lkml.org 
[lkml]   [2011]   [Apr]   [22]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
SubjectRe: [PATCH 1/1] perf tools: Add missing user space support for config1/config2
From
Date
On Fri, 2011-04-22 at 23:54 +0200, Peter Zijlstra wrote:
> On Fri, 2011-04-22 at 23:37 +0200, Peter Zijlstra wrote:
> > The below needs filling out for !x86 (which I filled out with
> > unsupported events) and x86 needs the offcore bits fixed to auto select
> > between the two offcore events.
>
> Urgh, so SNB has different MSR_OFFCORE_RESPONSE bits and needs another table.

Also, NHM offcore bits were wrong... it implemented _ACCESS as _HIT and
counted OTHER_CORE_HIT* as MISS even though its clearly documented as an
L3 hit.

Current scribblings below..

---
arch/arm/kernel/perf_event_v6.c | 28 ++++
arch/arm/kernel/perf_event_v7.c | 28 ++++
arch/arm/kernel/perf_event_xscale.c | 14 ++
arch/mips/kernel/perf_event_mipsxx.c | 28 ++++
arch/powerpc/kernel/e500-pmu.c | 5 +
arch/powerpc/kernel/mpc7450-pmu.c | 5 +
arch/powerpc/kernel/power4-pmu.c | 5 +
arch/powerpc/kernel/power5+-pmu.c | 5 +
arch/powerpc/kernel/power5-pmu.c | 5 +
arch/powerpc/kernel/power6-pmu.c | 5 +
arch/powerpc/kernel/power7-pmu.c | 5 +
arch/powerpc/kernel/ppc970-pmu.c | 5 +
arch/sh/kernel/cpu/sh4/perf_event.c | 15 ++
arch/sh/kernel/cpu/sh4a/perf_event.c | 15 ++
arch/sparc/kernel/perf_event.c | 42 ++++++
arch/x86/kernel/cpu/perf_event_amd.c | 14 ++
arch/x86/kernel/cpu/perf_event_intel.c | 253 +++++++++++++++++++++++++++-----
arch/x86/kernel/cpu/perf_event_p4.c | 14 ++
include/linux/perf_event.h | 3 +-
19 files changed, 458 insertions(+), 36 deletions(-)
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index f1e8dd9..02178da 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -173,6 +173,20 @@ static const unsigned armv6_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
+ [C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
};

enum armv6mpcore_perf_types {
@@ -310,6 +324,20 @@ static const unsigned armv6mpcore_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
+ [C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
};

static inline unsigned long
diff --git a/arch/arm/kernel/perf_event_v7.c b/arch/arm/kernel/perf_event_v7.c
index 4960686..79ffc83 100644
--- a/arch/arm/kernel/perf_event_v7.c
+++ b/arch/arm/kernel/perf_event_v7.c
@@ -255,6 +255,20 @@ static const unsigned armv7_a8_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
+ [C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
};

/*
@@ -371,6 +385,20 @@ static const unsigned armv7_a9_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
+ [C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
};

/*
diff --git a/arch/arm/kernel/perf_event_xscale.c b/arch/arm/kernel/perf_event_xscale.c
index 39affbe..7ed1a55 100644
--- a/arch/arm/kernel/perf_event_xscale.c
+++ b/arch/arm/kernel/perf_event_xscale.c
@@ -144,6 +144,20 @@ static const unsigned xscale_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
[C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
},
},
+ [C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = CACHE_OP_UNSUPPORTED,
+ [C(RESULT_MISS)] = CACHE_OP_UNSUPPORTED,
+ },
+ },
};

#define XSCALE_PMU_ENABLE 0x001
diff --git a/arch/mips/kernel/perf_event_mipsxx.c b/arch/mips/kernel/perf_event_mipsxx.c
index 75266ff..e5ad09a 100644
--- a/arch/mips/kernel/perf_event_mipsxx.c
+++ b/arch/mips/kernel/perf_event_mipsxx.c
@@ -377,6 +377,20 @@ static const struct mips_perf_event mipsxxcore_cache_map
[C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
},
},
+[C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+},
};

/* 74K core has completely different cache event map. */
@@ -480,6 +494,20 @@ static const struct mips_perf_event mipsxx74Kcore_cache_map
[C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
},
},
+[C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ [C(RESULT_MISS)] = { UNSUPPORTED_PERF_EVENT_ID },
+ },
+},
};

#ifdef CONFIG_MIPS_MT_SMP
diff --git a/arch/powerpc/kernel/e500-pmu.c b/arch/powerpc/kernel/e500-pmu.c
index b150b51..cb2e294 100644
--- a/arch/powerpc/kernel/e500-pmu.c
+++ b/arch/powerpc/kernel/e500-pmu.c
@@ -75,6 +75,11 @@ static int e500_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
+ [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */
+ [C(OP_READ)] = { -1, -1 },
+ [C(OP_WRITE)] = { -1, -1 },
+ [C(OP_PREFETCH)] = { -1, -1 },
+ },
};

static int num_events = 128;
diff --git a/arch/powerpc/kernel/mpc7450-pmu.c b/arch/powerpc/kernel/mpc7450-pmu.c
index 2cc5e03..845a584 100644
--- a/arch/powerpc/kernel/mpc7450-pmu.c
+++ b/arch/powerpc/kernel/mpc7450-pmu.c
@@ -388,6 +388,11 @@ static int mpc7450_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
+ [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */
+ [C(OP_READ)] = { -1, -1 },
+ [C(OP_WRITE)] = { -1, -1 },
+ [C(OP_PREFETCH)] = { -1, -1 },
+ },
};

struct power_pmu mpc7450_pmu = {
diff --git a/arch/powerpc/kernel/power4-pmu.c b/arch/powerpc/kernel/power4-pmu.c
index ead8b3c..e9dbc2d 100644
--- a/arch/powerpc/kernel/power4-pmu.c
+++ b/arch/powerpc/kernel/power4-pmu.c
@@ -587,6 +587,11 @@ static int power4_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
+ [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */
+ [C(OP_READ)] = { -1, -1 },
+ [C(OP_WRITE)] = { -1, -1 },
+ [C(OP_PREFETCH)] = { -1, -1 },
+ },
};

static struct power_pmu power4_pmu = {
diff --git a/arch/powerpc/kernel/power5+-pmu.c b/arch/powerpc/kernel/power5+-pmu.c
index eca0ac5..f58a2bd 100644
--- a/arch/powerpc/kernel/power5+-pmu.c
+++ b/arch/powerpc/kernel/power5+-pmu.c
@@ -653,6 +653,11 @@ static int power5p_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
+ [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */
+ [C(OP_READ)] = { -1, -1 },
+ [C(OP_WRITE)] = { -1, -1 },
+ [C(OP_PREFETCH)] = { -1, -1 },
+ },
};

static struct power_pmu power5p_pmu = {
diff --git a/arch/powerpc/kernel/power5-pmu.c b/arch/powerpc/kernel/power5-pmu.c
index d5ff0f6..b1acab6 100644
--- a/arch/powerpc/kernel/power5-pmu.c
+++ b/arch/powerpc/kernel/power5-pmu.c
@@ -595,6 +595,11 @@ static int power5_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
+ [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */
+ [C(OP_READ)] = { -1, -1 },
+ [C(OP_WRITE)] = { -1, -1 },
+ [C(OP_PREFETCH)] = { -1, -1 },
+ },
};

static struct power_pmu power5_pmu = {
diff --git a/arch/powerpc/kernel/power6-pmu.c b/arch/powerpc/kernel/power6-pmu.c
index 3160392..b24a3a2 100644
--- a/arch/powerpc/kernel/power6-pmu.c
+++ b/arch/powerpc/kernel/power6-pmu.c
@@ -516,6 +516,11 @@ static int power6_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
+ [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */
+ [C(OP_READ)] = { -1, -1 },
+ [C(OP_WRITE)] = { -1, -1 },
+ [C(OP_PREFETCH)] = { -1, -1 },
+ },
};

static struct power_pmu power6_pmu = {
diff --git a/arch/powerpc/kernel/power7-pmu.c b/arch/powerpc/kernel/power7-pmu.c
index 593740f..6d9dccb 100644
--- a/arch/powerpc/kernel/power7-pmu.c
+++ b/arch/powerpc/kernel/power7-pmu.c
@@ -342,6 +342,11 @@ static int power7_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
+ [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */
+ [C(OP_READ)] = { -1, -1 },
+ [C(OP_WRITE)] = { -1, -1 },
+ [C(OP_PREFETCH)] = { -1, -1 },
+ },
};

static struct power_pmu power7_pmu = {
diff --git a/arch/powerpc/kernel/ppc970-pmu.c b/arch/powerpc/kernel/ppc970-pmu.c
index 9a6e093..b121de9 100644
--- a/arch/powerpc/kernel/ppc970-pmu.c
+++ b/arch/powerpc/kernel/ppc970-pmu.c
@@ -467,6 +467,11 @@ static int ppc970_cache_events[C(MAX)][C(OP_MAX)][C(RESULT_MAX)] = {
[C(OP_WRITE)] = { -1, -1 },
[C(OP_PREFETCH)] = { -1, -1 },
},
+ [C(NODE)] = { /* RESULT_ACCESS RESULT_MISS */
+ [C(OP_READ)] = { -1, -1 },
+ [C(OP_WRITE)] = { -1, -1 },
+ [C(OP_PREFETCH)] = { -1, -1 },
+ },
};

static struct power_pmu ppc970_pmu = {
diff --git a/arch/sh/kernel/cpu/sh4/perf_event.c b/arch/sh/kernel/cpu/sh4/perf_event.c
index 748955d..fa4f724 100644
--- a/arch/sh/kernel/cpu/sh4/perf_event.c
+++ b/arch/sh/kernel/cpu/sh4/perf_event.c
@@ -180,6 +180,21 @@ static const int sh7750_cache_events
[ C(RESULT_MISS) ] = -1,
},
},
+
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
};

static int sh7750_event_map(int event)
diff --git a/arch/sh/kernel/cpu/sh4a/perf_event.c b/arch/sh/kernel/cpu/sh4a/perf_event.c
index 17e6beb..84a2c39 100644
--- a/arch/sh/kernel/cpu/sh4a/perf_event.c
+++ b/arch/sh/kernel/cpu/sh4a/perf_event.c
@@ -205,6 +205,21 @@ static const int sh4a_cache_events
[ C(RESULT_MISS) ] = -1,
},
},
+
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
};

static int sh4a_event_map(int event)
diff --git a/arch/sparc/kernel/perf_event.c b/arch/sparc/kernel/perf_event.c
index ee8426e..d890e0f 100644
--- a/arch/sparc/kernel/perf_event.c
+++ b/arch/sparc/kernel/perf_event.c
@@ -245,6 +245,20 @@ static const cache_map_t ultra3_cache_map = {
[ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
},
},
+[C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = { CACHE_OP_UNSUPPORTED },
+ [C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED },
+ [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED },
+ [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
+ },
+},
};

static const struct sparc_pmu ultra3_pmu = {
@@ -360,6 +374,20 @@ static const cache_map_t niagara1_cache_map = {
[ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
},
},
+[C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = { CACHE_OP_UNSUPPORTED },
+ [C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED },
+ [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED },
+ [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
+ },
+},
};

static const struct sparc_pmu niagara1_pmu = {
@@ -472,6 +500,20 @@ static const cache_map_t niagara2_cache_map = {
[ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
},
},
+[C(NODE)] = {
+ [C(OP_READ)] = {
+ [C(RESULT_ACCESS)] = { CACHE_OP_UNSUPPORTED },
+ [C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED },
+ [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = { CACHE_OP_UNSUPPORTED },
+ [ C(RESULT_MISS) ] = { CACHE_OP_UNSUPPORTED },
+ },
+},
};

static const struct sparc_pmu niagara2_pmu = {
diff --git a/arch/x86/kernel/cpu/perf_event_amd.c b/arch/x86/kernel/cpu/perf_event_amd.c
index cf4e369..01c7dd3 100644
--- a/arch/x86/kernel/cpu/perf_event_amd.c
+++ b/arch/x86/kernel/cpu/perf_event_amd.c
@@ -89,6 +89,20 @@ static __initconst const u64 amd_hw_cache_event_ids
[ C(RESULT_MISS) ] = -1,
},
},
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0xb8e9, /* CPU Request to Memory, l+r */
+ [ C(RESULT_MISS) ] = 0x98e9, /* CPU Request to Memory, r */
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
};

/*
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 43fa20b..fe4e8b1 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -150,6 +150,86 @@ static u64 intel_pmu_event_map(int hw_event)
return intel_perfmon_event_map[hw_event];
}

+/*
+ * Sandy Bridge MSR_OFFCORE_RESPONSE bits;
+ * See IA32 SDM Vol 3B 30.8.5
+ */
+
+#define SNB_DMND_DATA_RD (1 << 0)
+#define SNB_DMND_RFO (1 << 1)
+#define SNB_DMND_IFETCH (1 << 2)
+#define SNB_DMND_WB (1 << 3)
+#define SNB_PF_DATA_RD (1 << 4)
+#define SNB_PF_DATA_RFO (1 << 5)
+#define SNB_PF_IFETCH (1 << 6)
+#define SNB_PF_LLC_DATA_RD (1 << 7)
+#define SNB_PF_LLC_RFO (1 << 8)
+#define SNB_PF_LLC_IFETCH (1 << 9)
+#define SNB_BUS_LOCKS (1 << 10)
+#define SNB_STRM_ST (1 << 11)
+ /* hole */
+#define SNB_OFFCORE_OTHER (1 << 15)
+#define SNB_COMMON (1 << 16)
+#define SNB_NO_SUPP (1 << 17)
+#define SNB_LLC_HITM (1 << 18)
+#define SNB_LLC_HITE (1 << 19)
+#define SNB_LLC_HITS (1 << 20)
+#define SNB_LLC_HITF (1 << 21)
+ /* hole */
+#define SNB_SNP_NONE (1 << 31)
+#define SNB_SNP_NOT_NEEDED (1 << 32)
+#define SNB_SNP_MISS (1 << 33)
+#define SNB_SNP_NO_FWD (1 << 34)
+#define SNB_SNP_FWD (1 << 35)
+#define SNB_HITM (1 << 36)
+#define SNB_NON_DRAM (1 << 37)
+
+#define SNB_DMND_READ (SNB_DMND_DATA_RD)
+#define SNB_DMND_WRITE (SNB_DMND_RFO|SNB_DMND_WB|SNB_STRM_ST)
+#define SNB_DMND_PREFETCH (SNB_PF_DATA_RD|SNB_PF_DATA_RFO)
+
+#define SNB_L3_HIT ()
+#define SNB_L3_MISS ()
+#define SNB_L3_ACCESS (SNB_L3_HIT|SNB_L3_MISS)
+
+#define SNB_ALL_DRAM ()
+#define SNB_REMOTE_DRAM ()
+
+static __initconst const u64 snb_hw_cache_extra_regs
+ [PERF_COUNT_HW_CACHE_MAX]
+ [PERF_COUNT_HW_CACHE_OP_MAX]
+ [PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(LL ) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_L3_ACCESS,
+ [ C(RESULT_MISS) ] = SNB_DMND_READ|SNB_L3_MISS,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_L3_ACCESS,
+ [ C(RESULT_MISS) ] = SNB_DMND_WRITE|SNB_L3_MISS,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_L3_ACCESS,
+ [ C(RESULT_MISS) ] = SNB_DMND_PREFETCH|SNB_L3_MISS,
+ },
+ }
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_READ|SNB_ALL_DRAM,
+ [ C(RESULT_MISS) ] = SNB_DMND_READ|SNB_REMOTE_DRAM,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_WRITE|SNB_ALL_DRAM,
+ [ C(RESULT_MISS) ] = SNB_DMND_WRITE|SNB_REMOTE_DRAM,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = SNB_DMND_PREFETCH|SNB_ALL_DRAM,
+ [ C(RESULT_MISS) ] = SNB_DMND_PREFETCH|SNB_REMOTE_DRAM,
+ },
+ },
+};
+
static __initconst const u64 snb_hw_cache_event_ids
[PERF_COUNT_HW_CACHE_MAX]
[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -184,26 +264,23 @@ static __initconst const u64 snb_hw_cache_event_ids
},
},
[ C(LL ) ] = {
- /*
- * TBD: Need Off-core Response Performance Monitoring support
- */
[ C(OP_READ) ] = {
- /* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_WRITE) ] = {
- /* OFFCORE_RESPONSE_0.ANY_RFO.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.ANY_RFO.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
- /* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
@@ -248,6 +325,20 @@ static __initconst const u64 snb_hw_cache_event_ids
[ C(RESULT_MISS) ] = -1,
},
},
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01b7, /* OFFCORE_RESP */
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ },
};

static __initconst const u64 westmere_hw_cache_event_ids
@@ -285,26 +376,26 @@ static __initconst const u64 westmere_hw_cache_event_ids
},
[ C(LL ) ] = {
[ C(OP_READ) ] = {
- /* OFFCORE_RESPONSE_0.ANY_DATA.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.ANY_DATA.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.ANY_DATA.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.ANY_DATA.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
/*
* Use RFO, not WRITEBACK, because a write miss would typically occur
* on RFO.
*/
[ C(OP_WRITE) ] = {
- /* OFFCORE_RESPONSE_1.ANY_RFO.LOCAL_CACHE */
- [ C(RESULT_ACCESS) ] = 0x01bb,
- /* OFFCORE_RESPONSE_0.ANY_RFO.ANY_LLC_MISS */
+ /* OFFCORE_RESPONSE.ANY_RFO.LOCAL_CACHE */
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ /* OFFCORE_RESPONSE.ANY_RFO.ANY_LLC_MISS */
[ C(RESULT_MISS) ] = 0x01b7,
},
[ C(OP_PREFETCH) ] = {
- /* OFFCORE_RESPONSE_0.PREFETCH.LOCAL_CACHE */
+ /* OFFCORE_RESPONSE.PREFETCH.LOCAL_CACHE */
[ C(RESULT_ACCESS) ] = 0x01b7,
- /* OFFCORE_RESPONSE_1.PREFETCH.ANY_LLC_MISS */
- [ C(RESULT_MISS) ] = 0x01bb,
+ /* OFFCORE_RESPONSE.PREFETCH.ANY_LLC_MISS */
+ [ C(RESULT_MISS) ] = 0x01b7,
},
},
[ C(DTLB) ] = {
@@ -349,19 +440,53 @@ static __initconst const u64 westmere_hw_cache_event_ids
[ C(RESULT_MISS) ] = -1,
},
},
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01b7, /* OFFCORE_RESP */
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ },
};

/*
- * OFFCORE_RESPONSE MSR bits (subset), See IA32 SDM Vol 3 30.6.1.3
+ * Nehalem/Westmere MSR_OFFCORE_RESPONSE bits;
+ * See IA32 SDM Vol 3B 30.6.1.3
*/

-#define DMND_DATA_RD (1 << 0)
-#define DMND_RFO (1 << 1)
-#define DMND_WB (1 << 3)
-#define PF_DATA_RD (1 << 4)
-#define PF_DATA_RFO (1 << 5)
-#define RESP_UNCORE_HIT (1 << 8)
-#define RESP_MISS (0xf600) /* non uncore hit */
+#define NHM_DMND_DATA_RD (1 << 0)
+#define NHM_DMND_RFO (1 << 1)
+#define NHM_DMND_IFETCH (1 << 2)
+#define NHM_DMND_WB (1 << 3)
+#define NHM_PF_DATA_RD (1 << 4)
+#define NHM_PF_DATA_RFO (1 << 5)
+#define NHM_PF_IFETCH (1 << 6)
+#define NHM_OFFCORE_OTHER (1 << 7)
+#define NHM_UNCORE_HIT (1 << 8)
+#define NHM_OTHER_CORE_HIT_SNP (1 << 9)
+#define NHM_OTHER_CORE_HITM (1 << 10)
+ /* reserved */
+#define NHM_REMOTE_CACHE_FWD (1 << 12)
+#define NHM_REMOTE_DRAM (1 << 13)
+#define NHM_LOCAL_DRAM (1 << 14)
+#define NHM_NON_DRAM (1 << 15)
+
+#define NHM_ALL_DRAM (NHM_REMOTE_DRAM|NHM_LOCAL_DRAM)
+
+#define NHM_DMND_READ (NHM_DMND_DATA_RD)
+#define NHM_DMND_WRITE (NHM_DMND_RFO|NHM_DMND_WB)
+#define NHM_DMND_PREFETCH (NHM_PF_DATA_RD|NHM_PF_DATA_RFO)
+
+#define NHM_L3_HIT (NHM_UNCORE_HIT|NHM_OTHER_CORE_HIT_SNP|NHM_OTHER_CORE_HITM)
+#define NHM_L3_MISS (NHM_NON_DRAM|NHM_ALL_DRAM|NHM_REMOTE_CACHE_FWD)
+#define NHM_L3_ACCESS (NHM_L3_HIT|NHM_L3_MISS)

static __initconst const u64 nehalem_hw_cache_extra_regs
[PERF_COUNT_HW_CACHE_MAX]
@@ -370,18 +495,32 @@ static __initconst const u64 nehalem_hw_cache_extra_regs
{
[ C(LL ) ] = {
[ C(OP_READ) ] = {
- [ C(RESULT_ACCESS) ] = DMND_DATA_RD|RESP_UNCORE_HIT,
- [ C(RESULT_MISS) ] = DMND_DATA_RD|RESP_MISS,
+ [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_L3_MISS,
},
[ C(OP_WRITE) ] = {
- [ C(RESULT_ACCESS) ] = DMND_RFO|DMND_WB|RESP_UNCORE_HIT,
- [ C(RESULT_MISS) ] = DMND_RFO|DMND_WB|RESP_MISS,
+ [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_L3_MISS,
},
[ C(OP_PREFETCH) ] = {
- [ C(RESULT_ACCESS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_UNCORE_HIT,
- [ C(RESULT_MISS) ] = PF_DATA_RD|PF_DATA_RFO|RESP_MISS,
+ [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_L3_ACCESS,
+ [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_L3_MISS,
},
}
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = NHM_DMND_READ|NHM_ALL_DRAM,
+ [ C(RESULT_MISS) ] = NHM_DMND_READ|NHM_REMOTE_DRAM,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = NHM_DMND_WRITE|NHM_ALL_DRAM,
+ [ C(RESULT_MISS) ] = NHM_DMND_WRITE|NHM_REMOTE_DRAM,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = NHM_DMND_PREFETCH|NHM_ALL_DRAM,
+ [ C(RESULT_MISS) ] = NHM_DMND_PREFETCH|NHM_REMOTE_DRAM,
+ },
+ },
};

static __initconst const u64 nehalem_hw_cache_event_ids
@@ -483,6 +622,20 @@ static __initconst const u64 nehalem_hw_cache_event_ids
[ C(RESULT_MISS) ] = -1,
},
},
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01b7, /* OFFCORE_RESP */
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = 0x01b7,
+ [ C(RESULT_MISS) ] = 0x01b7,
+ },
+ },
};

static __initconst const u64 core2_hw_cache_event_ids
@@ -574,6 +727,20 @@ static __initconst const u64 core2_hw_cache_event_ids
[ C(RESULT_MISS) ] = -1,
},
},
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
};

static __initconst const u64 atom_hw_cache_event_ids
@@ -665,6 +832,20 @@ static __initconst const u64 atom_hw_cache_event_ids
[ C(RESULT_MISS) ] = -1,
},
},
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
};

static void intel_pmu_disable_all(void)
@@ -1444,6 +1625,8 @@ static __init int intel_pmu_init(void)
case 42: /* SandyBridge */
memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, snb_hw_cache_extra_regs,
+ sizeof(hw_cache_extra_regs));

intel_pmu_lbr_init_nhm();

diff --git a/arch/x86/kernel/cpu/perf_event_p4.c b/arch/x86/kernel/cpu/perf_event_p4.c
index 74507c1..e802c7e 100644
--- a/arch/x86/kernel/cpu/perf_event_p4.c
+++ b/arch/x86/kernel/cpu/perf_event_p4.c
@@ -554,6 +554,20 @@ static __initconst const u64 p4_hw_cache_event_ids
[ C(RESULT_MISS) ] = -1,
},
},
+ [ C(NODE) ] = {
+ [ C(OP_READ) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_WRITE) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ [ C(OP_PREFETCH) ] = {
+ [ C(RESULT_ACCESS) ] = -1,
+ [ C(RESULT_MISS) ] = -1,
+ },
+ },
};

static u64 p4_general_events[PERF_COUNT_HW_MAX] = {
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index ee9f1e7..df4a841 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -59,7 +59,7 @@ enum perf_hw_id {
/*
* Generalized hardware cache events:
*
- * { L1-D, L1-I, LLC, ITLB, DTLB, BPU } x
+ * { L1-D, L1-I, LLC, ITLB, DTLB, BPU, NODE } x
* { read, write, prefetch } x
* { accesses, misses }
*/
@@ -70,6 +70,7 @@ enum perf_hw_cache_id {
PERF_COUNT_HW_CACHE_DTLB = 3,
PERF_COUNT_HW_CACHE_ITLB = 4,
PERF_COUNT_HW_CACHE_BPU = 5,
+ PERF_COUNT_HW_CACHE_NODE = 6,

PERF_COUNT_HW_CACHE_MAX, /* non-ABI */
};



\
 
 \ /
  Last update: 2011-04-23 00:57    [W:0.252 / U:0.296 seconds]
©2003-2014 Jasper Spaans. Advertise on this site