19 files changed, 96 insertions, 76 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index 1286a73ebdbc..f901658d9f7c 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -3,10 +3,6 @@
 # Makefile for the linux kernel.
 #
 
-extra-y	:= head_$(BITS).o
-extra-y	+= head$(BITS).o
-extra-y	+= ebda.o
-extra-y	+= platform-quirks.o
 extra-y	+= vmlinux.lds
 
 CPPFLAGS_vmlinux.lds += -U$(UTS_MACHINE)
@@ -33,6 +29,8 @@ KASAN_SANITIZE_sev.o					:= n
 # With some compiler versions the generated code results in boot hangs, caused
 # by several compilation units. To be safe, disable all instrumentation.
 KCSAN_SANITIZE := n
+KMSAN_SANITIZE_head$(BITS).o				:= n
+KMSAN_SANITIZE_nmi.o					:= n
 
 # If instrumentation of this dir is enabled, boot hangs during first second.
 # Probably could be more selective here, but note that files related to irqs,
@@ -42,7 +40,11 @@ KCOV_INSTRUMENT		:= n
 
 CFLAGS_irq.o := -I $(srctree)/$(src)/../include/asm/trace
 
-obj-y			:= process_$(BITS).o signal.o
+obj-y			+= head_$(BITS).o
+obj-y			+= head$(BITS).o
+obj-y			+= ebda.o
+obj-y			+= platform-quirks.o
+obj-y			+= process_$(BITS).o signal.o
 obj-$(CONFIG_COMPAT)	+= signal_compat.o
 obj-y			+= traps.o idt.o irq.o irq_$(BITS).o dumpstack_$(BITS).o
 obj-y			+= time.o ioport.o dumpstack.o nmi.o
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 9661e3e802be..f10a921ee756 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -12,6 +12,7 @@ endif
 # If these files are instrumented, boot hangs during the first second.
 KCOV_INSTRUMENT_common.o := n
 KCOV_INSTRUMENT_perf_event.o := n
+KMSAN_SANITIZE_common.o := n
 
 # As above, instrumenting secondary CPU boot code causes boot hangs.
 KCSAN_SANITIZE_common.o := n
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 48276c0e479d..860b60273df3 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -503,7 +503,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 		va_align.flags    = ALIGN_VA_32 | ALIGN_VA_64;
 
 		/* A random value per boot for bit slice [12:upper_bit) */
-		va_align.bits = get_random_int() & va_align.mask;
+		va_align.bits = get_random_u32() & va_align.mask;
 	}
 
 	if (cpu_has(c, X86_FEATURE_MWAITX))
diff --git a/arch/x86/kernel/cpu/microcode/amd.c b/arch/x86/kernel/cpu/microcode/amd.c
index e7410e98fc1f..3a35dec3ec55 100644
--- a/arch/x86/kernel/cpu/microcode/amd.c
+++ b/arch/x86/kernel/cpu/microcode/amd.c
@@ -440,7 +440,13 @@ apply_microcode_early_amd(u32 cpuid_1_eax, void *ucode, size_t size, bool save_p
 		return ret;
 
 	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
-	if (rev >= mc->hdr.patch_id)
+
+	/*
+	 * Allow application of the same revision to pick up SMT-specific
+	 * changes even if the revision of the other SMT thread is already
+	 * up-to-date.
+	 */
+	if (rev > mc->hdr.patch_id)
 		return ret;
 
 	if (!__apply_microcode_amd(mc)) {
@@ -528,8 +534,12 @@ void load_ucode_amd_ap(unsigned int cpuid_1_eax)
 
 	native_rdmsr(MSR_AMD64_PATCH_LEVEL, rev, dummy);
 
-	/* Check whether we have saved a new patch already: */
-	if (*new_rev && rev < mc->hdr.patch_id) {
+	/*
+	 * Check whether a new patch has been saved already. Also, allow application of
+	 * the same revision in order to pick up SMT-thread-specific configuration even
+	 * if the sibling SMT thread already has an up-to-date revision.
+	 */
+	if (*new_rev && rev <= mc->hdr.patch_id) {
 		if (!__apply_microcode_amd(mc)) {
 			*new_rev = mc->hdr.patch_id;
 			return;
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index de62b0b87ced..3266ea36667c 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -66,9 +66,6 @@ struct rdt_hw_resource rdt_resources_all[] = {
 			.rid			= RDT_RESOURCE_L3,
 			.name			= "L3",
 			.cache_level		= 3,
-			.cache = {
-				.min_cbm_bits	= 1,
-			},
 			.domains		= domain_init(RDT_RESOURCE_L3),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -83,9 +80,6 @@ struct rdt_hw_resource rdt_resources_all[] = {
 			.rid			= RDT_RESOURCE_L2,
 			.name			= "L2",
 			.cache_level		= 2,
-			.cache = {
-				.min_cbm_bits	= 1,
-			},
 			.domains		= domain_init(RDT_RESOURCE_L2),
 			.parse_ctrlval		= parse_cbm,
 			.format_str		= "%d=%0*x",
@@ -836,6 +830,7 @@ static __init void rdt_init_res_defs_intel(void)
 			r->cache.arch_has_sparse_bitmaps = false;
 			r->cache.arch_has_empty_bitmaps = false;
 			r->cache.arch_has_per_cpu_cfg = false;
+			r->cache.min_cbm_bits = 1;
 		} else if (r->rid == RDT_RESOURCE_MBA) {
 			hw_res->msr_base = MSR_IA32_MBA_THRTL_BASE;
 			hw_res->msr_update = mba_wrmsr_intel;
@@ -856,6 +851,7 @@ static __init void rdt_init_res_defs_amd(void)
 			r->cache.arch_has_sparse_bitmaps = true;
 			r->cache.arch_has_empty_bitmaps = true;
 			r->cache.arch_has_per_cpu_cfg = true;
+			r->cache.min_cbm_bits = 0;
 		} else if (r->rid == RDT_RESOURCE_MBA) {
 			hw_res->msr_base = MSR_IA32_MBA_BW_BASE;
 			hw_res->msr_update = mba_wrmsr_amd;
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index fd44b54c90d5..fc01f81f6e2a 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -45,6 +45,7 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_PROC_FEEDBACK,    CPUID_EDX, 11, 0x80000007, 0 },
 	{ X86_FEATURE_MBA,		CPUID_EBX,  6, 0x80000008, 0 },
 	{ X86_FEATURE_PERFMON_V2,	CPUID_EAX,  0, 0x80000022, 0 },
+	{ X86_FEATURE_AMD_LBR_V2,	CPUID_EAX,  1, 0x80000022, 0 },
 	{ 0, 0, 0, 0, 0 }
 };
 
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 132a2de44d2f..5e868b62a7c4 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -96,6 +96,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width;
 	unsigned int core_select_mask, core_level_siblings;
 	unsigned int die_select_mask, die_level_siblings;
+	unsigned int pkg_mask_width;
 	bool die_level_present = false;
 	int leaf;
 
@@ -111,10 +112,10 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
 	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 	die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
-	die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+	pkg_mask_width = die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 
 	sub_index = 1;
-	do {
+	while (true) {
 		cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx);
 
 		/*
@@ -132,10 +133,15 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 		}
 
+		if (LEAFB_SUBTYPE(ecx) != INVALID_TYPE)
+			pkg_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+		else
+			break;
+
 		sub_index++;
-	} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
+	}
 
-	core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
+	core_select_mask = (~(-1 << pkg_mask_width)) >> ht_mask_width;
 	die_select_mask = (~(-1 << die_plus_mask_width)) >>
 				core_plus_mask_width;
 
@@ -148,7 +154,7 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 	}
 
 	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid,
-				die_plus_mask_width);
+				pkg_mask_width);
 	/*
 	 * Reinit the apicid, now that we have extended initial_apicid.
 	 */
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index b3dba35f466e..0bf6779187dd 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -177,6 +177,12 @@ static void show_regs_if_on_stack(struct stack_info *info, struct pt_regs *regs,
 	}
 }
 
+/*
+ * This function reads pointers from the stack and dereferences them. The
+ * pointers may not have their KMSAN shadow set up properly, which may result
+ * in false positive reports. Disable instrumentation to avoid those.
+ */
+__no_kmsan_checks
 static void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			unsigned long *stack, const char *log_lvl)
 {
diff --git a/arch/x86/kernel/fpu/init.c b/arch/x86/kernel/fpu/init.c
index 621f4b6cac4a..8946f89761cc 100644
--- a/arch/x86/kernel/fpu/init.c
+++ b/arch/x86/kernel/fpu/init.c
@@ -210,13 +210,6 @@ static void __init fpu__init_system_xstate_size_legacy(void)
 	fpstate_reset(&current->thread.fpu);
 }
 
-static void __init fpu__init_init_fpstate(void)
-{
-	/* Bring init_fpstate size and features up to date */
-	init_fpstate.size		= fpu_kernel_cfg.max_size;
-	init_fpstate.xfeatures		= fpu_kernel_cfg.max_features;
-}
-
 /*
  * Called on the boot CPU once per system bootup, to set up the initial
  * FPU state that is later cloned into all processes:
@@ -236,5 +229,4 @@ void __init fpu__init_system(struct cpuinfo_x86 *c)
 	fpu__init_system_xstate_size_legacy();
 	fpu__init_system_xstate(fpu_kernel_cfg.max_size);
 	fpu__init_task_struct_size();
-	fpu__init_init_fpstate();
 }
diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
index c8340156bfd2..59e543b95a3c 100644
--- a/arch/x86/kernel/fpu/xstate.c
+++ b/arch/x86/kernel/fpu/xstate.c
@@ -360,7 +360,7 @@ static void __init setup_init_fpu_buf(void)
 
 	print_xstate_features();
 
-	xstate_init_xcomp_bv(&init_fpstate.regs.xsave, fpu_kernel_cfg.max_features);
+	xstate_init_xcomp_bv(&init_fpstate.regs.xsave, init_fpstate.xfeatures);
 
 	/*
 	 * Init all the features state with header.xfeatures being 0x0
@@ -678,20 +678,6 @@ static unsigned int __init get_xsave_size_user(void)
 	return ebx;
 }
 
-/*
- * Will the runtime-enumerated 'xstate_size' fit in the init
- * task's statically-allocated buffer?
- */
-static bool __init is_supported_xstate_size(unsigned int test_xstate_size)
-{
-	if (test_xstate_size <= sizeof(init_fpstate.regs))
-		return true;
-
-	pr_warn("x86/fpu: xstate buffer too small (%zu < %d), disabling xsave\n",
-			sizeof(init_fpstate.regs), test_xstate_size);
-	return false;
-}
-
 static int __init init_xstate_size(void)
 {
 	/* Recompute the context size for enabled features: */
@@ -717,10 +703,6 @@ static int __init init_xstate_size(void)
 	kernel_default_size =
 		xstate_calculate_size(fpu_kernel_cfg.default_features, compacted);
 
-	/* Ensure we have the space to store all default enabled features. */
-	if (!is_supported_xstate_size(kernel_default_size))
-		return -EINVAL;
-
 	if (!paranoid_xstate_size_valid(kernel_size))
 		return -EINVAL;
 
@@ -875,6 +857,19 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
 	update_regset_xstate_info(fpu_user_cfg.max_size,
 				  fpu_user_cfg.max_features);
 
+	/*
+	 * init_fpstate excludes dynamic states as they are large but init
+	 * state is zero.
+	 */
+	init_fpstate.size		= fpu_kernel_cfg.default_size;
+	init_fpstate.xfeatures		= fpu_kernel_cfg.default_features;
+
+	if (init_fpstate.size > sizeof(init_fpstate.regs)) {
+		pr_warn("x86/fpu: init_fpstate buffer too small (%zu < %d), disabling XSAVE\n",
+			sizeof(init_fpstate.regs), init_fpstate.size);
+		goto out_disable;
+	}
+
 	setup_init_fpu_buf();
 
 	/*
@@ -1130,6 +1125,15 @@ void __copy_xstate_to_uabi_buf(struct membuf to, struct fpstate *fpstate,
 	 */
 	mask = fpstate->user_xfeatures;
 
+	/*
+	 * Dynamic features are not present in init_fpstate. When they are
+	 * in an all zeros init state, remove those from 'mask' to zero
+	 * those features in the user buffer instead of retrieving them
+	 * from init_fpstate.
+	 */
+	if (fpu_state_size_dynamic())
+		mask &= (header.xfeatures | xinit->header.xcomp_bv);
+
 	for_each_extended_xfeature(i, mask) {
 		/*
 		 * If there was a feature or alignment gap, zero the space
diff --git a/arch/x86/kernel/ftrace_64.S b/arch/x86/kernel/ftrace_64.S
index dfeb227de561..2a4be92fd144 100644
--- a/arch/x86/kernel/ftrace_64.S
+++ b/arch/x86/kernel/ftrace_64.S
@@ -4,6 +4,7 @@
  */
 
 #include <linux/linkage.h>
+#include <linux/cfi_types.h>
 #include <asm/ptrace.h>
 #include <asm/ftrace.h>
 #include <asm/export.h>
@@ -129,6 +130,14 @@
 
 	.endm
 
+SYM_TYPED_FUNC_START(ftrace_stub)
+	RET
+SYM_FUNC_END(ftrace_stub)
+
+SYM_TYPED_FUNC_START(ftrace_stub_graph)
+	RET
+SYM_FUNC_END(ftrace_stub_graph)
+
 #ifdef CONFIG_DYNAMIC_FTRACE
 
 SYM_FUNC_START(__fentry__)
@@ -172,21 +181,10 @@ SYM_INNER_LABEL(ftrace_call, SYM_L_GLOBAL)
 	 */
 SYM_INNER_LABEL(ftrace_caller_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
-
-	jmp ftrace_epilogue
+	RET
 SYM_FUNC_END(ftrace_caller);
 STACK_FRAME_NON_STANDARD_FP(ftrace_caller)
 
-SYM_FUNC_START(ftrace_epilogue)
-/*
- * This is weak to keep gas from relaxing the jumps.
- */
-SYM_INNER_LABEL_ALIGN(ftrace_stub, SYM_L_WEAK)
-	UNWIND_HINT_FUNC
-	ENDBR
-	RET
-SYM_FUNC_END(ftrace_epilogue)
-
 SYM_FUNC_START(ftrace_regs_caller)
 	/* Save the current flags before any operations that can change them */
 	pushfq
@@ -262,14 +260,11 @@ SYM_INNER_LABEL(ftrace_regs_caller_jmp, SYM_L_GLOBAL)
 	popfq
 
 	/*
-	 * As this jmp to ftrace_epilogue can be a short jump
-	 * it must not be copied into the trampoline.
-	 * The trampoline will add the code to jump
-	 * to the return.
+	 * The trampoline will add the return.
 	 */
 SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	ANNOTATE_NOENDBR
-	jmp ftrace_epilogue
+	RET
 
 	/* Swap the flags with orig_rax */
 1:	movq MCOUNT_REG_SIZE(%rsp), %rdi
@@ -280,7 +275,7 @@ SYM_INNER_LABEL(ftrace_regs_caller_end, SYM_L_GLOBAL)
 	/* Restore flags */
 	popfq
 	UNWIND_HINT_FUNC
-	jmp	ftrace_epilogue
+	RET
 
 SYM_FUNC_END(ftrace_regs_caller)
 STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
@@ -291,9 +286,6 @@ STACK_FRAME_NON_STANDARD_FP(ftrace_regs_caller)
 SYM_FUNC_START(__fentry__)
 	cmpq $ftrace_stub, ftrace_trace_function
 	jnz trace
-
-SYM_INNER_LABEL(ftrace_stub, SYM_L_GLOBAL)
-	ENDBR
 	RET
 
 trace:
diff --git a/arch/x86/kernel/kprobes/core.c b/arch/x86/kernel/kprobes/core.c
index 4c3c27b6aea3..eb8bc82846b9 100644
--- a/arch/x86/kernel/kprobes/core.c
+++ b/arch/x86/kernel/kprobes/core.c
@@ -59,8 +59,6 @@
 DEFINE_PER_CPU(struct kprobe *, current_kprobe) = NULL;
 DEFINE_PER_CPU(struct kprobe_ctlblk, kprobe_ctlblk);
 
-#define stack_addr(regs) ((unsigned long *)regs->sp)
-
 #define W(row, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb, bc, bd, be, bf)\
 	(((b0##UL << 0x0)|(b1##UL << 0x1)|(b2##UL << 0x2)|(b3##UL << 0x3) |   \
 	  (b4##UL << 0x4)|(b5##UL << 0x5)|(b6##UL << 0x6)|(b7##UL << 0x7) |   \
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index b1abf663417c..c032edcd3d95 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -53,7 +53,7 @@ static unsigned long int get_module_load_offset(void)
 		 */
 		if (module_load_offset == 0)
 			module_load_offset =
-				(get_random_int() % 1024 + 1) * PAGE_SIZE;
+				(prandom_u32_max(1024) + 1) * PAGE_SIZE;
 		mutex_unlock(&module_kaslr_mutex);
 	}
 	return module_load_offset;
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 58a6ea472db9..c21b7347a26d 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -965,7 +965,7 @@ early_param("idle", idle_setup);
 unsigned long arch_align_stack(unsigned long sp)
 {
 	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
-		sp -= get_random_int() % 8192;
+		sp -= prandom_u32_max(8192);
 	return sp & ~0xf;
 }
 
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 1962008fe743..6b3418bff326 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -553,6 +553,7 @@ void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp, bool x32)
  * Kprobes not supported here. Set the probe on schedule instead.
  * Function graph tracer not supported too.
  */
+__no_kmsan_checks
 __visible __notrace_funcgraph struct task_struct *
 __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 {
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index f24227bc3220..3f3ea0287f69 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -1316,7 +1316,7 @@ static void __init smp_sanity_check(void)
 			nr++;
 		}
 
-		nr_cpu_ids = 8;
+		set_nr_cpu_ids(8);
 	}
 #endif
 
@@ -1569,7 +1569,7 @@ __init void prefill_possible_map(void)
 		possible = i;
 	}
 
-	nr_cpu_ids = possible;
+	set_nr_cpu_ids(possible);
 
 	pr_info("Allowing %d CPUs, %d hotplug CPUs\n",
 		possible, max_t(int, possible - num_processors, 0));
diff --git a/arch/x86/kernel/tboot.c b/arch/x86/kernel/tboot.c
index 3bacd935f840..4c1bcb6053fc 100644
--- a/arch/x86/kernel/tboot.c
+++ b/arch/x86/kernel/tboot.c
@@ -95,7 +95,7 @@ void __init tboot_probe(void)
 
 static pgd_t *tboot_pg_dir;
 static struct mm_struct tboot_mm = {
-	.mm_rb          = RB_ROOT,
+	.mm_mt          = MTREE_INIT_EXT(mm_mt, MM_MT_FLAGS, tboot_mm.mmap_lock),
 	.pgd            = swapper_pg_dir,
 	.mm_users       = ATOMIC_INIT(2),
 	.mm_count       = ATOMIC_INIT(1),
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index 8e1c50c86e5d..d8ba93778ae3 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -183,6 +183,16 @@ static struct pt_regs *decode_frame_pointer(unsigned long *bp)
 }
 #endif
 
+/*
+ * While walking the stack, KMSAN may stomp on stale locals from other
+ * functions that were marked as uninitialized upon function exit, and
+ * now hold the call frame information for the current function (e.g. the frame
+ * pointer). Because KMSAN does not specifically mark call frames as
+ * initialized, false positive reports are possible. To prevent such reports,
+ * we mark the functions scanning the stack (here and below) with
+ * __no_kmsan_checks.
+ */
+__no_kmsan_checks
 static bool update_stack_state(struct unwind_state *state,
 			       unsigned long *next_bp)
 {
@@ -250,6 +260,7 @@ static bool update_stack_state(struct unwind_state *state,
 	return true;
 }
 
+__no_kmsan_checks
 bool unwind_next_frame(struct unwind_state *state)
 {
 	struct pt_regs *regs;
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
index 0ea57da92940..c059820dfaea 100644
--- a/arch/x86/kernel/unwind_orc.c
+++ b/arch/x86/kernel/unwind_orc.c
@@ -713,7 +713,7 @@ void __unwind_start(struct unwind_state *state, struct task_struct *task,
 	/* Otherwise, skip ahead to the user-specified starting frame: */
 	while (!unwind_done(state) &&
 	       (!on_stack(&state->stack_info, first_frame, sizeof(long)) ||
-			state->sp < (unsigned long)first_frame))
+			state->sp <= (unsigned long)first_frame))
 		unwind_next_frame(state);
 
 	return;