diff options
Diffstat (limited to 'include')
174 files changed, 4506 insertions, 1740 deletions
diff --git a/include/acpi/processor.h b/include/acpi/processor.h index 7146a8e9e9c2..d0eccbd920e5 100644 --- a/include/acpi/processor.h +++ b/include/acpi/processor.h @@ -417,15 +417,32 @@ static inline void acpi_processor_throttling_init(void) {} #endif /* CONFIG_ACPI_CPU_FREQ_PSS */ /* in processor_idle.c */ +extern struct cpuidle_driver acpi_idle_driver; #ifdef CONFIG_ACPI_PROCESSOR_IDLE -void acpi_processor_power_init(struct acpi_processor *pr); -void acpi_processor_power_exit(struct acpi_processor *pr); +int acpi_processor_power_init(struct acpi_processor *pr); +int acpi_processor_power_exit(struct acpi_processor *pr); int acpi_processor_power_state_has_changed(struct acpi_processor *pr); int acpi_processor_hotplug(struct acpi_processor *pr); -void acpi_processor_register_idle_driver(void); -void acpi_processor_unregister_idle_driver(void); -int acpi_processor_ffh_lpi_probe(unsigned int cpu); -int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi); +#else +static inline int acpi_processor_power_init(struct acpi_processor *pr) +{ + return -ENODEV; +} + +static inline int acpi_processor_power_exit(struct acpi_processor *pr) +{ + return -ENODEV; +} + +static inline int acpi_processor_power_state_has_changed(struct acpi_processor *pr) +{ + return -ENODEV; +} + +static inline int acpi_processor_hotplug(struct acpi_processor *pr) +{ + return -ENODEV; +} #endif /* CONFIG_ACPI_PROCESSOR_IDLE */ /* in processor_thermal.c */ @@ -448,6 +465,11 @@ static inline void acpi_thermal_cpufreq_exit(struct cpufreq_policy *policy) } #endif /* CONFIG_CPU_FREQ */ +#ifdef CONFIG_ACPI_PROCESSOR_IDLE +extern int acpi_processor_ffh_lpi_probe(unsigned int cpu); +extern int acpi_processor_ffh_lpi_enter(struct acpi_lpi_state *lpi); +#endif + void acpi_processor_init_invariance_cppc(void); #endif diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index 387720933973..09e8eccee8ed 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -13,10 +13,19 @@ #define BUGFLAG_ONCE (1 << 1) #define BUGFLAG_DONE (1 << 2) #define BUGFLAG_NO_CUT_HERE (1 << 3) /* CUT_HERE already sent */ +#define BUGFLAG_ARGS (1 << 4) #define BUGFLAG_TAINT(taint) ((taint) << 8) #define BUG_GET_TAINT(bug) ((bug)->flags >> 8) #endif +#ifndef WARN_CONDITION_STR +#ifdef CONFIG_DEBUG_BUGVERBOSE_DETAILED +# define WARN_CONDITION_STR(cond_str) "[" cond_str "] " +#else +# define WARN_CONDITION_STR(cond_str) +#endif +#endif /* WARN_CONDITION_STR */ + #ifndef __ASSEMBLY__ #include <linux/panic.h> #include <linux/printk.h> @@ -29,19 +38,20 @@ void __warn(const char *file, int line, void *caller, unsigned taint, #ifdef CONFIG_BUG -#ifdef CONFIG_GENERIC_BUG -struct bug_entry { #ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS - unsigned long bug_addr; +#define BUG_REL(type, name) type name #else - signed int bug_addr_disp; +#define BUG_REL(type, name) signed int name##_disp #endif -#ifdef CONFIG_DEBUG_BUGVERBOSE -#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS - const char *file; -#else - signed int file_disp; + +#ifdef CONFIG_GENERIC_BUG +struct bug_entry { + BUG_REL(unsigned long, bug_addr); +#ifdef HAVE_ARCH_BUG_FORMAT + BUG_REL(const char *, format); #endif +#ifdef CONFIG_DEBUG_BUGVERBOSE + BUG_REL(const char *, file); unsigned short line; #endif unsigned short flags; @@ -92,28 +102,50 @@ void warn_slowpath_fmt(const char *file, const int line, unsigned taint, const char *fmt, ...); extern __printf(1, 2) void __warn_printk(const char *fmt, ...); -#ifndef __WARN_FLAGS -#define __WARN() __WARN_printf(TAINT_WARN, NULL) +#ifdef __WARN_FLAGS +#define __WARN() __WARN_FLAGS("", BUGFLAG_TAINT(TAINT_WARN)) + +#ifndef WARN_ON +#define WARN_ON(condition) ({ \ + int __ret_warn_on = !!(condition); \ + if (unlikely(__ret_warn_on)) \ + __WARN_FLAGS(#condition, \ + BUGFLAG_TAINT(TAINT_WARN)); \ + unlikely(__ret_warn_on); \ +}) +#endif + +#ifndef WARN_ON_ONCE +#define WARN_ON_ONCE(condition) ({ \ + int __ret_warn_on = !!(condition); \ + if (unlikely(__ret_warn_on)) \ + __WARN_FLAGS(#condition, \ + BUGFLAG_ONCE | \ + BUGFLAG_TAINT(TAINT_WARN)); \ + unlikely(__ret_warn_on); \ +}) +#endif +#endif /* __WARN_FLAGS */ + +#if defined(__WARN_FLAGS) && !defined(__WARN_printf) #define __WARN_printf(taint, arg...) do { \ instrumentation_begin(); \ - warn_slowpath_fmt(__FILE__, __LINE__, taint, arg); \ + __warn_printk(arg); \ + __WARN_FLAGS("", BUGFLAG_NO_CUT_HERE | BUGFLAG_TAINT(taint));\ instrumentation_end(); \ } while (0) -#else -#define __WARN() __WARN_FLAGS(BUGFLAG_TAINT(TAINT_WARN)) +#endif + +#ifndef __WARN_printf #define __WARN_printf(taint, arg...) do { \ instrumentation_begin(); \ - __warn_printk(arg); \ - __WARN_FLAGS(BUGFLAG_NO_CUT_HERE | BUGFLAG_TAINT(taint));\ + warn_slowpath_fmt(__FILE__, __LINE__, taint, arg); \ instrumentation_end(); \ } while (0) -#define WARN_ON_ONCE(condition) ({ \ - int __ret_warn_on = !!(condition); \ - if (unlikely(__ret_warn_on)) \ - __WARN_FLAGS(BUGFLAG_ONCE | \ - BUGFLAG_TAINT(TAINT_WARN)); \ - unlikely(__ret_warn_on); \ -}) +#endif + +#ifndef __WARN +#define __WARN() __WARN_printf(TAINT_WARN, NULL) #endif /* used internally by panic.c */ @@ -148,8 +180,10 @@ extern __printf(1, 2) void __warn_printk(const char *fmt, ...); DO_ONCE_LITE_IF(condition, WARN_ON, 1) #endif +#ifndef WARN_ONCE #define WARN_ONCE(condition, format...) \ DO_ONCE_LITE_IF(condition, WARN, 1, format) +#endif #define WARN_TAINT_ONCE(condition, taint, format...) \ DO_ONCE_LITE_IF(condition, WARN_TAINT, 1, taint, format) diff --git a/include/asm-generic/thread_info_tif.h b/include/asm-generic/thread_info_tif.h index ee3793e9b1a4..da1610a78f92 100644 --- a/include/asm-generic/thread_info_tif.h +++ b/include/asm-generic/thread_info_tif.h @@ -45,4 +45,7 @@ # define _TIF_RESTORE_SIGMASK BIT(TIF_RESTORE_SIGMASK) #endif +#define TIF_RSEQ 11 // Run RSEQ fast path +#define _TIF_RSEQ BIT(TIF_RSEQ) + #endif /* _ASM_GENERIC_THREAD_INFO_TIF_H_ */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 8a9a2e732a65..a464ff6c1a61 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -87,39 +87,56 @@ #define ALIGN_FUNCTION() . = ALIGN(CONFIG_FUNCTION_ALIGNMENT) /* - * LD_DEAD_CODE_DATA_ELIMINATION option enables -fdata-sections, which - * generates .data.identifier sections, which need to be pulled in with - * .data. We don't want to pull in .data..other sections, which Linux - * has defined. Same for text and bss. + * Support -ffunction-sections by matching .text and .text.*, + * but exclude '.text..*', .text.startup[.*], and .text.exit[.*]. * - * With LTO_CLANG, the linker also splits sections by default, so we need - * these macros to combine the sections during the final link. + * .text.startup and .text.startup.* are matched later by INIT_TEXT, and + * .text.exit and .text.exit.* are matched later by EXIT_TEXT, so they must be + * explicitly excluded here. * - * With AUTOFDO_CLANG and PROPELLER_CLANG, by default, the linker splits - * text sections and regroups functions into subsections. + * Other .text.* sections that are typically grouped separately, such as + * .text.unlikely or .text.hot, must be matched explicitly before using + * TEXT_MAIN. * - * RODATA_MAIN is not used because existing code already defines .rodata.x - * sections to be brought in with rodata. + * NOTE: builds *with* and *without* -ffunction-sections are both supported by + * this single macro. Even with -ffunction-sections, there may be some objects + * NOT compiled with the flag due to the use of a specific Makefile override + * like cflags-y or AUTOFDO_PROFILE_foo.o. So this single catchall rule is + * needed to support mixed object builds. + * + * One implication is that functions named startup(), exit(), split(), + * unlikely(), hot(), and unknown() are not allowed in the kernel due to the + * ambiguity of their section names with -ffunction-sections. For example, + * .text.startup could be __attribute__((constructor)) code in a *non* + * ffunction-sections object, which should be placed in .init.text; or it could + * be an actual function named startup() in an ffunction-sections object, which + * should be placed in .text. The build will detect and complain about any such + * ambiguously named functions. + */ +#define TEXT_MAIN \ + .text \ + .text.[_0-9A-Za-df-rt-z]* \ + .text.s[_0-9A-Za-su-z]* .text.s .text.s.* \ + .text.st[_0-9A-Zb-z]* .text.st .text.st.* \ + .text.sta[_0-9A-Za-qs-z]* .text.sta .text.sta.* \ + .text.star[_0-9A-Za-su-z]* .text.star .text.star.* \ + .text.start[_0-9A-Za-tv-z]* .text.start .text.start.* \ + .text.startu[_0-9A-Za-oq-z]* .text.startu .text.startu.* \ + .text.startup[_0-9A-Za-z]* \ + .text.e[_0-9A-Za-wy-z]* .text.e .text.e.* \ + .text.ex[_0-9A-Za-hj-z]* .text.ex .text.ex.* \ + .text.exi[_0-9A-Za-su-z]* .text.exi .text.exi.* \ + .text.exit[_0-9A-Za-z]* + +/* + * Support -fdata-sections by matching .data, .data.*, and others, + * but exclude '.data..*'. */ -#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) || \ -defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) -#define TEXT_MAIN .text .text.[0-9a-zA-Z_]* -#else -#define TEXT_MAIN .text -#endif -#if defined(CONFIG_LD_DEAD_CODE_DATA_ELIMINATION) || defined(CONFIG_LTO_CLANG) #define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data.rel.* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$L* #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]* #define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L* #define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..L* .bss..compoundliteral* #define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]* -#else -#define DATA_MAIN .data .data.rel .data.rel.local -#define SDATA_MAIN .sdata -#define RODATA_MAIN .rodata -#define BSS_MAIN .bss -#define SBSS_MAIN .sbss -#endif /* * GCC 4.5 and later have a 32 bytes section alignment for structures. @@ -581,9 +598,8 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) * during second ld run in second ld pass when generating System.map * * TEXT_MAIN here will match symbols with a fixed pattern (for example, - * .text.hot or .text.unlikely) if dead code elimination or - * function-section is enabled. Match these symbols first before - * TEXT_MAIN to ensure they are grouped together. + * .text.hot or .text.unlikely). Match those before TEXT_MAIN to ensure + * they get grouped together. * * Also placing .text.hot section at the beginning of a page, this * would help the TLB performance. @@ -729,16 +745,16 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) #define INIT_TEXT \ *(.init.text .init.text.*) \ - *(.text.startup) + *(.text.startup .text.startup.*) #define EXIT_DATA \ *(.exit.data .exit.data.*) \ *(.fini_array .fini_array.*) \ - *(.dtors .dtors.*) \ + *(.dtors .dtors.*) #define EXIT_TEXT \ *(.exit.text) \ - *(.text.exit) \ + *(.text.exit .text.exit.*) #define EXIT_CALL \ *(.exitcall.exit) @@ -832,7 +848,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) /* Required sections not related to debugging. */ #define ELF_DETAILS \ - .modinfo : { *(.modinfo) } \ + .modinfo : { *(.modinfo) . = ALIGN(8); } \ .comment 0 : { *(.comment) } \ .symtab 0 : { *(.symtab) } \ .strtab 0 : { *(.strtab) } \ @@ -955,7 +971,8 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG) #define RUNTIME_CONST_VARIABLES \ RUNTIME_CONST(shift, d_hash_shift) \ - RUNTIME_CONST(ptr, dentry_hashtable) + RUNTIME_CONST(ptr, dentry_hashtable) \ + RUNTIME_CONST(ptr, __dentry_cache) /* Alignment must be consistent with (kunit_suite *) in include/kunit/test.h */ #define KUNIT_TABLE() \ diff --git a/include/drm/Makefile b/include/drm/Makefile index 1df6962556ef..48fae3f167c7 100644 --- a/include/drm/Makefile +++ b/include/drm/Makefile @@ -11,7 +11,7 @@ always-$(CONFIG_DRM_HEADER_TEST) += \ quiet_cmd_hdrtest = HDRTEST $(patsubst %.hdrtest,%.h,$@) cmd_hdrtest = \ $(CC) $(c_flags) -fsyntax-only -x c /dev/null -include $< -include $<; \ - PYTHONDONTWRITEBYTECODE=1 $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \ + PYTHONDONTWRITEBYTECODE=1 $(PYTHON3) $(KERNELDOC) -none $(if $(CONFIG_WERROR)$(CONFIG_DRM_WERROR),-Werror) $<; \ touch $@ $(obj)/%.hdrtest: $(src)/%.h FORCE diff --git a/include/drm/drm_gpuvm.h b/include/drm/drm_gpuvm.h index 8890ded1d907..476990e761f8 100644 --- a/include/drm/drm_gpuvm.h +++ b/include/drm/drm_gpuvm.h @@ -1078,7 +1078,7 @@ struct drm_gpuva_ops { */ struct drm_gpuvm_map_req { /** - * @op_map: struct drm_gpuva_op_map + * @map: struct drm_gpuva_op_map */ struct drm_gpuva_op_map map; }; diff --git a/include/drm/intel/pciids.h b/include/drm/intel/pciids.h index da6301a6fcea..69d4ae92d822 100644 --- a/include/drm/intel/pciids.h +++ b/include/drm/intel/pciids.h @@ -877,7 +877,10 @@ MACRO__(0xB08F, ## __VA_ARGS__), \ MACRO__(0xB090, ## __VA_ARGS__), \ MACRO__(0xB0A0, ## __VA_ARGS__), \ - MACRO__(0xB0B0, ## __VA_ARGS__), \ + MACRO__(0xB0B0, ## __VA_ARGS__) + +/* WCL */ +#define INTEL_WCL_IDS(MACRO__, ...) \ MACRO__(0xFD80, ## __VA_ARGS__), \ MACRO__(0xFD81, ## __VA_ARGS__) diff --git a/include/kvm/arm_arch_timer.h b/include/kvm/arm_arch_timer.h index 681cf0c8b9df..7310841f4512 100644 --- a/include/kvm/arm_arch_timer.h +++ b/include/kvm/arm_arch_timer.h @@ -51,8 +51,6 @@ struct arch_timer_vm_data { }; struct arch_timer_context { - struct kvm_vcpu *vcpu; - /* Emulated Timer (may be unused) */ struct hrtimer hrtimer; u64 ns_frac; @@ -71,6 +69,9 @@ struct arch_timer_context { bool level; } irq; + /* Who am I? */ + enum kvm_arch_timers timer_id; + /* Duplicated state from arch_timer.c for convenience */ u32 host_timer_irq; }; @@ -106,9 +107,6 @@ void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu); void kvm_timer_init_vm(struct kvm *kvm); -u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid); -int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value); - int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); @@ -127,9 +125,9 @@ void kvm_timer_init_vhe(void); #define vcpu_hvtimer(v) (&(v)->arch.timer_cpu.timers[TIMER_HVTIMER]) #define vcpu_hptimer(v) (&(v)->arch.timer_cpu.timers[TIMER_HPTIMER]) -#define arch_timer_ctx_index(ctx) ((ctx) - vcpu_timer((ctx)->vcpu)->timers) - -#define timer_vm_data(ctx) (&(ctx)->vcpu->kvm->arch.timer_data) +#define arch_timer_ctx_index(ctx) ((ctx)->timer_id) +#define timer_context_to_vcpu(ctx) container_of((ctx), struct kvm_vcpu, arch.timer_cpu.timers[(ctx)->timer_id]) +#define timer_vm_data(ctx) (&(timer_context_to_vcpu(ctx)->kvm->arch.timer_data)) #define timer_irq(ctx) (timer_vm_data(ctx)->ppi[arch_timer_ctx_index(ctx)]) u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, @@ -178,4 +176,14 @@ static inline u64 timer_get_offset(struct arch_timer_context *ctxt) return offset; } +static inline void timer_set_offset(struct arch_timer_context *ctxt, u64 offset) +{ + if (!ctxt->offset.vm_offset) { + WARN(offset, "timer %d\n", arch_timer_ctx_index(ctxt)); + return; + } + + WRITE_ONCE(*ctxt->offset.vm_offset, offset); +} + #endif diff --git a/include/linux/acpi.h b/include/linux/acpi.h index 5ff5d99f6ead..607db773b672 100644 --- a/include/linux/acpi.h +++ b/include/linux/acpi.h @@ -1509,12 +1509,19 @@ static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console) #if IS_ENABLED(CONFIG_ACPI_GENERIC_GSI) int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res); +const struct cpumask *acpi_irq_get_affinity(acpi_handle handle, + unsigned int index); #else static inline int acpi_irq_get(acpi_handle handle, unsigned int index, struct resource *res) { return -EINVAL; } +static inline const struct cpumask *acpi_irq_get_affinity(acpi_handle handle, + unsigned int index) +{ + return NULL; +} #endif #ifdef CONFIG_ACPI_LPIT diff --git a/include/linux/annotate.h b/include/linux/annotate.h new file mode 100644 index 000000000000..7c10d34d198c --- /dev/null +++ b/include/linux/annotate.h @@ -0,0 +1,134 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_ANNOTATE_H +#define _LINUX_ANNOTATE_H + +#include <linux/objtool_types.h> + +#ifdef CONFIG_OBJTOOL + +#ifndef __ASSEMBLY__ + +#define __ASM_ANNOTATE(section, label, type) \ + ".pushsection " section ",\"M\", @progbits, 8\n\t" \ + ".long " __stringify(label) " - .\n\t" \ + ".long " __stringify(type) "\n\t" \ + ".popsection\n\t" + +#define ASM_ANNOTATE_LABEL(label, type) \ + __ASM_ANNOTATE(".discard.annotate_insn", label, type) + +#define ASM_ANNOTATE(type) \ + "911:\n\t" \ + ASM_ANNOTATE_LABEL(911b, type) + +#define ASM_ANNOTATE_DATA(type) \ + "912:\n\t" \ + __ASM_ANNOTATE(".discard.annotate_data", 912b, type) + +#else /* __ASSEMBLY__ */ + +.macro __ANNOTATE section, type +.Lhere_\@: + .pushsection \section, "M", @progbits, 8 + .long .Lhere_\@ - . + .long \type + .popsection +.endm + +.macro ANNOTATE type + __ANNOTATE ".discard.annotate_insn", \type +.endm + +.macro ANNOTATE_DATA type + __ANNOTATE ".discard.annotate_data", \type +.endm + +#endif /* __ASSEMBLY__ */ + +#else /* !CONFIG_OBJTOOL */ +#ifndef __ASSEMBLY__ +#define ASM_ANNOTATE_LABEL(label, type) "" +#define ASM_ANNOTATE(type) +#define ASM_ANNOTATE_DATA(type) +#else /* __ASSEMBLY__ */ +.macro ANNOTATE type +.endm +.macro ANNOTATE_DATA type +.endm +#endif /* __ASSEMBLY__ */ +#endif /* !CONFIG_OBJTOOL */ + +#ifndef __ASSEMBLY__ + +/* + * Annotate away the various 'relocation to !ENDBR` complaints; knowing that + * these relocations will never be used for indirect calls. + */ +#define ANNOTATE_NOENDBR ASM_ANNOTATE(ANNOTYPE_NOENDBR) +#define ANNOTATE_NOENDBR_SYM(sym) asm(ASM_ANNOTATE_LABEL(sym, ANNOTYPE_NOENDBR)) + +/* + * This should be used immediately before an indirect jump/call. It tells + * objtool the subsequent indirect jump/call is vouched safe for retpoline + * builds. + */ +#define ANNOTATE_RETPOLINE_SAFE ASM_ANNOTATE(ANNOTYPE_RETPOLINE_SAFE) +/* + * See linux/instrumentation.h + */ +#define ANNOTATE_INSTR_BEGIN(label) ASM_ANNOTATE_LABEL(label, ANNOTYPE_INSTR_BEGIN) +#define ANNOTATE_INSTR_END(label) ASM_ANNOTATE_LABEL(label, ANNOTYPE_INSTR_END) +/* + * objtool annotation to ignore the alternatives and only consider the original + * instruction(s). + */ +#define ANNOTATE_IGNORE_ALTERNATIVE ASM_ANNOTATE(ANNOTYPE_IGNORE_ALTS) +/* + * This macro indicates that the following intra-function call is valid. + * Any non-annotated intra-function call will cause objtool to issue a warning. + */ +#define ANNOTATE_INTRA_FUNCTION_CALL ASM_ANNOTATE(ANNOTYPE_INTRA_FUNCTION_CALL) +/* + * Use objtool to validate the entry requirement that all code paths do + * VALIDATE_UNRET_END before RET. + * + * NOTE: The macro must be used at the beginning of a global symbol, otherwise + * it will be ignored. + */ +#define ANNOTATE_UNRET_BEGIN ASM_ANNOTATE(ANNOTYPE_UNRET_BEGIN) +/* + * This should be used to refer to an instruction that is considered + * terminating, like a noreturn CALL or UD2 when we know they are not -- eg + * WARN using UD2. + */ +#define ANNOTATE_REACHABLE(label) ASM_ANNOTATE_LABEL(label, ANNOTYPE_REACHABLE) +/* + * This should not be used; it annotates away CFI violations. There are a few + * valid use cases like kexec handover to the next kernel image, and there is + * no security concern there. + * + * There are also a few real issues annotated away, like EFI because we can't + * control the EFI code. + */ +#define ANNOTATE_NOCFI_SYM(sym) asm(ASM_ANNOTATE_LABEL(sym, ANNOTYPE_NOCFI)) + +/* + * Annotate a special section entry. This emables livepatch module generation + * to find and extract individual special section entries as needed. + */ +#define ANNOTATE_DATA_SPECIAL ASM_ANNOTATE_DATA(ANNOTYPE_DATA_SPECIAL) + +#else /* __ASSEMBLY__ */ +#define ANNOTATE_NOENDBR ANNOTATE type=ANNOTYPE_NOENDBR +#define ANNOTATE_RETPOLINE_SAFE ANNOTATE type=ANNOTYPE_RETPOLINE_SAFE +/* ANNOTATE_INSTR_BEGIN ANNOTATE type=ANNOTYPE_INSTR_BEGIN */ +/* ANNOTATE_INSTR_END ANNOTATE type=ANNOTYPE_INSTR_END */ +#define ANNOTATE_IGNORE_ALTERNATIVE ANNOTATE type=ANNOTYPE_IGNORE_ALTS +#define ANNOTATE_INTRA_FUNCTION_CALL ANNOTATE type=ANNOTYPE_INTRA_FUNCTION_CALL +#define ANNOTATE_UNRET_BEGIN ANNOTATE type=ANNOTYPE_UNRET_BEGIN +#define ANNOTATE_REACHABLE ANNOTATE type=ANNOTYPE_REACHABLE +#define ANNOTATE_NOCFI_SYM ANNOTATE type=ANNOTYPE_NOCFI +#define ANNOTATE_DATA_SPECIAL ANNOTATE_DATA type=ANNOTYPE_DATA_SPECIAL +#endif /* __ASSEMBLY__ */ + +#endif /* _LINUX_ANNOTATE_H */ diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h index cd7ee4df9045..81e603839c4a 100644 --- a/include/linux/arm_ffa.h +++ b/include/linux/arm_ffa.h @@ -338,6 +338,7 @@ struct ffa_mem_region_attributes { * an `struct ffa_mem_region_addr_range`. */ u32 composite_off; + u8 impdef_val[16]; u64 reserved; }; @@ -417,15 +418,31 @@ struct ffa_mem_region { #define CONSTITUENTS_OFFSET(x) \ (offsetof(struct ffa_composite_mem_region, constituents[x])) +#define FFA_EMAD_HAS_IMPDEF_FIELD(version) ((version) >= FFA_VERSION_1_2) +#define FFA_MEM_REGION_HAS_EP_MEM_OFFSET(version) ((version) > FFA_VERSION_1_0) + +static inline u32 ffa_emad_size_get(u32 ffa_version) +{ + u32 sz; + struct ffa_mem_region_attributes *ep_mem_access; + + if (FFA_EMAD_HAS_IMPDEF_FIELD(ffa_version)) + sz = sizeof(*ep_mem_access); + else + sz = sizeof(*ep_mem_access) - sizeof(ep_mem_access->impdef_val); + + return sz; +} + static inline u32 ffa_mem_desc_offset(struct ffa_mem_region *buf, int count, u32 ffa_version) { - u32 offset = count * sizeof(struct ffa_mem_region_attributes); + u32 offset = count * ffa_emad_size_get(ffa_version); /* * Earlier to v1.1, the endpoint memory descriptor array started at * offset 32(i.e. offset of ep_mem_offset in the current structure) */ - if (ffa_version <= FFA_VERSION_1_0) + if (!FFA_MEM_REGION_HAS_EP_MEM_OFFSET(ffa_version)) offset += offsetof(struct ffa_mem_region, ep_mem_offset); else offset += sizeof(struct ffa_mem_region); diff --git a/include/linux/ata.h b/include/linux/ata.h index 792e10a09787..c9013e472aa3 100644 --- a/include/linux/ata.h +++ b/include/linux/ata.h @@ -566,6 +566,7 @@ struct ata_bmdma_prd { #define ata_id_has_ncq(id) ((id)[ATA_ID_SATA_CAPABILITY] & (1 << 8)) #define ata_id_queue_depth(id) (((id)[ATA_ID_QUEUE_DEPTH] & 0x1f) + 1) #define ata_id_removable(id) ((id)[ATA_ID_CONFIG] & (1 << 7)) +#define ata_id_is_locked(id) (((id)[ATA_ID_DLF] & 0x7) == 0x7) #define ata_id_has_atapi_AN(id) \ ((((id)[ATA_ID_SATA_CAPABILITY] != 0x0000) && \ ((id)[ATA_ID_SATA_CAPABILITY] != 0xffff)) && \ diff --git a/include/linux/atomic/atomic-instrumented.h b/include/linux/atomic/atomic-instrumented.h index 9409a6ddf3e0..37ab6314a9f7 100644 --- a/include/linux/atomic/atomic-instrumented.h +++ b/include/linux/atomic/atomic-instrumented.h @@ -1276,7 +1276,7 @@ atomic_try_cmpxchg(atomic_t *v, int *old, int new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg(v, old, new); } @@ -1298,7 +1298,7 @@ static __always_inline bool atomic_try_cmpxchg_acquire(atomic_t *v, int *old, int new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_acquire(v, old, new); } @@ -1321,7 +1321,7 @@ atomic_try_cmpxchg_release(atomic_t *v, int *old, int new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_release(v, old, new); } @@ -1343,7 +1343,7 @@ static __always_inline bool atomic_try_cmpxchg_relaxed(atomic_t *v, int *old, int new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_try_cmpxchg_relaxed(v, old, new); } @@ -2854,7 +2854,7 @@ atomic64_try_cmpxchg(atomic64_t *v, s64 *old, s64 new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg(v, old, new); } @@ -2876,7 +2876,7 @@ static __always_inline bool atomic64_try_cmpxchg_acquire(atomic64_t *v, s64 *old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_acquire(v, old, new); } @@ -2899,7 +2899,7 @@ atomic64_try_cmpxchg_release(atomic64_t *v, s64 *old, s64 new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_release(v, old, new); } @@ -2921,7 +2921,7 @@ static __always_inline bool atomic64_try_cmpxchg_relaxed(atomic64_t *v, s64 *old, s64 new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic64_try_cmpxchg_relaxed(v, old, new); } @@ -4432,7 +4432,7 @@ atomic_long_try_cmpxchg(atomic_long_t *v, long *old, long new) { kcsan_mb(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg(v, old, new); } @@ -4454,7 +4454,7 @@ static __always_inline bool atomic_long_try_cmpxchg_acquire(atomic_long_t *v, long *old, long new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_acquire(v, old, new); } @@ -4477,7 +4477,7 @@ atomic_long_try_cmpxchg_release(atomic_long_t *v, long *old, long new) { kcsan_release(); instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_release(v, old, new); } @@ -4499,7 +4499,7 @@ static __always_inline bool atomic_long_try_cmpxchg_relaxed(atomic_long_t *v, long *old, long new) { instrument_atomic_read_write(v, sizeof(*v)); - instrument_atomic_read_write(old, sizeof(*old)); + instrument_read_write(old, sizeof(*old)); return raw_atomic_long_try_cmpxchg_relaxed(v, old, new); } @@ -5050,4 +5050,4 @@ atomic_long_dec_if_positive(atomic_long_t *v) #endif /* _LINUX_ATOMIC_INSTRUMENTED_H */ -// 8829b337928e9508259079d32581775ececd415b +// f618ac667f868941a84ce0ab2242f1786e049ed4 diff --git a/include/linux/backing-dev-defs.h b/include/linux/backing-dev-defs.h index c5c9d89c73ed..610ef62b6a32 100644 --- a/include/linux/backing-dev-defs.h +++ b/include/linux/backing-dev-defs.h @@ -63,6 +63,8 @@ enum wb_reason { struct wb_completion { atomic_t cnt; wait_queue_head_t *waitq; + unsigned long progress_stamp; /* The jiffies when slow progress is detected */ + unsigned long wait_start; /* The jiffies when waiting for the writeback work to finish */ }; #define __WB_COMPLETION_INIT(_waitq) \ diff --git a/include/linux/backing-dev.h b/include/linux/backing-dev.h index 3e64f14739dd..0c8342747cab 100644 --- a/include/linux/backing-dev.h +++ b/include/linux/backing-dev.h @@ -277,10 +277,11 @@ unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) rcu_read_lock(); /* - * Paired with store_release in inode_switch_wbs_work_fn() and + * Paired with a release fence in inode_do_switch_wbs() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ - cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; + cookie->locked = inode_state_read_once(inode) & I_WB_SWITCH; + smp_rmb(); if (unlikely(cookie->locked)) xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 595217b7a6e7..b0395e4ccf90 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -45,6 +45,7 @@ struct device; * bitmap_copy(dst, src, nbits) *dst = *src * bitmap_and(dst, src1, src2, nbits) *dst = *src1 & *src2 * bitmap_or(dst, src1, src2, nbits) *dst = *src1 | *src2 + * bitmap_weighted_or(dst, src1, src2, nbits) *dst = *src1 | *src2. Returns Hamming Weight of dst * bitmap_xor(dst, src1, src2, nbits) *dst = *src1 ^ *src2 * bitmap_andnot(dst, src1, src2, nbits) *dst = *src1 & ~(*src2) * bitmap_complement(dst, src, nbits) *dst = ~(*src) @@ -165,6 +166,8 @@ bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); +unsigned int __bitmap_weighted_or(unsigned long *dst, const unsigned long *bitmap1, + const unsigned long *bitmap2, unsigned int nbits); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, @@ -338,6 +341,18 @@ void bitmap_or(unsigned long *dst, const unsigned long *src1, } static __always_inline +unsigned int bitmap_weighted_or(unsigned long *dst, const unsigned long *src1, + const unsigned long *src2, unsigned int nbits) +{ + if (small_const_nbits(nbits)) { + *dst = *src1 | *src2; + return hweight_long(*dst & BITMAP_LAST_WORD_MASK(nbits)); + } else { + return __bitmap_weighted_or(dst, src1, src2, nbits); + } +} + +static __always_inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h index 8e8d1cc8b06c..44c30183ecc3 100644 --- a/include/linux/blk_types.h +++ b/include/linux/blk_types.h @@ -341,15 +341,15 @@ enum req_op { /* write the zero filled sector many times */ REQ_OP_WRITE_ZEROES = (__force blk_opf_t)9, /* Open a zone */ - REQ_OP_ZONE_OPEN = (__force blk_opf_t)10, + REQ_OP_ZONE_OPEN = (__force blk_opf_t)11, /* Close a zone */ - REQ_OP_ZONE_CLOSE = (__force blk_opf_t)11, + REQ_OP_ZONE_CLOSE = (__force blk_opf_t)13, /* Transition a zone to full */ - REQ_OP_ZONE_FINISH = (__force blk_opf_t)13, + REQ_OP_ZONE_FINISH = (__force blk_opf_t)15, /* reset a zone write pointer */ - REQ_OP_ZONE_RESET = (__force blk_opf_t)15, + REQ_OP_ZONE_RESET = (__force blk_opf_t)17, /* reset all the zone present on the device */ - REQ_OP_ZONE_RESET_ALL = (__force blk_opf_t)17, + REQ_OP_ZONE_RESET_ALL = (__force blk_opf_t)19, /* Driver private requests */ REQ_OP_DRV_IN = (__force blk_opf_t)34, @@ -478,6 +478,7 @@ static inline bool op_is_zone_mgmt(enum req_op op) { switch (op & REQ_OP_MASK) { case REQ_OP_ZONE_RESET: + case REQ_OP_ZONE_RESET_ALL: case REQ_OP_ZONE_OPEN: case REQ_OP_ZONE_CLOSE: case REQ_OP_ZONE_FINISH: diff --git a/include/linux/bpf.h b/include/linux/bpf.h index a98c83346134..d808253f2e94 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -2499,6 +2499,8 @@ int bpf_map_alloc_pages(const struct bpf_map *map, int nid, #ifdef CONFIG_MEMCG void *bpf_map_kmalloc_node(const struct bpf_map *map, size_t size, gfp_t flags, int node); +void *bpf_map_kmalloc_nolock(const struct bpf_map *map, size_t size, gfp_t flags, + int node); void *bpf_map_kzalloc(const struct bpf_map *map, size_t size, gfp_t flags); void *bpf_map_kvcalloc(struct bpf_map *map, size_t n, size_t size, gfp_t flags); @@ -2511,6 +2513,8 @@ void __percpu *bpf_map_alloc_percpu(const struct bpf_map *map, size_t size, */ #define bpf_map_kmalloc_node(_map, _size, _flags, _node) \ kmalloc_node(_size, _flags, _node) +#define bpf_map_kmalloc_nolock(_map, _size, _flags, _node) \ + kmalloc_nolock(_size, _flags, _node) #define bpf_map_kzalloc(_map, _size, _flags) \ kzalloc(_size, _flags) #define bpf_map_kvcalloc(_map, _n, _size, _flags) \ diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h index 15c35655f482..115a964f3006 100644 --- a/include/linux/brcmphy.h +++ b/include/linux/brcmphy.h @@ -137,6 +137,7 @@ #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC 0x07 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_WIRESPEED_EN 0x0010 +#define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RSVD 0x0060 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_EN 0x0080 #define MII_BCM54XX_AUXCTL_SHDWSEL_MISC_RGMII_SKEW_EN 0x0100 #define MII_BCM54XX_AUXCTL_MISC_FORCE_AMDIX 0x0200 diff --git a/include/linux/bug.h b/include/linux/bug.h index a9948a9f1093..17a4933c611b 100644 --- a/include/linux/bug.h +++ b/include/linux/bug.h @@ -42,6 +42,7 @@ void bug_get_file_line(struct bug_entry *bug, const char **file, struct bug_entry *find_bug(unsigned long bugaddr); enum bug_trap_type report_bug(unsigned long bug_addr, struct pt_regs *regs); +enum bug_trap_type report_bug_entry(struct bug_entry *bug, struct pt_regs *regs); /* These are defined by the architecture */ int is_valid_bugaddr(unsigned long addr); @@ -62,6 +63,13 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr, } struct bug_entry; + +static inline enum bug_trap_type +report_bug_entry(struct bug_entry *bug, struct pt_regs *regs) +{ + return BUG_TRAP_TYPE_BUG; +} + static inline void bug_get_file_line(struct bug_entry *bug, const char **file, unsigned int *line) { diff --git a/include/linux/cc_platform.h b/include/linux/cc_platform.h index 7fcec025c5e0..559353ad64ac 100644 --- a/include/linux/cc_platform.h +++ b/include/linux/cc_platform.h @@ -74,7 +74,7 @@ enum cc_attr { CC_ATTR_GUEST_UNROLL_STRING_IO, /** - * @CC_ATTR_SEV_SNP: Guest SNP is active. + * @CC_ATTR_GUEST_SEV_SNP: Guest SNP is active. * * The platform/OS is running as a guest/virtual machine and actively * using AMD SEV-SNP features. diff --git a/include/linux/ceph/libceph.h b/include/linux/ceph/libceph.h index 733e7f93db66..63e0e2aa1ce9 100644 --- a/include/linux/ceph/libceph.h +++ b/include/linux/ceph/libceph.h @@ -306,8 +306,7 @@ struct ceph_entity_addr *ceph_client_addr(struct ceph_client *client); u64 ceph_client_gid(struct ceph_client *client); extern void ceph_destroy_client(struct ceph_client *client); extern void ceph_reset_client_addr(struct ceph_client *client); -extern int __ceph_open_session(struct ceph_client *client, - unsigned long started); +extern int __ceph_open_session(struct ceph_client *client); extern int ceph_open_session(struct ceph_client *client); int ceph_wait_for_latest_osdmap(struct ceph_client *client, unsigned long timeout); diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h index 93318fce31f3..b760a3c470a5 100644 --- a/include/linux/cgroup-defs.h +++ b/include/linux/cgroup-defs.h @@ -452,7 +452,7 @@ struct cgroup_freezer_state { int nr_frozen_tasks; /* Freeze time data consistency protection */ - seqcount_t freeze_seq; + seqcount_spinlock_t freeze_seq; /* * Most recent time the cgroup was requested to freeze. diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h index 2573585b7f06..0b55a8f6c59e 100644 --- a/include/linux/cleanup.h +++ b/include/linux/cleanup.h @@ -208,7 +208,7 @@ */ #define DEFINE_FREE(_name, _type, _free) \ - static inline void __free_##_name(void *p) { _type _T = *(_type *)p; _free; } + static __always_inline void __free_##_name(void *p) { _type _T = *(_type *)p; _free; } #define __free(_name) __cleanup(__free_##_name) @@ -220,7 +220,7 @@ __val; \ }) -static inline __must_check +static __always_inline __must_check const volatile void * __must_check_fn(const volatile void *val) { return val; } @@ -261,6 +261,10 @@ const volatile void * __must_check_fn(const volatile void *val) * CLASS(name, var)(args...): * declare the variable @var as an instance of the named class * + * CLASS_INIT(name, var, init_expr): + * declare the variable @var as an instance of the named class with + * custom initialization expression. + * * Ex. * * DEFINE_CLASS(fdget, struct fd, fdput(_T), fdget(fd), int fd) @@ -274,31 +278,35 @@ const volatile void * __must_check_fn(const volatile void *val) #define DEFINE_CLASS(_name, _type, _exit, _init, _init_args...) \ typedef _type class_##_name##_t; \ -static inline void class_##_name##_destructor(_type *p) \ +static __always_inline void class_##_name##_destructor(_type *p) \ { _type _T = *p; _exit; } \ -static inline _type class_##_name##_constructor(_init_args) \ +static __always_inline _type class_##_name##_constructor(_init_args) \ { _type t = _init; return t; } #define EXTEND_CLASS(_name, ext, _init, _init_args...) \ typedef class_##_name##_t class_##_name##ext##_t; \ -static inline void class_##_name##ext##_destructor(class_##_name##_t *p)\ +static __always_inline void class_##_name##ext##_destructor(class_##_name##_t *p) \ { class_##_name##_destructor(p); } \ -static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ +static __always_inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \ { class_##_name##_t t = _init; return t; } #define CLASS(_name, var) \ class_##_name##_t var __cleanup(class_##_name##_destructor) = \ class_##_name##_constructor -#define scoped_class(_name, var, args) \ - for (CLASS(_name, var)(args); \ - __guard_ptr(_name)(&var) || !__is_cond_ptr(_name); \ - ({ goto _label; })) \ - if (0) { \ -_label: \ - break; \ +#define CLASS_INIT(_name, _var, _init_expr) \ + class_##_name##_t _var __cleanup(class_##_name##_destructor) = (_init_expr) + +#define __scoped_class(_name, var, _label, args...) \ + for (CLASS(_name, var)(args); ; ({ goto _label; })) \ + if (0) { \ +_label: \ + break; \ } else +#define scoped_class(_name, var, args...) \ + __scoped_class(_name, var, __UNIQUE_ID(label), args) + /* * DEFINE_GUARD(name, type, lock, unlock): * trivial wrapper around DEFINE_CLASS() above specifically @@ -340,6 +348,11 @@ _label: \ #define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond) \ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond +#define DEFINE_CLASS_IS_UNCONDITIONAL(_name) \ + __DEFINE_CLASS_IS_CONDITIONAL(_name, false); \ + static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \ + { return (void *)1; } + #define __GUARD_IS_ERR(_ptr) \ ({ \ unsigned long _rc = (__force unsigned long)(_ptr); \ @@ -347,7 +360,7 @@ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond }) #define __DEFINE_GUARD_LOCK_PTR(_name, _exp) \ - static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \ + static __always_inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \ { \ void *_ptr = (void *)(__force unsigned long)*(_exp); \ if (IS_ERR(_ptr)) { \ @@ -355,7 +368,7 @@ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond } \ return _ptr; \ } \ - static inline int class_##_name##_lock_err(class_##_name##_t *_T) \ + static __always_inline int class_##_name##_lock_err(class_##_name##_t *_T) \ { \ long _rc = (__force unsigned long)*(_exp); \ if (!_rc) { \ @@ -384,9 +397,9 @@ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond EXTEND_CLASS(_name, _ext, \ ({ void *_t = _T; int _RET = (_lock); if (_T && !(_cond)) _t = ERR_PTR(_RET); _t; }), \ class_##_name##_t _T) \ - static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \ + static __always_inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \ { return class_##_name##_lock_ptr(_T); } \ - static inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \ + static __always_inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \ { return class_##_name##_lock_err(_T); } /* @@ -466,7 +479,7 @@ typedef struct { \ __VA_ARGS__; \ } class_##_name##_t; \ \ -static inline void class_##_name##_destructor(class_##_name##_t *_T) \ +static __always_inline void class_##_name##_destructor(class_##_name##_t *_T) \ { \ if (!__GUARD_IS_ERR(_T->lock)) { _unlock; } \ } \ @@ -474,7 +487,7 @@ static inline void class_##_name##_destructor(class_##_name##_t *_T) \ __DEFINE_GUARD_LOCK_PTR(_name, &_T->lock) #define __DEFINE_LOCK_GUARD_1(_name, _type, _lock) \ -static inline class_##_name##_t class_##_name##_constructor(_type *l) \ +static __always_inline class_##_name##_t class_##_name##_constructor(_type *l) \ { \ class_##_name##_t _t = { .lock = l }, *_T = &_t; \ _lock; \ @@ -482,7 +495,7 @@ static inline class_##_name##_t class_##_name##_constructor(_type *l) \ } #define __DEFINE_LOCK_GUARD_0(_name, _lock) \ -static inline class_##_name##_t class_##_name##_constructor(void) \ +static __always_inline class_##_name##_t class_##_name##_constructor(void) \ { \ class_##_name##_t _t = { .lock = (void*)1 }, \ *_T __maybe_unused = &_t; \ @@ -508,9 +521,9 @@ __DEFINE_LOCK_GUARD_0(_name, _lock) if (_T->lock && !(_cond)) _T->lock = ERR_PTR(_RET);\ _t; }), \ typeof_member(class_##_name##_t, lock) l) \ - static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \ + static __always_inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \ { return class_##_name##_lock_ptr(_T); } \ - static inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \ + static __always_inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \ { return class_##_name##_lock_err(_T); } #define DEFINE_LOCK_GUARD_1_COND_3(_name, _ext, _lock) \ diff --git a/include/linux/compiler.h b/include/linux/compiler.h index 5b45ea7dff3e..ab181d87d71d 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -163,7 +163,11 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, __asm__ ("" : "=r" (var) : "0" (var)) #endif -#define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __COUNTER__) +/* Format: __UNIQUE_ID_<name>_<__COUNTER__> */ +#define __UNIQUE_ID(name) \ + __PASTE(__UNIQUE_ID_, \ + __PASTE(name, \ + __PASTE(_, __COUNTER__))) /** * data_race - mark an expression as containing intentional data races @@ -283,7 +287,7 @@ static inline void *offset_to_ptr(const int *off) */ #define ___ADDRESSABLE(sym, __attrs) \ static void * __used __attrs \ - __UNIQUE_ID(__PASTE(__addressable_,sym)) = (void *)(uintptr_t)&sym; + __UNIQUE_ID(__PASTE(addressable_, sym)) = (void *)(uintptr_t)&sym; #define __ADDRESSABLE(sym) \ ___ADDRESSABLE(sym, __section(".discard.addressable")) diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h index 59288a2c1ad2..0a1b9598940d 100644 --- a/include/linux/compiler_types.h +++ b/include/linux/compiler_types.h @@ -250,10 +250,9 @@ struct ftrace_likely_data { /* * GCC does not warn about unused static inline functions for -Wunused-function. * Suppress the warning in clang as well by using __maybe_unused, but enable it - * for W=1 build. This will allow clang to find unused functions. Remove the - * __inline_maybe_unused entirely after fixing most of -Wunused-function warnings. + * for W=2 build. This will allow clang to find unused functions. */ -#ifdef KBUILD_EXTRA_WARN1 +#ifdef KBUILD_EXTRA_WARN2 #define __inline_maybe_unused #else #define __inline_maybe_unused __maybe_unused @@ -461,6 +460,12 @@ struct ftrace_likely_data { # define __nocfi #endif +#if defined(CONFIG_ARCH_USES_CFI_GENERIC_LLVM_PASS) +# define __nocfi_generic __nocfi +#else +# define __nocfi_generic +#endif + /* * Any place that could be marked with the "alloc_size" attribute is also * a place to be marked with the "malloc" attribute, except those that may diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index ff8f41ab7ce6..afedfd5bea07 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -126,6 +126,7 @@ extern struct cpumask __cpu_dying_mask; #define cpu_dying_mask ((const struct cpumask *)&__cpu_dying_mask) extern atomic_t __num_online_cpus; +extern unsigned int __num_possible_cpus; extern cpumask_t cpus_booted_once_mask; @@ -729,6 +730,22 @@ void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, } /** + * cpumask_weighted_or - *dstp = *src1p | *src2p and return the weight of the result + * @dstp: the cpumask result + * @src1p: the first input + * @src2p: the second input + * + * Return: The number of bits set in the resulting cpumask @dstp + */ +static __always_inline +unsigned int cpumask_weighted_or(struct cpumask *dstp, const struct cpumask *src1p, + const struct cpumask *src2p) +{ + return bitmap_weighted_or(cpumask_bits(dstp), cpumask_bits(src1p), + cpumask_bits(src2p), small_cpumask_bits); +} + +/** * cpumask_xor - *dstp = *src1p ^ *src2p * @dstp: the cpumask result * @src1p: the first input @@ -1005,6 +1022,7 @@ static __always_inline unsigned int cpumask_size(void) #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly +#define CPUMASK_VAR_NULL NULL bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); @@ -1051,6 +1069,7 @@ static __always_inline bool cpumask_available(cpumask_var_t mask) #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly +#define CPUMASK_VAR_NULL {} static __always_inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { @@ -1136,13 +1155,13 @@ void init_cpu_possible(const struct cpumask *src); #define __assign_cpu(cpu, mask, val) \ __assign_bit(cpumask_check(cpu), cpumask_bits(mask), (val)) -#define set_cpu_possible(cpu, possible) assign_cpu((cpu), &__cpu_possible_mask, (possible)) #define set_cpu_enabled(cpu, enabled) assign_cpu((cpu), &__cpu_enabled_mask, (enabled)) #define set_cpu_present(cpu, present) assign_cpu((cpu), &__cpu_present_mask, (present)) #define set_cpu_active(cpu, active) assign_cpu((cpu), &__cpu_active_mask, (active)) #define set_cpu_dying(cpu, dying) assign_cpu((cpu), &__cpu_dying_mask, (dying)) void set_cpu_online(unsigned int cpu, bool online); +void set_cpu_possible(unsigned int cpu, bool possible); /** * to_cpumask - convert a NR_CPUS bitmap to a struct cpumask * @@ -1195,7 +1214,12 @@ static __always_inline unsigned int num_online_cpus(void) { return raw_atomic_read(&__num_online_cpus); } -#define num_possible_cpus() cpumask_weight(cpu_possible_mask) + +static __always_inline unsigned int num_possible_cpus(void) +{ + return __num_possible_cpus; +} + #define num_enabled_cpus() cpumask_weight(cpu_enabled_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) diff --git a/include/linux/cred.h b/include/linux/cred.h index 89ae50ad2ace..343a140a6ba2 100644 --- a/include/linux/cred.h +++ b/include/linux/cred.h @@ -20,6 +20,8 @@ struct cred; struct inode; +extern struct task_struct init_task; + /* * COW Supplementary groups list */ @@ -156,6 +158,11 @@ extern struct cred *prepare_exec_creds(void); extern int commit_creds(struct cred *); extern void abort_creds(struct cred *); extern struct cred *prepare_kernel_cred(struct task_struct *); +static inline const struct cred *kernel_cred(void) +{ + /* shut up sparse */ + return rcu_dereference_raw(init_task.cred); +} extern int set_security_override(struct cred *, u32); extern int set_security_override_from_ctx(struct cred *, const char *); extern int set_create_files_as(struct cred *, struct inode *); @@ -180,6 +187,16 @@ static inline const struct cred *revert_creds(const struct cred *revert_cred) return rcu_replace_pointer(current->cred, revert_cred, 1); } +DEFINE_CLASS(override_creds, + const struct cred *, + revert_creds(_T), + override_creds(override_cred), const struct cred *override_cred) + +#define scoped_with_creds(cred) \ + scoped_class(override_creds, __UNIQUE_ID(label), cred) + +#define scoped_with_kernel_creds() scoped_with_creds(kernel_cred()) + /** * get_cred_many - Get references on a set of credentials * @cred: The credentials to reference @@ -263,6 +280,11 @@ static inline void put_cred(const struct cred *cred) put_cred_many(cred, 1); } +DEFINE_CLASS(prepare_creds, + struct cred *, + if (_T) put_cred(_T), + prepare_creds(), void) + DEFINE_FREE(put_cred, struct cred *, if (!IS_ERR_OR_NULL(_T)) put_cred(_T)) /** diff --git a/include/linux/delay.h b/include/linux/delay.h index 89866bab100d..46412c00033a 100644 --- a/include/linux/delay.h +++ b/include/linux/delay.h @@ -68,7 +68,7 @@ void usleep_range_state(unsigned long min, unsigned long max, * @min: Minimum time in microseconds to sleep * @max: Maximum time in microseconds to sleep * - * For basic information please refere to usleep_range_state(). + * For basic information please refer to usleep_range_state(). * * The task will be in the state TASK_UNINTERRUPTIBLE during the sleep. */ @@ -82,10 +82,10 @@ static inline void usleep_range(unsigned long min, unsigned long max) * @min: Minimum time in microseconds to sleep * @max: Maximum time in microseconds to sleep * - * For basic information please refere to usleep_range_state(). + * For basic information please refer to usleep_range_state(). * * The sleeping task has the state TASK_IDLE during the sleep to prevent - * contribution to the load avarage. + * contribution to the load average. */ static inline void usleep_range_idle(unsigned long min, unsigned long max) { @@ -96,7 +96,7 @@ static inline void usleep_range_idle(unsigned long min, unsigned long max) * ssleep - wrapper for seconds around msleep * @seconds: Requested sleep duration in seconds * - * Please refere to msleep() for detailed information. + * Please refer to msleep() for detailed information. */ static inline void ssleep(unsigned int seconds) { diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index 8248ff9363ee..2ceda49c609f 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -90,7 +90,7 @@ */ #define DMA_MAPPING_ERROR (~(dma_addr_t)0) -#define DMA_BIT_MASK(n) (((n) == 64) ? ~0ULL : ((1ULL<<(n))-1)) +#define DMA_BIT_MASK(n) GENMASK_ULL(n - 1, 0) struct dma_iova_state { dma_addr_t addr; diff --git a/include/linux/elfnote.h b/include/linux/elfnote.h index 69b136e4dd2b..bb3dcded055f 100644 --- a/include/linux/elfnote.h +++ b/include/linux/elfnote.h @@ -60,23 +60,21 @@ #else /* !__ASSEMBLER__ */ #include <uapi/linux/elf.h> +#include <linux/compiler.h> /* * Use an anonymous structure which matches the shape of * Elf{32,64}_Nhdr, but includes the name and desc data. The size and * type of name and desc depend on the macro arguments. "name" must - * be a literal string, and "desc" must be passed by value. You may - * only define one note per line, since __LINE__ is used to generate - * unique symbols. + * be a literal string, and "desc" must be passed by value. */ -#define _ELFNOTE_PASTE(a,b) a##b -#define _ELFNOTE(size, name, unique, type, desc) \ +#define ELFNOTE(size, name, type, desc) \ static const struct { \ struct elf##size##_note _nhdr; \ unsigned char _name[sizeof(name)] \ __attribute__((aligned(sizeof(Elf##size##_Word)))); \ typeof(desc) _desc \ __attribute__((aligned(sizeof(Elf##size##_Word)))); \ - } _ELFNOTE_PASTE(_note_, unique) \ + } __UNIQUE_ID(note) \ __used \ __attribute__((section(".note." name), \ aligned(sizeof(Elf##size##_Word)), \ @@ -89,11 +87,10 @@ name, \ desc \ } -#define ELFNOTE(size, name, type, desc) \ - _ELFNOTE(size, name, __LINE__, type, desc) #define ELFNOTE32(name, type, desc) ELFNOTE(32, name, type, desc) #define ELFNOTE64(name, type, desc) ELFNOTE(64, name, type, desc) + #endif /* __ASSEMBLER__ */ #endif /* _LINUX_ELFNOTE_H */ diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h index 7177436f0f9e..87efb38b7081 100644 --- a/include/linux/entry-common.h +++ b/include/linux/entry-common.h @@ -3,11 +3,11 @@ #define __LINUX_ENTRYCOMMON_H #include <linux/irq-entry-common.h> +#include <linux/livepatch.h> #include <linux/ptrace.h> +#include <linux/resume_user_mode.h> #include <linux/seccomp.h> #include <linux/sched.h> -#include <linux/livepatch.h> -#include <linux/resume_user_mode.h> #include <asm/entry-common.h> #include <asm/syscall.h> @@ -37,6 +37,7 @@ SYSCALL_WORK_SYSCALL_AUDIT | \ SYSCALL_WORK_SYSCALL_USER_DISPATCH | \ ARCH_SYSCALL_WORK_ENTER) + #define SYSCALL_WORK_EXIT (SYSCALL_WORK_SYSCALL_TRACEPOINT | \ SYSCALL_WORK_SYSCALL_TRACE | \ SYSCALL_WORK_SYSCALL_AUDIT | \ @@ -44,25 +45,7 @@ SYSCALL_WORK_SYSCALL_EXIT_TRAP | \ ARCH_SYSCALL_WORK_EXIT) -/** - * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts - * @regs: Pointer to currents pt_regs - * - * Invoked from architecture specific syscall entry code with interrupts - * disabled. The calling code has to be non-instrumentable. When the - * function returns all state is correct, interrupts are enabled and the - * subsequent functions can be instrumented. - * - * This handles lockdep, RCU (context tracking) and tracing state, i.e. - * the functionality provided by enter_from_user_mode(). - * - * This is invoked when there is extra architecture specific functionality - * to be done between establishing state and handling user mode entry work. - */ -void syscall_enter_from_user_mode_prepare(struct pt_regs *regs); - -long syscall_trace_enter(struct pt_regs *regs, long syscall, - unsigned long work); +long syscall_trace_enter(struct pt_regs *regs, long syscall, unsigned long work); /** * syscall_enter_from_user_mode_work - Check and handle work before invoking @@ -71,8 +54,8 @@ long syscall_trace_enter(struct pt_regs *regs, long syscall, * @syscall: The syscall number * * Invoked from architecture specific syscall entry code with interrupts - * enabled after invoking syscall_enter_from_user_mode_prepare() and extra - * architecture specific work. + * enabled after invoking enter_from_user_mode(), enabling interrupts and + * extra architecture specific work. * * Returns: The original or a modified syscall number * @@ -108,8 +91,9 @@ static __always_inline long syscall_enter_from_user_mode_work(struct pt_regs *re * function returns all state is correct, interrupts are enabled and the * subsequent functions can be instrumented. * - * This is combination of syscall_enter_from_user_mode_prepare() and - * syscall_enter_from_user_mode_work(). + * This is the combination of enter_from_user_mode() and + * syscall_enter_from_user_mode_work() to be used when there is no + * architecture specific work to be done between the two. * * Returns: The original or a modified syscall number. See * syscall_enter_from_user_mode_work() for further explanation. @@ -162,7 +146,7 @@ static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs) local_irq_enable(); } - rseq_syscall(regs); + rseq_debug_syscall_return(regs); /* * Do one-time syscall specific work. If these work items are @@ -172,7 +156,7 @@ static __always_inline void syscall_exit_to_user_mode_work(struct pt_regs *regs) if (unlikely(work & SYSCALL_WORK_EXIT)) syscall_exit_work(regs, work); local_irq_disable_exit_to_user(); - exit_to_user_mode_prepare(regs); + syscall_exit_to_user_mode_prepare(regs); } /** diff --git a/include/linux/entry-virt.h b/include/linux/entry-virt.h index 42c89e3e5ca7..bfa767702d9a 100644 --- a/include/linux/entry-virt.h +++ b/include/linux/entry-virt.h @@ -32,7 +32,7 @@ */ static inline int arch_xfer_to_guest_mode_handle_work(unsigned long ti_work); -#ifndef arch_xfer_to_guest_mode_work +#ifndef arch_xfer_to_guest_mode_handle_work static inline int arch_xfer_to_guest_mode_handle_work(unsigned long ti_work) { return 0; diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c2d8b4ec62eb..5c9162193d26 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -492,7 +492,7 @@ struct ethtool_pause_stats { }; #define ETHTOOL_MAX_LANES 8 -/** +/* * IEEE 802.3ck/df defines 16 bins for FEC histogram plus one more for * the end-of-list marker, total 17 items */ diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h index d0cf10d5e0f7..f0cf2714ec52 100644 --- a/include/linux/exportfs.h +++ b/include/linux/exportfs.h @@ -320,9 +320,6 @@ static inline bool exportfs_can_decode_fh(const struct export_operations *nop) static inline bool exportfs_can_encode_fh(const struct export_operations *nop, int fh_flags) { - if (!nop) - return false; - /* * If a non-decodeable file handle was requested, we only need to make * sure that filesystem did not opt-out of encoding fid. @@ -330,6 +327,10 @@ static inline bool exportfs_can_encode_fh(const struct export_operations *nop, if (fh_flags & EXPORT_FH_FID) return exportfs_can_encode_fid(nop); + /* Normal file handles cannot be created without export ops */ + if (!nop) + return false; + /* * If a connectable file handle was requested, we need to make sure that * filesystem can also decode connected file handles. diff --git a/include/linux/fbcon.h b/include/linux/fbcon.h index 81f0e698acbf..f206370060e1 100644 --- a/include/linux/fbcon.h +++ b/include/linux/fbcon.h @@ -18,6 +18,7 @@ void fbcon_suspended(struct fb_info *info); void fbcon_resumed(struct fb_info *info); int fbcon_mode_deleted(struct fb_info *info, struct fb_videomode *mode); +void fbcon_delete_modelist(struct list_head *head); void fbcon_new_modelist(struct fb_info *info); void fbcon_get_requirement(struct fb_info *info, struct fb_blit_caps *caps); @@ -38,6 +39,7 @@ static inline void fbcon_suspended(struct fb_info *info) {} static inline void fbcon_resumed(struct fb_info *info) {} static inline int fbcon_mode_deleted(struct fb_info *info, struct fb_videomode *mode) { return 0; } +static inline void fbcon_delete_modelist(struct list_head *head) {} static inline void fbcon_new_modelist(struct fb_info *info) {} static inline void fbcon_get_requirement(struct fb_info *info, struct fb_blit_caps *caps) {} diff --git a/include/linux/file.h b/include/linux/file.h index af1768d934a0..cf389fde9bc2 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -127,4 +127,130 @@ extern void __fput_sync(struct file *); extern unsigned int sysctl_nr_open_min, sysctl_nr_open_max; +/* + * fd_prepare: Combined fd + file allocation cleanup class. + * @err: Error code to indicate if allocation succeeded. + * @__fd: Allocated fd (may not be accessed directly) + * @__file: Allocated struct file pointer (may not be accessed directly) + * + * Allocates an fd and a file together. On error paths, automatically cleans + * up whichever resource was successfully allocated. Allows flexible file + * allocation with different functions per usage. + * + * Do not use directly. + */ +struct fd_prepare { + s32 err; + s32 __fd; /* do not access directly */ + struct file *__file; /* do not access directly */ +}; + +/* Typedef for fd_prepare cleanup guards. */ +typedef struct fd_prepare class_fd_prepare_t; + +/* + * Accessors for fd_prepare class members. + * _Generic() is used for zero-cost type safety. + */ +#define fd_prepare_fd(_fdf) \ + (_Generic((_fdf), struct fd_prepare: (_fdf).__fd)) + +#define fd_prepare_file(_fdf) \ + (_Generic((_fdf), struct fd_prepare: (_fdf).__file)) + +/* Do not use directly. */ +static inline void class_fd_prepare_destructor(const struct fd_prepare *fdf) +{ + if (unlikely(fdf->err)) { + if (likely(fdf->__fd >= 0)) + put_unused_fd(fdf->__fd); + if (unlikely(!IS_ERR_OR_NULL(fdf->__file))) + fput(fdf->__file); + } +} + +/* Do not use directly. */ +static inline int class_fd_prepare_lock_err(const struct fd_prepare *fdf) +{ + if (unlikely(fdf->err)) + return fdf->err; + if (unlikely(fdf->__fd < 0)) + return fdf->__fd; + if (unlikely(IS_ERR(fdf->__file))) + return PTR_ERR(fdf->__file); + if (unlikely(!fdf->__file)) + return -ENOMEM; + return 0; +} + +/* + * __FD_PREPARE_INIT - Helper to initialize fd_prepare class. + * @_fd_flags: flags for get_unused_fd_flags() + * @_file_owned: expression that returns struct file * + * + * Returns a struct fd_prepare with fd, file, and err set. + * If fd allocation fails, fd will be negative and err will be set. If + * fd succeeds but file_init_expr fails, file will be ERR_PTR and err + * will be set. The err field is the single source of truth for error + * checking. + */ +#define __FD_PREPARE_INIT(_fd_flags, _file_owned) \ + ({ \ + struct fd_prepare fdf = { \ + .__fd = get_unused_fd_flags((_fd_flags)), \ + }; \ + if (likely(fdf.__fd >= 0)) \ + fdf.__file = (_file_owned); \ + fdf.err = ACQUIRE_ERR(fd_prepare, &fdf); \ + fdf; \ + }) + +/* + * FD_PREPARE - Macro to declare and initialize an fd_prepare variable. + * + * Declares and initializes an fd_prepare variable with automatic + * cleanup. No separate scope required - cleanup happens when variable + * goes out of scope. + * + * @_fdf: name of struct fd_prepare variable to define + * @_fd_flags: flags for get_unused_fd_flags() + * @_file_owned: struct file to take ownership of (can be expression) + */ +#define FD_PREPARE(_fdf, _fd_flags, _file_owned) \ + CLASS_INIT(fd_prepare, _fdf, __FD_PREPARE_INIT(_fd_flags, _file_owned)) + +/* + * fd_publish - Publish prepared fd and file to the fd table. + * @_fdf: struct fd_prepare variable + */ +#define fd_publish(_fdf) \ + ({ \ + struct fd_prepare *fdp = &(_fdf); \ + VFS_WARN_ON_ONCE(fdp->err); \ + VFS_WARN_ON_ONCE(fdp->__fd < 0); \ + VFS_WARN_ON_ONCE(IS_ERR_OR_NULL(fdp->__file)); \ + fd_install(fdp->__fd, fdp->__file); \ + fdp->__fd; \ + }) + +/* Do not use directly. */ +#define __FD_ADD(_fdf, _fd_flags, _file_owned) \ + ({ \ + FD_PREPARE(_fdf, _fd_flags, _file_owned); \ + s32 ret = _fdf.err; \ + if (likely(!ret)) \ + ret = fd_publish(_fdf); \ + ret; \ + }) + +/* + * FD_ADD - Allocate and install an fd and file in one step. + * @_fd_flags: flags for get_unused_fd_flags() + * @_file_owned: struct file to take ownership of + * + * Returns the allocated fd number, or negative error code on failure. + */ +#define FD_ADD(_fd_flags, _file_owned) \ + __FD_ADD(__UNIQUE_ID(fd_prepare), _fd_flags, _file_owned) + #endif /* __LINUX_FILE_H */ diff --git a/include/linux/filelock.h b/include/linux/filelock.h index c2ce8ba05d06..54b824c05299 100644 --- a/include/linux/filelock.h +++ b/include/linux/filelock.h @@ -159,6 +159,8 @@ int fcntl_setlk64(unsigned int, struct file *, unsigned int, int fcntl_setlease(unsigned int fd, struct file *filp, int arg); int fcntl_getlease(struct file *filp); +int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg); +int fcntl_getdeleg(struct file *filp, struct delegation *deleg); static inline bool lock_is_unlock(struct file_lock *fl) { @@ -212,7 +214,14 @@ int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); void locks_init_lease(struct file_lease *); void locks_free_lease(struct file_lease *fl); struct file_lease *locks_alloc_lease(void); -int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); + +#define LEASE_BREAK_LEASE BIT(0) // break leases and delegations +#define LEASE_BREAK_DELEG BIT(1) // break delegations only +#define LEASE_BREAK_LAYOUT BIT(2) // break layouts only +#define LEASE_BREAK_NONBLOCK BIT(3) // non-blocking break +#define LEASE_BREAK_OPEN_RDONLY BIT(4) // readonly open event + +int __break_lease(struct inode *inode, unsigned int flags); void lease_get_mtime(struct inode *, struct timespec64 *time); int generic_setlease(struct file *, int, struct file_lease **, void **priv); int kernel_setlease(struct file *, int, struct file_lease **, void **); @@ -271,6 +280,16 @@ static inline int fcntl_getlease(struct file *filp) return F_UNLCK; } +static inline int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg) +{ + return -EINVAL; +} + +static inline int fcntl_getdeleg(struct file *filp, struct delegation *deleg) +{ + return -EINVAL; +} + static inline bool lock_is_unlock(struct file_lock *fl) { return false; @@ -367,7 +386,7 @@ static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *f return -ENOLCK; } -static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) +static inline int __break_lease(struct inode *inode, unsigned int flags) { return 0; } @@ -428,6 +447,17 @@ static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) } #ifdef CONFIG_FILE_LOCKING +static inline unsigned int openmode_to_lease_flags(unsigned int mode) +{ + unsigned int flags = 0; + + if ((mode & O_ACCMODE) == O_RDONLY) + flags |= LEASE_BREAK_OPEN_RDONLY; + if (mode & O_NONBLOCK) + flags |= LEASE_BREAK_NONBLOCK; + return flags; +} + static inline int break_lease(struct inode *inode, unsigned int mode) { struct file_lock_context *flctx; @@ -443,11 +473,11 @@ static inline int break_lease(struct inode *inode, unsigned int mode) return 0; smp_mb(); if (!list_empty_careful(&flctx->flc_lease)) - return __break_lease(inode, mode, FL_LEASE); + return __break_lease(inode, LEASE_BREAK_LEASE | openmode_to_lease_flags(mode)); return 0; } -static inline int break_deleg(struct inode *inode, unsigned int mode) +static inline int break_deleg(struct inode *inode, unsigned int flags) { struct file_lock_context *flctx; @@ -461,60 +491,84 @@ static inline int break_deleg(struct inode *inode, unsigned int mode) if (!flctx) return 0; smp_mb(); - if (!list_empty_careful(&flctx->flc_lease)) - return __break_lease(inode, mode, FL_DELEG); + if (!list_empty_careful(&flctx->flc_lease)) { + flags |= LEASE_BREAK_DELEG; + return __break_lease(inode, flags); + } return 0; } -static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) +struct delegated_inode { + struct inode *di_inode; +}; + +static inline bool is_delegated(struct delegated_inode *di) +{ + return di->di_inode; +} + +static inline int try_break_deleg(struct inode *inode, + struct delegated_inode *di) { int ret; - ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); - if (ret == -EWOULDBLOCK && delegated_inode) { - *delegated_inode = inode; + ret = break_deleg(inode, LEASE_BREAK_NONBLOCK); + if (ret == -EWOULDBLOCK && di) { + di->di_inode = inode; ihold(inode); } return ret; } -static inline int break_deleg_wait(struct inode **delegated_inode) +static inline int break_deleg_wait(struct delegated_inode *di) { int ret; - ret = break_deleg(*delegated_inode, O_WRONLY); - iput(*delegated_inode); - *delegated_inode = NULL; + ret = break_deleg(di->di_inode, 0); + iput(di->di_inode); + di->di_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { smp_mb(); - if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) - return __break_lease(inode, - wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, - FL_LAYOUT); + if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) { + unsigned int flags = LEASE_BREAK_LAYOUT; + + if (!wait) + flags |= LEASE_BREAK_NONBLOCK; + + return __break_lease(inode, flags); + } return 0; } #else /* !CONFIG_FILE_LOCKING */ -static inline int break_lease(struct inode *inode, unsigned int mode) +struct delegated_inode { }; + +static inline bool is_delegated(struct delegated_inode *di) +{ + return false; +} + +static inline int break_lease(struct inode *inode, bool wait) { return 0; } -static inline int break_deleg(struct inode *inode, unsigned int mode) +static inline int break_deleg(struct inode *inode, unsigned int flags) { return 0; } -static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) +static inline int try_break_deleg(struct inode *inode, + struct delegated_inode *delegated_inode) { return 0; } -static inline int break_deleg_wait(struct inode **delegated_inode) +static inline int break_deleg_wait(struct delegated_inode *delegated_inode) { BUG(); return 0; diff --git a/include/linux/filter.h b/include/linux/filter.h index f5c859b8131a..973233b82dc1 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -901,6 +901,26 @@ static inline void bpf_compute_data_pointers(struct sk_buff *skb) cb->data_end = skb->data + skb_headlen(skb); } +static inline int bpf_prog_run_data_pointers( + const struct bpf_prog *prog, + struct sk_buff *skb) +{ + struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; + void *save_data_meta, *save_data_end; + int res; + + save_data_meta = cb->data_meta; + save_data_end = cb->data_end; + + bpf_compute_data_pointers(skb); + res = bpf_prog_run(prog, skb); + + cb->data_meta = save_data_meta; + cb->data_end = save_data_end; + + return res; +} + /* Similar to bpf_compute_data_pointers(), except that save orginal * data in cb->data and cb->meta_data for restore. */ diff --git a/include/linux/fs.h b/include/linux/fs.h index c895146c1444..ce25feb06727 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2,6 +2,7 @@ #ifndef _LINUX_FS_H #define _LINUX_FS_H +#include <linux/fs/super.h> #include <linux/vfsdebug.h> #include <linux/linkage.h> #include <linux/wait_bit.h> @@ -11,7 +12,6 @@ #include <linux/stat.h> #include <linux/cache.h> #include <linux/list.h> -#include <linux/list_lru.h> #include <linux/llist.h> #include <linux/radix-tree.h> #include <linux/xarray.h> @@ -37,7 +37,6 @@ #include <linux/uuid.h> #include <linux/errseq.h> #include <linux/ioprio.h> -#include <linux/fs_types.h> #include <linux/build_bug.h> #include <linux/stddef.h> #include <linux/mount.h> @@ -52,11 +51,9 @@ #include <asm/byteorder.h> #include <uapi/linux/fs.h> -struct backing_dev_info; struct bdi_writeback; struct bio; struct io_comp_batch; -struct export_operations; struct fiemap_extent_info; struct hd_geometry; struct iovec; @@ -70,16 +67,13 @@ struct vfsmount; struct cred; struct swap_info_struct; struct seq_file; -struct workqueue_struct; struct iov_iter; -struct fscrypt_operations; -struct fsverity_operations; struct fsnotify_mark_connector; -struct fsnotify_sb_info; struct fs_context; struct fs_parameter_spec; struct file_kattr; struct iomap_ops; +struct delegated_inode; extern void __init inode_init(void); extern void __init inode_init_early(void); @@ -299,11 +293,6 @@ struct iattr { }; /* - * Includes for diskquotas. - */ -#include <linux/quota.h> - -/* * Maximum number of layers of fs stack. Needs to be limited to * prevent kernel stack overflow */ @@ -367,23 +356,9 @@ struct readahead_control; #define IOCB_NOIO (1 << 20) /* can use bio alloc cache */ #define IOCB_ALLOC_CACHE (1 << 21) -/* - * IOCB_DIO_CALLER_COMP can be set by the iocb owner, to indicate that the - * iocb completion can be passed back to the owner for execution from a safe - * context rather than needing to be punted through a workqueue. If this - * flag is set, the bio completion handling may set iocb->dio_complete to a - * handler function and iocb->private to context information for that handler. - * The issuer should call the handler with that context information from task - * context to complete the processing of the iocb. Note that while this - * provides a task context for the dio_complete() callback, it should only be - * used on the completion side for non-IO generating completions. It's fine to - * call blocking functions from this callback, but they should not wait for - * unrelated IO (like cache flushing, new IO generation, etc). - */ -#define IOCB_DIO_CALLER_COMP (1 << 22) /* kiocb is a read or write operation submitted by fs/aio.c. */ -#define IOCB_AIO_RW (1 << 23) -#define IOCB_HAS_METADATA (1 << 24) +#define IOCB_AIO_RW (1 << 22) +#define IOCB_HAS_METADATA (1 << 23) /* for use in trace events */ #define TRACE_IOCB_STRINGS \ @@ -400,7 +375,6 @@ struct readahead_control; { IOCB_WAITQ, "WAITQ" }, \ { IOCB_NOIO, "NOIO" }, \ { IOCB_ALLOC_CACHE, "ALLOC_CACHE" }, \ - { IOCB_DIO_CALLER_COMP, "CALLER_COMP" }, \ { IOCB_AIO_RW, "AIO_RW" }, \ { IOCB_HAS_METADATA, "AIO_HAS_METADATA" } @@ -412,23 +386,13 @@ struct kiocb { int ki_flags; u16 ki_ioprio; /* See linux/ioprio.h */ u8 ki_write_stream; - union { - /* - * Only used for async buffered reads, where it denotes the - * page waitqueue associated with completing the read. Valid - * IFF IOCB_WAITQ is set. - */ - struct wait_page_queue *ki_waitq; - /* - * Can be used for O_DIRECT IO, where the completion handling - * is punted back to the issuer of the IO. May only be set - * if IOCB_DIO_CALLER_COMP is set by the issuer, and the issuer - * must then check for presence of this handler when ki_complete - * is invoked. The data passed in to this handler must be - * assigned to ->private when dio_complete is assigned. - */ - ssize_t (*dio_complete)(void *data); - }; + + /* + * Only used for async buffered reads, where it denotes the page + * waitqueue associated with completing the read. + * Valid IFF IOCB_WAITQ is set. + */ + struct wait_page_queue *ki_waitq; }; static inline bool is_sync_kiocb(struct kiocb *kiocb) @@ -659,13 +623,14 @@ is_uncached_acl(struct posix_acl *acl) return (long)acl & 1; } -#define IOP_FASTPERM 0x0001 -#define IOP_LOOKUP 0x0002 -#define IOP_NOFOLLOW 0x0004 -#define IOP_XATTR 0x0008 +#define IOP_FASTPERM 0x0001 +#define IOP_LOOKUP 0x0002 +#define IOP_NOFOLLOW 0x0004 +#define IOP_XATTR 0x0008 #define IOP_DEFAULT_READLINK 0x0010 -#define IOP_MGTIME 0x0020 -#define IOP_CACHED_LINK 0x0040 +#define IOP_MGTIME 0x0020 +#define IOP_CACHED_LINK 0x0040 +#define IOP_FASTPERM_MAY_EXEC 0x0080 /* * Inode state bits. Protected by inode->i_lock @@ -759,7 +724,7 @@ enum inode_state_bits { /* reserved wait address bit 3 */ }; -enum inode_state_flags_t { +enum inode_state_flags_enum { I_NEW = (1U << __I_NEW), I_SYNC = (1U << __I_SYNC), I_LRU_ISOLATING = (1U << __I_LRU_ISOLATING), @@ -786,6 +751,13 @@ enum inode_state_flags_t { #define I_DIRTY_ALL (I_DIRTY | I_DIRTY_TIME) /* + * Use inode_state_read() & friends to access. + */ +struct inode_state_flags { + enum inode_state_flags_enum __state; +}; + +/* * Keep mostly read-only and often accessed (especially for * the RCU path lookup and 'stat' data) fields at the beginning * of the 'struct inode' @@ -793,14 +765,13 @@ enum inode_state_flags_t { struct inode { umode_t i_mode; unsigned short i_opflags; - kuid_t i_uid; - kgid_t i_gid; unsigned int i_flags; - #ifdef CONFIG_FS_POSIX_ACL struct posix_acl *i_acl; struct posix_acl *i_default_acl; #endif + kuid_t i_uid; + kgid_t i_gid; const struct inode_operations *i_op; struct super_block *i_sb; @@ -843,7 +814,7 @@ struct inode { #endif /* Misc */ - enum inode_state_flags_t i_state; + struct inode_state_flags i_state; /* 32-bit hole */ struct rw_semaphore i_rwsem; @@ -902,6 +873,80 @@ struct inode { void *i_private; /* fs or device private pointer */ } __randomize_layout; +/* + * i_state handling + * + * We hide all of it behind helpers so that we can validate consumers. + */ +static inline enum inode_state_flags_enum inode_state_read_once(struct inode *inode) +{ + return READ_ONCE(inode->i_state.__state); +} + +static inline enum inode_state_flags_enum inode_state_read(struct inode *inode) +{ + lockdep_assert_held(&inode->i_lock); + return inode->i_state.__state; +} + +static inline void inode_state_set_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, inode->i_state.__state | flags); +} + +static inline void inode_state_set(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_set_raw(inode, flags); +} + +static inline void inode_state_clear_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, inode->i_state.__state & ~flags); +} + +static inline void inode_state_clear(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_clear_raw(inode, flags); +} + +static inline void inode_state_assign_raw(struct inode *inode, + enum inode_state_flags_enum flags) +{ + WRITE_ONCE(inode->i_state.__state, flags); +} + +static inline void inode_state_assign(struct inode *inode, + enum inode_state_flags_enum flags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_assign_raw(inode, flags); +} + +static inline void inode_state_replace_raw(struct inode *inode, + enum inode_state_flags_enum clearflags, + enum inode_state_flags_enum setflags) +{ + enum inode_state_flags_enum flags; + flags = inode->i_state.__state; + flags &= ~clearflags; + flags |= setflags; + inode_state_assign_raw(inode, flags); +} + +static inline void inode_state_replace(struct inode *inode, + enum inode_state_flags_enum clearflags, + enum inode_state_flags_enum setflags) +{ + lockdep_assert_held(&inode->i_lock); + inode_state_replace_raw(inode, clearflags, setflags); +} + static inline void inode_set_cached_link(struct inode *inode, char *link, int linklen) { VFS_WARN_ON_INODE(strlen(link) != linklen, inode); @@ -949,6 +994,8 @@ static inline void inode_fake_hash(struct inode *inode) hlist_add_fake(&inode->i_hash); } +void wait_on_new_inode(struct inode *inode); + /* * inode->i_rwsem nesting subclasses for the lock validator: * @@ -1348,49 +1395,6 @@ extern pid_t f_getown(struct file *filp); extern int send_sigurg(struct file *file); /* - * sb->s_flags. Note that these mirror the equivalent MS_* flags where - * represented in both. - */ -#define SB_RDONLY BIT(0) /* Mount read-only */ -#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ -#define SB_NODEV BIT(2) /* Disallow access to device special files */ -#define SB_NOEXEC BIT(3) /* Disallow program execution */ -#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ -#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ -#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ -#define SB_NOATIME BIT(10) /* Do not update access times. */ -#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ -#define SB_SILENT BIT(15) -#define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ -#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ -#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ -#define SB_I_VERSION BIT(23) /* Update inode I_version field */ -#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ - -/* These sb flags are internal to the kernel */ -#define SB_DEAD BIT(21) -#define SB_DYING BIT(24) -#define SB_FORCE BIT(27) -#define SB_NOSEC BIT(28) -#define SB_BORN BIT(29) -#define SB_ACTIVE BIT(30) -#define SB_NOUSER BIT(31) - -/* These flags relate to encoding and casefolding */ -#define SB_ENC_STRICT_MODE_FL (1 << 0) -#define SB_ENC_NO_COMPAT_FALLBACK_FL (1 << 1) - -#define sb_has_strict_encoding(sb) \ - (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) - -#if IS_ENABLED(CONFIG_UNICODE) -#define sb_no_casefold_compat_fallback(sb) \ - (sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL) -#else -#define sb_no_casefold_compat_fallback(sb) (1) -#endif - -/* * Umount options */ @@ -1400,191 +1404,6 @@ extern int send_sigurg(struct file *file); #define UMOUNT_NOFOLLOW 0x00000008 /* Don't follow symlink on umount */ #define UMOUNT_UNUSED 0x80000000 /* Flag guaranteed to be unused */ -/* sb->s_iflags */ -#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ -#define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ -#define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ -#define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ - -/* sb->s_iflags to limit user namespace mounts */ -#define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ -#define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 -#define SB_I_UNTRUSTED_MOUNTER 0x00000040 -#define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 - -#define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ -#define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ -#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ -#define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ -#define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ -#define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ -#define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ - -/* Possible states of 'frozen' field */ -enum { - SB_UNFROZEN = 0, /* FS is unfrozen */ - SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ - SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ - SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop - * internal threads if needed) */ - SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ -}; - -#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) - -struct sb_writers { - unsigned short frozen; /* Is sb frozen? */ - int freeze_kcount; /* How many kernel freeze requests? */ - int freeze_ucount; /* How many userspace freeze requests? */ - const void *freeze_owner; /* Owner of the freeze */ - struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; -}; - -struct mount; - -struct super_block { - struct list_head s_list; /* Keep this first */ - dev_t s_dev; /* search index; _not_ kdev_t */ - unsigned char s_blocksize_bits; - unsigned long s_blocksize; - loff_t s_maxbytes; /* Max file size */ - struct file_system_type *s_type; - const struct super_operations *s_op; - const struct dquot_operations *dq_op; - const struct quotactl_ops *s_qcop; - const struct export_operations *s_export_op; - unsigned long s_flags; - unsigned long s_iflags; /* internal SB_I_* flags */ - unsigned long s_magic; - struct dentry *s_root; - struct rw_semaphore s_umount; - int s_count; - atomic_t s_active; -#ifdef CONFIG_SECURITY - void *s_security; -#endif - const struct xattr_handler * const *s_xattr; -#ifdef CONFIG_FS_ENCRYPTION - const struct fscrypt_operations *s_cop; - struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ -#endif -#ifdef CONFIG_FS_VERITY - const struct fsverity_operations *s_vop; -#endif -#if IS_ENABLED(CONFIG_UNICODE) - struct unicode_map *s_encoding; - __u16 s_encoding_flags; -#endif - struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ - struct mount *s_mounts; /* list of mounts; _not_ for fs use */ - struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ - struct file *s_bdev_file; - struct backing_dev_info *s_bdi; - struct mtd_info *s_mtd; - struct hlist_node s_instances; - unsigned int s_quota_types; /* Bitmask of supported quota types */ - struct quota_info s_dquot; /* Diskquota specific options */ - - struct sb_writers s_writers; - - /* - * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and - * s_fsnotify_info together for cache efficiency. They are frequently - * accessed and rarely modified. - */ - void *s_fs_info; /* Filesystem private info */ - - /* Granularity of c/m/atime in ns (cannot be worse than a second) */ - u32 s_time_gran; - /* Time limits for c/m/atime in seconds */ - time64_t s_time_min; - time64_t s_time_max; -#ifdef CONFIG_FSNOTIFY - u32 s_fsnotify_mask; - struct fsnotify_sb_info *s_fsnotify_info; -#endif - - /* - * q: why are s_id and s_sysfs_name not the same? both are human - * readable strings that identify the filesystem - * a: s_id is allowed to change at runtime; it's used in log messages, - * and we want to when a device starts out as single device (s_id is dev - * name) but then a device is hot added and we have to switch to - * identifying it by UUID - * but s_sysfs_name is a handle for programmatic access, and can't - * change at runtime - */ - char s_id[32]; /* Informational name */ - uuid_t s_uuid; /* UUID */ - u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ - - /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ - char s_sysfs_name[UUID_STRING_LEN + 1]; - - unsigned int s_max_links; - unsigned int s_d_flags; /* default d_flags for dentries */ - - /* - * The next field is for VFS *only*. No filesystems have any business - * even looking at it. You had been warned. - */ - struct mutex s_vfs_rename_mutex; /* Kludge */ - - /* - * Filesystem subtype. If non-empty the filesystem type field - * in /proc/mounts will be "type.subtype" - */ - const char *s_subtype; - - const struct dentry_operations *__s_d_op; /* default d_op for dentries */ - - struct shrinker *s_shrink; /* per-sb shrinker handle */ - - /* Number of inodes with nlink == 0 but still referenced */ - atomic_long_t s_remove_count; - - /* Read-only state of the superblock is being changed */ - int s_readonly_remount; - - /* per-sb errseq_t for reporting writeback errors via syncfs */ - errseq_t s_wb_err; - - /* AIO completions deferred from interrupt context */ - struct workqueue_struct *s_dio_done_wq; - struct hlist_head s_pins; - - /* - * Owning user namespace and default context in which to - * interpret filesystem uids, gids, quotas, device nodes, - * xattrs and security labels. - */ - struct user_namespace *s_user_ns; - - /* - * The list_lru structure is essentially just a pointer to a table - * of per-node lru lists, each of which has its own spinlock. - * There is no need to put them into separate cachelines. - */ - struct list_lru s_dentry_lru; - struct list_lru s_inode_lru; - struct rcu_head rcu; - struct work_struct destroy_work; - - struct mutex s_sync_lock; /* sync serialisation lock */ - - /* - * Indicates how deep in a filesystem stack this SB is - */ - int s_stack_depth; - - /* s_inode_list_lock protects s_inodes */ - spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; - struct list_head s_inodes; /* all inodes */ - - spinlock_t s_inode_wblist_lock; - struct list_head s_inodes_wb; /* writeback inodes */ -} __randomize_layout; - static inline struct user_namespace *i_user_ns(const struct inode *inode) { return inode->i_sb->s_user_ns; @@ -1902,66 +1721,6 @@ struct timespec64 simple_inode_init_ts(struct inode *inode); * Snapshotting support. */ -/* - * These are internal functions, please use sb_start_{write,pagefault,intwrite} - * instead. - */ -static inline void __sb_end_write(struct super_block *sb, int level) -{ - percpu_up_read(sb->s_writers.rw_sem + level-1); -} - -static inline void __sb_start_write(struct super_block *sb, int level) -{ - percpu_down_read_freezable(sb->s_writers.rw_sem + level - 1, true); -} - -static inline bool __sb_start_write_trylock(struct super_block *sb, int level) -{ - return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); -} - -#define __sb_writers_acquired(sb, lev) \ - percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev)-1], 1, _THIS_IP_) -#define __sb_writers_release(sb, lev) \ - percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev)-1], _THIS_IP_) - -/** - * __sb_write_started - check if sb freeze level is held - * @sb: the super we write to - * @level: the freeze level - * - * * > 0 - sb freeze level is held - * * 0 - sb freeze level is not held - * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN - */ -static inline int __sb_write_started(const struct super_block *sb, int level) -{ - return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); -} - -/** - * sb_write_started - check if SB_FREEZE_WRITE is held - * @sb: the super we write to - * - * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. - */ -static inline bool sb_write_started(const struct super_block *sb) -{ - return __sb_write_started(sb, SB_FREEZE_WRITE); -} - -/** - * sb_write_not_started - check if SB_FREEZE_WRITE is not held - * @sb: the super we write to - * - * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. - */ -static inline bool sb_write_not_started(const struct super_block *sb) -{ - return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; -} - /** * file_write_started - check if SB_FREEZE_WRITE is held * @file: the file we write to @@ -1992,137 +1751,26 @@ static inline bool file_write_not_started(const struct file *file) return sb_write_not_started(file_inode(file)->i_sb); } -/** - * sb_end_write - drop write access to a superblock - * @sb: the super we wrote to - * - * Decrement number of writers to the filesystem. Wake up possible waiters - * wanting to freeze the filesystem. - */ -static inline void sb_end_write(struct super_block *sb) -{ - __sb_end_write(sb, SB_FREEZE_WRITE); -} - -/** - * sb_end_pagefault - drop write access to a superblock from a page fault - * @sb: the super we wrote to - * - * Decrement number of processes handling write page fault to the filesystem. - * Wake up possible waiters wanting to freeze the filesystem. - */ -static inline void sb_end_pagefault(struct super_block *sb) -{ - __sb_end_write(sb, SB_FREEZE_PAGEFAULT); -} - -/** - * sb_end_intwrite - drop write access to a superblock for internal fs purposes - * @sb: the super we wrote to - * - * Decrement fs-internal number of writers to the filesystem. Wake up possible - * waiters wanting to freeze the filesystem. - */ -static inline void sb_end_intwrite(struct super_block *sb) -{ - __sb_end_write(sb, SB_FREEZE_FS); -} - -/** - * sb_start_write - get write access to a superblock - * @sb: the super we write to - * - * When a process wants to write data or metadata to a file system (i.e. dirty - * a page or an inode), it should embed the operation in a sb_start_write() - - * sb_end_write() pair to get exclusion against file system freezing. This - * function increments number of writers preventing freezing. If the file - * system is already frozen, the function waits until the file system is - * thawed. - * - * Since freeze protection behaves as a lock, users have to preserve - * ordering of freeze protection and other filesystem locks. Generally, - * freeze protection should be the outermost lock. In particular, we have: - * - * sb_start_write - * -> i_rwsem (write path, truncate, directory ops, ...) - * -> s_umount (freeze_super, thaw_super) - */ -static inline void sb_start_write(struct super_block *sb) -{ - __sb_start_write(sb, SB_FREEZE_WRITE); -} - -static inline bool sb_start_write_trylock(struct super_block *sb) -{ - return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); -} - -/** - * sb_start_pagefault - get write access to a superblock from a page fault - * @sb: the super we write to - * - * When a process starts handling write page fault, it should embed the - * operation into sb_start_pagefault() - sb_end_pagefault() pair to get - * exclusion against file system freezing. This is needed since the page fault - * is going to dirty a page. This function increments number of running page - * faults preventing freezing. If the file system is already frozen, the - * function waits until the file system is thawed. - * - * Since page fault freeze protection behaves as a lock, users have to preserve - * ordering of freeze protection and other filesystem locks. It is advised to - * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault - * handling code implies lock dependency: - * - * mmap_lock - * -> sb_start_pagefault - */ -static inline void sb_start_pagefault(struct super_block *sb) -{ - __sb_start_write(sb, SB_FREEZE_PAGEFAULT); -} - -/** - * sb_start_intwrite - get write access to a superblock for internal fs purposes - * @sb: the super we write to - * - * This is the third level of protection against filesystem freezing. It is - * free for use by a filesystem. The only requirement is that it must rank - * below sb_start_pagefault. - * - * For example filesystem can call sb_start_intwrite() when starting a - * transaction which somewhat eases handling of freezing for internal sources - * of filesystem changes (internal fs threads, discarding preallocation on file - * close, etc.). - */ -static inline void sb_start_intwrite(struct super_block *sb) -{ - __sb_start_write(sb, SB_FREEZE_FS); -} - -static inline bool sb_start_intwrite_trylock(struct super_block *sb) -{ - return __sb_start_write_trylock(sb, SB_FREEZE_FS); -} - bool inode_owner_or_capable(struct mnt_idmap *idmap, const struct inode *inode); /* * VFS helper functions.. */ -int vfs_create(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t, bool); +int vfs_create(struct mnt_idmap *, struct dentry *, umode_t, + struct delegated_inode *); struct dentry *vfs_mkdir(struct mnt_idmap *, struct inode *, - struct dentry *, umode_t); + struct dentry *, umode_t, struct delegated_inode *); int vfs_mknod(struct mnt_idmap *, struct inode *, struct dentry *, - umode_t, dev_t); + umode_t, dev_t, struct delegated_inode *); int vfs_symlink(struct mnt_idmap *, struct inode *, - struct dentry *, const char *); + struct dentry *, const char *, struct delegated_inode *); int vfs_link(struct dentry *, struct mnt_idmap *, struct inode *, - struct dentry *, struct inode **); -int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *); + struct dentry *, struct delegated_inode *); +int vfs_rmdir(struct mnt_idmap *, struct inode *, struct dentry *, + struct delegated_inode *); int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *, - struct inode **); + struct delegated_inode *); /** * struct renamedata - contains all information required for renaming @@ -2140,7 +1788,7 @@ struct renamedata { struct dentry *old_dentry; struct dentry *new_parent; struct dentry *new_dentry; - struct inode **delegated_inode; + struct delegated_inode *delegated_inode; unsigned int flags; } __randomize_layout; @@ -2150,7 +1798,7 @@ static inline int vfs_whiteout(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry) { return vfs_mknod(idmap, dir, dentry, S_IFCHR | WHITEOUT_MODE, - WHITEOUT_DEV); + WHITEOUT_DEV, NULL); } struct file *kernel_tmpfile_open(struct mnt_idmap *idmap, @@ -2431,72 +2079,6 @@ extern loff_t vfs_dedupe_file_range_one(struct file *src_file, loff_t src_pos, struct file *dst_file, loff_t dst_pos, loff_t len, unsigned int remap_flags); -/** - * enum freeze_holder - holder of the freeze - * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem - * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem - * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed - * @FREEZE_EXCL: a freeze that can only be undone by the owner - * - * Indicate who the owner of the freeze or thaw request is and whether - * the freeze needs to be exclusive or can nest. - * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the - * same holder aren't allowed. It is however allowed to hold a single - * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at - * the same time. This is relied upon by some filesystems during online - * repair or similar. - */ -enum freeze_holder { - FREEZE_HOLDER_KERNEL = (1U << 0), - FREEZE_HOLDER_USERSPACE = (1U << 1), - FREEZE_MAY_NEST = (1U << 2), - FREEZE_EXCL = (1U << 3), -}; - -struct super_operations { - struct inode *(*alloc_inode)(struct super_block *sb); - void (*destroy_inode)(struct inode *); - void (*free_inode)(struct inode *); - - void (*dirty_inode) (struct inode *, int flags); - int (*write_inode) (struct inode *, struct writeback_control *wbc); - int (*drop_inode) (struct inode *); - void (*evict_inode) (struct inode *); - void (*put_super) (struct super_block *); - int (*sync_fs)(struct super_block *sb, int wait); - int (*freeze_super) (struct super_block *, enum freeze_holder who, const void *owner); - int (*freeze_fs) (struct super_block *); - int (*thaw_super) (struct super_block *, enum freeze_holder who, const void *owner); - int (*unfreeze_fs) (struct super_block *); - int (*statfs) (struct dentry *, struct kstatfs *); - int (*remount_fs) (struct super_block *, int *, char *); - void (*umount_begin) (struct super_block *); - - int (*show_options)(struct seq_file *, struct dentry *); - int (*show_devname)(struct seq_file *, struct dentry *); - int (*show_path)(struct seq_file *, struct dentry *); - int (*show_stats)(struct seq_file *, struct dentry *); -#ifdef CONFIG_QUOTA - ssize_t (*quota_read)(struct super_block *, int, char *, size_t, loff_t); - ssize_t (*quota_write)(struct super_block *, int, const char *, size_t, loff_t); - struct dquot __rcu **(*get_dquots)(struct inode *); -#endif - long (*nr_cached_objects)(struct super_block *, - struct shrink_control *); - long (*free_cached_objects)(struct super_block *, - struct shrink_control *); - /* - * If a filesystem can support graceful removal of a device and - * continue read-write operations, implement this callback. - * - * Return 0 if the filesystem can continue read-write. - * Non-zero return value or no such callback means the fs will be shutdown - * as usual. - */ - int (*remove_bdev)(struct super_block *sb, struct block_device *bdev); - void (*shutdown)(struct super_block *sb); -}; - /* * Inode flags - they have no relation to superblock flags now */ @@ -2539,7 +2121,6 @@ struct super_operations { */ #define __IS_FLG(inode, flg) ((inode)->i_sb->s_flags & (flg)) -static inline bool sb_rdonly(const struct super_block *sb) { return sb->s_flags & SB_RDONLY; } #define IS_RDONLY(inode) sb_rdonly((inode)->i_sb) #define IS_SYNC(inode) (__IS_FLG(inode, SB_SYNCHRONOUS) || \ ((inode)->i_flags & S_SYNC)) @@ -2635,8 +2216,8 @@ static inline int icount_read(const struct inode *inode) */ static inline bool inode_is_dirtytime_only(struct inode *inode) { - return (inode->i_state & (I_DIRTY_TIME | I_NEW | - I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; + return (inode_state_read_once(inode) & + (I_DIRTY_TIME | I_NEW | I_FREEING | I_WILL_FREE)) == I_DIRTY_TIME; } extern void inc_nlink(struct inode *inode); @@ -2689,6 +2270,7 @@ struct file_system_type { #define FS_ALLOW_IDMAP 32 /* FS has been updated to handle vfs idmappings. */ #define FS_MGTIME 64 /* FS uses multigrain timestamps */ #define FS_LBS 128 /* FS supports LBS */ +#define FS_POWER_FREEZE 256 /* Always freeze on suspend/hibernate */ #define FS_RENAME_DOES_D_MOVE 32768 /* FS will handle d_move() during rename() internally. */ int (*init_fs_context)(struct fs_context *); const struct fs_parameter_spec *parameters; @@ -2773,10 +2355,6 @@ extern int unregister_filesystem(struct file_system_type *); extern int vfs_statfs(const struct path *, struct kstatfs *); extern int user_statfs(const char __user *, struct kstatfs *); extern int fd_statfs(int, struct kstatfs *); -int freeze_super(struct super_block *super, enum freeze_holder who, - const void *freeze_owner); -int thaw_super(struct super_block *super, enum freeze_holder who, - const void *freeze_owner); extern __printf(2, 3) int super_setup_bdi_name(struct super_block *sb, char *fmt, ...); extern int super_setup_bdi(struct super_block *sb); @@ -2819,10 +2397,9 @@ static inline void super_set_sysfs_name_generic(struct super_block *sb, const ch va_end(args); } -extern int current_umask(void); - extern void ihold(struct inode * inode); extern void iput(struct inode *); +void iput_not_last(struct inode *); int inode_update_timestamps(struct inode *inode, int flags); int generic_update_time(struct inode *, int); @@ -2963,12 +2540,6 @@ extern struct kmem_cache *names_cachep; #define __getname() kmem_cache_alloc(names_cachep, GFP_KERNEL) #define __putname(name) kmem_cache_free(names_cachep, (void *)(name)) -extern struct super_block *blockdev_superblock; -static inline bool sb_is_blkdev_sb(struct super_block *sb) -{ - return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; -} - void emergency_thaw_all(void); extern int sync_filesystem(struct super_block *); extern const struct file_operations def_blk_fops; @@ -3014,7 +2585,7 @@ extern int __must_check file_fdatawait_range(struct file *file, loff_t lstart, extern int __must_check file_check_and_advance_wb_err(struct file *file); extern int __must_check file_write_and_wait_range(struct file *file, loff_t start, loff_t end); -int filemap_fdatawrite_range_kick(struct address_space *mapping, loff_t start, +int filemap_flush_range(struct address_space *mapping, loff_t start, loff_t end); static inline int file_write_and_wait(struct file *file) @@ -3051,8 +2622,8 @@ static inline ssize_t generic_write_sync(struct kiocb *iocb, ssize_t count) } else if (iocb->ki_flags & IOCB_DONTCACHE) { struct address_space *mapping = iocb->ki_filp->f_mapping; - filemap_fdatawrite_range_kick(mapping, iocb->ki_pos - count, - iocb->ki_pos - 1); + filemap_flush_range(mapping, iocb->ki_pos - count, + iocb->ki_pos - 1); } return count; @@ -3071,7 +2642,7 @@ static inline int bmap(struct inode *inode, sector_t *block) #endif int notify_change(struct mnt_idmap *, struct dentry *, - struct iattr *, struct inode **); + struct iattr *, struct delegated_inode *); int inode_permission(struct mnt_idmap *, struct inode *, int); int generic_permission(struct mnt_idmap *, struct inode *, int); static inline int file_permission(struct file *file, int mask) @@ -3101,7 +2672,7 @@ static inline bool inode_wrong_type(const struct inode *inode, umode_t mode) * file_start_write - get write access to a superblock for regular file io * @file: the file we want to write to * - * This is a variant of sb_start_write() which is a noop on non-regualr file. + * This is a variant of sb_start_write() which is a noop on non-regular file. * Should be matched with a call to file_end_write(). */ static inline void file_start_write(struct file *file) @@ -3269,6 +2840,7 @@ extern struct file * open_exec(const char *); /* fs/dcache.c -- generic fs support functions */ extern bool is_subdir(struct dentry *, struct dentry *); extern bool path_is_under(const struct path *, const struct path *); +u64 vfsmount_to_propagation_flags(struct vfsmount *mnt); extern char *file_path(struct file *, char *, int); @@ -3326,7 +2898,7 @@ extern void d_mark_dontcache(struct inode *inode); extern struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), - void *data); + void *data, bool *isnew); extern struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data); extern struct inode *ilookup(struct super_block *sb, unsigned long ino); @@ -3378,11 +2950,9 @@ static inline bool is_zero_ino(ino_t ino) return (u32)ino == 0; } -/* - * inode->i_lock must be held - */ static inline void __iget(struct inode *inode) { + lockdep_assert_held(&inode->i_lock); atomic_inc(&inode->i_count); } @@ -3421,10 +2991,7 @@ static inline void remove_inode_hash(struct inode *inode) } extern void inode_sb_list_add(struct inode *inode); -extern void inode_add_lru(struct inode *inode); - -extern int sb_set_blocksize(struct super_block *, int); -extern int sb_min_blocksize(struct super_block *, int); +extern void inode_lru_list_add(struct inode *inode); int generic_file_mmap(struct file *, struct vm_area_struct *); int generic_file_mmap_prepare(struct vm_area_desc *desc); @@ -3606,9 +3173,11 @@ extern void drop_super_exclusive(struct super_block *sb); extern void iterate_supers(void (*f)(struct super_block *, void *), void *arg); extern void iterate_supers_type(struct file_system_type *, void (*)(struct super_block *, void *), void *); -void filesystems_freeze(void); +void filesystems_freeze(bool freeze_all); void filesystems_thaw(void); +void end_dirop(struct dentry *de); + extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); @@ -3745,38 +3314,6 @@ static inline bool generic_ci_validate_strict_name(struct inode *dir, } #endif -static inline struct unicode_map *sb_encoding(const struct super_block *sb) -{ -#if IS_ENABLED(CONFIG_UNICODE) - return sb->s_encoding; -#else - return NULL; -#endif -} - -static inline bool sb_has_encoding(const struct super_block *sb) -{ - return !!sb_encoding(sb); -} - -/* - * Compare if two super blocks have the same encoding and flags - */ -static inline bool sb_same_encoding(const struct super_block *sb1, - const struct super_block *sb2) -{ -#if IS_ENABLED(CONFIG_UNICODE) - if (sb1->s_encoding == sb2->s_encoding) - return true; - - return (sb1->s_encoding && sb2->s_encoding && - (sb1->s_encoding->version == sb2->s_encoding->version) && - (sb1->s_encoding_flags == sb2->s_encoding_flags)); -#else - return true; -#endif -} - int may_setattr(struct mnt_idmap *idmap, struct inode *inode, unsigned int ia_valid); int setattr_prepare(struct mnt_idmap *, struct dentry *, struct iattr *); diff --git a/include/linux/fs/super.h b/include/linux/fs/super.h new file mode 100644 index 000000000000..f21ffbb6dea5 --- /dev/null +++ b/include/linux/fs/super.h @@ -0,0 +1,238 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FS_SUPER_H +#define _LINUX_FS_SUPER_H + +#include <linux/fs/super_types.h> +#include <linux/unicode.h> + +/* + * These are internal functions, please use sb_start_{write,pagefault,intwrite} + * instead. + */ +static inline void __sb_end_write(struct super_block *sb, int level) +{ + percpu_up_read(sb->s_writers.rw_sem + level - 1); +} + +static inline void __sb_start_write(struct super_block *sb, int level) +{ + percpu_down_read_freezable(sb->s_writers.rw_sem + level - 1, true); +} + +static inline bool __sb_start_write_trylock(struct super_block *sb, int level) +{ + return percpu_down_read_trylock(sb->s_writers.rw_sem + level - 1); +} + +#define __sb_writers_acquired(sb, lev) \ + percpu_rwsem_acquire(&(sb)->s_writers.rw_sem[(lev) - 1], 1, _THIS_IP_) +#define __sb_writers_release(sb, lev) \ + percpu_rwsem_release(&(sb)->s_writers.rw_sem[(lev) - 1], _THIS_IP_) + +/** + * __sb_write_started - check if sb freeze level is held + * @sb: the super we write to + * @level: the freeze level + * + * * > 0 - sb freeze level is held + * * 0 - sb freeze level is not held + * * < 0 - !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN + */ +static inline int __sb_write_started(const struct super_block *sb, int level) +{ + return lockdep_is_held_type(sb->s_writers.rw_sem + level - 1, 1); +} + +/** + * sb_write_started - check if SB_FREEZE_WRITE is held + * @sb: the super we write to + * + * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. + */ +static inline bool sb_write_started(const struct super_block *sb) +{ + return __sb_write_started(sb, SB_FREEZE_WRITE); +} + +/** + * sb_write_not_started - check if SB_FREEZE_WRITE is not held + * @sb: the super we write to + * + * May be false positive with !CONFIG_LOCKDEP/LOCK_STATE_UNKNOWN. + */ +static inline bool sb_write_not_started(const struct super_block *sb) +{ + return __sb_write_started(sb, SB_FREEZE_WRITE) <= 0; +} + +/** + * sb_end_write - drop write access to a superblock + * @sb: the super we wrote to + * + * Decrement number of writers to the filesystem. Wake up possible waiters + * wanting to freeze the filesystem. + */ +static inline void sb_end_write(struct super_block *sb) +{ + __sb_end_write(sb, SB_FREEZE_WRITE); +} + +/** + * sb_end_pagefault - drop write access to a superblock from a page fault + * @sb: the super we wrote to + * + * Decrement number of processes handling write page fault to the filesystem. + * Wake up possible waiters wanting to freeze the filesystem. + */ +static inline void sb_end_pagefault(struct super_block *sb) +{ + __sb_end_write(sb, SB_FREEZE_PAGEFAULT); +} + +/** + * sb_end_intwrite - drop write access to a superblock for internal fs purposes + * @sb: the super we wrote to + * + * Decrement fs-internal number of writers to the filesystem. Wake up possible + * waiters wanting to freeze the filesystem. + */ +static inline void sb_end_intwrite(struct super_block *sb) +{ + __sb_end_write(sb, SB_FREEZE_FS); +} + +/** + * sb_start_write - get write access to a superblock + * @sb: the super we write to + * + * When a process wants to write data or metadata to a file system (i.e. dirty + * a page or an inode), it should embed the operation in a sb_start_write() - + * sb_end_write() pair to get exclusion against file system freezing. This + * function increments number of writers preventing freezing. If the file + * system is already frozen, the function waits until the file system is + * thawed. + * + * Since freeze protection behaves as a lock, users have to preserve + * ordering of freeze protection and other filesystem locks. Generally, + * freeze protection should be the outermost lock. In particular, we have: + * + * sb_start_write + * -> i_rwsem (write path, truncate, directory ops, ...) + * -> s_umount (freeze_super, thaw_super) + */ +static inline void sb_start_write(struct super_block *sb) +{ + __sb_start_write(sb, SB_FREEZE_WRITE); +} + +DEFINE_GUARD(super_write, + struct super_block *, + sb_start_write(_T), + sb_end_write(_T)) + +static inline bool sb_start_write_trylock(struct super_block *sb) +{ + return __sb_start_write_trylock(sb, SB_FREEZE_WRITE); +} + +/** + * sb_start_pagefault - get write access to a superblock from a page fault + * @sb: the super we write to + * + * When a process starts handling write page fault, it should embed the + * operation into sb_start_pagefault() - sb_end_pagefault() pair to get + * exclusion against file system freezing. This is needed since the page fault + * is going to dirty a page. This function increments number of running page + * faults preventing freezing. If the file system is already frozen, the + * function waits until the file system is thawed. + * + * Since page fault freeze protection behaves as a lock, users have to preserve + * ordering of freeze protection and other filesystem locks. It is advised to + * put sb_start_pagefault() close to mmap_lock in lock ordering. Page fault + * handling code implies lock dependency: + * + * mmap_lock + * -> sb_start_pagefault + */ +static inline void sb_start_pagefault(struct super_block *sb) +{ + __sb_start_write(sb, SB_FREEZE_PAGEFAULT); +} + +/** + * sb_start_intwrite - get write access to a superblock for internal fs purposes + * @sb: the super we write to + * + * This is the third level of protection against filesystem freezing. It is + * free for use by a filesystem. The only requirement is that it must rank + * below sb_start_pagefault. + * + * For example filesystem can call sb_start_intwrite() when starting a + * transaction which somewhat eases handling of freezing for internal sources + * of filesystem changes (internal fs threads, discarding preallocation on file + * close, etc.). + */ +static inline void sb_start_intwrite(struct super_block *sb) +{ + __sb_start_write(sb, SB_FREEZE_FS); +} + +static inline bool sb_start_intwrite_trylock(struct super_block *sb) +{ + return __sb_start_write_trylock(sb, SB_FREEZE_FS); +} + +static inline bool sb_rdonly(const struct super_block *sb) +{ + return sb->s_flags & SB_RDONLY; +} + +static inline bool sb_is_blkdev_sb(struct super_block *sb) +{ + return IS_ENABLED(CONFIG_BLOCK) && sb == blockdev_superblock; +} + +#if IS_ENABLED(CONFIG_UNICODE) +static inline struct unicode_map *sb_encoding(const struct super_block *sb) +{ + return sb->s_encoding; +} + +/* Compare if two super blocks have the same encoding and flags */ +static inline bool sb_same_encoding(const struct super_block *sb1, + const struct super_block *sb2) +{ + if (sb1->s_encoding == sb2->s_encoding) + return true; + + return (sb1->s_encoding && sb2->s_encoding && + (sb1->s_encoding->version == sb2->s_encoding->version) && + (sb1->s_encoding_flags == sb2->s_encoding_flags)); +} +#else +static inline struct unicode_map *sb_encoding(const struct super_block *sb) +{ + return NULL; +} + +static inline bool sb_same_encoding(const struct super_block *sb1, + const struct super_block *sb2) +{ + return true; +} +#endif + +static inline bool sb_has_encoding(const struct super_block *sb) +{ + return !!sb_encoding(sb); +} + +int sb_set_blocksize(struct super_block *sb, int size); +int __must_check sb_min_blocksize(struct super_block *sb, int size); + +int freeze_super(struct super_block *super, enum freeze_holder who, + const void *freeze_owner); +int thaw_super(struct super_block *super, enum freeze_holder who, + const void *freeze_owner); + +#endif /* _LINUX_FS_SUPER_H */ diff --git a/include/linux/fs/super_types.h b/include/linux/fs/super_types.h new file mode 100644 index 000000000000..6bd3009e09b3 --- /dev/null +++ b/include/linux/fs/super_types.h @@ -0,0 +1,336 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_FS_SUPER_TYPES_H +#define _LINUX_FS_SUPER_TYPES_H + +#include <linux/fs_dirent.h> +#include <linux/errseq.h> +#include <linux/list_lru.h> +#include <linux/list.h> +#include <linux/list_bl.h> +#include <linux/llist.h> +#include <linux/uidgid.h> +#include <linux/uuid.h> +#include <linux/percpu-rwsem.h> +#include <linux/workqueue_types.h> +#include <linux/quota.h> + +struct backing_dev_info; +struct block_device; +struct dentry; +struct dentry_operations; +struct dquot_operations; +struct export_operations; +struct file; +struct file_system_type; +struct fscrypt_operations; +struct fsnotify_sb_info; +struct fsverity_operations; +struct kstatfs; +struct mount; +struct mtd_info; +struct quotactl_ops; +struct shrinker; +struct unicode_map; +struct user_namespace; +struct workqueue_struct; +struct writeback_control; +struct xattr_handler; + +extern struct super_block *blockdev_superblock; + +/* Possible states of 'frozen' field */ +enum { + SB_UNFROZEN = 0, /* FS is unfrozen */ + SB_FREEZE_WRITE = 1, /* Writes, dir ops, ioctls frozen */ + SB_FREEZE_PAGEFAULT = 2, /* Page faults stopped as well */ + SB_FREEZE_FS = 3, /* For internal FS use (e.g. to stop internal threads if needed) */ + SB_FREEZE_COMPLETE = 4, /* ->freeze_fs finished successfully */ +}; + +#define SB_FREEZE_LEVELS (SB_FREEZE_COMPLETE - 1) + +struct sb_writers { + unsigned short frozen; /* Is sb frozen? */ + int freeze_kcount; /* How many kernel freeze requests? */ + int freeze_ucount; /* How many userspace freeze requests? */ + const void *freeze_owner; /* Owner of the freeze */ + struct percpu_rw_semaphore rw_sem[SB_FREEZE_LEVELS]; +}; + +/** + * enum freeze_holder - holder of the freeze + * @FREEZE_HOLDER_KERNEL: kernel wants to freeze or thaw filesystem + * @FREEZE_HOLDER_USERSPACE: userspace wants to freeze or thaw filesystem + * @FREEZE_MAY_NEST: whether nesting freeze and thaw requests is allowed + * @FREEZE_EXCL: a freeze that can only be undone by the owner + * + * Indicate who the owner of the freeze or thaw request is and whether + * the freeze needs to be exclusive or can nest. + * Without @FREEZE_MAY_NEST, multiple freeze and thaw requests from the + * same holder aren't allowed. It is however allowed to hold a single + * @FREEZE_HOLDER_USERSPACE and a single @FREEZE_HOLDER_KERNEL freeze at + * the same time. This is relied upon by some filesystems during online + * repair or similar. + */ +enum freeze_holder { + FREEZE_HOLDER_KERNEL = (1U << 0), + FREEZE_HOLDER_USERSPACE = (1U << 1), + FREEZE_MAY_NEST = (1U << 2), + FREEZE_EXCL = (1U << 3), +}; + +struct super_operations { + struct inode *(*alloc_inode)(struct super_block *sb); + void (*destroy_inode)(struct inode *inode); + void (*free_inode)(struct inode *inode); + void (*dirty_inode)(struct inode *inode, int flags); + int (*write_inode)(struct inode *inode, struct writeback_control *wbc); + int (*drop_inode)(struct inode *inode); + void (*evict_inode)(struct inode *inode); + void (*put_super)(struct super_block *sb); + int (*sync_fs)(struct super_block *sb, int wait); + int (*freeze_super)(struct super_block *sb, enum freeze_holder who, + const void *owner); + int (*freeze_fs)(struct super_block *sb); + int (*thaw_super)(struct super_block *sb, enum freeze_holder who, + const void *owner); + int (*unfreeze_fs)(struct super_block *sb); + int (*statfs)(struct dentry *dentry, struct kstatfs *kstatfs); + int (*remount_fs) (struct super_block *, int *, char *); + void (*umount_begin)(struct super_block *sb); + + int (*show_options)(struct seq_file *seq, struct dentry *dentry); + int (*show_devname)(struct seq_file *seq, struct dentry *dentry); + int (*show_path)(struct seq_file *seq, struct dentry *dentry); + int (*show_stats)(struct seq_file *seq, struct dentry *dentry); +#ifdef CONFIG_QUOTA + ssize_t (*quota_read)(struct super_block *sb, int type, char *data, + size_t len, loff_t off); + ssize_t (*quota_write)(struct super_block *sb, int type, + const char *data, size_t len, loff_t off); + struct dquot __rcu **(*get_dquots)(struct inode *inode); +#endif + long (*nr_cached_objects)(struct super_block *sb, + struct shrink_control *sc); + long (*free_cached_objects)(struct super_block *sb, + struct shrink_control *sc); + /* + * If a filesystem can support graceful removal of a device and + * continue read-write operations, implement this callback. + * + * Return 0 if the filesystem can continue read-write. + * Non-zero return value or no such callback means the fs will be shutdown + * as usual. + */ + int (*remove_bdev)(struct super_block *sb, struct block_device *bdev); + void (*shutdown)(struct super_block *sb); +}; + +struct super_block { + struct list_head s_list; /* Keep this first */ + dev_t s_dev; /* search index; _not_ kdev_t */ + unsigned char s_blocksize_bits; + unsigned long s_blocksize; + loff_t s_maxbytes; /* Max file size */ + struct file_system_type *s_type; + const struct super_operations *s_op; + const struct dquot_operations *dq_op; + const struct quotactl_ops *s_qcop; + const struct export_operations *s_export_op; + unsigned long s_flags; + unsigned long s_iflags; /* internal SB_I_* flags */ + unsigned long s_magic; + struct dentry *s_root; + struct rw_semaphore s_umount; + int s_count; + atomic_t s_active; +#ifdef CONFIG_SECURITY + void *s_security; +#endif + const struct xattr_handler *const *s_xattr; +#ifdef CONFIG_FS_ENCRYPTION + const struct fscrypt_operations *s_cop; + struct fscrypt_keyring *s_master_keys; /* master crypto keys in use */ +#endif +#ifdef CONFIG_FS_VERITY + const struct fsverity_operations *s_vop; +#endif +#if IS_ENABLED(CONFIG_UNICODE) + struct unicode_map *s_encoding; + __u16 s_encoding_flags; +#endif + struct hlist_bl_head s_roots; /* alternate root dentries for NFS */ + struct mount *s_mounts; /* list of mounts; _not_ for fs use */ + struct block_device *s_bdev; /* can go away once we use an accessor for @s_bdev_file */ + struct file *s_bdev_file; + struct backing_dev_info *s_bdi; + struct mtd_info *s_mtd; + struct hlist_node s_instances; + unsigned int s_quota_types; /* Bitmask of supported quota types */ + struct quota_info s_dquot; /* Diskquota specific options */ + + struct sb_writers s_writers; + + /* + * Keep s_fs_info, s_time_gran, s_fsnotify_mask, and + * s_fsnotify_info together for cache efficiency. They are frequently + * accessed and rarely modified. + */ + void *s_fs_info; /* Filesystem private info */ + + /* Granularity of c/m/atime in ns (cannot be worse than a second) */ + u32 s_time_gran; + /* Time limits for c/m/atime in seconds */ + time64_t s_time_min; + time64_t s_time_max; +#ifdef CONFIG_FSNOTIFY + u32 s_fsnotify_mask; + struct fsnotify_sb_info *s_fsnotify_info; +#endif + + /* + * q: why are s_id and s_sysfs_name not the same? both are human + * readable strings that identify the filesystem + * a: s_id is allowed to change at runtime; it's used in log messages, + * and we want to when a device starts out as single device (s_id is dev + * name) but then a device is hot added and we have to switch to + * identifying it by UUID + * but s_sysfs_name is a handle for programmatic access, and can't + * change at runtime + */ + char s_id[32]; /* Informational name */ + uuid_t s_uuid; /* UUID */ + u8 s_uuid_len; /* Default 16, possibly smaller for weird filesystems */ + + /* if set, fs shows up under sysfs at /sys/fs/$FSTYP/s_sysfs_name */ + char s_sysfs_name[UUID_STRING_LEN + 1]; + + unsigned int s_max_links; + unsigned int s_d_flags; /* default d_flags for dentries */ + + /* + * The next field is for VFS *only*. No filesystems have any business + * even looking at it. You had been warned. + */ + struct mutex s_vfs_rename_mutex; /* Kludge */ + + /* + * Filesystem subtype. If non-empty the filesystem type field + * in /proc/mounts will be "type.subtype" + */ + const char *s_subtype; + + const struct dentry_operations *__s_d_op; /* default d_op for dentries */ + + struct shrinker *s_shrink; /* per-sb shrinker handle */ + + /* Number of inodes with nlink == 0 but still referenced */ + atomic_long_t s_remove_count; + + /* Read-only state of the superblock is being changed */ + int s_readonly_remount; + + /* per-sb errseq_t for reporting writeback errors via syncfs */ + errseq_t s_wb_err; + + /* AIO completions deferred from interrupt context */ + struct workqueue_struct *s_dio_done_wq; + struct hlist_head s_pins; + + /* + * Owning user namespace and default context in which to + * interpret filesystem uids, gids, quotas, device nodes, + * xattrs and security labels. + */ + struct user_namespace *s_user_ns; + + /* + * The list_lru structure is essentially just a pointer to a table + * of per-node lru lists, each of which has its own spinlock. + * There is no need to put them into separate cachelines. + */ + struct list_lru s_dentry_lru; + struct list_lru s_inode_lru; + struct rcu_head rcu; + struct work_struct destroy_work; + + struct mutex s_sync_lock; /* sync serialisation lock */ + + /* + * Indicates how deep in a filesystem stack this SB is + */ + int s_stack_depth; + + /* s_inode_list_lock protects s_inodes */ + spinlock_t s_inode_list_lock ____cacheline_aligned_in_smp; + struct list_head s_inodes; /* all inodes */ + + spinlock_t s_inode_wblist_lock; + struct list_head s_inodes_wb; /* writeback inodes */ + long s_min_writeback_pages; +} __randomize_layout; + +/* + * sb->s_flags. Note that these mirror the equivalent MS_* flags where + * represented in both. + */ +#define SB_RDONLY BIT(0) /* Mount read-only */ +#define SB_NOSUID BIT(1) /* Ignore suid and sgid bits */ +#define SB_NODEV BIT(2) /* Disallow access to device special files */ +#define SB_NOEXEC BIT(3) /* Disallow program execution */ +#define SB_SYNCHRONOUS BIT(4) /* Writes are synced at once */ +#define SB_MANDLOCK BIT(6) /* Allow mandatory locks on an FS */ +#define SB_DIRSYNC BIT(7) /* Directory modifications are synchronous */ +#define SB_NOATIME BIT(10) /* Do not update access times. */ +#define SB_NODIRATIME BIT(11) /* Do not update directory access times */ +#define SB_SILENT BIT(15) +#define SB_POSIXACL BIT(16) /* Supports POSIX ACLs */ +#define SB_INLINECRYPT BIT(17) /* Use blk-crypto for encrypted files */ +#define SB_KERNMOUNT BIT(22) /* this is a kern_mount call */ +#define SB_I_VERSION BIT(23) /* Update inode I_version field */ +#define SB_LAZYTIME BIT(25) /* Update the on-disk [acm]times lazily */ + +/* These sb flags are internal to the kernel */ +#define SB_DEAD BIT(21) +#define SB_DYING BIT(24) +#define SB_FORCE BIT(27) +#define SB_NOSEC BIT(28) +#define SB_BORN BIT(29) +#define SB_ACTIVE BIT(30) +#define SB_NOUSER BIT(31) + +/* These flags relate to encoding and casefolding */ +#define SB_ENC_STRICT_MODE_FL (1 << 0) +#define SB_ENC_NO_COMPAT_FALLBACK_FL (1 << 1) + +#define sb_has_strict_encoding(sb) \ + (sb->s_encoding_flags & SB_ENC_STRICT_MODE_FL) + +#if IS_ENABLED(CONFIG_UNICODE) +#define sb_no_casefold_compat_fallback(sb) \ + (sb->s_encoding_flags & SB_ENC_NO_COMPAT_FALLBACK_FL) +#else +#define sb_no_casefold_compat_fallback(sb) (1) +#endif + +/* sb->s_iflags */ +#define SB_I_CGROUPWB 0x00000001 /* cgroup-aware writeback enabled */ +#define SB_I_NOEXEC 0x00000002 /* Ignore executables on this fs */ +#define SB_I_NODEV 0x00000004 /* Ignore devices on this fs */ +#define SB_I_STABLE_WRITES 0x00000008 /* don't modify blks until WB is done */ + +/* sb->s_iflags to limit user namespace mounts */ +#define SB_I_USERNS_VISIBLE 0x00000010 /* fstype already mounted */ +#define SB_I_IMA_UNVERIFIABLE_SIGNATURE 0x00000020 +#define SB_I_UNTRUSTED_MOUNTER 0x00000040 +#define SB_I_EVM_HMAC_UNSUPPORTED 0x00000080 + +#define SB_I_SKIP_SYNC 0x00000100 /* Skip superblock at global sync */ +#define SB_I_PERSB_BDI 0x00000200 /* has a per-sb bdi */ +#define SB_I_TS_EXPIRY_WARNED 0x00000400 /* warned about timestamp range expiry */ +#define SB_I_RETIRED 0x00000800 /* superblock shouldn't be reused */ +#define SB_I_NOUMASK 0x00001000 /* VFS does not apply umask */ +#define SB_I_NOIDMAP 0x00002000 /* No idmapped mounts on this superblock */ +#define SB_I_ALLOW_HSM 0x00004000 /* Allow HSM events on this superblock */ + +#endif /* _LINUX_FS_SUPER_TYPES_H */ diff --git a/include/linux/fs_types.h b/include/linux/fs_dirent.h index 54816791196f..92f75c5bac19 100644 --- a/include/linux/fs_types.h +++ b/include/linux/fs_dirent.h @@ -1,6 +1,9 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _LINUX_FS_TYPES_H -#define _LINUX_FS_TYPES_H +#ifndef _LINUX_FS_DIRENT_H +#define _LINUX_FS_DIRENT_H + +#include <linux/stat.h> +#include <linux/types.h> /* * This is a header for the common implementation of dirent @@ -66,10 +69,10 @@ /* * declarations for helper functions, accompanying implementation - * is in fs/fs_types.c + * is in fs/fs_dirent.c */ extern unsigned char fs_ftype_to_dtype(unsigned int filetype); extern unsigned char fs_umode_to_ftype(umode_t mode); extern unsigned char fs_umode_to_dtype(umode_t mode); -#endif +#endif /* _LINUX_FS_DIRENT_H */ diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h index baf200ab5c77..0070764b790a 100644 --- a/include/linux/fs_struct.h +++ b/include/linux/fs_struct.h @@ -2,6 +2,7 @@ #ifndef _LINUX_FS_STRUCT_H #define _LINUX_FS_STRUCT_H +#include <linux/sched.h> #include <linux/path.h> #include <linux/spinlock.h> #include <linux/seqlock.h> @@ -41,4 +42,9 @@ static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) extern bool current_chrooted(void); +static inline int current_umask(void) +{ + return current->fs->umask; +} + #endif /* _LINUX_FS_STRUCT_H */ diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h index 7ded7df6e9b5..07f8c309e432 100644 --- a/include/linux/ftrace.h +++ b/include/linux/ftrace.h @@ -193,6 +193,10 @@ static __always_inline struct pt_regs *ftrace_get_regs(struct ftrace_regs *fregs #if !defined(CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS) || \ defined(CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS) +#ifndef arch_ftrace_partial_regs +#define arch_ftrace_partial_regs(regs) do {} while (0) +#endif + static __always_inline struct pt_regs * ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs) { @@ -202,7 +206,11 @@ ftrace_partial_regs(struct ftrace_regs *fregs, struct pt_regs *regs) * Since arch_ftrace_get_regs() will check some members and may return * NULL, we can not use it. */ - return &arch_ftrace_regs(fregs)->regs; + regs = &arch_ftrace_regs(fregs)->regs; + + /* Allow arch specific updates to regs. */ + arch_ftrace_partial_regs(regs); + return regs; } #endif /* !CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS || CONFIG_HAVE_FTRACE_REGS_HAVING_PT_REGS */ diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 0ceb4e09306c..623bee335383 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -7,6 +7,7 @@ #include <linux/mmzone.h> #include <linux/topology.h> #include <linux/alloc_tag.h> +#include <linux/cleanup.h> #include <linux/sched.h> struct vm_area_struct; @@ -463,4 +464,6 @@ static inline struct folio *folio_alloc_gigantic_noprof(int order, gfp_t gfp, /* This should be paired with folio_put() rather than free_contig_range(). */ #define folio_alloc_gigantic(...) alloc_hooks(folio_alloc_gigantic_noprof(__VA_ARGS__)) +DEFINE_FREE(free_page, void *, free_page((unsigned long)_T)) + #endif /* __LINUX_GFP_H */ diff --git a/include/linux/gpio/regmap.h b/include/linux/gpio/regmap.h index 622a2939ebe0..87983a5f3681 100644 --- a/include/linux/gpio/regmap.h +++ b/include/linux/gpio/regmap.h @@ -38,6 +38,10 @@ struct regmap; * offset to a register/bitmask pair. If not * given the default gpio_regmap_simple_xlate() * is used. + * @fixed_direction_output: + * (Optional) Bitmap representing the fixed direction of + * the GPIO lines. Useful when there are GPIO lines with a + * fixed direction mixed together in the same register. * @drvdata: (Optional) Pointer to driver specific data which is * not used by gpio-remap but is provided "as is" to the * driver callback(s). @@ -85,6 +89,7 @@ struct gpio_regmap_config { int reg_stride; int ngpio_per_reg; struct irq_domain *irq_domain; + unsigned long *fixed_direction_output; #ifdef CONFIG_REGMAP_IRQ struct regmap_irq_chip *regmap_irq_chip; diff --git a/include/linux/hid.h b/include/linux/hid.h index e1b673ad7457..a4ddb94e3ee5 100644 --- a/include/linux/hid.h +++ b/include/linux/hid.h @@ -1292,4 +1292,15 @@ void hid_quirks_exit(__u16 bus); #define hid_dbg_once(hid, fmt, ...) \ dev_dbg_once(&(hid)->dev, fmt, ##__VA_ARGS__) +#define hid_err_ratelimited(hid, fmt, ...) \ + dev_err_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__) +#define hid_notice_ratelimited(hid, fmt, ...) \ + dev_notice_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__) +#define hid_warn_ratelimited(hid, fmt, ...) \ + dev_warn_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__) +#define hid_info_ratelimited(hid, fmt, ...) \ + dev_info_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__) +#define hid_dbg_ratelimited(hid, fmt, ...) \ + dev_dbg_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__) + #endif diff --git a/include/linux/highmem.h b/include/linux/highmem.h index 105cc4c00cc3..abc20f9810fd 100644 --- a/include/linux/highmem.h +++ b/include/linux/highmem.h @@ -249,10 +249,12 @@ static inline void clear_highpage_kasan_tagged(struct page *page) kunmap_local(kaddr); } -#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGE +#ifndef __HAVE_ARCH_TAG_CLEAR_HIGHPAGES -static inline void tag_clear_highpage(struct page *page) +/* Return false to let people know we did not initialize the pages */ +static inline bool tag_clear_highpages(struct page *page, int numpages) { + return false; } #endif diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index f327d62fc985..71ac78b9f834 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -376,45 +376,30 @@ bool non_uniform_split_supported(struct folio *folio, unsigned int new_order, int folio_split(struct folio *folio, unsigned int new_order, struct page *page, struct list_head *list); /* - * try_folio_split - try to split a @folio at @page using non uniform split. + * try_folio_split_to_order - try to split a @folio at @page to @new_order using + * non uniform split. * @folio: folio to be split - * @page: split to order-0 at the given page - * @list: store the after-split folios + * @page: split to @new_order at the given page + * @new_order: the target split order * - * Try to split a @folio at @page using non uniform split to order-0, if - * non uniform split is not supported, fall back to uniform split. + * Try to split a @folio at @page using non uniform split to @new_order, if + * non uniform split is not supported, fall back to uniform split. After-split + * folios are put back to LRU list. Use min_order_for_split() to get the lower + * bound of @new_order. * * Return: 0: split is successful, otherwise split failed. */ -static inline int try_folio_split(struct folio *folio, struct page *page, - struct list_head *list) +static inline int try_folio_split_to_order(struct folio *folio, + struct page *page, unsigned int new_order) { - int ret = min_order_for_split(folio); - - if (ret < 0) - return ret; - - if (!non_uniform_split_supported(folio, 0, false)) - return split_huge_page_to_list_to_order(&folio->page, list, - ret); - return folio_split(folio, ret, page, list); + if (!non_uniform_split_supported(folio, new_order, /* warns= */ false)) + return split_huge_page_to_list_to_order(&folio->page, NULL, + new_order); + return folio_split(folio, new_order, page, NULL); } static inline int split_huge_page(struct page *page) { - struct folio *folio = page_folio(page); - int ret = min_order_for_split(folio); - - if (ret < 0) - return ret; - - /* - * split_huge_page() locks the page before splitting and - * expects the same page that has been split to be locked when - * returned. split_folio(page_folio(page)) cannot be used here - * because it converts the page to folio and passes the head - * page to be split. - */ - return split_huge_page_to_list_to_order(page, NULL, ret); + return split_huge_page_to_list_to_order(page, NULL, 0); } void deferred_split_folio(struct folio *folio, bool partially_mapped); @@ -597,14 +582,20 @@ static inline int split_huge_page(struct page *page) return -EINVAL; } +static inline int min_order_for_split(struct folio *folio) +{ + VM_WARN_ON_ONCE_FOLIO(1, folio); + return -EINVAL; +} + static inline int split_folio_to_list(struct folio *folio, struct list_head *list) { VM_WARN_ON_ONCE_FOLIO(1, folio); return -EINVAL; } -static inline int try_folio_split(struct folio *folio, struct page *page, - struct list_head *list) +static inline int try_folio_split_to_order(struct folio *folio, + struct page *page, unsigned int new_order) { VM_WARN_ON_ONCE_FOLIO(1, folio); return -EINVAL; diff --git a/include/linux/hung_task.h b/include/linux/hung_task.h index 34e615c76ca5..c4403eeb7144 100644 --- a/include/linux/hung_task.h +++ b/include/linux/hung_task.h @@ -20,6 +20,10 @@ * always zero. So we can use these bits to encode the specific blocking * type. * + * Note that on architectures where this is not guaranteed, or for any + * unaligned lock, this tracking mechanism is silently skipped for that + * lock. + * * Type encoding: * 00 - Blocked on mutex (BLOCKER_TYPE_MUTEX) * 01 - Blocked on semaphore (BLOCKER_TYPE_SEM) @@ -45,7 +49,7 @@ static inline void hung_task_set_blocker(void *lock, unsigned long type) * If the lock pointer matches the BLOCKER_TYPE_MASK, return * without writing anything. */ - if (WARN_ON_ONCE(lock_ptr & BLOCKER_TYPE_MASK)) + if (lock_ptr & BLOCKER_TYPE_MASK) return; WRITE_ONCE(current->blocker, lock_ptr | type); @@ -53,8 +57,6 @@ static inline void hung_task_set_blocker(void *lock, unsigned long type) static inline void hung_task_clear_blocker(void) { - WARN_ON_ONCE(!READ_ONCE(current->blocker)); - WRITE_ONCE(current->blocker, 0UL); } diff --git a/include/linux/iio/buffer-dma.h b/include/linux/iio/buffer-dma.h index 5eb66a399002..4f33e6a39797 100644 --- a/include/linux/iio/buffer-dma.h +++ b/include/linux/iio/buffer-dma.h @@ -174,5 +174,6 @@ int iio_dma_buffer_enqueue_dmabuf(struct iio_buffer *buffer, size_t size, bool cyclic); void iio_dma_buffer_lock_queue(struct iio_buffer *buffer); void iio_dma_buffer_unlock_queue(struct iio_buffer *buffer); +struct device *iio_dma_buffer_get_dma_dev(struct iio_buffer *buffer); #endif diff --git a/include/linux/iio/buffer_impl.h b/include/linux/iio/buffer_impl.h index e72552e026f3..8d770ced66b2 100644 --- a/include/linux/iio/buffer_impl.h +++ b/include/linux/iio/buffer_impl.h @@ -50,6 +50,7 @@ struct sg_table; * @enqueue_dmabuf: called from userspace via ioctl to queue this DMABUF * object to this buffer. Requires a valid DMABUF fd, that * was previouly attached to this buffer. + * @get_dma_dev: called to get the DMA channel associated with this buffer. * @lock_queue: called when the core needs to lock the buffer queue; * it is used when enqueueing DMABUF objects. * @unlock_queue: used to unlock a previously locked buffer queue @@ -90,6 +91,7 @@ struct iio_buffer_access_funcs { struct iio_dma_buffer_block *block, struct dma_fence *fence, struct sg_table *sgt, size_t size, bool cyclic); + struct device * (*get_dma_dev)(struct iio_buffer *buffer); void (*lock_queue)(struct iio_buffer *buffer); void (*unlock_queue)(struct iio_buffer *buffer); diff --git a/include/linux/init.h b/include/linux/init.h index 17c1bc712e23..40331923b9f4 100644 --- a/include/linux/init.h +++ b/include/linux/init.h @@ -200,12 +200,13 @@ extern struct module __this_module; /* Format: <modname>__<counter>_<line>_<fn> */ #define __initcall_id(fn) \ + __PASTE(kmod_, \ __PASTE(__KBUILD_MODNAME, \ __PASTE(__, \ __PASTE(__COUNTER__, \ __PASTE(_, \ __PASTE(__LINE__, \ - __PASTE(_, fn)))))) + __PASTE(_, fn))))))) /* Format: __<prefix>__<iid><id> */ #define __initcall_name(prefix, __iid, id) \ diff --git a/include/linux/init_task.h b/include/linux/init_task.h index bccb3f1f6262..a6cb241ea00c 100644 --- a/include/linux/init_task.h +++ b/include/linux/init_task.h @@ -25,7 +25,6 @@ extern struct files_struct init_files; extern struct fs_struct init_fs; extern struct nsproxy init_nsproxy; -extern struct cred init_cred; #ifndef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE #define INIT_PREV_CPUTIME(x) .prev_cputime = { \ diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h index 51b6484c0493..266f2b39213a 100644 --- a/include/linux/interrupt.h +++ b/include/linux/interrupt.h @@ -109,6 +109,7 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); * @name: name of the device * @dev_id: cookie to identify the device * @percpu_dev_id: cookie to identify the device + * @affinity: CPUs this irqaction is allowed to run on * @next: pointer to the next irqaction for shared interrupts * @irq: interrupt number * @flags: flags (see IRQF_* above) @@ -121,8 +122,11 @@ typedef irqreturn_t (*irq_handler_t)(int, void *); */ struct irqaction { irq_handler_t handler; - void *dev_id; - void __percpu *percpu_dev_id; + union { + void *dev_id; + void __percpu *percpu_dev_id; + }; + const struct cpumask *affinity; struct irqaction *next; irq_handler_t thread_fn; struct task_struct *thread; @@ -179,7 +183,7 @@ request_any_context_irq(unsigned int irq, irq_handler_t handler, extern int __must_check __request_percpu_irq(unsigned int irq, irq_handler_t handler, unsigned long flags, const char *devname, - void __percpu *percpu_dev_id); + const cpumask_t *affinity, void __percpu *percpu_dev_id); extern int __must_check request_nmi(unsigned int irq, irq_handler_t handler, unsigned long flags, @@ -190,12 +194,21 @@ request_percpu_irq(unsigned int irq, irq_handler_t handler, const char *devname, void __percpu *percpu_dev_id) { return __request_percpu_irq(irq, handler, 0, - devname, percpu_dev_id); + devname, NULL, percpu_dev_id); +} + +static inline int __must_check +request_percpu_irq_affinity(unsigned int irq, irq_handler_t handler, + const char *devname, const cpumask_t *affinity, + void __percpu *percpu_dev_id) +{ + return __request_percpu_irq(irq, handler, 0, + devname, affinity, percpu_dev_id); } extern int __must_check -request_percpu_nmi(unsigned int irq, irq_handler_t handler, - const char *devname, void __percpu *dev); +request_percpu_nmi(unsigned int irq, irq_handler_t handler, const char *name, + const struct cpumask *affinity, void __percpu *dev_id); extern const void *free_irq(unsigned int, void *); extern void free_percpu_irq(unsigned int, void __percpu *); diff --git a/include/linux/interval_tree.h b/include/linux/interval_tree.h index 2b8026a39906..9d5791e9f737 100644 --- a/include/linux/interval_tree.h +++ b/include/linux/interval_tree.h @@ -20,6 +20,10 @@ interval_tree_remove(struct interval_tree_node *node, struct rb_root_cached *root); extern struct interval_tree_node * +interval_tree_subtree_search(struct interval_tree_node *node, + unsigned long start, unsigned long last); + +extern struct interval_tree_node * interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); diff --git a/include/linux/interval_tree_generic.h b/include/linux/interval_tree_generic.h index 1b400f26f63d..c5a2fed49eb0 100644 --- a/include/linux/interval_tree_generic.h +++ b/include/linux/interval_tree_generic.h @@ -77,7 +77,7 @@ ITSTATIC void ITPREFIX ## _remove(ITSTRUCT *node, \ * Cond2: start <= ITLAST(node) \ */ \ \ -static ITSTRUCT * \ +ITSTATIC ITSTRUCT * \ ITPREFIX ## _subtree_search(ITSTRUCT *node, ITTYPE start, ITTYPE last) \ { \ while (true) { \ diff --git a/include/linux/iomap.h b/include/linux/iomap.h index 73dceabc21c8..520e967cb501 100644 --- a/include/linux/iomap.h +++ b/include/linux/iomap.h @@ -9,6 +9,7 @@ #include <linux/types.h> #include <linux/mm_types.h> #include <linux/blkdev.h> +#include <linux/pagevec.h> struct address_space; struct fiemap_extent_info; @@ -16,6 +17,7 @@ struct inode; struct iomap_iter; struct iomap_dio; struct iomap_writepage_ctx; +struct iomap_read_folio_ctx; struct iov_iter; struct kiocb; struct page; @@ -241,11 +243,12 @@ struct iomap_iter { unsigned flags; struct iomap iomap; struct iomap srcmap; + struct folio_batch *fbatch; void *private; }; int iomap_iter(struct iomap_iter *iter, const struct iomap_ops *ops); -int iomap_iter_advance(struct iomap_iter *iter, u64 *count); +int iomap_iter_advance(struct iomap_iter *iter, u64 count); /** * iomap_length_trim - trimmed length of the current iomap iteration @@ -282,9 +285,7 @@ static inline u64 iomap_length(const struct iomap_iter *iter) */ static inline int iomap_iter_advance_full(struct iomap_iter *iter) { - u64 length = iomap_length(iter); - - return iomap_iter_advance(iter, &length); + return iomap_iter_advance(iter, iomap_length(iter)); } /** @@ -339,8 +340,10 @@ static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter) ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops, void *private); -int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops); -void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops); +void iomap_read_folio(const struct iomap_ops *ops, + struct iomap_read_folio_ctx *ctx); +void iomap_readahead(const struct iomap_ops *ops, + struct iomap_read_folio_ctx *ctx); bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count); struct folio *iomap_get_folio(struct iomap_iter *iter, loff_t pos, size_t len); bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags); @@ -349,6 +352,8 @@ bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio); int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops); +loff_t iomap_fill_dirty_folios(struct iomap_iter *iter, loff_t offset, + loff_t length); int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero, const struct iomap_ops *ops, const struct iomap_write_ops *write_ops, void *private); @@ -430,6 +435,10 @@ struct iomap_writeback_ops { * An existing mapping from a previous call to this method can be reused * by the file system if it is still valid. * + * If this succeeds, iomap_finish_folio_write() must be called once + * writeback completes for the range, regardless of whether the + * writeback succeeded or failed. + * * Returns the number of bytes processed or a negative errno. */ ssize_t (*writeback_range)(struct iomap_writepage_ctx *wpc, @@ -467,14 +476,41 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio, loff_t pos, loff_t end_pos, unsigned int dirty_len); int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error); -void iomap_start_folio_write(struct inode *inode, struct folio *folio, - size_t len); +void iomap_finish_folio_read(struct folio *folio, size_t off, size_t len, + int error); void iomap_finish_folio_write(struct inode *inode, struct folio *folio, size_t len); int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio); int iomap_writepages(struct iomap_writepage_ctx *wpc); +struct iomap_read_folio_ctx { + const struct iomap_read_ops *ops; + struct folio *cur_folio; + struct readahead_control *rac; + void *read_ctx; +}; + +struct iomap_read_ops { + /* + * Read in a folio range. + * + * If this succeeds, iomap_finish_folio_read() must be called after the + * range is read in, regardless of whether the read succeeded or failed. + * + * Returns 0 on success or a negative error on failure. + */ + int (*read_folio_range)(const struct iomap_iter *iter, + struct iomap_read_folio_ctx *ctx, size_t len); + + /* + * Submit any pending read requests. + * + * This is optional. + */ + void (*submit_read)(struct iomap_read_folio_ctx *ctx); +}; + /* * Flags for direct I/O ->end_io: */ @@ -518,6 +554,14 @@ struct iomap_dio_ops { */ #define IOMAP_DIO_PARTIAL (1 << 2) +/* + * Ensure each bio is aligned to fs block size. + * + * For filesystems which need to calculate/verify the checksum of each fs + * block. Otherwise they may not be able to handle unaligned bios. + */ +#define IOMAP_DIO_FSBLOCK_ALIGNED (1 << 3) + ssize_t iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, const struct iomap_ops *ops, const struct iomap_dio_ops *dops, unsigned int dio_flags, void *private, size_t done_before); @@ -540,4 +584,30 @@ int iomap_swapfile_activate(struct swap_info_struct *sis, extern struct bio_set iomap_ioend_bioset; +#ifdef CONFIG_BLOCK +extern const struct iomap_read_ops iomap_bio_read_ops; + +static inline void iomap_bio_read_folio(struct folio *folio, + const struct iomap_ops *ops) +{ + struct iomap_read_folio_ctx ctx = { + .ops = &iomap_bio_read_ops, + .cur_folio = folio, + }; + + iomap_read_folio(ops, &ctx); +} + +static inline void iomap_bio_readahead(struct readahead_control *rac, + const struct iomap_ops *ops) +{ + struct iomap_read_folio_ctx ctx = { + .ops = &iomap_bio_read_ops, + .rac = rac, + }; + + iomap_readahead(ops, &ctx); +} +#endif /* CONFIG_BLOCK */ + #endif /* LINUX_IOMAP_H */ diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h index d643c7c87822..6ab913e57da0 100644 --- a/include/linux/irq-entry-common.h +++ b/include/linux/irq-entry-common.h @@ -2,11 +2,12 @@ #ifndef __LINUX_IRQENTRYCOMMON_H #define __LINUX_IRQENTRYCOMMON_H +#include <linux/context_tracking.h> +#include <linux/kmsan.h> +#include <linux/rseq_entry.h> #include <linux/static_call_types.h> #include <linux/syscalls.h> -#include <linux/context_tracking.h> #include <linux/tick.h> -#include <linux/kmsan.h> #include <linux/unwind_deferred.h> #include <asm/entry-common.h> @@ -29,7 +30,7 @@ #define EXIT_TO_USER_MODE_WORK \ (_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE | \ _TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY | \ - _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | \ + _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL | _TIF_RSEQ | \ ARCH_EXIT_TO_USER_MODE_WORK) /** @@ -67,6 +68,7 @@ static __always_inline bool arch_in_rcu_eqs(void) { return false; } /** * enter_from_user_mode - Establish state when coming from user mode + * @regs: Pointer to currents pt_regs * * Syscall/interrupt entry disables interrupts, but user mode is traced as * interrupts enabled. Also with NO_HZ_FULL RCU might be idle. @@ -195,14 +197,11 @@ static __always_inline void arch_exit_to_user_mode(void) { } */ void arch_do_signal_or_restart(struct pt_regs *regs); -/** - * exit_to_user_mode_loop - do any pending work before leaving to user space - */ -unsigned long exit_to_user_mode_loop(struct pt_regs *regs, - unsigned long ti_work); +/* Handle pending TIF work */ +unsigned long exit_to_user_mode_loop(struct pt_regs *regs, unsigned long ti_work); /** - * exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required + * __exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required * @regs: Pointer to pt_regs on entry stack * * 1) check that interrupts are disabled @@ -210,8 +209,10 @@ unsigned long exit_to_user_mode_loop(struct pt_regs *regs, * 3) call exit_to_user_mode_loop() if any flags from * EXIT_TO_USER_MODE_WORK are set * 4) check that interrupts are still disabled + * + * Don't invoke directly, use the syscall/irqentry_ prefixed variants below */ -static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs) +static __always_inline void __exit_to_user_mode_prepare(struct pt_regs *regs) { unsigned long ti_work; @@ -225,13 +226,52 @@ static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs) ti_work = exit_to_user_mode_loop(regs, ti_work); arch_exit_to_user_mode_prepare(regs, ti_work); +} +static __always_inline void __exit_to_user_mode_validate(void) +{ /* Ensure that kernel state is sane for a return to userspace */ kmap_assert_nomap(); lockdep_assert_irqs_disabled(); lockdep_sys_exit(); } +/* Temporary workaround to keep ARM64 alive */ +static __always_inline void exit_to_user_mode_prepare_legacy(struct pt_regs *regs) +{ + __exit_to_user_mode_prepare(regs); + rseq_exit_to_user_mode_legacy(); + __exit_to_user_mode_validate(); +} + +/** + * syscall_exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required + * @regs: Pointer to pt_regs on entry stack + * + * Wrapper around __exit_to_user_mode_prepare() to separate the exit work for + * syscalls and interrupts. + */ +static __always_inline void syscall_exit_to_user_mode_prepare(struct pt_regs *regs) +{ + __exit_to_user_mode_prepare(regs); + rseq_syscall_exit_to_user_mode(); + __exit_to_user_mode_validate(); +} + +/** + * irqentry_exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required + * @regs: Pointer to pt_regs on entry stack + * + * Wrapper around __exit_to_user_mode_prepare() to separate the exit work for + * syscalls and interrupts. + */ +static __always_inline void irqentry_exit_to_user_mode_prepare(struct pt_regs *regs) +{ + __exit_to_user_mode_prepare(regs); + rseq_irqentry_exit_to_user_mode(); + __exit_to_user_mode_validate(); +} + /** * exit_to_user_mode - Fixup state when exiting to user mode * @@ -253,11 +293,11 @@ static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs) static __always_inline void exit_to_user_mode(void) { instrumentation_begin(); + unwind_reset_info(); trace_hardirqs_on_prepare(); lockdep_hardirqs_on_prepare(); instrumentation_end(); - unwind_reset_info(); user_enter_irqoff(); arch_exit_to_user_mode(); lockdep_hardirqs_on(CALLER_ADDR0); @@ -274,7 +314,11 @@ static __always_inline void exit_to_user_mode(void) * * The function establishes state (lockdep, RCU (context tracking), tracing) */ -void irqentry_enter_from_user_mode(struct pt_regs *regs); +static __always_inline void irqentry_enter_from_user_mode(struct pt_regs *regs) +{ + enter_from_user_mode(regs); + rseq_note_user_irq_entry(); +} /** * irqentry_exit_to_user_mode - Interrupt exit work @@ -289,7 +333,13 @@ void irqentry_enter_from_user_mode(struct pt_regs *regs); * Interrupt exit is not invoking #1 which is the syscall specific one time * work. */ -void irqentry_exit_to_user_mode(struct pt_regs *regs); +static __always_inline void irqentry_exit_to_user_mode(struct pt_regs *regs) +{ + instrumentation_begin(); + irqentry_exit_to_user_mode_prepare(regs); + instrumentation_end(); + exit_to_user_mode(); +} #ifndef irqentry_state /** @@ -354,6 +404,7 @@ irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs); * Conditional reschedule with additional sanity checks. */ void raw_irqentry_exit_cond_resched(void); + #ifdef CONFIG_PREEMPT_DYNAMIC #if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL) #define irqentry_exit_cond_resched_dynamic_enabled raw_irqentry_exit_cond_resched diff --git a/include/linux/irq.h b/include/linux/irq.h index c67e76fbcc07..4a9f1d7b08c3 100644 --- a/include/linux/irq.h +++ b/include/linux/irq.h @@ -655,7 +655,6 @@ extern void handle_bad_irq(struct irq_desc *desc); extern void handle_nested_irq(unsigned int irq); extern void handle_fasteoi_nmi(struct irq_desc *desc); -extern void handle_percpu_devid_fasteoi_nmi(struct irq_desc *desc); extern int irq_chip_compose_msi_msg(struct irq_data *data, struct msi_msg *msg); extern int irq_chip_pm_get(struct irq_data *data); @@ -719,10 +718,6 @@ static inline void irq_set_chip_and_handler(unsigned int irq, } extern int irq_set_percpu_devid(unsigned int irq); -extern int irq_set_percpu_devid_partition(unsigned int irq, - const struct cpumask *affinity); -extern int irq_get_percpu_devid_partition(unsigned int irq, - struct cpumask *affinity); extern void __irq_set_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained, diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h index 136f2980cba3..c5afd053ae32 100644 --- a/include/linux/irq_work.h +++ b/include/linux/irq_work.h @@ -2,8 +2,9 @@ #ifndef _LINUX_IRQ_WORK_H #define _LINUX_IRQ_WORK_H -#include <linux/smp_types.h> +#include <linux/irq_work_types.h> #include <linux/rcuwait.h> +#include <linux/smp_types.h> /* * An entry can be in one of four states: @@ -14,12 +15,6 @@ * busy NULL, 2 -> {free, claimed} : callback in progress, can be claimed */ -struct irq_work { - struct __call_single_node node; - void (*func)(struct irq_work *); - struct rcuwait irqwait; -}; - #define __IRQ_WORK_INIT(_func, _flags) (struct irq_work){ \ .node = { .u_flags = (_flags), }, \ .func = (_func), \ diff --git a/include/linux/irq_work_types.h b/include/linux/irq_work_types.h new file mode 100644 index 000000000000..73abec5bb06e --- /dev/null +++ b/include/linux/irq_work_types.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_IRQ_WORK_TYPES_H +#define _LINUX_IRQ_WORK_TYPES_H + +#include <linux/smp_types.h> +#include <linux/types.h> + +struct irq_work { + struct __call_single_node node; + void (*func)(struct irq_work *); + struct rcuwait irqwait; +}; + +#endif diff --git a/include/linux/irqchip.h b/include/linux/irqchip.h index d5e6024cb2a8..bc4ddacd6ddc 100644 --- a/include/linux/irqchip.h +++ b/include/linux/irqchip.h @@ -17,12 +17,18 @@ #include <linux/of_irq.h> #include <linux/platform_device.h> +typedef int (*platform_irq_probe_t)(struct platform_device *, struct device_node *); + /* Undefined on purpose */ extern of_irq_init_cb_t typecheck_irq_init_cb; +extern platform_irq_probe_t typecheck_irq_probe; #define typecheck_irq_init_cb(fn) \ (__typecheck(typecheck_irq_init_cb, &fn) ? fn : fn) +#define typecheck_irq_probe(fn) \ + (__typecheck(typecheck_irq_probe, &fn) ? fn : fn) + /* * This macro must be used by the different irqchip drivers to declare * the association between their DT compatible string and their @@ -42,7 +48,7 @@ extern int platform_irqchip_probe(struct platform_device *pdev); static const struct of_device_id drv_name##_irqchip_match_table[] = { #define IRQCHIP_MATCH(compat, fn) { .compatible = compat, \ - .data = typecheck_irq_init_cb(fn), }, + .data = typecheck_irq_probe(fn), }, #define IRQCHIP_PLATFORM_DRIVER_END(drv_name, ...) \ diff --git a/include/linux/irqchip/irq-partition-percpu.h b/include/linux/irqchip/irq-partition-percpu.h deleted file mode 100644 index b35ee22c278f..000000000000 --- a/include/linux/irqchip/irq-partition-percpu.h +++ /dev/null @@ -1,53 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0-only */ -/* - * Copyright (C) 2016 ARM Limited, All Rights Reserved. - * Author: Marc Zyngier <marc.zyngier@arm.com> - */ - -#ifndef __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H -#define __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H - -#include <linux/fwnode.h> -#include <linux/cpumask_types.h> -#include <linux/irqdomain.h> - -struct partition_affinity { - cpumask_t mask; - void *partition_id; -}; - -struct partition_desc; - -#ifdef CONFIG_PARTITION_PERCPU -int partition_translate_id(struct partition_desc *desc, void *partition_id); -struct partition_desc *partition_create_desc(struct fwnode_handle *fwnode, - struct partition_affinity *parts, - int nr_parts, - int chained_irq, - const struct irq_domain_ops *ops); -struct irq_domain *partition_get_domain(struct partition_desc *dsc); -#else -static inline int partition_translate_id(struct partition_desc *desc, - void *partition_id) -{ - return -EINVAL; -} - -static inline -struct partition_desc *partition_create_desc(struct fwnode_handle *fwnode, - struct partition_affinity *parts, - int nr_parts, - int chained_irq, - const struct irq_domain_ops *ops) -{ - return NULL; -} - -static inline -struct irq_domain *partition_get_domain(struct partition_desc *dsc) -{ - return NULL; -} -#endif - -#endif /* __LINUX_IRQCHIP_IRQ_PARTITION_PERCPU_H */ diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h index fd091c35d572..37e0b5b5600a 100644 --- a/include/linux/irqdesc.h +++ b/include/linux/irqdesc.h @@ -82,7 +82,6 @@ struct irq_desc { int threads_handled_last; raw_spinlock_t lock; struct cpumask *percpu_enabled; - const struct cpumask *percpu_affinity; #ifdef CONFIG_SMP const struct cpumask *affinity_hint; struct irq_affinity_notify *affinity_notify; diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h index 4a86e6b915dd..952d3c8dd6b7 100644 --- a/include/linux/irqdomain.h +++ b/include/linux/irqdomain.h @@ -44,6 +44,23 @@ struct irq_fwspec { u32 param[IRQ_DOMAIN_IRQ_SPEC_PARAMS]; }; +/** + * struct irq_fwspec_info - firmware provided IRQ information structure + * + * @flags: Information validity flags + * @affinity: Affinity mask for this interrupt + * + * This structure reports firmware-specific information about an + * interrupt. The only significant information is the affinity of a + * per-CPU interrupt, but this is designed to be extended as required. + */ +struct irq_fwspec_info { + unsigned long flags; + const struct cpumask *affinity; +}; + +#define IRQ_FWSPEC_INFO_AFFINITY_VALID BIT(0) + /* Conversion function from of_phandle_args fields to fwspec */ void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, unsigned int count, struct irq_fwspec *fwspec); @@ -69,6 +86,9 @@ void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args, * @translate: Given @fwspec, decode the hardware irq number (@out_hwirq) and * linux irq type value (@out_type). This is a generalised @xlate * (over struct irq_fwspec) and is preferred if provided. + * @get_fwspec_info: + * Given @fwspec, report additional firmware-provided information in + * @info. Optional. * @debug_show: For domains to show specific data for an interrupt in debugfs. * * Functions below are provided by the driver and called whenever a new mapping @@ -96,6 +116,7 @@ struct irq_domain_ops { void (*deactivate)(struct irq_domain *d, struct irq_data *irq_data); int (*translate)(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *out_hwirq, unsigned int *out_type); + int (*get_fwspec_info)(struct irq_fwspec *fwspec, struct irq_fwspec_info *info); #endif #ifdef CONFIG_GENERIC_IRQ_DEBUGFS void (*debug_show)(struct seq_file *m, struct irq_domain *d, @@ -602,6 +623,8 @@ void irq_domain_free_irqs_parent(struct irq_domain *domain, unsigned int irq_bas int irq_domain_disconnect_hierarchy(struct irq_domain *domain, unsigned int virq); +int irq_populate_fwspec_info(struct irq_fwspec *fwspec, struct irq_fwspec_info *info); + static inline bool irq_domain_is_hierarchy(struct irq_domain *domain) { return domain->flags & IRQ_DOMAIN_FLAG_HIERARCHY; @@ -685,6 +708,10 @@ static inline bool irq_domain_is_msi_device(struct irq_domain *domain) return false; } +static inline int irq_populate_fwspec_info(struct irq_fwspec *fwspec, struct irq_fwspec_info *info) +{ + return -EINVAL; +} #endif /* CONFIG_IRQ_DOMAIN_HIERARCHY */ #ifdef CONFIG_GENERIC_MSI_IRQ @@ -703,12 +730,6 @@ static inline void msi_device_domain_free_wired(struct irq_domain *domain, unsig } #endif -/* Deprecated functions. Will be removed in the merge window */ -static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node) -{ - return node ? &node->fwnode : NULL; -} - static inline struct irq_domain *irq_domain_add_tree(struct device_node *of_node, const struct irq_domain_ops *ops, void *host_data) diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index fa36e70df088..5bd76cf394fa 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -729,7 +729,17 @@ static inline bool kvm_arch_has_private_mem(struct kvm *kvm) #endif #ifdef CONFIG_KVM_GUEST_MEMFD -bool kvm_arch_supports_gmem_mmap(struct kvm *kvm); +bool kvm_arch_supports_gmem_init_shared(struct kvm *kvm); + +static inline u64 kvm_gmem_get_supported_flags(struct kvm *kvm) +{ + u64 flags = GUEST_MEMFD_FLAG_MMAP; + + if (!kvm || kvm_arch_supports_gmem_init_shared(kvm)) + flags |= GUEST_MEMFD_FLAG_INIT_SHARED; + + return flags; +} #endif #ifndef kvm_arch_has_readonly_mem diff --git a/include/linux/kvm_types.h b/include/linux/kvm_types.h index 490464c205b4..a568d8e6f4e8 100644 --- a/include/linux/kvm_types.h +++ b/include/linux/kvm_types.h @@ -11,8 +11,22 @@ #ifdef KVM_SUB_MODULES #define EXPORT_SYMBOL_FOR_KVM_INTERNAL(symbol) \ EXPORT_SYMBOL_FOR_MODULES(symbol, __stringify(KVM_SUB_MODULES)) +#define EXPORT_SYMBOL_FOR_KVM(symbol) \ + EXPORT_SYMBOL_FOR_MODULES(symbol, "kvm," __stringify(KVM_SUB_MODULES)) #else #define EXPORT_SYMBOL_FOR_KVM_INTERNAL(symbol) +/* + * Allow architectures to provide a custom EXPORT_SYMBOL_FOR_KVM, but only + * if there are no submodules, e.g. to allow suppressing exports if KVM=m, but + * kvm.ko won't actually be built (due to lack of at least one submodule). + */ +#ifndef EXPORT_SYMBOL_FOR_KVM +#if IS_MODULE(CONFIG_KVM) +#define EXPORT_SYMBOL_FOR_KVM(symbol) EXPORT_SYMBOL_FOR_MODULES(symbol, "kvm") +#else +#define EXPORT_SYMBOL_FOR_KVM(symbol) +#endif /* IS_MODULE(CONFIG_KVM) */ +#endif /* EXPORT_SYMBOL_FOR_KVM */ #endif #ifndef __ASSEMBLER__ diff --git a/include/linux/libata.h b/include/linux/libata.h index 21de0935775d..7a98de1cc995 100644 --- a/include/linux/libata.h +++ b/include/linux/libata.h @@ -1594,6 +1594,12 @@ do { \ #define ata_dev_dbg(dev, fmt, ...) \ ata_dev_printk(debug, dev, fmt, ##__VA_ARGS__) +#define ata_dev_warn_once(dev, fmt, ...) \ + pr_warn_once("ata%u.%02u: " fmt, \ + (dev)->link->ap->print_id, \ + (dev)->link->pmp + (dev)->devno, \ + ##__VA_ARGS__) + static inline void ata_print_version_once(const struct device *dev, const char *version) { diff --git a/include/linux/livepatch.h b/include/linux/livepatch.h index 51a258c24ff5..772919e8096a 100644 --- a/include/linux/livepatch.h +++ b/include/linux/livepatch.h @@ -13,6 +13,7 @@ #include <linux/ftrace.h> #include <linux/completion.h> #include <linux/list.h> +#include <linux/livepatch_external.h> #include <linux/livepatch_sched.h> #if IS_ENABLED(CONFIG_LIVEPATCH) @@ -77,30 +78,6 @@ struct klp_func { bool transition; }; -struct klp_object; - -/** - * struct klp_callbacks - pre/post live-(un)patch callback structure - * @pre_patch: executed before code patching - * @post_patch: executed after code patching - * @pre_unpatch: executed before code unpatching - * @post_unpatch: executed after code unpatching - * @post_unpatch_enabled: flag indicating if post-unpatch callback - * should run - * - * All callbacks are optional. Only the pre-patch callback, if provided, - * will be unconditionally executed. If the parent klp_object fails to - * patch for any reason, including a non-zero error status returned from - * the pre-patch callback, no further callbacks will be executed. - */ -struct klp_callbacks { - int (*pre_patch)(struct klp_object *obj); - void (*post_patch)(struct klp_object *obj); - void (*pre_unpatch)(struct klp_object *obj); - void (*post_unpatch)(struct klp_object *obj); - bool post_unpatch_enabled; -}; - /** * struct klp_object - kernel object structure for live patching * @name: module name (or NULL for vmlinux) diff --git a/include/linux/livepatch_external.h b/include/linux/livepatch_external.h new file mode 100644 index 000000000000..138af19b0f5c --- /dev/null +++ b/include/linux/livepatch_external.h @@ -0,0 +1,76 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* + * External livepatch interfaces for patch creation tooling + */ + +#ifndef _LINUX_LIVEPATCH_EXTERNAL_H_ +#define _LINUX_LIVEPATCH_EXTERNAL_H_ + +#include <linux/types.h> + +#define KLP_RELOC_SEC_PREFIX ".klp.rela." +#define KLP_SYM_PREFIX ".klp.sym." + +#define __KLP_PRE_PATCH_PREFIX __klp_pre_patch_callback_ +#define __KLP_POST_PATCH_PREFIX __klp_post_patch_callback_ +#define __KLP_PRE_UNPATCH_PREFIX __klp_pre_unpatch_callback_ +#define __KLP_POST_UNPATCH_PREFIX __klp_post_unpatch_callback_ + +#define KLP_PRE_PATCH_PREFIX __stringify(__KLP_PRE_PATCH_PREFIX) +#define KLP_POST_PATCH_PREFIX __stringify(__KLP_POST_PATCH_PREFIX) +#define KLP_PRE_UNPATCH_PREFIX __stringify(__KLP_PRE_UNPATCH_PREFIX) +#define KLP_POST_UNPATCH_PREFIX __stringify(__KLP_POST_UNPATCH_PREFIX) + +struct klp_object; + +typedef int (*klp_pre_patch_t)(struct klp_object *obj); +typedef void (*klp_post_patch_t)(struct klp_object *obj); +typedef void (*klp_pre_unpatch_t)(struct klp_object *obj); +typedef void (*klp_post_unpatch_t)(struct klp_object *obj); + +/** + * struct klp_callbacks - pre/post live-(un)patch callback structure + * @pre_patch: executed before code patching + * @post_patch: executed after code patching + * @pre_unpatch: executed before code unpatching + * @post_unpatch: executed after code unpatching + * @post_unpatch_enabled: flag indicating if post-unpatch callback + * should run + * + * All callbacks are optional. Only the pre-patch callback, if provided, + * will be unconditionally executed. If the parent klp_object fails to + * patch for any reason, including a non-zero error status returned from + * the pre-patch callback, no further callbacks will be executed. + */ +struct klp_callbacks { + klp_pre_patch_t pre_patch; + klp_post_patch_t post_patch; + klp_pre_unpatch_t pre_unpatch; + klp_post_unpatch_t post_unpatch; + bool post_unpatch_enabled; +}; + +/* + * 'struct klp_{func,object}_ext' are compact "external" representations of + * 'struct klp_{func,object}'. They are used by objtool for livepatch + * generation. The structs are then read by the livepatch module and converted + * to the real structs before calling klp_enable_patch(). + * + * TODO make these the official API for klp_enable_patch(). That should + * simplify livepatch's interface as well as its data structure lifetime + * management. + */ +struct klp_func_ext { + const char *old_name; + void *new_func; + unsigned long sympos; +}; + +struct klp_object_ext { + const char *name; + struct klp_func_ext *funcs; + struct klp_callbacks callbacks; + unsigned int nr_funcs; +}; + +#endif /* _LINUX_LIVEPATCH_EXTERNAL_H_ */ diff --git a/include/linux/livepatch_helpers.h b/include/linux/livepatch_helpers.h new file mode 100644 index 000000000000..99d68d0773fa --- /dev/null +++ b/include/linux/livepatch_helpers.h @@ -0,0 +1,77 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_LIVEPATCH_HELPERS_H +#define _LINUX_LIVEPATCH_HELPERS_H + +/* + * Interfaces for use by livepatch patches + */ + +#include <linux/syscalls.h> +#include <linux/livepatch.h> + +#ifdef MODULE +#define KLP_OBJNAME __KBUILD_MODNAME +#else +#define KLP_OBJNAME vmlinux +#endif + +/* Livepatch callback registration */ + +#define KLP_CALLBACK_PTRS ".discard.klp_callback_ptrs" + +#define KLP_PRE_PATCH_CALLBACK(func) \ + klp_pre_patch_t __used __section(KLP_CALLBACK_PTRS) \ + __PASTE(__KLP_PRE_PATCH_PREFIX, KLP_OBJNAME) = func + +#define KLP_POST_PATCH_CALLBACK(func) \ + klp_post_patch_t __used __section(KLP_CALLBACK_PTRS) \ + __PASTE(__KLP_POST_PATCH_PREFIX, KLP_OBJNAME) = func + +#define KLP_PRE_UNPATCH_CALLBACK(func) \ + klp_pre_unpatch_t __used __section(KLP_CALLBACK_PTRS) \ + __PASTE(__KLP_PRE_UNPATCH_PREFIX, KLP_OBJNAME) = func + +#define KLP_POST_UNPATCH_CALLBACK(func) \ + klp_post_unpatch_t __used __section(KLP_CALLBACK_PTRS) \ + __PASTE(__KLP_POST_UNPATCH_PREFIX, KLP_OBJNAME) = func + +/* + * Replace static_call() usage with this macro when create-diff-object + * recommends it due to the original static call key living in a module. + * + * This converts the static call to a regular indirect call. + */ +#define KLP_STATIC_CALL(name) \ + ((typeof(STATIC_CALL_TRAMP(name))*)(STATIC_CALL_KEY(name).func)) + +/* Syscall patching */ + +#define KLP_SYSCALL_DEFINE1(name, ...) KLP_SYSCALL_DEFINEx(1, _##name, __VA_ARGS__) +#define KLP_SYSCALL_DEFINE2(name, ...) KLP_SYSCALL_DEFINEx(2, _##name, __VA_ARGS__) +#define KLP_SYSCALL_DEFINE3(name, ...) KLP_SYSCALL_DEFINEx(3, _##name, __VA_ARGS__) +#define KLP_SYSCALL_DEFINE4(name, ...) KLP_SYSCALL_DEFINEx(4, _##name, __VA_ARGS__) +#define KLP_SYSCALL_DEFINE5(name, ...) KLP_SYSCALL_DEFINEx(5, _##name, __VA_ARGS__) +#define KLP_SYSCALL_DEFINE6(name, ...) KLP_SYSCALL_DEFINEx(6, _##name, __VA_ARGS__) + +#define KLP_SYSCALL_DEFINEx(x, sname, ...) \ + __KLP_SYSCALL_DEFINEx(x, sname, __VA_ARGS__) + +#ifdef CONFIG_X86_64 +// TODO move this to arch/x86/include/asm/syscall_wrapper.h and share code +#define __KLP_SYSCALL_DEFINEx(x, name, ...) \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)); \ + static inline long __klp_do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__));\ + __X64_SYS_STUBx(x, name, __VA_ARGS__) \ + __IA32_SYS_STUBx(x, name, __VA_ARGS__) \ + static long __se_sys##name(__MAP(x,__SC_LONG,__VA_ARGS__)) \ + { \ + long ret = __klp_do_sys##name(__MAP(x,__SC_CAST,__VA_ARGS__));\ + __MAP(x,__SC_TEST,__VA_ARGS__); \ + __PROTECT(x, ret,__MAP(x,__SC_ARGS,__VA_ARGS__)); \ + return ret; \ + } \ + static inline long __klp_do_sys##name(__MAP(x,__SC_DECL,__VA_ARGS__)) + +#endif + +#endif /* _LINUX_LIVEPATCH_HELPERS_H */ diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h index 0d91d060e3e9..b0e6ab329b00 100644 --- a/include/linux/local_lock.h +++ b/include/linux/local_lock.h @@ -6,6 +6,7 @@ /** * local_lock_init - Runtime initialize a lock instance + * @lock: The lock variable */ #define local_lock_init(lock) __local_lock_init(lock) @@ -52,7 +53,8 @@ __local_unlock_irqrestore(this_cpu_ptr(lock), flags) /** - * local_lock_init - Runtime initialize a lock instance + * local_trylock_init - Runtime initialize a lock instance + * @lock: The lock variable */ #define local_trylock_init(lock) __local_trylock_init(lock) diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h index a4dc479157b5..8f82b4eb542f 100644 --- a/include/linux/local_lock_internal.h +++ b/include/linux/local_lock_internal.h @@ -99,18 +99,18 @@ do { \ #define __local_lock_acquire(lock) \ do { \ - local_trylock_t *tl; \ - local_lock_t *l; \ + local_trylock_t *__tl; \ + local_lock_t *__l; \ \ - l = (local_lock_t *)(lock); \ - tl = (local_trylock_t *)l; \ + __l = (local_lock_t *)(lock); \ + __tl = (local_trylock_t *)__l; \ _Generic((lock), \ local_trylock_t *: ({ \ - lockdep_assert(tl->acquired == 0); \ - WRITE_ONCE(tl->acquired, 1); \ + lockdep_assert(__tl->acquired == 0); \ + WRITE_ONCE(__tl->acquired, 1); \ }), \ local_lock_t *: (void)0); \ - local_lock_acquire(l); \ + local_lock_acquire(__l); \ } while (0) #define __local_lock(lock) \ @@ -133,36 +133,36 @@ do { \ #define __local_trylock(lock) \ ({ \ - local_trylock_t *tl; \ + local_trylock_t *__tl; \ \ preempt_disable(); \ - tl = (lock); \ - if (READ_ONCE(tl->acquired)) { \ + __tl = (lock); \ + if (READ_ONCE(__tl->acquired)) { \ preempt_enable(); \ - tl = NULL; \ + __tl = NULL; \ } else { \ - WRITE_ONCE(tl->acquired, 1); \ + WRITE_ONCE(__tl->acquired, 1); \ local_trylock_acquire( \ - (local_lock_t *)tl); \ + (local_lock_t *)__tl); \ } \ - !!tl; \ + !!__tl; \ }) #define __local_trylock_irqsave(lock, flags) \ ({ \ - local_trylock_t *tl; \ + local_trylock_t *__tl; \ \ local_irq_save(flags); \ - tl = (lock); \ - if (READ_ONCE(tl->acquired)) { \ + __tl = (lock); \ + if (READ_ONCE(__tl->acquired)) { \ local_irq_restore(flags); \ - tl = NULL; \ + __tl = NULL; \ } else { \ - WRITE_ONCE(tl->acquired, 1); \ + WRITE_ONCE(__tl->acquired, 1); \ local_trylock_acquire( \ - (local_lock_t *)tl); \ + (local_lock_t *)__tl); \ } \ - !!tl; \ + !!__tl; \ }) /* preemption or migration must be disabled before calling __local_lock_is_locked */ @@ -170,16 +170,16 @@ do { \ #define __local_lock_release(lock) \ do { \ - local_trylock_t *tl; \ - local_lock_t *l; \ + local_trylock_t *__tl; \ + local_lock_t *__l; \ \ - l = (local_lock_t *)(lock); \ - tl = (local_trylock_t *)l; \ - local_lock_release(l); \ + __l = (local_lock_t *)(lock); \ + __tl = (local_trylock_t *)__l; \ + local_lock_release(__l); \ _Generic((lock), \ local_trylock_t *: ({ \ - lockdep_assert(tl->acquired == 1); \ - WRITE_ONCE(tl->acquired, 0); \ + lockdep_assert(__tl->acquired == 1); \ + WRITE_ONCE(__tl->acquired, 0); \ }), \ local_lock_t *: (void)0); \ } while (0) @@ -223,12 +223,12 @@ typedef spinlock_t local_trylock_t; #define INIT_LOCAL_LOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) #define INIT_LOCAL_TRYLOCK(lockname) __LOCAL_SPIN_LOCK_UNLOCKED((lockname)) -#define __local_lock_init(l) \ +#define __local_lock_init(__l) \ do { \ - local_spin_lock_init((l)); \ + local_spin_lock_init((__l)); \ } while (0) -#define __local_trylock_init(l) __local_lock_init(l) +#define __local_trylock_init(__l) __local_lock_init(__l) #define __local_lock(__lock) \ do { \ diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h index 67964dc4db95..dd634103b014 100644 --- a/include/linux/lockdep.h +++ b/include/linux/lockdep.h @@ -616,7 +616,7 @@ do { \ #define lockdep_assert_in_softirq() \ do { \ WARN_ON_ONCE(__lockdep_enabled && \ - (!in_softirq() || in_irq() || in_nmi())); \ + (!in_softirq() || in_hardirq() || in_nmi())); \ } while (0) extern void lockdep_assert_in_softirq_func(void); diff --git a/include/linux/mailbox/mtk-cmdq-mailbox.h b/include/linux/mailbox/mtk-cmdq-mailbox.h index 4c1a91b07de3..e1555e06e7e5 100644 --- a/include/linux/mailbox/mtk-cmdq-mailbox.h +++ b/include/linux/mailbox/mtk-cmdq-mailbox.h @@ -77,6 +77,16 @@ struct cmdq_pkt { size_t buf_size; /* real buffer size */ }; +/** + * cmdq_get_shift_pa() - get the shift bits of physical address + * @chan: mailbox channel + * + * GCE can only fetch the command buffer address from a 32-bit register. + * Some SOCs support more than 32-bit command buffer address for GCE, which + * requires some shift bits to make the address fit into the 32-bit register. + * + * Return: the shift bits of physical address + */ u8 cmdq_get_shift_pa(struct mbox_chan *chan); #endif /* __MTK_CMDQ_MAILBOX_H__ */ diff --git a/include/linux/map_benchmark.h b/include/linux/map_benchmark.h index 62674c83bde4..48e2ff95332f 100644 --- a/include/linux/map_benchmark.h +++ b/include/linux/map_benchmark.h @@ -27,5 +27,6 @@ struct map_benchmark { __u32 dma_dir; /* DMA data direction */ __u32 dma_trans_ns; /* time for DMA transmission in ns */ __u32 granule; /* how many PAGE_SIZE will do map/unmap once a time */ + __u8 expansion[76]; /* For future use */ }; #endif /* _KERNEL_DMA_BENCHMARK_H */ diff --git a/include/linux/misc_cgroup.h b/include/linux/misc_cgroup.h index 71cf5bfc6349..0cb36a3ffc47 100644 --- a/include/linux/misc_cgroup.h +++ b/include/linux/misc_cgroup.h @@ -19,7 +19,7 @@ enum misc_res_type { MISC_CG_RES_SEV_ES, #endif #ifdef CONFIG_INTEL_TDX_HOST - /* Intel TDX HKIDs resource */ + /** @MISC_CG_RES_TDX: Intel TDX HKIDs resource */ MISC_CG_RES_TDX, #endif /** @MISC_CG_RES_TYPES: count of enum misc_res_type constants */ diff --git a/include/linux/mlx5/cq.h b/include/linux/mlx5/cq.h index 7ef2c7c7d803..9d47cdc727ad 100644 --- a/include/linux/mlx5/cq.h +++ b/include/linux/mlx5/cq.h @@ -183,6 +183,7 @@ static inline void mlx5_cq_put(struct mlx5_core_cq *cq) complete(&cq->free); } +void mlx5_add_cq_to_tasklet(struct mlx5_core_cq *cq, struct mlx5_eqe *eqe); int mlx5_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, u32 *in, int inlen, u32 *out, int outlen); int mlx5_core_create_cq(struct mlx5_core_dev *dev, struct mlx5_core_cq *cq, diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 07614cd95bed..1b0b36aa2a76 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -10833,7 +10833,9 @@ struct mlx5_ifc_pcam_regs_5000_to_507f_bits { u8 port_access_reg_cap_mask_127_to_96[0x20]; u8 port_access_reg_cap_mask_95_to_64[0x20]; - u8 port_access_reg_cap_mask_63_to_36[0x1c]; + u8 port_access_reg_cap_mask_63[0x1]; + u8 pphcr[0x1]; + u8 port_access_reg_cap_mask_61_to_36[0x1a]; u8 pplm[0x1]; u8 port_access_reg_cap_mask_34_to_32[0x3]; diff --git a/include/linux/mm.h b/include/linux/mm.h index d16b33bacc32..8dc0a07570cc 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2074,7 +2074,7 @@ static inline unsigned long folio_nr_pages(const struct folio *folio) return folio_large_nr_pages(folio); } -#if !defined(CONFIG_ARCH_HAS_GIGANTIC_PAGE) +#if !defined(CONFIG_HAVE_GIGANTIC_FOLIOS) /* * We don't expect any folios that exceed buddy sizes (and consequently * memory sections). @@ -2087,10 +2087,17 @@ static inline unsigned long folio_nr_pages(const struct folio *folio) * pages are guaranteed to be contiguous. */ #define MAX_FOLIO_ORDER PFN_SECTION_SHIFT -#else +#elif defined(CONFIG_HUGETLB_PAGE) /* * There is no real limit on the folio size. We limit them to the maximum we - * currently expect (e.g., hugetlb, dax). + * currently expect (see CONFIG_HAVE_GIGANTIC_FOLIOS): with hugetlb, we expect + * no folios larger than 16 GiB on 64bit and 1 GiB on 32bit. + */ +#define MAX_FOLIO_ORDER get_order(IS_ENABLED(CONFIG_64BIT) ? SZ_16G : SZ_1G) +#else +/* + * Without hugetlb, gigantic folios that are bigger than a single PUD are + * currently impossible. */ #define MAX_FOLIO_ORDER PUD_ORDER #endif @@ -2401,31 +2408,6 @@ struct zap_details { /* Set in unmap_vmas() to indicate a final unmap call. Only used by hugetlb */ #define ZAP_FLAG_UNMAP ((__force zap_flags_t) BIT(1)) -#ifdef CONFIG_SCHED_MM_CID -void sched_mm_cid_before_execve(struct task_struct *t); -void sched_mm_cid_after_execve(struct task_struct *t); -void sched_mm_cid_fork(struct task_struct *t); -void sched_mm_cid_exit_signals(struct task_struct *t); -static inline int task_mm_cid(struct task_struct *t) -{ - return t->mm_cid; -} -#else -static inline void sched_mm_cid_before_execve(struct task_struct *t) { } -static inline void sched_mm_cid_after_execve(struct task_struct *t) { } -static inline void sched_mm_cid_fork(struct task_struct *t) { } -static inline void sched_mm_cid_exit_signals(struct task_struct *t) { } -static inline int task_mm_cid(struct task_struct *t) -{ - /* - * Use the processor id as a fall-back when the mm cid feature is - * disabled. This provides functional per-cpu data structure accesses - * in user-space, althrough it won't provide the memory usage benefits. - */ - return raw_smp_processor_id(); -} -#endif - #ifdef CONFIG_MMU extern bool can_do_mlock(void); #else @@ -3369,6 +3351,8 @@ void vma_interval_tree_insert_after(struct vm_area_struct *node, struct rb_root_cached *root); void vma_interval_tree_remove(struct vm_area_struct *node, struct rb_root_cached *root); +struct vm_area_struct *vma_interval_tree_subtree_search(struct vm_area_struct *node, + unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long start, unsigned long last); struct vm_area_struct *vma_interval_tree_iter_next(struct vm_area_struct *node, @@ -3495,10 +3479,10 @@ struct vm_unmapped_area_info { extern unsigned long vm_unmapped_area(struct vm_unmapped_area_info *info); /* truncate.c */ -extern void truncate_inode_pages(struct address_space *, loff_t); -extern void truncate_inode_pages_range(struct address_space *, - loff_t lstart, loff_t lend); -extern void truncate_inode_pages_final(struct address_space *); +void truncate_inode_pages(struct address_space *mapping, loff_t lstart); +void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, + uoff_t lend); +void truncate_inode_pages_final(struct address_space *mapping); /* generic vm_area_ops exported for stackable file systems */ extern vm_fault_t filemap_fault(struct vm_fault *vmf); diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 90e5790c318f..3b7d05e7169c 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -20,6 +20,7 @@ #include <linux/seqlock.h> #include <linux/percpu_counter.h> #include <linux/types.h> +#include <linux/rseq_types.h> #include <linux/bitmap.h> #include <asm/mmu.h> @@ -922,14 +923,6 @@ struct vm_area_struct { #define vma_policy(vma) NULL #endif -#ifdef CONFIG_SCHED_MM_CID -struct mm_cid { - u64 time; - int cid; - int recent_cid; -}; -#endif - /* * Opaque type representing current mm_struct flag state. Must be accessed via * mm_flags_xxx() helper functions. @@ -991,44 +984,9 @@ struct mm_struct { */ atomic_t mm_users; -#ifdef CONFIG_SCHED_MM_CID - /** - * @pcpu_cid: Per-cpu current cid. - * - * Keep track of the currently allocated mm_cid for each cpu. - * The per-cpu mm_cid values are serialized by their respective - * runqueue locks. - */ - struct mm_cid __percpu *pcpu_cid; - /* - * @mm_cid_next_scan: Next mm_cid scan (in jiffies). - * - * When the next mm_cid scan is due (in jiffies). - */ - unsigned long mm_cid_next_scan; - /** - * @nr_cpus_allowed: Number of CPUs allowed for mm. - * - * Number of CPUs allowed in the union of all mm's - * threads allowed CPUs. - */ - unsigned int nr_cpus_allowed; - /** - * @max_nr_cid: Maximum number of allowed concurrency - * IDs allocated. - * - * Track the highest number of allowed concurrency IDs - * allocated for the mm. - */ - atomic_t max_nr_cid; - /** - * @cpus_allowed_lock: Lock protecting mm cpus_allowed. - * - * Provide mutual exclusion for mm cpus_allowed and - * mm nr_cpus_allowed updates. - */ - raw_spinlock_t cpus_allowed_lock; -#endif + /* MM CID related storage */ + struct mm_mm_cid mm_cid; + #ifdef CONFIG_MMU atomic_long_t pgtables_bytes; /* size of all page tables */ #endif @@ -1370,37 +1328,6 @@ static inline void vma_iter_init(struct vma_iterator *vmi, } #ifdef CONFIG_SCHED_MM_CID - -enum mm_cid_state { - MM_CID_UNSET = -1U, /* Unset state has lazy_put flag set. */ - MM_CID_LAZY_PUT = (1U << 31), -}; - -static inline bool mm_cid_is_unset(int cid) -{ - return cid == MM_CID_UNSET; -} - -static inline bool mm_cid_is_lazy_put(int cid) -{ - return !mm_cid_is_unset(cid) && (cid & MM_CID_LAZY_PUT); -} - -static inline bool mm_cid_is_valid(int cid) -{ - return !(cid & MM_CID_LAZY_PUT); -} - -static inline int mm_cid_set_lazy_put(int cid) -{ - return cid | MM_CID_LAZY_PUT; -} - -static inline int mm_cid_clear_lazy_put(int cid) -{ - return cid & ~MM_CID_LAZY_PUT; -} - /* * mm_cpus_allowed: Union of all mm's threads allowed CPUs. */ @@ -1415,37 +1342,21 @@ static inline cpumask_t *mm_cpus_allowed(struct mm_struct *mm) } /* Accessor for struct mm_struct's cidmask. */ -static inline cpumask_t *mm_cidmask(struct mm_struct *mm) +static inline unsigned long *mm_cidmask(struct mm_struct *mm) { unsigned long cid_bitmap = (unsigned long)mm_cpus_allowed(mm); /* Skip mm_cpus_allowed */ cid_bitmap += cpumask_size(); - return (struct cpumask *)cid_bitmap; + return (unsigned long *)cid_bitmap; } -static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) -{ - int i; - - for_each_possible_cpu(i) { - struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, i); - - pcpu_cid->cid = MM_CID_UNSET; - pcpu_cid->recent_cid = MM_CID_UNSET; - pcpu_cid->time = 0; - } - mm->nr_cpus_allowed = p->nr_cpus_allowed; - atomic_set(&mm->max_nr_cid, 0); - raw_spin_lock_init(&mm->cpus_allowed_lock); - cpumask_copy(mm_cpus_allowed(mm), &p->cpus_mask); - cpumask_clear(mm_cidmask(mm)); -} +void mm_init_cid(struct mm_struct *mm, struct task_struct *p); static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct *p) { - mm->pcpu_cid = alloc_percpu_noprof(struct mm_cid); - if (!mm->pcpu_cid) + mm->mm_cid.pcpu = alloc_percpu_noprof(struct mm_cid_pcpu); + if (!mm->mm_cid.pcpu) return -ENOMEM; mm_init_cid(mm, p); return 0; @@ -1454,37 +1365,24 @@ static inline int mm_alloc_cid_noprof(struct mm_struct *mm, struct task_struct * static inline void mm_destroy_cid(struct mm_struct *mm) { - free_percpu(mm->pcpu_cid); - mm->pcpu_cid = NULL; + free_percpu(mm->mm_cid.pcpu); + mm->mm_cid.pcpu = NULL; } static inline unsigned int mm_cid_size(void) { - return 2 * cpumask_size(); /* mm_cpus_allowed(), mm_cidmask(). */ + /* mm_cpus_allowed(), mm_cidmask(). */ + return cpumask_size() + bitmap_size(num_possible_cpus()); } -static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) -{ - struct cpumask *mm_allowed = mm_cpus_allowed(mm); - - if (!mm) - return; - /* The mm_cpus_allowed is the union of each thread allowed CPUs masks. */ - raw_spin_lock(&mm->cpus_allowed_lock); - cpumask_or(mm_allowed, mm_allowed, cpumask); - WRITE_ONCE(mm->nr_cpus_allowed, cpumask_weight(mm_allowed)); - raw_spin_unlock(&mm->cpus_allowed_lock); -} #else /* CONFIG_SCHED_MM_CID */ static inline void mm_init_cid(struct mm_struct *mm, struct task_struct *p) { } static inline int mm_alloc_cid(struct mm_struct *mm, struct task_struct *p) { return 0; } static inline void mm_destroy_cid(struct mm_struct *mm) { } - static inline unsigned int mm_cid_size(void) { return 0; } -static inline void mm_set_cpus_allowed(struct mm_struct *mm, const struct cpumask *cpumask) { } #endif /* CONFIG_SCHED_MM_CID */ struct mmu_gather; diff --git a/include/linux/module.h b/include/linux/module.h index e135cc79acee..d80c3ea57472 100644 --- a/include/linux/module.h +++ b/include/linux/module.h @@ -251,10 +251,11 @@ struct module_kobject *lookup_or_create_module_kobject(const char *name); */ #define __mod_device_table(type, name) \ __PASTE(__mod_device_table__, \ + __PASTE(kmod_, \ __PASTE(__KBUILD_MODNAME, \ __PASTE(__, \ __PASTE(type, \ - __PASTE(__, name))))) + __PASTE(__, name)))))) /* Creates an alias so file2alias.c can find device table. */ #define MODULE_DEVICE_TABLE(type, name) \ diff --git a/include/linux/msi.h b/include/linux/msi.h index d415dd15a0a9..8003e3218c46 100644 --- a/include/linux/msi.h +++ b/include/linux/msi.h @@ -701,9 +701,6 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg); void pci_msi_mask_irq(struct irq_data *data); void pci_msi_unmask_irq(struct irq_data *data); -struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode, - struct msi_domain_info *info, - struct irq_domain *parent); u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev); u32 pci_msi_map_rid_ctlr_node(struct pci_dev *pdev, struct device_node **node); struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev); diff --git a/include/linux/mutex.h b/include/linux/mutex.h index 847b81ca6436..bf535f0118bb 100644 --- a/include/linux/mutex.h +++ b/include/linux/mutex.h @@ -86,8 +86,23 @@ do { \ #define DEFINE_MUTEX(mutexname) \ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) -extern void __mutex_init(struct mutex *lock, const char *name, - struct lock_class_key *key); +#ifdef CONFIG_DEBUG_LOCK_ALLOC +void mutex_init_lockep(struct mutex *lock, const char *name, struct lock_class_key *key); + +static inline void __mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key) +{ + mutex_init_lockep(lock, name, key); +} +#else +extern void mutex_init_generic(struct mutex *lock); + +static inline void __mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key) +{ + mutex_init_generic(lock); +} +#endif /* !CONFIG_DEBUG_LOCK_ALLOC */ /** * mutex_is_locked - is the mutex locked @@ -111,17 +126,27 @@ extern bool mutex_is_locked(struct mutex *lock); #define DEFINE_MUTEX(mutexname) \ struct mutex mutexname = __MUTEX_INITIALIZER(mutexname) -extern void __mutex_rt_init(struct mutex *lock, const char *name, - struct lock_class_key *key); - #define mutex_is_locked(l) rt_mutex_base_is_locked(&(l)->rtmutex) -#define __mutex_init(mutex, name, key) \ -do { \ - rt_mutex_base_init(&(mutex)->rtmutex); \ - __mutex_rt_init((mutex), name, key); \ -} while (0) +#ifdef CONFIG_DEBUG_LOCK_ALLOC +extern void mutex_rt_init_lockdep(struct mutex *mutex, const char *name, + struct lock_class_key *key); + +static inline void __mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key) +{ + mutex_rt_init_lockdep(lock, name, key); +} +#else +extern void mutex_rt_init_generic(struct mutex *mutex); + +static inline void __mutex_init(struct mutex *lock, const char *name, + struct lock_class_key *key) +{ + mutex_rt_init_generic(lock); +} +#endif /* !CONFIG_LOCKDEP */ #endif /* CONFIG_PREEMPT_RT */ #ifdef CONFIG_DEBUG_MUTEXES diff --git a/include/linux/namei.h b/include/linux/namei.h index fed86221c69c..58600cf234bc 100644 --- a/include/linux/namei.h +++ b/include/linux/namei.h @@ -7,6 +7,7 @@ #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> +#include <linux/fs_struct.h> enum { MAX_NESTED_LINKS = 8 }; @@ -88,6 +89,81 @@ struct dentry *lookup_one_positive_killable(struct mnt_idmap *idmap, struct qstr *name, struct dentry *base); +struct dentry *start_creating(struct mnt_idmap *idmap, struct dentry *parent, + struct qstr *name); +struct dentry *start_removing(struct mnt_idmap *idmap, struct dentry *parent, + struct qstr *name); +struct dentry *start_creating_killable(struct mnt_idmap *idmap, + struct dentry *parent, + struct qstr *name); +struct dentry *start_removing_killable(struct mnt_idmap *idmap, + struct dentry *parent, + struct qstr *name); +struct dentry *start_creating_noperm(struct dentry *parent, struct qstr *name); +struct dentry *start_removing_noperm(struct dentry *parent, struct qstr *name); +struct dentry *start_creating_dentry(struct dentry *parent, + struct dentry *child); +struct dentry *start_removing_dentry(struct dentry *parent, + struct dentry *child); + +/* end_creating - finish action started with start_creating + * @child: dentry returned by start_creating() or vfs_mkdir() + * + * Unlock and release the child. This can be called after + * start_creating() whether that function succeeded or not, + * but it is not needed on failure. + * + * If vfs_mkdir() was called then the value returned from that function + * should be given for @child rather than the original dentry, as vfs_mkdir() + * may have provided a new dentry. + * + * + * If vfs_mkdir() was not called, then @child will be a valid dentry and + * @parent will be ignored. + */ +static inline void end_creating(struct dentry *child) +{ + end_dirop(child); +} + +/* end_creating_keep - finish action started with start_creating() and return result + * @child: dentry returned by start_creating() or vfs_mkdir() + * + * Unlock and return the child. This can be called after + * start_creating() whether that function succeeded or not, + * but it is not needed on failure. + * + * If vfs_mkdir() was called then the value returned from that function + * should be given for @child rather than the original dentry, as vfs_mkdir() + * may have provided a new dentry. + * + * Returns: @child, which may be a dentry or an error. + * + */ +static inline struct dentry *end_creating_keep(struct dentry *child) +{ + if (!IS_ERR(child)) + dget(child); + end_dirop(child); + return child; +} + +/** + * end_removing - finish action started with start_removing + * @child: dentry returned by start_removing() + * @parent: dentry given to start_removing() + * + * Unlock and release the child. + * + * This is identical to end_dirop(). It can be passed the result of + * start_removing() whether that was successful or not, but it not needed + * if start_removing() failed. + */ +static inline void end_removing(struct dentry *child) +{ + end_dirop(child); +} + extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); @@ -95,6 +171,13 @@ extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); +int start_renaming(struct renamedata *rd, int lookup_flags, + struct qstr *old_last, struct qstr *new_last); +int start_renaming_dentry(struct renamedata *rd, int lookup_flags, + struct dentry *old_dentry, struct qstr *new_last); +int start_renaming_two_dentries(struct renamedata *rd, + struct dentry *old_dentry, struct dentry *new_dentry); +void end_renaming(struct renamedata *rd); /** * mode_strip_umask - handle vfs umask stripping diff --git a/include/linux/net/intel/libie/fwlog.h b/include/linux/net/intel/libie/fwlog.h index 36b13fabca9e..7273c78c826b 100644 --- a/include/linux/net/intel/libie/fwlog.h +++ b/include/linux/net/intel/libie/fwlog.h @@ -78,8 +78,20 @@ struct libie_fwlog { ); }; +#if IS_ENABLED(CONFIG_LIBIE_FWLOG) int libie_fwlog_init(struct libie_fwlog *fwlog, struct libie_fwlog_api *api); void libie_fwlog_deinit(struct libie_fwlog *fwlog); void libie_fwlog_reregister(struct libie_fwlog *fwlog); void libie_get_fwlog_data(struct libie_fwlog *fwlog, u8 *buf, u16 len); +#else +static inline int libie_fwlog_init(struct libie_fwlog *fwlog, + struct libie_fwlog_api *api) +{ + return -EOPNOTSUPP; +} +static inline void libie_fwlog_deinit(struct libie_fwlog *fwlog) { } +static inline void libie_fwlog_reregister(struct libie_fwlog *fwlog) { } +static inline void libie_get_fwlog_data(struct libie_fwlog *fwlog, u8 *buf, + u16 len) { } +#endif /* CONFIG_LIBIE_FWLOG */ #endif /* _LIBIE_FWLOG_H_ */ diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index d56583572c98..31463286402f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -1659,6 +1659,7 @@ struct nfs_pgio_header { void *netfs; #endif + unsigned short retrans; int pnfs_error; int error; /* merge with pnfs_error */ unsigned int good_bytes; /* boundary of good data */ diff --git a/include/linux/ns/ns_common_types.h b/include/linux/ns/ns_common_types.h new file mode 100644 index 000000000000..b332b019b29c --- /dev/null +++ b/include/linux/ns/ns_common_types.h @@ -0,0 +1,196 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_NS_COMMON_TYPES_H +#define _LINUX_NS_COMMON_TYPES_H + +#include <linux/atomic.h> +#include <linux/ns/nstree_types.h> +#include <linux/rbtree.h> +#include <linux/refcount.h> +#include <linux/types.h> + +struct cgroup_namespace; +struct dentry; +struct ipc_namespace; +struct mnt_namespace; +struct net; +struct pid_namespace; +struct proc_ns_operations; +struct time_namespace; +struct user_namespace; +struct uts_namespace; + +extern struct cgroup_namespace init_cgroup_ns; +extern struct ipc_namespace init_ipc_ns; +extern struct mnt_namespace init_mnt_ns; +extern struct net init_net; +extern struct pid_namespace init_pid_ns; +extern struct time_namespace init_time_ns; +extern struct user_namespace init_user_ns; +extern struct uts_namespace init_uts_ns; + +extern const struct proc_ns_operations cgroupns_operations; +extern const struct proc_ns_operations ipcns_operations; +extern const struct proc_ns_operations mntns_operations; +extern const struct proc_ns_operations netns_operations; +extern const struct proc_ns_operations pidns_operations; +extern const struct proc_ns_operations pidns_for_children_operations; +extern const struct proc_ns_operations timens_operations; +extern const struct proc_ns_operations timens_for_children_operations; +extern const struct proc_ns_operations userns_operations; +extern const struct proc_ns_operations utsns_operations; + +/* + * Namespace lifetimes are managed via a two-tier reference counting model: + * + * (1) __ns_ref (refcount_t): Main reference count tracking memory + * lifetime. Controls when the namespace structure itself is freed. + * It also pins the namespace on the namespace trees whereas (2) + * only regulates their visibility to userspace. + * + * (2) __ns_ref_active (atomic_t): Reference count tracking active users. + * Controls visibility of the namespace in the namespace trees. + * Any live task that uses the namespace (via nsproxy or cred) holds + * an active reference. Any open file descriptor or bind-mount of + * the namespace holds an active reference. Once all tasks have + * called exited their namespaces and all file descriptors and + * bind-mounts have been released the active reference count drops + * to zero and the namespace becomes inactive. IOW, the namespace + * cannot be listed or opened via file handles anymore. + * + * Note that it is valid to transition from active to inactive and + * back from inactive to active e.g., when resurrecting an inactive + * namespace tree via the SIOCGSKNS ioctl(). + * + * Relationship and lifecycle states: + * + * - Active (__ns_ref_active > 0): + * Namespace is actively used and visible to userspace. The namespace + * can be reopened via /proc/<pid>/ns/<ns_type>, via namespace file + * handles, or discovered via listns(). + * + * - Inactive (__ns_ref_active == 0, __ns_ref > 0): + * No tasks are actively using the namespace and it isn't pinned by + * any bind-mounts or open file descriptors anymore. But the namespace + * is still kept alive by internal references. For example, the user + * namespace could be pinned by an open file through file->f_cred + * references when one of the now defunct tasks had opened a file and + * handed the file descriptor off to another process via a UNIX + * sockets. Such references keep the namespace structure alive through + * __ns_ref but will not hold an active reference. + * + * - Destroyed (__ns_ref == 0): + * No references remain. The namespace is removed from the tree and freed. + * + * State transitions: + * + * Active -> Inactive: + * When the last task using the namespace exits it drops its active + * references to all namespaces. However, user and pid namespaces + * remain accessible until the task has been reaped. + * + * Inactive -> Active: + * An inactive namespace tree might be resurrected due to e.g., the + * SIOCGSKNS ioctl() on a socket. + * + * Inactive -> Destroyed: + * When __ns_ref drops to zero the namespace is removed from the + * namespaces trees and the memory is freed (after RCU grace period). + * + * Initial namespaces: + * Boot-time namespaces (init_net, init_pid_ns, etc.) start with + * __ns_ref_active = 1 and remain active forever. + * + * @ns_type: type of namespace (e.g., CLONE_NEWNET) + * @stashed: cached dentry to be used by the vfs + * @ops: namespace operations + * @inum: namespace inode number (quickly recycled for non-initial namespaces) + * @__ns_ref: main reference count (do not use directly) + * @ns_tree: namespace tree nodes and active reference count + */ +struct ns_common { + u32 ns_type; + struct dentry *stashed; + const struct proc_ns_operations *ops; + unsigned int inum; + refcount_t __ns_ref; /* do not use directly */ + union { + struct ns_tree; + struct rcu_head ns_rcu; + }; +}; + +#define to_ns_common(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &(__ns)->ns, \ + const struct cgroup_namespace *: &(__ns)->ns, \ + struct ipc_namespace *: &(__ns)->ns, \ + const struct ipc_namespace *: &(__ns)->ns, \ + struct mnt_namespace *: &(__ns)->ns, \ + const struct mnt_namespace *: &(__ns)->ns, \ + struct net *: &(__ns)->ns, \ + const struct net *: &(__ns)->ns, \ + struct pid_namespace *: &(__ns)->ns, \ + const struct pid_namespace *: &(__ns)->ns, \ + struct time_namespace *: &(__ns)->ns, \ + const struct time_namespace *: &(__ns)->ns, \ + struct user_namespace *: &(__ns)->ns, \ + const struct user_namespace *: &(__ns)->ns, \ + struct uts_namespace *: &(__ns)->ns, \ + const struct uts_namespace *: &(__ns)->ns) + +#define ns_init_inum(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: CGROUP_NS_INIT_INO, \ + struct ipc_namespace *: IPC_NS_INIT_INO, \ + struct mnt_namespace *: MNT_NS_INIT_INO, \ + struct net *: NET_NS_INIT_INO, \ + struct pid_namespace *: PID_NS_INIT_INO, \ + struct time_namespace *: TIME_NS_INIT_INO, \ + struct user_namespace *: USER_NS_INIT_INO, \ + struct uts_namespace *: UTS_NS_INIT_INO) + +#define ns_init_ns(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: &init_cgroup_ns, \ + struct ipc_namespace *: &init_ipc_ns, \ + struct mnt_namespace *: &init_mnt_ns, \ + struct net *: &init_net, \ + struct pid_namespace *: &init_pid_ns, \ + struct time_namespace *: &init_time_ns, \ + struct user_namespace *: &init_user_ns, \ + struct uts_namespace *: &init_uts_ns) + +#define ns_init_id(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: CGROUP_NS_INIT_ID, \ + struct ipc_namespace *: IPC_NS_INIT_ID, \ + struct mnt_namespace *: MNT_NS_INIT_ID, \ + struct net *: NET_NS_INIT_ID, \ + struct pid_namespace *: PID_NS_INIT_ID, \ + struct time_namespace *: TIME_NS_INIT_ID, \ + struct user_namespace *: USER_NS_INIT_ID, \ + struct uts_namespace *: UTS_NS_INIT_ID) + +#define to_ns_operations(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: (IS_ENABLED(CONFIG_CGROUPS) ? &cgroupns_operations : NULL), \ + struct ipc_namespace *: (IS_ENABLED(CONFIG_IPC_NS) ? &ipcns_operations : NULL), \ + struct mnt_namespace *: &mntns_operations, \ + struct net *: (IS_ENABLED(CONFIG_NET_NS) ? &netns_operations : NULL), \ + struct pid_namespace *: (IS_ENABLED(CONFIG_PID_NS) ? &pidns_operations : NULL), \ + struct time_namespace *: (IS_ENABLED(CONFIG_TIME_NS) ? &timens_operations : NULL), \ + struct user_namespace *: (IS_ENABLED(CONFIG_USER_NS) ? &userns_operations : NULL), \ + struct uts_namespace *: (IS_ENABLED(CONFIG_UTS_NS) ? &utsns_operations : NULL)) + +#define ns_common_type(__ns) \ + _Generic((__ns), \ + struct cgroup_namespace *: CLONE_NEWCGROUP, \ + struct ipc_namespace *: CLONE_NEWIPC, \ + struct mnt_namespace *: CLONE_NEWNS, \ + struct net *: CLONE_NEWNET, \ + struct pid_namespace *: CLONE_NEWPID, \ + struct time_namespace *: CLONE_NEWTIME, \ + struct user_namespace *: CLONE_NEWUSER, \ + struct uts_namespace *: CLONE_NEWUTS) + +#endif /* _LINUX_NS_COMMON_TYPES_H */ diff --git a/include/linux/ns/nstree_types.h b/include/linux/ns/nstree_types.h new file mode 100644 index 000000000000..2fb28ee31efb --- /dev/null +++ b/include/linux/ns/nstree_types.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */ +#ifndef _LINUX_NSTREE_TYPES_H +#define _LINUX_NSTREE_TYPES_H + +#include <linux/rbtree.h> +#include <linux/list.h> + +/** + * struct ns_tree_root - Root of a namespace tree + * @ns_rb: Red-black tree root for efficient lookups + * @ns_list_head: List head for sequential iteration + * + * Each namespace tree maintains both an rbtree (for O(log n) lookups) + * and a list (for efficient sequential iteration). The list is kept in + * the same sorted order as the rbtree. + */ +struct ns_tree_root { + struct rb_root ns_rb; + struct list_head ns_list_head; +}; + +/** + * struct ns_tree_node - Node in a namespace tree + * @ns_node: Red-black tree node + * @ns_list_entry: List entry for sequential iteration + * + * Represents a namespace's position in a tree. Each namespace has + * multiple tree nodes for different trees (unified, per-type, owner). + */ +struct ns_tree_node { + struct rb_node ns_node; + struct list_head ns_list_entry; +}; + +/** + * struct ns_tree - Namespace tree nodes and active reference count + * @ns_id: Unique namespace identifier + * @__ns_ref_active: Active reference count (do not use directly) + * @ns_unified_node: Node in the global namespace tree + * @ns_tree_node: Node in the per-type namespace tree + * @ns_owner_node: Node in the owner namespace's tree of owned namespaces + * @ns_owner_root: Root of the tree of namespaces owned by this namespace + * (only used when this namespace is an owner) + */ +struct ns_tree { + u64 ns_id; + atomic_t __ns_ref_active; + struct ns_tree_node ns_unified_node; + struct ns_tree_node ns_tree_node; + struct ns_tree_node ns_owner_node; + struct ns_tree_root ns_owner_root; +}; + +#endif /* _LINUX_NSTREE_TYPES_H */ diff --git a/include/linux/ns_common.h b/include/linux/ns_common.h index f5b68b8abb54..825f5865bfc5 100644 --- a/include/linux/ns_common.h +++ b/include/linux/ns_common.h @@ -2,122 +2,44 @@ #ifndef _LINUX_NS_COMMON_H #define _LINUX_NS_COMMON_H +#include <linux/ns/ns_common_types.h> #include <linux/refcount.h> -#include <linux/rbtree.h> +#include <linux/vfsdebug.h> #include <uapi/linux/sched.h> +#include <uapi/linux/nsfs.h> -struct proc_ns_operations; - -struct cgroup_namespace; -struct ipc_namespace; -struct mnt_namespace; -struct net; -struct pid_namespace; -struct time_namespace; -struct user_namespace; -struct uts_namespace; - -extern struct cgroup_namespace init_cgroup_ns; -extern struct ipc_namespace init_ipc_ns; -extern struct mnt_namespace init_mnt_ns; -extern struct net init_net; -extern struct pid_namespace init_pid_ns; -extern struct time_namespace init_time_ns; -extern struct user_namespace init_user_ns; -extern struct uts_namespace init_uts_ns; - -extern const struct proc_ns_operations netns_operations; -extern const struct proc_ns_operations utsns_operations; -extern const struct proc_ns_operations ipcns_operations; -extern const struct proc_ns_operations pidns_operations; -extern const struct proc_ns_operations pidns_for_children_operations; -extern const struct proc_ns_operations userns_operations; -extern const struct proc_ns_operations mntns_operations; -extern const struct proc_ns_operations cgroupns_operations; -extern const struct proc_ns_operations timens_operations; -extern const struct proc_ns_operations timens_for_children_operations; - -struct ns_common { - u32 ns_type; - struct dentry *stashed; - const struct proc_ns_operations *ops; - unsigned int inum; - refcount_t __ns_ref; /* do not use directly */ - union { - struct { - u64 ns_id; - struct rb_node ns_tree_node; - struct list_head ns_list_node; - }; - struct rcu_head ns_rcu; - }; -}; - +bool is_current_namespace(struct ns_common *ns); int __ns_common_init(struct ns_common *ns, u32 ns_type, const struct proc_ns_operations *ops, int inum); void __ns_common_free(struct ns_common *ns); +struct ns_common *__must_check ns_owner(struct ns_common *ns); + +static __always_inline bool is_ns_init_inum(const struct ns_common *ns) +{ + VFS_WARN_ON_ONCE(ns->inum == 0); + return unlikely(in_range(ns->inum, MNT_NS_INIT_INO, + IPC_NS_INIT_INO - MNT_NS_INIT_INO + 1)); +} + +static __always_inline bool is_ns_init_id(const struct ns_common *ns) +{ + VFS_WARN_ON_ONCE(ns->ns_id == 0); + return ns->ns_id <= NS_LAST_INIT_ID; +} -#define to_ns_common(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: &(__ns)->ns, \ - const struct cgroup_namespace *: &(__ns)->ns, \ - struct ipc_namespace *: &(__ns)->ns, \ - const struct ipc_namespace *: &(__ns)->ns, \ - struct mnt_namespace *: &(__ns)->ns, \ - const struct mnt_namespace *: &(__ns)->ns, \ - struct net *: &(__ns)->ns, \ - const struct net *: &(__ns)->ns, \ - struct pid_namespace *: &(__ns)->ns, \ - const struct pid_namespace *: &(__ns)->ns, \ - struct time_namespace *: &(__ns)->ns, \ - const struct time_namespace *: &(__ns)->ns, \ - struct user_namespace *: &(__ns)->ns, \ - const struct user_namespace *: &(__ns)->ns, \ - struct uts_namespace *: &(__ns)->ns, \ - const struct uts_namespace *: &(__ns)->ns) - -#define ns_init_inum(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: CGROUP_NS_INIT_INO, \ - struct ipc_namespace *: IPC_NS_INIT_INO, \ - struct mnt_namespace *: MNT_NS_INIT_INO, \ - struct net *: NET_NS_INIT_INO, \ - struct pid_namespace *: PID_NS_INIT_INO, \ - struct time_namespace *: TIME_NS_INIT_INO, \ - struct user_namespace *: USER_NS_INIT_INO, \ - struct uts_namespace *: UTS_NS_INIT_INO) - -#define ns_init_ns(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: &init_cgroup_ns, \ - struct ipc_namespace *: &init_ipc_ns, \ - struct mnt_namespace *: &init_mnt_ns, \ - struct net *: &init_net, \ - struct pid_namespace *: &init_pid_ns, \ - struct time_namespace *: &init_time_ns, \ - struct user_namespace *: &init_user_ns, \ - struct uts_namespace *: &init_uts_ns) - -#define to_ns_operations(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: (IS_ENABLED(CONFIG_CGROUPS) ? &cgroupns_operations : NULL), \ - struct ipc_namespace *: (IS_ENABLED(CONFIG_IPC_NS) ? &ipcns_operations : NULL), \ - struct mnt_namespace *: &mntns_operations, \ - struct net *: (IS_ENABLED(CONFIG_NET_NS) ? &netns_operations : NULL), \ - struct pid_namespace *: (IS_ENABLED(CONFIG_PID_NS) ? &pidns_operations : NULL), \ - struct time_namespace *: (IS_ENABLED(CONFIG_TIME_NS) ? &timens_operations : NULL), \ - struct user_namespace *: (IS_ENABLED(CONFIG_USER_NS) ? &userns_operations : NULL), \ - struct uts_namespace *: (IS_ENABLED(CONFIG_UTS_NS) ? &utsns_operations : NULL)) - -#define ns_common_type(__ns) \ - _Generic((__ns), \ - struct cgroup_namespace *: CLONE_NEWCGROUP, \ - struct ipc_namespace *: CLONE_NEWIPC, \ - struct mnt_namespace *: CLONE_NEWNS, \ - struct net *: CLONE_NEWNET, \ - struct pid_namespace *: CLONE_NEWPID, \ - struct time_namespace *: CLONE_NEWTIME, \ - struct user_namespace *: CLONE_NEWUSER, \ - struct uts_namespace *: CLONE_NEWUTS) +#define NS_COMMON_INIT(nsname) \ +{ \ + .ns_type = ns_common_type(&nsname), \ + .ns_id = ns_init_id(&nsname), \ + .inum = ns_init_inum(&nsname), \ + .ops = to_ns_operations(&nsname), \ + .stashed = NULL, \ + .__ns_ref = REFCOUNT_INIT(1), \ + .__ns_ref_active = ATOMIC_INIT(1), \ + .ns_unified_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_unified_node.ns_list_entry), \ + .ns_tree_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_tree_node.ns_list_entry), \ + .ns_owner_node.ns_list_entry = LIST_HEAD_INIT(nsname.ns.ns_owner_node.ns_list_entry), \ + .ns_owner_root.ns_list_head = LIST_HEAD_INIT(nsname.ns.ns_owner_root.ns_list_head), \ +} #define ns_common_init(__ns) \ __ns_common_init(to_ns_common(__ns), \ @@ -133,21 +55,96 @@ void __ns_common_free(struct ns_common *ns); #define ns_common_free(__ns) __ns_common_free(to_ns_common((__ns))) +static __always_inline __must_check int __ns_ref_active_read(const struct ns_common *ns) +{ + return atomic_read(&ns->__ns_ref_active); +} + +static __always_inline __must_check int __ns_ref_read(const struct ns_common *ns) +{ + return refcount_read(&ns->__ns_ref); +} + static __always_inline __must_check bool __ns_ref_put(struct ns_common *ns) { - return refcount_dec_and_test(&ns->__ns_ref); + if (is_ns_init_id(ns)) { + VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); + return false; + } + if (refcount_dec_and_test(&ns->__ns_ref)) { + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns)); + return true; + } + return false; } static __always_inline __must_check bool __ns_ref_get(struct ns_common *ns) { - return refcount_inc_not_zero(&ns->__ns_ref); + if (is_ns_init_id(ns)) { + VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); + return true; + } + if (refcount_inc_not_zero(&ns->__ns_ref)) + return true; + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns)); + return false; } -#define ns_ref_read(__ns) refcount_read(&to_ns_common((__ns))->__ns_ref) -#define ns_ref_inc(__ns) refcount_inc(&to_ns_common((__ns))->__ns_ref) -#define ns_ref_get(__ns) __ns_ref_get(to_ns_common((__ns))) -#define ns_ref_put(__ns) __ns_ref_put(to_ns_common((__ns))) -#define ns_ref_put_and_lock(__ns, __lock) \ - refcount_dec_and_lock(&to_ns_common((__ns))->__ns_ref, (__lock)) +static __always_inline void __ns_ref_inc(struct ns_common *ns) +{ + if (is_ns_init_id(ns)) { + VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); + return; + } + refcount_inc(&ns->__ns_ref); +} + +static __always_inline __must_check bool __ns_ref_dec_and_lock(struct ns_common *ns, + spinlock_t *ns_lock) +{ + if (is_ns_init_id(ns)) { + VFS_WARN_ON_ONCE(__ns_ref_read(ns) != 1); + VFS_WARN_ON_ONCE(__ns_ref_active_read(ns) != 1); + return false; + } + return refcount_dec_and_lock(&ns->__ns_ref, ns_lock); +} + +#define ns_ref_read(__ns) __ns_ref_read(to_ns_common((__ns))) +#define ns_ref_inc(__ns) \ + do { if (__ns) __ns_ref_inc(to_ns_common((__ns))); } while (0) +#define ns_ref_get(__ns) \ + ((__ns) ? __ns_ref_get(to_ns_common((__ns))) : false) +#define ns_ref_put(__ns) \ + ((__ns) ? __ns_ref_put(to_ns_common((__ns))) : false) +#define ns_ref_put_and_lock(__ns, __ns_lock) \ + ((__ns) ? __ns_ref_dec_and_lock(to_ns_common((__ns)), __ns_lock) : false) + +#define ns_ref_active_read(__ns) \ + ((__ns) ? __ns_ref_active_read(to_ns_common(__ns)) : 0) + +void __ns_ref_active_put(struct ns_common *ns); + +#define ns_ref_active_put(__ns) \ + do { if (__ns) __ns_ref_active_put(to_ns_common(__ns)); } while (0) + +static __always_inline struct ns_common *__must_check ns_get_unless_inactive(struct ns_common *ns) +{ + if (!__ns_ref_active_read(ns)) { + VFS_WARN_ON_ONCE(is_ns_init_id(ns)); + return NULL; + } + if (!__ns_ref_get(ns)) + return NULL; + return ns; +} + +void __ns_ref_active_get(struct ns_common *ns); + +#define ns_ref_active_get(__ns) \ + do { if (__ns) __ns_ref_active_get(to_ns_common(__ns)); } while (0) #endif diff --git a/include/linux/nsfs.h b/include/linux/nsfs.h index e5a5fa83d36b..731b67fc2fec 100644 --- a/include/linux/nsfs.h +++ b/include/linux/nsfs.h @@ -37,4 +37,7 @@ void nsfs_init(void); #define current_in_namespace(__ns) (__current_namespace_from_type(__ns) == __ns) +void nsproxy_ns_active_get(struct nsproxy *ns); +void nsproxy_ns_active_put(struct nsproxy *ns); + #endif /* _LINUX_NSFS_H */ diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h index bd118a187dec..5a67648721c7 100644 --- a/include/linux/nsproxy.h +++ b/include/linux/nsproxy.h @@ -93,10 +93,13 @@ static inline struct cred *nsset_cred(struct nsset *set) */ int copy_namespaces(u64 flags, struct task_struct *tsk); -void exit_task_namespaces(struct task_struct *tsk); +void switch_cred_namespaces(const struct cred *old, const struct cred *new); +void exit_nsproxy_namespaces(struct task_struct *tsk); +void get_cred_namespaces(struct task_struct *tsk); +void exit_cred_namespaces(struct task_struct *tsk); void switch_task_namespaces(struct task_struct *tsk, struct nsproxy *new); int exec_task_namespaces(void); -void free_nsproxy(struct nsproxy *ns); +void deactivate_nsproxy(struct nsproxy *ns); int unshare_nsproxy_namespaces(unsigned long, struct nsproxy **, struct cred *, struct fs_struct *); int __init nsproxy_cache_init(void); @@ -104,7 +107,7 @@ int __init nsproxy_cache_init(void); static inline void put_nsproxy(struct nsproxy *ns) { if (refcount_dec_and_test(&ns->count)) - free_nsproxy(ns); + deactivate_nsproxy(ns); } static inline void get_nsproxy(struct nsproxy *ns) diff --git a/include/linux/nstree.h b/include/linux/nstree.h index 8b8636690473..175e4625bfa6 100644 --- a/include/linux/nstree.h +++ b/include/linux/nstree.h @@ -1,22 +1,34 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2025 Christian Brauner <brauner@kernel.org> */ #ifndef _LINUX_NSTREE_H #define _LINUX_NSTREE_H -#include <linux/ns_common.h> +#include <linux/ns/nstree_types.h> #include <linux/nsproxy.h> #include <linux/rbtree.h> #include <linux/seqlock.h> #include <linux/rculist.h> #include <linux/cookie.h> +#include <uapi/linux/nsfs.h> -extern struct ns_tree cgroup_ns_tree; -extern struct ns_tree ipc_ns_tree; -extern struct ns_tree mnt_ns_tree; -extern struct ns_tree net_ns_tree; -extern struct ns_tree pid_ns_tree; -extern struct ns_tree time_ns_tree; -extern struct ns_tree user_ns_tree; -extern struct ns_tree uts_ns_tree; +struct ns_common; + +extern struct ns_tree_root cgroup_ns_tree; +extern struct ns_tree_root ipc_ns_tree; +extern struct ns_tree_root mnt_ns_tree; +extern struct ns_tree_root net_ns_tree; +extern struct ns_tree_root pid_ns_tree; +extern struct ns_tree_root time_ns_tree; +extern struct ns_tree_root user_ns_tree; +extern struct ns_tree_root uts_ns_tree; + +void ns_tree_node_init(struct ns_tree_node *node); +void ns_tree_root_init(struct ns_tree_root *root); +bool ns_tree_node_empty(const struct ns_tree_node *node); +struct rb_node *ns_tree_node_add(struct ns_tree_node *node, + struct ns_tree_root *root, + int (*cmp)(struct rb_node *, const struct rb_node *)); +void ns_tree_node_del(struct ns_tree_node *node, struct ns_tree_root *root); #define to_ns_tree(__ns) \ _Generic((__ns), \ @@ -29,17 +41,21 @@ extern struct ns_tree uts_ns_tree; struct user_namespace *: &(user_ns_tree), \ struct uts_namespace *: &(uts_ns_tree)) -u64 ns_tree_gen_id(struct ns_common *ns); -void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree *ns_tree); -void __ns_tree_remove(struct ns_common *ns, struct ns_tree *ns_tree); +#define ns_tree_gen_id(__ns) \ + __ns_tree_gen_id(to_ns_common(__ns), \ + (((__ns) == ns_init_ns(__ns)) ? ns_init_id(__ns) : 0)) + +u64 __ns_tree_gen_id(struct ns_common *ns, u64 id); +void __ns_tree_add_raw(struct ns_common *ns, struct ns_tree_root *ns_tree); +void __ns_tree_remove(struct ns_common *ns, struct ns_tree_root *ns_tree); struct ns_common *ns_tree_lookup_rcu(u64 ns_id, int ns_type); struct ns_common *__ns_tree_adjoined_rcu(struct ns_common *ns, - struct ns_tree *ns_tree, + struct ns_tree_root *ns_tree, bool previous); -static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree) +static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree_root *ns_tree, u64 id) { - ns_tree_gen_id(ns); + __ns_tree_gen_id(ns, id); __ns_tree_add_raw(ns, ns_tree); } @@ -59,7 +75,9 @@ static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree) * This function assigns a new id to the namespace and adds it to the * appropriate namespace tree and list. */ -#define ns_tree_add(__ns) __ns_tree_add(to_ns_common(__ns), to_ns_tree(__ns)) +#define ns_tree_add(__ns) \ + __ns_tree_add(to_ns_common(__ns), to_ns_tree(__ns), \ + (((__ns) == ns_init_ns(__ns)) ? ns_init_id(__ns) : 0)) /** * ns_tree_remove - Remove a namespace from a namespace tree @@ -73,6 +91,6 @@ static inline void __ns_tree_add(struct ns_common *ns, struct ns_tree *ns_tree) #define ns_tree_adjoined_rcu(__ns, __previous) \ __ns_tree_adjoined_rcu(to_ns_common(__ns), to_ns_tree(__ns), __previous) -#define ns_tree_active(__ns) (!RB_EMPTY_NODE(&to_ns_common(__ns)->ns_tree_node)) +#define ns_tree_active(__ns) (!RB_EMPTY_NODE(&to_ns_common(__ns)->ns_tree_node.ns_node)) #endif /* _LINUX_NSTREE_H */ diff --git a/include/linux/objtool.h b/include/linux/objtool.h index 46ebaa46e6c5..b18ab53561c9 100644 --- a/include/linux/objtool.h +++ b/include/linux/objtool.h @@ -3,16 +3,16 @@ #define _LINUX_OBJTOOL_H #include <linux/objtool_types.h> +#include <linux/annotate.h> #ifdef CONFIG_OBJTOOL -#include <asm/asm.h> - #ifndef __ASSEMBLY__ -#define UNWIND_HINT(type, sp_reg, sp_offset, signal) \ +#define UNWIND_HINT(type, sp_reg, sp_offset, signal) \ "987: \n\t" \ ".pushsection .discard.unwind_hints\n\t" \ + ANNOTATE_DATA_SPECIAL \ /* struct unwind_hint */ \ ".long 987b - .\n\t" \ ".short " __stringify(sp_offset) "\n\t" \ @@ -53,16 +53,6 @@ #define __ASM_BREF(label) label ## b -#define __ASM_ANNOTATE(label, type) \ - ".pushsection .discard.annotate_insn,\"M\",@progbits,8\n\t" \ - ".long " __stringify(label) " - .\n\t" \ - ".long " __stringify(type) "\n\t" \ - ".popsection\n\t" - -#define ASM_ANNOTATE(type) \ - "911:\n\t" \ - __ASM_ANNOTATE(911b, type) - #else /* __ASSEMBLY__ */ /* @@ -89,6 +79,7 @@ .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .Lhere_\@: .pushsection .discard.unwind_hints + ANNOTATE_DATA_SPECIAL /* struct unwind_hint */ .long .Lhere_\@ - . .short \sp_offset @@ -101,7 +92,7 @@ .macro STACK_FRAME_NON_STANDARD func:req .pushsection .discard.func_stack_frame_non_standard, "aw" - .long \func - . + .quad \func .popsection .endm @@ -111,14 +102,6 @@ #endif .endm -.macro ANNOTATE type:req -.Lhere_\@: - .pushsection .discard.annotate_insn,"M",@progbits,8 - .long .Lhere_\@ - . - .long \type - .popsection -.endm - #endif /* __ASSEMBLY__ */ #else /* !CONFIG_OBJTOOL */ @@ -128,84 +111,15 @@ #define UNWIND_HINT(type, sp_reg, sp_offset, signal) "\n\t" #define STACK_FRAME_NON_STANDARD(func) #define STACK_FRAME_NON_STANDARD_FP(func) -#define __ASM_ANNOTATE(label, type) "" -#define ASM_ANNOTATE(type) #else .macro UNWIND_HINT type:req sp_reg=0 sp_offset=0 signal=0 .endm .macro STACK_FRAME_NON_STANDARD func:req .endm -.macro ANNOTATE type:req -.endm #endif #endif /* CONFIG_OBJTOOL */ -#ifndef __ASSEMBLY__ -/* - * Annotate away the various 'relocation to !ENDBR` complaints; knowing that - * these relocations will never be used for indirect calls. - */ -#define ANNOTATE_NOENDBR ASM_ANNOTATE(ANNOTYPE_NOENDBR) -#define ANNOTATE_NOENDBR_SYM(sym) asm(__ASM_ANNOTATE(sym, ANNOTYPE_NOENDBR)) - -/* - * This should be used immediately before an indirect jump/call. It tells - * objtool the subsequent indirect jump/call is vouched safe for retpoline - * builds. - */ -#define ANNOTATE_RETPOLINE_SAFE ASM_ANNOTATE(ANNOTYPE_RETPOLINE_SAFE) -/* - * See linux/instrumentation.h - */ -#define ANNOTATE_INSTR_BEGIN(label) __ASM_ANNOTATE(label, ANNOTYPE_INSTR_BEGIN) -#define ANNOTATE_INSTR_END(label) __ASM_ANNOTATE(label, ANNOTYPE_INSTR_END) -/* - * objtool annotation to ignore the alternatives and only consider the original - * instruction(s). - */ -#define ANNOTATE_IGNORE_ALTERNATIVE ASM_ANNOTATE(ANNOTYPE_IGNORE_ALTS) -/* - * This macro indicates that the following intra-function call is valid. - * Any non-annotated intra-function call will cause objtool to issue a warning. - */ -#define ANNOTATE_INTRA_FUNCTION_CALL ASM_ANNOTATE(ANNOTYPE_INTRA_FUNCTION_CALL) -/* - * Use objtool to validate the entry requirement that all code paths do - * VALIDATE_UNRET_END before RET. - * - * NOTE: The macro must be used at the beginning of a global symbol, otherwise - * it will be ignored. - */ -#define ANNOTATE_UNRET_BEGIN ASM_ANNOTATE(ANNOTYPE_UNRET_BEGIN) -/* - * This should be used to refer to an instruction that is considered - * terminating, like a noreturn CALL or UD2 when we know they are not -- eg - * WARN using UD2. - */ -#define ANNOTATE_REACHABLE(label) __ASM_ANNOTATE(label, ANNOTYPE_REACHABLE) -/* - * This should not be used; it annotates away CFI violations. There are a few - * valid use cases like kexec handover to the next kernel image, and there is - * no security concern there. - * - * There are also a few real issues annotated away, like EFI because we can't - * control the EFI code. - */ -#define ANNOTATE_NOCFI_SYM(sym) asm(__ASM_ANNOTATE(sym, ANNOTYPE_NOCFI)) - -#else -#define ANNOTATE_NOENDBR ANNOTATE type=ANNOTYPE_NOENDBR -#define ANNOTATE_RETPOLINE_SAFE ANNOTATE type=ANNOTYPE_RETPOLINE_SAFE -/* ANNOTATE_INSTR_BEGIN ANNOTATE type=ANNOTYPE_INSTR_BEGIN */ -/* ANNOTATE_INSTR_END ANNOTATE type=ANNOTYPE_INSTR_END */ -#define ANNOTATE_IGNORE_ALTERNATIVE ANNOTATE type=ANNOTYPE_IGNORE_ALTS -#define ANNOTATE_INTRA_FUNCTION_CALL ANNOTATE type=ANNOTYPE_INTRA_FUNCTION_CALL -#define ANNOTATE_UNRET_BEGIN ANNOTATE type=ANNOTYPE_UNRET_BEGIN -#define ANNOTATE_REACHABLE ANNOTATE type=ANNOTYPE_REACHABLE -#define ANNOTATE_NOCFI_SYM ANNOTATE type=ANNOTYPE_NOCFI -#endif - #if defined(CONFIG_NOINSTR_VALIDATION) && \ (defined(CONFIG_MITIGATION_UNRET_ENTRY) || defined(CONFIG_MITIGATION_SRSO)) #define VALIDATE_UNRET_BEGIN ANNOTATE_UNRET_BEGIN diff --git a/include/linux/objtool_types.h b/include/linux/objtool_types.h index aceac94632c8..c6def4049b1a 100644 --- a/include/linux/objtool_types.h +++ b/include/linux/objtool_types.h @@ -67,4 +67,6 @@ struct unwind_hint { #define ANNOTYPE_REACHABLE 8 #define ANNOTYPE_NOCFI 9 +#define ANNOTYPE_DATA_SPECIAL 1 + #endif /* _LINUX_OBJTOOL_TYPES_H */ diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h index 1db8543dfc8a..1c2bc0281807 100644 --- a/include/linux/of_irq.h +++ b/include/linux/of_irq.h @@ -43,6 +43,8 @@ extern int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_args *out_irq); extern int of_irq_count(struct device_node *dev); extern int of_irq_get(struct device_node *dev, int index); +extern const struct cpumask *of_irq_get_affinity(struct device_node *dev, + int index); extern int of_irq_get_byname(struct device_node *dev, const char *name); extern int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs); @@ -76,6 +78,11 @@ static inline int of_irq_get_byname(struct device_node *dev, const char *name) { return 0; } +static inline const struct cpumask *of_irq_get_affinity(struct device_node *dev, + int index) +{ + return NULL; +} static inline int of_irq_to_resource_table(struct device_node *dev, struct resource *res, int nr_irqs) { diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h index 09b581c1d878..e601a3144f28 100644 --- a/include/linux/pagemap.h +++ b/include/linux/pagemap.h @@ -38,6 +38,7 @@ int filemap_invalidate_pages(struct address_space *mapping, int write_inode_now(struct inode *, int sync); int filemap_fdatawrite(struct address_space *); int filemap_flush(struct address_space *); +int filemap_flush_nr(struct address_space *mapping, long *nr_to_write); int filemap_fdatawait_keep_errors(struct address_space *mapping); int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); int filemap_fdatawait_range_keep_errors(struct address_space *mapping, @@ -53,14 +54,10 @@ static inline int filemap_fdatawait(struct address_space *mapping) bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); -int __filemap_fdatawrite_range(struct address_space *mapping, - loff_t start, loff_t end, int sync_mode); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); int filemap_check_errors(struct address_space *mapping); void __filemap_set_wb_err(struct address_space *mapping, int err); -int filemap_fdatawrite_wbc(struct address_space *mapping, - struct writeback_control *wbc); int kiocb_write_and_wait(struct kiocb *iocb, size_t count); static inline int filemap_write_and_wait(struct address_space *mapping) @@ -942,6 +939,17 @@ static inline pgoff_t folio_next_index(const struct folio *folio) } /** + * folio_next_pos - Get the file position of the next folio. + * @folio: The current folio. + * + * Return: The position of the folio which follows this folio in the file. + */ +static inline loff_t folio_next_pos(const struct folio *folio) +{ + return (loff_t)folio_next_index(folio) << PAGE_SHIFT; +} + +/** * folio_file_page - The page for a particular index. * @folio: The folio which contains this index. * @index: The index we want to look up. @@ -977,6 +985,8 @@ unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch); +unsigned filemap_get_folios_dirty(struct address_space *mapping, + pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); struct folio *read_cache_folio(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); diff --git a/include/linux/pci.h b/include/linux/pci.h index d1fdf81fbe1e..bf97d49c23cf 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -412,6 +412,8 @@ struct pci_dev { u16 l1ss; /* L1SS Capability pointer */ #ifdef CONFIG_PCIEASPM struct pcie_link_state *link_state; /* ASPM link state */ + unsigned int aspm_l0s_support:1; /* ASPM L0s support */ + unsigned int aspm_l1_support:1; /* ASPM L1 support */ unsigned int ltr_path:1; /* Latency Tolerance Reporting supported from root to here */ #endif diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h index 93c9a26492fc..bab26a7d79f4 100644 --- a/include/linux/perf/arm_pmu.h +++ b/include/linux/perf/arm_pmu.h @@ -132,8 +132,6 @@ struct arm_pmu { #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu)) -DECLARE_PER_CPU(struct arm_pmu *, cpu_armpmu); - u64 armpmu_event_update(struct perf_event *event); int armpmu_event_set_period(struct perf_event *event); @@ -190,8 +188,8 @@ bool arm_pmu_irq_is_nmi(void); struct arm_pmu *armpmu_alloc(void); void armpmu_free(struct arm_pmu *pmu); int armpmu_register(struct arm_pmu *pmu); -int armpmu_request_irq(int irq, int cpu); -void armpmu_free_irq(int irq, int cpu); +int armpmu_request_irq(struct arm_pmu * __percpu *armpmu, int irq, int cpu); +void armpmu_free_irq(struct arm_pmu * __percpu *armpmu, int irq, int cpu); #define ARMV8_PMU_PDEV_NAME "armv8-pmu" diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h index fd1d91017b99..9870d768db4c 100644 --- a/include/linux/perf_event.h +++ b/include/linux/perf_event.h @@ -1720,7 +1720,7 @@ extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct p extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs); extern struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, bool kernel, bool user, - u32 max_stack, bool crosstask, bool add_mark); + u32 max_stack, bool crosstask, bool add_mark, u64 defer_cookie); extern int get_callchain_buffers(int max_stack); extern void put_callchain_buffers(void); extern struct perf_callchain_entry *get_callchain_entry(int *rctx); diff --git a/include/linux/pid_namespace.h b/include/linux/pid_namespace.h index 445517a72ad0..0e7ae12c96d2 100644 --- a/include/linux/pid_namespace.h +++ b/include/linux/pid_namespace.h @@ -61,8 +61,7 @@ static inline struct pid_namespace *to_pid_ns(struct ns_common *ns) static inline struct pid_namespace *get_pid_ns(struct pid_namespace *ns) { - if (ns != &init_pid_ns) - ns_ref_inc(ns); + ns_ref_inc(ns); return ns; } diff --git a/include/linux/pipe_fs_i.h b/include/linux/pipe_fs_i.h index 9d42d473d201..7f6a92ac9704 100644 --- a/include/linux/pipe_fs_i.h +++ b/include/linux/pipe_fs_i.h @@ -44,11 +44,11 @@ typedef unsigned int pipe_index_t; typedef unsigned short pipe_index_t; #endif -/* - * We have to declare this outside 'struct pipe_inode_info', - * but then we can't use 'union pipe_index' for an anonymous - * union, so we end up having to duplicate this declaration - * below. Annoying. +/** + * struct pipe_index - pipe indeces + * @head: The point of buffer production + * @tail: The point of buffer consumption + * @head_tail: unsigned long union of @head and @tail */ union pipe_index { unsigned long head_tail; @@ -63,9 +63,7 @@ union pipe_index { * @mutex: mutex protecting the whole thing * @rd_wait: reader wait point in case of empty pipe * @wr_wait: writer wait point in case of full pipe - * @head: The point of buffer production - * @tail: The point of buffer consumption - * @head_tail: unsigned long union of @head and @tail + * @pipe_index: the pipe indeces * @note_loss: The next read() should insert a data-lost message * @max_usage: The maximum number of slots that may be used in the ring * @ring_size: total number of buffers (should be a power of 2) @@ -87,14 +85,7 @@ struct pipe_inode_info { struct mutex mutex; wait_queue_head_t rd_wait, wr_wait; - /* This has to match the 'union pipe_index' above */ - union { - unsigned long head_tail; - struct { - pipe_index_t head; - pipe_index_t tail; - }; - }; + union pipe_index; unsigned int max_usage; unsigned int ring_size; diff --git a/include/linux/platform_data/x86/int3472.h b/include/linux/platform_data/x86/int3472.h index 1571e9157fa5..b1b837583d54 100644 --- a/include/linux/platform_data/x86/int3472.h +++ b/include/linux/platform_data/x86/int3472.h @@ -100,7 +100,6 @@ struct int3472_gpio_regulator { struct regulator_consumer_supply supply_map[GPIO_REGULATOR_SUPPLY_MAP_COUNT * 2]; char supply_name_upper[GPIO_SUPPLY_NAME_LENGTH]; char regulator_name[GPIO_REGULATOR_NAME_LENGTH]; - struct gpio_desc *ena_gpio; struct regulator_dev *rdev; struct regulator_desc rdesc; }; diff --git a/include/linux/platform_device.h b/include/linux/platform_device.h index 074754c23d33..ad66333ce85c 100644 --- a/include/linux/platform_device.h +++ b/include/linux/platform_device.h @@ -102,6 +102,8 @@ devm_platform_ioremap_resource_byname(struct platform_device *pdev, extern int platform_get_irq(struct platform_device *, unsigned int); extern int platform_get_irq_optional(struct platform_device *, unsigned int); +extern int platform_get_irq_affinity(struct platform_device *, unsigned int, + const struct cpumask **); extern int platform_irq_count(struct platform_device *); extern int devm_platform_get_irqs_affinity(struct platform_device *dev, struct irq_affinity *affd, diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h index a3f44f6c2da1..0b436e15f4cd 100644 --- a/include/linux/pm_runtime.h +++ b/include/linux/pm_runtime.h @@ -629,13 +629,13 @@ DEFINE_GUARD(pm_runtime_active_auto, struct device *, * device. */ DEFINE_GUARD_COND(pm_runtime_active, _try, - pm_runtime_get_active(_T, RPM_TRANSPARENT)) + pm_runtime_get_active(_T, RPM_TRANSPARENT), _RET == 0) DEFINE_GUARD_COND(pm_runtime_active, _try_enabled, - pm_runtime_resume_and_get(_T)) + pm_runtime_resume_and_get(_T), _RET == 0) DEFINE_GUARD_COND(pm_runtime_active_auto, _try, - pm_runtime_get_active(_T, RPM_TRANSPARENT)) + pm_runtime_get_active(_T, RPM_TRANSPARENT), _RET == 0) DEFINE_GUARD_COND(pm_runtime_active_auto, _try_enabled, - pm_runtime_resume_and_get(_T)) + pm_runtime_resume_and_get(_T), _RET == 0) /** * pm_runtime_put_sync - Drop device usage counter and run "idle check" if 0. diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 102202185d7a..d964f965c8ff 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -134,11 +134,9 @@ static __always_inline unsigned char interrupt_context_level(void) /* * The following macros are deprecated and should not be used in new code: - * in_irq() - Obsolete version of in_hardirq() * in_softirq() - We have BH disabled, or are processing softirqs * in_interrupt() - We're in NMI,IRQ,SoftIRQ context or have BH disabled */ -#define in_irq() (hardirq_count()) #define in_softirq() (softirq_count()) #define in_interrupt() (irq_count()) diff --git a/include/linux/prmt.h b/include/linux/prmt.h index c53ab287e932..8cdc987de963 100644 --- a/include/linux/prmt.h +++ b/include/linux/prmt.h @@ -4,9 +4,11 @@ #ifdef CONFIG_ACPI_PRMT void init_prmt(void); +bool acpi_prm_handler_available(const guid_t *handler_guid); int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer); #else static inline void init_prmt(void) { } +static inline bool acpi_prm_handler_available(const guid_t *handler_guid) { return false; } static inline int acpi_call_prm_handler(guid_t handler_guid, void *param_buffer) { return -EOPNOTSUPP; diff --git a/include/linux/pseudo_fs.h b/include/linux/pseudo_fs.h index 2503f7625d65..a651e60d9410 100644 --- a/include/linux/pseudo_fs.h +++ b/include/linux/pseudo_fs.h @@ -9,6 +9,7 @@ struct pseudo_fs_context { const struct xattr_handler * const *xattr; const struct dentry_operations *dops; unsigned long magic; + unsigned int s_d_flags; }; struct pseudo_fs_context *init_pseudo(struct fs_context *fc, diff --git a/include/linux/regmap.h b/include/linux/regmap.h index 4e1ac1fbcec4..55343795644b 100644 --- a/include/linux/regmap.h +++ b/include/linux/regmap.h @@ -1643,7 +1643,7 @@ struct regmap_irq_chip_data; * @status_invert: Inverted status register: cleared bits are active interrupts. * @status_is_level: Status register is actuall signal level: Xor status * register with previous value to get active interrupts. - * @wake_invert: Inverted wake register: cleared bits are wake enabled. + * @wake_invert: Inverted wake register: cleared bits are wake disabled. * @type_in_mask: Use the mask registers for controlling irq type. Use this if * the hardware provides separate bits for rising/falling edge * or low/high level interrupts and they should be combined into diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h index a7d92718b653..54701668b3df 100644 --- a/include/linux/resctrl.h +++ b/include/linux/resctrl.h @@ -206,6 +206,8 @@ struct rdt_mon_domain { * @arch_has_sparse_bitmasks: True if a bitmask like f00f is valid. * @arch_has_per_cpu_cfg: True if QOS_CFG register for this cache * level has CPU scope. + * @io_alloc_capable: True if portion of the cache can be configured + * for I/O traffic. */ struct resctrl_cache { unsigned int cbm_len; @@ -213,6 +215,7 @@ struct resctrl_cache { unsigned int shareable_bits; bool arch_has_sparse_bitmasks; bool arch_has_per_cpu_cfg; + bool io_alloc_capable; }; /** @@ -654,6 +657,27 @@ void resctrl_arch_reset_cntr(struct rdt_resource *r, struct rdt_mon_domain *d, u32 closid, u32 rmid, int cntr_id, enum resctrl_event_id eventid); +/** + * resctrl_arch_io_alloc_enable() - Enable/disable io_alloc feature. + * @r: The resctrl resource. + * @enable: Enable (true) or disable (false) io_alloc on resource @r. + * + * This can be called from any CPU. + * + * Return: + * 0 on success, <0 on error. + */ +int resctrl_arch_io_alloc_enable(struct rdt_resource *r, bool enable); + +/** + * resctrl_arch_get_io_alloc_enabled() - Get io_alloc feature state. + * @r: The resctrl resource. + * + * Return: + * true if io_alloc is enabled or false if disabled. + */ +bool resctrl_arch_get_io_alloc_enabled(struct rdt_resource *r); + extern unsigned int resctrl_rmid_realloc_threshold; extern unsigned int resctrl_rmid_realloc_limit; diff --git a/include/linux/restart_block.h b/include/linux/restart_block.h index 7e50bbc94e47..36ddfa1ec301 100644 --- a/include/linux/restart_block.h +++ b/include/linux/restart_block.h @@ -43,7 +43,7 @@ struct restart_block { struct __kernel_timespec __user *rmtp; struct old_timespec32 __user *compat_rmtp; }; - u64 expires; + ktime_t expires; } nanosleep; /* For poll */ struct { diff --git a/include/linux/resume_user_mode.h b/include/linux/resume_user_mode.h index e0135e0adae0..bf92227c78d0 100644 --- a/include/linux/resume_user_mode.h +++ b/include/linux/resume_user_mode.h @@ -59,7 +59,7 @@ static inline void resume_user_mode_work(struct pt_regs *regs) mem_cgroup_handle_over_high(GFP_KERNEL); blkcg_maybe_throttle_current(); - rseq_handle_notify_resume(NULL, regs); + rseq_handle_slowpath(regs); } #endif /* LINUX_RESUME_USER_MODE_H */ diff --git a/include/linux/rpmb.h b/include/linux/rpmb.h index cccda73eea4d..ed3f8e431eff 100644 --- a/include/linux/rpmb.h +++ b/include/linux/rpmb.h @@ -61,6 +61,50 @@ struct rpmb_dev { #define to_rpmb_dev(x) container_of((x), struct rpmb_dev, dev) +/** + * struct rpmb_frame - RPMB frame structure for authenticated access + * + * @stuff : stuff bytes, a padding/reserved area of 196 bytes at the + * beginning of the RPMB frame. They don’t carry meaningful + * data but are required to make the frame exactly 512 bytes. + * @key_mac : The authentication key or the message authentication + * code (MAC) depending on the request/response type. + * The MAC will be delivered in the last (or the only) + * block of data. + * @data : Data to be written or read by signed access. + * @nonce : Random number generated by the host for the requests + * and copied to the response by the RPMB engine. + * @write_counter: Counter value for the total amount of the successful + * authenticated data write requests made by the host. + * @addr : Address of the data to be programmed to or read + * from the RPMB. Address is the serial number of + * the accessed block (half sector 256B). + * @block_count : Number of blocks (half sectors, 256B) requested to be + * read/programmed. + * @result : Includes information about the status of the write counter + * (valid, expired) and result of the access made to the RPMB. + * @req_resp : Defines the type of request and response to/from the memory. + * + * The stuff bytes and big-endian properties are modeled to fit to the spec. + */ +struct rpmb_frame { + u8 stuff[196]; + u8 key_mac[32]; + u8 data[256]; + u8 nonce[16]; + __be32 write_counter; + __be16 addr; + __be16 block_count; + __be16 result; + __be16 req_resp; +}; + +#define RPMB_PROGRAM_KEY 0x1 /* Program RPMB Authentication Key */ +#define RPMB_GET_WRITE_COUNTER 0x2 /* Read RPMB write counter */ +#define RPMB_WRITE_DATA 0x3 /* Write data to RPMB partition */ +#define RPMB_READ_DATA 0x4 /* Read data from RPMB partition */ +#define RPMB_RESULT_READ 0x5 /* Read result request (Internal) */ + #if IS_ENABLED(CONFIG_RPMB) struct rpmb_dev *rpmb_dev_get(struct rpmb_dev *rdev); void rpmb_dev_put(struct rpmb_dev *rdev); diff --git a/include/linux/rseq.h b/include/linux/rseq.h index 69553e7c14c1..2266f4dc77b6 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -3,134 +3,164 @@ #define _LINUX_RSEQ_H #ifdef CONFIG_RSEQ - -#include <linux/preempt.h> #include <linux/sched.h> -#ifdef CONFIG_MEMBARRIER -# define RSEQ_EVENT_GUARD irq -#else -# define RSEQ_EVENT_GUARD preempt -#endif - -/* - * Map the event mask on the user-space ABI enum rseq_cs_flags - * for direct mask checks. - */ -enum rseq_event_mask_bits { - RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, - RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, - RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, -}; - -enum rseq_event_mask { - RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), - RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), - RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), -}; - -static inline void rseq_set_notify_resume(struct task_struct *t) -{ - if (t->rseq) - set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); -} +#include <uapi/linux/rseq.h> -void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); +void __rseq_handle_slowpath(struct pt_regs *regs); -static inline void rseq_handle_notify_resume(struct ksignal *ksig, - struct pt_regs *regs) +/* Invoked from resume_user_mode_work() */ +static inline void rseq_handle_slowpath(struct pt_regs *regs) { - if (current->rseq) - __rseq_handle_notify_resume(ksig, regs); + if (IS_ENABLED(CONFIG_GENERIC_ENTRY)) { + if (current->rseq.event.slowpath) + __rseq_handle_slowpath(regs); + } else { + /* '&' is intentional to spare one conditional branch */ + if (current->rseq.event.sched_switch & current->rseq.event.has_rseq) + __rseq_handle_slowpath(regs); + } } -static inline void rseq_signal_deliver(struct ksignal *ksig, - struct pt_regs *regs) -{ - scoped_guard(RSEQ_EVENT_GUARD) - __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); - rseq_handle_notify_resume(ksig, regs); -} +void __rseq_signal_deliver(int sig, struct pt_regs *regs); -/* rseq_preempt() requires preemption to be disabled. */ -static inline void rseq_preempt(struct task_struct *t) +/* + * Invoked from signal delivery to fixup based on the register context before + * switching to the signal delivery context. + */ +static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { - __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); - rseq_set_notify_resume(t); + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + /* '&' is intentional to spare one conditional branch */ + if (current->rseq.event.has_rseq & current->rseq.event.user_irq) + __rseq_signal_deliver(ksig->sig, regs); + } else { + if (current->rseq.event.has_rseq) + __rseq_signal_deliver(ksig->sig, regs); + } } -/* rseq_migrate() requires preemption to be disabled. */ -static inline void rseq_migrate(struct task_struct *t) +static inline void rseq_raise_notify_resume(struct task_struct *t) { - __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); - rseq_set_notify_resume(t); + set_tsk_thread_flag(t, TIF_RSEQ); } -/* - * If parent process has a registered restartable sequences area, the - * child inherits. Unregister rseq for a clone with CLONE_VM set. - */ -static inline void rseq_fork(struct task_struct *t, u64 clone_flags) +/* Invoked from context switch to force evaluation on exit to user */ +static __always_inline void rseq_sched_switch_event(struct task_struct *t) { - if (clone_flags & CLONE_VM) { - t->rseq = NULL; - t->rseq_len = 0; - t->rseq_sig = 0; - t->rseq_event_mask = 0; + struct rseq_event *ev = &t->rseq.event; + + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + /* + * Avoid a boat load of conditionals by using simple logic + * to determine whether NOTIFY_RESUME needs to be raised. + * + * It's required when the CPU or MM CID has changed or + * the entry was from user space. + */ + bool raise = (ev->user_irq | ev->ids_changed) & ev->has_rseq; + + if (raise) { + ev->sched_switch = true; + rseq_raise_notify_resume(t); + } } else { - t->rseq = current->rseq; - t->rseq_len = current->rseq_len; - t->rseq_sig = current->rseq_sig; - t->rseq_event_mask = current->rseq_event_mask; + if (ev->has_rseq) { + t->rseq.event.sched_switch = true; + rseq_raise_notify_resume(t); + } } } -static inline void rseq_execve(struct task_struct *t) +/* + * Invoked from __set_task_cpu() when a task migrates or from + * mm_cid_schedin() when the CID changes to enforce an IDs update. + * + * This does not raise TIF_NOTIFY_RESUME as that happens in + * rseq_sched_switch_event(). + */ +static __always_inline void rseq_sched_set_ids_changed(struct task_struct *t) { - t->rseq = NULL; - t->rseq_len = 0; - t->rseq_sig = 0; - t->rseq_event_mask = 0; + t->rseq.event.ids_changed = true; } -#else - -static inline void rseq_set_notify_resume(struct task_struct *t) -{ -} -static inline void rseq_handle_notify_resume(struct ksignal *ksig, - struct pt_regs *regs) +/* Enforce a full update after RSEQ registration and when execve() failed */ +static inline void rseq_force_update(void) { + if (current->rseq.event.has_rseq) { + current->rseq.event.ids_changed = true; + current->rseq.event.sched_switch = true; + rseq_raise_notify_resume(current); + } } -static inline void rseq_signal_deliver(struct ksignal *ksig, - struct pt_regs *regs) + +/* + * KVM/HYPERV invoke resume_user_mode_work() before entering guest mode, + * which clears TIF_NOTIFY_RESUME on architectures that don't use the + * generic TIF bits and therefore can't provide a separate TIF_RSEQ flag. + * + * To avoid updating user space RSEQ in that case just to do it eventually + * again before returning to user space, because __rseq_handle_slowpath() + * does nothing when invoked with NULL register state. + * + * After returning from guest mode, before exiting to userspace, hypervisors + * must invoke this function to re-raise TIF_NOTIFY_RESUME if necessary. + */ +static inline void rseq_virt_userspace_exit(void) { + /* + * The generic optimization for deferring RSEQ updates until the next + * exit relies on having a dedicated TIF_RSEQ. + */ + if (!IS_ENABLED(CONFIG_HAVE_GENERIC_TIF_BITS) && + current->rseq.event.sched_switch) + rseq_raise_notify_resume(current); } -static inline void rseq_preempt(struct task_struct *t) + +static inline void rseq_reset(struct task_struct *t) { + memset(&t->rseq, 0, sizeof(t->rseq)); + t->rseq.ids.cpu_id = RSEQ_CPU_ID_UNINITIALIZED; } -static inline void rseq_migrate(struct task_struct *t) + +static inline void rseq_execve(struct task_struct *t) { + rseq_reset(t); } + +/* + * If parent process has a registered restartable sequences area, the + * child inherits. Unregister rseq for a clone with CLONE_VM set. + * + * On fork, keep the IDs (CPU, MMCID) of the parent, which avoids a fault + * on the COW page on exit to user space, when the child stays on the same + * CPU as the parent. That's obviously not guaranteed, but in overcommit + * scenarios it is more likely and optimizes for the fork/exec case without + * taking the fault. + */ static inline void rseq_fork(struct task_struct *t, u64 clone_flags) { -} -static inline void rseq_execve(struct task_struct *t) -{ + if (clone_flags & CLONE_VM) + rseq_reset(t); + else + t->rseq = current->rseq; } -#endif +#else /* CONFIG_RSEQ */ +static inline void rseq_handle_slowpath(struct pt_regs *regs) { } +static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } +static inline void rseq_sched_switch_event(struct task_struct *t) { } +static inline void rseq_sched_set_ids_changed(struct task_struct *t) { } +static inline void rseq_force_update(void) { } +static inline void rseq_virt_userspace_exit(void) { } +static inline void rseq_fork(struct task_struct *t, u64 clone_flags) { } +static inline void rseq_execve(struct task_struct *t) { } +#endif /* !CONFIG_RSEQ */ #ifdef CONFIG_DEBUG_RSEQ - void rseq_syscall(struct pt_regs *regs); - -#else - -static inline void rseq_syscall(struct pt_regs *regs) -{ -} - -#endif +#else /* CONFIG_DEBUG_RSEQ */ +static inline void rseq_syscall(struct pt_regs *regs) { } +#endif /* !CONFIG_DEBUG_RSEQ */ #endif /* _LINUX_RSEQ_H */ diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h new file mode 100644 index 000000000000..c92167ff8a7f --- /dev/null +++ b/include/linux/rseq_entry.h @@ -0,0 +1,616 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_RSEQ_ENTRY_H +#define _LINUX_RSEQ_ENTRY_H + +/* Must be outside the CONFIG_RSEQ guard to resolve the stubs */ +#ifdef CONFIG_RSEQ_STATS +#include <linux/percpu.h> + +struct rseq_stats { + unsigned long exit; + unsigned long signal; + unsigned long slowpath; + unsigned long fastpath; + unsigned long ids; + unsigned long cs; + unsigned long clear; + unsigned long fixup; +}; + +DECLARE_PER_CPU(struct rseq_stats, rseq_stats); + +/* + * Slow path has interrupts and preemption enabled, but the fast path + * runs with interrupts disabled so there is no point in having the + * preemption checks implied in __this_cpu_inc() for every operation. + */ +#ifdef RSEQ_BUILD_SLOW_PATH +#define rseq_stat_inc(which) this_cpu_inc((which)) +#else +#define rseq_stat_inc(which) raw_cpu_inc((which)) +#endif + +#else /* CONFIG_RSEQ_STATS */ +#define rseq_stat_inc(x) do { } while (0) +#endif /* !CONFIG_RSEQ_STATS */ + +#ifdef CONFIG_RSEQ +#include <linux/jump_label.h> +#include <linux/rseq.h> +#include <linux/uaccess.h> + +#include <linux/tracepoint-defs.h> + +#ifdef CONFIG_TRACEPOINTS +DECLARE_TRACEPOINT(rseq_update); +DECLARE_TRACEPOINT(rseq_ip_fixup); +void __rseq_trace_update(struct task_struct *t); +void __rseq_trace_ip_fixup(unsigned long ip, unsigned long start_ip, + unsigned long offset, unsigned long abort_ip); + +static inline void rseq_trace_update(struct task_struct *t, struct rseq_ids *ids) +{ + if (tracepoint_enabled(rseq_update) && ids) + __rseq_trace_update(t); +} + +static inline void rseq_trace_ip_fixup(unsigned long ip, unsigned long start_ip, + unsigned long offset, unsigned long abort_ip) +{ + if (tracepoint_enabled(rseq_ip_fixup)) + __rseq_trace_ip_fixup(ip, start_ip, offset, abort_ip); +} + +#else /* CONFIG_TRACEPOINT */ +static inline void rseq_trace_update(struct task_struct *t, struct rseq_ids *ids) { } +static inline void rseq_trace_ip_fixup(unsigned long ip, unsigned long start_ip, + unsigned long offset, unsigned long abort_ip) { } +#endif /* !CONFIG_TRACEPOINT */ + +DECLARE_STATIC_KEY_MAYBE(CONFIG_RSEQ_DEBUG_DEFAULT_ENABLE, rseq_debug_enabled); + +#ifdef RSEQ_BUILD_SLOW_PATH +#define rseq_inline +#else +#define rseq_inline __always_inline +#endif + +bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr); +bool rseq_debug_validate_ids(struct task_struct *t); + +static __always_inline void rseq_note_user_irq_entry(void) +{ + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) + current->rseq.event.user_irq = true; +} + +/* + * Check whether there is a valid critical section and whether the + * instruction pointer in @regs is inside the critical section. + * + * - If the critical section is invalid, terminate the task. + * + * - If valid and the instruction pointer is inside, set it to the abort IP. + * + * - If valid and the instruction pointer is outside, clear the critical + * section address. + * + * Returns true, if the section was valid and either fixup or clear was + * done, false otherwise. + * + * In the failure case task::rseq_event::fatal is set when a invalid + * section was found. It's clear when the failure was an unresolved page + * fault. + * + * If inlined into the exit to user path with interrupts disabled, the + * caller has to protect against page faults with pagefault_disable(). + * + * In preemptible task context this would be counterproductive as the page + * faults could not be fully resolved. As a consequence unresolved page + * faults in task context are fatal too. + */ + +#ifdef RSEQ_BUILD_SLOW_PATH +/* + * The debug version is put out of line, but kept here so the code stays + * together. + * + * @csaddr has already been checked by the caller to be in user space + */ +bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, + unsigned long csaddr) +{ + struct rseq_cs __user *ucs = (struct rseq_cs __user *)(unsigned long)csaddr; + u64 start_ip, abort_ip, offset, cs_end, head, tasksize = TASK_SIZE; + unsigned long ip = instruction_pointer(regs); + u64 __user *uc_head = (u64 __user *) ucs; + u32 usig, __user *uc_sig; + + scoped_user_rw_access(ucs, efault) { + /* + * Evaluate the user pile and exit if one of the conditions + * is not fulfilled. + */ + unsafe_get_user(start_ip, &ucs->start_ip, efault); + if (unlikely(start_ip >= tasksize)) + goto die; + /* If outside, just clear the critical section. */ + if (ip < start_ip) + goto clear; + + unsafe_get_user(offset, &ucs->post_commit_offset, efault); + cs_end = start_ip + offset; + /* Check for overflow and wraparound */ + if (unlikely(cs_end >= tasksize || cs_end < start_ip)) + goto die; + + /* If not inside, clear it. */ + if (ip >= cs_end) + goto clear; + + unsafe_get_user(abort_ip, &ucs->abort_ip, efault); + /* Ensure it's "valid" */ + if (unlikely(abort_ip >= tasksize || abort_ip < sizeof(*uc_sig))) + goto die; + /* Validate that the abort IP is not in the critical section */ + if (unlikely(abort_ip - start_ip < offset)) + goto die; + + /* + * Check version and flags for 0. No point in emitting + * deprecated warnings before dying. That could be done in + * the slow path eventually, but *shrug*. + */ + unsafe_get_user(head, uc_head, efault); + if (unlikely(head)) + goto die; + + /* abort_ip - 4 is >= 0. See abort_ip check above */ + uc_sig = (u32 __user *)(unsigned long)(abort_ip - sizeof(*uc_sig)); + unsafe_get_user(usig, uc_sig, efault); + if (unlikely(usig != t->rseq.sig)) + goto die; + + /* rseq_event.user_irq is only valid if CONFIG_GENERIC_IRQ_ENTRY=y */ + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + /* If not in interrupt from user context, let it die */ + if (unlikely(!t->rseq.event.user_irq)) + goto die; + } + unsafe_put_user(0ULL, &t->rseq.usrptr->rseq_cs, efault); + instruction_pointer_set(regs, (unsigned long)abort_ip); + rseq_stat_inc(rseq_stats.fixup); + break; + clear: + unsafe_put_user(0ULL, &t->rseq.usrptr->rseq_cs, efault); + rseq_stat_inc(rseq_stats.clear); + abort_ip = 0ULL; + } + + if (unlikely(abort_ip)) + rseq_trace_ip_fixup(ip, start_ip, offset, abort_ip); + return true; +die: + t->rseq.event.fatal = true; +efault: + return false; +} + +/* + * On debug kernels validate that user space did not mess with it if the + * debug branch is enabled. + */ +bool rseq_debug_validate_ids(struct task_struct *t) +{ + struct rseq __user *rseq = t->rseq.usrptr; + u32 cpu_id, uval, node_id; + + /* + * On the first exit after registering the rseq region CPU ID is + * RSEQ_CPU_ID_UNINITIALIZED and node_id in user space is 0! + */ + node_id = t->rseq.ids.cpu_id != RSEQ_CPU_ID_UNINITIALIZED ? + cpu_to_node(t->rseq.ids.cpu_id) : 0; + + scoped_user_read_access(rseq, efault) { + unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault); + if (cpu_id != t->rseq.ids.cpu_id) + goto die; + unsafe_get_user(uval, &rseq->cpu_id, efault); + if (uval != cpu_id) + goto die; + unsafe_get_user(uval, &rseq->node_id, efault); + if (uval != node_id) + goto die; + unsafe_get_user(uval, &rseq->mm_cid, efault); + if (uval != t->rseq.ids.mm_cid) + goto die; + } + return true; +die: + t->rseq.event.fatal = true; +efault: + return false; +} + +#endif /* RSEQ_BUILD_SLOW_PATH */ + +/* + * This only ensures that abort_ip is in the user address space and + * validates that it is preceded by the signature. + * + * No other sanity checks are done here, that's what the debug code is for. + */ +static rseq_inline bool +rseq_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr) +{ + struct rseq_cs __user *ucs = (struct rseq_cs __user *)(unsigned long)csaddr; + unsigned long ip = instruction_pointer(regs); + unsigned long tasksize = TASK_SIZE; + u64 start_ip, abort_ip, offset; + u32 usig, __user *uc_sig; + + rseq_stat_inc(rseq_stats.cs); + + if (unlikely(csaddr >= tasksize)) { + t->rseq.event.fatal = true; + return false; + } + + if (static_branch_unlikely(&rseq_debug_enabled)) + return rseq_debug_update_user_cs(t, regs, csaddr); + + scoped_user_rw_access(ucs, efault) { + unsafe_get_user(start_ip, &ucs->start_ip, efault); + unsafe_get_user(offset, &ucs->post_commit_offset, efault); + unsafe_get_user(abort_ip, &ucs->abort_ip, efault); + + /* + * No sanity checks. If user space screwed it up, it can + * keep the pieces. That's what debug code is for. + * + * If outside, just clear the critical section. + */ + if (ip - start_ip >= offset) + goto clear; + + /* + * Two requirements for @abort_ip: + * - Must be in user space as x86 IRET would happily return to + * the kernel. + * - The four bytes preceding the instruction at @abort_ip must + * contain the signature. + * + * The latter protects against the following attack vector: + * + * An attacker with limited abilities to write, creates a critical + * section descriptor, sets the abort IP to a library function or + * some other ROP gadget and stores the address of the descriptor + * in TLS::rseq::rseq_cs. An RSEQ abort would then evade ROP + * protection. + */ + if (unlikely(abort_ip >= tasksize || abort_ip < sizeof(*uc_sig))) + goto die; + + /* The address is guaranteed to be >= 0 and < TASK_SIZE */ + uc_sig = (u32 __user *)(unsigned long)(abort_ip - sizeof(*uc_sig)); + unsafe_get_user(usig, uc_sig, efault); + if (unlikely(usig != t->rseq.sig)) + goto die; + + /* Invalidate the critical section */ + unsafe_put_user(0ULL, &t->rseq.usrptr->rseq_cs, efault); + /* Update the instruction pointer */ + instruction_pointer_set(regs, (unsigned long)abort_ip); + rseq_stat_inc(rseq_stats.fixup); + break; + clear: + unsafe_put_user(0ULL, &t->rseq.usrptr->rseq_cs, efault); + rseq_stat_inc(rseq_stats.clear); + abort_ip = 0ULL; + } + + if (unlikely(abort_ip)) + rseq_trace_ip_fixup(ip, start_ip, offset, abort_ip); + return true; +die: + t->rseq.event.fatal = true; +efault: + return false; +} + +/* + * Updates CPU ID, Node ID and MM CID and reads the critical section + * address, when @csaddr != NULL. This allows to put the ID update and the + * read under the same uaccess region to spare a separate begin/end. + * + * As this is either invoked from a C wrapper with @csaddr = NULL or from + * the fast path code with a valid pointer, a clever compiler should be + * able to optimize the read out. Spares a duplicate implementation. + * + * Returns true, if the operation was successful, false otherwise. + * + * In the failure case task::rseq_event::fatal is set when invalid data + * was found on debug kernels. It's clear when the failure was an unresolved page + * fault. + * + * If inlined into the exit to user path with interrupts disabled, the + * caller has to protect against page faults with pagefault_disable(). + * + * In preemptible task context this would be counterproductive as the page + * faults could not be fully resolved. As a consequence unresolved page + * faults in task context are fatal too. + */ +static rseq_inline +bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, + u32 node_id, u64 *csaddr) +{ + struct rseq __user *rseq = t->rseq.usrptr; + + if (static_branch_unlikely(&rseq_debug_enabled)) { + if (!rseq_debug_validate_ids(t)) + return false; + } + + scoped_user_rw_access(rseq, efault) { + unsafe_put_user(ids->cpu_id, &rseq->cpu_id_start, efault); + unsafe_put_user(ids->cpu_id, &rseq->cpu_id, efault); + unsafe_put_user(node_id, &rseq->node_id, efault); + unsafe_put_user(ids->mm_cid, &rseq->mm_cid, efault); + if (csaddr) + unsafe_get_user(*csaddr, &rseq->rseq_cs, efault); + } + + /* Cache the new values */ + t->rseq.ids.cpu_cid = ids->cpu_cid; + rseq_stat_inc(rseq_stats.ids); + rseq_trace_update(t, ids); + return true; +efault: + return false; +} + +/* + * Update user space with new IDs and conditionally check whether the task + * is in a critical section. + */ +static rseq_inline bool rseq_update_usr(struct task_struct *t, struct pt_regs *regs, + struct rseq_ids *ids, u32 node_id) +{ + u64 csaddr; + + if (!rseq_set_ids_get_csaddr(t, ids, node_id, &csaddr)) + return false; + + /* + * On architectures which utilize the generic entry code this + * allows to skip the critical section when the entry was not from + * a user space interrupt, unless debug mode is enabled. + */ + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + if (!static_branch_unlikely(&rseq_debug_enabled)) { + if (likely(!t->rseq.event.user_irq)) + return true; + } + } + if (likely(!csaddr)) + return true; + /* Sigh, this really needs to do work */ + return rseq_update_user_cs(t, regs, csaddr); +} + +/* + * If you want to use this then convert your architecture to the generic + * entry code. I'm tired of building workarounds for people who can't be + * bothered to make the maintenance of generic infrastructure less + * burdensome. Just sucking everything into the architecture code and + * thereby making others chase the horrible hacks and keep them working is + * neither acceptable nor sustainable. + */ +#ifdef CONFIG_GENERIC_ENTRY + +/* + * This is inlined into the exit path because: + * + * 1) It's a one time comparison in the fast path when there is no event to + * handle + * + * 2) The access to the user space rseq memory (TLS) is unlikely to fault + * so the straight inline operation is: + * + * - Four 32-bit stores only if CPU ID/ MM CID need to be updated + * - One 64-bit load to retrieve the critical section address + * + * 3) In the unlikely case that the critical section address is != NULL: + * + * - One 64-bit load to retrieve the start IP + * - One 64-bit load to retrieve the offset for calculating the end + * - One 64-bit load to retrieve the abort IP + * - One 64-bit load to retrieve the signature + * - One store to clear the critical section address + * + * The non-debug case implements only the minimal required checking. It + * provides protection against a rogue abort IP in kernel space, which + * would be exploitable at least on x86, and also against a rogue CS + * descriptor by checking the signature at the abort IP. Any fallout from + * invalid critical section descriptors is a user space problem. The debug + * case provides the full set of checks and terminates the task if a + * condition is not met. + * + * In case of a fault or an invalid value, this sets TIF_NOTIFY_RESUME and + * tells the caller to loop back into exit_to_user_mode_loop(). The rseq + * slow path there will handle the failure. + */ +static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct task_struct *t) +{ + /* + * Page faults need to be disabled as this is called with + * interrupts disabled + */ + guard(pagefault)(); + if (likely(!t->rseq.event.ids_changed)) { + struct rseq __user *rseq = t->rseq.usrptr; + /* + * If IDs have not changed rseq_event::user_irq must be true + * See rseq_sched_switch_event(). + */ + u64 csaddr; + + if (unlikely(get_user_inline(csaddr, &rseq->rseq_cs))) + return false; + + if (static_branch_unlikely(&rseq_debug_enabled) || unlikely(csaddr)) { + if (unlikely(!rseq_update_user_cs(t, regs, csaddr))) + return false; + } + return true; + } + + struct rseq_ids ids = { + .cpu_id = task_cpu(t), + .mm_cid = task_mm_cid(t), + }; + u32 node_id = cpu_to_node(ids.cpu_id); + + return rseq_update_usr(t, regs, &ids, node_id); +} + +static __always_inline bool __rseq_exit_to_user_mode_restart(struct pt_regs *regs) +{ + struct task_struct *t = current; + + /* + * If the task did not go through schedule or got the flag enforced + * by the rseq syscall or execve, then nothing to do here. + * + * CPU ID and MM CID can only change when going through a context + * switch. + * + * rseq_sched_switch_event() sets the rseq_event::sched_switch bit + * only when rseq_event::has_rseq is true. That conditional is + * required to avoid setting the TIF bit if RSEQ is not registered + * for a task. rseq_event::sched_switch is cleared when RSEQ is + * unregistered by a task so it's sufficient to check for the + * sched_switch bit alone. + * + * A sane compiler requires three instructions for the nothing to do + * case including clearing the events, but your mileage might vary. + */ + if (unlikely((t->rseq.event.sched_switch))) { + rseq_stat_inc(rseq_stats.fastpath); + + if (unlikely(!rseq_exit_user_update(regs, t))) + return true; + } + /* Clear state so next entry starts from a clean slate */ + t->rseq.event.events = 0; + return false; +} + +/* Required to allow conversion to GENERIC_ENTRY w/o GENERIC_TIF_BITS */ +#ifdef CONFIG_HAVE_GENERIC_TIF_BITS +static __always_inline bool test_tif_rseq(unsigned long ti_work) +{ + return ti_work & _TIF_RSEQ; +} + +static __always_inline void clear_tif_rseq(void) +{ + static_assert(TIF_RSEQ != TIF_NOTIFY_RESUME); + clear_thread_flag(TIF_RSEQ); +} +#else +static __always_inline bool test_tif_rseq(unsigned long ti_work) { return true; } +static __always_inline void clear_tif_rseq(void) { } +#endif + +static __always_inline bool +rseq_exit_to_user_mode_restart(struct pt_regs *regs, unsigned long ti_work) +{ + if (likely(!test_tif_rseq(ti_work))) + return false; + + if (unlikely(__rseq_exit_to_user_mode_restart(regs))) { + current->rseq.event.slowpath = true; + set_tsk_thread_flag(current, TIF_NOTIFY_RESUME); + return true; + } + + clear_tif_rseq(); + return false; +} + +#else /* CONFIG_GENERIC_ENTRY */ +static inline bool rseq_exit_to_user_mode_restart(struct pt_regs *regs, unsigned long ti_work) +{ + return false; +} +#endif /* !CONFIG_GENERIC_ENTRY */ + +static __always_inline void rseq_syscall_exit_to_user_mode(void) +{ + struct rseq_event *ev = ¤t->rseq.event; + + rseq_stat_inc(rseq_stats.exit); + + /* Needed to remove the store for the !lockdep case */ + if (IS_ENABLED(CONFIG_LOCKDEP)) { + WARN_ON_ONCE(ev->sched_switch); + ev->events = 0; + } +} + +static __always_inline void rseq_irqentry_exit_to_user_mode(void) +{ + struct rseq_event *ev = ¤t->rseq.event; + + rseq_stat_inc(rseq_stats.exit); + + lockdep_assert_once(!ev->sched_switch); + + /* + * Ensure that event (especially user_irq) is cleared when the + * interrupt did not result in a schedule and therefore the + * rseq processing could not clear it. + */ + ev->events = 0; +} + +/* Required to keep ARM64 working */ +static __always_inline void rseq_exit_to_user_mode_legacy(void) +{ + struct rseq_event *ev = ¤t->rseq.event; + + rseq_stat_inc(rseq_stats.exit); + + if (static_branch_unlikely(&rseq_debug_enabled)) + WARN_ON_ONCE(ev->sched_switch); + + /* + * Ensure that event (especially user_irq) is cleared when the + * interrupt did not result in a schedule and therefore the + * rseq processing did not clear it. + */ + ev->events = 0; +} + +void __rseq_debug_syscall_return(struct pt_regs *regs); + +static inline void rseq_debug_syscall_return(struct pt_regs *regs) +{ + if (static_branch_unlikely(&rseq_debug_enabled)) + __rseq_debug_syscall_return(regs); +} +#else /* CONFIG_RSEQ */ +static inline void rseq_note_user_irq_entry(void) { } +static inline bool rseq_exit_to_user_mode_restart(struct pt_regs *regs, unsigned long ti_work) +{ + return false; +} +static inline void rseq_syscall_exit_to_user_mode(void) { } +static inline void rseq_irqentry_exit_to_user_mode(void) { } +static inline void rseq_exit_to_user_mode_legacy(void) { } +static inline void rseq_debug_syscall_return(struct pt_regs *regs) { } +#endif /* !CONFIG_RSEQ */ + +#endif /* _LINUX_RSEQ_ENTRY_H */ diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h new file mode 100644 index 000000000000..332dc14b81c9 --- /dev/null +++ b/include/linux/rseq_types.h @@ -0,0 +1,164 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _LINUX_RSEQ_TYPES_H +#define _LINUX_RSEQ_TYPES_H + +#include <linux/irq_work_types.h> +#include <linux/types.h> +#include <linux/workqueue_types.h> + +#ifdef CONFIG_RSEQ +struct rseq; + +/** + * struct rseq_event - Storage for rseq related event management + * @all: Compound to initialize and clear the data efficiently + * @events: Compound to access events with a single load/store + * @sched_switch: True if the task was scheduled and needs update on + * exit to user + * @ids_changed: Indicator that IDs need to be updated + * @user_irq: True on interrupt entry from user mode + * @has_rseq: True if the task has a rseq pointer installed + * @error: Compound error code for the slow path to analyze + * @fatal: User space data corrupted or invalid + * @slowpath: Indicator that slow path processing via TIF_NOTIFY_RESUME + * is required + * + * @sched_switch and @ids_changed must be adjacent and the combo must be + * 16bit aligned to allow a single store, when both are set at the same + * time in the scheduler. + */ +struct rseq_event { + union { + u64 all; + struct { + union { + u32 events; + struct { + u8 sched_switch; + u8 ids_changed; + u8 user_irq; + }; + }; + + u8 has_rseq; + u8 __pad; + union { + u16 error; + struct { + u8 fatal; + u8 slowpath; + }; + }; + }; + }; +}; + +/** + * struct rseq_ids - Cache for ids, which need to be updated + * @cpu_cid: Compound of @cpu_id and @mm_cid to make the + * compiler emit a single compare on 64-bit + * @cpu_id: The CPU ID which was written last to user space + * @mm_cid: The MM CID which was written last to user space + * + * @cpu_id and @mm_cid are updated when the data is written to user space. + */ +struct rseq_ids { + union { + u64 cpu_cid; + struct { + u32 cpu_id; + u32 mm_cid; + }; + }; +}; + +/** + * struct rseq_data - Storage for all rseq related data + * @usrptr: Pointer to the registered user space RSEQ memory + * @len: Length of the RSEQ region + * @sig: Signature of critial section abort IPs + * @event: Storage for event management + * @ids: Storage for cached CPU ID and MM CID + */ +struct rseq_data { + struct rseq __user *usrptr; + u32 len; + u32 sig; + struct rseq_event event; + struct rseq_ids ids; +}; + +#else /* CONFIG_RSEQ */ +struct rseq_data { }; +#endif /* !CONFIG_RSEQ */ + +#ifdef CONFIG_SCHED_MM_CID + +#define MM_CID_UNSET BIT(31) +#define MM_CID_ONCPU BIT(30) +#define MM_CID_TRANSIT BIT(29) + +/** + * struct sched_mm_cid - Storage for per task MM CID data + * @active: MM CID is active for the task + * @cid: The CID associated to the task either permanently or + * borrowed from the CPU + */ +struct sched_mm_cid { + unsigned int active; + unsigned int cid; +}; + +/** + * struct mm_cid_pcpu - Storage for per CPU MM_CID data + * @cid: The CID associated to the CPU either permanently or + * while a task with a CID is running + */ +struct mm_cid_pcpu { + unsigned int cid; +}____cacheline_aligned_in_smp; + +/** + * struct mm_mm_cid - Storage for per MM CID data + * @pcpu: Per CPU storage for CIDs associated to a CPU + * @percpu: Set, when CIDs are in per CPU mode + * @transit: Set to MM_CID_TRANSIT during a mode change transition phase + * @max_cids: The exclusive maximum CID value for allocation and convergence + * @irq_work: irq_work to handle the affinity mode change case + * @work: Regular work to handle the affinity mode change case + * @lock: Spinlock to protect against affinity setting which can't take @mutex + * @mutex: Mutex to serialize forks and exits related to this mm + * @nr_cpus_allowed: The number of CPUs in the per MM allowed CPUs map. The map + * is growth only. + * @users: The number of tasks sharing this MM. Separate from mm::mm_users + * as that is modified by mmget()/mm_put() by other entities which + * do not actually share the MM. + * @pcpu_thrs: Threshold for switching back from per CPU mode + * @update_deferred: A deferred switch back to per task mode is pending. + */ +struct mm_mm_cid { + /* Hotpath read mostly members */ + struct mm_cid_pcpu __percpu *pcpu; + unsigned int percpu; + unsigned int transit; + unsigned int max_cids; + + /* Rarely used. Moves @lock and @mutex into the second cacheline */ + struct irq_work irq_work; + struct work_struct work; + + raw_spinlock_t lock; + struct mutex mutex; + + /* Low frequency modified */ + unsigned int nr_cpus_allowed; + unsigned int users; + unsigned int pcpu_thrs; + unsigned int update_deferred; +}____cacheline_aligned_in_smp; +#else /* CONFIG_SCHED_MM_CID */ +struct mm_mm_cid { }; +struct sched_mm_cid { }; +#endif /* !CONFIG_SCHED_MM_CID */ + +#endif diff --git a/include/linux/sched.h b/include/linux/sched.h index cbb7340c5866..fac12bb7dbe4 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -41,7 +41,7 @@ #include <linux/task_io_accounting.h> #include <linux/posix-timers_types.h> #include <linux/restart_block.h> -#include <uapi/linux/rseq.h> +#include <linux/rseq_types.h> #include <linux/seqlock_types.h> #include <linux/kcsan.h> #include <linux/rv.h> @@ -637,8 +637,8 @@ struct sched_rt_entity { #endif } __randomize_layout; -typedef bool (*dl_server_has_tasks_f)(struct sched_dl_entity *); -typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *); +struct rq_flags; +typedef struct task_struct *(*dl_server_pick_f)(struct sched_dl_entity *, struct rq_flags *rf); struct sched_dl_entity { struct rb_node rb_node; @@ -685,20 +685,22 @@ struct sched_dl_entity { * * @dl_server tells if this is a server entity. * - * @dl_defer tells if this is a deferred or regular server. For - * now only defer server exists. - * - * @dl_defer_armed tells if the deferrable server is waiting - * for the replenishment timer to activate it. - * * @dl_server_active tells if the dlserver is active(started). * dlserver is started on first cfs enqueue on an idle runqueue * and is stopped when a dequeue results in 0 cfs tasks on the * runqueue. In other words, dlserver is active only when cpu's * runqueue has atleast one cfs task. * + * @dl_defer tells if this is a deferred or regular server. For + * now only defer server exists. + * + * @dl_defer_armed tells if the deferrable server is waiting + * for the replenishment timer to activate it. + * * @dl_defer_running tells if the deferrable server is actually * running, skipping the defer phase. + * + * @dl_defer_idle tracks idle state */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; @@ -709,6 +711,7 @@ struct sched_dl_entity { unsigned int dl_defer : 1; unsigned int dl_defer_armed : 1; unsigned int dl_defer_running : 1; + unsigned int dl_defer_idle : 1; /* * Bandwidth enforcement timer. Each -deadline task has its @@ -730,9 +733,6 @@ struct sched_dl_entity { * dl_server_update(). * * @rq the runqueue this server is for - * - * @server_has_tasks() returns true if @server_pick return a - * runnable task. */ struct rq *rq; dl_server_pick_f server_pick_task; @@ -1406,33 +1406,8 @@ struct task_struct { unsigned long numa_pages_migrated; #endif /* CONFIG_NUMA_BALANCING */ -#ifdef CONFIG_RSEQ - struct rseq __user *rseq; - u32 rseq_len; - u32 rseq_sig; - /* - * RmW on rseq_event_mask must be performed atomically - * with respect to preemption. - */ - unsigned long rseq_event_mask; -# ifdef CONFIG_DEBUG_RSEQ - /* - * This is a place holder to save a copy of the rseq fields for - * validation of read-only fields. The struct rseq has a - * variable-length array at the end, so it cannot be used - * directly. Reserve a size large enough for the known fields. - */ - char rseq_fields[sizeof(struct rseq)]; -# endif -#endif - -#ifdef CONFIG_SCHED_MM_CID - int mm_cid; /* Current cid in mm */ - int last_mm_cid; /* Most recent cid in mm */ - int migrate_from_cpu; - int mm_cid_active; /* Whether cid bitmap is active */ - struct callback_head cid_work; -#endif + struct rseq_data rseq; + struct sched_mm_cid mm_cid; struct tlbflush_unmap_batch tlb_ubc; @@ -1861,8 +1836,8 @@ extern int task_can_attach(struct task_struct *p); extern int dl_bw_alloc(int cpu, u64 dl_bw); extern void dl_bw_free(int cpu, u64 dl_bw); -/* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */ -extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask); +/* set_cpus_allowed_force() - consider using set_cpus_allowed_ptr() instead */ +extern void set_cpus_allowed_force(struct task_struct *p, const struct cpumask *new_mask); /** * set_cpus_allowed_ptr - set CPU affinity mask of a task @@ -1901,6 +1876,7 @@ extern int sched_setscheduler(struct task_struct *, int, const struct sched_para extern int sched_setscheduler_nocheck(struct task_struct *, int, const struct sched_param *); extern void sched_set_fifo(struct task_struct *p); extern void sched_set_fifo_low(struct task_struct *p); +extern void sched_set_fifo_secondary(struct task_struct *p); extern void sched_set_normal(struct task_struct *p, int nice); extern int sched_setattr(struct task_struct *, const struct sched_attr *); extern int sched_setattr_nocheck(struct task_struct *, const struct sched_attr *); @@ -2058,6 +2034,13 @@ static inline int test_tsk_need_resched(struct task_struct *tsk) return unlikely(test_tsk_thread_flag(tsk,TIF_NEED_RESCHED)); } +static inline void set_need_resched_current(void) +{ + lockdep_assert_irqs_disabled(); + set_tsk_need_resched(current); + set_preempt_need_resched(); +} + /* * cond_resched() and cond_resched_lock(): latency reduction via * explicit rescheduling in places that are safe. The return @@ -2318,6 +2301,32 @@ static __always_inline void alloc_tag_restore(struct alloc_tag *tag, struct allo #define alloc_tag_restore(_tag, _old) do {} while (0) #endif +/* Avoids recursive inclusion hell */ +#ifdef CONFIG_SCHED_MM_CID +void sched_mm_cid_before_execve(struct task_struct *t); +void sched_mm_cid_after_execve(struct task_struct *t); +void sched_mm_cid_fork(struct task_struct *t); +void sched_mm_cid_exit(struct task_struct *t); +static __always_inline int task_mm_cid(struct task_struct *t) +{ + return t->mm_cid.cid & ~(MM_CID_ONCPU | MM_CID_TRANSIT); +} +#else +static inline void sched_mm_cid_before_execve(struct task_struct *t) { } +static inline void sched_mm_cid_after_execve(struct task_struct *t) { } +static inline void sched_mm_cid_fork(struct task_struct *t) { } +static inline void sched_mm_cid_exit(struct task_struct *t) { } +static __always_inline int task_mm_cid(struct task_struct *t) +{ + /* + * Use the processor id as a fall-back when the mm cid feature is + * disabled. This provides functional per-cpu data structure accesses + * in user-space, althrough it won't provide the memory usage benefits. + */ + return task_cpu(t); +} +#endif + #ifndef MODULE #ifndef COMPILE_OFFSETS @@ -2407,12 +2416,12 @@ static inline void __migrate_enable(void) { } * be defined in kernel/sched/core.c. */ #ifndef INSTANTIATE_EXPORTED_MIGRATE_DISABLE -static inline void migrate_disable(void) +static __always_inline void migrate_disable(void) { __migrate_disable(); } -static inline void migrate_enable(void) +static __always_inline void migrate_enable(void) { __migrate_enable(); } diff --git a/include/linux/sched/coredump.h b/include/linux/sched/coredump.h index b7fafe999073..624fda17a785 100644 --- a/include/linux/sched/coredump.h +++ b/include/linux/sched/coredump.h @@ -8,7 +8,7 @@ #define SUID_DUMP_USER 1 /* Dump as user of process */ #define SUID_DUMP_ROOT 2 /* Dump as root */ -static inline unsigned long __mm_flags_get_dumpable(struct mm_struct *mm) +static inline unsigned long __mm_flags_get_dumpable(const struct mm_struct *mm) { /* * By convention, dumpable bits are contained in first 32 bits of the diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index bbcfdf12aa6e..45c0022b91ce 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -92,6 +92,9 @@ struct sched_domain { unsigned int nr_balance_failed; /* initialise to 0 */ /* idle_balance() stats */ + unsigned int newidle_call; + unsigned int newidle_success; + unsigned int newidle_ratio; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; diff --git a/include/linux/seqlock.h b/include/linux/seqlock.h index 5ce48eab7a2a..a8a8661839b6 100644 --- a/include/linux/seqlock.h +++ b/include/linux/seqlock.h @@ -1209,4 +1209,118 @@ done_seqretry_irqrestore(seqlock_t *lock, int seq, unsigned long flags) if (seq & 1) read_sequnlock_excl_irqrestore(lock, flags); } + +enum ss_state { + ss_done = 0, + ss_lock, + ss_lock_irqsave, + ss_lockless, +}; + +struct ss_tmp { + enum ss_state state; + unsigned long data; + spinlock_t *lock; + spinlock_t *lock_irqsave; +}; + +static inline void __scoped_seqlock_cleanup(struct ss_tmp *sst) +{ + if (sst->lock) + spin_unlock(sst->lock); + if (sst->lock_irqsave) + spin_unlock_irqrestore(sst->lock_irqsave, sst->data); +} + +extern void __scoped_seqlock_invalid_target(void); + +#if (defined(CONFIG_CC_IS_GCC) && CONFIG_GCC_VERSION < 90000) || defined(CONFIG_KASAN) +/* + * For some reason some GCC-8 architectures (nios2, alpha) have trouble + * determining that the ss_done state is impossible in __scoped_seqlock_next() + * below. + * + * Similarly KASAN is known to confuse compilers enough to break this. But we + * don't care about code quality for KASAN builds anyway. + */ +static inline void __scoped_seqlock_bug(void) { } +#else +/* + * Canary for compiler optimization -- if the compiler doesn't realize this is + * an impossible state, it very likely generates sub-optimal code here. + */ +extern void __scoped_seqlock_bug(void); +#endif + +static inline void +__scoped_seqlock_next(struct ss_tmp *sst, seqlock_t *lock, enum ss_state target) +{ + switch (sst->state) { + case ss_done: + __scoped_seqlock_bug(); + return; + + case ss_lock: + case ss_lock_irqsave: + sst->state = ss_done; + return; + + case ss_lockless: + if (!read_seqretry(lock, sst->data)) { + sst->state = ss_done; + return; + } + break; + } + + switch (target) { + case ss_done: + __scoped_seqlock_invalid_target(); + return; + + case ss_lock: + sst->lock = &lock->lock; + spin_lock(sst->lock); + sst->state = ss_lock; + return; + + case ss_lock_irqsave: + sst->lock_irqsave = &lock->lock; + spin_lock_irqsave(sst->lock_irqsave, sst->data); + sst->state = ss_lock_irqsave; + return; + + case ss_lockless: + sst->data = read_seqbegin(lock); + return; + } +} + +#define __scoped_seqlock_read(_seqlock, _target, _s) \ + for (struct ss_tmp _s __cleanup(__scoped_seqlock_cleanup) = \ + { .state = ss_lockless, .data = read_seqbegin(_seqlock) }; \ + _s.state != ss_done; \ + __scoped_seqlock_next(&_s, _seqlock, _target)) + +/** + * scoped_seqlock_read (lock, ss_state) - execute the read side critical + * section without manual sequence + * counter handling or calls to other + * helpers + * @lock: pointer to seqlock_t protecting the data + * @ss_state: one of {ss_lock, ss_lock_irqsave, ss_lockless} indicating + * the type of critical read section + * + * Example: + * + * scoped_seqlock_read (&lock, ss_lock) { + * // read-side critical section + * } + * + * Starts with a lockess pass first. If it fails, restarts the critical + * section with the lock held. + */ +#define scoped_seqlock_read(_seqlock, _target) \ + __scoped_seqlock_read(_seqlock, _target, __UNIQUE_ID(seqlock)) + #endif /* __LINUX_SEQLOCK_H */ diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h index 0e47465ef0fd..774efe592a9a 100644 --- a/include/linux/shmem_fs.h +++ b/include/linux/shmem_fs.h @@ -111,7 +111,7 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); int shmem_writeout(struct folio *folio, struct swap_iocb **plug, struct list_head *folio_list); -void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end); +void shmem_truncate_range(struct inode *inode, loff_t start, uoff_t end); int shmem_unuse(unsigned int type); #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index fb3fec9affaa..a7cc3d1f4fd1 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -4204,6 +4204,9 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, struct sk_buff_head *sk_queue, unsigned int flags, int *off, int *err); struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, int *err); +__poll_t datagram_poll_queue(struct file *file, struct socket *sock, + struct poll_table_struct *wait, + struct sk_buff_head *rcv_queue); __poll_t datagram_poll(struct file *file, struct socket *sock, struct poll_table_struct *wait); int skb_copy_datagram_iter(const struct sk_buff *from, int offset, diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index 66c06fcdfe19..cf84d98964b2 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -77,6 +77,7 @@ struct cachestat_range; struct cachestat; struct statmount; struct mnt_id_req; +struct ns_id_req; struct xattr_args; struct file_attr; @@ -437,6 +438,9 @@ asmlinkage long sys_statmount(const struct mnt_id_req __user *req, asmlinkage long sys_listmount(const struct mnt_id_req __user *req, u64 __user *mnt_ids, size_t nr_mnt_ids, unsigned int flags); +asmlinkage long sys_listns(const struct ns_id_req __user *req, + u64 __user *ns_ids, size_t nr_ns_ids, + unsigned int flags); asmlinkage long sys_truncate(const char __user *path, long length); asmlinkage long sys_ftruncate(unsigned int fd, off_t length); #if BITS_PER_LONG == 32 diff --git a/include/linux/thread_info.h b/include/linux/thread_info.h index dd925d84fa46..b40de9bab4b7 100644 --- a/include/linux/thread_info.h +++ b/include/linux/thread_info.h @@ -67,6 +67,11 @@ enum syscall_work_bit { #define _TIF_NEED_RESCHED_LAZY _TIF_NEED_RESCHED #endif +#ifndef TIF_RSEQ +# define TIF_RSEQ TIF_NOTIFY_RESUME +# define _TIF_RSEQ _TIF_NOTIFY_RESUME +#endif + #ifdef __KERNEL__ #ifndef arch_set_restart_data diff --git a/include/linux/timer.h b/include/linux/timer.h index 0414d9e6b4fc..62e1cea71125 100644 --- a/include/linux/timer.h +++ b/include/linux/timer.h @@ -188,4 +188,13 @@ int timers_dead_cpu(unsigned int cpu); #define timers_dead_cpu NULL #endif +#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON) +extern int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask); +#else +static inline int tmigr_isolated_exclude_cpumask(struct cpumask *exclude_cpumask) +{ + return 0; +} +#endif + #endif diff --git a/include/linux/types.h b/include/linux/types.h index 6dfdb8e8e4c3..d4437e9c452c 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -50,6 +50,7 @@ typedef __kernel_old_gid_t old_gid_t; #if defined(__GNUC__) typedef __kernel_loff_t loff_t; +typedef __kernel_uoff_t uoff_t; #endif /* diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h index 1beb5b395d81..be395f5f7ee3 100644 --- a/include/linux/uaccess.h +++ b/include/linux/uaccess.h @@ -2,6 +2,7 @@ #ifndef __LINUX_UACCESS_H__ #define __LINUX_UACCESS_H__ +#include <linux/cleanup.h> #include <linux/fault-inject-usercopy.h> #include <linux/instrumented.h> #include <linux/minmax.h> @@ -35,9 +36,17 @@ #ifdef masked_user_access_begin #define can_do_masked_user_access() 1 +# ifndef masked_user_write_access_begin +# define masked_user_write_access_begin masked_user_access_begin +# endif +# ifndef masked_user_read_access_begin +# define masked_user_read_access_begin masked_user_access_begin +#endif #else #define can_do_masked_user_access() 0 #define masked_user_access_begin(src) NULL + #define masked_user_read_access_begin(src) NULL + #define masked_user_write_access_begin(src) NULL #define mask_user_address(src) (src) #endif @@ -518,7 +527,34 @@ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count); long strnlen_user_nofault(const void __user *unsafe_addr, long count); -#ifndef __get_kernel_nofault +#ifdef arch_get_kernel_nofault +/* + * Wrap the architecture implementation so that @label can be outside of a + * cleanup() scope. A regular C goto works correctly, but ASM goto does + * not. Clang rejects such an attempt, but GCC silently emits buggy code. + */ +#define __get_kernel_nofault(dst, src, type, label) \ +do { \ + __label__ local_label; \ + arch_get_kernel_nofault(dst, src, type, local_label); \ + if (0) { \ + local_label: \ + goto label; \ + } \ +} while (0) + +#define __put_kernel_nofault(dst, src, type, label) \ +do { \ + __label__ local_label; \ + arch_put_kernel_nofault(dst, src, type, local_label); \ + if (0) { \ + local_label: \ + goto label; \ + } \ +} while (0) + +#elif !defined(__get_kernel_nofault) /* arch_get_kernel_nofault */ + #define __get_kernel_nofault(dst, src, type, label) \ do { \ type __user *p = (type __force __user *)(src); \ @@ -535,7 +571,8 @@ do { \ if (__put_user(data, p)) \ goto label; \ } while (0) -#endif + +#endif /* !__get_kernel_nofault */ /** * get_kernel_nofault(): safely attempt to read from a location @@ -549,7 +586,42 @@ do { \ copy_from_kernel_nofault(&(val), __gk_ptr, sizeof(val));\ }) -#ifndef user_access_begin +#ifdef user_access_begin + +#ifdef arch_unsafe_get_user +/* + * Wrap the architecture implementation so that @label can be outside of a + * cleanup() scope. A regular C goto works correctly, but ASM goto does + * not. Clang rejects such an attempt, but GCC silently emits buggy code. + * + * Some architectures use internal local labels already, but this extra + * indirection here is harmless because the compiler optimizes it out + * completely in any case. This construct just ensures that the ASM GOTO + * target is always in the local scope. The C goto 'label' works correctly + * when leaving a cleanup() scope. + */ +#define unsafe_get_user(x, ptr, label) \ +do { \ + __label__ local_label; \ + arch_unsafe_get_user(x, ptr, local_label); \ + if (0) { \ + local_label: \ + goto label; \ + } \ +} while (0) + +#define unsafe_put_user(x, ptr, label) \ +do { \ + __label__ local_label; \ + arch_unsafe_put_user(x, ptr, local_label); \ + if (0) { \ + local_label: \ + goto label; \ + } \ +} while (0) +#endif /* arch_unsafe_get_user */ + +#else /* user_access_begin */ #define user_access_begin(ptr,len) access_ok(ptr, len) #define user_access_end() do { } while (0) #define unsafe_op_wrap(op, err) do { if (unlikely(op)) goto err; } while (0) @@ -559,7 +631,8 @@ do { \ #define unsafe_copy_from_user(d,s,l,e) unsafe_op_wrap(__copy_from_user(d,s,l),e) static inline unsigned long user_access_save(void) { return 0UL; } static inline void user_access_restore(unsigned long flags) { } -#endif +#endif /* !user_access_begin */ + #ifndef user_write_access_begin #define user_write_access_begin user_access_begin #define user_write_access_end user_access_end @@ -569,6 +642,239 @@ static inline void user_access_restore(unsigned long flags) { } #define user_read_access_end user_access_end #endif +/* Define RW variant so the below _mode macro expansion works */ +#define masked_user_rw_access_begin(u) masked_user_access_begin(u) +#define user_rw_access_begin(u, s) user_access_begin(u, s) +#define user_rw_access_end() user_access_end() + +/* Scoped user access */ +#define USER_ACCESS_GUARD(_mode) \ +static __always_inline void __user * \ +class_user_##_mode##_begin(void __user *ptr) \ +{ \ + return ptr; \ +} \ + \ +static __always_inline void \ +class_user_##_mode##_end(void __user *ptr) \ +{ \ + user_##_mode##_access_end(); \ +} \ + \ +DEFINE_CLASS(user_ ##_mode## _access, void __user *, \ + class_user_##_mode##_end(_T), \ + class_user_##_mode##_begin(ptr), void __user *ptr) \ + \ +static __always_inline class_user_##_mode##_access_t \ +class_user_##_mode##_access_ptr(void __user *scope) \ +{ \ + return scope; \ +} + +USER_ACCESS_GUARD(read) +USER_ACCESS_GUARD(write) +USER_ACCESS_GUARD(rw) +#undef USER_ACCESS_GUARD + +/** + * __scoped_user_access_begin - Start a scoped user access + * @mode: The mode of the access class (read, write, rw) + * @uptr: The pointer to access user space memory + * @size: Size of the access + * @elbl: Error label to goto when the access region is rejected + * + * Internal helper for __scoped_user_access(). Don't use directly. + */ +#define __scoped_user_access_begin(mode, uptr, size, elbl) \ +({ \ + typeof(uptr) __retptr; \ + \ + if (can_do_masked_user_access()) { \ + __retptr = masked_user_##mode##_access_begin(uptr); \ + } else { \ + __retptr = uptr; \ + if (!user_##mode##_access_begin(uptr, size)) \ + goto elbl; \ + } \ + __retptr; \ +}) + +/** + * __scoped_user_access - Open a scope for user access + * @mode: The mode of the access class (read, write, rw) + * @uptr: The pointer to access user space memory + * @size: Size of the access + * @elbl: Error label to goto when the access region is rejected. It + * must be placed outside the scope + * + * If the user access function inside the scope requires a fault label, it + * can use @elbl or a different label outside the scope, which requires + * that user access which is implemented with ASM GOTO has been properly + * wrapped. See unsafe_get_user() for reference. + * + * scoped_user_rw_access(ptr, efault) { + * unsafe_get_user(rval, &ptr->rval, efault); + * unsafe_put_user(wval, &ptr->wval, efault); + * } + * return 0; + * efault: + * return -EFAULT; + * + * The scope is internally implemented as a autoterminating nested for() + * loop, which can be left with 'return', 'break' and 'goto' at any + * point. + * + * When the scope is left user_##@_mode##_access_end() is automatically + * invoked. + * + * When the architecture supports masked user access and the access region + * which is determined by @uptr and @size is not a valid user space + * address, i.e. < TASK_SIZE, the scope sets the pointer to a faulting user + * space address and does not terminate early. This optimizes for the good + * case and lets the performance uncritical bad case go through the fault. + * + * The eventual modification of the pointer is limited to the scope. + * Outside of the scope the original pointer value is unmodified, so that + * the original pointer value is available for diagnostic purposes in an + * out of scope fault path. + * + * Nesting scoped user access into a user access scope is invalid and fails + * the build. Nesting into other guards, e.g. pagefault is safe. + * + * The masked variant does not check the size of the access and relies on a + * mapping hole (e.g. guard page) to catch an out of range pointer, the + * first access to user memory inside the scope has to be within + * @uptr ... @uptr + PAGE_SIZE - 1 + * + * Don't use directly. Use scoped_masked_user_$MODE_access() instead. + */ +#define __scoped_user_access(mode, uptr, size, elbl) \ +for (bool done = false; !done; done = true) \ + for (void __user *_tmpptr = __scoped_user_access_begin(mode, uptr, size, elbl); \ + !done; done = true) \ + for (CLASS(user_##mode##_access, scope)(_tmpptr); !done; done = true) \ + /* Force modified pointer usage within the scope */ \ + for (const typeof(uptr) uptr = _tmpptr; !done; done = true) + +/** + * scoped_user_read_access_size - Start a scoped user read access with given size + * @usrc: Pointer to the user space address to read from + * @size: Size of the access starting from @usrc + * @elbl: Error label to goto when the access region is rejected + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_read_access_size(usrc, size, elbl) \ + __scoped_user_access(read, usrc, size, elbl) + +/** + * scoped_user_read_access - Start a scoped user read access + * @usrc: Pointer to the user space address to read from + * @elbl: Error label to goto when the access region is rejected + * + * The size of the access starting from @usrc is determined via sizeof(*@usrc)). + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_read_access(usrc, elbl) \ + scoped_user_read_access_size(usrc, sizeof(*(usrc)), elbl) + +/** + * scoped_user_write_access_size - Start a scoped user write access with given size + * @udst: Pointer to the user space address to write to + * @size: Size of the access starting from @udst + * @elbl: Error label to goto when the access region is rejected + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_write_access_size(udst, size, elbl) \ + __scoped_user_access(write, udst, size, elbl) + +/** + * scoped_user_write_access - Start a scoped user write access + * @udst: Pointer to the user space address to write to + * @elbl: Error label to goto when the access region is rejected + * + * The size of the access starting from @udst is determined via sizeof(*@udst)). + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_write_access(udst, elbl) \ + scoped_user_write_access_size(udst, sizeof(*(udst)), elbl) + +/** + * scoped_user_rw_access_size - Start a scoped user read/write access with given size + * @uptr Pointer to the user space address to read from and write to + * @size: Size of the access starting from @uptr + * @elbl: Error label to goto when the access region is rejected + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_rw_access_size(uptr, size, elbl) \ + __scoped_user_access(rw, uptr, size, elbl) + +/** + * scoped_user_rw_access - Start a scoped user read/write access + * @uptr Pointer to the user space address to read from and write to + * @elbl: Error label to goto when the access region is rejected + * + * The size of the access starting from @uptr is determined via sizeof(*@uptr)). + * + * For further information see __scoped_user_access() above. + */ +#define scoped_user_rw_access(uptr, elbl) \ + scoped_user_rw_access_size(uptr, sizeof(*(uptr)), elbl) + +/** + * get_user_inline - Read user data inlined + * @val: The variable to store the value read from user memory + * @usrc: Pointer to the user space memory to read from + * + * Return: 0 if successful, -EFAULT when faulted + * + * Inlined variant of get_user(). Only use when there is a demonstrable + * performance reason. + */ +#define get_user_inline(val, usrc) \ +({ \ + __label__ efault; \ + typeof(usrc) _tmpsrc = usrc; \ + int _ret = 0; \ + \ + scoped_user_read_access(_tmpsrc, efault) \ + unsafe_get_user(val, _tmpsrc, efault); \ + if (0) { \ + efault: \ + _ret = -EFAULT; \ + } \ + _ret; \ +}) + +/** + * put_user_inline - Write to user memory inlined + * @val: The value to write + * @udst: Pointer to the user space memory to write to + * + * Return: 0 if successful, -EFAULT when faulted + * + * Inlined variant of put_user(). Only use when there is a demonstrable + * performance reason. + */ +#define put_user_inline(val, udst) \ +({ \ + __label__ efault; \ + typeof(udst) _tmpdst = udst; \ + int _ret = 0; \ + \ + scoped_user_write_access(_tmpdst, efault) \ + unsafe_put_user(val, _tmpdst, efault); \ + if (0) { \ + efault: \ + _ret = -EFAULT; \ + } \ + _ret; \ +}) + #ifdef CONFIG_HARDENED_USERCOPY void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h index 26122d00708a..bc7ae7d21900 100644 --- a/include/linux/unwind_deferred.h +++ b/include/linux/unwind_deferred.h @@ -6,16 +6,6 @@ #include <linux/unwind_user.h> #include <linux/unwind_deferred_types.h> -struct unwind_work; - -typedef void (*unwind_callback_t)(struct unwind_work *work, struct unwind_stacktrace *trace, u64 cookie); - -struct unwind_work { - struct list_head list; - unwind_callback_t func; - int bit; -}; - #ifdef CONFIG_UNWIND_USER enum { @@ -44,22 +34,22 @@ void unwind_deferred_task_exit(struct task_struct *task); static __always_inline void unwind_reset_info(void) { struct unwind_task_info *info = ¤t->unwind_info; - unsigned long bits; + unsigned long bits = atomic_long_read(&info->unwind_mask); /* Was there any unwinding? */ - if (unlikely(info->unwind_mask)) { - bits = info->unwind_mask; - do { - /* Is a task_work going to run again before going back */ - if (bits & UNWIND_PENDING) - return; - } while (!try_cmpxchg(&info->unwind_mask, &bits, 0UL)); - current->unwind_info.id.id = 0; - - if (unlikely(info->cache)) { - info->cache->nr_entries = 0; - info->cache->unwind_completed = 0; - } + if (likely(!bits)) + return; + + do { + /* Is a task_work going to run again before going back */ + if (bits & UNWIND_PENDING) + return; + } while (!atomic_long_try_cmpxchg(&info->unwind_mask, &bits, 0UL)); + current->unwind_info.id.id = 0; + + if (unlikely(info->cache)) { + info->cache->nr_entries = 0; + info->cache->unwind_completed = 0; } } @@ -68,9 +58,17 @@ static __always_inline void unwind_reset_info(void) static inline void unwind_task_init(struct task_struct *task) {} static inline void unwind_task_free(struct task_struct *task) {} -static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; } -static inline int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) { return -ENOSYS; } -static inline int unwind_deferred_request(struct unwind_work *work, u64 *timestamp) { return -ENOSYS; } +static inline int unwind_user_faultable(struct unwind_stacktrace *trace) +{ return -ENOSYS; } + +static inline int +unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) +{ return -ENOSYS; } + +static inline int +unwind_deferred_request(struct unwind_work *work, u64 *timestamp) +{ return -ENOSYS; } + static inline void unwind_deferred_cancel(struct unwind_work *work) {} static inline void unwind_deferred_task_exit(struct task_struct *task) {} diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h index 33b62ac25c86..18fa3932f61c 100644 --- a/include/linux/unwind_deferred_types.h +++ b/include/linux/unwind_deferred_types.h @@ -2,6 +2,9 @@ #ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H #define _LINUX_UNWIND_USER_DEFERRED_TYPES_H +#include <linux/types.h> +#include <linux/atomic.h> + struct unwind_cache { unsigned long unwind_completed; unsigned int nr_entries; @@ -30,10 +33,23 @@ union unwind_task_id { }; struct unwind_task_info { - unsigned long unwind_mask; + atomic_long_t unwind_mask; struct unwind_cache *cache; struct callback_head work; union unwind_task_id id; }; +struct unwind_work; +struct unwind_stacktrace; + +typedef void (*unwind_callback_t)(struct unwind_work *work, + struct unwind_stacktrace *trace, + u64 cookie); + +struct unwind_work { + struct list_head list; + unwind_callback_t func; + int bit; +}; + #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */ diff --git a/include/linux/unwind_user_types.h b/include/linux/unwind_user_types.h index a449f15be890..412729a269bc 100644 --- a/include/linux/unwind_user_types.h +++ b/include/linux/unwind_user_types.h @@ -36,8 +36,10 @@ struct unwind_user_state { unsigned long ip; unsigned long sp; unsigned long fp; + unsigned int ws; enum unwind_user_type current_type; unsigned int available_types; + bool topmost; bool done; }; diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h index 3aaf19e77558..8285b19a25e0 100644 --- a/include/linux/usb/gadget.h +++ b/include/linux/usb/gadget.h @@ -376,6 +376,9 @@ struct usb_gadget_ops { * can handle. The UDC must support this and all slower speeds and lower * number of lanes. * @state: the state we are now (attached, suspended, configured, etc) + * @state_lock: Spinlock protecting the `state` and `teardown` members. + * @teardown: True if the device is undergoing teardown, used to prevent + * new work from being scheduled during cleanup. * @name: Identifies the controller hardware type. Used in diagnostics * and sometimes configuration. * @dev: Driver model state for this abstract device. @@ -451,6 +454,8 @@ struct usb_gadget { enum usb_ssp_rate max_ssp_rate; enum usb_device_state state; + spinlock_t state_lock; + bool teardown; const char *name; struct device dev; unsigned isoch_delay; diff --git a/include/linux/user_namespace.h b/include/linux/user_namespace.h index 9a9aebbf96b9..9c3be157397e 100644 --- a/include/linux/user_namespace.h +++ b/include/linux/user_namespace.h @@ -166,13 +166,13 @@ static inline void set_userns_rlimit_max(struct user_namespace *ns, ns->rlimit_max[type] = max <= LONG_MAX ? max : LONG_MAX; } -#ifdef CONFIG_USER_NS - static inline struct user_namespace *to_user_ns(struct ns_common *ns) { return container_of(ns, struct user_namespace, ns); } +#ifdef CONFIG_USER_NS + static inline struct user_namespace *get_user_ns(struct user_namespace *ns) { if (ns) diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h index 20e0584db1dd..75dabb763c65 100644 --- a/include/linux/virtio_net.h +++ b/include/linux/virtio_net.h @@ -384,7 +384,8 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, struct virtio_net_hdr_v1_hash_tunnel *vhdr, bool tnl_hdr_negotiated, bool little_endian, - int vlan_hlen) + int vlan_hlen, + bool has_data_valid) { struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr; unsigned int inner_nh, outer_th; @@ -394,13 +395,18 @@ virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb, tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL | SKB_GSO_UDP_TUNNEL_CSUM); if (!tnl_gso_type) - return virtio_net_hdr_from_skb(skb, hdr, little_endian, false, - vlan_hlen); + return virtio_net_hdr_from_skb(skb, hdr, little_endian, + has_data_valid, vlan_hlen); /* Tunnel support not negotiated but skb ask for it. */ if (!tnl_hdr_negotiated) return -EINVAL; + vhdr->hash_hdr.hash_value_lo = 0; + vhdr->hash_hdr.hash_value_hi = 0; + vhdr->hash_hdr.hash_report = 0; + vhdr->hash_hdr.padding = 0; + /* Let the basic parsing deal with plain GSO features. */ skb_shinfo(skb)->gso_type &= ~tnl_gso_type; ret = virtio_net_hdr_from_skb(skb, hdr, true, false, vlan_hlen); diff --git a/include/linux/writeback.h b/include/linux/writeback.h index 22dd4adc5667..f48e8ccffe81 100644 --- a/include/linux/writeback.h +++ b/include/linux/writeback.h @@ -189,11 +189,11 @@ void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, void inode_wait_for_writeback(struct inode *inode); void inode_io_list_del(struct inode *inode); -/* writeback.h requires fs.h; it, too, is not included from here. */ -static inline void wait_on_inode(struct inode *inode) +static inline xa_mark_t wbc_to_tag(struct writeback_control *wbc) { - wait_var_event(inode_state_wait_address(inode, __I_NEW), - !(READ_ONCE(inode->i_state) & I_NEW)); + if (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages) + return PAGECACHE_TAG_TOWRITE; + return PAGECACHE_TAG_DIRTY; } #ifdef CONFIG_CGROUP_WRITEBACK @@ -234,7 +234,7 @@ static inline void inode_attach_wb(struct inode *inode, struct folio *folio) static inline void inode_detach_wb(struct inode *inode) { if (inode->i_wb) { - WARN_ON_ONCE(!(inode->i_state & I_CLEAR)); + WARN_ON_ONCE(!(inode_state_read_once(inode) & I_CLEAR)); wb_put(inode->i_wb); inode->i_wb = NULL; } @@ -374,4 +374,9 @@ bool redirty_page_for_writepage(struct writeback_control *, struct page *); void sb_mark_inode_writeback(struct inode *inode); void sb_clear_inode_writeback(struct inode *inode); +/* + * 4MB minimal write chunk size + */ +#define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) + #endif /* WRITEBACK_H */ diff --git a/include/linux/xattr.h b/include/linux/xattr.h index 86b0d47984a1..64e9afe7d647 100644 --- a/include/linux/xattr.h +++ b/include/linux/xattr.h @@ -85,12 +85,12 @@ int __vfs_setxattr_noperm(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); int __vfs_setxattr_locked(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int, - struct inode **); + struct delegated_inode *); int vfs_setxattr(struct mnt_idmap *, struct dentry *, const char *, const void *, size_t, int); int __vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); int __vfs_removexattr_locked(struct mnt_idmap *, struct dentry *, - const char *, struct inode **); + const char *, struct delegated_inode *); int vfs_removexattr(struct mnt_idmap *, struct dentry *, const char *); ssize_t generic_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size); diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h index 9ecc70baaca9..cb4c02d00759 100644 --- a/include/net/bluetooth/hci.h +++ b/include/net/bluetooth/hci.h @@ -434,6 +434,7 @@ enum { HCI_USER_CHANNEL, HCI_EXT_CONFIGURED, HCI_LE_ADV, + HCI_LE_ADV_0, HCI_LE_PER_ADV, HCI_LE_SCAN, HCI_SSP_ENABLED, @@ -2782,6 +2783,11 @@ struct hci_ev_le_per_adv_report { __u8 data[]; } __packed; +#define HCI_EV_LE_PA_SYNC_LOST 0x10 +struct hci_ev_le_pa_sync_lost { + __le16 handle; +} __packed; + #define LE_PA_DATA_COMPLETE 0x00 #define LE_PA_DATA_MORE_TO_COME 0x01 #define LE_PA_DATA_TRUNCATED 0x02 diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h index 2924c2bf2a98..0cb87687837f 100644 --- a/include/net/bluetooth/hci_core.h +++ b/include/net/bluetooth/hci_core.h @@ -244,6 +244,7 @@ struct adv_info { bool enabled; bool pending; bool periodic; + bool periodic_enabled; __u8 mesh; __u8 instance; __u8 handle; @@ -748,7 +749,6 @@ struct hci_conn { __u8 remote_cap; __u8 remote_auth; - __u8 remote_id; unsigned int sent; @@ -856,11 +856,12 @@ extern struct mutex hci_cb_list_lock; /* ----- HCI interface to upper protocols ----- */ int l2cap_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr); int l2cap_disconn_ind(struct hci_conn *hcon); -void l2cap_recv_acldata(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); +int l2cap_recv_acldata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, + u16 flags); #if IS_ENABLED(CONFIG_BT_BREDR) int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); -void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb); +int sco_recv_scodata(struct hci_dev *hdev, u16 handle, struct sk_buff *skb); #else static inline int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) @@ -868,23 +869,30 @@ static inline int sco_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, return 0; } -static inline void sco_recv_scodata(struct hci_conn *hcon, struct sk_buff *skb) +static inline int sco_recv_scodata(struct hci_dev *hdev, u16 handle, + struct sk_buff *skb) { + kfree_skb(skb); + return -ENOENT; } #endif #if IS_ENABLED(CONFIG_BT_LE) int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags); -void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, u16 flags); +int iso_recv(struct hci_dev *hdev, u16 handle, struct sk_buff *skb, + u16 flags); #else static inline int iso_connect_ind(struct hci_dev *hdev, bdaddr_t *bdaddr, __u8 *flags) { return 0; } -static inline void iso_recv(struct hci_conn *hcon, struct sk_buff *skb, - u16 flags) + +static inline int iso_recv(struct hci_dev *hdev, u16 handle, + struct sk_buff *skb, u16 flags) { + kfree_skb(skb); + return -ENOENT; } #endif diff --git a/include/net/bluetooth/l2cap.h b/include/net/bluetooth/l2cap.h index 4bb0eaedda18..00e182a22720 100644 --- a/include/net/bluetooth/l2cap.h +++ b/include/net/bluetooth/l2cap.h @@ -38,8 +38,8 @@ #define L2CAP_DEFAULT_TX_WINDOW 63 #define L2CAP_DEFAULT_EXT_WINDOW 0x3FFF #define L2CAP_DEFAULT_MAX_TX 3 -#define L2CAP_DEFAULT_RETRANS_TO 2 /* seconds */ -#define L2CAP_DEFAULT_MONITOR_TO 12 /* seconds */ +#define L2CAP_DEFAULT_RETRANS_TO 2000 /* 2 seconds */ +#define L2CAP_DEFAULT_MONITOR_TO 12000 /* 12 seconds */ #define L2CAP_DEFAULT_MAX_PDU_SIZE 1492 /* Sized for AMP packet */ #define L2CAP_DEFAULT_ACK_TO 200 #define L2CAP_DEFAULT_MAX_SDU_SIZE 0xFFFF diff --git a/include/net/bluetooth/mgmt.h b/include/net/bluetooth/mgmt.h index 74edea06985b..f5be96f08b9d 100644 --- a/include/net/bluetooth/mgmt.h +++ b/include/net/bluetooth/mgmt.h @@ -780,7 +780,7 @@ struct mgmt_adv_pattern { __u8 ad_type; __u8 offset; __u8 length; - __u8 value[31]; + __u8 value[HCI_MAX_AD_LENGTH]; } __packed; #define MGMT_OP_ADD_ADV_PATTERNS_MONITOR 0x0052 @@ -853,7 +853,7 @@ struct mgmt_cp_set_mesh { __le16 window; __le16 period; __u8 num_ad_types; - __u8 ad_types[]; + __u8 ad_types[] __counted_by(num_ad_types); } __packed; #define MGMT_SET_MESH_RECEIVER_SIZE 6 diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 781624f5913a..820e299f06b5 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -6435,6 +6435,11 @@ static inline void wiphy_delayed_work_init(struct wiphy_delayed_work *dwork, * after wiphy_lock() was called. Therefore, wiphy_cancel_work() can * use just cancel_work() instead of cancel_work_sync(), it requires * being in a section protected by wiphy_lock(). + * + * Note that these are scheduled with a timer where the accuracy + * becomes less the longer in the future the scheduled timer is. Use + * wiphy_hrtimer_work_queue() if the timer must be not be late by more + * than approximately 10 percent. */ void wiphy_delayed_work_queue(struct wiphy *wiphy, struct wiphy_delayed_work *dwork, @@ -6506,6 +6511,79 @@ void wiphy_delayed_work_flush(struct wiphy *wiphy, bool wiphy_delayed_work_pending(struct wiphy *wiphy, struct wiphy_delayed_work *dwork); +struct wiphy_hrtimer_work { + struct wiphy_work work; + struct wiphy *wiphy; + struct hrtimer timer; +}; + +enum hrtimer_restart wiphy_hrtimer_work_timer(struct hrtimer *t); + +static inline void wiphy_hrtimer_work_init(struct wiphy_hrtimer_work *hrwork, + wiphy_work_func_t func) +{ + hrtimer_setup(&hrwork->timer, wiphy_hrtimer_work_timer, + CLOCK_BOOTTIME, HRTIMER_MODE_REL); + wiphy_work_init(&hrwork->work, func); +} + +/** + * wiphy_hrtimer_work_queue - queue hrtimer work for the wiphy + * @wiphy: the wiphy to queue for + * @hrwork: the high resolution timer worker + * @delay: the delay given as a ktime_t + * + * Please refer to wiphy_delayed_work_queue(). The difference is that + * the hrtimer work uses a high resolution timer for scheduling. This + * may be needed if timeouts might be scheduled further in the future + * and the accuracy of the normal timer is not sufficient. + * + * Expect a delay of a few milliseconds as the timer is scheduled + * with some slack and some more time may pass between queueing the + * work and its start. + */ +void wiphy_hrtimer_work_queue(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork, + ktime_t delay); + +/** + * wiphy_hrtimer_work_cancel - cancel previously queued hrtimer work + * @wiphy: the wiphy, for debug purposes + * @hrtimer: the hrtimer work to cancel + * + * Cancel the work *without* waiting for it, this assumes being + * called under the wiphy mutex acquired by wiphy_lock(). + */ +void wiphy_hrtimer_work_cancel(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrtimer); + +/** + * wiphy_hrtimer_work_flush - flush previously queued hrtimer work + * @wiphy: the wiphy, for debug purposes + * @hrwork: the hrtimer work to flush + * + * Flush the work (i.e. run it if pending). This must be called + * under the wiphy mutex acquired by wiphy_lock(). + */ +void wiphy_hrtimer_work_flush(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork); + +/** + * wiphy_hrtimer_work_pending - Find out whether a wiphy hrtimer + * work item is currently pending. + * + * @wiphy: the wiphy, for debug purposes + * @hrwork: the hrtimer work in question + * + * Return: true if timer is pending, false otherwise + * + * Please refer to the wiphy_delayed_work_pending() documentation as + * this is the equivalent function for hrtimer based delayed work + * items. + */ +bool wiphy_hrtimer_work_pending(struct wiphy *wiphy, + struct wiphy_hrtimer_work *hrwork); + /** * enum ieee80211_ap_reg_power - regulatory power for an Access Point * diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 4314a97702ea..ecae35512b9b 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -611,6 +611,21 @@ struct metadata_dst *iptunnel_metadata_reply(struct metadata_dst *md, int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, int headroom, bool reply); +static inline void ip_tunnel_adj_headroom(struct net_device *dev, + unsigned int headroom) +{ + /* we must cap headroom to some upperlimit, else pskb_expand_head + * will overflow header offsets in skb_headers_offset_update(). + */ + const unsigned int max_allowed = 512; + + if (headroom > max_allowed) + headroom = max_allowed; + + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); +} + int iptunnel_handle_offloads(struct sk_buff *skb, int gso_type_mask); static inline int iptunnel_pull_offloads(struct sk_buff *skb) diff --git a/include/net/libeth/xdp.h b/include/net/libeth/xdp.h index bc3507edd589..898723ab62e8 100644 --- a/include/net/libeth/xdp.h +++ b/include/net/libeth/xdp.h @@ -513,7 +513,7 @@ struct libeth_xdp_tx_desc { * can't fail, but can send less frames if there's no enough free descriptors * available. The actual free space is returned by @prep from the driver. */ -static __always_inline u32 +static __always_inline __nocfi_generic u32 libeth_xdp_tx_xmit_bulk(const struct libeth_xdp_tx_frame *bulk, void *xdpsq, u32 n, bool unroll, u64 priv, u32 (*prep)(void *xdpsq, struct libeth_xdpsq *sq), diff --git a/include/net/pkt_cls.h b/include/net/pkt_cls.h index c64fd896b1f9..99ac747b7906 100644 --- a/include/net/pkt_cls.h +++ b/include/net/pkt_cls.h @@ -536,6 +536,8 @@ static inline unsigned char * tcf_get_base_ptr(struct sk_buff *skb, int layer) case TCF_LAYER_NETWORK: return skb_network_header(skb); case TCF_LAYER_TRANSPORT: + if (!skb_transport_header_was_set(skb)) + break; return skb_transport_header(skb); } diff --git a/include/net/tcp.h b/include/net/tcp.h index 5ca230ed526a..ab20f549b8f9 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -370,7 +370,7 @@ void tcp_delack_timer_handler(struct sock *sk); int tcp_ioctl(struct sock *sk, int cmd, int *karg); enum skb_drop_reason tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); -void tcp_rcvbuf_grow(struct sock *sk); +void tcp_rcvbuf_grow(struct sock *sk, u32 newval); void tcp_rcv_space_adjust(struct sock *sk); int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp); void tcp_twsk_destructor(struct sock *sk); diff --git a/include/net/tls.h b/include/net/tls.h index 857340338b69..c7bcdb3afad7 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -451,25 +451,26 @@ static inline void tls_offload_rx_resync_request(struct sock *sk, __be32 seq) /* Log all TLS record header TCP sequences in [seq, seq+len] */ static inline void -tls_offload_rx_resync_async_request_start(struct sock *sk, __be32 seq, u16 len) +tls_offload_rx_resync_async_request_start(struct tls_offload_resync_async *resync_async, + __be32 seq, u16 len) { - struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx); - - atomic64_set(&rx_ctx->resync_async->req, ((u64)ntohl(seq) << 32) | + atomic64_set(&resync_async->req, ((u64)ntohl(seq) << 32) | ((u64)len << 16) | RESYNC_REQ | RESYNC_REQ_ASYNC); - rx_ctx->resync_async->loglen = 0; - rx_ctx->resync_async->rcd_delta = 0; + resync_async->loglen = 0; + resync_async->rcd_delta = 0; } static inline void -tls_offload_rx_resync_async_request_end(struct sock *sk, __be32 seq) +tls_offload_rx_resync_async_request_end(struct tls_offload_resync_async *resync_async, + __be32 seq) { - struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_offload_context_rx *rx_ctx = tls_offload_ctx_rx(tls_ctx); + atomic64_set(&resync_async->req, ((u64)ntohl(seq) << 32) | RESYNC_REQ); +} - atomic64_set(&rx_ctx->resync_async->req, - ((u64)ntohl(seq) << 32) | RESYNC_REQ); +static inline void +tls_offload_rx_resync_async_request_cancel(struct tls_offload_resync_async *resync_async) +{ + atomic64_set(&resync_async->req, 0); } static inline void diff --git a/include/net/xfrm.h b/include/net/xfrm.h index f3014e4f54fc..0a14daaa5dd4 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -536,7 +536,8 @@ static inline int xfrm_af2proto(unsigned int family) static inline const struct xfrm_mode *xfrm_ip2inner_mode(struct xfrm_state *x, int ipproto) { - if ((ipproto == IPPROTO_IPIP && x->props.family == AF_INET) || + if ((x->sel.family != AF_UNSPEC) || + (ipproto == IPPROTO_IPIP && x->props.family == AF_INET) || (ipproto == IPPROTO_IPV6 && x->props.family == AF_INET6)) return &x->inner_mode; else diff --git a/include/scsi/scsi_device.h b/include/scsi/scsi_device.h index 6d6500148c4b..993008cdea65 100644 --- a/include/scsi/scsi_device.h +++ b/include/scsi/scsi_device.h @@ -252,8 +252,8 @@ struct scsi_device { unsigned int queue_stopped; /* request queue is quiesced */ bool offline_already; /* Device offline message logged */ - unsigned int ua_new_media_ctr; /* Counter for New Media UNIT ATTENTIONs */ - unsigned int ua_por_ctr; /* Counter for Power On / Reset UAs */ + atomic_t ua_new_media_ctr; /* Counter for New Media UNIT ATTENTIONs */ + atomic_t ua_por_ctr; /* Counter for Power On / Reset UAs */ atomic_t disk_events_disable_depth; /* disable depth for disk events */ @@ -693,10 +693,8 @@ static inline int scsi_device_busy(struct scsi_device *sdev) } /* Macros to access the UNIT ATTENTION counters */ -#define scsi_get_ua_new_media_ctr(sdev) \ - ((const unsigned int)(sdev->ua_new_media_ctr)) -#define scsi_get_ua_por_ctr(sdev) \ - ((const unsigned int)(sdev->ua_por_ctr)) +#define scsi_get_ua_new_media_ctr(sdev) atomic_read(&sdev->ua_new_media_ctr) +#define scsi_get_ua_por_ctr(sdev) atomic_read(&sdev->ua_por_ctr) #define MODULE_ALIAS_SCSI_DEVICE(type) \ MODULE_ALIAS("scsi:t-" __stringify(type) "*") diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h index ddd997ac3216..0fbcdb15c74b 100644 --- a/include/sound/tas2781.h +++ b/include/sound/tas2781.h @@ -120,8 +120,11 @@ enum audio_device { TAS2570, TAS2572, TAS2781, + TAS5802, + TAS5815, TAS5825, TAS5827, + TAS5828, TAS_OTHERS, }; diff --git a/include/trace/events/rseq.h b/include/trace/events/rseq.h index 823b47d1ba1e..ce85d650bf4b 100644 --- a/include/trace/events/rseq.h +++ b/include/trace/events/rseq.h @@ -21,9 +21,9 @@ TRACE_EVENT(rseq_update, ), TP_fast_assign( - __entry->cpu_id = raw_smp_processor_id(); + __entry->cpu_id = t->rseq.ids.cpu_id; __entry->node_id = cpu_to_node(__entry->cpu_id); - __entry->mm_cid = task_mm_cid(t); + __entry->mm_cid = t->rseq.ids.mm_cid; ), TP_printk("cpu_id=%d node_id=%d mm_cid=%d", __entry->cpu_id, diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 9d2c36c6a0ed..6757233bd064 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -218,6 +218,9 @@ TRACE_EVENT(tcp_rcvbuf_grow, __field(__u32, space) __field(__u32, ooo_space) __field(__u32, rcvbuf) + __field(__u32, rcv_ssthresh) + __field(__u32, window_clamp) + __field(__u32, rcv_wnd) __field(__u8, scaling_ratio) __field(__u16, sport) __field(__u16, dport) @@ -245,6 +248,9 @@ TRACE_EVENT(tcp_rcvbuf_grow, tp->rcv_nxt; __entry->rcvbuf = sk->sk_rcvbuf; + __entry->rcv_ssthresh = tp->rcv_ssthresh; + __entry->window_clamp = tp->window_clamp; + __entry->rcv_wnd = tp->rcv_wnd; __entry->scaling_ratio = tp->scaling_ratio; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); @@ -264,11 +270,14 @@ TRACE_EVENT(tcp_rcvbuf_grow, ), TP_printk("time=%u rtt_us=%u copied=%u inq=%u space=%u ooo=%u scaling_ratio=%u rcvbuf=%u " + "rcv_ssthresh=%u window_clamp=%u rcv_wnd=%u " "family=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 " "saddrv6=%pI6c daddrv6=%pI6c skaddr=%p sock_cookie=%llx", __entry->time, __entry->rtt_us, __entry->copied, __entry->inq, __entry->space, __entry->ooo_space, __entry->scaling_ratio, __entry->rcvbuf, + __entry->rcv_ssthresh, __entry->window_clamp, + __entry->rcv_wnd, show_family_name(__entry->family), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, diff --git a/include/trace/events/timer_migration.h b/include/trace/events/timer_migration.h index 47db5eaf2f9a..61171b13c687 100644 --- a/include/trace/events/timer_migration.h +++ b/include/trace/events/timer_migration.h @@ -173,14 +173,14 @@ DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_active, TP_ARGS(tmc) ); -DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_online, +DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_available, TP_PROTO(struct tmigr_cpu *tmc), TP_ARGS(tmc) ); -DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_offline, +DEFINE_EVENT(tmigr_cpugroup, tmigr_cpu_unavailable, TP_PROTO(struct tmigr_cpu *tmc), diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h index c08aff044e80..311a341e6fe4 100644 --- a/include/trace/events/writeback.h +++ b/include/trace/events/writeback.h @@ -120,7 +120,7 @@ DECLARE_EVENT_CLASS(writeback_dirty_inode_template, /* may be called for files on pseudo FSes w/ unregistered bdi */ strscpy_pad(__entry->name, bdi_dev_name(bdi), 32); __entry->ino = inode->i_ino; - __entry->state = inode->i_state; + __entry->state = inode_state_read_once(inode); __entry->flags = flags; ), @@ -748,7 +748,7 @@ TRACE_EVENT(writeback_sb_inodes_requeue, strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; - __entry->state = inode->i_state; + __entry->state = inode_state_read_once(inode); __entry->dirtied_when = inode->dirtied_when; __entry->cgroup_ino = __trace_wb_assign_cgroup(inode_to_wb(inode)); ), @@ -787,7 +787,7 @@ DECLARE_EVENT_CLASS(writeback_single_inode_template, strscpy_pad(__entry->name, bdi_dev_name(inode_to_bdi(inode)), 32); __entry->ino = inode->i_ino; - __entry->state = inode->i_state; + __entry->state = inode_state_read_once(inode); __entry->dirtied_when = inode->dirtied_when; __entry->writeback_index = inode->i_mapping->writeback_index; __entry->nr_to_write = nr_to_write; @@ -839,7 +839,7 @@ DECLARE_EVENT_CLASS(writeback_inode_template, TP_fast_assign( __entry->dev = inode->i_sb->s_dev; __entry->ino = inode->i_ino; - __entry->state = inode->i_state; + __entry->state = inode_state_read_once(inode); __entry->mode = inode->i_mode; __entry->dirtied_when = inode->dirtied_when; ), diff --git a/include/uapi/asm-generic/posix_types.h b/include/uapi/asm-generic/posix_types.h index b5f7594eee7a..0a90ad92dbf3 100644 --- a/include/uapi/asm-generic/posix_types.h +++ b/include/uapi/asm-generic/posix_types.h @@ -86,6 +86,7 @@ typedef struct { */ typedef __kernel_long_t __kernel_off_t; typedef long long __kernel_loff_t; +typedef unsigned long long __kernel_uoff_t; typedef __kernel_long_t __kernel_old_time_t; #ifndef __KERNEL__ typedef __kernel_long_t __kernel_time_t; diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h index 04e0077fb4c9..942370b3f5d2 100644 --- a/include/uapi/asm-generic/unistd.h +++ b/include/uapi/asm-generic/unistd.h @@ -857,9 +857,11 @@ __SYSCALL(__NR_open_tree_attr, sys_open_tree_attr) __SYSCALL(__NR_file_getattr, sys_file_getattr) #define __NR_file_setattr 469 __SYSCALL(__NR_file_setattr, sys_file_setattr) +#define __NR_listns 470 +__SYSCALL(__NR_listns, sys_listns) #undef __NR_syscalls -#define __NR_syscalls 470 +#define __NR_syscalls 471 /* * 32 bit systems traditionally used different diff --git a/include/uapi/drm/amdgpu_drm.h b/include/uapi/drm/amdgpu_drm.h index cd7402e36b6d..406a42be429b 100644 --- a/include/uapi/drm/amdgpu_drm.h +++ b/include/uapi/drm/amdgpu_drm.h @@ -1555,27 +1555,6 @@ struct drm_amdgpu_info_hw_ip { __u32 userq_num_slots; }; -/* GFX metadata BO sizes and alignment info (in bytes) */ -struct drm_amdgpu_info_uq_fw_areas_gfx { - /* shadow area size */ - __u32 shadow_size; - /* shadow area base virtual mem alignment */ - __u32 shadow_alignment; - /* context save area size */ - __u32 csa_size; - /* context save area base virtual mem alignment */ - __u32 csa_alignment; -}; - -/* IP specific fw related information used in the - * subquery AMDGPU_INFO_UQ_FW_AREAS - */ -struct drm_amdgpu_info_uq_fw_areas { - union { - struct drm_amdgpu_info_uq_fw_areas_gfx gfx; - }; -}; - struct drm_amdgpu_info_num_handles { /** Max handles as supported by firmware for UVD */ __u32 uvd_max_handles; diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h index ea91aa8afde9..e527b24bd824 100644 --- a/include/uapi/drm/drm_fourcc.h +++ b/include/uapi/drm/drm_fourcc.h @@ -979,14 +979,20 @@ extern "C" { * 2 = Gob Height 8, Turing+ Page Kind mapping * 3 = Reserved for future use. * - * 22:22 s Sector layout. On Tegra GPUs prior to Xavier, there is a further - * bit remapping step that occurs at an even lower level than the - * page kind and block linear swizzles. This causes the layout of - * surfaces mapped in those SOC's GPUs to be incompatible with the - * equivalent mapping on other GPUs in the same system. - * - * 0 = Tegra K1 - Tegra Parker/TX2 Layout. - * 1 = Desktop GPU and Tegra Xavier+ Layout + * 22:22 s Sector layout. There is a further bit remapping step that occurs + * 26:27 at an even lower level than the page kind and block linear + * swizzles. This causes the bit arrangement of surfaces in memory + * to differ subtly, and prevents direct sharing of surfaces between + * GPUs with different layouts. + * + * 0 = Tegra K1 - Tegra Parker/TX2 Layout + * 1 = Pre-GB20x, GB20x 32+ bpp, GB10, Tegra Xavier-Orin Layout + * 2 = GB20x(Blackwell 2)+ 8 bpp surface layout + * 3 = GB20x(Blackwell 2)+ 16 bpp surface layout + * 4 = Reserved for future use. + * 5 = Reserved for future use. + * 6 = Reserved for future use. + * 7 = Reserved for future use. * * 25:23 c Lossless Framebuffer Compression type. * @@ -1001,7 +1007,7 @@ extern "C" { * 6 = Reserved for future use * 7 = Reserved for future use * - * 55:25 - Reserved for future use. Must be zero. + * 55:28 - Reserved for future use. Must be zero. */ #define DRM_FORMAT_MOD_NVIDIA_BLOCK_LINEAR_2D(c, s, g, k, h) \ fourcc_mod_code(NVIDIA, (0x10 | \ @@ -1009,6 +1015,7 @@ extern "C" { (((k) & 0xff) << 12) | \ (((g) & 0x3) << 20) | \ (((s) & 0x1) << 22) | \ + (((s) & 0x6) << 25) | \ (((c) & 0x7) << 23))) /* To grandfather in prior block linear format modifiers to the above layout, diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h index 40ff19f52a8d..517489a7ec60 100644 --- a/include/uapi/drm/xe_drm.h +++ b/include/uapi/drm/xe_drm.h @@ -1013,6 +1013,20 @@ struct drm_xe_vm_destroy { * valid on VMs with DRM_XE_VM_CREATE_FLAG_FAULT_MODE set. The CPU address * mirror flag are only valid for DRM_XE_VM_BIND_OP_MAP operations, the BO * handle MBZ, and the BO offset MBZ. + * - %DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET - Can be used in combination with + * %DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR to reset madvises when the underlying + * CPU address space range is unmapped (typically with munmap(2) or brk(2)). + * The madvise values set with &DRM_IOCTL_XE_MADVISE are reset to the values + * that were present immediately after the &DRM_IOCTL_XE_VM_BIND. + * The reset GPU virtual address range is the intersection of the range bound + * using &DRM_IOCTL_XE_VM_BIND and the virtual CPU address space range + * unmapped. + * This functionality is present to mimic the behaviour of CPU address space + * madvises set using madvise(2), which are typically reset on unmap. + * Note: free(3) may or may not call munmap(2) and/or brk(2), and may thus + * not invoke autoreset. Neither will stack variables going out of scope. + * Therefore it's recommended to always explicitly reset the madvises when + * freeing the memory backing a region used in a &DRM_IOCTL_XE_MADVISE call. * * The @prefetch_mem_region_instance for %DRM_XE_VM_BIND_OP_PREFETCH can also be: * - %DRM_XE_CONSULT_MEM_ADVISE_PREF_LOC, which ensures prefetching occurs in @@ -1119,6 +1133,7 @@ struct drm_xe_vm_bind_op { #define DRM_XE_VM_BIND_FLAG_DUMPABLE (1 << 3) #define DRM_XE_VM_BIND_FLAG_CHECK_PXP (1 << 4) #define DRM_XE_VM_BIND_FLAG_CPU_ADDR_MIRROR (1 << 5) +#define DRM_XE_VM_BIND_FLAG_MADVISE_AUTORESET (1 << 6) /** @flags: Bind flags */ __u32 flags; diff --git a/include/uapi/linux/fb.h b/include/uapi/linux/fb.h index cde8f173f566..22acaaec7b1c 100644 --- a/include/uapi/linux/fb.h +++ b/include/uapi/linux/fb.h @@ -319,7 +319,7 @@ enum { #define FB_VBLANK_HAVE_VCOUNT 0x020 /* the vcount field is valid */ #define FB_VBLANK_HAVE_HCOUNT 0x040 /* the hcount field is valid */ #define FB_VBLANK_VSYNCING 0x080 /* currently in a vsync */ -#define FB_VBLANK_HAVE_VSYNC 0x100 /* verical syncs can be detected */ +#define FB_VBLANK_HAVE_VSYNC 0x100 /* vertical syncs can be detected */ struct fb_vblank { __u32 flags; /* FB_VBLANK flags */ diff --git a/include/uapi/linux/fcntl.h b/include/uapi/linux/fcntl.h index 3741ea1b73d8..5e277fd955aa 100644 --- a/include/uapi/linux/fcntl.h +++ b/include/uapi/linux/fcntl.h @@ -4,6 +4,11 @@ #include <asm/fcntl.h> #include <linux/openat2.h> +#ifdef __KERNEL__ +#include <linux/types.h> +#else +#include <stdint.h> +#endif #define F_SETLEASE (F_LINUX_SPECIFIC_BASE + 0) #define F_GETLEASE (F_LINUX_SPECIFIC_BASE + 1) @@ -79,6 +84,17 @@ */ #define RWF_WRITE_LIFE_NOT_SET RWH_WRITE_LIFE_NOT_SET +/* Set/Get delegations */ +#define F_GETDELEG (F_LINUX_SPECIFIC_BASE + 15) +#define F_SETDELEG (F_LINUX_SPECIFIC_BASE + 16) + +/* Argument structure for F_GETDELEG and F_SETDELEG */ +struct delegation { + uint32_t d_flags; /* Must be 0 */ + uint16_t d_type; /* F_RDLCK, F_WRLCK, F_UNLCK */ + uint16_t __pad; /* Must be 0 */ +}; + /* * Types of directory notifications that may be requested. */ diff --git a/include/uapi/linux/input-event-codes.h b/include/uapi/linux/input-event-codes.h index 4a9fbf42aa9f..30f3c9eaafaa 100644 --- a/include/uapi/linux/input-event-codes.h +++ b/include/uapi/linux/input-event-codes.h @@ -27,7 +27,7 @@ #define INPUT_PROP_TOPBUTTONPAD 0x04 /* softbuttons at top of pad */ #define INPUT_PROP_POINTING_STICK 0x05 /* is a pointing stick */ #define INPUT_PROP_ACCELEROMETER 0x06 /* has accelerometer */ -#define INPUT_PROP_HAPTIC_TOUCHPAD 0x07 /* is a haptic touchpad */ +#define INPUT_PROP_PRESSUREPAD 0x07 /* pressure triggers clicks */ #define INPUT_PROP_MAX 0x1f #define INPUT_PROP_CNT (INPUT_PROP_MAX + 1) @@ -631,6 +631,18 @@ #define KEY_BRIGHTNESS_MIN 0x250 /* Set Brightness to Minimum */ #define KEY_BRIGHTNESS_MAX 0x251 /* Set Brightness to Maximum */ +/* + * Keycodes for hotkeys toggling the electronic privacy screen found on some + * laptops on/off. Note when the embedded-controller turns on/off the eprivacy + * screen itself then the state should be reported through drm connecter props: + * https://www.kernel.org/doc/html/latest/gpu/drm-kms.html#standard-connector-properties + * Except when implementing the drm connecter properties API is not possible + * because e.g. the firmware does not allow querying the presence and/or status + * of the eprivacy screen at boot. + */ +#define KEY_EPRIVACY_SCREEN_ON 0x252 +#define KEY_EPRIVACY_SCREEN_OFF 0x253 + #define KEY_KBDINPUTASSIST_PREV 0x260 #define KEY_KBDINPUTASSIST_NEXT 0x261 #define KEY_KBDINPUTASSIST_PREVGROUP 0x262 diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h index 263bed13473e..b7c8dad26690 100644 --- a/include/uapi/linux/io_uring.h +++ b/include/uapi/linux/io_uring.h @@ -689,9 +689,6 @@ enum io_uring_register_op { /* query various aspects of io_uring, see linux/io_uring/query.h */ IORING_REGISTER_QUERY = 35, - /* return zcrx buffers back into circulation */ - IORING_REGISTER_ZCRX_REFILL = 36, - /* this goes last */ IORING_REGISTER_LAST, @@ -1073,15 +1070,6 @@ struct io_uring_zcrx_ifq_reg { __u64 __resv[3]; }; -struct io_uring_zcrx_sync_refill { - __u32 zcrx_id; - /* the number of entries to return */ - __u32 nr_entries; - /* pointer to an array of struct io_uring_zcrx_rqe */ - __u64 rqes; - __u64 __resv[2]; -}; - #ifdef __cplusplus } #endif diff --git a/include/uapi/linux/io_uring/query.h b/include/uapi/linux/io_uring/query.h index 5d754322a27c..3539ccbfd064 100644 --- a/include/uapi/linux/io_uring/query.h +++ b/include/uapi/linux/io_uring/query.h @@ -36,6 +36,9 @@ struct io_uring_query_opcode { __u64 enter_flags; /* Bitmask of all supported IOSQE_* flags */ __u64 sqe_flags; + /* The number of available query opcodes */ + __u32 nr_query_opcodes; + __u32 __pad; }; #endif diff --git a/include/uapi/linux/isst_if.h b/include/uapi/linux/isst_if.h index 8197a4800604..40aa545101a3 100644 --- a/include/uapi/linux/isst_if.h +++ b/include/uapi/linux/isst_if.h @@ -52,7 +52,7 @@ struct isst_if_cpu_map { /** * struct isst_if_cpu_maps - structure for CPU map IOCTL * @cmd_count: Number of CPU mapping command in cpu_map[] - * @cpu_map[]: Holds one or more CPU map data structure + * @cpu_map: Holds one or more CPU map data structure * * This structure used with ioctl ISST_IF_GET_PHY_ID to send * one or more CPU mapping commands. Here IOCTL return value indicates @@ -82,8 +82,8 @@ struct isst_if_io_reg { /** * struct isst_if_io_regs - structure for IO register commands - * @cmd_count: Number of io reg commands in io_reg[] - * @io_reg[]: Holds one or more io_reg command structure + * @req_count: Number of io reg commands in io_reg[] + * @io_reg: Holds one or more io_reg command structure * * This structure used with ioctl ISST_IF_IO_CMD to send * one or more read/write commands to PUNIT. Here IOCTL return value @@ -120,7 +120,7 @@ struct isst_if_mbox_cmd { /** * struct isst_if_mbox_cmds - structure for mailbox commands * @cmd_count: Number of mailbox commands in mbox_cmd[] - * @mbox_cmd[]: Holds one or more mbox commands + * @mbox_cmd: Holds one or more mbox commands * * This structure used with ioctl ISST_IF_MBOX_COMMAND to send * one or more mailbox commands to PUNIT. Here IOCTL return value @@ -152,7 +152,7 @@ struct isst_if_msr_cmd { /** * struct isst_if_msr_cmds - structure for msr commands * @cmd_count: Number of mailbox commands in msr_cmd[] - * @msr_cmd[]: Holds one or more msr commands + * @msr_cmd: Holds one or more msr commands * * This structure used with ioctl ISST_IF_MSR_COMMAND to send * one or more MSR commands. IOCTL return value indicates number of @@ -167,8 +167,9 @@ struct isst_if_msr_cmds { * struct isst_core_power - Structure to get/set core_power feature * @get_set: 0: Get, 1: Set * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @enable: Feature enable status + * @supported: Power domain supports SST_CP interface * @priority_type: Priority type for the feature (ordered/proportional) * * Structure to get/set core_power feature state using IOCTL @@ -187,11 +188,11 @@ struct isst_core_power { * struct isst_clos_param - Structure to get/set clos praram * @get_set: 0: Get, 1: Set * @socket_id: Socket/package id - * @power_domain: Power Domain id - * clos: Clos ID for the parameters - * min_freq_mhz: Minimum frequency in MHz - * max_freq_mhz: Maximum frequency in MHz - * prop_prio: Proportional priority from 0-15 + * @power_domain_id: Power Domain id + * @clos: Clos ID for the parameters + * @min_freq_mhz: Minimum frequency in MHz + * @max_freq_mhz: Maximum frequency in MHz + * @prop_prio: Proportional priority from 0-15 * * Structure to get/set per clos property using IOCTL * ISST_IF_CLOS_PARAM. @@ -209,7 +210,7 @@ struct isst_clos_param { /** * struct isst_if_clos_assoc - Structure to assign clos to a CPU * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @logical_cpu: CPU number * @clos: Clos ID to assign to the logical CPU * @@ -228,6 +229,7 @@ struct isst_if_clos_assoc { * @get_set: Request is for get or set * @punit_cpu_map: Set to 1 if the CPU number is punit numbering not * Linux CPU number + * @assoc_info: CLOS data for this CPU * * Structure used to get/set associate CPUs to clos using IOCTL * ISST_IF_CLOS_ASSOC. @@ -257,7 +259,7 @@ struct isst_tpmi_instance_count { /** * struct isst_perf_level_info - Structure to get information on SST-PP levels * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @logical_cpu: CPU number * @clos: Clos ID to assign to the logical CPU * @max_level: Maximum performance level supported by the platform @@ -267,8 +269,8 @@ struct isst_tpmi_instance_count { * @feature_state: SST-BF and SST-TF (enabled/disabled) status at current level * @locked: SST-PP performance level change is locked/unlocked * @enabled: SST-PP feature is enabled or not - * @sst-tf_support: SST-TF support status at this level - * @sst-bf_support: SST-BF support status at this level + * @sst_tf_support: SST-TF support status at this level + * @sst_bf_support: SST-BF support status at this level * * Structure to get SST-PP details using IOCTL ISST_IF_PERF_LEVELS. */ @@ -289,7 +291,7 @@ struct isst_perf_level_info { /** * struct isst_perf_level_control - Structure to set SST-PP level * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @level: level to set * * Structure used change SST-PP level using IOCTL ISST_IF_PERF_SET_LEVEL. @@ -303,7 +305,7 @@ struct isst_perf_level_control { /** * struct isst_perf_feature_control - Structure to activate SST-BF/SST-TF * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @feature: bit 0 = SST-BF state, bit 1 = SST-TF state * * Structure used to enable SST-BF/SST-TF using IOCTL ISST_IF_PERF_SET_FEATURE. @@ -320,7 +322,7 @@ struct isst_perf_feature_control { /** * struct isst_perf_level_data_info - Structure to get SST-PP level details * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @level: SST-PP level for which caller wants to get information * @tdp_ratio: TDP Ratio * @base_freq_mhz: Base frequency in MHz @@ -341,8 +343,8 @@ struct isst_perf_feature_control { * @pm_fabric_freq_mhz: Fabric (Uncore) minimum frequency * @max_buckets: Maximum trl buckets * @max_trl_levels: Maximum trl levels - * @bucket_core_counts[TRL_MAX_BUCKETS]: Number of cores per bucket - * @trl_freq_mhz[TRL_MAX_LEVELS][TRL_MAX_BUCKETS]: maximum frequency + * @bucket_core_counts: Number of cores per bucket + * @trl_freq_mhz: maximum frequency * for a bucket and trl level * * Structure used to get information on frequencies and TDP for a SST-PP @@ -402,7 +404,7 @@ struct isst_perf_level_fabric_info { /** * struct isst_perf_level_cpu_mask - Structure to get SST-PP level CPU mask * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @level: SST-PP level for which caller wants to get information * @punit_cpu_map: Set to 1 if the CPU number is punit numbering not * Linux CPU number. If 0 CPU buffer is copied to user space @@ -430,7 +432,7 @@ struct isst_perf_level_cpu_mask { /** * struct isst_base_freq_info - Structure to get SST-BF frequencies * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @level: SST-PP level for which caller wants to get information * @high_base_freq_mhz: High priority CPU base frequency * @low_base_freq_mhz: Low priority CPU base frequency @@ -453,9 +455,11 @@ struct isst_base_freq_info { /** * struct isst_turbo_freq_info - Structure to get SST-TF frequencies * @socket_id: Socket/package id - * @power_domain: Power Domain id + * @power_domain_id: Power Domain id * @level: SST-PP level for which caller wants to get information * @max_clip_freqs: Maximum number of low priority core clipping frequencies + * @max_buckets: Maximum trl buckets + * @max_trl_levels: Maximum trl levels * @lp_clip_freq_mhz: Clip frequencies per trl level * @bucket_core_counts: Maximum number of cores for a bucket * @trl_freq_mhz: Frequencies per trl level for each bucket diff --git a/include/uapi/linux/kvm.h b/include/uapi/linux/kvm.h index 6efa98a57ec1..52f6000ab020 100644 --- a/include/uapi/linux/kvm.h +++ b/include/uapi/linux/kvm.h @@ -962,7 +962,7 @@ struct kvm_enable_cap { #define KVM_CAP_ARM_EL2_E2H0 241 #define KVM_CAP_RISCV_MP_STATE_RESET 242 #define KVM_CAP_ARM_CACHEABLE_PFNMAP_SUPPORTED 243 -#define KVM_CAP_GUEST_MEMFD_MMAP 244 +#define KVM_CAP_GUEST_MEMFD_FLAGS 244 struct kvm_irq_routing_irqchip { __u32 irqchip; @@ -1599,7 +1599,8 @@ struct kvm_memory_attributes { #define KVM_MEMORY_ATTRIBUTE_PRIVATE (1ULL << 3) #define KVM_CREATE_GUEST_MEMFD _IOWR(KVMIO, 0xd4, struct kvm_create_guest_memfd) -#define GUEST_MEMFD_FLAG_MMAP (1ULL << 0) +#define GUEST_MEMFD_FLAG_MMAP (1ULL << 0) +#define GUEST_MEMFD_FLAG_INIT_SHARED (1ULL << 1) struct kvm_create_guest_memfd { __u64 size; diff --git a/include/uapi/linux/mount.h b/include/uapi/linux/mount.h index 7fa67c2031a5..5d3f8c9e3a62 100644 --- a/include/uapi/linux/mount.h +++ b/include/uapi/linux/mount.h @@ -197,7 +197,7 @@ struct statmount { */ struct mnt_id_req { __u32 size; - __u32 spare; + __u32 mnt_ns_fd; __u64 mnt_id; __u64 param; __u64 mnt_ns_id; diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h index e098759ec917..a25e38d1c874 100644 --- a/include/uapi/linux/nsfs.h +++ b/include/uapi/linux/nsfs.h @@ -67,4 +67,62 @@ struct nsfs_file_handle { #define NSFS_FILE_HANDLE_SIZE_VER0 16 /* sizeof first published struct */ #define NSFS_FILE_HANDLE_SIZE_LATEST sizeof(struct nsfs_file_handle) /* sizeof latest published struct */ +enum init_ns_id { + IPC_NS_INIT_ID = 1ULL, + UTS_NS_INIT_ID = 2ULL, + USER_NS_INIT_ID = 3ULL, + PID_NS_INIT_ID = 4ULL, + CGROUP_NS_INIT_ID = 5ULL, + TIME_NS_INIT_ID = 6ULL, + NET_NS_INIT_ID = 7ULL, + MNT_NS_INIT_ID = 8ULL, +#ifdef __KERNEL__ + NS_LAST_INIT_ID = MNT_NS_INIT_ID, +#endif +}; + +enum ns_type { + TIME_NS = (1ULL << 7), /* CLONE_NEWTIME */ + MNT_NS = (1ULL << 17), /* CLONE_NEWNS */ + CGROUP_NS = (1ULL << 25), /* CLONE_NEWCGROUP */ + UTS_NS = (1ULL << 26), /* CLONE_NEWUTS */ + IPC_NS = (1ULL << 27), /* CLONE_NEWIPC */ + USER_NS = (1ULL << 28), /* CLONE_NEWUSER */ + PID_NS = (1ULL << 29), /* CLONE_NEWPID */ + NET_NS = (1ULL << 30), /* CLONE_NEWNET */ +}; + +/** + * struct ns_id_req - namespace ID request structure + * @size: size of this structure + * @spare: reserved for future use + * @filter: filter mask + * @ns_id: last namespace id + * @user_ns_id: owning user namespace ID + * + * Structure for passing namespace ID and miscellaneous parameters to + * statns(2) and listns(2). + * + * For statns(2) @param represents the request mask. + * For listns(2) @param represents the last listed mount id (or zero). + */ +struct ns_id_req { + __u32 size; + __u32 spare; + __u64 ns_id; + struct /* listns */ { + __u32 ns_type; + __u32 spare2; + __u64 user_ns_id; + }; +}; + +/* + * Special @user_ns_id value that can be passed to listns() + */ +#define LISTNS_CURRENT_USER 0xffffffffffffffff /* Caller's userns */ + +/* List of all ns_id_req versions. */ +#define NS_ID_REQ_SIZE_VER0 32 /* sizeof first published struct */ + #endif /* __LINUX_NSFS_H */ diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index 78a362b80027..d292f96bc06f 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -463,7 +463,9 @@ struct perf_event_attr { inherit_thread : 1, /* children only inherit if cloned with CLONE_THREAD */ remove_on_exec : 1, /* event is removed from task on exec */ sigtrap : 1, /* send synchronous SIGTRAP on event */ - __reserved_1 : 26; + defer_callchain: 1, /* request PERF_RECORD_CALLCHAIN_DEFERRED records */ + defer_output : 1, /* output PERF_RECORD_CALLCHAIN_DEFERRED records */ + __reserved_1 : 24; union { __u32 wakeup_events; /* wake up every n events */ @@ -1239,6 +1241,22 @@ enum perf_event_type { */ PERF_RECORD_AUX_OUTPUT_HW_ID = 21, + /* + * This user callchain capture was deferred until shortly before + * returning to user space. Previous samples would have kernel + * callchains only and they need to be stitched with this to make full + * callchains. + * + * struct { + * struct perf_event_header header; + * u64 cookie; + * u64 nr; + * u64 ips[nr]; + * struct sample_id sample_id; + * }; + */ + PERF_RECORD_CALLCHAIN_DEFERRED = 22, + PERF_RECORD_MAX, /* non-ABI */ }; @@ -1269,6 +1287,7 @@ enum perf_callchain_context { PERF_CONTEXT_HV = (__u64)-32, PERF_CONTEXT_KERNEL = (__u64)-128, PERF_CONTEXT_USER = (__u64)-512, + PERF_CONTEXT_USER_DEFERRED = (__u64)-640, PERF_CONTEXT_GUEST = (__u64)-2048, PERF_CONTEXT_GUEST_KERNEL = (__u64)-2176, diff --git a/include/uapi/linux/pidfd.h b/include/uapi/linux/pidfd.h index 957db425d459..ea9a6811fc76 100644 --- a/include/uapi/linux/pidfd.h +++ b/include/uapi/linux/pidfd.h @@ -26,8 +26,12 @@ #define PIDFD_INFO_CGROUPID (1UL << 2) /* Always returned if available, even if not requested */ #define PIDFD_INFO_EXIT (1UL << 3) /* Only returned if requested. */ #define PIDFD_INFO_COREDUMP (1UL << 4) /* Only returned if requested. */ +#define PIDFD_INFO_SUPPORTED_MASK (1UL << 5) /* Want/got supported mask flags */ +#define PIDFD_INFO_COREDUMP_SIGNAL (1UL << 6) /* Always returned if PIDFD_INFO_COREDUMP is requested. */ #define PIDFD_INFO_SIZE_VER0 64 /* sizeof first published struct */ +#define PIDFD_INFO_SIZE_VER1 72 /* sizeof second published struct */ +#define PIDFD_INFO_SIZE_VER2 80 /* sizeof third published struct */ /* * Values for @coredump_mask in pidfd_info. @@ -91,8 +95,11 @@ struct pidfd_info { __u32 fsuid; __u32 fsgid; __s32 exit_code; - __u32 coredump_mask; - __u32 __spare1; + struct /* coredump info */ { + __u32 coredump_mask; + __u32 coredump_signal; + }; + __u64 supported_mask; /* Mask flags that this kernel supports */ }; #define PIDFS_IOCTL_MAGIC 0xFF diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h index c233aae5eac9..1b76d508400c 100644 --- a/include/uapi/linux/rseq.h +++ b/include/uapi/linux/rseq.h @@ -114,20 +114,13 @@ struct rseq { /* * Restartable sequences flags field. * - * This field should only be updated by the thread which - * registered this data structure. Read by the kernel. - * Mainly used for single-stepping through rseq critical sections - * with debuggers. - * - * - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT - * Inhibit instruction sequence block restart on preemption - * for this thread. - * - RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL - * Inhibit instruction sequence block restart on signal - * delivery for this thread. - * - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE - * Inhibit instruction sequence block restart on migration for - * this thread. + * This field was initially intended to allow event masking for + * single-stepping through rseq critical sections with debuggers. + * The kernel does not support this anymore and the relevant bits + * are checked for being always false: + * - RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT + * - RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL + * - RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE */ __u32 flags; diff --git a/include/uapi/linux/tee.h b/include/uapi/linux/tee.h index 386ad36f1a0a..cab5cadca8ef 100644 --- a/include/uapi/linux/tee.h +++ b/include/uapi/linux/tee.h @@ -249,8 +249,9 @@ struct tee_ioctl_param { * @cancel_id: [in] Cancellation id, a unique value to identify this request * @session: [out] Session id * @ret: [out] return value - * @ret_origin [out] origin of the return value - * @num_params [in] number of parameters following this struct + * @ret_origin: [out] origin of the return value + * @num_params: [in] number of &struct tee_ioctl_param entries in @params + * @params: array of ioctl parameters */ struct tee_ioctl_open_session_arg { __u8 uuid[TEE_IOCTL_UUID_LEN]; @@ -276,14 +277,14 @@ struct tee_ioctl_open_session_arg { struct tee_ioctl_buf_data) /** - * struct tee_ioctl_invoke_func_arg - Invokes a function in a Trusted - * Application + * struct tee_ioctl_invoke_arg - Invokes a function in a Trusted Application * @func: [in] Trusted Application function, specific to the TA * @session: [in] Session id * @cancel_id: [in] Cancellation id, a unique value to identify this request * @ret: [out] return value - * @ret_origin [out] origin of the return value - * @num_params [in] number of parameters following this struct + * @ret_origin: [out] origin of the return value + * @num_params: [in] number of parameters following this struct + * @params: array of ioctl parameters */ struct tee_ioctl_invoke_arg { __u32 func; @@ -338,7 +339,8 @@ struct tee_ioctl_close_session_arg { /** * struct tee_iocl_supp_recv_arg - Receive a request for a supplicant function * @func: [in] supplicant function - * @num_params [in/out] number of parameters following this struct + * @num_params: [in/out] number of &struct tee_ioctl_param entries in @params + * @params: array of ioctl parameters * * @num_params is the number of params that tee-supplicant has room to * receive when input, @num_params is the number of actual params @@ -363,7 +365,8 @@ struct tee_iocl_supp_recv_arg { /** * struct tee_iocl_supp_send_arg - Send a response to a received request * @ret: [out] return value - * @num_params [in] number of parameters following this struct + * @num_params: [in] number of &struct tee_ioctl_param entries in @params + * @params: array of ioctl parameters */ struct tee_iocl_supp_send_arg { __u32 ret; @@ -454,11 +457,13 @@ struct tee_ioctl_shm_register_fd_data { */ /** - * struct tee_ioctl_invoke_func_arg - Invokes an object in a Trusted Application + * struct tee_ioctl_object_invoke_arg - Invokes an object in a + * Trusted Application * @id: [in] Object id * @op: [in] Object operation, specific to the object * @ret: [out] return value * @num_params: [in] number of parameters following this struct + * @params: array of ioctl parameters */ struct tee_ioctl_object_invoke_arg { __u64 id; diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h index 8bf27ab8bcb4..1db45b01532b 100644 --- a/include/uapi/linux/virtio_net.h +++ b/include/uapi/linux/virtio_net.h @@ -193,7 +193,8 @@ struct virtio_net_hdr_v1 { struct virtio_net_hdr_v1_hash { struct virtio_net_hdr_v1 hdr; - __le32 hash_value; + __le16 hash_value_lo; + __le16 hash_value_hi; #define VIRTIO_NET_HASH_REPORT_NONE 0 #define VIRTIO_NET_HASH_REPORT_IPv4 1 #define VIRTIO_NET_HASH_REPORT_TCPv4 2 diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h index 9425cfd9d00e..0f95576bf1f6 100644 --- a/include/ufs/ufshcd.h +++ b/include/ufs/ufshcd.h @@ -688,6 +688,13 @@ enum ufshcd_quirks { * single doorbell mode. */ UFSHCD_QUIRK_BROKEN_LSDBS_CAP = 1 << 25, + + /* + * This quirk indicates that DME_LINKSTARTUP should not be issued a 2nd + * time (refer link_startup_again) after the 1st time was successful, + * because it causes link startup to become unreliable. + */ + UFSHCD_QUIRK_PERFORM_LINK_STARTUP_ONCE = 1 << 26, }; enum ufshcd_caps { |