* [PATCH 1/7] perf tools: Add a thread stack for synthesizing call chains
2014-10-30 14:09 [PATCH 0/7] perf tools: Add a thread stack for synthesizing call chains Adrian Hunter
@ 2014-10-30 14:09 ` Adrian Hunter
2014-11-03 13:08 ` Jiri Olsa
2014-11-07 5:28 ` [tip:perf/core] " tip-bot for Adrian Hunter
2014-10-30 14:09 ` [PATCH 2/7] perf tools: Add branch type to db export Adrian Hunter
` (6 subsequent siblings)
7 siblings, 2 replies; 18+ messages in thread
From: Adrian Hunter @ 2014-10-30 14:09 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Paul Mackerras, Stephane Eranian
Add a thread stack for synthesizing call chains from call
and return events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/Makefile.perf | 2 +
tools/perf/util/event.h | 26 +++++++
tools/perf/util/thread-stack.c | 172 +++++++++++++++++++++++++++++++++++++++++
tools/perf/util/thread-stack.h | 32 ++++++++
tools/perf/util/thread.c | 3 +
tools/perf/util/thread.h | 3 +
6 files changed, 238 insertions(+)
create mode 100644 tools/perf/util/thread-stack.c
create mode 100644 tools/perf/util/thread-stack.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 3caf7da..0ebcc4a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -317,6 +317,7 @@ LIB_H += ui/util.h
LIB_H += ui/ui.h
LIB_H += util/data.h
LIB_H += util/kvm-stat.h
+LIB_H += util/thread-stack.h
LIB_OBJS += $(OUTPUT)util/abspath.o
LIB_OBJS += $(OUTPUT)util/alias.o
@@ -394,6 +395,7 @@ LIB_OBJS += $(OUTPUT)util/srcline.o
LIB_OBJS += $(OUTPUT)util/data.o
LIB_OBJS += $(OUTPUT)util/tsc.o
LIB_OBJS += $(OUTPUT)util/cloexec.o
+LIB_OBJS += $(OUTPUT)util/thread-stack.o
LIB_OBJS += $(OUTPUT)ui/setup.o
LIB_OBJS += $(OUTPUT)ui/helpline.o
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8c7fe9d..7be3897 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -143,6 +143,32 @@ struct branch_stack {
struct branch_entry entries[0];
};
+enum {
+ PERF_IP_FLAG_BRANCH = 1ULL << 0,
+ PERF_IP_FLAG_CALL = 1ULL << 1,
+ PERF_IP_FLAG_RETURN = 1ULL << 2,
+ PERF_IP_FLAG_CONDITIONAL = 1ULL << 3,
+ PERF_IP_FLAG_SYSCALLRET = 1ULL << 4,
+ PERF_IP_FLAG_ASYNC = 1ULL << 5,
+ PERF_IP_FLAG_INTERRUPT = 1ULL << 6,
+ PERF_IP_FLAG_TX_ABORT = 1ULL << 7,
+ PERF_IP_FLAG_TRACE_BEGIN = 1ULL << 8,
+ PERF_IP_FLAG_TRACE_END = 1ULL << 9,
+ PERF_IP_FLAG_IN_TX = 1ULL << 10,
+};
+
+#define PERF_BRANCH_MASK (\
+ PERF_IP_FLAG_BRANCH |\
+ PERF_IP_FLAG_CALL |\
+ PERF_IP_FLAG_RETURN |\
+ PERF_IP_FLAG_CONDITIONAL |\
+ PERF_IP_FLAG_SYSCALLRET |\
+ PERF_IP_FLAG_ASYNC |\
+ PERF_IP_FLAG_INTERRUPT |\
+ PERF_IP_FLAG_TX_ABORT |\
+ PERF_IP_FLAG_TRACE_BEGIN |\
+ PERF_IP_FLAG_TRACE_END)
+
struct perf_sample {
u64 ip;
u32 pid, tid;
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
new file mode 100644
index 0000000..85b60d2
--- /dev/null
+++ b/tools/perf/util/thread-stack.c
@@ -0,0 +1,172 @@
+/*
+ * thread-stack.c: Synthesize a thread's stack using call / return events
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include "thread.h"
+#include "event.h"
+#include "util.h"
+#include "debug.h"
+#include "thread-stack.h"
+
+#define STACK_GROWTH 4096
+
+struct thread_stack_entry {
+ u64 ret_addr;
+};
+
+struct thread_stack {
+ struct thread_stack_entry *stack;
+ size_t cnt;
+ size_t sz;
+ u64 trace_nr;
+};
+
+static int thread_stack__grow(struct thread_stack *ts)
+{
+ struct thread_stack_entry *new_stack;
+ size_t sz, new_sz;
+
+ new_sz = ts->sz + STACK_GROWTH;
+ sz = new_sz * sizeof(struct thread_stack_entry);
+
+ new_stack = realloc(ts->stack, sz);
+ if (!new_stack)
+ return -ENOMEM;
+
+ ts->stack = new_stack;
+ ts->sz = new_sz;
+
+ return 0;
+}
+
+static struct thread_stack *thread_stack__new(void)
+{
+ struct thread_stack *ts;
+
+ ts = zalloc(sizeof(struct thread_stack));
+ if (!ts)
+ return NULL;
+
+ if (thread_stack__grow(ts)) {
+ free(ts);
+ return NULL;
+ }
+
+ return ts;
+}
+
+static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
+{
+ int err = 0;
+
+ if (ts->cnt == ts->sz) {
+ err = thread_stack__grow(ts);
+ if (err) {
+ pr_warning("Out of memory: discarding thread stack\n");
+ ts->cnt = 0;
+ }
+ }
+
+ ts->stack[ts->cnt++].ret_addr = ret_addr;
+
+ return err;
+}
+
+static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
+{
+ size_t i;
+
+ /*
+ * In some cases there may be functions which are not seen to return.
+ * For example when setjmp / longjmp has been used. Or the perf context
+ * switch in the kernel which doesn't stop and start tracing in exactly
+ * the same code path. When that happens the return address will be
+ * further down the stack. If the return address is not found at all,
+ * we assume the opposite (i.e. this is a return for a call that wasn't
+ * seen for some reason) and leave the stack alone.
+ */
+ for (i = ts->cnt; i; ) {
+ if (ts->stack[--i].ret_addr == ret_addr) {
+ ts->cnt = i;
+ return;
+ }
+ }
+}
+
+int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+ u64 to_ip, u16 insn_len, u64 trace_nr)
+{
+ if (!thread)
+ return -EINVAL;
+
+ if (!thread->ts) {
+ thread->ts = thread_stack__new();
+ if (!thread->ts) {
+ pr_warning("Out of memory: no thread stack\n");
+ return -ENOMEM;
+ }
+ thread->ts->trace_nr = trace_nr;
+ }
+
+ /*
+ * When the trace is discontinuous, the trace_nr changes. In that case
+ * the stack might be completely invalid. Better to report nothing than
+ * to report something misleading, so reset the stack count to zero.
+ */
+ if (trace_nr != thread->ts->trace_nr) {
+ thread->ts->trace_nr = trace_nr;
+ thread->ts->cnt = 0;
+ }
+
+ if (flags & PERF_IP_FLAG_CALL) {
+ u64 ret_addr;
+
+ if (!to_ip)
+ return 0;
+ ret_addr = from_ip + insn_len;
+ if (ret_addr == to_ip)
+ return 0; /* Zero-length calls are excluded */
+ return thread_stack__push(thread->ts, ret_addr);
+ } else if (flags & PERF_IP_FLAG_RETURN) {
+ if (!from_ip)
+ return 0;
+ thread_stack__pop(thread->ts, to_ip);
+ }
+
+ return 0;
+}
+
+void thread_stack__free(struct thread *thread)
+{
+ if (thread->ts) {
+ zfree(&thread->ts->stack);
+ zfree(&thread->ts);
+ }
+}
+
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+ size_t sz, u64 ip)
+{
+ size_t i;
+
+ if (!thread || !thread->ts)
+ chain->nr = 1;
+ else
+ chain->nr = min(sz, thread->ts->cnt + 1);
+
+ chain->ips[0] = ip;
+
+ for (i = 1; i < chain->nr; i++)
+ chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+}
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
new file mode 100644
index 0000000..7c41579
--- /dev/null
+++ b/tools/perf/util/thread-stack.h
@@ -0,0 +1,32 @@
+/*
+ * thread-stack.h: Synthesize a thread's stack using call / return events
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#ifndef __PERF_THREAD_STACK_H
+#define __PERF_THREAD_STACK_H
+
+#include <sys/types.h>
+
+#include <linux/types.h>
+
+struct thread;
+struct ip_callchain;
+
+int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+ u64 to_ip, u16 insn_len, u64 trace_nr);
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+ size_t sz, u64 ip);
+void thread_stack__free(struct thread *thread);
+
+#endif
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index bf5bf85..a2157f0 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -4,6 +4,7 @@
#include <string.h>
#include "session.h"
#include "thread.h"
+#include "thread-stack.h"
#include "util.h"
#include "debug.h"
#include "comm.h"
@@ -66,6 +67,8 @@ void thread__delete(struct thread *thread)
{
struct comm *comm, *tmp;
+ thread_stack__free(thread);
+
if (thread->mg) {
map_groups__put(thread->mg);
thread->mg = NULL;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index d34cf5c..160fd06 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -8,6 +8,8 @@
#include "symbol.h"
#include <strlist.h>
+struct thread_stack;
+
struct thread {
union {
struct rb_node rb_node;
@@ -26,6 +28,7 @@ struct thread {
u64 db_id;
void *priv;
+ struct thread_stack *ts;
};
struct machine;
--
1.9.1
^ permalink raw reply related [flat|nested] 18+ messages in thread* Re: [PATCH 1/7] perf tools: Add a thread stack for synthesizing call chains
2014-10-30 14:09 ` [PATCH 1/7] " Adrian Hunter
@ 2014-11-03 13:08 ` Jiri Olsa
2014-11-07 5:28 ` [tip:perf/core] " tip-bot for Adrian Hunter
1 sibling, 0 replies; 18+ messages in thread
From: Jiri Olsa @ 2014-11-03 13:08 UTC (permalink / raw)
To: Adrian Hunter
Cc: Arnaldo Carvalho de Melo, Peter Zijlstra, linux-kernel,
David Ahern, Frederic Weisbecker, Namhyung Kim, Paul Mackerras,
Stephane Eranian
On Thu, Oct 30, 2014 at 04:09:42PM +0200, Adrian Hunter wrote:
> Add a thread stack for synthesizing call chains from call
> and return events.
>
> Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
jirka
^ permalink raw reply [flat|nested] 18+ messages in thread
* [tip:perf/core] perf tools: Add a thread stack for synthesizing call chains
2014-10-30 14:09 ` [PATCH 1/7] " Adrian Hunter
2014-11-03 13:08 ` Jiri Olsa
@ 2014-11-07 5:28 ` tip-bot for Adrian Hunter
1 sibling, 0 replies; 18+ messages in thread
From: tip-bot for Adrian Hunter @ 2014-11-07 5:28 UTC (permalink / raw)
To: linux-tip-commits
Cc: linux-kernel, acme, fweisbec, eranian, jolsa, tglx, paulus, jolsa,
peterz, adrian.hunter, hpa, namhyung, dsahern, mingo
Commit-ID: 00447ccdf3335ea467841fc3c7d65ffd30748895
Gitweb: http://git.kernel.org/tip/00447ccdf3335ea467841fc3c7d65ffd30748895
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 30 Oct 2014 16:09:42 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 3 Nov 2014 17:10:59 -0300
perf tools: Add a thread stack for synthesizing call chains
Add a thread stack for synthesizing call chains from call and return
events.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1414678188-14946-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/Makefile.perf | 2 +
tools/perf/util/event.h | 26 ++++
tools/perf/util/thread-stack.c | 172 +++++++++++++++++++++
.../kxcjk_1013.h => tools/perf/util/thread-stack.h | 22 ++-
tools/perf/util/thread.c | 3 +
tools/perf/util/thread.h | 3 +
6 files changed, 222 insertions(+), 6 deletions(-)
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 3caf7da..0ebcc4a 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -317,6 +317,7 @@ LIB_H += ui/util.h
LIB_H += ui/ui.h
LIB_H += util/data.h
LIB_H += util/kvm-stat.h
+LIB_H += util/thread-stack.h
LIB_OBJS += $(OUTPUT)util/abspath.o
LIB_OBJS += $(OUTPUT)util/alias.o
@@ -394,6 +395,7 @@ LIB_OBJS += $(OUTPUT)util/srcline.o
LIB_OBJS += $(OUTPUT)util/data.o
LIB_OBJS += $(OUTPUT)util/tsc.o
LIB_OBJS += $(OUTPUT)util/cloexec.o
+LIB_OBJS += $(OUTPUT)util/thread-stack.o
LIB_OBJS += $(OUTPUT)ui/setup.o
LIB_OBJS += $(OUTPUT)ui/helpline.o
diff --git a/tools/perf/util/event.h b/tools/perf/util/event.h
index 8c7fe9d..7be3897 100644
--- a/tools/perf/util/event.h
+++ b/tools/perf/util/event.h
@@ -143,6 +143,32 @@ struct branch_stack {
struct branch_entry entries[0];
};
+enum {
+ PERF_IP_FLAG_BRANCH = 1ULL << 0,
+ PERF_IP_FLAG_CALL = 1ULL << 1,
+ PERF_IP_FLAG_RETURN = 1ULL << 2,
+ PERF_IP_FLAG_CONDITIONAL = 1ULL << 3,
+ PERF_IP_FLAG_SYSCALLRET = 1ULL << 4,
+ PERF_IP_FLAG_ASYNC = 1ULL << 5,
+ PERF_IP_FLAG_INTERRUPT = 1ULL << 6,
+ PERF_IP_FLAG_TX_ABORT = 1ULL << 7,
+ PERF_IP_FLAG_TRACE_BEGIN = 1ULL << 8,
+ PERF_IP_FLAG_TRACE_END = 1ULL << 9,
+ PERF_IP_FLAG_IN_TX = 1ULL << 10,
+};
+
+#define PERF_BRANCH_MASK (\
+ PERF_IP_FLAG_BRANCH |\
+ PERF_IP_FLAG_CALL |\
+ PERF_IP_FLAG_RETURN |\
+ PERF_IP_FLAG_CONDITIONAL |\
+ PERF_IP_FLAG_SYSCALLRET |\
+ PERF_IP_FLAG_ASYNC |\
+ PERF_IP_FLAG_INTERRUPT |\
+ PERF_IP_FLAG_TX_ABORT |\
+ PERF_IP_FLAG_TRACE_BEGIN |\
+ PERF_IP_FLAG_TRACE_END)
+
struct perf_sample {
u64 ip;
u32 pid, tid;
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
new file mode 100644
index 0000000..85b60d2
--- /dev/null
+++ b/tools/perf/util/thread-stack.c
@@ -0,0 +1,172 @@
+/*
+ * thread-stack.c: Synthesize a thread's stack using call / return events
+ * Copyright (c) 2014, Intel Corporation.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
+ * more details.
+ *
+ */
+
+#include "thread.h"
+#include "event.h"
+#include "util.h"
+#include "debug.h"
+#include "thread-stack.h"
+
+#define STACK_GROWTH 4096
+
+struct thread_stack_entry {
+ u64 ret_addr;
+};
+
+struct thread_stack {
+ struct thread_stack_entry *stack;
+ size_t cnt;
+ size_t sz;
+ u64 trace_nr;
+};
+
+static int thread_stack__grow(struct thread_stack *ts)
+{
+ struct thread_stack_entry *new_stack;
+ size_t sz, new_sz;
+
+ new_sz = ts->sz + STACK_GROWTH;
+ sz = new_sz * sizeof(struct thread_stack_entry);
+
+ new_stack = realloc(ts->stack, sz);
+ if (!new_stack)
+ return -ENOMEM;
+
+ ts->stack = new_stack;
+ ts->sz = new_sz;
+
+ return 0;
+}
+
+static struct thread_stack *thread_stack__new(void)
+{
+ struct thread_stack *ts;
+
+ ts = zalloc(sizeof(struct thread_stack));
+ if (!ts)
+ return NULL;
+
+ if (thread_stack__grow(ts)) {
+ free(ts);
+ return NULL;
+ }
+
+ return ts;
+}
+
+static int thread_stack__push(struct thread_stack *ts, u64 ret_addr)
+{
+ int err = 0;
+
+ if (ts->cnt == ts->sz) {
+ err = thread_stack__grow(ts);
+ if (err) {
+ pr_warning("Out of memory: discarding thread stack\n");
+ ts->cnt = 0;
+ }
+ }
+
+ ts->stack[ts->cnt++].ret_addr = ret_addr;
+
+ return err;
+}
+
+static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
+{
+ size_t i;
+
+ /*
+ * In some cases there may be functions which are not seen to return.
+ * For example when setjmp / longjmp has been used. Or the perf context
+ * switch in the kernel which doesn't stop and start tracing in exactly
+ * the same code path. When that happens the return address will be
+ * further down the stack. If the return address is not found at all,
+ * we assume the opposite (i.e. this is a return for a call that wasn't
+ * seen for some reason) and leave the stack alone.
+ */
+ for (i = ts->cnt; i; ) {
+ if (ts->stack[--i].ret_addr == ret_addr) {
+ ts->cnt = i;
+ return;
+ }
+ }
+}
+
+int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+ u64 to_ip, u16 insn_len, u64 trace_nr)
+{
+ if (!thread)
+ return -EINVAL;
+
+ if (!thread->ts) {
+ thread->ts = thread_stack__new();
+ if (!thread->ts) {
+ pr_warning("Out of memory: no thread stack\n");
+ return -ENOMEM;
+ }
+ thread->ts->trace_nr = trace_nr;
+ }
+
+ /*
+ * When the trace is discontinuous, the trace_nr changes. In that case
+ * the stack might be completely invalid. Better to report nothing than
+ * to report something misleading, so reset the stack count to zero.
+ */
+ if (trace_nr != thread->ts->trace_nr) {
+ thread->ts->trace_nr = trace_nr;
+ thread->ts->cnt = 0;
+ }
+
+ if (flags & PERF_IP_FLAG_CALL) {
+ u64 ret_addr;
+
+ if (!to_ip)
+ return 0;
+ ret_addr = from_ip + insn_len;
+ if (ret_addr == to_ip)
+ return 0; /* Zero-length calls are excluded */
+ return thread_stack__push(thread->ts, ret_addr);
+ } else if (flags & PERF_IP_FLAG_RETURN) {
+ if (!from_ip)
+ return 0;
+ thread_stack__pop(thread->ts, to_ip);
+ }
+
+ return 0;
+}
+
+void thread_stack__free(struct thread *thread)
+{
+ if (thread->ts) {
+ zfree(&thread->ts->stack);
+ zfree(&thread->ts);
+ }
+}
+
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+ size_t sz, u64 ip)
+{
+ size_t i;
+
+ if (!thread || !thread->ts)
+ chain->nr = 1;
+ else
+ chain->nr = min(sz, thread->ts->cnt + 1);
+
+ chain->ips[0] = ip;
+
+ for (i = 1; i < chain->nr; i++)
+ chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+}
diff --git a/include/linux/iio/accel/kxcjk_1013.h b/tools/perf/util/thread-stack.h
similarity index 51%
copy from include/linux/iio/accel/kxcjk_1013.h
copy to tools/perf/util/thread-stack.h
index fd1d540..7c41579 100644
--- a/include/linux/iio/accel/kxcjk_1013.h
+++ b/tools/perf/util/thread-stack.h
@@ -1,5 +1,5 @@
/*
- * KXCJK-1013 3-axis accelerometer Interface
+ * thread-stack.h: Synthesize a thread's stack using call / return events
* Copyright (c) 2014, Intel Corporation.
*
* This program is free software; you can redistribute it and/or modify it
@@ -10,13 +10,23 @@
* 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 __IIO_KXCJK_1013_H__
-#define __IIO_KXCJK_1013_H__
+#ifndef __PERF_THREAD_STACK_H
+#define __PERF_THREAD_STACK_H
+
+#include <sys/types.h>
+
+#include <linux/types.h>
+
+struct thread;
+struct ip_callchain;
-struct kxcjk_1013_platform_data {
- bool active_high_intr;
-};
+int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
+ u64 to_ip, u16 insn_len, u64 trace_nr);
+void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
+ size_t sz, u64 ip);
+void thread_stack__free(struct thread *thread);
#endif
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index bf5bf85..a2157f0 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -4,6 +4,7 @@
#include <string.h>
#include "session.h"
#include "thread.h"
+#include "thread-stack.h"
#include "util.h"
#include "debug.h"
#include "comm.h"
@@ -66,6 +67,8 @@ void thread__delete(struct thread *thread)
{
struct comm *comm, *tmp;
+ thread_stack__free(thread);
+
if (thread->mg) {
map_groups__put(thread->mg);
thread->mg = NULL;
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index d34cf5c..160fd06 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -8,6 +8,8 @@
#include "symbol.h"
#include <strlist.h>
+struct thread_stack;
+
struct thread {
union {
struct rb_node rb_node;
@@ -26,6 +28,7 @@ struct thread {
u64 db_id;
void *priv;
+ struct thread_stack *ts;
};
struct machine;
^ permalink raw reply related [flat|nested] 18+ messages in thread
* [PATCH 2/7] perf tools: Add branch type to db export
2014-10-30 14:09 [PATCH 0/7] perf tools: Add a thread stack for synthesizing call chains Adrian Hunter
2014-10-30 14:09 ` [PATCH 1/7] " Adrian Hunter
@ 2014-10-30 14:09 ` Adrian Hunter
2014-11-07 5:28 ` [tip:perf/core] " tip-bot for Adrian Hunter
2014-10-30 14:09 ` [PATCH 3/7] perf tools: Add branch_type and in_tx to Python export Adrian Hunter
` (5 subsequent siblings)
7 siblings, 1 reply; 18+ messages in thread
From: Adrian Hunter @ 2014-10-30 14:09 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Paul Mackerras, Stephane Eranian
Add the ability to export branch types through the
database export facility.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/db-export.c | 48 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/db-export.h | 6 ++++++
2 files changed, 54 insertions(+)
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index be128b0..bccb831 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -208,6 +208,15 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
return 0;
}
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+ const char *name)
+{
+ if (dbe->export_branch_type)
+ return dbe->export_branch_type(dbe, branch_type, name);
+
+ return 0;
+}
+
int db_export__sample(struct db_export *dbe, union perf_event *event,
struct perf_sample *sample, struct perf_evsel *evsel,
struct thread *thread, struct addr_location *al)
@@ -268,3 +277,42 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
return 0;
}
+
+static struct {
+ u32 branch_type;
+ const char *name;
+} branch_types[] = {
+ {0, "no branch"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "conditional jump"},
+ {PERF_IP_FLAG_BRANCH, "unconditional jump"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT,
+ "software interrupt"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT,
+ "return from interrupt"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET,
+ "system call"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET,
+ "return from system call"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "asynchronous branch"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
+ PERF_IP_FLAG_INTERRUPT, "hardware interrupt"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "transaction abort"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "trace begin"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "trace end"},
+ {0, NULL}
+};
+
+int db_export__branch_types(struct db_export *dbe)
+{
+ int i, err = 0;
+
+ for (i = 0; branch_types[i].name ; i++) {
+ err = db_export__branch_type(dbe, branch_types[i].branch_type,
+ branch_types[i].name);
+ if (err)
+ break;
+ }
+ return err;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index b3643e8..e4baa45 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -54,6 +54,8 @@ struct db_export {
struct machine *machine);
int (*export_symbol)(struct db_export *dbe, struct symbol *sym,
struct dso *dso);
+ int (*export_branch_type)(struct db_export *dbe, u32 branch_type,
+ const char *name);
int (*export_sample)(struct db_export *dbe, struct export_sample *es);
u64 evsel_last_db_id;
u64 machine_last_db_id;
@@ -79,8 +81,12 @@ int db_export__dso(struct db_export *dbe, struct dso *dso,
struct machine *machine);
int db_export__symbol(struct db_export *dbe, struct symbol *sym,
struct dso *dso);
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+ const char *name);
int db_export__sample(struct db_export *dbe, union perf_event *event,
struct perf_sample *sample, struct perf_evsel *evsel,
struct thread *thread, struct addr_location *al);
+int db_export__branch_types(struct db_export *dbe);
+
#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 18+ messages in thread* [tip:perf/core] perf tools: Add branch type to db export
2014-10-30 14:09 ` [PATCH 2/7] perf tools: Add branch type to db export Adrian Hunter
@ 2014-11-07 5:28 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 18+ messages in thread
From: tip-bot for Adrian Hunter @ 2014-11-07 5:28 UTC (permalink / raw)
To: linux-tip-commits
Cc: peterz, eranian, dsahern, fweisbec, linux-kernel, mingo,
adrian.hunter, jolsa, namhyung, hpa, tglx, acme, paulus
Commit-ID: f2bff007679e7d293cb07bb26e18ccf11cc1c4b2
Gitweb: http://git.kernel.org/tip/f2bff007679e7d293cb07bb26e18ccf11cc1c4b2
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 30 Oct 2014 16:09:43 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 3 Nov 2014 18:06:40 -0300
perf tools: Add branch type to db export
Add the ability to export branch types through the database export
facility.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1414678188-14946-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/db-export.c | 48 +++++++++++++++++++++++++++++++++++++++++++++
tools/perf/util/db-export.h | 6 ++++++
2 files changed, 54 insertions(+)
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index be128b0..bccb831 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -208,6 +208,15 @@ static int db_ids_from_al(struct db_export *dbe, struct addr_location *al,
return 0;
}
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+ const char *name)
+{
+ if (dbe->export_branch_type)
+ return dbe->export_branch_type(dbe, branch_type, name);
+
+ return 0;
+}
+
int db_export__sample(struct db_export *dbe, union perf_event *event,
struct perf_sample *sample, struct perf_evsel *evsel,
struct thread *thread, struct addr_location *al)
@@ -268,3 +277,42 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
return 0;
}
+
+static struct {
+ u32 branch_type;
+ const char *name;
+} branch_types[] = {
+ {0, "no branch"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL, "call"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN, "return"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CONDITIONAL, "conditional jump"},
+ {PERF_IP_FLAG_BRANCH, "unconditional jump"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_INTERRUPT,
+ "software interrupt"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_INTERRUPT,
+ "return from interrupt"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_SYSCALLRET,
+ "system call"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_RETURN | PERF_IP_FLAG_SYSCALLRET,
+ "return from system call"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_ASYNC, "asynchronous branch"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_CALL | PERF_IP_FLAG_ASYNC |
+ PERF_IP_FLAG_INTERRUPT, "hardware interrupt"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TX_ABORT, "transaction abort"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_BEGIN, "trace begin"},
+ {PERF_IP_FLAG_BRANCH | PERF_IP_FLAG_TRACE_END, "trace end"},
+ {0, NULL}
+};
+
+int db_export__branch_types(struct db_export *dbe)
+{
+ int i, err = 0;
+
+ for (i = 0; branch_types[i].name ; i++) {
+ err = db_export__branch_type(dbe, branch_types[i].branch_type,
+ branch_types[i].name);
+ if (err)
+ break;
+ }
+ return err;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index b3643e8..e4baa45 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -54,6 +54,8 @@ struct db_export {
struct machine *machine);
int (*export_symbol)(struct db_export *dbe, struct symbol *sym,
struct dso *dso);
+ int (*export_branch_type)(struct db_export *dbe, u32 branch_type,
+ const char *name);
int (*export_sample)(struct db_export *dbe, struct export_sample *es);
u64 evsel_last_db_id;
u64 machine_last_db_id;
@@ -79,8 +81,12 @@ int db_export__dso(struct db_export *dbe, struct dso *dso,
struct machine *machine);
int db_export__symbol(struct db_export *dbe, struct symbol *sym,
struct dso *dso);
+int db_export__branch_type(struct db_export *dbe, u32 branch_type,
+ const char *name);
int db_export__sample(struct db_export *dbe, union perf_event *event,
struct perf_sample *sample, struct perf_evsel *evsel,
struct thread *thread, struct addr_location *al);
+int db_export__branch_types(struct db_export *dbe);
+
#endif
^ permalink raw reply related [flat|nested] 18+ messages in thread
* [PATCH 3/7] perf tools: Add branch_type and in_tx to Python export
2014-10-30 14:09 [PATCH 0/7] perf tools: Add a thread stack for synthesizing call chains Adrian Hunter
2014-10-30 14:09 ` [PATCH 1/7] " Adrian Hunter
2014-10-30 14:09 ` [PATCH 2/7] perf tools: Add branch type to db export Adrian Hunter
@ 2014-10-30 14:09 ` Adrian Hunter
2014-11-07 5:28 ` [tip:perf/core] " tip-bot for Adrian Hunter
2014-10-30 14:09 ` [PATCH 4/7] perf tools: Enhance the thread stack to output call/return data Adrian Hunter
` (4 subsequent siblings)
7 siblings, 1 reply; 18+ messages in thread
From: Adrian Hunter @ 2014-10-30 14:09 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Paul Mackerras, Stephane Eranian
Add branch_type and in_tx to Python db export and
the export-to-postgresql.py script.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/scripts/python/export-to-postgresql.py | 32 ++++++++++++++++++----
.../util/scripting-engines/trace-event-python.c | 30 +++++++++++++++++++-
2 files changed, 55 insertions(+), 7 deletions(-)
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index d8f6df0..bb79aec 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -123,6 +123,10 @@ do_query(query, 'CREATE TABLE symbols ('
'sym_end bigint,'
'binding integer,'
'name varchar(2048))')
+do_query(query, 'CREATE TABLE branch_types ('
+ 'id integer NOT NULL,'
+ 'name varchar(80))')
+
if branches:
do_query(query, 'CREATE TABLE samples ('
'id bigint NOT NULL,'
@@ -139,7 +143,9 @@ if branches:
'to_dso_id bigint,'
'to_symbol_id bigint,'
'to_sym_offset bigint,'
- 'to_ip bigint)')
+ 'to_ip bigint,'
+ 'branch_type integer,'
+ 'in_tx boolean)')
else:
do_query(query, 'CREATE TABLE samples ('
'id bigint NOT NULL,'
@@ -160,7 +166,9 @@ else:
'period bigint,'
'weight bigint,'
'transaction bigint,'
- 'data_src bigint)')
+ 'data_src bigint,'
+ 'branch_type integer,'
+ 'in_tx boolean)')
do_query(query, 'CREATE VIEW samples_view AS '
'SELECT '
@@ -178,7 +186,9 @@ do_query(query, 'CREATE VIEW samples_view AS '
'to_hex(to_ip) AS to_ip_hex,'
'(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,'
'to_sym_offset,'
- '(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name'
+ '(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
+ '(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
+ 'in_tx'
' FROM samples')
@@ -234,6 +244,7 @@ comm_file = open_output_file("comm_table.bin")
comm_thread_file = open_output_file("comm_thread_table.bin")
dso_file = open_output_file("dso_table.bin")
symbol_file = open_output_file("symbol_table.bin")
+branch_type_file = open_output_file("branch_type_table.bin")
sample_file = open_output_file("sample_table.bin")
def trace_begin():
@@ -257,6 +268,7 @@ def trace_end():
copy_output_file(comm_thread_file, "comm_threads")
copy_output_file(dso_file, "dsos")
copy_output_file(symbol_file, "symbols")
+ copy_output_file(branch_type_file, "branch_types")
copy_output_file(sample_file, "samples")
print datetime.datetime.today(), "Removing intermediate files..."
@@ -267,6 +279,7 @@ def trace_end():
remove_output_file(comm_thread_file)
remove_output_file(dso_file)
remove_output_file(symbol_file)
+ remove_output_file(branch_type_file)
remove_output_file(sample_file)
os.rmdir(output_dir_name)
print datetime.datetime.today(), "Adding primary keys"
@@ -277,6 +290,7 @@ def trace_end():
do_query(query, 'ALTER TABLE comm_threads ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE dsos ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE symbols ADD PRIMARY KEY (id)')
+ do_query(query, 'ALTER TABLE branch_types ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE samples ADD PRIMARY KEY (id)')
print datetime.datetime.today(), "Adding foreign keys"
@@ -352,9 +366,15 @@ def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x
value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name)
symbol_file.write(value)
-def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, *x):
+def branch_type_table(branch_type, name, *x):
+ n = len(name)
+ fmt = "!hiii" + str(n) + "s"
+ value = struct.pack(fmt, 2, 4, branch_type, n, name)
+ branch_type_file.write(value)
+
+def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, *x):
if branches:
- value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiq", 15, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip)
+ value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiB", 17, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx)
else:
- value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiq", 19, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src)
+ value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx)
sample_file.write(value)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 2fd7ee8..f3ca779 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -66,6 +66,7 @@ struct tables {
PyObject *comm_thread_handler;
PyObject *dso_handler;
PyObject *symbol_handler;
+ PyObject *branch_type_handler;
PyObject *sample_handler;
bool db_export_mode;
};
@@ -664,13 +665,31 @@ static int python_export_symbol(struct db_export *dbe, struct symbol *sym,
return 0;
}
+static int python_export_branch_type(struct db_export *dbe, u32 branch_type,
+ const char *name)
+{
+ struct tables *tables = container_of(dbe, struct tables, dbe);
+ PyObject *t;
+
+ t = tuple_new(2);
+
+ tuple_set_s32(t, 0, branch_type);
+ tuple_set_string(t, 1, name);
+
+ call_object(tables->branch_type_handler, t, "branch_type_table");
+
+ Py_DECREF(t);
+
+ return 0;
+}
+
static int python_export_sample(struct db_export *dbe,
struct export_sample *es)
{
struct tables *tables = container_of(dbe, struct tables, dbe);
PyObject *t;
- t = tuple_new(19);
+ t = tuple_new(21);
tuple_set_u64(t, 0, es->db_id);
tuple_set_u64(t, 1, es->evsel->db_id);
@@ -691,6 +710,8 @@ static int python_export_sample(struct db_export *dbe,
tuple_set_u64(t, 16, es->sample->weight);
tuple_set_u64(t, 17, es->sample->transaction);
tuple_set_u64(t, 18, es->sample->data_src);
+ tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK);
+ tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX));
call_object(tables->sample_handler, t, "sample_table");
@@ -861,6 +882,7 @@ static void set_table_handlers(struct tables *tables)
SET_TABLE_HANDLER(comm_thread);
SET_TABLE_HANDLER(dso);
SET_TABLE_HANDLER(symbol);
+ SET_TABLE_HANDLER(branch_type);
SET_TABLE_HANDLER(sample);
}
@@ -910,6 +932,12 @@ static int python_start_script(const char *script, int argc, const char **argv)
set_table_handlers(tables);
+ if (tables->db_export_mode) {
+ err = db_export__branch_types(&tables->dbe);
+ if (err)
+ goto error;
+ }
+
return err;
error:
Py_Finalize();
--
1.9.1
^ permalink raw reply related [flat|nested] 18+ messages in thread* [tip:perf/core] perf tools: Add branch_type and in_tx to Python export
2014-10-30 14:09 ` [PATCH 3/7] perf tools: Add branch_type and in_tx to Python export Adrian Hunter
@ 2014-11-07 5:28 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 18+ messages in thread
From: tip-bot for Adrian Hunter @ 2014-11-07 5:28 UTC (permalink / raw)
To: linux-tip-commits
Cc: namhyung, linux-kernel, acme, dsahern, fweisbec, jolsa, mingo,
hpa, adrian.hunter, peterz, tglx, eranian, paulus
Commit-ID: c29414f5cfd641d956c5287848fdd8f25bb2afa3
Gitweb: http://git.kernel.org/tip/c29414f5cfd641d956c5287848fdd8f25bb2afa3
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 30 Oct 2014 16:09:44 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 3 Nov 2014 18:07:34 -0300
perf tools: Add branch_type and in_tx to Python export
Add branch_type and in_tx to Python db export and the
export-to-postgresql.py script.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1414678188-14946-4-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/scripts/python/export-to-postgresql.py | 32 ++++++++++++++++++----
.../util/scripting-engines/trace-event-python.c | 30 +++++++++++++++++++-
2 files changed, 55 insertions(+), 7 deletions(-)
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index d8f6df0..bb79aec 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -123,6 +123,10 @@ do_query(query, 'CREATE TABLE symbols ('
'sym_end bigint,'
'binding integer,'
'name varchar(2048))')
+do_query(query, 'CREATE TABLE branch_types ('
+ 'id integer NOT NULL,'
+ 'name varchar(80))')
+
if branches:
do_query(query, 'CREATE TABLE samples ('
'id bigint NOT NULL,'
@@ -139,7 +143,9 @@ if branches:
'to_dso_id bigint,'
'to_symbol_id bigint,'
'to_sym_offset bigint,'
- 'to_ip bigint)')
+ 'to_ip bigint,'
+ 'branch_type integer,'
+ 'in_tx boolean)')
else:
do_query(query, 'CREATE TABLE samples ('
'id bigint NOT NULL,'
@@ -160,7 +166,9 @@ else:
'period bigint,'
'weight bigint,'
'transaction bigint,'
- 'data_src bigint)')
+ 'data_src bigint,'
+ 'branch_type integer,'
+ 'in_tx boolean)')
do_query(query, 'CREATE VIEW samples_view AS '
'SELECT '
@@ -178,7 +186,9 @@ do_query(query, 'CREATE VIEW samples_view AS '
'to_hex(to_ip) AS to_ip_hex,'
'(SELECT name FROM symbols WHERE id = to_symbol_id) AS to_symbol,'
'to_sym_offset,'
- '(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name'
+ '(SELECT short_name FROM dsos WHERE id = to_dso_id) AS to_dso_short_name,'
+ '(SELECT name FROM branch_types WHERE id = branch_type) AS branch_type_name,'
+ 'in_tx'
' FROM samples')
@@ -234,6 +244,7 @@ comm_file = open_output_file("comm_table.bin")
comm_thread_file = open_output_file("comm_thread_table.bin")
dso_file = open_output_file("dso_table.bin")
symbol_file = open_output_file("symbol_table.bin")
+branch_type_file = open_output_file("branch_type_table.bin")
sample_file = open_output_file("sample_table.bin")
def trace_begin():
@@ -257,6 +268,7 @@ def trace_end():
copy_output_file(comm_thread_file, "comm_threads")
copy_output_file(dso_file, "dsos")
copy_output_file(symbol_file, "symbols")
+ copy_output_file(branch_type_file, "branch_types")
copy_output_file(sample_file, "samples")
print datetime.datetime.today(), "Removing intermediate files..."
@@ -267,6 +279,7 @@ def trace_end():
remove_output_file(comm_thread_file)
remove_output_file(dso_file)
remove_output_file(symbol_file)
+ remove_output_file(branch_type_file)
remove_output_file(sample_file)
os.rmdir(output_dir_name)
print datetime.datetime.today(), "Adding primary keys"
@@ -277,6 +290,7 @@ def trace_end():
do_query(query, 'ALTER TABLE comm_threads ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE dsos ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE symbols ADD PRIMARY KEY (id)')
+ do_query(query, 'ALTER TABLE branch_types ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE samples ADD PRIMARY KEY (id)')
print datetime.datetime.today(), "Adding foreign keys"
@@ -352,9 +366,15 @@ def symbol_table(symbol_id, dso_id, sym_start, sym_end, binding, symbol_name, *x
value = struct.pack(fmt, 6, 8, symbol_id, 8, dso_id, 8, sym_start, 8, sym_end, 4, binding, n, symbol_name)
symbol_file.write(value)
-def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, *x):
+def branch_type_table(branch_type, name, *x):
+ n = len(name)
+ fmt = "!hiii" + str(n) + "s"
+ value = struct.pack(fmt, 2, 4, branch_type, n, name)
+ branch_type_file.write(value)
+
+def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, symbol_id, sym_offset, ip, time, cpu, to_dso_id, to_symbol_id, to_sym_offset, to_ip, period, weight, transaction, data_src, branch_type, in_tx, *x):
if branches:
- value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiq", 15, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip)
+ value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiiiB", 17, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 4, branch_type, 1, in_tx)
else:
- value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiq", 19, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src)
+ value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx)
sample_file.write(value)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index 2fd7ee8..f3ca779 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -66,6 +66,7 @@ struct tables {
PyObject *comm_thread_handler;
PyObject *dso_handler;
PyObject *symbol_handler;
+ PyObject *branch_type_handler;
PyObject *sample_handler;
bool db_export_mode;
};
@@ -664,13 +665,31 @@ static int python_export_symbol(struct db_export *dbe, struct symbol *sym,
return 0;
}
+static int python_export_branch_type(struct db_export *dbe, u32 branch_type,
+ const char *name)
+{
+ struct tables *tables = container_of(dbe, struct tables, dbe);
+ PyObject *t;
+
+ t = tuple_new(2);
+
+ tuple_set_s32(t, 0, branch_type);
+ tuple_set_string(t, 1, name);
+
+ call_object(tables->branch_type_handler, t, "branch_type_table");
+
+ Py_DECREF(t);
+
+ return 0;
+}
+
static int python_export_sample(struct db_export *dbe,
struct export_sample *es)
{
struct tables *tables = container_of(dbe, struct tables, dbe);
PyObject *t;
- t = tuple_new(19);
+ t = tuple_new(21);
tuple_set_u64(t, 0, es->db_id);
tuple_set_u64(t, 1, es->evsel->db_id);
@@ -691,6 +710,8 @@ static int python_export_sample(struct db_export *dbe,
tuple_set_u64(t, 16, es->sample->weight);
tuple_set_u64(t, 17, es->sample->transaction);
tuple_set_u64(t, 18, es->sample->data_src);
+ tuple_set_s32(t, 19, es->sample->flags & PERF_BRANCH_MASK);
+ tuple_set_s32(t, 20, !!(es->sample->flags & PERF_IP_FLAG_IN_TX));
call_object(tables->sample_handler, t, "sample_table");
@@ -861,6 +882,7 @@ static void set_table_handlers(struct tables *tables)
SET_TABLE_HANDLER(comm_thread);
SET_TABLE_HANDLER(dso);
SET_TABLE_HANDLER(symbol);
+ SET_TABLE_HANDLER(branch_type);
SET_TABLE_HANDLER(sample);
}
@@ -910,6 +932,12 @@ static int python_start_script(const char *script, int argc, const char **argv)
set_table_handlers(tables);
+ if (tables->db_export_mode) {
+ err = db_export__branch_types(&tables->dbe);
+ if (err)
+ goto error;
+ }
+
return err;
error:
Py_Finalize();
^ permalink raw reply related [flat|nested] 18+ messages in thread
* [PATCH 4/7] perf tools: Enhance the thread stack to output call/return data
2014-10-30 14:09 [PATCH 0/7] perf tools: Add a thread stack for synthesizing call chains Adrian Hunter
` (2 preceding siblings ...)
2014-10-30 14:09 ` [PATCH 3/7] perf tools: Add branch_type and in_tx to Python export Adrian Hunter
@ 2014-10-30 14:09 ` Adrian Hunter
2014-11-03 13:11 ` Jiri Olsa
2014-11-07 5:28 ` [tip:perf/core] " tip-bot for Adrian Hunter
2014-10-30 14:09 ` [PATCH 5/7] perf tools: Add call information to the database export API Adrian Hunter
` (3 subsequent siblings)
7 siblings, 2 replies; 18+ messages in thread
From: Adrian Hunter @ 2014-10-30 14:09 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Paul Mackerras, Stephane Eranian
Enhance the thread stack to output detailed information
about paired calls and returns.
The enhanced processing consumes sample information via
thread_stack__process() and outputs information about
paired calls / returns via a call-back. While the
call-back makes it possible for the facility to be used
by arbitrary tools, a subsequent patch will provide the
information to Python scripting via the db-export
interface.
An important part of the call/return information is the
call path which provides a structure that defines a context
sensitive call graph.
Note that there are now two ways to use the thread stack.
For simply providing a call stack (like you would get
from the perf record -g option) the interface consists of
thread_stack__event() and thread_stack__sample(). Whereas
the enhanced interface consists of call_return_processor__new()
and thread_stack__process().
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/thread-stack.c | 585 ++++++++++++++++++++++++++++++++++++++++-
tools/perf/util/thread-stack.h | 79 ++++++
2 files changed, 659 insertions(+), 5 deletions(-)
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 85b60d2..9ed59a4 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -13,23 +13,96 @@
*
*/
+#include <linux/rbtree.h>
+#include <linux/list.h>
#include "thread.h"
#include "event.h"
+#include "machine.h"
#include "util.h"
#include "debug.h"
+#include "symbol.h"
+#include "comm.h"
#include "thread-stack.h"
-#define STACK_GROWTH 4096
+#define CALL_PATH_BLOCK_SHIFT 8
+#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT)
+#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1)
+struct call_path_block {
+ struct call_path cp[CALL_PATH_BLOCK_SIZE];
+ struct list_head node;
+};
+
+/**
+ * struct call_path_root - root of all call paths.
+ * @call_path: root call path
+ * @blocks: list of blocks to store call paths
+ * @next: next free space
+ * @sz: number of spaces
+ */
+struct call_path_root {
+ struct call_path call_path;
+ struct list_head blocks;
+ size_t next;
+ size_t sz;
+};
+
+/**
+ * struct call_return_processor - provides a call-back to consume call-return
+ * information.
+ * @cpr: call path root
+ * @process: call-back that accepts call/return information
+ * @data: anonymous data for call-back
+ */
+struct call_return_processor {
+ struct call_path_root *cpr;
+ int (*process)(struct call_return *cr, void *data);
+ void *data;
+};
+
+#define STACK_GROWTH 2048
+
+/**
+ * struct thread_stack_entry - thread stack entry.
+ * @ret_addr: return address
+ * @timestamp: timestamp (if known)
+ * @ref: external reference (e.g. db_id of sample)
+ * @branch_count: the branch count when the entry was created
+ * @cp: call path
+ * @no_call: a 'call' was not seen
+ */
struct thread_stack_entry {
u64 ret_addr;
+ u64 timestamp;
+ u64 ref;
+ u64 branch_count;
+ struct call_path *cp;
+ bool no_call;
};
+/**
+ * struct thread_stack - thread stack constructed from 'call' and 'return'
+ * branch samples.
+ * @stack: array that holds the stack
+ * @cnt: number of entries in the stack
+ * @sz: current maximum stack size
+ * @trace_nr: current trace number
+ * @branch_count: running branch count
+ * @kernel_start: kernel start address
+ * @last_time: last timestamp
+ * @crp: call/return processor
+ * @comm: current comm
+ */
struct thread_stack {
struct thread_stack_entry *stack;
size_t cnt;
size_t sz;
u64 trace_nr;
+ u64 branch_count;
+ u64 kernel_start;
+ u64 last_time;
+ struct call_return_processor *crp;
+ struct comm *comm;
};
static int thread_stack__grow(struct thread_stack *ts)
@@ -50,7 +123,8 @@ static int thread_stack__grow(struct thread_stack *ts)
return 0;
}
-static struct thread_stack *thread_stack__new(void)
+static struct thread_stack *thread_stack__new(struct thread *thread,
+ struct call_return_processor *crp)
{
struct thread_stack *ts;
@@ -63,6 +137,12 @@ static struct thread_stack *thread_stack__new(void)
return NULL;
}
+ if (thread->mg && thread->mg->machine)
+ ts->kernel_start = machine__kernel_start(thread->mg->machine);
+ else
+ ts->kernel_start = 1ULL << 63;
+ ts->crp = crp;
+
return ts;
}
@@ -104,6 +184,64 @@ static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
}
}
+static bool thread_stack__in_kernel(struct thread_stack *ts)
+{
+ if (!ts->cnt)
+ return false;
+
+ return ts->stack[ts->cnt - 1].cp->in_kernel;
+}
+
+static int thread_stack__call_return(struct thread *thread,
+ struct thread_stack *ts, size_t idx,
+ u64 timestamp, u64 ref, bool no_return)
+{
+ struct call_return_processor *crp = ts->crp;
+ struct thread_stack_entry *tse;
+ struct call_return cr = {
+ .thread = thread,
+ .comm = ts->comm,
+ .db_id = 0,
+ };
+
+ tse = &ts->stack[idx];
+ cr.cp = tse->cp;
+ cr.call_time = tse->timestamp;
+ cr.return_time = timestamp;
+ cr.branch_count = ts->branch_count - tse->branch_count;
+ cr.call_ref = tse->ref;
+ cr.return_ref = ref;
+ if (tse->no_call)
+ cr.flags |= CALL_RETURN_NO_CALL;
+ if (no_return)
+ cr.flags |= CALL_RETURN_NO_RETURN;
+
+ return crp->process(&cr, crp->data);
+}
+
+static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+{
+ struct call_return_processor *crp = ts->crp;
+ int err;
+
+ if (!crp) {
+ ts->cnt = 0;
+ return 0;
+ }
+
+ while (ts->cnt) {
+ err = thread_stack__call_return(thread, ts, --ts->cnt,
+ ts->last_time, 0, true);
+ if (err) {
+ pr_err("Error flushing thread stack!\n");
+ ts->cnt = 0;
+ return err;
+ }
+ }
+
+ return 0;
+}
+
int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
u64 to_ip, u16 insn_len, u64 trace_nr)
{
@@ -111,7 +249,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
return -EINVAL;
if (!thread->ts) {
- thread->ts = thread_stack__new();
+ thread->ts = thread_stack__new(thread, NULL);
if (!thread->ts) {
pr_warning("Out of memory: no thread stack\n");
return -ENOMEM;
@@ -122,13 +260,18 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
/*
* When the trace is discontinuous, the trace_nr changes. In that case
* the stack might be completely invalid. Better to report nothing than
- * to report something misleading, so reset the stack count to zero.
+ * to report something misleading, so flush the stack.
*/
if (trace_nr != thread->ts->trace_nr) {
+ if (thread->ts->trace_nr)
+ thread_stack__flush(thread, thread->ts);
thread->ts->trace_nr = trace_nr;
- thread->ts->cnt = 0;
}
+ /* Stop here if thread_stack__process() is in use */
+ if (thread->ts->crp)
+ return 0;
+
if (flags & PERF_IP_FLAG_CALL) {
u64 ret_addr;
@@ -147,9 +290,22 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
return 0;
}
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
+{
+ if (!thread || !thread->ts)
+ return;
+
+ if (trace_nr != thread->ts->trace_nr) {
+ if (thread->ts->trace_nr)
+ thread_stack__flush(thread, thread->ts);
+ thread->ts->trace_nr = trace_nr;
+ }
+}
+
void thread_stack__free(struct thread *thread)
{
if (thread->ts) {
+ thread_stack__flush(thread, thread->ts);
zfree(&thread->ts->stack);
zfree(&thread->ts);
}
@@ -170,3 +326,422 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
for (i = 1; i < chain->nr; i++)
chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
}
+
+static void call_path__init(struct call_path *cp, struct call_path *parent,
+ struct symbol *sym, u64 ip, bool in_kernel)
+{
+ cp->parent = parent;
+ cp->sym = sym;
+ cp->ip = sym ? 0 : ip;
+ cp->db_id = 0;
+ cp->in_kernel = in_kernel;
+ RB_CLEAR_NODE(&cp->rb_node);
+ cp->children = RB_ROOT;
+}
+
+static struct call_path_root *call_path_root__new(void)
+{
+ struct call_path_root *cpr;
+
+ cpr = zalloc(sizeof(struct call_path_root));
+ if (!cpr)
+ return NULL;
+ call_path__init(&cpr->call_path, NULL, NULL, 0, false);
+ INIT_LIST_HEAD(&cpr->blocks);
+ return cpr;
+}
+
+static void call_path_root__free(struct call_path_root *cpr)
+{
+ struct call_path_block *pos, *n;
+
+ list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
+ list_del(&pos->node);
+ free(pos);
+ }
+ free(cpr);
+}
+
+static struct call_path *call_path__new(struct call_path_root *cpr,
+ struct call_path *parent,
+ struct symbol *sym, u64 ip,
+ bool in_kernel)
+{
+ struct call_path_block *cpb;
+ struct call_path *cp;
+ size_t n;
+
+ if (cpr->next < cpr->sz) {
+ cpb = list_last_entry(&cpr->blocks, struct call_path_block,
+ node);
+ } else {
+ cpb = zalloc(sizeof(struct call_path_block));
+ if (!cpb)
+ return NULL;
+ list_add_tail(&cpb->node, &cpr->blocks);
+ cpr->sz += CALL_PATH_BLOCK_SIZE;
+ }
+
+ n = cpr->next++ & CALL_PATH_BLOCK_MASK;
+ cp = &cpb->cp[n];
+
+ call_path__init(cp, parent, sym, ip, in_kernel);
+
+ return cp;
+}
+
+static struct call_path *call_path__findnew(struct call_path_root *cpr,
+ struct call_path *parent,
+ struct symbol *sym, u64 ip, u64 ks)
+{
+ struct rb_node **p;
+ struct rb_node *node_parent = NULL;
+ struct call_path *cp;
+ bool in_kernel = ip >= ks;
+
+ if (sym)
+ ip = 0;
+
+ if (!parent)
+ return call_path__new(cpr, parent, sym, ip, in_kernel);
+
+ p = &parent->children.rb_node;
+ while (*p != NULL) {
+ node_parent = *p;
+ cp = rb_entry(node_parent, struct call_path, rb_node);
+
+ if (cp->sym == sym && cp->ip == ip)
+ return cp;
+
+ if (sym < cp->sym || (sym == cp->sym && ip < cp->ip))
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+
+ cp = call_path__new(cpr, parent, sym, ip, in_kernel);
+ if (!cp)
+ return NULL;
+
+ rb_link_node(&cp->rb_node, node_parent, p);
+ rb_insert_color(&cp->rb_node, &parent->children);
+
+ return cp;
+}
+
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+ void *data)
+{
+ struct call_return_processor *crp;
+
+ crp = zalloc(sizeof(struct call_return_processor));
+ if (!crp)
+ return NULL;
+ crp->cpr = call_path_root__new();
+ if (!crp->cpr)
+ goto out_free;
+ crp->process = process;
+ crp->data = data;
+ return crp;
+
+out_free:
+ free(crp);
+ return NULL;
+}
+
+void call_return_processor__free(struct call_return_processor *crp)
+{
+ if (crp) {
+ call_path_root__free(crp->cpr);
+ free(crp);
+ }
+}
+
+static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
+ u64 timestamp, u64 ref, struct call_path *cp,
+ bool no_call)
+{
+ struct thread_stack_entry *tse;
+ int err;
+
+ if (ts->cnt == ts->sz) {
+ err = thread_stack__grow(ts);
+ if (err)
+ return err;
+ }
+
+ tse = &ts->stack[ts->cnt++];
+ tse->ret_addr = ret_addr;
+ tse->timestamp = timestamp;
+ tse->ref = ref;
+ tse->branch_count = ts->branch_count;
+ tse->cp = cp;
+ tse->no_call = no_call;
+
+ return 0;
+}
+
+static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts,
+ u64 ret_addr, u64 timestamp, u64 ref,
+ struct symbol *sym)
+{
+ int err;
+
+ if (!ts->cnt)
+ return 1;
+
+ if (ts->cnt == 1) {
+ struct thread_stack_entry *tse = &ts->stack[0];
+
+ if (tse->cp->sym == sym)
+ return thread_stack__call_return(thread, ts, --ts->cnt,
+ timestamp, ref, false);
+ }
+
+ if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) {
+ return thread_stack__call_return(thread, ts, --ts->cnt,
+ timestamp, ref, false);
+ } else {
+ size_t i = ts->cnt - 1;
+
+ while (i--) {
+ if (ts->stack[i].ret_addr != ret_addr)
+ continue;
+ i += 1;
+ while (ts->cnt > i) {
+ err = thread_stack__call_return(thread, ts,
+ --ts->cnt,
+ timestamp, ref,
+ true);
+ if (err)
+ return err;
+ }
+ return thread_stack__call_return(thread, ts, --ts->cnt,
+ timestamp, ref, false);
+ }
+ }
+
+ return 1;
+}
+
+static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
+ struct perf_sample *sample,
+ struct addr_location *from_al,
+ struct addr_location *to_al, u64 ref)
+{
+ struct call_path_root *cpr = ts->crp->cpr;
+ struct call_path *cp;
+ struct symbol *sym;
+ u64 ip;
+
+ if (sample->ip) {
+ ip = sample->ip;
+ sym = from_al->sym;
+ } else if (sample->addr) {
+ ip = sample->addr;
+ sym = to_al->sym;
+ } else {
+ return 0;
+ }
+
+ cp = call_path__findnew(cpr, &cpr->call_path, sym, ip,
+ ts->kernel_start);
+ if (!cp)
+ return -ENOMEM;
+
+ return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
+ true);
+}
+
+static int thread_stack__no_call_return(struct thread *thread,
+ struct thread_stack *ts,
+ struct perf_sample *sample,
+ struct addr_location *from_al,
+ struct addr_location *to_al, u64 ref)
+{
+ struct call_path_root *cpr = ts->crp->cpr;
+ struct call_path *cp, *parent;
+ u64 ks = ts->kernel_start;
+ int err;
+
+ if (sample->ip >= ks && sample->addr < ks) {
+ /* Return to userspace, so pop all kernel addresses */
+ while (thread_stack__in_kernel(ts)) {
+ err = thread_stack__call_return(thread, ts, --ts->cnt,
+ sample->time, ref,
+ true);
+ if (err)
+ return err;
+ }
+
+ /* If the stack is empty, push the userspace address */
+ if (!ts->cnt) {
+ cp = call_path__findnew(cpr, &cpr->call_path,
+ to_al->sym, sample->addr,
+ ts->kernel_start);
+ if (!cp)
+ return -ENOMEM;
+ return thread_stack__push_cp(ts, 0, sample->time, ref,
+ cp, true);
+ }
+ } else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
+ /* Return to userspace, so pop all kernel addresses */
+ while (thread_stack__in_kernel(ts)) {
+ err = thread_stack__call_return(thread, ts, --ts->cnt,
+ sample->time, ref,
+ true);
+ if (err)
+ return err;
+ }
+ }
+
+ if (ts->cnt)
+ parent = ts->stack[ts->cnt - 1].cp;
+ else
+ parent = &cpr->call_path;
+
+ /* This 'return' had no 'call', so push and pop top of stack */
+ cp = call_path__findnew(cpr, parent, from_al->sym, sample->ip,
+ ts->kernel_start);
+ if (!cp)
+ return -ENOMEM;
+
+ err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
+ true);
+ if (err)
+ return err;
+
+ return thread_stack__pop_cp(thread, ts, sample->addr, sample->time, ref,
+ to_al->sym);
+}
+
+static int thread_stack__trace_begin(struct thread *thread,
+ struct thread_stack *ts, u64 timestamp,
+ u64 ref)
+{
+ struct thread_stack_entry *tse;
+ int err;
+
+ if (!ts->cnt)
+ return 0;
+
+ /* Pop trace end */
+ tse = &ts->stack[ts->cnt - 1];
+ if (tse->cp->sym == NULL && tse->cp->ip == 0) {
+ err = thread_stack__call_return(thread, ts, --ts->cnt,
+ timestamp, ref, false);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int thread_stack__trace_end(struct thread_stack *ts,
+ struct perf_sample *sample, u64 ref)
+{
+ struct call_path_root *cpr = ts->crp->cpr;
+ struct call_path *cp;
+ u64 ret_addr;
+
+ /* No point having 'trace end' on the bottom of the stack */
+ if (!ts->cnt || (ts->cnt == 1 && ts->stack[0].ref == ref))
+ return 0;
+
+ cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp, NULL, 0,
+ ts->kernel_start);
+ if (!cp)
+ return -ENOMEM;
+
+ ret_addr = sample->ip + sample->insn_len;
+
+ return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
+ false);
+}
+
+int thread_stack__process(struct thread *thread, struct comm *comm,
+ struct perf_sample *sample,
+ struct addr_location *from_al,
+ struct addr_location *to_al, u64 ref,
+ struct call_return_processor *crp)
+{
+ struct thread_stack *ts = thread->ts;
+ int err = 0;
+
+ if (ts) {
+ if (!ts->crp) {
+ /* Supersede thread_stack__event() */
+ thread_stack__free(thread);
+ thread->ts = thread_stack__new(thread, crp);
+ if (!thread->ts)
+ return -ENOMEM;
+ ts = thread->ts;
+ ts->comm = comm;
+ }
+ } else {
+ thread->ts = thread_stack__new(thread, crp);
+ if (!thread->ts)
+ return -ENOMEM;
+ ts = thread->ts;
+ ts->comm = comm;
+ }
+
+ /* Flush stack on exec */
+ if (ts->comm != comm && thread->pid_ == thread->tid) {
+ err = thread_stack__flush(thread, ts);
+ if (err)
+ return err;
+ ts->comm = comm;
+ }
+
+ /* If the stack is empty, put the current symbol on the stack */
+ if (!ts->cnt) {
+ err = thread_stack__bottom(thread, ts, sample, from_al, to_al,
+ ref);
+ if (err)
+ return err;
+ }
+
+ ts->branch_count += 1;
+ ts->last_time = sample->time;
+
+ if (sample->flags & PERF_IP_FLAG_CALL) {
+ struct call_path_root *cpr = ts->crp->cpr;
+ struct call_path *cp;
+ u64 ret_addr;
+
+ if (!sample->ip || !sample->addr)
+ return 0;
+
+ ret_addr = sample->ip + sample->insn_len;
+ if (ret_addr == sample->addr)
+ return 0; /* Zero-length calls are excluded */
+
+ cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
+ to_al->sym, sample->addr,
+ ts->kernel_start);
+ if (!cp)
+ return -ENOMEM;
+ err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
+ cp, false);
+ } else if (sample->flags & PERF_IP_FLAG_RETURN) {
+ if (!sample->ip || !sample->addr)
+ return 0;
+
+ err = thread_stack__pop_cp(thread, ts, sample->addr,
+ sample->time, ref, from_al->sym);
+ if (err) {
+ if (err < 0)
+ return err;
+ err = thread_stack__no_call_return(thread, ts, sample,
+ from_al, to_al, ref);
+ }
+ } else if (sample->flags & PERF_IP_FLAG_TRACE_BEGIN) {
+ err = thread_stack__trace_begin(thread, ts, sample->time, ref);
+ } else if (sample->flags & PERF_IP_FLAG_TRACE_END) {
+ err = thread_stack__trace_end(ts, sample, ref);
+ }
+
+ return err;
+}
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index 7c41579..b843bbe 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -19,14 +19,93 @@
#include <sys/types.h>
#include <linux/types.h>
+#include <linux/rbtree.h>
struct thread;
+struct comm;
struct ip_callchain;
+struct symbol;
+struct dso;
+struct call_return_processor;
+struct comm;
+struct perf_sample;
+struct addr_location;
+
+/*
+ * Call/Return flags.
+ *
+ * CALL_RETURN_NO_CALL: 'return' but no matching 'call'
+ * CALL_RETURN_NO_RETURN: 'call' but no matching 'return'
+ */
+enum {
+ CALL_RETURN_NO_CALL = 1 << 0,
+ CALL_RETURN_NO_RETURN = 1 << 1,
+};
+
+/**
+ * struct call_return - paired call/return information.
+ * @thread: thread in which call/return occurred
+ * @comm: comm in which call/return occurred
+ * @cp: call path
+ * @call_time: timestamp of call (if known)
+ * @return_time: timestamp of return (if known)
+ * @branch_count: number of branches seen between call and return
+ * @call_ref: external reference to 'call' sample (e.g. db_id)
+ * @return_ref: external reference to 'return' sample (e.g. db_id)
+ * @db_id: id used for db-export
+ * @flags: Call/Return flags
+ */
+struct call_return {
+ struct thread *thread;
+ struct comm *comm;
+ struct call_path *cp;
+ u64 call_time;
+ u64 return_time;
+ u64 branch_count;
+ u64 call_ref;
+ u64 return_ref;
+ u64 db_id;
+ u32 flags;
+};
+
+/**
+ * struct call_path - node in list of calls leading to a function call.
+ * @parent: call path to the parent function call
+ * @sym: symbol of function called
+ * @ip: only if sym is null, the ip of the function
+ * @db_id: id used for db-export
+ * @in_kernel: whether function is a in the kernel
+ * @rb_node: node in parent's tree of called functions
+ * @children: tree of call paths of functions called
+ *
+ * In combination with the call_return structure, the call_path structure
+ * defines a context-sensitve call-graph.
+ */
+struct call_path {
+ struct call_path *parent;
+ struct symbol *sym;
+ u64 ip;
+ u64 db_id;
+ bool in_kernel;
+ struct rb_node rb_node;
+ struct rb_root children;
+};
int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
u64 to_ip, u16 insn_len, u64 trace_nr);
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
size_t sz, u64 ip);
void thread_stack__free(struct thread *thread);
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+ void *data);
+void call_return_processor__free(struct call_return_processor *crp);
+int thread_stack__process(struct thread *thread, struct comm *comm,
+ struct perf_sample *sample,
+ struct addr_location *from_al,
+ struct addr_location *to_al, u64 ref,
+ struct call_return_processor *crp);
+
#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 18+ messages in thread* Re: [PATCH 4/7] perf tools: Enhance the thread stack to output call/return data
2014-10-30 14:09 ` [PATCH 4/7] perf tools: Enhance the thread stack to output call/return data Adrian Hunter
@ 2014-11-03 13:11 ` Jiri Olsa
2014-11-07 5:28 ` [tip:perf/core] " tip-bot for Adrian Hunter
1 sibling, 0 replies; 18+ messages in thread
From: Jiri Olsa @ 2014-11-03 13:11 UTC (permalink / raw)
To: Adrian Hunter
Cc: Arnaldo Carvalho de Melo, Peter Zijlstra, linux-kernel,
David Ahern, Frederic Weisbecker, Namhyung Kim, Paul Mackerras,
Stephane Eranian
On Thu, Oct 30, 2014 at 04:09:45PM +0200, Adrian Hunter wrote:
> Enhance the thread stack to output detailed information
> about paired calls and returns.
>
> The enhanced processing consumes sample information via
> thread_stack__process() and outputs information about
> paired calls / returns via a call-back. While the
> call-back makes it possible for the facility to be used
> by arbitrary tools, a subsequent patch will provide the
> information to Python scripting via the db-export
> interface.
>
> An important part of the call/return information is the
> call path which provides a structure that defines a context
> sensitive call graph.
>
> Note that there are now two ways to use the thread stack.
> For simply providing a call stack (like you would get
> from the perf record -g option) the interface consists of
> thread_stack__event() and thread_stack__sample(). Whereas
> the enhanced interface consists of call_return_processor__new()
> and thread_stack__process().
the interface seems pretty separated, with clear in and out values,
so it should be fairly easy to write automated tests for that ;-)
also given that there's no real user of this interface at the moment,
it'd be really nice to have ;-) anyway
Acked-by: Jiri Olsa <jolsa@kernel.org>
jirka
^ permalink raw reply [flat|nested] 18+ messages in thread
* [tip:perf/core] perf tools: Enhance the thread stack to output call/return data
2014-10-30 14:09 ` [PATCH 4/7] perf tools: Enhance the thread stack to output call/return data Adrian Hunter
2014-11-03 13:11 ` Jiri Olsa
@ 2014-11-07 5:28 ` tip-bot for Adrian Hunter
1 sibling, 0 replies; 18+ messages in thread
From: tip-bot for Adrian Hunter @ 2014-11-07 5:28 UTC (permalink / raw)
To: linux-tip-commits
Cc: namhyung, acme, paulus, eranian, hpa, jolsa, mingo, peterz, jolsa,
linux-kernel, dsahern, adrian.hunter, fweisbec, tglx
Commit-ID: 92a9e4f7db89a013e1bdef2e548928fc71e9867c
Gitweb: http://git.kernel.org/tip/92a9e4f7db89a013e1bdef2e548928fc71e9867c
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 30 Oct 2014 16:09:45 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 3 Nov 2014 17:43:56 -0300
perf tools: Enhance the thread stack to output call/return data
Enhance the thread stack to output detailed information about paired
calls and returns.
The enhanced processing consumes sample information via
thread_stack__process() and outputs information about paired calls /
returns via a call-back.
While the call-back makes it possible for the facility to be used by
arbitrary tools, a subsequent patch will provide the information to
Python scripting via the db-export interface.
An important part of the call/return information is the
call path which provides a structure that defines a context
sensitive call graph.
Note that there are now two ways to use the thread stack.
For simply providing a call stack (like you would get from the perf
record -g option) the interface consists of thread_stack__event() and
thread_stack__sample().
Whereas the enhanced interface consists of call_return_processor__new()
and thread_stack__process().
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1414678188-14946-5-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/thread-stack.c | 585 ++++++++++++++++++++++++++++++++++++++++-
tools/perf/util/thread-stack.h | 79 ++++++
2 files changed, 659 insertions(+), 5 deletions(-)
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index 85b60d2..9ed59a4 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -13,23 +13,96 @@
*
*/
+#include <linux/rbtree.h>
+#include <linux/list.h>
#include "thread.h"
#include "event.h"
+#include "machine.h"
#include "util.h"
#include "debug.h"
+#include "symbol.h"
+#include "comm.h"
#include "thread-stack.h"
-#define STACK_GROWTH 4096
+#define CALL_PATH_BLOCK_SHIFT 8
+#define CALL_PATH_BLOCK_SIZE (1 << CALL_PATH_BLOCK_SHIFT)
+#define CALL_PATH_BLOCK_MASK (CALL_PATH_BLOCK_SIZE - 1)
+struct call_path_block {
+ struct call_path cp[CALL_PATH_BLOCK_SIZE];
+ struct list_head node;
+};
+
+/**
+ * struct call_path_root - root of all call paths.
+ * @call_path: root call path
+ * @blocks: list of blocks to store call paths
+ * @next: next free space
+ * @sz: number of spaces
+ */
+struct call_path_root {
+ struct call_path call_path;
+ struct list_head blocks;
+ size_t next;
+ size_t sz;
+};
+
+/**
+ * struct call_return_processor - provides a call-back to consume call-return
+ * information.
+ * @cpr: call path root
+ * @process: call-back that accepts call/return information
+ * @data: anonymous data for call-back
+ */
+struct call_return_processor {
+ struct call_path_root *cpr;
+ int (*process)(struct call_return *cr, void *data);
+ void *data;
+};
+
+#define STACK_GROWTH 2048
+
+/**
+ * struct thread_stack_entry - thread stack entry.
+ * @ret_addr: return address
+ * @timestamp: timestamp (if known)
+ * @ref: external reference (e.g. db_id of sample)
+ * @branch_count: the branch count when the entry was created
+ * @cp: call path
+ * @no_call: a 'call' was not seen
+ */
struct thread_stack_entry {
u64 ret_addr;
+ u64 timestamp;
+ u64 ref;
+ u64 branch_count;
+ struct call_path *cp;
+ bool no_call;
};
+/**
+ * struct thread_stack - thread stack constructed from 'call' and 'return'
+ * branch samples.
+ * @stack: array that holds the stack
+ * @cnt: number of entries in the stack
+ * @sz: current maximum stack size
+ * @trace_nr: current trace number
+ * @branch_count: running branch count
+ * @kernel_start: kernel start address
+ * @last_time: last timestamp
+ * @crp: call/return processor
+ * @comm: current comm
+ */
struct thread_stack {
struct thread_stack_entry *stack;
size_t cnt;
size_t sz;
u64 trace_nr;
+ u64 branch_count;
+ u64 kernel_start;
+ u64 last_time;
+ struct call_return_processor *crp;
+ struct comm *comm;
};
static int thread_stack__grow(struct thread_stack *ts)
@@ -50,7 +123,8 @@ static int thread_stack__grow(struct thread_stack *ts)
return 0;
}
-static struct thread_stack *thread_stack__new(void)
+static struct thread_stack *thread_stack__new(struct thread *thread,
+ struct call_return_processor *crp)
{
struct thread_stack *ts;
@@ -63,6 +137,12 @@ static struct thread_stack *thread_stack__new(void)
return NULL;
}
+ if (thread->mg && thread->mg->machine)
+ ts->kernel_start = machine__kernel_start(thread->mg->machine);
+ else
+ ts->kernel_start = 1ULL << 63;
+ ts->crp = crp;
+
return ts;
}
@@ -104,6 +184,64 @@ static void thread_stack__pop(struct thread_stack *ts, u64 ret_addr)
}
}
+static bool thread_stack__in_kernel(struct thread_stack *ts)
+{
+ if (!ts->cnt)
+ return false;
+
+ return ts->stack[ts->cnt - 1].cp->in_kernel;
+}
+
+static int thread_stack__call_return(struct thread *thread,
+ struct thread_stack *ts, size_t idx,
+ u64 timestamp, u64 ref, bool no_return)
+{
+ struct call_return_processor *crp = ts->crp;
+ struct thread_stack_entry *tse;
+ struct call_return cr = {
+ .thread = thread,
+ .comm = ts->comm,
+ .db_id = 0,
+ };
+
+ tse = &ts->stack[idx];
+ cr.cp = tse->cp;
+ cr.call_time = tse->timestamp;
+ cr.return_time = timestamp;
+ cr.branch_count = ts->branch_count - tse->branch_count;
+ cr.call_ref = tse->ref;
+ cr.return_ref = ref;
+ if (tse->no_call)
+ cr.flags |= CALL_RETURN_NO_CALL;
+ if (no_return)
+ cr.flags |= CALL_RETURN_NO_RETURN;
+
+ return crp->process(&cr, crp->data);
+}
+
+static int thread_stack__flush(struct thread *thread, struct thread_stack *ts)
+{
+ struct call_return_processor *crp = ts->crp;
+ int err;
+
+ if (!crp) {
+ ts->cnt = 0;
+ return 0;
+ }
+
+ while (ts->cnt) {
+ err = thread_stack__call_return(thread, ts, --ts->cnt,
+ ts->last_time, 0, true);
+ if (err) {
+ pr_err("Error flushing thread stack!\n");
+ ts->cnt = 0;
+ return err;
+ }
+ }
+
+ return 0;
+}
+
int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
u64 to_ip, u16 insn_len, u64 trace_nr)
{
@@ -111,7 +249,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
return -EINVAL;
if (!thread->ts) {
- thread->ts = thread_stack__new();
+ thread->ts = thread_stack__new(thread, NULL);
if (!thread->ts) {
pr_warning("Out of memory: no thread stack\n");
return -ENOMEM;
@@ -122,13 +260,18 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
/*
* When the trace is discontinuous, the trace_nr changes. In that case
* the stack might be completely invalid. Better to report nothing than
- * to report something misleading, so reset the stack count to zero.
+ * to report something misleading, so flush the stack.
*/
if (trace_nr != thread->ts->trace_nr) {
+ if (thread->ts->trace_nr)
+ thread_stack__flush(thread, thread->ts);
thread->ts->trace_nr = trace_nr;
- thread->ts->cnt = 0;
}
+ /* Stop here if thread_stack__process() is in use */
+ if (thread->ts->crp)
+ return 0;
+
if (flags & PERF_IP_FLAG_CALL) {
u64 ret_addr;
@@ -147,9 +290,22 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
return 0;
}
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr)
+{
+ if (!thread || !thread->ts)
+ return;
+
+ if (trace_nr != thread->ts->trace_nr) {
+ if (thread->ts->trace_nr)
+ thread_stack__flush(thread, thread->ts);
+ thread->ts->trace_nr = trace_nr;
+ }
+}
+
void thread_stack__free(struct thread *thread)
{
if (thread->ts) {
+ thread_stack__flush(thread, thread->ts);
zfree(&thread->ts->stack);
zfree(&thread->ts);
}
@@ -170,3 +326,422 @@ void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
for (i = 1; i < chain->nr; i++)
chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
}
+
+static void call_path__init(struct call_path *cp, struct call_path *parent,
+ struct symbol *sym, u64 ip, bool in_kernel)
+{
+ cp->parent = parent;
+ cp->sym = sym;
+ cp->ip = sym ? 0 : ip;
+ cp->db_id = 0;
+ cp->in_kernel = in_kernel;
+ RB_CLEAR_NODE(&cp->rb_node);
+ cp->children = RB_ROOT;
+}
+
+static struct call_path_root *call_path_root__new(void)
+{
+ struct call_path_root *cpr;
+
+ cpr = zalloc(sizeof(struct call_path_root));
+ if (!cpr)
+ return NULL;
+ call_path__init(&cpr->call_path, NULL, NULL, 0, false);
+ INIT_LIST_HEAD(&cpr->blocks);
+ return cpr;
+}
+
+static void call_path_root__free(struct call_path_root *cpr)
+{
+ struct call_path_block *pos, *n;
+
+ list_for_each_entry_safe(pos, n, &cpr->blocks, node) {
+ list_del(&pos->node);
+ free(pos);
+ }
+ free(cpr);
+}
+
+static struct call_path *call_path__new(struct call_path_root *cpr,
+ struct call_path *parent,
+ struct symbol *sym, u64 ip,
+ bool in_kernel)
+{
+ struct call_path_block *cpb;
+ struct call_path *cp;
+ size_t n;
+
+ if (cpr->next < cpr->sz) {
+ cpb = list_last_entry(&cpr->blocks, struct call_path_block,
+ node);
+ } else {
+ cpb = zalloc(sizeof(struct call_path_block));
+ if (!cpb)
+ return NULL;
+ list_add_tail(&cpb->node, &cpr->blocks);
+ cpr->sz += CALL_PATH_BLOCK_SIZE;
+ }
+
+ n = cpr->next++ & CALL_PATH_BLOCK_MASK;
+ cp = &cpb->cp[n];
+
+ call_path__init(cp, parent, sym, ip, in_kernel);
+
+ return cp;
+}
+
+static struct call_path *call_path__findnew(struct call_path_root *cpr,
+ struct call_path *parent,
+ struct symbol *sym, u64 ip, u64 ks)
+{
+ struct rb_node **p;
+ struct rb_node *node_parent = NULL;
+ struct call_path *cp;
+ bool in_kernel = ip >= ks;
+
+ if (sym)
+ ip = 0;
+
+ if (!parent)
+ return call_path__new(cpr, parent, sym, ip, in_kernel);
+
+ p = &parent->children.rb_node;
+ while (*p != NULL) {
+ node_parent = *p;
+ cp = rb_entry(node_parent, struct call_path, rb_node);
+
+ if (cp->sym == sym && cp->ip == ip)
+ return cp;
+
+ if (sym < cp->sym || (sym == cp->sym && ip < cp->ip))
+ p = &(*p)->rb_left;
+ else
+ p = &(*p)->rb_right;
+ }
+
+ cp = call_path__new(cpr, parent, sym, ip, in_kernel);
+ if (!cp)
+ return NULL;
+
+ rb_link_node(&cp->rb_node, node_parent, p);
+ rb_insert_color(&cp->rb_node, &parent->children);
+
+ return cp;
+}
+
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+ void *data)
+{
+ struct call_return_processor *crp;
+
+ crp = zalloc(sizeof(struct call_return_processor));
+ if (!crp)
+ return NULL;
+ crp->cpr = call_path_root__new();
+ if (!crp->cpr)
+ goto out_free;
+ crp->process = process;
+ crp->data = data;
+ return crp;
+
+out_free:
+ free(crp);
+ return NULL;
+}
+
+void call_return_processor__free(struct call_return_processor *crp)
+{
+ if (crp) {
+ call_path_root__free(crp->cpr);
+ free(crp);
+ }
+}
+
+static int thread_stack__push_cp(struct thread_stack *ts, u64 ret_addr,
+ u64 timestamp, u64 ref, struct call_path *cp,
+ bool no_call)
+{
+ struct thread_stack_entry *tse;
+ int err;
+
+ if (ts->cnt == ts->sz) {
+ err = thread_stack__grow(ts);
+ if (err)
+ return err;
+ }
+
+ tse = &ts->stack[ts->cnt++];
+ tse->ret_addr = ret_addr;
+ tse->timestamp = timestamp;
+ tse->ref = ref;
+ tse->branch_count = ts->branch_count;
+ tse->cp = cp;
+ tse->no_call = no_call;
+
+ return 0;
+}
+
+static int thread_stack__pop_cp(struct thread *thread, struct thread_stack *ts,
+ u64 ret_addr, u64 timestamp, u64 ref,
+ struct symbol *sym)
+{
+ int err;
+
+ if (!ts->cnt)
+ return 1;
+
+ if (ts->cnt == 1) {
+ struct thread_stack_entry *tse = &ts->stack[0];
+
+ if (tse->cp->sym == sym)
+ return thread_stack__call_return(thread, ts, --ts->cnt,
+ timestamp, ref, false);
+ }
+
+ if (ts->stack[ts->cnt - 1].ret_addr == ret_addr) {
+ return thread_stack__call_return(thread, ts, --ts->cnt,
+ timestamp, ref, false);
+ } else {
+ size_t i = ts->cnt - 1;
+
+ while (i--) {
+ if (ts->stack[i].ret_addr != ret_addr)
+ continue;
+ i += 1;
+ while (ts->cnt > i) {
+ err = thread_stack__call_return(thread, ts,
+ --ts->cnt,
+ timestamp, ref,
+ true);
+ if (err)
+ return err;
+ }
+ return thread_stack__call_return(thread, ts, --ts->cnt,
+ timestamp, ref, false);
+ }
+ }
+
+ return 1;
+}
+
+static int thread_stack__bottom(struct thread *thread, struct thread_stack *ts,
+ struct perf_sample *sample,
+ struct addr_location *from_al,
+ struct addr_location *to_al, u64 ref)
+{
+ struct call_path_root *cpr = ts->crp->cpr;
+ struct call_path *cp;
+ struct symbol *sym;
+ u64 ip;
+
+ if (sample->ip) {
+ ip = sample->ip;
+ sym = from_al->sym;
+ } else if (sample->addr) {
+ ip = sample->addr;
+ sym = to_al->sym;
+ } else {
+ return 0;
+ }
+
+ cp = call_path__findnew(cpr, &cpr->call_path, sym, ip,
+ ts->kernel_start);
+ if (!cp)
+ return -ENOMEM;
+
+ return thread_stack__push_cp(thread->ts, ip, sample->time, ref, cp,
+ true);
+}
+
+static int thread_stack__no_call_return(struct thread *thread,
+ struct thread_stack *ts,
+ struct perf_sample *sample,
+ struct addr_location *from_al,
+ struct addr_location *to_al, u64 ref)
+{
+ struct call_path_root *cpr = ts->crp->cpr;
+ struct call_path *cp, *parent;
+ u64 ks = ts->kernel_start;
+ int err;
+
+ if (sample->ip >= ks && sample->addr < ks) {
+ /* Return to userspace, so pop all kernel addresses */
+ while (thread_stack__in_kernel(ts)) {
+ err = thread_stack__call_return(thread, ts, --ts->cnt,
+ sample->time, ref,
+ true);
+ if (err)
+ return err;
+ }
+
+ /* If the stack is empty, push the userspace address */
+ if (!ts->cnt) {
+ cp = call_path__findnew(cpr, &cpr->call_path,
+ to_al->sym, sample->addr,
+ ts->kernel_start);
+ if (!cp)
+ return -ENOMEM;
+ return thread_stack__push_cp(ts, 0, sample->time, ref,
+ cp, true);
+ }
+ } else if (thread_stack__in_kernel(ts) && sample->ip < ks) {
+ /* Return to userspace, so pop all kernel addresses */
+ while (thread_stack__in_kernel(ts)) {
+ err = thread_stack__call_return(thread, ts, --ts->cnt,
+ sample->time, ref,
+ true);
+ if (err)
+ return err;
+ }
+ }
+
+ if (ts->cnt)
+ parent = ts->stack[ts->cnt - 1].cp;
+ else
+ parent = &cpr->call_path;
+
+ /* This 'return' had no 'call', so push and pop top of stack */
+ cp = call_path__findnew(cpr, parent, from_al->sym, sample->ip,
+ ts->kernel_start);
+ if (!cp)
+ return -ENOMEM;
+
+ err = thread_stack__push_cp(ts, sample->addr, sample->time, ref, cp,
+ true);
+ if (err)
+ return err;
+
+ return thread_stack__pop_cp(thread, ts, sample->addr, sample->time, ref,
+ to_al->sym);
+}
+
+static int thread_stack__trace_begin(struct thread *thread,
+ struct thread_stack *ts, u64 timestamp,
+ u64 ref)
+{
+ struct thread_stack_entry *tse;
+ int err;
+
+ if (!ts->cnt)
+ return 0;
+
+ /* Pop trace end */
+ tse = &ts->stack[ts->cnt - 1];
+ if (tse->cp->sym == NULL && tse->cp->ip == 0) {
+ err = thread_stack__call_return(thread, ts, --ts->cnt,
+ timestamp, ref, false);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static int thread_stack__trace_end(struct thread_stack *ts,
+ struct perf_sample *sample, u64 ref)
+{
+ struct call_path_root *cpr = ts->crp->cpr;
+ struct call_path *cp;
+ u64 ret_addr;
+
+ /* No point having 'trace end' on the bottom of the stack */
+ if (!ts->cnt || (ts->cnt == 1 && ts->stack[0].ref == ref))
+ return 0;
+
+ cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp, NULL, 0,
+ ts->kernel_start);
+ if (!cp)
+ return -ENOMEM;
+
+ ret_addr = sample->ip + sample->insn_len;
+
+ return thread_stack__push_cp(ts, ret_addr, sample->time, ref, cp,
+ false);
+}
+
+int thread_stack__process(struct thread *thread, struct comm *comm,
+ struct perf_sample *sample,
+ struct addr_location *from_al,
+ struct addr_location *to_al, u64 ref,
+ struct call_return_processor *crp)
+{
+ struct thread_stack *ts = thread->ts;
+ int err = 0;
+
+ if (ts) {
+ if (!ts->crp) {
+ /* Supersede thread_stack__event() */
+ thread_stack__free(thread);
+ thread->ts = thread_stack__new(thread, crp);
+ if (!thread->ts)
+ return -ENOMEM;
+ ts = thread->ts;
+ ts->comm = comm;
+ }
+ } else {
+ thread->ts = thread_stack__new(thread, crp);
+ if (!thread->ts)
+ return -ENOMEM;
+ ts = thread->ts;
+ ts->comm = comm;
+ }
+
+ /* Flush stack on exec */
+ if (ts->comm != comm && thread->pid_ == thread->tid) {
+ err = thread_stack__flush(thread, ts);
+ if (err)
+ return err;
+ ts->comm = comm;
+ }
+
+ /* If the stack is empty, put the current symbol on the stack */
+ if (!ts->cnt) {
+ err = thread_stack__bottom(thread, ts, sample, from_al, to_al,
+ ref);
+ if (err)
+ return err;
+ }
+
+ ts->branch_count += 1;
+ ts->last_time = sample->time;
+
+ if (sample->flags & PERF_IP_FLAG_CALL) {
+ struct call_path_root *cpr = ts->crp->cpr;
+ struct call_path *cp;
+ u64 ret_addr;
+
+ if (!sample->ip || !sample->addr)
+ return 0;
+
+ ret_addr = sample->ip + sample->insn_len;
+ if (ret_addr == sample->addr)
+ return 0; /* Zero-length calls are excluded */
+
+ cp = call_path__findnew(cpr, ts->stack[ts->cnt - 1].cp,
+ to_al->sym, sample->addr,
+ ts->kernel_start);
+ if (!cp)
+ return -ENOMEM;
+ err = thread_stack__push_cp(ts, ret_addr, sample->time, ref,
+ cp, false);
+ } else if (sample->flags & PERF_IP_FLAG_RETURN) {
+ if (!sample->ip || !sample->addr)
+ return 0;
+
+ err = thread_stack__pop_cp(thread, ts, sample->addr,
+ sample->time, ref, from_al->sym);
+ if (err) {
+ if (err < 0)
+ return err;
+ err = thread_stack__no_call_return(thread, ts, sample,
+ from_al, to_al, ref);
+ }
+ } else if (sample->flags & PERF_IP_FLAG_TRACE_BEGIN) {
+ err = thread_stack__trace_begin(thread, ts, sample->time, ref);
+ } else if (sample->flags & PERF_IP_FLAG_TRACE_END) {
+ err = thread_stack__trace_end(ts, sample, ref);
+ }
+
+ return err;
+}
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index 7c41579..b843bbe 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -19,14 +19,93 @@
#include <sys/types.h>
#include <linux/types.h>
+#include <linux/rbtree.h>
struct thread;
+struct comm;
struct ip_callchain;
+struct symbol;
+struct dso;
+struct call_return_processor;
+struct comm;
+struct perf_sample;
+struct addr_location;
+
+/*
+ * Call/Return flags.
+ *
+ * CALL_RETURN_NO_CALL: 'return' but no matching 'call'
+ * CALL_RETURN_NO_RETURN: 'call' but no matching 'return'
+ */
+enum {
+ CALL_RETURN_NO_CALL = 1 << 0,
+ CALL_RETURN_NO_RETURN = 1 << 1,
+};
+
+/**
+ * struct call_return - paired call/return information.
+ * @thread: thread in which call/return occurred
+ * @comm: comm in which call/return occurred
+ * @cp: call path
+ * @call_time: timestamp of call (if known)
+ * @return_time: timestamp of return (if known)
+ * @branch_count: number of branches seen between call and return
+ * @call_ref: external reference to 'call' sample (e.g. db_id)
+ * @return_ref: external reference to 'return' sample (e.g. db_id)
+ * @db_id: id used for db-export
+ * @flags: Call/Return flags
+ */
+struct call_return {
+ struct thread *thread;
+ struct comm *comm;
+ struct call_path *cp;
+ u64 call_time;
+ u64 return_time;
+ u64 branch_count;
+ u64 call_ref;
+ u64 return_ref;
+ u64 db_id;
+ u32 flags;
+};
+
+/**
+ * struct call_path - node in list of calls leading to a function call.
+ * @parent: call path to the parent function call
+ * @sym: symbol of function called
+ * @ip: only if sym is null, the ip of the function
+ * @db_id: id used for db-export
+ * @in_kernel: whether function is a in the kernel
+ * @rb_node: node in parent's tree of called functions
+ * @children: tree of call paths of functions called
+ *
+ * In combination with the call_return structure, the call_path structure
+ * defines a context-sensitve call-graph.
+ */
+struct call_path {
+ struct call_path *parent;
+ struct symbol *sym;
+ u64 ip;
+ u64 db_id;
+ bool in_kernel;
+ struct rb_node rb_node;
+ struct rb_root children;
+};
int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
u64 to_ip, u16 insn_len, u64 trace_nr);
+void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
size_t sz, u64 ip);
void thread_stack__free(struct thread *thread);
+struct call_return_processor *
+call_return_processor__new(int (*process)(struct call_return *cr, void *data),
+ void *data);
+void call_return_processor__free(struct call_return_processor *crp);
+int thread_stack__process(struct thread *thread, struct comm *comm,
+ struct perf_sample *sample,
+ struct addr_location *from_al,
+ struct addr_location *to_al, u64 ref,
+ struct call_return_processor *crp);
+
#endif
^ permalink raw reply related [flat|nested] 18+ messages in thread
* [PATCH 5/7] perf tools: Add call information to the database export API
2014-10-30 14:09 [PATCH 0/7] perf tools: Add a thread stack for synthesizing call chains Adrian Hunter
` (3 preceding siblings ...)
2014-10-30 14:09 ` [PATCH 4/7] perf tools: Enhance the thread stack to output call/return data Adrian Hunter
@ 2014-10-30 14:09 ` Adrian Hunter
2014-11-07 5:29 ` [tip:perf/core] " tip-bot for Adrian Hunter
2014-10-30 14:09 ` [PATCH 6/7] perf tools: Add call information to Python export Adrian Hunter
` (2 subsequent siblings)
7 siblings, 1 reply; 18+ messages in thread
From: Adrian Hunter @ 2014-10-30 14:09 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Paul Mackerras, Stephane Eranian
Make it possible for the database export API to use the
enhanced thread stack and export detailed information
about paired calls and returns.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/db-export.c | 52 ++++++++++++++++++++++++++++++++++++++++++++-
tools/perf/util/db-export.h | 12 +++++++++++
2 files changed, 63 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index bccb831..017ecbb 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -21,6 +21,7 @@
#include "comm.h"
#include "symbol.h"
#include "event.h"
+#include "thread-stack.h"
#include "db-export.h"
int db_export__init(struct db_export *dbe)
@@ -29,8 +30,10 @@ int db_export__init(struct db_export *dbe)
return 0;
}
-void db_export__exit(struct db_export *dbe __maybe_unused)
+void db_export__exit(struct db_export *dbe)
{
+ call_return_processor__free(dbe->crp);
+ dbe->crp = NULL;
}
int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel)
@@ -270,6 +273,13 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
&es.addr_sym_db_id, &es.addr_offset);
if (err)
return err;
+ if (dbe->crp) {
+ err = thread_stack__process(thread, comm, sample, al,
+ &addr_al, es.db_id,
+ dbe->crp);
+ if (err)
+ return err;
+ }
}
if (dbe->export_sample)
@@ -316,3 +326,43 @@ int db_export__branch_types(struct db_export *dbe)
}
return err;
}
+
+int db_export__call_path(struct db_export *dbe, struct call_path *cp)
+{
+ int err;
+
+ if (cp->db_id)
+ return 0;
+
+ if (cp->parent) {
+ err = db_export__call_path(dbe, cp->parent);
+ if (err)
+ return err;
+ }
+
+ cp->db_id = ++dbe->call_path_last_db_id;
+
+ if (dbe->export_call_path)
+ return dbe->export_call_path(dbe, cp);
+
+ return 0;
+}
+
+int db_export__call_return(struct db_export *dbe, struct call_return *cr)
+{
+ int err;
+
+ if (cr->db_id)
+ return 0;
+
+ err = db_export__call_path(dbe, cr->cp);
+ if (err)
+ return err;
+
+ cr->db_id = ++dbe->call_return_last_db_id;
+
+ if (dbe->export_call_return)
+ return dbe->export_call_return(dbe, cr);
+
+ return 0;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index e4baa45..dd5ac2a 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -25,6 +25,9 @@ struct comm;
struct dso;
struct perf_sample;
struct addr_location;
+struct call_return_processor;
+struct call_path;
+struct call_return;
struct export_sample {
union perf_event *event;
@@ -57,6 +60,10 @@ struct db_export {
int (*export_branch_type)(struct db_export *dbe, u32 branch_type,
const char *name);
int (*export_sample)(struct db_export *dbe, struct export_sample *es);
+ int (*export_call_path)(struct db_export *dbe, struct call_path *cp);
+ int (*export_call_return)(struct db_export *dbe,
+ struct call_return *cr);
+ struct call_return_processor *crp;
u64 evsel_last_db_id;
u64 machine_last_db_id;
u64 thread_last_db_id;
@@ -65,6 +72,8 @@ struct db_export {
u64 dso_last_db_id;
u64 symbol_last_db_id;
u64 sample_last_db_id;
+ u64 call_path_last_db_id;
+ u64 call_return_last_db_id;
};
int db_export__init(struct db_export *dbe);
@@ -89,4 +98,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
int db_export__branch_types(struct db_export *dbe);
+int db_export__call_path(struct db_export *dbe, struct call_path *cp);
+int db_export__call_return(struct db_export *dbe, struct call_return *cr);
+
#endif
--
1.9.1
^ permalink raw reply related [flat|nested] 18+ messages in thread* [tip:perf/core] perf tools: Add call information to the database export API
2014-10-30 14:09 ` [PATCH 5/7] perf tools: Add call information to the database export API Adrian Hunter
@ 2014-11-07 5:29 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 18+ messages in thread
From: tip-bot for Adrian Hunter @ 2014-11-07 5:29 UTC (permalink / raw)
To: linux-tip-commits
Cc: peterz, tglx, mingo, fweisbec, eranian, acme, adrian.hunter, hpa,
paulus, namhyung, jolsa, linux-kernel, dsahern
Commit-ID: 88f50d602f500d206f2f5a9a9751dd45f2d97739
Gitweb: http://git.kernel.org/tip/88f50d602f500d206f2f5a9a9751dd45f2d97739
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 30 Oct 2014 16:09:46 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 3 Nov 2014 18:09:33 -0300
perf tools: Add call information to the database export API
Make it possible for the database export API to use the enhanced thread
stack and export detailed information about paired calls and returns.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1414678188-14946-6-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/db-export.c | 52 ++++++++++++++++++++++++++++++++++++++++++++-
tools/perf/util/db-export.h | 12 +++++++++++
2 files changed, 63 insertions(+), 1 deletion(-)
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index bccb831..017ecbb 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -21,6 +21,7 @@
#include "comm.h"
#include "symbol.h"
#include "event.h"
+#include "thread-stack.h"
#include "db-export.h"
int db_export__init(struct db_export *dbe)
@@ -29,8 +30,10 @@ int db_export__init(struct db_export *dbe)
return 0;
}
-void db_export__exit(struct db_export *dbe __maybe_unused)
+void db_export__exit(struct db_export *dbe)
{
+ call_return_processor__free(dbe->crp);
+ dbe->crp = NULL;
}
int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel)
@@ -270,6 +273,13 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
&es.addr_sym_db_id, &es.addr_offset);
if (err)
return err;
+ if (dbe->crp) {
+ err = thread_stack__process(thread, comm, sample, al,
+ &addr_al, es.db_id,
+ dbe->crp);
+ if (err)
+ return err;
+ }
}
if (dbe->export_sample)
@@ -316,3 +326,43 @@ int db_export__branch_types(struct db_export *dbe)
}
return err;
}
+
+int db_export__call_path(struct db_export *dbe, struct call_path *cp)
+{
+ int err;
+
+ if (cp->db_id)
+ return 0;
+
+ if (cp->parent) {
+ err = db_export__call_path(dbe, cp->parent);
+ if (err)
+ return err;
+ }
+
+ cp->db_id = ++dbe->call_path_last_db_id;
+
+ if (dbe->export_call_path)
+ return dbe->export_call_path(dbe, cp);
+
+ return 0;
+}
+
+int db_export__call_return(struct db_export *dbe, struct call_return *cr)
+{
+ int err;
+
+ if (cr->db_id)
+ return 0;
+
+ err = db_export__call_path(dbe, cr->cp);
+ if (err)
+ return err;
+
+ cr->db_id = ++dbe->call_return_last_db_id;
+
+ if (dbe->export_call_return)
+ return dbe->export_call_return(dbe, cr);
+
+ return 0;
+}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index e4baa45..dd5ac2a 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -25,6 +25,9 @@ struct comm;
struct dso;
struct perf_sample;
struct addr_location;
+struct call_return_processor;
+struct call_path;
+struct call_return;
struct export_sample {
union perf_event *event;
@@ -57,6 +60,10 @@ struct db_export {
int (*export_branch_type)(struct db_export *dbe, u32 branch_type,
const char *name);
int (*export_sample)(struct db_export *dbe, struct export_sample *es);
+ int (*export_call_path)(struct db_export *dbe, struct call_path *cp);
+ int (*export_call_return)(struct db_export *dbe,
+ struct call_return *cr);
+ struct call_return_processor *crp;
u64 evsel_last_db_id;
u64 machine_last_db_id;
u64 thread_last_db_id;
@@ -65,6 +72,8 @@ struct db_export {
u64 dso_last_db_id;
u64 symbol_last_db_id;
u64 sample_last_db_id;
+ u64 call_path_last_db_id;
+ u64 call_return_last_db_id;
};
int db_export__init(struct db_export *dbe);
@@ -89,4 +98,7 @@ int db_export__sample(struct db_export *dbe, union perf_event *event,
int db_export__branch_types(struct db_export *dbe);
+int db_export__call_path(struct db_export *dbe, struct call_path *cp);
+int db_export__call_return(struct db_export *dbe, struct call_return *cr);
+
#endif
^ permalink raw reply related [flat|nested] 18+ messages in thread
* [PATCH 6/7] perf tools: Add call information to Python export
2014-10-30 14:09 [PATCH 0/7] perf tools: Add a thread stack for synthesizing call chains Adrian Hunter
` (4 preceding siblings ...)
2014-10-30 14:09 ` [PATCH 5/7] perf tools: Add call information to the database export API Adrian Hunter
@ 2014-10-30 14:09 ` Adrian Hunter
2014-11-07 5:29 ` [tip:perf/core] " tip-bot for Adrian Hunter
2014-10-30 14:09 ` [PATCH 7/7] perf tools: Defer export of comms that were not 'set' Adrian Hunter
2014-11-03 21:13 ` [PATCH 0/7] perf tools: Add a thread stack for synthesizing call chains Arnaldo Carvalho de Melo
7 siblings, 1 reply; 18+ messages in thread
From: Adrian Hunter @ 2014-10-30 14:09 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Paul Mackerras, Stephane Eranian
Add the ability to export detailed information about
paired calls and returns to Python db export and
the export-to-postgresql.py script.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
.../scripts/python/bin/export-to-postgresql-report | 15 ++--
tools/perf/scripts/python/export-to-postgresql.py | 66 ++++++++++++++++-
.../util/scripting-engines/trace-event-python.c | 84 +++++++++++++++++++++-
3 files changed, 158 insertions(+), 7 deletions(-)
diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-report b/tools/perf/scripts/python/bin/export-to-postgresql-report
index a8fdd15..cd335b6 100644
--- a/tools/perf/scripts/python/bin/export-to-postgresql-report
+++ b/tools/perf/scripts/python/bin/export-to-postgresql-report
@@ -1,6 +1,6 @@
#!/bin/bash
# description: export perf data to a postgresql database
-# args: [database name] [columns]
+# args: [database name] [columns] [calls]
n_args=0
for i in "$@"
do
@@ -9,11 +9,16 @@ do
fi
n_args=$(( $n_args + 1 ))
done
-if [ "$n_args" -gt 2 ] ; then
- echo "usage: export-to-postgresql-report [database name] [columns]"
+if [ "$n_args" -gt 3 ] ; then
+ echo "usage: export-to-postgresql-report [database name] [columns] [calls]"
exit
fi
-if [ "$n_args" -gt 1 ] ; then
+if [ "$n_args" -gt 2 ] ; then
+ dbname=$1
+ columns=$2
+ calls=$3
+ shift 3
+elif [ "$n_args" -gt 1 ] ; then
dbname=$1
columns=$2
shift 2
@@ -21,4 +26,4 @@ elif [ "$n_args" -gt 0 ] ; then
dbname=$1
shift
fi
-perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns $calls
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index bb79aec..4cdafd8 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -40,10 +40,12 @@ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
#from Core import *
perf_db_export_mode = True
+perf_db_export_calls = False
def usage():
- print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>]"
+ print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>]"
print >> sys.stderr, "where: columns 'all' or 'branches'"
+ print >> sys.stderr, " calls 'calls' => create calls table"
raise Exception("Too few arguments")
if (len(sys.argv) < 2):
@@ -61,6 +63,12 @@ if columns not in ("all", "branches"):
branches = (columns == "branches")
+if (len(sys.argv) >= 4):
+ if (sys.argv[3] == "calls"):
+ perf_db_export_calls = True
+ else:
+ usage()
+
output_dir_name = os.getcwd() + "/" + dbname + "-perf-data"
os.mkdir(output_dir_name)
@@ -170,6 +178,25 @@ else:
'branch_type integer,'
'in_tx boolean)')
+if perf_db_export_calls:
+ do_query(query, 'CREATE TABLE call_paths ('
+ 'id bigint NOT NULL,'
+ 'parent_id bigint,'
+ 'symbol_id bigint,'
+ 'ip bigint)')
+ do_query(query, 'CREATE TABLE calls ('
+ 'id bigint NOT NULL,'
+ 'thread_id bigint,'
+ 'comm_id bigint,'
+ 'call_path_id bigint,'
+ 'call_time bigint,'
+ 'return_time bigint,'
+ 'branch_count bigint,'
+ 'call_id bigint,'
+ 'return_id bigint,'
+ 'parent_call_path_id bigint,'
+ 'flags integer)')
+
do_query(query, 'CREATE VIEW samples_view AS '
'SELECT '
'id,'
@@ -246,6 +273,9 @@ dso_file = open_output_file("dso_table.bin")
symbol_file = open_output_file("symbol_table.bin")
branch_type_file = open_output_file("branch_type_table.bin")
sample_file = open_output_file("sample_table.bin")
+if perf_db_export_calls:
+ call_path_file = open_output_file("call_path_table.bin")
+ call_file = open_output_file("call_table.bin")
def trace_begin():
print datetime.datetime.today(), "Writing to intermediate files..."
@@ -256,6 +286,9 @@ def trace_begin():
comm_table(0, "unknown")
dso_table(0, 0, "unknown", "unknown", "")
symbol_table(0, 0, 0, 0, 0, "unknown")
+ sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+ if perf_db_export_calls:
+ call_path_table(0, 0, 0, 0)
unhandled_count = 0
@@ -270,6 +303,9 @@ def trace_end():
copy_output_file(symbol_file, "symbols")
copy_output_file(branch_type_file, "branch_types")
copy_output_file(sample_file, "samples")
+ if perf_db_export_calls:
+ copy_output_file(call_path_file, "call_paths")
+ copy_output_file(call_file, "calls")
print datetime.datetime.today(), "Removing intermediate files..."
remove_output_file(evsel_file)
@@ -281,6 +317,9 @@ def trace_end():
remove_output_file(symbol_file)
remove_output_file(branch_type_file)
remove_output_file(sample_file)
+ if perf_db_export_calls:
+ remove_output_file(call_path_file)
+ remove_output_file(call_file)
os.rmdir(output_dir_name)
print datetime.datetime.today(), "Adding primary keys"
do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)')
@@ -292,6 +331,9 @@ def trace_end():
do_query(query, 'ALTER TABLE symbols ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE branch_types ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE samples ADD PRIMARY KEY (id)')
+ if perf_db_export_calls:
+ do_query(query, 'ALTER TABLE call_paths ADD PRIMARY KEY (id)')
+ do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)')
print datetime.datetime.today(), "Adding foreign keys"
do_query(query, 'ALTER TABLE threads '
@@ -313,6 +355,18 @@ def trace_end():
'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id),'
'ADD CONSTRAINT todsofk FOREIGN KEY (to_dso_id) REFERENCES dsos (id),'
'ADD CONSTRAINT tosymbolfk FOREIGN KEY (to_symbol_id) REFERENCES symbols (id)')
+ if perf_db_export_calls:
+ do_query(query, 'ALTER TABLE call_paths '
+ 'ADD CONSTRAINT parentfk FOREIGN KEY (parent_id) REFERENCES call_paths (id),'
+ 'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id)')
+ do_query(query, 'ALTER TABLE calls '
+ 'ADD CONSTRAINT threadfk FOREIGN KEY (thread_id) REFERENCES threads (id),'
+ 'ADD CONSTRAINT commfk FOREIGN KEY (comm_id) REFERENCES comms (id),'
+ 'ADD CONSTRAINT call_pathfk FOREIGN KEY (call_path_id) REFERENCES call_paths (id),'
+ 'ADD CONSTRAINT callfk FOREIGN KEY (call_id) REFERENCES samples (id),'
+ 'ADD CONSTRAINT returnfk FOREIGN KEY (return_id) REFERENCES samples (id),'
+ 'ADD CONSTRAINT parent_call_pathfk FOREIGN KEY (parent_call_path_id) REFERENCES call_paths (id)')
+ do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
if (unhandled_count):
print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
@@ -378,3 +432,13 @@ def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, sy
else:
value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx)
sample_file.write(value)
+
+def call_path_table(cp_id, parent_id, symbol_id, ip, *x):
+ fmt = "!hiqiqiqiq"
+ value = struct.pack(fmt, 4, 8, cp_id, 8, parent_id, 8, symbol_id, 8, ip)
+ call_path_file.write(value)
+
+def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, *x):
+ fmt = "!hiqiqiqiqiqiqiqiqiqiqii"
+ value = struct.pack(fmt, 11, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags)
+ call_file.write(value)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index f3ca779..cb1d960 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -37,6 +37,7 @@
#include "../comm.h"
#include "../machine.h"
#include "../db-export.h"
+#include "../thread-stack.h"
#include "../trace-event.h"
#include "../machine.h"
@@ -68,6 +69,8 @@ struct tables {
PyObject *symbol_handler;
PyObject *branch_type_handler;
PyObject *sample_handler;
+ PyObject *call_path_handler;
+ PyObject *call_return_handler;
bool db_export_mode;
};
@@ -720,6 +723,64 @@ static int python_export_sample(struct db_export *dbe,
return 0;
}
+static int python_export_call_path(struct db_export *dbe, struct call_path *cp)
+{
+ struct tables *tables = container_of(dbe, struct tables, dbe);
+ PyObject *t;
+ u64 parent_db_id, sym_db_id;
+
+ parent_db_id = cp->parent ? cp->parent->db_id : 0;
+ sym_db_id = cp->sym ? *(u64 *)symbol__priv(cp->sym) : 0;
+
+ t = tuple_new(4);
+
+ tuple_set_u64(t, 0, cp->db_id);
+ tuple_set_u64(t, 1, parent_db_id);
+ tuple_set_u64(t, 2, sym_db_id);
+ tuple_set_u64(t, 3, cp->ip);
+
+ call_object(tables->call_path_handler, t, "call_path_table");
+
+ Py_DECREF(t);
+
+ return 0;
+}
+
+static int python_export_call_return(struct db_export *dbe,
+ struct call_return *cr)
+{
+ struct tables *tables = container_of(dbe, struct tables, dbe);
+ u64 comm_db_id = cr->comm ? cr->comm->db_id : 0;
+ PyObject *t;
+
+ t = tuple_new(11);
+
+ tuple_set_u64(t, 0, cr->db_id);
+ tuple_set_u64(t, 1, cr->thread->db_id);
+ tuple_set_u64(t, 2, comm_db_id);
+ tuple_set_u64(t, 3, cr->cp->db_id);
+ tuple_set_u64(t, 4, cr->call_time);
+ tuple_set_u64(t, 5, cr->return_time);
+ tuple_set_u64(t, 6, cr->branch_count);
+ tuple_set_u64(t, 7, cr->call_ref);
+ tuple_set_u64(t, 8, cr->return_ref);
+ tuple_set_u64(t, 9, cr->cp->parent->db_id);
+ tuple_set_s32(t, 10, cr->flags);
+
+ call_object(tables->call_return_handler, t, "call_return_table");
+
+ Py_DECREF(t);
+
+ return 0;
+}
+
+static int python_process_call_return(struct call_return *cr, void *data)
+{
+ struct db_export *dbe = data;
+
+ return db_export__call_return(dbe, cr);
+}
+
static void python_process_general_event(struct perf_sample *sample,
struct perf_evsel *evsel,
struct thread *thread,
@@ -852,7 +913,9 @@ error:
static void set_table_handlers(struct tables *tables)
{
const char *perf_db_export_mode = "perf_db_export_mode";
- PyObject *db_export_mode;
+ const char *perf_db_export_calls = "perf_db_export_calls";
+ PyObject *db_export_mode, *db_export_calls;
+ bool export_calls = false;
int ret;
memset(tables, 0, sizeof(struct tables));
@@ -869,6 +932,23 @@ static void set_table_handlers(struct tables *tables)
if (!ret)
return;
+ tables->dbe.crp = NULL;
+ db_export_calls = PyDict_GetItemString(main_dict, perf_db_export_calls);
+ if (db_export_calls) {
+ ret = PyObject_IsTrue(db_export_calls);
+ if (ret == -1)
+ handler_call_die(perf_db_export_calls);
+ export_calls = !!ret;
+ }
+
+ if (export_calls) {
+ tables->dbe.crp =
+ call_return_processor__new(python_process_call_return,
+ &tables->dbe);
+ if (!tables->dbe.crp)
+ Py_FatalError("failed to create calls processor");
+ }
+
tables->db_export_mode = true;
/*
* Reserve per symbol space for symbol->db_id via symbol__priv()
@@ -884,6 +964,8 @@ static void set_table_handlers(struct tables *tables)
SET_TABLE_HANDLER(symbol);
SET_TABLE_HANDLER(branch_type);
SET_TABLE_HANDLER(sample);
+ SET_TABLE_HANDLER(call_path);
+ SET_TABLE_HANDLER(call_return);
}
/*
--
1.9.1
^ permalink raw reply related [flat|nested] 18+ messages in thread* [tip:perf/core] perf tools: Add call information to Python export
2014-10-30 14:09 ` [PATCH 6/7] perf tools: Add call information to Python export Adrian Hunter
@ 2014-11-07 5:29 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 18+ messages in thread
From: tip-bot for Adrian Hunter @ 2014-11-07 5:29 UTC (permalink / raw)
To: linux-tip-commits
Cc: jolsa, linux-kernel, hpa, peterz, mingo, paulus, acme,
adrian.hunter, fweisbec, dsahern, eranian, namhyung, tglx
Commit-ID: 6a70307ddcd9999598c399d55dc44c07816a575f
Gitweb: http://git.kernel.org/tip/6a70307ddcd9999598c399d55dc44c07816a575f
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 30 Oct 2014 16:09:47 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 3 Nov 2014 18:10:06 -0300
perf tools: Add call information to Python export
Add the ability to export detailed information about paired calls and
returns to Python db export and the export-to-postgresql.py script.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1414678188-14946-7-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
.../scripts/python/bin/export-to-postgresql-report | 15 ++--
tools/perf/scripts/python/export-to-postgresql.py | 66 ++++++++++++++++-
.../util/scripting-engines/trace-event-python.c | 84 +++++++++++++++++++++-
3 files changed, 158 insertions(+), 7 deletions(-)
diff --git a/tools/perf/scripts/python/bin/export-to-postgresql-report b/tools/perf/scripts/python/bin/export-to-postgresql-report
index a8fdd15..cd335b6 100644
--- a/tools/perf/scripts/python/bin/export-to-postgresql-report
+++ b/tools/perf/scripts/python/bin/export-to-postgresql-report
@@ -1,6 +1,6 @@
#!/bin/bash
# description: export perf data to a postgresql database
-# args: [database name] [columns]
+# args: [database name] [columns] [calls]
n_args=0
for i in "$@"
do
@@ -9,11 +9,16 @@ do
fi
n_args=$(( $n_args + 1 ))
done
-if [ "$n_args" -gt 2 ] ; then
- echo "usage: export-to-postgresql-report [database name] [columns]"
+if [ "$n_args" -gt 3 ] ; then
+ echo "usage: export-to-postgresql-report [database name] [columns] [calls]"
exit
fi
-if [ "$n_args" -gt 1 ] ; then
+if [ "$n_args" -gt 2 ] ; then
+ dbname=$1
+ columns=$2
+ calls=$3
+ shift 3
+elif [ "$n_args" -gt 1 ] ; then
dbname=$1
columns=$2
shift 2
@@ -21,4 +26,4 @@ elif [ "$n_args" -gt 0 ] ; then
dbname=$1
shift
fi
-perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns
+perf script $@ -s "$PERF_EXEC_PATH"/scripts/python/export-to-postgresql.py $dbname $columns $calls
diff --git a/tools/perf/scripts/python/export-to-postgresql.py b/tools/perf/scripts/python/export-to-postgresql.py
index bb79aec..4cdafd8 100644
--- a/tools/perf/scripts/python/export-to-postgresql.py
+++ b/tools/perf/scripts/python/export-to-postgresql.py
@@ -40,10 +40,12 @@ sys.path.append(os.environ['PERF_EXEC_PATH'] + \
#from Core import *
perf_db_export_mode = True
+perf_db_export_calls = False
def usage():
- print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>]"
+ print >> sys.stderr, "Usage is: export-to-postgresql.py <database name> [<columns>] [<calls>]"
print >> sys.stderr, "where: columns 'all' or 'branches'"
+ print >> sys.stderr, " calls 'calls' => create calls table"
raise Exception("Too few arguments")
if (len(sys.argv) < 2):
@@ -61,6 +63,12 @@ if columns not in ("all", "branches"):
branches = (columns == "branches")
+if (len(sys.argv) >= 4):
+ if (sys.argv[3] == "calls"):
+ perf_db_export_calls = True
+ else:
+ usage()
+
output_dir_name = os.getcwd() + "/" + dbname + "-perf-data"
os.mkdir(output_dir_name)
@@ -170,6 +178,25 @@ else:
'branch_type integer,'
'in_tx boolean)')
+if perf_db_export_calls:
+ do_query(query, 'CREATE TABLE call_paths ('
+ 'id bigint NOT NULL,'
+ 'parent_id bigint,'
+ 'symbol_id bigint,'
+ 'ip bigint)')
+ do_query(query, 'CREATE TABLE calls ('
+ 'id bigint NOT NULL,'
+ 'thread_id bigint,'
+ 'comm_id bigint,'
+ 'call_path_id bigint,'
+ 'call_time bigint,'
+ 'return_time bigint,'
+ 'branch_count bigint,'
+ 'call_id bigint,'
+ 'return_id bigint,'
+ 'parent_call_path_id bigint,'
+ 'flags integer)')
+
do_query(query, 'CREATE VIEW samples_view AS '
'SELECT '
'id,'
@@ -246,6 +273,9 @@ dso_file = open_output_file("dso_table.bin")
symbol_file = open_output_file("symbol_table.bin")
branch_type_file = open_output_file("branch_type_table.bin")
sample_file = open_output_file("sample_table.bin")
+if perf_db_export_calls:
+ call_path_file = open_output_file("call_path_table.bin")
+ call_file = open_output_file("call_table.bin")
def trace_begin():
print datetime.datetime.today(), "Writing to intermediate files..."
@@ -256,6 +286,9 @@ def trace_begin():
comm_table(0, "unknown")
dso_table(0, 0, "unknown", "unknown", "")
symbol_table(0, 0, 0, 0, 0, "unknown")
+ sample_table(0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0)
+ if perf_db_export_calls:
+ call_path_table(0, 0, 0, 0)
unhandled_count = 0
@@ -270,6 +303,9 @@ def trace_end():
copy_output_file(symbol_file, "symbols")
copy_output_file(branch_type_file, "branch_types")
copy_output_file(sample_file, "samples")
+ if perf_db_export_calls:
+ copy_output_file(call_path_file, "call_paths")
+ copy_output_file(call_file, "calls")
print datetime.datetime.today(), "Removing intermediate files..."
remove_output_file(evsel_file)
@@ -281,6 +317,9 @@ def trace_end():
remove_output_file(symbol_file)
remove_output_file(branch_type_file)
remove_output_file(sample_file)
+ if perf_db_export_calls:
+ remove_output_file(call_path_file)
+ remove_output_file(call_file)
os.rmdir(output_dir_name)
print datetime.datetime.today(), "Adding primary keys"
do_query(query, 'ALTER TABLE selected_events ADD PRIMARY KEY (id)')
@@ -292,6 +331,9 @@ def trace_end():
do_query(query, 'ALTER TABLE symbols ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE branch_types ADD PRIMARY KEY (id)')
do_query(query, 'ALTER TABLE samples ADD PRIMARY KEY (id)')
+ if perf_db_export_calls:
+ do_query(query, 'ALTER TABLE call_paths ADD PRIMARY KEY (id)')
+ do_query(query, 'ALTER TABLE calls ADD PRIMARY KEY (id)')
print datetime.datetime.today(), "Adding foreign keys"
do_query(query, 'ALTER TABLE threads '
@@ -313,6 +355,18 @@ def trace_end():
'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id),'
'ADD CONSTRAINT todsofk FOREIGN KEY (to_dso_id) REFERENCES dsos (id),'
'ADD CONSTRAINT tosymbolfk FOREIGN KEY (to_symbol_id) REFERENCES symbols (id)')
+ if perf_db_export_calls:
+ do_query(query, 'ALTER TABLE call_paths '
+ 'ADD CONSTRAINT parentfk FOREIGN KEY (parent_id) REFERENCES call_paths (id),'
+ 'ADD CONSTRAINT symbolfk FOREIGN KEY (symbol_id) REFERENCES symbols (id)')
+ do_query(query, 'ALTER TABLE calls '
+ 'ADD CONSTRAINT threadfk FOREIGN KEY (thread_id) REFERENCES threads (id),'
+ 'ADD CONSTRAINT commfk FOREIGN KEY (comm_id) REFERENCES comms (id),'
+ 'ADD CONSTRAINT call_pathfk FOREIGN KEY (call_path_id) REFERENCES call_paths (id),'
+ 'ADD CONSTRAINT callfk FOREIGN KEY (call_id) REFERENCES samples (id),'
+ 'ADD CONSTRAINT returnfk FOREIGN KEY (return_id) REFERENCES samples (id),'
+ 'ADD CONSTRAINT parent_call_pathfk FOREIGN KEY (parent_call_path_id) REFERENCES call_paths (id)')
+ do_query(query, 'CREATE INDEX pcpid_idx ON calls (parent_call_path_id)')
if (unhandled_count):
print datetime.datetime.today(), "Warning: ", unhandled_count, " unhandled events"
@@ -378,3 +432,13 @@ def sample_table(sample_id, evsel_id, machine_id, thread_id, comm_id, dso_id, sy
else:
value = struct.pack("!hiqiqiqiqiqiqiqiqiqiqiiiqiqiqiqiqiqiqiqiiiB", 21, 8, sample_id, 8, evsel_id, 8, machine_id, 8, thread_id, 8, comm_id, 8, dso_id, 8, symbol_id, 8, sym_offset, 8, ip, 8, time, 4, cpu, 8, to_dso_id, 8, to_symbol_id, 8, to_sym_offset, 8, to_ip, 8, period, 8, weight, 8, transaction, 8, data_src, 4, branch_type, 1, in_tx)
sample_file.write(value)
+
+def call_path_table(cp_id, parent_id, symbol_id, ip, *x):
+ fmt = "!hiqiqiqiq"
+ value = struct.pack(fmt, 4, 8, cp_id, 8, parent_id, 8, symbol_id, 8, ip)
+ call_path_file.write(value)
+
+def call_return_table(cr_id, thread_id, comm_id, call_path_id, call_time, return_time, branch_count, call_id, return_id, parent_call_path_id, flags, *x):
+ fmt = "!hiqiqiqiqiqiqiqiqiqiqii"
+ value = struct.pack(fmt, 11, 8, cr_id, 8, thread_id, 8, comm_id, 8, call_path_id, 8, call_time, 8, return_time, 8, branch_count, 8, call_id, 8, return_id, 8, parent_call_path_id, 4, flags)
+ call_file.write(value)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index f3ca779..cb1d960 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -37,6 +37,7 @@
#include "../comm.h"
#include "../machine.h"
#include "../db-export.h"
+#include "../thread-stack.h"
#include "../trace-event.h"
#include "../machine.h"
@@ -68,6 +69,8 @@ struct tables {
PyObject *symbol_handler;
PyObject *branch_type_handler;
PyObject *sample_handler;
+ PyObject *call_path_handler;
+ PyObject *call_return_handler;
bool db_export_mode;
};
@@ -720,6 +723,64 @@ static int python_export_sample(struct db_export *dbe,
return 0;
}
+static int python_export_call_path(struct db_export *dbe, struct call_path *cp)
+{
+ struct tables *tables = container_of(dbe, struct tables, dbe);
+ PyObject *t;
+ u64 parent_db_id, sym_db_id;
+
+ parent_db_id = cp->parent ? cp->parent->db_id : 0;
+ sym_db_id = cp->sym ? *(u64 *)symbol__priv(cp->sym) : 0;
+
+ t = tuple_new(4);
+
+ tuple_set_u64(t, 0, cp->db_id);
+ tuple_set_u64(t, 1, parent_db_id);
+ tuple_set_u64(t, 2, sym_db_id);
+ tuple_set_u64(t, 3, cp->ip);
+
+ call_object(tables->call_path_handler, t, "call_path_table");
+
+ Py_DECREF(t);
+
+ return 0;
+}
+
+static int python_export_call_return(struct db_export *dbe,
+ struct call_return *cr)
+{
+ struct tables *tables = container_of(dbe, struct tables, dbe);
+ u64 comm_db_id = cr->comm ? cr->comm->db_id : 0;
+ PyObject *t;
+
+ t = tuple_new(11);
+
+ tuple_set_u64(t, 0, cr->db_id);
+ tuple_set_u64(t, 1, cr->thread->db_id);
+ tuple_set_u64(t, 2, comm_db_id);
+ tuple_set_u64(t, 3, cr->cp->db_id);
+ tuple_set_u64(t, 4, cr->call_time);
+ tuple_set_u64(t, 5, cr->return_time);
+ tuple_set_u64(t, 6, cr->branch_count);
+ tuple_set_u64(t, 7, cr->call_ref);
+ tuple_set_u64(t, 8, cr->return_ref);
+ tuple_set_u64(t, 9, cr->cp->parent->db_id);
+ tuple_set_s32(t, 10, cr->flags);
+
+ call_object(tables->call_return_handler, t, "call_return_table");
+
+ Py_DECREF(t);
+
+ return 0;
+}
+
+static int python_process_call_return(struct call_return *cr, void *data)
+{
+ struct db_export *dbe = data;
+
+ return db_export__call_return(dbe, cr);
+}
+
static void python_process_general_event(struct perf_sample *sample,
struct perf_evsel *evsel,
struct thread *thread,
@@ -852,7 +913,9 @@ error:
static void set_table_handlers(struct tables *tables)
{
const char *perf_db_export_mode = "perf_db_export_mode";
- PyObject *db_export_mode;
+ const char *perf_db_export_calls = "perf_db_export_calls";
+ PyObject *db_export_mode, *db_export_calls;
+ bool export_calls = false;
int ret;
memset(tables, 0, sizeof(struct tables));
@@ -869,6 +932,23 @@ static void set_table_handlers(struct tables *tables)
if (!ret)
return;
+ tables->dbe.crp = NULL;
+ db_export_calls = PyDict_GetItemString(main_dict, perf_db_export_calls);
+ if (db_export_calls) {
+ ret = PyObject_IsTrue(db_export_calls);
+ if (ret == -1)
+ handler_call_die(perf_db_export_calls);
+ export_calls = !!ret;
+ }
+
+ if (export_calls) {
+ tables->dbe.crp =
+ call_return_processor__new(python_process_call_return,
+ &tables->dbe);
+ if (!tables->dbe.crp)
+ Py_FatalError("failed to create calls processor");
+ }
+
tables->db_export_mode = true;
/*
* Reserve per symbol space for symbol->db_id via symbol__priv()
@@ -884,6 +964,8 @@ static void set_table_handlers(struct tables *tables)
SET_TABLE_HANDLER(symbol);
SET_TABLE_HANDLER(branch_type);
SET_TABLE_HANDLER(sample);
+ SET_TABLE_HANDLER(call_path);
+ SET_TABLE_HANDLER(call_return);
}
/*
^ permalink raw reply related [flat|nested] 18+ messages in thread
* [PATCH 7/7] perf tools: Defer export of comms that were not 'set'
2014-10-30 14:09 [PATCH 0/7] perf tools: Add a thread stack for synthesizing call chains Adrian Hunter
` (5 preceding siblings ...)
2014-10-30 14:09 ` [PATCH 6/7] perf tools: Add call information to Python export Adrian Hunter
@ 2014-10-30 14:09 ` Adrian Hunter
2014-11-07 5:29 ` [tip:perf/core] perf tools: Defer export of comms that were not ' set' tip-bot for Adrian Hunter
2014-11-03 21:13 ` [PATCH 0/7] perf tools: Add a thread stack for synthesizing call chains Arnaldo Carvalho de Melo
7 siblings, 1 reply; 18+ messages in thread
From: Adrian Hunter @ 2014-10-30 14:09 UTC (permalink / raw)
To: Arnaldo Carvalho de Melo
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Paul Mackerras, Stephane Eranian
Tracing for a workload begins before the comm event
is seen, which results in the initial comm having a
string of the form ":<pid>" (e.g. ":12345"). In order
to export the correct string, defer the export until
the new script 'flush' callback.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
---
tools/perf/util/db-export.c | 62 +++++++++++++++++++++-
tools/perf/util/db-export.h | 3 ++
.../util/scripting-engines/trace-event-python.c | 4 +-
3 files changed, 67 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 017ecbb..c81dae3 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -21,17 +21,74 @@
#include "comm.h"
#include "symbol.h"
#include "event.h"
+#include "util.h"
#include "thread-stack.h"
#include "db-export.h"
+struct deferred_export {
+ struct list_head node;
+ struct comm *comm;
+};
+
+static int db_export__deferred(struct db_export *dbe)
+{
+ struct deferred_export *de;
+ int err;
+
+ while (!list_empty(&dbe->deferred)) {
+ de = list_entry(dbe->deferred.next, struct deferred_export,
+ node);
+ err = dbe->export_comm(dbe, de->comm);
+ list_del(&de->node);
+ free(de);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static void db_export__free_deferred(struct db_export *dbe)
+{
+ struct deferred_export *de;
+
+ while (!list_empty(&dbe->deferred)) {
+ de = list_entry(dbe->deferred.next, struct deferred_export,
+ node);
+ list_del(&de->node);
+ free(de);
+ }
+}
+
+static int db_export__defer_comm(struct db_export *dbe, struct comm *comm)
+{
+ struct deferred_export *de;
+
+ de = zalloc(sizeof(struct deferred_export));
+ if (!de)
+ return -ENOMEM;
+
+ de->comm = comm;
+ list_add_tail(&de->node, &dbe->deferred);
+
+ return 0;
+}
+
int db_export__init(struct db_export *dbe)
{
memset(dbe, 0, sizeof(struct db_export));
+ INIT_LIST_HEAD(&dbe->deferred);
return 0;
}
+int db_export__flush(struct db_export *dbe)
+{
+ return db_export__deferred(dbe);
+}
+
void db_export__exit(struct db_export *dbe)
{
+ db_export__free_deferred(dbe);
call_return_processor__free(dbe->crp);
dbe->crp = NULL;
}
@@ -115,7 +172,10 @@ int db_export__comm(struct db_export *dbe, struct comm *comm,
comm->db_id = ++dbe->comm_last_db_id;
if (dbe->export_comm) {
- err = dbe->export_comm(dbe, comm);
+ if (main_thread->comm_set)
+ err = dbe->export_comm(dbe, comm);
+ else
+ err = db_export__defer_comm(dbe, comm);
if (err)
return err;
}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index dd5ac2a..adbd22d 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -17,6 +17,7 @@
#define __PERF_DB_EXPORT_H
#include <linux/types.h>
+#include <linux/list.h>
struct perf_evsel;
struct machine;
@@ -74,9 +75,11 @@ struct db_export {
u64 sample_last_db_id;
u64 call_path_last_db_id;
u64 call_return_last_db_id;
+ struct list_head deferred;
};
int db_export__init(struct db_export *dbe);
+int db_export__flush(struct db_export *dbe);
void db_export__exit(struct db_export *dbe);
int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel);
int db_export__machine(struct db_export *dbe, struct machine *machine);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cb1d960..118bc62 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1030,7 +1030,9 @@ error:
static int python_flush_script(void)
{
- return 0;
+ struct tables *tables = &tables_global;
+
+ return db_export__flush(&tables->dbe);
}
/*
--
1.9.1
^ permalink raw reply related [flat|nested] 18+ messages in thread* [tip:perf/core] perf tools: Defer export of comms that were not ' set'
2014-10-30 14:09 ` [PATCH 7/7] perf tools: Defer export of comms that were not 'set' Adrian Hunter
@ 2014-11-07 5:29 ` tip-bot for Adrian Hunter
0 siblings, 0 replies; 18+ messages in thread
From: tip-bot for Adrian Hunter @ 2014-11-07 5:29 UTC (permalink / raw)
To: linux-tip-commits
Cc: jolsa, tglx, hpa, fweisbec, linux-kernel, dsahern, adrian.hunter,
namhyung, acme, paulus, peterz, mingo, eranian
Commit-ID: 758008b262f70be41104e4e33ba99181ac03775d
Gitweb: http://git.kernel.org/tip/758008b262f70be41104e4e33ba99181ac03775d
Author: Adrian Hunter <adrian.hunter@intel.com>
AuthorDate: Thu, 30 Oct 2014 16:09:48 +0200
Committer: Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Mon, 3 Nov 2014 18:11:59 -0300
perf tools: Defer export of comms that were not 'set'
Tracing for a workload begins before the comm event is seen, which
results in the initial comm having a string of the form ":<pid>" (e.g.
":12345").
In order to export the correct string, defer the export until the new
script 'flush' callback.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1414678188-14946-8-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
tools/perf/util/db-export.c | 62 +++++++++++++++++++++-
tools/perf/util/db-export.h | 3 ++
.../util/scripting-engines/trace-event-python.c | 4 +-
3 files changed, 67 insertions(+), 2 deletions(-)
diff --git a/tools/perf/util/db-export.c b/tools/perf/util/db-export.c
index 017ecbb..c81dae3 100644
--- a/tools/perf/util/db-export.c
+++ b/tools/perf/util/db-export.c
@@ -21,17 +21,74 @@
#include "comm.h"
#include "symbol.h"
#include "event.h"
+#include "util.h"
#include "thread-stack.h"
#include "db-export.h"
+struct deferred_export {
+ struct list_head node;
+ struct comm *comm;
+};
+
+static int db_export__deferred(struct db_export *dbe)
+{
+ struct deferred_export *de;
+ int err;
+
+ while (!list_empty(&dbe->deferred)) {
+ de = list_entry(dbe->deferred.next, struct deferred_export,
+ node);
+ err = dbe->export_comm(dbe, de->comm);
+ list_del(&de->node);
+ free(de);
+ if (err)
+ return err;
+ }
+
+ return 0;
+}
+
+static void db_export__free_deferred(struct db_export *dbe)
+{
+ struct deferred_export *de;
+
+ while (!list_empty(&dbe->deferred)) {
+ de = list_entry(dbe->deferred.next, struct deferred_export,
+ node);
+ list_del(&de->node);
+ free(de);
+ }
+}
+
+static int db_export__defer_comm(struct db_export *dbe, struct comm *comm)
+{
+ struct deferred_export *de;
+
+ de = zalloc(sizeof(struct deferred_export));
+ if (!de)
+ return -ENOMEM;
+
+ de->comm = comm;
+ list_add_tail(&de->node, &dbe->deferred);
+
+ return 0;
+}
+
int db_export__init(struct db_export *dbe)
{
memset(dbe, 0, sizeof(struct db_export));
+ INIT_LIST_HEAD(&dbe->deferred);
return 0;
}
+int db_export__flush(struct db_export *dbe)
+{
+ return db_export__deferred(dbe);
+}
+
void db_export__exit(struct db_export *dbe)
{
+ db_export__free_deferred(dbe);
call_return_processor__free(dbe->crp);
dbe->crp = NULL;
}
@@ -115,7 +172,10 @@ int db_export__comm(struct db_export *dbe, struct comm *comm,
comm->db_id = ++dbe->comm_last_db_id;
if (dbe->export_comm) {
- err = dbe->export_comm(dbe, comm);
+ if (main_thread->comm_set)
+ err = dbe->export_comm(dbe, comm);
+ else
+ err = db_export__defer_comm(dbe, comm);
if (err)
return err;
}
diff --git a/tools/perf/util/db-export.h b/tools/perf/util/db-export.h
index dd5ac2a..adbd22d 100644
--- a/tools/perf/util/db-export.h
+++ b/tools/perf/util/db-export.h
@@ -17,6 +17,7 @@
#define __PERF_DB_EXPORT_H
#include <linux/types.h>
+#include <linux/list.h>
struct perf_evsel;
struct machine;
@@ -74,9 +75,11 @@ struct db_export {
u64 sample_last_db_id;
u64 call_path_last_db_id;
u64 call_return_last_db_id;
+ struct list_head deferred;
};
int db_export__init(struct db_export *dbe);
+int db_export__flush(struct db_export *dbe);
void db_export__exit(struct db_export *dbe);
int db_export__evsel(struct db_export *dbe, struct perf_evsel *evsel);
int db_export__machine(struct db_export *dbe, struct machine *machine);
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cb1d960..118bc62 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1030,7 +1030,9 @@ error:
static int python_flush_script(void)
{
- return 0;
+ struct tables *tables = &tables_global;
+
+ return db_export__flush(&tables->dbe);
}
/*
^ permalink raw reply related [flat|nested] 18+ messages in thread
* Re: [PATCH 0/7] perf tools: Add a thread stack for synthesizing call chains
2014-10-30 14:09 [PATCH 0/7] perf tools: Add a thread stack for synthesizing call chains Adrian Hunter
` (6 preceding siblings ...)
2014-10-30 14:09 ` [PATCH 7/7] perf tools: Defer export of comms that were not 'set' Adrian Hunter
@ 2014-11-03 21:13 ` Arnaldo Carvalho de Melo
7 siblings, 0 replies; 18+ messages in thread
From: Arnaldo Carvalho de Melo @ 2014-11-03 21:13 UTC (permalink / raw)
To: Adrian Hunter
Cc: Peter Zijlstra, linux-kernel, David Ahern, Frederic Weisbecker,
Jiri Olsa, Namhyung Kim, Paul Mackerras, Stephane Eranian
Em Thu, Oct 30, 2014 at 04:09:41PM +0200, Adrian Hunter escreveu:
> Here are the thread stack patches again. Please let me
> know if you want more explanation.
>
> Changes:
>
> perf tools: Add a thread stack for synthesizing call chains
> Added some error returns
> Renamed PERF_FLAGS_ to PERF_IP_FLAGS_
>
> perf tools: Enhance the thread stack to output call/return data
> Expanded commit message
> Added more comments
>
Ok, applied the series, will run some more test on a few more distros in
KVM images and probably tomorrow will push this to Ingo.
- Arnaldo
^ permalink raw reply [flat|nested] 18+ messages in thread