From a5cdd40c9877e9aba704c020fd65d26b5cfecf18 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 16 Jul 2013 17:09:07 +0200
Subject: perf: Update perf_event_type documentation
Due to a discussion with Adrian I had a good look at the perf_event_type record
layout and found the documentation to be somewhat unclear.
Cc: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20130716150907.GL23818@dyad.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
include/uapi/linux/perf_event.h | 18 +++++++++++++++++-
1 file changed, 17 insertions(+), 1 deletion(-)
(limited to 'include/uapi/linux/perf_event.h')
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 0b1df41691e..00d8274730b 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -478,6 +478,16 @@ enum perf_event_type {
* file will be supported by older perf tools, with these new optional
* fields being ignored.
*
+ * struct sample_id {
+ * { u32 pid, tid; } && PERF_SAMPLE_TID
+ * { u64 time; } && PERF_SAMPLE_TIME
+ * { u64 id; } && PERF_SAMPLE_ID
+ * { u64 stream_id;} && PERF_SAMPLE_STREAM_ID
+ * { u32 cpu, res; } && PERF_SAMPLE_CPU
+ * } && perf_event_attr::sample_id_all
+ */
+
+ /*
* The MMAP events record the PROT_EXEC mappings so that we can
* correlate userspace IPs to code. They have the following structure:
*
@@ -498,6 +508,7 @@ enum perf_event_type {
* struct perf_event_header header;
* u64 id;
* u64 lost;
+ * struct sample_id sample_id;
* };
*/
PERF_RECORD_LOST = 2,
@@ -508,6 +519,7 @@ enum perf_event_type {
*
* u32 pid, tid;
* char comm[];
+ * struct sample_id sample_id;
* };
*/
PERF_RECORD_COMM = 3,
@@ -518,6 +530,7 @@ enum perf_event_type {
* u32 pid, ppid;
* u32 tid, ptid;
* u64 time;
+ * struct sample_id sample_id;
* };
*/
PERF_RECORD_EXIT = 4,
@@ -528,6 +541,7 @@ enum perf_event_type {
* u64 time;
* u64 id;
* u64 stream_id;
+ * struct sample_id sample_id;
* };
*/
PERF_RECORD_THROTTLE = 5,
@@ -539,6 +553,7 @@ enum perf_event_type {
* u32 pid, ppid;
* u32 tid, ptid;
* u64 time;
+ * struct sample_id sample_id;
* };
*/
PERF_RECORD_FORK = 7,
@@ -549,6 +564,7 @@ enum perf_event_type {
* u32 pid, tid;
*
* struct read_format values;
+ * struct sample_id sample_id;
* };
*/
PERF_RECORD_READ = 8,
@@ -596,7 +612,7 @@ enum perf_event_type {
* u64 dyn_size; } && PERF_SAMPLE_STACK_USER
*
* { u64 weight; } && PERF_SAMPLE_WEIGHT
- * { u64 data_src; } && PERF_SAMPLE_DATA_SRC
+ * { u64 data_src; } && PERF_SAMPLE_DATA_SRC
* };
*/
PERF_RECORD_SAMPLE = 9,
--
cgit v1.2.3-70-g09d2
From 860f085b74e9f0075de8140ed3a1e5b5e3e39aa8 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 28 Jun 2013 16:22:17 +0300
Subject: perf: Fix broken union in 'struct perf_event_mmap_page'
The capabilities bits must not be "union'ed" together.
Put them in a separate struct.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/r/1372425741-1676-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
include/uapi/linux/perf_event.h | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
(limited to 'include/uapi/linux/perf_event.h')
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 00d8274730b..0041aedf229 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -375,9 +375,11 @@ struct perf_event_mmap_page {
__u64 time_running; /* time event on cpu */
union {
__u64 capabilities;
- __u64 cap_usr_time : 1,
- cap_usr_rdpmc : 1,
- cap_____res : 62;
+ struct {
+ __u64 cap_usr_time : 1,
+ cap_usr_rdpmc : 1,
+ cap_____res : 62;
+ };
};
/*
--
cgit v1.2.3-70-g09d2
From c73deb6aecda2955716f31572516f09d930ef450 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Fri, 28 Jun 2013 16:22:18 +0300
Subject: perf/x86: Add ability to calculate TSC from perf sample timestamps
For modern CPUs, perf clock is directly related to TSC. TSC
can be calculated from perf clock and vice versa using a simple
calculation. Two of the three componenets of that calculation
are already exported in struct perf_event_mmap_page. This patch
exports the third.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1372425741-1676-3-git-send-email-adrian.hunter@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
arch/x86/include/asm/tsc.h | 1 +
arch/x86/kernel/cpu/perf_event.c | 6 ++++++
arch/x86/kernel/tsc.c | 6 ++++++
include/uapi/linux/perf_event.h | 22 ++++++++++++++++++++--
4 files changed, 33 insertions(+), 2 deletions(-)
(limited to 'include/uapi/linux/perf_event.h')
diff --git a/arch/x86/include/asm/tsc.h b/arch/x86/include/asm/tsc.h
index c91e8b9d588..235be70d5bb 100644
--- a/arch/x86/include/asm/tsc.h
+++ b/arch/x86/include/asm/tsc.h
@@ -49,6 +49,7 @@ extern void tsc_init(void);
extern void mark_tsc_unstable(char *reason);
extern int unsynchronized_tsc(void);
extern int check_tsc_unstable(void);
+extern int check_tsc_disabled(void);
extern unsigned long native_calibrate_tsc(void);
extern int tsc_clocksource_reliable;
diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index a7c7305030c..8355c84b972 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -1884,6 +1884,7 @@ static struct pmu pmu = {
void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
{
userpg->cap_usr_time = 0;
+ userpg->cap_usr_time_zero = 0;
userpg->cap_usr_rdpmc = x86_pmu.attr_rdpmc;
userpg->pmc_width = x86_pmu.cntval_bits;
@@ -1897,6 +1898,11 @@ void arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
userpg->time_mult = this_cpu_read(cyc2ns);
userpg->time_shift = CYC2NS_SCALE_FACTOR;
userpg->time_offset = this_cpu_read(cyc2ns_offset) - now;
+
+ if (sched_clock_stable && !check_tsc_disabled()) {
+ userpg->cap_usr_time_zero = 1;
+ userpg->time_zero = this_cpu_read(cyc2ns_offset);
+ }
}
/*
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 6ff49247edf..930e5d48f56 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -89,6 +89,12 @@ int check_tsc_unstable(void)
}
EXPORT_SYMBOL_GPL(check_tsc_unstable);
+int check_tsc_disabled(void)
+{
+ return tsc_disabled;
+}
+EXPORT_SYMBOL_GPL(check_tsc_disabled);
+
#ifdef CONFIG_X86_TSC
int __init notsc_setup(char *str)
{
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 0041aedf229..efef1d37a37 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -378,7 +378,8 @@ struct perf_event_mmap_page {
struct {
__u64 cap_usr_time : 1,
cap_usr_rdpmc : 1,
- cap_____res : 62;
+ cap_usr_time_zero : 1,
+ cap_____res : 61;
};
};
@@ -420,12 +421,29 @@ struct perf_event_mmap_page {
__u16 time_shift;
__u32 time_mult;
__u64 time_offset;
+ /*
+ * If cap_usr_time_zero, the hardware clock (e.g. TSC) can be calculated
+ * from sample timestamps.
+ *
+ * time = timestamp - time_zero;
+ * quot = time / time_mult;
+ * rem = time % time_mult;
+ * cyc = (quot << time_shift) + (rem << time_shift) / time_mult;
+ *
+ * And vice versa:
+ *
+ * quot = cyc >> time_shift;
+ * rem = cyc & ((1 << time_shift) - 1);
+ * timestamp = time_zero + quot * time_mult +
+ * ((rem * time_mult) >> time_shift);
+ */
+ __u64 time_zero;
/*
* Hole for extension of the self monitor capabilities
*/
- __u64 __reserved[120]; /* align to 1k */
+ __u64 __reserved[119]; /* align to 1k */
/*
* Control data for the mmap() data buffer.
--
cgit v1.2.3-70-g09d2
From cf4957f17f2a89984915ea808876d9c82225b862 Mon Sep 17 00:00:00 2001
From: Jiri Olsa <jolsa@redhat.com>
Date: Wed, 24 Oct 2012 13:37:58 +0200
Subject: perf: Add PERF_EVENT_IOC_ID ioctl to return event ID
The only way to get the event ID is by reading the event fd,
followed by parsing the ID value out of the returned data.
While this is ok for current read format used by perf tool,
it is not ok when we use PERF_FORMAT_GROUP format.
With this format the data are returned for the whole group
and there's no way to find out what ID belongs to our fd
(if we are not group leader event).
Adding a simple ioctl that returns event primary ID for given fd.
Signed-off-by: Jiri Olsa <jolsa@redhat.com>
Acked-by: Namhyung Kim <namhyung@kernel.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Link: http://lkml.kernel.org/n/tip-v1bn5cto707jn0bon34afqr1@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
include/uapi/linux/perf_event.h | 1 +
kernel/events/core.c | 9 +++++++++
2 files changed, 10 insertions(+)
(limited to 'include/uapi/linux/perf_event.h')
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index efef1d37a37..62c25a25291 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -321,6 +321,7 @@ struct perf_event_attr {
#define PERF_EVENT_IOC_PERIOD _IOW('$', 4, __u64)
#define PERF_EVENT_IOC_SET_OUTPUT _IO ('$', 5)
#define PERF_EVENT_IOC_SET_FILTER _IOW('$', 6, char *)
+#define PERF_EVENT_IOC_ID _IOR('$', 7, u64 *)
enum perf_event_ioc_flags {
PERF_IOC_FLAG_GROUP = 1U << 0,
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 916cf1f593b..5200b608b48 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3568,6 +3568,15 @@ static long perf_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case PERF_EVENT_IOC_PERIOD:
return perf_event_period(event, (u64 __user *)arg);
+ case PERF_EVENT_IOC_ID:
+ {
+ u64 id = primary_event_id(event);
+
+ if (copy_to_user((void __user *)arg, &id, sizeof(id)))
+ return -EFAULT;
+ return 0;
+ }
+
case PERF_EVENT_IOC_SET_OUTPUT:
{
int ret;
--
cgit v1.2.3-70-g09d2
From ff3d527cebc1fa3707c617bfe9e74f53fcfb0955 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Tue, 27 Aug 2013 11:23:07 +0300
Subject: perf: make events stream always parsable
The event stream is not always parsable because the format of a sample
is dependent on the sample_type of the selected event. When there is
more than one selected event and the sample_types are not the same then
parsing becomes problematic. A sample can be matched to its selected
event using the ID that is allocated when the event is opened.
Unfortunately, to get the ID from the sample means first parsing it.
This patch adds a new sample format bit PERF_SAMPLE_IDENTIFER that puts
the ID at a fixed position so that the ID can be retrieved without
parsing the sample. For sample events, that is the first position
immediately after the header. For non-sample events, that is the last
position.
In this respect parsing samples requires that the sample_type and ID
values are recorded. For example, perf tools records struct
perf_event_attr and the IDs within the perf.data file. Those must be
read first before it is possible to parse samples found later in the
perf.data file.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Tested-by: Stephane Eranian <eranian@google.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
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/1377591794-30553-6-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
include/uapi/linux/perf_event.h | 27 ++++++++++++++++++++-------
kernel/events/core.c | 11 ++++++++++-
2 files changed, 30 insertions(+), 8 deletions(-)
(limited to 'include/uapi/linux/perf_event.h')
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 62c25a25291..42cb7b62ca5 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -134,8 +134,9 @@ enum perf_event_sample_format {
PERF_SAMPLE_STACK_USER = 1U << 13,
PERF_SAMPLE_WEIGHT = 1U << 14,
PERF_SAMPLE_DATA_SRC = 1U << 15,
+ PERF_SAMPLE_IDENTIFIER = 1U << 16,
- PERF_SAMPLE_MAX = 1U << 16, /* non-ABI */
+ PERF_SAMPLE_MAX = 1U << 17, /* non-ABI */
};
/*
@@ -492,12 +493,12 @@ enum perf_event_type {
/*
* If perf_event_attr.sample_id_all is set then all event types will
* have the sample_type selected fields related to where/when
- * (identity) an event took place (TID, TIME, ID, CPU, STREAM_ID)
- * described in PERF_RECORD_SAMPLE below, it will be stashed just after
- * the perf_event_header and the fields already present for the existing
- * fields, i.e. at the end of the payload. That way a newer perf.data
- * file will be supported by older perf tools, with these new optional
- * fields being ignored.
+ * (identity) an event took place (TID, TIME, ID, STREAM_ID, CPU,
+ * IDENTIFIER) described in PERF_RECORD_SAMPLE below, it will be stashed
+ * just after the perf_event_header and the fields already present for
+ * the existing fields, i.e. at the end of the payload. That way a newer
+ * perf.data file will be supported by older perf tools, with these new
+ * optional fields being ignored.
*
* struct sample_id {
* { u32 pid, tid; } && PERF_SAMPLE_TID
@@ -505,7 +506,12 @@ enum perf_event_type {
* { u64 id; } && PERF_SAMPLE_ID
* { u64 stream_id;} && PERF_SAMPLE_STREAM_ID
* { u32 cpu, res; } && PERF_SAMPLE_CPU
+ * { u64 id; } && PERF_SAMPLE_IDENTIFIER
* } && perf_event_attr::sample_id_all
+ *
+ * Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID. The
+ * advantage of PERF_SAMPLE_IDENTIFIER is that its position is fixed
+ * relative to header.size.
*/
/*
@@ -594,6 +600,13 @@ enum perf_event_type {
* struct {
* struct perf_event_header header;
*
+ * #
+ * # Note that PERF_SAMPLE_IDENTIFIER duplicates PERF_SAMPLE_ID.
+ * # The advantage of PERF_SAMPLE_IDENTIFIER is that its position
+ * # is fixed relative to header.
+ * #
+ *
+ * { u64 id; } && PERF_SAMPLE_IDENTIFIER
* { u64 ip; } && PERF_SAMPLE_IP
* { u32 pid, tid; } && PERF_SAMPLE_TID
* { u64 time; } && PERF_SAMPLE_TIME
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 928fae7ca8c..15d0f2418e5 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -1213,6 +1213,9 @@ static void perf_event__id_header_size(struct perf_event *event)
if (sample_type & PERF_SAMPLE_TIME)
size += sizeof(data->time);
+ if (sample_type & PERF_SAMPLE_IDENTIFIER)
+ size += sizeof(data->id);
+
if (sample_type & PERF_SAMPLE_ID)
size += sizeof(data->id);
@@ -4280,7 +4283,7 @@ static void __perf_event_header__init_id(struct perf_event_header *header,
if (sample_type & PERF_SAMPLE_TIME)
data->time = perf_clock();
- if (sample_type & PERF_SAMPLE_ID)
+ if (sample_type & (PERF_SAMPLE_ID | PERF_SAMPLE_IDENTIFIER))
data->id = primary_event_id(event);
if (sample_type & PERF_SAMPLE_STREAM_ID)
@@ -4319,6 +4322,9 @@ static void __perf_event__output_id_sample(struct perf_output_handle *handle,
if (sample_type & PERF_SAMPLE_CPU)
perf_output_put(handle, data->cpu_entry);
+
+ if (sample_type & PERF_SAMPLE_IDENTIFIER)
+ perf_output_put(handle, data->id);
}
void perf_event__output_id_sample(struct perf_event *event,
@@ -4432,6 +4438,9 @@ void perf_output_sample(struct perf_output_handle *handle,
perf_output_put(handle, *header);
+ if (sample_type & PERF_SAMPLE_IDENTIFIER)
+ perf_output_put(handle, data->id);
+
if (sample_type & PERF_SAMPLE_IP)
perf_output_put(handle, data->ip);
--
cgit v1.2.3-70-g09d2
From 13d7a2410fa637f450a29ecb515ac318ee40c741 Mon Sep 17 00:00:00 2001
From: Stephane Eranian <eranian@google.com>
Date: Wed, 21 Aug 2013 12:10:24 +0200
Subject: perf: Add attr->mmap2 attribute to an event
Adds a new PERF_RECORD_MMAP2 record type which is essence
an expanded version of PERF_RECORD_MMAP.
Used to request mmap records with more information about
the mapping, including device major, minor and the inode
number and generation for mappings associated with files
or shared memory segments. Works for code and data
(with attr->mmap_data set).
Existing PERF_RECORD_MMAP record is unmodified by this patch.
Signed-off-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Link: http://lkml.kernel.org/r/1377079825-19057-2-git-send-email-eranian@google.com
[ Added Al to the Cc:. Are the ino, maj/min exports of vma->vm_file OK? ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
include/uapi/linux/perf_event.h | 24 ++++++++++++++++++++-
kernel/events/core.c | 46 +++++++++++++++++++++++++++++++++++++----
2 files changed, 65 insertions(+), 5 deletions(-)
(limited to 'include/uapi/linux/perf_event.h')
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 42cb7b62ca5..a77f43af72b 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -276,8 +276,9 @@ struct perf_event_attr {
exclude_callchain_kernel : 1, /* exclude kernel callchains */
exclude_callchain_user : 1, /* exclude user callchains */
+ mmap2 : 1, /* include mmap with inode data */
- __reserved_1 : 41;
+ __reserved_1 : 40;
union {
__u32 wakeup_events; /* wakeup every n events */
@@ -651,6 +652,27 @@ enum perf_event_type {
*/
PERF_RECORD_SAMPLE = 9,
+ /*
+ * The MMAP2 records are an augmented version of MMAP, they add
+ * maj, min, ino numbers to be used to uniquely identify each mapping
+ *
+ * struct {
+ * struct perf_event_header header;
+ *
+ * u32 pid, tid;
+ * u64 addr;
+ * u64 len;
+ * u64 pgoff;
+ * u32 maj;
+ * u32 min;
+ * u64 ino;
+ * u64 ino_generation;
+ * char filename[];
+ * struct sample_id sample_id;
+ * };
+ */
+ PERF_RECORD_MMAP2 = 10,
+
PERF_RECORD_MAX, /* non-ABI */
};
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 15d0f2418e5..c7ee497c39a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4776,7 +4776,7 @@ next:
/*
* task tracking -- fork/exit
*
- * enabled by: attr.comm | attr.mmap | attr.mmap_data | attr.task
+ * enabled by: attr.comm | attr.mmap | attr.mmap2 | attr.mmap_data | attr.task
*/
struct perf_task_event {
@@ -4796,8 +4796,9 @@ struct perf_task_event {
static int perf_event_task_match(struct perf_event *event)
{
- return event->attr.comm || event->attr.mmap ||
- event->attr.mmap_data || event->attr.task;
+ return event->attr.comm || event->attr.mmap ||
+ event->attr.mmap2 || event->attr.mmap_data ||
+ event->attr.task;
}
static void perf_event_task_output(struct perf_event *event,
@@ -4992,6 +4993,9 @@ struct perf_mmap_event {
const char *file_name;
int file_size;
+ int maj, min;
+ u64 ino;
+ u64 ino_generation;
struct {
struct perf_event_header header;
@@ -5012,7 +5016,7 @@ static int perf_event_mmap_match(struct perf_event *event,
int executable = vma->vm_flags & VM_EXEC;
return (!executable && event->attr.mmap_data) ||
- (executable && event->attr.mmap);
+ (executable && (event->attr.mmap || event->attr.mmap2));
}
static void perf_event_mmap_output(struct perf_event *event,
@@ -5027,6 +5031,13 @@ static void perf_event_mmap_output(struct perf_event *event,
if (!perf_event_mmap_match(event, data))
return;
+ if (event->attr.mmap2) {
+ mmap_event->event_id.header.type = PERF_RECORD_MMAP2;
+ mmap_event->event_id.header.size += sizeof(mmap_event->maj);
+ mmap_event->event_id.header.size += sizeof(mmap_event->min);
+ mmap_event->event_id.header.size += sizeof(mmap_event->ino);
+ }
+
perf_event_header__init_id(&mmap_event->event_id.header, &sample, event);
ret = perf_output_begin(&handle, event,
mmap_event->event_id.header.size);
@@ -5037,6 +5048,14 @@ static void perf_event_mmap_output(struct perf_event *event,
mmap_event->event_id.tid = perf_event_tid(event, current);
perf_output_put(&handle, mmap_event->event_id);
+
+ if (event->attr.mmap2) {
+ perf_output_put(&handle, mmap_event->maj);
+ perf_output_put(&handle, mmap_event->min);
+ perf_output_put(&handle, mmap_event->ino);
+ perf_output_put(&handle, mmap_event->ino_generation);
+ }
+
__output_copy(&handle, mmap_event->file_name,
mmap_event->file_size);
@@ -5051,6 +5070,8 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
{
struct vm_area_struct *vma = mmap_event->vma;
struct file *file = vma->vm_file;
+ int maj = 0, min = 0;
+ u64 ino = 0, gen = 0;
unsigned int size;
char tmp[16];
char *buf = NULL;
@@ -5059,6 +5080,8 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
memset(tmp, 0, sizeof(tmp));
if (file) {
+ struct inode *inode;
+ dev_t dev;
/*
* d_path works from the end of the rb backwards, so we
* need to add enough zero bytes after the string to handle
@@ -5074,6 +5097,13 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
name = strncpy(tmp, "//toolong", sizeof(tmp));
goto got_name;
}
+ inode = file_inode(vma->vm_file);
+ dev = inode->i_sb->s_dev;
+ ino = inode->i_ino;
+ gen = inode->i_generation;
+ maj = MAJOR(dev);
+ min = MINOR(dev);
+
} else {
if (arch_vma_name(mmap_event->vma)) {
name = strncpy(tmp, arch_vma_name(mmap_event->vma),
@@ -5104,6 +5134,10 @@ got_name:
mmap_event->file_name = name;
mmap_event->file_size = size;
+ mmap_event->maj = maj;
+ mmap_event->min = min;
+ mmap_event->ino = ino;
+ mmap_event->ino_generation = gen;
if (!(vma->vm_flags & VM_EXEC))
mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_DATA;
@@ -5140,6 +5174,10 @@ void perf_event_mmap(struct vm_area_struct *vma)
.len = vma->vm_end - vma->vm_start,
.pgoff = (u64)vma->vm_pgoff << PAGE_SHIFT,
},
+ /* .maj (attr_mmap2 only) */
+ /* .min (attr_mmap2 only) */
+ /* .ino (attr_mmap2 only) */
+ /* .ino_generation (attr_mmap2 only) */
};
perf_event_mmap_event(&mmap_event);
--
cgit v1.2.3-70-g09d2
From 274481de6cb69abdb49403ff32abb63c23743413 Mon Sep 17 00:00:00 2001
From: Vince Weaver <vincent.weaver@maine.edu>
Date: Fri, 23 Aug 2013 15:51:03 -0400
Subject: perf: Export struct perf_branch_entry to userspace
If PERF_SAMPLE_BRANCH_STACK is enabled then samples are returned
with the format { u64 from, to, flags } but the flags layout
is not specified.
This field has the type struct perf_branch_entry; move this
definition into include/uapi/linux/perf_event.h so users can
access these fields.
This is similar to the existing inclusion of perf_mem_data_src in
the include/uapi/linux/perf_event.h file.
Signed-off-by: Vince Weaver <vincent.weaver@maine.edu>
Acked-by: Stephane Eranian <eranian@google.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1308231544420.1889@vincent-weaver-1.um.maine.edu
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
include/linux/perf_event.h | 24 ------------------------
include/uapi/linux/perf_event.h | 24 ++++++++++++++++++++++++
2 files changed, 24 insertions(+), 24 deletions(-)
(limited to 'include/uapi/linux/perf_event.h')
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index c43f6eabad5..4019d82c3d0 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -63,30 +63,6 @@ struct perf_raw_record {
void *data;
};
-/*
- * single taken branch record layout:
- *
- * from: source instruction (may not always be a branch insn)
- * to: branch target
- * mispred: branch target was mispredicted
- * predicted: branch target was predicted
- *
- * support for mispred, predicted is optional. In case it
- * is not supported mispred = predicted = 0.
- *
- * in_tx: running in a hardware transaction
- * abort: aborting a hardware transaction
- */
-struct perf_branch_entry {
- __u64 from;
- __u64 to;
- __u64 mispred:1, /* target mispredicted */
- predicted:1,/* target predicted */
- in_tx:1, /* in transaction */
- abort:1, /* transaction abort */
- reserved:60;
-};
-
/*
* branch stack layout:
* nr: number of taken branches stored in entries[]
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index a77f43af72b..408b8c73073 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -757,4 +757,28 @@ union perf_mem_data_src {
#define PERF_MEM_S(a, s) \
(((u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
+/*
+ * single taken branch record layout:
+ *
+ * from: source instruction (may not always be a branch insn)
+ * to: branch target
+ * mispred: branch target was mispredicted
+ * predicted: branch target was predicted
+ *
+ * support for mispred, predicted is optional. In case it
+ * is not supported mispred = predicted = 0.
+ *
+ * in_tx: running in a hardware transaction
+ * abort: aborting a hardware transaction
+ */
+struct perf_branch_entry {
+ __u64 from;
+ __u64 to;
+ __u64 mispred:1, /* target mispredicted */
+ predicted:1,/* target predicted */
+ in_tx:1, /* in transaction */
+ abort:1, /* transaction abort */
+ reserved:60;
+};
+
#endif /* _UAPI_LINUX_PERF_EVENT_H */
--
cgit v1.2.3-70-g09d2
From fa0097ee690693006ab1aea6c01ad3c851b65c77 Mon Sep 17 00:00:00 2001
From: Adrian Hunter <adrian.hunter@intel.com>
Date: Sat, 31 Aug 2013 21:50:51 +0300
Subject: perf: Add a dummy software event to keep tracking
When an event is disabled the "tracking" events selected by the 'mmap',
'comm' and 'task' bits of struct perf_event_attr, are also disabled.
However, the information those events provide is necessary to resolve
symbols for when the main event is re-enabled.
The "tracking" events can be kept enabled by putting them on another
event, but that requires an event that otherwise does nothing. A new
software event PERF_COUNT_SW_DUMMY is added for that purpose.
Signed-off-by: Adrian Hunter <adrian.hunter@intel.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Namhyung Kim <namhyung@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1377975053-3811-2-git-send-email-adrian.hunter@intel.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
include/uapi/linux/perf_event.h | 1 +
1 file changed, 1 insertion(+)
(limited to 'include/uapi/linux/perf_event.h')
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 408b8c73073..ca1d90bcb74 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -109,6 +109,7 @@ enum perf_sw_ids {
PERF_COUNT_SW_PAGE_FAULTS_MAJ = 6,
PERF_COUNT_SW_ALIGNMENT_FAULTS = 7,
PERF_COUNT_SW_EMULATION_FAULTS = 8,
+ PERF_COUNT_SW_DUMMY = 9,
PERF_COUNT_SW_MAX, /* non-ABI */
};
--
cgit v1.2.3-70-g09d2