From: Stephane Eranian <eranian@google.com>
To: linux-kernel@vger.kernel.org
Cc: peterz@infradead.org, mingo@elte.hu, ak@linux.intel.com,
acme@redhat.com, jolsa@redhat.com, namhyung.kim@lge.com
Subject: [PATCH v6 07/18] perf: add generic memory sampling interface
Date: Tue, 15 Jan 2013 16:39:35 +0100 [thread overview]
Message-ID: <1358264386-24633-8-git-send-email-eranian@google.com> (raw)
In-Reply-To: <1358264386-24633-1-git-send-email-eranian@google.com>
This patch adds PERF_SAMPLE_DSRC.
PERF_SAMPLE_DSRC collects the data source, i.e., where
did the data associated with the sampled instruction
come from. Information is stored in a perf_mem_dsrc
structure. It contains opcode, mem level, tlb, snoop,
lock information, subject to availability in hardware.
Signed-off-by: Stephane Eranian <eranian@google.com>
---
include/linux/perf_event.h | 2 ++
include/uapi/linux/perf_event.h | 68 +++++++++++++++++++++++++++++++++++++--
kernel/events/core.c | 6 ++++
3 files changed, 74 insertions(+), 2 deletions(-)
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index bb2429d..8fe4610 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -579,6 +579,7 @@ struct perf_sample_data {
u32 reserved;
} cpu_entry;
u64 period;
+ union perf_mem_dsrc dsrc;
struct perf_callchain_entry *callchain;
struct perf_raw_record *raw;
struct perf_branch_stack *br_stack;
@@ -599,6 +600,7 @@ static inline void perf_sample_data_init(struct perf_sample_data *data,
data->regs_user.regs = NULL;
data->stack_user_size = 0;
data->weight = 0;
+ data->dsrc.val = 0;
}
extern void perf_output_sample(struct perf_output_handle *handle,
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 7e24641..8283218 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -133,9 +133,9 @@ enum perf_event_sample_format {
PERF_SAMPLE_REGS_USER = 1U << 12,
PERF_SAMPLE_STACK_USER = 1U << 13,
PERF_SAMPLE_WEIGHT = 1U << 14,
+ PERF_SAMPLE_DSRC = 1U << 15,
- PERF_SAMPLE_MAX = 1U << 15, /* non-ABI */
-
+ PERF_SAMPLE_MAX = 1U << 16, /* non-ABI */
};
/*
@@ -590,6 +590,7 @@ enum perf_event_type {
* char data[size];
* u64 dyn_size; } && PERF_SAMPLE_STACK_USER
* { u64 weight; } && PERF_SAMPLE_WEIGHT
+ * { u64 dsrc; } && PERF_SAMPLE_DSRC
* };
*/
PERF_RECORD_SAMPLE = 9,
@@ -615,4 +616,67 @@ enum perf_callchain_context {
#define PERF_FLAG_FD_OUTPUT (1U << 1)
#define PERF_FLAG_PID_CGROUP (1U << 2) /* pid=cgroup id, per-cpu mode only */
+union perf_mem_dsrc {
+ __u64 val;
+ struct {
+ __u64 mem_op:5, /* type of opcode */
+ mem_lvl:14, /* memory hierarchy level */
+ mem_snoop:5, /* snoop mode */
+ mem_lock:2, /* lock instr */
+ mem_dtlb:7, /* tlb access */
+ mem_rsvd:31;
+ };
+};
+
+/* type of opcode (load/store/prefetch,code) */
+#define PERF_MEM_OP_NA 0x01 /* not available */
+#define PERF_MEM_OP_LOAD 0x02 /* load instruction */
+#define PERF_MEM_OP_STORE 0x04 /* store instruction */
+#define PERF_MEM_OP_PFETCH 0x08 /* prefetch */
+#define PERF_MEM_OP_EXEC 0x10 /* code (execution) */
+#define PERF_MEM_OP_SHIFT 0
+
+/* memory hierarchy (memory level, hit or miss) */
+#define PERF_MEM_LVL_NA 0x01 /* not available */
+#define PERF_MEM_LVL_HIT 0x02 /* hit level */
+#define PERF_MEM_LVL_MISS 0x04 /* miss level */
+#define PERF_MEM_LVL_L1 0x08 /* L1 */
+#define PERF_MEM_LVL_LFB 0x10 /* Line Fill Buffer */
+#define PERF_MEM_LVL_L2 0x20 /* L2 hit */
+#define PERF_MEM_LVL_L3 0x40 /* L3 hit */
+#define PERF_MEM_LVL_LOC_RAM 0x80 /* Local DRAM */
+#define PERF_MEM_LVL_REM_RAM1 0x100 /* Remote DRAM (1 hop) */
+#define PERF_MEM_LVL_REM_RAM2 0x200 /* Remote DRAM (2 hops) */
+#define PERF_MEM_LVL_REM_CCE1 0x400 /* Remote Cache (1 hop) */
+#define PERF_MEM_LVL_REM_CCE2 0x800 /* Remote Cache (2 hops) */
+#define PERF_MEM_LVL_IO 0x1000 /* I/O memory */
+#define PERF_MEM_LVL_UNC 0x2000 /* Uncached memory */
+#define PERF_MEM_LVL_SHIFT 5
+
+/* snoop mode */
+#define PERF_MEM_SNOOP_NA 0x01 /* not available */
+#define PERF_MEM_SNOOP_NONE 0x02 /* no snoop */
+#define PERF_MEM_SNOOP_HIT 0x04 /* snoop hit */
+#define PERF_MEM_SNOOP_MISS 0x08 /* snoop miss */
+#define PERF_MEM_SNOOP_HITM 0x10 /* snoop hit modified */
+#define PERF_MEM_SNOOP_SHIFT 19
+
+/* locked instruction */
+#define PERF_MEM_LOCK_NA 0x01 /* not available */
+#define PERF_MEM_LOCK_LOCKED 0x02 /* locked transaction */
+#define PERF_MEM_LOCK_SHIFT 24
+
+/* TLB access */
+#define PERF_MEM_TLB_NA 0x01 /* not available */
+#define PERF_MEM_TLB_HIT 0x02 /* hit level */
+#define PERF_MEM_TLB_MISS 0x04 /* miss level */
+#define PERF_MEM_TLB_L1 0x08 /* L1 */
+#define PERF_MEM_TLB_L2 0x10 /* L2 */
+#define PERF_MEM_TLB_WK 0x20 /* Hardware Walker*/
+#define PERF_MEM_TLB_OS 0x40 /* OS fault handler */
+#define PERF_MEM_TLB_SHIFT 26
+
+#define PERF_MEM_S(a, s) \
+ (((u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT)
+
#endif /* _UAPI_LINUX_PERF_EVENT_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index bc2ce07..fd4ceea 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -958,6 +958,9 @@ static void perf_event__header_size(struct perf_event *event)
if (sample_type & PERF_SAMPLE_WEIGHT)
size += sizeof(data->weight);
+ if (sample_type & PERF_SAMPLE_DSRC)
+ size += sizeof(data->dsrc.val);
+
event->header_size = size;
}
@@ -4175,6 +4178,9 @@ void perf_output_sample(struct perf_output_handle *handle,
if (sample_type & PERF_SAMPLE_WEIGHT)
perf_output_put(handle, data->weight);
+
+ if (sample_type & PERF_SAMPLE_DSRC)
+ perf_output_put(handle, data->dsrc.val);
}
void perf_prepare_sample(struct perf_event_header *header,
--
1.7.9.5
next prev parent reply other threads:[~2013-01-15 15:49 UTC|newest]
Thread overview: 33+ messages / expand[flat|nested] mbox.gz Atom feed top
2013-01-15 15:39 [PATCH v6 00/18] perf: add memory access sampling support Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 01/18] perf, x86: Support CPU specific sysfs events Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 02/18] perf/x86: improve sysfs event mapping with event string Stephane Eranian
2013-01-18 22:57 ` Andi Kleen
2013-01-15 15:39 ` [PATCH v6 03/18] perf/x86: add flags to event constraints Stephane Eranian
2013-01-18 22:59 ` Andi Kleen
2013-01-22 14:22 ` Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 04/18] perf, core: Add a concept of a weightened sample Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 05/18] perf: add minimal support for PERF_SAMPLE_WEIGHT Stephane Eranian
2013-01-18 23:00 ` Andi Kleen
2013-01-22 14:30 ` Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 06/18] perf: add support for PERF_SAMPLE_ADDR in dump_sampple() Stephane Eranian
2013-01-15 15:39 ` Stephane Eranian [this message]
2013-01-18 23:06 ` [PATCH v6 07/18] perf: add generic memory sampling interface Andi Kleen
2013-01-23 16:54 ` Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 08/18] perf/x86: add memory profiling via PEBS Load Latency Stephane Eranian
2013-01-18 23:12 ` Andi Kleen
2013-01-15 15:39 ` [PATCH v6 09/18] perf/x86: export PEBS load latency threshold register to sysfs Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 10/18] perf/x86: add support for PEBS Precise Store Stephane Eranian
2013-01-18 23:21 ` Andi Kleen
2013-01-15 15:39 ` [PATCH v6 11/18] perf tools: add mem access sampling core support Stephane Eranian
2013-01-18 23:25 ` Andi Kleen
2013-01-15 15:39 ` [PATCH v6 12/18] perf report: add support for mem access profiling Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 13/18] perf record: " Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 14/18] perf tools: add new mem command for memory " Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 15/18] perf: add PERF_RECORD_MISC_MMAP_DATA to RECORD_MMAP Stephane Eranian
2013-01-18 23:25 ` Andi Kleen
2013-01-15 15:39 ` [PATCH v6 16/18] perf tools: detect data vs. text mappings Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 17/18] perf tools: Ignore ABS symbols when loading data maps Stephane Eranian
2013-01-15 15:39 ` [PATCH v6 18/18] perf tools: Fix output of symbol_daddr offset Stephane Eranian
2013-01-24 11:56 ` [PATCH v6 00/18] perf: add memory access sampling support Ingo Molnar
2013-01-24 13:39 ` Stephane Eranian
2013-01-24 13:41 ` Ingo Molnar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1358264386-24633-8-git-send-email-eranian@google.com \
--to=eranian@google.com \
--cc=acme@redhat.com \
--cc=ak@linux.intel.com \
--cc=jolsa@redhat.com \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=namhyung.kim@lge.com \
--cc=peterz@infradead.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox