x86/unwind: Add the ORC unwinder

Add the new ORC unwinder which is enabled by CONFIG_ORC_UNWINDER=y.
It plugs into the existing x86 unwinder framework.

It relies on objtool to generate the needed .orc_unwind and
.orc_unwind_ip sections.

For more details on why ORC is used instead of DWARF, see
Documentation/x86/orc-unwinder.txt - but the short version is
that it's a simplified, fundamentally more robust debugninfo
data structure, which also allows up to two orders of magnitude
faster lookups than the DWARF unwinder - which matters to
profiling workloads like perf.

Thanks to Andy Lutomirski for the performance improvement ideas:
splitting the ORC unwind table into two parallel arrays and creating a
fast lookup table to search a subset of the unwind table.

Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: live-patching@vger.kernel.org
Link: http://lkml.kernel.org/r/0a6cbfb40f8da99b7a45a1a8302dc6aef16ec812.1500938583.git.jpoimboe@redhat.com
[ Extended the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>

13 files changed, 751 insertions, 59 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 781521b7cf9e..7ccf26a427cb 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -157,6 +157,7 @@ config X86
 	select HAVE_MEMBLOCK
 	select HAVE_MEMBLOCK_NODE_MAP
 	select HAVE_MIXED_BREAKPOINTS_REGS
+	select HAVE_MOD_ARCH_SPECIFIC
 	select HAVE_NMI
 	select HAVE_OPROFILE
 	select HAVE_OPTPROBES
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index 353ed09f5fba..dc10ec6ead6e 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -355,4 +355,29 @@ config PUNIT_ATOM_DEBUG
 	  The current power state can be read from
 	  /sys/kernel/debug/punit_atom/dev_power_state
 
+config ORC_UNWINDER
+	bool "ORC unwinder"
+	depends on X86_64
+	select STACK_VALIDATION
+	---help---
+	  This option enables the ORC (Oops Rewind Capability) unwinder for
+	  unwinding kernel stack traces.  It uses a custom data format which is
+	  a simplified version of the DWARF Call Frame Information standard.
+
+	  This unwinder is more accurate across interrupt entry frames than the
+	  frame pointer unwinder.  It can also enable a 5-10% performance
+	  improvement across the entire kernel if CONFIG_FRAME_POINTER is
+	  disabled.
+
+	  Enabling this option will increase the kernel's runtime memory usage
+	  by roughly 2-4MB, depending on your kernel config.
+
+config FRAME_POINTER_UNWINDER
+	def_bool y
+	depends on !ORC_UNWINDER && FRAME_POINTER
+
+config GUESS_UNWINDER
+	def_bool y
+	depends on !ORC_UNWINDER && !FRAME_POINTER
+
 endmenu
diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index e3b7819caeef..9eb7c718aaf8 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -2,6 +2,15 @@
 #define _ASM_X86_MODULE_H
 
 #include <asm-generic/module.h>
+#include <asm/orc_types.h>
+
+struct mod_arch_specific {
+#ifdef CONFIG_ORC_UNWINDER
+	unsigned int num_orcs;
+	int *orc_unwind_ip;
+	struct orc_entry *orc_unwind;
+#endif
+};
 
 #ifdef CONFIG_X86_64
 /* X86_64 does not define MODULE_PROC_FAMILY */
diff --git a/arch/x86/include/asm/orc_lookup.h b/arch/x86/include/asm/orc_lookup.h
new file mode 100644
index 000000000000..91c8d868424d
--- /dev/null
+++ b/arch/x86/include/asm/orc_lookup.h
@@ -0,0 +1,46 @@
+/*
+ * Copyright (C) 2017 Josh Poimboeuf <jpoimboe@redhat.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+#ifndef _ORC_LOOKUP_H
+#define _ORC_LOOKUP_H
+
+/*
+ * This is a lookup table for speeding up access to the .orc_unwind table.
+ * Given an input address offset, the corresponding lookup table entry
+ * specifies a subset of the .orc_unwind table to search.
+ *
+ * Each block represents the end of the previous range and the start of the
+ * next range.  An extra block is added to give the last range an end.
+ *
+ * The block size should be a power of 2 to avoid a costly 'div' instruction.
+ *
+ * A block size of 256 was chosen because it roughly doubles unwinder
+ * performance while only adding ~5% to the ORC data footprint.
+ */
+#define LOOKUP_BLOCK_ORDER	8
+#define LOOKUP_BLOCK_SIZE	(1 << LOOKUP_BLOCK_ORDER)
+
+#ifndef LINKER_SCRIPT
+
+extern unsigned int orc_lookup[];
+extern unsigned int orc_lookup_end[];
+
+#define LOOKUP_START_IP		(unsigned long)_stext
+#define LOOKUP_STOP_IP		(unsigned long)_etext
+
+#endif /* LINKER_SCRIPT */
+
+#endif /* _ORC_LOOKUP_H */
diff --git a/arch/x86/include/asm/orc_types.h b/arch/x86/include/asm/orc_types.h
index 7dc777a6cb40..9c9dc579bd7d 100644
--- a/arch/x86/include/asm/orc_types.h
+++ b/arch/x86/include/asm/orc_types.h
@@ -88,7 +88,7 @@ struct orc_entry {
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
-};
+} __packed;
 
 /*
  * This struct is used by asm and inline asm code to manually annotate the
diff --git a/arch/x86/include/asm/unwind.h b/arch/x86/include/asm/unwind.h
index e6676495b125..25b8d31a007d 100644
--- a/arch/x86/include/asm/unwind.h
+++ b/arch/x86/include/asm/unwind.h
@@ -12,11 +12,14 @@ struct unwind_state {
 	struct task_struct *task;
 	int graph_idx;
 	bool error;
-#ifdef CONFIG_FRAME_POINTER
+#if defined(CONFIG_ORC_UNWINDER)
+	bool signal, full_regs;
+	unsigned long sp, bp, ip;
+	struct pt_regs *regs;
+#elif defined(CONFIG_FRAME_POINTER)
 	bool got_irq;
-	unsigned long *bp, *orig_sp;
+	unsigned long *bp, *orig_sp, ip;
 	struct pt_regs *regs;
-	unsigned long ip;
 #else
 	unsigned long *sp;
 #endif
@@ -24,41 +27,30 @@ struct unwind_state {
 
 void __unwind_start(struct unwind_state *state, struct task_struct *task,
 		    struct pt_regs *regs, unsigned long *first_frame);
-
 bool unwind_next_frame(struct unwind_state *state);
-
 unsigned long unwind_get_return_address(struct unwind_state *state);
+unsigned long *unwind_get_return_address_ptr(struct unwind_state *state);
 
 static inline bool unwind_done(struct unwind_state *state)
 {
 	return state->stack_info.type == STACK_TYPE_UNKNOWN;
 }
 
-static inline
-void unwind_start(struct unwind_state *state, struct task_struct *task,
-		  struct pt_regs *regs, unsigned long *first_frame)
-{
-	first_frame = first_frame ? : get_stack_pointer(task, regs);
-
-	__unwind_start(state, task, regs, first_frame);
-}
-
 static inline bool unwind_error(struct unwind_state *state)
 {
 	return state->error;
 }
 
-#ifdef CONFIG_FRAME_POINTER
-
 static inline
-unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
+void unwind_start(struct unwind_state *state, struct task_struct *task,
+		  struct pt_regs *regs, unsigned long *first_frame)
 {
-	if (unwind_done(state))
-		return NULL;
+	first_frame = first_frame ? : get_stack_pointer(task, regs);
 
-	return state->regs ? &state->regs->ip : state->bp + 1;
+	__unwind_start(state, task, regs, first_frame);
 }
 
+#if defined(CONFIG_ORC_UNWINDER) || defined(CONFIG_FRAME_POINTER)
 static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
 {
 	if (unwind_done(state))
@@ -66,20 +58,46 @@ static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
 
 	return state->regs;
 }
-
-#else /* !CONFIG_FRAME_POINTER */
-
-static inline
-unsigned long *unwind_get_return_address_ptr(struct unwind_state *state)
+#else
+static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
 {
 	return NULL;
 }
+#endif
 
-static inline struct pt_regs *unwind_get_entry_regs(struct unwind_state *state)
+#ifdef CONFIG_ORC_UNWINDER
+void unwind_init(void);
+void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size,
+			void *orc, size_t orc_size);
+#else
+static inline void unwind_init(void) {}
+static inline
+void unwind_module_init(struct module *mod, void *orc_ip, size_t orc_ip_size,
+			void *orc, size_t orc_size) {}
+#endif
+
+/*
+ * 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;						\
+})
+
+static inline bool task_on_another_cpu(struct task_struct *task)
 {
-	return NULL;
+#ifdef CONFIG_SMP
+	return task != current && task->on_cpu;
+#else
+	return false;
+#endif
 }
 
-#endif /* CONFIG_FRAME_POINTER */
-
 #endif /* _ASM_X86_UNWIND_H */
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/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/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/unwind_frame.c b/arch/x86/kernel/unwind_frame.c
index b9389d72b2f7..7574ef5f16ec 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 = .;