Skip to contentSkip to conversation

perf_counter, x86: Implement generalized cache event types, add AMD support

tip:perfcounters/core tip-bot for Thomas Gleixner 1 participant 1 message Jun 8, 2009 x86

lore
Share & tools
lore
#0 lore raw
Commit-ID:  f86748e91a14bd6cc49477560f33ed5d59896e89
Gitweb:     http://git.kernel.org/tip/f86748e91a14bd6cc49477560f33ed5d59896e89
Author:     Thomas Gleixner <[email protected]>
AuthorDate: Mon, 8 Jun 2009 22:33:10 +0200
Committer:  Ingo Molnar <[email protected]>
CommitDate: Mon, 8 Jun 2009 23:10:37 +0200

perf_counter, x86: Implement generalized cache event types, add AMD support

Fill in amd_hw_cache_event_id[] with the AMD CPU specific events, for family 0x0f, 0x10 and 0x11.

There's apparently no distinction between load and store events, so we only fill in the load events.

Cc Peter Zijlstra <[email protected]>
Cc Mike Galbraith <[email protected]>
Cc Paul Mackerras <[email protected]>
Cc Arnaldo Carvalho de Melo <[email protected]>

LKML-Reference: <new-submission>

---
 arch/x86/kernel/cpu/perf_counter.c |  102 ++++++++++++++++++++++++++++++++++++
 1 files changed, 102 insertions(+), 0 deletions(-)
arch/x86/kernel/cpu/perf_counter.c +102 -0
index 0339d19..93af821 100644
@@ -389,6 +389,97 @@ static u64 intel_pmu_raw_event(u64 event)
 	return event & CORE_EVNTSEL_MASK;
 }
 
+static const u64 amd_0f_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] =
+{
+ [ C(L1D) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(L1I ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080, /* Instruction cache fetches  */
+		[ C(RESULT_MISS)   ] = 0x0081, /* Instruction cache misses   */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(L2  ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(DTLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = 0,
+		[ C(RESULT_MISS)   ] = 0,
+	},
+ },
+ [ C(ITLB) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x0080, /* Instruction fecthes        */
+		[ C(RESULT_MISS)   ] = 0x0085, /* Instr. fetch ITLB misses   */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+ [ C(BPU ) ] = {
+	[ C(OP_READ) ] = {
+		[ C(RESULT_ACCESS) ] = 0x00c2, /* Retired Branch Instr.      */
+		[ C(RESULT_MISS)   ] = 0x00c3, /* Retired Mispredicted BI    */
+	},
+	[ C(OP_WRITE) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+	[ C(OP_PREFETCH) ] = {
+		[ C(RESULT_ACCESS) ] = -1,
+		[ C(RESULT_MISS)   ] = -1,
+	},
+ },
+};
+
 /*
  * AMD Performance Monitor K7 and later.
  */
@@ -1345,6 +1436,17 @@ static int intel_pmu_init(void)
 static int amd_pmu_init(void)
 {
 	x86_pmu = amd_pmu;
+
+	switch (boot_cpu_data.x86) {
+	case 0x0f:
+	case 0x10:
+	case 0x11:
+		memcpy(hw_cache_event_ids, amd_0f_hw_cache_event_ids,
+		       sizeof(hw_cache_event_ids));
+
+		pr_cont("AMD Family 0f/10/11 events, ");
+		break;
+	}
 	return 0;
 }