Re: [PATCH 1/1] perf tools: Add missing user space support for config1/config2

[Peter Zijlstra <peterz@infradead.org>]

On Fri, 2011-04-22 at 10:06 +0200, Ingo Molnar wrote:
> 
> I'm about to push out the patch attached below - it lays out the arguments in 
> detail. I don't think we have time to fix this properly for .39 - but memory 
> profiling could be a nice feature for v2.6.40. 

Does something like the below provide enough generic infrastructure to
allow the raw offcore bits again?

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.


Not-signed-off-by: /me
---
 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 |  167 +++++++++++++++++++++++++-------
 arch/x86/kernel/cpu/perf_event_p4.c    |   14 +++
 include/linux/perf_event.h             |    3 +-
 19 files changed, 373 insertions(+), 35 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..225efa0 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -184,26 +184,23 @@ 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 +245,20 @@ 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 +296,26 @@ 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 +360,51 @@ 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
  */
 
-#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 DMND_DATA_RD		(1 << 0)
+#define DMND_RFO		(1 << 1)
+#define DMND_IFETCH		(1 << 2)
+#define DMND_WB			(1 << 3)
+#define PF_DATA_RD		(1 << 4)
+#define PF_DATA_RFO		(1 << 5)
+#define PF_IFETCH		(1 << 6)
+#define OFFCORE_OTHER		(1 << 7)
+#define UNCORE_HIT		(1 << 8)
+#define OTHER_CORE_HIT_SNP	(1 << 9)
+#define OTHER_CORE_HITM		(1 << 10)
+				/* reserved */
+#define REMOTE_CACHE_FWD	(1 << 12)
+#define REMOTE_DRAM		(1 << 13)
+#define LOCAL_DRAM		(1 << 14)
+#define NON_DRAM		(1 << 15)
+
+#define ALL_DRAM	(REMOTE_DRAM|LOCAL_DRAM)
+
+#define DMND_READ	(DMND_DATA_RD)
+#define DMND_WRITE	(DMND_RFO|DMND_WB)
+#define DMND_PREFETCH	(PF_DATA_RD|PF_DATA_FRO)
+
+#define L3_HIT	(UNCORE_HIT|OTHER_CORE_HIT_SNP|OTHER_CORE_HITM)
+#define L3_MISS	(NON_DRAM|ALL_DRAM|REMOTE_CACHE_FWD)
 
 static __initconst const u64 nehalem_hw_cache_extra_regs
 				[PERF_COUNT_HW_CACHE_MAX]
@@ -370,18 +413,32 @@ 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) ] = DMND_READ|L3_HIT,
+		[ C(RESULT_MISS)   ] = DMND_READ|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) ] = DMND_WRITE|L3_HIT,
+		[ C(RESULT_MISS)   ] = DMND_WRITE|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) ] = DMND_PREFETCH|L3_HIT,
+		[ C(RESULT_MISS)   ] = DMND_PREFETCH|L3_MISS,
 	},
  }
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = DMND_READ|ALL_DRAM,
+		[ C(RESULT_MISS)   ] = DMND_READ|REMOTE_DRAM,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = DMND_WRITE|ALL_DRAM,
+		[ C(RESULT_MISS)   ] = DMND_WRITE|REMOTE_DRAM,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = DMND_PREFETCH|ALL_DRAM,
+		[ C(RESULT_MISS)   ] = DMND_PREFETCH|REMOTE_DRAM,
+	},
+ },
 };
 
 static __initconst const u64 nehalem_hw_cache_event_ids
@@ -483,6 +540,20 @@ 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 +645,20 @@ 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 +750,20 @@ 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)
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 */
 };