diff options
Diffstat (limited to 'arch/x86/events/perf_event.h')
| -rw-r--r-- | arch/x86/events/perf_event.h | 136 |
1 files changed, 99 insertions, 37 deletions
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h index a75955741c50..07fc84bb85c1 100644 --- a/arch/x86/events/perf_event.h +++ b/arch/x86/events/perf_event.h @@ -49,28 +49,33 @@ struct event_constraint { unsigned long idxmsk[BITS_TO_LONGS(X86_PMC_IDX_MAX)]; u64 idxmsk64; }; - u64 code; - u64 cmask; - int weight; - int overlap; - int flags; + u64 code; + u64 cmask; + int weight; + int overlap; + int flags; + unsigned int size; }; + +static inline bool constraint_match(struct event_constraint *c, u64 ecode) +{ + return ((ecode & c->cmask) - c->code) <= (u64)c->size; +} + /* * struct hw_perf_event.flags flags */ #define PERF_X86_EVENT_PEBS_LDLAT 0x0001 /* ld+ldlat data address sampling */ #define PERF_X86_EVENT_PEBS_ST 0x0002 /* st data address sampling */ #define PERF_X86_EVENT_PEBS_ST_HSW 0x0004 /* haswell style datala, store */ -#define PERF_X86_EVENT_COMMITTED 0x0008 /* event passed commit_txn */ -#define PERF_X86_EVENT_PEBS_LD_HSW 0x0010 /* haswell style datala, load */ -#define PERF_X86_EVENT_PEBS_NA_HSW 0x0020 /* haswell style datala, unknown */ -#define PERF_X86_EVENT_EXCL 0x0040 /* HT exclusivity on counter */ -#define PERF_X86_EVENT_DYNAMIC 0x0080 /* dynamic alloc'd constraint */ -#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0100 /* grant rdpmc permission */ -#define PERF_X86_EVENT_EXCL_ACCT 0x0200 /* accounted EXCL event */ -#define PERF_X86_EVENT_AUTO_RELOAD 0x0400 /* use PEBS auto-reload */ -#define PERF_X86_EVENT_LARGE_PEBS 0x0800 /* use large PEBS */ - +#define PERF_X86_EVENT_PEBS_LD_HSW 0x0008 /* haswell style datala, load */ +#define PERF_X86_EVENT_PEBS_NA_HSW 0x0010 /* haswell style datala, unknown */ +#define PERF_X86_EVENT_EXCL 0x0020 /* HT exclusivity on counter */ +#define PERF_X86_EVENT_DYNAMIC 0x0040 /* dynamic alloc'd constraint */ +#define PERF_X86_EVENT_RDPMC_ALLOWED 0x0080 /* grant rdpmc permission */ +#define PERF_X86_EVENT_EXCL_ACCT 0x0100 /* accounted EXCL event */ +#define PERF_X86_EVENT_AUTO_RELOAD 0x0200 /* use PEBS auto-reload */ +#define PERF_X86_EVENT_LARGE_PEBS 0x0400 /* use large PEBS */ struct amd_nb { int nb_id; /* NorthBridge id */ @@ -96,25 +101,43 @@ struct amd_nb { PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER | \ PERF_SAMPLE_PERIOD) -#define PEBS_REGS \ - (PERF_REG_X86_AX | \ - PERF_REG_X86_BX | \ - PERF_REG_X86_CX | \ - PERF_REG_X86_DX | \ - PERF_REG_X86_DI | \ - PERF_REG_X86_SI | \ - PERF_REG_X86_SP | \ - PERF_REG_X86_BP | \ - PERF_REG_X86_IP | \ - PERF_REG_X86_FLAGS | \ - PERF_REG_X86_R8 | \ - PERF_REG_X86_R9 | \ - PERF_REG_X86_R10 | \ - PERF_REG_X86_R11 | \ - PERF_REG_X86_R12 | \ - PERF_REG_X86_R13 | \ - PERF_REG_X86_R14 | \ - PERF_REG_X86_R15) +#define PEBS_GP_REGS \ + ((1ULL << PERF_REG_X86_AX) | \ + (1ULL << PERF_REG_X86_BX) | \ + (1ULL << PERF_REG_X86_CX) | \ + (1ULL << PERF_REG_X86_DX) | \ + (1ULL << PERF_REG_X86_DI) | \ + (1ULL << PERF_REG_X86_SI) | \ + (1ULL << PERF_REG_X86_SP) | \ + (1ULL << PERF_REG_X86_BP) | \ + (1ULL << PERF_REG_X86_IP) | \ + (1ULL << PERF_REG_X86_FLAGS) | \ + (1ULL << PERF_REG_X86_R8) | \ + (1ULL << PERF_REG_X86_R9) | \ + (1ULL << PERF_REG_X86_R10) | \ + (1ULL << PERF_REG_X86_R11) | \ + (1ULL << PERF_REG_X86_R12) | \ + (1ULL << PERF_REG_X86_R13) | \ + (1ULL << PERF_REG_X86_R14) | \ + (1ULL << PERF_REG_X86_R15)) + +#define PEBS_XMM_REGS \ + ((1ULL << PERF_REG_X86_XMM0) | \ + (1ULL << PERF_REG_X86_XMM1) | \ + (1ULL << PERF_REG_X86_XMM2) | \ + (1ULL << PERF_REG_X86_XMM3) | \ + (1ULL << PERF_REG_X86_XMM4) | \ + (1ULL << PERF_REG_X86_XMM5) | \ + (1ULL << PERF_REG_X86_XMM6) | \ + (1ULL << PERF_REG_X86_XMM7) | \ + (1ULL << PERF_REG_X86_XMM8) | \ + (1ULL << PERF_REG_X86_XMM9) | \ + (1ULL << PERF_REG_X86_XMM10) | \ + (1ULL << PERF_REG_X86_XMM11) | \ + (1ULL << PERF_REG_X86_XMM12) | \ + (1ULL << PERF_REG_X86_XMM13) | \ + (1ULL << PERF_REG_X86_XMM14) | \ + (1ULL << PERF_REG_X86_XMM15)) /* * Per register state. @@ -207,10 +230,16 @@ struct cpu_hw_events { int n_pebs; int n_large_pebs; + /* Current super set of events hardware configuration */ + u64 pebs_data_cfg; + u64 active_pebs_data_cfg; + int pebs_record_size; + /* * Intel LBR bits */ int lbr_users; + int lbr_pebs_users; struct perf_branch_stack lbr_stack; struct perf_branch_entry lbr_entries[MAX_LBR_ENTRIES]; struct er_account *lbr_sel; @@ -257,18 +286,29 @@ struct cpu_hw_events { void *kfree_on_online[X86_PERF_KFREE_MAX]; }; -#define __EVENT_CONSTRAINT(c, n, m, w, o, f) {\ +#define __EVENT_CONSTRAINT_RANGE(c, e, n, m, w, o, f) { \ { .idxmsk64 = (n) }, \ .code = (c), \ + .size = (e) - (c), \ .cmask = (m), \ .weight = (w), \ .overlap = (o), \ .flags = f, \ } +#define __EVENT_CONSTRAINT(c, n, m, w, o, f) \ + __EVENT_CONSTRAINT_RANGE(c, c, n, m, w, o, f) + #define EVENT_CONSTRAINT(c, n, m) \ __EVENT_CONSTRAINT(c, n, m, HWEIGHT(n), 0, 0) +/* + * The constraint_match() function only works for 'simple' event codes + * and not for extended (AMD64_EVENTSEL_EVENT) events codes. + */ +#define EVENT_CONSTRAINT_RANGE(c, e, n, m) \ + __EVENT_CONSTRAINT_RANGE(c, e, n, m, HWEIGHT(n), 0, 0) + #define INTEL_EXCLEVT_CONSTRAINT(c, n) \ __EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT, HWEIGHT(n),\ 0, PERF_X86_EVENT_EXCL) @@ -304,6 +344,12 @@ struct cpu_hw_events { EVENT_CONSTRAINT(c, n, ARCH_PERFMON_EVENTSEL_EVENT) /* + * Constraint on a range of Event codes + */ +#define INTEL_EVENT_CONSTRAINT_RANGE(c, e, n) \ + EVENT_CONSTRAINT_RANGE(c, e, n, ARCH_PERFMON_EVENTSEL_EVENT) + +/* * Constraint on the Event code + UMask + fixed-mask * * filter mask to validate fixed counter events. @@ -350,6 +396,9 @@ struct cpu_hw_events { #define INTEL_FLAGS_EVENT_CONSTRAINT(c, n) \ EVENT_CONSTRAINT(c, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) +#define INTEL_FLAGS_EVENT_CONSTRAINT_RANGE(c, e, n) \ + EVENT_CONSTRAINT_RANGE(c, e, n, INTEL_ARCH_EVENT_MASK|X86_ALL_EVENT_FLAGS) + /* Check only flags, but allow all event/umask */ #define INTEL_ALL_EVENT_CONSTRAINT(code, n) \ EVENT_CONSTRAINT(code, n, X86_ALL_EVENT_FLAGS) @@ -366,6 +415,11 @@ struct cpu_hw_events { ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) +#define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(code, end, n) \ + __EVENT_CONSTRAINT_RANGE(code, end, n, \ + ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ + HWEIGHT(n), 0, PERF_X86_EVENT_PEBS_LD_HSW) + #define INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_XLD(code, n) \ __EVENT_CONSTRAINT(code, n, \ ARCH_PERFMON_EVENTSEL_EVENT|X86_ALL_EVENT_FLAGS, \ @@ -473,6 +527,7 @@ union perf_capabilities { * values > 32bit. */ u64 full_width_write:1; + u64 pebs_baseline:1; }; u64 capabilities; }; @@ -613,14 +668,16 @@ struct x86_pmu { pebs_broken :1, pebs_prec_dist :1, pebs_no_tlb :1, - pebs_no_isolation :1; + pebs_no_isolation :1, + pebs_no_xmm_regs :1; int pebs_record_size; int pebs_buffer_size; + int max_pebs_events; void (*drain_pebs)(struct pt_regs *regs); struct event_constraint *pebs_constraints; void (*pebs_aliases)(struct perf_event *event); - int max_pebs_events; unsigned long large_pebs_flags; + u64 rtm_abort_event; /* * Intel LBR @@ -714,6 +771,7 @@ static struct perf_pmu_events_ht_attr event_attr_##v = { \ .event_str_ht = ht, \ } +struct pmu *x86_get_pmu(void); extern struct x86_pmu x86_pmu __read_mostly; static inline bool x86_pmu_has_lbr_callstack(void) @@ -941,6 +999,8 @@ extern struct event_constraint intel_bdw_pebs_event_constraints[]; extern struct event_constraint intel_skl_pebs_event_constraints[]; +extern struct event_constraint intel_icl_pebs_event_constraints[]; + struct event_constraint *intel_pebs_constraints(struct perf_event *event); void intel_pmu_pebs_add(struct perf_event *event); @@ -959,6 +1019,8 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in); void intel_pmu_auto_reload_read(struct perf_event *event); +void intel_pmu_store_pebs_lbrs(struct pebs_lbr *lbr); + void intel_ds_init(void); void intel_pmu_lbr_sched_task(struct perf_event_context *ctx, bool sched_in); |