[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20210114134044.1418404-4-jolsa@kernel.org>
Date: Thu, 14 Jan 2021 14:40:44 +0100
From: Jiri Olsa <jolsa@...nel.org>
To: Arnaldo Carvalho de Melo <acme@...nel.org>
Cc: Peter Zijlstra <peterz@...radead.org>,
lkml <linux-kernel@...r.kernel.org>, bpf@...r.kernel.org,
Peter Zijlstra <a.p.zijlstra@...llo.nl>,
Ingo Molnar <mingo@...nel.org>,
Mark Rutland <mark.rutland@....com>,
Namhyung Kim <namhyung@...nel.org>,
Alexander Shishkin <alexander.shishkin@...ux.intel.com>,
Michael Petlan <mpetlan@...hat.com>,
Song Liu <songliubraving@...com>,
Ian Rogers <irogers@...gle.com>,
Stephane Eranian <eranian@...gle.com>,
Alexei Budankov <abudankov@...wei.com>,
Andi Kleen <ak@...ux.intel.com>,
Adrian Hunter <adrian.hunter@...el.com>
Subject: [PATCH bpf-next 3/3] perf: Add build id data in mmap2 event
Adding support to carry build id data in mmap2 event.
The build id data replaces maj/min/ino/ino_generation
fields, which are also used to identify map's binary,
so it's ok to replace them with build id data:
union {
struct {
u32 maj;
u32 min;
u64 ino;
u64 ino_generation;
};
struct {
u8 build_id_size;
u8 __reserved_1;
u16 __reserved_2;
u8 build_id[20];
};
};
Replaced maj/min/ino/ino_generation fields give us size
of 24 bytes. We use 20 bytes for build id data, 1 byte
for size and rest is unused.
There's new misc bit for mmap2 to signal there's build
id data in it:
#define PERF_RECORD_MISC_MMAP_BUILD_ID (1 << 14)
Acked-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Signed-off-by: Jiri Olsa <jolsa@...nel.org>
---
include/uapi/linux/perf_event.h | 42 +++++++++++++++++++++++++++++----
kernel/events/core.c | 32 +++++++++++++++++++++----
2 files changed, 65 insertions(+), 9 deletions(-)
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index b15e3447cd9f..cb6f84103560 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -386,7 +386,8 @@ struct perf_event_attr {
aux_output : 1, /* generate AUX records instead of events */
cgroup : 1, /* include cgroup events */
text_poke : 1, /* include text poke events */
- __reserved_1 : 30;
+ build_id : 1, /* use build id in mmap2 events */
+ __reserved_1 : 29;
union {
__u32 wakeup_events; /* wakeup every n events */
@@ -659,6 +660,22 @@ struct perf_event_mmap_page {
__u64 aux_size;
};
+/*
+ * The current state of perf_event_header::misc bits usage:
+ * ('|' used bit, '-' unused bit)
+ *
+ * 012 CDEF
+ * |||---------||||
+ *
+ * Where:
+ * 0-2 CPUMODE_MASK
+ *
+ * C PROC_MAP_PARSE_TIMEOUT
+ * D MMAP_DATA / COMM_EXEC / FORK_EXEC / SWITCH_OUT
+ * E MMAP_BUILD_ID / EXACT_IP / SCHED_OUT_PREEMPT
+ * F (reserved)
+ */
+
#define PERF_RECORD_MISC_CPUMODE_MASK (7 << 0)
#define PERF_RECORD_MISC_CPUMODE_UNKNOWN (0 << 0)
#define PERF_RECORD_MISC_KERNEL (1 << 0)
@@ -690,6 +707,7 @@ struct perf_event_mmap_page {
*
* PERF_RECORD_MISC_EXACT_IP - PERF_RECORD_SAMPLE of precise events
* PERF_RECORD_MISC_SWITCH_OUT_PREEMPT - PERF_RECORD_SWITCH* events
+ * PERF_RECORD_MISC_MMAP_BUILD_ID - PERF_RECORD_MMAP2 event
*
*
* PERF_RECORD_MISC_EXACT_IP:
@@ -699,9 +717,13 @@ struct perf_event_mmap_page {
*
* PERF_RECORD_MISC_SWITCH_OUT_PREEMPT:
* Indicates that thread was preempted in TASK_RUNNING state.
+ *
+ * PERF_RECORD_MISC_MMAP_BUILD_ID:
+ * Indicates that mmap2 event carries build id data.
*/
#define PERF_RECORD_MISC_EXACT_IP (1 << 14)
#define PERF_RECORD_MISC_SWITCH_OUT_PREEMPT (1 << 14)
+#define PERF_RECORD_MISC_MMAP_BUILD_ID (1 << 14)
/*
* Reserve the last bit to indicate some extended misc field
*/
@@ -915,10 +937,20 @@ enum perf_event_type {
* u64 addr;
* u64 len;
* u64 pgoff;
- * u32 maj;
- * u32 min;
- * u64 ino;
- * u64 ino_generation;
+ * union {
+ * struct {
+ * u32 maj;
+ * u32 min;
+ * u64 ino;
+ * u64 ino_generation;
+ * };
+ * struct {
+ * u8 build_id_size;
+ * u8 __reserved_1;
+ * u16 __reserved_2;
+ * u8 build_id[20];
+ * };
+ * };
* u32 prot, flags;
* char filename[];
* struct sample_id sample_id;
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 55d18791a72d..c37401e3e5f7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -53,6 +53,7 @@
#include <linux/min_heap.h>
#include <linux/highmem.h>
#include <linux/pgtable.h>
+#include <linux/buildid.h>
#include "internal.h"
@@ -397,6 +398,7 @@ static atomic_t nr_ksymbol_events __read_mostly;
static atomic_t nr_bpf_events __read_mostly;
static atomic_t nr_cgroup_events __read_mostly;
static atomic_t nr_text_poke_events __read_mostly;
+static atomic_t nr_build_id_events __read_mostly;
static LIST_HEAD(pmus);
static DEFINE_MUTEX(pmus_lock);
@@ -4673,6 +4675,8 @@ static void unaccount_event(struct perf_event *event)
dec = true;
if (event->attr.mmap || event->attr.mmap_data)
atomic_dec(&nr_mmap_events);
+ if (event->attr.build_id)
+ atomic_dec(&nr_build_id_events);
if (event->attr.comm)
atomic_dec(&nr_comm_events);
if (event->attr.namespaces)
@@ -8046,6 +8050,8 @@ struct perf_mmap_event {
u64 ino;
u64 ino_generation;
u32 prot, flags;
+ u8 build_id[BUILD_ID_SIZE_MAX];
+ u32 build_id_size;
struct {
struct perf_event_header header;
@@ -8077,6 +8083,7 @@ static void perf_event_mmap_output(struct perf_event *event,
struct perf_sample_data sample;
int size = mmap_event->event_id.header.size;
u32 type = mmap_event->event_id.header.type;
+ bool use_build_id;
int ret;
if (!perf_event_mmap_match(event, data))
@@ -8101,13 +8108,25 @@ static void perf_event_mmap_output(struct perf_event *event,
mmap_event->event_id.pid = perf_event_pid(event, current);
mmap_event->event_id.tid = perf_event_tid(event, current);
+ use_build_id = event->attr.build_id && mmap_event->build_id_size;
+
+ if (event->attr.mmap2 && use_build_id)
+ mmap_event->event_id.header.misc |= PERF_RECORD_MISC_MMAP_BUILD_ID;
+
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);
+ if (use_build_id) {
+ u8 size[4] = { (u8) mmap_event->build_id_size, 0, 0, 0 };
+
+ __output_copy(&handle, size, 4);
+ __output_copy(&handle, mmap_event->build_id, BUILD_ID_SIZE_MAX);
+ } else {
+ 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);
+ }
perf_output_put(&handle, mmap_event->prot);
perf_output_put(&handle, mmap_event->flags);
}
@@ -8236,6 +8255,9 @@ static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
mmap_event->event_id.header.size = sizeof(mmap_event->event_id) + size;
+ if (atomic_read(&nr_build_id_events))
+ build_id_parse(vma, mmap_event->build_id, &mmap_event->build_id_size);
+
perf_iterate_sb(perf_event_mmap_output,
mmap_event,
NULL);
@@ -11172,6 +11194,8 @@ static void account_event(struct perf_event *event)
inc = true;
if (event->attr.mmap || event->attr.mmap_data)
atomic_inc(&nr_mmap_events);
+ if (event->attr.build_id)
+ atomic_inc(&nr_build_id_events);
if (event->attr.comm)
atomic_inc(&nr_comm_events);
if (event->attr.namespaces)
--
2.26.2
Powered by blists - more mailing lists