Merge remote-tracking branch 'torvalds/master' into perf/core

Minor conflict in tools/perf/arch/arm/util/auxtrace.c as one fix there
was cherry-picked for the last perf/urgent pull req to Linus, so was
already there.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

28 files changed, 146 insertions, 95 deletions

diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 7619742f91c9..5a828fde7a42 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -90,8 +90,8 @@ endif
 
 vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
 
-vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
+efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a
 
 # The compressed kernel is built with -fPIC/-fPIE so that a boot loader
 # can place it anywhere in memory and it will still run. However, since
@@ -115,7 +115,7 @@ endef
 quiet_cmd_check-and-link-vmlinux = LD      $@
       cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld)
 
-$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
+$(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE
 	$(call if_changed,check-and-link-vmlinux)
 
 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S
diff --git a/arch/x86/entry/Makefile b/arch/x86/entry/Makefile
index b7a5790d8d63..08bf95dbc911 100644
--- a/arch/x86/entry/Makefile
+++ b/arch/x86/entry/Makefile
@@ -7,12 +7,20 @@ KASAN_SANITIZE := n
 UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
-CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
-CFLAGS_REMOVE_syscall_32.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
-CFLAGS_REMOVE_syscall_64.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_common.o		= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_64.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_32.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_x32.o	= $(CC_FLAGS_FTRACE)
+
+CFLAGS_common.o			+= -fno-stack-protector
+CFLAGS_syscall_64.o		+= -fno-stack-protector
+CFLAGS_syscall_32.o		+= -fno-stack-protector
+CFLAGS_syscall_x32.o		+= -fno-stack-protector
 
 CFLAGS_syscall_64.o		+= $(call cc-option,-Wno-override-init,)
 CFLAGS_syscall_32.o		+= $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_x32.o		+= $(call cc-option,-Wno-override-init,)
+
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
 
diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
index e83b3f14897c..f09288431f28 100644
--- a/arch/x86/entry/common.c
+++ b/arch/x86/entry/common.c
@@ -46,7 +46,7 @@
 #include <trace/events/syscalls.h>
 
 /* Check that the stack and regs on entry from user mode are sane. */
-static void check_user_regs(struct pt_regs *regs)
+static noinstr void check_user_regs(struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) {
 		/*
@@ -294,7 +294,7 @@ static void __prepare_exit_to_usermode(struct pt_regs *regs)
 #endif
 }
 
-__visible noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
+static noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
 {
 	instrumentation_begin();
 	__prepare_exit_to_usermode(regs);
diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
index eeac6dc2adaa..80d3b30d3ee3 100644
--- a/arch/x86/include/asm/idtentry.h
+++ b/arch/x86/include/asm/idtentry.h
@@ -469,16 +469,15 @@ __visible noinstr void func(struct pt_regs *regs,			\
 	.align 8
 SYM_CODE_START(irq_entries_start)
     vector=FIRST_EXTERNAL_VECTOR
-    pos = .
     .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
 	UNWIND_HINT_IRET_REGS
+0 :
 	.byte	0x6a, vector
 	jmp	asm_common_interrupt
 	nop
 	/* Ensure that the above is 8 bytes max */
-	. = pos + 8
-    pos=pos+8
-    vector=vector+1
+	. = 0b + 8
+	vector = vector+1
     .endr
 SYM_CODE_END(irq_entries_start)
 
@@ -486,16 +485,15 @@ SYM_CODE_END(irq_entries_start)
 	.align 8
 SYM_CODE_START(spurious_entries_start)
     vector=FIRST_SYSTEM_VECTOR
-    pos = .
     .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
 	UNWIND_HINT_IRET_REGS
+0 :
 	.byte	0x6a, vector
 	jmp	asm_spurious_interrupt
 	nop
 	/* Ensure that the above is 8 bytes max */
-	. = pos + 8
-    pos=pos+8
-    vector=vector+1
+	. = 0b + 8
+	vector = vector+1
     .endr
 SYM_CODE_END(spurious_entries_start)
 #endif
@@ -553,7 +551,7 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_MC,	exc_machine_check);
 
 /* NMI */
 DECLARE_IDTENTRY_NMI(X86_TRAP_NMI,	exc_nmi);
-#ifdef CONFIG_XEN_PV
+#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64)
 DECLARE_IDTENTRY_RAW(X86_TRAP_NMI,	xenpv_exc_nmi);
 #endif
 
@@ -563,7 +561,7 @@ DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB,	exc_debug);
 #else
 DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	exc_debug);
 #endif
-#ifdef CONFIG_XEN_PV
+#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64)
 DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	xenpv_exc_debug);
 #endif
 
@@ -626,8 +624,8 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR,	sysvec_kvm_posted_intr_nested
 
 #if IS_ENABLED(CONFIG_HYPERV)
 DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_hyperv_callback);
-DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
-DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
 #endif
 
 #if IS_ENABLED(CONFIG_ACRN_GUEST)
diff --git a/arch/x86/include/asm/io_bitmap.h b/arch/x86/include/asm/io_bitmap.h
index ac1a99ffbd8d..7f080f5c7def 100644
--- a/arch/x86/include/asm/io_bitmap.h
+++ b/arch/x86/include/asm/io_bitmap.h
@@ -19,12 +19,28 @@ struct task_struct;
 void io_bitmap_share(struct task_struct *tsk);
 void io_bitmap_exit(struct task_struct *tsk);
 
+static inline void native_tss_invalidate_io_bitmap(void)
+{
+	/*
+	 * Invalidate the I/O bitmap by moving io_bitmap_base outside the
+	 * TSS limit so any subsequent I/O access from user space will
+	 * trigger a #GP.
+	 *
+	 * This is correct even when VMEXIT rewrites the TSS limit
+	 * to 0x67 as the only requirement is that the base points
+	 * outside the limit.
+	 */
+	this_cpu_write(cpu_tss_rw.x86_tss.io_bitmap_base,
+		       IO_BITMAP_OFFSET_INVALID);
+}
+
 void native_tss_update_io_bitmap(void);
 
 #ifdef CONFIG_PARAVIRT_XXL
 #include <asm/paravirt.h>
 #else
 #define tss_update_io_bitmap native_tss_update_io_bitmap
+#define tss_invalidate_io_bitmap native_tss_invalidate_io_bitmap
 #endif
 
 #else
diff --git a/arch/x86/include/asm/iosf_mbi.h b/arch/x86/include/asm/iosf_mbi.h
index 5270ff39b9af..a1911fea8739 100644
--- a/arch/x86/include/asm/iosf_mbi.h
+++ b/arch/x86/include/asm/iosf_mbi.h
@@ -39,6 +39,7 @@
 #define BT_MBI_UNIT_PMC		0x04
 #define BT_MBI_UNIT_GFX		0x06
 #define BT_MBI_UNIT_SMI		0x0C
+#define BT_MBI_UNIT_CCK		0x14
 #define BT_MBI_UNIT_USB		0x43
 #define BT_MBI_UNIT_SATA	0xA3
 #define BT_MBI_UNIT_PCIE	0xA6
diff --git a/arch/x86/include/asm/paravirt.h b/arch/x86/include/asm/paravirt.h
index 5ca5d297df75..3d2afecde50c 100644
--- a/arch/x86/include/asm/paravirt.h
+++ b/arch/x86/include/asm/paravirt.h
@@ -302,6 +302,11 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+static inline void tss_invalidate_io_bitmap(void)
+{
+	PVOP_VCALL0(cpu.invalidate_io_bitmap);
+}
+
 static inline void tss_update_io_bitmap(void)
 {
 	PVOP_VCALL0(cpu.update_io_bitmap);
diff --git a/arch/x86/include/asm/paravirt_types.h b/arch/x86/include/asm/paravirt_types.h
index 732f62e04ddb..8dfcb2508e6d 100644
--- a/arch/x86/include/asm/paravirt_types.h
+++ b/arch/x86/include/asm/paravirt_types.h
@@ -141,6 +141,7 @@ struct pv_cpu_ops {
 	void (*load_sp0)(unsigned long sp0);
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+	void (*invalidate_io_bitmap)(void);
 	void (*update_io_bitmap)(void);
 #endif
 
diff --git a/arch/x86/include/uapi/asm/kvm.h b/arch/x86/include/uapi/asm/kvm.h
index 17c5a038f42d..0780f97c1850 100644
--- a/arch/x86/include/uapi/asm/kvm.h
+++ b/arch/x86/include/uapi/asm/kvm.h
@@ -408,14 +408,15 @@ struct kvm_vmx_nested_state_data {
 };
 
 struct kvm_vmx_nested_state_hdr {
-	__u32 flags;
 	__u64 vmxon_pa;
 	__u64 vmcs12_pa;
-	__u64 preemption_timer_deadline;
 
 	struct {
 		__u16 flags;
 	} smm;
+
+	__u32 flags;
+	__u64 preemption_timer_deadline;
 };
 
 struct kvm_svm_nested_state_data {
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index ce61e3e7d399..81ffcfbfaef2 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -2316,12 +2316,12 @@ static int mp_irqdomain_create(int ioapic)
 	ip->irqdomain = irq_domain_create_linear(fn, hwirqs, cfg->ops,
 						 (void *)(long)ioapic);
 
-	/* Release fw handle if it was allocated above */
-	if (!cfg->dev)
-		irq_domain_free_fwnode(fn);
-
-	if (!ip->irqdomain)
+	if (!ip->irqdomain) {
+		/* Release fw handle if it was allocated above */
+		if (!cfg->dev)
+			irq_domain_free_fwnode(fn);
 		return -ENOMEM;
+	}
 
 	ip->irqdomain->parent = parent;
 
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 5cbaca58af95..c2b2911feeef 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -263,12 +263,13 @@ void __init arch_init_msi_domain(struct irq_domain *parent)
 		msi_default_domain =
 			pci_msi_create_irq_domain(fn, &pci_msi_domain_info,
 						  parent);
-		irq_domain_free_fwnode(fn);
 	}
-	if (!msi_default_domain)
+	if (!msi_default_domain) {
+		irq_domain_free_fwnode(fn);
 		pr_warn("failed to initialize irqdomain for MSI/MSI-x.\n");
-	else
+	} else {
 		msi_default_domain->flags |= IRQ_DOMAIN_MSI_NOMASK_QUIRK;
+	}
 }
 
 #ifdef CONFIG_IRQ_REMAP
@@ -301,7 +302,8 @@ struct irq_domain *arch_create_remap_msi_irq_domain(struct irq_domain *parent,
 	if (!fn)
 		return NULL;
 	d = pci_msi_create_irq_domain(fn, &pci_msi_ir_domain_info, parent);
-	irq_domain_free_fwnode(fn);
+	if (!d)
+		irq_domain_free_fwnode(fn);
 	return d;
 }
 #endif
@@ -364,7 +366,8 @@ static struct irq_domain *dmar_get_irq_domain(void)
 	if (fn) {
 		dmar_domain = msi_create_irq_domain(fn, &dmar_msi_domain_info,
 						    x86_vector_domain);
-		irq_domain_free_fwnode(fn);
+		if (!dmar_domain)
+			irq_domain_free_fwnode(fn);
 	}
 out:
 	mutex_unlock(&dmar_lock);
@@ -489,7 +492,10 @@ struct irq_domain *hpet_create_irq_domain(int hpet_id)
 	}
 
 	d = msi_create_irq_domain(fn, domain_info, parent);
-	irq_domain_free_fwnode(fn);
+	if (!d) {
+		irq_domain_free_fwnode(fn);
+		kfree(domain_info);
+	}
 	return d;
 }
 
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index c48be6e1f676..7649da2478d8 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -446,12 +446,10 @@ static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
 	trace_vector_activate(irqd->irq, apicd->is_managed,
 			      apicd->can_reserve, reserve);
 
-	/* Nothing to do for fixed assigned vectors */
-	if (!apicd->can_reserve && !apicd->is_managed)
-		return 0;
-
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	if (reserve || irqd_is_managed_and_shutdown(irqd))
+	if (!apicd->can_reserve && !apicd->is_managed)
+		assign_irq_vector_any_locked(irqd);
+	else if (reserve || irqd_is_managed_and_shutdown(irqd))
 		vector_assign_managed_shutdown(irqd);
 	else if (apicd->is_managed)
 		ret = activate_managed(irqd);
@@ -709,7 +707,6 @@ int __init arch_early_irq_init(void)
 	x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops,
 						   NULL);
 	BUG_ON(x86_vector_domain == NULL);
-	irq_domain_free_fwnode(fn);
 	irq_set_default_host(x86_vector_domain);
 
 	arch_init_msi_domain(x86_vector_domain);
@@ -775,20 +772,10 @@ void lapic_offline(void)
 static int apic_set_affinity(struct irq_data *irqd,
 			     const struct cpumask *dest, bool force)
 {
-	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	int err;
 
-	/*
-	 * Core code can call here for inactive interrupts. For inactive
-	 * interrupts which use managed or reservation mode there is no
-	 * point in going through the vector assignment right now as the
-	 * activation will assign a vector which fits the destination
-	 * cpumask. Let the core code store the destination mask and be
-	 * done with it.
-	 */
-	if (!irqd_is_activated(irqd) &&
-	    (apicd->is_managed || apicd->can_reserve))
-		return IRQ_SET_MASK_OK;
+	if (WARN_ON_ONCE(!irqd_is_activated(irqd)))
+		return -EIO;
 
 	raw_spin_lock(&vector_lock);
 	cpumask_and(vector_searchmask, dest, cpu_online_mask);
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index b037cfa7c0c5..7401cc12c3cc 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -71,6 +71,22 @@ static void printk_stack_address(unsigned long address, int reliable,
 	printk("%s %s%pB\n", log_lvl, reliable ? "" : "? ", (void *)address);
 }
 
+static int copy_code(struct pt_regs *regs, u8 *buf, unsigned long src,
+		     unsigned int nbytes)
+{
+	if (!user_mode(regs))
+		return copy_from_kernel_nofault(buf, (u8 *)src, nbytes);
+
+	/*
+	 * Make sure userspace isn't trying to trick us into dumping kernel
+	 * memory by pointing the userspace instruction pointer at it.
+	 */
+	if (__chk_range_not_ok(src, nbytes, TASK_SIZE_MAX))
+		return -EINVAL;
+
+	return copy_from_user_nmi(buf, (void __user *)src, nbytes);
+}
+
 /*
  * There are a couple of reasons for the 2/3rd prologue, courtesy of Linus:
  *
@@ -97,17 +113,8 @@ void show_opcodes(struct pt_regs *regs, const char *loglvl)
 #define OPCODE_BUFSIZE (PROLOGUE_SIZE + 1 + EPILOGUE_SIZE)
 	u8 opcodes[OPCODE_BUFSIZE];
 	unsigned long prologue = regs->ip - PROLOGUE_SIZE;
-	bool bad_ip;
-
-	/*
-	 * Make sure userspace isn't trying to trick us into dumping kernel
-	 * memory by pointing the userspace instruction pointer at it.
-	 */
-	bad_ip = user_mode(regs) &&
-		__chk_range_not_ok(prologue, OPCODE_BUFSIZE, TASK_SIZE_MAX);
 
-	if (bad_ip || copy_from_kernel_nofault(opcodes, (u8 *)prologue,
-					OPCODE_BUFSIZE)) {
+	if (copy_code(regs, opcodes, prologue, sizeof(opcodes))) {
 		printk("%sCode: Bad RIP value.\n", loglvl);
 	} else {
 		printk("%sCode: %" __stringify(PROLOGUE_SIZE) "ph <%02x> %"
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index bda2e5eaca0e..ad3a2b37927d 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -1074,7 +1074,7 @@ int copy_xstate_to_kernel(void *kbuf, struct xregs_state *xsave, unsigned int of
 		copy_part(offsetof(struct fxregs_state, st_space), 128,
 			  &xsave->i387.st_space, &kbuf, &offset_start, &count);
 	if (header.xfeatures & XFEATURE_MASK_SSE)
-		copy_part(xstate_offsets[XFEATURE_MASK_SSE], 256,
+		copy_part(xstate_offsets[XFEATURE_SSE], 256,
 			  &xsave->i387.xmm_space, &kbuf, &offset_start, &count);
 	/*
 	 * Fill xsave->i387.sw_reserved value for ptrace frame:
diff --git a/arch/x86/kernel/i8259.c b/arch/x86/kernel/i8259.c
index f3c76252247d..282b4ee1339f 100644
--- a/arch/x86/kernel/i8259.c
+++ b/arch/x86/kernel/i8259.c
@@ -207,7 +207,7 @@ spurious_8259A_irq:
 		 * lets ACK and report it. [once per IRQ]
 		 */
 		if (!(spurious_irq_mask & irqmask)) {
-			printk(KERN_DEBUG
+			printk_deferred(KERN_DEBUG
 			       "spurious 8259A interrupt: IRQ%d.\n", irq);
 			spurious_irq_mask |= irqmask;
 		}
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index 674a7d66d960..de2138ba38e5 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -324,7 +324,8 @@ struct paravirt_patch_template pv_ops = {
 	.cpu.swapgs		= native_swapgs,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
-	.cpu.update_io_bitmap	= native_tss_update_io_bitmap,
+	.cpu.invalidate_io_bitmap	= native_tss_invalidate_io_bitmap,
+	.cpu.update_io_bitmap		= native_tss_update_io_bitmap,
 #endif
 
 	.cpu.start_context_switch	= paravirt_nop,
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index f362ce0d5ac0..fe67dbd76e51 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -322,20 +322,6 @@ void arch_setup_new_exec(void)
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
-static inline void tss_invalidate_io_bitmap(struct tss_struct *tss)
-{
-	/*
-	 * Invalidate the I/O bitmap by moving io_bitmap_base outside the
-	 * TSS limit so any subsequent I/O access from user space will
-	 * trigger a #GP.
-	 *
-	 * This is correct even when VMEXIT rewrites the TSS limit
-	 * to 0x67 as the only requirement is that the base points
-	 * outside the limit.
-	 */
-	tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID;
-}
-
 static inline void switch_to_bitmap(unsigned long tifp)
 {
 	/*
@@ -346,7 +332,7 @@ static inline void switch_to_bitmap(unsigned long tifp)
 	 * user mode.
 	 */
 	if (tifp & _TIF_IO_BITMAP)
-		tss_invalidate_io_bitmap(this_cpu_ptr(&cpu_tss_rw));
+		tss_invalidate_io_bitmap();
 }
 
 static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm)
@@ -380,7 +366,7 @@ void native_tss_update_io_bitmap(void)
 	u16 *base = &tss->x86_tss.io_bitmap_base;
 
 	if (!test_thread_flag(TIF_IO_BITMAP)) {
-		tss_invalidate_io_bitmap(tss);
+		native_tss_invalidate_io_bitmap();
 		return;
 	}
 
diff --git a/arch/x86/kernel/stacktrace.c b/arch/x86/kernel/stacktrace.c
index 6ad43fc44556..2fd698e28e4d 100644
--- a/arch/x86/kernel/stacktrace.c
+++ b/arch/x86/kernel/stacktrace.c
@@ -58,7 +58,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 			 * or a page fault), which can make frame pointers
 			 * unreliable.
 			 */
-
 			if (IS_ENABLED(CONFIG_FRAME_POINTER))
 				return -EINVAL;
 		}
@@ -81,10 +80,6 @@ int arch_stack_walk_reliable(stack_trace_consume_fn consume_entry,
 	if (unwind_error(&state))
 		return -EINVAL;
 
-	/* Success path for non-user tasks, i.e. kthreads and idle tasks */
-	if (!(task->flags & (PF_KTHREAD | PF_IDLE)))
-		return -EINVAL;
-
 	return 0;
 }
 
diff --git a/arch/x86/kernel/traps.c b/arch/x86/kernel/traps.c
index b038695f36c5..b7cb3e0716f7 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -303,6 +303,8 @@ DEFINE_IDTENTRY_ERRORCODE(exc_alignment_check)
 
 	do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs,
 		error_code, BUS_ADRALN, NULL);
+
+	local_irq_disable();
 }
 
 #ifdef CONFIG_VMAP_STACK
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 7f969b2d240f..ec88bbe08a32 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -440,8 +440,11 @@ bool unwind_next_frame(struct unwind_state *state)
 	/*
 	 * Find the orc_entry associated with the text address.
 	 *
-	 * Decrement call return addresses by one so they work for sibling
-	 * calls and calls to noreturn functions.
+	 * For a call frame (as opposed to a signal frame), state->ip points to
+	 * the instruction after the call.  That instruction's stack layout
+	 * could be different from the call instruction's layout, for example
+	 * if the call was to a noreturn function.  So get the ORC data for the
+	 * call instruction itself.
 	 */
 	orc = orc_find(state->signal ? state->ip : state->ip - 1);
 	if (!orc) {
@@ -662,6 +665,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		state->sp = task->thread.sp;
 		state->bp = READ_ONCE_NOCHECK(frame->bp);
 		state->ip = READ_ONCE_NOCHECK(frame->ret_addr);
+		state->signal = (void *)state->ip == ret_from_fork;
 	}
 
 	if (get_stack_info((unsigned long *)state->sp, state->task,
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index 3bfc8dd8a43d..9a03e5b23135 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -358,6 +358,7 @@ SECTIONS
 	.bss : AT(ADDR(.bss) - LOAD_OFFSET) {
 		__bss_start = .;
 		*(.bss..page_aligned)
+		. = ALIGN(PAGE_SIZE);
 		*(BSS_MAIN)
 		BSS_DECRYPTED
 		. = ALIGN(PAGE_SIZE);
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 5bf72fc86a8e..4ce2ddd26c0b 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -2195,7 +2195,7 @@ void kvm_set_lapic_tscdeadline_msr(struct kvm_vcpu *vcpu, u64 data)
 {
 	struct kvm_lapic *apic = vcpu->arch.apic;
 
-	if (!lapic_in_kernel(vcpu) || apic_lvtt_oneshot(apic) ||
+	if (!kvm_apic_present(vcpu) || apic_lvtt_oneshot(apic) ||
 			apic_lvtt_period(apic))
 		return;
 
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index c0da4dd78ac5..5bbf76189afa 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -1090,7 +1090,7 @@ static void init_vmcb(struct vcpu_svm *svm)
 	svm->nested.vmcb = 0;
 	svm->vcpu.arch.hflags = 0;
 
-	if (pause_filter_count) {
+	if (!kvm_pause_in_guest(svm->vcpu.kvm)) {
 		control->pause_filter_count = pause_filter_count;
 		if (pause_filter_thresh)
 			control->pause_filter_thresh = pause_filter_thresh;
@@ -2693,7 +2693,7 @@ static int pause_interception(struct vcpu_svm *svm)
 	struct kvm_vcpu *vcpu = &svm->vcpu;
 	bool in_kernel = (svm_get_cpl(vcpu) == 0);
 
-	if (pause_filter_thresh)
+	if (!kvm_pause_in_guest(vcpu->kvm))
 		grow_ple_window(vcpu);
 
 	kvm_vcpu_on_spin(vcpu, in_kernel);
@@ -3780,7 +3780,7 @@ static void svm_handle_exit_irqoff(struct kvm_vcpu *vcpu)
 
 static void svm_sched_in(struct kvm_vcpu *vcpu, int cpu)
 {
-	if (pause_filter_thresh)
+	if (!kvm_pause_in_guest(vcpu->kvm))
 		shrink_ple_window(vcpu);
 }
 
@@ -3958,6 +3958,9 @@ static void svm_vm_destroy(struct kvm *kvm)
 
 static int svm_vm_init(struct kvm *kvm)
 {
+	if (!pause_filter_count || !pause_filter_thresh)
+		kvm->arch.pause_in_guest = true;
+
 	if (avic) {
 		int ret = avic_vm_init(kvm);
 		if (ret)
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index b26655104d4a..11e4df560018 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -6079,6 +6079,9 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	    ~(KVM_STATE_NESTED_SMM_GUEST_MODE | KVM_STATE_NESTED_SMM_VMXON))
 		return -EINVAL;
 
+	if (kvm_state->hdr.vmx.flags & ~KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE)
+		return -EINVAL;
+
 	/*
 	 * SMM temporarily disables VMX, so we cannot be in guest mode,
 	 * nor can VMLAUNCH/VMRESUME be pending.  Outside SMM, SMM flags
@@ -6108,9 +6111,16 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 	if (ret)
 		return ret;
 
-	/* Empty 'VMXON' state is permitted */
-	if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12))
-		return 0;
+	/* Empty 'VMXON' state is permitted if no VMCS loaded */
+	if (kvm_state->size < sizeof(*kvm_state) + sizeof(*vmcs12)) {
+		/* See vmx_has_valid_vmcs12.  */
+		if ((kvm_state->flags & KVM_STATE_NESTED_GUEST_MODE) ||
+		    (kvm_state->flags & KVM_STATE_NESTED_EVMCS) ||
+		    (kvm_state->hdr.vmx.vmcs12_pa != -1ull))
+			return -EINVAL;
+		else
+			return 0;
+	}
 
 	if (kvm_state->hdr.vmx.vmcs12_pa != -1ull) {
 		if (kvm_state->hdr.vmx.vmcs12_pa == kvm_state->hdr.vmx.vmxon_pa ||
@@ -6176,6 +6186,7 @@ static int vmx_set_nested_state(struct kvm_vcpu *vcpu,
 			goto error_guest_mode;
 	}
 
+	vmx->nested.has_preemption_timer_deadline = false;
 	if (kvm_state->hdr.vmx.flags & KVM_STATE_VMX_PREEMPTION_TIMER_DEADLINE) {
 		vmx->nested.has_preemption_timer_deadline = true;
 		vmx->nested.preemption_timer_deadline =
diff --git a/arch/x86/kvm/vmx/nested.h b/arch/x86/kvm/vmx/nested.h
index 758bccc26cf9..197148d76b8f 100644
--- a/arch/x86/kvm/vmx/nested.h
+++ b/arch/x86/kvm/vmx/nested.h
@@ -47,6 +47,11 @@ static inline struct vmcs12 *get_shadow_vmcs12(struct kvm_vcpu *vcpu)
 	return to_vmx(vcpu)->nested.cached_shadow_vmcs12;
 }
 
+/*
+ * Note: the same condition is checked against the state provided by userspace
+ * in vmx_set_nested_state; if it is satisfied, the nested state must include
+ * the VMCS12.
+ */
 static inline int vmx_has_valid_vmcs12(struct kvm_vcpu *vcpu)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
diff --git a/arch/x86/math-emu/wm_sqrt.S b/arch/x86/math-emu/wm_sqrt.S
index 3b2b58164ec1..40526dd85137 100644
--- a/arch/x86/math-emu/wm_sqrt.S
+++ b/arch/x86/math-emu/wm_sqrt.S
@@ -209,7 +209,7 @@ sqrt_stage_2_finish:
 
 #ifdef PARANOID
 /* It should be possible to get here only if the arg is ffff....ffff */
-	cmp	$0xffffffff,FPU_fsqrt_arg_1
+	cmpl	$0xffffffff,FPU_fsqrt_arg_1
 	jnz	sqrt_stage_2_error
 #endif /* PARANOID */
 
diff --git a/arch/x86/platform/uv/uv_irq.c b/arch/x86/platform/uv/uv_irq.c
index fc13cbbb2dce..abb6075397f0 100644
--- a/arch/x86/platform/uv/uv_irq.c
+++ b/arch/x86/platform/uv/uv_irq.c
@@ -167,9 +167,10 @@ static struct irq_domain *uv_get_irq_domain(void)
 		goto out;
 
 	uv_domain = irq_domain_create_tree(fn, &uv_domain_ops, NULL);
-	irq_domain_free_fwnode(fn);
 	if (uv_domain)
 		uv_domain->parent = x86_vector_domain;
+	else
+		irq_domain_free_fwnode(fn);
 out:
 	mutex_unlock(&uv_lock);
 
diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c
index 0d68948c82ad..c46b9f2e732f 100644
--- a/arch/x86/xen/enlighten_pv.c
+++ b/arch/x86/xen/enlighten_pv.c
@@ -870,6 +870,17 @@ static void xen_load_sp0(unsigned long sp0)
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+static void xen_invalidate_io_bitmap(void)
+{
+	struct physdev_set_iobitmap iobitmap = {
+		.bitmap = 0,
+		.nr_ports = 0,
+	};
+
+	native_tss_invalidate_io_bitmap();
+	HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap);
+}
+
 static void xen_update_io_bitmap(void)
 {
 	struct physdev_set_iobitmap iobitmap;
@@ -1099,6 +1110,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.load_sp0 = xen_load_sp0,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+	.invalidate_io_bitmap = xen_invalidate_io_bitmap,
 	.update_io_bitmap = xen_update_io_bitmap,
 #endif
 	.io_delay = xen_io_delay,