summaryrefslogtreecommitdiff
path: root/arch
diff options
context:
space:
mode:
authorHarish Chegondi <harish.chegondi@intel.com>2015-12-07 14:28:18 -0800
committerIngo Molnar <mingo@kernel.org>2016-01-06 11:15:37 +0100
commit1e7b93906249a7ccca730be03168ace15f95709e (patch)
tree623d42e00bdb7114c2ff07430ba7c40db18e0f58 /arch
parentd6980ef32570e2a26e05b1183788f4b70f1f27d0 (diff)
perf/x86/intel: Add perf core PMU support for Intel Knights Landing
Knights Landing core is based on Silvermont core with several differences. Like Silvermont, Knights Landing has 8 pairs of LBR MSRs. However, the LBR MSRs addresses match those of the Xeon cores' first 8 pairs of LBR MSRs Unlike Silvermont, Knights Landing supports hyperthreading. Knights Landing offcore response events config register mask is different from that of the Silvermont. This patch was developed based on a patch from Andi Kleen. For more details, please refer to the public document: https://software.intel.com/sites/default/files/managed/15/8d/IntelXeonPhi%E2%84%A2x200ProcessorPerformanceMonitoringReferenceManual_Volume1_Registers_v0%206.pdf Signed-off-by: Harish Chegondi <harish.chegondi@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Andi Kleen <andi.kleen@intel.com> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Harish Chegondi <harish.chegondi@gmail.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Kan Liang <kan.liang@intel.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Lukasz Anaczkowski <lukasz.anaczkowski@intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Vince Weaver <vincent.weaver@maine.edu> Link: http://lkml.kernel.org/r/d14593c7311f78c93c9cf6b006be843777c5ad5c.1449517401.git.harish.chegondi@intel.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
Diffstat (limited to 'arch')
-rw-r--r--arch/x86/kernel/cpu/perf_event.h2
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel.c62
-rw-r--r--arch/x86/kernel/cpu/perf_event_intel_lbr.c14
3 files changed, 78 insertions, 0 deletions
diff --git a/arch/x86/kernel/cpu/perf_event.h b/arch/x86/kernel/cpu/perf_event.h
index ce8768f27714..7bb61e32fb29 100644
--- a/arch/x86/kernel/cpu/perf_event.h
+++ b/arch/x86/kernel/cpu/perf_event.h
@@ -902,6 +902,8 @@ void intel_pmu_lbr_init_hsw(void);
void intel_pmu_lbr_init_skl(void);
+void intel_pmu_lbr_init_knl(void);
+
int intel_pmu_setup_lbr_filter(struct perf_event *event);
void intel_pt_interrupt(void);
diff --git a/arch/x86/kernel/cpu/perf_event_intel.c b/arch/x86/kernel/cpu/perf_event_intel.c
index 95980c0b9561..a667078a5180 100644
--- a/arch/x86/kernel/cpu/perf_event_intel.c
+++ b/arch/x86/kernel/cpu/perf_event_intel.c
@@ -185,6 +185,14 @@ struct event_constraint intel_skl_event_constraints[] = {
EVENT_CONSTRAINT_END
};
+static struct extra_reg intel_knl_extra_regs[] __read_mostly = {
+ INTEL_UEVENT_EXTRA_REG(0x01b7,
+ MSR_OFFCORE_RSP_0, 0x7f9ffbffffull, RSP_0),
+ INTEL_UEVENT_EXTRA_REG(0x02b7,
+ MSR_OFFCORE_RSP_1, 0x3f9ffbffffull, RSP_1),
+ EVENT_EXTRA_END
+};
+
static struct extra_reg intel_snb_extra_regs[] __read_mostly = {
/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x3f807f8fffull, RSP_0),
@@ -1457,6 +1465,42 @@ static __initconst const u64 slm_hw_cache_event_ids
},
};
+#define KNL_OT_L2_HITE BIT_ULL(19) /* Other Tile L2 Hit */
+#define KNL_OT_L2_HITF BIT_ULL(20) /* Other Tile L2 Hit */
+#define KNL_MCDRAM_LOCAL BIT_ULL(21)
+#define KNL_MCDRAM_FAR BIT_ULL(22)
+#define KNL_DDR_LOCAL BIT_ULL(23)
+#define KNL_DDR_FAR BIT_ULL(24)
+#define KNL_DRAM_ANY (KNL_MCDRAM_LOCAL | KNL_MCDRAM_FAR | \
+ KNL_DDR_LOCAL | KNL_DDR_FAR)
+#define KNL_L2_READ SLM_DMND_READ
+#define KNL_L2_WRITE SLM_DMND_WRITE
+#define KNL_L2_PREFETCH SLM_DMND_PREFETCH
+#define KNL_L2_ACCESS SLM_LLC_ACCESS
+#define KNL_L2_MISS (KNL_OT_L2_HITE | KNL_OT_L2_HITF | \
+ KNL_DRAM_ANY | SNB_SNP_ANY | \
+ SNB_NON_DRAM)
+
+static __initconst const u64 knl_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)] = KNL_L2_READ | KNL_L2_ACCESS,
+ [C(RESULT_MISS)] = 0,
+ },
+ [C(OP_WRITE)] = {
+ [C(RESULT_ACCESS)] = KNL_L2_WRITE | KNL_L2_ACCESS,
+ [C(RESULT_MISS)] = KNL_L2_WRITE | KNL_L2_MISS,
+ },
+ [C(OP_PREFETCH)] = {
+ [C(RESULT_ACCESS)] = KNL_L2_PREFETCH | KNL_L2_ACCESS,
+ [C(RESULT_MISS)] = KNL_L2_PREFETCH | KNL_L2_MISS,
+ },
+ },
+};
+
/*
* Use from PMIs where the LBRs are already disabled.
*/
@@ -3553,6 +3597,24 @@ __init int intel_pmu_init(void)
pr_cont("Broadwell events, ");
break;
+ case 87: /* Knights Landing Xeon Phi */
+ memcpy(hw_cache_event_ids,
+ slm_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs,
+ knl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+ intel_pmu_lbr_init_knl();
+
+ x86_pmu.event_constraints = intel_slm_event_constraints;
+ x86_pmu.pebs_constraints = intel_slm_pebs_event_constraints;
+ x86_pmu.extra_regs = intel_knl_extra_regs;
+
+ /* all extra regs are per-cpu when HT is on */
+ x86_pmu.flags |= PMU_FL_HAS_RSP_1;
+ x86_pmu.flags |= PMU_FL_NO_HT_SHARING;
+
+ pr_cont("Knights Landing events, ");
+ break;
+
case 78: /* 14nm Skylake Mobile */
case 94: /* 14nm Skylake Desktop */
x86_pmu.late_ack = true;
diff --git a/arch/x86/kernel/cpu/perf_event_intel_lbr.c b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
index 1390148ee2e6..653f88d25987 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_lbr.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_lbr.c
@@ -1046,3 +1046,17 @@ void __init intel_pmu_lbr_init_atom(void)
*/
pr_cont("8-deep LBR, ");
}
+
+/* Knights Landing */
+void intel_pmu_lbr_init_knl(void)
+{
+ x86_pmu.lbr_nr = 8;
+ x86_pmu.lbr_tos = MSR_LBR_TOS;
+ x86_pmu.lbr_from = MSR_LBR_NHM_FROM;
+ x86_pmu.lbr_to = MSR_LBR_NHM_TO;
+
+ x86_pmu.lbr_sel_mask = LBR_SEL_MASK;
+ x86_pmu.lbr_sel_map = snb_lbr_sel_map;
+
+ pr_cont("8-deep LBR, ");
+}