19 files changed, 762 insertions, 13 deletions

diff --git a/tools/perf/arch/arm/Makefile b/tools/perf/arch/arm/Makefile
index 15130b50dfe..09d62153d38 100644
--- a/tools/perf/arch/arm/Makefile
+++ b/tools/perf/arch/arm/Makefile
@@ -2,3 +2,13 @@ ifndef NO_DWARF
 PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
+ifndef NO_LIBUNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
+endif
+ifndef NO_LIBDW_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libdw.o
+endif
+ifndef NO_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
+endif
diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h
new file mode 100644
index 00000000000..f619c9c5a4b
--- /dev/null
+++ b/tools/perf/arch/arm/include/perf_regs.h
@@ -0,0 +1,59 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+void perf_regs_load(u64 *regs);
+
+#define PERF_REGS_MASK	((1ULL << PERF_REG_ARM_MAX) - 1)
+#define PERF_REGS_MAX	PERF_REG_ARM_MAX
+#define PERF_SAMPLE_REGS_ABI	PERF_SAMPLE_REGS_ABI_32
+
+#define PERF_REG_IP	PERF_REG_ARM_PC
+#define PERF_REG_SP	PERF_REG_ARM_SP
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM_R0:
+		return "r0";
+	case PERF_REG_ARM_R1:
+		return "r1";
+	case PERF_REG_ARM_R2:
+		return "r2";
+	case PERF_REG_ARM_R3:
+		return "r3";
+	case PERF_REG_ARM_R4:
+		return "r4";
+	case PERF_REG_ARM_R5:
+		return "r5";
+	case PERF_REG_ARM_R6:
+		return "r6";
+	case PERF_REG_ARM_R7:
+		return "r7";
+	case PERF_REG_ARM_R8:
+		return "r8";
+	case PERF_REG_ARM_R9:
+		return "r9";
+	case PERF_REG_ARM_R10:
+		return "r10";
+	case PERF_REG_ARM_FP:
+		return "fp";
+	case PERF_REG_ARM_IP:
+		return "ip";
+	case PERF_REG_ARM_SP:
+		return "sp";
+	case PERF_REG_ARM_LR:
+		return "lr";
+	case PERF_REG_ARM_PC:
+		return "pc";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm/tests/dwarf-unwind.c b/tools/perf/arch/arm/tests/dwarf-unwind.c
new file mode 100644
index 00000000000..9f870d27cb3
--- /dev/null
+++ b/tools/perf/arch/arm/tests/dwarf-unwind.c
@@ -0,0 +1,60 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_ARM_SP];
+
+	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = calloc(1, sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/arm/tests/regs_load.S b/tools/perf/arch/arm/tests/regs_load.S
new file mode 100644
index 00000000000..e09e983946f
--- /dev/null
+++ b/tools/perf/arch/arm/tests/regs_load.S
@@ -0,0 +1,58 @@
+#include <linux/linkage.h>
+
+#define R0 0x00
+#define R1 0x08
+#define R2 0x10
+#define R3 0x18
+#define R4 0x20
+#define R5 0x28
+#define R6 0x30
+#define R7 0x38
+#define R8 0x40
+#define R9 0x48
+#define SL 0x50
+#define FP 0x58
+#define IP 0x60
+#define SP 0x68
+#define LR 0x70
+#define PC 0x78
+
+/*
+ * Implementation of void perf_regs_load(u64 *regs);
+ *
+ * This functions fills in the 'regs' buffer from the actual registers values,
+ * in the way the perf built-in unwinding test expects them:
+ * - the PC at the time at the call to this function. Since this function
+ *   is called using a bl instruction, the PC value is taken from LR.
+ * The built-in unwinding test then unwinds the call stack from the dwarf
+ * information in unwind__get_entries.
+ *
+ * Notes:
+ * - the 8 bytes stride in the registers offsets comes from the fact
+ * that the registers are stored in an u64 array (u64 *regs),
+ * - the regs buffer needs to be zeroed before the call to this function,
+ * in this case using a calloc in dwarf-unwind.c.
+ */
+
+.text
+.type perf_regs_load,%function
+ENTRY(perf_regs_load)
+	str r0, [r0, #R0]
+	str r1, [r0, #R1]
+	str r2, [r0, #R2]
+	str r3, [r0, #R3]
+	str r4, [r0, #R4]
+	str r5, [r0, #R5]
+	str r6, [r0, #R6]
+	str r7, [r0, #R7]
+	str r8, [r0, #R8]
+	str r9, [r0, #R9]
+	str sl, [r0, #SL]
+	str fp, [r0, #FP]
+	str ip, [r0, #IP]
+	str sp, [r0, #SP]
+	str lr, [r0, #LR]
+	str lr, [r0, #PC]	// store pc as lr in order to skip the call
+	                        //  to this function
+	mov pc, lr
+ENDPROC(perf_regs_load)
diff --git a/tools/perf/arch/arm/util/unwind-libdw.c b/tools/perf/arch/arm/util/unwind-libdw.c
new file mode 100644
index 00000000000..b4176c60117
--- /dev/null
+++ b/tools/perf/arch/arm/util/unwind-libdw.c
@@ -0,0 +1,36 @@
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[PERF_REG_ARM_MAX];
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_ARM_##r);	\
+	val;							\
+})
+
+	dwarf_regs[0]  = REG(R0);
+	dwarf_regs[1]  = REG(R1);
+	dwarf_regs[2]  = REG(R2);
+	dwarf_regs[3]  = REG(R3);
+	dwarf_regs[4]  = REG(R4);
+	dwarf_regs[5]  = REG(R5);
+	dwarf_regs[6]  = REG(R6);
+	dwarf_regs[7]  = REG(R7);
+	dwarf_regs[8]  = REG(R8);
+	dwarf_regs[9]  = REG(R9);
+	dwarf_regs[10] = REG(R10);
+	dwarf_regs[11] = REG(FP);
+	dwarf_regs[12] = REG(IP);
+	dwarf_regs[13] = REG(SP);
+	dwarf_regs[14] = REG(LR);
+	dwarf_regs[15] = REG(PC);
+
+	return dwfl_thread_state_registers(thread, 0, PERF_REG_ARM_MAX,
+					   dwarf_regs);
+}
diff --git a/tools/perf/arch/arm/util/unwind-libunwind.c b/tools/perf/arch/arm/util/unwind-libunwind.c
new file mode 100644
index 00000000000..729ed69a666
--- /dev/null
+++ b/tools/perf/arch/arm/util/unwind-libunwind.c
@@ -0,0 +1,48 @@
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+
+int libunwind__arch_reg_id(int regnum)
+{
+	switch (regnum) {
+	case UNW_ARM_R0:
+		return PERF_REG_ARM_R0;
+	case UNW_ARM_R1:
+		return PERF_REG_ARM_R1;
+	case UNW_ARM_R2:
+		return PERF_REG_ARM_R2;
+	case UNW_ARM_R3:
+		return PERF_REG_ARM_R3;
+	case UNW_ARM_R4:
+		return PERF_REG_ARM_R4;
+	case UNW_ARM_R5:
+		return PERF_REG_ARM_R5;
+	case UNW_ARM_R6:
+		return PERF_REG_ARM_R6;
+	case UNW_ARM_R7:
+		return PERF_REG_ARM_R7;
+	case UNW_ARM_R8:
+		return PERF_REG_ARM_R8;
+	case UNW_ARM_R9:
+		return PERF_REG_ARM_R9;
+	case UNW_ARM_R10:
+		return PERF_REG_ARM_R10;
+	case UNW_ARM_R11:
+		return PERF_REG_ARM_FP;
+	case UNW_ARM_R12:
+		return PERF_REG_ARM_IP;
+	case UNW_ARM_R13:
+		return PERF_REG_ARM_SP;
+	case UNW_ARM_R14:
+		return PERF_REG_ARM_LR;
+	case UNW_ARM_R15:
+		return PERF_REG_ARM_PC;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}
diff --git a/tools/perf/arch/arm64/Makefile b/tools/perf/arch/arm64/Makefile
new file mode 100644
index 00000000000..67e9b3d38e8
--- /dev/null
+++ b/tools/perf/arch/arm64/Makefile
@@ -0,0 +1,7 @@
+ifndef NO_DWARF
+PERF_HAVE_DWARF_REGS := 1
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
+endif
+ifndef NO_LIBUNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
+endif
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
new file mode 100644
index 00000000000..e9441b9e2a3
--- /dev/null
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -0,0 +1,88 @@
+#ifndef ARCH_PERF_REGS_H
+#define ARCH_PERF_REGS_H
+
+#include <stdlib.h>
+#include <linux/types.h>
+#include <asm/perf_regs.h>
+
+#define PERF_REGS_MASK	((1ULL << PERF_REG_ARM64_MAX) - 1)
+#define PERF_REG_IP	PERF_REG_ARM64_PC
+#define PERF_REG_SP	PERF_REG_ARM64_SP
+
+static inline const char *perf_reg_name(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM64_X0:
+		return "x0";
+	case PERF_REG_ARM64_X1:
+		return "x1";
+	case PERF_REG_ARM64_X2:
+		return "x2";
+	case PERF_REG_ARM64_X3:
+		return "x3";
+	case PERF_REG_ARM64_X4:
+		return "x4";
+	case PERF_REG_ARM64_X5:
+		return "x5";
+	case PERF_REG_ARM64_X6:
+		return "x6";
+	case PERF_REG_ARM64_X7:
+		return "x7";
+	case PERF_REG_ARM64_X8:
+		return "x8";
+	case PERF_REG_ARM64_X9:
+		return "x9";
+	case PERF_REG_ARM64_X10:
+		return "x10";
+	case PERF_REG_ARM64_X11:
+		return "x11";
+	case PERF_REG_ARM64_X12:
+		return "x12";
+	case PERF_REG_ARM64_X13:
+		return "x13";
+	case PERF_REG_ARM64_X14:
+		return "x14";
+	case PERF_REG_ARM64_X15:
+		return "x15";
+	case PERF_REG_ARM64_X16:
+		return "x16";
+	case PERF_REG_ARM64_X17:
+		return "x17";
+	case PERF_REG_ARM64_X18:
+		return "x18";
+	case PERF_REG_ARM64_X19:
+		return "x19";
+	case PERF_REG_ARM64_X20:
+		return "x20";
+	case PERF_REG_ARM64_X21:
+		return "x21";
+	case PERF_REG_ARM64_X22:
+		return "x22";
+	case PERF_REG_ARM64_X23:
+		return "x23";
+	case PERF_REG_ARM64_X24:
+		return "x24";
+	case PERF_REG_ARM64_X25:
+		return "x25";
+	case PERF_REG_ARM64_X26:
+		return "x26";
+	case PERF_REG_ARM64_X27:
+		return "x27";
+	case PERF_REG_ARM64_X28:
+		return "x28";
+	case PERF_REG_ARM64_X29:
+		return "x29";
+	case PERF_REG_ARM64_SP:
+		return "sp";
+	case PERF_REG_ARM64_LR:
+		return "lr";
+	case PERF_REG_ARM64_PC:
+		return "pc";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+#endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm64/util/dwarf-regs.c b/tools/perf/arch/arm64/util/dwarf-regs.c
new file mode 100644
index 00000000000..d49efeb8172
--- /dev/null
+++ b/tools/perf/arch/arm64/util/dwarf-regs.c
@@ -0,0 +1,80 @@
+/*
+ * Mapping of DWARF debug register numbers into register names.
+ *
+ * Copyright (C) 2010 Will Deacon, ARM Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <stddef.h>
+#include <dwarf-regs.h>
+
+struct pt_regs_dwarfnum {
+	const char *name;
+	unsigned int dwarfnum;
+};
+
+#define STR(s) #s
+#define REG_DWARFNUM_NAME(r, num) {.name = r, .dwarfnum = num}
+#define GPR_DWARFNUM_NAME(num) \
+	{.name = STR(%x##num), .dwarfnum = num}
+#define REG_DWARFNUM_END {.name = NULL, .dwarfnum = 0}
+
+/*
+ * Reference:
+ * http://infocenter.arm.com/help/topic/com.arm.doc.ihi0057b/IHI0057B_aadwarf64.pdf
+ */
+static const struct pt_regs_dwarfnum regdwarfnum_table[] = {
+	GPR_DWARFNUM_NAME(0),
+	GPR_DWARFNUM_NAME(1),
+	GPR_DWARFNUM_NAME(2),
+	GPR_DWARFNUM_NAME(3),
+	GPR_DWARFNUM_NAME(4),
+	GPR_DWARFNUM_NAME(5),
+	GPR_DWARFNUM_NAME(6),
+	GPR_DWARFNUM_NAME(7),
+	GPR_DWARFNUM_NAME(8),
+	GPR_DWARFNUM_NAME(9),
+	GPR_DWARFNUM_NAME(10),
+	GPR_DWARFNUM_NAME(11),
+	GPR_DWARFNUM_NAME(12),
+	GPR_DWARFNUM_NAME(13),
+	GPR_DWARFNUM_NAME(14),
+	GPR_DWARFNUM_NAME(15),
+	GPR_DWARFNUM_NAME(16),
+	GPR_DWARFNUM_NAME(17),
+	GPR_DWARFNUM_NAME(18),
+	GPR_DWARFNUM_NAME(19),
+	GPR_DWARFNUM_NAME(20),
+	GPR_DWARFNUM_NAME(21),
+	GPR_DWARFNUM_NAME(22),
+	GPR_DWARFNUM_NAME(23),
+	GPR_DWARFNUM_NAME(24),
+	GPR_DWARFNUM_NAME(25),
+	GPR_DWARFNUM_NAME(26),
+	GPR_DWARFNUM_NAME(27),
+	GPR_DWARFNUM_NAME(28),
+	GPR_DWARFNUM_NAME(29),
+	REG_DWARFNUM_NAME("%lr", 30),
+	REG_DWARFNUM_NAME("%sp", 31),
+	REG_DWARFNUM_END,
+};
+
+/**
+ * get_arch_regstr() - lookup register name from it's DWARF register number
+ * @n:	the DWARF register number
+ *
+ * get_arch_regstr() returns the name of the register in struct
+ * regdwarfnum_table from it's DWARF register number. If the register is not
+ * found in the table, this returns NULL;
+ */
+const char *get_arch_regstr(unsigned int n)
+{
+	const struct pt_regs_dwarfnum *roff;
+	for (roff = regdwarfnum_table; roff->name != NULL; roff++)
+		if (roff->dwarfnum == n)
+			return roff->name;
+	return NULL;
+}
diff --git a/tools/perf/arch/arm64/util/unwind-libunwind.c b/tools/perf/arch/arm64/util/unwind-libunwind.c
new file mode 100644
index 00000000000..436ee43859d
--- /dev/null
+++ b/tools/perf/arch/arm64/util/unwind-libunwind.c
@@ -0,0 +1,82 @@
+
+#include <errno.h>
+#include <libunwind.h>
+#include "perf_regs.h"
+#include "../../util/unwind.h"
+
+int libunwind__arch_reg_id(int regnum)
+{
+	switch (regnum) {
+	case UNW_AARCH64_X0:
+		return PERF_REG_ARM64_X0;
+	case UNW_AARCH64_X1:
+		return PERF_REG_ARM64_X1;
+	case UNW_AARCH64_X2:
+		return PERF_REG_ARM64_X2;
+	case UNW_AARCH64_X3:
+		return PERF_REG_ARM64_X3;
+	case UNW_AARCH64_X4:
+		return PERF_REG_ARM64_X4;
+	case UNW_AARCH64_X5:
+		return PERF_REG_ARM64_X5;
+	case UNW_AARCH64_X6:
+		return PERF_REG_ARM64_X6;
+	case UNW_AARCH64_X7:
+		return PERF_REG_ARM64_X7;
+	case UNW_AARCH64_X8:
+		return PERF_REG_ARM64_X8;
+	case UNW_AARCH64_X9:
+		return PERF_REG_ARM64_X9;
+	case UNW_AARCH64_X10:
+		return PERF_REG_ARM64_X10;
+	case UNW_AARCH64_X11:
+		return PERF_REG_ARM64_X11;
+	case UNW_AARCH64_X12:
+		return PERF_REG_ARM64_X12;
+	case UNW_AARCH64_X13:
+		return PERF_REG_ARM64_X13;
+	case UNW_AARCH64_X14:
+		return PERF_REG_ARM64_X14;
+	case UNW_AARCH64_X15:
+		return PERF_REG_ARM64_X15;
+	case UNW_AARCH64_X16:
+		return PERF_REG_ARM64_X16;
+	case UNW_AARCH64_X17:
+		return PERF_REG_ARM64_X17;
+	case UNW_AARCH64_X18:
+		return PERF_REG_ARM64_X18;
+	case UNW_AARCH64_X19:
+		return PERF_REG_ARM64_X19;
+	case UNW_AARCH64_X20:
+		return PERF_REG_ARM64_X20;
+	case UNW_AARCH64_X21:
+		return PERF_REG_ARM64_X21;
+	case UNW_AARCH64_X22:
+		return PERF_REG_ARM64_X22;
+	case UNW_AARCH64_X23:
+		return PERF_REG_ARM64_X23;
+	case UNW_AARCH64_X24:
+		return PERF_REG_ARM64_X24;
+	case UNW_AARCH64_X25:
+		return PERF_REG_ARM64_X25;
+	case UNW_AARCH64_X26:
+		return PERF_REG_ARM64_X26;
+	case UNW_AARCH64_X27:
+		return PERF_REG_ARM64_X27;
+	case UNW_AARCH64_X28:
+		return PERF_REG_ARM64_X28;
+	case UNW_AARCH64_X29:
+		return PERF_REG_ARM64_X29;
+	case UNW_AARCH64_X30:
+		return PERF_REG_ARM64_LR;
+	case UNW_AARCH64_SP:
+		return PERF_REG_ARM64_SP;
+	case UNW_AARCH64_PC:
+		return PERF_REG_ARM64_PC;
+	default:
+		pr_err("unwind: invalid reg id %d\n", regnum);
+		return -EINVAL;
+	}
+
+	return -EINVAL;
+}
diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index aacef07ebf3..42faf369211 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -154,8 +154,7 @@ static int perf_session_env__lookup_binutils_path(struct perf_session_env *env,
 		}
 		if (lookup_path(buf))
 			goto out;
-		free(buf);
-		buf = NULL;
+		zfree(&buf);
 	}
 
 	if (!strcmp(arch, "arm"))
diff --git a/tools/perf/arch/x86/Makefile b/tools/perf/arch/x86/Makefile
index 8801fe02f20..1641542e363 100644
--- a/tools/perf/arch/x86/Makefile
+++ b/tools/perf/arch/x86/Makefile
@@ -3,7 +3,14 @@ PERF_HAVE_DWARF_REGS := 1
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/dwarf-regs.o
 endif
 ifndef NO_LIBUNWIND
-LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libunwind.o
+endif
+ifndef NO_LIBDW_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/unwind-libdw.o
+endif
+ifndef NO_DWARF_UNWIND
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/regs_load.o
+LIB_OBJS += $(OUTPUT)arch/$(ARCH)/tests/dwarf-unwind.o
 endif
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/header.o
 LIB_OBJS += $(OUTPUT)arch/$(ARCH)/util/tsc.o
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index 7fcdcdbee91..7df517acfef 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -2,17 +2,23 @@
 #define ARCH_PERF_REGS_H
 
 #include <stdlib.h>
-#include "../../util/types.h"
+#include <linux/types.h>
 #include <asm/perf_regs.h>
 
-#ifndef ARCH_X86_64
+void perf_regs_load(u64 *regs);
+
+#ifndef HAVE_ARCH_X86_64_SUPPORT
 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
+#define PERF_REGS_MAX PERF_REG_X86_32_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32
 #else
 #define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
 		       (1ULL << PERF_REG_X86_ES) | \
 		       (1ULL << PERF_REG_X86_FS) | \
 		       (1ULL << PERF_REG_X86_GS))
 #define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
+#define PERF_REGS_MAX PERF_REG_X86_64_MAX
+#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
 #endif
 #define PERF_REG_IP PERF_REG_X86_IP
 #define PERF_REG_SP PERF_REG_X86_SP
@@ -52,7 +58,7 @@ static inline const char *perf_reg_name(int id)
 		return "FS";
 	case PERF_REG_X86_GS:
 		return "GS";
-#ifdef ARCH_X86_64
+#ifdef HAVE_ARCH_X86_64_SUPPORT
 	case PERF_REG_X86_R8:
 		return "R8";
 	case PERF_REG_X86_R9:
@@ -69,7 +75,7 @@ static inline const char *perf_reg_name(int id)
 		return "R14";
 	case PERF_REG_X86_R15:
 		return "R15";
-#endif /* ARCH_X86_64 */
+#endif /* HAVE_ARCH_X86_64_SUPPORT */
 	default:
 		return NULL;
 	}
diff --git a/tools/perf/arch/x86/tests/dwarf-unwind.c b/tools/perf/arch/x86/tests/dwarf-unwind.c
new file mode 100644
index 00000000000..9f89f899ccc
--- /dev/null
+++ b/tools/perf/arch/x86/tests/dwarf-unwind.c
@@ -0,0 +1,60 @@
+#include <string.h>
+#include "perf_regs.h"
+#include "thread.h"
+#include "map.h"
+#include "event.h"
+#include "tests/tests.h"
+
+#define STACK_SIZE 8192
+
+static int sample_ustack(struct perf_sample *sample,
+			 struct thread *thread, u64 *regs)
+{
+	struct stack_dump *stack = &sample->user_stack;
+	struct map *map;
+	unsigned long sp;
+	u64 stack_size, *buf;
+
+	buf = malloc(STACK_SIZE);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	sp = (unsigned long) regs[PERF_REG_X86_SP];
+
+	map = map_groups__find(thread->mg, MAP__VARIABLE, (u64) sp);
+	if (!map) {
+		pr_debug("failed to get stack map\n");
+		free(buf);
+		return -1;
+	}
+
+	stack_size = map->end - sp;
+	stack_size = stack_size > STACK_SIZE ? STACK_SIZE : stack_size;
+
+	memcpy(buf, (void *) sp, stack_size);
+	stack->data = (char *) buf;
+	stack->size = stack_size;
+	return 0;
+}
+
+int test__arch_unwind_sample(struct perf_sample *sample,
+			     struct thread *thread)
+{
+	struct regs_dump *regs = &sample->user_regs;
+	u64 *buf;
+
+	buf = malloc(sizeof(u64) * PERF_REGS_MAX);
+	if (!buf) {
+		pr_debug("failed to allocate sample uregs data\n");
+		return -1;
+	}
+
+	perf_regs_load(buf);
+	regs->abi  = PERF_SAMPLE_REGS_ABI;
+	regs->regs = buf;
+	regs->mask = PERF_REGS_MASK;
+
+	return sample_ustack(sample, thread, buf);
+}
diff --git a/tools/perf/arch/x86/tests/regs_load.S b/tools/perf/arch/x86/tests/regs_load.S
new file mode 100644
index 00000000000..60875d5c556
--- /dev/null
+++ b/tools/perf/arch/x86/tests/regs_load.S
@@ -0,0 +1,98 @@
+#include <linux/linkage.h>
+
+#define AX	 0
+#define BX	 1 * 8
+#define CX	 2 * 8
+#define DX	 3 * 8
+#define SI	 4 * 8
+#define DI	 5 * 8
+#define BP	 6 * 8
+#define SP	 7 * 8
+#define IP	 8 * 8
+#define FLAGS	 9 * 8
+#define CS	10 * 8
+#define SS	11 * 8
+#define DS	12 * 8
+#define ES	13 * 8
+#define FS	14 * 8
+#define GS	15 * 8
+#define R8	16 * 8
+#define R9	17 * 8
+#define R10	18 * 8
+#define R11	19 * 8
+#define R12	20 * 8
+#define R13	21 * 8
+#define R14	22 * 8
+#define R15	23 * 8
+
+.text
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+ENTRY(perf_regs_load)
+	movq %rax, AX(%rdi)
+	movq %rbx, BX(%rdi)
+	movq %rcx, CX(%rdi)
+	movq %rdx, DX(%rdi)
+	movq %rsi, SI(%rdi)
+	movq %rdi, DI(%rdi)
+	movq %rbp, BP(%rdi)
+
+	leaq 8(%rsp), %rax /* exclude this call.  */
+	movq %rax, SP(%rdi)
+
+	movq 0(%rsp), %rax
+	movq %rax, IP(%rdi)
+
+	movq $0, FLAGS(%rdi)
+	movq $0, CS(%rdi)
+	movq $0, SS(%rdi)
+	movq $0, DS(%rdi)
+	movq $0, ES(%rdi)
+	movq $0, FS(%rdi)
+	movq $0, GS(%rdi)
+
+	movq %r8,  R8(%rdi)
+	movq %r9,  R9(%rdi)
+	movq %r10, R10(%rdi)
+	movq %r11, R11(%rdi)
+	movq %r12, R12(%rdi)
+	movq %r13, R13(%rdi)
+	movq %r14, R14(%rdi)
+	movq %r15, R15(%rdi)
+	ret
+ENDPROC(perf_regs_load)
+#else
+ENTRY(perf_regs_load)
+	push %edi
+	movl 8(%esp), %edi
+	movl %eax, AX(%edi)
+	movl %ebx, BX(%edi)
+	movl %ecx, CX(%edi)
+	movl %edx, DX(%edi)
+	movl %esi, SI(%edi)
+	pop %eax
+	movl %eax, DI(%edi)
+	movl %ebp, BP(%edi)
+
+	leal 4(%esp), %eax /* exclude this call.  */
+	movl %eax, SP(%edi)
+
+	movl 0(%esp), %eax
+	movl %eax, IP(%edi)
+
+	movl $0, FLAGS(%edi)
+	movl $0, CS(%edi)
+	movl $0, SS(%edi)
+	movl $0, DS(%edi)
+	movl $0, ES(%edi)
+	movl $0, FS(%edi)
+	movl $0, GS(%edi)
+	ret
+ENDPROC(perf_regs_load)
+#endif
+
+/*
+ * We need to provide note.GNU-stack section, saying that we want
+ * NOT executable stack. Otherwise the final linking will assume that
+ * the ELF stack should not be restricted at all and set it RWX.
+ */
+.section .note.GNU-stack,"",@progbits
diff --git a/tools/perf/arch/x86/util/tsc.c b/tools/perf/arch/x86/util/tsc.c
index b2519e49424..40021fa3129 100644
--- a/tools/perf/arch/x86/util/tsc.c
+++ b/tools/perf/arch/x86/util/tsc.c
@@ -4,7 +4,7 @@
 #include <linux/perf_event.h>
 
 #include "../../perf.h"
-#include "../../util/types.h"
+#include <linux/types.h>
 #include "../../util/debug.h"
 #include "tsc.h"
 
diff --git a/tools/perf/arch/x86/util/tsc.h b/tools/perf/arch/x86/util/tsc.h
index a24dec81c79..2affe0366b5 100644
--- a/tools/perf/arch/x86/util/tsc.h
+++ b/tools/perf/arch/x86/util/tsc.h
@@ -1,7 +1,7 @@
 #ifndef TOOLS_PERF_ARCH_X86_UTIL_TSC_H__
 #define TOOLS_PERF_ARCH_X86_UTIL_TSC_H__
 
-#include "../../util/types.h"
+#include <linux/types.h>
 
 struct perf_tsc_conversion {
 	u16 time_shift;
diff --git a/tools/perf/arch/x86/util/unwind-libdw.c b/tools/perf/arch/x86/util/unwind-libdw.c
new file mode 100644
index 00000000000..c4b72176ca8
--- /dev/null
+++ b/tools/perf/arch/x86/util/unwind-libdw.c
@@ -0,0 +1,51 @@
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[17];
+	unsigned nregs;
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_X86_##r);	\
+	val;							\
+})
+
+	if (user_regs->abi == PERF_SAMPLE_REGS_ABI_32) {
+		dwarf_regs[0] = REG(AX);
+		dwarf_regs[1] = REG(CX);
+		dwarf_regs[2] = REG(DX);
+		dwarf_regs[3] = REG(BX);
+		dwarf_regs[4] = REG(SP);
+		dwarf_regs[5] = REG(BP);
+		dwarf_regs[6] = REG(SI);
+		dwarf_regs[7] = REG(DI);
+		dwarf_regs[8] = REG(IP);
+		nregs = 9;
+	} else {
+		dwarf_regs[0]  = REG(AX);
+		dwarf_regs[1]  = REG(DX);
+		dwarf_regs[2]  = REG(CX);
+		dwarf_regs[3]  = REG(BX);
+		dwarf_regs[4]  = REG(SI);
+		dwarf_regs[5]  = REG(DI);
+		dwarf_regs[6]  = REG(BP);
+		dwarf_regs[7]  = REG(SP);
+		dwarf_regs[8]  = REG(R8);
+		dwarf_regs[9]  = REG(R9);
+		dwarf_regs[10] = REG(R10);
+		dwarf_regs[11] = REG(R11);
+		dwarf_regs[12] = REG(R12);
+		dwarf_regs[13] = REG(R13);
+		dwarf_regs[14] = REG(R14);
+		dwarf_regs[15] = REG(R15);
+		dwarf_regs[16] = REG(IP);
+		nregs = 17;
+	}
+
+	return dwfl_thread_state_registers(thread, 0, nregs, dwarf_regs);
+}
diff --git a/tools/perf/arch/x86/util/unwind.c b/tools/perf/arch/x86/util/unwind-libunwind.c
index 78d956eff96..3261f68c6a7 100644
--- a/tools/perf/arch/x86/util/unwind.c
+++ b/tools/perf/arch/x86/util/unwind-libunwind.c
@@ -4,8 +4,8 @@
 #include "perf_regs.h"
 #include "../../util/unwind.h"
 
-#ifdef ARCH_X86_64
-int unwind__arch_reg_id(int regnum)
+#ifdef HAVE_ARCH_X86_64_SUPPORT
+int libunwind__arch_reg_id(int regnum)
 {
 	int id;
 
@@ -69,7 +69,7 @@ int unwind__arch_reg_id(int regnum)
 	return id;
 }
 #else
-int unwind__arch_reg_id(int regnum)
+int libunwind__arch_reg_id(int regnum)
 {
 	int id;
 
@@ -108,4 +108,4 @@ int unwind__arch_reg_id(int regnum)
 
 	return id;
 }
-#endif /* ARCH_X86_64 */
+#endif /* HAVE_ARCH_X86_64_SUPPORT */