perf tools: Introduce an abstraction for AUX Area and Instruction Tracing

The thread-stack represents a thread's current stack. When a thread exits there can still be many functions on the stack e.g. exit() can be called many levels deep, so all the callers will never return. To get that information output, the thread-stack must be flushed.

Previously it was assumed the thread-stack would be flushed when the struct thread was deleted. With thread ref-counting it is no longer clear when that will be, if ever. So instead

explicitly flush all the thread-stacks at the end of a session.

Signed-off-by Adrian Hunter <[email protected]>

---
 tools/perf/util/machine.c      | 21 +++++++++++++++++++++
 tools/perf/util/machine.h      |  3 +++
 tools/perf/util/session.c      | 20 ++++++++++++++++++++
 tools/perf/util/thread-stack.c | 18 +++++++++++++-----
 tools/perf/util/thread-stack.h |  1 +
 5 files changed, 58 insertions(+), 5 deletions(-)

tools/perf/util/machine.c +21 -0

index 0c0e61c..c0c29b9 100644
@@ -1845,6 +1845,27 @@ int machine__for_each_thread(struct machine *machine,
 	return rc;
 }
 
+int machines__for_each_thread(struct machines *machines,
+			      int (*fn)(struct thread *thread, void *p),
+			      void *priv)
+{
+	struct rb_node *nd;
+	int rc = 0;
+
+	rc = machine__for_each_thread(&machines->host, fn, priv);
+	if (rc != 0)
+		return rc;
+
+	for (nd = rb_first(&machines->guests); nd; nd = rb_next(nd)) {
+		struct machine *machine = rb_entry(nd, struct machine, rb_node);
+
+		rc = machine__for_each_thread(machine, fn, priv);
+		if (rc != 0)
+			return rc;
+	}
+	return rc;
+}
+
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,
 				  perf_event__handler_t process, bool data_mmap)

tools/perf/util/machine.h +3 -0

index c7963c6..6b4a6fb 100644
@@ -213,6 +213,9 @@ size_t machine__fprintf_vmlinux_path(struct machine *machine, FILE *fp);
 int machine__for_each_thread(struct machine *machine,
 			     int (*fn)(struct thread *thread, void *p),
 			     void *priv);
+int machines__for_each_thread(struct machines *machines,
+			      int (*fn)(struct thread *thread, void *p),
+			      void *priv);
 
 int __machine__synthesize_threads(struct machine *machine, struct perf_tool *tool,
 				  struct target *target, struct thread_map *threads,

tools/perf/util/session.c +20 -0

index 39fe09d..b44bb2a 100644
@@ -16,6 +16,7 @@
 #include "perf_regs.h"
 #include "asm/bug.h"
 #include "auxtrace.h"
+#include "thread-stack.h"
 
 static int perf_session__deliver_event(struct perf_session *session,
 				       union perf_event *event,

@@ -1320,6 +1321,19 @@ static void perf_session__warn_about_errors(const struct perf_session *session)
 	events_stats__auxtrace_error_warn(stats);
 }
 
+static int perf_session__flush_thread_stack(struct thread *thread,
+					    void *p __maybe_unused)
+{
+	return thread_stack__flush(thread);
+}
+
+static int perf_session__flush_thread_stacks(struct perf_session *session)
+{
+	return machines__for_each_thread(&session->machines,
+					 perf_session__flush_thread_stack,
+					 NULL);
+}
+
 volatile int session_done;
 
 static int __perf_session__process_pipe_events(struct perf_session *session)

@@ -1409,6 +1423,9 @@ done:
 	if (err)
 		goto out_err;
 	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	free(buf);
 	perf_session__warn_about_errors(session);

@@ -1559,6 +1576,9 @@ out:
 	if (err)
 		goto out_err;
 	err = auxtrace__flush_events(session, tool);
+	if (err)
+		goto out_err;
+	err = perf_session__flush_thread_stacks(session);
 out_err:
 	ui_progress__finish();
 	perf_session__warn_about_errors(session);

tools/perf/util/thread-stack.c +13 -5

index 9ed59a4..679688e 100644
@@ -219,7 +219,7 @@ static int thread_stack__call_return(struct thread *thread,
 	return crp->process(&cr, crp->data);
 }
 
-static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+static int __thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 {
 	struct call_return_processor *crp = ts->crp;
 	int err;

@@ -242,6 +242,14 @@ static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
 	return 0;
 }
 
+int thread_stack__flush(struct thread *thread)
+{
+	if (thread->ts)
+		return __thread_stack__flush(thread, thread->ts);
+
+	return 0;
+}
+
 int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 			u64 to_ip, u16 insn_len, u64 trace_nr)
 {

@@ -264,7 +272,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 	 */
 	if (trace_nr != thread->ts->trace_nr) {
 		if (thread->ts->trace_nr)
-			thread_stack__flush(thread, thread->ts);
+			__thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
 	}
 

@@ -297,7 +305,7 @@ void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
 
 	if (trace_nr != thread->ts->trace_nr) {
 		if (thread->ts->trace_nr)
-			thread_stack__flush(thread, thread->ts);
+			__thread_stack__flush(thread, thread->ts);
 		thread->ts->trace_nr = trace_nr;
 	}
 }

@@ -305,7 +313,7 @@ void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
 void thread_stack__free(struct thread *thread)
 {
 	if (thread->ts) {
-		thread_stack__flush(thread, thread->ts);
+		__thread_stack__flush(thread, thread->ts);
 		zfree(&thread->ts->stack);
 		zfree(&thread->ts);
 	}

@@ -689,7 +697,7 @@ int thread_stack__process(struct thread *thread, struct comm *comm,
 
 	/* Flush stack on exec */
 	if (ts->comm != comm && thread->pid_ == thread->tid) {
-		err = thread_stack__flush(thread, ts);
+		err = __thread_stack__flush(thread, ts);
 		if (err)
 			return err;
 		ts->comm = comm;

tools/perf/util/thread-stack.h +1 -0

index b843bbe..e1528f1 100644
@@ -96,6 +96,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
 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);
+int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 
 struct call_return_processor *

Signature · 1 line

1.9.1

Em Fri, May 29, 2015 at 04:33:30PM +0300, Adrian Hunter escreveu:

Quoted 9 lines

The thread-stack represents a thread's current stack. When a thread exits there can still be many functions on the stack e.g. exit() can be called many levels deep, so all the callers will never return. To get that information output, the thread-stack must be flushed.

Previously it was assumed the thread-stack would be flushed when the struct thread was deleted. With thread ref-counting it is no longer clear when that will be, if ever. So instead

It'll be when the last reference to that thread is released.

- Arnaldo

Quoted 1 line

explicitly flush all the thread-stacks at the end of a session.

If after the session ends you have no more need for those thread stacks, that is the right way to do it.

With tools like 'report', after the session ends we should have all the unreferenced threads deleted.

Previously they were not being deleted at all, i.e. they were simply moved to the dead_threads list and sat there because I didn't knew if some hist_entry, say, had a pointer to it.

So, unless I am missing something, this patch is required irrespective of thread refcounting, no?

I'm applying it to my work branch where I'm trying to test all this.

Add support for decoding instructions for Intel Processor Trace. The kernel x86 instruction decoder is used for this.

This essentially provides intel_pt_get_insn() which takes a binary buffer, uses the kernel's x86 instruction decoder to get details of the instruction and then categorizes it for consumption by an Intel PT decoder.

Signed-off-by Adrian Hunter <[email protected]>

---
 tools/build/Makefile.build                         |   2 +
 tools/perf/.gitignore                              |   2 +
 tools/perf/Makefile.perf                           |  12 +-
 tools/perf/util/intel-pt-decoder/Build             |  15 +-
 .../util/intel-pt-decoder/intel-pt-insn-decoder.c  | 246 +++++++++++++++++++++
 .../util/intel-pt-decoder/intel-pt-insn-decoder.h  |  65 ++++++
 6 files changed, 339 insertions(+), 3 deletions(-)
 create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
 create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h

tools/build/Makefile.build +2 -0

index 10df572..7ad74e4 100644
@@ -57,6 +57,8 @@ quiet_cmd_cc_i_c = CPP      $@
 quiet_cmd_cc_s_c = AS       $@
       cmd_cc_s_c = $(CC) $(c_flags) -S -o $@ $<
 
+quiet_cmd_gen = GEN      $@
+
 # Link agregate command
 # If there's nothing to link, create empty $@ object.
 quiet_cmd_ld_multi = LD       $@

tools/perf/.gitignore +2 -0

index 812f904..c88d5c5 100644
@@ -28,3 +28,5 @@ config.mak.autogen
 *-flex.*
 *.pyc
 *.pyo
+util/intel-pt-decoder/inat-tables.c
+util/intel-pt-decoder/inat.c

tools/perf/Makefile.perf +10 -2

index 5816a3b..3ae3a8e 100644
@@ -76,6 +76,12 @@ include config/utilities.mak
 #
 # Define NO_AUXTRACE if you do not want AUX area tracing support
 
+# As per kernel Makefile, avoid funny character set dependencies
+unexport LC_ALL
+LC_COLLATE=C
+LC_NUMERIC=C
+export LC_COLLATE LC_NUMERIC
+
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))

@@ -122,6 +128,7 @@ INSTALL = install
 FLEX    = flex
 BISON   = bison
 STRIP   = strip
+AWK     = awk
 
 LIB_DIR          = $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/

@@ -272,7 +279,7 @@ strip: $(PROGRAMS) $(OUTPUT)perf
 
 PERF_IN := $(OUTPUT)perf-in.o
 
-export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX
+export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX AWK
 build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
 $(PERF_IN): $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h FORCE

@@ -536,7 +543,8 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean
 	$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) .config-detected
 	$(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)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
+	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
+		$(OUTPUT)util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 

tools/perf/util/intel-pt-decoder/Build +14 -1

index 9d67381..f5f7f87 100644
@@ -1 +1,14 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o
+libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o
+
+inat_tables_script = ../../arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = ../../arch/x86/lib/x86-opcode-map.txt
+
+$(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+	@$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
+
+$(OUTPUT)util/intel-pt-decoder/inat.c:
+	@$(call echo-cmd,gen)cp ../../arch/x86/lib/inat.c $(OUTPUT)util/intel-pt-decoder/inat.c
+
+$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: $(OUTPUT)util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
+
+CFLAGS_intel-pt-insn-decoder.o += -I../../arch/x86/include -I$(OUTPUT)util/intel-pt-decoder -I../../arch/x86/lib -Wno-override-init

tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c new file +246 -0

new file mode 100644
index 0000000..2fa82c5
@@ -0,0 +1,246 @@
+/*
+ * intel_pt_insn_decoder.c: Intel Processor Trace support
+ * Copyright (c) 2013-2014, 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 <stdio.h>
+#include <string.h>
+#include <endian.h>
+#include <byteswap.h>
+
+#include "event.h"
+
+#include <asm/insn.h>
+
+#include "inat.c"
+#include <insn.c>
+
+#include "intel-pt-insn-decoder.h"
+
+/* Based on branch_type() from perf_event_intel_lbr.c */
+static void intel_pt_insn_decoder(struct insn *insn,
+				  struct intel_pt_insn *intel_pt_insn)
+{
+	enum intel_pt_insn_op op = INTEL_PT_OP_OTHER;
+	enum intel_pt_insn_branch branch = INTEL_PT_BR_NO_BRANCH;
+	int ext;
+
+	if (insn_is_avx(insn)) {
+		intel_pt_insn->op = INTEL_PT_OP_OTHER;
+		intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH;
+		intel_pt_insn->length = insn->length;
+		return;
+	}
+
+	switch (insn->opcode.bytes[0]) {
+	case 0xf:
+		switch (insn->opcode.bytes[1]) {
+		case 0x05: /* syscall */
+		case 0x34: /* sysenter */
+			op = INTEL_PT_OP_SYSCALL;
+			branch = INTEL_PT_BR_INDIRECT;
+			break;
+		case 0x07: /* sysret */
+		case 0x35: /* sysexit */
+			op = INTEL_PT_OP_SYSRET;
+			branch = INTEL_PT_BR_INDIRECT;
+			break;
+		case 0x80 ... 0x8f: /* jcc */
+			op = INTEL_PT_OP_JCC;
+			branch = INTEL_PT_BR_CONDITIONAL;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 0x70 ... 0x7f: /* jcc */
+		op = INTEL_PT_OP_JCC;
+		branch = INTEL_PT_BR_CONDITIONAL;
+		break;
+	case 0xc2: /* near ret */
+	case 0xc3: /* near ret */
+	case 0xca: /* far ret */
+	case 0xcb: /* far ret */
+		op = INTEL_PT_OP_RET;
+		branch = INTEL_PT_BR_INDIRECT;
+		break;
+	case 0xcf: /* iret */
+		op = INTEL_PT_OP_IRET;
+		branch = INTEL_PT_BR_INDIRECT;
+		break;
+	case 0xcc ... 0xce: /* int */
+		op = INTEL_PT_OP_INT;
+		branch = INTEL_PT_BR_INDIRECT;
+		break;
+	case 0xe8: /* call near rel */
+		op = INTEL_PT_OP_CALL;
+		branch = INTEL_PT_BR_UNCONDITIONAL;
+		break;
+	case 0x9a: /* call far absolute */
+		op = INTEL_PT_OP_CALL;
+		branch = INTEL_PT_BR_INDIRECT;
+		break;
+	case 0xe0 ... 0xe2: /* loop */
+		op = INTEL_PT_OP_LOOP;
+		branch = INTEL_PT_BR_CONDITIONAL;
+		break;
+	case 0xe3: /* jcc */
+		op = INTEL_PT_OP_JCC;
+		branch = INTEL_PT_BR_CONDITIONAL;
+		break;
+	case 0xe9: /* jmp */
+	case 0xeb: /* jmp */
+		op = INTEL_PT_OP_JMP;
+		branch = INTEL_PT_BR_UNCONDITIONAL;
+		break;
+	case 0xea: /* far jmp */
+		op = INTEL_PT_OP_JMP;
+		branch = INTEL_PT_BR_INDIRECT;
+		break;
+	case 0xff: /* call near absolute, call far absolute ind */
+		ext = (insn->modrm.bytes[0] >> 3) & 0x7;
+		switch (ext) {
+		case 2: /* near ind call */
+		case 3: /* far ind call */
+			op = INTEL_PT_OP_CALL;
+			branch = INTEL_PT_BR_INDIRECT;
+			break;
+		case 4:
+		case 5:
+			op = INTEL_PT_OP_JMP;
+			branch = INTEL_PT_BR_INDIRECT;
+			break;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	intel_pt_insn->op = op;
+	intel_pt_insn->branch = branch;
+	intel_pt_insn->length = insn->length;
+
+	if (branch == INTEL_PT_BR_CONDITIONAL ||
+	    branch == INTEL_PT_BR_UNCONDITIONAL) {
+#if __BYTE_ORDER == __BIG_ENDIAN
+		switch (insn->immediate.nbytes) {
+		case 1:
+			intel_pt_insn->rel = insn->immediate.value;
+			break;
+		case 2:
+			intel_pt_insn->rel =
+					bswap_16((short)insn->immediate.value);
+			break;
+		case 4:
+			intel_pt_insn->rel = bswap_32(insn->immediate.value);
+			break;
+		}
+#else
+		intel_pt_insn->rel = insn->immediate.value;
+#endif
+	}
+}
+
+int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
+		      struct intel_pt_insn *intel_pt_insn)
+{
+	struct insn insn;
+
+	insn_init(&insn, buf, len, x86_64);
+	insn_get_length(&insn);
+	if (!insn_complete(&insn) || insn.length > len)
+		return -1;
+	intel_pt_insn_decoder(&insn, intel_pt_insn);
+	if (insn.length < INTEL_PT_INSN_DBG_BUF_SZ)
+		memcpy(intel_pt_insn->buf, buf, insn.length);
+	else
+		memcpy(intel_pt_insn->buf, buf, INTEL_PT_INSN_DBG_BUF_SZ);
+	return 0;
+}
+
+const char *branch_name[] = {
+	[INTEL_PT_OP_OTHER]	= "Other",
+	[INTEL_PT_OP_CALL]	= "Call",
+	[INTEL_PT_OP_RET]	= "Ret",
+	[INTEL_PT_OP_JCC]	= "Jcc",
+	[INTEL_PT_OP_JMP]	= "Jmp",
+	[INTEL_PT_OP_LOOP]	= "Loop",
+	[INTEL_PT_OP_IRET]	= "IRet",
+	[INTEL_PT_OP_INT]	= "Int",
+	[INTEL_PT_OP_SYSCALL]	= "Syscall",
+	[INTEL_PT_OP_SYSRET]	= "Sysret",
+};
+
+const char *intel_pt_insn_name(enum intel_pt_insn_op op)
+{
+	return branch_name[op];
+}
+
+int intel_pt_insn_desc(const struct intel_pt_insn *intel_pt_insn, char *buf,
+		       size_t buf_len)
+{
+	switch (intel_pt_insn->branch) {
+	case INTEL_PT_BR_CONDITIONAL:
+	case INTEL_PT_BR_UNCONDITIONAL:
+		return snprintf(buf, buf_len, "%s %s%d",
+				intel_pt_insn_name(intel_pt_insn->op),
+				intel_pt_insn->rel > 0 ? "+" : "",
+				intel_pt_insn->rel);
+	case INTEL_PT_BR_NO_BRANCH:
+	case INTEL_PT_BR_INDIRECT:
+		return snprintf(buf, buf_len, "%s",
+				intel_pt_insn_name(intel_pt_insn->op));
+	default:
+		break;
+	}
+	return 0;
+}
+
+size_t intel_pt_insn_max_size(void)
+{
+	return MAX_INSN_SIZE;
+}
+
+int intel_pt_insn_type(enum intel_pt_insn_op op)
+{
+	switch (op) {
+	case INTEL_PT_OP_OTHER:
+		return 0;
+	case INTEL_PT_OP_CALL:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL;
+	case INTEL_PT_OP_RET:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN;
+	case INTEL_PT_OP_JCC:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL;
+	case INTEL_PT_OP_JMP:
+		return PERF_IP_FLAG_BRANCH;
+	case INTEL_PT_OP_LOOP:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL;
+	case INTEL_PT_OP_IRET:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN |
+		       PERF_IP_FLAG_INTERRUPT;
+	case INTEL_PT_OP_INT:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
+		       PERF_IP_FLAG_INTERRUPT;
+	case INTEL_PT_OP_SYSCALL:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
+		       PERF_IP_FLAG_SYSCALLRET;
+	case INTEL_PT_OP_SYSRET:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN |
+		       PERF_IP_FLAG_SYSCALLRET;
+	default:
+		return 0;
+	}
+}

tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h new file +65 -0

new file mode 100644
index 0000000..b0adbf3
@@ -0,0 +1,65 @@
+/*
+ * intel_pt_insn_decoder.h: Intel Processor Trace support
+ * Copyright (c) 2013-2014, 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 INCLUDE__INTEL_PT_INSN_DECODER_H__
+#define INCLUDE__INTEL_PT_INSN_DECODER_H__
+
+#include <stddef.h>
+#include <stdint.h>
+
+#define INTEL_PT_INSN_DESC_MAX		32
+#define INTEL_PT_INSN_DBG_BUF_SZ	16
+
+enum intel_pt_insn_op {
+	INTEL_PT_OP_OTHER,
+	INTEL_PT_OP_CALL,
+	INTEL_PT_OP_RET,
+	INTEL_PT_OP_JCC,
+	INTEL_PT_OP_JMP,
+	INTEL_PT_OP_LOOP,
+	INTEL_PT_OP_IRET,
+	INTEL_PT_OP_INT,
+	INTEL_PT_OP_SYSCALL,
+	INTEL_PT_OP_SYSRET,
+};
+
+enum intel_pt_insn_branch {
+	INTEL_PT_BR_NO_BRANCH,
+	INTEL_PT_BR_INDIRECT,
+	INTEL_PT_BR_CONDITIONAL,
+	INTEL_PT_BR_UNCONDITIONAL,
+};
+
+struct intel_pt_insn {
+	enum intel_pt_insn_op		op;
+	enum intel_pt_insn_branch	branch;
+	int				length;
+	int32_t				rel;
+	unsigned char			buf[INTEL_PT_INSN_DBG_BUF_SZ];
+};
+
+int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
+		      struct intel_pt_insn *intel_pt_insn);
+
+const char *intel_pt_insn_name(enum intel_pt_insn_op op);
+
+int intel_pt_insn_desc(const struct intel_pt_insn *intel_pt_insn, char *buf,
+		       size_t buf_len);
+
+size_t intel_pt_insn_max_size(void);
+
+int intel_pt_insn_type(enum intel_pt_insn_op op);
+
+#endif

Signature · 1 line

1.9.1

Em Fri, May 29, 2015 at 04:33:33PM +0300, Adrian Hunter escreveu:

Quoted 2 lines

Add support for decoding instructions for Intel Processor Trace. The kernel x86 instruction decoder is used for this.

Ok, but we don't access kernel header files directly, and:

[acme@zoo linux]$ find . -name "insn.h" ./arch/x86/include/asm/insn.h ./arch/arm64/include/asm/insn.h ./arch/arm/include/asm/insn.h
[acme@zoo linux]$ find /usr/include -name "insn.h" [acme@zoo linux]$

But I need to look more into this patch to figure out if this is something generated at build time, etc, but before that I found a problem:

So:

Review

Quoted 2 lines

(quoted diff) +2 -0

+inat_tables_script = ../../arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = ../../arch/x86/lib/x86-opcode-map.txt

These need to go into tools/perf/MANIFEST, so that:

[acme@zoo linux]$ make help | grep perf
perf-tar-src-pkg - Build perf-4.1.0-rc5.tar source tarball
perf-targz-src-pkg - Build perf-4.1.0-rc5.tar.gz source tarball perf-tarbz2-src-pkg - Build perf-4.1.0-rc5.tar.bz2 source tarball perf-tarxz-src-pkg - Build perf-4.1.0-rc5.tar.xz source tarball
[acme@zoo linux]$

Continue to work, in fact, there is a test for that, that will run when you do the build tests:

make -C tools/perf build-test

It is one of the last to be tested, so you may want to do it directly:

[acme@zoo linux]$ make -C tools/perf -f tests/make tarpkg
make: Entering directory '/home/git/linux/tools/perf'
- tarpkg: ./tests/perf-targz-src-pkg .
make: Leaving directory '/home/git/linux/tools/perf' [acme@zoo linux]$

After I apply this patch, I get:

Applying: perf tools: Add Intel PT instruction decoder [tmp.perf/pt 1ab14c4be64b] perf tools: Add Intel PT instruction decoder
Author: Adrian Hunter <[email protected]>
Date: Fri May 29 16:33:33 2015 +0300

 6 files changed, 339 insertions(+), 3 deletions(-)
 rewrite tools/perf/util/intel-pt-decoder/Build (100%)
 create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
 create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h

[acme@zoo linux]$ fg
bash: fg: current: no such job
[acme@zoo linux]$ make -C tools/perf -f tests/make tarpkg
make: Entering directory '/home/git/linux/tools/perf'
- tarpkg: ./tests/perf-targz-src-pkg . tests/make:224: recipe for target 'tarpkg' failed
make: *** [tarpkg] Error 2
make: Leaving directory '/home/git/linux/tools/perf' [acme@zoo linux]$

Doing it manually to see what happened:

[acme@zoo linux]$ make perf-tar-src-pkg
TAR
[acme@zoo linux]$ ls -la perf-4.1.0-rc5.tar -rw-rw-r--. 1 acme acme 5027840 Jun 18 19:24 perf-4.1.0-rc5.tar [acme@zoo linux]$ mv perf-4.1.0-rc5.tar /tmp [acme@zoo linux]$ cd /tmp
[acme@zoo tmp]$ tar xf perf-4.1.0-rc5.tar
[acme@zoo tmp]$ cd perf-4.1.0-rc5/
[acme@zoo perf-4.1.0-rc5]$ make -C tools/perf
make: Entering directory '/tmp/perf-4.1.0-rc5/tools/perf'
BUILD: Doing 'make -j4' parallel build

Auto-detecting system features:

...                         dwarf: [ on  ]
...                         glibc: [ on  ]
...                          gtk2: [ on  ]
...                      libaudit: [ on  ]
...                        libbfd: [ on  ]
...                        libelf: [ on  ]
...                       libnuma: [ on  ]
...                       libperl: [ on  ]
...                     libpython: [ on  ]
...                      libslang: [ on  ]
...                     libunwind: [ on  ]
...            libdw-dwarf-unwind: [ on  ]
...                          zlib: [ on  ]
...                          lzma: [ on  ]

CC util/abspath.o
CC fd/array.o
PERF_VERSION = 4.1.rc5.g1ab14c

  CC       fs/fs.o
  CC       event-parse.o
  LD       fd/libapi-in.o
  CC       event-plugin.o
  CC       fs/debugfs.o
  CC       util/alias.o
  CC       trace-seq.o
<SNIP>
  CC       util/cloexec.o
  CC       util/thread-stack.o
  CC       builtin-kmem.o
  CC       builtin-lock.o
  CC       util/auxtrace.o
  CC       util/intel-pt-decoder/intel-pt-pkt-decoder.o

make[4]: *** No rule to make target '../../arch/x86/tools/gen-insn-attr-x86.awk', needed by 'util/intel-pt-decoder/inat-tables.c'. Stop. make[4]: *** Waiting for unfinished jobs....
GEN util/intel-pt-decoder/inat.c
cp: cannot stat ‘../../arch/x86/lib/inat.c’: No such file or directory
util/intel-pt-decoder/Build:10: recipe for target 'util/intel-pt-decoder/inat.c' failed
make[4]: *** [util/intel-pt-decoder/inat.c] Error 1
/tmp/perf-4.1.0-rc5/tools/build/Makefile.build:109: recipe for target 'intel-pt-decoder' failed
make[3]: *** [intel-pt-decoder] Error 2
make[3]: *** Waiting for unfinished jobs....
CC builtin-kvm.o
CC builtin-inject.o
/tmp/perf-4.1.0-rc5/tools/build/Makefile.build:109: recipe for target 'util' failed
make[2]: *** [util] Error 2
Makefile.perf:380: recipe for target 'libperf-in.o' failed
make[1]: *** [libperf-in.o] Error 2
make[1]: *** Waiting for unfinished jobs....

  CC       builtin-mem.o
  CC       builtin-data.o
  CC       builtin-trace.o

<SNIP>
LD tests/perf-in.o
LD perf-in.o
Makefile:68: recipe for target 'all' failed
make: *** [all] Error 2
make: Leaving directory '/tmp/perf-4.1.0-rc5/tools/perf' [acme@zoo perf-4.1.0-rc5]$

The patch fixed up wrt some recent changes to .gitignore and the makefiles is in my git tree at git.kernel.org, branch tmp.perf/pt.

Calling it a day, will continue on this tomorrow.

- Arnaldo

Quoted 421 lines

This essentially provides intel_pt_get_insn() which takes a binary buffer, uses the kernel's x86 instruction decoder to get details of the instruction and then categorizes it for consumption by an Intel PT decoder.

Signed-off-by Adrian Hunter <[email protected]>

---
 tools/build/Makefile.build                         |   2 +
 tools/perf/.gitignore                              |   2 +
 tools/perf/Makefile.perf                           |  12 +-
 tools/perf/util/intel-pt-decoder/Build             |  15 +-
 .../util/intel-pt-decoder/intel-pt-insn-decoder.c  | 246 +++++++++++++++++++++
 .../util/intel-pt-decoder/intel-pt-insn-decoder.h  |  65 ++++++
 6 files changed, 339 insertions(+), 3 deletions(-)
 create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c
 create mode 100644 tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h

tools/build/Makefile.build +2 -0

index 10df572..7ad74e4 100644
@@ -57,6 +57,8 @@ quiet_cmd_cc_i_c = CPP      $@
 quiet_cmd_cc_s_c = AS       $@
       cmd_cc_s_c = $(CC) $(c_flags) -S -o $@ $<
 
+quiet_cmd_gen = GEN      $@
+
 # Link agregate command
 # If there's nothing to link, create empty $@ object.
 quiet_cmd_ld_multi = LD       $@

tools/perf/.gitignore +2 -0

index 812f904..c88d5c5 100644
@@ -28,3 +28,5 @@ config.mak.autogen
 *-flex.*
 *.pyc
 *.pyo
+util/intel-pt-decoder/inat-tables.c
+util/intel-pt-decoder/inat.c

tools/perf/Makefile.perf +10 -2

index 5816a3b..3ae3a8e 100644
@@ -76,6 +76,12 @@ include config/utilities.mak
 #
 # Define NO_AUXTRACE if you do not want AUX area tracing support
 
+# As per kernel Makefile, avoid funny character set dependencies
+unexport LC_ALL
+LC_COLLATE=C
+LC_NUMERIC=C
+export LC_COLLATE LC_NUMERIC
+
 ifeq ($(srctree),)
 srctree := $(patsubst %/,%,$(dir $(shell pwd)))
 srctree := $(patsubst %/,%,$(dir $(srctree)))

@@ -122,6 +128,7 @@ INSTALL = install
 FLEX    = flex
 BISON   = bison
 STRIP   = strip
+AWK     = awk
 
 LIB_DIR          = $(srctree)/tools/lib/api/
 TRACE_EVENT_DIR = $(srctree)/tools/lib/traceevent/

@@ -272,7 +279,7 @@ strip: $(PROGRAMS) $(OUTPUT)perf
 
 PERF_IN := $(OUTPUT)perf-in.o
 
-export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX
+export srctree OUTPUT RM CC LD AR CFLAGS V BISON FLEX AWK
 build := -f $(srctree)/tools/build/Makefile.build dir=. obj
 
 $(PERF_IN): $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h FORCE

@@ -536,7 +543,8 @@ clean: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean config-clean
 	$(Q)find . -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) .config-detected
 	$(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)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex*
+	$(call QUIET_CLEAN, core-gen)   $(RM)  *.spec *.pyc *.pyo */*.pyc */*.pyo $(OUTPUT)common-cmds.h TAGS tags cscope* $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)FEATURE-DUMP $(OUTPUT)util/*-bison* $(OUTPUT)util/*-flex* \
+		$(OUTPUT)util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
 	$(QUIET_SUBDIR0)Documentation $(QUIET_SUBDIR1) clean
 	$(python-clean)
 

tools/perf/util/intel-pt-decoder/Build +14 -1

index 9d67381..f5f7f87 100644
@@ -1 +1,14 @@
-libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o
+libperf-$(CONFIG_AUXTRACE) += intel-pt-pkt-decoder.o intel-pt-insn-decoder.o
+
+inat_tables_script = ../../arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = ../../arch/x86/lib/x86-opcode-map.txt
+
+$(OUTPUT)util/intel-pt-decoder/inat-tables.c: $(inat_tables_script) $(inat_tables_maps)
+	@$(call echo-cmd,gen)$(AWK) -f $(inat_tables_script) $(inat_tables_maps) > $@ || rm -f $@
+
+$(OUTPUT)util/intel-pt-decoder/inat.c:
+	@$(call echo-cmd,gen)cp ../../arch/x86/lib/inat.c $(OUTPUT)util/intel-pt-decoder/inat.c
+
+$(OUTPUT)util/intel-pt-decoder/intel-pt-insn-decoder.o: $(OUTPUT)util/intel-pt-decoder/inat.c $(OUTPUT)util/intel-pt-decoder/inat-tables.c
+
+CFLAGS_intel-pt-insn-decoder.o += -I../../arch/x86/include -I$(OUTPUT)util/intel-pt-decoder -I../../arch/x86/lib -Wno-override-init

tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.c new file +246 -0

new file mode 100644
index 0000000..2fa82c5
@@ -0,0 +1,246 @@
+/*
+ * intel_pt_insn_decoder.c: Intel Processor Trace support
+ * Copyright (c) 2013-2014, 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 <stdio.h>
+#include <string.h>
+#include <endian.h>
+#include <byteswap.h>
+
+#include "event.h"
+
+#include <asm/insn.h>
+
+#include "inat.c"
+#include <insn.c>
+
+#include "intel-pt-insn-decoder.h"
+
+/* Based on branch_type() from perf_event_intel_lbr.c */
+static void intel_pt_insn_decoder(struct insn *insn,
+				  struct intel_pt_insn *intel_pt_insn)
+{
+	enum intel_pt_insn_op op = INTEL_PT_OP_OTHER;
+	enum intel_pt_insn_branch branch = INTEL_PT_BR_NO_BRANCH;
+	int ext;
+
+	if (insn_is_avx(insn)) {
+		intel_pt_insn->op = INTEL_PT_OP_OTHER;
+		intel_pt_insn->branch = INTEL_PT_BR_NO_BRANCH;
+		intel_pt_insn->length = insn->length;
+		return;
+	}
+
+	switch (insn->opcode.bytes[0]) {
+	case 0xf:
+		switch (insn->opcode.bytes[1]) {
+		case 0x05: /* syscall */
+		case 0x34: /* sysenter */
+			op = INTEL_PT_OP_SYSCALL;
+			branch = INTEL_PT_BR_INDIRECT;
+			break;
+		case 0x07: /* sysret */
+		case 0x35: /* sysexit */
+			op = INTEL_PT_OP_SYSRET;
+			branch = INTEL_PT_BR_INDIRECT;
+			break;
+		case 0x80 ... 0x8f: /* jcc */
+			op = INTEL_PT_OP_JCC;
+			branch = INTEL_PT_BR_CONDITIONAL;
+			break;
+		default:
+			break;
+		}
+		break;
+	case 0x70 ... 0x7f: /* jcc */
+		op = INTEL_PT_OP_JCC;
+		branch = INTEL_PT_BR_CONDITIONAL;
+		break;
+	case 0xc2: /* near ret */
+	case 0xc3: /* near ret */
+	case 0xca: /* far ret */
+	case 0xcb: /* far ret */
+		op = INTEL_PT_OP_RET;
+		branch = INTEL_PT_BR_INDIRECT;
+		break;
+	case 0xcf: /* iret */
+		op = INTEL_PT_OP_IRET;
+		branch = INTEL_PT_BR_INDIRECT;
+		break;
+	case 0xcc ... 0xce: /* int */
+		op = INTEL_PT_OP_INT;
+		branch = INTEL_PT_BR_INDIRECT;
+		break;
+	case 0xe8: /* call near rel */
+		op = INTEL_PT_OP_CALL;
+		branch = INTEL_PT_BR_UNCONDITIONAL;
+		break;
+	case 0x9a: /* call far absolute */
+		op = INTEL_PT_OP_CALL;
+		branch = INTEL_PT_BR_INDIRECT;
+		break;
+	case 0xe0 ... 0xe2: /* loop */
+		op = INTEL_PT_OP_LOOP;
+		branch = INTEL_PT_BR_CONDITIONAL;
+		break;
+	case 0xe3: /* jcc */
+		op = INTEL_PT_OP_JCC;
+		branch = INTEL_PT_BR_CONDITIONAL;
+		break;
+	case 0xe9: /* jmp */
+	case 0xeb: /* jmp */
+		op = INTEL_PT_OP_JMP;
+		branch = INTEL_PT_BR_UNCONDITIONAL;
+		break;
+	case 0xea: /* far jmp */
+		op = INTEL_PT_OP_JMP;
+		branch = INTEL_PT_BR_INDIRECT;
+		break;
+	case 0xff: /* call near absolute, call far absolute ind */
+		ext = (insn->modrm.bytes[0] >> 3) & 0x7;
+		switch (ext) {
+		case 2: /* near ind call */
+		case 3: /* far ind call */
+			op = INTEL_PT_OP_CALL;
+			branch = INTEL_PT_BR_INDIRECT;
+			break;
+		case 4:
+		case 5:
+			op = INTEL_PT_OP_JMP;
+			branch = INTEL_PT_BR_INDIRECT;
+			break;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+
+	intel_pt_insn->op = op;
+	intel_pt_insn->branch = branch;
+	intel_pt_insn->length = insn->length;
+
+	if (branch == INTEL_PT_BR_CONDITIONAL ||
+	    branch == INTEL_PT_BR_UNCONDITIONAL) {
+#if __BYTE_ORDER == __BIG_ENDIAN
+		switch (insn->immediate.nbytes) {
+		case 1:
+			intel_pt_insn->rel = insn->immediate.value;
+			break;
+		case 2:
+			intel_pt_insn->rel =
+					bswap_16((short)insn->immediate.value);
+			break;
+		case 4:
+			intel_pt_insn->rel = bswap_32(insn->immediate.value);
+			break;
+		}
+#else
+		intel_pt_insn->rel = insn->immediate.value;
+#endif
+	}
+}
+
+int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
+		      struct intel_pt_insn *intel_pt_insn)
+{
+	struct insn insn;
+
+	insn_init(&insn, buf, len, x86_64);
+	insn_get_length(&insn);
+	if (!insn_complete(&insn) || insn.length > len)
+		return -1;
+	intel_pt_insn_decoder(&insn, intel_pt_insn);
+	if (insn.length < INTEL_PT_INSN_DBG_BUF_SZ)
+		memcpy(intel_pt_insn->buf, buf, insn.length);
+	else
+		memcpy(intel_pt_insn->buf, buf, INTEL_PT_INSN_DBG_BUF_SZ);
+	return 0;
+}
+
+const char *branch_name[] = {
+	[INTEL_PT_OP_OTHER]	= "Other",
+	[INTEL_PT_OP_CALL]	= "Call",
+	[INTEL_PT_OP_RET]	= "Ret",
+	[INTEL_PT_OP_JCC]	= "Jcc",
+	[INTEL_PT_OP_JMP]	= "Jmp",
+	[INTEL_PT_OP_LOOP]	= "Loop",
+	[INTEL_PT_OP_IRET]	= "IRet",
+	[INTEL_PT_OP_INT]	= "Int",
+	[INTEL_PT_OP_SYSCALL]	= "Syscall",
+	[INTEL_PT_OP_SYSRET]	= "Sysret",
+};
+
+const char *intel_pt_insn_name(enum intel_pt_insn_op op)
+{
+	return branch_name[op];
+}
+
+int intel_pt_insn_desc(const struct intel_pt_insn *intel_pt_insn, char *buf,
+		       size_t buf_len)
+{
+	switch (intel_pt_insn->branch) {
+	case INTEL_PT_BR_CONDITIONAL:
+	case INTEL_PT_BR_UNCONDITIONAL:
+		return snprintf(buf, buf_len, "%s %s%d",
+				intel_pt_insn_name(intel_pt_insn->op),
+				intel_pt_insn->rel > 0 ? "+" : "",
+				intel_pt_insn->rel);
+	case INTEL_PT_BR_NO_BRANCH:
+	case INTEL_PT_BR_INDIRECT:
+		return snprintf(buf, buf_len, "%s",
+				intel_pt_insn_name(intel_pt_insn->op));
+	default:
+		break;
+	}
+	return 0;
+}
+
+size_t intel_pt_insn_max_size(void)
+{
+	return MAX_INSN_SIZE;
+}
+
+int intel_pt_insn_type(enum intel_pt_insn_op op)
+{
+	switch (op) {
+	case INTEL_PT_OP_OTHER:
+		return 0;
+	case INTEL_PT_OP_CALL:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL;
+	case INTEL_PT_OP_RET:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN;
+	case INTEL_PT_OP_JCC:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL;
+	case INTEL_PT_OP_JMP:
+		return PERF_IP_FLAG_BRANCH;
+	case INTEL_PT_OP_LOOP:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL;
+	case INTEL_PT_OP_IRET:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN |
+		       PERF_IP_FLAG_INTERRUPT;
+	case INTEL_PT_OP_INT:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
+		       PERF_IP_FLAG_INTERRUPT;
+	case INTEL_PT_OP_SYSCALL:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
+		       PERF_IP_FLAG_SYSCALLRET;
+	case INTEL_PT_OP_SYSRET:
+		return PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN |
+		       PERF_IP_FLAG_SYSCALLRET;
+	default:
+		return 0;
+	}
+}

tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h new file +59 -0

new file mode 100644
index 0000000..b0adbf3
@@ -0,0 +1,65 @@
+/*
+ * intel_pt_insn_decoder.h: Intel Processor Trace support
+ * Copyright (c) 2013-2014, 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 INCLUDE__INTEL_PT_INSN_DECODER_H__
+#define INCLUDE__INTEL_PT_INSN_DECODER_H__
+
+#include <stddef.h>
+#include <stdint.h>
+
+#define INTEL_PT_INSN_DESC_MAX		32
+#define INTEL_PT_INSN_DBG_BUF_SZ	16
+
+enum intel_pt_insn_op {
+	INTEL_PT_OP_OTHER,
+	INTEL_PT_OP_CALL,
+	INTEL_PT_OP_RET,
+	INTEL_PT_OP_JCC,
+	INTEL_PT_OP_JMP,
+	INTEL_PT_OP_LOOP,
+	INTEL_PT_OP_IRET,
+	INTEL_PT_OP_INT,
+	INTEL_PT_OP_SYSCALL,
+	INTEL_PT_OP_SYSRET,
+};
+
+enum intel_pt_insn_branch {
+	INTEL_PT_BR_NO_BRANCH,
+	INTEL_PT_BR_INDIRECT,
+	INTEL_PT_BR_CONDITIONAL,
+	INTEL_PT_BR_UNCONDITIONAL,
+};
+
+struct intel_pt_insn {
+	enum intel_pt_insn_op		op;
+	enum intel_pt_insn_branch	branch;
+	int				length;
+	int32_t				rel;
+	unsigned char			buf[INTEL_PT_INSN_DBG_BUF_SZ];
+};
+
+int intel_pt_get_insn(const unsigned char *buf, size_t len, int x86_64,
+		      struct intel_pt_insn *intel_pt_insn);
+
+const char *intel_pt_insn_name(enum intel_pt_insn_op op);
+
+int intel_pt_insn_desc(const struct intel_pt_insn *intel_pt_insn, char *buf,
+		       size_t buf_len);

Quoted 8 lines

tools/perf/util/intel-pt-decoder/intel-pt-insn-decoder.h new file +6 -0

+
+size_t intel_pt_insn_max_size(void);
+
+int intel_pt_insn_type(enum intel_pt_insn_op op);
+
+#endif

Signature · 1 line

1.9.1

Em Thu, Jun 18, 2015 at 07:29:41PM -0300, Arnaldo Carvalho de Melo escreveu:

Quoted 17 lines

Em Fri, May 29, 2015 at 04:33:33PM +0300, Adrian Hunter escreveu:

Quoted 2 lines

Add support for decoding instructions for Intel Processor Trace. The kernel x86 instruction decoder is used for this.

Ok, but we don't access kernel header files directly, and:

[acme@zoo linux]$ find . -name "insn.h" ./arch/x86/include/asm/insn.h ./arch/arm64/include/asm/insn.h ./arch/arm/include/asm/insn.h
[acme@zoo linux]$ find /usr/include -name "insn.h" [acme@zoo linux]$

But I need to look more into this patch to figure out if this is something generated at build time, etc, but before that I found a problem:

Quoted 6 lines

So:

Review

Quoted 2 lines

(quoted diff) +2 -0

+inat_tables_script = ../../arch/x86/tools/gen-insn-attr-x86.awk
+inat_tables_maps = ../../arch/x86/lib/x86-opcode-map.txt

These need to go into tools/perf/MANIFEST, so that:

So, after adding:

tools/perf/MANIFEST +7 -0

index fe50a1b34aa0..4e5662d8c274 100644
@@ -58,6 +58,13 @@ include/linux/stringify.h
 lib/hweight.c
 lib/rbtree.c
 include/linux/swab.h
+arch/x86/lib/insn.c
+arch/x86/lib/inat.c
+arch/x86/include/asm/insn.h
+arch/x86/include/asm/inat.h
+arch/x86/include/asm/inat_types.h
+arch/x86/tools/gen-insn-attr-x86.awk
+arch/x86/lib/x86-opcode-map.txt
 arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h
 arch/*/include/uapi/asm/perf_regs.h

The test passes:

[acme@zoo linux]$ make -C tools/perf -f tests/make tarpkg && echo Ok
make: Entering directory '/home/git/linux/tools/perf'
- tarpkg: ./tests/perf-targz-src-pkg .
make: Leaving directory '/home/git/linux/tools/perf'
Ok
[acme@zoo linux]$

Merging these changes with this changeset to continue testing...

Add support for Intel Processor Trace.

Intel PT support fits within the new auxtrace infrastructure. Recording is supporting by identifying the Intel PT PMU, parsing options and setting up events. Decoding is supported by queuing up trace data by cpu or thread and then decoding synchronously delivering synthesized event samples into the session processing for tools to consume.

Signed-off-by Adrian Hunter <[email protected]>

---
 tools/perf/arch/x86/util/Build      |    2 +
 tools/perf/arch/x86/util/intel-pt.c |  752 ++++++++++++++
 tools/perf/util/Build               |    1 +
 tools/perf/util/intel-pt.c          | 1889 +++++++++++++++++++++++++++++++++++
 tools/perf/util/intel-pt.h          |   51 +
 5 files changed, 2695 insertions(+)
 create mode 100644 tools/perf/arch/x86/util/intel-pt.c
 create mode 100644 tools/perf/util/intel-pt.c
 create mode 100644 tools/perf/util/intel-pt.h

tools/perf/arch/x86/util/Build +2 -0

index cfbccc4..1396088 100644
@@ -6,3 +6,5 @@ libperf-$(CONFIG_DWARF) += dwarf-regs.o
 
 libperf-$(CONFIG_LIBUNWIND)          += unwind-libunwind.o
 libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
+
+libperf-$(CONFIG_AUXTRACE) += intel-pt.o

tools/perf/arch/x86/util/intel-pt.c new file +752 -0

new file mode 100644
index 0000000..da7d2c1
@@ -0,0 +1,752 @@
+/*
+ * intel_pt.c: Intel Processor Trace support
+ * Copyright (c) 2013-2015, 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 <stdbool.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/log2.h>
+
+#include "../../perf.h"
+#include "../../util/session.h"
+#include "../../util/event.h"
+#include "../../util/evlist.h"
+#include "../../util/evsel.h"
+#include "../../util/cpumap.h"
+#include "../../util/parse-options.h"
+#include "../../util/parse-events.h"
+#include "../../util/pmu.h"
+#include "../../util/debug.h"
+#include "../../util/auxtrace.h"
+#include "../../util/tsc.h"
+#include "../../util/intel-pt.h"
+
+#define KiB(x) ((x) * 1024)
+#define MiB(x) ((x) * 1024 * 1024)
+#define KiB_MASK(x) (KiB(x) - 1)
+#define MiB_MASK(x) (MiB(x) - 1)
+
+#define INTEL_PT_DEFAULT_SAMPLE_SIZE	KiB(4)
+
+#define INTEL_PT_MAX_SAMPLE_SIZE	KiB(60)
+
+#define INTEL_PT_PSB_PERIOD_NEAR	256
+
+struct intel_pt_snapshot_ref {
+	void *ref_buf;
+	size_t ref_offset;
+	bool wrapped;
+};
+
+struct intel_pt_recording {
+	struct auxtrace_record		itr;
+	struct perf_pmu			*intel_pt_pmu;
+	int				have_sched_switch;
+	struct perf_evlist		*evlist;
+	bool				snapshot_mode;
+	bool				snapshot_init_done;
+	size_t				snapshot_size;
+	size_t				snapshot_ref_buf_size;
+	int				snapshot_ref_cnt;
+	struct intel_pt_snapshot_ref	*snapshot_refs;
+};
+
+static int intel_pt_parse_terms_with_default(struct list_head *formats,
+					     const char *str,
+					     u64 *config)
+{
+	struct list_head *terms;
+	struct perf_event_attr attr = { .size = 0, };
+	int err;
+
+	terms = malloc(sizeof(struct list_head));
+	if (!terms)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(terms);
+
+	err = parse_events_terms(terms, str);
+	if (err)
+		goto out_free;
+
+	attr.config = *config;
+	err = perf_pmu__config_terms(formats, &attr, terms, true, NULL);
+	if (err)
+		goto out_free;
+
+	*config = attr.config;
+out_free:
+	parse_events__free_terms(terms);
+	return err;
+}
+
+static int intel_pt_parse_terms(struct list_head *formats, const char *str,
+				u64 *config)
+{
+	*config = 0;
+	return intel_pt_parse_terms_with_default(formats, str, config);
+}
+
+static size_t intel_pt_psb_period(struct perf_pmu *intel_pt_pmu __maybe_unused,
+				  struct perf_evlist *evlist __maybe_unused)
+{
+	return 256;
+}
+
+static u64 intel_pt_default_config(struct perf_pmu *intel_pt_pmu)
+{
+	u64 config;
+
+	intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &config);
+	return config;
+}
+
+static int intel_pt_parse_snapshot_options(struct auxtrace_record *itr,
+					   struct record_opts *opts,
+					   const char *str)
+{
+	struct intel_pt_recording *ptr =
+			container_of(itr, struct intel_pt_recording, itr);
+	unsigned long long snapshot_size = 0;
+	char *endptr;
+
+	if (str) {
+		snapshot_size = strtoull(str, &endptr, 0);
+		if (*endptr || snapshot_size > SIZE_MAX)
+			return -1;
+	}
+
+	opts->auxtrace_snapshot_mode = true;
+	opts->auxtrace_snapshot_size = snapshot_size;
+
+	ptr->snapshot_size = snapshot_size;
+
+	return 0;
+}
+
+struct perf_event_attr *
+intel_pt_pmu_default_config(struct perf_pmu *intel_pt_pmu)
+{
+	struct perf_event_attr *attr;
+
+	attr = zalloc(sizeof(struct perf_event_attr));
+	if (!attr)
+		return NULL;
+
+	attr->config = intel_pt_default_config(intel_pt_pmu);
+
+	intel_pt_pmu->selectable = true;
+
+	return attr;
+}
+
+static size_t intel_pt_info_priv_size(struct auxtrace_record *itr __maybe_unused)
+{
+	return INTEL_PT_AUXTRACE_PRIV_SIZE;
+}
+
+static int intel_pt_info_fill(struct auxtrace_record *itr,
+			      struct perf_session *session,
+			      struct auxtrace_info_event *auxtrace_info,
+			      size_t priv_size)
+{
+	struct intel_pt_recording *ptr =
+			container_of(itr, struct intel_pt_recording, itr);
+	struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
+	struct perf_event_mmap_page *pc;
+	struct perf_tsc_conversion tc = { .time_mult = 0, };
+	bool cap_user_time_zero = false, per_cpu_mmaps;
+	u64 tsc_bit, noretcomp_bit;
+	int err;
+
+	if (priv_size != INTEL_PT_AUXTRACE_PRIV_SIZE)
+		return -EINVAL;
+
+	intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit);
+	intel_pt_parse_terms(&intel_pt_pmu->format, "noretcomp",
+			     &noretcomp_bit);
+
+	if (!session->evlist->nr_mmaps)
+		return -EINVAL;
+
+	pc = session->evlist->mmap[0].base;
+	if (pc) {
+		err = perf_read_tsc_conversion(pc, &tc);
+		if (err) {
+			if (err != -EOPNOTSUPP)
+				return err;
+		} else {
+			cap_user_time_zero = tc.time_mult != 0;
+		}
+		if (!cap_user_time_zero)
+			ui__warning("Intel Processor Trace: TSC not available\n");
+	}
+
+	per_cpu_mmaps = !cpu_map__empty(session->evlist->cpus);
+
+	auxtrace_info->type = PERF_AUXTRACE_INTEL_PT;
+	auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type;
+	auxtrace_info->priv[INTEL_PT_TIME_SHIFT] = tc.time_shift;
+	auxtrace_info->priv[INTEL_PT_TIME_MULT] = tc.time_mult;
+	auxtrace_info->priv[INTEL_PT_TIME_ZERO] = tc.time_zero;
+	auxtrace_info->priv[INTEL_PT_CAP_USER_TIME_ZERO] = cap_user_time_zero;
+	auxtrace_info->priv[INTEL_PT_TSC_BIT] = tsc_bit;
+	auxtrace_info->priv[INTEL_PT_NORETCOMP_BIT] = noretcomp_bit;
+	auxtrace_info->priv[INTEL_PT_HAVE_SCHED_SWITCH] = ptr->have_sched_switch;
+	auxtrace_info->priv[INTEL_PT_SNAPSHOT_MODE] = ptr->snapshot_mode;
+	auxtrace_info->priv[INTEL_PT_PER_CPU_MMAPS] = per_cpu_mmaps;
+
+	return 0;
+}
+
+static int intel_pt_track_switches(struct perf_evlist *evlist)
+{
+	const char *sched_switch = "sched:sched_switch";
+	struct perf_evsel *evsel;
+	int err;
+
+	if (!perf_evlist__can_select_event(evlist, sched_switch))
+		return -EPERM;
+
+	err = parse_events(evlist, sched_switch, NULL);
+	if (err) {
+		pr_debug2("%s: failed to parse %s, error %d\n",
+			  __func__, sched_switch, err);
+		return err;
+	}
+
+	evsel = perf_evlist__last(evlist);
+
+	perf_evsel__set_sample_bit(evsel, CPU);
+	perf_evsel__set_sample_bit(evsel, TIME);
+
+	evsel->system_wide = true;
+	evsel->no_aux_samples = true;
+	evsel->immediate = true;
+
+	return 0;
+}
+
+static int intel_pt_recording_options(struct auxtrace_record *itr,
+				      struct perf_evlist *evlist,
+				      struct record_opts *opts)
+{
+	struct intel_pt_recording *ptr =
+			container_of(itr, struct intel_pt_recording, itr);
+	struct perf_pmu *intel_pt_pmu = ptr->intel_pt_pmu;
+	bool have_timing_info;
+	struct perf_evsel *evsel, *intel_pt_evsel = NULL;
+	const struct cpu_map *cpus = evlist->cpus;
+	bool privileged = geteuid() == 0 || perf_event_paranoid() < 0;
+	u64 tsc_bit;
+
+	ptr->evlist = evlist;
+	ptr->snapshot_mode = opts->auxtrace_snapshot_mode;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type == intel_pt_pmu->type) {
+			if (intel_pt_evsel) {
+				pr_err("There may be only one " INTEL_PT_PMU_NAME " event\n");
+				return -EINVAL;
+			}
+			evsel->attr.freq = 0;
+			evsel->attr.sample_period = 1;
+			intel_pt_evsel = evsel;
+			opts->full_auxtrace = true;
+		}
+	}
+
+	if (opts->auxtrace_snapshot_mode && !opts->full_auxtrace) {
+		pr_err("Snapshot mode (-S option) requires " INTEL_PT_PMU_NAME " PMU event (-e " INTEL_PT_PMU_NAME ")\n");
+		return -EINVAL;
+	}
+
+	if (opts->use_clockid) {
+		pr_err("Cannot use clockid (-k option) with " INTEL_PT_PMU_NAME "\n");
+		return -EINVAL;
+	}
+
+	if (!opts->full_auxtrace)
+		return 0;
+
+	/* Set default sizes for snapshot mode */
+	if (opts->auxtrace_snapshot_mode) {
+		size_t psb_period = intel_pt_psb_period(intel_pt_pmu, evlist);
+
+		if (!opts->auxtrace_snapshot_size && !opts->auxtrace_mmap_pages) {
+			if (privileged) {
+				opts->auxtrace_mmap_pages = MiB(4) / page_size;
+			} else {
+				opts->auxtrace_mmap_pages = KiB(128) / page_size;
+				if (opts->mmap_pages == UINT_MAX)
+					opts->mmap_pages = KiB(256) / page_size;
+			}
+		} else if (!opts->auxtrace_mmap_pages && !privileged &&
+			   opts->mmap_pages == UINT_MAX) {
+			opts->mmap_pages = KiB(256) / page_size;
+		}
+		if (!opts->auxtrace_snapshot_size)
+			opts->auxtrace_snapshot_size =
+				opts->auxtrace_mmap_pages * (size_t)page_size;
+		if (!opts->auxtrace_mmap_pages) {
+			size_t sz = opts->auxtrace_snapshot_size;
+
+			sz = round_up(sz, page_size) / page_size;
+			opts->auxtrace_mmap_pages = roundup_pow_of_two(sz);
+		}
+		if (opts->auxtrace_snapshot_size >
+				opts->auxtrace_mmap_pages * (size_t)page_size) {
+			pr_err("Snapshot size %zu must not be greater than AUX area tracing mmap size %zu\n",
+			       opts->auxtrace_snapshot_size,
+			       opts->auxtrace_mmap_pages * (size_t)page_size);
+			return -EINVAL;
+		}
+		if (!opts->auxtrace_snapshot_size || !opts->auxtrace_mmap_pages) {
+			pr_err("Failed to calculate default snapshot size and/or AUX area tracing mmap pages\n");
+			return -EINVAL;
+		}
+		pr_debug2("Intel PT snapshot size: %zu\n",
+			  opts->auxtrace_snapshot_size);
+		if (psb_period &&
+		    opts->auxtrace_snapshot_size <= psb_period +
+						  INTEL_PT_PSB_PERIOD_NEAR)
+			ui__warning("Intel PT snapshot size (%zu) may be too small for PSB period (%zu)\n",
+				    opts->auxtrace_snapshot_size, psb_period);
+	}
+
+	/* Set default sizes for full trace mode */
+	if (opts->full_auxtrace && !opts->auxtrace_mmap_pages) {
+		if (privileged) {
+			opts->auxtrace_mmap_pages = MiB(4) / page_size;
+		} else {
+			opts->auxtrace_mmap_pages = KiB(128) / page_size;
+			if (opts->mmap_pages == UINT_MAX)
+				opts->mmap_pages = KiB(256) / page_size;
+		}
+	}
+
+	/* Validate auxtrace_mmap_pages */
+	if (opts->auxtrace_mmap_pages) {
+		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
+		size_t min_sz;
+
+		if (opts->auxtrace_snapshot_mode)
+			min_sz = KiB(4);
+		else
+			min_sz = KiB(8);
+
+		if (sz < min_sz || !is_power_of_2(sz)) {
+			pr_err("Invalid mmap size for Intel Processor Trace: must be at least %zuKiB and a power of 2\n",
+			       min_sz / 1024);
+			return -EINVAL;
+		}
+	}
+
+	intel_pt_parse_terms(&intel_pt_pmu->format, "tsc", &tsc_bit);
+
+	if (opts->full_auxtrace && (intel_pt_evsel->attr.config & tsc_bit))
+		have_timing_info = true;
+	else
+		have_timing_info = false;
+
+	/*
+	 * Per-cpu recording needs sched_switch events to distinguish different
+	 * threads.
+	 */
+	if (have_timing_info && !cpu_map__empty(cpus)) {
+		int err;
+
+		err = intel_pt_track_switches(evlist);
+		if (err == -EPERM)
+			pr_debug2("Unable to select sched:sched_switch\n");
+		else if (err)
+			return err;
+		else
+			ptr->have_sched_switch = 1;
+	}
+
+	if (intel_pt_evsel) {
+		/*
+		 * To obtain the auxtrace buffer file descriptor, the auxtrace
+		 * event must come first.
+		 */
+		perf_evlist__to_front(evlist, intel_pt_evsel);
+		/*
+		 * In the case of per-cpu mmaps, we need the CPU on the
+		 * AUX event.
+		 */
+		if (!cpu_map__empty(cpus))
+			perf_evsel__set_sample_bit(intel_pt_evsel, CPU);
+	}
+
+	/* Add dummy event to keep tracking */
+	if (opts->full_auxtrace) {
+		struct perf_evsel *tracking_evsel;
+		int err;
+
+		err = parse_events(evlist, "dummy:u", NULL);
+		if (err)
+			return err;
+
+		tracking_evsel = perf_evlist__last(evlist);
+
+		perf_evlist__set_tracking_event(evlist, tracking_evsel);
+
+		tracking_evsel->attr.freq = 0;
+		tracking_evsel->attr.sample_period = 1;
+
+		/* In per-cpu case, always need the time of mmap events etc */
+		if (!cpu_map__empty(cpus))
+			perf_evsel__set_sample_bit(tracking_evsel, TIME);
+	}
+
+	/*
+	 * Warn the user when we do not have enough information to decode i.e.
+	 * per-cpu with no sched_switch (except workload-only).
+	 */
+	if (!ptr->have_sched_switch && !cpu_map__empty(cpus) &&
+	    !target__none(&opts->target))
+		ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n");
+
+	return 0;
+}
+
+static int intel_pt_snapshot_start(struct auxtrace_record *itr)
+{
+	struct intel_pt_recording *ptr =
+			container_of(itr, struct intel_pt_recording, itr);
+	struct perf_evsel *evsel;
+
+	evlist__for_each(ptr->evlist, evsel) {
+		if (evsel->attr.type == ptr->intel_pt_pmu->type)
+			return perf_evlist__disable_event(ptr->evlist, evsel);
+	}
+	return -EINVAL;
+}
+
+static int intel_pt_snapshot_finish(struct auxtrace_record *itr)
+{
+	struct intel_pt_recording *ptr =
+			container_of(itr, struct intel_pt_recording, itr);
+	struct perf_evsel *evsel;
+
+	evlist__for_each(ptr->evlist, evsel) {
+		if (evsel->attr.type == ptr->intel_pt_pmu->type)
+			return perf_evlist__enable_event(ptr->evlist, evsel);
+	}
+	return -EINVAL;
+}
+
+static int intel_pt_alloc_snapshot_refs(struct intel_pt_recording *ptr, int idx)
+{
+	const size_t sz = sizeof(struct intel_pt_snapshot_ref);
+	int cnt = ptr->snapshot_ref_cnt, new_cnt = cnt * 2;
+	struct intel_pt_snapshot_ref *refs;
+
+	if (!new_cnt)
+		new_cnt = 16;
+
+	while (new_cnt <= idx)
+		new_cnt *= 2;
+
+	refs = calloc(new_cnt, sz);
+	if (!refs)
+		return -ENOMEM;
+
+	memcpy(refs, ptr->snapshot_refs, cnt * sz);
+
+	ptr->snapshot_refs = refs;
+	ptr->snapshot_ref_cnt = new_cnt;
+
+	return 0;
+}
+
+static void intel_pt_free_snapshot_refs(struct intel_pt_recording *ptr)
+{
+	int i;
+
+	for (i = 0; i < ptr->snapshot_ref_cnt; i++)
+		zfree(&ptr->snapshot_refs[i].ref_buf);
+	zfree(&ptr->snapshot_refs);
+}
+
+static void intel_pt_recording_free(struct auxtrace_record *itr)
+{
+	struct intel_pt_recording *ptr =
+			container_of(itr, struct intel_pt_recording, itr);
+
+	intel_pt_free_snapshot_refs(ptr);
+	free(ptr);
+}
+
+static int intel_pt_alloc_snapshot_ref(struct intel_pt_recording *ptr, int idx,
+				       size_t snapshot_buf_size)
+{
+	size_t ref_buf_size = ptr->snapshot_ref_buf_size;
+	void *ref_buf;
+
+	ref_buf = zalloc(ref_buf_size);
+	if (!ref_buf)
+		return -ENOMEM;
+
+	ptr->snapshot_refs[idx].ref_buf = ref_buf;
+	ptr->snapshot_refs[idx].ref_offset = snapshot_buf_size - ref_buf_size;
+
+	return 0;
+}
+
+static size_t intel_pt_snapshot_ref_buf_size(struct intel_pt_recording *ptr,
+					     size_t snapshot_buf_size)
+{
+	const size_t max_size = 256 * 1024;
+	size_t buf_size = 0, psb_period;
+
+	if (ptr->snapshot_size <= 64 * 1024)
+		return 0;
+
+	psb_period = intel_pt_psb_period(ptr->intel_pt_pmu, ptr->evlist);
+	if (psb_period)
+		buf_size = psb_period * 2;
+
+	if (!buf_size || buf_size > max_size)
+		buf_size = max_size;
+
+	if (buf_size >= snapshot_buf_size)
+		return 0;
+
+	if (buf_size >= ptr->snapshot_size / 2)
+		return 0;
+
+	return buf_size;
+}
+
+static int intel_pt_snapshot_init(struct intel_pt_recording *ptr,
+				  size_t snapshot_buf_size)
+{
+	if (ptr->snapshot_init_done)
+		return 0;
+
+	ptr->snapshot_init_done = true;
+
+	ptr->snapshot_ref_buf_size = intel_pt_snapshot_ref_buf_size(ptr,
+							snapshot_buf_size);
+
+	return 0;
+}
+
+/**
+ * intel_pt_compare_buffers - compare bytes in a buffer to a circular buffer.
+ * @buf1: first buffer
+ * @compare_size: number of bytes to compare
+ * @buf2: second buffer (a circular buffer)
+ * @offs2: offset in second buffer
+ * @buf2_size: size of second buffer
+ *
+ * The comparison allows for the possibility that the bytes to compare in the
+ * circular buffer are not contiguous.  It is assumed that @compare_size <=
+ * @buf2_size.  This function returns %false if the bytes are identical, %true
+ * otherwise.
+ */
+static bool intel_pt_compare_buffers(void *buf1, size_t compare_size,
+				     void *buf2, size_t offs2, size_t buf2_size)
+{
+	size_t end2 = offs2 + compare_size, part_size;
+
+	if (end2 <= buf2_size)
+		return memcmp(buf1, buf2 + offs2, compare_size);
+
+	part_size = end2 - buf2_size;
+	if (memcmp(buf1, buf2 + offs2, part_size))
+		return true;
+
+	compare_size -= part_size;
+
+	return memcmp(buf1 + part_size, buf2, compare_size);
+}
+
+static bool intel_pt_compare_ref(void *ref_buf, size_t ref_offset,
+				 size_t ref_size, size_t buf_size,
+				 void *data, size_t head)
+{
+	size_t ref_end = ref_offset + ref_size;
+
+	if (ref_end > buf_size) {
+		if (head > ref_offset || head < ref_end - buf_size)
+			return true;
+	} else if (head > ref_offset && head < ref_end) {
+		return true;
+	}
+
+	return intel_pt_compare_buffers(ref_buf, ref_size, data, ref_offset,
+					buf_size);
+}
+
+static void intel_pt_copy_ref(void *ref_buf, size_t ref_size, size_t buf_size,
+			      void *data, size_t head)
+{
+	if (head >= ref_size) {
+		memcpy(ref_buf, data + head - ref_size, ref_size);
+	} else {
+		memcpy(ref_buf, data, head);
+		ref_size -= head;
+		memcpy(ref_buf + head, data + buf_size - ref_size, ref_size);
+	}
+}
+
+static bool intel_pt_wrapped(struct intel_pt_recording *ptr, int idx,
+			     struct auxtrace_mmap *mm, unsigned char *data,
+			     u64 head)
+{
+	struct intel_pt_snapshot_ref *ref = &ptr->snapshot_refs[idx];
+	bool wrapped;
+
+	wrapped = intel_pt_compare_ref(ref->ref_buf, ref->ref_offset,
+				       ptr->snapshot_ref_buf_size, mm->len,
+				       data, head);
+
+	intel_pt_copy_ref(ref->ref_buf, ptr->snapshot_ref_buf_size, mm->len,
+			  data, head);
+
+	return wrapped;
+}
+
+static bool intel_pt_first_wrap(u64 *data, size_t buf_size)
+{
+	int i, a, b;
+
+	b = buf_size >> 3;
+	a = b - 512;
+	if (a < 0)
+		a = 0;
+
+	for (i = a; i < b; i++) {
+		if (data[i])
+			return true;
+	}
+
+	return false;
+}
+
+static int intel_pt_find_snapshot(struct auxtrace_record *itr, int idx,
+				  struct auxtrace_mmap *mm, unsigned char *data,
+				  u64 *head, u64 *old)
+{
+	struct intel_pt_recording *ptr =
+			container_of(itr, struct intel_pt_recording, itr);
+	bool wrapped;
+	int err;
+
+	pr_debug3("%s: mmap index %d old head %zu new head %zu\n",
+		  __func__, idx, (size_t)*old, (size_t)*head);
+
+	err = intel_pt_snapshot_init(ptr, mm->len);
+	if (err)
+		goto out_err;
+
+	if (idx >= ptr->snapshot_ref_cnt) {
+		err = intel_pt_alloc_snapshot_refs(ptr, idx);
+		if (err)
+			goto out_err;
+	}
+
+	if (ptr->snapshot_ref_buf_size) {
+		if (!ptr->snapshot_refs[idx].ref_buf) {
+			err = intel_pt_alloc_snapshot_ref(ptr, idx, mm->len);
+			if (err)
+				goto out_err;
+		}
+		wrapped = intel_pt_wrapped(ptr, idx, mm, data, *head);
+	} else {
+		wrapped = ptr->snapshot_refs[idx].wrapped;
+		if (!wrapped && intel_pt_first_wrap((u64 *)data, mm->len)) {
+			ptr->snapshot_refs[idx].wrapped = true;
+			wrapped = true;
+		}
+	}
+
+	/*
+	 * In full trace mode 'head' continually increases.  However in snapshot
+	 * mode 'head' is an offset within the buffer.  Here 'old' and 'head'
+	 * are adjusted to match the full trace case which expects that 'old' is
+	 * always less than 'head'.
+	 */
+	if (wrapped) {
+		*old = *head;
+		*head += mm->len;
+	} else {
+		if (mm->mask)
+			*old &= mm->mask;
+		else
+			*old %= mm->len;
+		if (*old > *head)
+			*head += mm->len;
+	}
+
+	pr_debug3("%s: wrap-around %sdetected, adjusted old head %zu adjusted new head %zu\n",
+		  __func__, wrapped ? "" : "not ", (size_t)*old, (size_t)*head);
+
+	return 0;
+
+out_err:
+	pr_err("%s: failed, error %d\n", __func__, err);
+	return err;
+}
+
+static u64 intel_pt_reference(struct auxtrace_record *itr __maybe_unused)
+{
+	return rdtsc();
+}
+
+static int intel_pt_read_finish(struct auxtrace_record *itr, int idx)
+{
+	struct intel_pt_recording *ptr =
+			container_of(itr, struct intel_pt_recording, itr);
+	struct perf_evsel *evsel;
+
+	evlist__for_each(ptr->evlist, evsel) {
+		if (evsel->attr.type == ptr->intel_pt_pmu->type)
+			return perf_evlist__enable_event_idx(ptr->evlist, evsel,
+							     idx);
+	}
+	return -EINVAL;
+}
+
+struct auxtrace_record *intel_pt_recording_init(int *err)
+{
+	struct perf_pmu *intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
+	struct intel_pt_recording *ptr;
+
+	if (!intel_pt_pmu)
+		return NULL;
+
+	ptr = zalloc(sizeof(struct intel_pt_recording));
+	if (!ptr) {
+		*err = -ENOMEM;
+		return NULL;
+	}
+
+	ptr->intel_pt_pmu = intel_pt_pmu;
+	ptr->itr.recording_options = intel_pt_recording_options;
+	ptr->itr.info_priv_size = intel_pt_info_priv_size;
+	ptr->itr.info_fill = intel_pt_info_fill;
+	ptr->itr.free = intel_pt_recording_free;
+	ptr->itr.snapshot_start = intel_pt_snapshot_start;
+	ptr->itr.snapshot_finish = intel_pt_snapshot_finish;
+	ptr->itr.find_snapshot = intel_pt_find_snapshot;
+	ptr->itr.parse_snapshot_options = intel_pt_parse_snapshot_options;
+	ptr->itr.reference = intel_pt_reference;
+	ptr->itr.read_finish = intel_pt_read_finish;
+	return &ptr->itr;
+}

tools/perf/util/Build +1 -0

index 86c81f6..ec7ab9d 100644
@@ -76,6 +76,7 @@ libperf-y += cloexec.o
 libperf-y += thread-stack.o
 libperf-$(CONFIG_AUXTRACE) += auxtrace.o
 libperf-$(CONFIG_AUXTRACE) += intel-pt-decoder/
+libperf-$(CONFIG_AUXTRACE) += intel-pt.o
 libperf-y += parse-branch-options.o
 
 libperf-$(CONFIG_LIBELF) += symbol-elf.o

tools/perf/util/intel-pt.c new file +1889 -0

new file mode 100644
index 0000000..6d66879
@@ -0,0 +1,1889 @@
+/*
+ * intel_pt.c: Intel Processor Trace support
+ * Copyright (c) 2013-2015, 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 <stdio.h>
+#include <stdbool.h>
+#include <errno.h>
+#include <linux/kernel.h>
+#include <linux/types.h>
+
+#include "../perf.h"
+#include "session.h"
+#include "machine.h"
+#include "tool.h"
+#include "event.h"
+#include "evlist.h"
+#include "evsel.h"
+#include "map.h"
+#include "color.h"
+#include "util.h"
+#include "thread.h"
+#include "thread-stack.h"
+#include "symbol.h"
+#include "callchain.h"
+#include "dso.h"
+#include "debug.h"
+#include "auxtrace.h"
+#include "tsc.h"
+#include "intel-pt.h"
+
+#include "intel-pt-decoder/intel-pt-log.h"
+#include "intel-pt-decoder/intel-pt-decoder.h"
+#include "intel-pt-decoder/intel-pt-insn-decoder.h"
+#include "intel-pt-decoder/intel-pt-pkt-decoder.h"
+
+#define MAX_TIMESTAMP (~0ULL)
+
+struct intel_pt {
+	struct auxtrace auxtrace;
+	struct auxtrace_queues queues;
+	struct auxtrace_heap heap;
+	u32 auxtrace_type;
+	struct perf_session *session;
+	struct machine *machine;
+	struct perf_evsel *switch_evsel;
+	struct thread *unknown_thread;
+	bool timeless_decoding;
+	bool sampling_mode;
+	bool snapshot_mode;
+	bool per_cpu_mmaps;
+	bool have_tsc;
+	bool data_queued;
+	bool est_tsc;
+	bool sync_switch;
+	bool est_tsc_orig;
+	int have_sched_switch;
+	u32 pmu_type;
+	u64 kernel_start;
+	u64 switch_ip;
+	u64 ptss_ip;
+
+	struct perf_tsc_conversion tc;
+	bool cap_user_time_zero;
+
+	struct itrace_synth_opts synth_opts;
+
+	bool sample_instructions;
+	u64 instructions_sample_type;
+	u64 instructions_sample_period;
+	u64 instructions_id;
+
+	bool sample_branches;
+	u32 branches_filter;
+	u64 branches_sample_type;
+	u64 branches_id;
+
+	bool sample_transactions;
+	u64 transactions_sample_type;
+	u64 transactions_id;
+
+	bool synth_needs_swap;
+
+	u64 tsc_bit;
+	u64 noretcomp_bit;
+};
+
+enum switch_state {
+	INTEL_PT_SS_NOT_TRACING,
+	INTEL_PT_SS_UNKNOWN,
+	INTEL_PT_SS_TRACING,
+	INTEL_PT_SS_EXPECTING_SWITCH_EVENT,
+	INTEL_PT_SS_EXPECTING_SWITCH_IP,
+};
+
+struct intel_pt_queue {
+	struct intel_pt *pt;
+	unsigned int queue_nr;
+	struct auxtrace_buffer *buffer;
+	void *decoder;
+	const struct intel_pt_state *state;
+	struct ip_callchain *chain;
+	union perf_event *event_buf;
+	bool on_heap;
+	bool stop;
+	bool step_through_buffers;
+	bool use_buffer_pid_tid;
+	pid_t pid, tid;
+	int cpu;
+	int switch_state;
+	pid_t next_tid;
+	struct thread *thread;
+	bool exclude_kernel;
+	bool have_sample;
+	u64 time;
+	u64 timestamp;
+	u32 flags;
+	u16 insn_len;
+};
+
+static void intel_pt_dump(struct intel_pt *pt __maybe_unused,
+			  unsigned char *buf, size_t len)
+{
+	struct intel_pt_pkt packet;
+	size_t pos = 0;
+	int ret, pkt_len, i;
+	char desc[INTEL_PT_PKT_DESC_MAX];
+	const char *color = PERF_COLOR_BLUE;
+
+	color_fprintf(stdout, color,
+		      ". ... Intel Processor Trace data: size %zu bytes\n",
+		      len);
+
+	while (len) {
+		ret = intel_pt_get_packet(buf, len, &packet);
+		if (ret > 0)
+			pkt_len = ret;
+		else
+			pkt_len = 1;
+		printf(".");
+		color_fprintf(stdout, color, "  %08x: ", pos);
+		for (i = 0; i < pkt_len; i++)
+			color_fprintf(stdout, color, " %02x", buf[i]);
+		for (; i < 16; i++)
+			color_fprintf(stdout, color, "   ");
+		if (ret > 0) {
+			ret = intel_pt_pkt_desc(&packet, desc,
+						INTEL_PT_PKT_DESC_MAX);
+			if (ret > 0)
+				color_fprintf(stdout, color, " %s\n", desc);
+		} else {
+			color_fprintf(stdout, color, " Bad packet!\n");
+		}
+		pos += pkt_len;
+		buf += pkt_len;
+		len -= pkt_len;
+	}
+}
+
+static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
+				size_t len)
+{
+	printf(".\n");
+	intel_pt_dump(pt, buf, len);
+}
+
+static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
+				   struct auxtrace_buffer *b)
+{
+	void *start;
+
+	start = intel_pt_find_overlap(a->data, a->size, b->data, b->size,
+				      pt->have_tsc);
+	if (!start)
+		return -EINVAL;
+	b->use_size = b->data + b->size - start;
+	b->use_data = start;
+	return 0;
+}
+
+static void intel_pt_use_buffer_pid_tid(struct intel_pt_queue *ptq,
+					struct auxtrace_queue *queue,
+					struct auxtrace_buffer *buffer)
+{
+	if (queue->cpu == -1 && buffer->cpu != -1)
+		ptq->cpu = buffer->cpu;
+
+	ptq->pid = buffer->pid;
+	ptq->tid = buffer->tid;
+
+	intel_pt_log("queue %u cpu %d pid %d tid %d\n",
+		     ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid);
+
+	ptq->thread = NULL;
+
+	if (ptq->tid != -1) {
+		if (ptq->pid != -1)
+			ptq->thread = machine__findnew_thread(ptq->pt->machine,
+							      ptq->pid,
+							      ptq->tid);
+		else
+			ptq->thread = machine__find_thread(ptq->pt->machine, -1,
+							   ptq->tid);
+	}
+}
+
+/* This function assumes data is processed sequentially only */
+static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
+{
+	struct intel_pt_queue *ptq = data;
+	struct auxtrace_buffer *buffer = ptq->buffer, *old_buffer = buffer;
+	struct auxtrace_queue *queue;
+
+	if (ptq->stop) {
+		b->len = 0;
+		return 0;
+	}
+
+	queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
+
+	buffer = auxtrace_buffer__next(queue, buffer);
+	if (!buffer) {
+		if (old_buffer)
+			auxtrace_buffer__drop_data(old_buffer);
+		b->len = 0;
+		return 0;
+	}
+
+	ptq->buffer = buffer;
+
+	if (!buffer->data) {
+		int fd = perf_data_file__fd(ptq->pt->session->file);
+
+		buffer->data = auxtrace_buffer__get_data(buffer, fd);
+		if (!buffer->data)
+			return -ENOMEM;
+	}
+
+	if (ptq->pt->snapshot_mode && !buffer->consecutive && old_buffer &&
+	    intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer))
+		return -ENOMEM;
+
+	if (old_buffer)
+		auxtrace_buffer__drop_data(old_buffer);
+
+	if (buffer->use_data) {
+		b->len = buffer->use_size;
+		b->buf = buffer->use_data;
+	} else {
+		b->len = buffer->size;
+		b->buf = buffer->data;
+	}
+	b->ref_timestamp = buffer->reference;
+
+	if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode &&
+						      !buffer->consecutive)) {
+		b->consecutive = false;
+		b->trace_nr = buffer->buffer_nr;
+	} else {
+		b->consecutive = true;
+	}
+
+	if (ptq->use_buffer_pid_tid && (ptq->pid != buffer->pid ||
+					ptq->tid != buffer->tid))
+		intel_pt_use_buffer_pid_tid(ptq, queue, buffer);
+
+	if (ptq->step_through_buffers)
+		ptq->stop = true;
+
+	if (!b->len)
+		return intel_pt_get_trace(b, data);
+
+	return 0;
+}
+
+struct intel_pt_cache_entry {
+	struct auxtrace_cache_entry	entry;
+	u64				insn_cnt;
+	u64				byte_cnt;
+	enum intel_pt_insn_op		op;
+	enum intel_pt_insn_branch	branch;
+	int				length;
+	int32_t				rel;
+};
+
+static int intel_pt_config_div(const char *var, const char *value, void *data)
+{
+	int *d = data;
+	long val;
+
+	if (!strcmp(var, "intel-pt.cache-divisor")) {
+		val = strtol(value, NULL, 0);
+		if (val > 0 && val <= INT_MAX)
+			*d = val;
+	}
+
+	return 0;
+}
+
+static int intel_pt_cache_divisor(void)
+{
+	static int d;
+
+	if (d)
+		return d;
+
+	perf_config(intel_pt_config_div, &d);
+
+	if (!d)
+		d = 64;
+
+	return d;
+}
+
+static unsigned int intel_pt_cache_size(struct dso *dso,
+					struct machine *machine)
+{
+	off_t size;
+
+	size = dso__data_size(dso, machine);
+	size /= intel_pt_cache_divisor();
+	if (size < 1000)
+		return 10;
+	if (size > (1 << 21))
+		return 21;
+	return 32 - __builtin_clz(size);
+}
+
+static struct auxtrace_cache *intel_pt_cache(struct dso *dso,
+					     struct machine *machine)
+{
+	struct auxtrace_cache *c;
+	unsigned int bits;
+
+	if (dso->auxtrace_cache)
+		return dso->auxtrace_cache;
+
+	bits = intel_pt_cache_size(dso, machine);
+
+	/* Ignoring cache creation failure */
+	c = auxtrace_cache__new(bits, sizeof(struct intel_pt_cache_entry), 200);
+
+	dso->auxtrace_cache = c;
+
+	return c;
+}
+
+static int intel_pt_cache_add(struct dso *dso, struct machine *machine,
+			      u64 offset, u64 insn_cnt, u64 byte_cnt,
+			      struct intel_pt_insn *intel_pt_insn)
+{
+	struct auxtrace_cache *c = intel_pt_cache(dso, machine);
+	struct intel_pt_cache_entry *e;
+	int err;
+
+	if (!c)
+		return -ENOMEM;
+
+	e = auxtrace_cache__alloc_entry(c);
+	if (!e)
+		return -ENOMEM;
+
+	e->insn_cnt = insn_cnt;
+	e->byte_cnt = byte_cnt;
+	e->op = intel_pt_insn->op;
+	e->branch = intel_pt_insn->branch;
+	e->length = intel_pt_insn->length;
+	e->rel = intel_pt_insn->rel;
+
+	err = auxtrace_cache__add(c, offset, &e->entry);
+	if (err)
+		auxtrace_cache__free_entry(c, e);
+
+	return err;
+}
+
+static struct intel_pt_cache_entry *
+intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset)
+{
+	struct auxtrace_cache *c = intel_pt_cache(dso, machine);
+
+	if (!c)
+		return NULL;
+
+	return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
+}
+
+static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
+				   uint64_t *insn_cnt_ptr, uint64_t *ip,
+				   uint64_t to_ip, uint64_t max_insn_cnt,
+				   void *data)
+{
+	struct intel_pt_queue *ptq = data;
+	struct machine *machine = ptq->pt->machine;
+	struct thread *thread;
+	struct addr_location al;
+	unsigned char buf[1024];
+	size_t bufsz;
+	ssize_t len;
+	int x86_64;
+	u8 cpumode;
+	u64 offset, start_offset, start_ip;
+	u64 insn_cnt = 0;
+	bool one_map = true;
+
+	if (to_ip && *ip == to_ip)
+		goto out_no_cache;
+
+	bufsz = intel_pt_insn_max_size();
+
+	if (*ip >= ptq->pt->kernel_start)
+		cpumode = PERF_RECORD_MISC_KERNEL;
+	else
+		cpumode = PERF_RECORD_MISC_USER;
+
+	thread = ptq->thread;
+	if (!thread) {
+		if (cpumode != PERF_RECORD_MISC_KERNEL)
+			return -EINVAL;
+		thread = ptq->pt->unknown_thread;
+	}
+
+	while (1) {
+		thread__find_addr_map(thread, cpumode, MAP__FUNCTION, *ip, &al);
+		if (!al.map || !al.map->dso)
+			return -EINVAL;
+
+		if (al.map->dso->data.status == DSO_DATA_STATUS_ERROR &&
+		    dso__data_status_seen(al.map->dso,
+					  DSO_DATA_STATUS_SEEN_ITRACE))
+			return -ENOENT;
+
+		offset = al.map->map_ip(al.map, *ip);
+
+		if (!to_ip && one_map) {
+			struct intel_pt_cache_entry *e;
+
+			e = intel_pt_cache_lookup(al.map->dso, machine, offset);
+			if (e &&
+			    (!max_insn_cnt || e->insn_cnt <= max_insn_cnt)) {
+				*insn_cnt_ptr = e->insn_cnt;
+				*ip += e->byte_cnt;
+				intel_pt_insn->op = e->op;
+				intel_pt_insn->branch = e->branch;
+				intel_pt_insn->length = e->length;
+				intel_pt_insn->rel = e->rel;
+				intel_pt_log_insn_no_data(intel_pt_insn, *ip);
+				return 0;
+			}
+		}
+
+		start_offset = offset;
+		start_ip = *ip;
+
+		/* Load maps to ensure dso->is_64_bit has been updated */
+		map__load(al.map, machine->symbol_filter);
+
+		x86_64 = al.map->dso->is_64_bit;
+
+		while (1) {
+			len = dso__data_read_offset(al.map->dso, machine,
+						    offset, buf, bufsz);
+			if (len <= 0)
+				return -EINVAL;
+
+			if (intel_pt_get_insn(buf, len, x86_64, intel_pt_insn))
+				return -EINVAL;
+
+			intel_pt_log_insn(intel_pt_insn, *ip);
+
+			insn_cnt += 1;
+
+			if (intel_pt_insn->branch != INTEL_PT_BR_NO_BRANCH)
+				goto out;
+
+			if (max_insn_cnt && insn_cnt >= max_insn_cnt)
+				goto out_no_cache;
+
+			*ip += intel_pt_insn->length;
+
+			if (to_ip && *ip == to_ip)
+				goto out_no_cache;
+
+			if (*ip >= al.map->end)
+				break;
+
+			offset += intel_pt_insn->length;
+		}
+		one_map = false;
+	}
+out:
+	*insn_cnt_ptr = insn_cnt;
+
+	if (!one_map)
+		goto out_no_cache;
+
+	/*
+	 * Didn't lookup in the 'to_ip' case, so do it now to prevent duplicate
+	 * entries.
+	 */
+	if (to_ip) {
+		struct intel_pt_cache_entry *e;
+
+		e = intel_pt_cache_lookup(al.map->dso, machine, start_offset);
+		if (e)
+			return 0;
+	}
+
+	/* Ignore cache errors */
+	intel_pt_cache_add(al.map->dso, machine, start_offset, insn_cnt,
+			   *ip - start_ip, intel_pt_insn);
+
+	return 0;
+
+out_no_cache:
+	*insn_cnt_ptr = insn_cnt;
+	return 0;
+}
+
+static bool intel_pt_get_config(struct intel_pt *pt,
+				struct perf_event_attr *attr, u64 *config)
+{
+	if (attr->type == pt->pmu_type) {
+		if (config)
+			*config = attr->config;
+		return true;
+	}
+
+	return false;
+}
+
+static bool intel_pt_exclude_kernel(struct intel_pt *pt)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(pt->session->evlist, evsel) {
+		if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
+		    !evsel->attr.exclude_kernel)
+			return false;
+	}
+	return true;
+}
+
+static bool intel_pt_return_compression(struct intel_pt *pt)
+{
+	struct perf_evsel *evsel;
+	u64 config;
+
+	if (!pt->noretcomp_bit)
+		return true;
+
+	evlist__for_each(pt->session->evlist, evsel) {
+		if (intel_pt_get_config(pt, &evsel->attr, &config) &&
+		    (config & pt->noretcomp_bit))
+			return false;
+	}
+	return true;
+}
+
+static bool intel_pt_timeless_decoding(struct intel_pt *pt)
+{
+	struct perf_evsel *evsel;
+	bool timeless_decoding = true;
+	u64 config;
+
+	if (!pt->tsc_bit || !pt->cap_user_time_zero)
+		return true;
+
+	evlist__for_each(pt->session->evlist, evsel) {
+		if (!(evsel->attr.sample_type & PERF_SAMPLE_TIME))
+			return true;
+		if (intel_pt_get_config(pt, &evsel->attr, &config)) {
+			if (config & pt->tsc_bit)
+				timeless_decoding = false;
+			else
+				return true;
+		}
+	}
+	return timeless_decoding;
+}
+
+static bool intel_pt_tracing_kernel(struct intel_pt *pt)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each(pt->session->evlist, evsel) {
+		if (intel_pt_get_config(pt, &evsel->attr, NULL) &&
+		    !evsel->attr.exclude_kernel)
+			return true;
+	}
+	return false;
+}
+
+static bool intel_pt_have_tsc(struct intel_pt *pt)
+{
+	struct perf_evsel *evsel;
+	bool have_tsc = false;
+	u64 config;
+
+	if (!pt->tsc_bit)
+		return false;
+
+	evlist__for_each(pt->session->evlist, evsel) {
+		if (intel_pt_get_config(pt, &evsel->attr, &config)) {
+			if (config & pt->tsc_bit)
+				have_tsc = true;
+			else
+				return false;
+		}
+	}
+	return have_tsc;
+}
+
+static u64 intel_pt_ns_to_ticks(const struct intel_pt *pt, u64 ns)
+{
+	u64 quot, rem;
+
+	quot = ns / pt->tc.time_mult;
+	rem  = ns % pt->tc.time_mult;
+	return (quot << pt->tc.time_shift) + (rem << pt->tc.time_shift) /
+		pt->tc.time_mult;
+}
+
+static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
+						   unsigned int queue_nr)
+{
+	struct intel_pt_params params = { .get_trace = 0, };
+	struct intel_pt_queue *ptq;
+
+	ptq = zalloc(sizeof(struct intel_pt_queue));
+	if (!ptq)
+		return NULL;
+
+	if (pt->synth_opts.callchain) {
+		size_t sz = sizeof(struct ip_callchain);
+
+		sz += pt->synth_opts.callchain_sz * sizeof(u64);
+		ptq->chain = zalloc(sz);
+		if (!ptq->chain)
+			goto out_free;
+	}
+
+	ptq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
+	if (!ptq->event_buf)
+		goto out_free;
+
+	ptq->pt = pt;
+	ptq->queue_nr = queue_nr;
+	ptq->exclude_kernel = intel_pt_exclude_kernel(pt);
+	ptq->pid = -1;
+	ptq->tid = -1;
+	ptq->cpu = -1;
+	ptq->next_tid = -1;
+
+	params.get_trace = intel_pt_get_trace;
+	params.walk_insn = intel_pt_walk_next_insn;
+	params.data = ptq;
+	params.return_compression = intel_pt_return_compression(pt);
+
+	if (pt->synth_opts.instructions) {
+		if (pt->synth_opts.period) {
+			switch (pt->synth_opts.period_type) {
+			case PERF_ITRACE_PERIOD_INSTRUCTIONS:
+				params.period_type =
+						INTEL_PT_PERIOD_INSTRUCTIONS;
+				params.period = pt->synth_opts.period;
+				break;
+			case PERF_ITRACE_PERIOD_TICKS:
+				params.period_type = INTEL_PT_PERIOD_TICKS;
+				params.period = pt->synth_opts.period;
+				break;
+			case PERF_ITRACE_PERIOD_NANOSECS:
+				params.period_type = INTEL_PT_PERIOD_TICKS;
+				params.period = intel_pt_ns_to_ticks(pt,
+							pt->synth_opts.period);
+				break;
+			default:
+				break;
+			}
+		}
+
+		if (!params.period) {
+			params.period_type = INTEL_PT_PERIOD_INSTRUCTIONS;
+			params.period = 1000;
+		}
+	}
+
+	ptq->decoder = intel_pt_decoder_new(&params);
+	if (!ptq->decoder)
+		goto out_free;
+
+	return ptq;
+
+out_free:
+	zfree(&ptq->event_buf);
+	zfree(&ptq->chain);
+	free(ptq);
+	return NULL;
+}
+
+static void intel_pt_free_queue(void *priv)
+{
+	struct intel_pt_queue *ptq = priv;
+
+	if (!ptq)
+		return;
+	intel_pt_decoder_free(ptq->decoder);
+	zfree(&ptq->event_buf);
+	zfree(&ptq->chain);
+	free(ptq);
+}
+
+static void intel_pt_set_pid_tid_cpu(struct intel_pt *pt,
+				     struct auxtrace_queue *queue)
+{
+	struct intel_pt_queue *ptq = queue->priv;
+
+	if (queue->tid == -1 || pt->have_sched_switch) {
+		ptq->tid = machine__get_current_tid(pt->machine, ptq->cpu);
+		ptq->thread = NULL;
+	}
+
+	if (!ptq->thread && ptq->tid != -1)
+		ptq->thread = machine__find_thread(pt->machine, -1, ptq->tid);
+
+	if (ptq->thread) {
+		ptq->pid = ptq->thread->pid_;
+		if (queue->cpu == -1)
+			ptq->cpu = ptq->thread->cpu;
+	}
+}
+
+static void intel_pt_sample_flags(struct intel_pt_queue *ptq)
+{
+	if (ptq->state->flags & INTEL_PT_ABORT_TX) {
+		ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT;
+	} else if (ptq->state->flags & INTEL_PT_ASYNC) {
+		if (ptq->state->to_ip)
+			ptq->flags = PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL |
+				     PERF_IP_FLAG_ASYNC |
+				     PERF_IP_FLAG_INTERRUPT;
+		else
+			ptq->flags = PERF_IP_FLAG_BRANCH |
+				     PERF_IP_FLAG_TRACE_END;
+		ptq->insn_len = 0;
+	} else {
+		if (ptq->state->from_ip)
+			ptq->flags = intel_pt_insn_type(ptq->state->insn_op);
+		else
+			ptq->flags = PERF_IP_FLAG_BRANCH |
+				     PERF_IP_FLAG_TRACE_BEGIN;
+		if (ptq->state->flags & INTEL_PT_IN_TX)
+			ptq->flags |= PERF_IP_FLAG_IN_TX;
+		ptq->insn_len = ptq->state->insn_len;
+	}
+}
+
+static int intel_pt_setup_queue(struct intel_pt *pt,
+				struct auxtrace_queue *queue,
+				unsigned int queue_nr)
+{
+	struct intel_pt_queue *ptq = queue->priv;
+
+	if (list_empty(&queue->head))
+		return 0;
+
+	if (!ptq) {
+		ptq = intel_pt_alloc_queue(pt, queue_nr);
+		if (!ptq)
+			return -ENOMEM;
+		queue->priv = ptq;
+
+		if (queue->cpu != -1)
+			ptq->cpu = queue->cpu;
+		ptq->tid = queue->tid;
+
+		if (pt->sampling_mode) {
+			if (pt->timeless_decoding)
+				ptq->step_through_buffers = true;
+			if (pt->timeless_decoding || !pt->have_sched_switch)
+				ptq->use_buffer_pid_tid = true;
+		}
+	}
+
+	if (!ptq->on_heap &&
+	    (!pt->sync_switch ||
+	     ptq->switch_state != INTEL_PT_SS_EXPECTING_SWITCH_EVENT)) {
+		const struct intel_pt_state *state;
+		int ret;
+
+		if (pt->timeless_decoding)
+			return 0;
+
+		intel_pt_log("queue %u getting timestamp\n", queue_nr);
+		intel_pt_log("queue %u decoding cpu %d pid %d tid %d\n",
+			     queue_nr, ptq->cpu, ptq->pid, ptq->tid);
+		while (1) {
+			state = intel_pt_decode(ptq->decoder);
+			if (state->err) {
+				if (state->err == INTEL_PT_ERR_NODATA) {
+					intel_pt_log("queue %u has no timestamp\n",
+						     queue_nr);
+					return 0;
+				}
+				continue;
+			}
+			if (state->timestamp)
+				break;
+		}
+
+		ptq->timestamp = state->timestamp;
+		intel_pt_log("queue %u timestamp 0x%" PRIx64 "\n",
+			     queue_nr, ptq->timestamp);
+		ptq->state = state;
+		ptq->have_sample = true;
+		intel_pt_sample_flags(ptq);
+		ret = auxtrace_heap__add(&pt->heap, queue_nr, ptq->timestamp);
+		if (ret)
+			return ret;
+		ptq->on_heap = true;
+	}
+
+	return 0;
+}
+
+static int intel_pt_setup_queues(struct intel_pt *pt)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < pt->queues.nr_queues; i++) {
+		ret = intel_pt_setup_queue(pt, &pt->queues.queue_array[i], i);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
+static int intel_pt_inject_event(union perf_event *event,
+				 struct perf_sample *sample, u64 type,
+				 bool swapped)
+{
+	event->header.size = perf_event__sample_event_size(sample, type, 0);
+	return perf_event__synthesize_sample(event, type, 0, sample, swapped);
+}
+
+static int intel_pt_synth_branch_sample(struct intel_pt_queue *ptq)
+{
+	int ret;
+	struct intel_pt *pt = ptq->pt;
+	union perf_event *event = ptq->event_buf;
+	struct perf_sample sample = { .ip = 0, };
+
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.size = sizeof(struct perf_event_header);
+
+	if (!pt->timeless_decoding)
+		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
+
+	sample.ip = ptq->state->from_ip;
+	sample.pid = ptq->pid;
+	sample.tid = ptq->tid;
+	sample.addr = ptq->state->to_ip;
+	sample.id = ptq->pt->branches_id;
+	sample.stream_id = ptq->pt->branches_id;
+	sample.period = 1;
+	sample.cpu = ptq->cpu;
+
+	if (pt->branches_filter && !(pt->branches_filter & ptq->flags))
+		return 0;
+
+	if (pt->synth_opts.inject) {
+		ret = intel_pt_inject_event(event, &sample,
+					    pt->branches_sample_type,
+					    pt->synth_needs_swap);
+		if (ret)
+			return ret;
+	}
+
+	ret = perf_session__deliver_synth_event(pt->session, event, &sample);
+	if (ret)
+		pr_err("Intel Processor Trace: failed to deliver branch event, error %d\n",
+		       ret);
+
+	return ret;
+}
+
+static int intel_pt_synth_instruction_sample(struct intel_pt_queue *ptq)
+{
+	int ret;
+	struct intel_pt *pt = ptq->pt;
+	union perf_event *event = ptq->event_buf;
+	struct perf_sample sample = { .ip = 0, };
+
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.size = sizeof(struct perf_event_header);
+
+	if (!pt->timeless_decoding)
+		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
+
+	sample.ip = ptq->state->from_ip;
+	sample.pid = ptq->pid;
+	sample.tid = ptq->tid;
+	sample.addr = ptq->state->to_ip;
+	sample.id = ptq->pt->instructions_id;
+	sample.stream_id = ptq->pt->instructions_id;
+	sample.period = ptq->pt->instructions_sample_period;
+	sample.cpu = ptq->cpu;
+
+	if (pt->synth_opts.callchain) {
+		thread_stack__sample(ptq->thread, ptq->chain,
+				     pt->synth_opts.callchain_sz, sample.ip);
+		sample.callchain = ptq->chain;
+	}
+
+	if (pt->synth_opts.inject) {
+		ret = intel_pt_inject_event(event, &sample,
+					    pt->instructions_sample_type,
+					    pt->synth_needs_swap);
+		if (ret)
+			return ret;
+	}
+
+	ret = perf_session__deliver_synth_event(pt->session, event, &sample);
+	if (ret)
+		pr_err("Intel Processor Trace: failed to deliver instruction event, error %d\n",
+		       ret);
+
+	return ret;
+}
+
+static int intel_pt_synth_transaction_sample(struct intel_pt_queue *ptq)
+{
+	int ret;
+	struct intel_pt *pt = ptq->pt;
+	union perf_event *event = ptq->event_buf;
+	struct perf_sample sample = { .ip = 0, };
+
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.size = sizeof(struct perf_event_header);
+
+	if (!pt->timeless_decoding)
+		sample.time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
+
+	sample.ip = ptq->state->from_ip;
+	sample.pid = ptq->pid;
+	sample.tid = ptq->tid;
+	sample.addr = ptq->state->to_ip;
+	sample.id = ptq->pt->transactions_id;
+	sample.stream_id = ptq->pt->transactions_id;
+	sample.period = 1;
+	sample.cpu = ptq->cpu;
+	sample.flags = ptq->flags;
+	sample.insn_len = ptq->insn_len;
+
+	if (pt->synth_opts.callchain) {
+		thread_stack__sample(ptq->thread, ptq->chain,
+				     pt->synth_opts.callchain_sz, sample.ip);
+		sample.callchain = ptq->chain;
+	}
+
+	if (pt->synth_opts.inject) {
+		ret = intel_pt_inject_event(event, &sample,
+					    pt->transactions_sample_type,
+					    pt->synth_needs_swap);
+		if (ret)
+			return ret;
+	}
+
+	ret = perf_session__deliver_synth_event(pt->session, event, &sample);
+	if (ret)
+		pr_err("Intel Processor Trace: failed to deliver transaction event, error %d\n",
+		       ret);
+
+	return ret;
+}
+
+static int intel_pt_synth_error(struct intel_pt *pt, int code, int cpu,
+				pid_t pid, pid_t tid, u64 ip)
+{
+	union perf_event event;
+	char msg[MAX_AUXTRACE_ERROR_MSG];
+	int err;
+
+	intel_pt__strerror(code, msg, MAX_AUXTRACE_ERROR_MSG);
+
+	auxtrace_synth_error(&event.auxtrace_error, PERF_AUXTRACE_ERROR_ITRACE,
+			     code, cpu, pid, tid, ip, msg);
+
+	err = perf_session__deliver_synth_event(pt->session, &event, NULL);
+	if (err)
+		pr_err("Intel Processor Trace: failed to deliver error event, error %d\n",
+		       err);
+
+	return err;
+}
+
+static int intel_pt_next_tid(struct intel_pt *pt, struct intel_pt_queue *ptq)
+{
+	struct auxtrace_queue *queue;
+	pid_t tid = ptq->next_tid;
+	int err;
+
+	if (tid == -1)
+		return 0;
+
+	intel_pt_log("switch: cpu %d tid %d\n", ptq->cpu, tid);
+
+	err = machine__set_current_tid(pt->machine, ptq->cpu, -1, tid);
+
+	queue = &pt->queues.queue_array[ptq->queue_nr];
+	intel_pt_set_pid_tid_cpu(pt, queue);
+
+	ptq->next_tid = -1;
+
+	return err;
+}
+
+static inline bool intel_pt_is_switch_ip(struct intel_pt_queue *ptq, u64 ip)
+{
+	struct intel_pt *pt = ptq->pt;
+
+	return ip == pt->switch_ip &&
+	       (ptq->flags & PERF_IP_FLAG_BRANCH) &&
+	       !(ptq->flags & (PERF_IP_FLAG_CONDITIONAL | PERF_IP_FLAG_ASYNC |
+			       PERF_IP_FLAG_INTERRUPT | PERF_IP_FLAG_TX_ABORT));
+}
+
+static int intel_pt_sample(struct intel_pt_queue *ptq)
+{
+	const struct intel_pt_state *state = ptq->state;
+	struct intel_pt *pt = ptq->pt;
+	int err;
+
+	if (!ptq->have_sample)
+		return 0;
+
+	ptq->have_sample = false;
+
+	if (pt->sample_instructions &&
+	    (state->type & INTEL_PT_INSTRUCTION)) {
+		err = intel_pt_synth_instruction_sample(ptq);
+		if (err)
+			return err;
+	}
+
+	if (pt->sample_transactions &&
+	    (state->type & INTEL_PT_TRANSACTION)) {
+		err = intel_pt_synth_transaction_sample(ptq);
+		if (err)
+			return err;
+	}
+
+	if (!(state->type & INTEL_PT_BRANCH))
+		return 0;
+
+	if (pt->synth_opts.callchain)
+		thread_stack__event(ptq->thread, ptq->flags, state->from_ip,
+				    state->to_ip, ptq->insn_len,
+				    state->trace_nr);
+
+	if (pt->sample_branches) {
+		err = intel_pt_synth_branch_sample(ptq);
+		if (err)
+			return err;
+	}
+
+	if (!pt->sync_switch)
+		return 0;
+
+	if (intel_pt_is_switch_ip(ptq, state->to_ip)) {
+		switch (ptq->switch_state) {
+		case INTEL_PT_SS_UNKNOWN:
+		case INTEL_PT_SS_EXPECTING_SWITCH_IP:
+			err = intel_pt_next_tid(pt, ptq);
+			if (err)
+				return err;
+			ptq->switch_state = INTEL_PT_SS_TRACING;
+			break;
+		default:
+			ptq->switch_state = INTEL_PT_SS_EXPECTING_SWITCH_EVENT;
+			return 1;
+		}
+	} else if (!state->to_ip) {
+		ptq->switch_state = INTEL_PT_SS_NOT_TRACING;
+	} else if (ptq->switch_state == INTEL_PT_SS_NOT_TRACING) {
+		ptq->switch_state = INTEL_PT_SS_UNKNOWN;
+	} else if (ptq->switch_state == INTEL_PT_SS_UNKNOWN &&
+		   state->to_ip == pt->ptss_ip &&
+		   (ptq->flags & PERF_IP_FLAG_CALL)) {
+		ptq->switch_state = INTEL_PT_SS_TRACING;
+	}
+
+	return 0;
+}
+
+static u64 intel_pt_switch_ip(struct machine *machine, u64 *ptss_ip)
+{
+	struct map *map;
+	struct symbol *sym, *start;
+	u64 ip, switch_ip = 0;
+
+	if (ptss_ip)
+		*ptss_ip = 0;
+
+	map = machine__kernel_map(machine, MAP__FUNCTION);
+	if (!map)
+		return 0;
+
+	if (map__load(map, machine->symbol_filter))
+		return 0;
+
+	start = dso__first_symbol(map->dso, MAP__FUNCTION);
+
+	for (sym = start; sym; sym = dso__next_symbol(sym)) {
+		if (sym->binding == STB_GLOBAL &&
+		    !strcmp(sym->name, "__switch_to")) {
+			ip = map->unmap_ip(map, sym->start);
+			if (ip >= map->start && ip < map->end) {
+				switch_ip = ip;
+				break;
+			}
+		}
+	}
+
+	if (!switch_ip || !ptss_ip)
+		return 0;
+
+	for (sym = start; sym; sym = dso__next_symbol(sym)) {
+		if (!strcmp(sym->name, "perf_trace_sched_switch")) {
+			ip = map->unmap_ip(map, sym->start);
+			if (ip >= map->start && ip < map->end) {
+				*ptss_ip = ip;
+				break;
+			}
+		}
+	}
+
+	return switch_ip;
+}
+
+static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
+{
+	const struct intel_pt_state *state = ptq->state;
+	struct intel_pt *pt = ptq->pt;
+	int err;
+
+	if (!pt->kernel_start) {
+		pt->kernel_start = machine__kernel_start(pt->machine);
+		if (pt->per_cpu_mmaps && pt->have_sched_switch &&
+		    !pt->timeless_decoding && intel_pt_tracing_kernel(pt) &&
+		    !pt->sampling_mode) {
+			pt->switch_ip = intel_pt_switch_ip(pt->machine,
+							   &pt->ptss_ip);
+			if (pt->switch_ip) {
+				intel_pt_log("switch_ip: %"PRIx64" ptss_ip: %"PRIx64"\n",
+					     pt->switch_ip, pt->ptss_ip);
+				pt->sync_switch = true;
+				pt->est_tsc_orig = pt->est_tsc;
+				pt->est_tsc = false;
+			}
+		}
+	}
+
+	intel_pt_log("queue %u decoding cpu %d pid %d tid %d\n",
+		     ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid);
+	while (1) {
+		err = intel_pt_sample(ptq);
+		if (err)
+			return err;
+
+		state = intel_pt_decode(ptq->decoder);
+		if (state->err) {
+			if (state->err == INTEL_PT_ERR_NODATA)
+				return 1;
+			if (pt->sync_switch &&
+			    state->from_ip >= pt->kernel_start) {
+				pt->sync_switch = false;
+				pt->est_tsc = pt->est_tsc_orig;
+				intel_pt_next_tid(pt, ptq);
+			}
+			if (pt->synth_opts.errors) {
+				err = intel_pt_synth_error(pt, state->err,
+							   ptq->cpu, ptq->pid,
+							   ptq->tid,
+							   state->from_ip);
+				if (err)
+					return err;
+			}
+			continue;
+		}
+
+		ptq->state = state;
+		ptq->have_sample = true;
+		intel_pt_sample_flags(ptq);
+
+		/* Use estimated TSC upon return to user space */
+		if (pt->est_tsc) {
+			if (state->from_ip >= pt->kernel_start &&
+			    state->to_ip &&
+			    state->to_ip < pt->kernel_start)
+				ptq->timestamp = state->est_timestamp;
+			else if (state->timestamp > ptq->timestamp)
+				ptq->timestamp = state->timestamp;
+		/* Use estimated TSC in unknown switch state */
+		} else if (pt->sync_switch &&
+			   ptq->switch_state == INTEL_PT_SS_UNKNOWN &&
+			   state->to_ip == pt->switch_ip &&
+			   (ptq->flags & PERF_IP_FLAG_CALL) &&
+			   ptq->next_tid == -1) {
+			ptq->timestamp = state->est_timestamp;
+		} else if (state->timestamp > ptq->timestamp) {
+			ptq->timestamp = state->timestamp;
+		}
+
+		if (!pt->timeless_decoding && ptq->timestamp >= *timestamp) {
+			*timestamp = ptq->timestamp;
+			return 0;
+		}
+	}
+	return 0;
+}
+
+static inline int intel_pt_update_queues(struct intel_pt *pt)
+{
+	if (pt->queues.new_data) {
+		pt->queues.new_data = false;
+		return intel_pt_setup_queues(pt);
+	}
+	return 0;
+}
+
+static int intel_pt_process_queues(struct intel_pt *pt, u64 timestamp)
+{
+	unsigned int queue_nr;
+	u64 ts;
+	int ret;
+
+	while (1) {
+		struct auxtrace_queue *queue;
+		struct intel_pt_queue *ptq;
+
+		if (!pt->heap.heap_cnt)
+			return 0;
+
+		if (pt->heap.heap_array[0].ordinal >= timestamp)
+			return 0;
+
+		queue_nr = pt->heap.heap_array[0].queue_nr;
+		queue = &pt->queues.queue_array[queue_nr];
+		ptq = queue->priv;
+
+		intel_pt_log("queue %u processing 0x%" PRIx64 " to 0x%" PRIx64 "\n",
+			     queue_nr, pt->heap.heap_array[0].ordinal,
+			     timestamp);
+
+		auxtrace_heap__pop(&pt->heap);
+
+		if (pt->heap.heap_cnt) {
+			ts = pt->heap.heap_array[0].ordinal + 1;
+			if (ts > timestamp)
+				ts = timestamp;
+		} else {
+			ts = timestamp;
+		}
+
+		intel_pt_set_pid_tid_cpu(pt, queue);
+
+		ret = intel_pt_run_decoder(ptq, &ts);
+
+		if (ret < 0) {
+			auxtrace_heap__add(&pt->heap, queue_nr, ts);
+			return ret;
+		}
+
+		if (!ret) {
+			ret = auxtrace_heap__add(&pt->heap, queue_nr, ts);
+			if (ret < 0)
+				return ret;
+		} else {
+			ptq->on_heap = false;
+		}
+	}
+
+	return 0;
+}
+
+static int intel_pt_process_timeless_queues(struct intel_pt *pt, pid_t tid,
+					    u64 time_)
+{
+	struct auxtrace_queues *queues = &pt->queues;
+	unsigned int i;
+	u64 ts = 0;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		struct auxtrace_queue *queue = &pt->queues.queue_array[i];
+		struct intel_pt_queue *ptq = queue->priv;
+
+		if (ptq && (tid == -1 || ptq->tid == tid)) {
+			ptq->time = time_;
+			intel_pt_set_pid_tid_cpu(pt, queue);
+			intel_pt_run_decoder(ptq, &ts);
+		}
+	}
+	return 0;
+}
+
+static int intel_pt_lost(struct intel_pt *pt, struct perf_sample *sample)
+{
+	return intel_pt_synth_error(pt, INTEL_PT_ERR_LOST, sample->cpu,
+				    sample->pid, sample->tid, 0);
+}
+
+static struct intel_pt_queue *intel_pt_cpu_to_ptq(struct intel_pt *pt, int cpu)
+{
+	unsigned i, j;
+
+	if (cpu < 0 || !pt->queues.nr_queues)
+		return NULL;
+
+	if ((unsigned)cpu >= pt->queues.nr_queues)
+		i = pt->queues.nr_queues - 1;
+	else
+		i = cpu;
+
+	if (pt->queues.queue_array[i].cpu == cpu)
+		return pt->queues.queue_array[i].priv;
+
+	for (j = 0; i > 0; j++) {
+		if (pt->queues.queue_array[--i].cpu == cpu)
+			return pt->queues.queue_array[i].priv;
+	}
+
+	for (; j < pt->queues.nr_queues; j++) {
+		if (pt->queues.queue_array[j].cpu == cpu)
+			return pt->queues.queue_array[j].priv;
+	}
+
+	return NULL;
+}
+
+static int intel_pt_process_switch(struct intel_pt *pt,
+				   struct perf_sample *sample)
+{
+	struct intel_pt_queue *ptq;
+	struct perf_evsel *evsel;
+	pid_t tid;
+	int cpu, err;
+
+	evsel = perf_evlist__id2evsel(pt->session->evlist, sample->id);
+	if (evsel != pt->switch_evsel)
+		return 0;
+
+	tid = perf_evsel__intval(evsel, sample, "next_pid");
+	cpu = sample->cpu;
+
+	intel_pt_log("sched_switch: cpu %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
+		     cpu, tid, sample->time, perf_time_to_tsc(sample->time,
+		     &pt->tc));
+
+	if (!pt->sync_switch)
+		goto out;
+
+	ptq = intel_pt_cpu_to_ptq(pt, cpu);
+	if (!ptq)
+		goto out;
+
+	switch (ptq->switch_state) {
+	case INTEL_PT_SS_NOT_TRACING:
+		ptq->next_tid = -1;
+		break;
+	case INTEL_PT_SS_UNKNOWN:
+	case INTEL_PT_SS_TRACING:
+		ptq->next_tid = tid;
+		ptq->switch_state = INTEL_PT_SS_EXPECTING_SWITCH_IP;
+		return 0;
+	case INTEL_PT_SS_EXPECTING_SWITCH_EVENT:
+		if (!ptq->on_heap) {
+			ptq->timestamp = perf_time_to_tsc(sample->time,
+							  &pt->tc);
+			err = auxtrace_heap__add(&pt->heap, ptq->queue_nr,
+						 ptq->timestamp);
+			if (err)
+				return err;
+			ptq->on_heap = true;
+		}
+		ptq->switch_state = INTEL_PT_SS_TRACING;
+		break;
+	case INTEL_PT_SS_EXPECTING_SWITCH_IP:
+		ptq->next_tid = tid;
+		intel_pt_log("ERROR: cpu %d expecting switch ip\n", cpu);
+		break;
+	default:
+		break;
+	}
+out:
+	return machine__set_current_tid(pt->machine, cpu, -1, tid);
+}
+
+static int intel_pt_process_itrace_start(struct intel_pt *pt,
+					 union perf_event *event,
+					 struct perf_sample *sample)
+{
+	if (!pt->per_cpu_mmaps)
+		return 0;
+
+	intel_pt_log("itrace_start: cpu %d pid %d tid %d time %"PRIu64" tsc %#"PRIx64"\n",
+		     sample->cpu, event->itrace_start.pid,
+		     event->itrace_start.tid, sample->time,
+		     perf_time_to_tsc(sample->time, &pt->tc));
+
+	return machine__set_current_tid(pt->machine, sample->cpu,
+					event->itrace_start.pid,
+					event->itrace_start.tid);
+}
+
+static int intel_pt_process_event(struct perf_session *session,
+				  union perf_event *event,
+				  struct perf_sample *sample,
+				  struct perf_tool *tool)
+{
+	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+					   auxtrace);
+	u64 timestamp;
+	int err = 0;
+
+	if (dump_trace)
+		return 0;
+
+	if (!tool->ordered_events) {
+		pr_err("Intel Processor Trace requires ordered events\n");
+		return -EINVAL;
+	}
+
+	if (sample->time)
+		timestamp = perf_time_to_tsc(sample->time, &pt->tc);
+	else
+		timestamp = 0;
+
+	if (timestamp || pt->timeless_decoding) {
+		err = intel_pt_update_queues(pt);
+		if (err)
+			return err;
+	}
+
+	if (pt->timeless_decoding) {
+		if (event->header.type == PERF_RECORD_EXIT) {
+			err = intel_pt_process_timeless_queues(pt,
+							       event->comm.tid,
+							       sample->time);
+		}
+	} else if (timestamp) {
+		err = intel_pt_process_queues(pt, timestamp);
+	}
+	if (err)
+		return err;
+
+	if (event->header.type == PERF_RECORD_AUX &&
+	    (event->aux.flags & PERF_AUX_FLAG_TRUNCATED) &&
+	    pt->synth_opts.errors)
+		err = intel_pt_lost(pt, sample);
+
+	if (pt->switch_evsel && event->header.type == PERF_RECORD_SAMPLE)
+		err = intel_pt_process_switch(pt, sample);
+	else if (event->header.type == PERF_RECORD_ITRACE_START)
+		err = intel_pt_process_itrace_start(pt, event, sample);
+
+	return err;
+}
+
+static int intel_pt_flush(struct perf_session *session, struct perf_tool *tool)
+{
+	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+					   auxtrace);
+	int ret;
+
+	if (dump_trace)
+		return 0;
+
+	if (!tool->ordered_events)
+		return -EINVAL;
+
+	ret = intel_pt_update_queues(pt);
+	if (ret < 0)
+		return ret;
+
+	if (pt->timeless_decoding)
+		return intel_pt_process_timeless_queues(pt, -1,
+							MAX_TIMESTAMP - 1);
+
+	return intel_pt_process_queues(pt, MAX_TIMESTAMP);
+}
+
+static void intel_pt_free_events(struct perf_session *session)
+{
+	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+					   auxtrace);
+	struct auxtrace_queues *queues = &pt->queues;
+	unsigned int i;
+
+	for (i = 0; i < queues->nr_queues; i++) {
+		intel_pt_free_queue(queues->queue_array[i].priv);
+		queues->queue_array[i].priv = NULL;
+	}
+	intel_pt_log_disable();
+	auxtrace_queues__free(queues);
+}
+
+static void intel_pt_free(struct perf_session *session)
+{
+	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+					   auxtrace);
+
+	auxtrace_heap__free(&pt->heap);
+	intel_pt_free_events(session);
+	session->auxtrace = NULL;
+	thread__delete(pt->unknown_thread);
+	free(pt);
+}
+
+static int intel_pt_process_auxtrace_event(struct perf_session *session,
+					   union perf_event *event,
+					   struct perf_tool *tool __maybe_unused)
+{
+	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
+					   auxtrace);
+
+	if (pt->sampling_mode)
+		return 0;
+
+	if (!pt->data_queued) {
+		struct auxtrace_buffer *buffer;
+		off_t data_offset;
+		int fd = perf_data_file__fd(session->file);
+		int err;
+
+		if (perf_data_file__is_pipe(session->file)) {
+			data_offset = 0;
+		} else {
+			data_offset = lseek(fd, 0, SEEK_CUR);
+			if (data_offset == -1)
+				return -errno;
+		}
+
+		err = auxtrace_queues__add_event(&pt->queues, session, event,
+						 data_offset, &buffer);
+		if (err)
+			return err;
+
+		/* Dump here now we have copied a piped trace out of the pipe */
+		if (dump_trace) {
+			if (auxtrace_buffer__get_data(buffer, fd)) {
+				intel_pt_dump_event(pt, buffer->data,
+						    buffer->size);
+				auxtrace_buffer__put_data(buffer);
+			}
+		}
+	}
+
+	return 0;
+}
+
+struct intel_pt_synth {
+	struct perf_tool dummy_tool;
+	struct perf_session *session;
+};
+
+static int intel_pt_event_synth(struct perf_tool *tool,
+				union perf_event *event,
+				struct perf_sample *sample __maybe_unused,
+				struct machine *machine __maybe_unused)
+{
+	struct intel_pt_synth *intel_pt_synth =
+			container_of(tool, struct intel_pt_synth, dummy_tool);
+
+	return perf_session__deliver_synth_event(intel_pt_synth->session, event,
+						 NULL);
+}
+
+static int intel_pt_synth_event(struct perf_session *session,
+				struct perf_event_attr *attr, u64 id)
+{
+	struct intel_pt_synth intel_pt_synth;
+
+	memset(&intel_pt_synth, 0, sizeof(struct intel_pt_synth));
+	intel_pt_synth.session = session;
+
+	return perf_event__synthesize_attr(&intel_pt_synth.dummy_tool, attr, 1,
+					   &id, intel_pt_event_synth);
+}
+
+static int intel_pt_synth_events(struct intel_pt *pt,
+				 struct perf_session *session)
+{
+	struct perf_evlist *evlist = session->evlist;
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr;
+	bool found = false;
+	u64 id;
+	int err;
+
+	evlist__for_each(evlist, evsel) {
+		if (evsel->attr.type == pt->pmu_type && evsel->ids) {
+			found = true;
+			break;
+		}
+	}
+
+	if (!found) {
+		pr_debug("There are no selected events with Intel Processor Trace data\n");
+		return 0;
+	}
+
+	memset(&attr, 0, sizeof(struct perf_event_attr));
+	attr.size = sizeof(struct perf_event_attr);
+	attr.type = PERF_TYPE_HARDWARE;
+	attr.sample_type = evsel->attr.sample_type & PERF_SAMPLE_MASK;
+	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
+			    PERF_SAMPLE_PERIOD;
+	if (pt->timeless_decoding)
+		attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
+	else
+		attr.sample_type |= PERF_SAMPLE_TIME;
+	if (!pt->per_cpu_mmaps)
+		attr.sample_type &= ~(u64)PERF_SAMPLE_CPU;
+	attr.exclude_user = evsel->attr.exclude_user;
+	attr.exclude_kernel = evsel->attr.exclude_kernel;
+	attr.exclude_hv = evsel->attr.exclude_hv;
+	attr.exclude_host = evsel->attr.exclude_host;
+	attr.exclude_guest = evsel->attr.exclude_guest;
+	attr.sample_id_all = evsel->attr.sample_id_all;
+	attr.read_format = evsel->attr.read_format;
+
+	id = evsel->id[0] + 1000000000;
+	if (!id)
+		id = 1;
+
+	if (pt->synth_opts.instructions) {
+		attr.config = PERF_COUNT_HW_INSTRUCTIONS;
+		if (pt->synth_opts.period_type == PERF_ITRACE_PERIOD_NANOSECS)
+			attr.sample_period =
+				intel_pt_ns_to_ticks(pt, pt->synth_opts.period);
+		else
+			attr.sample_period = pt->synth_opts.period;
+		pt->instructions_sample_period = attr.sample_period;
+		if (pt->synth_opts.callchain)
+			attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
+		pr_debug("Synthesizing 'instructions' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
+			 id, (u64)attr.sample_type);
+		err = intel_pt_synth_event(session, &attr, id);
+		if (err) {
+			pr_err("%s: failed to synthesize 'instructions' event type\n",
+			       __func__);
+			return err;
+		}
+		pt->sample_instructions = true;
+		pt->instructions_sample_type = attr.sample_type;
+		pt->instructions_id = id;
+		id += 1;
+	}
+
+	if (pt->synth_opts.transactions) {
+		attr.config = PERF_COUNT_HW_INSTRUCTIONS;
+		attr.sample_period = 1;
+		if (pt->synth_opts.callchain)
+			attr.sample_type |= PERF_SAMPLE_CALLCHAIN;
+		pr_debug("Synthesizing 'transactions' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
+			 id, (u64)attr.sample_type);
+		err = intel_pt_synth_event(session, &attr, id);
+		if (err) {
+			pr_err("%s: failed to synthesize 'transactions' event type\n",
+			       __func__);
+			return err;
+		}
+		pt->sample_transactions = true;
+		pt->transactions_id = id;
+		id += 1;
+		evlist__for_each(evlist, evsel) {
+			if (evsel->id && evsel->id[0] == pt->transactions_id) {
+				if (evsel->name)
+					zfree(&evsel->name);
+				evsel->name = strdup("transactions");
+				break;
+			}
+		}
+	}
+
+	if (pt->synth_opts.branches) {
+		attr.config = PERF_COUNT_HW_BRANCH_INSTRUCTIONS;
+		attr.sample_period = 1;
+		attr.sample_type |= PERF_SAMPLE_ADDR;
+		attr.sample_type &= ~(u64)PERF_SAMPLE_CALLCHAIN;
+		pr_debug("Synthesizing 'branches' event with id %" PRIu64 " sample type %#" PRIx64 "\n",
+			 id, (u64)attr.sample_type);
+		err = intel_pt_synth_event(session, &attr, id);
+		if (err) {
+			pr_err("%s: failed to synthesize 'branches' event type\n",
+			       __func__);
+			return err;
+		}
+		pt->sample_branches = true;
+		pt->branches_sample_type = attr.sample_type;
+		pt->branches_id = id;
+	}
+
+	pt->synth_needs_swap = evsel->needs_swap;
+
+	return 0;
+}
+
+static struct perf_evsel *intel_pt_find_sched_switch(struct perf_evlist *evlist)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_reverse(evlist, evsel) {
+		const char *name = perf_evsel__name(evsel);
+
+		if (!strcmp(name, "sched:sched_switch"))
+			return evsel;
+	}
+
+	return NULL;
+}
+
+static const char * const intel_pt_info_fmts[] = {
+	[INTEL_PT_PMU_TYPE]		= "  PMU Type           %"PRId64"\n",
+	[INTEL_PT_TIME_SHIFT]		= "  Time Shift         %"PRIu64"\n",
+	[INTEL_PT_TIME_MULT]		= "  Time Muliplier     %"PRIu64"\n",
+	[INTEL_PT_TIME_ZERO]		= "  Time Zero          %"PRIu64"\n",
+	[INTEL_PT_CAP_USER_TIME_ZERO]	= "  Cap Time Zero      %"PRId64"\n",
+	[INTEL_PT_TSC_BIT]		= "  TSC bit            %#"PRIx64"\n",
+	[INTEL_PT_NORETCOMP_BIT]	= "  NoRETComp bit      %#"PRIx64"\n",
+	[INTEL_PT_HAVE_SCHED_SWITCH]	= "  Have sched_switch  %"PRId64"\n",
+	[INTEL_PT_SNAPSHOT_MODE]	= "  Snapshot mode      %"PRId64"\n",
+	[INTEL_PT_PER_CPU_MMAPS]	= "  Per-cpu maps       %"PRId64"\n",
+};
+
+static void intel_pt_print_info(u64 *arr, int start, int finish)
+{
+	int i;
+
+	if (!dump_trace)
+		return;
+
+	for (i = start; i <= finish; i++)
+		fprintf(stdout, intel_pt_info_fmts[i], arr[i]);
+}
+
+int intel_pt_process_auxtrace_info(union perf_event *event,
+				   struct perf_session *session)
+{
+	struct auxtrace_info_event *auxtrace_info = &event->auxtrace_info;
+	size_t min_sz = sizeof(u64) * INTEL_PT_PER_CPU_MMAPS;
+	struct intel_pt *pt;
+	int err;
+
+	if (auxtrace_info->header.size < sizeof(struct auxtrace_info_event) +
+					min_sz)
+		return -EINVAL;
+
+	pt = zalloc(sizeof(struct intel_pt));
+	if (!pt)
+		return -ENOMEM;
+
+	err = auxtrace_queues__init(&pt->queues);
+	if (err)
+		goto err_free;
+
+	intel_pt_log_set_name(INTEL_PT_PMU_NAME);
+
+	pt->session = session;
+	pt->machine = &session->machines.host; /* No kvm support */
+	pt->auxtrace_type = auxtrace_info->type;
+	pt->pmu_type = auxtrace_info->priv[INTEL_PT_PMU_TYPE];
+	pt->tc.time_shift = auxtrace_info->priv[INTEL_PT_TIME_SHIFT];
+	pt->tc.time_mult = auxtrace_info->priv[INTEL_PT_TIME_MULT];
+	pt->tc.time_zero = auxtrace_info->priv[INTEL_PT_TIME_ZERO];
+	pt->cap_user_time_zero = auxtrace_info->priv[INTEL_PT_CAP_USER_TIME_ZERO];
+	pt->tsc_bit = auxtrace_info->priv[INTEL_PT_TSC_BIT];
+	pt->noretcomp_bit = auxtrace_info->priv[INTEL_PT_NORETCOMP_BIT];
+	pt->have_sched_switch = auxtrace_info->priv[INTEL_PT_HAVE_SCHED_SWITCH];
+	pt->snapshot_mode = auxtrace_info->priv[INTEL_PT_SNAPSHOT_MODE];
+	pt->per_cpu_mmaps = auxtrace_info->priv[INTEL_PT_PER_CPU_MMAPS];
+	intel_pt_print_info(&auxtrace_info->priv[0], INTEL_PT_PMU_TYPE,
+			    INTEL_PT_PER_CPU_MMAPS);
+
+	pt->timeless_decoding = intel_pt_timeless_decoding(pt);
+	pt->have_tsc = intel_pt_have_tsc(pt);
+	pt->sampling_mode = false;
+	pt->est_tsc = pt->per_cpu_mmaps && !pt->timeless_decoding;
+
+	pt->unknown_thread = thread__new(999999999, 999999999);
+	if (!pt->unknown_thread) {
+		err = -ENOMEM;
+		goto err_free_queues;
+	}
+	err = thread__set_comm(pt->unknown_thread, "unknown", 0);
+	if (err)
+		goto err_delete_thread;
+	if (thread__init_map_groups(pt->unknown_thread, pt->machine)) {
+		err = -ENOMEM;
+		goto err_delete_thread;
+	}
+
+	pt->auxtrace.process_event = intel_pt_process_event;
+	pt->auxtrace.process_auxtrace_event = intel_pt_process_auxtrace_event;
+	pt->auxtrace.flush_events = intel_pt_flush;
+	pt->auxtrace.free_events = intel_pt_free_events;
+	pt->auxtrace.free = intel_pt_free;
+	session->auxtrace = &pt->auxtrace;
+
+	if (dump_trace)
+		return 0;
+
+	if (pt->have_sched_switch == 1) {
+		pt->switch_evsel = intel_pt_find_sched_switch(session->evlist);
+		if (!pt->switch_evsel) {
+			pr_err("%s: missing sched_switch event\n", __func__);
+			goto err_delete_thread;
+		}
+	}
+
+	if (session->itrace_synth_opts && session->itrace_synth_opts->set) {
+		pt->synth_opts = *session->itrace_synth_opts;
+	} else {
+		itrace_synth_opts__set_default(&pt->synth_opts);
+		if (use_browser != -1) {
+			pt->synth_opts.branches = false;
+			pt->synth_opts.callchain = true;
+		}
+	}
+
+	if (pt->synth_opts.log)
+		intel_pt_log_enable();
+
+	if (pt->synth_opts.calls)
+		pt->branches_filter |= PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
+				       PERF_IP_FLAG_TRACE_END;
+	if (pt->synth_opts.returns)
+		pt->branches_filter |= PERF_IP_FLAG_RETURN |
+				       PERF_IP_FLAG_TRACE_BEGIN;
+
+	if (pt->synth_opts.callchain && !symbol_conf.use_callchain) {
+		symbol_conf.use_callchain = true;
+		if (callchain_register_param(&callchain_param) < 0) {
+			symbol_conf.use_callchain = false;
+			pt->synth_opts.callchain = false;
+		}
+	}
+
+	err = intel_pt_synth_events(pt, session);
+	if (err)
+		goto err_delete_thread;
+
+	err = auxtrace_queues__process_index(&pt->queues, session);
+	if (err)
+		goto err_delete_thread;
+
+	if (pt->queues.populated)
+		pt->data_queued = true;
+
+	if (pt->timeless_decoding)
+		pr_debug2("Intel PT decoding without timestamps\n");
+
+	return 0;
+
+err_delete_thread:
+	thread__delete(pt->unknown_thread);
+err_free_queues:
+	intel_pt_log_disable();
+	auxtrace_queues__free(&pt->queues);
+	session->auxtrace = NULL;
+err_free:
+	free(pt);
+	return err;
+}

tools/perf/util/intel-pt.h new file +51 -0

new file mode 100644
index 0000000..a1bfe93
@@ -0,0 +1,51 @@
+/*
+ * intel_pt.h: Intel Processor Trace support
+ * Copyright (c) 2013-2015, 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 INCLUDE__PERF_INTEL_PT_H__
+#define INCLUDE__PERF_INTEL_PT_H__
+
+#define INTEL_PT_PMU_NAME "intel_pt"
+
+enum {
+	INTEL_PT_PMU_TYPE,
+	INTEL_PT_TIME_SHIFT,
+	INTEL_PT_TIME_MULT,
+	INTEL_PT_TIME_ZERO,
+	INTEL_PT_CAP_USER_TIME_ZERO,
+	INTEL_PT_TSC_BIT,
+	INTEL_PT_NORETCOMP_BIT,
+	INTEL_PT_HAVE_SCHED_SWITCH,
+	INTEL_PT_SNAPSHOT_MODE,
+	INTEL_PT_PER_CPU_MMAPS,
+	INTEL_PT_AUXTRACE_PRIV_MAX,
+};
+
+#define INTEL_PT_AUXTRACE_PRIV_SIZE (INTEL_PT_AUXTRACE_PRIV_MAX * sizeof(u64))
+
+struct auxtrace_record;
+struct perf_tool;
+union perf_event;
+struct perf_session;
+struct perf_event_attr;
+struct perf_pmu;
+
+struct auxtrace_record *intel_pt_recording_init(int *err);
+
+int intel_pt_process_auxtrace_info(union perf_event *event,
+				   struct perf_session *session);
+
+struct perf_event_attr *intel_pt_pmu_default_config(struct perf_pmu *pmu);
+
+#endif

Signature · 1 line

1.9.1