perf, arch: Add generic NODE cache events

Add a NODE level to the generic cache events which is used to measure
local vs remote memory accesses. Like all other cache events, an
ACCESS is HIT+MISS, if there is no way to distinguish between reads
and writes do reads only etc..

The below needs filling out for !x86 (which I filled out with
unsupported events).

I'm fairly sure ARM can leave it like that since it doesn't strike me as
an architecture that even has NUMA support. SH might have something since
it does appear to have some NUMA bits.

Sparc64, PowerPC and MIPS certainly want a good look there since they
clearly are NUMA capable.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: David Miller <davem@davemloft.net>
Cc: Anton Blanchard <anton@samba.org>
Cc: David Daney <ddaney@caviumnetworks.com>
Cc: Deng-Cheng Zhu <dengcheng.zhu@gmail.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Stephane Eranian <eranian@google.com>
Link: http://lkml.kernel.org/r/1303508226.4865.8.camel@laptopSigned-off-by: Ingo Molnar <mingo@elte.hu>

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

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,
+		},
+	},
 };
 
 /*

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

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

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;

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 = {

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 = {

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 = {

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 = {

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 = {

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 = {

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 = {

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)

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)

arch/sparc/kernel/perf_event.c

@@ -246,6 +246,20 @@ 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 = {
@@ -361,6 +375,20 @@ 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 = {
@@ -473,6 +501,20 @@ 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 = {

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,
+	},
+ },
 };
 
 /*

arch/x86/kernel/cpu/perf_event_intel.c

@@ -226,6 +226,21 @@ static __initconst const u64 snb_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 westmere_hw_cache_event_ids
@@ -327,6 +342,20 @@ static __initconst const u64 westmere_hw_cache_event_ids
 		[ C(RESULT_MISS)   ] = -1,
 	},
  },
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		[ 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,
+	},
+ },
 };
 
 /*
@@ -379,7 +408,21 @@ static __initconst const u64 nehalem_hw_cache_extra_regs
 		[ 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
@@ -481,6 +524,20 @@ static __initconst const u64 nehalem_hw_cache_event_ids
 		[ C(RESULT_MISS)   ] = -1,
 	},
  },
+ [ C(NODE) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x01b7,
+		[ 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

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] = {

include/linux/perf_event.h

@@ -61,7 +61,7 @@ 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 }
  */
@@ -72,6 +72,7 @@ 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 */
 };