Merge branch 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x86 asm updates from Ingo Molnar:

 - Introduce the ORC unwinder, which can be enabled via
   CONFIG_ORC_UNWINDER=y.

   The ORC unwinder is a lightweight, Linux kernel specific debuginfo
   implementation, which aims to be DWARF done right for unwinding.
   Objtool is used to generate the ORC unwinder tables during build, so
   the data format is flexible and kernel internal: there's no
   dependency on debuginfo created by an external toolchain.

   The ORC unwinder is almost two orders of magnitude faster than the
   (out of tree) DWARF unwinder - which is important for perf call graph
   profiling. It is also significantly simpler and is coded defensively:
   there has not been a single ORC related kernel crash so far, even
   with early versions. (knock on wood!)

   But the main advantage is that enabling the ORC unwinder allows
   CONFIG_FRAME_POINTERS to be turned off - which speeds up the kernel
   measurably:

   With frame pointers disabled, GCC does not have to add frame pointer
   instrumentation code to every function in the kernel. The kernel's
   .text size decreases by about 3.2%, resulting in better cache
   utilization and fewer instructions executed, resulting in a broad
   kernel-wide speedup. Average speedup of system calls should be
   roughly in the 1-3% range - measurements by Mel Gorman [1] have shown
   a speedup of 5-10% for some function execution intense workloads.

   The main cost of the unwinder is that the unwinder data has to be
   stored in RAM: the memory cost is 2-4MB of RAM, depending on kernel
   config - which is a modest cost on modern x86 systems.

   Given how young the ORC unwinder code is it's not enabled by default
   - but given the performance advantages the plan is to eventually make
   it the default unwinder on x86.

   See Documentation/x86/orc-unwinder.txt for more details.

 - Remove lguest support: its intended role was that of a temporary
   proof of concept for virtualization, plus its removal will enable the
   reduction (removal) of the paravirt API as well, so Rusty agreed to
   its removal. (Juergen Gross)

 - Clean up and fix FSGS related functionality (Andy Lutomirski)

 - Clean up IO access APIs (Andy Shevchenko)

 - Enhance the symbol namespace (Jiri Slaby)

* 'x86-asm-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (47 commits)
  objtool: Handle GCC stack pointer adjustment bug
  x86/entry/64: Use ENTRY() instead of ALIGN+GLOBAL for stub32_clone()
  x86/fpu/math-emu: Add ENDPROC to functions
  x86/boot/64: Extract efi_pe_entry() from startup_64()
  x86/boot/32: Extract efi_pe_entry() from startup_32()
  x86/lguest: Remove lguest support
  x86/paravirt/xen: Remove xen_patch()
  objtool: Fix objtool fallthrough detection with function padding
  x86/xen/64: Fix the reported SS and CS in SYSCALL
  objtool: Track DRAP separately from callee-saved registers
  objtool: Fix validate_branch() return codes
  x86: Clarify/fix no-op barriers for text_poke_bp()
  x86/switch_to/64: Rewrite FS/GS switching yet again to fix AMD CPUs
  selftests/x86/fsgsbase: Test selectors 1, 2, and 3
  x86/fsgsbase/64: Report FSBASE and GSBASE correctly in core dumps
  x86/fsgsbase/64: Fully initialize FS and GS state in start_thread_common
  x86/asm: Fix UNWIND_HINT_REGS macro for older binutils
  x86/asm/32: Fix regs_get_register() on segment registers
  x86/xen/64: Rearrange the SYSCALL entries
  x86/asm/32: Remove a bunch of '& 0xffff' from pt_regs segment reads
  ...

19 files changed, 817 insertions, 190 deletions

diff --git a/arch/x86/kernel/Makefile b/arch/x86/kernel/Makefile
index a01892bdd61a..287eac7d207f 100644
--- a/arch/x86/kernel/Makefile
+++ b/arch/x86/kernel/Makefile
@@ -126,11 +126,9 @@ obj-$(CONFIG_PERF_EVENTS)		+= perf_regs.o
 obj-$(CONFIG_TRACING)			+= tracepoint.o
 obj-$(CONFIG_SCHED_MC_PRIO)		+= itmt.o
 
-ifdef CONFIG_FRAME_POINTER
-obj-y					+= unwind_frame.o
-else
-obj-y					+= unwind_guess.o
-endif
+obj-$(CONFIG_ORC_UNWINDER)		+= unwind_orc.o
+obj-$(CONFIG_FRAME_POINTER_UNWINDER)	+= unwind_frame.o
+obj-$(CONFIG_GUESS_UNWINDER)		+= unwind_guess.o
 
 ###
 # 64 bit specific files
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index 32e14d137416..3344d3382e91 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -742,7 +742,16 @@ static void *bp_int3_handler, *bp_int3_addr;
 
 int poke_int3_handler(struct pt_regs *regs)
 {
-	/* bp_patching_in_progress */
+	/*
+	 * Having observed our INT3 instruction, we now must observe
+	 * bp_patching_in_progress.
+	 *
+	 * 	in_progress = TRUE		INT3
+	 * 	WMB				RMB
+	 * 	write INT3			if (in_progress)
+	 *
+	 * Idem for bp_int3_handler.
+	 */
 	smp_rmb();
 
 	if (likely(!bp_patching_in_progress))
@@ -788,9 +797,8 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 	bp_int3_addr = (u8 *)addr + sizeof(int3);
 	bp_patching_in_progress = true;
 	/*
-	 * Corresponding read barrier in int3 notifier for
-	 * making sure the in_progress flags is correctly ordered wrt.
-	 * patching
+	 * Corresponding read barrier in int3 notifier for making sure the
+	 * in_progress and handler are correctly ordered wrt. patching.
 	 */
 	smp_wmb();
 
@@ -815,9 +823,11 @@ void *text_poke_bp(void *addr, const void *opcode, size_t len, void *handler)
 	text_poke(addr, opcode, sizeof(int3));
 
 	on_each_cpu(do_sync_core, NULL, 1);
-
+	/*
+	 * sync_core() implies an smp_mb() and orders this store against
+	 * the writing of the new instruction.
+	 */
 	bp_patching_in_progress = false;
-	smp_wmb();
 
 	return addr;
 }
diff --git a/arch/x86/kernel/asm-offsets_32.c b/arch/x86/kernel/asm-offsets_32.c
index 880aa093268d..710edab9e644 100644
--- a/arch/x86/kernel/asm-offsets_32.c
+++ b/arch/x86/kernel/asm-offsets_32.c
@@ -4,9 +4,6 @@
 
 #include <asm/ucontext.h>
 
-#include <linux/lguest.h>
-#include "../../../drivers/lguest/lg.h"
-
 #define __SYSCALL_I386(nr, sym, qual) [nr] = 1,
 static char syscalls[] = {
 #include <asm/syscalls_32.h>
@@ -62,23 +59,6 @@ void foo(void)
 	OFFSET(stack_canary_offset, stack_canary, canary);
 #endif
 
-#if defined(CONFIG_LGUEST) || defined(CONFIG_LGUEST_GUEST) || defined(CONFIG_LGUEST_MODULE)
-	BLANK();
-	OFFSET(LGUEST_DATA_irq_enabled, lguest_data, irq_enabled);
-	OFFSET(LGUEST_DATA_irq_pending, lguest_data, irq_pending);
-
-	BLANK();
-	OFFSET(LGUEST_PAGES_host_gdt_desc, lguest_pages, state.host_gdt_desc);
-	OFFSET(LGUEST_PAGES_host_idt_desc, lguest_pages, state.host_idt_desc);
-	OFFSET(LGUEST_PAGES_host_cr3, lguest_pages, state.host_cr3);
-	OFFSET(LGUEST_PAGES_host_sp, lguest_pages, state.host_sp);
-	OFFSET(LGUEST_PAGES_guest_gdt_desc, lguest_pages,state.guest_gdt_desc);
-	OFFSET(LGUEST_PAGES_guest_idt_desc, lguest_pages,state.guest_idt_desc);
-	OFFSET(LGUEST_PAGES_guest_gdt, lguest_pages, state.guest_gdt);
-	OFFSET(LGUEST_PAGES_regs_trapnum, lguest_pages, regs.trapnum);
-	OFFSET(LGUEST_PAGES_regs_errcode, lguest_pages, regs.errcode);
-	OFFSET(LGUEST_PAGES_regs, lguest_pages, regs);
-#endif
 	BLANK();
 	DEFINE(__NR_syscall_max, sizeof(syscalls) - 1);
 	DEFINE(NR_syscalls, sizeof(syscalls));
diff --git a/arch/x86/kernel/dumpstack.c b/arch/x86/kernel/dumpstack.c
index dbce3cca94cb..f13b4c00a5de 100644
--- a/arch/x86/kernel/dumpstack.c
+++ b/arch/x86/kernel/dumpstack.c
@@ -94,6 +94,9 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 		if (stack_name)
 			printk("%s <%s>\n", log_lvl, stack_name);
 
+		if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
+			__show_regs(regs, 0);
+
 		/*
 		 * Scan the stack, printing any text addresses we find.  At the
 		 * same time, follow proper stack frames with the unwinder.
@@ -118,10 +121,8 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			 * Don't print regs->ip again if it was already printed
 			 * by __show_regs() below.
 			 */
-			if (regs && stack == &regs->ip) {
-				unwind_next_frame(&state);
-				continue;
-			}
+			if (regs && stack == &regs->ip)
+				goto next;
 
 			if (stack == ret_addr_p)
 				reliable = 1;
@@ -144,6 +145,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 			if (!reliable)
 				continue;
 
+next:
 			/*
 			 * Get the next frame from the unwinder.  No need to
 			 * check for an error: if anything goes wrong, the rest
@@ -153,7 +155,7 @@ void show_trace_log_lvl(struct task_struct *task, struct pt_regs *regs,
 
 			/* if the frame has entry regs, print them */
 			regs = unwind_get_entry_regs(&state);
-			if (regs)
+			if (regs && on_stack(&stack_info, regs, sizeof(*regs)))
 				__show_regs(regs, 0);
 		}
 
@@ -265,7 +267,7 @@ int __die(const char *str, struct pt_regs *regs, long err)
 #ifdef CONFIG_X86_32
 	if (user_mode(regs)) {
 		sp = regs->sp;
-		ss = regs->ss & 0xffff;
+		ss = regs->ss;
 	} else {
 		sp = kernel_stack_pointer(regs);
 		savesegment(ss, ss);
diff --git a/arch/x86/kernel/dumpstack_32.c b/arch/x86/kernel/dumpstack_32.c
index e5f0b40e66d2..4f0481474903 100644
--- a/arch/x86/kernel/dumpstack_32.c
+++ b/arch/x86/kernel/dumpstack_32.c
@@ -37,7 +37,7 @@ static bool in_hardirq_stack(unsigned long *stack, struct stack_info *info)
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack < begin || stack > end)
+	if (stack <= begin || stack > end)
 		return false;
 
 	info->type	= STACK_TYPE_IRQ;
@@ -62,7 +62,7 @@ static bool in_softirq_stack(unsigned long *stack, struct stack_info *info)
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack < begin || stack > end)
+	if (stack <= begin || stack > end)
 		return false;
 
 	info->type	= STACK_TYPE_SOFTIRQ;
diff --git a/arch/x86/kernel/dumpstack_64.c b/arch/x86/kernel/dumpstack_64.c
index 3e1471d57487..225af4184f06 100644
--- a/arch/x86/kernel/dumpstack_64.c
+++ b/arch/x86/kernel/dumpstack_64.c
@@ -55,7 +55,7 @@ static bool in_exception_stack(unsigned long *stack, struct stack_info *info)
 		begin = end - (exception_stack_sizes[k] / sizeof(long));
 		regs  = (struct pt_regs *)end - 1;
 
-		if (stack < begin || stack >= end)
+		if (stack <= begin || stack >= end)
 			continue;
 
 		info->type	= STACK_TYPE_EXCEPTION + k;
@@ -78,7 +78,7 @@ static bool in_irq_stack(unsigned long *stack, struct stack_info *info)
 	 * This is a software stack, so 'end' can be a valid stack pointer.
 	 * It just means the stack is empty.
 	 */
-	if (stack < begin || stack > end)
+	if (stack <= begin || stack > end)
 		return false;
 
 	info->type	= STACK_TYPE_IRQ;
diff --git a/arch/x86/kernel/head_32.S b/arch/x86/kernel/head_32.S
index 1f85ee8f9439..29da9599fec0 100644
--- a/arch/x86/kernel/head_32.S
+++ b/arch/x86/kernel/head_32.S
@@ -155,7 +155,6 @@ ENTRY(startup_32)
 	jmp *%eax
 
 .Lbad_subarch:
-WEAK(lguest_entry)
 WEAK(xen_entry)
 	/* Unknown implementation; there's really
 	   nothing we can do at this point. */
@@ -165,7 +164,6 @@ WEAK(xen_entry)
 
 subarch_entries:
 	.long .Ldefault_entry		/* normal x86/PC */
-	.long lguest_entry		/* lguest hypervisor */
 	.long xen_entry			/* Xen hypervisor */
 	.long .Ldefault_entry		/* Moorestown MID */
 num_subarch_entries = (. - subarch_entries) / 4
@@ -457,12 +455,9 @@ early_idt_handler_common:
 	/* The vector number is in pt_regs->gs */
 
 	cld
-	pushl	%fs		/* pt_regs->fs */
-	movw	$0, 2(%esp)	/* clear high bits (some CPUs leave garbage) */
-	pushl	%es		/* pt_regs->es */
-	movw	$0, 2(%esp)	/* clear high bits (some CPUs leave garbage) */
-	pushl	%ds		/* pt_regs->ds */
-	movw	$0, 2(%esp)	/* clear high bits (some CPUs leave garbage) */
+	pushl	%fs		/* pt_regs->fs (__fsh varies by model) */
+	pushl	%es		/* pt_regs->es (__esh varies by model) */
+	pushl	%ds		/* pt_regs->ds (__dsh varies by model) */
 	pushl	%eax		/* pt_regs->ax */
 	pushl	%ebp		/* pt_regs->bp */
 	pushl	%edi		/* pt_regs->di */
@@ -479,9 +474,8 @@ early_idt_handler_common:
 	/* Load the vector number into EDX */
 	movl	PT_GS(%esp), %edx
 
-	/* Load GS into pt_regs->gs and clear high bits */
+	/* Load GS into pt_regs->gs (and maybe clobber __gsh) */
 	movw	%gs, PT_GS(%esp)
-	movw	$0, PT_GS+2(%esp)
 
 	movl	%esp, %eax	/* args are pt_regs (EAX), trapnr (EDX) */
 	call	early_fixup_exception
@@ -493,10 +487,10 @@ early_idt_handler_common:
 	popl	%edi		/* pt_regs->di */
 	popl	%ebp		/* pt_regs->bp */
 	popl	%eax		/* pt_regs->ax */
-	popl	%ds		/* pt_regs->ds */
-	popl	%es		/* pt_regs->es */
-	popl	%fs		/* pt_regs->fs */
-	popl	%gs		/* pt_regs->gs */
+	popl	%ds		/* pt_regs->ds (always ignores __dsh) */
+	popl	%es		/* pt_regs->es (always ignores __esh) */
+	popl	%fs		/* pt_regs->fs (always ignores __fsh) */
+	popl	%gs		/* pt_regs->gs (always ignores __gsh) */
 	decl	%ss:early_recursion_flag
 	addl	$4, %esp	/* pop pt_regs->orig_ax */
 	iret
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index a870910c8565..f0e64db18ac8 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -21,6 +21,25 @@
 #include <asm/mmu_context.h>
 #include <asm/syscalls.h>
 
+static void refresh_ldt_segments(void)
+{
+#ifdef CONFIG_X86_64
+	unsigned short sel;
+
+	/*
+	 * Make sure that the cached DS and ES descriptors match the updated
+	 * LDT.
+	 */
+	savesegment(ds, sel);
+	if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT)
+		loadsegment(ds, sel);
+
+	savesegment(es, sel);
+	if ((sel & SEGMENT_TI_MASK) == SEGMENT_LDT)
+		loadsegment(es, sel);
+#endif
+}
+
 /* context.lock is held for us, so we don't need any locking. */
 static void flush_ldt(void *__mm)
 {
@@ -32,6 +51,8 @@ static void flush_ldt(void *__mm)
 
 	pc = &mm->context;
 	set_ldt(pc->ldt->entries, pc->ldt->nr_entries);
+
+	refresh_ldt_segments();
 }
 
 /* The caller must call finalize_ldt_struct on the result. LDT starts zeroed. */
diff --git a/arch/x86/kernel/module.c b/arch/x86/kernel/module.c
index f67bd3205df7..62e7d70aadd5 100644
--- a/arch/x86/kernel/module.c
+++ b/arch/x86/kernel/module.c
@@ -35,6 +35,7 @@
 #include <asm/page.h>
 #include <asm/pgtable.h>
 #include <asm/setup.h>
+#include <asm/unwind.h>
 
 #if 0
 #define DEBUGP(fmt, ...)				\
@@ -213,7 +214,7 @@ int module_finalize(const Elf_Ehdr *hdr,
 		    struct module *me)
 {
 	const Elf_Shdr *s, *text = NULL, *alt = NULL, *locks = NULL,
-		*para = NULL;
+		*para = NULL, *orc = NULL, *orc_ip = NULL;
 	char *secstrings = (void *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
 
 	for (s = sechdrs; s < sechdrs + hdr->e_shnum; s++) {
@@ -225,6 +226,10 @@ int module_finalize(const Elf_Ehdr *hdr,
 			locks = s;
 		if (!strcmp(".parainstructions", secstrings + s->sh_name))
 			para = s;
+		if (!strcmp(".orc_unwind", secstrings + s->sh_name))
+			orc = s;
+		if (!strcmp(".orc_unwind_ip", secstrings + s->sh_name))
+			orc_ip = s;
 	}
 
 	if (alt) {
@@ -248,6 +253,10 @@ int module_finalize(const Elf_Ehdr *hdr,
 	/* make jump label nops */
 	jump_label_apply_nops(me);
 
+	if (orc && orc_ip)
+		unwind_module_init(me, (void *)orc_ip->sh_addr, orc_ip->sh_size,
+				   (void *)orc->sh_addr, orc->sh_size);
+
 	return 0;
 }
 
diff --git a/arch/x86/kernel/platform-quirks.c b/arch/x86/kernel/platform-quirks.c
index 91271122f0df..502a77d0adb0 100644
--- a/arch/x86/kernel/platform-quirks.c
+++ b/arch/x86/kernel/platform-quirks.c
@@ -16,7 +16,6 @@ void __init x86_early_init_platform_quirks(void)
 		x86_platform.legacy.reserve_bios_regions = 1;
 		break;
 	case X86_SUBARCH_XEN:
-	case X86_SUBARCH_LGUEST:
 		x86_platform.legacy.devices.pnpbios = 0;
 		x86_platform.legacy.rtc = 0;
 		break;
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index c6d6dc5f8bb2..efc5eeb58292 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -68,7 +68,7 @@ void __show_regs(struct pt_regs *regs, int all)
 
 	if (user_mode(regs)) {
 		sp = regs->sp;
-		ss = regs->ss & 0xffff;
+		ss = regs->ss;
 		gs = get_user_gs(regs);
 	} else {
 		sp = kernel_stack_pointer(regs);
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index c3169be4c596..c85269a76511 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -69,8 +69,7 @@ void __show_regs(struct pt_regs *regs, int all)
 	unsigned int fsindex, gsindex;
 	unsigned int ds, cs, es;
 
-	printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs & 0xffff,
-		(void *)regs->ip);
+	printk(KERN_DEFAULT "RIP: %04lx:%pS\n", regs->cs, (void *)regs->ip);
 	printk(KERN_DEFAULT "RSP: %04lx:%016lx EFLAGS: %08lx", regs->ss,
 		regs->sp, regs->flags);
 	if (regs->orig_ax != -1)
@@ -149,6 +148,123 @@ void release_thread(struct task_struct *dead_task)
 	}
 }
 
+enum which_selector {
+	FS,
+	GS
+};
+
+/*
+ * Saves the FS or GS base for an outgoing thread if FSGSBASE extensions are
+ * not available.  The goal is to be reasonably fast on non-FSGSBASE systems.
+ * It's forcibly inlined because it'll generate better code and this function
+ * is hot.
+ */
+static __always_inline void save_base_legacy(struct task_struct *prev_p,
+					     unsigned short selector,
+					     enum which_selector which)
+{
+	if (likely(selector == 0)) {
+		/*
+		 * On Intel (without X86_BUG_NULL_SEG), the segment base could
+		 * be the pre-existing saved base or it could be zero.  On AMD
+		 * (with X86_BUG_NULL_SEG), the segment base could be almost
+		 * anything.
+		 *
+		 * This branch is very hot (it's hit twice on almost every
+		 * context switch between 64-bit programs), and avoiding
+		 * the RDMSR helps a lot, so we just assume that whatever
+		 * value is already saved is correct.  This matches historical
+		 * Linux behavior, so it won't break existing applications.
+		 *
+		 * To avoid leaking state, on non-X86_BUG_NULL_SEG CPUs, if we
+		 * report that the base is zero, it needs to actually be zero:
+		 * see the corresponding logic in load_seg_legacy.
+		 */
+	} else {
+		/*
+		 * If the selector is 1, 2, or 3, then the base is zero on
+		 * !X86_BUG_NULL_SEG CPUs and could be anything on
+		 * X86_BUG_NULL_SEG CPUs.  In the latter case, Linux
+		 * has never attempted to preserve the base across context
+		 * switches.
+		 *
+		 * If selector > 3, then it refers to a real segment, and
+		 * saving the base isn't necessary.
+		 */
+		if (which == FS)
+			prev_p->thread.fsbase = 0;
+		else
+			prev_p->thread.gsbase = 0;
+	}
+}
+
+static __always_inline void save_fsgs(struct task_struct *task)
+{
+	savesegment(fs, task->thread.fsindex);
+	savesegment(gs, task->thread.gsindex);
+	save_base_legacy(task, task->thread.fsindex, FS);
+	save_base_legacy(task, task->thread.gsindex, GS);
+}
+
+static __always_inline void loadseg(enum which_selector which,
+				    unsigned short sel)
+{
+	if (which == FS)
+		loadsegment(fs, sel);
+	else
+		load_gs_index(sel);
+}
+
+static __always_inline void load_seg_legacy(unsigned short prev_index,
+					    unsigned long prev_base,
+					    unsigned short next_index,
+					    unsigned long next_base,
+					    enum which_selector which)
+{
+	if (likely(next_index <= 3)) {
+		/*
+		 * The next task is using 64-bit TLS, is not using this
+		 * segment at all, or is having fun with arcane CPU features.
+		 */
+		if (next_base == 0) {
+			/*
+			 * Nasty case: on AMD CPUs, we need to forcibly zero
+			 * the base.
+			 */
+			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
+				loadseg(which, __USER_DS);
+				loadseg(which, next_index);
+			} else {
+				/*
+				 * We could try to exhaustively detect cases
+				 * under which we can skip the segment load,
+				 * but there's really only one case that matters
+				 * for performance: if both the previous and
+				 * next states are fully zeroed, we can skip
+				 * the load.
+				 *
+				 * (This assumes that prev_base == 0 has no
+				 * false positives.  This is the case on
+				 * Intel-style CPUs.)
+				 */
+				if (likely(prev_index | next_index | prev_base))
+					loadseg(which, next_index);
+			}
+		} else {
+			if (prev_index != next_index)
+				loadseg(which, next_index);
+			wrmsrl(which == FS ? MSR_FS_BASE : MSR_KERNEL_GS_BASE,
+			       next_base);
+		}
+	} else {
+		/*
+		 * The next task is using a real segment.  Loading the selector
+		 * is sufficient.
+		 */
+		loadseg(which, next_index);
+	}
+}
+
 int copy_thread_tls(unsigned long clone_flags, unsigned long sp,
 		unsigned long arg, struct task_struct *p, unsigned long tls)
 {
@@ -229,10 +345,19 @@ start_thread_common(struct pt_regs *regs, unsigned long new_ip,
 		    unsigned long new_sp,
 		    unsigned int _cs, unsigned int _ss, unsigned int _ds)
 {
+	WARN_ON_ONCE(regs != current_pt_regs());
+
+	if (static_cpu_has(X86_BUG_NULL_SEG)) {
+		/* Loading zero below won't clear the base. */
+		loadsegment(fs, __USER_DS);
+		load_gs_index(__USER_DS);
+	}
+
 	loadsegment(fs, 0);
 	loadsegment(es, _ds);
 	loadsegment(ds, _ds);
 	load_gs_index(0);
+
 	regs->ip		= new_ip;
 	regs->sp		= new_sp;
 	regs->cs		= _cs;
@@ -277,7 +402,9 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	struct fpu *next_fpu = &next->fpu;
 	int cpu = smp_processor_id();
 	struct tss_struct *tss = &per_cpu(cpu_tss, cpu);
-	unsigned prev_fsindex, prev_gsindex;
+
+	WARN_ON_ONCE(IS_ENABLED(CONFIG_DEBUG_ENTRY) &&
+		     this_cpu_read(irq_count) != -1);
 
 	switch_fpu_prepare(prev_fpu, cpu);
 
@@ -286,8 +413,7 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	 *
 	 * (e.g. xen_load_tls())
 	 */
-	savesegment(fs, prev_fsindex);
-	savesegment(gs, prev_gsindex);
+	save_fsgs(prev_p);
 
 	/*
 	 * Load TLS before restoring any segments so that segment loads
@@ -326,108 +452,10 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 	if (unlikely(next->ds | prev->ds))
 		loadsegment(ds, next->ds);
 
-	/*
-	 * Switch FS and GS.
-	 *
-	 * These are even more complicated than DS and ES: they have
-	 * 64-bit bases are that controlled by arch_prctl.  The bases
-	 * don't necessarily match the selectors, as user code can do
-	 * any number of things to cause them to be inconsistent.
-	 *
-	 * We don't promise to preserve the bases if the selectors are
-	 * nonzero.  We also don't promise to preserve the base if the
-	 * selector is zero and the base doesn't match whatever was
-	 * most recently passed to ARCH_SET_FS/GS.  (If/when the
-	 * FSGSBASE instructions are enabled, we'll need to offer
-	 * stronger guarantees.)
-	 *
-	 * As an invariant,
-	 * (fsbase != 0 && fsindex != 0) || (gsbase != 0 && gsindex != 0) is
-	 * impossible.
-	 */
-	if (next->fsindex) {
-		/* Loading a nonzero value into FS sets the index and base. */
-		loadsegment(fs, next->fsindex);
-	} else {
-		if (next->fsbase) {
-			/* Next index is zero but next base is nonzero. */
-			if (prev_fsindex)
-				loadsegment(fs, 0);
-			wrmsrl(MSR_FS_BASE, next->fsbase);
-		} else {
-			/* Next base and index are both zero. */
-			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
-				/*
-				 * We don't know the previous base and can't
-				 * find out without RDMSR.  Forcibly clear it.
-				 */
-				loadsegment(fs, __USER_DS);
-				loadsegment(fs, 0);
-			} else {
-				/*
-				 * If the previous index is zero and ARCH_SET_FS
-				 * didn't change the base, then the base is
-				 * also zero and we don't need to do anything.
-				 */
-				if (prev->fsbase || prev_fsindex)
-					loadsegment(fs, 0);
-			}
-		}
-	}
-	/*
-	 * Save the old state and preserve the invariant.
-	 * NB: if prev_fsindex == 0, then we can't reliably learn the base
-	 * without RDMSR because Intel user code can zero it without telling
-	 * us and AMD user code can program any 32-bit value without telling
-	 * us.
-	 */
-	if (prev_fsindex)
-		prev->fsbase = 0;
-	prev->fsindex = prev_fsindex;
-
-	if (next->gsindex) {
-		/* Loading a nonzero value into GS sets the index and base. */
-		load_gs_index(next->gsindex);
-	} else {
-		if (next->gsbase) {
-			/* Next index is zero but next base is nonzero. */
-			if (prev_gsindex)
-				load_gs_index(0);
-			wrmsrl(MSR_KERNEL_GS_BASE, next->gsbase);
-		} else {
-			/* Next base and index are both zero. */
-			if (static_cpu_has_bug(X86_BUG_NULL_SEG)) {
-				/*
-				 * We don't know the previous base and can't
-				 * find out without RDMSR.  Forcibly clear it.
-				 *
-				 * This contains a pointless SWAPGS pair.
-				 * Fixing it would involve an explicit check
-				 * for Xen or a new pvop.
-				 */
-				load_gs_index(__USER_DS);
-				load_gs_index(0);
-			} else {
-				/*
-				 * If the previous index is zero and ARCH_SET_GS
-				 * didn't change the base, then the base is
-				 * also zero and we don't need to do anything.
-				 */
-				if (prev->gsbase || prev_gsindex)
-					load_gs_index(0);
-			}
-		}
-	}
-	/*
-	 * Save the old state and preserve the invariant.
-	 * NB: if prev_gsindex == 0, then we can't reliably learn the base
-	 * without RDMSR because Intel user code can zero it without telling
-	 * us and AMD user code can program any 32-bit value without telling
-	 * us.
-	 */
-	if (prev_gsindex)
-		prev->gsbase = 0;
-	prev->gsindex = prev_gsindex;
+	load_seg_legacy(prev->fsindex, prev->fsbase,
+			next->fsindex, next->fsbase, FS);
+	load_seg_legacy(prev->gsindex, prev->gsbase,
+			next->gsindex, next->gsbase, GS);
 
 	switch_fpu_finish(next_fpu, cpu);
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 3486d0498800..ecab32282f0f 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -115,6 +115,7 @@
 #include <asm/microcode.h>
 #include <asm/mmu_context.h>
 #include <asm/kaslr.h>
+#include <asm/unwind.h>
 
 /*
  * max_low_pfn_mapped: highest direct mapped pfn under 4GB
@@ -1310,6 +1311,8 @@ void __init setup_arch(char **cmdline_p)
 	if (efi_enabled(EFI_BOOT))
 		efi_apply_memmap_quirks();
 #endif
+
+	unwind_init();
 }
 
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index cc30a74e4adb..e04442345fc0 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -256,7 +256,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 			sp = current->sas_ss_sp + current->sas_ss_size;
 	} else if (IS_ENABLED(CONFIG_X86_32) &&
 		   !onsigstack &&
-		   (regs->ss & 0xffff) != __USER_DS &&
+		   regs->ss != __USER_DS &&
 		   !(ka->sa.sa_flags & SA_RESTORER) &&
 		   ka->sa.sa_restorer) {
 		/* This is the legacy signal stack switching. */
diff --git a/arch/x86/kernel/step.c b/arch/x86/kernel/step.c
index 5f25cfbd952e..5ee663836c08 100644
--- a/arch/x86/kernel/step.c
+++ b/arch/x86/kernel/step.c
@@ -13,7 +13,7 @@ unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *re
 	unsigned long addr, seg;
 
 	addr = regs->ip;
-	seg = regs->cs & 0xffff;
+	seg = regs->cs;
 	if (v8086_mode(regs)) {
 		addr = (addr & 0xffff) + (seg << 4);
 		return addr;
diff --git a/arch/x86/kernel/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index c29e5bc7e9c9..d145a0b1f529 100644
--- a/arch/x86/kernel/unwind_frame.c
+++ b/arch/x86/kernel/unwind_frame.c
@@ -10,20 +10,22 @@
 
 #define FRAME_HEADER_SIZE (sizeof(long) * 2)
 
-/*
- * This disables KASAN checking when reading a value from another task's stack,
- * since the other task could be running on another CPU and could have poisoned
- * the stack in the meantime.
- */
-#define READ_ONCE_TASK_STACK(task, x)			\
-({							\
-	unsigned long val;				\
-	if (task == current)				\
-		val = READ_ONCE(x);			\
-	else						\
-		val = READ_ONCE_NOCHECK(x);		\
-	val;						\
-})
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return 0;
+
+	return __kernel_text_address(state->ip) ? state->ip : 0;
+}
+EXPORT_SYMBOL_GPL(unwind_get_return_address);
+
+unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return NULL;
+
+	return state->regs ? &state->regs->ip : state->bp + 1;
+}
 
 static void unwind_dump(struct unwind_state *state)
 {
@@ -66,15 +68,6 @@ static void unwind_dump(struct unwind_state *state)
 	}
 }
 
-unsigned long unwind_get_return_address(struct unwind_state *state)
-{
-	if (unwind_done(state))
-		return 0;
-
-	return __kernel_text_address(state->ip) ? state->ip : 0;
-}
-EXPORT_SYMBOL_GPL(unwind_get_return_address);
-
 static size_t regs_size(struct pt_regs *regs)
 {
 	/* x86_32 regs from kernel mode are two words shorter: */
diff --git a/arch/x86/kernel/unwind_guess.c b/arch/x86/kernel/unwind_guess.c
index 039f36738e49..4f0e17b90463 100644
--- a/arch/x86/kernel/unwind_guess.c
+++ b/arch/x86/kernel/unwind_guess.c
@@ -19,6 +19,11 @@ unsigned long unwind_get_return_address(struct unwind_state *state)
 }
 EXPORT_SYMBOL_GPL(unwind_get_return_address);
 
+unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
+{
+	return NULL;
+}
+
 bool unwind_next_frame(struct unwind_state *state)
 {
 	struct stack_info *info = &state->stack_info;
diff --git a/arch/x86/kernel/unwind_orc.c b/arch/x86/kernel/unwind_orc.c
new file mode 100644
index 000000000000..570b70d3f604
--- /dev/null
+++ b/arch/x86/kernel/unwind_orc.c
@@ -0,0 +1,582 @@
+#include <linux/module.h>
+#include <linux/sort.h>
+#include <asm/ptrace.h>
+#include <asm/stacktrace.h>
+#include <asm/unwind.h>
+#include <asm/orc_types.h>
+#include <asm/orc_lookup.h>
+#include <asm/sections.h>
+
+#define orc_warn(fmt, ...) \
+	printk_deferred_once(KERN_WARNING pr_fmt("WARNING: " fmt), ##__VA_ARGS__)
+
+extern int __start_orc_unwind_ip[];
+extern int __stop_orc_unwind_ip[];
+extern struct orc_entry __start_orc_unwind[];
+extern struct orc_entry __stop_orc_unwind[];
+
+static DEFINE_MUTEX(sort_mutex);
+int *cur_orc_ip_table = __start_orc_unwind_ip;
+struct orc_entry *cur_orc_table = __start_orc_unwind;
+
+unsigned int lookup_num_blocks;
+bool orc_init;
+
+static inline unsigned long orc_ip(const int *ip)
+{
+	return (unsigned long)ip + *ip;
+}
+
+static struct orc_entry *__orc_find(int *ip_table, struct orc_entry *u_table,
+				    unsigned int num_entries, unsigned long ip)
+{
+	int *first = ip_table;
+	int *last = ip_table + num_entries - 1;
+	int *mid = first, *found = first;
+
+	if (!num_entries)
+		return NULL;
+
+	/*
+	 * Do a binary range search to find the rightmost duplicate of a given
+	 * starting address.  Some entries are section terminators which are
+	 * "weak" entries for ensuring there are no gaps.  They should be
+	 * ignored when they conflict with a real entry.
+	 */
+	while (first <= last) {
+		mid = first + ((last - first) / 2);
+
+		if (orc_ip(mid) <= ip) {
+			found = mid;
+			first = mid + 1;
+		} else
+			last = mid - 1;
+	}
+
+	return u_table + (found - ip_table);
+}
+
+#ifdef CONFIG_MODULES
+static struct orc_entry *orc_module_find(unsigned long ip)
+{
+	struct module *mod;
+
+	mod = __module_address(ip);
+	if (!mod || !mod->arch.orc_unwind || !mod->arch.orc_unwind_ip)
+		return NULL;
+	return __orc_find(mod->arch.orc_unwind_ip, mod->arch.orc_unwind,
+			  mod->arch.num_orcs, ip);
+}
+#else
+static struct orc_entry *orc_module_find(unsigned long ip)
+{
+	return NULL;
+}
+#endif
+
+static struct orc_entry *orc_find(unsigned long ip)
+{
+	if (!orc_init)
+		return NULL;
+
+	/* For non-init vmlinux addresses, use the fast lookup table: */
+	if (ip >= LOOKUP_START_IP && ip < LOOKUP_STOP_IP) {
+		unsigned int idx, start, stop;
+
+		idx = (ip - LOOKUP_START_IP) / LOOKUP_BLOCK_SIZE;
+
+		if (unlikely((idx >= lookup_num_blocks-1))) {
+			orc_warn("WARNING: bad lookup idx: idx=%u num=%u ip=%lx\n",
+				 idx, lookup_num_blocks, ip);
+			return NULL;
+		}
+
+		start = orc_lookup[idx];
+		stop = orc_lookup[idx + 1] + 1;
+
+		if (unlikely((__start_orc_unwind + start >= __stop_orc_unwind) ||
+			     (__start_orc_unwind + stop > __stop_orc_unwind))) {
+			orc_warn("WARNING: bad lookup value: idx=%u num=%u start=%u stop=%u ip=%lx\n",
+				 idx, lookup_num_blocks, start, stop, ip);
+			return NULL;
+		}
+
+		return __orc_find(__start_orc_unwind_ip + start,
+				  __start_orc_unwind + start, stop - start, ip);
+	}
+
+	/* vmlinux .init slow lookup: */
+	if (ip >= (unsigned long)_sinittext && ip < (unsigned long)_einittext)
+		return __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
+				  __stop_orc_unwind_ip - __start_orc_unwind_ip, ip);
+
+	/* Module lookup: */
+	return orc_module_find(ip);
+}
+
+static void orc_sort_swap(void *_a, void *_b, int size)
+{
+	struct orc_entry *orc_a, *orc_b;
+	struct orc_entry orc_tmp;
+	int *a = _a, *b = _b, tmp;
+	int delta = _b - _a;
+
+	/* Swap the .orc_unwind_ip entries: */
+	tmp = *a;
+	*a = *b + delta;
+	*b = tmp - delta;
+
+	/* Swap the corresponding .orc_unwind entries: */
+	orc_a = cur_orc_table + (a - cur_orc_ip_table);
+	orc_b = cur_orc_table + (b - cur_orc_ip_table);
+	orc_tmp = *orc_a;
+	*orc_a = *orc_b;
+	*orc_b = orc_tmp;
+}
+
+static int orc_sort_cmp(const void *_a, const void *_b)
+{
+	struct orc_entry *orc_a;
+	const int *a = _a, *b = _b;
+	unsigned long a_val = orc_ip(a);
+	unsigned long b_val = orc_ip(b);
+
+	if (a_val > b_val)
+		return 1;
+	if (a_val < b_val)
+		return -1;
+
+	/*
+	 * The "weak" section terminator entries need to always be on the left
+	 * to ensure the lookup code skips them in favor of real entries.
+	 * These terminator entries exist to handle any gaps created by
+	 * whitelisted .o files which didn't get objtool generation.
+	 */
+	orc_a = cur_orc_table + (a - cur_orc_ip_table);
+	return orc_a->sp_reg == ORC_REG_UNDEFINED ? -1 : 1;
+}
+
+#ifdef CONFIG_MODULES
+void unwind_module_init(struct module *mod, void *_orc_ip, size_t orc_ip_size,
+			void *_orc, size_t orc_size)
+{
+	int *orc_ip = _orc_ip;
+	struct orc_entry *orc = _orc;
+	unsigned int num_entries = orc_ip_size / sizeof(int);
+
+	WARN_ON_ONCE(orc_ip_size % sizeof(int) != 0 ||
+		     orc_size % sizeof(*orc) != 0 ||
+		     num_entries != orc_size / sizeof(*orc));
+
+	/*
+	 * The 'cur_orc_*' globals allow the orc_sort_swap() callback to
+	 * associate an .orc_unwind_ip table entry with its corresponding
+	 * .orc_unwind entry so they can both be swapped.
+	 */
+	mutex_lock(&sort_mutex);
+	cur_orc_ip_table = orc_ip;
+	cur_orc_table = orc;
+	sort(orc_ip, num_entries, sizeof(int), orc_sort_cmp, orc_sort_swap);
+	mutex_unlock(&sort_mutex);
+
+	mod->arch.orc_unwind_ip = orc_ip;
+	mod->arch.orc_unwind = orc;
+	mod->arch.num_orcs = num_entries;
+}
+#endif
+
+void __init unwind_init(void)
+{
+	size_t orc_ip_size = (void *)__stop_orc_unwind_ip - (void *)__start_orc_unwind_ip;
+	size_t orc_size = (void *)__stop_orc_unwind - (void *)__start_orc_unwind;
+	size_t num_entries = orc_ip_size / sizeof(int);
+	struct orc_entry *orc;
+	int i;
+
+	if (!num_entries || orc_ip_size % sizeof(int) != 0 ||
+	    orc_size % sizeof(struct orc_entry) != 0 ||
+	    num_entries != orc_size / sizeof(struct orc_entry)) {
+		orc_warn("WARNING: Bad or missing .orc_unwind table.  Disabling unwinder.\n");
+		return;
+	}
+
+	/* Sort the .orc_unwind and .orc_unwind_ip tables: */
+	sort(__start_orc_unwind_ip, num_entries, sizeof(int), orc_sort_cmp,
+	     orc_sort_swap);
+
+	/* Initialize the fast lookup table: */
+	lookup_num_blocks = orc_lookup_end - orc_lookup;
+	for (i = 0; i < lookup_num_blocks-1; i++) {
+		orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind,
+				 num_entries,
+				 LOOKUP_START_IP + (LOOKUP_BLOCK_SIZE * i));
+		if (!orc) {
+			orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
+			return;
+		}
+
+		orc_lookup[i] = orc - __start_orc_unwind;
+	}
+
+	/* Initialize the ending block: */
+	orc = __orc_find(__start_orc_unwind_ip, __start_orc_unwind, num_entries,
+			 LOOKUP_STOP_IP);
+	if (!orc) {
+		orc_warn("WARNING: Corrupt .orc_unwind table.  Disabling unwinder.\n");
+		return;
+	}
+	orc_lookup[lookup_num_blocks-1] = orc - __start_orc_unwind;
+
+	orc_init = true;
+}
+
+unsigned long unwind_get_return_address(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return 0;
+
+	return __kernel_text_address(state->ip) ? state->ip : 0;
+}
+EXPORT_SYMBOL_GPL(unwind_get_return_address);
+
+unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
+{
+	if (unwind_done(state))
+		return NULL;
+
+	if (state->regs)
+		return &state->regs->ip;
+
+	if (state->sp)
+		return (unsigned long *)state->sp - 1;
+
+	return NULL;
+}
+
+static bool stack_access_ok(struct unwind_state *state, unsigned long addr,
+			    size_t len)
+{
+	struct stack_info *info = &state->stack_info;
+
+	/*
+	 * If the address isn't on the current stack, switch to the next one.
+	 *
+	 * We may have to traverse multiple stacks to deal with the possibility
+	 * that info->next_sp could point to an empty stack and the address
+	 * could be on a subsequent stack.
+	 */
+	while (!on_stack(info, (void *)addr, len))
+		if (get_stack_info(info->next_sp, state->task, info,
+				   &state->stack_mask))
+			return false;
+
+	return true;
+}
+
+static bool deref_stack_reg(struct unwind_state *state, unsigned long addr,
+			    unsigned long *val)
+{
+	if (!stack_access_ok(state, addr, sizeof(long)))
+		return false;
+
+	*val = READ_ONCE_TASK_STACK(state->task, *(unsigned long *)addr);
+	return true;
+}
+
+#define REGS_SIZE (sizeof(struct pt_regs))
+#define SP_OFFSET (offsetof(struct pt_regs, sp))
+#define IRET_REGS_SIZE (REGS_SIZE - offsetof(struct pt_regs, ip))
+#define IRET_SP_OFFSET (SP_OFFSET - offsetof(struct pt_regs, ip))
+
+static bool deref_stack_regs(struct unwind_state *state, unsigned long addr,
+			     unsigned long *ip, unsigned long *sp, bool full)
+{
+	size_t regs_size = full ? REGS_SIZE : IRET_REGS_SIZE;
+	size_t sp_offset = full ? SP_OFFSET : IRET_SP_OFFSET;
+	struct pt_regs *regs = (struct pt_regs *)(addr + regs_size - REGS_SIZE);
+
+	if (IS_ENABLED(CONFIG_X86_64)) {
+		if (!stack_access_ok(state, addr, regs_size))
+			return false;
+
+		*ip = regs->ip;
+		*sp = regs->sp;
+
+		return true;
+	}
+
+	if (!stack_access_ok(state, addr, sp_offset))
+		return false;
+
+	*ip = regs->ip;
+
+	if (user_mode(regs)) {
+		if (!stack_access_ok(state, addr + sp_offset,
+				     REGS_SIZE - SP_OFFSET))
+			return false;
+
+		*sp = regs->sp;
+	} else
+		*sp = (unsigned long)&regs->sp;
+
+	return true;
+}
+
+bool unwind_next_frame(struct unwind_state *state)
+{
+	unsigned long ip_p, sp, orig_ip, prev_sp = state->sp;
+	enum stack_type prev_type = state->stack_info.type;
+	struct orc_entry *orc;
+	struct pt_regs *ptregs;
+	bool indirect = false;
+
+	if (unwind_done(state))
+		return false;
+
+	/* Don't let modules unload while we're reading their ORC data. */
+	preempt_disable();
+
+	/* Have we reached the end? */
+	if (state->regs && user_mode(state->regs))
+		goto done;
+
+	/*
+	 * 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.
+	 */
+	orc = orc_find(state->signal ? state->ip : state->ip - 1);
+	if (!orc || orc->sp_reg == ORC_REG_UNDEFINED)
+		goto done;
+	orig_ip = state->ip;
+
+	/* Find the previous frame's stack: */
+	switch (orc->sp_reg) {
+	case ORC_REG_SP:
+		sp = state->sp + orc->sp_offset;
+		break;
+
+	case ORC_REG_BP:
+		sp = state->bp + orc->sp_offset;
+		break;
+
+	case ORC_REG_SP_INDIRECT:
+		sp = state->sp + orc->sp_offset;
+		indirect = true;
+		break;
+
+	case ORC_REG_BP_INDIRECT:
+		sp = state->bp + orc->sp_offset;
+		indirect = true;
+		break;
+
+	case ORC_REG_R10:
+		if (!state->regs || !state->full_regs) {
+			orc_warn("missing regs for base reg R10 at ip %p\n",
+				 (void *)state->ip);
+			goto done;
+		}
+		sp = state->regs->r10;
+		break;
+
+	case ORC_REG_R13:
+		if (!state->regs || !state->full_regs) {
+			orc_warn("missing regs for base reg R13 at ip %p\n",
+				 (void *)state->ip);
+			goto done;
+		}
+		sp = state->regs->r13;
+		break;
+
+	case ORC_REG_DI:
+		if (!state->regs || !state->full_regs) {
+			orc_warn("missing regs for base reg DI at ip %p\n",
+				 (void *)state->ip);
+			goto done;
+		}
+		sp = state->regs->di;
+		break;
+
+	case ORC_REG_DX:
+		if (!state->regs || !state->full_regs) {
+			orc_warn("missing regs for base reg DX at ip %p\n",
+				 (void *)state->ip);
+			goto done;
+		}
+		sp = state->regs->dx;
+		break;
+
+	default:
+		orc_warn("unknown SP base reg %d for ip %p\n",
+			 orc->sp_reg, (void *)state->ip);
+		goto done;
+	}
+
+	if (indirect) {
+		if (!deref_stack_reg(state, sp, &sp))
+			goto done;
+	}
+
+	/* Find IP, SP and possibly regs: */
+	switch (orc->type) {
+	case ORC_TYPE_CALL:
+		ip_p = sp - sizeof(long);
+
+		if (!deref_stack_reg(state, ip_p, &state->ip))
+			goto done;
+
+		state->ip = ftrace_graph_ret_addr(state->task, &state->graph_idx,
+						  state->ip, (void *)ip_p);
+
+		state->sp = sp;
+		state->regs = NULL;
+		state->signal = false;
+		break;
+
+	case ORC_TYPE_REGS:
+		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, true)) {
+			orc_warn("can't dereference registers at %p for ip %p\n",
+				 (void *)sp, (void *)orig_ip);
+			goto done;
+		}
+
+		state->regs = (struct pt_regs *)sp;
+		state->full_regs = true;
+		state->signal = true;
+		break;
+
+	case ORC_TYPE_REGS_IRET:
+		if (!deref_stack_regs(state, sp, &state->ip, &state->sp, false)) {
+			orc_warn("can't dereference iret registers at %p for ip %p\n",
+				 (void *)sp, (void *)orig_ip);
+			goto done;
+		}
+
+		ptregs = container_of((void *)sp, struct pt_regs, ip);
+		if ((unsigned long)ptregs >= prev_sp &&
+		    on_stack(&state->stack_info, ptregs, REGS_SIZE)) {
+			state->regs = ptregs;
+			state->full_regs = false;
+		} else
+			state->regs = NULL;
+
+		state->signal = true;
+		break;
+
+	default:
+		orc_warn("unknown .orc_unwind entry type %d\n", orc->type);
+		break;
+	}
+
+	/* Find BP: */
+	switch (orc->bp_reg) {
+	case ORC_REG_UNDEFINED:
+		if (state->regs && state->full_regs)
+			state->bp = state->regs->bp;
+		break;
+
+	case ORC_REG_PREV_SP:
+		if (!deref_stack_reg(state, sp + orc->bp_offset, &state->bp))
+			goto done;
+		break;
+
+	case ORC_REG_BP:
+		if (!deref_stack_reg(state, state->bp + orc->bp_offset, &state->bp))
+			goto done;
+		break;
+
+	default:
+		orc_warn("unknown BP base reg %d for ip %p\n",
+			 orc->bp_reg, (void *)orig_ip);
+		goto done;
+	}
+
+	/* Prevent a recursive loop due to bad ORC data: */
+	if (state->stack_info.type == prev_type &&
+	    on_stack(&state->stack_info, (void *)state->sp, sizeof(long)) &&
+	    state->sp <= prev_sp) {
+		orc_warn("stack going in the wrong direction? ip=%p\n",
+			 (void *)orig_ip);
+		goto done;
+	}
+
+	preempt_enable();
+	return true;
+
+done:
+	preempt_enable();
+	state->stack_info.type = STACK_TYPE_UNKNOWN;
+	return false;
+}
+EXPORT_SYMBOL_GPL(unwind_next_frame);
+
+void __unwind_start(struct unwind_state *state, struct task_struct *task,
+		    struct pt_regs *regs, unsigned long *first_frame)
+{
+	memset(state, 0, sizeof(*state));
+	state->task = task;
+
+	/*
+	 * Refuse to unwind the stack of a task while it's executing on another
+	 * CPU.  This check is racy, but that's ok: the unwinder has other
+	 * checks to prevent it from going off the rails.
+	 */
+	if (task_on_another_cpu(task))
+		goto done;
+
+	if (regs) {
+		if (user_mode(regs))
+			goto done;
+
+		state->ip = regs->ip;
+		state->sp = kernel_stack_pointer(regs);
+		state->bp = regs->bp;
+		state->regs = regs;
+		state->full_regs = true;
+		state->signal = true;
+
+	} else if (task == current) {
+		asm volatile("lea (%%rip), %0\n\t"
+			     "mov %%rsp, %1\n\t"
+			     "mov %%rbp, %2\n\t"
+			     : "=r" (state->ip), "=r" (state->sp),
+			       "=r" (state->bp));
+
+	} else {
+		struct inactive_task_frame *frame = (void *)task->thread.sp;
+
+		state->sp = task->thread.sp;
+		state->bp = READ_ONCE_NOCHECK(frame->bp);
+		state->ip = READ_ONCE_NOCHECK(frame->ret_addr);
+	}
+
+	if (get_stack_info((unsigned long *)state->sp, state->task,
+			   &state->stack_info, &state->stack_mask))
+		return;
+
+	/*
+	 * The caller can provide the address of the first frame directly
+	 * (first_frame) or indirectly (regs->sp) to indicate which stack frame
+	 * to start unwinding at.  Skip ahead until we reach it.
+	 */
+
+	/* When starting from regs, skip the regs frame: */
+	if (regs) {
+		unwind_next_frame(state);
+		return;
+	}
+
+	/* 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))
+		unwind_next_frame(state);
+
+	return;
+
+done:
+	state->stack_info.type = STACK_TYPE_UNKNOWN;
+	return;
+}
+EXPORT_SYMBOL_GPL(__unwind_start);
diff --git a/arch/x86/kernel/vmlinux.lds.S b/arch/x86/kernel/vmlinux.lds.S
index c8a3b61be0aa..f05f00acac89 100644
--- a/arch/x86/kernel/vmlinux.lds.S
+++ b/arch/x86/kernel/vmlinux.lds.S
@@ -24,6 +24,7 @@
 #include <asm/asm-offsets.h>
 #include <asm/thread_info.h>
 #include <asm/page_types.h>
+#include <asm/orc_lookup.h>
 #include <asm/cache.h>
 #include <asm/boot.h>
 
@@ -148,6 +149,8 @@ SECTIONS
 
 	BUG_TABLE
 
+	ORC_UNWIND_TABLE
+
 	. = ALIGN(PAGE_SIZE);
 	__vvar_page = .;