diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 8dfc9fd094a3..dc0f6ed35b08 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -177,6 +177,9 @@ struct x86_pmu_capability {
 #define IBS_CAPS_BRNTRGT		(1U<<5)
 #define IBS_CAPS_OPCNTEXT		(1U<<6)
 #define IBS_CAPS_RIPINVALIDCHK		(1U<<7)
+#define IBS_CAPS_OPBRNFUSE		(1U<<8)
+#define IBS_CAPS_FETCHCTLEXTD		(1U<<9)
+#define IBS_CAPS_OPDATA4		(1U<<10)
 
 #define IBS_CAPS_DEFAULT		(IBS_CAPS_AVAIL		\
 					 | IBS_CAPS_FETCHSAM	\
diff --git a/arch/x86/include/uapi/asm/msr-index.h b/arch/x86/include/uapi/asm/msr-index.h
index e21331ce368f..8f02f6990759 100644
--- a/arch/x86/include/uapi/asm/msr-index.h
+++ b/arch/x86/include/uapi/asm/msr-index.h
@@ -206,6 +206,7 @@
 #define MSR_AMD64_IBSOP_REG_MASK	((1UL<<MSR_AMD64_IBSOP_REG_COUNT)-1)
 #define MSR_AMD64_IBSCTL		0xc001103a
 #define MSR_AMD64_IBSBRTARGET		0xc001103b
+#define MSR_AMD64_IBSOPDATA4		0xc001103d
 #define MSR_AMD64_IBS_REG_COUNT_MAX	8 /* includes MSR_AMD64_IBSBRTARGET */
 
 /* Fam 16h MSRs */
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index fc5eb390b368..4e6cdb0ddc70 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -253,6 +253,10 @@ struct cpu_hw_events {
 #define INTEL_UEVENT_CONSTRAINT(c, n)	\
 	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK)
 
+/* Like UEVENT_CONSTRAINT, but match flags too */
+#define INTEL_FLAGS_UEVENT_CONSTRAINT(c, n)	\
+	EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS)
+
 #define INTEL_PLD_CONSTRAINT(c, n)	\
 	__EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS, \
 			   HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LDLAT)
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index cbb1be3ed9e4..a61f5c6911da 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -565,6 +565,21 @@ static int perf_ibs_handle_irq(struct perf_ibs *perf_ibs, struct pt_regs *iregs)
 				       perf_ibs->offset_max,
 				       offset + 1);
 	} while (offset < offset_max);
+	if (event->attr.sample_type & PERF_SAMPLE_RAW) {
+		/*
+		 * Read IbsBrTarget and IbsOpData4 separately
+		 * depending on their availability.
+		 * Can't add to offset_max as they are staggered
+		 */
+		if (ibs_caps & IBS_CAPS_BRNTRGT) {
+			rdmsrl(MSR_AMD64_IBSBRTARGET, *buf++);
+			size++;
+		}
+		if (ibs_caps & IBS_CAPS_OPDATA4) {
+			rdmsrl(MSR_AMD64_IBSOPDATA4, *buf++);
+			size++;
+		}
+	}
 	ibs_data.size = sizeof(u64) * size;
 
 	regs = *iregs;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_ds.c b/arch/x86/kernel/cpu/perf_event_intel_ds.c
index 46211bcc813e..495ae9793628 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_ds.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_ds.c
@@ -552,18 +552,18 @@ int intel_pmu_drain_bts_buffer(void)
  * PEBS
  */
 struct event_constraint intel_core2_pebs_event_constraints[] = {
-	INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
-	INTEL_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
-	INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
-	INTEL_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
-	INTEL_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0xfec1, 0x1), /* X87_OPS_RETIRED.ANY */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* BR_INST_RETIRED.MISPRED */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x1fc7, 0x1), /* SIMD_INST_RETURED.ANY */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
 	EVENT_CONSTRAINT_END
 };
 
 struct event_constraint intel_atom_pebs_event_constraints[] = {
-	INTEL_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
-	INTEL_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
-	INTEL_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c0, 0x1), /* INST_RETIRED.ANY */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x00c5, 0x1), /* MISPREDICTED_BRANCH_RETIRED */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0x1),    /* MEM_LOAD_RETIRED.* */
 	EVENT_CONSTRAINT_END
 };
 
@@ -577,36 +577,36 @@ struct event_constraint intel_slm_pebs_event_constraints[] = {
 
 struct event_constraint intel_nehalem_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
-	INTEL_EVENT_CONSTRAINT(0xc0, 0xf),    /* INST_RETIRED.ANY */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf),    /* INST_RETIRED.ANY */
 	INTEL_EVENT_CONSTRAINT(0xc2, 0xf),    /* UOPS_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
-	INTEL_EVENT_CONSTRAINT(0xc7, 0xf),    /* SSEX_UOPS_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
-	INTEL_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x02c5, 0xf), /* BR_MISP_RETIRED.NEAR_CALL */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf),    /* SSEX_UOPS_RETIRED.* */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
 	EVENT_CONSTRAINT_END
 };
 
 struct event_constraint intel_westmere_pebs_event_constraints[] = {
 	INTEL_PLD_CONSTRAINT(0x100b, 0xf),      /* MEM_INST_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
-	INTEL_EVENT_CONSTRAINT(0xc0, 0xf),    /* INSTR_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0x0f, 0xf),    /* MEM_UNCORE_RETIRED.* */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x010c, 0xf), /* MEM_STORE_RETIRED.DTLB_MISS */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xf),    /* INSTR_RETIRED.* */
 	INTEL_EVENT_CONSTRAINT(0xc2, 0xf),    /* UOPS_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xc7, 0xf),    /* SSEX_UOPS_RETIRED.* */
-	INTEL_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
-	INTEL_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
-	INTEL_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xc4, 0xf),    /* BR_INST_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xc5, 0xf),    /* BR_MISP_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xc7, 0xf),    /* SSEX_UOPS_RETIRED.* */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x20c8, 0xf), /* ITLB_MISS_RETIRED */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xcb, 0xf),    /* MEM_LOAD_RETIRED.* */
+	INTEL_FLAGS_EVENT_CONSTRAINT(0xf7, 0xf),    /* FP_ASSIST.* */
 	EVENT_CONSTRAINT_END
 };
 
 struct event_constraint intel_snb_pebs_event_constraints[] = {
-	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
 	INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
 	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
@@ -617,7 +617,7 @@ struct event_constraint intel_snb_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_ivb_pebs_event_constraints[] = {
-        INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+        INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
         INTEL_PLD_CONSTRAINT(0x01cd, 0x8),    /* MEM_TRANS_RETIRED.LAT_ABOVE_THR */
 	INTEL_PST_CONSTRAINT(0x02cd, 0x8),    /* MEM_TRANS_RETIRED.PRECISE_STORES */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
@@ -628,7 +628,7 @@ struct event_constraint intel_ivb_pebs_event_constraints[] = {
 };
 
 struct event_constraint intel_hsw_pebs_event_constraints[] = {
-	INTEL_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
+	INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x2), /* INST_RETIRED.PRECDIST */
 	INTEL_PLD_CONSTRAINT(0x01cd, 0xf),    /* MEM_TRANS_RETIRED.* */
 	/* UOPS_RETIRED.ALL, inv=1, cmask=16 (cycles:p). */
 	INTEL_FLAGS_EVENT_CONSTRAINT(0x108001c2, 0xf),
@@ -886,6 +886,29 @@ static void __intel_pmu_pebs_event(struct perf_event *event,
 	regs.bp = pebs->bp;
 	regs.sp = pebs->sp;
 
+	if (sample_type & PERF_SAMPLE_REGS_INTR) {
+		regs.ax = pebs->ax;
+		regs.bx = pebs->bx;
+		regs.cx = pebs->cx;
+		regs.dx = pebs->dx;
+		regs.si = pebs->si;
+		regs.di = pebs->di;
+		regs.bp = pebs->bp;
+		regs.sp = pebs->sp;
+
+		regs.flags = pebs->flags;
+#ifndef CONFIG_X86_32
+		regs.r8 = pebs->r8;
+		regs.r9 = pebs->r9;
+		regs.r10 = pebs->r10;
+		regs.r11 = pebs->r11;
+		regs.r12 = pebs->r12;
+		regs.r13 = pebs->r13;
+		regs.r14 = pebs->r14;
+		regs.r15 = pebs->r15;
+#endif
+	}
+
 	if (event->attr.precise_ip > 1 && x86_pmu.intel_cap.pebs_format >= 2) {
 		regs.ip = pebs->real_ip;
 		regs.flags |= PERF_EFLAGS_EXACT;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
index f9ed429d6e4f..745b158e9a65 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore_snbep.c
@@ -449,7 +449,11 @@ static struct attribute *snbep_uncore_qpi_formats_attr[] = {
 static struct uncore_event_desc snbep_uncore_imc_events[] = {
 	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0xff,umask=0x00"),
 	INTEL_UNCORE_EVENT_DESC(cas_count_read,  "event=0x04,umask=0x03"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
 	INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
 	{ /* end: all zeroes */ },
 };
 
@@ -2036,7 +2040,11 @@ static struct intel_uncore_type hswep_uncore_ha = {
 static struct uncore_event_desc hswep_uncore_imc_events[] = {
 	INTEL_UNCORE_EVENT_DESC(clockticks,      "event=0x00,umask=0x00"),
 	INTEL_UNCORE_EVENT_DESC(cas_count_read,  "event=0x04,umask=0x03"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_read.unit, "MiB"),
 	INTEL_UNCORE_EVENT_DESC(cas_count_write, "event=0x04,umask=0x0c"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write.scale, "6.103515625e-5"),
+	INTEL_UNCORE_EVENT_DESC(cas_count_write.unit, "MiB"),
 	{ /* end: all zeroes */ },
 };
 
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 893a0d07986f..486e84ccb1f9 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -79,7 +79,7 @@ struct perf_branch_stack {
 	struct perf_branch_entry	entries[0];
 };
 
-struct perf_regs_user {
+struct perf_regs {
 	__u64		abi;
 	struct pt_regs	*regs;
 };
@@ -580,34 +580,40 @@ extern u64 perf_event_read_value(struct perf_event *event,
 
 
 struct perf_sample_data {
-	u64				type;
+	/*
+	 * Fields set by perf_sample_data_init(), group so as to
+	 * minimize the cachelines touched.
+	 */
+	u64				addr;
+	struct perf_raw_record		*raw;
+	struct perf_branch_stack	*br_stack;
+	u64				period;
+	u64				weight;
+	u64				txn;
+	union  perf_mem_data_src	data_src;
 
+	/*
+	 * The other fields, optionally {set,used} by
+	 * perf_{prepare,output}_sample().
+	 */
+	u64				type;
 	u64				ip;
 	struct {
 		u32	pid;
 		u32	tid;
 	}				tid_entry;
 	u64				time;
-	u64				addr;
 	u64				id;
 	u64				stream_id;
 	struct {
 		u32	cpu;
 		u32	reserved;
 	}				cpu_entry;
-	u64				period;
-	union  perf_mem_data_src	data_src;
 	struct perf_callchain_entry	*callchain;
-	struct perf_raw_record		*raw;
-	struct perf_branch_stack	*br_stack;
-	struct perf_regs_user		regs_user;
+	struct perf_regs		regs_user;
+	struct perf_regs		regs_intr;
 	u64				stack_user_size;
-	u64				weight;
-	/*
-	 * Transaction flags for abort events:
-	 */
-	u64				txn;
-};
+} ____cacheline_aligned;
 
 /* default value for data source */
 #define PERF_MEM_NA (PERF_MEM_S(OP, NA)   |\
@@ -624,9 +630,6 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
 	data->raw  = NULL;
 	data->br_stack = NULL;
 	data->period = period;
-	data->regs_user.abi = PERF_SAMPLE_REGS_ABI_NONE;
-	data->regs_user.regs = NULL;
-	data->stack_user_size = 0;
 	data->weight = 0;
 	data->data_src.val = PERF_MEM_NA;
 	data->txn = 0;
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 9d845404d875..9b79abbd1ab8 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -137,8 +137,9 @@ enum perf_event_sample_format {
 	PERF_SAMPLE_DATA_SRC			= 1U << 15,
 	PERF_SAMPLE_IDENTIFIER			= 1U << 16,
 	PERF_SAMPLE_TRANSACTION			= 1U << 17,
+	PERF_SAMPLE_REGS_INTR			= 1U << 18,
 
-	PERF_SAMPLE_MAX = 1U << 18,		/* non-ABI */
+	PERF_SAMPLE_MAX = 1U << 19,		/* non-ABI */
 };
 
 /*
@@ -238,6 +239,7 @@ enum perf_event_read_format {
 #define PERF_ATTR_SIZE_VER2	80	/* add: branch_sample_type */
 #define PERF_ATTR_SIZE_VER3	96	/* add: sample_regs_user */
 					/* add: sample_stack_user */
+#define PERF_ATTR_SIZE_VER4	104	/* add: sample_regs_intr */
 
 /*
  * Hardware event_id to monitor via a performance monitoring event:
@@ -334,6 +336,15 @@ struct perf_event_attr {
 
 	/* Align to u64. */
 	__u32	__reserved_2;
+	/*
+	 * Defines set of regs to dump for each sample
+	 * state captured on:
+	 *  - precise = 0: PMU interrupt
+	 *  - precise > 0: sampled instruction
+	 *
+	 * See asm/perf_regs.h for details.
+	 */
+	__u64	sample_regs_intr;
 };
 
 #define perf_flags(attr)	(*(&(attr)->read_format + 1))
@@ -686,6 +697,8 @@ enum perf_event_type {
 	 *	{ u64			weight;   } && PERF_SAMPLE_WEIGHT
 	 *	{ u64			data_src; } && PERF_SAMPLE_DATA_SRC
 	 *	{ u64			transaction; } && PERF_SAMPLE_TRANSACTION
+	 *	{ u64			abi; # enum perf_sample_regs_abi
+	 *	  u64			regs[weight(mask)]; } && PERF_SAMPLE_REGS_INTR
 	 * };
 	 */
 	PERF_RECORD_SAMPLE			= 9,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1cd5eef1fcdd..3e19d3ebc29c 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4460,7 +4460,7 @@ perf_output_sample_regs(struct perf_output_handle *handle,
 	}
 }
 
-static void perf_sample_regs_user(struct perf_regs_user *regs_user,
+static void perf_sample_regs_user(struct perf_regs *regs_user,
 				  struct pt_regs *regs)
 {
 	if (!user_mode(regs)) {
@@ -4471,11 +4471,22 @@ static void perf_sample_regs_user(struct perf_regs_user *regs_user,
 	}
 
 	if (regs) {
-		regs_user->regs = regs;
 		regs_user->abi  = perf_reg_abi(current);
+		regs_user->regs = regs;
+	} else {
+		regs_user->abi = PERF_SAMPLE_REGS_ABI_NONE;
+		regs_user->regs = NULL;
 	}
 }
 
+static void perf_sample_regs_intr(struct perf_regs *regs_intr,
+				  struct pt_regs *regs)
+{
+	regs_intr->regs = regs;
+	regs_intr->abi  = perf_reg_abi(current);
+}
+
+
 /*
  * Get remaining task size from user stack pointer.
  *
@@ -4857,6 +4868,23 @@ void perf_output_sample(struct perf_output_handle *handle,
 	if (sample_type & PERF_SAMPLE_TRANSACTION)
 		perf_output_put(handle, data->txn);
 
+	if (sample_type & PERF_SAMPLE_REGS_INTR) {
+		u64 abi = data->regs_intr.abi;
+		/*
+		 * If there are no regs to dump, notice it through
+		 * first u64 being zero (PERF_SAMPLE_REGS_ABI_NONE).
+		 */
+		perf_output_put(handle, abi);
+
+		if (abi) {
+			u64 mask = event->attr.sample_regs_intr;
+
+			perf_output_sample_regs(handle,
+						data->regs_intr.regs,
+						mask);
+		}
+	}
+
 	if (!event->attr.watermark) {
 		int wakeup_events = event->attr.wakeup_events;
 
@@ -4922,12 +4950,13 @@ void perf_prepare_sample(struct perf_event_header *header,
 		header->size += size;
 	}
 
+	if (sample_type & (PERF_SAMPLE_REGS_USER | PERF_SAMPLE_STACK_USER))
+		perf_sample_regs_user(&data->regs_user, regs);
+
 	if (sample_type & PERF_SAMPLE_REGS_USER) {
 		/* regs dump ABI info */
 		int size = sizeof(u64);
 
-		perf_sample_regs_user(&data->regs_user, regs);
-
 		if (data->regs_user.regs) {
 			u64 mask = event->attr.sample_regs_user;
 			size += hweight64(mask) * sizeof(u64);
@@ -4943,15 +4972,11 @@ void perf_prepare_sample(struct perf_event_header *header,
 		 * in case new sample type is added, because we could eat
 		 * up the rest of the sample size.
 		 */
-		struct perf_regs_user *uregs = &data->regs_user;
 		u16 stack_size = event->attr.sample_stack_user;
 		u16 size = sizeof(u64);
 
-		if (!uregs->abi)
-			perf_sample_regs_user(uregs, regs);
-
 		stack_size = perf_sample_ustack_size(stack_size, header->size,
-						     uregs->regs);
+						     data->regs_user.regs);
 
 		/*
 		 * If there is something to dump, add space for the dump
@@ -4964,6 +4989,21 @@ void perf_prepare_sample(struct perf_event_header *header,
 		data->stack_user_size = stack_size;
 		header->size += size;
 	}
+
+	if (sample_type & PERF_SAMPLE_REGS_INTR) {
+		/* regs dump ABI info */
+		int size = sizeof(u64);
+
+		perf_sample_regs_intr(&data->regs_intr, regs);
+
+		if (data->regs_intr.regs) {
+			u64 mask = event->attr.sample_regs_intr;
+
+			size += hweight64(mask) * sizeof(u64);
+		}
+
+		header->size += size;
+	}
 }
 
 static void perf_event_output(struct perf_event *event,
@@ -7151,6 +7191,8 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
 			ret = -EINVAL;
 	}
 
+	if (attr->sample_type & PERF_SAMPLE_REGS_INTR)
+		ret = perf_reg_validate(attr->sample_regs_intr);
 out:
 	return ret;
 
diff --git a/tools/perf/.gitignore b/tools/perf/.gitignore
index 717221e98450..40399c3d97d6 100644
--- a/tools/perf/.gitignore
+++ b/tools/perf/.gitignore
@@ -2,6 +2,8 @@ PERF-CFLAGS
 PERF-GUI-VARS
 PERF-VERSION-FILE
 perf
+perf-read-vdso32
+perf-read-vdsox32
 perf-help
 perf-record
 perf-report
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 398f8d53bd6d..af9a54ece024 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -214,6 +214,12 @@ if combined with -a or -C options.
 After starting the program, wait msecs before measuring. This is useful to
 filter out the startup phase of the program, which is often very different.
 
+-I::
+--intr-regs::
+Capture machine state (registers) at interrupt, i.e., on counter overflows for
+each sample. List of captured registers depends on the architecture. This option
+is off by default.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 0927bf4e6c2a..dd7cccdde498 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -159,7 +159,7 @@ OPTIONS
 --dump-raw-trace::
         Dump raw trace in ASCII.
 
--g [type,min[,limit],order[,key]]::
+-g [type,min[,limit],order[,key][,branch]]::
 --call-graph::
         Display call chains using type, min percent threshold, optional print
 	limit and order.
@@ -177,6 +177,11 @@ OPTIONS
 	- function: compare on functions
 	- address: compare on individual code addresses
 
+	branch can be:
+	- branch: include last branch information in callgraph
+	when available. Usually more convenient to use --branch-history
+	for this.
+
 	Default: fractal,0.5,callee,function.
 
 --children::
@@ -266,6 +271,11 @@ OPTIONS
 	branch stacks and it will automatically switch to the branch view mode,
 	unless --no-branch-stack is used.
 
+--branch-history::
+	Add the addresses of sampled taken branches to the callstack.
+	This allows to examine the path the program took to each sample.
+	The data collection must have used -b (or -j) and -g.
+
 --objdump=<path>::
         Path to objdump binary.
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 262916f4a377..478efa9b2364 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -60,6 +60,15 @@ include config/utilities.mak
 #
 # Define NO_LIBDW_DWARF_UNWIND if you do not want libdw support
 # for dwarf backtrace post unwind.
+#
+# Define NO_PERF_READ_VDSO32 if you do not want to build perf-read-vdso32
+# for reading the 32-bit compatibility VDSO in 64-bit mode
+#
+# Define NO_PERF_READ_VDSOX32 if you do not want to build perf-read-vdsox32
+# for reading the x32 mode 32-bit compatibility VDSO in 64-bit mode
+#
+# Define NO_ZLIB if you do not want to support compressed kernel modules
+
 
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
@@ -171,11 +180,16 @@ $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS)
 
 SCRIPTS = $(patsubst %.sh,%,$(SCRIPT_SH))
 
-#
-# Single 'perf' binary right now:
-#
 PROGRAMS += $(OUTPUT)perf
 
+ifndef NO_PERF_READ_VDSO32
+PROGRAMS += $(OUTPUT)perf-read-vdso32
+endif
+
+ifndef NO_PERF_READ_VDSOX32
+PROGRAMS += $(OUTPUT)perf-read-vdsox32
+endif
+
 # what 'all' will build and 'install' will install, in perfexecdir
 ALL_PROGRAMS = $(PROGRAMS) $(SCRIPTS)
 
@@ -247,12 +261,14 @@ LIB_H += util/annotate.h
 LIB_H += util/cache.h
 LIB_H += util/callchain.h
 LIB_H += util/build-id.h
+LIB_H += util/db-export.h
 LIB_H += util/debug.h
 LIB_H += util/pmu.h
 LIB_H += util/event.h
 LIB_H += util/evsel.h
 LIB_H += util/evlist.h
 LIB_H += util/exec_cmd.h
+LIB_H += util/find-vdso-map.c
 LIB_H += util/levenshtein.h
 LIB_H += util/machine.h
 LIB_H += util/map.h
@@ -304,6 +320,7 @@ LIB_H += ui/util.h
 LIB_H += ui/ui.h
 LIB_H += util/data.h
 LIB_H += util/kvm-stat.h
+LIB_H += util/thread-stack.h
 
 LIB_OBJS += $(OUTPUT)util/abspath.o
 LIB_OBJS += $(OUTPUT)util/alias.o
@@ -311,6 +328,7 @@ LIB_OBJS += $(OUTPUT)util/annotate.o
 LIB_OBJS += $(OUTPUT)util/build-id.o
 LIB_OBJS += $(OUTPUT)util/config.o
 LIB_OBJS += $(OUTPUT)util/ctype.o
+LIB_OBJS += $(OUTPUT)util/db-export.o
 LIB_OBJS += $(OUTPUT)util/pmu.o
 LIB_OBJS += $(OUTPUT)util/environment.o
 LIB_OBJS += $(OUTPUT)util/event.o
@@ -380,6 +398,7 @@ LIB_OBJS += $(OUTPUT)util/srcline.o
 LIB_OBJS += $(OUTPUT)util/data.o
 LIB_OBJS += $(OUTPUT)util/tsc.o
 LIB_OBJS += $(OUTPUT)util/cloexec.o
+LIB_OBJS += $(OUTPUT)util/thread-stack.o
 
 LIB_OBJS += $(OUTPUT)ui/setup.o
 LIB_OBJS += $(OUTPUT)ui/helpline.o
@@ -478,8 +497,6 @@ ifneq ($(OUTPUT),)
 endif
 
 ifdef NO_LIBELF
-EXTLIBS := $(filter-out -lelf,$(EXTLIBS))
-
 # Remove ELF/DWARF dependent codes
 LIB_OBJS := $(filter-out $(OUTPUT)util/symbol-elf.o,$(LIB_OBJS))
 LIB_OBJS := $(filter-out $(OUTPUT)util/dwarf-aux.o,$(LIB_OBJS))
@@ -568,6 +585,10 @@ ifndef NO_LIBNUMA
   BUILTIN_OBJS += $(OUTPUT)bench/numa.o
 endif
 
+ifndef NO_ZLIB
+  LIB_OBJS += $(OUTPUT)util/zlib.o
+endif
+
 ifdef ASCIIDOC8
   export ASCIIDOC8
 endif
@@ -732,6 +753,16 @@ $(OUTPUT)scripts/python/Perf-Trace-Util/Context.o: scripts/python/Perf-Trace-Uti
 $(OUTPUT)perf-%: %.o $(PERFLIBS)
 	$(QUIET_LINK)$(CC) $(CFLAGS) -o $@ $(LDFLAGS) $(filter %.o,$^) $(LIBS)
 
+ifndef NO_PERF_READ_VDSO32
+$(OUTPUT)perf-read-vdso32: perf-read-vdso.c util/find-vdso-map.c
+	$(QUIET_CC)$(CC) -m32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
+endif
+
+ifndef NO_PERF_READ_VDSOX32
+$(OUTPUT)perf-read-vdsox32: perf-read-vdso.c util/find-vdso-map.c
+	$(QUIET_CC)$(CC) -mx32 $(filter -static,$(LDFLAGS)) -Wall -Werror -o $@ perf-read-vdso.c
+endif
+
 $(LIB_OBJS) $(BUILTIN_OBJS): $(LIB_H)
 $(patsubst perf-%,%.o,$(PROGRAMS)): $(LIB_H) $(wildcard */*.h)
 
@@ -876,6 +907,14 @@ install-bin: all install-gtk
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \
 		$(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \
 		$(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace'
+ifndef NO_PERF_READ_VDSO32
+	$(call QUIET_INSTALL, perf-read-vdso32) \
+		$(INSTALL) $(OUTPUT)perf-read-vdso32 '$(DESTDIR_SQ)$(bindir_SQ)';
+endif
+ifndef NO_PERF_READ_VDSOX32
+	$(call QUIET_INSTALL, perf-read-vdsox32) \
+		$(INSTALL) $(OUTPUT)perf-read-vdsox32 '$(DESTDIR_SQ)$(bindir_SQ)';
+endif
 	$(call QUIET_INSTALL, libexec) \
 		$(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 	$(call QUIET_INSTALL, perf-archive) \
@@ -928,7 +967,7 @@ config-clean:
 
 clean: $(LIBTRACEEVENT)-clean $(LIBAPIKFS)-clean config-clean
 	$(call QUIET_CLEAN, core-objs)  $(RM) $(LIB_OBJS) $(BUILTIN_OBJS) $(LIB_FILE) $(OUTPUT)perf-archive $(OUTPUT)perf-with-kcore $(OUTPUT)perf.o $(LANG_BINDINGS) $(GTK_OBJS)
-	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf
+	$(call QUIET_CLEAN, core-progs) $(RM) $(ALL_PROGRAMS) perf perf-read-vdso32 perf-read-vdsox32
 	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)PERF-CFLAGS $(OUTPUT)PERF-FEATURES $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
index d73ef8bb08c7..3bb50eac5542 100644
--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
@@ -145,7 +145,7 @@ static Dwarf_Frame *get_dwarf_frame(Dwfl_Module *mod, Dwarf_Addr pc)
  *		yet used)
  *	-1 in case of errors
  */
-static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
+static int check_return_addr(struct dso *dso, Dwarf_Addr pc)
 {
 	int		rc = -1;
 	Dwfl		*dwfl;
@@ -156,15 +156,27 @@ static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
 	Dwarf_Addr	end = pc;
 	bool		signalp;
 
-	dwfl = dwfl_begin(&offline_callbacks);
-	if (!dwfl) {
-		pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
-		return -1;
-	}
+	dwfl = dso->dwfl;
 
-	if (dwfl_report_offline(dwfl, "",  exec_file, -1) == NULL) {
-		pr_debug("dwfl_report_offline() failed %s\n", dwarf_errmsg(-1));
-		goto out;
+	if (!dwfl) {
+		dwfl = dwfl_begin(&offline_callbacks);
+		if (!dwfl) {
+			pr_debug("dwfl_begin() failed: %s\n", dwarf_errmsg(-1));
+			return -1;
+		}
+
+		if (dwfl_report_offline(dwfl, "", dso->long_name, -1) == NULL) {
+			pr_debug("dwfl_report_offline() failed %s\n",
+						dwarf_errmsg(-1));
+			/*
+			 * We normally cache the DWARF debug info and never
+			 * call dwfl_end(). But to prevent fd leak, free in
+			 * case of error.
+			 */
+			dwfl_end(dwfl);
+			goto out;
+		}
+		dso->dwfl = dwfl;
 	}
 
 	mod = dwfl_addrmodule(dwfl, pc);
@@ -194,7 +206,6 @@ static int check_return_addr(const char *exec_file, Dwarf_Addr pc)
 	rc = check_return_reg(ra_regno, frame);
 
 out:
-	dwfl_end(dwfl);
 	return rc;
 }
 
@@ -221,8 +232,7 @@ out:
  *	index:	of callchain entry that needs to be ignored (if any)
  *	-1	if no entry needs to be ignored or in case of errors
  */
-int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
-				struct ip_callchain *chain)
+int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
 {
 	struct addr_location al;
 	struct dso *dso = NULL;
@@ -235,7 +245,7 @@ int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
 
 	ip = chain->ips[2];
 
-	thread__find_addr_location(thread, machine, PERF_RECORD_MISC_USER,
+	thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
 			MAP__FUNCTION, ip, &al);
 
 	if (al.map)
@@ -246,7 +256,7 @@ int arch_skip_callchain_idx(struct machine *machine, struct thread *thread,
 		return skip_slot;
 	}
 
-	rc = check_return_addr(dso->long_name, ip);
+	rc = check_return_addr(dso, ip);
 
 	pr_debug("DSO %s, nr %" PRIx64 ", ip 0x%" PRIx64 "rc %d\n",
 				dso->long_name, chain->nr, ip, rc);
diff --git a/tools/perf/builtin-diff.c b/tools/perf/builtin-diff.c
index 25114c9a6801..1ce425d101a9 100644
--- a/tools/perf/builtin-diff.c
+++ b/tools/perf/builtin-diff.c
@@ -357,6 +357,7 @@ static int diff__process_sample_event(struct perf_tool *tool __maybe_unused,
 static struct perf_tool tool = {
 	.sample	= diff__process_sample_event,
 	.mmap	= perf_event__process_mmap,
+	.mmap2	= perf_event__process_mmap2,
 	.comm	= perf_event__process_comm,
 	.exit	= perf_event__process_exit,
 	.fork	= perf_event__process_fork,
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index de99ca1bb942..84df2deed988 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -217,8 +217,7 @@ static int perf_event__inject_buildid(struct perf_tool *tool,
 		goto repipe;
 	}
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->ip, &al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
 
 	if (al.map != NULL) {
 		if (!al.map->dso->hit) {
@@ -410,6 +409,7 @@ int cmd_inject(int argc, const char **argv, const char *prefix __maybe_unused)
 			.tracing_data	= perf_event__repipe_op2_synth,
 			.finished_round	= perf_event__repipe_op2_synth,
 			.build_id	= perf_event__repipe_op2_synth,
+			.id_index	= perf_event__repipe_op2_synth,
 		},
 		.input_name  = "-",
 		.samples = LIST_HEAD_INIT(inject.samples),
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index b65eb0507b38..3c0f3d4fb021 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -1132,6 +1132,10 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 		"-m", "1024",
 		"-c", "1",
 	};
+	const char * const kvm_stat_record_usage[] = {
+		"perf kvm stat record [<options>]",
+		NULL
+	};
 	const char * const *events_tp;
 	events_tp_size = 0;
 
@@ -1159,6 +1163,27 @@ kvm_events_record(struct perf_kvm_stat *kvm, int argc, const char **argv)
 	for (j = 1; j < (unsigned int)argc; j++, i++)
 		rec_argv[i] = argv[j];
 
+	set_option_flag(record_options, 'e', "event", PARSE_OPT_HIDDEN);
+	set_option_flag(record_options, 0, "filter", PARSE_OPT_HIDDEN);
+	set_option_flag(record_options, 'R', "raw-samples", PARSE_OPT_HIDDEN);
+
+	set_option_flag(record_options, 'F', "freq", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 0, "group", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'g', NULL, PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 0, "call-graph", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'd', "data", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'T', "timestamp", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'P', "period", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'n', "no-samples", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'N', "no-buildid-cache", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'B', "no-buildid", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'G', "cgroup", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'b', "branch-any", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'j', "branch-filter", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 'W', "weight", PARSE_OPT_DISABLED);
+	set_option_flag(record_options, 0, "transaction", PARSE_OPT_DISABLED);
+
+	record_usage = kvm_stat_record_usage;
 	return cmd_record(i, rec_argv, NULL);
 }
 
diff --git a/tools/perf/builtin-probe.c b/tools/perf/builtin-probe.c
index 7af26acf06d9..921bb6942503 100644
--- a/tools/perf/builtin-probe.c
+++ b/tools/perf/builtin-probe.c
@@ -55,6 +55,7 @@ static struct {
 	bool show_funcs;
 	bool mod_events;
 	bool uprobes;
+	bool quiet;
 	int nevents;
 	struct perf_probe_event events[MAX_PROBES];
 	struct strlist *dellist;
@@ -312,9 +313,11 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 #endif
 		NULL
 };
-	const struct option options[] = {
+	struct option options[] = {
 	OPT_INCR('v', "verbose", &verbose,
 		    "be more verbose (show parsed arguments, etc)"),
+	OPT_BOOLEAN('q', "quiet", &params.quiet,
+		    "be quiet (do not show any mesages)"),
 	OPT_BOOLEAN('l', "list", &params.list_events,
 		    "list up current probe events"),
 	OPT_CALLBACK('d', "del", NULL, "[GROUP:]EVENT", "delete a probe event.",
@@ -382,6 +385,14 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	};
 	int ret;
 
+	set_option_flag(options, 'a', "add", PARSE_OPT_EXCLUSIVE);
+	set_option_flag(options, 'd', "del", PARSE_OPT_EXCLUSIVE);
+	set_option_flag(options, 'l', "list", PARSE_OPT_EXCLUSIVE);
+#ifdef HAVE_DWARF_SUPPORT
+	set_option_flag(options, 'L', "line", PARSE_OPT_EXCLUSIVE);
+	set_option_flag(options, 'V', "vars", PARSE_OPT_EXCLUSIVE);
+#endif
+
 	argc = parse_options(argc, argv, options, probe_usage,
 			     PARSE_OPT_STOP_AT_NON_OPTION);
 	if (argc > 0) {
@@ -396,6 +407,14 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		}
 	}
 
+	if (params.quiet) {
+		if (verbose != 0) {
+			pr_err("  Error: -v and -q are exclusive.\n");
+			return -EINVAL;
+		}
+		verbose = -1;
+	}
+
 	if (params.max_probe_points == 0)
 		params.max_probe_points = MAX_PROBES;
 
@@ -409,22 +428,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 
 	if (params.list_events) {
-		if (params.mod_events) {
-			pr_err("  Error: Don't use --list with --add/--del.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_lines) {
-			pr_err("  Error: Don't use --list with --line.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_vars) {
-			pr_err(" Error: Don't use --list with --vars.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_funcs) {
-			pr_err("  Error: Don't use --list with --funcs.\n");
-			usage_with_options(probe_usage, options);
-		}
 		if (params.uprobes) {
 			pr_warning("  Error: Don't use --list with --exec.\n");
 			usage_with_options(probe_usage, options);
@@ -435,19 +438,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		return ret;
 	}
 	if (params.show_funcs) {
-		if (params.nevents != 0 || params.dellist) {
-			pr_err("  Error: Don't use --funcs with"
-			       " --add/--del.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_lines) {
-			pr_err("  Error: Don't use --funcs with --line.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_vars) {
-			pr_err("  Error: Don't use --funcs with --vars.\n");
-			usage_with_options(probe_usage, options);
-		}
 		if (!params.filter)
 			params.filter = strfilter__new(DEFAULT_FUNC_FILTER,
 						       NULL);
@@ -462,16 +452,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 
 #ifdef HAVE_DWARF_SUPPORT
 	if (params.show_lines) {
-		if (params.mod_events) {
-			pr_err("  Error: Don't use --line with"
-			       " --add/--del.\n");
-			usage_with_options(probe_usage, options);
-		}
-		if (params.show_vars) {
-			pr_err(" Error: Don't use --line with --vars.\n");
-			usage_with_options(probe_usage, options);
-		}
-
 		ret = show_line_range(&params.line_range, params.target,
 				      params.uprobes);
 		if (ret < 0)
@@ -479,11 +459,6 @@ __cmd_probe(int argc, const char **argv, const char *prefix __maybe_unused)
 		return ret;
 	}
 	if (params.show_vars) {
-		if (params.mod_events) {
-			pr_err("  Error: Don't use --vars with"
-			       " --add/--del.\n");
-			usage_with_options(probe_usage, options);
-		}
 		if (!params.filter)
 			params.filter = strfilter__new(DEFAULT_VAR_FILTER,
 						       NULL);
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 2583a9b04317..8648c6d3003d 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -200,6 +200,17 @@ static int process_buildids(struct record *rec)
 	if (size == 0)
 		return 0;
 
+	/*
+	 * During this process, it'll load kernel map and replace the
+	 * dso->long_name to a real pathname it found.  In this case
+	 * we prefer the vmlinux path like
+	 *   /lib/modules/3.16.4/build/vmlinux
+	 *
+	 * rather than build-id path (in debug directory).
+	 *   $HOME/.debug/.build-id/f0/6e17aa50adf4d00b88925e03775de107611551
+	 */
+	symbol_conf.ignore_vmlinux_buildid = true;
+
 	return __perf_session__process_events(session, start,
 					      size - start,
 					      size, &build_id__mark_dso_hit_ops);
@@ -680,11 +691,12 @@ static int perf_record_config(const char *var, const char *value, void *cb)
 	return perf_default_config(var, value, cb);
 }
 
-static const char * const record_usage[] = {
+static const char * const __record_usage[] = {
 	"perf record [<options>] [<command>]",
 	"perf record [<options>] -- <command> [<options>]",
 	NULL
 };
+const char * const *record_usage = __record_usage;
 
 /*
  * XXX Ideally would be local to cmd_record() and passed to a record__new
@@ -725,7 +737,7 @@ const char record_callchain_help[] = CALLCHAIN_HELP "fp";
  * perf_evlist__prepare_workload, etc instead of fork+exec'in 'perf record',
  * using pipes, etc.
  */
-const struct option record_options[] = {
+struct option __record_options[] = {
 	OPT_CALLBACK('e', "event", &record.evlist, "event",
 		     "event selector. use 'perf list' to list available events",
 		     parse_events_option),
@@ -799,9 +811,13 @@ const struct option record_options[] = {
 		    "sample transaction flags (special events only)"),
 	OPT_BOOLEAN(0, "per-thread", &record.opts.target.per_thread,
 		    "use per-thread mmaps"),
+	OPT_BOOLEAN('I', "intr-regs", &record.opts.sample_intr_regs,
+		    "Sample machine registers on interrupt"),
 	OPT_END()
 };
 
+struct option *record_options = __record_options;
+
 int cmd_record(int argc, const char **argv, const char *prefix __maybe_unused)
 {
 	int err = -ENOMEM;
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 140a6cd88351..39367609c707 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -226,8 +226,9 @@ static int report__setup_sample_type(struct report *rep)
 			return -EINVAL;
 		}
 		if (symbol_conf.use_callchain) {
-			ui__error("Selected -g but no callchain data. Did "
-				    "you call 'perf record' without -g?\n");
+			ui__error("Selected -g or --branch-history but no "
+				  "callchain data. Did\n"
+				  "you call 'perf record' without -g?\n");
 			return -1;
 		}
 	} else if (!rep->dont_use_callchains &&
@@ -575,6 +576,7 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	struct stat st;
 	bool has_br_stack = false;
 	int branch_mode = -1;
+	bool branch_call_mode = false;
 	char callchain_default_opt[] = "fractal,0.5,callee";
 	const char * const report_usage[] = {
 		"perf report [<options>]",
@@ -637,8 +639,8 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 		   "regex filter to identify parent, see: '--sort parent'"),
 	OPT_BOOLEAN('x', "exclude-other", &symbol_conf.exclude_other,
 		    "Only display entries with parent-match"),
-	OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order",
-		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address). "
+	OPT_CALLBACK_DEFAULT('g', "call-graph", &report, "output_type,min_percent[,print_limit],call_order[,branch]",
+		     "Display callchains using output_type (graph, flat, fractal, or none) , min percent threshold, optional print limit, callchain order, key (function or address), add branches. "
 		     "Default: fractal,0.5,callee,function", &report_parse_callchain_opt, callchain_default_opt),
 	OPT_BOOLEAN(0, "children", &symbol_conf.cumulate_callchain,
 		    "Accumulate callchains of children and show total overhead as well"),
@@ -684,7 +686,10 @@ int cmd_report(int argc, const char **argv, const char *prefix __maybe_unused)
 	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
 		    "Show event group information together"),
 	OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
-		    "use branch records for histogram filling", parse_branch_mode),
+		    "use branch records for per branch histogram filling",
+		    parse_branch_mode),
+	OPT_BOOLEAN(0, "branch-history", &branch_call_mode,
+		    "add last branch records to call history"),
 	OPT_STRING(0, "objdump", &objdump_path, "path",
 		   "objdump binary to use for disassembly and annotations"),
 	OPT_BOOLEAN(0, "demangle", &symbol_conf.demangle,
@@ -745,10 +750,24 @@ repeat:
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
-	if ((branch_mode == -1 && has_br_stack) || branch_mode == 1) {
+	/*
+	 * Branch mode is a tristate:
+	 * -1 means default, so decide based on the file having branch data.
+	 * 0/1 means the user chose a mode.
+	 */
+	if (((branch_mode == -1 && has_br_stack) || branch_mode == 1) &&
+	    branch_call_mode == -1) {
 		sort__mode = SORT_MODE__BRANCH;
 		symbol_conf.cumulate_callchain = false;
 	}
+	if (branch_call_mode) {
+		callchain_param.key = CCKEY_ADDRESS;
+		callchain_param.branch_callstack = 1;
+		symbol_conf.use_callchain = true;
+		callchain_register_param(&callchain_param);
+		if (sort_order == NULL)
+			sort_order = "srcline,symbol,dso";
+	}
 
 	if (report.mem_mode) {
 		if (sort__mode == SORT_MODE__BRANCH) {
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 9708a1290571..ce304dfd962a 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -23,7 +23,6 @@ static char const		*generate_script_lang;
 static bool			debug_mode;
 static u64			last_timestamp;
 static u64			nr_unordered;
-extern const struct option	record_options[];
 static bool			no_callchain;
 static bool			latency_format;
 static bool			system_wide;
@@ -379,7 +378,6 @@ static void print_sample_start(struct perf_sample *sample,
 
 static void print_sample_addr(union perf_event *event,
 			  struct perf_sample *sample,
-			  struct machine *machine,
 			  struct thread *thread,
 			  struct perf_event_attr *attr)
 {
@@ -390,7 +388,7 @@ static void print_sample_addr(union perf_event *event,
 	if (!sample_addr_correlates_sym(attr))
 		return;
 
-	perf_event__preprocess_sample_addr(event, sample, machine, thread, &al);
+	perf_event__preprocess_sample_addr(event, sample, thread, &al);
 
 	if (PRINT_FIELD(SYM)) {
 		printf(" ");
@@ -438,7 +436,7 @@ static void print_sample_bts(union perf_event *event,
 	    ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
 	     !output[attr->type].user_set)) {
 		printf(" => ");
-		print_sample_addr(event, sample, al->machine, thread, attr);
+		print_sample_addr(event, sample, thread, attr);
 	}
 
 	if (print_srcline_last)
@@ -475,7 +473,7 @@ static void process_event(union perf_event *event, struct perf_sample *sample,
 		event_format__print(evsel->tp_format, sample->cpu,
 				    sample->raw_data, sample->raw_size);
 	if (PRINT_FIELD(ADDR))
-		print_sample_addr(event, sample, al->machine, thread, attr);
+		print_sample_addr(event, sample, thread, attr);
 
 	if (PRINT_FIELD(IP)) {
 		if (!symbol_conf.use_callchain)
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 055ce9232c9e..891086376381 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -388,20 +388,102 @@ static void update_shadow_stats(struct perf_evsel *counter, u64 *count)
 		update_stats(&runtime_itlb_cache_stats[0], count[0]);
 }
 
+static void zero_per_pkg(struct perf_evsel *counter)
+{
+	if (counter->per_pkg_mask)
+		memset(counter->per_pkg_mask, 0, MAX_NR_CPUS);
+}
+
+static int check_per_pkg(struct perf_evsel *counter, int cpu, bool *skip)
+{
+	unsigned long *mask = counter->per_pkg_mask;
+	struct cpu_map *cpus = perf_evsel__cpus(counter);
+	int s;
+
+	*skip = false;
+
+	if (!counter->per_pkg)
+		return 0;
+
+	if (cpu_map__empty(cpus))
+		return 0;
+
+	if (!mask) {
+		mask = zalloc(MAX_NR_CPUS);
+		if (!mask)
+			return -ENOMEM;
+
+		counter->per_pkg_mask = mask;
+	}
+
+	s = cpu_map__get_socket(cpus, cpu);
+	if (s < 0)
+		return -1;
+
+	*skip = test_and_set_bit(s, mask) == 1;
+	return 0;
+}
+
+static int read_cb(struct perf_evsel *evsel, int cpu, int thread __maybe_unused,
+		   struct perf_counts_values *count)
+{
+	struct perf_counts_values *aggr = &evsel->counts->aggr;
+	static struct perf_counts_values zero;
+	bool skip = false;
+
+	if (check_per_pkg(evsel, cpu, &skip)) {
+		pr_err("failed to read per-pkg counter\n");
+		return -1;
+	}
+
+	if (skip)
+		count = &zero;
+
+	switch (aggr_mode) {
+	case AGGR_CORE:
+	case AGGR_SOCKET:
+	case AGGR_NONE:
+		if (!evsel->snapshot)
+			perf_evsel__compute_deltas(evsel, cpu, count);
+		perf_counts_values__scale(count, scale, NULL);
+		evsel->counts->cpu[cpu] = *count;
+		update_shadow_stats(evsel, count->values);
+		break;
+	case AGGR_GLOBAL:
+		aggr->val += count->val;
+		if (scale) {
+			aggr->ena += count->ena;
+			aggr->run += count->run;
+		}
+	default:
+		break;
+	}
+
+	return 0;
+}
+
+static int read_counter(struct perf_evsel *counter);
+
 /*
  * Read out the results of a single counter:
  * aggregate counts across CPUs in system-wide mode
  */
 static int read_counter_aggr(struct perf_evsel *counter)
 {
+	struct perf_counts_values *aggr = &counter->counts->aggr;
 	struct perf_stat *ps = counter->priv;
 	u64 *count = counter->counts->aggr.values;
 	int i;
 
-	if (__perf_evsel__read(counter, perf_evsel__nr_cpus(counter),
-			       thread_map__nr(evsel_list->threads), scale) < 0)
+	aggr->val = aggr->ena = aggr->run = 0;
+
+	if (read_counter(counter))
 		return -1;
 
+	if (!counter->snapshot)
+		perf_evsel__compute_deltas(counter, -1, aggr);
+	perf_counts_values__scale(aggr, scale, &counter->counts->scaled);
+
 	for (i = 0; i < 3; i++)
 		update_stats(&ps->res_stats[i], count[i]);
 
@@ -424,16 +506,21 @@ static int read_counter_aggr(struct perf_evsel *counter)
  */
 static int read_counter(struct perf_evsel *counter)
 {
-	u64 *count;
-	int cpu;
+	int nthreads = thread_map__nr(evsel_list->threads);
+	int ncpus = perf_evsel__nr_cpus(counter);
+	int cpu, thread;
 
-	for (cpu = 0; cpu < perf_evsel__nr_cpus(counter); cpu++) {
-		if (__perf_evsel__read_on_cpu(counter, cpu, 0, scale) < 0)
-			return -1;
+	if (counter->system_wide)
+		nthreads = 1;
 
-		count = counter->counts->cpu[cpu].values;
+	if (counter->per_pkg)
+		zero_per_pkg(counter);
 
-		update_shadow_stats(counter, count);
+	for (thread = 0; thread < nthreads; thread++) {
+		for (cpu = 0; cpu < ncpus; cpu++) {
+			if (perf_evsel__read_cb(counter, cpu, thread, read_cb))
+				return -1;
+		}
 	}
 
 	return 0;
diff --git a/tools/perf/builtin-timechart.c b/tools/perf/builtin-timechart.c
index 35b425b6293f..f3bb1a4bf060 100644
--- a/tools/perf/builtin-timechart.c
+++ b/tools/perf/builtin-timechart.c
@@ -528,7 +528,7 @@ static const char *cat_backtrace(union perf_event *event,
 		}
 
 		tal.filtered = 0;
-		thread__find_addr_location(al.thread, machine, cpumode,
+		thread__find_addr_location(al.thread, cpumode,
 					   MAP__FUNCTION, ip, &tal);
 
 		if (tal.sym)
@@ -1963,7 +1963,7 @@ int cmd_timechart(int argc, const char **argv,
 		NULL
 	};
 
-	const struct option record_options[] = {
+	const struct option timechart_record_options[] = {
 	OPT_BOOLEAN('P', "power-only", &tchart.power_only, "output power data only"),
 	OPT_BOOLEAN('T', "tasks-only", &tchart.tasks_only,
 		    "output processes data only"),
@@ -1972,7 +1972,7 @@ int cmd_timechart(int argc, const char **argv,
 	OPT_BOOLEAN('g', "callchain", &tchart.with_backtrace, "record callchain"),
 	OPT_END()
 	};
-	const char * const record_usage[] = {
+	const char * const timechart_record_usage[] = {
 		"perf timechart record [<options>]",
 		NULL
 	};
@@ -1985,7 +1985,8 @@ int cmd_timechart(int argc, const char **argv,
 	}
 
 	if (argc && !strncmp(argv[0], "rec", 3)) {
-		argc = parse_options(argc, argv, record_options, record_usage,
+		argc = parse_options(argc, argv, timechart_record_options,
+				     timechart_record_usage,
 				     PARSE_OPT_STOP_AT_NON_OPTION);
 
 		if (tchart.power_only && tchart.tasks_only) {
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index fb126459b134..83a4835c8118 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -1846,7 +1846,7 @@ static int trace__pgfault(struct trace *trace,
 	if (trace->summary_only)
 		return 0;
 
-	thread__find_addr_location(thread, trace->host, cpumode, MAP__FUNCTION,
+	thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
 			      sample->ip, &al);
 
 	trace__fprintf_entry_head(trace, thread, 0, sample->time, trace->output);
@@ -1859,11 +1859,11 @@ static int trace__pgfault(struct trace *trace,
 
 	fprintf(trace->output, "] => ");
 
-	thread__find_addr_location(thread, trace->host, cpumode, MAP__VARIABLE,
+	thread__find_addr_location(thread, cpumode, MAP__VARIABLE,
 				   sample->addr, &al);
 
 	if (!al.map) {
-		thread__find_addr_location(thread, trace->host, cpumode,
+		thread__find_addr_location(thread, cpumode,
 					   MAP__FUNCTION, sample->addr, &al);
 
 		if (al.map)
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 58f609198c6d..5d4b039fe1ed 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -150,7 +150,7 @@ CFLAGS += -std=gnu99
 # adding assembler files missing the .GNU-stack linker note.
 LDFLAGS += -Wl,-z,noexecstack
 
-EXTLIBS = -lelf -lpthread -lrt -lm -ldl
+EXTLIBS = -lpthread -lrt -lm -ldl
 
 ifneq ($(OUTPUT),)
   OUTPUT_FEATURES = $(OUTPUT)config/feature-checks/
@@ -200,7 +200,8 @@ CORE_FEATURE_TESTS =			\
 	libunwind			\
 	stackprotector-all		\
 	timerfd				\
-	libdw-dwarf-unwind
+	libdw-dwarf-unwind		\
+	zlib
 
 LIB_FEATURE_TESTS =			\
 	dwarf				\
@@ -214,7 +215,8 @@ LIB_FEATURE_TESTS =			\
 	libpython			\
 	libslang			\
 	libunwind			\
-	libdw-dwarf-unwind
+	libdw-dwarf-unwind		\
+	zlib
 
 VF_FEATURE_TESTS =			\
 	backtrace			\
@@ -230,7 +232,9 @@ VF_FEATURE_TESTS =			\
 	bionic				\
 	liberty				\
 	liberty-z			\
-	cplus-demangle
+	cplus-demangle			\
+	compile-32			\
+	compile-x32
 
 # Set FEATURE_CHECK_(C|LD)FLAGS-all for all CORE_FEATURE_TESTS features.
 # If in the future we need per-feature checks/flags for features not
@@ -350,6 +354,7 @@ endif # NO_LIBELF
 
 ifndef NO_LIBELF
   CFLAGS += -DHAVE_LIBELF_SUPPORT
+  EXTLIBS += -lelf
 
   ifeq ($(feature-libelf-mmap), 1)
     CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT
@@ -369,7 +374,7 @@ ifndef NO_LIBELF
     else
       CFLAGS += -DHAVE_DWARF_SUPPORT $(LIBDW_CFLAGS)
       LDFLAGS += $(LIBDW_LDFLAGS)
-      EXTLIBS += -lelf -ldw
+      EXTLIBS += -ldw
     endif # PERF_HAVE_DWARF_REGS
   endif # NO_DWARF
 endif # NO_LIBELF
@@ -602,6 +607,15 @@ ifneq ($(filter -lbfd,$(EXTLIBS)),)
   CFLAGS += -DHAVE_LIBBFD_SUPPORT
 endif
 
+ifndef NO_ZLIB
+  ifeq ($(feature-zlib), 1)
+    CFLAGS += -DHAVE_ZLIB_SUPPORT
+    EXTLIBS += -lz
+  else
+    NO_ZLIB := 1
+  endif
+endif
+
 ifndef NO_BACKTRACE
   ifeq ($(feature-backtrace), 1)
     CFLAGS += -DHAVE_BACKTRACE_SUPPORT
@@ -622,6 +636,31 @@ ifdef HAVE_KVM_STAT_SUPPORT
     CFLAGS += -DHAVE_KVM_STAT_SUPPORT
 endif
 
+ifeq (${IS_64_BIT}, 1)
+  ifndef NO_PERF_READ_VDSO32
+    $(call feature_check,compile-32)
+    ifeq ($(feature-compile-32), 1)
+      CFLAGS += -DHAVE_PERF_READ_VDSO32
+    else
+      NO_PERF_READ_VDSO32 := 1
+    endif
+  endif
+  ifneq (${IS_X86_64}, 1)
+    NO_PERF_READ_VDSOX32 := 1
+  endif
+  ifndef NO_PERF_READ_VDSOX32
+    $(call feature_check,compile-x32)
+    ifeq ($(feature-compile-x32), 1)
+      CFLAGS += -DHAVE_PERF_READ_VDSOX32
+    else
+      NO_PERF_READ_VDSOX32 := 1
+    endif
+  endif
+else
+  NO_PERF_READ_VDSO32 := 1
+  NO_PERF_READ_VDSOX32 := 1
+endif
+
 # Among the variables below, these:
 #   perfexecdir
 #   template_dir
diff --git a/tools/perf/config/Makefile.arch b/tools/perf/config/Makefile.arch
index 4b06719ee984..851cd0172a76 100644
--- a/tools/perf/config/Makefile.arch
+++ b/tools/perf/config/Makefile.arch
@@ -21,3 +21,11 @@ ifeq ($(ARCH),x86_64)
     RAW_ARCH := x86_64
   endif
 endif
+
+ifeq (${IS_X86_64}, 1)
+  IS_64_BIT := 1
+else ifeq ($(ARCH),x86)
+  IS_64_BIT := 0
+else
+  IS_64_BIT := $(shell echo __LP64__ | ${CC} ${CFLAGS} -E -x c - | tail -n 1)
+endif
diff --git a/tools/perf/config/feature-checks/Makefile b/tools/perf/config/feature-checks/Makefile
index 72ab2984718e..53f19b5dbc37 100644
--- a/tools/perf/config/feature-checks/Makefile
+++ b/tools/perf/config/feature-checks/Makefile
@@ -27,7 +27,10 @@ FILES=					\
 	test-libunwind-debug-frame.bin	\
 	test-stackprotector-all.bin	\
 	test-timerfd.bin		\
-	test-libdw-dwarf-unwind.bin
+	test-libdw-dwarf-unwind.bin	\
+	test-compile-32.bin		\
+	test-compile-x32.bin		\
+	test-zlib.bin
 
 CC := $(CROSS_COMPILE)gcc -MD
 PKG_CONFIG := $(CROSS_COMPILE)pkg-config
@@ -39,7 +42,7 @@ BUILD = $(CC) $(CFLAGS) -o $(OUTPUT)$@ $(patsubst %.bin,%.c,$@) $(LDFLAGS)
 ###############################
 
 test-all.bin:
-	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl
+	$(BUILD) -Werror -fstack-protector-all -O2 -Werror -D_FORTIFY_SOURCE=2 -ldw -lelf -lnuma -lelf -laudit -I/usr/include/slang -lslang $(shell $(PKG_CONFIG) --libs --cflags gtk+-2.0 2>/dev/null) $(FLAGS_PERL_EMBED) $(FLAGS_PYTHON_EMBED) -DPACKAGE='"perf"' -lbfd -ldl -lz
 
 test-hello.bin:
 	$(BUILD)
@@ -131,6 +134,15 @@ test-libdw-dwarf-unwind.bin:
 test-sync-compare-and-swap.bin:
 	$(BUILD) -Werror
 
+test-compile-32.bin:
+	$(CC) -m32 -o $(OUTPUT)$@ test-compile.c
+
+test-compile-x32.bin:
+	$(CC) -mx32 -o $(OUTPUT)$@ test-compile.c
+
+test-zlib.bin:
+	$(BUILD) -lz
+
 -include *.d
 
 ###############################
diff --git a/tools/perf/config/feature-checks/test-all.c b/tools/perf/config/feature-checks/test-all.c
index a7d022e161c0..652e0098eba6 100644
--- a/tools/perf/config/feature-checks/test-all.c
+++ b/tools/perf/config/feature-checks/test-all.c
@@ -93,6 +93,10 @@
 # include "test-sync-compare-and-swap.c"
 #undef main
 
+#define main main_test_zlib
+# include "test-zlib.c"
+#undef main
+
 int main(int argc, char *argv[])
 {
 	main_test_libpython();
@@ -116,6 +120,7 @@ int main(int argc, char *argv[])
 	main_test_stackprotector_all();
 	main_test_libdw_dwarf_unwind();
 	main_test_sync_compare_and_swap(argc, argv);
+	main_test_zlib();
 
 	return 0;
 }
diff --git a/tools/perf/config/feature-checks/test-compile.c b/tools/perf/config/feature-checks/test-compile.c
new file mode 100644
index 000000000000..31dbf45bf99c
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-compile.c
@@ -0,0 +1,4 @@
+int main(void)
+{
+	return 0;
+}
diff --git a/tools/perf/config/feature-checks/test-zlib.c b/tools/perf/config/feature-checks/test-zlib.c
new file mode 100644
index 000000000000..e111fff6240e
--- /dev/null
+++ b/tools/perf/config/feature-checks/test-zlib.c
@@ -0,0 +1,9 @@
+#include <zlib.h>
+
+int main(void)
+{
+	z_stream zs;
+
+	inflateInit(&zs);
+	return 0;
+}
diff --git a/tools/perf/perf-read-vdso.c b/tools/perf/perf-read-vdso.c
new file mode 100644
index 000000000000..764e2547c25a
--- /dev/null
+++ b/tools/perf/perf-read-vdso.c
@@ -0,0 +1,34 @@
+#include <stdio.h>
+#include <string.h>
+
+#define VDSO__MAP_NAME "[vdso]"
+
+/*
+ * Include definition of find_vdso_map() also used in util/vdso.c for
+ * building perf.
+ */
+#include "util/find-vdso-map.c"
+
+int main(void)
+{
+	void *start, *end;
+	size_t size, written;
+
+	if (find_vdso_map(&start, &end))
+		return 1;
+
+	size = end - start;
+
+	while (size) {
+		written = fwrite(start, 1, size, stdout);
+		if (!written)
+			return 1;
+		start += written;
+		size -= written;
+	}
+
+	if (fflush(stdout))
+		return 1;
+
+	return 0;
+}
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 220d44e44c1b..1dabb8553499 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -52,6 +52,7 @@ struct record_opts {
 	bool	     sample_weight;
 	bool	     sample_time;
 	bool	     period;
+	bool	     sample_intr_regs;
 	unsigned int freq;
 	unsigned int mmap_pages;
 	unsigned int user_freq;
@@ -62,4 +63,7 @@ struct record_opts {
 	unsigned     initial_delay;
 };
 
+struct option;
+extern const char * const *record_usage;
+extern struct option *record_options;
 #endif
diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-record b/tools/perf/scripts/python/bin/export-to-postgresql-record
new file mode 100644
index 000000000000..221d66e05713
--- /dev/null
+++ b/tools/perf/scripts/python/bin/export-to-postgresql-record
@@ -0,0 +1,8 @@
+#!/bin/bash
+
+#
+# export perf data to a postgresql database. Can cover
+# perf ip samples (excluding the tracepoints). No special
+# record requirements, just record what you want to export.
+#
+perf record $@
diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-report b/tools/perf/scripts/python/bin/export-to-postgresql-report
new file mode 100644
index 000000000000..cd335b6e2a01
--- /dev/null
+++ b/tools/perf/scripts/python/bin/export-to-postgresql-report
@@ -0,0 +1,29 @@
+#!/bin/bash
+# description: export perf data to a postgresql database
+# args: [database name] [columns] [calls]
+n_args=0
+for i in "$@"
+do
+    if expr match "$i" "-" > /dev/null ; then
+	break
+    fi
+    n_args=$(( $n_args + 1 ))
+done
+if [ "$n_args" -gt 3 ] ; then
+    echo "usage: export-to-postgresql-report [database name] [columns] [calls]"
+    exit
+fi
+if [ "$n_args" -gt 2 ] ; then
+    dbname=$1
+    columns=$2
+    calls=$3
+    shift 3
+elif [ "$n_args" -gt 1 ] ; then
+    dbname=$1
+    columns=$2
+    shift 2
+elif [ "$n_args" -gt 0 ] ; then
+    dbname=$1
+    shift
+fi
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns $calls
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
new file mode 100644
index 000000000000..4cdafd880074
--- /dev/null
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -0,0 +1,444 @@
+# export-to-postgresql.py: export perf data to a postgresql database
+# Copyright (c) 2014, Intel Corporation.
+#
+# This program is free software; you can redistribute it and/or modify it
+# under the terms and conditions of the GNU General Public License,
+# version 2, as published by the Free Software Foundation.
+#
+# This program is distributed in the hope 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.
+
+import os
+import sys
+import struct
+import datetime
+
+from PySide.QtSql import *
+
+# Need to access PostgreSQL C library directly to use COPY FROM STDIN
+from ctypes import *
+libpq = CDLL("libpq.so.5")
+PQconnectdb = libpq.PQconnectdb
+PQconnectdb.restype = c_void_p
+PQfinish = libpq.PQfinish
+PQstatus = libpq.PQstatus
+PQexec = libpq.PQexec
+PQexec.restype = c_void_p
+PQresultStatus = libpq.PQresultStatus
+PQputCopyData = libpq.PQputCopyData
+PQputCopyData.argtypes = [ c_void_p, c_void_p, c_int ]
+PQputCopyEnd = libpq.PQputCopyEnd
+PQputCopyEnd.argtypes = [ c_void_p, c_void_p ]
+
+sys.path.append(os.environ['PERF_EXEC_PATH'] + \
+	'/scripts/python/Perf-Trace-Util/lib/Perf/Trace')
+
+# These perf imports are not used at present
+#from perf_trace_context import *
+#from Core import *
+
+perf_db_export_mode = True
+perf_db_export_calls = False
+
+def usage():
+	print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>]"
+	print >> sys.stderr, "where:	columns		'all' or 'branches'"
+	print >> sys.stderr, "		calls		'calls' => create calls table"
+	raise Exception("Too few arguments")
+
+if (len(sys.argv) < 2):
+	usage()
+
+dbname = sys.argv[1]
+
+if (len(sys.argv) >= 3):
+	columns = sys.argv[2]
+else:
+	columns = "all"
+
+if columns not in ("all", "branches"):
+	usage()
+
+branches = (columns == "branches")
+
+if (len(sys.argv) >= 4):
+	if (sys.argv[3] == "calls"):
+		perf_db_export_calls = True
+	else:
+		usage()
+
+output_dir_name = os.getcwd() + "/" + dbname + "-perf-data"
+os.mkdir(output_dir_name)
+
+def do_query(q, s):
+	if (q.exec_(s)):
+		return
+	raise Exception("Query failed: " + q.lastError().text())
+
+print datetime.datetime.today(), "Creating database..."
+
+db = QSqlDatabase.addDatabase('QPSQL')
+query = QSqlQuery(db)
+db.setDatabaseName('postgres')
+db.open()
+try:
+	do_query(query, 'CREATE DATABASE ' + dbname)
+except:
+	os.rmdir(output_dir_name)
+	raise
+query.finish()
+query.clear()
+db.close()
+
+db.setDatabaseName(dbname)
+db.open()
+
+query = QSqlQuery(db)
+do_query(query, 'SET client_min_messages TO WARNING')
+
+do_query(query, 'CREATE TABLE selected_events ('
+		'id		bigint		NOT NULL,'
+		'name		varchar(80))')
+do_query(query, 'CREATE TABLE machines ('
+		'id		bigint		NOT NULL,'
+		'pid		integer,'
+		'root_dir 	varchar(4096))')
+do_query(query, 'CREATE TABLE threads ('
+		'id		bigint		NOT NULL,'
+		'machine_id	bigint,'
+		'process_id	bigint,'
+		'pid		integer,'
+		'tid		integer)')
+do_query(query, 'CREATE TABLE comms ('
+		'id		bigint		NOT NULL,'
+		'comm		varchar(16))')
+do_query(query, 'CREATE TABLE comm_threads ('
+		'id		bigint		NOT NULL,'
+		'comm_id	bigint,'
+		'thread_id	bigint)')
+do_query(query, 'CREATE TABLE dsos ('
+		'id		bigint		NOT NULL,'
+		'machine_id	bigint,'
+		'short_name	varchar(256),'
+		'long_name	varchar(4096),'
+		'build_id	varchar(64))')
+do_query(query, 'CREATE TABLE symbols ('
+		'id		bigint		NOT NULL,'
+		'dso_id		bigint,'
+		'sym_start	bigint,'
+		'sym_end	bigint,'
+		'binding	integer,'
+		'name		varchar(2048))')
+do_query(query, 'CREATE TABLE branch_types ('
+		'id		integer		NOT NULL,'
+		'name		varchar(80))')
+
+if branches:
+	do_query(query, 'CREATE TABLE samples ('
+		'id		bigint		NOT NULL,'
+		'evsel_id	bigint,'
+		'machine_id	bigint,'
+		'thread_id	bigint,'
+		'comm_id	bigint,'
+		'dso_id		bigint,'
+		'symbol_id	bigint,'
+		'sym_offset	bigint,'
+		'ip		bigint,'
+		'time		bigint,'
+		'cpu		integer,'
+		'to_dso_id	bigint,'
+		'to_symbol_id	bigint,'
+		'to_sym_offset	bigint,'
+		'to_ip		bigint,'
+		'branch_type	integer,'
+		'in_tx		boolean)')
+else:
+	do_query(query, 'CREATE TABLE samples ('
+		'id		bigint		NOT NULL,'
+		'evsel_id	bigint,'
+		'machine_id	bigint,'
+		'thread_id	bigint,'
+		'comm_id	bigint,'
+		'dso_id		bigint,'
+		'symbol_id	bigint,'
+		'sym_offset	bigint,'
+		'ip		bigint,'
+		'time		bigint,'
+		'cpu		integer,'
+		'to_dso_id	bigint,'
+		'to_symbol_id	bigint,'
+		'to_sym_offset	bigint,'
+		'to_ip		bigint,'
+		'period		bigint,'
+		'weight		bigint,'
+		'transaction	bigint,'
+		'data_src	bigint,'
+		'branch_type	integer,'
+		'in_tx		boolean)')
+
+if perf_db_export_calls:
+	do_query(query, 'CREATE TABLE call_paths ('
+		'id		bigint		NOT NULL,'
+		'parent_id	bigint,'
+		'symbol_id	bigint,'
+		'ip		bigint)')
+	do_query(query, 'CREATE TABLE calls ('
+		'id		bigint		NOT NULL,'
+		'thread_id	bigint,'
+		'comm_id	bigint,'
+		'call_path_id	bigint,'
+		'call_time	bigint,'
+		'return_time	bigint,'
+		'branch_count	bigint,'
+		'call_id	bigint,'
+		'return_id	bigint,'
+		'parent_call_path_id	bigint,'
+		'flags		integer)')
+
+do_query(query, 'CREATE VIEW samples_view AS '
+	'SELECT '
+		'id,'
+		'time,'
+		'cpu,'
+		'(SELECT pid FROM threads WHERE id = thread_id) AS pid,'
+		'(SELECT tid FROM threads WHERE id = thread_id) AS tid,'
+		'(SELECT comm FROM comms WHERE id = comm_id) AS command,'
+		'(SELECT name FROM selected_events WHERE id = evsel_id) AS event,'
+		'to_hex(ip) AS ip_hex,'
+		'(SELECT name FROM symbols WHERE id = symbol_id) AS symbol,'
+		'sym_offset,'
+		'(SELECT short_name FROM dsos WHERE id = dso_id) AS dso_short_name,'
+		'to_hex(to_ip) AS to_ip_hex,'
+		'(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,'
+		'to_sym_offset,'
+		'(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
+		'(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
+		'in_tx'
+	' FROM samples')
+
+
+file_header = struct.pack("!11sii", "PGCOPY\n\377\r\n\0", 0, 0)
+file_trailer = "\377\377"
+
+def open_output_file(file_name):
+	path_name = output_dir_name + "/" + file_name
+	file = open(path_name, "w+")
+	file.write(file_header)
+	return file
+
+def close_output_file(file):
+	file.write(file_trailer)
+	file.close()
+
+def copy_output_file_direct(file, table_name):
+	close_output_file(file)
+	sql = "COPY " + table_name + " FROM '" + file.name + "' (FORMAT 'binary')"
+	do_query(query, sql)
+
+# Use COPY FROM STDIN because security may prevent postgres from accessing the files directly
+def copy_output_file(file, table_name):
+	conn = PQconnectdb("dbname = " + dbname)
+	if (PQstatus(conn)):
+		raise Exception("COPY FROM STDIN PQconnectdb failed")
+	file.write(file_trailer)
+	file.seek(0)
+	sql = "COPY " + table_name + " FROM STDIN (FORMAT 'binary')"
+	res = PQexec(conn, sql)
+	if (PQresultStatus(res) != 4):
+		raise Exception("COPY FROM STDIN PQexec failed")
+	data = file.read(65536)
+	while (len(data)):
+		ret = PQputCopyData(conn, data, len(data))
+		if (ret != 1):
+			raise Exception("COPY FROM STDIN PQputCopyData failed, error " + str(ret))
+		data = file.read(65536)
+	ret = PQputCopyEnd(conn, None)
+	if (ret != 1):
+		raise Exception("COPY FROM STDIN PQputCopyEnd failed, error " + str(ret))
+	PQfinish(conn)
+
+def remove_output_file(file):
+	name = file.name
+	file.close()
+	os.unlink(name)
+
+evsel_file		= open_output_file("evsel_table.bin")
+machine_file		= open_output_file("machine_table.bin")
+thread_file		= open_output_file("thread_table.bin")
+comm_file		= open_output_file("comm_table.bin")
+comm_thread_file	= open_output_file("comm_thread_table.bin")
+dso_file		= open_output_file("dso_table.bin")
+symbol_file		= open_output_file("symbol_table.bin")
+branch_type_file	= open_output_file("branch_type_table.bin")
+sample_file		= open_output_file("sample_table.bin")
+if perf_db_export_calls:
+	call_path_file		= open_output_file("call_path_table.bin")
+	call_file		= open_output_file("call_table.bin")
+
+def trace_begin():
+	print datetime.datetime.today(), "Writing to intermediate files..."
+	# id == 0 means unknown.  It is easier to create records for them than replace the zeroes with NULLs
+	evsel_table(0, "unknown")
+	machine_table(0, 0, "unknown")
+	thread_table(0, 0, 0, -1, -1)
+	comm_table(0, "unknown")
+	dso_table(0, 0, "unknown", "unknown", "")
+	symbol_table(0, 0, 0, 0, 0, "unknown")
+	sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+	if perf_db_export_calls:
+		call_path_table(0, 0, 0, 0)
+
+unhandled_count = 0
+
+def trace_end():
+	print datetime.datetime.today(), "Copying to database..."
+	copy_output_file(evsel_file,		"selected_events")
+	copy_output_file(machine_file,		"machines")
+	copy_output_file(thread_file,		"threads")
+	copy_output_file(comm_file,		"comms")
+	copy_output_file(comm_thread_file,	"comm_threads")
+	copy_output_file(dso_file,		"dsos")
+	copy_output_file(symbol_file,		"symbols")
+	copy_output_file(branch_type_file,	"branch_types")
+	copy_output_file(sample_file,		"samples")
+	if perf_db_export_calls:
+		copy_output_file(call_path_file,	"call_paths")
+		copy_output_file(call_file,		"calls")
+
+	print datetime.datetime.today(), "Removing intermediate files..."
+	remove_output_file(evsel_file)
+	remove_output_file(machine_file)
+	remove_output_file(thread_file)
+	remove_output_file(comm_file)
+	remove_output_file(comm_thread_file)
+	remove_output_file(dso_file)
+	remove_output_file(symbol_file)
+	remove_output_file(branch_type_file)
+	remove_output_file(sample_file)
+	if perf_db_export_calls:
+		remove_output_file(call_path_file)
+		remove_output_file(call_file)
+	os.rmdir(output_dir_name)
+	print datetime.datetime.today(), "Adding primary keys"
+	do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE machines        ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE threads         ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE comms           ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE comm_threads    ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE dsos            ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE symbols         ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE branch_types    ADD PRIMARY KEY (id)')
+	do_query(query, 'ALTER TABLE samples         ADD PRIMARY KEY (id)')
+	if perf_db_export_calls:
+		do_query(query, 'ALTER TABLE call_paths      ADD PRIMARY KEY (id)')
+		do_query(query, 'ALTER TABLE calls           ADD PRIMARY KEY (id)')
+
+	print datetime.datetime.today(), "Adding foreign keys"
+	do_query(query, 'ALTER TABLE threads '
+					'ADD CONSTRAINT machinefk  FOREIGN KEY (machine_id)   REFERENCES machines   (id),'
+					'ADD CONSTRAINT processfk  FOREIGN KEY (process_id)   REFERENCES threads    (id)')
+	do_query(query, 'ALTER TABLE comm_threads '
+					'ADD CONSTRAINT commfk     FOREIGN KEY (comm_id)      REFERENCES comms      (id),'
+					'ADD CONSTRAINT threadfk   FOREIGN KEY (thread_id)    REFERENCES threads    (id)')
+	do_query(query, 'ALTER TABLE dsos '
+					'ADD CONSTRAINT machinefk  FOREIGN KEY (machine_id)   REFERENCES machines   (id)')
+	do_query(query, 'ALTER TABLE symbols '
+					'ADD CONSTRAINT dsofk      FOREIGN KEY (dso_id)       REFERENCES dsos       (id)')
+	do_query(query, 'ALTER TABLE samples '
+					'ADD CONSTRAINT evselfk    FOREIGN KEY (evsel_id)     REFERENCES selected_events (id),'
+					'ADD CONSTRAINT machinefk  FOREIGN KEY (machine_id)   REFERENCES machines   (id),'
+					'ADD CONSTRAINT threadfk   FOREIGN KEY (thread_id)    REFERENCES threads    (id),'
+					'ADD CONSTRAINT commfk     FOREIGN KEY (comm_id)      REFERENCES comms      (id),'
+					'ADD CONSTRAINT dsofk      FOREIGN KEY (dso_id)       REFERENCES dsos       (id),'
+					'ADD CONSTRAINT symbolfk   FOREIGN KEY (symbol_id)    REFERENCES symbols    (id),'
+					'ADD CONSTRAINT todsofk    FOREIGN KEY (to_dso_id)    REFERENCES dsos       (id),'
+					'ADD CONSTRAINT tosymbolfk FOREIGN KEY (to_symbol_id) REFERENCES symbols    (id)')
+	if perf_db_export_calls:
+		do_query(query, 'ALTER TABLE call_paths '
+					'ADD CONSTRAINT parentfk    FOREIGN KEY (parent_id)    REFERENCES call_paths (id),'
+					'ADD CONSTRAINT symbolfk    FOREIGN KEY (symbol_id)    REFERENCES symbols    (id)')
+		do_query(query, 'ALTER TABLE calls '
+					'ADD CONSTRAINT threadfk    FOREIGN KEY (thread_id)    REFERENCES threads    (id),'
+					'ADD CONSTRAINT commfk      FOREIGN KEY (comm_id)      REFERENCES comms      (id),'
+					'ADD CONSTRAINT call_pathfk FOREIGN KEY (call_path_id) REFERENCES call_paths (id),'
+					'ADD CONSTRAINT callfk      FOREIGN KEY (call_id)      REFERENCES samples    (id),'
+					'ADD CONSTRAINT returnfk    FOREIGN KEY (return_id)    REFERENCES samples    (id),'
+					'ADD CONSTRAINT parent_call_pathfk FOREIGN KEY (parent_call_path_id) REFERENCES call_paths (id)')
+		do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
+
+	if (unhandled_count):
+		print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
+	print datetime.datetime.today(), "Done"
+
+def trace_unhandled(event_name, context, event_fields_dict):
+	global unhandled_count
+	unhandled_count += 1
+
+def sched__sched_switch(*x):
+	pass
+
+def evsel_table(evsel_id, evsel_name, *x):
+	n = len(evsel_name)
+	fmt = "!hiqi" + str(n) + "s"
+	value = struct.pack(fmt, 2, 8, evsel_id, n, evsel_name)
+	evsel_file.write(value)
+
+def machine_table(machine_id, pid, root_dir, *x):
+	n = len(root_dir)
+	fmt = "!hiqiii" + str(n) + "s"
+	value = struct.pack(fmt, 3, 8, machine_id, 4, pid, n, root_dir)
+	machine_file.write(value)
+
+def thread_table(thread_id, machine_id, process_id, pid, tid, *x):
+	value = struct.pack("!hiqiqiqiiii", 5, 8, thread_id, 8, machine_id, 8, process_id, 4, pid, 4, tid)
+	thread_file.write(value)
+
+def comm_table(comm_id, comm_str, *x):
+	n = len(comm_str)
+	fmt = "!hiqi" + str(n) + "s"
+	value = struct.pack(fmt, 2, 8, comm_id, n, comm_str)
+	comm_file.write(value)
+
+def comm_thread_table(comm_thread_id, comm_id, thread_id, *x):
+	fmt = "!hiqiqiq"
+	value = struct.pack(fmt, 3, 8, comm_thread_id, 8, comm_id, 8, thread_id)
+	comm_thread_file.write(value)
+
+def dso_table(dso_id, machine_id, short_name, long_name, build_id, *x):
+	n1 = len(short_name)
+	n2 = len(long_name)
+	n3 = len(build_id)
+	fmt = "!hiqiqi" + str(n1) + "si"  + str(n2) + "si" + str(n3) + "s"
+	value = struct.pack(fmt, 5, 8, dso_id, 8, machine_id, n1, short_name, n2, long_name, n3, build_id)
+	dso_file.write(value)
+
+def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x):
+	n = len(symbol_name)
+	fmt = "!hiqiqiqiqiii" + str(n) + "s"
+	value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name)
+	symbol_file.write(value)
+
+def branch_type_table(branch_type, name, *x):
+	n = len(name)
+	fmt = "!hiii" + str(n) + "s"
+	value = struct.pack(fmt, 2, 4, branch_type, n, name)
+	branch_type_file.write(value)
+
+def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, *x):
+	if branches:
+		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiB", 17, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx)
+	else:
+		value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx)
+	sample_file.write(value)
+
+def call_path_table(cp_id, parent_id, symbol_id, ip, *x):
+	fmt = "!hiqiqiqiq"
+	value = struct.pack(fmt, 4, 8, cp_id, 8, parent_id, 8, symbol_id, 8, ip)
+	call_path_file.write(value)
+
+def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, *x):
+	fmt = "!hiqiqiqiqiqiqiqiqiqiqii"
+	value = struct.pack(fmt, 11, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags)
+	call_file.write(value)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 162c978f1491..4b7d9ab0f049 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -85,7 +85,7 @@ static struct test {
 		.func = test__hists_link,
 	},
 	{
-		.desc = "Try 'use perf' in python, checking link problems",
+		.desc = "Try 'import perf' in python, checking link problems",
 		.func = test__python_use,
 	},
 	{
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 67f2d6323558..f671ec37a7c4 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -133,8 +133,7 @@ static int read_via_objdump(const char *filename, u64 addr, void *buf,
 }
 
 static int read_object_code(u64 addr, size_t len, u8 cpumode,
-			    struct thread *thread, struct machine *machine,
-			    struct state *state)
+			    struct thread *thread, struct state *state)
 {
 	struct addr_location al;
 	unsigned char buf1[BUFSZ];
@@ -145,8 +144,7 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 
 	pr_debug("Reading object code for memory address: %#"PRIx64"\n", addr);
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION, addr,
-			      &al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, addr, &al);
 	if (!al.map || !al.map->dso) {
 		pr_debug("thread__find_addr_map failed\n");
 		return -1;
@@ -170,8 +168,8 @@ static int read_object_code(u64 addr, size_t len, u8 cpumode,
 		len = al.map->end - addr;
 
 	/* Read the object code using perf */
-	ret_len = dso__data_read_offset(al.map->dso, machine, al.addr, buf1,
-					len);
+	ret_len = dso__data_read_offset(al.map->dso, thread->mg->machine,
+					al.addr, buf1, len);
 	if (ret_len != len) {
 		pr_debug("dso__data_read_offset failed\n");
 		return -1;
@@ -264,8 +262,7 @@ static int process_sample_event(struct machine *machine,
 
 	cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	return read_object_code(sample.ip, READLEN, cpumode, thread, machine,
-				state);
+	return read_object_code(sample.ip, READLEN, cpumode, thread, state);
 }
 
 static int process_event(struct machine *machine, struct perf_evlist *evlist,
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index fc25e57f4a5d..ab28cca2cb97 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -59,7 +59,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 }
 
 __attribute__ ((noinline))
-static int unwind_thread(struct thread *thread, struct machine *machine)
+static int unwind_thread(struct thread *thread)
 {
 	struct perf_sample sample;
 	unsigned long cnt = 0;
@@ -72,7 +72,7 @@ static int unwind_thread(struct thread *thread, struct machine *machine)
 		goto out;
 	}
 
-	err = unwind__get_entries(unwind_entry, &cnt, machine, thread,
+	err = unwind__get_entries(unwind_entry, &cnt, thread,
 				  &sample, MAX_STACK);
 	if (err)
 		pr_debug("unwind failed\n");
@@ -89,21 +89,21 @@ static int unwind_thread(struct thread *thread, struct machine *machine)
 }
 
 __attribute__ ((noinline))
-static int krava_3(struct thread *thread, struct machine *machine)
+static int krava_3(struct thread *thread)
 {
-	return unwind_thread(thread, machine);
+	return unwind_thread(thread);
 }
 
 __attribute__ ((noinline))
-static int krava_2(struct thread *thread, struct machine *machine)
+static int krava_2(struct thread *thread)
 {
-	return krava_3(thread, machine);
+	return krava_3(thread);
 }
 
 __attribute__ ((noinline))
-static int krava_1(struct thread *thread, struct machine *machine)
+static int krava_1(struct thread *thread)
 {
-	return krava_2(thread, machine);
+	return krava_2(thread);
 }
 
 int test__dwarf_unwind(void)
@@ -137,7 +137,7 @@ int test__dwarf_unwind(void)
 		goto out;
 	}
 
-	err = krava_1(thread, machine);
+	err = krava_1(thread);
 
  out:
 	machine__delete_threads(machine);
diff --git a/tools/perf/tests/hists_filter.c b/tools/perf/tests/hists_filter.c
index 5a31787cc6b9..74f257a81265 100644
--- a/tools/perf/tests/hists_filter.c
+++ b/tools/perf/tests/hists_filter.c
@@ -43,7 +43,7 @@ static struct sample fake_samples[] = {
 };
 
 static int add_hist_entries(struct perf_evlist *evlist,
-			    struct machine *machine __maybe_unused)
+			    struct machine *machine)
 {
 	struct perf_evsel *evsel;
 	struct addr_location al;
diff --git a/tools/perf/tests/mmap-thread-lookup.c b/tools/perf/tests/mmap-thread-lookup.c
index 4a456fef66ca..2113f1c8611f 100644
--- a/tools/perf/tests/mmap-thread-lookup.c
+++ b/tools/perf/tests/mmap-thread-lookup.c
@@ -187,7 +187,7 @@ static int mmap_events(synth_cb synth)
 
 		pr_debug("looking for map %p\n", td->map);
 
-		thread__find_addr_map(thread, machine,
+		thread__find_addr_map(thread,
 				      PERF_RECORD_MISC_USER, MAP__FUNCTION,
 				      (unsigned long) (td->map + 1), &al);
 
diff --git a/tools/perf/tests/sample-parsing.c b/tools/perf/tests/sample-parsing.c
index ca292f9a4ae2..4908c648a597 100644
--- a/tools/perf/tests/sample-parsing.c
+++ b/tools/perf/tests/sample-parsing.c
@@ -126,16 +126,28 @@ static bool samples_same(const struct perf_sample *s1,
 	if (type & PERF_SAMPLE_TRANSACTION)
 		COMP(transaction);
 
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		size_t sz = hweight_long(s1->intr_regs.mask) * sizeof(u64);
+
+		COMP(intr_regs.mask);
+		COMP(intr_regs.abi);
+		if (s1->intr_regs.abi &&
+		    (!s1->intr_regs.regs || !s2->intr_regs.regs ||
+		     memcmp(s1->intr_regs.regs, s2->intr_regs.regs, sz))) {
+			pr_debug("Samples differ at 'intr_regs'\n");
+			return false;
+		}
+	}
+
 	return true;
 }
 
-static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
+static int do_test(u64 sample_type, u64 sample_regs, u64 read_format)
 {
 	struct perf_evsel evsel = {
 		.needs_swap = false,
 		.attr = {
 			.sample_type = sample_type,
-			.sample_regs_user = sample_regs_user,
 			.read_format = read_format,
 		},
 	};
@@ -154,7 +166,7 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 		/* 1 branch_entry */
 		.data = {1, 211, 212, 213},
 	};
-	u64 user_regs[64];
+	u64 regs[64];
 	const u64 raw_data[] = {0x123456780a0b0c0dULL, 0x1102030405060708ULL};
 	const u64 data[] = {0x2211443366558877ULL, 0, 0xaabbccddeeff4321ULL};
 	struct perf_sample sample = {
@@ -176,8 +188,8 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 		.branch_stack	= &branch_stack.branch_stack,
 		.user_regs	= {
 			.abi	= PERF_SAMPLE_REGS_ABI_64,
-			.mask	= sample_regs_user,
-			.regs	= user_regs,
+			.mask	= sample_regs,
+			.regs	= regs,
 		},
 		.user_stack	= {
 			.size	= sizeof(data),
@@ -187,14 +199,25 @@ static int do_test(u64 sample_type, u64 sample_regs_user, u64 read_format)
 			.time_enabled = 0x030a59d664fca7deULL,
 			.time_running = 0x011b6ae553eb98edULL,
 		},
+		.intr_regs	= {
+			.abi	= PERF_SAMPLE_REGS_ABI_64,
+			.mask	= sample_regs,
+			.regs	= regs,
+		},
 	};
 	struct sample_read_value values[] = {{1, 5}, {9, 3}, {2, 7}, {6, 4},};
 	struct perf_sample sample_out;
 	size_t i, sz, bufsz;
 	int err, ret = -1;
 
-	for (i = 0; i < sizeof(user_regs); i++)
-		*(i + (u8 *)user_regs) = i & 0xfe;
+	if (sample_type & PERF_SAMPLE_REGS_USER)
+		evsel.attr.sample_regs_user = sample_regs;
+
+	if (sample_type & PERF_SAMPLE_REGS_INTR)
+		evsel.attr.sample_regs_intr = sample_regs;
+
+	for (i = 0; i < sizeof(regs); i++)
+		*(i + (u8 *)regs) = i & 0xfe;
 
 	if (read_format & PERF_FORMAT_GROUP) {
 		sample.read.group.nr     = 4;
@@ -271,7 +294,7 @@ int test__sample_parsing(void)
 {
 	const u64 rf[] = {4, 5, 6, 7, 12, 13, 14, 15};
 	u64 sample_type;
-	u64 sample_regs_user;
+	u64 sample_regs;
 	size_t i;
 	int err;
 
@@ -280,7 +303,7 @@ int test__sample_parsing(void)
 	 * were added.  Please actually update the test rather than just change
 	 * the condition below.
 	 */
-	if (PERF_SAMPLE_MAX > PERF_SAMPLE_TRANSACTION << 1) {
+	if (PERF_SAMPLE_MAX > PERF_SAMPLE_REGS_INTR << 1) {
 		pr_debug("sample format has changed, some new PERF_SAMPLE_ bit was introduced - test needs updating\n");
 		return -1;
 	}
@@ -297,22 +320,24 @@ int test__sample_parsing(void)
 			}
 			continue;
 		}
+		sample_regs = 0;
 
 		if (sample_type == PERF_SAMPLE_REGS_USER)
-			sample_regs_user = 0x3fff;
-		else
-			sample_regs_user = 0;
+			sample_regs = 0x3fff;
 
-		err = do_test(sample_type, sample_regs_user, 0);
+		if (sample_type == PERF_SAMPLE_REGS_INTR)
+			sample_regs = 0xff0fff;
+
+		err = do_test(sample_type, sample_regs, 0);
 		if (err)
 			return err;
 	}
 
 	/* Test all sample format bits together */
 	sample_type = PERF_SAMPLE_MAX - 1;
-	sample_regs_user = 0x3fff;
+	sample_regs = 0x3fff; /* shared yb intr and user regs */
 	for (i = 0; i < ARRAY_SIZE(rf); i++) {
-		err = do_test(sample_type, sample_regs_user, rf[i]);
+		err = do_test(sample_type, sample_regs, rf[i]);
 		if (err)
 			return err;
 	}
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index f0697a3aede0..1e0a2fd80115 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -27,6 +27,7 @@ static struct annotate_browser_opt {
 	bool hide_src_code,
 	     use_offset,
 	     jump_arrows,
+	     show_linenr,
 	     show_nr_jumps;
 } annotate_browser__opts = {
 	.use_offset	= true,
@@ -128,7 +129,11 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 	if (!*dl->line)
 		slsmg_write_nstring(" ", width - pcnt_width);
 	else if (dl->offset == -1) {
-		printed = scnprintf(bf, sizeof(bf), "%*s  ",
+		if (dl->line_nr && annotate_browser__opts.show_linenr)
+			printed = scnprintf(bf, sizeof(bf), "%-*d ",
+					ab->addr_width + 1, dl->line_nr);
+		else
+			printed = scnprintf(bf, sizeof(bf), "%*s  ",
 				    ab->addr_width, " ");
 		slsmg_write_nstring(bf, printed);
 		slsmg_write_nstring(dl->line, width - printed - pcnt_width + 1);
@@ -733,6 +738,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"o             Toggle disassembler output/simplified view\n"
 		"s             Toggle source code view\n"
 		"/             Search string\n"
+		"k             Toggle line numbers\n"
 		"r             Run available scripts\n"
 		"?             Search string backwards\n");
 			continue;
@@ -741,6 +747,10 @@ static int annotate_browser__run(struct annotate_browser *browser,
 				script_browse(NULL);
 				continue;
 			}
+		case 'k':
+			annotate_browser__opts.show_linenr =
+				!annotate_browser__opts.show_linenr;
+			break;
 		case 'H':
 			nd = browser->curr_hot;
 			break;
@@ -984,6 +994,7 @@ static struct annotate_config {
 } annotate__configs[] = {
 	ANNOTATE_CFG(hide_src_code),
 	ANNOTATE_CFG(jump_arrows),
+	ANNOTATE_CFG(show_linenr),
 	ANNOTATE_CFG(show_nr_jumps),
 	ANNOTATE_CFG(use_offset),
 };
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index cfb976b3de3a..502daff76ceb 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -227,10 +227,14 @@ static void callchain_node__init_have_children_rb_tree(struct callchain_node *no
 	}
 }
 
-static void callchain_node__init_have_children(struct callchain_node *node)
+static void callchain_node__init_have_children(struct callchain_node *node,
+					       bool has_sibling)
 {
 	struct callchain_list *chain;
 
+	chain = list_entry(node->val.next, struct callchain_list, list);
+	chain->ms.has_children = has_sibling;
+
 	if (!list_empty(&node->val)) {
 		chain = list_entry(node->val.prev, struct callchain_list, list);
 		chain->ms.has_children = !RB_EMPTY_ROOT(&node->rb_root);
@@ -241,11 +245,12 @@ static void callchain_node__init_have_children(struct callchain_node *node)
 
 static void callchain__init_have_children(struct rb_root *root)
 {
-	struct rb_node *nd;
+	struct rb_node *nd = rb_first(root);
+	bool has_sibling = nd && rb_next(nd);
 
 	for (nd = rb_first(root); nd; nd = rb_next(nd)) {
 		struct callchain_node *node = rb_entry(nd, struct callchain_node, rb_node);
-		callchain_node__init_have_children(node);
+		callchain_node__init_have_children(node, has_sibling);
 	}
 }
 
@@ -463,23 +468,6 @@ out:
 	return key;
 }
 
-static char *callchain_list__sym_name(struct callchain_list *cl,
-				      char *bf, size_t bfsize, bool show_dso)
-{
-	int printed;
-
-	if (cl->ms.sym)
-		printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
-	else
-		printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
-
-	if (show_dso)
-		scnprintf(bf + printed, bfsize - printed, " %s",
-			  cl->ms.map ? cl->ms.map->dso->short_name : "unknown");
-
-	return bf;
-}
-
 struct callchain_print_arg {
 	/* for hists browser */
 	off_t	row_offset;
@@ -559,8 +547,11 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 	struct rb_node *node;
 	int first_row = row, offset = level * LEVEL_OFFSET_STEP;
 	u64 new_total;
+	bool need_percent;
 
 	node = rb_first(root);
+	need_percent = !!rb_next(node);
+
 	while (node) {
 		struct callchain_node *child = rb_entry(node, struct callchain_node, rb_node);
 		struct rb_node *next = rb_next(node);
@@ -577,7 +568,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 
 			if (first)
 				first = false;
-			else if (level > 1)
+			else if (need_percent)
 				extra_offset = LEVEL_OFFSET_STEP;
 
 			folded_sign = callchain_list__folded(chain);
@@ -590,7 +581,7 @@ static int hist_browser__show_callchain(struct hist_browser *browser,
 			str = callchain_list__sym_name(chain, bf, sizeof(bf),
 						       browser->show_dso);
 
-			if (was_first && level > 1) {
+			if (was_first && need_percent) {
 				double percent = cumul * 100.0 / total;
 
 				if (asprintf(&alloc_str, "%2.2f%% %s", percent, str) < 0)
@@ -807,6 +798,13 @@ static int hist_browser__show_entry(struct hist_browser *browser,
 			.is_current_entry = current_entry,
 		};
 
+		if (callchain_param.mode == CHAIN_GRAPH_REL) {
+			if (symbol_conf.cumulate_callchain)
+				total = entry->stat_acc->period;
+			else
+				total = entry->stat.period;
+		}
+
 		printed += hist_browser__show_callchain(browser,
 					&entry->sorted_chain, 1, row, total,
 					hist_browser__show_callchain_entry, &arg,
diff --git a/tools/perf/ui/gtk/hists.c b/tools/perf/ui/gtk/hists.c
index fc654fb77ace..4b3585eed1e8 100644
--- a/tools/perf/ui/gtk/hists.c
+++ b/tools/perf/ui/gtk/hists.c
@@ -89,15 +89,6 @@ void perf_gtk__init_hpp(void)
 				perf_gtk__hpp_color_overhead_acc;
 }
 
-static void callchain_list__sym_name(struct callchain_list *cl,
-				     char *bf, size_t bfsize)
-{
-	if (cl->ms.sym)
-		scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
-	else
-		scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
-}
-
 static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
 				    GtkTreeIter *parent, int col, u64 total)
 {
@@ -128,7 +119,7 @@ static void perf_gtk__add_callchain(struct rb_root *root, GtkTreeStore *store,
 			scnprintf(buf, sizeof(buf), "%5.2f%%", percent);
 			gtk_tree_store_set(store, &iter, 0, buf, -1);
 
-			callchain_list__sym_name(chain, buf, sizeof(buf));
+			callchain_list__sym_name(chain, buf, sizeof(buf), false);
 			gtk_tree_store_set(store, &iter, col, buf, -1);
 
 			if (need_new_parent) {
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 15b451acbde6..dfcbc90146ef 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -41,6 +41,7 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
 {
 	int i;
 	size_t ret = 0;
+	char bf[1024];
 
 	ret += callchain__fprintf_left_margin(fp, left_margin);
 	for (i = 0; i < depth; i++) {
@@ -56,11 +57,8 @@ static size_t ipchain__fprintf_graph(FILE *fp, struct callchain_list *chain,
 		} else
 			ret += fprintf(fp, "%s", "          ");
 	}
-	if (chain->ms.sym)
-		ret += fprintf(fp, "%s\n", chain->ms.sym->name);
-	else
-		ret += fprintf(fp, "0x%0" PRIx64 "\n", chain->ip);
-
+	fputs(callchain_list__sym_name(chain, bf, sizeof(bf), false), fp);
+	fputc('\n', fp);
 	return ret;
 }
 
@@ -168,6 +166,7 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 	struct rb_node *node;
 	int i = 0;
 	int ret = 0;
+	char bf[1024];
 
 	/*
 	 * If have one single callchain root, don't bother printing
@@ -196,10 +195,8 @@ static size_t callchain__fprintf_graph(FILE *fp, struct rb_root *root,
 			} else
 				ret += callchain__fprintf_left_margin(fp, left_margin);
 
-			if (chain->ms.sym)
-				ret += fprintf(fp, " %s\n", chain->ms.sym->name);
-			else
-				ret += fprintf(fp, " %p\n", (void *)(long)chain->ip);
+			ret += fprintf(fp, "%s\n", callchain_list__sym_name(chain, bf, sizeof(bf),
+							false));
 
 			if (++entries_printed == callchain_param.print_limit)
 				break;
@@ -219,6 +216,7 @@ static size_t __callchain__fprintf_flat(FILE *fp, struct callchain_node *node,
 {
 	struct callchain_list *chain;
 	size_t ret = 0;
+	char bf[1024];
 
 	if (!node)
 		return 0;
@@ -229,11 +227,8 @@ static size_t __callchain__fprintf_flat(FILE *fp, struct callchain_node *node,
 	list_for_each_entry(chain, &node->val, list) {
 		if (chain->ip >= PERF_CONTEXT_MAX)
 			continue;
-		if (chain->ms.sym)
-			ret += fprintf(fp, "                %s\n", chain->ms.sym->name);
-		else
-			ret += fprintf(fp, "                %p\n",
-					(void *)(long)chain->ip);
+		ret += fprintf(fp, "                %s\n", callchain_list__sym_name(chain,
+					bf, sizeof(bf), false));
 	}
 
 	return ret;
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7dabde14ea54..79999ceaf2be 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -17,11 +17,13 @@
 #include "debug.h"
 #include "annotate.h"
 #include "evsel.h"
+#include <regex.h>
 #include <pthread.h>
 #include <linux/bitops.h>
 
 const char 	*disassembler_style;
 const char	*objdump_path;
+static regex_t	 file_lineno;
 
 static struct ins *ins__find(const char *name);
 static int disasm_line__parse(char *line, char **namep, char **rawp);
@@ -570,13 +572,15 @@ out_free_name:
 	return -1;
 }
 
-static struct disasm_line *disasm_line__new(s64 offset, char *line, size_t privsize)
+static struct disasm_line *disasm_line__new(s64 offset, char *line,
+					size_t privsize, int line_nr)
 {
 	struct disasm_line *dl = zalloc(sizeof(*dl) + privsize);
 
 	if (dl != NULL) {
 		dl->offset = offset;
 		dl->line = strdup(line);
+		dl->line_nr = line_nr;
 		if (dl->line == NULL)
 			goto out_delete;
 
@@ -788,13 +792,15 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
  * The ops.raw part will be parsed further according to type of the instruction.
  */
 static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
-				      FILE *file, size_t privsize)
+				      FILE *file, size_t privsize,
+				      int *line_nr)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct disasm_line *dl;
 	char *line = NULL, *parsed_line, *tmp, *tmp2, *c;
 	size_t line_len;
 	s64 line_ip, offset = -1;
+	regmatch_t match[2];
 
 	if (getline(&line, &line_len, file) < 0)
 		return -1;
@@ -812,6 +818,12 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 	line_ip = -1;
 	parsed_line = line;
 
+	/* /filename:linenr ? Save line number and ignore. */
+	if (regexec(&file_lineno, line, 2, match, 0) == 0) {
+		*line_nr = atoi(line + match[1].rm_so);
+		return 0;
+	}
+
 	/*
 	 * Strip leading spaces:
 	 */
@@ -842,8 +854,9 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 			parsed_line = tmp2 + 1;
 	}
 
-	dl = disasm_line__new(offset, parsed_line, privsize);
+	dl = disasm_line__new(offset, parsed_line, privsize, *line_nr);
 	free(line);
+	(*line_nr)++;
 
 	if (dl == NULL)
 		return -1;
@@ -869,6 +882,11 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 	return 0;
 }
 
+static __attribute__((constructor)) void symbol__init_regexpr(void)
+{
+	regcomp(&file_lineno, "^/[^:]+:([0-9]+)", REG_EXTENDED);
+}
+
 static void delete_last_nop(struct symbol *sym)
 {
 	struct annotation *notes = symbol__annotation(sym);
@@ -904,6 +922,7 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 	char symfs_filename[PATH_MAX];
 	struct kcore_extract kce;
 	bool delete_extract = false;
+	int lineno = 0;
 
 	if (filename)
 		symbol__join_symfs(symfs_filename, filename);
@@ -915,6 +934,8 @@ int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
 			return -ENOMEM;
 		}
 		goto fallback;
+	} else if (dso__is_kcore(dso)) {
+		goto fallback;
 	} else if (readlink(symfs_filename, command, sizeof(command)) < 0 ||
 		   strstr(command, "[kernel.kallsyms]") ||
 		   access(symfs_filename, R_OK)) {
@@ -982,7 +1003,7 @@ fallback:
 	snprintf(command, sizeof(command),
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
-		 " -d %s %s -C %s 2>/dev/null|grep -v %s|expand",
+		 " -l -d %s %s -C %s 2>/dev/null|grep -v %s|expand",
 		 objdump_path ? objdump_path : "objdump",
 		 disassembler_style ? "-M " : "",
 		 disassembler_style ? disassembler_style : "",
@@ -999,7 +1020,8 @@ fallback:
 		goto out_free_filename;
 
 	while (!feof(file))
-		if (symbol__parse_objdump_line(sym, map, file, privsize) < 0)
+		if (symbol__parse_objdump_line(sym, map, file, privsize,
+			    &lineno) < 0)
 			break;
 
 	/*
@@ -1170,7 +1192,7 @@ static int symbol__get_source_line(struct symbol *sym, struct map *map,
 			goto next;
 
 		offset = start + i;
-		src_line->path = get_srcline(map->dso, offset);
+		src_line->path = get_srcline(map->dso, offset, NULL, false);
 		insert_source_line(&tmp_root, src_line);
 
 	next:
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 112d6e268150..0784a9420528 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -58,6 +58,7 @@ struct disasm_line {
 	char		    *line;
 	char		    *name;
 	struct ins	    *ins;
+	int		    line_nr;
 	struct ins_operands ops;
 };
 
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index a904a4cfe7d3..e8d79e5bfaf7 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -15,6 +15,11 @@
 #include "debug.h"
 #include "session.h"
 #include "tool.h"
+#include "header.h"
+#include "vdso.h"
+
+
+static bool no_buildid_cache;
 
 int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 			   union perf_event *event,
@@ -33,8 +38,7 @@ int build_id__mark_dso_hit(struct perf_tool *tool __maybe_unused,
 		return -1;
 	}
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->ip, &al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, &al);
 
 	if (al.map != NULL)
 		al.map->dso->hit = 1;
@@ -106,3 +110,343 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size)
 			 build_id_hex, build_id_hex + 2);
 	return bf;
 }
+
+#define dsos__for_each_with_build_id(pos, head)	\
+	list_for_each_entry(pos, head, node)	\
+		if (!pos->has_build_id)		\
+			continue;		\
+		else
+
+static int write_buildid(const char *name, size_t name_len, u8 *build_id,
+			 pid_t pid, u16 misc, int fd)
+{
+	int err;
+	struct build_id_event b;
+	size_t len;
+
+	len = name_len + 1;
+	len = PERF_ALIGN(len, NAME_ALIGN);
+
+	memset(&b, 0, sizeof(b));
+	memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
+	b.pid = pid;
+	b.header.misc = misc;
+	b.header.size = sizeof(b) + len;
+
+	err = writen(fd, &b, sizeof(b));
+	if (err < 0)
+		return err;
+
+	return write_padded(fd, name, name_len + 1, len);
+}
+
+static int __dsos__write_buildid_table(struct list_head *head,
+				       struct machine *machine,
+				       pid_t pid, u16 misc, int fd)
+{
+	char nm[PATH_MAX];
+	struct dso *pos;
+
+	dsos__for_each_with_build_id(pos, head) {
+		int err;
+		const char *name;
+		size_t name_len;
+
+		if (!pos->hit)
+			continue;
+
+		if (dso__is_vdso(pos)) {
+			name = pos->short_name;
+			name_len = pos->short_name_len + 1;
+		} else if (dso__is_kcore(pos)) {
+			machine__mmap_name(machine, nm, sizeof(nm));
+			name = nm;
+			name_len = strlen(nm) + 1;
+		} else {
+			name = pos->long_name;
+			name_len = pos->long_name_len + 1;
+		}
+
+		err = write_buildid(name, name_len, pos->build_id,
+				    pid, misc, fd);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int machine__write_buildid_table(struct machine *machine, int fd)
+{
+	int err;
+	u16 kmisc = PERF_RECORD_MISC_KERNEL,
+	    umisc = PERF_RECORD_MISC_USER;
+
+	if (!machine__is_host(machine)) {
+		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+		umisc = PERF_RECORD_MISC_GUEST_USER;
+	}
+
+	err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
+					  machine->pid, kmisc, fd);
+	if (err == 0)
+		err = __dsos__write_buildid_table(&machine->user_dsos.head,
+						  machine, machine->pid, umisc,
+						  fd);
+	return err;
+}
+
+int perf_session__write_buildid_table(struct perf_session *session, int fd)
+{
+	struct rb_node *nd;
+	int err = machine__write_buildid_table(&session->machines.host, fd);
+
+	if (err)
+		return err;
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		err = machine__write_buildid_table(pos, fd);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+static int __dsos__hit_all(struct list_head *head)
+{
+	struct dso *pos;
+
+	list_for_each_entry(pos, head, node)
+		pos->hit = true;
+
+	return 0;
+}
+
+static int machine__hit_all_dsos(struct machine *machine)
+{
+	int err;
+
+	err = __dsos__hit_all(&machine->kernel_dsos.head);
+	if (err)
+		return err;
+
+	return __dsos__hit_all(&machine->user_dsos.head);
+}
+
+int dsos__hit_all(struct perf_session *session)
+{
+	struct rb_node *nd;
+	int err;
+
+	err = machine__hit_all_dsos(&session->machines.host);
+	if (err)
+		return err;
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+
+		err = machine__hit_all_dsos(pos);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+void disable_buildid_cache(void)
+{
+	no_buildid_cache = true;
+}
+
+int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
+			  const char *name, bool is_kallsyms, bool is_vdso)
+{
+	const size_t size = PATH_MAX;
+	char *realname, *filename = zalloc(size),
+	     *linkname = zalloc(size), *targetname;
+	int len, err = -1;
+	bool slash = is_kallsyms || is_vdso;
+
+	if (is_kallsyms) {
+		if (symbol_conf.kptr_restrict) {
+			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
+			err = 0;
+			goto out_free;
+		}
+		realname = (char *) name;
+	} else
+		realname = realpath(name, NULL);
+
+	if (realname == NULL || filename == NULL || linkname == NULL)
+		goto out_free;
+
+	len = scnprintf(filename, size, "%s%s%s",
+		       debugdir, slash ? "/" : "",
+		       is_vdso ? DSO__NAME_VDSO : realname);
+	if (mkdir_p(filename, 0755))
+		goto out_free;
+
+	snprintf(filename + len, size - len, "/%s", sbuild_id);
+
+	if (access(filename, F_OK)) {
+		if (is_kallsyms) {
+			 if (copyfile("/proc/kallsyms", filename))
+				goto out_free;
+		} else if (link(realname, filename) && copyfile(name, filename))
+			goto out_free;
+	}
+
+	len = scnprintf(linkname, size, "%s/.build-id/%.2s",
+		       debugdir, sbuild_id);
+
+	if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
+		goto out_free;
+
+	snprintf(linkname + len, size - len, "/%s", sbuild_id + 2);
+	targetname = filename + strlen(debugdir) - 5;
+	memcpy(targetname, "../..", 5);
+
+	if (symlink(targetname, linkname) == 0)
+		err = 0;
+out_free:
+	if (!is_kallsyms)
+		free(realname);
+	free(filename);
+	free(linkname);
+	return err;
+}
+
+static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
+				 const char *name, const char *debugdir,
+				 bool is_kallsyms, bool is_vdso)
+{
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+
+	build_id__sprintf(build_id, build_id_size, sbuild_id);
+
+	return build_id_cache__add_s(sbuild_id, debugdir, name,
+				     is_kallsyms, is_vdso);
+}
+
+int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
+{
+	const size_t size = PATH_MAX;
+	char *filename = zalloc(size),
+	     *linkname = zalloc(size);
+	int err = -1;
+
+	if (filename == NULL || linkname == NULL)
+		goto out_free;
+
+	snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+		 debugdir, sbuild_id, sbuild_id + 2);
+
+	if (access(linkname, F_OK))
+		goto out_free;
+
+	if (readlink(linkname, filename, size - 1) < 0)
+		goto out_free;
+
+	if (unlink(linkname))
+		goto out_free;
+
+	/*
+	 * Since the link is relative, we must make it absolute:
+	 */
+	snprintf(linkname, size, "%s/.build-id/%.2s/%s",
+		 debugdir, sbuild_id, filename);
+
+	if (unlink(linkname))
+		goto out_free;
+
+	err = 0;
+out_free:
+	free(filename);
+	free(linkname);
+	return err;
+}
+
+static int dso__cache_build_id(struct dso *dso, struct machine *machine,
+			       const char *debugdir)
+{
+	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
+	bool is_vdso = dso__is_vdso(dso);
+	const char *name = dso->long_name;
+	char nm[PATH_MAX];
+
+	if (dso__is_kcore(dso)) {
+		is_kallsyms = true;
+		machine__mmap_name(machine, nm, sizeof(nm));
+		name = nm;
+	}
+	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
+				     debugdir, is_kallsyms, is_vdso);
+}
+
+static int __dsos__cache_build_ids(struct list_head *head,
+				   struct machine *machine, const char *debugdir)
+{
+	struct dso *pos;
+	int err = 0;
+
+	dsos__for_each_with_build_id(pos, head)
+		if (dso__cache_build_id(pos, machine, debugdir))
+			err = -1;
+
+	return err;
+}
+
+static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
+{
+	int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine,
+					  debugdir);
+	ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine,
+				       debugdir);
+	return ret;
+}
+
+int perf_session__cache_build_ids(struct perf_session *session)
+{
+	struct rb_node *nd;
+	int ret;
+	char debugdir[PATH_MAX];
+
+	if (no_buildid_cache)
+		return 0;
+
+	snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
+
+	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
+		return -1;
+
+	ret = machine__cache_build_ids(&session->machines.host, debugdir);
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret |= machine__cache_build_ids(pos, debugdir);
+	}
+	return ret ? -1 : 0;
+}
+
+static bool machine__read_build_ids(struct machine *machine, bool with_hits)
+{
+	bool ret;
+
+	ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
+	ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
+	return ret;
+}
+
+bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
+{
+	struct rb_node *nd;
+	bool ret = machine__read_build_ids(&session->machines.host, with_hits);
+
+	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+		ret |= machine__read_build_ids(pos, with_hits);
+	}
+
+	return ret;
+}
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index ae392561470b..8236319514d5 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -15,4 +15,16 @@ char *dso__build_id_filename(const struct dso *dso, char *bf, size_t size);
 int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct perf_evsel *evsel,
 			   struct machine *machine);
+
+int dsos__hit_all(struct perf_session *session);
+
+bool perf_session__read_build_ids(struct perf_session *session, bool with_hits);
+int perf_session__write_buildid_table(struct perf_session *session, int fd);
+int perf_session__cache_build_ids(struct perf_session *session);
+
+int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
+			  const char *name, bool is_kallsyms, bool is_vdso);
+int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
+void disable_buildid_cache(void);
+
 #endif
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index c84d3f8dcb75..cf524a35cc84 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -149,6 +149,10 @@ static int parse_callchain_sort_key(const char *value)
 		callchain_param.key = CCKEY_ADDRESS;
 		return 0;
 	}
+	if (!strncmp(value, "branch", strlen(value))) {
+		callchain_param.branch_callstack = 1;
+		return 0;
+	}
 	return -1;
 }
 
@@ -754,8 +758,8 @@ int sample__resolve_callchain(struct perf_sample *sample, struct symbol **parent
 
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain ||
 	    sort__has_parent) {
-		return machine__resolve_callchain(al->machine, evsel, al->thread,
-						  sample, parent, al, max_stack);
+		return thread__resolve_callchain(al->thread, evsel, sample,
+						 parent, al, max_stack);
 	}
 	return 0;
 }
@@ -808,3 +812,32 @@ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *
 out:
 	return 1;
 }
+
+char *callchain_list__sym_name(struct callchain_list *cl,
+			       char *bf, size_t bfsize, bool show_dso)
+{
+	int printed;
+
+	if (cl->ms.sym) {
+		if (callchain_param.key == CCKEY_ADDRESS &&
+		    cl->ms.map && !cl->srcline)
+			cl->srcline = get_srcline(cl->ms.map->dso,
+						  map__rip_2objdump(cl->ms.map,
+								    cl->ip),
+						  cl->ms.sym, false);
+		if (cl->srcline)
+			printed = scnprintf(bf, bfsize, "%s %s",
+					cl->ms.sym->name, cl->srcline);
+		else
+			printed = scnprintf(bf, bfsize, "%s", cl->ms.sym->name);
+	} else
+		printed = scnprintf(bf, bfsize, "%#" PRIx64, cl->ip);
+
+	if (show_dso)
+		scnprintf(bf + printed, bfsize - printed, " %s",
+			  cl->ms.map ?
+			  cl->ms.map->dso->short_name :
+			  "unknown");
+
+	return bf;
+}
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 94cfefddf4db..dbc08cf5f970 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -63,6 +63,7 @@ struct callchain_param {
 	sort_chain_func_t	sort;
 	enum chain_order	order;
 	enum chain_key		key;
+	bool			branch_callstack;
 };
 
 extern struct callchain_param callchain_param;
@@ -70,6 +71,7 @@ extern struct callchain_param callchain_param;
 struct callchain_list {
 	u64			ip;
 	struct map_symbol	ms;
+	char		       *srcline;
 	struct list_head	list;
 };
 
@@ -184,15 +186,16 @@ static inline void callchain_cursor_snapshot(struct callchain_cursor *dest,
 }
 
 #ifdef HAVE_SKIP_CALLCHAIN_IDX
-extern int arch_skip_callchain_idx(struct machine *machine,
-			struct thread *thread, struct ip_callchain *chain);
+extern int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain);
 #else
-static inline int arch_skip_callchain_idx(struct machine *machine __maybe_unused,
-			struct thread *thread __maybe_unused,
+static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 			struct ip_callchain *chain __maybe_unused)
 {
 	return -1;
 }
 #endif
 
+char *callchain_list__sym_name(struct callchain_list *cl,
+			       char *bf, size_t bfsize, bool show_dso);
+
 #endif	/* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/comm.h b/tools/perf/util/comm.h
index 51c10ab257f8..71c9c39340d4 100644
--- a/tools/perf/util/comm.h
+++ b/tools/perf/util/comm.h
@@ -12,6 +12,10 @@ struct comm {
 	u64 start;
 	struct list_head list;
 	bool exec;
+	union { /* Tool specific area */
+		void	*priv;
+		u64	db_id;
+	};
 };
 
 void comm__free(struct comm *comm);
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
new file mode 100644
index 000000000000..c81dae399763
--- /dev/null
+++ b/tools/perf/util/db-export.c
@@ -0,0 +1,428 @@
+/*
+ * db-export.c: Support for exporting data suitable for import to a database
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ */
+
+#include <errno.h>
+
+#include "evsel.h"
+#include "machine.h"
+#include "thread.h"
+#include "comm.h"
+#include "symbol.h"
+#include "event.h"
+#include "util.h"
+#include "thread-stack.h"
+#include "db-export.h"
+
+struct deferred_export {
+	struct list_head node;
+	struct comm *comm;
+};
+
+static int db_export__deferred(struct db_export *dbe)
+{
+	struct deferred_export *de;
+	int err;
+
+	while (!list_empty(&dbe->deferred)) {
+		de = list_entry(dbe->deferred.next, struct deferred_export,
+				node);
+		err = dbe->export_comm(dbe, de->comm);
+		list_del(&de->node);
+		free(de);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static void db_export__free_deferred(struct db_export *dbe)
+{
+	struct deferred_export *de;
+
+	while (!list_empty(&dbe->deferred)) {
+		de = list_entry(dbe->deferred.next, struct deferred_export,
+				node);
+		list_del(&de->node);
+		free(de);
+	}
+}
+
+static int db_export__defer_comm(struct db_export *dbe, struct comm *comm)
+{
+	struct deferred_export *de;
+
+	de = zalloc(sizeof(struct deferred_export));
+	if (!de)
+		return -ENOMEM;
+
+	de->comm = comm;
+	list_add_tail(&de->node, &dbe->deferred);
+
+	return 0;
+}
+
+int db_export__init(struct db_export *dbe)
+{
+	memset(dbe, 0, sizeof(struct db_export));
+	INIT_LIST_HEAD(&dbe->deferred);
+	return 0;
+}
+
+int db_export__flush(struct db_export *dbe)
+{
+	return db_export__deferred(dbe);
+}
+
+void db_export__exit(struct db_export *dbe)
+{
+	db_export__free_deferred(dbe);
+	call_return_processor__free(dbe->crp);
+	dbe->crp = NULL;
+}
+
+int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel)
+{
+	if (evsel->db_id)
+		return 0;
+
+	evsel->db_id = ++dbe->evsel_last_db_id;
+
+	if (dbe->export_evsel)
+		return dbe->export_evsel(dbe, evsel);
+
+	return 0;
+}
+
+int db_export__machine(struct db_export *dbe, struct machine *machine)
+{
+	if (machine->db_id)
+		return 0;
+
+	machine->db_id = ++dbe->machine_last_db_id;
+
+	if (dbe->export_machine)
+		return dbe->export_machine(dbe, machine);
+
+	return 0;
+}
+
+int db_export__thread(struct db_export *dbe, struct thread *thread,
+		      struct machine *machine, struct comm *comm)
+{
+	u64 main_thread_db_id = 0;
+	int err;
+
+	if (thread->db_id)
+		return 0;
+
+	thread->db_id = ++dbe->thread_last_db_id;
+
+	if (thread->pid_ != -1) {
+		struct thread *main_thread;
+
+		if (thread->pid_ == thread->tid) {
+			main_thread = thread;
+		} else {
+			main_thread = machine__findnew_thread(machine,
+							      thread->pid_,
+							      thread->pid_);
+			if (!main_thread)
+				return -ENOMEM;
+			err = db_export__thread(dbe, main_thread, machine,
+						comm);
+			if (err)
+				return err;
+			if (comm) {
+				err = db_export__comm_thread(dbe, comm, thread);
+				if (err)
+					return err;
+			}
+		}
+		main_thread_db_id = main_thread->db_id;
+	}
+
+	if (dbe->export_thread)
+		return dbe->export_thread(dbe, thread, main_thread_db_id,
+					  machine);
+
+	return 0;
+}
+
+int db_export__comm(struct db_export *dbe, struct comm *comm,
+		    struct thread *main_thread)
+{
+	int err;
+
+	if (comm->db_id)
+		return 0;
+
+	comm->db_id = ++dbe->comm_last_db_id;
+
+	if (dbe->export_comm) {
+		if (main_thread->comm_set)
+			err = dbe->export_comm(dbe, comm);
+		else
+			err = db_export__defer_comm(dbe, comm);
+		if (err)
+			return err;
+	}
+
+	return db_export__comm_thread(dbe, comm, main_thread);
+}
+
+int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
+			   struct thread *thread)
+{
+	u64 db_id;
+
+	db_id = ++dbe->comm_thread_last_db_id;
+
+	if (dbe->export_comm_thread)
+		return dbe->export_comm_thread(dbe, db_id, comm, thread);
+
+	return 0;
+}
+
+int db_export__dso(struct db_export *dbe, struct dso *dso,
+		   struct machine *machine)
+{
+	if (dso->db_id)
+		return 0;
+
+	dso->db_id = ++dbe->dso_last_db_id;
+
+	if (dbe->export_dso)
+		return dbe->export_dso(dbe, dso, machine);
+
+	return 0;
+}
+
+int db_export__symbol(struct db_export *dbe, struct symbol *sym,
+		      struct dso *dso)
+{
+	u64 *sym_db_id = symbol__priv(sym);
+
+	if (*sym_db_id)
+		return 0;
+
+	*sym_db_id = ++dbe->symbol_last_db_id;
+
+	if (dbe->export_symbol)
+		return dbe->export_symbol(dbe, sym, dso);
+
+	return 0;
+}
+
+static struct thread *get_main_thread(struct machine *machine, struct thread *thread)
+{
+	if (thread->pid_ == thread->tid)
+		return thread;
+
+	if (thread->pid_ == -1)
+		return NULL;
+
+	return machine__find_thread(machine, thread->pid_, thread->pid_);
+}
+
+static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
+			  u64 *dso_db_id, u64 *sym_db_id, u64 *offset)
+{
+	int err;
+
+	if (al->map) {
+		struct dso *dso = al->map->dso;
+
+		err = db_export__dso(dbe, dso, al->machine);
+		if (err)
+			return err;
+		*dso_db_id = dso->db_id;
+
+		if (!al->sym) {
+			al->sym = symbol__new(al->addr, 0, 0, "unknown");
+			if (al->sym)
+				symbols__insert(&dso->symbols[al->map->type],
+						al->sym);
+		}
+
+		if (al->sym) {
+			u64 *db_id = symbol__priv(al->sym);
+
+			err = db_export__symbol(dbe, al->sym, dso);
+			if (err)
+				return err;
+			*sym_db_id = *db_id;
+			*offset = al->addr - al->sym->start;
+		}
+	}
+
+	return 0;
+}
+
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+			   const char *name)
+{
+	if (dbe->export_branch_type)
+		return dbe->export_branch_type(dbe, branch_type, name);
+
+	return 0;
+}
+
+int db_export__sample(struct db_export *dbe, union perf_event *event,
+		      struct perf_sample *sample, struct perf_evsel *evsel,
+		      struct thread *thread, struct addr_location *al)
+{
+	struct export_sample es = {
+		.event = event,
+		.sample = sample,
+		.evsel = evsel,
+		.thread = thread,
+		.al = al,
+	};
+	struct thread *main_thread;
+	struct comm *comm = NULL;
+	int err;
+
+	err = db_export__evsel(dbe, evsel);
+	if (err)
+		return err;
+
+	err = db_export__machine(dbe, al->machine);
+	if (err)
+		return err;
+
+	main_thread = get_main_thread(al->machine, thread);
+	if (main_thread)
+		comm = machine__thread_exec_comm(al->machine, main_thread);
+
+	err = db_export__thread(dbe, thread, al->machine, comm);
+	if (err)
+		return err;
+
+	if (comm) {
+		err = db_export__comm(dbe, comm, main_thread);
+		if (err)
+			return err;
+		es.comm_db_id = comm->db_id;
+	}
+
+	es.db_id = ++dbe->sample_last_db_id;
+
+	err = db_ids_from_al(dbe, al, &es.dso_db_id, &es.sym_db_id, &es.offset);
+	if (err)
+		return err;
+
+	if ((evsel->attr.sample_type & PERF_SAMPLE_ADDR) &&
+	    sample_addr_correlates_sym(&evsel->attr)) {
+		struct addr_location addr_al;
+
+		perf_event__preprocess_sample_addr(event, sample, thread, &addr_al);
+		err = db_ids_from_al(dbe, &addr_al, &es.addr_dso_db_id,
+				     &es.addr_sym_db_id, &es.addr_offset);
+		if (err)
+			return err;
+		if (dbe->crp) {
+			err = thread_stack__process(thread, comm, sample, al,
+						    &addr_al, es.db_id,
+						    dbe->crp);
+			if (err)
+				return err;
+		}
+	}
+
+	if (dbe->export_sample)
+		return dbe->export_sample(dbe, &es);
+
+	return 0;
+}
+
+static struct {
+	u32 branch_type;
+	const char *name;
+} branch_types[] = {
+	{0, "no branch"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "conditional jump"},
+	{PERF_IP_FLAG_BRANCH, "unconditional jump"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT,
+	 "software interrupt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT,
+	 "return from interrupt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET,
+	 "system call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET,
+	 "return from system call"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "asynchronous branch"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
+	 PERF_IP_FLAG_INTERRUPT, "hardware interrupt"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "transaction abort"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "trace begin"},
+	{PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "trace end"},
+	{0, NULL}
+};
+
+int db_export__branch_types(struct db_export *dbe)
+{
+	int i, err = 0;
+
+	for (i = 0; branch_types[i].name ; i++) {
+		err = db_export__branch_type(dbe, branch_types[i].branch_type,
+					     branch_types[i].name);
+		if (err)
+			break;
+	}
+	return err;
+}
+
+int db_export__call_path(struct db_export *dbe, struct call_path *cp)
+{
+	int err;
+
+	if (cp->db_id)
+		return 0;
+
+	if (cp->parent) {
+		err = db_export__call_path(dbe, cp->parent);
+		if (err)
+			return err;
+	}
+
+	cp->db_id = ++dbe->call_path_last_db_id;
+
+	if (dbe->export_call_path)
+		return dbe->export_call_path(dbe, cp);
+
+	return 0;
+}
+
+int db_export__call_return(struct db_export *dbe, struct call_return *cr)
+{
+	int err;
+
+	if (cr->db_id)
+		return 0;
+
+	err = db_export__call_path(dbe, cr->cp);
+	if (err)
+		return err;
+
+	cr->db_id = ++dbe->call_return_last_db_id;
+
+	if (dbe->export_call_return)
+		return dbe->export_call_return(dbe, cr);
+
+	return 0;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
new file mode 100644
index 000000000000..adbd22d66798
--- /dev/null
+++ b/tools/perf/util/db-export.h
@@ -0,0 +1,107 @@
+/*
+ * db-export.h: Support for exporting data suitable for import to a database
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ */
+
+#ifndef __PERF_DB_EXPORT_H
+#define __PERF_DB_EXPORT_H
+
+#include <linux/types.h>
+#include <linux/list.h>
+
+struct perf_evsel;
+struct machine;
+struct thread;
+struct comm;
+struct dso;
+struct perf_sample;
+struct addr_location;
+struct call_return_processor;
+struct call_path;
+struct call_return;
+
+struct export_sample {
+	union perf_event	*event;
+	struct perf_sample	*sample;
+	struct perf_evsel	*evsel;
+	struct thread		*thread;
+	struct addr_location	*al;
+	u64			db_id;
+	u64			comm_db_id;
+	u64			dso_db_id;
+	u64			sym_db_id;
+	u64			offset; /* ip offset from symbol start */
+	u64			addr_dso_db_id;
+	u64			addr_sym_db_id;
+	u64			addr_offset; /* addr offset from symbol start */
+};
+
+struct db_export {
+	int (*export_evsel)(struct db_export *dbe, struct perf_evsel *evsel);
+	int (*export_machine)(struct db_export *dbe, struct machine *machine);
+	int (*export_thread)(struct db_export *dbe, struct thread *thread,
+			     u64 main_thread_db_id, struct machine *machine);
+	int (*export_comm)(struct db_export *dbe, struct comm *comm);
+	int (*export_comm_thread)(struct db_export *dbe, u64 db_id,
+				  struct comm *comm, struct thread *thread);
+	int (*export_dso)(struct db_export *dbe, struct dso *dso,
+			  struct machine *machine);
+	int (*export_symbol)(struct db_export *dbe, struct symbol *sym,
+			     struct dso *dso);
+	int (*export_branch_type)(struct db_export *dbe, u32 branch_type,
+				  const char *name);
+	int (*export_sample)(struct db_export *dbe, struct export_sample *es);
+	int (*export_call_path)(struct db_export *dbe, struct call_path *cp);
+	int (*export_call_return)(struct db_export *dbe,
+				  struct call_return *cr);
+	struct call_return_processor *crp;
+	u64 evsel_last_db_id;
+	u64 machine_last_db_id;
+	u64 thread_last_db_id;
+	u64 comm_last_db_id;
+	u64 comm_thread_last_db_id;
+	u64 dso_last_db_id;
+	u64 symbol_last_db_id;
+	u64 sample_last_db_id;
+	u64 call_path_last_db_id;
+	u64 call_return_last_db_id;
+	struct list_head deferred;
+};
+
+int db_export__init(struct db_export *dbe);
+int db_export__flush(struct db_export *dbe);
+void db_export__exit(struct db_export *dbe);
+int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel);
+int db_export__machine(struct db_export *dbe, struct machine *machine);
+int db_export__thread(struct db_export *dbe, struct thread *thread,
+		      struct machine *machine, struct comm *comm);
+int db_export__comm(struct db_export *dbe, struct comm *comm,
+		    struct thread *main_thread);
+int db_export__comm_thread(struct db_export *dbe, struct comm *comm,
+			   struct thread *thread);
+int db_export__dso(struct db_export *dbe, struct dso *dso,
+		   struct machine *machine);
+int db_export__symbol(struct db_export *dbe, struct symbol *sym,
+		      struct dso *dso);
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+			   const char *name);
+int db_export__sample(struct db_export *dbe, union perf_event *event,
+		      struct perf_sample *sample, struct perf_evsel *evsel,
+		      struct thread *thread, struct addr_location *al);
+
+int db_export__branch_types(struct db_export *dbe);
+
+int db_export__call_path(struct db_export *dbe, struct call_path *cp);
+int db_export__call_return(struct db_export *dbe, struct call_return *cr);
+
+#endif
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index ba357f3226c6..ad60b2f20258 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -19,13 +19,14 @@
 int verbose;
 bool dump_trace = false, quiet = false;
 int debug_ordered_events;
+static int redirect_to_stderr;
 
 static int _eprintf(int level, int var, const char *fmt, va_list args)
 {
 	int ret = 0;
 
 	if (var >= level) {
-		if (use_browser >= 1)
+		if (use_browser >= 1 && !redirect_to_stderr)
 			ui_helpline__vshow(fmt, args);
 		else
 			ret = vfprintf(stderr, fmt, args);
@@ -145,6 +146,7 @@ static struct debug_variable {
 } debug_variables[] = {
 	{ .name = "verbose",		.ptr = &verbose },
 	{ .name = "ordered-events",	.ptr = &debug_ordered_events},
+	{ .name = "stderr",		.ptr = &redirect_to_stderr},
 	{ .name = NULL, }
 };
 
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 0247acfdfaca..45be944d450a 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -21,8 +21,10 @@ char dso__symtab_origin(const struct dso *dso)
 		[DSO_BINARY_TYPE__BUILDID_DEBUGINFO]		= 'b',
 		[DSO_BINARY_TYPE__SYSTEM_PATH_DSO]		= 'd',
 		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE]		= 'K',
+		[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP]	= 'm',
 		[DSO_BINARY_TYPE__GUEST_KALLSYMS]		= 'g',
 		[DSO_BINARY_TYPE__GUEST_KMODULE]		= 'G',
+		[DSO_BINARY_TYPE__GUEST_KMODULE_COMP]		= 'M',
 		[DSO_BINARY_TYPE__GUEST_VMLINUX]		= 'V',
 	};
 
@@ -112,11 +114,13 @@ int dso__read_binary_type_filename(const struct dso *dso,
 		break;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
+	case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
 		path__join3(filename, size, symbol_conf.symfs,
 			    root_dir, dso->long_name);
 		break;
 
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
 		__symbol__join_symfs(filename, size, dso->long_name);
 		break;
 
@@ -137,6 +141,73 @@ int dso__read_binary_type_filename(const struct dso *dso,
 	return ret;
 }
 
+static const struct {
+	const char *fmt;
+	int (*decompress)(const char *input, int output);
+} compressions[] = {
+#ifdef HAVE_ZLIB_SUPPORT
+	{ "gz", gzip_decompress_to_file },
+#endif
+	{ NULL, NULL },
+};
+
+bool is_supported_compression(const char *ext)
+{
+	unsigned i;
+
+	for (i = 0; compressions[i].fmt; i++) {
+		if (!strcmp(ext, compressions[i].fmt))
+			return true;
+	}
+	return false;
+}
+
+bool is_kmodule_extension(const char *ext)
+{
+	if (strncmp(ext, "ko", 2))
+		return false;
+
+	if (ext[2] == '\0' || (ext[2] == '.' && is_supported_compression(ext+3)))
+		return true;
+
+	return false;
+}
+
+bool is_kernel_module(const char *pathname, bool *compressed)
+{
+	const char *ext = strrchr(pathname, '.');
+
+	if (ext == NULL)
+		return false;
+
+	if (is_supported_compression(ext + 1)) {
+		if (compressed)
+			*compressed = true;
+		ext -= 3;
+	} else if (compressed)
+		*compressed = false;
+
+	return is_kmodule_extension(ext + 1);
+}
+
+bool decompress_to_file(const char *ext, const char *filename, int output_fd)
+{
+	unsigned i;
+
+	for (i = 0; compressions[i].fmt; i++) {
+		if (!strcmp(ext, compressions[i].fmt))
+			return !compressions[i].decompress(filename,
+							   output_fd);
+	}
+	return false;
+}
+
+bool dso__needs_decompress(struct dso *dso)
+{
+	return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
+}
+
 /*
  * Global list of open DSOs and the counter.
  */
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index acb651acc7fd..3782c82c6e44 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -22,7 +22,9 @@ enum dso_binary_type {
 	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
 	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
 	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__GUEST_KMODULE_COMP,
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP,
 	DSO_BINARY_TYPE__KCORE,
 	DSO_BINARY_TYPE__GUEST_KCORE,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
@@ -127,6 +129,7 @@ struct dso {
 	const char	 *long_name;
 	u16		 long_name_len;
 	u16		 short_name_len;
+	void		*dwfl;			/* DWARF debug info */
 
 	/* dso data file */
 	struct {
@@ -138,6 +141,11 @@ struct dso {
 		struct list_head open_entry;
 	} data;
 
+	union { /* Tool specific area */
+		void	 *priv;
+		u64	 db_id;
+	};
+
 	char		 name[0];
 };
 
@@ -179,6 +187,11 @@ int dso__kernel_module_get_build_id(struct dso *dso, const char *root_dir);
 char dso__symtab_origin(const struct dso *dso);
 int dso__read_binary_type_filename(const struct dso *dso, enum dso_binary_type type,
 				   char *root_dir, char *filename, size_t size);
+bool is_supported_compression(const char *ext);
+bool is_kmodule_extension(const char *ext);
+bool is_kernel_module(const char *pathname, bool *compressed);
+bool decompress_to_file(const char *ext, const char *filename, int output_fd);
+bool dso__needs_decompress(struct dso *dso);
 
 /*
  * The dso__data_* external interface provides following functions:
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 4af6b279e34a..6c6d044e959a 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -28,6 +28,7 @@ static const char *perf_event__names[] = {
 	[PERF_RECORD_HEADER_TRACING_DATA]	= "TRACING_DATA",
 	[PERF_RECORD_HEADER_BUILD_ID]		= "BUILD_ID",
 	[PERF_RECORD_FINISHED_ROUND]		= "FINISHED_ROUND",
+	[PERF_RECORD_ID_INDEX]			= "ID_INDEX",
 };
 
 const char *perf_event__name(unsigned int id)
@@ -730,12 +731,12 @@ int perf_event__process(struct perf_tool *tool __maybe_unused,
 	return machine__process_event(machine, event, sample);
 }
 
-void thread__find_addr_map(struct thread *thread,
-			   struct machine *machine, u8 cpumode,
+void thread__find_addr_map(struct thread *thread, u8 cpumode,
 			   enum map_type type, u64 addr,
 			   struct addr_location *al)
 {
 	struct map_groups *mg = thread->mg;
+	struct machine *machine = mg->machine;
 	bool load_map = false;
 
 	al->machine = machine;
@@ -806,14 +807,14 @@ try_again:
 	}
 }
 
-void thread__find_addr_location(struct thread *thread, struct machine *machine,
+void thread__find_addr_location(struct thread *thread,
 				u8 cpumode, enum map_type type, u64 addr,
 				struct addr_location *al)
 {
-	thread__find_addr_map(thread, machine, cpumode, type, addr, al);
+	thread__find_addr_map(thread, cpumode, type, addr, al);
 	if (al->map != NULL)
 		al->sym = map__find_symbol(al->map, al->addr,
-					   machine->symbol_filter);
+					   thread->mg->machine->symbol_filter);
 	else
 		al->sym = NULL;
 }
@@ -842,8 +843,7 @@ int perf_event__preprocess_sample(const union perf_event *event,
 	    machine->vmlinux_maps[MAP__FUNCTION] == NULL)
 		machine__create_kernel_maps(machine);
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->ip, al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
 			al->level == 'H' ? "[hypervisor]" : "<not found>");
@@ -902,16 +902,14 @@ bool sample_addr_correlates_sym(struct perf_event_attr *attr)
 
 void perf_event__preprocess_sample_addr(union perf_event *event,
 					struct perf_sample *sample,
-					struct machine *machine,
 					struct thread *thread,
 					struct addr_location *al)
 {
 	u8 cpumode = event->header.misc & PERF_RECORD_MISC_CPUMODE_MASK;
 
-	thread__find_addr_map(thread, machine, cpumode, MAP__FUNCTION,
-			      sample->addr, al);
+	thread__find_addr_map(thread, cpumode, MAP__FUNCTION, sample->addr, al);
 	if (!al->map)
-		thread__find_addr_map(thread, machine, cpumode, MAP__VARIABLE,
+		thread__find_addr_map(thread, cpumode, MAP__VARIABLE,
 				      sample->addr, al);
 
 	al->cpu = sample->cpu;
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 5699e7e2a790..09b9e8d3fcf7 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -143,6 +143,32 @@ struct branch_stack {
 	struct branch_entry	entries[0];
 };
 
+enum {
+	PERF_IP_FLAG_BRANCH		= 1ULL << 0,
+	PERF_IP_FLAG_CALL		= 1ULL << 1,
+	PERF_IP_FLAG_RETURN		= 1ULL << 2,
+	PERF_IP_FLAG_CONDITIONAL	= 1ULL << 3,
+	PERF_IP_FLAG_SYSCALLRET		= 1ULL << 4,
+	PERF_IP_FLAG_ASYNC		= 1ULL << 5,
+	PERF_IP_FLAG_INTERRUPT		= 1ULL << 6,
+	PERF_IP_FLAG_TX_ABORT		= 1ULL << 7,
+	PERF_IP_FLAG_TRACE_BEGIN	= 1ULL << 8,
+	PERF_IP_FLAG_TRACE_END		= 1ULL << 9,
+	PERF_IP_FLAG_IN_TX		= 1ULL << 10,
+};
+
+#define PERF_BRANCH_MASK		(\
+	PERF_IP_FLAG_BRANCH		|\
+	PERF_IP_FLAG_CALL		|\
+	PERF_IP_FLAG_RETURN		|\
+	PERF_IP_FLAG_CONDITIONAL	|\
+	PERF_IP_FLAG_SYSCALLRET		|\
+	PERF_IP_FLAG_ASYNC		|\
+	PERF_IP_FLAG_INTERRUPT		|\
+	PERF_IP_FLAG_TX_ABORT		|\
+	PERF_IP_FLAG_TRACE_BEGIN	|\
+	PERF_IP_FLAG_TRACE_END)
+
 struct perf_sample {
 	u64 ip;
 	u32 pid, tid;
@@ -162,6 +188,7 @@ struct perf_sample {
 	struct ip_callchain *callchain;
 	struct branch_stack *branch_stack;
 	struct regs_dump  user_regs;
+	struct regs_dump  intr_regs;
 	struct stack_dump user_stack;
 	struct sample_read read;
 };
@@ -187,6 +214,7 @@ enum perf_user_event_type { /* above any possible kernel type */
 	PERF_RECORD_HEADER_TRACING_DATA		= 66,
 	PERF_RECORD_HEADER_BUILD_ID		= 67,
 	PERF_RECORD_FINISHED_ROUND		= 68,
+	PERF_RECORD_ID_INDEX			= 69,
 	PERF_RECORD_HEADER_MAX
 };
 
@@ -239,6 +267,19 @@ struct tracing_data_event {
 	u32 size;
 };
 
+struct id_index_entry {
+	u64 id;
+	u64 idx;
+	u64 cpu;
+	u64 tid;
+};
+
+struct id_index_event {
+	struct perf_event_header header;
+	u64 nr;
+	struct id_index_entry entries[0];
+};
+
 union perf_event {
 	struct perf_event_header	header;
 	struct mmap_event		mmap;
@@ -253,6 +294,7 @@ union perf_event {
 	struct event_type_event		event_type;
 	struct tracing_data_event	tracing_data;
 	struct build_id_event		build_id;
+	struct id_index_event		id_index;
 };
 
 void perf_event__print_totals(void);
@@ -322,7 +364,6 @@ bool is_bts_event(struct perf_event_attr *attr);
 bool sample_addr_correlates_sym(struct perf_event_attr *attr);
 void perf_event__preprocess_sample_addr(union perf_event *event,
 					struct perf_sample *sample,
-					struct machine *machine,
 					struct thread *thread,
 					struct addr_location *al);
 
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 3c9e77d6b4c2..cfbe2b99b9aa 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -413,7 +413,7 @@ int perf_evlist__alloc_pollfd(struct perf_evlist *evlist)
 	int nfds = 0;
 	struct perf_evsel *evsel;
 
-	list_for_each_entry(evsel, &evlist->entries, node) {
+	evlist__for_each(evlist, evsel) {
 		if (evsel->system_wide)
 			nfds += nr_cpus;
 		else
@@ -527,6 +527,22 @@ static int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 	return 0;
 }
 
+static void perf_evlist__set_sid_idx(struct perf_evlist *evlist,
+				     struct perf_evsel *evsel, int idx, int cpu,
+				     int thread)
+{
+	struct perf_sample_id *sid = SID(evsel, cpu, thread);
+	sid->idx = idx;
+	if (evlist->cpus && cpu >= 0)
+		sid->cpu = evlist->cpus->map[cpu];
+	else
+		sid->cpu = -1;
+	if (!evsel->system_wide && evlist->threads && thread >= 0)
+		sid->tid = evlist->threads->map[thread];
+	else
+		sid->tid = -1;
+}
+
 struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id)
 {
 	struct hlist_head *head;
@@ -800,14 +816,26 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 			perf_evlist__mmap_get(evlist, idx);
 		}
 
-		if (__perf_evlist__add_pollfd(evlist, fd, idx) < 0) {
+		/*
+		 * The system_wide flag causes a selected event to be opened
+		 * always without a pid.  Consequently it will never get a
+		 * POLLHUP, but it is used for tracking in combination with
+		 * other events, so it should not need to be polled anyway.
+		 * Therefore don't add it for polling.
+		 */
+		if (!evsel->system_wide &&
+		    __perf_evlist__add_pollfd(evlist, fd, idx) < 0) {
 			perf_evlist__mmap_put(evlist, idx);
 			return -1;
 		}
 
-		if ((evsel->attr.read_format & PERF_FORMAT_ID) &&
-		    perf_evlist__id_add_fd(evlist, evsel, cpu, thread, fd) < 0)
-			return -1;
+		if (evsel->attr.read_format & PERF_FORMAT_ID) {
+			if (perf_evlist__id_add_fd(evlist, evsel, cpu, thread,
+						   fd) < 0)
+				return -1;
+			perf_evlist__set_sid_idx(evlist, evsel, idx, cpu,
+						 thread);
+		}
 	}
 
 	return 0;
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 2f9e68025ede..1e90c8557ede 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -658,9 +658,22 @@ void perf_evsel__config(struct perf_evsel *evsel, struct record_opts *opts)
 		attr->mmap_data = track;
 	}
 
+	/*
+	 * We don't allow user space callchains for  function trace
+	 * event, due to issues with page faults while tracing page
+	 * fault handler and its overall trickiness nature.
+	 */
+	if (perf_evsel__is_function_event(evsel))
+		evsel->attr.exclude_callchain_user = 1;
+
 	if (callchain_param.enabled && !evsel->no_aux_samples)
 		perf_evsel__config_callgraph(evsel);
 
+	if (opts->sample_intr_regs) {
+		attr->sample_regs_intr = PERF_REGS_MASK;
+		perf_evsel__set_sample_bit(evsel, REGS_INTR);
+	}
+
 	if (target__has_cpu(&opts->target))
 		perf_evsel__set_sample_bit(evsel, CPU);
 
@@ -853,8 +866,6 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	perf_evsel__free_id(evsel);
 	close_cgroup(evsel->cgrp);
 	zfree(&evsel->group_name);
-	if (evsel->tp_format)
-		pevent_free_format(evsel->tp_format);
 	zfree(&evsel->name);
 	perf_evsel__object.fini(evsel);
 }
@@ -865,9 +876,8 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-static inline void compute_deltas(struct perf_evsel *evsel,
-				  int cpu,
-				  struct perf_counts_values *count)
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+				struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
 
@@ -887,6 +897,42 @@ static inline void compute_deltas(struct perf_evsel *evsel,
 	count->run = count->run - tmp.run;
 }
 
+void perf_counts_values__scale(struct perf_counts_values *count,
+			       bool scale, s8 *pscaled)
+{
+	s8 scaled = 0;
+
+	if (scale) {
+		if (count->run == 0) {
+			scaled = -1;
+			count->val = 0;
+		} else if (count->run < count->ena) {
+			scaled = 1;
+			count->val = (u64)((double) count->val * count->ena / count->run + 0.5);
+		}
+	} else
+		count->ena = count->run = 0;
+
+	if (pscaled)
+		*pscaled = scaled;
+}
+
+int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
+			perf_evsel__read_cb_t cb)
+{
+	struct perf_counts_values count;
+
+	memset(&count, 0, sizeof(count));
+
+	if (FD(evsel, cpu, thread) < 0)
+		return -EINVAL;
+
+	if (readn(FD(evsel, cpu, thread), &count, sizeof(count)) < 0)
+		return -errno;
+
+	return cb(evsel, cpu, thread, &count);
+}
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale)
 {
@@ -902,69 +948,12 @@ int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) < 0)
 		return -errno;
 
-	compute_deltas(evsel, cpu, &count);
-
-	if (scale) {
-		if (count.run == 0)
-			count.val = 0;
-		else if (count.run < count.ena)
-			count.val = (u64)((double)count.val * count.ena / count.run + 0.5);
-	} else
-		count.ena = count.run = 0;
-
+	perf_evsel__compute_deltas(evsel, cpu, &count);
+	perf_counts_values__scale(&count, scale, NULL);
 	evsel->counts->cpu[cpu] = count;
 	return 0;
 }
 
-int __perf_evsel__read(struct perf_evsel *evsel,
-		       int ncpus, int nthreads, bool scale)
-{
-	size_t nv = scale ? 3 : 1;
-	int cpu, thread;
-	struct perf_counts_values *aggr = &evsel->counts->aggr, count;
-
-	if (evsel->system_wide)
-		nthreads = 1;
-
-	aggr->val = aggr->ena = aggr->run = 0;
-
-	for (cpu = 0; cpu < ncpus; cpu++) {
-		for (thread = 0; thread < nthreads; thread++) {
-			if (FD(evsel, cpu, thread) < 0)
-				continue;
-
-			if (readn(FD(evsel, cpu, thread),
-				  &count, nv * sizeof(u64)) < 0)
-				return -errno;
-
-			aggr->val += count.val;
-			if (scale) {
-				aggr->ena += count.ena;
-				aggr->run += count.run;
-			}
-		}
-	}
-
-	compute_deltas(evsel, -1, aggr);
-
-	evsel->counts->scaled = 0;
-	if (scale) {
-		if (aggr->run == 0) {
-			evsel->counts->scaled = -1;
-			aggr->val = 0;
-			return 0;
-		}
-
-		if (aggr->run < aggr->ena) {
-			evsel->counts->scaled = 1;
-			aggr->val = (u64)((double)aggr->val * aggr->ena / aggr->run + 0.5);
-		}
-	} else
-		aggr->ena = aggr->run = 0;
-
-	return 0;
-}
-
 static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread)
 {
 	struct perf_evsel *leader = evsel->leader;
@@ -1039,6 +1028,7 @@ static size_t perf_event_attr__fprintf(struct perf_event_attr *attr, FILE *fp)
 	ret += PRINT_ATTR_X64(branch_sample_type);
 	ret += PRINT_ATTR_X64(sample_regs_user);
 	ret += PRINT_ATTR_U32(sample_stack_user);
+	ret += PRINT_ATTR_X64(sample_regs_intr);
 
 	ret += fprintf(fp, "%.60s\n", graph_dotted_line);
 
@@ -1538,6 +1528,23 @@ int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 		array++;
 	}
 
+	data->intr_regs.abi = PERF_SAMPLE_REGS_ABI_NONE;
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		OVERFLOW_CHECK_u64(array);
+		data->intr_regs.abi = *array;
+		array++;
+
+		if (data->intr_regs.abi != PERF_SAMPLE_REGS_ABI_NONE) {
+			u64 mask = evsel->attr.sample_regs_intr;
+
+			sz = hweight_long(mask) * sizeof(u64);
+			OVERFLOW_CHECK(array, sz, max_size);
+			data->intr_regs.mask = mask;
+			data->intr_regs.regs = (u64 *)array;
+			array = (void *)array + sz;
+		}
+	}
+
 	return 0;
 }
 
@@ -1633,6 +1640,16 @@ size_t perf_event__sample_event_size(const struct perf_sample *sample, u64 type,
 	if (type & PERF_SAMPLE_TRANSACTION)
 		result += sizeof(u64);
 
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		if (sample->intr_regs.abi) {
+			result += sizeof(u64);
+			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			result += sz;
+		} else {
+			result += sizeof(u64);
+		}
+	}
+
 	return result;
 }
 
@@ -1811,6 +1828,17 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type,
 		array++;
 	}
 
+	if (type & PERF_SAMPLE_REGS_INTR) {
+		if (sample->intr_regs.abi) {
+			*array++ = sample->intr_regs.abi;
+			sz = hweight_long(sample->intr_regs.mask) * sizeof(u64);
+			memcpy(array, sample->intr_regs.regs, sz);
+			array = (void *)array + sz;
+		} else {
+			*array++ = 0;
+		}
+	}
+
 	return 0;
 }
 
@@ -1940,7 +1968,7 @@ static int sample_type__fprintf(FILE *fp, bool *first, u64 value)
 		bit_name(READ), bit_name(CALLCHAIN), bit_name(ID), bit_name(CPU),
 		bit_name(PERIOD), bit_name(STREAM_ID), bit_name(RAW),
 		bit_name(BRANCH_STACK), bit_name(REGS_USER), bit_name(STACK_USER),
-		bit_name(IDENTIFIER),
+		bit_name(IDENTIFIER), bit_name(REGS_INTR),
 		{ .name = NULL, }
 	};
 #undef bit_name
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 163c5604e5d1..38622747d130 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -36,6 +36,9 @@ struct perf_sample_id {
 	struct hlist_node 	node;
 	u64		 	id;
 	struct perf_evsel	*evsel;
+	int			idx;
+	int			cpu;
+	pid_t			tid;
 
 	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
 	u64			period;
@@ -54,6 +57,7 @@ struct cgroup_sel;
  * @is_pos: the position (counting backwards) of the event id (PERF_SAMPLE_ID or
  *          PERF_SAMPLE_IDENTIFIER) in a non-sample event i.e. if sample_id_all
  *          is used there is an id sample appended to non-sample events
+ * @priv:   And what is in its containing unnamed union are tool specific
  */
 struct perf_evsel {
 	struct list_head	node;
@@ -69,10 +73,12 @@ struct perf_evsel {
 	char			*name;
 	double			scale;
 	const char		*unit;
+	bool			snapshot;
 	struct event_format	*tp_format;
 	union {
 		void		*priv;
 		off_t		id_offset;
+		u64		db_id;
 	};
 	struct cgroup_sel	*cgrp;
 	void			*handler;
@@ -86,6 +92,8 @@ struct perf_evsel {
 	bool			immediate;
 	bool			system_wide;
 	bool			tracking;
+	bool			per_pkg;
+	unsigned long		*per_pkg_mask;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
@@ -105,6 +113,12 @@ struct thread_map;
 struct perf_evlist;
 struct record_opts;
 
+void perf_counts_values__scale(struct perf_counts_values *count,
+			       bool scale, s8 *pscaled);
+
+void perf_evsel__compute_deltas(struct perf_evsel *evsel, int cpu,
+				struct perf_counts_values *count);
+
 int perf_evsel__object_config(size_t object_size,
 			      int (*init)(struct perf_evsel *evsel),
 			      void (*fini)(struct perf_evsel *evsel));
@@ -222,6 +236,13 @@ static inline bool perf_evsel__match2(struct perf_evsel *e1,
 	 (a)->attr.type == (b)->attr.type &&	\
 	 (a)->attr.config == (b)->attr.config)
 
+typedef int (perf_evsel__read_cb_t)(struct perf_evsel *evsel,
+				    int cpu, int thread,
+				    struct perf_counts_values *count);
+
+int perf_evsel__read_cb(struct perf_evsel *evsel, int cpu, int thread,
+			perf_evsel__read_cb_t cb);
+
 int __perf_evsel__read_on_cpu(struct perf_evsel *evsel,
 			      int cpu, int thread, bool scale);
 
@@ -251,35 +272,6 @@ static inline int perf_evsel__read_on_cpu_scaled(struct perf_evsel *evsel,
 	return __perf_evsel__read_on_cpu(evsel, cpu, thread, true);
 }
 
-int __perf_evsel__read(struct perf_evsel *evsel, int ncpus, int nthreads,
-		       bool scale);
-
-/**
- * perf_evsel__read - Read the aggregate results on all CPUs
- *
- * @evsel - event selector to read value
- * @ncpus - Number of cpus affected, from zero
- * @nthreads - Number of threads affected, from zero
- */
-static inline int perf_evsel__read(struct perf_evsel *evsel,
-				    int ncpus, int nthreads)
-{
-	return __perf_evsel__read(evsel, ncpus, nthreads, false);
-}
-
-/**
- * perf_evsel__read_scaled - Read the aggregate results on all CPUs, scaled
- *
- * @evsel - event selector to read value
- * @ncpus - Number of cpus affected, from zero
- * @nthreads - Number of threads affected, from zero
- */
-static inline int perf_evsel__read_scaled(struct perf_evsel *evsel,
-					  int ncpus, int nthreads)
-{
-	return __perf_evsel__read(evsel, ncpus, nthreads, true);
-}
-
 int perf_evsel__parse_sample(struct perf_evsel *evsel, union perf_event *event,
 			     struct perf_sample *sample);
 
diff --git a/tools/perf/util/find-vdso-map.c b/tools/perf/util/find-vdso-map.c
new file mode 100644
index 000000000000..95ef1cffc056
--- /dev/null
+++ b/tools/perf/util/find-vdso-map.c
@@ -0,0 +1,30 @@
+static int find_vdso_map(void **start, void **end)
+{
+	FILE *maps;
+	char line[128];
+	int found = 0;
+
+	maps = fopen("/proc/self/maps", "r");
+	if (!maps) {
+		fprintf(stderr, "vdso: cannot open maps\n");
+		return -1;
+	}
+
+	while (!found && fgets(line, sizeof(line), maps)) {
+		int m = -1;
+
+		/* We care only about private r-x mappings. */
+		if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
+				start, end, &m))
+			continue;
+		if (m < 0)
+			continue;
+
+		if (!strncmp(&line[m], VDSO__MAP_NAME,
+			     sizeof(VDSO__MAP_NAME) - 1))
+			found = 1;
+	}
+
+	fclose(maps);
+	return !found;
+}
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index 26f5b2fe5dc8..b20e40c74468 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -24,8 +24,6 @@
 #include "build-id.h"
 #include "data.h"
 
-static bool no_buildid_cache = false;
-
 static u32 header_argc;
 static const char **header_argv;
 
@@ -79,10 +77,7 @@ static int do_write(int fd, const void *buf, size_t size)
 	return 0;
 }
 
-#define NAME_ALIGN 64
-
-static int write_padded(int fd, const void *bf, size_t count,
-			size_t count_aligned)
+int write_padded(int fd, const void *bf, size_t count, size_t count_aligned)
 {
 	static const char zero_buf[NAME_ALIGN];
 	int err = do_write(fd, bf, count);
@@ -171,340 +166,6 @@ perf_header__set_cmdline(int argc, const char **argv)
 	return 0;
 }
 
-#define dsos__for_each_with_build_id(pos, head)	\
-	list_for_each_entry(pos, head, node)	\
-		if (!pos->has_build_id)		\
-			continue;		\
-		else
-
-static int write_buildid(const char *name, size_t name_len, u8 *build_id,
-			 pid_t pid, u16 misc, int fd)
-{
-	int err;
-	struct build_id_event b;
-	size_t len;
-
-	len = name_len + 1;
-	len = PERF_ALIGN(len, NAME_ALIGN);
-
-	memset(&b, 0, sizeof(b));
-	memcpy(&b.build_id, build_id, BUILD_ID_SIZE);
-	b.pid = pid;
-	b.header.misc = misc;
-	b.header.size = sizeof(b) + len;
-
-	err = do_write(fd, &b, sizeof(b));
-	if (err < 0)
-		return err;
-
-	return write_padded(fd, name, name_len + 1, len);
-}
-
-static int __dsos__hit_all(struct list_head *head)
-{
-	struct dso *pos;
-
-	list_for_each_entry(pos, head, node)
-		pos->hit = true;
-
-	return 0;
-}
-
-static int machine__hit_all_dsos(struct machine *machine)
-{
-	int err;
-
-	err = __dsos__hit_all(&machine->kernel_dsos.head);
-	if (err)
-		return err;
-
-	return __dsos__hit_all(&machine->user_dsos.head);
-}
-
-int dsos__hit_all(struct perf_session *session)
-{
-	struct rb_node *nd;
-	int err;
-
-	err = machine__hit_all_dsos(&session->machines.host);
-	if (err)
-		return err;
-
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-
-		err = machine__hit_all_dsos(pos);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int __dsos__write_buildid_table(struct list_head *head,
-				       struct machine *machine,
-				       pid_t pid, u16 misc, int fd)
-{
-	char nm[PATH_MAX];
-	struct dso *pos;
-
-	dsos__for_each_with_build_id(pos, head) {
-		int err;
-		const char *name;
-		size_t name_len;
-
-		if (!pos->hit)
-			continue;
-
-		if (dso__is_vdso(pos)) {
-			name = pos->short_name;
-			name_len = pos->short_name_len + 1;
-		} else if (dso__is_kcore(pos)) {
-			machine__mmap_name(machine, nm, sizeof(nm));
-			name = nm;
-			name_len = strlen(nm) + 1;
-		} else {
-			name = pos->long_name;
-			name_len = pos->long_name_len + 1;
-		}
-
-		err = write_buildid(name, name_len, pos->build_id,
-				    pid, misc, fd);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
-static int machine__write_buildid_table(struct machine *machine, int fd)
-{
-	int err;
-	u16 kmisc = PERF_RECORD_MISC_KERNEL,
-	    umisc = PERF_RECORD_MISC_USER;
-
-	if (!machine__is_host(machine)) {
-		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
-		umisc = PERF_RECORD_MISC_GUEST_USER;
-	}
-
-	err = __dsos__write_buildid_table(&machine->kernel_dsos.head, machine,
-					  machine->pid, kmisc, fd);
-	if (err == 0)
-		err = __dsos__write_buildid_table(&machine->user_dsos.head,
-						  machine, machine->pid, umisc,
-						  fd);
-	return err;
-}
-
-static int dsos__write_buildid_table(struct perf_header *header, int fd)
-{
-	struct perf_session *session = container_of(header,
-			struct perf_session, header);
-	struct rb_node *nd;
-	int err = machine__write_buildid_table(&session->machines.host, fd);
-
-	if (err)
-		return err;
-
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		err = machine__write_buildid_table(pos, fd);
-		if (err)
-			break;
-	}
-	return err;
-}
-
-int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-			  const char *name, bool is_kallsyms, bool is_vdso)
-{
-	const size_t size = PATH_MAX;
-	char *realname, *filename = zalloc(size),
-	     *linkname = zalloc(size), *targetname;
-	int len, err = -1;
-	bool slash = is_kallsyms || is_vdso;
-
-	if (is_kallsyms) {
-		if (symbol_conf.kptr_restrict) {
-			pr_debug("Not caching a kptr_restrict'ed /proc/kallsyms\n");
-			err = 0;
-			goto out_free;
-		}
-		realname = (char *) name;
-	} else
-		realname = realpath(name, NULL);
-
-	if (realname == NULL || filename == NULL || linkname == NULL)
-		goto out_free;
-
-	len = scnprintf(filename, size, "%s%s%s",
-		       debugdir, slash ? "/" : "",
-		       is_vdso ? DSO__NAME_VDSO : realname);
-	if (mkdir_p(filename, 0755))
-		goto out_free;
-
-	snprintf(filename + len, size - len, "/%s", sbuild_id);
-
-	if (access(filename, F_OK)) {
-		if (is_kallsyms) {
-			 if (copyfile("/proc/kallsyms", filename))
-				goto out_free;
-		} else if (link(realname, filename) && copyfile(name, filename))
-			goto out_free;
-	}
-
-	len = scnprintf(linkname, size, "%s/.build-id/%.2s",
-		       debugdir, sbuild_id);
-
-	if (access(linkname, X_OK) && mkdir_p(linkname, 0755))
-		goto out_free;
-
-	snprintf(linkname + len, size - len, "/%s", sbuild_id + 2);
-	targetname = filename + strlen(debugdir) - 5;
-	memcpy(targetname, "../..", 5);
-
-	if (symlink(targetname, linkname) == 0)
-		err = 0;
-out_free:
-	if (!is_kallsyms)
-		free(realname);
-	free(filename);
-	free(linkname);
-	return err;
-}
-
-static int build_id_cache__add_b(const u8 *build_id, size_t build_id_size,
-				 const char *name, const char *debugdir,
-				 bool is_kallsyms, bool is_vdso)
-{
-	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
-
-	build_id__sprintf(build_id, build_id_size, sbuild_id);
-
-	return build_id_cache__add_s(sbuild_id, debugdir, name,
-				     is_kallsyms, is_vdso);
-}
-
-int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir)
-{
-	const size_t size = PATH_MAX;
-	char *filename = zalloc(size),
-	     *linkname = zalloc(size);
-	int err = -1;
-
-	if (filename == NULL || linkname == NULL)
-		goto out_free;
-
-	snprintf(linkname, size, "%s/.build-id/%.2s/%s",
-		 debugdir, sbuild_id, sbuild_id + 2);
-
-	if (access(linkname, F_OK))
-		goto out_free;
-
-	if (readlink(linkname, filename, size - 1) < 0)
-		goto out_free;
-
-	if (unlink(linkname))
-		goto out_free;
-
-	/*
-	 * Since the link is relative, we must make it absolute:
-	 */
-	snprintf(linkname, size, "%s/.build-id/%.2s/%s",
-		 debugdir, sbuild_id, filename);
-
-	if (unlink(linkname))
-		goto out_free;
-
-	err = 0;
-out_free:
-	free(filename);
-	free(linkname);
-	return err;
-}
-
-static int dso__cache_build_id(struct dso *dso, struct machine *machine,
-			       const char *debugdir)
-{
-	bool is_kallsyms = dso->kernel && dso->long_name[0] != '/';
-	bool is_vdso = dso__is_vdso(dso);
-	const char *name = dso->long_name;
-	char nm[PATH_MAX];
-
-	if (dso__is_kcore(dso)) {
-		is_kallsyms = true;
-		machine__mmap_name(machine, nm, sizeof(nm));
-		name = nm;
-	}
-	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
-				     debugdir, is_kallsyms, is_vdso);
-}
-
-static int __dsos__cache_build_ids(struct list_head *head,
-				   struct machine *machine, const char *debugdir)
-{
-	struct dso *pos;
-	int err = 0;
-
-	dsos__for_each_with_build_id(pos, head)
-		if (dso__cache_build_id(pos, machine, debugdir))
-			err = -1;
-
-	return err;
-}
-
-static int machine__cache_build_ids(struct machine *machine, const char *debugdir)
-{
-	int ret = __dsos__cache_build_ids(&machine->kernel_dsos.head, machine,
-					  debugdir);
-	ret |= __dsos__cache_build_ids(&machine->user_dsos.head, machine,
-				       debugdir);
-	return ret;
-}
-
-static int perf_session__cache_build_ids(struct perf_session *session)
-{
-	struct rb_node *nd;
-	int ret;
-	char debugdir[PATH_MAX];
-
-	snprintf(debugdir, sizeof(debugdir), "%s", buildid_dir);
-
-	if (mkdir(debugdir, 0755) != 0 && errno != EEXIST)
-		return -1;
-
-	ret = machine__cache_build_ids(&session->machines.host, debugdir);
-
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret |= machine__cache_build_ids(pos, debugdir);
-	}
-	return ret ? -1 : 0;
-}
-
-static bool machine__read_build_ids(struct machine *machine, bool with_hits)
-{
-	bool ret;
-
-	ret  = __dsos__read_build_ids(&machine->kernel_dsos.head, with_hits);
-	ret |= __dsos__read_build_ids(&machine->user_dsos.head, with_hits);
-	return ret;
-}
-
-static bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
-{
-	struct rb_node *nd;
-	bool ret = machine__read_build_ids(&session->machines.host, with_hits);
-
-	for (nd = rb_first(&session->machines.guests); nd; nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret |= machine__read_build_ids(pos, with_hits);
-	}
-
-	return ret;
-}
-
 static int write_tracing_data(int fd, struct perf_header *h __maybe_unused,
 			    struct perf_evlist *evlist)
 {
@@ -523,13 +184,12 @@ static int write_build_id(int fd, struct perf_header *h,
 	if (!perf_session__read_build_ids(session, true))
 		return -1;
 
-	err = dsos__write_buildid_table(h, fd);
+	err = perf_session__write_buildid_table(session, fd);
 	if (err < 0) {
 		pr_debug("failed to write buildid table\n");
 		return err;
 	}
-	if (!no_buildid_cache)
-		perf_session__cache_build_ids(session);
+	perf_session__cache_build_ids(session);
 
 	return 0;
 }
@@ -601,8 +261,10 @@ static int __write_cpudesc(int fd, const char *cpuinfo_proc)
 			break;
 	}
 
-	if (ret)
+	if (ret) {
+		ret = -1;
 		goto done;
+	}
 
 	s = buf;
 
@@ -965,7 +627,8 @@ static int write_total_mem(int fd, struct perf_header *h __maybe_unused,
 		n = sscanf(buf, "%*s %"PRIu64, &mem);
 		if (n == 1)
 			ret = do_write(fd, &mem, sizeof(mem));
-	}
+	} else
+		ret = -1;
 	free(buf);
 	fclose(fp);
 	return ret;
@@ -1603,7 +1266,7 @@ static int __event_process_build_id(struct build_id_event *bev,
 
 		dso__set_build_id(dso, &bev->build_id);
 
-		if (filename[0] == '[')
+		if (!is_kernel_module(filename, NULL))
 			dso->kernel = dso_type;
 
 		build_id__sprintf(dso->build_id, sizeof(dso->build_id),
@@ -2477,6 +2140,7 @@ static const int attr_file_abi_sizes[] = {
 	[1] = PERF_ATTR_SIZE_VER1,
 	[2] = PERF_ATTR_SIZE_VER2,
 	[3] = PERF_ATTR_SIZE_VER3,
+	[4] = PERF_ATTR_SIZE_VER4,
 	0,
 };
 
@@ -3124,8 +2788,3 @@ int perf_event__process_build_id(struct perf_tool *tool __maybe_unused,
 				 session);
 	return 0;
 }
-
-void disable_buildid_cache(void)
-{
-	no_buildid_cache = true;
-}
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index 8f5cbaea64a5..3bb90ac172a1 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -122,10 +122,6 @@ int perf_header__process_sections(struct perf_header *header, int fd,
 
 int perf_header__fprintf_info(struct perf_session *s, FILE *fp, bool full);
 
-int build_id_cache__add_s(const char *sbuild_id, const char *debugdir,
-			  const char *name, bool is_kallsyms, bool is_vdso);
-int build_id_cache__remove_s(const char *sbuild_id, const char *debugdir);
-
 int perf_event__synthesize_attr(struct perf_tool *tool,
 				struct perf_event_attr *attr, u32 ids, u64 *id,
 				perf_event__handler_t process);
@@ -151,7 +147,9 @@ int perf_event__process_build_id(struct perf_tool *tool,
 				 struct perf_session *session);
 bool is_perf_magic(u64 magic);
 
-int dsos__hit_all(struct perf_session *session);
+#define NAME_ALIGN 64
+
+int write_padded(int fd, const void *bf, size_t count, size_t count_aligned);
 
 /*
  * arch specific callback
diff --git a/tools/perf/util/include/linux/bitmap.h b/tools/perf/util/include/linux/bitmap.h
index 01ffd12dc791..40bd21488032 100644
--- a/tools/perf/util/include/linux/bitmap.h
+++ b/tools/perf/util/include/linux/bitmap.h
@@ -46,4 +46,21 @@ static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
 		__bitmap_or(dst, src1, src2, nbits);
 }
 
+/**
+ * test_and_set_bit - Set a bit and return its old value
+ * @nr: Bit to set
+ * @addr: Address to count from
+ */
+static inline int test_and_set_bit(int nr, unsigned long *addr)
+{
+	unsigned long mask = BIT_MASK(nr);
+	unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr);
+	unsigned long old;
+
+	old = *p;
+	*p = old | mask;
+
+	return (old & mask) != 0;
+}
+
 #endif /* _PERF_BITOPS_H */
diff --git a/tools/perf/util/include/linux/bitops.h b/tools/perf/util/include/linux/bitops.h
index dadfa7e54287..c3294163de17 100644
--- a/tools/perf/util/include/linux/bitops.h
+++ b/tools/perf/util/include/linux/bitops.h
@@ -15,6 +15,8 @@
 #define BITS_TO_U64(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u64))
 #define BITS_TO_U32(nr)         DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(u32))
 #define BITS_TO_BYTES(nr)       DIV_ROUND_UP(nr, BITS_PER_BYTE)
+#define BIT_WORD(nr)            ((nr) / BITS_PER_LONG)
+#define BIT_MASK(nr)            (1UL << ((nr) % BITS_PER_LONG))
 
 #define for_each_set_bit(bit, addr, size) \
 	for ((bit) = find_first_bit((addr), (size));		\
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 34fc7c8672e4..15dd0a9691ce 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -12,6 +12,7 @@
 #include <stdbool.h>
 #include <symbol/kallsyms.h>
 #include "unwind.h"
+#include "linux/hash.h"
 
 static void dsos__init(struct dsos *dsos)
 {
@@ -21,7 +22,7 @@ static void dsos__init(struct dsos *dsos)
 
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
-	map_groups__init(&machine->kmaps);
+	map_groups__init(&machine->kmaps, machine);
 	RB_CLEAR_NODE(&machine->rb_node);
 	dsos__init(&machine->user_dsos);
 	dsos__init(&machine->kernel_dsos);
@@ -32,7 +33,6 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 
 	machine->vdso_info = NULL;
 
-	machine->kmaps.machine = machine;
 	machine->pid = pid;
 
 	machine->symbol_filter = NULL;
@@ -319,7 +319,7 @@ static void machine__update_thread_pid(struct machine *machine,
 		goto out_err;
 
 	if (!leader->mg)
-		leader->mg = map_groups__new();
+		leader->mg = map_groups__new(machine);
 
 	if (!leader->mg)
 		goto out_err;
@@ -465,6 +465,7 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 {
 	struct map *map;
 	struct dso *dso = __dsos__findnew(&machine->kernel_dsos, filename);
+	bool compressed;
 
 	if (dso == NULL)
 		return NULL;
@@ -477,6 +478,11 @@ struct map *machine__new_module(struct machine *machine, u64 start,
 		dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
 	else
 		dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
+
+	/* _KMODULE_COMP should be next to _KMODULE */
+	if (is_kernel_module(filename, &compressed) && compressed)
+		dso->symtab_type++;
+
 	map_groups__insert(&machine->kmaps, map);
 	return map;
 }
@@ -862,8 +868,14 @@ static int map_groups__set_modules_path_dir(struct map_groups *mg,
 			struct map *map;
 			char *long_name;
 
-			if (dot == NULL || strcmp(dot, ".ko"))
+			if (dot == NULL)
 				continue;
+
+			/* On some system, modules are compressed like .ko.gz */
+			if (is_supported_compression(dot + 1) &&
+			    is_kmodule_extension(dot - 2))
+				dot -= 3;
+
 			snprintf(dso_name, sizeof(dso_name), "[%.*s]",
 				 (int)(dot - dent->d_name), dent->d_name);
 
@@ -1045,6 +1057,11 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			dot = strrchr(name, '.');
 			if (dot == NULL)
 				goto out_problem;
+			/* On some system, modules are compressed like .ko.gz */
+			if (is_supported_compression(dot + 1))
+				dot -= 3;
+			if (!is_kmodule_extension(dot + 1))
+				goto out_problem;
 			snprintf(short_module_name, sizeof(short_module_name),
 					"[%.*s]", (int)(dot - name), name);
 			strxfrchar(short_module_name, '-', '_');
@@ -1069,8 +1086,20 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		 * Should be there already, from the build-id table in
 		 * the header.
 		 */
-		struct dso *kernel = __dsos__findnew(&machine->kernel_dsos,
-						     kmmap_prefix);
+		struct dso *kernel = NULL;
+		struct dso *dso;
+
+		list_for_each_entry(dso, &machine->kernel_dsos.head, node) {
+			if (is_kernel_module(dso->long_name, NULL))
+				continue;
+
+			kernel = dso;
+			break;
+		}
+
+		if (kernel == NULL)
+			kernel = __dsos__findnew(&machine->kernel_dsos,
+						 kmmap_prefix);
 		if (kernel == NULL)
 			goto out_problem;
 
@@ -1078,6 +1107,9 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (__machine__create_kernel_maps(machine, kernel) < 0)
 			goto out_problem;
 
+		if (strstr(kernel->long_name, "vmlinux"))
+			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
+
 		machine__set_kernel_mmap_len(machine, event);
 
 		/*
@@ -1290,7 +1322,7 @@ static bool symbol__match_regex(struct symbol *sym, regex_t *regex)
 	return 0;
 }
 
-static void ip__resolve_ams(struct machine *machine, struct thread *thread,
+static void ip__resolve_ams(struct thread *thread,
 			    struct addr_map_symbol *ams,
 			    u64 ip)
 {
@@ -1304,7 +1336,7 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread,
 	 * Thus, we have to try consecutively until we find a match
 	 * or else, the symbol is unknown
 	 */
-	thread__find_cpumode_addr_location(thread, machine, MAP__FUNCTION, ip, &al);
+	thread__find_cpumode_addr_location(thread, MAP__FUNCTION, ip, &al);
 
 	ams->addr = ip;
 	ams->al_addr = al.addr;
@@ -1312,23 +1344,21 @@ static void ip__resolve_ams(struct machine *machine, struct thread *thread,
 	ams->map = al.map;
 }
 
-static void ip__resolve_data(struct machine *machine, struct thread *thread,
+static void ip__resolve_data(struct thread *thread,
 			     u8 m, struct addr_map_symbol *ams, u64 addr)
 {
 	struct addr_location al;
 
 	memset(&al, 0, sizeof(al));
 
-	thread__find_addr_location(thread, machine, m, MAP__VARIABLE, addr,
-				   &al);
+	thread__find_addr_location(thread, m, MAP__VARIABLE, addr, &al);
 	if (al.map == NULL) {
 		/*
 		 * some shared data regions have execute bit set which puts
 		 * their mapping in the MAP__FUNCTION type array.
 		 * Check there as a fallback option before dropping the sample.
 		 */
-		thread__find_addr_location(thread, machine, m, MAP__FUNCTION, addr,
-					   &al);
+		thread__find_addr_location(thread, m, MAP__FUNCTION, addr, &al);
 	}
 
 	ams->addr = addr;
@@ -1345,14 +1375,45 @@ struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 	if (!mi)
 		return NULL;
 
-	ip__resolve_ams(al->machine, al->thread, &mi->iaddr, sample->ip);
-	ip__resolve_data(al->machine, al->thread, al->cpumode,
-			 &mi->daddr, sample->addr);
+	ip__resolve_ams(al->thread, &mi->iaddr, sample->ip);
+	ip__resolve_data(al->thread, al->cpumode, &mi->daddr, sample->addr);
 	mi->data_src.val = sample->data_src;
 
 	return mi;
 }
 
+static int add_callchain_ip(struct thread *thread,
+			    struct symbol **parent,
+			    struct addr_location *root_al,
+			    int cpumode,
+			    u64 ip)
+{
+	struct addr_location al;
+
+	al.filtered = 0;
+	al.sym = NULL;
+	if (cpumode == -1)
+		thread__find_cpumode_addr_location(thread, MAP__FUNCTION,
+						   ip, &al);
+	else
+		thread__find_addr_location(thread, cpumode, MAP__FUNCTION,
+				   ip, &al);
+	if (al.sym != NULL) {
+		if (sort__has_parent && !*parent &&
+		    symbol__match_regex(al.sym, &parent_regex))
+			*parent = al.sym;
+		else if (have_ignore_callees && root_al &&
+		  symbol__match_regex(al.sym, &ignore_callees_regex)) {
+			/* Treat this symbol as the root,
+			   forgetting its callees. */
+			*root_al = al;
+			callchain_cursor_reset(&callchain_cursor);
+		}
+	}
+
+	return callchain_cursor_append(&callchain_cursor, al.addr, al.map, al.sym);
+}
+
 struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 					   struct addr_location *al)
 {
@@ -1364,16 +1425,57 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 		return NULL;
 
 	for (i = 0; i < bs->nr; i++) {
-		ip__resolve_ams(al->machine, al->thread, &bi[i].to, bs->entries[i].to);
-		ip__resolve_ams(al->machine, al->thread, &bi[i].from, bs->entries[i].from);
+		ip__resolve_ams(al->thread, &bi[i].to, bs->entries[i].to);
+		ip__resolve_ams(al->thread, &bi[i].from, bs->entries[i].from);
 		bi[i].flags = bs->entries[i].flags;
 	}
 	return bi;
 }
 
-static int machine__resolve_callchain_sample(struct machine *machine,
-					     struct thread *thread,
+#define CHASHSZ 127
+#define CHASHBITS 7
+#define NO_ENTRY 0xff
+
+#define PERF_MAX_BRANCH_DEPTH 127
+
+/* Remove loops. */
+static int remove_loops(struct branch_entry *l, int nr)
+{
+	int i, j, off;
+	unsigned char chash[CHASHSZ];
+
+	memset(chash, NO_ENTRY, sizeof(chash));
+
+	BUG_ON(PERF_MAX_BRANCH_DEPTH > 255);
+
+	for (i = 0; i < nr; i++) {
+		int h = hash_64(l[i].from, CHASHBITS) % CHASHSZ;
+
+		/* no collision handling for now */
+		if (chash[h] == NO_ENTRY) {
+			chash[h] = i;
+		} else if (l[chash[h]].from == l[i].from) {
+			bool is_loop = true;
+			/* check if it is a real loop */
+			off = 0;
+			for (j = chash[h]; j < i && i + off < nr; j++, off++)
+				if (l[j].from != l[i + off].from) {
+					is_loop = false;
+					break;
+				}
+			if (is_loop) {
+				memmove(l + i, l + i + off,
+					(nr - (i + off)) * sizeof(*l));
+				nr -= off;
+			}
+		}
+	}
+	return nr;
+}
+
+static int thread__resolve_callchain_sample(struct thread *thread,
 					     struct ip_callchain *chain,
+					     struct branch_stack *branch,
 					     struct symbol **parent,
 					     struct addr_location *root_al,
 					     int max_stack)
@@ -1383,24 +1485,83 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 	int i;
 	int j;
 	int err;
-	int skip_idx __maybe_unused;
-
-	callchain_cursor_reset(&callchain_cursor);
-
-	if (chain->nr > PERF_MAX_STACK_DEPTH) {
-		pr_warning("corrupted callchain. skipping...\n");
-		return 0;
-	}
+	int skip_idx = -1;
+	int first_call = 0;
 
 	/*
 	 * Based on DWARF debug information, some architectures skip
 	 * a callchain entry saved by the kernel.
 	 */
-	skip_idx = arch_skip_callchain_idx(machine, thread, chain);
+	if (chain->nr < PERF_MAX_STACK_DEPTH)
+		skip_idx = arch_skip_callchain_idx(thread, chain);
 
-	for (i = 0; i < chain_nr; i++) {
+	callchain_cursor_reset(&callchain_cursor);
+
+	/*
+	 * Add branches to call stack for easier browsing. This gives
+	 * more context for a sample than just the callers.
+	 *
+	 * This uses individual histograms of paths compared to the
+	 * aggregated histograms the normal LBR mode uses.
+	 *
+	 * Limitations for now:
+	 * - No extra filters
+	 * - No annotations (should annotate somehow)
+	 */
+
+	if (branch && callchain_param.branch_callstack) {
+		int nr = min(max_stack, (int)branch->nr);
+		struct branch_entry be[nr];
+
+		if (branch->nr > PERF_MAX_BRANCH_DEPTH) {
+			pr_warning("corrupted branch chain. skipping...\n");
+			goto check_calls;
+		}
+
+		for (i = 0; i < nr; i++) {
+			if (callchain_param.order == ORDER_CALLEE) {
+				be[i] = branch->entries[i];
+				/*
+				 * Check for overlap into the callchain.
+				 * The return address is one off compared to
+				 * the branch entry. To adjust for this
+				 * assume the calling instruction is not longer
+				 * than 8 bytes.
+				 */
+				if (i == skip_idx ||
+				    chain->ips[first_call] >= PERF_CONTEXT_MAX)
+					first_call++;
+				else if (be[i].from < chain->ips[first_call] &&
+				    be[i].from >= chain->ips[first_call] - 8)
+					first_call++;
+			} else
+				be[i] = branch->entries[branch->nr - i - 1];
+		}
+
+		nr = remove_loops(be, nr);
+
+		for (i = 0; i < nr; i++) {
+			err = add_callchain_ip(thread, parent, root_al,
+					       -1, be[i].to);
+			if (!err)
+				err = add_callchain_ip(thread, parent, root_al,
+						       -1, be[i].from);
+			if (err == -EINVAL)
+				break;
+			if (err)
+				return err;
+		}
+		chain_nr -= nr;
+	}
+
+check_calls:
+	if (chain->nr > PERF_MAX_STACK_DEPTH) {
+		pr_warning("corrupted callchain. skipping...\n");
+		return 0;
+	}
+
+	for (i = first_call; i < chain_nr; i++) {
 		u64 ip;
-		struct addr_location al;
 
 		if (callchain_param.order == ORDER_CALLEE)
 			j = i;
@@ -1437,24 +1598,10 @@ static int machine__resolve_callchain_sample(struct machine *machine,
 			continue;
 		}
 
-		al.filtered = 0;
-		thread__find_addr_location(thread, machine, cpumode,
-					   MAP__FUNCTION, ip, &al);
-		if (al.sym != NULL) {
-			if (sort__has_parent && !*parent &&
-			    symbol__match_regex(al.sym, &parent_regex))
-				*parent = al.sym;
-			else if (have_ignore_callees && root_al &&
-			  symbol__match_regex(al.sym, &ignore_callees_regex)) {
-				/* Treat this symbol as the root,
-				   forgetting its callees. */
-				*root_al = al;
-				callchain_cursor_reset(&callchain_cursor);
-			}
-		}
-
-		err = callchain_cursor_append(&callchain_cursor,
-					      ip, al.map, al.sym);
+		err = add_callchain_ip(thread, parent, root_al,
+				       cpumode, ip);
+		if (err == -EINVAL)
+			break;
 		if (err)
 			return err;
 	}
@@ -1469,19 +1616,16 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 				       entry->map, entry->sym);
 }
 
-int machine__resolve_callchain(struct machine *machine,
-			       struct perf_evsel *evsel,
-			       struct thread *thread,
-			       struct perf_sample *sample,
-			       struct symbol **parent,
-			       struct addr_location *root_al,
-			       int max_stack)
+int thread__resolve_callchain(struct thread *thread,
+			      struct perf_evsel *evsel,
+			      struct perf_sample *sample,
+			      struct symbol **parent,
+			      struct addr_location *root_al,
+			      int max_stack)
 {
-	int ret;
-
-	ret = machine__resolve_callchain_sample(machine, thread,
-						sample->callchain, parent,
-						root_al, max_stack);
+	int ret = thread__resolve_callchain_sample(thread, sample->callchain,
+						   sample->branch_stack,
+						   parent, root_al, max_stack);
 	if (ret)
 		return ret;
 
@@ -1495,7 +1639,7 @@ int machine__resolve_callchain(struct machine *machine,
 	    (!sample->user_stack.size))
 		return 0;
 
-	return unwind__get_entries(unwind_entry, &callchain_cursor, machine,
+	return unwind__get_entries(unwind_entry, &callchain_cursor,
 				   thread, sample, max_stack);
 
 }
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 2b651a7f5d0d..e8b7779a0a3f 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -40,6 +40,10 @@ struct machine {
 	u64		  kernel_start;
 	symbol_filter_t	  symbol_filter;
 	pid_t		  *current_tid;
+	union { /* Tool specific area */
+		void	  *priv;
+		u64	  db_id;
+	};
 };
 
 static inline
@@ -122,13 +126,12 @@ struct branch_info *sample__resolve_bstack(struct perf_sample *sample,
 					   struct addr_location *al);
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 				     struct addr_location *al);
-int machine__resolve_callchain(struct machine *machine,
-			       struct perf_evsel *evsel,
-			       struct thread *thread,
-			       struct perf_sample *sample,
-			       struct symbol **parent,
-			       struct addr_location *root_al,
-			       int max_stack);
+int thread__resolve_callchain(struct thread *thread,
+			      struct perf_evsel *evsel,
+			      struct perf_sample *sample,
+			      struct symbol **parent,
+			      struct addr_location *root_al,
+			      int max_stack);
 
 /*
  * Default guest kernel is defined by parameter --guestkallsyms
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 2137c4596ec7..62ca9f2607d5 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -360,7 +360,7 @@ int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
 
 	if (map && map->dso) {
 		srcline = get_srcline(map->dso,
-				      map__rip_2objdump(map, addr));
+				      map__rip_2objdump(map, addr), NULL, true);
 		if (srcline != SRCLINE_UNKNOWN)
 			ret = fprintf(fp, "%s%s", prefix, srcline);
 		free_srcline(srcline);
@@ -413,14 +413,14 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	return ip + map->reloc;
 }
 
-void map_groups__init(struct map_groups *mg)
+void map_groups__init(struct map_groups *mg, struct machine *machine)
 {
 	int i;
 	for (i = 0; i < MAP__NR_TYPES; ++i) {
 		mg->maps[i] = RB_ROOT;
 		INIT_LIST_HEAD(&mg->removed_maps[i]);
 	}
-	mg->machine = NULL;
+	mg->machine = machine;
 	mg->refcnt = 1;
 }
 
@@ -471,12 +471,12 @@ bool map_groups__empty(struct map_groups *mg)
 	return true;
 }
 
-struct map_groups *map_groups__new(void)
+struct map_groups *map_groups__new(struct machine *machine)
 {
 	struct map_groups *mg = malloc(sizeof(*mg));
 
 	if (mg != NULL)
-		map_groups__init(mg);
+		map_groups__init(mg, machine);
 
 	return mg;
 }
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 2f83954af050..6951a9d42339 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -64,7 +64,7 @@ struct map_groups {
 	int		 refcnt;
 };
 
-struct map_groups *map_groups__new(void);
+struct map_groups *map_groups__new(struct machine *machine);
 void map_groups__delete(struct map_groups *mg);
 bool map_groups__empty(struct map_groups *mg);
 
@@ -150,7 +150,7 @@ void maps__remove(struct rb_root *maps, struct map *map);
 struct map *maps__find(struct rb_root *maps, u64 addr);
 struct map *maps__first(struct rb_root *maps);
 struct map *maps__next(struct map *map);
-void map_groups__init(struct map_groups *mg);
+void map_groups__init(struct map_groups *mg, struct machine *machine);
 void map_groups__exit(struct map_groups *mg);
 int map_groups__clone(struct map_groups *mg,
 		      struct map_groups *parent, enum map_type type);
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index c659a3ca1283..77b43fe43d55 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -681,6 +681,8 @@ int parse_events_add_pmu(struct list_head *list, int *idx,
 	if (evsel) {
 		evsel->unit = info.unit;
 		evsel->scale = info.scale;
+		evsel->per_pkg = info.per_pkg;
+		evsel->snapshot = info.snapshot;
 	}
 
 	return evsel ? 0 : -ENOMEM;
diff --git a/tools/perf/util/parse-options.c b/tools/perf/util/parse-options.c
index bf48092983c6..f62dee7bd924 100644
--- a/tools/perf/util/parse-options.c
+++ b/tools/perf/util/parse-options.c
@@ -42,7 +42,26 @@ static int get_value(struct parse_opt_ctx_t *p,
 		return opterror(opt, "takes no value", flags);
 	if (unset && (opt->flags & PARSE_OPT_NONEG))
 		return opterror(opt, "isn't available", flags);
+	if (opt->flags & PARSE_OPT_DISABLED)
+		return opterror(opt, "is not usable", flags);
 
+	if (opt->flags & PARSE_OPT_EXCLUSIVE) {
+		if (p->excl_opt) {
+			char msg[128];
+
+			if (((flags & OPT_SHORT) && p->excl_opt->short_name) ||
+			    p->excl_opt->long_name == NULL) {
+				scnprintf(msg, sizeof(msg), "cannot be used with switch `%c'",
+					  p->excl_opt->short_name);
+			} else {
+				scnprintf(msg, sizeof(msg), "cannot be used with %s",
+					  p->excl_opt->long_name);
+			}
+			opterror(opt, msg, flags);
+			return -3;
+		}
+		p->excl_opt = opt;
+	}
 	if (!(flags & OPT_SHORT) && p->opt) {
 		switch (opt->type) {
 		case OPTION_CALLBACK:
@@ -343,13 +362,14 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 		       const char * const usagestr[])
 {
 	int internal_help = !(ctx->flags & PARSE_OPT_NO_INTERNAL_HELP);
+	int excl_short_opt = 1;
+	const char *arg;
 
 	/* we must reset ->opt, unknown short option leave it dangling */
 	ctx->opt = NULL;
 
 	for (; ctx->argc; ctx->argc--, ctx->argv++) {
-		const char *arg = ctx->argv[0];
-
+		arg = ctx->argv[0];
 		if (*arg != '-' || !arg[1]) {
 			if (ctx->flags & PARSE_OPT_STOP_AT_NON_OPTION)
 				break;
@@ -358,19 +378,21 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 		}
 
 		if (arg[1] != '-') {
-			ctx->opt = arg + 1;
+			ctx->opt = ++arg;
 			if (internal_help && *ctx->opt == 'h')
 				return usage_with_options_internal(usagestr, options, 0);
 			switch (parse_short_opt(ctx, options)) {
 			case -1:
-				return parse_options_usage(usagestr, options, arg + 1, 1);
+				return parse_options_usage(usagestr, options, arg, 1);
 			case -2:
 				goto unknown;
+			case -3:
+				goto exclusive;
 			default:
 				break;
 			}
 			if (ctx->opt)
-				check_typos(arg + 1, options);
+				check_typos(arg, options);
 			while (ctx->opt) {
 				if (internal_help && *ctx->opt == 'h')
 					return usage_with_options_internal(usagestr, options, 0);
@@ -387,6 +409,8 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 					ctx->argv[0] = strdup(ctx->opt - 1);
 					*(char *)ctx->argv[0] = '-';
 					goto unknown;
+				case -3:
+					goto exclusive;
 				default:
 					break;
 				}
@@ -402,19 +426,23 @@ int parse_options_step(struct parse_opt_ctx_t *ctx,
 			break;
 		}
 
-		if (internal_help && !strcmp(arg + 2, "help-all"))
+		arg += 2;
+		if (internal_help && !strcmp(arg, "help-all"))
 			return usage_with_options_internal(usagestr, options, 1);
-		if (internal_help && !strcmp(arg + 2, "help"))
+		if (internal_help && !strcmp(arg, "help"))
 			return usage_with_options_internal(usagestr, options, 0);
-		if (!strcmp(arg + 2, "list-opts"))
+		if (!strcmp(arg, "list-opts"))
 			return PARSE_OPT_LIST_OPTS;
-		if (!strcmp(arg + 2, "list-cmds"))
+		if (!strcmp(arg, "list-cmds"))
 			return PARSE_OPT_LIST_SUBCMDS;
-		switch (parse_long_opt(ctx, arg + 2, options)) {
+		switch (parse_long_opt(ctx, arg, options)) {
 		case -1:
-			return parse_options_usage(usagestr, options, arg + 2, 0);
+			return parse_options_usage(usagestr, options, arg, 0);
 		case -2:
 			goto unknown;
+		case -3:
+			excl_short_opt = 0;
+			goto exclusive;
 		default:
 			break;
 		}
@@ -426,6 +454,17 @@ unknown:
 		ctx->opt = NULL;
 	}
 	return PARSE_OPT_DONE;
+
+exclusive:
+	parse_options_usage(usagestr, options, arg, excl_short_opt);
+	if ((excl_short_opt && ctx->excl_opt->short_name) ||
+	    ctx->excl_opt->long_name == NULL) {
+		char opt = ctx->excl_opt->short_name;
+		parse_options_usage(NULL, options, &opt, 1);
+	} else {
+		parse_options_usage(NULL, options, ctx->excl_opt->long_name, 0);
+	}
+	return PARSE_OPT_HELP;
 }
 
 int parse_options_end(struct parse_opt_ctx_t *ctx)
@@ -509,6 +548,8 @@ static void print_option_help(const struct option *opts, int full)
 	}
 	if (!full && (opts->flags & PARSE_OPT_HIDDEN))
 		return;
+	if (opts->flags & PARSE_OPT_DISABLED)
+		return;
 
 	pos = fprintf(stderr, "    ");
 	if (opts->short_name)
@@ -679,3 +720,16 @@ int parse_opt_verbosity_cb(const struct option *opt,
 	}
 	return 0;
 }
+
+void set_option_flag(struct option *opts, int shortopt, const char *longopt,
+		     int flag)
+{
+	for (; opts->type != OPTION_END; opts++) {
+		if ((shortopt && opts->short_name == shortopt) ||
+		    (opts->long_name && longopt &&
+		     !strcmp(opts->long_name, longopt))) {
+			opts->flags |= flag;
+			break;
+		}
+	}
+}
diff --git a/tools/perf/util/parse-options.h b/tools/perf/util/parse-options.h
index b59ba858e73d..97b153fb4999 100644
--- a/tools/perf/util/parse-options.h
+++ b/tools/perf/util/parse-options.h
@@ -38,6 +38,8 @@ enum parse_opt_option_flags {
 	PARSE_OPT_NONEG   = 4,
 	PARSE_OPT_HIDDEN  = 8,
 	PARSE_OPT_LASTARG_DEFAULT = 16,
+	PARSE_OPT_DISABLED = 32,
+	PARSE_OPT_EXCLUSIVE = 64,
 };
 
 struct option;
@@ -173,6 +175,7 @@ struct parse_opt_ctx_t {
 	const char **out;
 	int argc, cpidx;
 	const char *opt;
+	const struct option *excl_opt;
 	int flags;
 };
 
@@ -211,4 +214,5 @@ extern int parse_opt_verbosity_cb(const struct option *, const char *, int);
 
 extern const char *parse_options_fix_filename(const char *prefix, const char *file);
 
+void set_option_flag(struct option *opts, int sopt, const char *lopt, int flag);
 #endif /* __PERF_PARSE_OPTIONS_H */
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index e243ad962a4d..5c9c4947cfb4 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -163,6 +163,41 @@ error:
 	return -1;
 }
 
+static int
+perf_pmu__parse_per_pkg(struct perf_pmu_alias *alias, char *dir, char *name)
+{
+	char path[PATH_MAX];
+	int fd;
+
+	snprintf(path, PATH_MAX, "%s/%s.per-pkg", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	close(fd);
+
+	alias->per_pkg = true;
+	return 0;
+}
+
+static int perf_pmu__parse_snapshot(struct perf_pmu_alias *alias,
+				    char *dir, char *name)
+{
+	char path[PATH_MAX];
+	int fd;
+
+	snprintf(path, PATH_MAX, "%s/%s.snapshot", dir, name);
+
+	fd = open(path, O_RDONLY);
+	if (fd == -1)
+		return -1;
+
+	alias->snapshot = true;
+	close(fd);
+	return 0;
+}
+
 static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FILE *file)
 {
 	struct perf_pmu_alias *alias;
@@ -181,6 +216,7 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	INIT_LIST_HEAD(&alias->terms);
 	alias->scale = 1.0;
 	alias->unit[0] = '\0';
+	alias->per_pkg = false;
 
 	ret = parse_events_terms(&alias->terms, buf);
 	if (ret) {
@@ -194,6 +230,8 @@ static int perf_pmu__new_alias(struct list_head *list, char *dir, char *name, FI
 	 */
 	perf_pmu__parse_unit(alias, dir, name);
 	perf_pmu__parse_scale(alias, dir, name);
+	perf_pmu__parse_per_pkg(alias, dir, name);
+	perf_pmu__parse_snapshot(alias, dir, name);
 
 	list_add_tail(&alias->list, list);
 
@@ -209,6 +247,10 @@ static inline bool pmu_alias_info_file(char *name)
 		return true;
 	if (len > 6 && !strcmp(name + len - 6, ".scale"))
 		return true;
+	if (len > 8 && !strcmp(name + len - 8, ".per-pkg"))
+		return true;
+	if (len > 9 && !strcmp(name + len - 9, ".snapshot"))
+		return true;
 
 	return false;
 }
@@ -617,23 +659,27 @@ static struct perf_pmu_alias *pmu_find_alias(struct perf_pmu *pmu,
 }
 
 
-static int check_unit_scale(struct perf_pmu_alias *alias,
-			    const char **unit, double *scale)
+static int check_info_data(struct perf_pmu_alias *alias,
+			   struct perf_pmu_info *info)
 {
 	/*
 	 * Only one term in event definition can
-	 * define unit and scale, fail if there's
-	 * more than one.
+	 * define unit, scale and snapshot, fail
+	 * if there's more than one.
 	 */
-	if ((*unit && alias->unit) ||
-	    (*scale && alias->scale))
+	if ((info->unit && alias->unit) ||
+	    (info->scale && alias->scale) ||
+	    (info->snapshot && alias->snapshot))
 		return -EINVAL;
 
 	if (alias->unit)
-		*unit = alias->unit;
+		info->unit = alias->unit;
 
 	if (alias->scale)
-		*scale = alias->scale;
+		info->scale = alias->scale;
+
+	if (alias->snapshot)
+		info->snapshot = alias->snapshot;
 
 	return 0;
 }
@@ -649,12 +695,15 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 	struct perf_pmu_alias *alias;
 	int ret;
 
+	info->per_pkg = false;
+
 	/*
 	 * Mark unit and scale as not set
 	 * (different from default values, see below)
 	 */
-	info->unit   = NULL;
-	info->scale  = 0.0;
+	info->unit     = NULL;
+	info->scale    = 0.0;
+	info->snapshot = false;
 
 	list_for_each_entry_safe(term, h, head_terms, list) {
 		alias = pmu_find_alias(pmu, term);
@@ -664,10 +713,13 @@ int perf_pmu__check_alias(struct perf_pmu *pmu, struct list_head *head_terms,
 		if (ret)
 			return ret;
 
-		ret = check_unit_scale(alias, &info->unit, &info->scale);
+		ret = check_info_data(alias, info);
 		if (ret)
 			return ret;
 
+		if (alias->per_pkg)
+			info->per_pkg = true;
+
 		list_del(&term->list);
 		free(term);
 	}
@@ -747,15 +799,18 @@ void print_pmu_events(const char *event_glob, bool name_only)
 
 	pmu = NULL;
 	len = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		list_for_each_entry(alias, &pmu->aliases, list)
 			len++;
-	aliases = malloc(sizeof(char *) * len);
+		if (pmu->selectable)
+			len++;
+	}
+	aliases = zalloc(sizeof(char *) * len);
 	if (!aliases)
-		return;
+		goto out_enomem;
 	pmu = NULL;
 	j = 0;
-	while ((pmu = perf_pmu__scan(pmu)) != NULL)
+	while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 		list_for_each_entry(alias, &pmu->aliases, list) {
 			char *name = format_alias(buf, sizeof(buf), pmu, alias);
 			bool is_cpu = !strcmp(pmu->name, "cpu");
@@ -765,13 +820,23 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			      (!is_cpu && strglobmatch(alias->name,
 						       event_glob))))
 				continue;
-			aliases[j] = name;
+
 			if (is_cpu && !name_only)
-				aliases[j] = format_alias_or(buf, sizeof(buf),
-							      pmu, alias);
-			aliases[j] = strdup(aliases[j]);
+				name = format_alias_or(buf, sizeof(buf), pmu, alias);
+
+			aliases[j] = strdup(name);
+			if (aliases[j] == NULL)
+				goto out_enomem;
 			j++;
 		}
+		if (pmu->selectable) {
+			char *s;
+			if (asprintf(&s, "%s//", pmu->name) < 0)
+				goto out_enomem;
+			aliases[j] = s;
+			j++;
+		}
+	}
 	len = j;
 	qsort(aliases, len, sizeof(char *), cmp_string);
 	for (j = 0; j < len; j++) {
@@ -780,12 +845,20 @@ void print_pmu_events(const char *event_glob, bool name_only)
 			continue;
 		}
 		printf("  %-50s [Kernel PMU event]\n", aliases[j]);
-		zfree(&aliases[j]);
 		printed++;
 	}
 	if (printed)
 		printf("\n");
-	free(aliases);
+out_free:
+	for (j = 0; j < len; j++)
+		zfree(&aliases[j]);
+	zfree(&aliases);
+	return;
+
+out_enomem:
+	printf("FATAL: not enough memory to print PMU events\n");
+	if (aliases)
+		goto out_free;
 }
 
 bool pmu_have_event(const char *pname, const char *name)
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index fe9dfbee8eed..6b1249fbdb5f 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -18,6 +18,7 @@ struct perf_event_attr;
 struct perf_pmu {
 	char *name;
 	__u32 type;
+	bool selectable;
 	struct perf_event_attr *default_config;
 	struct cpu_map *cpus;
 	struct list_head format;  /* HEAD struct perf_pmu_format -> list */
@@ -28,6 +29,8 @@ struct perf_pmu {
 struct perf_pmu_info {
 	const char *unit;
 	double scale;
+	bool per_pkg;
+	bool snapshot;
 };
 
 #define UNIT_MAX_LEN	31 /* max length for event unit name */
@@ -38,6 +41,8 @@ struct perf_pmu_alias {
 	struct list_head list;  /* ELEM */
 	char unit[UNIT_MAX_LEN+1];
 	double scale;
+	bool per_pkg;
+	bool snapshot;
 };
 
 struct perf_pmu *perf_pmu__find(const char *name);
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index c150ca4343eb..28eb1417cb2a 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -1910,21 +1910,21 @@ static int show_perf_probe_event(struct perf_probe_event *pev,
 	if (ret < 0)
 		return ret;
 
-	printf("  %-20s (on %s", buf, place);
+	pr_info("  %-20s (on %s", buf, place);
 	if (module)
-		printf(" in %s", module);
+		pr_info(" in %s", module);
 
 	if (pev->nargs > 0) {
-		printf(" with");
+		pr_info(" with");
 		for (i = 0; i < pev->nargs; i++) {
 			ret = synthesize_perf_probe_arg(&pev->args[i],
 							buf, 128);
 			if (ret < 0)
 				break;
-			printf(" %s", buf);
+			pr_info(" %s", buf);
 		}
 	}
-	printf(")\n");
+	pr_info(")\n");
 	free(place);
 	return ret;
 }
@@ -2124,7 +2124,7 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 	}
 
 	ret = 0;
-	printf("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
+	pr_info("Added new event%s\n", (ntevs > 1) ? "s:" : ":");
 	for (i = 0; i < ntevs; i++) {
 		tev = &tevs[i];
 		if (pev->event)
@@ -2179,8 +2179,8 @@ static int __add_probe_trace_events(struct perf_probe_event *pev,
 
 	if (ret >= 0) {
 		/* Show how to use the event. */
-		printf("\nYou can now use it in all perf tools, such as:\n\n");
-		printf("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
+		pr_info("\nYou can now use it in all perf tools, such as:\n\n");
+		pr_info("\tperf record -e %s:%s -aR sleep 1\n\n", tev->group,
 			 tev->event);
 	}
 
@@ -2444,7 +2444,7 @@ static int __del_trace_probe_event(int fd, struct str_node *ent)
 		goto error;
 	}
 
-	printf("Removed event: %s\n", ent->s);
+	pr_info("Removed event: %s\n", ent->s);
 	return 0;
 error:
 	pr_warning("Failed to delete event: %s\n",
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index 0a01bac4ce02..22ebc46226e7 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -24,6 +24,7 @@
 #include <string.h>
 #include <ctype.h>
 #include <errno.h>
+#include <linux/bitmap.h>
 
 #include "../util.h"
 #include <EXTERN.h>
@@ -57,7 +58,7 @@ INTERP my_perl;
 #define FTRACE_MAX_EVENT				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
 
-struct event_format *events[FTRACE_MAX_EVENT];
+static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT);
 
 extern struct scripting_context *scripting_context;
 
@@ -238,35 +239,15 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
-{
-	static char ev_name[256];
-	struct event_format *event;
-	int type = evsel->attr.config;
-
-	if (events[type])
-		return events[type];
-
-	events[type] = event = evsel->tp_format;
-	if (!event)
-		return NULL;
-
-	sprintf(ev_name, "%s::%s", event->system, event->name);
-
-	define_event_symbols(event, ev_name, event->print_fmt.args);
-
-	return event;
-}
-
 static void perl_process_tracepoint(struct perf_sample *sample,
 				    struct perf_evsel *evsel,
 				    struct thread *thread)
 {
+	struct event_format *event = evsel->tp_format;
 	struct format_field *field;
 	static char handler[256];
 	unsigned long long val;
 	unsigned long s, ns;
-	struct event_format *event;
 	int pid;
 	int cpu = sample->cpu;
 	void *data = sample->raw_data;
@@ -278,7 +259,6 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 	if (evsel->attr.type != PERF_TYPE_TRACEPOINT)
 		return;
 
-	event = find_cache_event(evsel);
 	if (!event)
 		die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
 
@@ -286,6 +266,9 @@ static void perl_process_tracepoint(struct perf_sample *sample,
 
 	sprintf(handler, "%s::%s", event->system, event->name);
 
+	if (!test_and_set_bit(event->id, events_defined))
+		define_event_symbols(event, handler, event->print_fmt.args);
+
 	s = nsecs / NSECS_PER_SEC;
 	ns = nsecs - s * NSECS_PER_SEC;
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 496f21cadd97..d808a328f4dc 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -24,7 +24,9 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
+#include <stdbool.h>
 #include <errno.h>
+#include <linux/bitmap.h>
 
 #include "../../perf.h"
 #include "../debug.h"
@@ -33,6 +35,10 @@
 #include "../util.h"
 #include "../event.h"
 #include "../thread.h"
+#include "../comm.h"
+#include "../machine.h"
+#include "../db-export.h"
+#include "../thread-stack.h"
 #include "../trace-event.h"
 #include "../machine.h"
 
@@ -41,7 +47,7 @@ PyMODINIT_FUNC initperf_trace_context(void);
 #define FTRACE_MAX_EVENT				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
 
-struct event_format *events[FTRACE_MAX_EVENT];
+static DECLARE_BITMAP(events_defined, FTRACE_MAX_EVENT);
 
 #define MAX_FIELDS	64
 #define N_COMMON_FIELDS	7
@@ -53,6 +59,24 @@ static int zero_flag_atom;
 
 static PyObject *main_module, *main_dict;
 
+struct tables {
+	struct db_export	dbe;
+	PyObject		*evsel_handler;
+	PyObject		*machine_handler;
+	PyObject		*thread_handler;
+	PyObject		*comm_handler;
+	PyObject		*comm_thread_handler;
+	PyObject		*dso_handler;
+	PyObject		*symbol_handler;
+	PyObject		*branch_type_handler;
+	PyObject		*sample_handler;
+	PyObject		*call_path_handler;
+	PyObject		*call_return_handler;
+	bool			db_export_mode;
+};
+
+static struct tables tables_global;
+
 static void handler_call_die(const char *handler_name) NORETURN;
 static void handler_call_die(const char *handler_name)
 {
@@ -232,31 +256,6 @@ static void define_event_symbols(struct event_format *event,
 		define_event_symbols(event, ev_name, args->next);
 }
 
-static inline struct event_format *find_cache_event(struct perf_evsel *evsel)
-{
-	static char ev_name[256];
-	struct event_format *event;
-	int type = evsel->attr.config;
-
-	/*
- 	 * XXX: Do we really need to cache this since now we have evsel->tp_format
- 	 * cached already? Need to re-read this "cache" routine that as well calls
- 	 * define_event_symbols() :-\
- 	 */
-	if (events[type])
-		return events[type];
-
-	events[type] = event = evsel->tp_format;
-	if (!event)
-		return NULL;
-
-	sprintf(ev_name, "%s__%s", event->system, event->name);
-
-	define_event_symbols(event, ev_name, event->print_fmt.args);
-
-	return event;
-}
-
 static PyObject *get_field_numeric_entry(struct event_format *event,
 		struct format_field *field, void *data)
 {
@@ -312,9 +311,9 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 	if (!symbol_conf.use_callchain || !sample->callchain)
 		goto exit;
 
-	if (machine__resolve_callchain(al->machine, evsel, al->thread,
-					   sample, NULL, NULL,
-					   PERF_MAX_STACK_DEPTH) != 0) {
+	if (thread__resolve_callchain(al->thread, evsel,
+				      sample, NULL, NULL,
+				      PERF_MAX_STACK_DEPTH) != 0) {
 		pr_err("Failed to resolve callchain. Skipping\n");
 		goto exit;
 	}
@@ -380,12 +379,12 @@ static void python_process_tracepoint(struct perf_sample *sample,
 				      struct thread *thread,
 				      struct addr_location *al)
 {
+	struct event_format *event = evsel->tp_format;
 	PyObject *handler, *context, *t, *obj, *callchain;
 	PyObject *dict = NULL;
 	static char handler_name[256];
 	struct format_field *field;
 	unsigned long s, ns;
-	struct event_format *event;
 	unsigned n = 0;
 	int pid;
 	int cpu = sample->cpu;
@@ -397,7 +396,6 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	if (!t)
 		Py_FatalError("couldn't create Python tuple");
 
-	event = find_cache_event(evsel);
 	if (!event)
 		die("ug! no event found for type %d", (int)evsel->attr.config);
 
@@ -405,6 +403,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
 
 	sprintf(handler_name, "%s__%s", event->system, event->name);
 
+	if (!test_and_set_bit(event->id, events_defined))
+		define_event_symbols(event, handler_name, event->print_fmt.args);
+
 	handler = get_handler(handler_name);
 	if (!handler) {
 		dict = PyDict_New();
@@ -475,6 +476,289 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	Py_DECREF(t);
 }
 
+static PyObject *tuple_new(unsigned int sz)
+{
+	PyObject *t;
+
+	t = PyTuple_New(sz);
+	if (!t)
+		Py_FatalError("couldn't create Python tuple");
+	return t;
+}
+
+static int tuple_set_u64(PyObject *t, unsigned int pos, u64 val)
+{
+#if BITS_PER_LONG == 64
+	return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+#endif
+#if BITS_PER_LONG == 32
+	return PyTuple_SetItem(t, pos, PyLong_FromLongLong(val));
+#endif
+}
+
+static int tuple_set_s32(PyObject *t, unsigned int pos, s32 val)
+{
+	return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+}
+
+static int tuple_set_string(PyObject *t, unsigned int pos, const char *s)
+{
+	return PyTuple_SetItem(t, pos, PyString_FromString(s));
+}
+
+static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(2);
+
+	tuple_set_u64(t, 0, evsel->db_id);
+	tuple_set_string(t, 1, perf_evsel__name(evsel));
+
+	call_object(tables->evsel_handler, t, "evsel_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_machine(struct db_export *dbe,
+				 struct machine *machine)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(3);
+
+	tuple_set_u64(t, 0, machine->db_id);
+	tuple_set_s32(t, 1, machine->pid);
+	tuple_set_string(t, 2, machine->root_dir ? machine->root_dir : "");
+
+	call_object(tables->machine_handler, t, "machine_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_thread(struct db_export *dbe, struct thread *thread,
+				u64 main_thread_db_id, struct machine *machine)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(5);
+
+	tuple_set_u64(t, 0, thread->db_id);
+	tuple_set_u64(t, 1, machine->db_id);
+	tuple_set_u64(t, 2, main_thread_db_id);
+	tuple_set_s32(t, 3, thread->pid_);
+	tuple_set_s32(t, 4, thread->tid);
+
+	call_object(tables->thread_handler, t, "thread_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_comm(struct db_export *dbe, struct comm *comm)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(2);
+
+	tuple_set_u64(t, 0, comm->db_id);
+	tuple_set_string(t, 1, comm__str(comm));
+
+	call_object(tables->comm_handler, t, "comm_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_comm_thread(struct db_export *dbe, u64 db_id,
+				     struct comm *comm, struct thread *thread)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(3);
+
+	tuple_set_u64(t, 0, db_id);
+	tuple_set_u64(t, 1, comm->db_id);
+	tuple_set_u64(t, 2, thread->db_id);
+
+	call_object(tables->comm_thread_handler, t, "comm_thread_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_dso(struct db_export *dbe, struct dso *dso,
+			     struct machine *machine)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	char sbuild_id[BUILD_ID_SIZE * 2 + 1];
+	PyObject *t;
+
+	build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
+
+	t = tuple_new(5);
+
+	tuple_set_u64(t, 0, dso->db_id);
+	tuple_set_u64(t, 1, machine->db_id);
+	tuple_set_string(t, 2, dso->short_name);
+	tuple_set_string(t, 3, dso->long_name);
+	tuple_set_string(t, 4, sbuild_id);
+
+	call_object(tables->dso_handler, t, "dso_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_symbol(struct db_export *dbe, struct symbol *sym,
+				struct dso *dso)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	u64 *sym_db_id = symbol__priv(sym);
+	PyObject *t;
+
+	t = tuple_new(6);
+
+	tuple_set_u64(t, 0, *sym_db_id);
+	tuple_set_u64(t, 1, dso->db_id);
+	tuple_set_u64(t, 2, sym->start);
+	tuple_set_u64(t, 3, sym->end);
+	tuple_set_s32(t, 4, sym->binding);
+	tuple_set_string(t, 5, sym->name);
+
+	call_object(tables->symbol_handler, t, "symbol_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_branch_type(struct db_export *dbe, u32 branch_type,
+				     const char *name)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(2);
+
+	tuple_set_s32(t, 0, branch_type);
+	tuple_set_string(t, 1, name);
+
+	call_object(tables->branch_type_handler, t, "branch_type_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_sample(struct db_export *dbe,
+				struct export_sample *es)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+
+	t = tuple_new(21);
+
+	tuple_set_u64(t, 0, es->db_id);
+	tuple_set_u64(t, 1, es->evsel->db_id);
+	tuple_set_u64(t, 2, es->al->machine->db_id);
+	tuple_set_u64(t, 3, es->thread->db_id);
+	tuple_set_u64(t, 4, es->comm_db_id);
+	tuple_set_u64(t, 5, es->dso_db_id);
+	tuple_set_u64(t, 6, es->sym_db_id);
+	tuple_set_u64(t, 7, es->offset);
+	tuple_set_u64(t, 8, es->sample->ip);
+	tuple_set_u64(t, 9, es->sample->time);
+	tuple_set_s32(t, 10, es->sample->cpu);
+	tuple_set_u64(t, 11, es->addr_dso_db_id);
+	tuple_set_u64(t, 12, es->addr_sym_db_id);
+	tuple_set_u64(t, 13, es->addr_offset);
+	tuple_set_u64(t, 14, es->sample->addr);
+	tuple_set_u64(t, 15, es->sample->period);
+	tuple_set_u64(t, 16, es->sample->weight);
+	tuple_set_u64(t, 17, es->sample->transaction);
+	tuple_set_u64(t, 18, es->sample->data_src);
+	tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK);
+	tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX));
+
+	call_object(tables->sample_handler, t, "sample_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_call_path(struct db_export *dbe, struct call_path *cp)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	PyObject *t;
+	u64 parent_db_id, sym_db_id;
+
+	parent_db_id = cp->parent ? cp->parent->db_id : 0;
+	sym_db_id = cp->sym ? *(u64 *)symbol__priv(cp->sym) : 0;
+
+	t = tuple_new(4);
+
+	tuple_set_u64(t, 0, cp->db_id);
+	tuple_set_u64(t, 1, parent_db_id);
+	tuple_set_u64(t, 2, sym_db_id);
+	tuple_set_u64(t, 3, cp->ip);
+
+	call_object(tables->call_path_handler, t, "call_path_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_export_call_return(struct db_export *dbe,
+				     struct call_return *cr)
+{
+	struct tables *tables = container_of(dbe, struct tables, dbe);
+	u64 comm_db_id = cr->comm ? cr->comm->db_id : 0;
+	PyObject *t;
+
+	t = tuple_new(11);
+
+	tuple_set_u64(t, 0, cr->db_id);
+	tuple_set_u64(t, 1, cr->thread->db_id);
+	tuple_set_u64(t, 2, comm_db_id);
+	tuple_set_u64(t, 3, cr->cp->db_id);
+	tuple_set_u64(t, 4, cr->call_time);
+	tuple_set_u64(t, 5, cr->return_time);
+	tuple_set_u64(t, 6, cr->branch_count);
+	tuple_set_u64(t, 7, cr->call_ref);
+	tuple_set_u64(t, 8, cr->return_ref);
+	tuple_set_u64(t, 9, cr->cp->parent->db_id);
+	tuple_set_s32(t, 10, cr->flags);
+
+	call_object(tables->call_return_handler, t, "call_return_table");
+
+	Py_DECREF(t);
+
+	return 0;
+}
+
+static int python_process_call_return(struct call_return *cr, void *data)
+{
+	struct db_export *dbe = data;
+
+	return db_export__call_return(dbe, cr);
+}
+
 static void python_process_general_event(struct perf_sample *sample,
 					 struct perf_evsel *evsel,
 					 struct thread *thread,
@@ -551,19 +835,25 @@ exit:
 	Py_DECREF(t);
 }
 
-static void python_process_event(union perf_event *event __maybe_unused,
+static void python_process_event(union perf_event *event,
 				 struct perf_sample *sample,
 				 struct perf_evsel *evsel,
 				 struct thread *thread,
 				 struct addr_location *al)
 {
+	struct tables *tables = &tables_global;
+
 	switch (evsel->attr.type) {
 	case PERF_TYPE_TRACEPOINT:
 		python_process_tracepoint(sample, evsel, thread, al);
 		break;
 	/* Reserve for future process_hw/sw/raw APIs */
 	default:
-		python_process_general_event(sample, evsel, thread, al);
+		if (tables->db_export_mode)
+			db_export__sample(&tables->dbe, event, sample, evsel,
+					  thread, al);
+		else
+			python_process_general_event(sample, evsel, thread, al);
 	}
 }
 
@@ -589,11 +879,79 @@ error:
 	return -1;
 }
 
+#define SET_TABLE_HANDLER_(name, handler_name, table_name) do {		\
+	tables->handler_name = get_handler(#table_name);		\
+	if (tables->handler_name)					\
+		tables->dbe.export_ ## name = python_export_ ## name;	\
+} while (0)
+
+#define SET_TABLE_HANDLER(name) \
+	SET_TABLE_HANDLER_(name, name ## _handler, name ## _table)
+
+static void set_table_handlers(struct tables *tables)
+{
+	const char *perf_db_export_mode = "perf_db_export_mode";
+	const char *perf_db_export_calls = "perf_db_export_calls";
+	PyObject *db_export_mode, *db_export_calls;
+	bool export_calls = false;
+	int ret;
+
+	memset(tables, 0, sizeof(struct tables));
+	if (db_export__init(&tables->dbe))
+		Py_FatalError("failed to initialize export");
+
+	db_export_mode = PyDict_GetItemString(main_dict, perf_db_export_mode);
+	if (!db_export_mode)
+		return;
+
+	ret = PyObject_IsTrue(db_export_mode);
+	if (ret == -1)
+		handler_call_die(perf_db_export_mode);
+	if (!ret)
+		return;
+
+	tables->dbe.crp = NULL;
+	db_export_calls = PyDict_GetItemString(main_dict, perf_db_export_calls);
+	if (db_export_calls) {
+		ret = PyObject_IsTrue(db_export_calls);
+		if (ret == -1)
+			handler_call_die(perf_db_export_calls);
+		export_calls = !!ret;
+	}
+
+	if (export_calls) {
+		tables->dbe.crp =
+			call_return_processor__new(python_process_call_return,
+						   &tables->dbe);
+		if (!tables->dbe.crp)
+			Py_FatalError("failed to create calls processor");
+	}
+
+	tables->db_export_mode = true;
+	/*
+	 * Reserve per symbol space for symbol->db_id via symbol__priv()
+	 */
+	symbol_conf.priv_size = sizeof(u64);
+
+	SET_TABLE_HANDLER(evsel);
+	SET_TABLE_HANDLER(machine);
+	SET_TABLE_HANDLER(thread);
+	SET_TABLE_HANDLER(comm);
+	SET_TABLE_HANDLER(comm_thread);
+	SET_TABLE_HANDLER(dso);
+	SET_TABLE_HANDLER(symbol);
+	SET_TABLE_HANDLER(branch_type);
+	SET_TABLE_HANDLER(sample);
+	SET_TABLE_HANDLER(call_path);
+	SET_TABLE_HANDLER(call_return);
+}
+
 /*
  * Start trace script
  */
 static int python_start_script(const char *script, int argc, const char **argv)
 {
+	struct tables *tables = &tables_global;
 	const char **command_line;
 	char buf[PATH_MAX];
 	int i, err = 0;
@@ -632,6 +990,14 @@ static int python_start_script(const char *script, int argc, const char **argv)
 
 	free(command_line);
 
+	set_table_handlers(tables);
+
+	if (tables->db_export_mode) {
+		err = db_export__branch_types(&tables->dbe);
+		if (err)
+			goto error;
+	}
+
 	return err;
 error:
 	Py_Finalize();
@@ -642,7 +1008,9 @@ error:
 
 static int python_flush_script(void)
 {
-	return 0;
+	struct tables *tables = &tables_global;
+
+	return db_export__flush(&tables->dbe);
 }
 
 /*
@@ -650,8 +1018,12 @@ static int python_flush_script(void)
  */
 static int python_stop_script(void)
 {
+	struct tables *tables = &tables_global;
+
 	try_call_object("trace_end", NULL);
 
+	db_export__exit(&tables->dbe);
+
 	Py_XDECREF(main_dict);
 	Py_XDECREF(main_module);
 	Py_Finalize();
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 6702ac28754b..6ac62ae6b8fa 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -228,6 +228,15 @@ static int process_finished_round(struct perf_tool *tool,
 				  union perf_event *event,
 				  struct perf_session *session);
 
+static int process_id_index_stub(struct perf_tool *tool __maybe_unused,
+				 union perf_event *event __maybe_unused,
+				 struct perf_session *perf_session
+				 __maybe_unused)
+{
+	dump_printf(": unhandled!\n");
+	return 0;
+}
+
 void perf_tool__fill_defaults(struct perf_tool *tool)
 {
 	if (tool->sample == NULL)
@@ -262,6 +271,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
 		else
 			tool->finished_round = process_finished_round_stub;
 	}
+	if (tool->id_index == NULL)
+		tool->id_index = process_id_index_stub;
 }
  
 static void swap_sample_id_all(union perf_event *event, void *data)
@@ -460,6 +471,7 @@ static perf_event__swap_op perf_event__swap_ops[] = {
 	[PERF_RECORD_HEADER_EVENT_TYPE]	  = perf_event__event_type_swap,
 	[PERF_RECORD_HEADER_TRACING_DATA] = perf_event__tracing_data_swap,
 	[PERF_RECORD_HEADER_BUILD_ID]	  = NULL,
+	[PERF_RECORD_ID_INDEX]		  = perf_event__all64_swap,
 	[PERF_RECORD_HEADER_MAX]	  = NULL,
 };
 
@@ -580,15 +592,46 @@ static void regs_dump__printf(u64 mask, u64 *regs)
 	}
 }
 
+static const char *regs_abi[] = {
+	[PERF_SAMPLE_REGS_ABI_NONE] = "none",
+	[PERF_SAMPLE_REGS_ABI_32] = "32-bit",
+	[PERF_SAMPLE_REGS_ABI_64] = "64-bit",
+};
+
+static inline const char *regs_dump_abi(struct regs_dump *d)
+{
+	if (d->abi > PERF_SAMPLE_REGS_ABI_64)
+		return "unknown";
+
+	return regs_abi[d->abi];
+}
+
+static void regs__printf(const char *type, struct regs_dump *regs)
+{
+	u64 mask = regs->mask;
+
+	printf("... %s regs: mask 0x%" PRIx64 " ABI %s\n",
+	       type,
+	       mask,
+	       regs_dump_abi(regs));
+
+	regs_dump__printf(mask, regs->regs);
+}
+
 static void regs_user__printf(struct perf_sample *sample)
 {
 	struct regs_dump *user_regs = &sample->user_regs;
 
-	if (user_regs->regs) {
-		u64 mask = user_regs->mask;
-		printf("... user regs: mask 0x%" PRIx64 "\n", mask);
-		regs_dump__printf(mask, user_regs->regs);
-	}
+	if (user_regs->regs)
+		regs__printf("user", user_regs);
+}
+
+static void regs_intr__printf(struct perf_sample *sample)
+{
+	struct regs_dump *intr_regs = &sample->intr_regs;
+
+	if (intr_regs->regs)
+		regs__printf("intr", intr_regs);
 }
 
 static void stack_user__printf(struct stack_dump *dump)
@@ -687,6 +730,9 @@ static void dump_sample(struct perf_evsel *evsel, union perf_event *event,
 	if (sample_type & PERF_SAMPLE_REGS_USER)
 		regs_user__printf(sample);
 
+	if (sample_type & PERF_SAMPLE_REGS_INTR)
+		regs_intr__printf(sample);
+
 	if (sample_type & PERF_SAMPLE_STACK_USER)
 		stack_user__printf(&sample->user_stack);
 
@@ -888,11 +934,26 @@ static s64 perf_session__process_user_event(struct perf_session *session,
 		return tool->build_id(tool, event, session);
 	case PERF_RECORD_FINISHED_ROUND:
 		return tool->finished_round(tool, event, session);
+	case PERF_RECORD_ID_INDEX:
+		return tool->id_index(tool, event, session);
 	default:
 		return -EINVAL;
 	}
 }
 
+int perf_session__deliver_synth_event(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_tool *tool)
+{
+	events_stats__inc(&session->stats, event->header.type);
+
+	if (event->header.type >= PERF_RECORD_USER_TYPE_START)
+		return perf_session__process_user_event(session, event, tool, 0);
+
+	return perf_session__deliver_event(session, event, sample, tool, 0);
+}
+
 static void event_swap(union perf_event *event, bool sample_id_all)
 {
 	perf_event__swap_op swap;
@@ -1417,9 +1478,9 @@ void perf_evsel__print_ip(struct perf_evsel *evsel, struct perf_sample *sample,
 	if (symbol_conf.use_callchain && sample->callchain) {
 		struct addr_location node_al;
 
-		if (machine__resolve_callchain(al->machine, evsel, al->thread,
-					       sample, NULL, NULL,
-					       PERF_MAX_STACK_DEPTH) != 0) {
+		if (thread__resolve_callchain(al->thread, evsel,
+					      sample, NULL, NULL,
+					      PERF_MAX_STACK_DEPTH) != 0) {
 			if (verbose)
 				error("Failed to resolve callchain. Skipping\n");
 			return;
@@ -1594,3 +1655,111 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 out:
 	return err;
 }
+
+int perf_event__process_id_index(struct perf_tool *tool __maybe_unused,
+				 union perf_event *event,
+				 struct perf_session *session)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct id_index_event *ie = &event->id_index;
+	size_t i, nr, max_nr;
+
+	max_nr = (ie->header.size - sizeof(struct id_index_event)) /
+		 sizeof(struct id_index_entry);
+	nr = ie->nr;
+	if (nr > max_nr)
+		return -EINVAL;
+
+	if (dump_trace)
+		fprintf(stdout, " nr: %zu\n", nr);
+
+	for (i = 0; i < nr; i++) {
+		struct id_index_entry *e = &ie->entries[i];
+		struct perf_sample_id *sid;
+
+		if (dump_trace) {
+			fprintf(stdout,	" ... id: %"PRIu64, e->id);
+			fprintf(stdout,	"  idx: %"PRIu64, e->idx);
+			fprintf(stdout,	"  cpu: %"PRId64, e->cpu);
+			fprintf(stdout,	"  tid: %"PRId64"\n", e->tid);
+		}
+
+		sid = perf_evlist__id2sid(evlist, e->id);
+		if (!sid)
+			return -ENOENT;
+		sid->idx = e->idx;
+		sid->cpu = e->cpu;
+		sid->tid = e->tid;
+	}
+	return 0;
+}
+
+int perf_event__synthesize_id_index(struct perf_tool *tool,
+				    perf_event__handler_t process,
+				    struct perf_evlist *evlist,
+				    struct machine *machine)
+{
+	union perf_event *ev;
+	struct perf_evsel *evsel;
+	size_t nr = 0, i = 0, sz, max_nr, n;
+	int err;
+
+	pr_debug2("Synthesizing id index\n");
+
+	max_nr = (UINT16_MAX - sizeof(struct id_index_event)) /
+		 sizeof(struct id_index_entry);
+
+	evlist__for_each(evlist, evsel)
+		nr += evsel->ids;
+
+	n = nr > max_nr ? max_nr : nr;
+	sz = sizeof(struct id_index_event) + n * sizeof(struct id_index_entry);
+	ev = zalloc(sz);
+	if (!ev)
+		return -ENOMEM;
+
+	ev->id_index.header.type = PERF_RECORD_ID_INDEX;
+	ev->id_index.header.size = sz;
+	ev->id_index.nr = n;
+
+	evlist__for_each(evlist, evsel) {
+		u32 j;
+
+		for (j = 0; j < evsel->ids; j++) {
+			struct id_index_entry *e;
+			struct perf_sample_id *sid;
+
+			if (i >= n) {
+				err = process(tool, ev, NULL, machine);
+				if (err)
+					goto out_err;
+				nr -= n;
+				i = 0;
+			}
+
+			e = &ev->id_index.entries[i++];
+
+			e->id = evsel->id[j];
+
+			sid = perf_evlist__id2sid(evlist, e->id);
+			if (!sid) {
+				free(ev);
+				return -ENOENT;
+			}
+
+			e->idx = sid->idx;
+			e->cpu = sid->cpu;
+			e->tid = sid->tid;
+		}
+	}
+
+	sz = sizeof(struct id_index_event) + nr * sizeof(struct id_index_entry);
+	ev->id_index.header.size = sz;
+	ev->id_index.nr = nr;
+
+	err = process(tool, ev, NULL, machine);
+out_err:
+	free(ev);
+
+	return err;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index a4be851f1a90..dc26ebf60fe4 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -126,4 +126,19 @@ int __perf_session__set_tracepoints_handlers(struct perf_session *session,
 extern volatile int session_done;
 
 #define session_done()	ACCESS_ONCE(session_done)
+
+int perf_session__deliver_synth_event(struct perf_session *session,
+				      union perf_event *event,
+				      struct perf_sample *sample,
+				      struct perf_tool *tool);
+
+int perf_event__process_id_index(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session);
+
+int perf_event__synthesize_id_index(struct perf_tool *tool,
+				    perf_event__handler_t process,
+				    struct perf_evlist *evlist,
+				    struct machine *machine);
+
 #endif /* __PERF_SESSION_H */
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 9402885a77f3..9139dda9f9a3 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -291,7 +291,8 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 		else {
 			struct map *map = left->ms.map;
 			left->srcline = get_srcline(map->dso,
-					    map__rip_2objdump(map, left->ip));
+					   map__rip_2objdump(map, left->ip),
+						    left->ms.sym, true);
 		}
 	}
 	if (!right->srcline) {
@@ -300,7 +301,8 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 		else {
 			struct map *map = right->ms.map;
 			right->srcline = get_srcline(map->dso,
-					    map__rip_2objdump(map, right->ip));
+					     map__rip_2objdump(map, right->ip),
+						     right->ms.sym, true);
 		}
 	}
 	return strcmp(right->srcline, left->srcline);
@@ -309,7 +311,7 @@ sort__srcline_cmp(struct hist_entry *left, struct hist_entry *right)
 static int hist_entry__srcline_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
-	return repsep_snprintf(bf, size, "%*.*-s", width, width, he->srcline);
+	return repsep_snprintf(bf, size, "%-*.*s", width, width, he->srcline);
 }
 
 struct sort_entry sort_srcline = {
diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
index f3e4bc5fe5d2..e73b6a5c9e0f 100644
--- a/tools/perf/util/srcline.c
+++ b/tools/perf/util/srcline.c
@@ -8,6 +8,8 @@
 #include "util/util.h"
 #include "util/debug.h"
 
+#include "symbol.h"
+
 #ifdef HAVE_LIBBFD_SUPPORT
 
 /*
@@ -250,7 +252,8 @@ void dso__free_a2l(struct dso *dso __maybe_unused)
  */
 #define A2L_FAIL_LIMIT 123
 
-char *get_srcline(struct dso *dso, unsigned long addr)
+char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym,
+		  bool show_sym)
 {
 	char *file = NULL;
 	unsigned line = 0;
@@ -258,7 +261,7 @@ char *get_srcline(struct dso *dso, unsigned long addr)
 	const char *dso_name;
 
 	if (!dso->has_srcline)
-		return SRCLINE_UNKNOWN;
+		goto out;
 
 	if (dso->symsrc_filename)
 		dso_name = dso->symsrc_filename;
@@ -274,7 +277,7 @@ char *get_srcline(struct dso *dso, unsigned long addr)
 	if (!addr2line(dso_name, addr, &file, &line, dso))
 		goto out;
 
-	if (asprintf(&srcline, "%s:%u", file, line) < 0) {
+	if (asprintf(&srcline, "%s:%u", basename(file), line) < 0) {
 		free(file);
 		goto out;
 	}
@@ -289,7 +292,13 @@ out:
 		dso->has_srcline = 0;
 		dso__free_a2l(dso);
 	}
-	return SRCLINE_UNKNOWN;
+	if (sym) {
+		if (asprintf(&srcline, "%s+%ld", show_sym ? sym->name : "",
+					addr - sym->start) < 0)
+			return SRCLINE_UNKNOWN;
+	} else if (asprintf(&srcline, "%s[%lx]", dso->short_name, addr) < 0)
+		return SRCLINE_UNKNOWN;
+	return srcline;
 }
 
 void free_srcline(char *srcline)
diff --git a/tools/perf/util/symbol-elf.c b/tools/perf/util/symbol-elf.c
index 1e23a5bfb044..06fcd1bf98b6 100644
--- a/tools/perf/util/symbol-elf.c
+++ b/tools/perf/util/symbol-elf.c
@@ -11,6 +11,27 @@
 #include <symbol/kallsyms.h>
 #include "debug.h"
 
+#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
+extern char *cplus_demangle(const char *, int);
+
+static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
+{
+	return cplus_demangle(c, i);
+}
+#else
+#ifdef NO_DEMANGLE
+static inline char *bfd_demangle(void __maybe_unused *v,
+				 const char __maybe_unused *c,
+				 int __maybe_unused i)
+{
+	return NULL;
+}
+#else
+#define PACKAGE 'perf'
+#include <bfd.h>
+#endif
+#endif
+
 #ifndef HAVE_ELF_GETPHDRNUM_SUPPORT
 static int elf_getphdrnum(Elf *elf, size_t *dst)
 {
@@ -546,6 +567,35 @@ static int dso__swap_init(struct dso *dso, unsigned char eidata)
 	return 0;
 }
 
+static int decompress_kmodule(struct dso *dso, const char *name,
+			      enum dso_binary_type type)
+{
+	int fd;
+	const char *ext = strrchr(name, '.');
+	char tmpbuf[] = "/tmp/perf-kmod-XXXXXX";
+
+	if ((type != DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP &&
+	     type != DSO_BINARY_TYPE__GUEST_KMODULE_COMP) ||
+	    type != dso->symtab_type)
+		return -1;
+
+	if (!ext || !is_supported_compression(ext + 1))
+		return -1;
+
+	fd = mkstemp(tmpbuf);
+	if (fd < 0)
+		return -1;
+
+	if (!decompress_to_file(ext + 1, name, fd)) {
+		close(fd);
+		fd = -1;
+	}
+
+	unlink(tmpbuf);
+
+	return fd;
+}
+
 bool symsrc__possibly_runtime(struct symsrc *ss)
 {
 	return ss->dynsym || ss->opdsec;
@@ -571,7 +621,11 @@ int symsrc__init(struct symsrc *ss, struct dso *dso, const char *name,
 	Elf *elf;
 	int fd;
 
-	fd = open(name, O_RDONLY);
+	if (dso__needs_decompress(dso))
+		fd = decompress_kmodule(dso, name, type);
+	else
+		fd = open(name, O_RDONLY);
+
 	if (fd < 0)
 		return -1;
 
diff --git a/tools/perf/util/symbol-minimal.c b/tools/perf/util/symbol-minimal.c
index c9541fea9514..fa585c63f56a 100644
--- a/tools/perf/util/symbol-minimal.c
+++ b/tools/perf/util/symbol-minimal.c
@@ -341,7 +341,6 @@ int dso__load_sym(struct dso *dso, struct map *map __maybe_unused,
 
 	if (filename__read_build_id(ss->name, build_id, BUILD_ID_SIZE) > 0) {
 		dso__set_build_id(dso, build_id);
-		return 1;
 	}
 	return 0;
 }
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 078331140d8c..c24c5b83156c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -51,7 +51,9 @@ static enum dso_binary_type binary_type_symtab[] = {
 	DSO_BINARY_TYPE__BUILDID_DEBUGINFO,
 	DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
 	DSO_BINARY_TYPE__GUEST_KMODULE,
+	DSO_BINARY_TYPE__GUEST_KMODULE_COMP,
 	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE,
+	DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP,
 	DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO,
 	DSO_BINARY_TYPE__NOT_FOUND,
 };
@@ -1300,7 +1302,9 @@ static bool dso__is_compatible_symtab_type(struct dso *dso, bool kmod,
 		return dso->kernel == DSO_TYPE_GUEST_KERNEL;
 
 	case DSO_BINARY_TYPE__GUEST_KMODULE:
+	case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
 	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
+	case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
 		/*
 		 * kernel modules know their symtab type - it's set when
 		 * creating a module dso in machine__new_module().
@@ -1368,7 +1372,9 @@ int dso__load(struct dso *dso, struct map *map, symbol_filter_t filter)
 		return -1;
 
 	kmod = dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE ||
-		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE;
+		dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE ||
+		dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
 
 	/*
 	 * Iterate over candidate debug images.
@@ -1505,12 +1511,10 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 			   symbol_filter_t filter)
 {
 	int i, err = 0;
-	char *filename;
+	char *filename = NULL;
 
-	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
-		 vmlinux_path__nr_entries + 1);
-
-	filename = dso__build_id_filename(dso, NULL, 0);
+	if (!symbol_conf.ignore_vmlinux_buildid)
+		filename = dso__build_id_filename(dso, NULL, 0);
 	if (filename != NULL) {
 		err = dso__load_vmlinux(dso, map, filename, true, filter);
 		if (err > 0)
@@ -1518,6 +1522,9 @@ int dso__load_vmlinux_path(struct dso *dso, struct map *map,
 		free(filename);
 	}
 
+	pr_debug("Looking at the vmlinux_path (%d entries long)\n",
+		 vmlinux_path__nr_entries + 1);
+
 	for (i = 0; i < vmlinux_path__nr_entries; ++i) {
 		err = dso__load_vmlinux(dso, map, vmlinux_path[i], false, filter);
 		if (err > 0)
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index eb2c19bf8d90..9d602e9c6f59 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -23,27 +23,6 @@
 
 #include "dso.h"
 
-#ifdef HAVE_CPLUS_DEMANGLE_SUPPORT
-extern char *cplus_demangle(const char *, int);
-
-static inline char *bfd_demangle(void __maybe_unused *v, const char *c, int i)
-{
-	return cplus_demangle(c, i);
-}
-#else
-#ifdef NO_DEMANGLE
-static inline char *bfd_demangle(void __maybe_unused *v,
-				 const char __maybe_unused *c,
-				 int __maybe_unused i)
-{
-	return NULL;
-}
-#else
-#define PACKAGE 'perf'
-#include <bfd.h>
-#endif
-#endif
-
 /*
  * libelf 0.8.x and earlier do not support ELF_C_READ_MMAP;
  * for newer versions we can use mmap to reduce memory usage:
@@ -105,6 +84,7 @@ struct symbol_conf {
 	unsigned short	nr_events;
 	bool		try_vmlinux_path,
 			ignore_vmlinux,
+			ignore_vmlinux_buildid,
 			show_kernel_path,
 			use_modules,
 			sort_by_name,
@@ -122,7 +102,8 @@ struct symbol_conf {
 			demangle,
 			demangle_kernel,
 			filter_relative,
-			show_hist_headers;
+			show_hist_headers,
+			branch_callstack;
 	const char	*vmlinux_name,
 			*kallsyms_name,
 			*source_prefix,
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
new file mode 100644
index 000000000000..9ed59a452d1f
--- /dev/null
+++ b/tools/perf/util/thread-stack.c
@@ -0,0 +1,747 @@
+/*
+ * thread-stack.c: Synthesize a thread's stack using call / return events
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ */
+
+#include <linux/rbtree.h>
+#include <linux/list.h>
+#include "thread.h"
+#include "event.h"
+#include "machine.h"
+#include "util.h"
+#include "debug.h"
+#include "symbol.h"
+#include "comm.h"
+#include "thread-stack.h"
+
+#define CALL_PATH_BLOCK_SHIFT 8
+#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT)
+#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1)
+
+struct call_path_block {
+	struct call_path cp[CALL_PATH_BLOCK_SIZE];
+	struct list_head node;
+};
+
+/**
+ * struct call_path_root - root of all call paths.
+ * @call_path: root call path
+ * @blocks: list of blocks to store call paths
+ * @next: next free space
+ * @sz: number of spaces
+ */
+struct call_path_root {
+	struct call_path call_path;
+	struct list_head blocks;
+	size_t next;
+	size_t sz;
+};
+
+/**
+ * struct call_return_processor - provides a call-back to consume call-return
+ *                                information.
+ * @cpr: call path root
+ * @process: call-back that accepts call/return information
+ * @data: anonymous data for call-back
+ */
+struct call_return_processor {
+	struct call_path_root *cpr;
+	int (*process)(struct call_return *cr, void *data);
+	void *data;
+};
+
+#define STACK_GROWTH 2048
+
+/**
+ * struct thread_stack_entry - thread stack entry.
+ * @ret_addr: return address
+ * @timestamp: timestamp (if known)
+ * @ref: external reference (e.g. db_id of sample)
+ * @branch_count: the branch count when the entry was created
+ * @cp: call path
+ * @no_call: a 'call' was not seen
+ */
+struct thread_stack_entry {
+	u64 ret_addr;
+	u64 timestamp;
+	u64 ref;
+	u64 branch_count;
+	struct call_path *cp;
+	bool no_call;
+};
+
+/**
+ * struct thread_stack - thread stack constructed from 'call' and 'return'
+ *                       branch samples.
+ * @stack: array that holds the stack
+ * @cnt: number of entries in the stack
+ * @sz: current maximum stack size
+ * @trace_nr: current trace number
+ * @branch_count: running branch count
+ * @kernel_start: kernel start address
+ * @last_time: last timestamp
+ * @crp: call/return processor
+ * @comm: current comm
+ */
+struct thread_stack {
+	struct thread_stack_entry *stack;
+	size_t cnt;
+	size_t sz;
+	u64 trace_nr;
+	u64 branch_count;
+	u64 kernel_start;
+	u64 last_time;
+	struct call_return_processor *crp;
+	struct comm *comm;
+};
+
+static int thread_stack__grow(struct thread_stack *ts)
+{
+	struct thread_stack_entry *new_stack;
+	size_t sz, new_sz;
+
+	new_sz = ts->sz + STACK_GROWTH;
+	sz = new_sz * sizeof(struct thread_stack_entry);
+
+	new_stack = realloc(ts->stack, sz);
+	if (!new_stack)
+		return -ENOMEM;
+
+	ts->stack = new_stack;
+	ts->sz = new_sz;
+
+	return 0;
+}
+
+static struct thread_stack *thread_stack__new(struct thread *thread,
+					      struct call_return_processor *crp)
+{
+	struct thread_stack *ts;
+
+	ts = zalloc(sizeof(struct thread_stack));
+	if (!ts)
+		return NULL;
+
+	if (thread_stack__grow(ts)) {
+		free(ts);
+		return NULL;
+	}
+
+	if (thread->mg && thread->mg->machine)
+		ts->kernel_start = machine__kernel_start(thread->mg->machine);
+	else
+		ts->kernel_start = 1ULL << 63;
+	ts->crp = crp;
+
+	return ts;
+}
+
+static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
+{
+	int err = 0;
+
+	if (ts->cnt == ts->sz) {
+		err = thread_stack__grow(ts);
+		if (err) {
+			pr_warning("Out of memory: discarding thread stack\n");
+			ts->cnt = 0;
+		}
+	}
+
+	ts->stack[ts->cnt++].ret_addr = ret_addr;
+
+	return err;
+}
+
+static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
+{
+	size_t i;
+
+	/*
+	 * In some cases there may be functions which are not seen to return.
+	 * For example when setjmp / longjmp has been used.  Or the perf context
+	 * switch in the kernel which doesn't stop and start tracing in exactly
+	 * the same code path.  When that happens the return address will be
+	 * further down the stack.  If the return address is not found at all,
+	 * we assume the opposite (i.e. this is a return for a call that wasn't
+	 * seen for some reason) and leave the stack alone.
+	 */
+	for (i = ts->cnt; i; ) {
+		if (ts->stack[--i].ret_addr == ret_addr) {
+			ts->cnt = i;
+			return;
+		}
+	}
+}
+
+static bool thread_stack__in_kernel(struct thread_stack *ts)
+{
+	if (!ts->cnt)
+		return false;
+
+	return ts->stack[ts->cnt - 1].cp->in_kernel;
+}
+
+static int thread_stack__call_return(struct thread *thread,
+				     struct thread_stack *ts, size_t idx,
+				     u64 timestamp, u64 ref, bool no_return)
+{
+	struct call_return_processor *crp = ts->crp;
+	struct thread_stack_entry *tse;
+	struct call_return cr = {
+		.thread = thread,
+		.comm = ts->comm,
+		.db_id = 0,
+	};
+
+	tse = &ts->stack[idx];
+	cr.cp = tse->cp;
+	cr.call_time = tse->timestamp;
+	cr.return_time = timestamp;
+	cr.branch_count = ts->branch_count - tse->branch_count;
+	cr.call_ref = tse->ref;
+	cr.return_ref = ref;
+	if (tse->no_call)
+		cr.flags |= CALL_RETURN_NO_CALL;
+	if (no_return)
+		cr.flags |= CALL_RETURN_NO_RETURN;
+
+	return crp->process(&cr, crp->data);
+}
+
+static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+{
+	struct call_return_processor *crp = ts->crp;
+	int err;
+
+	if (!crp) {
+		ts->cnt = 0;
+		return 0;
+	}
+
+	while (ts->cnt) {
+		err = thread_stack__call_return(thread, ts, --ts->cnt,
+						ts->last_time, 0, true);
+		if (err) {
+			pr_err("Error flushing thread stack!\n");
+			ts->cnt = 0;
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+			u64 to_ip, u16 insn_len, u64 trace_nr)
+{
+	if (!thread)
+		return -EINVAL;
+
+	if (!thread->ts) {
+		thread->ts = thread_stack__new(thread, NULL);
+		if (!thread->ts) {
+			pr_warning("Out of memory: no thread stack\n");
+			return -ENOMEM;
+		}
+		thread->ts->trace_nr = trace_nr;
+	}
+
+	/*
+	 * When the trace is discontinuous, the trace_nr changes.  In that case
+	 * the stack might be completely invalid.  Better to report nothing than
+	 * to report something misleading, so flush the stack.
+	 */
+	if (trace_nr != thread->ts->trace_nr) {
+		if (thread->ts->trace_nr)
+			thread_stack__flush(thread, thread->ts);
+		thread->ts->trace_nr = trace_nr;
+	}
+
+	/* Stop here if thread_stack__process() is in use */
+	if (thread->ts->crp)
+		return 0;
+
+	if (flags & PERF_IP_FLAG_CALL) {
+		u64 ret_addr;
+
+		if (!to_ip)
+			return 0;
+		ret_addr = from_ip + insn_len;
+		if (ret_addr == to_ip)
+			return 0; /* Zero-length calls are excluded */
+		return thread_stack__push(thread->ts, ret_addr);
+	} else if (flags & PERF_IP_FLAG_RETURN) {
+		if (!from_ip)
+			return 0;
+		thread_stack__pop(thread->ts, to_ip);
+	}
+
+	return 0;
+}
+
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
+{
+	if (!thread || !thread->ts)
+		return;
+
+	if (trace_nr != thread->ts->trace_nr) {
+		if (thread->ts->trace_nr)
+			thread_stack__flush(thread, thread->ts);
+		thread->ts->trace_nr = trace_nr;
+	}
+}
+
+void thread_stack__free(struct thread *thread)
+{
+	if (thread->ts) {
+		thread_stack__flush(thread, thread->ts);
+		zfree(&thread->ts->stack);
+		zfree(&thread->ts);
+	}
+}
+
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+			  size_t sz, u64 ip)
+{
+	size_t i;
+
+	if (!thread || !thread->ts)
+		chain->nr = 1;
+	else
+		chain->nr = min(sz, thread->ts->cnt + 1);
+
+	chain->ips[0] = ip;
+
+	for (i = 1; i < chain->nr; i++)
+		chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+}
+
+static void call_path__init(struct call_path *cp, struct call_path *parent,
+			    struct symbol *sym, u64 ip, bool in_kernel)
+{
+	cp->parent = parent;
+	cp->sym = sym;
+	cp->ip = sym ? 0 : ip;
+	cp->db_id = 0;
+	cp->in_kernel = in_kernel;
+	RB_CLEAR_NODE(&cp->rb_node);
+	cp->children = RB_ROOT;
+}
+
+static struct call_path_root *call_path_root__new(void)
+{
+	struct call_path_root *cpr;
+
+	cpr = zalloc(sizeof(struct call_path_root));
+	if (!cpr)
+		return NULL;
+	call_path__init(&cpr->call_path, NULL, NULL, 0, false);
+	INIT_LIST_HEAD(&cpr->blocks);
+	return cpr;
+}
+
+static void call_path_root__free(struct call_path_root *cpr)
+{
+	struct call_path_block *pos, *n;
+
+	list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
+		list_del(&pos->node);
+		free(pos);
+	}
+	free(cpr);
+}
+
+static struct call_path *call_path__new(struct call_path_root *cpr,
+					struct call_path *parent,
+					struct symbol *sym, u64 ip,
+					bool in_kernel)
+{
+	struct call_path_block *cpb;
+	struct call_path *cp;
+	size_t n;
+
+	if (cpr->next < cpr->sz) {
+		cpb = list_last_entry(&cpr->blocks, struct call_path_block,
+				      node);
+	} else {
+		cpb = zalloc(sizeof(struct call_path_block));
+		if (!cpb)
+			return NULL;
+		list_add_tail(&cpb->node, &cpr->blocks);
+		cpr->sz += CALL_PATH_BLOCK_SIZE;
+	}
+
+	n = cpr->next++ & CALL_PATH_BLOCK_MASK;
+	cp = &cpb->cp[n];
+
+	call_path__init(cp, parent, sym, ip, in_kernel);
+
+	return cp;
+}
+
+static struct call_path *call_path__findnew(struct call_path_root *cpr,
+					    struct call_path *parent,
+					    struct symbol *sym, u64 ip, u64 ks)
+{
+	struct rb_node **p;
+	struct rb_node *node_parent = NULL;
+	struct call_path *cp;
+	bool in_kernel = ip >= ks;
+
+	if (sym)
+		ip = 0;
+
+	if (!parent)
+		return call_path__new(cpr, parent, sym, ip, in_kernel);
+
+	p = &parent->children.rb_node;
+	while (*p != NULL) {
+		node_parent = *p;
+		cp = rb_entry(node_parent, struct call_path, rb_node);
+
+		if (cp->sym == sym && cp->ip == ip)
+			return cp;
+
+		if (sym < cp->sym || (sym == cp->sym && ip < cp->ip))
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	cp = call_path__new(cpr, parent, sym, ip, in_kernel);
+	if (!cp)
+		return NULL;
+
+	rb_link_node(&cp->rb_node, node_parent, p);
+	rb_insert_color(&cp->rb_node, &parent->children);
+
+	return cp;
+}
+
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+			   void *data)
+{
+	struct call_return_processor *crp;
+
+	crp = zalloc(sizeof(struct call_return_processor));
+	if (!crp)
+		return NULL;
+	crp->cpr = call_path_root__new();
+	if (!crp->cpr)
+		goto out_free;
+	crp->process = process;
+	crp->data = data;
+	return crp;
+
+out_free:
+	free(crp);
+	return NULL;
+}
+
+void call_return_processor__free(struct call_return_processor *crp)
+{
+	if (crp) {
+		call_path_root__free(crp->cpr);
+		free(crp);
+	}
+}
+
+static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
+				 u64 timestamp, u64 ref, struct call_path *cp,
+				 bool no_call)
+{
+	struct thread_stack_entry *tse;
+	int err;
+
+	if (ts->cnt == ts->sz) {
+		err = thread_stack__grow(ts);
+		if (err)
+			return err;
+	}
+
+	tse = &ts->stack[ts->cnt++];
+	tse->ret_addr = ret_addr;
+	tse->timestamp = timestamp;
+	tse->ref = ref;
+	tse->branch_count = ts->branch_count;
+	tse->cp = cp;
+	tse->no_call = no_call;
+
+	return 0;
+}
+
+static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts,
+				u64 ret_addr, u64 timestamp, u64 ref,
+				struct symbol *sym)
+{
+	int err;
+
+	if (!ts->cnt)
+		return 1;
+
+	if (ts->cnt == 1) {
+		struct thread_stack_entry *tse = &ts->stack[0];
+
+		if (tse->cp->sym == sym)
+			return thread_stack__call_return(thread, ts, --ts->cnt,
+							 timestamp, ref, false);
+	}
+
+	if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) {
+		return thread_stack__call_return(thread, ts, --ts->cnt,
+						 timestamp, ref, false);
+	} else {
+		size_t i = ts->cnt - 1;
+
+		while (i--) {
+			if (ts->stack[i].ret_addr != ret_addr)
+				continue;
+			i += 1;
+			while (ts->cnt > i) {
+				err = thread_stack__call_return(thread, ts,
+								--ts->cnt,
+								timestamp, ref,
+								true);
+				if (err)
+					return err;
+			}
+			return thread_stack__call_return(thread, ts, --ts->cnt,
+							 timestamp, ref, false);
+		}
+	}
+
+	return 1;
+}
+
+static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
+				struct perf_sample *sample,
+				struct addr_location *from_al,
+				struct addr_location *to_al, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp;
+	struct symbol *sym;
+	u64 ip;
+
+	if (sample->ip) {
+		ip = sample->ip;
+		sym = from_al->sym;
+	} else if (sample->addr) {
+		ip = sample->addr;
+		sym = to_al->sym;
+	} else {
+		return 0;
+	}
+
+	cp = call_path__findnew(cpr, &cpr->call_path, sym, ip,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
+				     true);
+}
+
+static int thread_stack__no_call_return(struct thread *thread,
+					struct thread_stack *ts,
+					struct perf_sample *sample,
+					struct addr_location *from_al,
+					struct addr_location *to_al, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp, *parent;
+	u64 ks = ts->kernel_start;
+	int err;
+
+	if (sample->ip >= ks && sample->addr < ks) {
+		/* Return to userspace, so pop all kernel addresses */
+		while (thread_stack__in_kernel(ts)) {
+			err = thread_stack__call_return(thread, ts, --ts->cnt,
+							sample->time, ref,
+							true);
+			if (err)
+				return err;
+		}
+
+		/* If the stack is empty, push the userspace address */
+		if (!ts->cnt) {
+			cp = call_path__findnew(cpr, &cpr->call_path,
+						to_al->sym, sample->addr,
+						ts->kernel_start);
+			if (!cp)
+				return -ENOMEM;
+			return thread_stack__push_cp(ts, 0, sample->time, ref,
+						     cp, true);
+		}
+	} else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
+		/* Return to userspace, so pop all kernel addresses */
+		while (thread_stack__in_kernel(ts)) {
+			err = thread_stack__call_return(thread, ts, --ts->cnt,
+							sample->time, ref,
+							true);
+			if (err)
+				return err;
+		}
+	}
+
+	if (ts->cnt)
+		parent = ts->stack[ts->cnt - 1].cp;
+	else
+		parent = &cpr->call_path;
+
+	/* This 'return' had no 'call', so push and pop top of stack */
+	cp = call_path__findnew(cpr, parent, from_al->sym, sample->ip,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
+				    true);
+	if (err)
+		return err;
+
+	return thread_stack__pop_cp(thread, ts, sample->addr, sample->time, ref,
+				    to_al->sym);
+}
+
+static int thread_stack__trace_begin(struct thread *thread,
+				     struct thread_stack *ts, u64 timestamp,
+				     u64 ref)
+{
+	struct thread_stack_entry *tse;
+	int err;
+
+	if (!ts->cnt)
+		return 0;
+
+	/* Pop trace end */
+	tse = &ts->stack[ts->cnt - 1];
+	if (tse->cp->sym == NULL && tse->cp->ip == 0) {
+		err = thread_stack__call_return(thread, ts, --ts->cnt,
+						timestamp, ref, false);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int thread_stack__trace_end(struct thread_stack *ts,
+				   struct perf_sample *sample, u64 ref)
+{
+	struct call_path_root *cpr = ts->crp->cpr;
+	struct call_path *cp;
+	u64 ret_addr;
+
+	/* No point having 'trace end' on the bottom of the stack */
+	if (!ts->cnt || (ts->cnt == 1 && ts->stack[0].ref == ref))
+		return 0;
+
+	cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp, NULL, 0,
+				ts->kernel_start);
+	if (!cp)
+		return -ENOMEM;
+
+	ret_addr = sample->ip + sample->insn_len;
+
+	return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
+				     false);
+}
+
+int thread_stack__process(struct thread *thread, struct comm *comm,
+			  struct perf_sample *sample,
+			  struct addr_location *from_al,
+			  struct addr_location *to_al, u64 ref,
+			  struct call_return_processor *crp)
+{
+	struct thread_stack *ts = thread->ts;
+	int err = 0;
+
+	if (ts) {
+		if (!ts->crp) {
+			/* Supersede thread_stack__event() */
+			thread_stack__free(thread);
+			thread->ts = thread_stack__new(thread, crp);
+			if (!thread->ts)
+				return -ENOMEM;
+			ts = thread->ts;
+			ts->comm = comm;
+		}
+	} else {
+		thread->ts = thread_stack__new(thread, crp);
+		if (!thread->ts)
+			return -ENOMEM;
+		ts = thread->ts;
+		ts->comm = comm;
+	}
+
+	/* Flush stack on exec */
+	if (ts->comm != comm && thread->pid_ == thread->tid) {
+		err = thread_stack__flush(thread, ts);
+		if (err)
+			return err;
+		ts->comm = comm;
+	}
+
+	/* If the stack is empty, put the current symbol on the stack */
+	if (!ts->cnt) {
+		err = thread_stack__bottom(thread, ts, sample, from_al, to_al,
+					   ref);
+		if (err)
+			return err;
+	}
+
+	ts->branch_count += 1;
+	ts->last_time = sample->time;
+
+	if (sample->flags & PERF_IP_FLAG_CALL) {
+		struct call_path_root *cpr = ts->crp->cpr;
+		struct call_path *cp;
+		u64 ret_addr;
+
+		if (!sample->ip || !sample->addr)
+			return 0;
+
+		ret_addr = sample->ip + sample->insn_len;
+		if (ret_addr == sample->addr)
+			return 0; /* Zero-length calls are excluded */
+
+		cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
+					to_al->sym, sample->addr,
+					ts->kernel_start);
+		if (!cp)
+			return -ENOMEM;
+		err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
+					    cp, false);
+	} else if (sample->flags & PERF_IP_FLAG_RETURN) {
+		if (!sample->ip || !sample->addr)
+			return 0;
+
+		err = thread_stack__pop_cp(thread, ts, sample->addr,
+					   sample->time, ref, from_al->sym);
+		if (err) {
+			if (err < 0)
+				return err;
+			err = thread_stack__no_call_return(thread, ts, sample,
+							   from_al, to_al, ref);
+		}
+	} else if (sample->flags & PERF_IP_FLAG_TRACE_BEGIN) {
+		err = thread_stack__trace_begin(thread, ts, sample->time, ref);
+	} else if (sample->flags & PERF_IP_FLAG_TRACE_END) {
+		err = thread_stack__trace_end(ts, sample, ref);
+	}
+
+	return err;
+}
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
new file mode 100644
index 000000000000..b843bbef8ba2
--- /dev/null
+++ b/tools/perf/util/thread-stack.h
@@ -0,0 +1,111 @@
+/*
+ * thread-stack.h: Synthesize a thread's stack using call / return events
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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.
+ *
+ */
+
+#ifndef __PERF_THREAD_STACK_H
+#define __PERF_THREAD_STACK_H
+
+#include <sys/types.h>
+
+#include <linux/types.h>
+#include <linux/rbtree.h>
+
+struct thread;
+struct comm;
+struct ip_callchain;
+struct symbol;
+struct dso;
+struct call_return_processor;
+struct comm;
+struct perf_sample;
+struct addr_location;
+
+/*
+ * Call/Return flags.
+ *
+ * CALL_RETURN_NO_CALL: 'return' but no matching 'call'
+ * CALL_RETURN_NO_RETURN: 'call' but no matching 'return'
+ */
+enum {
+	CALL_RETURN_NO_CALL	= 1 << 0,
+	CALL_RETURN_NO_RETURN	= 1 << 1,
+};
+
+/**
+ * struct call_return - paired call/return information.
+ * @thread: thread in which call/return occurred
+ * @comm: comm in which call/return occurred
+ * @cp: call path
+ * @call_time: timestamp of call (if known)
+ * @return_time: timestamp of return (if known)
+ * @branch_count: number of branches seen between call and return
+ * @call_ref: external reference to 'call' sample (e.g. db_id)
+ * @return_ref:  external reference to 'return' sample (e.g. db_id)
+ * @db_id: id used for db-export
+ * @flags: Call/Return flags
+ */
+struct call_return {
+	struct thread *thread;
+	struct comm *comm;
+	struct call_path *cp;
+	u64 call_time;
+	u64 return_time;
+	u64 branch_count;
+	u64 call_ref;
+	u64 return_ref;
+	u64 db_id;
+	u32 flags;
+};
+
+/**
+ * struct call_path - node in list of calls leading to a function call.
+ * @parent: call path to the parent function call
+ * @sym: symbol of function called
+ * @ip: only if sym is null, the ip of the function
+ * @db_id: id used for db-export
+ * @in_kernel: whether function is a in the kernel
+ * @rb_node: node in parent's tree of called functions
+ * @children: tree of call paths of functions called
+ *
+ * In combination with the call_return structure, the call_path structure
+ * defines a context-sensitve call-graph.
+ */
+struct call_path {
+	struct call_path *parent;
+	struct symbol *sym;
+	u64 ip;
+	u64 db_id;
+	bool in_kernel;
+	struct rb_node rb_node;
+	struct rb_root children;
+};
+
+int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+			u64 to_ip, u16 insn_len, u64 trace_nr);
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+			  size_t sz, u64 ip);
+void thread_stack__free(struct thread *thread);
+
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+			   void *data);
+void call_return_processor__free(struct call_return_processor *crp);
+int thread_stack__process(struct thread *thread, struct comm *comm,
+			  struct perf_sample *sample,
+			  struct addr_location *from_al,
+			  struct addr_location *to_al, u64 ref,
+			  struct call_return_processor *crp);
+
+#endif
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index c41411726c7a..9ebc8b1f9be5 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -4,6 +4,7 @@
 #include <string.h>
 #include "session.h"
 #include "thread.h"
+#include "thread-stack.h"
 #include "util.h"
 #include "debug.h"
 #include "comm.h"
@@ -15,7 +16,7 @@ int thread__init_map_groups(struct thread *thread, struct machine *machine)
 	pid_t pid = thread->pid_;
 
 	if (pid == thread->tid || pid == -1) {
-		thread->mg = map_groups__new();
+		thread->mg = map_groups__new(machine);
 	} else {
 		leader = machine__findnew_thread(machine, pid, pid);
 		if (leader)
@@ -66,6 +67,8 @@ void thread__delete(struct thread *thread)
 {
 	struct comm *comm, *tmp;
 
+	thread_stack__free(thread);
+
 	if (thread->mg) {
 		map_groups__put(thread->mg);
 		thread->mg = NULL;
@@ -100,15 +103,14 @@ struct comm *thread__exec_comm(const struct thread *thread)
 	return last;
 }
 
-/* CHECKME: time should always be 0 if event aren't ordered */
 int __thread__set_comm(struct thread *thread, const char *str, u64 timestamp,
 		       bool exec)
 {
 	struct comm *new, *curr = thread__comm(thread);
 	int err;
 
-	/* Override latest entry if it had no specific time coverage */
-	if (!curr->start && !curr->exec) {
+	/* Override the default :tid entry */
+	if (!thread->comm_set) {
 		err = comm__override(curr, str, timestamp, exec);
 		if (err)
 			return err;
@@ -198,7 +200,6 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread,
-					struct machine *machine,
 					enum map_type type, u64 addr,
 					struct addr_location *al)
 {
@@ -211,8 +212,7 @@ void thread__find_cpumode_addr_location(struct thread *thread,
 	};
 
 	for (i = 0; i < ARRAY_SIZE(cpumodes); i++) {
-		thread__find_addr_location(thread, machine, cpumodes[i], type,
-					   addr, al);
+		thread__find_addr_location(thread, cpumodes[i], type, addr, al);
 		if (al->map)
 			break;
 	}
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 8c75fa774706..160fd066a7d1 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -8,6 +8,8 @@
 #include "symbol.h"
 #include <strlist.h>
 
+struct thread_stack;
+
 struct thread {
 	union {
 		struct rb_node	 rb_node;
@@ -23,8 +25,10 @@ struct thread {
 	bool			dead; /* if set thread has exited */
 	struct list_head	comm_list;
 	int			comm_len;
+	u64			db_id;
 
 	void			*priv;
+	struct thread_stack	*ts;
 };
 
 struct machine;
@@ -54,16 +58,15 @@ void thread__insert_map(struct thread *thread, struct map *map);
 int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
-void thread__find_addr_map(struct thread *thread, struct machine *machine,
+void thread__find_addr_map(struct thread *thread,
 			   u8 cpumode, enum map_type type, u64 addr,
 			   struct addr_location *al);
 
-void thread__find_addr_location(struct thread *thread, struct machine *machine,
+void thread__find_addr_location(struct thread *thread,
 				u8 cpumode, enum map_type type, u64 addr,
 				struct addr_location *al);
 
 void thread__find_cpumode_addr_location(struct thread *thread,
-					struct machine *machine,
 					enum map_type type, u64 addr,
 					struct addr_location *al);
 
diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
index f11636966a0f..bb2708bbfaca 100644
--- a/tools/perf/util/tool.h
+++ b/tools/perf/util/tool.h
@@ -39,7 +39,8 @@ struct perf_tool {
 	event_attr_op	attr;
 	event_op2	tracing_data;
 	event_op2	finished_round,
-			build_id;
+			build_id,
+			id_index;
 	bool		ordered_events;
 	bool		ordering_requires_timestamps;
 };
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 7419768c38b1..2dcfe9a7c8d0 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -26,7 +26,7 @@ static int __report_module(struct addr_location *al, u64 ip,
 	Dwfl_Module *mod;
 	struct dso *dso = NULL;
 
-	thread__find_addr_location(ui->thread, ui->machine,
+	thread__find_addr_location(ui->thread,
 				   PERF_RECORD_MISC_USER,
 				   MAP__FUNCTION, ip, al);
 
@@ -89,7 +89,7 @@ static int access_dso_mem(struct unwind_info *ui, Dwarf_Addr addr,
 	struct addr_location al;
 	ssize_t size;
 
-	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, addr, &al);
 	if (!al.map) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
@@ -164,14 +164,14 @@ frame_callback(Dwfl_Frame *state, void *arg)
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-			struct machine *machine, struct thread *thread,
+			struct thread *thread,
 			struct perf_sample *data,
 			int max_stack)
 {
 	struct unwind_info ui = {
 		.sample		= data,
 		.thread		= thread,
-		.machine	= machine,
+		.machine	= thread->mg->machine,
 		.cb		= cb,
 		.arg		= arg,
 		.max_stack	= max_stack,
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 4d45c0dfe343..371219a6daf1 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -284,7 +284,7 @@ static struct map *find_map(unw_word_t ip, struct unwind_info *ui)
 {
 	struct addr_location al;
 
-	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, ip, &al);
 	return al.map;
 }
@@ -374,7 +374,7 @@ static int access_dso_mem(struct unwind_info *ui, unw_word_t addr,
 	struct addr_location al;
 	ssize_t size;
 
-	thread__find_addr_map(ui->thread, ui->machine, PERF_RECORD_MISC_USER,
+	thread__find_addr_map(ui->thread, PERF_RECORD_MISC_USER,
 			      MAP__FUNCTION, addr, &al);
 	if (!al.map) {
 		pr_debug("unwind: no map for %lx\n", (unsigned long)addr);
@@ -476,14 +476,13 @@ static void put_unwind_info(unw_addr_space_t __maybe_unused as,
 	pr_debug("unwind: put_unwind_info called\n");
 }
 
-static int entry(u64 ip, struct thread *thread, struct machine *machine,
+static int entry(u64 ip, struct thread *thread,
 		 unwind_entry_cb_t cb, void *arg)
 {
 	struct unwind_entry e;
 	struct addr_location al;
 
-	thread__find_addr_location(thread, machine,
-				   PERF_RECORD_MISC_USER,
+	thread__find_addr_location(thread, PERF_RECORD_MISC_USER,
 				   MAP__FUNCTION, ip, &al);
 
 	e.ip = ip;
@@ -586,21 +585,21 @@ static int get_entries(struct unwind_info *ui, unwind_entry_cb_t cb,
 		unw_word_t ip;
 
 		unw_get_reg(&c, UNW_REG_IP, &ip);
-		ret = ip ? entry(ip, ui->thread, ui->machine, cb, arg) : 0;
+		ret = ip ? entry(ip, ui->thread, cb, arg) : 0;
 	}
 
 	return ret;
 }
 
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-			struct machine *machine, struct thread *thread,
+			struct thread *thread,
 			struct perf_sample *data, int max_stack)
 {
 	u64 ip;
 	struct unwind_info ui = {
 		.sample       = data,
 		.thread       = thread,
-		.machine      = machine,
+		.machine      = thread->mg->machine,
 	};
 	int ret;
 
@@ -611,7 +610,7 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (ret)
 		return ret;
 
-	ret = entry(ip, thread, machine, cb, arg);
+	ret = entry(ip, thread, cb, arg);
 	if (ret)
 		return -ENOMEM;
 
diff --git a/tools/perf/util/unwind.h b/tools/perf/util/unwind.h
index f50b737235eb..12790cf94618 100644
--- a/tools/perf/util/unwind.h
+++ b/tools/perf/util/unwind.h
@@ -16,7 +16,6 @@ typedef int (*unwind_entry_cb_t)(struct unwind_entry *entry, void *arg);
 
 #ifdef HAVE_DWARF_UNWIND_SUPPORT
 int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
-			struct machine *machine,
 			struct thread *thread,
 			struct perf_sample *data, int max_stack);
 /* libunwind specific */
@@ -38,7 +37,6 @@ static inline void unwind__finish_access(struct thread *thread __maybe_unused) {
 static inline int
 unwind__get_entries(unwind_entry_cb_t cb __maybe_unused,
 		    void *arg __maybe_unused,
-		    struct machine *machine __maybe_unused,
 		    struct thread *thread __maybe_unused,
 		    struct perf_sample *data __maybe_unused,
 		    int max_stack __maybe_unused)
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 80bfdaa0e2a4..419bee030f83 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -154,7 +154,6 @@ extern void set_die_routine(void (*routine)(const char *err, va_list params) NOR
 
 extern int prefixcmp(const char *str, const char *prefix);
 extern void set_buildid_dir(void);
-extern void disable_buildid_cache(void);
 
 static inline const char *skip_prefix(const char *str, const char *prefix)
 {
@@ -338,8 +337,10 @@ static inline int path__join3(char *bf, size_t size,
 }
 
 struct dso;
+struct symbol;
 
-char *get_srcline(struct dso *dso, unsigned long addr);
+char *get_srcline(struct dso *dso, unsigned long addr, struct symbol *sym,
+		  bool show_sym);
 void free_srcline(char *srcline);
 
 int filename__read_int(const char *filename, int *value);
@@ -351,4 +352,9 @@ void mem_bswap_32(void *src, int byte_size);
 
 const char *get_filename_for_perf_kvm(void);
 bool find_process(const char *name);
+
+#ifdef HAVE_ZLIB_SUPPORT
+int gzip_decompress_to_file(const char *input, int output_fd);
+#endif
+
 #endif /* GIT_COMPAT_UTIL_H */
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index adca69384fcc..5c7dd796979d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -12,9 +12,16 @@
 #include "util.h"
 #include "symbol.h"
 #include "machine.h"
+#include "thread.h"
 #include "linux/string.h"
 #include "debug.h"
 
+/*
+ * Include definition of find_vdso_map() also used in perf-read-vdso.c for
+ * building perf-read-vdso32 and perf-read-vdsox32.
+ */
+#include "find-vdso-map.c"
+
 #define VDSO__TEMP_FILE_NAME "/tmp/perf-vdso.so-XXXXXX"
 
 struct vdso_file {
@@ -22,10 +29,15 @@ struct vdso_file {
 	bool error;
 	char temp_file_name[sizeof(VDSO__TEMP_FILE_NAME)];
 	const char *dso_name;
+	const char *read_prog;
 };
 
 struct vdso_info {
 	struct vdso_file vdso;
+#if BITS_PER_LONG == 64
+	struct vdso_file vdso32;
+	struct vdso_file vdsox32;
+#endif
 };
 
 static struct vdso_info *vdso_info__new(void)
@@ -35,42 +47,23 @@ static struct vdso_info *vdso_info__new(void)
 			.temp_file_name = VDSO__TEMP_FILE_NAME,
 			.dso_name = DSO__NAME_VDSO,
 		},
+#if BITS_PER_LONG == 64
+		.vdso32  = {
+			.temp_file_name = VDSO__TEMP_FILE_NAME,
+			.dso_name = DSO__NAME_VDSO32,
+			.read_prog = "perf-read-vdso32",
+		},
+		.vdsox32  = {
+			.temp_file_name = VDSO__TEMP_FILE_NAME,
+			.dso_name = DSO__NAME_VDSOX32,
+			.read_prog = "perf-read-vdsox32",
+		},
+#endif
 	};
 
 	return memdup(&vdso_info_init, sizeof(vdso_info_init));
 }
 
-static int find_vdso_map(void **start, void **end)
-{
-	FILE *maps;
-	char line[128];
-	int found = 0;
-
-	maps = fopen("/proc/self/maps", "r");
-	if (!maps) {
-		pr_err("vdso: cannot open maps\n");
-		return -1;
-	}
-
-	while (!found && fgets(line, sizeof(line), maps)) {
-		int m = -1;
-
-		/* We care only about private r-x mappings. */
-		if (2 != sscanf(line, "%p-%p r-xp %*x %*x:%*x %*u %n",
-				start, end, &m))
-			continue;
-		if (m < 0)
-			continue;
-
-		if (!strncmp(&line[m], VDSO__MAP_NAME,
-			     sizeof(VDSO__MAP_NAME) - 1))
-			found = 1;
-	}
-
-	fclose(maps);
-	return !found;
-}
-
 static char *get_file(struct vdso_file *vdso_file)
 {
 	char *vdso = NULL;
@@ -117,6 +110,12 @@ void vdso__exit(struct machine *machine)
 
 	if (vdso_info->vdso.found)
 		unlink(vdso_info->vdso.temp_file_name);
+#if BITS_PER_LONG == 64
+	if (vdso_info->vdso32.found)
+		unlink(vdso_info->vdso32.temp_file_name);
+	if (vdso_info->vdsox32.found)
+		unlink(vdso_info->vdsox32.temp_file_name);
+#endif
 
 	zfree(&machine->vdso_info);
 }
@@ -135,6 +134,153 @@ static struct dso *vdso__new(struct machine *machine, const char *short_name,
 	return dso;
 }
 
+#if BITS_PER_LONG == 64
+
+static enum dso_type machine__thread_dso_type(struct machine *machine,
+					      struct thread *thread)
+{
+	enum dso_type dso_type = DSO__TYPE_UNKNOWN;
+	struct map *map;
+	struct dso *dso;
+
+	map = map_groups__first(thread->mg, MAP__FUNCTION);
+	for (; map ; map = map_groups__next(map)) {
+		dso = map->dso;
+		if (!dso || dso->long_name[0] != '/')
+			continue;
+		dso_type = dso__type(dso, machine);
+		if (dso_type != DSO__TYPE_UNKNOWN)
+			break;
+	}
+
+	return dso_type;
+}
+
+static int vdso__do_copy_compat(FILE *f, int fd)
+{
+	char buf[4096];
+	size_t count;
+
+	while (1) {
+		count = fread(buf, 1, sizeof(buf), f);
+		if (ferror(f))
+			return -errno;
+		if (feof(f))
+			break;
+		if (count && writen(fd, buf, count) != (ssize_t)count)
+			return -errno;
+	}
+
+	return 0;
+}
+
+static int vdso__copy_compat(const char *prog, int fd)
+{
+	FILE *f;
+	int err;
+
+	f = popen(prog, "r");
+	if (!f)
+		return -errno;
+
+	err = vdso__do_copy_compat(f, fd);
+
+	if (pclose(f) == -1)
+		return -errno;
+
+	return err;
+}
+
+static int vdso__create_compat_file(const char *prog, char *temp_name)
+{
+	int fd, err;
+
+	fd = mkstemp(temp_name);
+	if (fd < 0)
+		return -errno;
+
+	err = vdso__copy_compat(prog, fd);
+
+	if (close(fd) == -1)
+		return -errno;
+
+	return err;
+}
+
+static const char *vdso__get_compat_file(struct vdso_file *vdso_file)
+{
+	int err;
+
+	if (vdso_file->found)
+		return vdso_file->temp_file_name;
+
+	if (vdso_file->error)
+		return NULL;
+
+	err = vdso__create_compat_file(vdso_file->read_prog,
+				       vdso_file->temp_file_name);
+	if (err) {
+		pr_err("%s failed, error %d\n", vdso_file->read_prog, err);
+		vdso_file->error = true;
+		return NULL;
+	}
+
+	vdso_file->found = true;
+
+	return vdso_file->temp_file_name;
+}
+
+static struct dso *vdso__findnew_compat(struct machine *machine,
+					struct vdso_file *vdso_file)
+{
+	const char *file_name;
+	struct dso *dso;
+
+	dso = dsos__find(&machine->user_dsos, vdso_file->dso_name, true);
+	if (dso)
+		return dso;
+
+	file_name = vdso__get_compat_file(vdso_file);
+	if (!file_name)
+		return NULL;
+
+	return vdso__new(machine, vdso_file->dso_name, file_name);
+}
+
+static int vdso__dso_findnew_compat(struct machine *machine,
+				    struct thread *thread,
+				    struct vdso_info *vdso_info,
+				    struct dso **dso)
+{
+	enum dso_type dso_type;
+
+	dso_type = machine__thread_dso_type(machine, thread);
+
+#ifndef HAVE_PERF_READ_VDSO32
+	if (dso_type == DSO__TYPE_32BIT)
+		return 0;
+#endif
+#ifndef HAVE_PERF_READ_VDSOX32
+	if (dso_type == DSO__TYPE_X32BIT)
+		return 0;
+#endif
+
+	switch (dso_type) {
+	case DSO__TYPE_32BIT:
+		*dso = vdso__findnew_compat(machine, &vdso_info->vdso32);
+		return 1;
+	case DSO__TYPE_X32BIT:
+		*dso = vdso__findnew_compat(machine, &vdso_info->vdsox32);
+		return 1;
+	case DSO__TYPE_UNKNOWN:
+	case DSO__TYPE_64BIT:
+	default:
+		return 0;
+	}
+}
+
+#endif
+
 struct dso *vdso__dso_findnew(struct machine *machine,
 			      struct thread *thread __maybe_unused)
 {
@@ -148,6 +294,11 @@ struct dso *vdso__dso_findnew(struct machine *machine,
 	if (!vdso_info)
 		return NULL;
 
+#if BITS_PER_LONG == 64
+	if (vdso__dso_findnew_compat(machine, thread, vdso_info, &dso))
+		return dso;
+#endif
+
 	dso = dsos__find(&machine->user_dsos, DSO__NAME_VDSO, true);
 	if (!dso) {
 		char *file;
@@ -164,5 +315,7 @@ struct dso *vdso__dso_findnew(struct machine *machine,
 
 bool dso__is_vdso(struct dso *dso)
 {
-	return !strcmp(dso->short_name, DSO__NAME_VDSO);
+	return !strcmp(dso->short_name, DSO__NAME_VDSO) ||
+	       !strcmp(dso->short_name, DSO__NAME_VDSO32) ||
+	       !strcmp(dso->short_name, DSO__NAME_VDSOX32);
 }
diff --git a/tools/perf/util/vdso.h b/tools/perf/util/vdso.h
index af9d6929a215..d97da1616f0c 100644
--- a/tools/perf/util/vdso.h
+++ b/tools/perf/util/vdso.h
@@ -7,7 +7,9 @@
 
 #define VDSO__MAP_NAME "[vdso]"
 
-#define DSO__NAME_VDSO "[vdso]"
+#define DSO__NAME_VDSO    "[vdso]"
+#define DSO__NAME_VDSO32  "[vdso32]"
+#define DSO__NAME_VDSOX32 "[vdsox32]"
 
 static inline bool is_vdso_map(const char *filename)
 {
diff --git a/tools/perf/util/zlib.c b/tools/perf/util/zlib.c
new file mode 100644
index 000000000000..495a449fc25c
--- /dev/null
+++ b/tools/perf/util/zlib.c
@@ -0,0 +1,78 @@
+#include <stdio.h>
+#include <unistd.h>
+#include <sys/stat.h>
+#include <sys/mman.h>
+#include <zlib.h>
+
+#include "util/util.h"
+#include "util/debug.h"
+
+
+#define CHUNK_SIZE  16384
+
+int gzip_decompress_to_file(const char *input, int output_fd)
+{
+	int ret = Z_STREAM_ERROR;
+	int input_fd;
+	void *ptr;
+	int len;
+	struct stat stbuf;
+	unsigned char buf[CHUNK_SIZE];
+	z_stream zs = {
+		.zalloc		= Z_NULL,
+		.zfree		= Z_NULL,
+		.opaque		= Z_NULL,
+		.avail_in	= 0,
+		.next_in	= Z_NULL,
+	};
+
+	input_fd = open(input, O_RDONLY);
+	if (input_fd < 0)
+		return -1;
+
+	if (fstat(input_fd, &stbuf) < 0)
+		goto out_close;
+
+	ptr = mmap(NULL, stbuf.st_size, PROT_READ, MAP_PRIVATE, input_fd, 0);
+	if (ptr == MAP_FAILED)
+		goto out_close;
+
+	if (inflateInit2(&zs, 16 + MAX_WBITS) != Z_OK)
+		goto out_unmap;
+
+	zs.next_in = ptr;
+	zs.avail_in = stbuf.st_size;
+
+	do {
+		zs.next_out = buf;
+		zs.avail_out = CHUNK_SIZE;
+
+		ret = inflate(&zs, Z_NO_FLUSH);
+		switch (ret) {
+		case Z_NEED_DICT:
+			ret = Z_DATA_ERROR;
+			/* fall through */
+		case Z_DATA_ERROR:
+		case Z_MEM_ERROR:
+			goto out;
+		default:
+			break;
+		}
+
+		len = CHUNK_SIZE - zs.avail_out;
+		if (writen(output_fd, buf, len) != len) {
+			ret = Z_DATA_ERROR;
+			goto out;
+		}
+
+	} while (ret != Z_STREAM_END);
+
+out:
+	inflateEnd(&zs);
+out_unmap:
+	munmap(ptr, stbuf.st_size);
+out_close:
+	close(input_fd);
+
+	return ret == Z_STREAM_END ? 0 : -1;
+}