vcpu != per_cpu(last_vcpu, cpu)) {
+ /*
+ * Flush the branch predictor when switching vCPUs on the same
+ * physical CPU, as each vCPU needs its own branch prediction
+ * domain. No IBPB is needed when switching between L1 and L2
+ * on the same vCPU unless IBRS is advertised to the vCPU; that
+ * is handled on the nested VM-Exit path.
+ */
+ if (static_branch_likely(&switch_vcpu_ibpb))
+ indirect_branch_prediction_barrier();
+ per_cpu(last_vcpu, cpu) = vcpu;
+ }
+
/* Save host pkru register if supported */
vcpu->arch.host_pkru = read_pkru();
@@ -5117,6 +5155,9 @@ void kvm_arch_vcpu_put(struct kvm_vcpu *vcpu)
static int kvm_vcpu_ioctl_get_lapic(struct kvm_vcpu *vcpu,
struct kvm_lapic_state *s)
{
+ if (vcpu->arch.apic->guest_apic_protected)
+ return -EINVAL;
+
kvm_x86_call(sync_pir_to_irr)(vcpu);
return kvm_apic_get_state(vcpu, s);
@@ -5127,6 +5168,9 @@ static int kvm_vcpu_ioctl_set_lapic(struct kvm_vcpu *vcpu,
{
int r;
+ if (vcpu->arch.apic->guest_apic_protected)
+ return -EINVAL;
+
r = kvm_apic_set_state(vcpu, s);
if (r)
return r;
@@ -5448,12 +5492,6 @@ static int kvm_vcpu_ioctl_x86_set_vcpu_events(struct kvm_vcpu *vcpu,
(events->exception.nr > 31 || events->exception.nr == NMI_VECTOR))
return -EINVAL;
- /* INITs are latched while in SMM */
- if (events->flags & KVM_VCPUEVENT_VALID_SMM &&
- (events->smi.smm || events->smi.pending) &&
- vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED)
- return -EINVAL;
-
process_nmi(vcpu);
/*
@@ -6147,6 +6185,10 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
u32 user_tsc_khz;
r = -EINVAL;
+
+ if (vcpu->arch.guest_tsc_protected)
+ goto out;
+
user_tsc_khz = (u32)arg;
if (kvm_caps.has_tsc_control &&
@@ -6304,6 +6346,12 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
case KVM_SET_DEVICE_ATTR:
r = kvm_vcpu_ioctl_device_attr(vcpu, ioctl, argp);
break;
+ case KVM_MEMORY_ENCRYPT_OP:
+ r = -ENOTTY;
+ if (!kvm_x86_ops.vcpu_mem_enc_ioctl)
+ goto out;
+ r = kvm_x86_ops.vcpu_mem_enc_ioctl(vcpu, argp);
+ break;
default:
r = -EINVAL;
}
@@ -6350,135 +6398,6 @@ static int kvm_vm_ioctl_set_nr_mmu_pages(struct kvm *kvm,
return 0;
}
-static int kvm_vm_ioctl_get_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
-{
- struct kvm_pic *pic = kvm->arch.vpic;
- int r;
-
- r = 0;
- switch (chip->chip_id) {
- case KVM_IRQCHIP_PIC_MASTER:
- memcpy(&chip->chip.pic, &pic->pics[0],
- sizeof(struct kvm_pic_state));
- break;
- case KVM_IRQCHIP_PIC_SLAVE:
- memcpy(&chip->chip.pic, &pic->pics[1],
- sizeof(struct kvm_pic_state));
- break;
- case KVM_IRQCHIP_IOAPIC:
- kvm_get_ioapic(kvm, &chip->chip.ioapic);
- break;
- default:
- r = -EINVAL;
- break;
- }
- return r;
-}
-
-static int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
-{
- struct kvm_pic *pic = kvm->arch.vpic;
- int r;
-
- r = 0;
- switch (chip->chip_id) {
- case KVM_IRQCHIP_PIC_MASTER:
- spin_lock(&pic->lock);
- memcpy(&pic->pics[0], &chip->chip.pic,
- sizeof(struct kvm_pic_state));
- spin_unlock(&pic->lock);
- break;
- case KVM_IRQCHIP_PIC_SLAVE:
- spin_lock(&pic->lock);
- memcpy(&pic->pics[1], &chip->chip.pic,
- sizeof(struct kvm_pic_state));
- spin_unlock(&pic->lock);
- break;
- case KVM_IRQCHIP_IOAPIC:
- kvm_set_ioapic(kvm, &chip->chip.ioapic);
- break;
- default:
- r = -EINVAL;
- break;
- }
- kvm_pic_update_irq(pic);
- return r;
-}
-
-static int kvm_vm_ioctl_get_pit(struct kvm *kvm, struct kvm_pit_state *ps)
-{
- struct kvm_kpit_state *kps = &kvm->arch.vpit->pit_state;
-
- BUILD_BUG_ON(sizeof(*ps) != sizeof(kps->channels));
-
- mutex_lock(&kps->lock);
- memcpy(ps, &kps->channels, sizeof(*ps));
- mutex_unlock(&kps->lock);
- return 0;
-}
-
-static int kvm_vm_ioctl_set_pit(struct kvm *kvm, struct kvm_pit_state *ps)
-{
- int i;
- struct kvm_pit *pit = kvm->arch.vpit;
-
- mutex_lock(&pit->pit_state.lock);
- memcpy(&pit->pit_state.channels, ps, sizeof(*ps));
- for (i = 0; i < 3; i++)
- kvm_pit_load_count(pit, i, ps->channels[i].count, 0);
- mutex_unlock(&pit->pit_state.lock);
- return 0;
-}
-
-static int kvm_vm_ioctl_get_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
-{
- mutex_lock(&kvm->arch.vpit->pit_state.lock);
- memcpy(ps->channels, &kvm->arch.vpit->pit_state.channels,
- sizeof(ps->channels));
- ps->flags = kvm->arch.vpit->pit_state.flags;
- mutex_unlock(&kvm->arch.vpit->pit_state.lock);
- memset(&ps->reserved, 0, sizeof(ps->reserved));
- return 0;
-}
-
-static int kvm_vm_ioctl_set_pit2(struct kvm *kvm, struct kvm_pit_state2 *ps)
-{
- int start = 0;
- int i;
- u32 prev_legacy, cur_legacy;
- struct kvm_pit *pit = kvm->arch.vpit;
-
- mutex_lock(&pit->pit_state.lock);
- prev_legacy = pit->pit_state.flags & KVM_PIT_FLAGS_HPET_LEGACY;
- cur_legacy = ps->flags & KVM_PIT_FLAGS_HPET_LEGACY;
- if (!prev_legacy && cur_legacy)
- start = 1;
- memcpy(&pit->pit_state.channels, &ps->channels,
- sizeof(pit->pit_state.channels));
- pit->pit_state.flags = ps->flags;
- for (i = 0; i < 3; i++)
- kvm_pit_load_count(pit, i, pit->pit_state.channels[i].count,
- start && i == 0);
- mutex_unlock(&pit->pit_state.lock);
- return 0;
-}
-
-static int kvm_vm_ioctl_reinject(struct kvm *kvm,
- struct kvm_reinject_control *control)
-{
- struct kvm_pit *pit = kvm->arch.vpit;
-
- /* pit->pit_state.lock was overloaded to prevent userspace from getting
- * an inconsistent state after running multiple KVM_REINJECT_CONTROL
- * ioctls in parallel. Use a separate lock if that ioctl isn't rare.
- */
- mutex_lock(&pit->pit_state.lock);
- kvm_pit_set_reinject(pit, control->pit_reinject);
- mutex_unlock(&pit->pit_state.lock);
-
- return 0;
-}
-
void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
{
@@ -6491,25 +6410,13 @@ void kvm_arch_sync_dirty_log(struct kvm *kvm, struct kvm_memory_slot *memslot)
struct kvm_vcpu *vcpu;
unsigned long i;
- if (!kvm_x86_ops.cpu_dirty_log_size)
+ if (!kvm->arch.cpu_dirty_log_size)
return;
kvm_for_each_vcpu(i, vcpu, kvm)
kvm_vcpu_kick(vcpu);
}
-int kvm_vm_ioctl_irq_line(struct kvm *kvm, struct kvm_irq_level *irq_event,
- bool line_status)
-{
- if (!irqchip_in_kernel(kvm))
- return -ENXIO;
-
- irq_event->status = kvm_set_irq(kvm, KVM_USERSPACE_IRQ_SOURCE_ID,
- irq_event->irq, irq_event->level,
- line_status);
- return 0;
-}
-
int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
struct kvm_enable_cap *cap)
{
@@ -6521,11 +6428,11 @@ int kvm_vm_ioctl_enable_cap(struct kvm *kvm,
switch (cap->cap) {
case KVM_CAP_DISABLE_QUIRKS2:
r = -EINVAL;
- if (cap->args[0] & ~KVM_X86_VALID_QUIRKS)
+ if (cap->args[0] & ~kvm_caps.supported_quirks)
break;
fallthrough;
case KVM_CAP_DISABLE_QUIRKS:
- kvm->arch.disabled_quirks = cap->args[0];
+ kvm->arch.disabled_quirks |= cap->args[0] & kvm_caps.supported_quirks;
r = 0;
break;
case KVM_CAP_SPLIT_IRQCHIP: {
@@ -6574,17 +6481,11 @@ split_irqchip_unlock:
if (!mitigate_smt_rsb && boot_cpu_has_bug(X86_BUG_SMT_RSB) &&
cpu_smt_possible() &&
- (cap->args[0] & ~KVM_X86_DISABLE_EXITS_PAUSE))
+ (cap->args[0] & ~(KVM_X86_DISABLE_EXITS_PAUSE |
+ KVM_X86_DISABLE_EXITS_APERFMPERF)))
pr_warn_once(SMT_RSB_MSG);
- if (cap->args[0] & KVM_X86_DISABLE_EXITS_PAUSE)
- kvm->arch.pause_in_guest = true;
- if (cap->args[0] & KVM_X86_DISABLE_EXITS_MWAIT)
- kvm->arch.mwait_in_guest = true;
- if (cap->args[0] & KVM_X86_DISABLE_EXITS_HLT)
- kvm->arch.hlt_in_guest = true;
- if (cap->args[0] & KVM_X86_DISABLE_EXITS_CSTATE)
- kvm->arch.cstate_in_guest = true;
+ kvm_disable_exits(kvm, cap->args[0]);
r = 0;
disable_exits_unlock:
mutex_unlock(&kvm->lock);
@@ -7021,9 +6922,11 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
struct kvm *kvm = filp->private_data;
void __user *argp = (void __user *)arg;
int r = -ENOTTY;
+
+#ifdef CONFIG_KVM_IOAPIC
/*
* This union makes it completely explicit to gcc-3.x
- * that these two variables' stack usage should be
+ * that these three variables' stack usage should be
* combined, not added together.
*/
union {
@@ -7031,6 +6934,7 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
struct kvm_pit_state2 ps2;
struct kvm_pit_config pit_config;
} u;
+#endif
switch (ioctl) {
case KVM_SET_TSS_ADDR:
@@ -7054,6 +6958,7 @@ set_identity_unlock:
case KVM_SET_NR_MMU_PAGES:
r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg);
break;
+#ifdef CONFIG_KVM_IOAPIC
case KVM_CREATE_IRQCHIP: {
mutex_lock(&kvm->lock);
@@ -7075,7 +6980,7 @@ set_identity_unlock:
goto create_irqchip_unlock;
}
- r = kvm_setup_default_irq_routing(kvm);
+ r = kvm_setup_default_ioapic_and_pic_routing(kvm);
if (r) {
kvm_ioapic_destroy(kvm);
kvm_pic_destroy(kvm);
@@ -7123,7 +7028,7 @@ set_identity_unlock:
}
r = -ENXIO;
- if (!irqchip_kernel(kvm))
+ if (!irqchip_full(kvm))
goto get_irqchip_out;
r = kvm_vm_ioctl_get_irqchip(kvm, chip);
if (r)
@@ -7147,7 +7052,7 @@ set_identity_unlock:
}
r = -ENXIO;
- if (!irqchip_kernel(kvm))
+ if (!irqchip_full(kvm))
goto set_irqchip_out;
r = kvm_vm_ioctl_set_irqchip(kvm, chip);
set_irqchip_out:
@@ -7220,6 +7125,7 @@ set_pit2_out:
r = kvm_vm_ioctl_reinject(kvm, &control);
break;
}
+#endif
case KVM_SET_BOOT_CPU_ID:
r = 0;
mutex_lock(&kvm->lock);
@@ -7290,23 +7196,25 @@ set_pit2_out:
if (user_tsc_khz == 0)
user_tsc_khz = tsc_khz;
- WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz);
- r = 0;
-
+ mutex_lock(&kvm->lock);
+ if (!kvm->created_vcpus) {
+ WRITE_ONCE(kvm->arch.default_tsc_khz, user_tsc_khz);
+ r = 0;
+ }
+ mutex_unlock(&kvm->lock);
goto out;
}
case KVM_GET_TSC_KHZ: {
r = READ_ONCE(kvm->arch.default_tsc_khz);
goto out;
}
- case KVM_MEMORY_ENCRYPT_OP: {
+ case KVM_MEMORY_ENCRYPT_OP:
r = -ENOTTY;
if (!kvm_x86_ops.mem_enc_ioctl)
goto out;
r = kvm_x86_call(mem_enc_ioctl)(kvm, argp);
break;
- }
case KVM_MEMORY_ENCRYPT_REG_REGION: {
struct kvm_enc_region region;
@@ -8000,7 +7908,7 @@ static int emulator_read_write(struct x86_emulate_ctxt *ctxt,
return rc;
if (!vcpu->mmio_nr_fragments)
- return rc;
+ return X86EMUL_CONTINUE;
gpa = vcpu->mmio_fragments[0].gpa;
@@ -8245,8 +8153,7 @@ static int kvm_emulate_wbinvd_noskip(struct kvm_vcpu *vcpu)
int cpu = get_cpu();
cpumask_set_cpu(cpu, vcpu->arch.wbinvd_dirty_mask);
- on_each_cpu_mask(vcpu->arch.wbinvd_dirty_mask,
- wbinvd_ipi, NULL, 1);
+ wbinvd_on_cpus_mask(vcpu->arch.wbinvd_dirty_mask);
put_cpu();
cpumask_clear(vcpu->arch.wbinvd_dirty_mask);
} else
@@ -9338,7 +9245,7 @@ static int complete_fast_pio_out(struct kvm_vcpu *vcpu)
{
vcpu->arch.pio.count = 0;
- if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip)))
+ if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip)))
return 1;
return kvm_skip_emulated_instruction(vcpu);
@@ -9363,7 +9270,7 @@ static int kvm_fast_pio_out(struct kvm_vcpu *vcpu, int size,
complete_fast_pio_out_port_0x7e;
kvm_skip_emulated_instruction(vcpu);
} else {
- vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
+ vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu);
vcpu->arch.complete_userspace_io = complete_fast_pio_out;
}
return 0;
@@ -9376,7 +9283,7 @@ static int complete_fast_pio_in(struct kvm_vcpu *vcpu)
/* We should only ever be called with arch.pio.count equal to 1 */
BUG_ON(vcpu->arch.pio.count != 1);
- if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.pio.linear_rip))) {
+ if (unlikely(!kvm_is_linear_rip(vcpu, vcpu->arch.cui_linear_rip))) {
vcpu->arch.pio.count = 0;
return 1;
}
@@ -9405,7 +9312,7 @@ static int kvm_fast_pio_in(struct kvm_vcpu *vcpu, int size,
return ret;
}
- vcpu->arch.pio.linear_rip = kvm_get_linear_rip(vcpu);
+ vcpu->arch.cui_linear_rip = kvm_get_linear_rip(vcpu);
vcpu->arch.complete_userspace_io = complete_fast_pio_in;
return 0;
@@ -9738,7 +9645,7 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
* with an exception. PAT[0] is set to WB on RESET and also by the
* kernel, i.e. failure indicates a kernel bug or broken firmware.
*/
- if (rdmsrl_safe(MSR_IA32_CR_PAT, &host_pat) ||
+ if (rdmsrq_safe(MSR_IA32_CR_PAT, &host_pat) ||
(host_pat & GENMASK(2, 0)) != 6) {
pr_err("host PAT[0] is not WB\n");
return -EIO;
@@ -9771,21 +9678,26 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
kvm_host.xcr0 = xgetbv(XCR_XFEATURE_ENABLED_MASK);
kvm_caps.supported_xcr0 = kvm_host.xcr0 & KVM_SUPPORTED_XCR0;
}
+ kvm_caps.supported_quirks = KVM_X86_VALID_QUIRKS;
+ kvm_caps.inapplicable_quirks = KVM_X86_CONDITIONAL_QUIRKS;
- rdmsrl_safe(MSR_EFER, &kvm_host.efer);
+ rdmsrq_safe(MSR_EFER, &kvm_host.efer);
if (boot_cpu_has(X86_FEATURE_XSAVES))
- rdmsrl(MSR_IA32_XSS, kvm_host.xss);
+ rdmsrq(MSR_IA32_XSS, kvm_host.xss);
kvm_init_pmu_capability(ops->pmu_ops);
if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES))
- rdmsrl(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities);
+ rdmsrq(MSR_IA32_ARCH_CAPABILITIES, kvm_host.arch_capabilities);
r = ops->hardware_setup();
if (r != 0)
goto out_mmu_exit;
+ enable_device_posted_irqs &= enable_apicv &&
+ irq_remapping_cap(IRQ_POSTING_CAP);
+
kvm_ops_update(ops);
for_each_online_cpu(cpu) {
@@ -9815,6 +9727,10 @@ int kvm_x86_vendor_init(struct kvm_x86_init_ops *ops)
if (IS_ENABLED(CONFIG_KVM_SW_PROTECTED_VM) && tdp_mmu_enabled)
kvm_caps.supported_vm_types |= BIT(KVM_X86_SW_PROTECTED_VM);
+ /* KVM always ignores guest PAT for shadow paging. */
+ if (!tdp_enabled)
+ kvm_caps.supported_quirks &= ~KVM_X86_QUIRK_IGNORE_GUEST_PAT;
+
if (!kvm_cpu_cap_has(X86_FEATURE_XSAVES))
kvm_caps.supported_xss = 0;
@@ -10023,13 +9939,16 @@ static int complete_hypercall_exit(struct kvm_vcpu *vcpu)
return kvm_skip_emulated_instruction(vcpu);
}
-int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
- unsigned long a0, unsigned long a1,
- unsigned long a2, unsigned long a3,
- int op_64_bit, int cpl,
+int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, int cpl,
int (*complete_hypercall)(struct kvm_vcpu *))
{
unsigned long ret;
+ unsigned long nr = kvm_rax_read(vcpu);
+ unsigned long a0 = kvm_rbx_read(vcpu);
+ unsigned long a1 = kvm_rcx_read(vcpu);
+ unsigned long a2 = kvm_rdx_read(vcpu);
+ unsigned long a3 = kvm_rsi_read(vcpu);
+ int op_64_bit = is_64_bit_hypercall(vcpu);
++vcpu->stat.hypercalls;
@@ -10132,9 +10051,7 @@ int kvm_emulate_hypercall(struct kvm_vcpu *vcpu)
if (kvm_hv_hypercall_enabled(vcpu))
return kvm_hv_hypercall(vcpu);
- return __kvm_emulate_hypercall(vcpu, rax, rbx, rcx, rdx, rsi,
- is_64_bit_hypercall(vcpu),
- kvm_x86_call(get_cpl)(vcpu),
+ return __kvm_emulate_hypercall(vcpu, kvm_x86_call(get_cpl)(vcpu),
complete_hypercall_exit);
}
EXPORT_SYMBOL_GPL(kvm_emulate_hypercall);
@@ -10664,13 +10581,16 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
return;
bitmap_zero(vcpu->arch.ioapic_handled_vectors, 256);
+ vcpu->arch.highest_stale_pending_ioapic_eoi = -1;
kvm_x86_call(sync_pir_to_irr)(vcpu);
if (irqchip_split(vcpu->kvm))
kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
+#ifdef CONFIG_KVM_IOAPIC
else if (ioapic_in_kernel(vcpu->kvm))
kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
+#endif
if (is_guest_mode(vcpu))
vcpu->arch.load_eoi_exitmap_pending = true;
@@ -10724,6 +10644,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
dm_request_for_irq_injection(vcpu) &&
kvm_cpu_accept_dm_intr(vcpu);
fastpath_t exit_fastpath;
+ u64 run_flags, debug_ctl;
bool req_immediate_exit = false;
@@ -10871,8 +10792,14 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
kvm_vcpu_update_apicv(vcpu);
if (kvm_check_request(KVM_REQ_APF_READY, vcpu))
kvm_check_async_pf_completion(vcpu);
+
+ /*
+ * Recalc MSR intercepts as userspace may want to intercept
+ * accesses to MSRs that KVM would otherwise pass through to
+ * the guest.
+ */
if (kvm_check_request(KVM_REQ_MSR_FILTER_CHANGED, vcpu))
- kvm_x86_call(msr_filter_changed)(vcpu);
+ kvm_x86_call(recalc_msr_intercepts)(vcpu);
if (kvm_check_request(KVM_REQ_UPDATE_CPU_DIRTY_LOGGING, vcpu))
kvm_x86_call(update_cpu_dirty_logging)(vcpu);
@@ -10968,30 +10895,44 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
goto cancel_injection;
}
- if (req_immediate_exit)
+ run_flags = 0;
+ if (req_immediate_exit) {
+ run_flags |= KVM_RUN_FORCE_IMMEDIATE_EXIT;
kvm_make_request(KVM_REQ_EVENT, vcpu);
+ }
fpregs_assert_state_consistent();
if (test_thread_flag(TIF_NEED_FPU_LOAD))
switch_fpu_return();
if (vcpu->arch.guest_fpu.xfd_err)
- wrmsrl(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
+ wrmsrq(MSR_IA32_XFD_ERR, vcpu->arch.guest_fpu.xfd_err);
- if (unlikely(vcpu->arch.switch_db_regs)) {
- set_debugreg(0, 7);
+ if (unlikely(vcpu->arch.switch_db_regs &&
+ !(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH))) {
+ set_debugreg(DR7_FIXED_1, 7);
set_debugreg(vcpu->arch.eff_db[0], 0);
set_debugreg(vcpu->arch.eff_db[1], 1);
set_debugreg(vcpu->arch.eff_db[2], 2);
set_debugreg(vcpu->arch.eff_db[3], 3);
/* When KVM_DEBUGREG_WONT_EXIT, dr6 is accessible in guest. */
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT))
- kvm_x86_call(set_dr6)(vcpu, vcpu->arch.dr6);
+ run_flags |= KVM_RUN_LOAD_GUEST_DR6;
} else if (unlikely(hw_breakpoint_active())) {
- set_debugreg(0, 7);
+ set_debugreg(DR7_FIXED_1, 7);
}
- vcpu->arch.host_debugctl = get_debugctlmsr();
+ /*
+ * Refresh the host DEBUGCTL snapshot after disabling IRQs, as DEBUGCTL
+ * can be modified in IRQ context, e.g. via SMP function calls. Inform
+ * vendor code if any host-owned bits were changed, e.g. so that the
+ * value loaded into hardware while running the guest can be updated.
+ */
+ debug_ctl = get_debugctlmsr();
+ if ((debug_ctl ^ vcpu->arch.host_debugctl) & kvm_x86_ops.HOST_OWNED_DEBUGCTL &&
+ !vcpu->arch.guest_state_protected)
+ run_flags |= KVM_RUN_LOAD_DEBUGCTL;
+ vcpu->arch.host_debugctl = debug_ctl;
guest_timing_enter_irqoff();
@@ -11005,8 +10946,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
WARN_ON_ONCE((kvm_vcpu_apicv_activated(vcpu) != kvm_vcpu_apicv_active(vcpu)) &&
(kvm_get_apic_mode(vcpu) != LAPIC_MODE_DISABLED));
- exit_fastpath = kvm_x86_call(vcpu_run)(vcpu,
- req_immediate_exit);
+ exit_fastpath = kvm_x86_call(vcpu_run)(vcpu, run_flags);
if (likely(exit_fastpath != EXIT_FASTPATH_REENTER_GUEST))
break;
@@ -11018,6 +10958,8 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
break;
}
+ run_flags = 0;
+
/* Note, VM-Exits that go down the "slow" path are accounted below. */
++vcpu->stat.exits;
}
@@ -11030,6 +10972,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
*/
if (unlikely(vcpu->arch.switch_db_regs & KVM_DEBUGREG_WONT_EXIT)) {
WARN_ON(vcpu->guest_debug & KVM_GUESTDBG_USE_HW_BP);
+ WARN_ON(vcpu->arch.switch_db_regs & KVM_DEBUGREG_AUTO_SWITCH);
kvm_x86_call(sync_dirty_debug_regs)(vcpu);
kvm_update_dr0123(vcpu);
kvm_update_dr7(vcpu);
@@ -11062,7 +11005,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
kvm_x86_call(handle_exit_irqoff)(vcpu);
if (vcpu->arch.guest_fpu.xfd_err)
- wrmsrl(MSR_IA32_XFD_ERR, 0);
+ wrmsrq(MSR_IA32_XFD_ERR, 0);
/*
* Consume any pending interrupts, including the possible source of
@@ -11134,7 +11077,7 @@ static bool kvm_vcpu_running(struct kvm_vcpu *vcpu)
!vcpu->arch.apf.halted);
}
-static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
+bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
{
if (!list_empty_careful(&vcpu->async_pf.done))
return true;
@@ -11143,9 +11086,6 @@ static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
kvm_apic_init_sipi_allowed(vcpu))
return true;
- if (vcpu->arch.pv.pv_unhalted)
- return true;
-
if (kvm_is_exception_pending(vcpu))
return true;
@@ -11183,10 +11123,12 @@ static bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
return false;
}
+EXPORT_SYMBOL_GPL(kvm_vcpu_has_events);
int kvm_arch_vcpu_runnable(struct kvm_vcpu *vcpu)
{
- return kvm_vcpu_running(vcpu) || kvm_vcpu_has_events(vcpu);
+ return kvm_vcpu_running(vcpu) || vcpu->arch.pv.pv_unhalted ||
+ kvm_vcpu_has_events(vcpu);
}
/* Called within kvm->srcu read side. */
@@ -11320,7 +11262,7 @@ static int __kvm_emulate_halt(struct kvm_vcpu *vcpu, int state, int reason)
*/
++vcpu->stat.halt_exits;
if (lapic_in_kernel(vcpu)) {
- if (kvm_vcpu_has_events(vcpu))
+ if (kvm_vcpu_has_events(vcpu) || vcpu->arch.pv.pv_unhalted)
state = KVM_MP_STATE_RUNNABLE;
kvm_set_mp_state(vcpu, state);
return 1;
@@ -11491,6 +11433,28 @@ static void kvm_put_guest_fpu(struct kvm_vcpu *vcpu)
trace_kvm_fpu(0);
}
+static int kvm_x86_vcpu_pre_run(struct kvm_vcpu *vcpu)
+{
+ /*
+ * SIPI_RECEIVED is obsolete; KVM leaves the vCPU in Wait-For-SIPI and
+ * tracks the pending SIPI separately. SIPI_RECEIVED is still accepted
+ * by KVM_SET_VCPU_EVENTS for backwards compatibility, but should be
+ * converted to INIT_RECEIVED.
+ */
+ if (WARN_ON_ONCE(vcpu->arch.mp_state == KVM_MP_STATE_SIPI_RECEIVED))
+ return -EINVAL;
+
+ /*
+ * Disallow running the vCPU if userspace forced it into an impossible
+ * MP_STATE, e.g. if the vCPU is in WFS but SIPI is blocked.
+ */
+ if (vcpu->arch.mp_state == KVM_MP_STATE_INIT_RECEIVED &&
+ !kvm_apic_init_sipi_allowed(vcpu))
+ return -EINVAL;
+
+ return kvm_x86_call(vcpu_pre_run)(vcpu);
+}
+
int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
{
struct kvm_queued_exception *ex = &vcpu->arch.exception;
@@ -11593,7 +11557,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
goto out;
}
- r = kvm_x86_call(vcpu_pre_run)(vcpu);
+ r = kvm_x86_vcpu_pre_run(vcpu);
if (r <= 0)
goto out;
@@ -11837,21 +11801,16 @@ int kvm_arch_vcpu_ioctl_set_mpstate(struct kvm_vcpu *vcpu,
}
/*
- * Pending INITs are reported using KVM_SET_VCPU_EVENTS, disallow
- * forcing the guest into INIT/SIPI if those events are supposed to be
- * blocked. KVM prioritizes SMI over INIT, so reject INIT/SIPI state
- * if an SMI is pending as well.
+ * SIPI_RECEIVED is obsolete and no longer used internally; KVM instead
+ * leaves the vCPU in INIT_RECIEVED (Wait-For-SIPI) and pends the SIPI.
+ * Translate SIPI_RECEIVED as appropriate for backwards compatibility.
*/
- if ((!kvm_apic_init_sipi_allowed(vcpu) || vcpu->arch.smi_pending) &&
- (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED ||
- mp_state->mp_state == KVM_MP_STATE_INIT_RECEIVED))
- goto out;
-
if (mp_state->mp_state == KVM_MP_STATE_SIPI_RECEIVED) {
- kvm_set_mp_state(vcpu, KVM_MP_STATE_INIT_RECEIVED);
+ mp_state->mp_state = KVM_MP_STATE_INIT_RECEIVED;
set_bit(KVM_APIC_SIPI, &vcpu->arch.apic->pending_events);
- } else
- kvm_set_mp_state(vcpu, mp_state->mp_state);
+ }
+
+ kvm_set_mp_state(vcpu, mp_state->mp_state);
kvm_make_request(KVM_REQ_EVENT, vcpu);
ret = 0;
@@ -12388,13 +12347,16 @@ void kvm_arch_vcpu_postcreate(struct kvm_vcpu *vcpu)
void kvm_arch_vcpu_destroy(struct kvm_vcpu *vcpu)
{
- int idx;
+ int idx, cpu;
kvm_clear_async_pf_completion_queue(vcpu);
kvm_mmu_unload(vcpu);
kvmclock_reset(vcpu);
+ for_each_possible_cpu(cpu)
+ cmpxchg(per_cpu_ptr(&last_vcpu, cpu), vcpu, NULL);
+
kvm_x86_call(vcpu_free)(vcpu);
kmem_cache_free(x86_emulator_cache, vcpu->arch.emulate_ctxt);
@@ -12694,6 +12656,7 @@ bool kvm_vcpu_is_reset_bsp(struct kvm_vcpu *vcpu)
{
return vcpu->kvm->arch.bsp_vcpu_id == vcpu->vcpu_id;
}
+EXPORT_SYMBOL_GPL(kvm_vcpu_is_reset_bsp);
bool kvm_vcpu_is_bsp(struct kvm_vcpu *vcpu)
{
@@ -12723,26 +12686,22 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
/* Decided by the vendor code for other VM types. */
kvm->arch.pre_fault_allowed =
type == KVM_X86_DEFAULT_VM || type == KVM_X86_SW_PROTECTED_VM;
+ kvm->arch.disabled_quirks = kvm_caps.inapplicable_quirks & kvm_caps.supported_quirks;
ret = kvm_page_track_init(kvm);
if (ret)
goto out;
- kvm_mmu_init_vm(kvm);
+ ret = kvm_mmu_init_vm(kvm);
+ if (ret)
+ goto out_cleanup_page_track;
ret = kvm_x86_call(vm_init)(kvm);
if (ret)
goto out_uninit_mmu;
- INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
atomic_set(&kvm->arch.noncoherent_dma_count, 0);
- /* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
- set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
- /* Reserve bit 1 of irq_sources_bitmap for irqfd-resampler */
- set_bit(KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
- &kvm->arch.irq_sources_bitmap);
-
raw_spin_lock_init(&kvm->arch.tsc_write_lock);
mutex_init(&kvm->arch.apic_map_lock);
seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock);
@@ -12781,6 +12740,7 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
out_uninit_mmu:
kvm_mmu_uninit_vm(kvm);
+out_cleanup_page_track:
kvm_page_track_cleanup(kvm);
out:
return ret;
@@ -12873,9 +12833,12 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm)
cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
+#ifdef CONFIG_KVM_IOAPIC
kvm_free_pit(kvm);
+#endif
kvm_mmu_pre_destroy_vm(kvm);
+ static_call_cond(kvm_x86_vm_pre_destroy)(kvm);
}
void kvm_arch_destroy_vm(struct kvm *kvm)
@@ -12896,8 +12859,10 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
}
kvm_destroy_vcpus(kvm);
kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
+#ifdef CONFIG_KVM_IOAPIC
kvm_pic_destroy(kvm);
kvm_ioapic_destroy(kvm);
+#endif
kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
kvm_mmu_uninit_vm(kvm);
@@ -13073,7 +13038,7 @@ static void kvm_mmu_update_cpu_dirty_logging(struct kvm *kvm, bool enable)
{
int nr_slots;
- if (!kvm_x86_ops.cpu_dirty_log_size)
+ if (!kvm->arch.cpu_dirty_log_size)
return;
nr_slots = atomic_read(&kvm->nr_memslots_dirty_logging);
@@ -13145,7 +13110,7 @@ static void kvm_mmu_slot_apply_flags(struct kvm *kvm,
if (READ_ONCE(eager_page_split))
kvm_mmu_slot_try_split_huge_pages(kvm, new, PG_LEVEL_4K);
- if (kvm_x86_ops.cpu_dirty_log_size) {
+ if (kvm->arch.cpu_dirty_log_size) {
kvm_mmu_slot_leaf_clear_dirty(kvm, new);
kvm_mmu_slot_remove_write_access(kvm, new, PG_LEVEL_2M);
} else {
@@ -13507,25 +13472,6 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu)
return kvm_lapic_enabled(vcpu) && apf_pageready_slot_free(vcpu);
}
-void kvm_arch_start_assignment(struct kvm *kvm)
-{
- if (atomic_inc_return(&kvm->arch.assigned_device_count) == 1)
- kvm_x86_call(pi_start_assignment)(kvm);
-}
-EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);
-
-void kvm_arch_end_assignment(struct kvm *kvm)
-{
- atomic_dec(&kvm->arch.assigned_device_count);
-}
-EXPORT_SYMBOL_GPL(kvm_arch_end_assignment);
-
-bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm)
-{
- return raw_atomic_read(&kvm->arch.assigned_device_count);
-}
-EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device);
-
static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm)
{
/*
@@ -13534,8 +13480,10 @@ static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm)
* due to toggling the "ignore PAT" bit. Zap all SPTEs when the first
* (or last) non-coherent device is (un)registered to so that new SPTEs
* with the correct "ignore guest PAT" setting are created.
+ *
+ * If KVM always honors guest PAT, however, there is nothing to do.
*/
- if (kvm_mmu_may_ignore_guest_pat())
+ if (kvm_check_has_quirk(kvm, KVM_X86_QUIRK_IGNORE_GUEST_PAT))
kvm_zap_gfn_range(kvm, gpa_to_gfn(0), gpa_to_gfn(~0ULL));
}
@@ -13559,77 +13507,6 @@ bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
}
EXPORT_SYMBOL_GPL(kvm_arch_has_noncoherent_dma);
-int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
- struct irq_bypass_producer *prod)
-{
- struct kvm_kernel_irqfd *irqfd =
- container_of(cons, struct kvm_kernel_irqfd, consumer);
- struct kvm *kvm = irqfd->kvm;
- int ret;
-
- kvm_arch_start_assignment(irqfd->kvm);
-
- spin_lock_irq(&kvm->irqfds.lock);
- irqfd->producer = prod;
-
- ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
- prod->irq, irqfd->gsi, 1);
- if (ret)
- kvm_arch_end_assignment(irqfd->kvm);
-
- spin_unlock_irq(&kvm->irqfds.lock);
-
-
- return ret;
-}
-
-void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
- struct irq_bypass_producer *prod)
-{
- int ret;
- struct kvm_kernel_irqfd *irqfd =
- container_of(cons, struct kvm_kernel_irqfd, consumer);
- struct kvm *kvm = irqfd->kvm;
-
- WARN_ON(irqfd->producer != prod);
-
- /*
- * When producer of consumer is unregistered, we change back to
- * remapped mode, so we can re-use the current implementation
- * when the irq is masked/disabled or the consumer side (KVM
- * int this case doesn't want to receive the interrupts.
- */
- spin_lock_irq(&kvm->irqfds.lock);
- irqfd->producer = NULL;
-
- ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
- prod->irq, irqfd->gsi, 0);
- if (ret)
- printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
- " fails: %d\n", irqfd->consumer.token, ret);
-
- spin_unlock_irq(&kvm->irqfds.lock);
-
-
- kvm_arch_end_assignment(irqfd->kvm);
-}
-
-int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
- uint32_t guest_irq, bool set)
-{
- return kvm_x86_call(pi_update_irte)(kvm, host_irq, guest_irq, set);
-}
-
-bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
- struct kvm_kernel_irq_routing_entry *new)
-{
- if (old->type != KVM_IRQ_ROUTING_MSI ||
- new->type != KVM_IRQ_ROUTING_MSI)
- return true;
-
- return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
-}
-
bool kvm_vector_hashing_enabled(void)
{
return vector_hashing;
@@ -13668,12 +13545,12 @@ int kvm_spec_ctrl_test_value(u64 value)
local_irq_save(flags);
- if (rdmsrl_safe(MSR_IA32_SPEC_CTRL, &saved_value))
+ if (rdmsrq_safe(MSR_IA32_SPEC_CTRL, &saved_value))
ret = 1;
- else if (wrmsrl_safe(MSR_IA32_SPEC_CTRL, value))
+ else if (wrmsrq_safe(MSR_IA32_SPEC_CTRL, value))
ret = 1;
else
- wrmsrl(MSR_IA32_SPEC_CTRL, saved_value);
+ wrmsrq(MSR_IA32_SPEC_CTRL, saved_value);
local_irq_restore(flags);
@@ -14012,6 +13889,7 @@ EXPORT_SYMBOL_GPL(kvm_sev_es_string_io);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_entry);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_exit);
+EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_mmio);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_fast_mmio);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_inj_virq);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_page_fault);
@@ -14028,7 +13906,6 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_nested_intercepts);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_write_tsc_offset);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_ple_window_update);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pml_full);
-EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_pi_irte_update);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_unaccelerated_access);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_incomplete_ipi);
EXPORT_TRACEPOINT_SYMBOL_GPL(kvm_avic_ga_log);
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index 9dc32a409076..bcfd9b719ada 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -10,6 +10,8 @@
#include "kvm_emulate.h"
#include "cpuid.h"
+#define KVM_MAX_MCE_BANKS 32
+
struct kvm_caps {
/* control of guest tsc rate supported? */
bool has_tsc_control;
@@ -32,6 +34,9 @@ struct kvm_caps {
u64 supported_xcr0;
u64 supported_xss;
u64 supported_perf_cap;
+
+ u64 supported_quirks;
+ u64 inapplicable_quirks;
};
struct kvm_host_values {
@@ -50,6 +55,28 @@ struct kvm_host_values {
void kvm_spurious_fault(void);
+#define SIZE_OF_MEMSLOTS_HASHTABLE \
+ (sizeof(((struct kvm_memslots *)0)->id_hash) * 2 * KVM_MAX_NR_ADDRESS_SPACES)
+
+/* Sanity check the size of the memslot hash tables. */
+static_assert(SIZE_OF_MEMSLOTS_HASHTABLE ==
+ (1024 * (1 + IS_ENABLED(CONFIG_X86_64)) * (1 + IS_ENABLED(CONFIG_KVM_SMM))));
+
+/*
+ * Assert that "struct kvm_{svm,vmx,tdx}" is an order-0 or order-1 allocation.
+ * Spilling over to an order-2 allocation isn't fundamentally problematic, but
+ * isn't expected to happen in the foreseeable future (O(years)). Assert that
+ * the size is an order-0 allocation when ignoring the memslot hash tables, to
+ * help detect and debug unexpected size increases.
+ */
+#define KVM_SANITY_CHECK_VM_STRUCT_SIZE(x) \
+do { \
+ BUILD_BUG_ON(get_order(sizeof(struct x) - SIZE_OF_MEMSLOTS_HASHTABLE) && \
+ !IS_ENABLED(CONFIG_DEBUG_KERNEL) && !IS_ENABLED(CONFIG_KASAN)); \
+ BUILD_BUG_ON(get_order(sizeof(struct x)) > 1 && \
+ !IS_ENABLED(CONFIG_DEBUG_KERNEL) && !IS_ENABLED(CONFIG_KASAN)); \
+} while (0)
+
#define KVM_NESTED_VMENTER_CONSISTENCY_CHECK(consistency_check) \
({ \
bool failed = (consistency_check); \
@@ -116,6 +143,24 @@ static inline void kvm_leave_nested(struct kvm_vcpu *vcpu)
kvm_x86_ops.nested_ops->leave_nested(vcpu);
}
+/*
+ * If IBRS is advertised to the vCPU, KVM must flush the indirect branch
+ * predictors when transitioning from L2 to L1, as L1 expects hardware (KVM in
+ * this case) to provide separate predictor modes. Bare metal isolates the host
+ * from the guest, but doesn't isolate different guests from one another (in
+ * this case L1 and L2). The exception is if bare metal supports same mode IBRS,
+ * which offers protection within the same mode, and hence protects L1 from L2.
+ */
+static inline void kvm_nested_vmexit_handle_ibrs(struct kvm_vcpu *vcpu)
+{
+ if (cpu_feature_enabled(X86_FEATURE_AMD_IBRS_SAME_MODE))
+ return;
+
+ if (guest_cpu_cap_has(vcpu, X86_FEATURE_SPEC_CTRL) ||
+ guest_cpu_cap_has(vcpu, X86_FEATURE_AMD_IBRS))
+ indirect_branch_prediction_barrier();
+}
+
static inline bool kvm_vcpu_has_run(struct kvm_vcpu *vcpu)
{
return vcpu->arch.last_vmentry_cpu != -1;
@@ -476,24 +521,34 @@ static inline u64 nsec_to_cycles(struct kvm_vcpu *vcpu, u64 nsec)
__rem; \
})
+static inline void kvm_disable_exits(struct kvm *kvm, u64 mask)
+{
+ kvm->arch.disabled_exits |= mask;
+}
+
static inline bool kvm_mwait_in_guest(struct kvm *kvm)
{
- return kvm->arch.mwait_in_guest;
+ return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_MWAIT;
}
static inline bool kvm_hlt_in_guest(struct kvm *kvm)
{
- return kvm->arch.hlt_in_guest;
+ return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_HLT;
}
static inline bool kvm_pause_in_guest(struct kvm *kvm)
{
- return kvm->arch.pause_in_guest;
+ return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_PAUSE;
}
static inline bool kvm_cstate_in_guest(struct kvm *kvm)
{
- return kvm->arch.cstate_in_guest;
+ return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_CSTATE;
+}
+
+static inline bool kvm_aperfmperf_in_guest(struct kvm *kvm)
+{
+ return kvm->arch.disabled_exits & KVM_X86_DISABLE_EXITS_APERFMPERF;
}
static inline bool kvm_notify_vmexit_enabled(struct kvm *kvm)
@@ -629,25 +684,17 @@ static inline bool user_exit_on_hypercall(struct kvm *kvm, unsigned long hc_nr)
return kvm->arch.hypercall_exit_enabled & BIT(hc_nr);
}
-int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, unsigned long nr,
- unsigned long a0, unsigned long a1,
- unsigned long a2, unsigned long a3,
- int op_64_bit, int cpl,
+int ____kvm_emulate_hypercall(struct kvm_vcpu *vcpu, int cpl,
int (*complete_hypercall)(struct kvm_vcpu *));
-#define __kvm_emulate_hypercall(_vcpu, nr, a0, a1, a2, a3, op_64_bit, cpl, complete_hypercall) \
-({ \
- int __ret; \
- \
- __ret = ____kvm_emulate_hypercall(_vcpu, \
- kvm_##nr##_read(_vcpu), kvm_##a0##_read(_vcpu), \
- kvm_##a1##_read(_vcpu), kvm_##a2##_read(_vcpu), \
- kvm_##a3##_read(_vcpu), op_64_bit, cpl, \
- complete_hypercall); \
- \
- if (__ret > 0) \
- __ret = complete_hypercall(_vcpu); \
- __ret; \
+#define __kvm_emulate_hypercall(_vcpu, cpl, complete_hypercall) \
+({ \
+ int __ret; \
+ __ret = ____kvm_emulate_hypercall(_vcpu, cpl, complete_hypercall); \
+ \
+ if (__ret > 0) \
+ __ret = complete_hypercall(_vcpu); \
+ __ret; \
})
int kvm_emulate_hypercall(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/xen.c b/arch/x86/kvm/xen.c
index 38b33cdd4232..d6b2a665b499 100644
--- a/arch/x86/kvm/xen.c
+++ b/arch/x86/kvm/xen.c
@@ -1526,7 +1526,7 @@ static bool kvm_xen_schedop_poll(struct kvm_vcpu *vcpu, bool longmode,
if (kvm_read_guest_virt(vcpu, (gva_t)sched_poll.ports, ports,
sched_poll.nr_ports * sizeof(*ports), &e)) {
*r = -EFAULT;
- return true;
+ goto out;
}
for (i = 0; i < sched_poll.nr_ports; i++) {
@@ -1571,7 +1571,8 @@ out:
static void cancel_evtchn_poll(struct timer_list *t)
{
- struct kvm_vcpu *vcpu = from_timer(vcpu, t, arch.xen.poll_timer);
+ struct kvm_vcpu *vcpu = timer_container_of(vcpu, t,
+ arch.xen.poll_timer);
kvm_make_request(KVM_REQ_UNBLOCK, vcpu);
kvm_vcpu_kick(vcpu);
@@ -1970,8 +1971,19 @@ int kvm_xen_setup_evtchn(struct kvm *kvm,
{
struct kvm_vcpu *vcpu;
- if (ue->u.xen_evtchn.port >= max_evtchn_port(kvm))
- return -EINVAL;
+ /*
+ * Don't check for the port being within range of max_evtchn_port().
+ * Userspace can configure what ever targets it likes; events just won't
+ * be delivered if/while the target is invalid, just like userspace can
+ * configure MSIs which target non-existent APICs.
+ *
+ * This allow on Live Migration and Live Update, the IRQ routing table
+ * can be restored *independently* of other things like creating vCPUs,
+ * without imposing an ordering dependency on userspace. In this
+ * particular case, the problematic ordering would be with setting the
+ * Xen 'long mode' flag, which changes max_evtchn_port() to allow 4096
+ * instead of 1024 event channels.
+ */
/* We only support 2 level event channels for now */
if (ue->u.xen_evtchn.priority != KVM_IRQ_ROUTING_XEN_EVTCHN_PRIO_2LEVEL)
diff --git a/arch/x86/lib/.gitignore b/arch/x86/lib/.gitignore
index 8ae0f93ecbfd..ec2131c9fd20 100644
--- a/arch/x86/lib/.gitignore
+++ b/arch/x86/lib/.gitignore
@@ -1,2 +1,6 @@
# SPDX-License-Identifier: GPL-2.0-only
+
+# This now-removed directory used to contain generated files.
+/crypto/
+
inat-tables.c
diff --git a/arch/x86/lib/Makefile b/arch/x86/lib/Makefile
index 1c50352eb49f..2dba7f83ef97 100644
--- a/arch/x86/lib/Makefile
+++ b/arch/x86/lib/Makefile
@@ -38,16 +38,6 @@ lib-$(CONFIG_RANDOMIZE_BASE) += kaslr.o
lib-$(CONFIG_FUNCTION_ERROR_INJECTION) += error-inject.o
lib-$(CONFIG_MITIGATION_RETPOLINE) += retpoline.o
-obj-$(CONFIG_CRC32_ARCH) += crc32-x86.o
-crc32-x86-y := crc32-glue.o crc32-pclmul.o
-crc32-x86-$(CONFIG_64BIT) += crc32c-3way.o
-
-obj-$(CONFIG_CRC64_ARCH) += crc64-x86.o
-crc64-x86-y := crc64-glue.o crc64-pclmul.o
-
-obj-$(CONFIG_CRC_T10DIF_ARCH) += crc-t10dif-x86.o
-crc-t10dif-x86-y := crc-t10dif-glue.o crc16-msb-pclmul.o
-
obj-y += msr.o msr-reg.o msr-reg-export.o hweight.o
obj-y += iomem.o
diff --git a/arch/x86/lib/cache-smp.c b/arch/x86/lib/cache-smp.c
index 7af743bd3b13..c5c60d07308c 100644
--- a/arch/x86/lib/cache-smp.c
+++ b/arch/x86/lib/cache-smp.c
@@ -14,9 +14,31 @@ void wbinvd_on_cpu(int cpu)
}
EXPORT_SYMBOL(wbinvd_on_cpu);
-int wbinvd_on_all_cpus(void)
+void wbinvd_on_all_cpus(void)
{
on_each_cpu(__wbinvd, NULL, 1);
- return 0;
}
EXPORT_SYMBOL(wbinvd_on_all_cpus);
+
+void wbinvd_on_cpus_mask(struct cpumask *cpus)
+{
+ on_each_cpu_mask(cpus, __wbinvd, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(wbinvd_on_cpus_mask);
+
+static void __wbnoinvd(void *dummy)
+{
+ wbnoinvd();
+}
+
+void wbnoinvd_on_all_cpus(void)
+{
+ on_each_cpu(__wbnoinvd, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(wbnoinvd_on_all_cpus);
+
+void wbnoinvd_on_cpus_mask(struct cpumask *cpus)
+{
+ on_each_cpu_mask(cpus, __wbnoinvd, NULL, 1);
+}
+EXPORT_SYMBOL_GPL(wbnoinvd_on_cpus_mask);
diff --git a/arch/x86/lib/crc-pclmul-consts.h b/arch/x86/lib/crc-pclmul-consts.h
deleted file mode 100644
index fcc63c064333..000000000000
--- a/arch/x86/lib/crc-pclmul-consts.h
+++ /dev/null
@@ -1,195 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * CRC constants generated by:
- *
- * ./scripts/gen-crc-consts.py x86_pclmul crc16_msb_0x8bb7,crc32_lsb_0xedb88320,crc64_msb_0x42f0e1eba9ea3693,crc64_lsb_0x9a6c9329ac4bc9b5
- *
- * Do not edit manually.
- */
-
-/*
- * CRC folding constants generated for most-significant-bit-first CRC-16 using
- * G(x) = x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x^1 + x^0
- */
-static const struct {
- u8 bswap_mask[16];
- u64 fold_across_2048_bits_consts[2];
- u64 fold_across_1024_bits_consts[2];
- u64 fold_across_512_bits_consts[2];
- u64 fold_across_256_bits_consts[2];
- u64 fold_across_128_bits_consts[2];
- u8 shuf_table[48];
- u64 barrett_reduction_consts[2];
-} crc16_msb_0x8bb7_consts ____cacheline_aligned __maybe_unused = {
- .bswap_mask = {15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0},
- .fold_across_2048_bits_consts = {
- 0xdccf000000000000, /* LO64_TERMS: (x^2000 mod G) * x^48 */
- 0x4b0b000000000000, /* HI64_TERMS: (x^2064 mod G) * x^48 */
- },
- .fold_across_1024_bits_consts = {
- 0x9d9d000000000000, /* LO64_TERMS: (x^976 mod G) * x^48 */
- 0x7cf5000000000000, /* HI64_TERMS: (x^1040 mod G) * x^48 */
- },
- .fold_across_512_bits_consts = {
- 0x044c000000000000, /* LO64_TERMS: (x^464 mod G) * x^48 */
- 0xe658000000000000, /* HI64_TERMS: (x^528 mod G) * x^48 */
- },
- .fold_across_256_bits_consts = {
- 0x6ee3000000000000, /* LO64_TERMS: (x^208 mod G) * x^48 */
- 0xe7b5000000000000, /* HI64_TERMS: (x^272 mod G) * x^48 */
- },
- .fold_across_128_bits_consts = {
- 0x2d56000000000000, /* LO64_TERMS: (x^80 mod G) * x^48 */
- 0x06df000000000000, /* HI64_TERMS: (x^144 mod G) * x^48 */
- },
- .shuf_table = {
- -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
- 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
- -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
- },
- .barrett_reduction_consts = {
- 0x8bb7000000000000, /* LO64_TERMS: (G - x^16) * x^48 */
- 0xf65a57f81d33a48a, /* HI64_TERMS: (floor(x^79 / G) * x) - x^64 */
- },
-};
-
-/*
- * CRC folding constants generated for least-significant-bit-first CRC-32 using
- * G(x) = x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 + x^7 +
- * x^5 + x^4 + x^2 + x^1 + x^0
- */
-static const struct {
- u64 fold_across_2048_bits_consts[2];
- u64 fold_across_1024_bits_consts[2];
- u64 fold_across_512_bits_consts[2];
- u64 fold_across_256_bits_consts[2];
- u64 fold_across_128_bits_consts[2];
- u8 shuf_table[48];
- u64 barrett_reduction_consts[2];
-} crc32_lsb_0xedb88320_consts ____cacheline_aligned __maybe_unused = {
- .fold_across_2048_bits_consts = {
- 0x00000000ce3371cb, /* HI64_TERMS: (x^2079 mod G) * x^32 */
- 0x00000000e95c1271, /* LO64_TERMS: (x^2015 mod G) * x^32 */
- },
- .fold_across_1024_bits_consts = {
- 0x0000000033fff533, /* HI64_TERMS: (x^1055 mod G) * x^32 */
- 0x00000000910eeec1, /* LO64_TERMS: (x^991 mod G) * x^32 */
- },
- .fold_across_512_bits_consts = {
- 0x000000008f352d95, /* HI64_TERMS: (x^543 mod G) * x^32 */
- 0x000000001d9513d7, /* LO64_TERMS: (x^479 mod G) * x^32 */
- },
- .fold_across_256_bits_consts = {
- 0x00000000f1da05aa, /* HI64_TERMS: (x^287 mod G) * x^32 */
- 0x0000000081256527, /* LO64_TERMS: (x^223 mod G) * x^32 */
- },
- .fold_across_128_bits_consts = {
- 0x00000000ae689191, /* HI64_TERMS: (x^159 mod G) * x^32 */
- 0x00000000ccaa009e, /* LO64_TERMS: (x^95 mod G) * x^32 */
- },
- .shuf_table = {
- -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
- 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
- -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
- },
- .barrett_reduction_consts = {
- 0xb4e5b025f7011641, /* HI64_TERMS: floor(x^95 / G) */
- 0x00000001db710640, /* LO64_TERMS: (G - x^32) * x^31 */
- },
-};
-
-/*
- * CRC folding constants generated for most-significant-bit-first CRC-64 using
- * G(x) = x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 +
- * x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 +
- * x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 +
- * x^7 + x^4 + x^1 + x^0
- */
-static const struct {
- u8 bswap_mask[16];
- u64 fold_across_2048_bits_consts[2];
- u64 fold_across_1024_bits_consts[2];
- u64 fold_across_512_bits_consts[2];
- u64 fold_across_256_bits_consts[2];
- u64 fold_across_128_bits_consts[2];
- u8 shuf_table[48];
- u64 barrett_reduction_consts[2];
-} crc64_msb_0x42f0e1eba9ea3693_consts ____cacheline_aligned __maybe_unused = {
- .bswap_mask = {15, 14, 13, 12, 11, 10, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0},
- .fold_across_2048_bits_consts = {
- 0x7f52691a60ddc70d, /* LO64_TERMS: (x^2048 mod G) * x^0 */
- 0x7036b0389f6a0c82, /* HI64_TERMS: (x^2112 mod G) * x^0 */
- },
- .fold_across_1024_bits_consts = {
- 0x05cf79dea9ac37d6, /* LO64_TERMS: (x^1024 mod G) * x^0 */
- 0x001067e571d7d5c2, /* HI64_TERMS: (x^1088 mod G) * x^0 */
- },
- .fold_across_512_bits_consts = {
- 0x5f6843ca540df020, /* LO64_TERMS: (x^512 mod G) * x^0 */
- 0xddf4b6981205b83f, /* HI64_TERMS: (x^576 mod G) * x^0 */
- },
- .fold_across_256_bits_consts = {
- 0x571bee0a227ef92b, /* LO64_TERMS: (x^256 mod G) * x^0 */
- 0x44bef2a201b5200c, /* HI64_TERMS: (x^320 mod G) * x^0 */
- },
- .fold_across_128_bits_consts = {
- 0x05f5c3c7eb52fab6, /* LO64_TERMS: (x^128 mod G) * x^0 */
- 0x4eb938a7d257740e, /* HI64_TERMS: (x^192 mod G) * x^0 */
- },
- .shuf_table = {
- -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
- 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
- -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
- },
- .barrett_reduction_consts = {
- 0x42f0e1eba9ea3693, /* LO64_TERMS: (G - x^64) * x^0 */
- 0x578d29d06cc4f872, /* HI64_TERMS: (floor(x^127 / G) * x) - x^64 */
- },
-};
-
-/*
- * CRC folding constants generated for least-significant-bit-first CRC-64 using
- * G(x) = x^64 + x^63 + x^61 + x^59 + x^58 + x^56 + x^55 + x^52 + x^49 + x^48 +
- * x^47 + x^46 + x^44 + x^41 + x^37 + x^36 + x^34 + x^32 + x^31 + x^28 +
- * x^26 + x^23 + x^22 + x^19 + x^16 + x^13 + x^12 + x^10 + x^9 + x^6 +
- * x^4 + x^3 + x^0
- */
-static const struct {
- u64 fold_across_2048_bits_consts[2];
- u64 fold_across_1024_bits_consts[2];
- u64 fold_across_512_bits_consts[2];
- u64 fold_across_256_bits_consts[2];
- u64 fold_across_128_bits_consts[2];
- u8 shuf_table[48];
- u64 barrett_reduction_consts[2];
-} crc64_lsb_0x9a6c9329ac4bc9b5_consts ____cacheline_aligned __maybe_unused = {
- .fold_across_2048_bits_consts = {
- 0x37ccd3e14069cabc, /* HI64_TERMS: (x^2111 mod G) * x^0 */
- 0xa043808c0f782663, /* LO64_TERMS: (x^2047 mod G) * x^0 */
- },
- .fold_across_1024_bits_consts = {
- 0xa1ca681e733f9c40, /* HI64_TERMS: (x^1087 mod G) * x^0 */
- 0x5f852fb61e8d92dc, /* LO64_TERMS: (x^1023 mod G) * x^0 */
- },
- .fold_across_512_bits_consts = {
- 0x0c32cdb31e18a84a, /* HI64_TERMS: (x^575 mod G) * x^0 */
- 0x62242240ace5045a, /* LO64_TERMS: (x^511 mod G) * x^0 */
- },
- .fold_across_256_bits_consts = {
- 0xb0bc2e589204f500, /* HI64_TERMS: (x^319 mod G) * x^0 */
- 0xe1e0bb9d45d7a44c, /* LO64_TERMS: (x^255 mod G) * x^0 */
- },
- .fold_across_128_bits_consts = {
- 0xeadc41fd2ba3d420, /* HI64_TERMS: (x^191 mod G) * x^0 */
- 0x21e9761e252621ac, /* LO64_TERMS: (x^127 mod G) * x^0 */
- },
- .shuf_table = {
- -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
- 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15,
- -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1, -1,
- },
- .barrett_reduction_consts = {
- 0x27ecfa329aef9f77, /* HI64_TERMS: floor(x^127 / G) */
- 0x34d926535897936a, /* LO64_TERMS: (G - x^64 - x^0) / x */
- },
-};
diff --git a/arch/x86/lib/crc-pclmul-template.S b/arch/x86/lib/crc-pclmul-template.S
deleted file mode 100644
index ae0b6144c503..000000000000
--- a/arch/x86/lib/crc-pclmul-template.S
+++ /dev/null
@@ -1,582 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-//
-// Template to generate [V]PCLMULQDQ-based CRC functions for x86
-//
-// Copyright 2025 Google LLC
-//
-// Author: Eric Biggers <ebiggers@google.com>
-
-#include <linux/linkage.h>
-#include <linux/objtool.h>
-
-// Offsets within the generated constants table
-.set OFFSETOF_BSWAP_MASK, -5*16 // msb-first CRCs only
-.set OFFSETOF_FOLD_ACROSS_2048_BITS_CONSTS, -4*16 // must precede next
-.set OFFSETOF_FOLD_ACROSS_1024_BITS_CONSTS, -3*16 // must precede next
-.set OFFSETOF_FOLD_ACROSS_512_BITS_CONSTS, -2*16 // must precede next
-.set OFFSETOF_FOLD_ACROSS_256_BITS_CONSTS, -1*16 // must precede next
-.set OFFSETOF_FOLD_ACROSS_128_BITS_CONSTS, 0*16 // must be 0
-.set OFFSETOF_SHUF_TABLE, 1*16
-.set OFFSETOF_BARRETT_REDUCTION_CONSTS, 4*16
-
-// Emit a VEX (or EVEX) coded instruction if allowed, or emulate it using the
-// corresponding non-VEX instruction plus any needed moves. The supported
-// instruction formats are:
-//
-// - Two-arg [src, dst], where the non-VEX format is the same.
-// - Three-arg [src1, src2, dst] where the non-VEX format is
-// [src1, src2_and_dst]. If src2 != dst, then src1 must != dst too.
-//
-// \insn gives the instruction without a "v" prefix and including any immediate
-// argument if needed to make the instruction follow one of the above formats.
-// If \unaligned_mem_tmp is given, then the emitted non-VEX code moves \arg1 to
-// it first; this is needed when \arg1 is an unaligned mem operand.
-.macro _cond_vex insn:req, arg1:req, arg2:req, arg3, unaligned_mem_tmp
-.if AVX_LEVEL == 0
- // VEX not allowed. Emulate it.
- .ifnb \arg3 // Three-arg [src1, src2, dst]
- .ifc "\arg2", "\arg3" // src2 == dst?
- .ifnb \unaligned_mem_tmp
- movdqu \arg1, \unaligned_mem_tmp
- \insn \unaligned_mem_tmp, \arg3
- .else
- \insn \arg1, \arg3
- .endif
- .else // src2 != dst
- .ifc "\arg1", "\arg3"
- .error "Can't have src1 == dst when src2 != dst"
- .endif
- .ifnb \unaligned_mem_tmp
- movdqu \arg1, \unaligned_mem_tmp
- movdqa \arg2, \arg3
- \insn \unaligned_mem_tmp, \arg3
- .else
- movdqa \arg2, \arg3
- \insn \arg1, \arg3
- .endif
- .endif
- .else // Two-arg [src, dst]
- .ifnb \unaligned_mem_tmp
- movdqu \arg1, \unaligned_mem_tmp
- \insn \unaligned_mem_tmp, \arg2
- .else
- \insn \arg1, \arg2
- .endif
- .endif
-.else
- // VEX is allowed. Emit the desired instruction directly.
- .ifnb \arg3
- v\insn \arg1, \arg2, \arg3
- .else
- v\insn \arg1, \arg2
- .endif
-.endif
-.endm
-
-// Broadcast an aligned 128-bit mem operand to all 128-bit lanes of a vector
-// register of length VL.
-.macro _vbroadcast src, dst
-.if VL == 16
- _cond_vex movdqa, \src, \dst
-.elseif VL == 32
- vbroadcasti128 \src, \dst
-.else
- vbroadcasti32x4 \src, \dst
-.endif
-.endm
-
-// Load \vl bytes from the unaligned mem operand \src into \dst, and if the CRC
-// is msb-first use \bswap_mask to reflect the bytes within each 128-bit lane.
-.macro _load_data vl, src, bswap_mask, dst
-.if \vl < 64
- _cond_vex movdqu, "\src", \dst
-.else
- vmovdqu8 \src, \dst
-.endif
-.if !LSB_CRC
- _cond_vex pshufb, \bswap_mask, \dst, \dst
-.endif
-.endm
-
-.macro _prepare_v0 vl, v0, v1, bswap_mask
-.if LSB_CRC
- .if \vl < 64
- _cond_vex pxor, (BUF), \v0, \v0, unaligned_mem_tmp=\v1
- .else
- vpxorq (BUF), \v0, \v0
- .endif
-.else
- _load_data \vl, (BUF), \bswap_mask, \v1
- .if \vl < 64
- _cond_vex pxor, \v1, \v0, \v0
- .else
- vpxorq \v1, \v0, \v0
- .endif
-.endif
-.endm
-
-// The x^0..x^63 terms, i.e. poly128 mod x^64, i.e. the physically low qword for
-// msb-first order or the physically high qword for lsb-first order
-#define LO64_TERMS 0
-
-// The x^64..x^127 terms, i.e. floor(poly128 / x^64), i.e. the physically high
-// qword for msb-first order or the physically low qword for lsb-first order
-#define HI64_TERMS 1
-
-// Multiply the given \src1_terms of each 128-bit lane of \src1 by the given
-// \src2_terms of each 128-bit lane of \src2, and write the result(s) to \dst.
-.macro _pclmulqdq src1, src1_terms, src2, src2_terms, dst
- _cond_vex "pclmulqdq $((\src1_terms ^ LSB_CRC) << 4) ^ (\src2_terms ^ LSB_CRC),", \
- \src1, \src2, \dst
-.endm
-
-// Fold \acc into \data and store the result back into \acc. \data can be an
-// unaligned mem operand if using VEX is allowed and the CRC is lsb-first so no
-// byte-reflection is needed; otherwise it must be a vector register. \consts
-// is a vector register containing the needed fold constants, and \tmp is a
-// temporary vector register. All arguments must be the same length.
-.macro _fold_vec acc, data, consts, tmp
- _pclmulqdq \consts, HI64_TERMS, \acc, HI64_TERMS, \tmp
- _pclmulqdq \consts, LO64_TERMS, \acc, LO64_TERMS, \acc
-.if AVX_LEVEL <= 2
- _cond_vex pxor, \data, \tmp, \tmp
- _cond_vex pxor, \tmp, \acc, \acc
-.else
- vpternlogq $0x96, \data, \tmp, \acc
-.endif
-.endm
-
-// Fold \acc into \data and store the result back into \acc. \data is an
-// unaligned mem operand, \consts is a vector register containing the needed
-// fold constants, \bswap_mask is a vector register containing the
-// byte-reflection table if the CRC is msb-first, and \tmp1 and \tmp2 are
-// temporary vector registers. All arguments must have length \vl.
-.macro _fold_vec_mem vl, acc, data, consts, bswap_mask, tmp1, tmp2
-.if AVX_LEVEL == 0 || !LSB_CRC
- _load_data \vl, \data, \bswap_mask, \tmp1
- _fold_vec \acc, \tmp1, \consts, \tmp2
-.else
- _fold_vec \acc, \data, \consts, \tmp1
-.endif
-.endm
-
-// Load the constants for folding across 2**i vectors of length VL at a time
-// into all 128-bit lanes of the vector register CONSTS.
-.macro _load_vec_folding_consts i
- _vbroadcast OFFSETOF_FOLD_ACROSS_128_BITS_CONSTS+(4-LOG2_VL-\i)*16(CONSTS_PTR), \
- CONSTS
-.endm
-
-// Given vector registers \v0 and \v1 of length \vl, fold \v0 into \v1 and store
-// the result back into \v0. If the remaining length mod \vl is nonzero, also
-// fold \vl data bytes from BUF. For both operations the fold distance is \vl.
-// \consts must be a register of length \vl containing the fold constants.
-.macro _fold_vec_final vl, v0, v1, consts, bswap_mask, tmp1, tmp2
- _fold_vec \v0, \v1, \consts, \tmp1
- test $\vl, LEN8
- jz .Lfold_vec_final_done\@
- _fold_vec_mem \vl, \v0, (BUF), \consts, \bswap_mask, \tmp1, \tmp2
- add $\vl, BUF
-.Lfold_vec_final_done\@:
-.endm
-
-// This macro generates the body of a CRC function with the following prototype:
-//
-// crc_t crc_func(crc_t crc, const u8 *buf, size_t len, const void *consts);
-//
-// |crc| is the initial CRC, and crc_t is a data type wide enough to hold it.
-// |buf| is the data to checksum. |len| is the data length in bytes, which must
-// be at least 16. |consts| is a pointer to the fold_across_128_bits_consts
-// field of the constants struct that was generated for the chosen CRC variant.
-//
-// Moving onto the macro parameters, \n is the number of bits in the CRC, e.g.
-// 32 for a CRC-32. Currently the supported values are 8, 16, 32, and 64. If
-// the file is compiled in i386 mode, then the maximum supported value is 32.
-//
-// \lsb_crc is 1 if the CRC processes the least significant bit of each byte
-// first, i.e. maps bit0 to x^7, bit1 to x^6, ..., bit7 to x^0. \lsb_crc is 0
-// if the CRC processes the most significant bit of each byte first, i.e. maps
-// bit0 to x^0, bit1 to x^1, bit7 to x^7.
-//
-// \vl is the maximum length of vector register to use in bytes: 16, 32, or 64.
-//
-// \avx_level is the level of AVX support to use: 0 for SSE only, 2 for AVX2, or
-// 512 for AVX512.
-//
-// If \vl == 16 && \avx_level == 0, the generated code requires:
-// PCLMULQDQ && SSE4.1. (Note: all known CPUs with PCLMULQDQ also have SSE4.1.)
-//
-// If \vl == 32 && \avx_level == 2, the generated code requires:
-// VPCLMULQDQ && AVX2.
-//
-// If \vl == 64 && \avx_level == 512, the generated code requires:
-// VPCLMULQDQ && AVX512BW && AVX512VL.
-//
-// Other \vl and \avx_level combinations are either not supported or not useful.
-.macro _crc_pclmul n, lsb_crc, vl, avx_level
- .set LSB_CRC, \lsb_crc
- .set VL, \vl
- .set AVX_LEVEL, \avx_level
-
- // Define aliases for the xmm, ymm, or zmm registers according to VL.
-.irp i, 0,1,2,3,4,5,6,7
- .if VL == 16
- .set V\i, %xmm\i
- .set LOG2_VL, 4
- .elseif VL == 32
- .set V\i, %ymm\i
- .set LOG2_VL, 5
- .elseif VL == 64
- .set V\i, %zmm\i
- .set LOG2_VL, 6
- .else
- .error "Unsupported vector length"
- .endif
-.endr
- // Define aliases for the function parameters.
- // Note: when crc_t is shorter than u32, zero-extension to 32 bits is
- // guaranteed by the ABI. Zero-extension to 64 bits is *not* guaranteed
- // when crc_t is shorter than u64.
-#ifdef __x86_64__
-.if \n <= 32
- .set CRC, %edi
-.else
- .set CRC, %rdi
-.endif
- .set BUF, %rsi
- .set LEN, %rdx
- .set LEN32, %edx
- .set LEN8, %dl
- .set CONSTS_PTR, %rcx
-#else
- // 32-bit support, assuming -mregparm=3 and not including support for
- // CRC-64 (which would use both eax and edx to pass the crc parameter).
- .set CRC, %eax
- .set BUF, %edx
- .set LEN, %ecx
- .set LEN32, %ecx
- .set LEN8, %cl
- .set CONSTS_PTR, %ebx // Passed on stack
-#endif
-
- // Define aliases for some local variables. V0-V5 are used without
- // aliases (for accumulators, data, temporary values, etc). Staying
- // within the first 8 vector registers keeps the code 32-bit SSE
- // compatible and reduces the size of 64-bit SSE code slightly.
- .set BSWAP_MASK, V6
- .set BSWAP_MASK_YMM, %ymm6
- .set BSWAP_MASK_XMM, %xmm6
- .set CONSTS, V7
- .set CONSTS_YMM, %ymm7
- .set CONSTS_XMM, %xmm7
-
- // Use ANNOTATE_NOENDBR to suppress an objtool warning, since the
- // functions generated by this macro are called only by static_call.
- ANNOTATE_NOENDBR
-
-#ifdef __i386__
- push CONSTS_PTR
- mov 8(%esp), CONSTS_PTR
-#endif
-
- // Create a 128-bit vector that contains the initial CRC in the end
- // representing the high-order polynomial coefficients, and the rest 0.
- // If the CRC is msb-first, also load the byte-reflection table.
-.if \n <= 32
- _cond_vex movd, CRC, %xmm0
-.else
- _cond_vex movq, CRC, %xmm0
-.endif
-.if !LSB_CRC
- _cond_vex pslldq, $(128-\n)/8, %xmm0, %xmm0
- _vbroadcast OFFSETOF_BSWAP_MASK(CONSTS_PTR), BSWAP_MASK
-.endif
-
- // Load the first vector of data and XOR the initial CRC into the
- // appropriate end of the first 128-bit lane of data. If LEN < VL, then
- // use a short vector and jump ahead to the final reduction. (LEN >= 16
- // is guaranteed here but not necessarily LEN >= VL.)
-.if VL >= 32
- cmp $VL, LEN
- jae .Lat_least_1vec\@
- .if VL == 64
- cmp $32, LEN32
- jb .Lless_than_32bytes\@
- _prepare_v0 32, %ymm0, %ymm1, BSWAP_MASK_YMM
- add $32, BUF
- jmp .Lreduce_256bits_to_128bits\@
-.Lless_than_32bytes\@:
- .endif
- _prepare_v0 16, %xmm0, %xmm1, BSWAP_MASK_XMM
- add $16, BUF
- vmovdqa OFFSETOF_FOLD_ACROSS_128_BITS_CONSTS(CONSTS_PTR), CONSTS_XMM
- jmp .Lcheck_for_partial_block\@
-.Lat_least_1vec\@:
-.endif
- _prepare_v0 VL, V0, V1, BSWAP_MASK
-
- // Handle VL <= LEN < 4*VL.
- cmp $4*VL-1, LEN
- ja .Lat_least_4vecs\@
- add $VL, BUF
- // If VL <= LEN < 2*VL, then jump ahead to the reduction from 1 vector.
- // If VL==16 then load fold_across_128_bits_consts first, as the final
- // reduction depends on it and it won't be loaded anywhere else.
- cmp $2*VL-1, LEN32
-.if VL == 16
- _cond_vex movdqa, OFFSETOF_FOLD_ACROSS_128_BITS_CONSTS(CONSTS_PTR), CONSTS_XMM
-.endif
- jbe .Lreduce_1vec_to_128bits\@
- // Otherwise 2*VL <= LEN < 4*VL. Load one more vector and jump ahead to
- // the reduction from 2 vectors.
- _load_data VL, (BUF), BSWAP_MASK, V1
- add $VL, BUF
- jmp .Lreduce_2vecs_to_1\@
-
-.Lat_least_4vecs\@:
- // Load 3 more vectors of data.
- _load_data VL, 1*VL(BUF), BSWAP_MASK, V1
- _load_data VL, 2*VL(BUF), BSWAP_MASK, V2
- _load_data VL, 3*VL(BUF), BSWAP_MASK, V3
- sub $-4*VL, BUF // Shorter than 'add 4*VL' when VL=32
- add $-4*VL, LEN // Shorter than 'sub 4*VL' when VL=32
-
- // Main loop: while LEN >= 4*VL, fold the 4 vectors V0-V3 into the next
- // 4 vectors of data and write the result back to V0-V3.
- cmp $4*VL-1, LEN // Shorter than 'cmp 4*VL' when VL=32
- jbe .Lreduce_4vecs_to_2\@
- _load_vec_folding_consts 2
-.Lfold_4vecs_loop\@:
- _fold_vec_mem VL, V0, 0*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
- _fold_vec_mem VL, V1, 1*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
- _fold_vec_mem VL, V2, 2*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
- _fold_vec_mem VL, V3, 3*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
- sub $-4*VL, BUF
- add $-4*VL, LEN
- cmp $4*VL-1, LEN
- ja .Lfold_4vecs_loop\@
-
- // Fold V0,V1 into V2,V3 and write the result back to V0,V1. Then fold
- // two more vectors of data from BUF, if at least that much remains.
-.Lreduce_4vecs_to_2\@:
- _load_vec_folding_consts 1
- _fold_vec V0, V2, CONSTS, V4
- _fold_vec V1, V3, CONSTS, V4
- test $2*VL, LEN8
- jz .Lreduce_2vecs_to_1\@
- _fold_vec_mem VL, V0, 0*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
- _fold_vec_mem VL, V1, 1*VL(BUF), CONSTS, BSWAP_MASK, V4, V5
- sub $-2*VL, BUF
-
- // Fold V0 into V1 and write the result back to V0. Then fold one more
- // vector of data from BUF, if at least that much remains.
-.Lreduce_2vecs_to_1\@:
- _load_vec_folding_consts 0
- _fold_vec_final VL, V0, V1, CONSTS, BSWAP_MASK, V4, V5
-
-.Lreduce_1vec_to_128bits\@:
-.if VL == 64
- // Reduce 512-bit %zmm0 to 256-bit %ymm0. Then fold 256 more bits of
- // data from BUF, if at least that much remains.
- vbroadcasti128 OFFSETOF_FOLD_ACROSS_256_BITS_CONSTS(CONSTS_PTR), CONSTS_YMM
- vextracti64x4 $1, %zmm0, %ymm1
- _fold_vec_final 32, %ymm0, %ymm1, CONSTS_YMM, BSWAP_MASK_YMM, %ymm4, %ymm5
-.Lreduce_256bits_to_128bits\@:
-.endif
-.if VL >= 32
- // Reduce 256-bit %ymm0 to 128-bit %xmm0. Then fold 128 more bits of
- // data from BUF, if at least that much remains.
- vmovdqa OFFSETOF_FOLD_ACROSS_128_BITS_CONSTS(CONSTS_PTR), CONSTS_XMM
- vextracti128 $1, %ymm0, %xmm1
- _fold_vec_final 16, %xmm0, %xmm1, CONSTS_XMM, BSWAP_MASK_XMM, %xmm4, %xmm5
-.Lcheck_for_partial_block\@:
-.endif
- and $15, LEN32
- jz .Lreduce_128bits_to_crc\@
-
- // 1 <= LEN <= 15 data bytes remain in BUF. The polynomial is now
- // A*(x^(8*LEN)) + B, where A is the 128-bit polynomial stored in %xmm0
- // and B is the polynomial of the remaining LEN data bytes. To reduce
- // this to 128 bits without needing fold constants for each possible
- // LEN, rearrange this expression into C1*(x^128) + C2, where
- // C1 = floor(A / x^(128 - 8*LEN)) and C2 = A*x^(8*LEN) + B mod x^128.
- // Then fold C1 into C2, which is just another fold across 128 bits.
-
-.if !LSB_CRC || AVX_LEVEL == 0
- // Load the last 16 data bytes. Note that originally LEN was >= 16.
- _load_data 16, "-16(BUF,LEN)", BSWAP_MASK_XMM, %xmm2
-.endif // Else will use vpblendvb mem operand later.
-.if !LSB_CRC
- neg LEN // Needed for indexing shuf_table
-.endif
-
- // tmp = A*x^(8*LEN) mod x^128
- // lsb: pshufb by [LEN, LEN+1, ..., 15, -1, -1, ..., -1]
- // i.e. right-shift by LEN bytes.
- // msb: pshufb by [-1, -1, ..., -1, 0, 1, ..., 15-LEN]
- // i.e. left-shift by LEN bytes.
- _cond_vex movdqu, "OFFSETOF_SHUF_TABLE+16(CONSTS_PTR,LEN)", %xmm3
- _cond_vex pshufb, %xmm3, %xmm0, %xmm1
-
- // C1 = floor(A / x^(128 - 8*LEN))
- // lsb: pshufb by [-1, -1, ..., -1, 0, 1, ..., LEN-1]
- // i.e. left-shift by 16-LEN bytes.
- // msb: pshufb by [16-LEN, 16-LEN+1, ..., 15, -1, -1, ..., -1]
- // i.e. right-shift by 16-LEN bytes.
- _cond_vex pshufb, "OFFSETOF_SHUF_TABLE+32*!LSB_CRC(CONSTS_PTR,LEN)", \
- %xmm0, %xmm0, unaligned_mem_tmp=%xmm4
-
- // C2 = tmp + B. This is just a blend of tmp with the last 16 data
- // bytes (reflected if msb-first). The blend mask is the shuffle table
- // that was used to create tmp. 0 selects tmp, and 1 last16databytes.
-.if AVX_LEVEL == 0
- movdqa %xmm0, %xmm4
- movdqa %xmm3, %xmm0
- pblendvb %xmm2, %xmm1 // uses %xmm0 as implicit operand
- movdqa %xmm4, %xmm0
-.elseif LSB_CRC
- vpblendvb %xmm3, -16(BUF,LEN), %xmm1, %xmm1
-.else
- vpblendvb %xmm3, %xmm2, %xmm1, %xmm1
-.endif
-
- // Fold C1 into C2 and store the 128-bit result in %xmm0.
- _fold_vec %xmm0, %xmm1, CONSTS_XMM, %xmm4
-
-.Lreduce_128bits_to_crc\@:
- // Compute the CRC as %xmm0 * x^n mod G. Here %xmm0 means the 128-bit
- // polynomial stored in %xmm0 (using either lsb-first or msb-first bit
- // order according to LSB_CRC), and G is the CRC's generator polynomial.
-
- // First, multiply %xmm0 by x^n and reduce the result to 64+n bits:
- //
- // t0 := (x^(64+n) mod G) * floor(%xmm0 / x^64) +
- // x^n * (%xmm0 mod x^64)
- //
- // Store t0 * x^(64-n) in %xmm0. I.e., actually do:
- //
- // %xmm0 := ((x^(64+n) mod G) * x^(64-n)) * floor(%xmm0 / x^64) +
- // x^64 * (%xmm0 mod x^64)
- //
- // The extra unreduced factor of x^(64-n) makes floor(t0 / x^n) aligned
- // to the HI64_TERMS of %xmm0 so that the next pclmulqdq can easily
- // select it. The 64-bit constant (x^(64+n) mod G) * x^(64-n) in the
- // msb-first case, or (x^(63+n) mod G) * x^(64-n) in the lsb-first case
- // (considering the extra factor of x that gets implicitly introduced by
- // each pclmulqdq when using lsb-first order), is identical to the
- // constant that was used earlier for folding the LO64_TERMS across 128
- // bits. Thus it's already available in LO64_TERMS of CONSTS_XMM.
- _pclmulqdq CONSTS_XMM, LO64_TERMS, %xmm0, HI64_TERMS, %xmm1
-.if LSB_CRC
- _cond_vex psrldq, $8, %xmm0, %xmm0 // x^64 * (%xmm0 mod x^64)
-.else
- _cond_vex pslldq, $8, %xmm0, %xmm0 // x^64 * (%xmm0 mod x^64)
-.endif
- _cond_vex pxor, %xmm1, %xmm0, %xmm0
- // The HI64_TERMS of %xmm0 now contain floor(t0 / x^n).
- // The LO64_TERMS of %xmm0 now contain (t0 mod x^n) * x^(64-n).
-
- // First step of Barrett reduction: Compute floor(t0 / G). This is the
- // polynomial by which G needs to be multiplied to cancel out the x^n
- // and higher terms of t0, i.e. to reduce t0 mod G. First do:
- //
- // t1 := floor(x^(63+n) / G) * x * floor(t0 / x^n)
- //
- // Then the desired value floor(t0 / G) is floor(t1 / x^64). The 63 in
- // x^(63+n) is the maximum degree of floor(t0 / x^n) and thus the lowest
- // value that makes enough precision be carried through the calculation.
- //
- // The '* x' makes it so the result is floor(t1 / x^64) rather than
- // floor(t1 / x^63), making it qword-aligned in HI64_TERMS so that it
- // can be extracted much more easily in the next step. In the lsb-first
- // case the '* x' happens implicitly. In the msb-first case it must be
- // done explicitly; floor(x^(63+n) / G) * x is a 65-bit constant, so the
- // constant passed to pclmulqdq is (floor(x^(63+n) / G) * x) - x^64, and
- // the multiplication by the x^64 term is handled using a pxor. The
- // pxor causes the low 64 terms of t1 to be wrong, but they are unused.
- _cond_vex movdqa, OFFSETOF_BARRETT_REDUCTION_CONSTS(CONSTS_PTR), CONSTS_XMM
- _pclmulqdq CONSTS_XMM, HI64_TERMS, %xmm0, HI64_TERMS, %xmm1
-.if !LSB_CRC
- _cond_vex pxor, %xmm0, %xmm1, %xmm1 // += x^64 * floor(t0 / x^n)
-.endif
- // The HI64_TERMS of %xmm1 now contain floor(t1 / x^64) = floor(t0 / G).
-
- // Second step of Barrett reduction: Cancel out the x^n and higher terms
- // of t0 by subtracting the needed multiple of G. This gives the CRC:
- //
- // crc := t0 - (G * floor(t0 / G))
- //
- // But %xmm0 contains t0 * x^(64-n), so it's more convenient to do:
- //
- // crc := ((t0 * x^(64-n)) - ((G * x^(64-n)) * floor(t0 / G))) / x^(64-n)
- //
- // Furthermore, since the resulting CRC is n-bit, if mod x^n is
- // explicitly applied to it then the x^n term of G makes no difference
- // in the result and can be omitted. This helps keep the constant
- // multiplier in 64 bits in most cases. This gives the following:
- //
- // %xmm0 := %xmm0 - (((G - x^n) * x^(64-n)) * floor(t0 / G))
- // crc := (%xmm0 / x^(64-n)) mod x^n
- //
- // In the lsb-first case, each pclmulqdq implicitly introduces
- // an extra factor of x, so in that case the constant that needs to be
- // passed to pclmulqdq is actually '(G - x^n) * x^(63-n)' when n <= 63.
- // For lsb-first CRCs where n=64, the extra factor of x cannot be as
- // easily avoided. In that case, instead pass '(G - x^n - x^0) / x' to
- // pclmulqdq and handle the x^0 term (i.e. 1) separately. (All CRC
- // polynomials have nonzero x^n and x^0 terms.) It works out as: the
- // CRC has be XORed with the physically low qword of %xmm1, representing
- // floor(t0 / G). The most efficient way to do that is to move it to
- // the physically high qword and use a ternlog to combine the two XORs.
-.if LSB_CRC && \n == 64
- _cond_vex punpcklqdq, %xmm1, %xmm2, %xmm2
- _pclmulqdq CONSTS_XMM, LO64_TERMS, %xmm1, HI64_TERMS, %xmm1
- .if AVX_LEVEL <= 2
- _cond_vex pxor, %xmm2, %xmm0, %xmm0
- _cond_vex pxor, %xmm1, %xmm0, %xmm0
- .else
- vpternlogq $0x96, %xmm2, %xmm1, %xmm0
- .endif
- _cond_vex "pextrq $1,", %xmm0, %rax // (%xmm0 / x^0) mod x^64
-.else
- _pclmulqdq CONSTS_XMM, LO64_TERMS, %xmm1, HI64_TERMS, %xmm1
- _cond_vex pxor, %xmm1, %xmm0, %xmm0
- .if \n == 8
- _cond_vex "pextrb $7 + LSB_CRC,", %xmm0, %eax // (%xmm0 / x^56) mod x^8
- .elseif \n == 16
- _cond_vex "pextrw $3 + LSB_CRC,", %xmm0, %eax // (%xmm0 / x^48) mod x^16
- .elseif \n == 32
- _cond_vex "pextrd $1 + LSB_CRC,", %xmm0, %eax // (%xmm0 / x^32) mod x^32
- .else // \n == 64 && !LSB_CRC
- _cond_vex movq, %xmm0, %rax // (%xmm0 / x^0) mod x^64
- .endif
-.endif
-
-.if VL > 16
- vzeroupper // Needed when ymm or zmm registers may have been used.
-.endif
-#ifdef __i386__
- pop CONSTS_PTR
-#endif
- RET
-.endm
-
-#ifdef CONFIG_AS_VPCLMULQDQ
-#define DEFINE_CRC_PCLMUL_FUNCS(prefix, bits, lsb) \
-SYM_FUNC_START(prefix##_pclmul_sse); \
- _crc_pclmul n=bits, lsb_crc=lsb, vl=16, avx_level=0; \
-SYM_FUNC_END(prefix##_pclmul_sse); \
- \
-SYM_FUNC_START(prefix##_vpclmul_avx2); \
- _crc_pclmul n=bits, lsb_crc=lsb, vl=32, avx_level=2; \
-SYM_FUNC_END(prefix##_vpclmul_avx2); \
- \
-SYM_FUNC_START(prefix##_vpclmul_avx512); \
- _crc_pclmul n=bits, lsb_crc=lsb, vl=64, avx_level=512; \
-SYM_FUNC_END(prefix##_vpclmul_avx512);
-#else
-#define DEFINE_CRC_PCLMUL_FUNCS(prefix, bits, lsb) \
-SYM_FUNC_START(prefix##_pclmul_sse); \
- _crc_pclmul n=bits, lsb_crc=lsb, vl=16, avx_level=0; \
-SYM_FUNC_END(prefix##_pclmul_sse);
-#endif // !CONFIG_AS_VPCLMULQDQ
diff --git a/arch/x86/lib/crc-pclmul-template.h b/arch/x86/lib/crc-pclmul-template.h
deleted file mode 100644
index c5b3bfe11d8d..000000000000
--- a/arch/x86/lib/crc-pclmul-template.h
+++ /dev/null
@@ -1,76 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * Macros for accessing the [V]PCLMULQDQ-based CRC functions that are
- * instantiated by crc-pclmul-template.S
- *
- * Copyright 2025 Google LLC
- *
- * Author: Eric Biggers <ebiggers@google.com>
- */
-#ifndef _CRC_PCLMUL_TEMPLATE_H
-#define _CRC_PCLMUL_TEMPLATE_H
-
-#include <asm/cpufeatures.h>
-#include <asm/simd.h>
-#include <crypto/internal/simd.h>
-#include <linux/static_call.h>
-#include "crc-pclmul-consts.h"
-
-#define DECLARE_CRC_PCLMUL_FUNCS(prefix, crc_t) \
-crc_t prefix##_pclmul_sse(crc_t crc, const u8 *p, size_t len, \
- const void *consts_ptr); \
-crc_t prefix##_vpclmul_avx2(crc_t crc, const u8 *p, size_t len, \
- const void *consts_ptr); \
-crc_t prefix##_vpclmul_avx512(crc_t crc, const u8 *p, size_t len, \
- const void *consts_ptr); \
-DEFINE_STATIC_CALL(prefix##_pclmul, prefix##_pclmul_sse)
-
-#define INIT_CRC_PCLMUL(prefix) \
-do { \
- if (IS_ENABLED(CONFIG_AS_VPCLMULQDQ) && \
- boot_cpu_has(X86_FEATURE_VPCLMULQDQ) && \
- boot_cpu_has(X86_FEATURE_AVX2) && \
- cpu_has_xfeatures(XFEATURE_MASK_YMM, NULL)) { \
- if (boot_cpu_has(X86_FEATURE_AVX512BW) && \
- boot_cpu_has(X86_FEATURE_AVX512VL) && \
- !boot_cpu_has(X86_FEATURE_PREFER_YMM) && \
- cpu_has_xfeatures(XFEATURE_MASK_AVX512, NULL)) { \
- static_call_update(prefix##_pclmul, \
- prefix##_vpclmul_avx512); \
- } else { \
- static_call_update(prefix##_pclmul, \
- prefix##_vpclmul_avx2); \
- } \
- } \
-} while (0)
-
-/*
- * Call a [V]PCLMULQDQ optimized CRC function if the data length is at least 16
- * bytes, the CPU has PCLMULQDQ support, and the current context may use SIMD.
- *
- * 16 bytes is the minimum length supported by the [V]PCLMULQDQ functions.
- * There is overhead associated with kernel_fpu_begin() and kernel_fpu_end(),
- * varying by CPU and factors such as which parts of the "FPU" state userspace
- * has touched, which could result in a larger cutoff being better. Indeed, a
- * larger cutoff is usually better for a *single* message. However, the
- * overhead of the FPU section gets amortized if multiple FPU sections get
- * executed before returning to userspace, since the XSAVE and XRSTOR occur only
- * once. Considering that and the fact that the [V]PCLMULQDQ code is lighter on
- * the dcache than the table-based code is, a 16-byte cutoff seems to work well.
- */
-#define CRC_PCLMUL(crc, p, len, prefix, consts, have_pclmulqdq) \
-do { \
- if ((len) >= 16 && static_branch_likely(&(have_pclmulqdq)) && \
- crypto_simd_usable()) { \
- const void *consts_ptr; \
- \
- consts_ptr = (consts).fold_across_128_bits_consts; \
- kernel_fpu_begin(); \
- crc = static_call(prefix##_pclmul)((crc), (p), (len), \
- consts_ptr); \
- kernel_fpu_end(); \
- return crc; \
- } \
-} while (0)
-
-#endif /* _CRC_PCLMUL_TEMPLATE_H */
diff --git a/arch/x86/lib/crc-t10dif-glue.c b/arch/x86/lib/crc-t10dif-glue.c
deleted file mode 100644
index f89c335cde3c..000000000000
--- a/arch/x86/lib/crc-t10dif-glue.c
+++ /dev/null
@@ -1,40 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * CRC-T10DIF using [V]PCLMULQDQ instructions
- *
- * Copyright 2024 Google LLC
- */
-
-#include <linux/crc-t10dif.h>
-#include <linux/module.h>
-#include "crc-pclmul-template.h"
-
-static DEFINE_STATIC_KEY_FALSE(have_pclmulqdq);
-
-DECLARE_CRC_PCLMUL_FUNCS(crc16_msb, u16);
-
-u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len)
-{
- CRC_PCLMUL(crc, p, len, crc16_msb, crc16_msb_0x8bb7_consts,
- have_pclmulqdq);
- return crc_t10dif_generic(crc, p, len);
-}
-EXPORT_SYMBOL(crc_t10dif_arch);
-
-static int __init crc_t10dif_x86_init(void)
-{
- if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) {
- static_branch_enable(&have_pclmulqdq);
- INIT_CRC_PCLMUL(crc16_msb);
- }
- return 0;
-}
-arch_initcall(crc_t10dif_x86_init);
-
-static void __exit crc_t10dif_x86_exit(void)
-{
-}
-module_exit(crc_t10dif_x86_exit);
-
-MODULE_DESCRIPTION("CRC-T10DIF using [V]PCLMULQDQ instructions");
-MODULE_LICENSE("GPL");
diff --git a/arch/x86/lib/crc16-msb-pclmul.S b/arch/x86/lib/crc16-msb-pclmul.S
deleted file mode 100644
index e9fe248093a8..000000000000
--- a/arch/x86/lib/crc16-msb-pclmul.S
+++ /dev/null
@@ -1,6 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-// Copyright 2025 Google LLC
-
-#include "crc-pclmul-template.S"
-
-DEFINE_CRC_PCLMUL_FUNCS(crc16_msb, /* bits= */ 16, /* lsb= */ 0)
diff --git a/arch/x86/lib/crc32-glue.c b/arch/x86/lib/crc32-glue.c
deleted file mode 100644
index e3f93b17ac3f..000000000000
--- a/arch/x86/lib/crc32-glue.c
+++ /dev/null
@@ -1,111 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * x86-optimized CRC32 functions
- *
- * Copyright (C) 2008 Intel Corporation
- * Copyright 2012 Xyratex Technology Limited
- * Copyright 2024 Google LLC
- */
-
-#include <linux/crc32.h>
-#include <linux/module.h>
-#include "crc-pclmul-template.h"
-
-static DEFINE_STATIC_KEY_FALSE(have_crc32);
-static DEFINE_STATIC_KEY_FALSE(have_pclmulqdq);
-
-DECLARE_CRC_PCLMUL_FUNCS(crc32_lsb, u32);
-
-u32 crc32_le_arch(u32 crc, const u8 *p, size_t len)
-{
- CRC_PCLMUL(crc, p, len, crc32_lsb, crc32_lsb_0xedb88320_consts,
- have_pclmulqdq);
- return crc32_le_base(crc, p, len);
-}
-EXPORT_SYMBOL(crc32_le_arch);
-
-#ifdef CONFIG_X86_64
-#define CRC32_INST "crc32q %1, %q0"
-#else
-#define CRC32_INST "crc32l %1, %0"
-#endif
-
-/*
- * Use carryless multiply version of crc32c when buffer size is >= 512 to
- * account for FPU state save/restore overhead.
- */
-#define CRC32C_PCLMUL_BREAKEVEN 512
-
-asmlinkage u32 crc32c_x86_3way(u32 crc, const u8 *buffer, size_t len);
-
-u32 crc32c_arch(u32 crc, const u8 *p, size_t len)
-{
- size_t num_longs;
-
- if (!static_branch_likely(&have_crc32))
- return crc32c_base(crc, p, len);
-
- if (IS_ENABLED(CONFIG_X86_64) && len >= CRC32C_PCLMUL_BREAKEVEN &&
- static_branch_likely(&have_pclmulqdq) && crypto_simd_usable()) {
- kernel_fpu_begin();
- crc = crc32c_x86_3way(crc, p, len);
- kernel_fpu_end();
- return crc;
- }
-
- for (num_longs = len / sizeof(unsigned long);
- num_longs != 0; num_longs--, p += sizeof(unsigned long))
- asm(CRC32_INST : "+r" (crc) : ASM_INPUT_RM (*(unsigned long *)p));
-
- if (sizeof(unsigned long) > 4 && (len & 4)) {
- asm("crc32l %1, %0" : "+r" (crc) : ASM_INPUT_RM (*(u32 *)p));
- p += 4;
- }
- if (len & 2) {
- asm("crc32w %1, %0" : "+r" (crc) : ASM_INPUT_RM (*(u16 *)p));
- p += 2;
- }
- if (len & 1)
- asm("crc32b %1, %0" : "+r" (crc) : ASM_INPUT_RM (*p));
-
- return crc;
-}
-EXPORT_SYMBOL(crc32c_arch);
-
-u32 crc32_be_arch(u32 crc, const u8 *p, size_t len)
-{
- return crc32_be_base(crc, p, len);
-}
-EXPORT_SYMBOL(crc32_be_arch);
-
-static int __init crc32_x86_init(void)
-{
- if (boot_cpu_has(X86_FEATURE_XMM4_2))
- static_branch_enable(&have_crc32);
- if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) {
- static_branch_enable(&have_pclmulqdq);
- INIT_CRC_PCLMUL(crc32_lsb);
- }
- return 0;
-}
-arch_initcall(crc32_x86_init);
-
-static void __exit crc32_x86_exit(void)
-{
-}
-module_exit(crc32_x86_exit);
-
-u32 crc32_optimizations(void)
-{
- u32 optimizations = 0;
-
- if (static_key_enabled(&have_crc32))
- optimizations |= CRC32C_OPTIMIZATION;
- if (static_key_enabled(&have_pclmulqdq))
- optimizations |= CRC32_LE_OPTIMIZATION;
- return optimizations;
-}
-EXPORT_SYMBOL(crc32_optimizations);
-
-MODULE_DESCRIPTION("x86-optimized CRC32 functions");
-MODULE_LICENSE("GPL");
diff --git a/arch/x86/lib/crc32-pclmul.S b/arch/x86/lib/crc32-pclmul.S
deleted file mode 100644
index f20f40fb0172..000000000000
--- a/arch/x86/lib/crc32-pclmul.S
+++ /dev/null
@@ -1,6 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-// Copyright 2025 Google LLC
-
-#include "crc-pclmul-template.S"
-
-DEFINE_CRC_PCLMUL_FUNCS(crc32_lsb, /* bits= */ 32, /* lsb= */ 1)
diff --git a/arch/x86/lib/crc32c-3way.S b/arch/x86/lib/crc32c-3way.S
deleted file mode 100644
index 9b8770503bbc..000000000000
--- a/arch/x86/lib/crc32c-3way.S
+++ /dev/null
@@ -1,360 +0,0 @@
-/*
- * Implement fast CRC32C with PCLMULQDQ instructions. (x86_64)
- *
- * The white papers on CRC32C calculations with PCLMULQDQ instruction can be
- * downloaded from:
- * http://www.intel.com/content/dam/www/public/us/en/documents/white-papers/crc-iscsi-polynomial-crc32-instruction-paper.pdf
- * http://www.intel.com/content/dam/www/public/us/en/documents/white-papers/fast-crc-computation-paper.pdf
- *
- * Copyright (C) 2012 Intel Corporation.
- * Copyright 2024 Google LLC
- *
- * Authors:
- * Wajdi Feghali <wajdi.k.feghali@intel.com>
- * James Guilford <james.guilford@intel.com>
- * David Cote <david.m.cote@intel.com>
- * Tim Chen <tim.c.chen@linux.intel.com>
- *
- * This software is available to you under a choice of one of two
- * licenses. You may choose to be licensed under the terms of the GNU
- * General Public License (GPL) Version 2, available from the file
- * COPYING in the main directory of this source tree, or the
- * OpenIB.org BSD license below:
- *
- * Redistribution and use in source and binary forms, with or
- * without modification, are permitted provided that the following
- * conditions are met:
- *
- * - Redistributions of source code must retain the above
- * copyright notice, this list of conditions and the following
- * disclaimer.
- *
- * - Redistributions in binary form must reproduce the above
- * copyright notice, this list of conditions and the following
- * disclaimer in the documentation and/or other materials
- * provided with the distribution.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
- * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
- * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
- * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
- * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
- * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
- * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
- * SOFTWARE.
- */
-
-#include <linux/linkage.h>
-
-## ISCSI CRC 32 Implementation with crc32 and pclmulqdq Instruction
-
-# Define threshold below which buffers are considered "small" and routed to
-# regular CRC code that does not interleave the CRC instructions.
-#define SMALL_SIZE 200
-
-# u32 crc32c_x86_3way(u32 crc, const u8 *buffer, size_t len);
-
-.text
-SYM_FUNC_START(crc32c_x86_3way)
-#define crc0 %edi
-#define crc0_q %rdi
-#define bufp %rsi
-#define bufp_d %esi
-#define len %rdx
-#define len_dw %edx
-#define n_misaligned %ecx /* overlaps chunk_bytes! */
-#define n_misaligned_q %rcx
-#define chunk_bytes %ecx /* overlaps n_misaligned! */
-#define chunk_bytes_q %rcx
-#define crc1 %r8
-#define crc2 %r9
-
- cmp $SMALL_SIZE, len
- jb .Lsmall
-
- ################################################################
- ## 1) ALIGN:
- ################################################################
- mov bufp_d, n_misaligned
- neg n_misaligned
- and $7, n_misaligned # calculate the misalignment amount of
- # the address
- je .Laligned # Skip if aligned
-
- # Process 1 <= n_misaligned <= 7 bytes individually in order to align
- # the remaining data to an 8-byte boundary.
-.Ldo_align:
- movq (bufp), %rax
- add n_misaligned_q, bufp
- sub n_misaligned_q, len
-.Lalign_loop:
- crc32b %al, crc0 # compute crc32 of 1-byte
- shr $8, %rax # get next byte
- dec n_misaligned
- jne .Lalign_loop
-.Laligned:
-
- ################################################################
- ## 2) PROCESS BLOCK:
- ################################################################
-
- cmp $128*24, len
- jae .Lfull_block
-
-.Lpartial_block:
- # Compute floor(len / 24) to get num qwords to process from each lane.
- imul $2731, len_dw, %eax # 2731 = ceil(2^16 / 24)
- shr $16, %eax
- jmp .Lcrc_3lanes
-
-.Lfull_block:
- # Processing 128 qwords from each lane.
- mov $128, %eax
-
- ################################################################
- ## 3) CRC each of three lanes:
- ################################################################
-
-.Lcrc_3lanes:
- xor crc1,crc1
- xor crc2,crc2
- mov %eax, chunk_bytes
- shl $3, chunk_bytes # num bytes to process from each lane
- sub $5, %eax # 4 for 4x_loop, 1 for special last iter
- jl .Lcrc_3lanes_4x_done
-
- # Unroll the loop by a factor of 4 to reduce the overhead of the loop
- # bookkeeping instructions, which can compete with crc32q for the ALUs.
-.Lcrc_3lanes_4x_loop:
- crc32q (bufp), crc0_q
- crc32q (bufp,chunk_bytes_q), crc1
- crc32q (bufp,chunk_bytes_q,2), crc2
- crc32q 8(bufp), crc0_q
- crc32q 8(bufp,chunk_bytes_q), crc1
- crc32q 8(bufp,chunk_bytes_q,2), crc2
- crc32q 16(bufp), crc0_q
- crc32q 16(bufp,chunk_bytes_q), crc1
- crc32q 16(bufp,chunk_bytes_q,2), crc2
- crc32q 24(bufp), crc0_q
- crc32q 24(bufp,chunk_bytes_q), crc1
- crc32q 24(bufp,chunk_bytes_q,2), crc2
- add $32, bufp
- sub $4, %eax
- jge .Lcrc_3lanes_4x_loop
-
-.Lcrc_3lanes_4x_done:
- add $4, %eax
- jz .Lcrc_3lanes_last_qword
-
-.Lcrc_3lanes_1x_loop:
- crc32q (bufp), crc0_q
- crc32q (bufp,chunk_bytes_q), crc1
- crc32q (bufp,chunk_bytes_q,2), crc2
- add $8, bufp
- dec %eax
- jnz .Lcrc_3lanes_1x_loop
-
-.Lcrc_3lanes_last_qword:
- crc32q (bufp), crc0_q
- crc32q (bufp,chunk_bytes_q), crc1
-# SKIP crc32q (bufp,chunk_bytes_q,2), crc2 ; Don't do this one yet
-
- ################################################################
- ## 4) Combine three results:
- ################################################################
-
- lea (K_table-8)(%rip), %rax # first entry is for idx 1
- pmovzxdq (%rax,chunk_bytes_q), %xmm0 # 2 consts: K1:K2
- lea (chunk_bytes,chunk_bytes,2), %eax # chunk_bytes * 3
- sub %rax, len # len -= chunk_bytes * 3
-
- movq crc0_q, %xmm1 # CRC for block 1
- pclmulqdq $0x00, %xmm0, %xmm1 # Multiply by K2
-
- movq crc1, %xmm2 # CRC for block 2
- pclmulqdq $0x10, %xmm0, %xmm2 # Multiply by K1
-
- pxor %xmm2,%xmm1
- movq %xmm1, %rax
- xor (bufp,chunk_bytes_q,2), %rax
- mov crc2, crc0_q
- crc32 %rax, crc0_q
- lea 8(bufp,chunk_bytes_q,2), bufp
-
- ################################################################
- ## 5) If more blocks remain, goto (2):
- ################################################################
-
- cmp $128*24, len
- jae .Lfull_block
- cmp $SMALL_SIZE, len
- jae .Lpartial_block
-
- #######################################################################
- ## 6) Process any remainder without interleaving:
- #######################################################################
-.Lsmall:
- test len_dw, len_dw
- jz .Ldone
- mov len_dw, %eax
- shr $3, %eax
- jz .Ldo_dword
-.Ldo_qwords:
- crc32q (bufp), crc0_q
- add $8, bufp
- dec %eax
- jnz .Ldo_qwords
-.Ldo_dword:
- test $4, len_dw
- jz .Ldo_word
- crc32l (bufp), crc0
- add $4, bufp
-.Ldo_word:
- test $2, len_dw
- jz .Ldo_byte
- crc32w (bufp), crc0
- add $2, bufp
-.Ldo_byte:
- test $1, len_dw
- jz .Ldone
- crc32b (bufp), crc0
-.Ldone:
- mov crc0, %eax
- RET
-SYM_FUNC_END(crc32c_x86_3way)
-
-.section .rodata, "a", @progbits
- ################################################################
- ## PCLMULQDQ tables
- ## Table is 128 entries x 2 words (8 bytes) each
- ################################################################
-.align 8
-K_table:
- .long 0x493c7d27, 0x00000001
- .long 0xba4fc28e, 0x493c7d27
- .long 0xddc0152b, 0xf20c0dfe
- .long 0x9e4addf8, 0xba4fc28e
- .long 0x39d3b296, 0x3da6d0cb
- .long 0x0715ce53, 0xddc0152b
- .long 0x47db8317, 0x1c291d04
- .long 0x0d3b6092, 0x9e4addf8
- .long 0xc96cfdc0, 0x740eef02
- .long 0x878a92a7, 0x39d3b296
- .long 0xdaece73e, 0x083a6eec
- .long 0xab7aff2a, 0x0715ce53
- .long 0x2162d385, 0xc49f4f67
- .long 0x83348832, 0x47db8317
- .long 0x299847d5, 0x2ad91c30
- .long 0xb9e02b86, 0x0d3b6092
- .long 0x18b33a4e, 0x6992cea2
- .long 0xb6dd949b, 0xc96cfdc0
- .long 0x78d9ccb7, 0x7e908048
- .long 0xbac2fd7b, 0x878a92a7
- .long 0xa60ce07b, 0x1b3d8f29
- .long 0xce7f39f4, 0xdaece73e
- .long 0x61d82e56, 0xf1d0f55e
- .long 0xd270f1a2, 0xab7aff2a
- .long 0xc619809d, 0xa87ab8a8
- .long 0x2b3cac5d, 0x2162d385
- .long 0x65863b64, 0x8462d800
- .long 0x1b03397f, 0x83348832
- .long 0xebb883bd, 0x71d111a8
- .long 0xb3e32c28, 0x299847d5
- .long 0x064f7f26, 0xffd852c6
- .long 0xdd7e3b0c, 0xb9e02b86
- .long 0xf285651c, 0xdcb17aa4
- .long 0x10746f3c, 0x18b33a4e
- .long 0xc7a68855, 0xf37c5aee
- .long 0x271d9844, 0xb6dd949b
- .long 0x8e766a0c, 0x6051d5a2
- .long 0x93a5f730, 0x78d9ccb7
- .long 0x6cb08e5c, 0x18b0d4ff
- .long 0x6b749fb2, 0xbac2fd7b
- .long 0x1393e203, 0x21f3d99c
- .long 0xcec3662e, 0xa60ce07b
- .long 0x96c515bb, 0x8f158014
- .long 0xe6fc4e6a, 0xce7f39f4
- .long 0x8227bb8a, 0xa00457f7
- .long 0xb0cd4768, 0x61d82e56
- .long 0x39c7ff35, 0x8d6d2c43
- .long 0xd7a4825c, 0xd270f1a2
- .long 0x0ab3844b, 0x00ac29cf
- .long 0x0167d312, 0xc619809d
- .long 0xf6076544, 0xe9adf796
- .long 0x26f6a60a, 0x2b3cac5d
- .long 0xa741c1bf, 0x96638b34
- .long 0x98d8d9cb, 0x65863b64
- .long 0x49c3cc9c, 0xe0e9f351
- .long 0x68bce87a, 0x1b03397f
- .long 0x57a3d037, 0x9af01f2d
- .long 0x6956fc3b, 0xebb883bd
- .long 0x42d98888, 0x2cff42cf
- .long 0x3771e98f, 0xb3e32c28
- .long 0xb42ae3d9, 0x88f25a3a
- .long 0x2178513a, 0x064f7f26
- .long 0xe0ac139e, 0x4e36f0b0
- .long 0x170076fa, 0xdd7e3b0c
- .long 0x444dd413, 0xbd6f81f8
- .long 0x6f345e45, 0xf285651c
- .long 0x41d17b64, 0x91c9bd4b
- .long 0xff0dba97, 0x10746f3c
- .long 0xa2b73df1, 0x885f087b
- .long 0xf872e54c, 0xc7a68855
- .long 0x1e41e9fc, 0x4c144932
- .long 0x86d8e4d2, 0x271d9844
- .long 0x651bd98b, 0x52148f02
- .long 0x5bb8f1bc, 0x8e766a0c
- .long 0xa90fd27a, 0xa3c6f37a
- .long 0xb3af077a, 0x93a5f730
- .long 0x4984d782, 0xd7c0557f
- .long 0xca6ef3ac, 0x6cb08e5c
- .long 0x234e0b26, 0x63ded06a
- .long 0xdd66cbbb, 0x6b749fb2
- .long 0x4597456a, 0x4d56973c
- .long 0xe9e28eb4, 0x1393e203
- .long 0x7b3ff57a, 0x9669c9df
- .long 0xc9c8b782, 0xcec3662e
- .long 0x3f70cc6f, 0xe417f38a
- .long 0x93e106a4, 0x96c515bb
- .long 0x62ec6c6d, 0x4b9e0f71
- .long 0xd813b325, 0xe6fc4e6a
- .long 0x0df04680, 0xd104b8fc
- .long 0x2342001e, 0x8227bb8a
- .long 0x0a2a8d7e, 0x5b397730
- .long 0x6d9a4957, 0xb0cd4768
- .long 0xe8b6368b, 0xe78eb416
- .long 0xd2c3ed1a, 0x39c7ff35
- .long 0x995a5724, 0x61ff0e01
- .long 0x9ef68d35, 0xd7a4825c
- .long 0x0c139b31, 0x8d96551c
- .long 0xf2271e60, 0x0ab3844b
- .long 0x0b0bf8ca, 0x0bf80dd2
- .long 0x2664fd8b, 0x0167d312
- .long 0xed64812d, 0x8821abed
- .long 0x02ee03b2, 0xf6076544
- .long 0x8604ae0f, 0x6a45d2b2
- .long 0x363bd6b3, 0x26f6a60a
- .long 0x135c83fd, 0xd8d26619
- .long 0x5fabe670, 0xa741c1bf
- .long 0x35ec3279, 0xde87806c
- .long 0x00bcf5f6, 0x98d8d9cb
- .long 0x8ae00689, 0x14338754
- .long 0x17f27698, 0x49c3cc9c
- .long 0x58ca5f00, 0x5bd2011f
- .long 0xaa7c7ad5, 0x68bce87a
- .long 0xb5cfca28, 0xdd07448e
- .long 0xded288f8, 0x57a3d037
- .long 0x59f229bc, 0xdde8f5b9
- .long 0x6d390dec, 0x6956fc3b
- .long 0x37170390, 0xa3e3e02c
- .long 0x6353c1cc, 0x42d98888
- .long 0xc4584f5c, 0xd73c7bea
- .long 0xf48642e9, 0x3771e98f
- .long 0x531377e2, 0x80ff0093
- .long 0xdd35bc8d, 0xb42ae3d9
- .long 0xb25b29f2, 0x8fe4c34d
- .long 0x9a5ede41, 0x2178513a
- .long 0xa563905d, 0xdf99fc11
- .long 0x45cddf4e, 0xe0ac139e
- .long 0xacfa3103, 0x6c23e841
- .long 0xa51b6135, 0x170076fa
diff --git a/arch/x86/lib/crc64-glue.c b/arch/x86/lib/crc64-glue.c
deleted file mode 100644
index b0e1b719ecbf..000000000000
--- a/arch/x86/lib/crc64-glue.c
+++ /dev/null
@@ -1,50 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * CRC64 using [V]PCLMULQDQ instructions
- *
- * Copyright 2025 Google LLC
- */
-
-#include <linux/crc64.h>
-#include <linux/module.h>
-#include "crc-pclmul-template.h"
-
-static DEFINE_STATIC_KEY_FALSE(have_pclmulqdq);
-
-DECLARE_CRC_PCLMUL_FUNCS(crc64_msb, u64);
-DECLARE_CRC_PCLMUL_FUNCS(crc64_lsb, u64);
-
-u64 crc64_be_arch(u64 crc, const u8 *p, size_t len)
-{
- CRC_PCLMUL(crc, p, len, crc64_msb, crc64_msb_0x42f0e1eba9ea3693_consts,
- have_pclmulqdq);
- return crc64_be_generic(crc, p, len);
-}
-EXPORT_SYMBOL_GPL(crc64_be_arch);
-
-u64 crc64_nvme_arch(u64 crc, const u8 *p, size_t len)
-{
- CRC_PCLMUL(crc, p, len, crc64_lsb, crc64_lsb_0x9a6c9329ac4bc9b5_consts,
- have_pclmulqdq);
- return crc64_nvme_generic(crc, p, len);
-}
-EXPORT_SYMBOL_GPL(crc64_nvme_arch);
-
-static int __init crc64_x86_init(void)
-{
- if (boot_cpu_has(X86_FEATURE_PCLMULQDQ)) {
- static_branch_enable(&have_pclmulqdq);
- INIT_CRC_PCLMUL(crc64_msb);
- INIT_CRC_PCLMUL(crc64_lsb);
- }
- return 0;
-}
-arch_initcall(crc64_x86_init);
-
-static void __exit crc64_x86_exit(void)
-{
-}
-module_exit(crc64_x86_exit);
-
-MODULE_DESCRIPTION("CRC64 using [V]PCLMULQDQ instructions");
-MODULE_LICENSE("GPL");
diff --git a/arch/x86/lib/crc64-pclmul.S b/arch/x86/lib/crc64-pclmul.S
deleted file mode 100644
index 4173051b5197..000000000000
--- a/arch/x86/lib/crc64-pclmul.S
+++ /dev/null
@@ -1,7 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-// Copyright 2025 Google LLC
-
-#include "crc-pclmul-template.S"
-
-DEFINE_CRC_PCLMUL_FUNCS(crc64_msb, /* bits= */ 64, /* lsb= */ 0)
-DEFINE_CRC_PCLMUL_FUNCS(crc64_lsb, /* bits= */ 64, /* lsb= */ 1)
diff --git a/arch/x86/lib/delay.c b/arch/x86/lib/delay.c
index e86eda2c0b04..eb2d2e1cbddd 100644
--- a/arch/x86/lib/delay.c
+++ b/arch/x86/lib/delay.c
@@ -75,7 +75,7 @@ static void delay_tsc(u64 cycles)
/* Allow RT tasks to run */
preempt_enable();
- rep_nop();
+ native_pause();
preempt_disable();
/*
diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 98631c0e7a11..4e385cbfd444 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -13,6 +13,7 @@
#include <asm/insn.h>
#include <asm/insn-eval.h>
#include <asm/ldt.h>
+#include <asm/msr.h>
#include <asm/vm86.h>
#undef pr_fmt
@@ -631,14 +632,21 @@ static bool get_desc(struct desc_struct *out, unsigned short sel)
/* Bits [15:3] contain the index of the desired entry. */
sel >>= 3;
- mutex_lock(&current->active_mm->context.lock);
- ldt = current->active_mm->context.ldt;
+ /*
+ * If we're not in a valid context with a real (not just lazy)
+ * user mm, then don't even try.
+ */
+ if (!nmi_uaccess_okay())
+ return false;
+
+ mutex_lock(&current->mm->context.lock);
+ ldt = current->mm->context.ldt;
if (ldt && sel < ldt->nr_entries) {
*out = ldt->entries[sel];
success = true;
}
- mutex_unlock(&current->active_mm->context.lock);
+ mutex_unlock(&current->mm->context.lock);
return success;
}
@@ -702,16 +710,16 @@ unsigned long insn_get_seg_base(struct pt_regs *regs, int seg_reg_idx)
unsigned long base;
if (seg_reg_idx == INAT_SEG_REG_FS) {
- rdmsrl(MSR_FS_BASE, base);
+ rdmsrq(MSR_FS_BASE, base);
} else if (seg_reg_idx == INAT_SEG_REG_GS) {
/*
* swapgs was called at the kernel entry point. Thus,
* MSR_KERNEL_GS_BASE will have the user-space GS base.
*/
if (user_mode(regs))
- rdmsrl(MSR_KERNEL_GS_BASE, base);
+ rdmsrq(MSR_KERNEL_GS_BASE, base);
else
- rdmsrl(MSR_GS_BASE, base);
+ rdmsrq(MSR_GS_BASE, base);
} else {
base = 0;
}
diff --git a/arch/x86/lib/insn.c b/arch/x86/lib/insn.c
index 6ffb931b9fb1..149a57e334ab 100644
--- a/arch/x86/lib/insn.c
+++ b/arch/x86/lib/insn.c
@@ -324,6 +324,11 @@ int insn_get_opcode(struct insn *insn)
}
insn->attr = inat_get_opcode_attribute(op);
+ if (insn->x86_64 && inat_is_invalid64(insn->attr)) {
+ /* This instruction is invalid, like UD2. Stop decoding. */
+ insn->attr &= INAT_INV64;
+ }
+
while (inat_is_escape(insn->attr)) {
/* Get escaped opcode */
op = get_next(insn_byte_t, insn);
@@ -337,6 +342,7 @@ int insn_get_opcode(struct insn *insn)
insn->attr = 0;
return -EINVAL;
}
+
end:
opcode->got = 1;
return 0;
@@ -658,7 +664,6 @@ int insn_get_immediate(struct insn *insn)
}
if (!inat_has_immediate(insn->attr))
- /* no immediates */
goto done;
switch (inat_immediate_size(insn->attr)) {
diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
index 5eecb45d05d5..c20e04764edc 100644
--- a/arch/x86/lib/iomem.c
+++ b/arch/x86/lib/iomem.c
@@ -10,7 +10,7 @@
static __always_inline void rep_movs(void *to, const void *from, size_t n)
{
unsigned long d0, d1, d2;
- asm volatile("rep ; movsl\n\t"
+ asm volatile("rep movsl\n\t"
"testb $2,%b4\n\t"
"je 1f\n\t"
"movsw\n"
diff --git a/arch/x86/lib/kaslr.c b/arch/x86/lib/kaslr.c
index a58f451a7dd3..b5893928d55c 100644
--- a/arch/x86/lib/kaslr.c
+++ b/arch/x86/lib/kaslr.c
@@ -8,7 +8,7 @@
*/
#include <asm/asm.h>
#include <asm/kaslr.h>
-#include <asm/msr.h>
+#include <asm/tsc.h>
#include <asm/archrandom.h>
#include <asm/e820/api.h>
#include <asm/shared/io.h>
diff --git a/arch/x86/lib/memcpy_64.S b/arch/x86/lib/memcpy_64.S
index 0ae2e1712e2e..12a23fa7c44c 100644
--- a/arch/x86/lib/memcpy_64.S
+++ b/arch/x86/lib/memcpy_64.S
@@ -41,6 +41,7 @@ SYM_FUNC_END(__memcpy)
EXPORT_SYMBOL(__memcpy)
SYM_FUNC_ALIAS_MEMFUNC(memcpy, __memcpy)
+SYM_PIC_ALIAS(memcpy)
EXPORT_SYMBOL(memcpy)
SYM_FUNC_START_LOCAL(memcpy_orig)
diff --git a/arch/x86/lib/memset_64.S b/arch/x86/lib/memset_64.S
index d66b710d628f..fb5a03cf5ab7 100644
--- a/arch/x86/lib/memset_64.S
+++ b/arch/x86/lib/memset_64.S
@@ -42,6 +42,7 @@ SYM_FUNC_END(__memset)
EXPORT_SYMBOL(__memset)
SYM_FUNC_ALIAS_MEMFUNC(memset, __memset)
+SYM_PIC_ALIAS(memset)
EXPORT_SYMBOL(memset)
SYM_FUNC_START_LOCAL(memset_orig)
diff --git a/arch/x86/lib/msr-smp.c b/arch/x86/lib/msr-smp.c
index acd463d887e1..b8f63419e6ae 100644
--- a/arch/x86/lib/msr-smp.c
+++ b/arch/x86/lib/msr-smp.c
@@ -47,7 +47,7 @@ int rdmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 *l, u32 *h)
}
EXPORT_SYMBOL(rdmsr_on_cpu);
-int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+int rdmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
{
int err;
struct msr_info rv;
@@ -60,7 +60,7 @@ int rdmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
return err;
}
-EXPORT_SYMBOL(rdmsrl_on_cpu);
+EXPORT_SYMBOL(rdmsrq_on_cpu);
int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
{
@@ -78,7 +78,7 @@ int wrmsr_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
}
EXPORT_SYMBOL(wrmsr_on_cpu);
-int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+int wrmsrq_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
{
int err;
struct msr_info rv;
@@ -92,7 +92,7 @@ int wrmsrl_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
return err;
}
-EXPORT_SYMBOL(wrmsrl_on_cpu);
+EXPORT_SYMBOL(wrmsrq_on_cpu);
static void __rwmsr_on_cpus(const struct cpumask *mask, u32 msr_no,
struct msr __percpu *msrs,
@@ -204,7 +204,7 @@ int wrmsr_safe_on_cpu(unsigned int cpu, u32 msr_no, u32 l, u32 h)
}
EXPORT_SYMBOL(wrmsr_safe_on_cpu);
-int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
+int wrmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
{
int err;
struct msr_info rv;
@@ -218,9 +218,9 @@ int wrmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 q)
return err ? err : rv.err;
}
-EXPORT_SYMBOL(wrmsrl_safe_on_cpu);
+EXPORT_SYMBOL(wrmsrq_safe_on_cpu);
-int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
+int rdmsrq_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
{
u32 low, high;
int err;
@@ -230,7 +230,7 @@ int rdmsrl_safe_on_cpu(unsigned int cpu, u32 msr_no, u64 *q)
return err;
}
-EXPORT_SYMBOL(rdmsrl_safe_on_cpu);
+EXPORT_SYMBOL(rdmsrq_safe_on_cpu);
/*
* These variants are significantly slower, but allows control over
diff --git a/arch/x86/lib/msr.c b/arch/x86/lib/msr.c
index 5a18ecc04a6c..4ef7c6dcbea6 100644
--- a/arch/x86/lib/msr.c
+++ b/arch/x86/lib/msr.c
@@ -41,7 +41,7 @@ static int msr_read(u32 msr, struct msr *m)
int err;
u64 val;
- err = rdmsrl_safe(msr, &val);
+ err = rdmsrq_safe(msr, &val);
if (!err)
m->q = val;
@@ -58,7 +58,7 @@ static int msr_read(u32 msr, struct msr *m)
*/
static int msr_write(u32 msr, struct msr *m)
{
- return wrmsrl_safe(msr, m->q);
+ return wrmsrq_safe(msr, m->q);
}
static inline int __flip_bit(u32 msr, u8 bit, bool set)
@@ -122,23 +122,23 @@ int msr_clear_bit(u32 msr, u8 bit)
EXPORT_SYMBOL_GPL(msr_clear_bit);
#ifdef CONFIG_TRACEPOINTS
-void do_trace_write_msr(unsigned int msr, u64 val, int failed)
+void do_trace_write_msr(u32 msr, u64 val, int failed)
{
trace_write_msr(msr, val, failed);
}
EXPORT_SYMBOL(do_trace_write_msr);
EXPORT_TRACEPOINT_SYMBOL(write_msr);
-void do_trace_read_msr(unsigned int msr, u64 val, int failed)
+void do_trace_read_msr(u32 msr, u64 val, int failed)
{
trace_read_msr(msr, val, failed);
}
EXPORT_SYMBOL(do_trace_read_msr);
EXPORT_TRACEPOINT_SYMBOL(read_msr);
-void do_trace_rdpmc(unsigned counter, u64 val, int failed)
+void do_trace_rdpmc(u32 msr, u64 val, int failed)
{
- trace_rdpmc(counter, val, failed);
+ trace_rdpmc(msr, val, failed);
}
EXPORT_SYMBOL(do_trace_rdpmc);
EXPORT_TRACEPOINT_SYMBOL(rdpmc);
diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S
index 39374949daa2..d78d769a02bd 100644
--- a/arch/x86/lib/retpoline.S
+++ b/arch/x86/lib/retpoline.S
@@ -40,6 +40,7 @@ SYM_INNER_LABEL(__x86_indirect_thunk_\reg, SYM_L_GLOBAL)
ALTERNATIVE_2 __stringify(RETPOLINE \reg), \
__stringify(lfence; ANNOTATE_RETPOLINE_SAFE; jmp *%\reg; int3), X86_FEATURE_RETPOLINE_LFENCE, \
__stringify(ANNOTATE_RETPOLINE_SAFE; jmp *%\reg), ALT_NOT(X86_FEATURE_RETPOLINE)
+SYM_PIC_ALIAS(__x86_indirect_thunk_\reg)
.endm
@@ -442,6 +443,7 @@ SYM_CODE_START(__x86_return_thunk)
#endif
int3
SYM_CODE_END(__x86_return_thunk)
+SYM_PIC_ALIAS(__x86_return_thunk)
EXPORT_SYMBOL(__x86_return_thunk)
#endif /* CONFIG_MITIGATION_RETHUNK */
diff --git a/arch/x86/lib/string_32.c b/arch/x86/lib/string_32.c
index 53b3f202267c..f87ec24fa579 100644
--- a/arch/x86/lib/string_32.c
+++ b/arch/x86/lib/string_32.c
@@ -40,8 +40,7 @@ char *strncpy(char *dest, const char *src, size_t count)
"stosb\n\t"
"testb %%al,%%al\n\t"
"jne 1b\n\t"
- "rep\n\t"
- "stosb\n"
+ "rep stosb\n"
"2:"
: "=&S" (d0), "=&D" (d1), "=&c" (d2), "=&a" (d3)
: "0" (src), "1" (dest), "2" (count) : "memory");
@@ -54,8 +53,7 @@ EXPORT_SYMBOL(strncpy);
char *strcat(char *dest, const char *src)
{
int d0, d1, d2, d3;
- asm volatile("repne\n\t"
- "scasb\n\t"
+ asm volatile("repne scasb\n\t"
"decl %1\n"
"1:\tlodsb\n\t"
"stosb\n\t"
@@ -72,8 +70,7 @@ EXPORT_SYMBOL(strcat);
char *strncat(char *dest, const char *src, size_t count)
{
int d0, d1, d2, d3;
- asm volatile("repne\n\t"
- "scasb\n\t"
+ asm volatile("repne scasb\n\t"
"decl %1\n\t"
"movl %8,%3\n"
"1:\tdecl %3\n\t"
@@ -167,8 +164,7 @@ size_t strlen(const char *s)
{
int d0;
size_t res;
- asm volatile("repne\n\t"
- "scasb"
+ asm volatile("repne scasb"
: "=c" (res), "=&D" (d0)
: "1" (s), "a" (0), "0" (0xffffffffu)
: "memory");
@@ -184,8 +180,7 @@ void *memchr(const void *cs, int c, size_t count)
void *res;
if (!count)
return NULL;
- asm volatile("repne\n\t"
- "scasb\n\t"
+ asm volatile("repne scasb\n\t"
"je 1f\n\t"
"movl $1,%0\n"
"1:\tdecl %0"
@@ -202,7 +197,7 @@ void *memscan(void *addr, int c, size_t size)
{
if (!size)
return addr;
- asm volatile("repnz; scasb\n\t"
+ asm volatile("repnz scasb\n\t"
"jnz 1f\n\t"
"dec %%edi\n"
"1:"
diff --git a/arch/x86/lib/strstr_32.c b/arch/x86/lib/strstr_32.c
index 38f37df056f7..28267985e85f 100644
--- a/arch/x86/lib/strstr_32.c
+++ b/arch/x86/lib/strstr_32.c
@@ -8,16 +8,14 @@ int d0, d1;
register char *__res;
__asm__ __volatile__(
"movl %6,%%edi\n\t"
- "repne\n\t"
- "scasb\n\t"
+ "repne scasb\n\t"
"notl %%ecx\n\t"
"decl %%ecx\n\t" /* NOTE! This also sets Z if searchstring='' */
"movl %%ecx,%%edx\n"
"1:\tmovl %6,%%edi\n\t"
"movl %%esi,%%eax\n\t"
"movl %%edx,%%ecx\n\t"
- "repe\n\t"
- "cmpsb\n\t"
+ "repe cmpsb\n\t"
"je 2f\n\t" /* also works for empty string, see above */
"xchgl %%eax,%%esi\n\t"
"incl %%esi\n\t"
diff --git a/arch/x86/lib/usercopy_32.c b/arch/x86/lib/usercopy_32.c
index 422257c350c6..f6f436f1d573 100644
--- a/arch/x86/lib/usercopy_32.c
+++ b/arch/x86/lib/usercopy_32.c
@@ -38,9 +38,9 @@ do { \
might_fault(); \
__asm__ __volatile__( \
ASM_STAC "\n" \
- "0: rep; stosl\n" \
+ "0: rep stosl\n" \
" movl %2,%0\n" \
- "1: rep; stosb\n" \
+ "1: rep stosb\n" \
"2: " ASM_CLAC "\n" \
_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN4, %2) \
_ASM_EXTABLE_UA(1b, 2b) \
@@ -140,9 +140,9 @@ __copy_user_intel(void __user *to, const void *from, unsigned long size)
" shrl $2, %0\n"
" andl $3, %%eax\n"
" cld\n"
- "99: rep; movsl\n"
+ "99: rep movsl\n"
"36: movl %%eax, %0\n"
- "37: rep; movsb\n"
+ "37: rep movsb\n"
"100:\n"
_ASM_EXTABLE_UA(1b, 100b)
_ASM_EXTABLE_UA(2b, 100b)
@@ -242,9 +242,9 @@ static unsigned long __copy_user_intel_nocache(void *to,
" shrl $2, %0\n"
" andl $3, %%eax\n"
" cld\n"
- "6: rep; movsl\n"
+ "6: rep movsl\n"
" movl %%eax,%0\n"
- "7: rep; movsb\n"
+ "7: rep movsb\n"
"8:\n"
_ASM_EXTABLE_UA(0b, 8b)
_ASM_EXTABLE_UA(1b, 8b)
@@ -293,14 +293,14 @@ do { \
" negl %0\n" \
" andl $7,%0\n" \
" subl %0,%3\n" \
- "4: rep; movsb\n" \
+ "4: rep movsb\n" \
" movl %3,%0\n" \
" shrl $2,%0\n" \
" andl $3,%3\n" \
" .align 2,0x90\n" \
- "0: rep; movsl\n" \
+ "0: rep movsl\n" \
" movl %3,%0\n" \
- "1: rep; movsb\n" \
+ "1: rep movsb\n" \
"2:\n" \
_ASM_EXTABLE_TYPE_REG(4b, 2b, EX_TYPE_UCOPY_LEN1, %3) \
_ASM_EXTABLE_TYPE_REG(0b, 2b, EX_TYPE_UCOPY_LEN4, %3) \
diff --git a/arch/x86/lib/x86-opcode-map.txt b/arch/x86/lib/x86-opcode-map.txt
index f5dd84eb55dc..262f7ca1fb95 100644
--- a/arch/x86/lib/x86-opcode-map.txt
+++ b/arch/x86/lib/x86-opcode-map.txt
@@ -35,7 +35,7 @@
# - (!F3) : the last prefix is not 0xF3 (including non-last prefix case)
# - (66&F2): Both 0x66 and 0xF2 prefixes are specified.
#
-# REX2 Prefix
+# REX2 Prefix Superscripts
# - (!REX2): REX2 is not allowed
# - (REX2): REX2 variant e.g. JMPABS
@@ -147,7 +147,7 @@ AVXcode:
# 0x60 - 0x6f
60: PUSHA/PUSHAD (i64)
61: POPA/POPAD (i64)
-62: BOUND Gv,Ma (i64) | EVEX (Prefix)
+62: BOUND Gv,Ma (i64) | EVEX (Prefix),(o64)
63: ARPL Ew,Gw (i64) | MOVSXD Gv,Ev (o64)
64: SEG=FS (Prefix)
65: SEG=GS (Prefix)
@@ -253,8 +253,8 @@ c0: Grp2 Eb,Ib (1A)
c1: Grp2 Ev,Ib (1A)
c2: RETN Iw (f64)
c3: RETN
-c4: LES Gz,Mp (i64) | VEX+2byte (Prefix)
-c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix)
+c4: LES Gz,Mp (i64) | VEX+2byte (Prefix),(o64)
+c5: LDS Gz,Mp (i64) | VEX+1byte (Prefix),(o64)
c6: Grp11A Eb,Ib (1A)
c7: Grp11B Ev,Iz (1A)
c8: ENTER Iw,Ib
@@ -286,10 +286,10 @@ df: ESC
# Note: "forced64" is Intel CPU behavior: they ignore 0x66 prefix
# in 64-bit mode. AMD CPUs accept 0x66 prefix, it causes RIP truncation
# to 16 bits. In 32-bit mode, 0x66 is accepted by both Intel and AMD.
-e0: LOOPNE/LOOPNZ Jb (f64) (!REX2)
-e1: LOOPE/LOOPZ Jb (f64) (!REX2)
-e2: LOOP Jb (f64) (!REX2)
-e3: JrCXZ Jb (f64) (!REX2)
+e0: LOOPNE/LOOPNZ Jb (f64),(!REX2)
+e1: LOOPE/LOOPZ Jb (f64),(!REX2)
+e2: LOOP Jb (f64),(!REX2)
+e3: JrCXZ Jb (f64),(!REX2)
e4: IN AL,Ib (!REX2)
e5: IN eAX,Ib (!REX2)
e6: OUT Ib,AL (!REX2)
@@ -298,10 +298,10 @@ e7: OUT Ib,eAX (!REX2)
# in "near" jumps and calls is 16-bit. For CALL,
# push of return address is 16-bit wide, RSP is decremented by 2
# but is not truncated to 16 bits, unlike RIP.
-e8: CALL Jz (f64) (!REX2)
-e9: JMP-near Jz (f64) (!REX2)
-ea: JMP-far Ap (i64) (!REX2)
-eb: JMP-short Jb (f64) (!REX2)
+e8: CALL Jz (f64),(!REX2)
+e9: JMP-near Jz (f64),(!REX2)
+ea: JMP-far Ap (i64),(!REX2)
+eb: JMP-short Jb (f64),(!REX2)
ec: IN AL,DX (!REX2)
ed: IN eAX,DX (!REX2)
ee: OUT DX,AL (!REX2)
@@ -478,22 +478,22 @@ AVXcode: 1
7f: movq Qq,Pq | vmovdqa Wx,Vx (66) | vmovdqa32/64 Wx,Vx (66),(evo) | vmovdqu Wx,Vx (F3) | vmovdqu32/64 Wx,Vx (F3),(evo) | vmovdqu8/16 Wx,Vx (F2),(ev)
# 0x0f 0x80-0x8f
# Note: "forced64" is Intel CPU behavior (see comment about CALL insn).
-80: JO Jz (f64) (!REX2)
-81: JNO Jz (f64) (!REX2)
-82: JB/JC/JNAE Jz (f64) (!REX2)
-83: JAE/JNB/JNC Jz (f64) (!REX2)
-84: JE/JZ Jz (f64) (!REX2)
-85: JNE/JNZ Jz (f64) (!REX2)
-86: JBE/JNA Jz (f64) (!REX2)
-87: JA/JNBE Jz (f64) (!REX2)
-88: JS Jz (f64) (!REX2)
-89: JNS Jz (f64) (!REX2)
-8a: JP/JPE Jz (f64) (!REX2)
-8b: JNP/JPO Jz (f64) (!REX2)
-8c: JL/JNGE Jz (f64) (!REX2)
-8d: JNL/JGE Jz (f64) (!REX2)
-8e: JLE/JNG Jz (f64) (!REX2)
-8f: JNLE/JG Jz (f64) (!REX2)
+80: JO Jz (f64),(!REX2)
+81: JNO Jz (f64),(!REX2)
+82: JB/JC/JNAE Jz (f64),(!REX2)
+83: JAE/JNB/JNC Jz (f64),(!REX2)
+84: JE/JZ Jz (f64),(!REX2)
+85: JNE/JNZ Jz (f64),(!REX2)
+86: JBE/JNA Jz (f64),(!REX2)
+87: JA/JNBE Jz (f64),(!REX2)
+88: JS Jz (f64),(!REX2)
+89: JNS Jz (f64),(!REX2)
+8a: JP/JPE Jz (f64),(!REX2)
+8b: JNP/JPO Jz (f64),(!REX2)
+8c: JL/JNGE Jz (f64),(!REX2)
+8d: JNL/JGE Jz (f64),(!REX2)
+8e: JLE/JNG Jz (f64),(!REX2)
+8f: JNLE/JG Jz (f64),(!REX2)
# 0x0f 0x90-0x9f
90: SETO Eb | kmovw/q Vk,Wk | kmovb/d Vk,Wk (66)
91: SETNO Eb | kmovw/q Mv,Vk | kmovb/d Mv,Vk (66)
diff --git a/arch/x86/math-emu/fpu_aux.c b/arch/x86/math-emu/fpu_aux.c
index d62662bdd460..5f253ae406b6 100644
--- a/arch/x86/math-emu/fpu_aux.c
+++ b/arch/x86/math-emu/fpu_aux.c
@@ -53,7 +53,7 @@ void fpstate_init_soft(struct swregs_state *soft)
void finit(void)
{
- fpstate_init_soft(&current->thread.fpu.fpstate->regs.soft);
+ fpstate_init_soft(&x86_task_fpu(current)->fpstate->regs.soft);
}
/*
diff --git a/arch/x86/math-emu/fpu_entry.c b/arch/x86/math-emu/fpu_entry.c
index 91c52ead1226..5034df617740 100644
--- a/arch/x86/math-emu/fpu_entry.c
+++ b/arch/x86/math-emu/fpu_entry.c
@@ -641,7 +641,7 @@ int fpregs_soft_set(struct task_struct *target,
unsigned int pos, unsigned int count,
const void *kbuf, const void __user *ubuf)
{
- struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft;
+ struct swregs_state *s387 = &x86_task_fpu(target)->fpstate->regs.soft;
void *space = s387->st_space;
int ret;
int offset, other, i, tags, regnr, tag, newtop;
@@ -692,7 +692,7 @@ int fpregs_soft_get(struct task_struct *target,
const struct user_regset *regset,
struct membuf to)
{
- struct swregs_state *s387 = &target->thread.fpu.fpstate->regs.soft;
+ struct swregs_state *s387 = &x86_task_fpu(target)->fpstate->regs.soft;
const void *space = s387->st_space;
int offset = (S387->ftop & 7) * 10, other = 80 - offset;
diff --git a/arch/x86/math-emu/fpu_system.h b/arch/x86/math-emu/fpu_system.h
index eec3e4805c75..5e238e930fe3 100644
--- a/arch/x86/math-emu/fpu_system.h
+++ b/arch/x86/math-emu/fpu_system.h
@@ -73,7 +73,7 @@ static inline bool seg_writable(struct desc_struct *d)
return (d->type & SEG_TYPE_EXECUTE_MASK) == SEG_TYPE_WRITABLE;
}
-#define I387 (&current->thread.fpu.fpstate->regs)
+#define I387 (&x86_task_fpu(current)->fpstate->regs)
#define FPU_info (I387->soft.info)
#define FPU_CS (*(unsigned short *) &(FPU_info->regs->cs))
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 32035d5be5a0..5b9908f13dcf 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -3,12 +3,10 @@
KCOV_INSTRUMENT_tlb.o := n
KCOV_INSTRUMENT_mem_encrypt.o := n
KCOV_INSTRUMENT_mem_encrypt_amd.o := n
-KCOV_INSTRUMENT_mem_encrypt_identity.o := n
KCOV_INSTRUMENT_pgprot.o := n
KASAN_SANITIZE_mem_encrypt.o := n
KASAN_SANITIZE_mem_encrypt_amd.o := n
-KASAN_SANITIZE_mem_encrypt_identity.o := n
KASAN_SANITIZE_pgprot.o := n
# Disable KCSAN entirely, because otherwise we get warnings that some functions
@@ -16,12 +14,10 @@ KASAN_SANITIZE_pgprot.o := n
KCSAN_SANITIZE := n
# Avoid recursion by not calling KMSAN hooks for CEA code.
KMSAN_SANITIZE_cpu_entry_area.o := n
-KMSAN_SANITIZE_mem_encrypt_identity.o := n
ifdef CONFIG_FUNCTION_TRACER
CFLAGS_REMOVE_mem_encrypt.o = -pg
CFLAGS_REMOVE_mem_encrypt_amd.o = -pg
-CFLAGS_REMOVE_mem_encrypt_identity.o = -pg
CFLAGS_REMOVE_pgprot.o = -pg
endif
@@ -32,9 +28,6 @@ obj-y += pat/
# Make sure __phys_addr has no stackprotector
CFLAGS_physaddr.o := -fno-stack-protector
-CFLAGS_mem_encrypt_identity.o := -fno-stack-protector
-
-CFLAGS_fault.o := -I $(src)/../include/asm/trace
obj-$(CONFIG_X86_32) += pgtable_32.o iomap_32.o
@@ -52,7 +45,7 @@ obj-$(CONFIG_MMIOTRACE) += mmiotrace.o
mmiotrace-y := kmmio.o pf_in.o mmio-mod.o
obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o
-obj-$(CONFIG_NUMA) += numa.o numa_$(BITS).o
+obj-$(CONFIG_NUMA) += numa.o
obj-$(CONFIG_AMD_NUMA) += amdtopology.o
obj-$(CONFIG_ACPI_NUMA) += srat.o
@@ -63,5 +56,4 @@ obj-$(CONFIG_MITIGATION_PAGE_TABLE_ISOLATION) += pti.o
obj-$(CONFIG_X86_MEM_ENCRYPT) += mem_encrypt.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_amd.o
-obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_identity.o
obj-$(CONFIG_AMD_MEM_ENCRYPT) += mem_encrypt_boot.o
diff --git a/arch/x86/mm/amdtopology.c b/arch/x86/mm/amdtopology.c
index 628833afee37..f980b0eb0105 100644
--- a/arch/x86/mm/amdtopology.c
+++ b/arch/x86/mm/amdtopology.c
@@ -25,7 +25,7 @@
#include <asm/numa.h>
#include <asm/mpspec.h>
#include <asm/apic.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
static unsigned char __initdata nodeids[8];
diff --git a/arch/x86/mm/dump_pagetables.c b/arch/x86/mm/dump_pagetables.c
index 89079ea73e65..a4700ef6eb64 100644
--- a/arch/x86/mm/dump_pagetables.c
+++ b/arch/x86/mm/dump_pagetables.c
@@ -266,6 +266,32 @@ static void effective_prot(struct ptdump_state *pt_st, int level, u64 val)
st->prot_levels[level] = effective;
}
+static void effective_prot_pte(struct ptdump_state *st, pte_t pte)
+{
+ effective_prot(st, 4, pte_val(pte));
+}
+
+static void effective_prot_pmd(struct ptdump_state *st, pmd_t pmd)
+{
+ effective_prot(st, 3, pmd_val(pmd));
+}
+
+static void effective_prot_pud(struct ptdump_state *st, pud_t pud)
+{
+ effective_prot(st, 2, pud_val(pud));
+}
+
+static void effective_prot_p4d(struct ptdump_state *st, p4d_t p4d)
+{
+ effective_prot(st, 1, p4d_val(p4d));
+}
+
+static void effective_prot_pgd(struct ptdump_state *st, pgd_t pgd)
+{
+ effective_prot(st, 0, pgd_val(pgd));
+}
+
+
/*
* This function gets called on a break in a continuous series
* of PTE entries; the next one is different so we need to
@@ -362,6 +388,38 @@ static void note_page(struct ptdump_state *pt_st, unsigned long addr, int level,
}
}
+static void note_page_pte(struct ptdump_state *pt_st, unsigned long addr, pte_t pte)
+{
+ note_page(pt_st, addr, 4, pte_val(pte));
+}
+
+static void note_page_pmd(struct ptdump_state *pt_st, unsigned long addr, pmd_t pmd)
+{
+ note_page(pt_st, addr, 3, pmd_val(pmd));
+}
+
+static void note_page_pud(struct ptdump_state *pt_st, unsigned long addr, pud_t pud)
+{
+ note_page(pt_st, addr, 2, pud_val(pud));
+}
+
+static void note_page_p4d(struct ptdump_state *pt_st, unsigned long addr, p4d_t p4d)
+{
+ note_page(pt_st, addr, 1, p4d_val(p4d));
+}
+
+static void note_page_pgd(struct ptdump_state *pt_st, unsigned long addr, pgd_t pgd)
+{
+ note_page(pt_st, addr, 0, pgd_val(pgd));
+}
+
+static void note_page_flush(struct ptdump_state *pt_st)
+{
+ pte_t pte_zero = {0};
+
+ note_page(pt_st, 0, -1, pte_val(pte_zero));
+}
+
bool ptdump_walk_pgd_level_core(struct seq_file *m,
struct mm_struct *mm, pgd_t *pgd,
bool checkwx, bool dmesg)
@@ -378,8 +436,17 @@ bool ptdump_walk_pgd_level_core(struct seq_file *m,
struct pg_state st = {
.ptdump = {
- .note_page = note_page,
- .effective_prot = effective_prot,
+ .note_page_pte = note_page_pte,
+ .note_page_pmd = note_page_pmd,
+ .note_page_pud = note_page_pud,
+ .note_page_p4d = note_page_p4d,
+ .note_page_pgd = note_page_pgd,
+ .note_page_flush = note_page_flush,
+ .effective_prot_pte = effective_prot_pte,
+ .effective_prot_pmd = effective_prot_pmd,
+ .effective_prot_pud = effective_prot_pud,
+ .effective_prot_p4d = effective_prot_p4d,
+ .effective_prot_pgd = effective_prot_pgd,
.range = ptdump_ranges
},
.level = -1,
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 51986e8a9d35..2fdc1f1f5adb 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -111,7 +111,7 @@ static bool ex_handler_sgx(const struct exception_table_entry *fixup,
/*
* Handler for when we fail to restore a task's FPU state. We should never get
- * here because the FPU state of a task using the FPU (task->thread.fpu.state)
+ * here because the FPU state of a task using the FPU (struct fpu::fpstate)
* should always be valid. However, past bugs have allowed userspace to set
* reserved bits in the XSAVE area using PTRACE_SETREGSET or sys_rt_sigreturn().
* These caused XRSTOR to fail when switching to the task, leaking the FPU
@@ -122,13 +122,12 @@ static bool ex_handler_sgx(const struct exception_table_entry *fixup,
static bool ex_handler_fprestore(const struct exception_table_entry *fixup,
struct pt_regs *regs)
{
- regs->ip = ex_fixup_addr(fixup);
-
WARN_ONCE(1, "Bad FPU state detected at %pB, reinitializing FPU registers.",
(void *)instruction_pointer(regs));
fpu_reset_from_exception_fixup();
- return true;
+
+ return ex_handler_default(fixup, regs);
}
/*
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 296d294142c8..998bd807fc7b 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -13,7 +13,6 @@
#include <linux/mmiotrace.h> /* kmmio_handler, ... */
#include <linux/perf_event.h> /* perf_sw_event */
#include <linux/hugetlb.h> /* hstate_index_to_shift */
-#include <linux/prefetch.h> /* prefetchw */
#include <linux/context_tracking.h> /* exception_enter(), ... */
#include <linux/uaccess.h> /* faulthandler_disabled() */
#include <linux/efi.h> /* efi_crash_gracefully_on_page_fault()*/
@@ -38,7 +37,7 @@
#include <asm/sev.h> /* snp_dump_hva_rmpentry() */
#define CREATE_TRACE_POINTS
-#include <asm/trace/exceptions.h>
+#include <trace/events/exceptions.h>
/*
* Returns 0 if mmiotrace is disabled, or if the fault is not
@@ -1455,9 +1454,6 @@ static __always_inline void
trace_page_fault_entries(struct pt_regs *regs, unsigned long error_code,
unsigned long address)
{
- if (!trace_pagefault_enabled())
- return;
-
if (user_mode(regs))
trace_page_fault_user(address, regs, error_code);
else
@@ -1496,8 +1492,6 @@ DEFINE_IDTENTRY_RAW_ERRORCODE(exc_page_fault)
address = cpu_feature_enabled(X86_FEATURE_FRED) ? fred_event_data(regs) : read_cr2();
- prefetchw(&current->mm->mmap_lock);
-
/*
* KVM uses #PF vector to deliver 'page not present' events to guests
* (asynchronous page fault mechanism). The event happens when a
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index bfa444a7dbb0..bb57e93b4caf 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -28,6 +28,7 @@
#include <asm/text-patching.h>
#include <asm/memtype.h>
#include <asm/paravirt.h>
+#include <asm/mmu_context.h>
/*
* We need to define the tracepoints somewhere, and tlb.c
@@ -173,11 +174,7 @@ __ref void *alloc_low_pages(unsigned int num)
* randomization is enabled.
*/
-#ifndef CONFIG_X86_5LEVEL
-#define INIT_PGD_PAGE_TABLES 3
-#else
#define INIT_PGD_PAGE_TABLES 4
-#endif
#ifndef CONFIG_RANDOMIZE_MEMORY
#define INIT_PGD_PAGE_COUNT (2 * INIT_PGD_PAGE_TABLES)
@@ -824,31 +821,33 @@ void __init poking_init(void)
spinlock_t *ptl;
pte_t *ptep;
- poking_mm = mm_alloc();
- BUG_ON(!poking_mm);
+ text_poke_mm = mm_alloc();
+ BUG_ON(!text_poke_mm);
/* Xen PV guests need the PGD to be pinned. */
- paravirt_enter_mmap(poking_mm);
+ paravirt_enter_mmap(text_poke_mm);
+
+ set_notrack_mm(text_poke_mm);
/*
* Randomize the poking address, but make sure that the following page
* will be mapped at the same PMD. We need 2 pages, so find space for 3,
* and adjust the address if the PMD ends after the first one.
*/
- poking_addr = TASK_UNMAPPED_BASE;
+ text_poke_mm_addr = TASK_UNMAPPED_BASE;
if (IS_ENABLED(CONFIG_RANDOMIZE_BASE))
- poking_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) %
+ text_poke_mm_addr += (kaslr_get_random_long("Poking") & PAGE_MASK) %
(TASK_SIZE - TASK_UNMAPPED_BASE - 3 * PAGE_SIZE);
- if (((poking_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
- poking_addr += PAGE_SIZE;
+ if (((text_poke_mm_addr + PAGE_SIZE) & ~PMD_MASK) == 0)
+ text_poke_mm_addr += PAGE_SIZE;
/*
* We need to trigger the allocation of the page-tables that will be
* needed for poking now. Later, poking may be performed in an atomic
* section, which might cause allocation to fail.
*/
- ptep = get_locked_pte(poking_mm, poking_addr, &ptl);
+ ptep = get_locked_pte(text_poke_mm, text_poke_mm_addr, &ptl);
BUG_ON(!ptep);
pte_unmap_unlock(ptep, ptl);
}
@@ -1064,13 +1063,9 @@ unsigned long arch_max_swapfile_size(void)
static struct execmem_info execmem_info __ro_after_init;
#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX
-void execmem_fill_trapping_insns(void *ptr, size_t size, bool writeable)
+void execmem_fill_trapping_insns(void *ptr, size_t size)
{
- /* fill memory with INT3 instructions */
- if (writeable)
- memset(ptr, INT3_INSN_OPCODE, size);
- else
- text_poke_set(ptr, INT3_INSN_OPCODE, size);
+ memset(ptr, INT3_INSN_OPCODE, size);
}
#endif
@@ -1103,7 +1098,21 @@ struct execmem_info __init *execmem_arch_setup(void)
.pgprot = pgprot,
.alignment = MODULE_ALIGN,
},
- [EXECMEM_KPROBES ... EXECMEM_BPF] = {
+ [EXECMEM_KPROBES] = {
+ .flags = flags,
+ .start = start,
+ .end = MODULES_END,
+ .pgprot = PAGE_KERNEL_ROX,
+ .alignment = MODULE_ALIGN,
+ },
+ [EXECMEM_FTRACE] = {
+ .flags = flags,
+ .start = start,
+ .end = MODULES_END,
+ .pgprot = pgprot,
+ .alignment = MODULE_ALIGN,
+ },
+ [EXECMEM_BPF] = {
.flags = EXECMEM_KASAN_SHADOW,
.start = start,
.end = MODULES_END,
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index bb8d99e717b9..8a34fff6ab2b 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -30,7 +30,6 @@
#include <linux/initrd.h>
#include <linux/cpumask.h>
#include <linux/gfp.h>
-#include <linux/execmem.h>
#include <asm/asm.h>
#include <asm/bios_ebda.h>
@@ -613,7 +612,6 @@ void __init find_low_pfn_range(void)
highmem_pfn_init();
}
-#ifndef CONFIG_NUMA
void __init initmem_init(void)
{
#ifdef CONFIG_HIGHMEM
@@ -634,12 +632,6 @@ void __init initmem_init(void)
printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
pages_to_mb(max_low_pfn));
- setup_bootmem_allocator();
-}
-#endif /* !CONFIG_NUMA */
-
-void __init setup_bootmem_allocator(void)
-{
printk(KERN_INFO " mapped low ram: 0 - %08lx\n",
max_pfn_mapped<<PAGE_SHIFT);
printk(KERN_INFO " low ram: 0 - %08lx\n", max_low_pfn<<PAGE_SHIFT);
@@ -756,8 +748,6 @@ void mark_rodata_ro(void)
pr_info("Write protecting kernel text and read-only data: %luk\n",
size >> 10);
- execmem_cache_make_ro();
-
kernel_set_to_readonly = 1;
#ifdef CONFIG_CPA_DEBUG
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 949a447f75ec..76e33bd7c556 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -34,7 +34,6 @@
#include <linux/gfp.h>
#include <linux/kcore.h>
#include <linux/bootmem_info.h>
-#include <linux/execmem.h>
#include <asm/processor.h>
#include <asm/bios_ebda.h>
@@ -806,12 +805,17 @@ kernel_physical_mapping_change(unsigned long paddr_start,
}
#ifndef CONFIG_NUMA
-void __init initmem_init(void)
+static __always_inline void x86_numa_init(void)
{
memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
}
#endif
+void __init initmem_init(void)
+{
+ x86_numa_init();
+}
+
void __init paging_init(void)
{
sparse_init();
@@ -828,7 +832,6 @@ void __init paging_init(void)
zone_sizes_init();
}
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
#define PAGE_UNUSED 0xFD
/*
@@ -927,7 +930,6 @@ static void __meminit vmemmap_use_new_sub_pmd(unsigned long start, unsigned long
if (!IS_ALIGNED(end, PMD_SIZE))
unused_pmd_start = end;
}
-#endif
/*
* Memory hotplug specific functions
@@ -1147,16 +1149,13 @@ remove_pmd_table(pmd_t *pmd_start, unsigned long addr, unsigned long end,
pmd_clear(pmd);
spin_unlock(&init_mm.page_table_lock);
pages++;
- }
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
- else if (vmemmap_pmd_is_unused(addr, next)) {
+ } else if (vmemmap_pmd_is_unused(addr, next)) {
free_hugepage_table(pmd_page(*pmd),
altmap);
spin_lock(&init_mm.page_table_lock);
pmd_clear(pmd);
spin_unlock(&init_mm.page_table_lock);
}
-#endif
continue;
}
@@ -1392,8 +1391,6 @@ void mark_rodata_ro(void)
(end - start) >> 10);
set_memory_ro(start, (end - start) >> PAGE_SHIFT);
- execmem_cache_make_ro();
-
kernel_set_to_readonly = 1;
/*
@@ -1467,16 +1464,21 @@ static unsigned long probe_memory_block_size(void)
}
/*
- * Use max block size to minimize overhead on bare metal, where
- * alignment for memory hotplug isn't a concern.
+ * When hotplug alignment is not a concern, maximize blocksize
+ * to minimize overhead. Otherwise, align to the lesser of advice
+ * alignment and end of memory alignment.
*/
- if (!boot_cpu_has(X86_FEATURE_HYPERVISOR)) {
+ bz = memory_block_advised_max_size();
+ if (!bz) {
bz = MAX_BLOCK_SIZE;
- goto done;
+ if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR))
+ goto done;
+ } else {
+ bz = max(min(bz, MAX_BLOCK_SIZE), MIN_MEMORY_BLOCK_SIZE);
}
/* Find the largest allowed block size that aligns to memory end */
- for (bz = MAX_BLOCK_SIZE; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
+ for (; bz > MIN_MEMORY_BLOCK_SIZE; bz >>= 1) {
if (IS_ALIGNED(boot_mem_end, bz))
break;
}
@@ -1495,7 +1497,6 @@ unsigned long memory_block_size_bytes(void)
return memory_block_size_probed;
}
-#ifdef CONFIG_SPARSEMEM_VMEMMAP
/*
* Initialise the sparsemem vmemmap using huge-pages at the PMD level.
*/
@@ -1642,4 +1643,3 @@ void __meminit vmemmap_populate_print_last(void)
node_start = 0;
}
}
-#endif
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index 331e101bf801..12c8180ca1ba 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -71,7 +71,7 @@ int ioremap_change_attr(unsigned long vaddr, unsigned long size,
static unsigned int __ioremap_check_ram(struct resource *res)
{
unsigned long start_pfn, stop_pfn;
- unsigned long i;
+ unsigned long pfn;
if ((res->flags & IORESOURCE_SYSTEM_RAM) != IORESOURCE_SYSTEM_RAM)
return 0;
@@ -79,9 +79,8 @@ static unsigned int __ioremap_check_ram(struct resource *res)
start_pfn = (res->start + PAGE_SIZE - 1) >> PAGE_SHIFT;
stop_pfn = (res->end + 1) >> PAGE_SHIFT;
if (stop_pfn > start_pfn) {
- for (i = 0; i < (stop_pfn - start_pfn); ++i)
- if (pfn_valid(start_pfn + i) &&
- !PageReserved(pfn_to_page(start_pfn + i)))
+ for_each_valid_pfn(pfn, start_pfn, stop_pfn)
+ if (!PageReserved(pfn_to_page(pfn)))
return IORES_MAP_SYSTEM_RAM;
}
diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
index 7490ff6d83b1..faf3a13fb6ba 100644
--- a/arch/x86/mm/mem_encrypt_amd.c
+++ b/arch/x86/mm/mem_encrypt_amd.c
@@ -40,7 +40,9 @@
* section is later cleared.
*/
u64 sme_me_mask __section(".data") = 0;
+SYM_PIC_ALIAS(sme_me_mask);
u64 sev_status __section(".data") = 0;
+SYM_PIC_ALIAS(sev_status);
u64 sev_check_data __section(".data") = 0;
EXPORT_SYMBOL(sme_me_mask);
diff --git a/arch/x86/mm/mm_internal.h b/arch/x86/mm/mm_internal.h
index 3f37b5c80bb3..097aadc250f7 100644
--- a/arch/x86/mm/mm_internal.h
+++ b/arch/x86/mm/mm_internal.h
@@ -25,4 +25,8 @@ void update_cache_mode_entry(unsigned entry, enum page_cache_mode cache);
extern unsigned long tlb_single_page_flush_ceiling;
+#ifdef CONFIG_NUMA
+void __init x86_numa_init(void);
+#endif
+
#endif /* __X86_MM_INTERNAL_H */
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index 64e5cdb2460a..c24890c40138 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -18,9 +18,10 @@
#include <asm/e820/api.h>
#include <asm/proto.h>
#include <asm/dma.h>
-#include <asm/amd_nb.h>
+#include <asm/numa.h>
+#include <asm/amd/nb.h>
-#include "numa_internal.h"
+#include "mm_internal.h"
int numa_off;
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
deleted file mode 100644
index 65fda406e6f2..000000000000
--- a/arch/x86/mm/numa_32.c
+++ /dev/null
@@ -1,61 +0,0 @@
-/*
- * Written by: Patricia Gaughen <gone@us.ibm.com>, IBM Corporation
- * August 2002: added remote node KVA remap - Martin J. Bligh
- *
- * Copyright (C) 2002, IBM Corp.
- *
- * All rights reserved.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation; either version 2 of the License, or
- * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
- * NON INFRINGEMENT. See the GNU General Public License for more
- * details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/memblock.h>
-#include <linux/init.h>
-#include <linux/vmalloc.h>
-#include <asm/pgtable_areas.h>
-
-#include "numa_internal.h"
-
-extern unsigned long highend_pfn, highstart_pfn;
-
-void __init initmem_init(void)
-{
- x86_numa_init();
-
-#ifdef CONFIG_HIGHMEM
- highstart_pfn = highend_pfn = max_pfn;
- if (max_pfn > max_low_pfn)
- highstart_pfn = max_low_pfn;
- printk(KERN_NOTICE "%ldMB HIGHMEM available.\n",
- pages_to_mb(highend_pfn - highstart_pfn));
- high_memory = (void *) __va(highstart_pfn * PAGE_SIZE - 1) + 1;
-#else
- high_memory = (void *) __va(max_low_pfn * PAGE_SIZE - 1) + 1;
-#endif
- printk(KERN_NOTICE "%ldMB LOWMEM available.\n",
- pages_to_mb(max_low_pfn));
- printk(KERN_DEBUG "max_low_pfn = %lx, highstart_pfn = %lx\n",
- max_low_pfn, highstart_pfn);
-
- printk(KERN_DEBUG "Low memory ends at vaddr %08lx\n",
- (ulong) pfn_to_kaddr(max_low_pfn));
-
- printk(KERN_DEBUG "High memory starts at vaddr %08lx\n",
- (ulong) pfn_to_kaddr(highstart_pfn));
-
- __vmalloc_start_set = true;
- setup_bootmem_allocator();
-}
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
deleted file mode 100644
index 59d80160fa5a..000000000000
--- a/arch/x86/mm/numa_64.c
+++ /dev/null
@@ -1,13 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Generic VM initialization for x86-64 NUMA setups.
- * Copyright 2002,2003 Andi Kleen, SuSE Labs.
- */
-#include <linux/memblock.h>
-
-#include "numa_internal.h"
-
-void __init initmem_init(void)
-{
- x86_numa_init();
-}
diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h
deleted file mode 100644
index 11e1ff370c10..000000000000
--- a/arch/x86/mm/numa_internal.h
+++ /dev/null
@@ -1,10 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __X86_MM_NUMA_INTERNAL_H
-#define __X86_MM_NUMA_INTERNAL_H
-
-#include <linux/types.h>
-#include <asm/numa.h>
-
-void __init x86_numa_init(void);
-
-#endif /* __X86_MM_NUMA_INTERNAL_H */
diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 72d8cbc61158..c09284302dd3 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -36,8 +36,8 @@
#include <linux/debugfs.h>
#include <linux/ioport.h>
#include <linux/kernel.h>
-#include <linux/pfn_t.h>
#include <linux/slab.h>
+#include <linux/io.h>
#include <linux/mm.h>
#include <linux/highmem.h>
#include <linux/fs.h>
@@ -232,7 +232,7 @@ void pat_cpu_init(void)
panic("x86/PAT: PAT enabled, but not supported by secondary CPU\n");
}
- wrmsrl(MSR_IA32_CR_PAT, pat_msr_val);
+ wrmsrq(MSR_IA32_CR_PAT, pat_msr_val);
__flush_tlb_all();
}
@@ -256,7 +256,7 @@ void __init pat_bp_init(void)
if (!cpu_feature_enabled(X86_FEATURE_PAT))
pat_disable("PAT not supported by the CPU.");
else
- rdmsrl(MSR_IA32_CR_PAT, pat_msr_val);
+ rdmsrq(MSR_IA32_CR_PAT, pat_msr_val);
if (!pat_msr_val) {
pat_disable("PAT support disabled by the firmware.");
@@ -682,6 +682,7 @@ static enum page_cache_mode lookup_memtype(u64 paddr)
/**
* pat_pfn_immune_to_uc_mtrr - Check whether the PAT memory type
* of @pfn cannot be overridden by UC MTRR memory type.
+ * @pfn: The page frame number to check.
*
* Only to be called when PAT is enabled.
*
@@ -773,46 +774,27 @@ pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
return vma_prot;
}
-#ifdef CONFIG_STRICT_DEVMEM
-/* This check is done in drivers/char/mem.c in case of STRICT_DEVMEM */
-static inline int range_is_allowed(unsigned long pfn, unsigned long size)
+static inline void pgprot_set_cachemode(pgprot_t *prot, enum page_cache_mode pcm)
{
- return 1;
-}
-#else
-/* This check is needed to avoid cache aliasing when PAT is enabled */
-static inline int range_is_allowed(unsigned long pfn, unsigned long size)
-{
- u64 from = ((u64)pfn) << PAGE_SHIFT;
- u64 to = from + size;
- u64 cursor = from;
-
- if (!pat_enabled())
- return 1;
-
- while (cursor < to) {
- if (!devmem_is_allowed(pfn))
- return 0;
- cursor += PAGE_SIZE;
- pfn++;
- }
- return 1;
+ *prot = __pgprot((pgprot_val(*prot) & ~_PAGE_CACHE_MASK) |
+ cachemode2protval(pcm));
}
-#endif /* CONFIG_STRICT_DEVMEM */
int phys_mem_access_prot_allowed(struct file *file, unsigned long pfn,
unsigned long size, pgprot_t *vma_prot)
{
enum page_cache_mode pcm = _PAGE_CACHE_MODE_WB;
+ if (!pat_enabled())
+ return 1;
+
if (!range_is_allowed(pfn, size))
return 0;
if (file->f_flags & O_DSYNC)
pcm = _PAGE_CACHE_MODE_UC_MINUS;
- *vma_prot = __pgprot((pgprot_val(*vma_prot) & ~_PAGE_CACHE_MASK) |
- cachemode2protval(pcm));
+ pgprot_set_cachemode(vma_prot, pcm);
return 1;
}
@@ -853,8 +835,7 @@ int memtype_kernel_map_sync(u64 base, unsigned long size,
* Reserved non RAM regions only and after successful memtype_reserve,
* this func also keeps identity mapping (if any) in sync with this new prot.
*/
-static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
- int strict_prot)
+static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot)
{
int is_ram = 0;
int ret;
@@ -880,9 +861,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
(unsigned long long)paddr,
(unsigned long long)(paddr + size - 1),
cattr_name(pcm));
- *vma_prot = __pgprot((pgprot_val(*vma_prot) &
- (~_PAGE_CACHE_MASK)) |
- cachemode2protval(pcm));
+ pgprot_set_cachemode(vma_prot, pcm);
}
return 0;
}
@@ -892,8 +871,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
return ret;
if (pcm != want_pcm) {
- if (strict_prot ||
- !is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
+ if (!is_new_memtype_allowed(paddr, size, want_pcm, pcm)) {
memtype_free(paddr, paddr + size);
pr_err("x86/PAT: %s:%d map pfn expected mapping type %s for [mem %#010Lx-%#010Lx], got %s\n",
current->comm, current->pid,
@@ -903,13 +881,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
cattr_name(pcm));
return -EINVAL;
}
- /*
- * We allow returning different type than the one requested in
- * non strict case.
- */
- *vma_prot = __pgprot((pgprot_val(*vma_prot) &
- (~_PAGE_CACHE_MASK)) |
- cachemode2protval(pcm));
+ pgprot_set_cachemode(vma_prot, pcm);
}
if (memtype_kernel_map_sync(paddr, size, pcm) < 0) {
@@ -932,124 +904,14 @@ static void free_pfn_range(u64 paddr, unsigned long size)
memtype_free(paddr, paddr + size);
}
-static int follow_phys(struct vm_area_struct *vma, unsigned long *prot,
- resource_size_t *phys)
-{
- struct follow_pfnmap_args args = { .vma = vma, .address = vma->vm_start };
-
- if (follow_pfnmap_start(&args))
- return -EINVAL;
-
- /* Never return PFNs of anon folios in COW mappings. */
- if (!args.special) {
- follow_pfnmap_end(&args);
- return -EINVAL;
- }
-
- *prot = pgprot_val(args.pgprot);
- *phys = (resource_size_t)args.pfn << PAGE_SHIFT;
- follow_pfnmap_end(&args);
- return 0;
-}
-
-static int get_pat_info(struct vm_area_struct *vma, resource_size_t *paddr,
- pgprot_t *pgprot)
-{
- unsigned long prot;
-
- VM_WARN_ON_ONCE(!(vma->vm_flags & VM_PAT));
-
- /*
- * We need the starting PFN and cachemode used for track_pfn_remap()
- * that covered the whole VMA. For most mappings, we can obtain that
- * information from the page tables. For COW mappings, we might now
- * suddenly have anon folios mapped and follow_phys() will fail.
- *
- * Fallback to using vma->vm_pgoff, see remap_pfn_range_notrack(), to
- * detect the PFN. If we need the cachemode as well, we're out of luck
- * for now and have to fail fork().
- */
- if (!follow_phys(vma, &prot, paddr)) {
- if (pgprot)
- *pgprot = __pgprot(prot);
- return 0;
- }
- if (is_cow_mapping(vma->vm_flags)) {
- if (pgprot)
- return -EINVAL;
- *paddr = (resource_size_t)vma->vm_pgoff << PAGE_SHIFT;
- return 0;
- }
- WARN_ON_ONCE(1);
- return -EINVAL;
-}
-
-int track_pfn_copy(struct vm_area_struct *dst_vma,
- struct vm_area_struct *src_vma, unsigned long *pfn)
-{
- const unsigned long vma_size = src_vma->vm_end - src_vma->vm_start;
- resource_size_t paddr;
- pgprot_t pgprot;
- int rc;
-
- if (!(src_vma->vm_flags & VM_PAT))
- return 0;
-
- /*
- * Duplicate the PAT information for the dst VMA based on the src
- * VMA.
- */
- if (get_pat_info(src_vma, &paddr, &pgprot))
- return -EINVAL;
- rc = reserve_pfn_range(paddr, vma_size, &pgprot, 1);
- if (rc)
- return rc;
-
- /* Reservation for the destination VMA succeeded. */
- vm_flags_set(dst_vma, VM_PAT);
- *pfn = PHYS_PFN(paddr);
- return 0;
-}
-
-void untrack_pfn_copy(struct vm_area_struct *dst_vma, unsigned long pfn)
-{
- untrack_pfn(dst_vma, pfn, dst_vma->vm_end - dst_vma->vm_start, true);
- /*
- * Reservation was freed, any copied page tables will get cleaned
- * up later, but without getting PAT involved again.
- */
-}
-
-/*
- * prot is passed in as a parameter for the new mapping. If the vma has
- * a linear pfn mapping for the entire range, or no vma is provided,
- * reserve the entire pfn + size range with single reserve_pfn_range
- * call.
- */
-int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
- unsigned long pfn, unsigned long addr, unsigned long size)
+int pfnmap_setup_cachemode(unsigned long pfn, unsigned long size, pgprot_t *prot)
{
resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
enum page_cache_mode pcm;
- /* reserve the whole chunk starting from paddr */
- if (!vma || (addr == vma->vm_start
- && size == (vma->vm_end - vma->vm_start))) {
- int ret;
-
- ret = reserve_pfn_range(paddr, size, prot, 0);
- if (ret == 0 && vma)
- vm_flags_set(vma, VM_PAT);
- return ret;
- }
-
if (!pat_enabled())
return 0;
- /*
- * For anything smaller than the vma size we set prot based on the
- * lookup.
- */
pcm = lookup_memtype(paddr);
/* Check memtype for the remaining pages */
@@ -1060,70 +922,35 @@ int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
return -EINVAL;
}
- *prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
- cachemode2protval(pcm));
-
+ pgprot_set_cachemode(prot, pcm);
return 0;
}
-void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot, pfn_t pfn)
+int pfnmap_track(unsigned long pfn, unsigned long size, pgprot_t *prot)
{
- enum page_cache_mode pcm;
-
- if (!pat_enabled())
- return;
+ const resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
- /* Set prot based on lookup */
- pcm = lookup_memtype(pfn_t_to_phys(pfn));
- *prot = __pgprot((pgprot_val(*prot) & (~_PAGE_CACHE_MASK)) |
- cachemode2protval(pcm));
+ return reserve_pfn_range(paddr, size, prot);
}
-/*
- * untrack_pfn is called while unmapping a pfnmap for a region.
- * untrack can be called for a specific region indicated by pfn and size or
- * can be for the entire vma (in which case pfn, size are zero).
- */
-void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
- unsigned long size, bool mm_wr_locked)
+void pfnmap_untrack(unsigned long pfn, unsigned long size)
{
- resource_size_t paddr;
-
- if (vma && !(vma->vm_flags & VM_PAT))
- return;
+ const resource_size_t paddr = (resource_size_t)pfn << PAGE_SHIFT;
- /* free the chunk starting from pfn or the whole chunk */
- paddr = (resource_size_t)pfn << PAGE_SHIFT;
- if (!paddr && !size) {
- if (get_pat_info(vma, &paddr, NULL))
- return;
- size = vma->vm_end - vma->vm_start;
- }
free_pfn_range(paddr, size);
- if (vma) {
- if (mm_wr_locked)
- vm_flags_clear(vma, VM_PAT);
- else
- __vm_flags_mod(vma, 0, VM_PAT);
- }
-}
-
-void untrack_pfn_clear(struct vm_area_struct *vma)
-{
- vm_flags_clear(vma, VM_PAT);
}
pgprot_t pgprot_writecombine(pgprot_t prot)
{
- return __pgprot(pgprot_val(prot) |
- cachemode2protval(_PAGE_CACHE_MODE_WC));
+ pgprot_set_cachemode(&prot, _PAGE_CACHE_MODE_WC);
+ return prot;
}
EXPORT_SYMBOL_GPL(pgprot_writecombine);
pgprot_t pgprot_writethrough(pgprot_t prot)
{
- return __pgprot(pgprot_val(prot) |
- cachemode2protval(_PAGE_CACHE_MODE_WT));
+ pgprot_set_cachemode(&prot, _PAGE_CACHE_MODE_WT);
+ return prot;
}
EXPORT_SYMBOL_GPL(pgprot_writethrough);
diff --git a/arch/x86/mm/pat/memtype_interval.c b/arch/x86/mm/pat/memtype_interval.c
index 645613d59942..e5844ed1311e 100644
--- a/arch/x86/mm/pat/memtype_interval.c
+++ b/arch/x86/mm/pat/memtype_interval.c
@@ -49,32 +49,6 @@ INTERVAL_TREE_DEFINE(struct memtype, rb, u64, subtree_max_end,
static struct rb_root_cached memtype_rbroot = RB_ROOT_CACHED;
-enum {
- MEMTYPE_EXACT_MATCH = 0,
- MEMTYPE_END_MATCH = 1
-};
-
-static struct memtype *memtype_match(u64 start, u64 end, int match_type)
-{
- struct memtype *entry_match;
-
- entry_match = interval_iter_first(&memtype_rbroot, start, end-1);
-
- while (entry_match != NULL && entry_match->start < end) {
- if ((match_type == MEMTYPE_EXACT_MATCH) &&
- (entry_match->start == start) && (entry_match->end == end))
- return entry_match;
-
- if ((match_type == MEMTYPE_END_MATCH) &&
- (entry_match->start < start) && (entry_match->end == end))
- return entry_match;
-
- entry_match = interval_iter_next(entry_match, start, end-1);
- }
-
- return NULL; /* Returns NULL if there is no match */
-}
-
static int memtype_check_conflict(u64 start, u64 end,
enum page_cache_mode reqtype,
enum page_cache_mode *newtype)
@@ -130,35 +104,16 @@ int memtype_check_insert(struct memtype *entry_new, enum page_cache_mode *ret_ty
struct memtype *memtype_erase(u64 start, u64 end)
{
- struct memtype *entry_old;
-
- /*
- * Since the memtype_rbroot tree allows overlapping ranges,
- * memtype_erase() checks with EXACT_MATCH first, i.e. free
- * a whole node for the munmap case. If no such entry is found,
- * it then checks with END_MATCH, i.e. shrink the size of a node
- * from the end for the mremap case.
- */
- entry_old = memtype_match(start, end, MEMTYPE_EXACT_MATCH);
- if (!entry_old) {
- entry_old = memtype_match(start, end, MEMTYPE_END_MATCH);
- if (!entry_old)
- return ERR_PTR(-EINVAL);
+ struct memtype *entry = interval_iter_first(&memtype_rbroot, start, end - 1);
+
+ while (entry && entry->start < end) {
+ if (entry->start == start && entry->end == end) {
+ interval_remove(entry, &memtype_rbroot);
+ return entry;
+ }
+ entry = interval_iter_next(entry, start, end - 1);
}
-
- if (entry_old->start == start) {
- /* munmap: erase this node */
- interval_remove(entry_old, &memtype_rbroot);
- } else {
- /* mremap: update the end value of this node */
- interval_remove(entry_old, &memtype_rbroot);
- entry_old->end = start;
- interval_insert(entry_old, &memtype_rbroot);
-
- return NULL;
- }
-
- return entry_old;
+ return ERR_PTR(-EINVAL);
}
struct memtype *memtype_lookup(u64 addr)
diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
index def3d9284254..8834c76f91c9 100644
--- a/arch/x86/mm/pat/set_memory.c
+++ b/arch/x86/mm/pat/set_memory.c
@@ -889,7 +889,7 @@ static void __set_pmd_pte(pte_t *kpte, unsigned long address, pte_t pte)
/* change init_mm */
set_pte_atomic(kpte, pte);
#ifdef CONFIG_X86_32
- if (!SHARED_KERNEL_PMD) {
+ {
struct page *page;
list_for_each_entry(page, &pgd_list, lru) {
@@ -1257,6 +1257,9 @@ static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
pgprot_t pgprot;
int i = 0;
+ if (!cpu_feature_enabled(X86_FEATURE_PSE))
+ return 0;
+
addr &= PMD_MASK;
pte = pte_offset_kernel(pmd, addr);
first = *pte;
@@ -1293,7 +1296,7 @@ static int collapse_pmd_page(pmd_t *pmd, unsigned long addr,
/* Queue the page table to be freed after TLB flush */
list_add(&page_ptdesc(pmd_page(old_pmd))->pt_list, pgtables);
- if (IS_ENABLED(CONFIG_X86_32) && !SHARED_KERNEL_PMD) {
+ if (IS_ENABLED(CONFIG_X86_32)) {
struct page *page;
/* Update all PGD tables to use the same large page */
@@ -2148,6 +2151,19 @@ static inline int cpa_clear_pages_array(struct page **pages, int numpages,
CPA_PAGES_ARRAY, pages);
}
+/*
+ * __set_memory_prot is an internal helper for callers that have been passed
+ * a pgprot_t value from upper layers and a reservation has already been taken.
+ * If you want to set the pgprot to a specific page protocol, use the
+ * set_memory_xx() functions.
+ */
+int __set_memory_prot(unsigned long addr, int numpages, pgprot_t prot)
+{
+ return change_page_attr_set_clr(&addr, numpages, prot,
+ __pgprot(~pgprot_val(prot)), 0, 0,
+ NULL);
+}
+
int _set_memory_uc(unsigned long addr, int numpages)
{
/*
diff --git a/arch/x86/mm/pgprot.c b/arch/x86/mm/pgprot.c
index c84bd9540b16..dc1afd5c839d 100644
--- a/arch/x86/mm/pgprot.c
+++ b/arch/x86/mm/pgprot.c
@@ -32,7 +32,7 @@ void add_encrypt_protection_map(void)
protection_map[i] = pgprot_encrypted(protection_map[i]);
}
-pgprot_t vm_get_page_prot(unsigned long vm_flags)
+pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
{
unsigned long val = pgprot_val(protection_map[vm_flags &
(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index f7ae44d3dd9e..ddf248c3ee7d 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -10,6 +10,7 @@
#ifdef CONFIG_DYNAMIC_PHYSICAL_MASK
phys_addr_t physical_mask __ro_after_init = (1ULL << __PHYSICAL_MASK_SHIFT) - 1;
EXPORT_SYMBOL(physical_mask);
+SYM_PIC_ALIAS(physical_mask);
#endif
pgtable_t pte_alloc_one(struct mm_struct *mm)
@@ -68,12 +69,6 @@ static inline void pgd_list_del(pgd_t *pgd)
list_del(&ptdesc->pt_list);
}
-#define UNSHARED_PTRS_PER_PGD \
- (SHARED_KERNEL_PMD ? KERNEL_PGD_BOUNDARY : PTRS_PER_PGD)
-#define MAX_UNSHARED_PTRS_PER_PGD \
- MAX_T(size_t, KERNEL_PGD_BOUNDARY, PTRS_PER_PGD)
-
-
static void pgd_set_mm(pgd_t *pgd, struct mm_struct *mm)
{
virt_to_ptdesc(pgd)->pt_mm = mm;
@@ -86,29 +81,19 @@ struct mm_struct *pgd_page_get_mm(struct page *page)
static void pgd_ctor(struct mm_struct *mm, pgd_t *pgd)
{
- /* If the pgd points to a shared pagetable level (either the
- ptes in non-PAE, or shared PMD in PAE), then just copy the
- references from swapper_pg_dir. */
- if (CONFIG_PGTABLE_LEVELS == 2 ||
- (CONFIG_PGTABLE_LEVELS == 3 && SHARED_KERNEL_PMD) ||
- CONFIG_PGTABLE_LEVELS >= 4) {
+ /* PAE preallocates all its PMDs. No cloning needed. */
+ if (!IS_ENABLED(CONFIG_X86_PAE))
clone_pgd_range(pgd + KERNEL_PGD_BOUNDARY,
swapper_pg_dir + KERNEL_PGD_BOUNDARY,
KERNEL_PGD_PTRS);
- }
- /* list required to sync kernel mapping updates */
- if (!SHARED_KERNEL_PMD) {
- pgd_set_mm(pgd, mm);
- pgd_list_add(pgd);
- }
+ /* List used to sync kernel mapping updates */
+ pgd_set_mm(pgd, mm);
+ pgd_list_add(pgd);
}
static void pgd_dtor(pgd_t *pgd)
{
- if (SHARED_KERNEL_PMD)
- return;
-
spin_lock(&pgd_lock);
pgd_list_del(pgd);
spin_unlock(&pgd_lock);
@@ -132,15 +117,15 @@ static void pgd_dtor(pgd_t *pgd)
* processor notices the update. Since this is expensive, and
* all 4 top-level entries are used almost immediately in a
* new process's life, we just pre-populate them here.
- *
- * Also, if we're in a paravirt environment where the kernel pmd is
- * not shared between pagetables (!SHARED_KERNEL_PMDS), we allocate
- * and initialize the kernel pmds here.
*/
-#define PREALLOCATED_PMDS UNSHARED_PTRS_PER_PGD
-#define MAX_PREALLOCATED_PMDS MAX_UNSHARED_PTRS_PER_PGD
+#define PREALLOCATED_PMDS PTRS_PER_PGD
/*
+ * "USER_PMDS" are the PMDs for the user copy of the page tables when
+ * PTI is enabled. They do not exist when PTI is disabled. Note that
+ * this is distinct from the user _portion_ of the kernel page tables
+ * which always exists.
+ *
* We allocate separate PMDs for the kernel part of the user page-table
* when PTI is enabled. We need them to map the per-process LDT into the
* user-space page-table.
@@ -169,7 +154,6 @@ void pud_populate(struct mm_struct *mm, pud_t *pudp, pmd_t *pmd)
/* No need to prepopulate any pagetable entries in non-PAE modes. */
#define PREALLOCATED_PMDS 0
-#define MAX_PREALLOCATED_PMDS 0
#define PREALLOCATED_USER_PMDS 0
#define MAX_PREALLOCATED_USER_PMDS 0
#endif /* CONFIG_X86_PAE */
@@ -205,7 +189,7 @@ static int preallocate_pmds(struct mm_struct *mm, pmd_t *pmds[], int count)
if (!ptdesc)
failed = true;
- if (ptdesc && !pagetable_pmd_ctor(ptdesc)) {
+ if (ptdesc && !pagetable_pmd_ctor(mm, ptdesc)) {
pagetable_free(ptdesc);
ptdesc = NULL;
failed = true;
@@ -318,68 +302,15 @@ static void pgd_prepopulate_user_pmd(struct mm_struct *mm,
{
}
#endif
-/*
- * Xen paravirt assumes pgd table should be in one page. 64 bit kernel also
- * assumes that pgd should be in one page.
- *
- * But kernel with PAE paging that is not running as a Xen domain
- * only needs to allocate 32 bytes for pgd instead of one page.
- */
-#ifdef CONFIG_X86_PAE
-
-#include <linux/slab.h>
-
-#define PGD_SIZE (PTRS_PER_PGD * sizeof(pgd_t))
-#define PGD_ALIGN 32
-
-static struct kmem_cache *pgd_cache;
-
-void __init pgtable_cache_init(void)
-{
- /*
- * When PAE kernel is running as a Xen domain, it does not use
- * shared kernel pmd. And this requires a whole page for pgd.
- */
- if (!SHARED_KERNEL_PMD)
- return;
-
- /*
- * when PAE kernel is not running as a Xen domain, it uses
- * shared kernel pmd. Shared kernel pmd does not require a whole
- * page for pgd. We are able to just allocate a 32-byte for pgd.
- * During boot time, we create a 32-byte slab for pgd table allocation.
- */
- pgd_cache = kmem_cache_create("pgd_cache", PGD_SIZE, PGD_ALIGN,
- SLAB_PANIC, NULL);
-}
static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
{
/*
- * If no SHARED_KERNEL_PMD, PAE kernel is running as a Xen domain.
- * We allocate one page for pgd.
- */
- if (!SHARED_KERNEL_PMD)
- return __pgd_alloc(mm, pgd_allocation_order());
-
- /*
- * Now PAE kernel is not running as a Xen domain. We can allocate
- * a 32-byte slab for pgd to save memory space.
+ * PTI and Xen need a whole page for the PAE PGD
+ * even though the hardware only needs 32 bytes.
+ *
+ * For simplicity, allocate a page for all users.
*/
- return kmem_cache_alloc(pgd_cache, GFP_PGTABLE_USER);
-}
-
-static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
-{
- if (!SHARED_KERNEL_PMD)
- __pgd_free(mm, pgd);
- else
- kmem_cache_free(pgd_cache, pgd);
-}
-#else
-
-static inline pgd_t *_pgd_alloc(struct mm_struct *mm)
-{
return __pgd_alloc(mm, pgd_allocation_order());
}
@@ -387,13 +318,12 @@ static inline void _pgd_free(struct mm_struct *mm, pgd_t *pgd)
{
__pgd_free(mm, pgd);
}
-#endif /* CONFIG_X86_PAE */
pgd_t *pgd_alloc(struct mm_struct *mm)
{
pgd_t *pgd;
pmd_t *u_pmds[MAX_PREALLOCATED_USER_PMDS];
- pmd_t *pmds[MAX_PREALLOCATED_PMDS];
+ pmd_t *pmds[PREALLOCATED_PMDS];
pgd = _pgd_alloc(mm);
@@ -613,11 +543,11 @@ pud_t pudp_invalidate(struct vm_area_struct *vma, unsigned long address,
#endif
/**
- * reserve_top_address - reserves a hole in the top of kernel address space
- * @reserve - size of hole to reserve
+ * reserve_top_address - Reserve a hole in the top of the kernel address space
+ * @reserve: Size of hole to reserve
*
* Can be used to relocate the fixmap area and poke a hole in the top
- * of kernel address space to make room for a hypervisor.
+ * of the kernel address space to make room for a hypervisor.
*/
void __init reserve_top_address(unsigned long reserve)
{
@@ -662,9 +592,12 @@ void native_set_fixmap(unsigned /* enum fixed_addresses */ idx,
}
#ifdef CONFIG_HAVE_ARCH_HUGE_VMAP
-#ifdef CONFIG_X86_5LEVEL
+#if CONFIG_PGTABLE_LEVELS > 4
/**
- * p4d_set_huge - setup kernel P4D mapping
+ * p4d_set_huge - Set up kernel P4D mapping
+ * @p4d: Pointer to the P4D entry
+ * @addr: Virtual address associated with the P4D entry
+ * @prot: Protection bits to use
*
* No 512GB pages yet -- always return 0
*/
@@ -674,9 +607,10 @@ int p4d_set_huge(p4d_t *p4d, phys_addr_t addr, pgprot_t prot)
}
/**
- * p4d_clear_huge - clear kernel P4D mapping when it is set
+ * p4d_clear_huge - Clear kernel P4D mapping when it is set
+ * @p4d: Pointer to the P4D entry to clear
*
- * No 512GB pages yet -- always return 0
+ * No 512GB pages yet -- do nothing
*/
void p4d_clear_huge(p4d_t *p4d)
{
@@ -684,7 +618,10 @@ void p4d_clear_huge(p4d_t *p4d)
#endif
/**
- * pud_set_huge - setup kernel PUD mapping
+ * pud_set_huge - Set up kernel PUD mapping
+ * @pud: Pointer to the PUD entry
+ * @addr: Virtual address associated with the PUD entry
+ * @prot: Protection bits to use
*
* MTRRs can override PAT memory types with 4KiB granularity. Therefore, this
* function sets up a huge page only if the complete range has the same MTRR
@@ -715,7 +652,10 @@ int pud_set_huge(pud_t *pud, phys_addr_t addr, pgprot_t prot)
}
/**
- * pmd_set_huge - setup kernel PMD mapping
+ * pmd_set_huge - Set up kernel PMD mapping
+ * @pmd: Pointer to the PMD entry
+ * @addr: Virtual address associated with the PMD entry
+ * @prot: Protection bits to use
*
* See text over pud_set_huge() above.
*
@@ -744,7 +684,8 @@ int pmd_set_huge(pmd_t *pmd, phys_addr_t addr, pgprot_t prot)
}
/**
- * pud_clear_huge - clear kernel PUD mapping when it is set
+ * pud_clear_huge - Clear kernel PUD mapping when it is set
+ * @pud: Pointer to the PUD entry to clear.
*
* Returns 1 on success and 0 on failure (no PUD map is found).
*/
@@ -759,7 +700,8 @@ int pud_clear_huge(pud_t *pud)
}
/**
- * pmd_clear_huge - clear kernel PMD mapping when it is set
+ * pmd_clear_huge - Clear kernel PMD mapping when it is set
+ * @pmd: Pointer to the PMD entry to clear.
*
* Returns 1 on success and 0 on failure (no PMD map is found).
*/
@@ -775,11 +717,11 @@ int pmd_clear_huge(pmd_t *pmd)
#ifdef CONFIG_X86_64
/**
- * pud_free_pmd_page - Clear pud entry and free pmd page.
- * @pud: Pointer to a PUD.
- * @addr: Virtual address associated with pud.
+ * pud_free_pmd_page - Clear PUD entry and free PMD page
+ * @pud: Pointer to a PUD
+ * @addr: Virtual address associated with PUD
*
- * Context: The pud range has been unmapped and TLB purged.
+ * Context: The PUD range has been unmapped and TLB purged.
* Return: 1 if clearing the entry succeeded. 0 otherwise.
*
* NOTE: Callers must allow a single page allocation.
@@ -809,24 +751,23 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
for (i = 0; i < PTRS_PER_PMD; i++) {
if (!pmd_none(pmd_sv[i])) {
pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
- free_page((unsigned long)pte);
+ pte_free_kernel(&init_mm, pte);
}
}
free_page((unsigned long)pmd_sv);
- pagetable_dtor(virt_to_ptdesc(pmd));
- free_page((unsigned long)pmd);
+ pmd_free(&init_mm, pmd);
return 1;
}
/**
- * pmd_free_pte_page - Clear pmd entry and free pte page.
- * @pmd: Pointer to a PMD.
- * @addr: Virtual address associated with pmd.
+ * pmd_free_pte_page - Clear PMD entry and free PTE page.
+ * @pmd: Pointer to the PMD
+ * @addr: Virtual address associated with PMD
*
- * Context: The pmd range has been unmapped and TLB purged.
+ * Context: The PMD range has been unmapped and TLB purged.
* Return: 1 if clearing the entry succeeded. 0 otherwise.
*/
int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
@@ -839,7 +780,7 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
/* INVLPG to clear all paging-structure caches */
flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
- free_page((unsigned long)pte);
+ pte_free_kernel(&init_mm, pte);
return 1;
}
@@ -848,7 +789,7 @@ int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
/*
* Disable free page handling on x86-PAE. This assures that ioremap()
- * does not update sync'd pmd entries. See vmalloc_sync_one().
+ * does not update sync'd PMD entries. See vmalloc_sync_one().
*/
int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
{
diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
index 5f0d579932c6..b10d4d131dce 100644
--- a/arch/x86/mm/pti.c
+++ b/arch/x86/mm/pti.c
@@ -38,6 +38,7 @@
#include <asm/desc.h>
#include <asm/sections.h>
#include <asm/set_memory.h>
+#include <asm/bugs.h>
#undef pr_fmt
#define pr_fmt(fmt) "Kernel/User page tables isolation: " fmt
@@ -84,7 +85,8 @@ void __init pti_check_boottime_disable(void)
return;
}
- if (cpu_mitigations_off())
+ if (pti_mode == PTI_AUTO &&
+ !cpu_attack_vector_mitigated(CPU_MITIGATE_USER_KERNEL))
pti_mode = PTI_FORCE_OFF;
if (pti_mode == PTI_FORCE_OFF) {
pti_print_if_insecure("disabled on command line.");
@@ -98,6 +100,11 @@ void __init pti_check_boottime_disable(void)
return;
setup_force_cpu_cap(X86_FEATURE_PTI);
+
+ if (cpu_feature_enabled(X86_FEATURE_INVLPGB)) {
+ pr_debug("PTI enabled, disabling INVLPGB\n");
+ setup_clear_cpu_cap(X86_FEATURE_INVLPGB);
+ }
}
static int __init pti_parse_cmdline(char *arg)
@@ -185,7 +192,7 @@ static p4d_t *pti_user_pagetable_walk_p4d(unsigned long address)
set_pgd(pgd, __pgd(_KERNPG_TABLE | __pa(new_p4d_page)));
}
- BUILD_BUG_ON(pgd_leaf(*pgd) != 0);
+ BUILD_BUG_ON(pgd_leaf(*pgd));
return p4d_offset(pgd, address);
}
@@ -206,7 +213,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
if (!p4d)
return NULL;
- BUILD_BUG_ON(p4d_leaf(*p4d) != 0);
+ BUILD_BUG_ON(p4d_leaf(*p4d));
if (p4d_none(*p4d)) {
unsigned long new_pud_page = __get_free_page(gfp);
if (WARN_ON_ONCE(!new_pud_page))
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index b6d6750e4bd1..39f80111e6f1 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -19,6 +19,7 @@
#include <asm/cache.h>
#include <asm/cacheflush.h>
#include <asm/apic.h>
+#include <asm/msr.h>
#include <asm/perf_event.h>
#include <asm/tlb.h>
@@ -215,16 +216,20 @@ static void clear_asid_other(void)
atomic64_t last_mm_ctx_id = ATOMIC64_INIT(1);
+struct new_asid {
+ unsigned int asid : 16;
+ unsigned int need_flush : 1;
+};
-static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
- u16 *new_asid, bool *need_flush)
+static struct new_asid choose_new_asid(struct mm_struct *next, u64 next_tlb_gen)
{
+ struct new_asid ns;
u16 asid;
if (!static_cpu_has(X86_FEATURE_PCID)) {
- *new_asid = 0;
- *need_flush = true;
- return;
+ ns.asid = 0;
+ ns.need_flush = 1;
+ return ns;
}
/*
@@ -235,9 +240,9 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
u16 global_asid = mm_global_asid(next);
if (global_asid) {
- *new_asid = global_asid;
- *need_flush = false;
- return;
+ ns.asid = global_asid;
+ ns.need_flush = 0;
+ return ns;
}
}
@@ -249,22 +254,23 @@ static void choose_new_asid(struct mm_struct *next, u64 next_tlb_gen,
next->context.ctx_id)
continue;
- *new_asid = asid;
- *need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) <
- next_tlb_gen);
- return;
+ ns.asid = asid;
+ ns.need_flush = (this_cpu_read(cpu_tlbstate.ctxs[asid].tlb_gen) < next_tlb_gen);
+ return ns;
}
/*
* We don't currently own an ASID slot on this CPU.
* Allocate a slot.
*/
- *new_asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1;
- if (*new_asid >= TLB_NR_DYN_ASIDS) {
- *new_asid = 0;
+ ns.asid = this_cpu_add_return(cpu_tlbstate.next_asid, 1) - 1;
+ if (ns.asid >= TLB_NR_DYN_ASIDS) {
+ ns.asid = 0;
this_cpu_write(cpu_tlbstate.next_asid, 1);
}
- *need_flush = true;
+ ns.need_flush = true;
+
+ return ns;
}
/*
@@ -623,7 +629,7 @@ static void l1d_flush_evaluate(unsigned long prev_mm, unsigned long next_mm,
{
/* Flush L1D if the outgoing task requests it */
if (prev_mm & LAST_USER_MM_L1D_FLUSH)
- wrmsrl(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
+ wrmsrq(MSR_IA32_FLUSH_CMD, L1D_FLUSH);
/* Check whether the incoming task opted in for L1D flush */
if (likely(!(next_mm & LAST_USER_MM_L1D_FLUSH)))
@@ -781,9 +787,9 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
unsigned cpu = smp_processor_id();
unsigned long new_lam;
+ struct new_asid ns;
u64 next_tlb_gen;
- bool need_flush;
- u16 new_asid;
+
/* We don't want flush_tlb_func() to run concurrently with us. */
if (IS_ENABLED(CONFIG_PROVE_LOCKING))
@@ -847,14 +853,15 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
* mm_cpumask. The TLB shootdown code can figure out from
* cpu_tlbstate_shared.is_lazy whether or not to send an IPI.
*/
- if (IS_ENABLED(CONFIG_DEBUG_VM) && WARN_ON_ONCE(prev != &init_mm &&
+ if (IS_ENABLED(CONFIG_DEBUG_VM) &&
+ WARN_ON_ONCE(prev != &init_mm && !is_notrack_mm(prev) &&
!cpumask_test_cpu(cpu, mm_cpumask(next))))
cpumask_set_cpu(cpu, mm_cpumask(next));
/* Check if the current mm is transitioning to a global ASID */
if (mm_needs_global_asid(next, prev_asid)) {
next_tlb_gen = atomic64_read(&next->context.tlb_gen);
- choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+ ns = choose_new_asid(next, next_tlb_gen);
goto reload_tlb;
}
@@ -889,8 +896,8 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
* TLB contents went out of date while we were in lazy
* mode. Fall through to the TLB switching code below.
*/
- new_asid = prev_asid;
- need_flush = true;
+ ns.asid = prev_asid;
+ ns.need_flush = true;
} else {
/*
* Apply process to process speculation vulnerability
@@ -906,34 +913,26 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
this_cpu_write(cpu_tlbstate.loaded_mm, LOADED_MM_SWITCHING);
barrier();
- /*
- * Leave this CPU in prev's mm_cpumask. Atomic writes to
- * mm_cpumask can be expensive under contention. The CPU
- * will be removed lazily at TLB flush time.
- */
- VM_WARN_ON_ONCE(prev != &init_mm && !cpumask_test_cpu(cpu,
- mm_cpumask(prev)));
-
/* Start receiving IPIs and then read tlb_gen (and LAM below) */
if (next != &init_mm && !cpumask_test_cpu(cpu, mm_cpumask(next)))
cpumask_set_cpu(cpu, mm_cpumask(next));
next_tlb_gen = atomic64_read(&next->context.tlb_gen);
- choose_new_asid(next, next_tlb_gen, &new_asid, &need_flush);
+ ns = choose_new_asid(next, next_tlb_gen);
}
reload_tlb:
new_lam = mm_lam_cr3_mask(next);
- if (need_flush) {
- VM_WARN_ON_ONCE(is_global_asid(new_asid));
- this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
- this_cpu_write(cpu_tlbstate.ctxs[new_asid].tlb_gen, next_tlb_gen);
- load_new_mm_cr3(next->pgd, new_asid, new_lam, true);
+ if (ns.need_flush) {
+ VM_WARN_ON_ONCE(is_global_asid(ns.asid));
+ this_cpu_write(cpu_tlbstate.ctxs[ns.asid].ctx_id, next->context.ctx_id);
+ this_cpu_write(cpu_tlbstate.ctxs[ns.asid].tlb_gen, next_tlb_gen);
+ load_new_mm_cr3(next->pgd, ns.asid, new_lam, true);
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, TLB_FLUSH_ALL);
} else {
/* The new ASID is already up to date. */
- load_new_mm_cr3(next->pgd, new_asid, new_lam, false);
+ load_new_mm_cr3(next->pgd, ns.asid, new_lam, false);
trace_tlb_flush(TLB_FLUSH_ON_TASK_SWITCH, 0);
}
@@ -942,7 +941,7 @@ reload_tlb:
barrier();
this_cpu_write(cpu_tlbstate.loaded_mm, next);
- this_cpu_write(cpu_tlbstate.loaded_mm_asid, new_asid);
+ this_cpu_write(cpu_tlbstate.loaded_mm_asid, ns.asid);
cpu_tlbstate_update_lam(new_lam, mm_untag_mask(next));
if (next != prev) {
@@ -973,6 +972,77 @@ void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
}
/*
+ * Using a temporary mm allows to set temporary mappings that are not accessible
+ * by other CPUs. Such mappings are needed to perform sensitive memory writes
+ * that override the kernel memory protections (e.g., W^X), without exposing the
+ * temporary page-table mappings that are required for these write operations to
+ * other CPUs. Using a temporary mm also allows to avoid TLB shootdowns when the
+ * mapping is torn down. Temporary mms can also be used for EFI runtime service
+ * calls or similar functionality.
+ *
+ * It is illegal to schedule while using a temporary mm -- the context switch
+ * code is unaware of the temporary mm and does not know how to context switch.
+ * Use a real (non-temporary) mm in a kernel thread if you need to sleep.
+ *
+ * Note: For sensitive memory writes, the temporary mm needs to be used
+ * exclusively by a single core, and IRQs should be disabled while the
+ * temporary mm is loaded, thereby preventing interrupt handler bugs from
+ * overriding the kernel memory protection.
+ */
+struct mm_struct *use_temporary_mm(struct mm_struct *temp_mm)
+{
+ struct mm_struct *prev_mm;
+
+ lockdep_assert_preemption_disabled();
+ guard(irqsave)();
+
+ /*
+ * Make sure not to be in TLB lazy mode, as otherwise we'll end up
+ * with a stale address space WITHOUT being in lazy mode after
+ * restoring the previous mm.
+ */
+ if (this_cpu_read(cpu_tlbstate_shared.is_lazy))
+ leave_mm();
+
+ prev_mm = this_cpu_read(cpu_tlbstate.loaded_mm);
+ switch_mm_irqs_off(NULL, temp_mm, current);
+
+ /*
+ * If breakpoints are enabled, disable them while the temporary mm is
+ * used. Userspace might set up watchpoints on addresses that are used
+ * in the temporary mm, which would lead to wrong signals being sent or
+ * crashes.
+ *
+ * Note that breakpoints are not disabled selectively, which also causes
+ * kernel breakpoints (e.g., perf's) to be disabled. This might be
+ * undesirable, but still seems reasonable as the code that runs in the
+ * temporary mm should be short.
+ */
+ if (hw_breakpoint_active())
+ hw_breakpoint_disable();
+
+ return prev_mm;
+}
+
+void unuse_temporary_mm(struct mm_struct *prev_mm)
+{
+ lockdep_assert_preemption_disabled();
+ guard(irqsave)();
+
+ /* Clear the cpumask, to indicate no TLB flushing is needed anywhere */
+ cpumask_clear_cpu(smp_processor_id(), mm_cpumask(this_cpu_read(cpu_tlbstate.loaded_mm)));
+
+ switch_mm_irqs_off(NULL, prev_mm, current);
+
+ /*
+ * Restore the breakpoints if they were disabled before the temporary mm
+ * was loaded.
+ */
+ if (hw_breakpoint_active())
+ hw_breakpoint_restore();
+}
+
+/*
* Call this when reinitializing a CPU. It fixes the following potential
* problems:
*
diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index ea4dd5b393aa..7e3fca164620 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -631,7 +631,7 @@ static int __bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
goto out;
ret = 1;
if (memcmp(ip, new_insn, X86_PATCH_SIZE)) {
- text_poke_bp(ip, new_insn, X86_PATCH_SIZE, NULL);
+ smp_text_poke_single(ip, new_insn, X86_PATCH_SIZE, NULL);
ret = 0;
}
out:
@@ -3501,13 +3501,6 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs, image, buf);
}
-static const char *bpf_get_prog_name(struct bpf_prog *prog)
-{
- if (prog->aux->ksym.prog)
- return prog->aux->ksym.name;
- return prog->aux->name;
-}
-
static void priv_stack_init_guard(void __percpu *priv_stack_ptr, int alloc_size)
{
int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3;
@@ -3531,7 +3524,7 @@ static void priv_stack_check_guard(void __percpu *priv_stack_ptr, int alloc_size
if (stack_ptr[0] != PRIV_STACK_GUARD_VAL ||
stack_ptr[underflow_idx] != PRIV_STACK_GUARD_VAL) {
pr_err("BPF private stack overflow/underflow detected for prog %sx\n",
- bpf_get_prog_name(prog));
+ bpf_jit_get_prog_name(prog));
break;
}
}
@@ -3845,7 +3838,6 @@ void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp
}
return;
#endif
- WARN(1, "verification of programs using bpf_throw should have failed\n");
}
void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
diff --git a/arch/x86/pci/Makefile b/arch/x86/pci/Makefile
index 4933fb337983..c1efd5b0d198 100644
--- a/arch/x86/pci/Makefile
+++ b/arch/x86/pci/Makefile
@@ -8,13 +8,13 @@ obj-$(CONFIG_PCI_OLPC) += olpc.o
obj-$(CONFIG_PCI_XEN) += xen.o
obj-y += fixup.o
-obj-$(CONFIG_X86_INTEL_CE) += ce4100.o
obj-$(CONFIG_ACPI) += acpi.o
obj-y += legacy.o irq.o
-obj-$(CONFIG_X86_NUMACHIP) += numachip.o
+obj-$(CONFIG_X86_INTEL_CE) += ce4100.o
+obj-$(CONFIG_X86_INTEL_MID) += intel_mid.o
-obj-$(CONFIG_X86_INTEL_MID) += intel_mid_pci.o
+obj-$(CONFIG_X86_NUMACHIP) += numachip.o
obj-y += common.o early.o
obj-y += bus_numa.o
diff --git a/arch/x86/pci/amd_bus.c b/arch/x86/pci/amd_bus.c
index 631512f7ec85..99b1727136c1 100644
--- a/arch/x86/pci/amd_bus.c
+++ b/arch/x86/pci/amd_bus.c
@@ -5,7 +5,7 @@
#include <linux/cpu.h>
#include <linux/range.h>
-#include <asm/amd_nb.h>
+#include <asm/amd/nb.h>
#include <asm/pci_x86.h>
#include <asm/pci-direct.h>
@@ -202,7 +202,7 @@ static int __init early_root_info_init(void)
/* need to take out [0, TOM) for RAM*/
address = MSR_K8_TOP_MEM1;
- rdmsrl(address, val);
+ rdmsrq(address, val);
end = (val & 0xffffff800000ULL);
printk(KERN_INFO "TOM: %016llx aka %lldM\n", end, end>>20);
if (end < (1ULL<<32))
@@ -293,12 +293,12 @@ static int __init early_root_info_init(void)
/* need to take out [4G, TOM2) for RAM*/
/* SYS_CFG */
address = MSR_AMD64_SYSCFG;
- rdmsrl(address, val);
+ rdmsrq(address, val);
/* TOP_MEM2 is enabled? */
if (val & (1<<21)) {
/* TOP_MEM2 */
address = MSR_K8_TOP_MEM2;
- rdmsrl(address, val);
+ rdmsrq(address, val);
end = (val & 0xffffff800000ULL);
printk(KERN_INFO "TOM2: %016llx aka %lldM\n", end, end>>20);
subtract_range(range, RANGE_NUM, 1ULL<<32, end);
@@ -341,10 +341,10 @@ static int amd_bus_cpu_online(unsigned int cpu)
{
u64 reg;
- rdmsrl(MSR_AMD64_NB_CFG, reg);
+ rdmsrq(MSR_AMD64_NB_CFG, reg);
if (!(reg & ENABLE_CF8_EXT_CFG)) {
reg |= ENABLE_CF8_EXT_CFG;
- wrmsrl(MSR_AMD64_NB_CFG, reg);
+ wrmsrq(MSR_AMD64_NB_CFG, reg);
}
return 0;
}
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index efefeb82ab61..e7e71490bd25 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -9,7 +9,7 @@
#include <linux/pci.h>
#include <linux/suspend.h>
#include <linux/vgaarb.h>
-#include <asm/amd_node.h>
+#include <asm/amd/node.h>
#include <asm/hpet.h>
#include <asm/pci_x86.h>
@@ -970,13 +970,13 @@ static void amd_rp_pme_suspend(struct pci_dev *dev)
struct pci_dev *rp;
/*
- * PM_SUSPEND_ON means we're doing runtime suspend, which means
+ * If system suspend is not in progress, we're doing runtime suspend, so
* amd-pmc will not be involved so PMEs during D3 work as advertised.
*
* The PMEs *do* work if amd-pmc doesn't put the SoC in the hardware
* sleep state, but we assume amd-pmc is always present.
*/
- if (pm_suspend_target_state == PM_SUSPEND_ON)
+ if (!pm_suspend_in_progress())
return;
rp = pcie_find_root_port(dev);
diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid.c
index b433b1753016..b433b1753016 100644
--- a/arch/x86/pci/intel_mid_pci.c
+++ b/arch/x86/pci/intel_mid.c
diff --git a/arch/x86/pci/mmconfig-shared.c b/arch/x86/pci/mmconfig-shared.c
index 39255f0eb14d..1f4522325920 100644
--- a/arch/x86/pci/mmconfig-shared.c
+++ b/arch/x86/pci/mmconfig-shared.c
@@ -22,9 +22,10 @@
#include <linux/slab.h>
#include <linux/mutex.h>
#include <linux/rculist.h>
+#include <asm/acpi.h>
#include <asm/e820/api.h>
+#include <asm/msr.h>
#include <asm/pci_x86.h>
-#include <asm/acpi.h>
/* Indicate if the ECAM resources have been placed into the resource table */
static bool pci_mmcfg_running_state;
diff --git a/arch/x86/platform/ce4100/ce4100.c b/arch/x86/platform/ce4100/ce4100.c
index f8126821a94d..aaa7017416f7 100644
--- a/arch/x86/platform/ce4100/ce4100.c
+++ b/arch/x86/platform/ce4100/ce4100.c
@@ -5,19 +5,12 @@
* (C) Copyright 2010 Intel Corporation
*/
#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/irq.h>
#include <linux/reboot.h>
-#include <linux/serial_reg.h>
-#include <linux/serial_8250.h>
#include <asm/ce4100.h>
#include <asm/prom.h>
#include <asm/setup.h>
-#include <asm/i8259.h>
#include <asm/io.h>
-#include <asm/io_apic.h>
-#include <asm/emergency-restart.h>
/*
* The CE4100 platform has an internal 8051 Microcontroller which is
@@ -31,94 +24,6 @@ static void ce4100_power_off(void)
outb(0x4, 0xcf9);
}
-#ifdef CONFIG_SERIAL_8250
-
-static unsigned int mem_serial_in(struct uart_port *p, int offset)
-{
- offset = offset << p->regshift;
- return readl(p->membase + offset);
-}
-
-/*
- * The UART Tx interrupts are not set under some conditions and therefore serial
- * transmission hangs. This is a silicon issue and has not been root caused. The
- * workaround for this silicon issue checks UART_LSR_THRE bit and UART_LSR_TEMT
- * bit of LSR register in interrupt handler to see whether at least one of these
- * two bits is set, if so then process the transmit request. If this workaround
- * is not applied, then the serial transmission may hang. This workaround is for
- * errata number 9 in Errata - B step.
-*/
-
-static unsigned int ce4100_mem_serial_in(struct uart_port *p, int offset)
-{
- unsigned int ret, ier, lsr;
-
- if (offset == UART_IIR) {
- offset = offset << p->regshift;
- ret = readl(p->membase + offset);
- if (ret & UART_IIR_NO_INT) {
- /* see if the TX interrupt should have really set */
- ier = mem_serial_in(p, UART_IER);
- /* see if the UART's XMIT interrupt is enabled */
- if (ier & UART_IER_THRI) {
- lsr = mem_serial_in(p, UART_LSR);
- /* now check to see if the UART should be
- generating an interrupt (but isn't) */
- if (lsr & (UART_LSR_THRE | UART_LSR_TEMT))
- ret &= ~UART_IIR_NO_INT;
- }
- }
- } else
- ret = mem_serial_in(p, offset);
- return ret;
-}
-
-static void ce4100_mem_serial_out(struct uart_port *p, int offset, int value)
-{
- offset = offset << p->regshift;
- writel(value, p->membase + offset);
-}
-
-static void ce4100_serial_fixup(int port, struct uart_port *up,
- u32 *capabilities)
-{
-#ifdef CONFIG_EARLY_PRINTK
- /*
- * Over ride the legacy port configuration that comes from
- * asm/serial.h. Using the ioport driver then switching to the
- * PCI memmaped driver hangs the IOAPIC
- */
- if (up->iotype != UPIO_MEM32) {
- up->uartclk = 14745600;
- up->mapbase = 0xdffe0200;
- set_fixmap_nocache(FIX_EARLYCON_MEM_BASE,
- up->mapbase & PAGE_MASK);
- up->membase =
- (void __iomem *)__fix_to_virt(FIX_EARLYCON_MEM_BASE);
- up->membase += up->mapbase & ~PAGE_MASK;
- up->mapbase += port * 0x100;
- up->membase += port * 0x100;
- up->iotype = UPIO_MEM32;
- up->regshift = 2;
- up->irq = 4;
- }
-#endif
- up->iobase = 0;
- up->serial_in = ce4100_mem_serial_in;
- up->serial_out = ce4100_mem_serial_out;
-
- *capabilities |= (1 << 12);
-}
-
-static __init void sdv_serial_fixup(void)
-{
- serial8250_set_isa_configurator(ce4100_serial_fixup);
-}
-
-#else
-static inline void sdv_serial_fixup(void) {};
-#endif
-
static void __init sdv_arch_setup(void)
{
sdv_serial_fixup();
diff --git a/arch/x86/platform/efi/efi_64.c b/arch/x86/platform/efi/efi_64.c
index a4b4ebd41b8f..b4409df2105a 100644
--- a/arch/x86/platform/efi/efi_64.c
+++ b/arch/x86/platform/efi/efi_64.c
@@ -89,6 +89,7 @@ int __init efi_alloc_page_tables(void)
efi_mm.pgd = efi_pgd;
mm_init_cpumask(&efi_mm);
init_new_context(NULL, &efi_mm);
+ set_notrack_mm(&efi_mm);
return 0;
@@ -215,8 +216,8 @@ int __init efi_setup_page_tables(unsigned long pa_memmap, unsigned num_pages)
* When SEV-ES is active, the GHCB as set by the kernel will be used
* by firmware. Create a 1:1 unencrypted mapping for each GHCB.
*/
- if (sev_es_efi_map_ghcbs(pgd)) {
- pr_err("Failed to create 1:1 mapping for the GHCBs!\n");
+ if (sev_es_efi_map_ghcbs_cas(pgd)) {
+ pr_err("Failed to create 1:1 mapping for the GHCBs and CAs!\n");
return 1;
}
@@ -434,15 +435,12 @@ void __init efi_dump_pagetable(void)
*/
static void efi_enter_mm(void)
{
- efi_prev_mm = current->active_mm;
- current->active_mm = &efi_mm;
- switch_mm(efi_prev_mm, &efi_mm, NULL);
+ efi_prev_mm = use_temporary_mm(&efi_mm);
}
static void efi_leave_mm(void)
{
- current->active_mm = efi_prev_mm;
- switch_mm(&efi_mm, efi_prev_mm, NULL);
+ unuse_temporary_mm(efi_prev_mm);
}
void arch_efi_call_virt_setup(void)
diff --git a/arch/x86/platform/olpc/olpc-xo1-rtc.c b/arch/x86/platform/olpc/olpc-xo1-rtc.c
index 57f210cda761..ee77d57bcab7 100644
--- a/arch/x86/platform/olpc/olpc-xo1-rtc.c
+++ b/arch/x86/platform/olpc/olpc-xo1-rtc.c
@@ -64,9 +64,9 @@ static int __init xo1_rtc_init(void)
of_node_put(node);
pr_info("olpc-xo1-rtc: Initializing OLPC XO-1 RTC\n");
- rdmsrl(MSR_RTC_DOMA_OFFSET, rtc_info.rtc_day_alarm);
- rdmsrl(MSR_RTC_MONA_OFFSET, rtc_info.rtc_mon_alarm);
- rdmsrl(MSR_RTC_CEN_OFFSET, rtc_info.rtc_century);
+ rdmsrq(MSR_RTC_DOMA_OFFSET, rtc_info.rtc_day_alarm);
+ rdmsrq(MSR_RTC_MONA_OFFSET, rtc_info.rtc_mon_alarm);
+ rdmsrq(MSR_RTC_CEN_OFFSET, rtc_info.rtc_century);
r = platform_device_register(&xo1_rtc_device);
if (r)
diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c
index 63066e7c8517..30751b42d54e 100644
--- a/arch/x86/platform/olpc/olpc-xo1-sci.c
+++ b/arch/x86/platform/olpc/olpc-xo1-sci.c
@@ -325,7 +325,7 @@ static int setup_sci_interrupt(struct platform_device *pdev)
dev_info(&pdev->dev, "SCI unmapped. Mapping to IRQ 3\n");
sci_irq = 3;
lo |= 0x00300000;
- wrmsrl(0x51400020, lo);
+ wrmsrq(0x51400020, lo);
}
/* Select level triggered in PIC */
diff --git a/arch/x86/platform/pvh/head.S b/arch/x86/platform/pvh/head.S
index cfa18ec7d55f..1d78e5631bb8 100644
--- a/arch/x86/platform/pvh/head.S
+++ b/arch/x86/platform/pvh/head.S
@@ -87,8 +87,7 @@ SYM_CODE_START(pvh_start_xen)
mov %ebx, %esi
movl rva(pvh_start_info_sz)(%ebp), %ecx
shr $2,%ecx
- rep
- movsl
+ rep movsl
leal rva(early_stack_end)(%ebp), %esp
diff --git a/arch/x86/power/cpu.c b/arch/x86/power/cpu.c
index 08e76a5ca155..916441f5e85c 100644
--- a/arch/x86/power/cpu.c
+++ b/arch/x86/power/cpu.c
@@ -27,6 +27,7 @@
#include <asm/mmu_context.h>
#include <asm/cpu_device_id.h>
#include <asm/microcode.h>
+#include <asm/msr.h>
#include <asm/fred.h>
#ifdef CONFIG_X86_32
@@ -44,7 +45,7 @@ static void msr_save_context(struct saved_context *ctxt)
while (msr < end) {
if (msr->valid)
- rdmsrl(msr->info.msr_no, msr->info.reg.q);
+ rdmsrq(msr->info.msr_no, msr->info.reg.q);
msr++;
}
}
@@ -56,7 +57,7 @@ static void msr_restore_context(struct saved_context *ctxt)
while (msr < end) {
if (msr->valid)
- wrmsrl(msr->info.msr_no, msr->info.reg.q);
+ wrmsrq(msr->info.msr_no, msr->info.reg.q);
msr++;
}
}
@@ -110,12 +111,12 @@ static void __save_processor_state(struct saved_context *ctxt)
savesegment(ds, ctxt->ds);
savesegment(es, ctxt->es);
- rdmsrl(MSR_FS_BASE, ctxt->fs_base);
- rdmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
- rdmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
+ rdmsrq(MSR_FS_BASE, ctxt->fs_base);
+ rdmsrq(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+ rdmsrq(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
mtrr_save_fixed_ranges(NULL);
- rdmsrl(MSR_EFER, ctxt->efer);
+ rdmsrq(MSR_EFER, ctxt->efer);
#endif
/*
@@ -125,7 +126,7 @@ static void __save_processor_state(struct saved_context *ctxt)
ctxt->cr2 = read_cr2();
ctxt->cr3 = __read_cr3();
ctxt->cr4 = __read_cr4();
- ctxt->misc_enable_saved = !rdmsrl_safe(MSR_IA32_MISC_ENABLE,
+ ctxt->misc_enable_saved = !rdmsrq_safe(MSR_IA32_MISC_ENABLE,
&ctxt->misc_enable);
msr_save_context(ctxt);
}
@@ -198,7 +199,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
struct cpuinfo_x86 *c;
if (ctxt->misc_enable_saved)
- wrmsrl(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
+ wrmsrq(MSR_IA32_MISC_ENABLE, ctxt->misc_enable);
/*
* control registers
*/
@@ -208,7 +209,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
__write_cr4(ctxt->cr4);
#else
/* CONFIG X86_64 */
- wrmsrl(MSR_EFER, ctxt->efer);
+ wrmsrq(MSR_EFER, ctxt->efer);
__write_cr4(ctxt->cr4);
#endif
write_cr3(ctxt->cr3);
@@ -231,7 +232,7 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
* handlers or in complicated helpers like load_gs_index().
*/
#ifdef CONFIG_X86_64
- wrmsrl(MSR_GS_BASE, ctxt->kernelmode_gs_base);
+ wrmsrq(MSR_GS_BASE, ctxt->kernelmode_gs_base);
/*
* Reinitialize FRED to ensure the FRED MSRs contain the same values
@@ -267,8 +268,8 @@ static void notrace __restore_processor_state(struct saved_context *ctxt)
* restoring the selectors clobbers the bases. Keep in mind
* that MSR_KERNEL_GS_BASE is horribly misnamed.
*/
- wrmsrl(MSR_FS_BASE, ctxt->fs_base);
- wrmsrl(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
+ wrmsrq(MSR_FS_BASE, ctxt->fs_base);
+ wrmsrq(MSR_KERNEL_GS_BASE, ctxt->usermode_gs_base);
#else
loadsegment(gs, ctxt->gs);
#endif
@@ -414,7 +415,7 @@ static int msr_build_context(const u32 *msr_id, const int num)
u64 dummy;
msr_array[i].info.msr_no = msr_id[j];
- msr_array[i].valid = !rdmsrl_safe(msr_id[j], &dummy);
+ msr_array[i].valid = !rdmsrq_safe(msr_id[j], &dummy);
msr_array[i].info.reg.q = 0;
}
saved_msrs->num = total_num;
diff --git a/arch/x86/power/hibernate.c b/arch/x86/power/hibernate.c
index 5b81d19cd114..a2294c1649f6 100644
--- a/arch/x86/power/hibernate.c
+++ b/arch/x86/power/hibernate.c
@@ -42,6 +42,7 @@ unsigned long relocated_restore_code __visible;
/**
* pfn_is_nosave - check if given pfn is in the 'nosave' section
+ * @pfn: the page frame number to check.
*/
int pfn_is_nosave(unsigned long pfn)
{
@@ -86,7 +87,10 @@ static inline u32 compute_e820_crc32(struct e820_table *table)
/**
* arch_hibernation_header_save - populate the architecture specific part
* of a hibernation image header
- * @addr: address to save the data at
+ * @addr: address where architecture specific header data will be saved.
+ * @max_size: maximum size of architecture specific data in hibernation header.
+ *
+ * Return: 0 on success, -EOVERFLOW if max_size is insufficient.
*/
int arch_hibernation_header_save(void *addr, unsigned int max_size)
{
@@ -188,7 +192,8 @@ out:
int arch_resume_nosmt(void)
{
- int ret = 0;
+ int ret;
+
/*
* We reached this while coming out of hibernation. This means
* that SMT siblings are sleeping in hlt, as mwait is not safe
@@ -202,18 +207,10 @@ int arch_resume_nosmt(void)
* Called with hotplug disabled.
*/
cpu_hotplug_enable();
- if (cpu_smt_control == CPU_SMT_DISABLED ||
- cpu_smt_control == CPU_SMT_FORCE_DISABLED) {
- enum cpuhp_smt_control old = cpu_smt_control;
-
- ret = cpuhp_smt_enable();
- if (ret)
- goto out;
- ret = cpuhp_smt_disable(old);
- if (ret)
- goto out;
- }
-out:
+
+ ret = arch_cpu_rescan_dead_smt_siblings();
+
cpu_hotplug_disable();
+
return ret;
}
diff --git a/arch/x86/power/hibernate_asm_32.S b/arch/x86/power/hibernate_asm_32.S
index 5606a15cf9a1..fb910d9f8471 100644
--- a/arch/x86/power/hibernate_asm_32.S
+++ b/arch/x86/power/hibernate_asm_32.S
@@ -69,8 +69,7 @@ copy_loop:
movl pbe_orig_address(%edx), %edi
movl $(PAGE_SIZE >> 2), %ecx
- rep
- movsl
+ rep movsl
movl pbe_next(%edx), %edx
jmp copy_loop
diff --git a/arch/x86/power/hibernate_asm_64.S b/arch/x86/power/hibernate_asm_64.S
index 66f066b8feda..c73be0a02a6c 100644
--- a/arch/x86/power/hibernate_asm_64.S
+++ b/arch/x86/power/hibernate_asm_64.S
@@ -138,8 +138,7 @@ SYM_FUNC_START(core_restore_code)
movq pbe_address(%rdx), %rsi
movq pbe_orig_address(%rdx), %rdi
movq $(PAGE_SIZE >> 3), %rcx
- rep
- movsq
+ rep movsq
/* progress to the next pbe */
movq pbe_next(%rdx), %rdx
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index ebdfd7b84feb..e0a607a14e7e 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -35,7 +35,7 @@ targets += purgatory.ro purgatory.chk
PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
PURGATORY_CFLAGS := -mcmodel=small -ffreestanding -fno-zero-initialized-in-bss -g0
PURGATORY_CFLAGS += -fpic -fvisibility=hidden
-PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
+PURGATORY_CFLAGS += $(DISABLE_KSTACK_ERASE) -DDISABLE_BRANCH_PROFILING
PURGATORY_CFLAGS += -fno-stack-protector
# Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
diff --git a/arch/x86/purgatory/purgatory.c b/arch/x86/purgatory/purgatory.c
index aea47e793963..655139dd0532 100644
--- a/arch/x86/purgatory/purgatory.c
+++ b/arch/x86/purgatory/purgatory.c
@@ -25,7 +25,7 @@ static int verify_sha256_digest(void)
{
struct kexec_sha_region *ptr, *end;
u8 digest[SHA256_DIGEST_SIZE];
- struct sha256_state sctx;
+ struct sha256_ctx sctx;
sha256_init(&sctx);
end = purgatory_sha_regions + ARRAY_SIZE(purgatory_sha_regions);
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index f9bc444a3064..88be32026768 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -9,6 +9,7 @@
#include <asm/realmode.h>
#include <asm/tlbflush.h>
#include <asm/crash.h>
+#include <asm/msr.h>
#include <asm/sev.h>
struct real_mode_header *real_mode_header;
@@ -65,6 +66,8 @@ void __init reserve_real_mode(void)
* setup_arch().
*/
memblock_reserve(0, SZ_1M);
+
+ memblock_clear_kho_scratch(0, SZ_1M);
}
static void __init sme_sev_setup_real_mode(struct trampoline_header *th)
@@ -145,7 +148,7 @@ static void __init setup_real_mode(void)
* Some AMD processors will #GP(0) if EFER.LMA is set in WRMSR
* so we need to mask it out.
*/
- rdmsrl(MSR_EFER, efer);
+ rdmsrq(MSR_EFER, efer);
trampoline_header->efer = efer & ~EFER_LMA;
trampoline_header->start = (u64) secondary_startup_64;
diff --git a/arch/x86/tools/gen-insn-attr-x86.awk b/arch/x86/tools/gen-insn-attr-x86.awk
index 5770c8097f32..2c19d7fc8a85 100644
--- a/arch/x86/tools/gen-insn-attr-x86.awk
+++ b/arch/x86/tools/gen-insn-attr-x86.awk
@@ -64,6 +64,8 @@ BEGIN {
modrm_expr = "^([CDEGMNPQRSUVW/][a-z]+|NTA|T[012])"
force64_expr = "\\([df]64\\)"
+ invalid64_expr = "\\(i64\\)"
+ only64_expr = "\\(o64\\)"
rex_expr = "^((REX(\\.[XRWB]+)+)|(REX$))"
rex2_expr = "\\(REX2\\)"
no_rex2_expr = "\\(!REX2\\)"
@@ -319,6 +321,11 @@ function convert_operands(count,opnd, i,j,imm,mod)
if (match(ext, force64_expr))
flags = add_flags(flags, "INAT_FORCE64")
+ # check invalid in 64-bit (and no only64)
+ if (match(ext, invalid64_expr) &&
+ !match($0, only64_expr))
+ flags = add_flags(flags, "INAT_INV64")
+
# check REX2 not allowed
if (match(ext, no_rex2_expr))
flags = add_flags(flags, "INAT_NO_REX2")
diff --git a/arch/x86/tools/insn_decoder_test.c b/arch/x86/tools/insn_decoder_test.c
index 08cd913cbd4e..8bf15c4aefa9 100644
--- a/arch/x86/tools/insn_decoder_test.c
+++ b/arch/x86/tools/insn_decoder_test.c
@@ -167,7 +167,7 @@ int main(int argc, char **argv)
pr_warn("Decoded and checked %d instructions with %d "
"failures\n", insns, warnings);
else
- fprintf(stdout, "%s: success: Decoded and checked %d"
+ fprintf(stdout, " %s: success: Decoded and checked %d"
" instructions\n", prog, insns);
return 0;
}
diff --git a/arch/x86/tools/insn_sanity.c b/arch/x86/tools/insn_sanity.c
index 213f35f94feb..e743f0ea01ee 100644
--- a/arch/x86/tools/insn_sanity.c
+++ b/arch/x86/tools/insn_sanity.c
@@ -253,9 +253,9 @@ int main(int argc, char **argv)
}
fprintf((errors) ? stderr : stdout,
- "%s: %s: decoded and checked %d %s instructions with %d errors (seed:0x%x)\n",
+ " %s: %s: Decoded and checked %d %s instructions with %d errors (seed:0x%x)\n",
prog,
- (errors) ? "Failure" : "Success",
+ (errors) ? "failure" : "success",
insns,
(input_file) ? "given" : "random",
errors,
diff --git a/arch/x86/um/asm/checksum.h b/arch/x86/um/asm/checksum.h
index b07824500363..ddc144657efa 100644
--- a/arch/x86/um/asm/checksum.h
+++ b/arch/x86/um/asm/checksum.h
@@ -20,6 +20,9 @@
*/
extern __wsum csum_partial(const void *buff, int len, __wsum sum);
+/* Do not call this directly. Declared for export type visibility. */
+extern __visible __wsum csum_partial_copy_generic(const void *src, void *dst, int len);
+
/**
* csum_fold - Fold and invert a 32bit checksum.
* sum: 32bit unfolded sum
diff --git a/arch/x86/um/asm/processor.h b/arch/x86/um/asm/processor.h
index 478710384b34..e222d2ae28fd 100644
--- a/arch/x86/um/asm/processor.h
+++ b/arch/x86/um/asm/processor.h
@@ -21,10 +21,10 @@
#include <asm/user.h>
-/* REP NOP (PAUSE) is a good thing to insert into busy-wait loops. */
-static __always_inline void rep_nop(void)
+/* PAUSE is a good thing to insert into busy-wait loops. */
+static __always_inline void native_pause(void)
{
- __asm__ __volatile__("rep;nop": : :"memory");
+ __asm__ __volatile__("pause": : :"memory");
}
static __always_inline void cpu_relax(void)
@@ -33,7 +33,7 @@ static __always_inline void cpu_relax(void)
time_travel_mode == TT_MODE_EXTERNAL)
time_travel_ndelay(1);
else
- rep_nop();
+ native_pause();
}
#define task_pt_regs(t) (&(t)->thread.regs)
diff --git a/arch/x86/um/asm/syscall.h b/arch/x86/um/asm/syscall.h
index 56a2f0913e3c..d6208d0fad51 100644
--- a/arch/x86/um/asm/syscall.h
+++ b/arch/x86/um/asm/syscall.h
@@ -9,6 +9,8 @@ typedef asmlinkage long (*sys_call_ptr_t)(unsigned long, unsigned long,
unsigned long, unsigned long,
unsigned long, unsigned long);
+extern const sys_call_ptr_t sys_call_table[];
+
static inline int syscall_get_arch(struct task_struct *task)
{
#ifdef CONFIG_X86_32
diff --git a/arch/x86/um/os-Linux/mcontext.c b/arch/x86/um/os-Linux/mcontext.c
index 37decaa74761..a21403df6663 100644
--- a/arch/x86/um/os-Linux/mcontext.c
+++ b/arch/x86/um/os-Linux/mcontext.c
@@ -1,7 +1,10 @@
// SPDX-License-Identifier: GPL-2.0
-#include <sys/ucontext.h>
#define __FRAME_OFFSETS
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <sys/ucontext.h>
#include <asm/ptrace.h>
+#include <asm/sigcontext.h>
#include <sysdep/ptrace.h>
#include <sysdep/mcontext.h>
#include <arch.h>
@@ -18,6 +21,10 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
COPY2(UESP, ESP); /* sic */
COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX);
COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS);
+#undef COPY2
+#undef COPY
+#undef COPY_SEG
+#undef COPY_SEG_CPL3
#else
#define COPY2(X,Y) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##Y]
#define COPY(X) regs->gp[X/sizeof(unsigned long)] = mc->gregs[REG_##X]
@@ -29,6 +36,8 @@ void get_regs_from_mc(struct uml_pt_regs *regs, mcontext_t *mc)
COPY2(EFLAGS, EFL);
COPY2(CS, CSGSFS);
regs->gp[SS / sizeof(unsigned long)] = mc->gregs[REG_CSGSFS] >> 48;
+#undef COPY2
+#undef COPY
#endif
}
@@ -42,3 +51,210 @@ void mc_set_rip(void *_mc, void *target)
mc->gregs[REG_RIP] = (unsigned long)target;
#endif
}
+
+/* Same thing, but the copy macros are turned around. */
+void get_mc_from_regs(struct uml_pt_regs *regs, mcontext_t *mc, int single_stepping)
+{
+#ifdef __i386__
+#define COPY2(X,Y) mc->gregs[REG_##Y] = regs->gp[X]
+#define COPY(X) mc->gregs[REG_##X] = regs->gp[X]
+#define COPY_SEG(X) mc->gregs[REG_##X] = regs->gp[X] & 0xffff;
+#define COPY_SEG_CPL3(X) mc->gregs[REG_##X] = (regs->gp[X] & 0xffff) | 3;
+ COPY_SEG(GS); COPY_SEG(FS); COPY_SEG(ES); COPY_SEG(DS);
+ COPY(EDI); COPY(ESI); COPY(EBP);
+ COPY2(UESP, ESP); /* sic */
+ COPY(EBX); COPY(EDX); COPY(ECX); COPY(EAX);
+ COPY(EIP); COPY_SEG_CPL3(CS); COPY(EFL); COPY_SEG_CPL3(SS);
+#else
+#define COPY2(X,Y) mc->gregs[REG_##Y] = regs->gp[X/sizeof(unsigned long)]
+#define COPY(X) mc->gregs[REG_##X] = regs->gp[X/sizeof(unsigned long)]
+ COPY(R8); COPY(R9); COPY(R10); COPY(R11);
+ COPY(R12); COPY(R13); COPY(R14); COPY(R15);
+ COPY(RDI); COPY(RSI); COPY(RBP); COPY(RBX);
+ COPY(RDX); COPY(RAX); COPY(RCX); COPY(RSP);
+ COPY(RIP);
+ COPY2(EFLAGS, EFL);
+ mc->gregs[REG_CSGSFS] = mc->gregs[REG_CSGSFS] & 0xffffffffffffl;
+ mc->gregs[REG_CSGSFS] |= (regs->gp[SS / sizeof(unsigned long)] & 0xffff) << 48;
+#endif
+
+ if (single_stepping)
+ mc->gregs[REG_EFL] |= X86_EFLAGS_TF;
+ else
+ mc->gregs[REG_EFL] &= ~X86_EFLAGS_TF;
+}
+
+#ifdef CONFIG_X86_32
+struct _xstate_64 {
+ struct _fpstate_64 fpstate;
+ struct _header xstate_hdr;
+ struct _ymmh_state ymmh;
+ /* New processor state extensions go here: */
+};
+
+/* Not quite the right structures as these contain more information */
+int um_i387_from_fxsr(struct _fpstate_32 *i387,
+ const struct _fpstate_64 *fxsave);
+int um_fxsr_from_i387(struct _fpstate_64 *fxsave,
+ const struct _fpstate_32 *from);
+#else
+#define _xstate_64 _xstate
+#endif
+
+static struct _fpstate *get_fpstate(struct stub_data *data,
+ mcontext_t *mcontext,
+ int *fp_size)
+{
+ struct _fpstate *res;
+
+ /* Assume floating point registers are on the same page */
+ res = (void *)(((unsigned long)mcontext->fpregs &
+ (UM_KERN_PAGE_SIZE - 1)) +
+ (unsigned long)&data->sigstack[0]);
+
+ if ((void *)res + sizeof(struct _fpstate) >
+ (void *)data->sigstack + sizeof(data->sigstack))
+ return NULL;
+
+ if (res->sw_reserved.magic1 != FP_XSTATE_MAGIC1) {
+ *fp_size = sizeof(struct _fpstate);
+ } else {
+ char *magic2_addr;
+
+ magic2_addr = (void *)res;
+ magic2_addr += res->sw_reserved.extended_size;
+ magic2_addr -= FP_XSTATE_MAGIC2_SIZE;
+
+ /* We still need to be within our stack */
+ if ((void *)magic2_addr >
+ (void *)data->sigstack + sizeof(data->sigstack))
+ return NULL;
+
+ /* If we do not read MAGIC2, then we did something wrong */
+ if (*(__u32 *)magic2_addr != FP_XSTATE_MAGIC2)
+ return NULL;
+
+ /* Remove MAGIC2 from the size, we do not save/restore it */
+ *fp_size = res->sw_reserved.extended_size -
+ FP_XSTATE_MAGIC2_SIZE;
+ }
+
+ return res;
+}
+
+int get_stub_state(struct uml_pt_regs *regs, struct stub_data *data,
+ unsigned long *fp_size_out)
+{
+ mcontext_t *mcontext;
+ struct _fpstate *fpstate_stub;
+ struct _xstate_64 *xstate_stub;
+ int fp_size, xstate_size;
+
+ /* mctx_offset is verified by wait_stub_done_seccomp */
+ mcontext = (void *)&data->sigstack[data->mctx_offset];
+
+ get_regs_from_mc(regs, mcontext);
+
+ fpstate_stub = get_fpstate(data, mcontext, &fp_size);
+ if (!fpstate_stub)
+ return -EINVAL;
+
+#ifdef CONFIG_X86_32
+ xstate_stub = (void *)&fpstate_stub->_fxsr_env;
+ xstate_size = fp_size - offsetof(struct _fpstate_32, _fxsr_env);
+#else
+ xstate_stub = (void *)fpstate_stub;
+ xstate_size = fp_size;
+#endif
+
+ if (fp_size_out)
+ *fp_size_out = xstate_size;
+
+ if (xstate_size > host_fp_size)
+ return -ENOSPC;
+
+ memcpy(&regs->fp, xstate_stub, xstate_size);
+
+ /* We do not need to read the x86_64 FS_BASE/GS_BASE registers as
+ * we do not permit userspace to set them directly.
+ */
+
+#ifdef CONFIG_X86_32
+ /* Read the i387 legacy FP registers */
+ if (um_fxsr_from_i387((void *)&regs->fp, fpstate_stub))
+ return -EINVAL;
+#endif
+
+ return 0;
+}
+
+/* Copied because we cannot include regset.h here. */
+struct task_struct;
+struct user_regset;
+struct membuf {
+ void *p;
+ size_t left;
+};
+
+int fpregs_legacy_get(struct task_struct *target,
+ const struct user_regset *regset,
+ struct membuf to);
+
+int set_stub_state(struct uml_pt_regs *regs, struct stub_data *data,
+ int single_stepping)
+{
+ mcontext_t *mcontext;
+ struct _fpstate *fpstate_stub;
+ struct _xstate_64 *xstate_stub;
+ int fp_size, xstate_size;
+
+ /* mctx_offset is verified by wait_stub_done_seccomp */
+ mcontext = (void *)&data->sigstack[data->mctx_offset];
+
+ if ((unsigned long)mcontext < (unsigned long)data->sigstack ||
+ (unsigned long)mcontext >
+ (unsigned long) data->sigstack +
+ sizeof(data->sigstack) - sizeof(*mcontext))
+ return -EINVAL;
+
+ get_mc_from_regs(regs, mcontext, single_stepping);
+
+ fpstate_stub = get_fpstate(data, mcontext, &fp_size);
+ if (!fpstate_stub)
+ return -EINVAL;
+
+#ifdef CONFIG_X86_32
+ xstate_stub = (void *)&fpstate_stub->_fxsr_env;
+ xstate_size = fp_size - offsetof(struct _fpstate_32, _fxsr_env);
+#else
+ xstate_stub = (void *)fpstate_stub;
+ xstate_size = fp_size;
+#endif
+
+ memcpy(xstate_stub, &regs->fp, xstate_size);
+
+#ifdef __i386__
+ /*
+ * On x86, the GDT entries are updated by arch_set_tls.
+ */
+
+ /* Store the i387 legacy FP registers which the host will use */
+ if (um_i387_from_fxsr(fpstate_stub, (void *)&regs->fp))
+ return -EINVAL;
+#else
+ /*
+ * On x86_64, we need to sync the FS_BASE/GS_BASE registers using the
+ * arch specific data.
+ */
+ if (data->arch_data.fs_base != regs->gp[FS_BASE / sizeof(unsigned long)]) {
+ data->arch_data.fs_base = regs->gp[FS_BASE / sizeof(unsigned long)];
+ data->arch_data.sync |= STUB_SYNC_FS_BASE;
+ }
+ if (data->arch_data.gs_base != regs->gp[GS_BASE / sizeof(unsigned long)]) {
+ data->arch_data.gs_base = regs->gp[GS_BASE / sizeof(unsigned long)];
+ data->arch_data.sync |= STUB_SYNC_GS_BASE;
+ }
+#endif
+
+ return 0;
+}
diff --git a/arch/x86/um/ptrace.c b/arch/x86/um/ptrace.c
index 57c504fd5626..2635ca2595a3 100644
--- a/arch/x86/um/ptrace.c
+++ b/arch/x86/um/ptrace.c
@@ -25,7 +25,8 @@ static inline unsigned short twd_i387_to_fxsr(unsigned short twd)
return tmp;
}
-static inline unsigned long twd_fxsr_to_i387(struct user_fxsr_struct *fxsave)
+static inline unsigned long
+twd_fxsr_to_i387(const struct user_fxsr_struct *fxsave)
{
struct _fpxreg *st = NULL;
unsigned long twd = (unsigned long) fxsave->twd;
@@ -69,12 +70,16 @@ static inline unsigned long twd_fxsr_to_i387(struct user_fxsr_struct *fxsave)
return ret;
}
-/* Get/set the old 32bit i387 registers (pre-FPX) */
-static int fpregs_legacy_get(struct task_struct *target,
- const struct user_regset *regset,
- struct membuf to)
+/*
+ * Get/set the old 32bit i387 registers (pre-FPX)
+ *
+ * We provide simple wrappers for mcontext.c, they are only defined locally
+ * because mcontext.c is userspace facing and needs to a different definition
+ * of the structures.
+ */
+static int _um_i387_from_fxsr(struct membuf to,
+ const struct user_fxsr_struct *fxsave)
{
- struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp;
int i;
membuf_store(&to, (unsigned long)fxsave->cwd | 0xffff0000ul);
@@ -91,23 +96,36 @@ static int fpregs_legacy_get(struct task_struct *target,
return 0;
}
-static int fpregs_legacy_set(struct task_struct *target,
+int um_i387_from_fxsr(struct user_i387_struct *i387,
+ const struct user_fxsr_struct *fxsave);
+
+int um_i387_from_fxsr(struct user_i387_struct *i387,
+ const struct user_fxsr_struct *fxsave)
+{
+ struct membuf to = {
+ .p = i387,
+ .left = sizeof(*i387),
+ };
+
+ return _um_i387_from_fxsr(to, fxsave);
+}
+
+static int fpregs_legacy_get(struct task_struct *target,
const struct user_regset *regset,
- unsigned int pos, unsigned int count,
- const void *kbuf, const void __user *ubuf)
+ struct membuf to)
{
struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp;
- const struct user_i387_struct *from;
- struct user_i387_struct buf;
- int i;
- if (ubuf) {
- if (copy_from_user(&buf, ubuf, sizeof(buf)))
- return -EFAULT;
- from = &buf;
- } else {
- from = kbuf;
- }
+ return _um_i387_from_fxsr(to, fxsave);
+}
+
+int um_fxsr_from_i387(struct user_fxsr_struct *fxsave,
+ const struct user_i387_struct *from);
+
+int um_fxsr_from_i387(struct user_fxsr_struct *fxsave,
+ const struct user_i387_struct *from)
+{
+ int i;
fxsave->cwd = (unsigned short)(from->cwd & 0xffff);
fxsave->swd = (unsigned short)(from->swd & 0xffff);
@@ -125,6 +143,26 @@ static int fpregs_legacy_set(struct task_struct *target,
return 0;
}
+
+static int fpregs_legacy_set(struct task_struct *target,
+ const struct user_regset *regset,
+ unsigned int pos, unsigned int count,
+ const void *kbuf, const void __user *ubuf)
+{
+ struct user_fxsr_struct *fxsave = (void *)target->thread.regs.regs.fp;
+ const struct user_i387_struct *from;
+ struct user_i387_struct buf;
+
+ if (ubuf) {
+ if (copy_from_user(&buf, ubuf, sizeof(buf)))
+ return -EFAULT;
+ from = &buf;
+ } else {
+ from = kbuf;
+ }
+
+ return um_fxsr_from_i387(fxsave, from);
+}
#endif
static int genregs_get(struct task_struct *target,
@@ -198,7 +236,7 @@ static int generic_fpregs_set(struct task_struct *target,
static struct user_regset uml_regsets[] __ro_after_init = {
[REGSET_GENERAL] = {
- .core_note_type = NT_PRSTATUS,
+ USER_REGSET_NOTE_TYPE(PRSTATUS),
.n = sizeof(struct user_regs_struct) / sizeof(long),
.size = sizeof(long),
.align = sizeof(long),
@@ -208,7 +246,7 @@ static struct user_regset uml_regsets[] __ro_after_init = {
#ifdef CONFIG_X86_32
/* Old FP registers, they are needed in signal frames */
[REGSET_FP_LEGACY] = {
- .core_note_type = NT_PRFPREG,
+ USER_REGSET_NOTE_TYPE(PRFPREG),
.n = sizeof(struct user_i387_ia32_struct) / sizeof(long),
.size = sizeof(long),
.align = sizeof(long),
@@ -219,10 +257,10 @@ static struct user_regset uml_regsets[] __ro_after_init = {
#endif
[REGSET_FP] = {
#ifdef CONFIG_X86_32
- .core_note_type = NT_PRXFPREG,
+ USER_REGSET_NOTE_TYPE(PRXFPREG),
.n = sizeof(struct user32_fxsr_struct) / sizeof(long),
#else
- .core_note_type = NT_PRFPREG,
+ USER_REGSET_NOTE_TYPE(PRFPREG),
.n = sizeof(struct user_i387_struct) / sizeof(long),
#endif
.size = sizeof(long),
@@ -232,7 +270,7 @@ static struct user_regset uml_regsets[] __ro_after_init = {
.set = generic_fpregs_set,
},
[REGSET_XSTATE] = {
- .core_note_type = NT_X86_XSTATE,
+ USER_REGSET_NOTE_TYPE(X86_XSTATE),
.size = sizeof(long),
.align = sizeof(long),
.active = generic_fpregs_active,
diff --git a/arch/x86/um/shared/sysdep/kernel-offsets.h b/arch/x86/um/shared/sysdep/kernel-offsets.h
index 48de3a71f845..6fd1ed400399 100644
--- a/arch/x86/um/shared/sysdep/kernel-offsets.h
+++ b/arch/x86/um/shared/sysdep/kernel-offsets.h
@@ -4,7 +4,9 @@
#include <linux/elf.h>
#include <linux/crypto.h>
#include <linux/kbuild.h>
+#include <linux/audit.h>
#include <asm/mman.h>
+#include <asm/seccomp.h>
/* workaround for a warning with -Wmissing-prototypes */
void foo(void);
diff --git a/arch/x86/um/shared/sysdep/mcontext.h b/arch/x86/um/shared/sysdep/mcontext.h
index b724c54da316..6fe490cc5b98 100644
--- a/arch/x86/um/shared/sysdep/mcontext.h
+++ b/arch/x86/um/shared/sysdep/mcontext.h
@@ -6,7 +6,16 @@
#ifndef __SYS_SIGCONTEXT_X86_H
#define __SYS_SIGCONTEXT_X86_H
+#include <stub-data.h>
+
extern void get_regs_from_mc(struct uml_pt_regs *, mcontext_t *);
+extern void get_mc_from_regs(struct uml_pt_regs *regs, mcontext_t *mc,
+ int single_stepping);
+
+extern int get_stub_state(struct uml_pt_regs *regs, struct stub_data *data,
+ unsigned long *fp_size_out);
+extern int set_stub_state(struct uml_pt_regs *regs, struct stub_data *data,
+ int single_stepping);
#ifdef __i386__
diff --git a/arch/x86/um/shared/sysdep/ptrace.h b/arch/x86/um/shared/sysdep/ptrace.h
index 8f7476ff6e95..572ea2d79131 100644
--- a/arch/x86/um/shared/sysdep/ptrace.h
+++ b/arch/x86/um/shared/sysdep/ptrace.h
@@ -44,18 +44,6 @@
#include "ptrace_64.h"
#endif
-struct syscall_args {
- unsigned long args[6];
-};
-
-#define SYSCALL_ARGS(r) ((struct syscall_args) \
- { .args = { UPT_SYSCALL_ARG1(r), \
- UPT_SYSCALL_ARG2(r), \
- UPT_SYSCALL_ARG3(r), \
- UPT_SYSCALL_ARG4(r), \
- UPT_SYSCALL_ARG5(r), \
- UPT_SYSCALL_ARG6(r) } } )
-
extern unsigned long host_fp_size;
struct uml_pt_regs {
diff --git a/arch/x86/um/shared/sysdep/stub-data.h b/arch/x86/um/shared/sysdep/stub-data.h
new file mode 100644
index 000000000000..82b1b7f8ac3d
--- /dev/null
+++ b/arch/x86/um/shared/sysdep/stub-data.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __ARCH_STUB_DATA_H
+#define __ARCH_STUB_DATA_H
+
+#ifdef __i386__
+#include <generated/asm-offsets.h>
+#include <asm/ldt.h>
+
+struct stub_data_arch {
+ int sync;
+ struct user_desc tls[UM_KERN_GDT_ENTRY_TLS_ENTRIES];
+};
+#else
+#define STUB_SYNC_FS_BASE (1 << 0)
+#define STUB_SYNC_GS_BASE (1 << 1)
+struct stub_data_arch {
+ int sync;
+ unsigned long fs_base;
+ unsigned long gs_base;
+};
+#endif
+
+#endif /* __ARCH_STUB_DATA_H */
diff --git a/arch/x86/um/shared/sysdep/stub.h b/arch/x86/um/shared/sysdep/stub.h
index dc89f4423454..4fa58f5b4fca 100644
--- a/arch/x86/um/shared/sysdep/stub.h
+++ b/arch/x86/um/shared/sysdep/stub.h
@@ -13,3 +13,5 @@
extern void stub_segv_handler(int, siginfo_t *, void *);
extern void stub_syscall_handler(void);
+extern void stub_signal_interrupt(int, siginfo_t *, void *);
+extern void stub_signal_restorer(void);
diff --git a/arch/x86/um/shared/sysdep/stub_32.h b/arch/x86/um/shared/sysdep/stub_32.h
index 390988132c0a..df568fc3ceb4 100644
--- a/arch/x86/um/shared/sysdep/stub_32.h
+++ b/arch/x86/um/shared/sysdep/stub_32.h
@@ -131,4 +131,17 @@ static __always_inline void *get_stub_data(void)
"call *%%eax ;" \
:: "i" ((1 + STUB_DATA_PAGES) * UM_KERN_PAGE_SIZE), \
"i" (&fn))
+
+static __always_inline void
+stub_seccomp_restore_state(struct stub_data_arch *arch)
+{
+ for (int i = 0; i < sizeof(arch->tls) / sizeof(arch->tls[0]); i++) {
+ if (arch->sync & (1 << i))
+ stub_syscall1(__NR_set_thread_area,
+ (unsigned long) &arch->tls[i]);
+ }
+
+ arch->sync = 0;
+}
+
#endif
diff --git a/arch/x86/um/shared/sysdep/stub_64.h b/arch/x86/um/shared/sysdep/stub_64.h
index 294affbec742..9cfd31afa769 100644
--- a/arch/x86/um/shared/sysdep/stub_64.h
+++ b/arch/x86/um/shared/sysdep/stub_64.h
@@ -10,6 +10,7 @@
#include <sysdep/ptrace_user.h>
#include <generated/asm-offsets.h>
#include <linux/stddef.h>
+#include <asm/prctl.h>
#define STUB_MMAP_NR __NR_mmap
#define MMAP_OFFSET(o) (o)
@@ -134,4 +135,20 @@ static __always_inline void *get_stub_data(void)
"call *%%rax ;" \
:: "i" ((1 + STUB_DATA_PAGES) * UM_KERN_PAGE_SIZE), \
"i" (&fn))
+
+static __always_inline void
+stub_seccomp_restore_state(struct stub_data_arch *arch)
+{
+ /*
+ * We could use _writefsbase_u64/_writegsbase_u64 if the host reports
+ * support in the hwcaps (HWCAP2_FSGSBASE).
+ */
+ if (arch->sync & STUB_SYNC_FS_BASE)
+ stub_syscall2(__NR_arch_prctl, ARCH_SET_FS, arch->fs_base);
+ if (arch->sync & STUB_SYNC_GS_BASE)
+ stub_syscall2(__NR_arch_prctl, ARCH_SET_GS, arch->gs_base);
+
+ arch->sync = 0;
+}
+
#endif
diff --git a/arch/x86/um/shared/sysdep/syscalls.h b/arch/x86/um/shared/sysdep/syscalls.h
deleted file mode 100644
index b2060ac707f0..000000000000
--- a/arch/x86/um/shared/sysdep/syscalls.h
+++ /dev/null
@@ -1,6 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifdef __i386__
-#include "syscalls_32.h"
-#else
-#include "syscalls_64.h"
-#endif
diff --git a/arch/x86/um/shared/sysdep/syscalls_32.h b/arch/x86/um/shared/sysdep/syscalls_32.h
deleted file mode 100644
index f6e9f84397e7..000000000000
--- a/arch/x86/um/shared/sysdep/syscalls_32.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- * Copyright (C) 2000 - 2008 Jeff Dike (jdike@{addtoit,linux.intel}.com)
- * Licensed under the GPL
- */
-
-#include <asm/unistd.h>
-#include <sysdep/ptrace.h>
-
-typedef long syscall_handler_t(struct syscall_args);
-
-extern syscall_handler_t *sys_call_table[];
-
-#define EXECUTE_SYSCALL(syscall, regs) \
- ((*sys_call_table[syscall]))(SYSCALL_ARGS(&regs->regs))
diff --git a/arch/x86/um/shared/sysdep/syscalls_64.h b/arch/x86/um/shared/sysdep/syscalls_64.h
deleted file mode 100644
index b6b997225841..000000000000
--- a/arch/x86/um/shared/sysdep/syscalls_64.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright 2003 PathScale, Inc.
- *
- * Licensed under the GPL
- */
-
-#ifndef __SYSDEP_X86_64_SYSCALLS_H__
-#define __SYSDEP_X86_64_SYSCALLS_H__
-
-#include <linux/msg.h>
-#include <linux/shm.h>
-
-typedef long syscall_handler_t(long, long, long, long, long, long);
-
-extern syscall_handler_t *sys_call_table[];
-
-#define EXECUTE_SYSCALL(syscall, regs) \
- (((*sys_call_table[syscall]))(UPT_SYSCALL_ARG1(&regs->regs), \
- UPT_SYSCALL_ARG2(&regs->regs), \
- UPT_SYSCALL_ARG3(&regs->regs), \
- UPT_SYSCALL_ARG4(&regs->regs), \
- UPT_SYSCALL_ARG5(&regs->regs), \
- UPT_SYSCALL_ARG6(&regs->regs)))
-
-extern syscall_handler_t sys_modify_ldt;
-extern syscall_handler_t sys_arch_prctl;
-
-#endif
diff --git a/arch/x86/um/tls_32.c b/arch/x86/um/tls_32.c
index fbb129023080..1909c2e640b2 100644
--- a/arch/x86/um/tls_32.c
+++ b/arch/x86/um/tls_32.c
@@ -12,6 +12,7 @@
#include <skas.h>
#include <sysdep/tls.h>
#include <asm/desc.h>
+#include <stub-data.h>
/*
* If needed we can detect when it's uninitialized.
@@ -21,14 +22,25 @@
static int host_supports_tls = -1;
int host_gdt_entry_tls_min;
-static int do_set_thread_area(struct user_desc *info)
+static int do_set_thread_area(struct task_struct* task, struct user_desc *info)
{
int ret;
- u32 cpu;
- cpu = get_cpu();
- ret = os_set_thread_area(info, userspace_pid[cpu]);
- put_cpu();
+ if (info->entry_number < host_gdt_entry_tls_min ||
+ info->entry_number >= host_gdt_entry_tls_min + GDT_ENTRY_TLS_ENTRIES)
+ return -EINVAL;
+
+ if (using_seccomp) {
+ int idx = info->entry_number - host_gdt_entry_tls_min;
+ struct stub_data *data = (void *)task->mm->context.id.stack;
+
+ data->arch_data.tls[idx] = *info;
+ data->arch_data.sync |= BIT(idx);
+
+ return 0;
+ }
+
+ ret = os_set_thread_area(info, task->mm->context.id.pid);
if (ret)
printk(KERN_ERR "PTRACE_SET_THREAD_AREA failed, err = %d, "
@@ -97,7 +109,7 @@ static int load_TLS(int flags, struct task_struct *to)
if (!(flags & O_FORCE) && curr->flushed)
continue;
- ret = do_set_thread_area(&curr->tls);
+ ret = do_set_thread_area(current, &curr->tls);
if (ret)
goto out;
@@ -174,7 +186,7 @@ int arch_switch_tls(struct task_struct *to)
/*
* We have no need whatsoever to switch TLS for kernel threads; beyond
* that, that would also result in us calling os_set_thread_area with
- * userspace_pid[cpu] == 0, which gives an error.
+ * task->mm == NULL, which would cause a crash.
*/
if (likely(to->mm))
return load_TLS(O_FORCE, to);
@@ -275,7 +287,7 @@ SYSCALL_DEFINE1(set_thread_area, struct user_desc __user *, user_desc)
return -EFAULT;
}
- ret = do_set_thread_area(&info);
+ ret = do_set_thread_area(current, &info);
if (ret)
return ret;
return set_tls_entry(current, &info, idx, 1);
diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
index fc473ca12c44..942372e69b4d 100644
--- a/arch/x86/virt/svm/sev.c
+++ b/arch/x86/virt/svm/sev.c
@@ -27,9 +27,10 @@
#include <asm/smp.h>
#include <asm/cpu.h>
#include <asm/apic.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/cmdline.h>
#include <asm/iommu.h>
+#include <asm/msr.h>
/*
* The RMP entry information as returned by the RMPREAD instruction.
@@ -136,11 +137,11 @@ static int __mfd_enable(unsigned int cpu)
if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return 0;
- rdmsrl(MSR_AMD64_SYSCFG, val);
+ rdmsrq(MSR_AMD64_SYSCFG, val);
val |= MSR_AMD64_SYSCFG_MFDM;
- wrmsrl(MSR_AMD64_SYSCFG, val);
+ wrmsrq(MSR_AMD64_SYSCFG, val);
return 0;
}
@@ -157,12 +158,12 @@ static int __snp_enable(unsigned int cpu)
if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
return 0;
- rdmsrl(MSR_AMD64_SYSCFG, val);
+ rdmsrq(MSR_AMD64_SYSCFG, val);
val |= MSR_AMD64_SYSCFG_SNP_EN;
val |= MSR_AMD64_SYSCFG_SNP_VMPL_EN;
- wrmsrl(MSR_AMD64_SYSCFG, val);
+ wrmsrq(MSR_AMD64_SYSCFG, val);
return 0;
}
@@ -522,7 +523,7 @@ int __init snp_rmptable_init(void)
* Check if SEV-SNP is already enabled, this can happen in case of
* kexec boot.
*/
- rdmsrl(MSR_AMD64_SYSCFG, val);
+ rdmsrq(MSR_AMD64_SYSCFG, val);
if (val & MSR_AMD64_SYSCFG_SNP_EN)
goto skip_enable;
@@ -576,8 +577,8 @@ static bool probe_contiguous_rmptable_info(void)
{
u64 rmp_sz, rmp_base, rmp_end;
- rdmsrl(MSR_AMD64_RMP_BASE, rmp_base);
- rdmsrl(MSR_AMD64_RMP_END, rmp_end);
+ rdmsrq(MSR_AMD64_RMP_BASE, rmp_base);
+ rdmsrq(MSR_AMD64_RMP_END, rmp_end);
if (!(rmp_base & RMP_ADDR_MASK) || !(rmp_end & RMP_ADDR_MASK)) {
pr_err("Memory for the RMP table has not been reserved by BIOS\n");
@@ -610,13 +611,13 @@ static bool probe_segmented_rmptable_info(void)
unsigned int eax, ebx, segment_shift, segment_shift_min, segment_shift_max;
u64 rmp_base, rmp_end;
- rdmsrl(MSR_AMD64_RMP_BASE, rmp_base);
+ rdmsrq(MSR_AMD64_RMP_BASE, rmp_base);
if (!(rmp_base & RMP_ADDR_MASK)) {
pr_err("Memory for the RMP table has not been reserved by BIOS\n");
return false;
}
- rdmsrl(MSR_AMD64_RMP_END, rmp_end);
+ rdmsrq(MSR_AMD64_RMP_END, rmp_end);
WARN_ONCE(rmp_end & RMP_ADDR_MASK,
"Segmented RMP enabled but RMP_END MSR is non-zero\n");
@@ -652,7 +653,7 @@ static bool probe_segmented_rmptable_info(void)
bool snp_probe_rmptable_info(void)
{
if (cpu_feature_enabled(X86_FEATURE_SEGMENTED_RMP))
- rdmsrl(MSR_AMD64_RMP_CFG, rmp_cfg);
+ rdmsrq(MSR_AMD64_RMP_CFG, rmp_cfg);
if (rmp_cfg & MSR_AMD64_SEG_RMP_ENABLED)
return probe_segmented_rmptable_info();
diff --git a/arch/x86/virt/vmx/tdx/seamcall.S b/arch/x86/virt/vmx/tdx/seamcall.S
index 5b1f2286aea9..6854c52c374b 100644
--- a/arch/x86/virt/vmx/tdx/seamcall.S
+++ b/arch/x86/virt/vmx/tdx/seamcall.S
@@ -41,6 +41,9 @@ SYM_FUNC_START(__seamcall_ret)
TDX_MODULE_CALL host=1 ret=1
SYM_FUNC_END(__seamcall_ret)
+/* KVM requires non-instrumentable __seamcall_saved_ret() for TDH.VP.ENTER */
+.section .noinstr.text, "ax"
+
/*
* __seamcall_saved_ret() - Host-side interface functions to SEAM software
* (the P-SEAMLDR or the TDX module), with saving output registers to the
diff --git a/arch/x86/virt/vmx/tdx/tdx.c b/arch/x86/virt/vmx/tdx/tdx.c
index 7fdb37387886..c7a9a087ccaf 100644
--- a/arch/x86/virt/vmx/tdx/tdx.c
+++ b/arch/x86/virt/vmx/tdx/tdx.c
@@ -5,6 +5,7 @@
* Intel Trusted Domain Extensions (TDX) support
*/
+#include "asm/page_types.h"
#define pr_fmt(fmt) "virt/tdx: " fmt
#include <linux/types.h>
@@ -27,6 +28,7 @@
#include <linux/log2.h>
#include <linux/acpi.h>
#include <linux/suspend.h>
+#include <linux/idr.h>
#include <asm/page.h>
#include <asm/special_insns.h>
#include <asm/msr-index.h>
@@ -42,6 +44,8 @@ static u32 tdx_global_keyid __ro_after_init;
static u32 tdx_guest_keyid_start __ro_after_init;
static u32 tdx_nr_guest_keyids __ro_after_init;
+static DEFINE_IDA(tdx_guest_keyid_pool);
+
static DEFINE_PER_CPU(bool, tdx_lp_initialized);
static struct tdmr_info_list tdx_tdmr_list;
@@ -52,6 +56,8 @@ static DEFINE_MUTEX(tdx_module_lock);
/* All TDX-usable memory regions. Protected by mem_hotplug_lock. */
static LIST_HEAD(tdx_memlist);
+static struct tdx_sys_info tdx_sysinfo;
+
typedef void (*sc_err_func_t)(u64 fn, u64 err, struct tdx_module_args *args);
static inline void seamcall_err(u64 fn, u64 err, struct tdx_module_args *args)
@@ -69,8 +75,9 @@ static inline void seamcall_err_ret(u64 fn, u64 err,
args->r9, args->r10, args->r11);
}
-static inline int sc_retry_prerr(sc_func_t func, sc_err_func_t err_func,
- u64 fn, struct tdx_module_args *args)
+static __always_inline int sc_retry_prerr(sc_func_t func,
+ sc_err_func_t err_func,
+ u64 fn, struct tdx_module_args *args)
{
u64 sret = sc_retry(func, fn, args);
@@ -1060,15 +1067,14 @@ static int init_tdmrs(struct tdmr_info_list *tdmr_list)
static int init_tdx_module(void)
{
- struct tdx_sys_info sysinfo;
int ret;
- ret = get_tdx_sys_info(&sysinfo);
+ ret = get_tdx_sys_info(&tdx_sysinfo);
if (ret)
return ret;
/* Check whether the kernel can support this module */
- ret = check_features(&sysinfo);
+ ret = check_features(&tdx_sysinfo);
if (ret)
return ret;
@@ -1089,12 +1095,12 @@ static int init_tdx_module(void)
goto out_put_tdxmem;
/* Allocate enough space for constructing TDMRs */
- ret = alloc_tdmr_list(&tdx_tdmr_list, &sysinfo.tdmr);
+ ret = alloc_tdmr_list(&tdx_tdmr_list, &tdx_sysinfo.tdmr);
if (ret)
goto err_free_tdxmem;
/* Cover all TDX-usable memory regions in TDMRs */
- ret = construct_tdmrs(&tdx_memlist, &tdx_tdmr_list, &sysinfo.tdmr);
+ ret = construct_tdmrs(&tdx_memlist, &tdx_tdmr_list, &tdx_sysinfo.tdmr);
if (ret)
goto err_free_tdmrs;
@@ -1456,3 +1462,411 @@ void __init tdx_init(void)
check_tdx_erratum();
}
+
+const struct tdx_sys_info *tdx_get_sysinfo(void)
+{
+ const struct tdx_sys_info *p = NULL;
+
+ /* Make sure all fields in @tdx_sysinfo have been populated */
+ mutex_lock(&tdx_module_lock);
+ if (tdx_module_status == TDX_MODULE_INITIALIZED)
+ p = (const struct tdx_sys_info *)&tdx_sysinfo;
+ mutex_unlock(&tdx_module_lock);
+
+ return p;
+}
+EXPORT_SYMBOL_GPL(tdx_get_sysinfo);
+
+u32 tdx_get_nr_guest_keyids(void)
+{
+ return tdx_nr_guest_keyids;
+}
+EXPORT_SYMBOL_GPL(tdx_get_nr_guest_keyids);
+
+int tdx_guest_keyid_alloc(void)
+{
+ return ida_alloc_range(&tdx_guest_keyid_pool, tdx_guest_keyid_start,
+ tdx_guest_keyid_start + tdx_nr_guest_keyids - 1,
+ GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(tdx_guest_keyid_alloc);
+
+void tdx_guest_keyid_free(unsigned int keyid)
+{
+ ida_free(&tdx_guest_keyid_pool, keyid);
+}
+EXPORT_SYMBOL_GPL(tdx_guest_keyid_free);
+
+static inline u64 tdx_tdr_pa(struct tdx_td *td)
+{
+ return page_to_phys(td->tdr_page);
+}
+
+static inline u64 tdx_tdvpr_pa(struct tdx_vp *td)
+{
+ return page_to_phys(td->tdvpr_page);
+}
+
+/*
+ * The TDX module exposes a CLFLUSH_BEFORE_ALLOC bit to specify whether
+ * a CLFLUSH of pages is required before handing them to the TDX module.
+ * Be conservative and make the code simpler by doing the CLFLUSH
+ * unconditionally.
+ */
+static void tdx_clflush_page(struct page *page)
+{
+ clflush_cache_range(page_to_virt(page), PAGE_SIZE);
+}
+
+noinstr __flatten u64 tdh_vp_enter(struct tdx_vp *td, struct tdx_module_args *args)
+{
+ args->rcx = tdx_tdvpr_pa(td);
+
+ return __seamcall_saved_ret(TDH_VP_ENTER, args);
+}
+EXPORT_SYMBOL_GPL(tdh_vp_enter);
+
+u64 tdh_mng_addcx(struct tdx_td *td, struct page *tdcs_page)
+{
+ struct tdx_module_args args = {
+ .rcx = page_to_phys(tdcs_page),
+ .rdx = tdx_tdr_pa(td),
+ };
+
+ tdx_clflush_page(tdcs_page);
+ return seamcall(TDH_MNG_ADDCX, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_mng_addcx);
+
+u64 tdh_mem_page_add(struct tdx_td *td, u64 gpa, struct page *page, struct page *source, u64 *ext_err1, u64 *ext_err2)
+{
+ struct tdx_module_args args = {
+ .rcx = gpa,
+ .rdx = tdx_tdr_pa(td),
+ .r8 = page_to_phys(page),
+ .r9 = page_to_phys(source),
+ };
+ u64 ret;
+
+ tdx_clflush_page(page);
+ ret = seamcall_ret(TDH_MEM_PAGE_ADD, &args);
+
+ *ext_err1 = args.rcx;
+ *ext_err2 = args.rdx;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mem_page_add);
+
+u64 tdh_mem_sept_add(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2)
+{
+ struct tdx_module_args args = {
+ .rcx = gpa | level,
+ .rdx = tdx_tdr_pa(td),
+ .r8 = page_to_phys(page),
+ };
+ u64 ret;
+
+ tdx_clflush_page(page);
+ ret = seamcall_ret(TDH_MEM_SEPT_ADD, &args);
+
+ *ext_err1 = args.rcx;
+ *ext_err2 = args.rdx;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mem_sept_add);
+
+u64 tdh_vp_addcx(struct tdx_vp *vp, struct page *tdcx_page)
+{
+ struct tdx_module_args args = {
+ .rcx = page_to_phys(tdcx_page),
+ .rdx = tdx_tdvpr_pa(vp),
+ };
+
+ tdx_clflush_page(tdcx_page);
+ return seamcall(TDH_VP_ADDCX, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_vp_addcx);
+
+u64 tdh_mem_page_aug(struct tdx_td *td, u64 gpa, int level, struct page *page, u64 *ext_err1, u64 *ext_err2)
+{
+ struct tdx_module_args args = {
+ .rcx = gpa | level,
+ .rdx = tdx_tdr_pa(td),
+ .r8 = page_to_phys(page),
+ };
+ u64 ret;
+
+ tdx_clflush_page(page);
+ ret = seamcall_ret(TDH_MEM_PAGE_AUG, &args);
+
+ *ext_err1 = args.rcx;
+ *ext_err2 = args.rdx;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mem_page_aug);
+
+u64 tdh_mem_range_block(struct tdx_td *td, u64 gpa, int level, u64 *ext_err1, u64 *ext_err2)
+{
+ struct tdx_module_args args = {
+ .rcx = gpa | level,
+ .rdx = tdx_tdr_pa(td),
+ };
+ u64 ret;
+
+ ret = seamcall_ret(TDH_MEM_RANGE_BLOCK, &args);
+
+ *ext_err1 = args.rcx;
+ *ext_err2 = args.rdx;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mem_range_block);
+
+u64 tdh_mng_key_config(struct tdx_td *td)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdr_pa(td),
+ };
+
+ return seamcall(TDH_MNG_KEY_CONFIG, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_mng_key_config);
+
+u64 tdh_mng_create(struct tdx_td *td, u16 hkid)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdr_pa(td),
+ .rdx = hkid,
+ };
+
+ tdx_clflush_page(td->tdr_page);
+ return seamcall(TDH_MNG_CREATE, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_mng_create);
+
+u64 tdh_vp_create(struct tdx_td *td, struct tdx_vp *vp)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdvpr_pa(vp),
+ .rdx = tdx_tdr_pa(td),
+ };
+
+ tdx_clflush_page(vp->tdvpr_page);
+ return seamcall(TDH_VP_CREATE, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_vp_create);
+
+u64 tdh_mng_rd(struct tdx_td *td, u64 field, u64 *data)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdr_pa(td),
+ .rdx = field,
+ };
+ u64 ret;
+
+ ret = seamcall_ret(TDH_MNG_RD, &args);
+
+ /* R8: Content of the field, or 0 in case of error. */
+ *data = args.r8;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mng_rd);
+
+u64 tdh_mr_extend(struct tdx_td *td, u64 gpa, u64 *ext_err1, u64 *ext_err2)
+{
+ struct tdx_module_args args = {
+ .rcx = gpa,
+ .rdx = tdx_tdr_pa(td),
+ };
+ u64 ret;
+
+ ret = seamcall_ret(TDH_MR_EXTEND, &args);
+
+ *ext_err1 = args.rcx;
+ *ext_err2 = args.rdx;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mr_extend);
+
+u64 tdh_mr_finalize(struct tdx_td *td)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdr_pa(td),
+ };
+
+ return seamcall(TDH_MR_FINALIZE, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_mr_finalize);
+
+u64 tdh_vp_flush(struct tdx_vp *vp)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdvpr_pa(vp),
+ };
+
+ return seamcall(TDH_VP_FLUSH, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_vp_flush);
+
+u64 tdh_mng_vpflushdone(struct tdx_td *td)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdr_pa(td),
+ };
+
+ return seamcall(TDH_MNG_VPFLUSHDONE, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_mng_vpflushdone);
+
+u64 tdh_mng_key_freeid(struct tdx_td *td)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdr_pa(td),
+ };
+
+ return seamcall(TDH_MNG_KEY_FREEID, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_mng_key_freeid);
+
+u64 tdh_mng_init(struct tdx_td *td, u64 td_params, u64 *extended_err)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdr_pa(td),
+ .rdx = td_params,
+ };
+ u64 ret;
+
+ ret = seamcall_ret(TDH_MNG_INIT, &args);
+
+ *extended_err = args.rcx;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mng_init);
+
+u64 tdh_vp_rd(struct tdx_vp *vp, u64 field, u64 *data)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdvpr_pa(vp),
+ .rdx = field,
+ };
+ u64 ret;
+
+ ret = seamcall_ret(TDH_VP_RD, &args);
+
+ /* R8: Content of the field, or 0 in case of error. */
+ *data = args.r8;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_vp_rd);
+
+u64 tdh_vp_wr(struct tdx_vp *vp, u64 field, u64 data, u64 mask)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdvpr_pa(vp),
+ .rdx = field,
+ .r8 = data,
+ .r9 = mask,
+ };
+
+ return seamcall(TDH_VP_WR, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_vp_wr);
+
+u64 tdh_vp_init(struct tdx_vp *vp, u64 initial_rcx, u32 x2apicid)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdvpr_pa(vp),
+ .rdx = initial_rcx,
+ .r8 = x2apicid,
+ };
+
+ /* apicid requires version == 1. */
+ return seamcall(TDH_VP_INIT | (1ULL << TDX_VERSION_SHIFT), &args);
+}
+EXPORT_SYMBOL_GPL(tdh_vp_init);
+
+/*
+ * TDX ABI defines output operands as PT, OWNER and SIZE. These are TDX defined fomats.
+ * So despite the names, they must be interpted specially as described by the spec. Return
+ * them only for error reporting purposes.
+ */
+u64 tdh_phymem_page_reclaim(struct page *page, u64 *tdx_pt, u64 *tdx_owner, u64 *tdx_size)
+{
+ struct tdx_module_args args = {
+ .rcx = page_to_phys(page),
+ };
+ u64 ret;
+
+ ret = seamcall_ret(TDH_PHYMEM_PAGE_RECLAIM, &args);
+
+ *tdx_pt = args.rcx;
+ *tdx_owner = args.rdx;
+ *tdx_size = args.r8;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_phymem_page_reclaim);
+
+u64 tdh_mem_track(struct tdx_td *td)
+{
+ struct tdx_module_args args = {
+ .rcx = tdx_tdr_pa(td),
+ };
+
+ return seamcall(TDH_MEM_TRACK, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_mem_track);
+
+u64 tdh_mem_page_remove(struct tdx_td *td, u64 gpa, u64 level, u64 *ext_err1, u64 *ext_err2)
+{
+ struct tdx_module_args args = {
+ .rcx = gpa | level,
+ .rdx = tdx_tdr_pa(td),
+ };
+ u64 ret;
+
+ ret = seamcall_ret(TDH_MEM_PAGE_REMOVE, &args);
+
+ *ext_err1 = args.rcx;
+ *ext_err2 = args.rdx;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(tdh_mem_page_remove);
+
+u64 tdh_phymem_cache_wb(bool resume)
+{
+ struct tdx_module_args args = {
+ .rcx = resume ? 1 : 0,
+ };
+
+ return seamcall(TDH_PHYMEM_CACHE_WB, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_phymem_cache_wb);
+
+u64 tdh_phymem_page_wbinvd_tdr(struct tdx_td *td)
+{
+ struct tdx_module_args args = {};
+
+ args.rcx = mk_keyed_paddr(tdx_global_keyid, td->tdr_page);
+
+ return seamcall(TDH_PHYMEM_PAGE_WBINVD, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_phymem_page_wbinvd_tdr);
+
+u64 tdh_phymem_page_wbinvd_hkid(u64 hkid, struct page *page)
+{
+ struct tdx_module_args args = {};
+
+ args.rcx = mk_keyed_paddr(hkid, page);
+
+ return seamcall(TDH_PHYMEM_PAGE_WBINVD, &args);
+}
+EXPORT_SYMBOL_GPL(tdh_phymem_page_wbinvd_hkid);
diff --git a/arch/x86/virt/vmx/tdx/tdx.h b/arch/x86/virt/vmx/tdx/tdx.h
index 4e3d533cdd61..82bb82be8567 100644
--- a/arch/x86/virt/vmx/tdx/tdx.h
+++ b/arch/x86/virt/vmx/tdx/tdx.h
@@ -3,7 +3,6 @@
#define _X86_VIRT_TDX_H
#include <linux/bits.h>
-#include "tdx_global_metadata.h"
/*
* This file contains both macros and data structures defined by the TDX
@@ -15,13 +14,46 @@
/*
* TDX module SEAMCALL leaf functions
*/
-#define TDH_PHYMEM_PAGE_RDMD 24
-#define TDH_SYS_KEY_CONFIG 31
-#define TDH_SYS_INIT 33
-#define TDH_SYS_RD 34
-#define TDH_SYS_LP_INIT 35
-#define TDH_SYS_TDMR_INIT 36
-#define TDH_SYS_CONFIG 45
+#define TDH_VP_ENTER 0
+#define TDH_MNG_ADDCX 1
+#define TDH_MEM_PAGE_ADD 2
+#define TDH_MEM_SEPT_ADD 3
+#define TDH_VP_ADDCX 4
+#define TDH_MEM_PAGE_AUG 6
+#define TDH_MEM_RANGE_BLOCK 7
+#define TDH_MNG_KEY_CONFIG 8
+#define TDH_MNG_CREATE 9
+#define TDH_MNG_RD 11
+#define TDH_MR_EXTEND 16
+#define TDH_MR_FINALIZE 17
+#define TDH_VP_FLUSH 18
+#define TDH_MNG_VPFLUSHDONE 19
+#define TDH_VP_CREATE 10
+#define TDH_MNG_KEY_FREEID 20
+#define TDH_MNG_INIT 21
+#define TDH_VP_INIT 22
+#define TDH_PHYMEM_PAGE_RDMD 24
+#define TDH_VP_RD 26
+#define TDH_PHYMEM_PAGE_RECLAIM 28
+#define TDH_MEM_PAGE_REMOVE 29
+#define TDH_SYS_KEY_CONFIG 31
+#define TDH_SYS_INIT 33
+#define TDH_SYS_RD 34
+#define TDH_SYS_LP_INIT 35
+#define TDH_SYS_TDMR_INIT 36
+#define TDH_MEM_TRACK 38
+#define TDH_PHYMEM_CACHE_WB 40
+#define TDH_PHYMEM_PAGE_WBINVD 41
+#define TDH_VP_WR 43
+#define TDH_SYS_CONFIG 45
+
+/*
+ * SEAMCALL leaf:
+ *
+ * Bit 15:0 Leaf number
+ * Bit 23:16 Version number
+ */
+#define TDX_VERSION_SHIFT 16
/* TDX page types */
#define PT_NDA 0x0
diff --git a/arch/x86/virt/vmx/tdx/tdx_global_metadata.c b/arch/x86/virt/vmx/tdx/tdx_global_metadata.c
index 8027a24d1c6e..13ad2663488b 100644
--- a/arch/x86/virt/vmx/tdx/tdx_global_metadata.c
+++ b/arch/x86/virt/vmx/tdx/tdx_global_metadata.c
@@ -37,12 +37,62 @@ static int get_tdx_sys_info_tdmr(struct tdx_sys_info_tdmr *sysinfo_tdmr)
return ret;
}
+static int get_tdx_sys_info_td_ctrl(struct tdx_sys_info_td_ctrl *sysinfo_td_ctrl)
+{
+ int ret = 0;
+ u64 val;
+
+ if (!ret && !(ret = read_sys_metadata_field(0x9800000100000000, &val)))
+ sysinfo_td_ctrl->tdr_base_size = val;
+ if (!ret && !(ret = read_sys_metadata_field(0x9800000100000100, &val)))
+ sysinfo_td_ctrl->tdcs_base_size = val;
+ if (!ret && !(ret = read_sys_metadata_field(0x9800000100000200, &val)))
+ sysinfo_td_ctrl->tdvps_base_size = val;
+
+ return ret;
+}
+
+static int get_tdx_sys_info_td_conf(struct tdx_sys_info_td_conf *sysinfo_td_conf)
+{
+ int ret = 0;
+ u64 val;
+ int i, j;
+
+ if (!ret && !(ret = read_sys_metadata_field(0x1900000300000000, &val)))
+ sysinfo_td_conf->attributes_fixed0 = val;
+ if (!ret && !(ret = read_sys_metadata_field(0x1900000300000001, &val)))
+ sysinfo_td_conf->attributes_fixed1 = val;
+ if (!ret && !(ret = read_sys_metadata_field(0x1900000300000002, &val)))
+ sysinfo_td_conf->xfam_fixed0 = val;
+ if (!ret && !(ret = read_sys_metadata_field(0x1900000300000003, &val)))
+ sysinfo_td_conf->xfam_fixed1 = val;
+ if (!ret && !(ret = read_sys_metadata_field(0x9900000100000004, &val)))
+ sysinfo_td_conf->num_cpuid_config = val;
+ if (!ret && !(ret = read_sys_metadata_field(0x9900000100000008, &val)))
+ sysinfo_td_conf->max_vcpus_per_td = val;
+ if (sysinfo_td_conf->num_cpuid_config > ARRAY_SIZE(sysinfo_td_conf->cpuid_config_leaves))
+ return -EINVAL;
+ for (i = 0; i < sysinfo_td_conf->num_cpuid_config; i++)
+ if (!ret && !(ret = read_sys_metadata_field(0x9900000300000400 + i, &val)))
+ sysinfo_td_conf->cpuid_config_leaves[i] = val;
+ if (sysinfo_td_conf->num_cpuid_config > ARRAY_SIZE(sysinfo_td_conf->cpuid_config_values))
+ return -EINVAL;
+ for (i = 0; i < sysinfo_td_conf->num_cpuid_config; i++)
+ for (j = 0; j < 2; j++)
+ if (!ret && !(ret = read_sys_metadata_field(0x9900000300000500 + i * 2 + j, &val)))
+ sysinfo_td_conf->cpuid_config_values[i][j] = val;
+
+ return ret;
+}
+
static int get_tdx_sys_info(struct tdx_sys_info *sysinfo)
{
int ret = 0;
ret = ret ?: get_tdx_sys_info_features(&sysinfo->features);
ret = ret ?: get_tdx_sys_info_tdmr(&sysinfo->tdmr);
+ ret = ret ?: get_tdx_sys_info_td_ctrl(&sysinfo->td_ctrl);
+ ret = ret ?: get_tdx_sys_info_td_conf(&sysinfo->td_conf);
return ret;
}
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 846b5737d320..26bbaf4b7330 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -49,7 +49,7 @@
#include <xen/hvc-console.h>
#include <xen/acpi.h>
-#include <asm/cpuid.h>
+#include <asm/cpuid/api.h>
#include <asm/paravirt.h>
#include <asm/apic.h>
#include <asm/page.h>
@@ -61,6 +61,7 @@
#include <asm/processor.h>
#include <asm/proto.h>
#include <asm/msr-index.h>
+#include <asm/msr.h>
#include <asm/traps.h>
#include <asm/setup.h>
#include <asm/desc.h>
@@ -1086,15 +1087,15 @@ static void xen_write_cr4(unsigned long cr4)
native_write_cr4(cr4);
}
-static u64 xen_do_read_msr(unsigned int msr, int *err)
+static u64 xen_do_read_msr(u32 msr, int *err)
{
u64 val = 0; /* Avoid uninitialized value for safe variant. */
- if (pmu_msr_read(msr, &val, err))
+ if (pmu_msr_chk_emulated(msr, &val, true))
return val;
if (err)
- val = native_read_msr_safe(msr, err);
+ *err = native_read_msr_safe(msr, &val);
else
val = native_read_msr(msr);
@@ -1110,17 +1111,9 @@ static u64 xen_do_read_msr(unsigned int msr, int *err)
return val;
}
-static void set_seg(unsigned int which, unsigned int low, unsigned int high,
- int *err)
+static void set_seg(u32 which, u64 base)
{
- u64 base = ((u64)high << 32) | low;
-
- if (HYPERVISOR_set_segment_base(which, base) == 0)
- return;
-
- if (err)
- *err = -EIO;
- else
+ if (HYPERVISOR_set_segment_base(which, base))
WARN(1, "Xen set_segment_base(%u, %llx) failed\n", which, base);
}
@@ -1129,20 +1122,19 @@ static void set_seg(unsigned int which, unsigned int low, unsigned int high,
* With err == NULL write_msr() semantics are selected.
* Supplying an err pointer requires err to be pre-initialized with 0.
*/
-static void xen_do_write_msr(unsigned int msr, unsigned int low,
- unsigned int high, int *err)
+static void xen_do_write_msr(u32 msr, u64 val, int *err)
{
switch (msr) {
case MSR_FS_BASE:
- set_seg(SEGBASE_FS, low, high, err);
+ set_seg(SEGBASE_FS, val);
break;
case MSR_KERNEL_GS_BASE:
- set_seg(SEGBASE_GS_USER, low, high, err);
+ set_seg(SEGBASE_GS_USER, val);
break;
case MSR_GS_BASE:
- set_seg(SEGBASE_GS_KERNEL, low, high, err);
+ set_seg(SEGBASE_GS_KERNEL, val);
break;
case MSR_STAR:
@@ -1158,42 +1150,45 @@ static void xen_do_write_msr(unsigned int msr, unsigned int low,
break;
default:
- if (!pmu_msr_write(msr, low, high, err)) {
- if (err)
- *err = native_write_msr_safe(msr, low, high);
- else
- native_write_msr(msr, low, high);
- }
+ if (pmu_msr_chk_emulated(msr, &val, false))
+ return;
+
+ if (err)
+ *err = native_write_msr_safe(msr, val);
+ else
+ native_write_msr(msr, val);
}
}
-static u64 xen_read_msr_safe(unsigned int msr, int *err)
+static int xen_read_msr_safe(u32 msr, u64 *val)
{
- return xen_do_read_msr(msr, err);
+ int err = 0;
+
+ *val = xen_do_read_msr(msr, &err);
+ return err;
}
-static int xen_write_msr_safe(unsigned int msr, unsigned int low,
- unsigned int high)
+static int xen_write_msr_safe(u32 msr, u64 val)
{
int err = 0;
- xen_do_write_msr(msr, low, high, &err);
+ xen_do_write_msr(msr, val, &err);
return err;
}
-static u64 xen_read_msr(unsigned int msr)
+static u64 xen_read_msr(u32 msr)
{
- int err;
+ int err = 0;
return xen_do_read_msr(msr, xen_msr_safe ? &err : NULL);
}
-static void xen_write_msr(unsigned int msr, unsigned low, unsigned high)
+static void xen_write_msr(u32 msr, u64 val)
{
int err;
- xen_do_write_msr(msr, low, high, xen_msr_safe ? &err : NULL);
+ xen_do_write_msr(msr, val, xen_msr_safe ? &err : NULL);
}
/* This is called once we have the cpu_possible_mask */
diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
index 38971c6dcd4b..2a4a8deaf612 100644
--- a/arch/x86/xen/mmu_pv.c
+++ b/arch/x86/xen/mmu_pv.c
@@ -578,7 +578,6 @@ static void xen_set_p4d(p4d_t *ptr, p4d_t val)
xen_mc_issue(XEN_LAZY_MMU);
}
-#if CONFIG_PGTABLE_LEVELS >= 5
__visible p4dval_t xen_p4d_val(p4d_t p4d)
{
return pte_mfn_to_pfn(p4d.p4d);
@@ -592,7 +591,6 @@ __visible p4d_t xen_make_p4d(p4dval_t p4d)
return native_make_p4d(p4d);
}
PV_CALLEE_SAVE_REGS_THUNK(xen_make_p4d);
-#endif /* CONFIG_PGTABLE_LEVELS >= 5 */
static void xen_pmd_walk(struct mm_struct *mm, pmd_t *pmd,
void (*func)(struct mm_struct *mm, struct page *,
@@ -2222,10 +2220,8 @@ static const typeof(pv_ops) xen_mmu_ops __initconst = {
.alloc_pud = xen_alloc_pmd_init,
.release_pud = xen_release_pmd_init,
-#if CONFIG_PGTABLE_LEVELS >= 5
.p4d_val = PV_CALLEE_SAVE(xen_p4d_val),
.make_p4d = PV_CALLEE_SAVE(xen_make_p4d),
-#endif
.enter_mmap = xen_enter_mmap,
.exit_mmap = xen_exit_mmap,
diff --git a/arch/x86/xen/pmu.c b/arch/x86/xen/pmu.c
index f06987b0efc3..8f89ce0b67e3 100644
--- a/arch/x86/xen/pmu.c
+++ b/arch/x86/xen/pmu.c
@@ -2,6 +2,7 @@
#include <linux/types.h>
#include <linux/interrupt.h>
+#include <asm/msr.h>
#include <asm/xen/hypercall.h>
#include <xen/xen.h>
#include <xen/page.h>
@@ -128,7 +129,7 @@ static inline uint32_t get_fam15h_addr(u32 addr)
return addr;
}
-static inline bool is_amd_pmu_msr(unsigned int msr)
+static bool is_amd_pmu_msr(u32 msr)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD &&
boot_cpu_data.x86_vendor != X86_VENDOR_HYGON)
@@ -194,8 +195,7 @@ static bool is_intel_pmu_msr(u32 msr_index, int *type, int *index)
}
}
-static bool xen_intel_pmu_emulate(unsigned int msr, u64 *val, int type,
- int index, bool is_read)
+static bool xen_intel_pmu_emulate(u32 msr, u64 *val, int type, int index, bool is_read)
{
uint64_t *reg = NULL;
struct xen_pmu_intel_ctxt *ctxt;
@@ -257,7 +257,7 @@ static bool xen_intel_pmu_emulate(unsigned int msr, u64 *val, int type,
return false;
}
-static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
+static bool xen_amd_pmu_emulate(u32 msr, u64 *val, bool is_read)
{
uint64_t *reg = NULL;
int i, off = 0;
@@ -298,55 +298,20 @@ static bool xen_amd_pmu_emulate(unsigned int msr, u64 *val, bool is_read)
return false;
}
-static bool pmu_msr_chk_emulated(unsigned int msr, uint64_t *val, bool is_read,
- bool *emul)
+bool pmu_msr_chk_emulated(u32 msr, u64 *val, bool is_read)
{
int type, index = 0;
if (is_amd_pmu_msr(msr))
- *emul = xen_amd_pmu_emulate(msr, val, is_read);
- else if (is_intel_pmu_msr(msr, &type, &index))
- *emul = xen_intel_pmu_emulate(msr, val, type, index, is_read);
- else
- return false;
-
- return true;
-}
-
-bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err)
-{
- bool emulated;
+ return xen_amd_pmu_emulate(msr, val, is_read);
- if (!pmu_msr_chk_emulated(msr, val, true, &emulated))
- return false;
+ if (is_intel_pmu_msr(msr, &type, &index))
+ return xen_intel_pmu_emulate(msr, val, type, index, is_read);
- if (!emulated) {
- *val = err ? native_read_msr_safe(msr, err)
- : native_read_msr(msr);
- }
-
- return true;
-}
-
-bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err)
-{
- uint64_t val = ((uint64_t)high << 32) | low;
- bool emulated;
-
- if (!pmu_msr_chk_emulated(msr, &val, false, &emulated))
- return false;
-
- if (!emulated) {
- if (err)
- *err = native_write_msr_safe(msr, low, high);
- else
- native_write_msr(msr, low, high);
- }
-
- return true;
+ return false;
}
-static unsigned long long xen_amd_read_pmc(int counter)
+static u64 xen_amd_read_pmc(int counter)
{
struct xen_pmu_amd_ctxt *ctxt;
uint64_t *counter_regs;
@@ -354,11 +319,12 @@ static unsigned long long xen_amd_read_pmc(int counter)
uint8_t xenpmu_flags = get_xenpmu_flags();
if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) {
- uint32_t msr;
- int err;
+ u32 msr;
+ u64 val;
msr = amd_counters_base + (counter * amd_msr_step);
- return native_read_msr_safe(msr, &err);
+ native_read_msr_safe(msr, &val);
+ return val;
}
ctxt = &xenpmu_data->pmu.c.amd;
@@ -366,7 +332,7 @@ static unsigned long long xen_amd_read_pmc(int counter)
return counter_regs[counter];
}
-static unsigned long long xen_intel_read_pmc(int counter)
+static u64 xen_intel_read_pmc(int counter)
{
struct xen_pmu_intel_ctxt *ctxt;
uint64_t *fixed_counters;
@@ -375,15 +341,16 @@ static unsigned long long xen_intel_read_pmc(int counter)
uint8_t xenpmu_flags = get_xenpmu_flags();
if (!xenpmu_data || !(xenpmu_flags & XENPMU_IRQ_PROCESSING)) {
- uint32_t msr;
- int err;
+ u32 msr;
+ u64 val;
if (counter & (1 << INTEL_PMC_TYPE_SHIFT))
msr = MSR_CORE_PERF_FIXED_CTR0 + (counter & 0xffff);
else
msr = MSR_IA32_PERFCTR0 + counter;
- return native_read_msr_safe(msr, &err);
+ native_read_msr_safe(msr, &val);
+ return val;
}
ctxt = &xenpmu_data->pmu.c.intel;
@@ -396,7 +363,7 @@ static unsigned long long xen_intel_read_pmc(int counter)
return arch_cntr_pair[counter].counter;
}
-unsigned long long xen_read_pmc(int counter)
+u64 xen_read_pmc(int counter)
{
if (boot_cpu_data.x86_vendor != X86_VENDOR_INTEL)
return xen_amd_read_pmc(counter);
diff --git a/arch/x86/xen/suspend.c b/arch/x86/xen/suspend.c
index 77a6ea1c60e4..ba2f17e64321 100644
--- a/arch/x86/xen/suspend.c
+++ b/arch/x86/xen/suspend.c
@@ -13,6 +13,7 @@
#include <asm/xen/hypercall.h>
#include <asm/xen/page.h>
#include <asm/fixmap.h>
+#include <asm/msr.h>
#include "xen-ops.h"
@@ -39,7 +40,7 @@ void xen_arch_post_suspend(int cancelled)
static void xen_vcpu_notify_restore(void *data)
{
if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL))
- wrmsrl(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl));
+ wrmsrq(MSR_IA32_SPEC_CTRL, this_cpu_read(spec_ctrl));
/* Boot processor notified via generic timekeeping_resume() */
if (smp_processor_id() == 0)
@@ -55,9 +56,9 @@ static void xen_vcpu_notify_suspend(void *data)
tick_suspend_local();
if (xen_pv_domain() && boot_cpu_has(X86_FEATURE_SPEC_CTRL)) {
- rdmsrl(MSR_IA32_SPEC_CTRL, tmp);
+ rdmsrq(MSR_IA32_SPEC_CTRL, tmp);
this_cpu_write(spec_ctrl, tmp);
- wrmsrl(MSR_IA32_SPEC_CTRL, 0);
+ wrmsrq(MSR_IA32_SPEC_CTRL, 0);
}
}
diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
index 25e318ef27d6..090349baec09 100644
--- a/arch/x86/xen/xen-ops.h
+++ b/arch/x86/xen/xen-ops.h
@@ -271,10 +271,9 @@ void xen_pmu_finish(int cpu);
static inline void xen_pmu_init(int cpu) {}
static inline void xen_pmu_finish(int cpu) {}
#endif
-bool pmu_msr_read(unsigned int msr, uint64_t *val, int *err);
-bool pmu_msr_write(unsigned int msr, uint32_t low, uint32_t high, int *err);
+bool pmu_msr_chk_emulated(u32 msr, u64 *val, bool is_read);
int pmu_apic_update(uint32_t reg);
-unsigned long long xen_read_pmc(int counter);
+u64 xen_read_pmc(int counter);
#ifdef CONFIG_SMP