All of lore.kernel.org
 help / color / mirror / Atom feed
From: tip-bot for Andi Kleen <tipbot@zytor.com>
To: linux-tip-commits@vger.kernel.org
Cc: linux-kernel@vger.kernel.org, acme@redhat.com, mingo@kernel.org,
	peterz@infradead.org, hpa@zytor.com, ak@linux.intel.com,
	tglx@linutronix.de, jolsa@kernel.org
Subject: [tip:perf/core] perf tools: Add support for printing new mem_info encodings
Date: Thu, 24 Aug 2017 01:23:09 -0700	[thread overview]
Message-ID: <tip-52839e653b5629bd237ad2ecdd8fdd897fcd5712@git.kernel.org> (raw)
In-Reply-To: <20170816222156.19953-4-andi@firstfloor.org>

Commit-ID:  52839e653b5629bd237ad2ecdd8fdd897fcd5712
Gitweb:     http://git.kernel.org/tip/52839e653b5629bd237ad2ecdd8fdd897fcd5712
Author:     Andi Kleen <ak@linux.intel.com>
AuthorDate: Wed, 16 Aug 2017 15:21:55 -0700
Committer:  Arnaldo Carvalho de Melo <acme@redhat.com>
CommitDate: Tue, 22 Aug 2017 12:30:25 -0300

perf tools: Add support for printing new mem_info encodings

Add decoding for the new "lvlx" and "snoopx" meminfo fields added
earlier to the kernel so that "perf mem report" and other tools can
print it properly.

v2: Merge with persistent memory patch.
Switch to new bit encoding for each combination.

v3: Switch to generic lvlnum field.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Link: http://lkml.kernel.org/r/20170816222156.19953-4-andi@firstfloor.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/include/uapi/linux/perf_event.h | 30 ++++++++++++++++++++++--
 tools/perf/util/mem-events.c          | 43 ++++++++++++++++++++++++++++++++---
 2 files changed, 68 insertions(+), 5 deletions(-)

diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 642db5f..2a37ae9 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -954,14 +954,20 @@ union perf_mem_data_src {
 			mem_snoop:5,	/* snoop mode */
 			mem_lock:2,	/* lock instr */
 			mem_dtlb:7,	/* tlb access */
-			mem_rsvd:31;
+			mem_lvl_num:4,	/* memory hierarchy level number */
+			mem_remote:1,   /* remote */
+			mem_snoopx:2,	/* snoop mode, ext */
+			mem_rsvd:24;
 	};
 };
 #elif defined(__BIG_ENDIAN_BITFIELD)
 union perf_mem_data_src {
 	__u64 val;
 	struct {
-		__u64	mem_rsvd:31,
+		__u64	mem_rsvd:24,
+			mem_snoopx:2,	/* snoop mode, ext */
+			mem_remote:1,   /* remote */
+			mem_lvl_num:4,	/* memory hierarchy level number */
 			mem_dtlb:7,	/* tlb access */
 			mem_lock:2,	/* lock instr */
 			mem_snoop:5,	/* snoop mode */
@@ -998,6 +1004,22 @@ union perf_mem_data_src {
 #define PERF_MEM_LVL_UNC	0x2000 /* Uncached memory */
 #define PERF_MEM_LVL_SHIFT	5
 
+#define PERF_MEM_REMOTE_REMOTE	0x01  /* Remote */
+#define PERF_MEM_REMOTE_SHIFT	37
+
+#define PERF_MEM_LVLNUM_L1	0x01 /* L1 */
+#define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
+#define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
+#define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
+/* 5-0xa available */
+#define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
+#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB */
+#define PERF_MEM_LVLNUM_RAM	0x0d /* RAM */
+#define PERF_MEM_LVLNUM_PMEM	0x0e /* PMEM */
+#define PERF_MEM_LVLNUM_NA	0x0f /* N/A */
+
+#define PERF_MEM_LVLNUM_SHIFT	33
+
 /* snoop mode */
 #define PERF_MEM_SNOOP_NA	0x01 /* not available */
 #define PERF_MEM_SNOOP_NONE	0x02 /* no snoop */
@@ -1006,6 +1028,10 @@ union perf_mem_data_src {
 #define PERF_MEM_SNOOP_HITM	0x10 /* snoop hit modified */
 #define PERF_MEM_SNOOP_SHIFT	19
 
+#define PERF_MEM_SNOOPX_FWD	0x01 /* forward */
+/* 1 free */
+#define PERF_MEM_SNOOPX_SHIFT	37
+
 /* locked instruction */
 #define PERF_MEM_LOCK_NA	0x01 /* not available */
 #define PERF_MEM_LOCK_LOCKED	0x02 /* locked transaction */
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 06f5a3a..ced4f3f 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -166,11 +166,20 @@ static const char * const mem_lvl[] = {
 	"Uncached",
 };
 
+static const char * const mem_lvlnum[] = {
+	[PERF_MEM_LVLNUM_ANY_CACHE] = "Any cache",
+	[PERF_MEM_LVLNUM_LFB] = "LFB",
+	[PERF_MEM_LVLNUM_RAM] = "RAM",
+	[PERF_MEM_LVLNUM_PMEM] = "PMEM",
+	[PERF_MEM_LVLNUM_NA] = "N/A",
+};
+
 int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 {
 	size_t i, l = 0;
 	u64 m =  PERF_MEM_LVL_NA;
 	u64 hit, miss;
+	int printed;
 
 	if (mem_info)
 		m  = mem_info->data_src.mem_lvl;
@@ -184,17 +193,37 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	/* already taken care of */
 	m &= ~(PERF_MEM_LVL_HIT|PERF_MEM_LVL_MISS);
 
+
+	if (mem_info && mem_info->data_src.mem_remote) {
+		strcat(out, "Remote ");
+		l += 7;
+	}
+
+	printed = 0;
 	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
 		if (!(m & 0x1))
 			continue;
-		if (l) {
+		if (printed++) {
 			strcat(out, " or ");
 			l += 4;
 		}
 		l += scnprintf(out + l, sz - l, mem_lvl[i]);
 	}
-	if (*out == '\0')
-		l += scnprintf(out, sz - l, "N/A");
+
+	if (mem_info && mem_info->data_src.mem_lvl_num) {
+		int lvl = mem_info->data_src.mem_lvl_num;
+		if (printed++) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		if (mem_lvlnum[lvl])
+			l += scnprintf(out + l, sz - l, mem_lvlnum[lvl]);
+		else
+			l += scnprintf(out + l, sz - l, "L%d", lvl);
+	}
+
+	if (l == 0)
+		l += scnprintf(out + l, sz - l, "N/A");
 	if (hit)
 		l += scnprintf(out + l, sz - l, " hit");
 	if (miss)
@@ -231,6 +260,14 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 		}
 		l += scnprintf(out + l, sz - l, snoop_access[i]);
 	}
+	if (mem_info &&
+	     (mem_info->data_src.mem_snoopx & PERF_MEM_SNOOPX_FWD)) {
+		if (l) {
+			strcat(out, " or ");
+			l += 4;
+		}
+		l += scnprintf(out + l, sz - l, "Fwd");
+	}
 
 	if (*out == '\0')
 		l += scnprintf(out, sz - l, "N/A");

  parent reply	other threads:[~2017-08-24  8:25 UTC|newest]

Thread overview: 15+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-08-16 22:21 Fix Skylake PEBS data source for perf v5 Andi Kleen
2017-08-16 22:21 ` [PATCH v5 1/4] perf/x86: Move Nehalem PEBS code to flag Andi Kleen
2017-08-25 11:53   ` [tip:perf/core] " tip-bot for Andi Kleen
2017-08-16 22:21 ` [PATCH v5 2/4] perf/x86: Fix data source decoding for Skylake Andi Kleen
2017-08-25 11:53   ` [tip:perf/core] " tip-bot for Andi Kleen
2017-08-16 22:21 ` [PATCH v5 3/4] perf, tools: Add support for printing new mem_info encodings Andi Kleen
2017-08-23 13:01   ` Jiri Olsa
2017-08-23 14:00     ` Andi Kleen
2017-08-23 14:14       ` Jiri Olsa
2017-08-23 15:59         ` Andi Kleen
2017-08-24  8:23           ` Jiri Olsa
2017-08-24  8:23   ` tip-bot for Andi Kleen [this message]
2017-08-16 22:21 ` [PATCH v5 4/4] perf, tools: Add test cases for new data source encoding Andi Kleen
2017-08-24  8:23   ` [tip:perf/core] perf test: " tip-bot for Andi Kleen
2017-08-22 15:37 ` Fix Skylake PEBS data source for perf v5 Arnaldo Carvalho de Melo

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=tip-52839e653b5629bd237ad2ecdd8fdd897fcd5712@git.kernel.org \
    --to=tipbot@zytor.com \
    --cc=acme@redhat.com \
    --cc=ak@linux.intel.com \
    --cc=hpa@zytor.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-tip-commits@vger.kernel.org \
    --cc=mingo@kernel.org \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.