diff options
Diffstat (limited to 'arch/x86/events/intel/ds.c')
| -rw-r--r-- | arch/x86/events/intel/ds.c | 1538 |
1 files changed, 1239 insertions, 299 deletions
diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c index 8647713276a7..feb1c3cf63e4 100644 --- a/arch/x86/events/intel/ds.c +++ b/arch/x86/events/intel/ds.c @@ -2,12 +2,16 @@ #include <linux/bitops.h> #include <linux/types.h> #include <linux/slab.h> +#include <linux/sched/clock.h> #include <asm/cpu_entry_area.h> +#include <asm/debugreg.h> #include <asm/perf_event.h> #include <asm/tlbflush.h> #include <asm/insn.h> #include <asm/io.h> +#include <asm/msr.h> +#include <asm/timer.h> #include "../perf_event.h" @@ -53,6 +57,22 @@ union intel_x86_pebs_dse { unsigned int st_lat_locked:1; unsigned int ld_reserved3:26; }; + struct { + unsigned int mtl_dse:5; + unsigned int mtl_locked:1; + unsigned int mtl_stlb_miss:1; + unsigned int mtl_fwd_blk:1; + unsigned int ld_reserved4:24; + }; + struct { + unsigned int lnc_dse:8; + unsigned int ld_reserved5:2; + unsigned int lnc_stlb_miss:1; + unsigned int lnc_locked:1; + unsigned int lnc_data_blk:1; + unsigned int lnc_addr_blk:1; + unsigned int ld_reserved6:18; + }; }; @@ -67,7 +87,7 @@ union intel_x86_pebs_dse { #define SNOOP_NONE_MISS (P(SNOOP, NONE) | P(SNOOP, MISS)) /* Version for Sandy Bridge and later */ -static u64 pebs_data_source[] = { +static u64 pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = { P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA),/* 0x00:ukn L3 */ OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 local */ OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x02: LFB hit */ @@ -94,15 +114,118 @@ void __init intel_pmu_pebs_data_source_nhm(void) pebs_data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); } -void __init intel_pmu_pebs_data_source_skl(bool pmem) +static void __init __intel_pmu_pebs_data_source_skl(bool pmem, u64 *data_source) { u64 pmem_or_l4 = pmem ? LEVEL(PMEM) : LEVEL(L4); - pebs_data_source[0x08] = OP_LH | pmem_or_l4 | P(SNOOP, HIT); - pebs_data_source[0x09] = OP_LH | pmem_or_l4 | REM | P(SNOOP, HIT); - pebs_data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE); - pebs_data_source[0x0c] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOPX, FWD); - pebs_data_source[0x0d] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOP, HITM); + data_source[0x08] = OP_LH | pmem_or_l4 | P(SNOOP, HIT); + data_source[0x09] = OP_LH | pmem_or_l4 | REM | P(SNOOP, HIT); + data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE); + data_source[0x0c] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOPX, FWD); + data_source[0x0d] = OP_LH | LEVEL(ANY_CACHE) | REM | P(SNOOP, HITM); +} + +void __init intel_pmu_pebs_data_source_skl(bool pmem) +{ + __intel_pmu_pebs_data_source_skl(pmem, pebs_data_source); +} + +static void __init __intel_pmu_pebs_data_source_grt(u64 *data_source) +{ + data_source[0x05] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HIT); + data_source[0x06] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); + data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD); +} + +void __init intel_pmu_pebs_data_source_grt(void) +{ + __intel_pmu_pebs_data_source_grt(pebs_data_source); +} + +void __init intel_pmu_pebs_data_source_adl(void) +{ + u64 *data_source; + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].pebs_data_source; + memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); + __intel_pmu_pebs_data_source_skl(false, data_source); + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source; + memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); + __intel_pmu_pebs_data_source_grt(data_source); +} + +static void __init __intel_pmu_pebs_data_source_cmt(u64 *data_source) +{ + data_source[0x07] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD); + data_source[0x08] = OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM); + data_source[0x0a] = OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, NONE); + data_source[0x0b] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, NONE); + data_source[0x0c] = OP_LH | LEVEL(RAM) | REM | P(SNOOPX, FWD); + data_source[0x0d] = OP_LH | LEVEL(RAM) | REM | P(SNOOP, HITM); +} + +void __init intel_pmu_pebs_data_source_mtl(void) +{ + u64 *data_source; + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].pebs_data_source; + memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); + __intel_pmu_pebs_data_source_skl(false, data_source); + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source; + memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); + __intel_pmu_pebs_data_source_cmt(data_source); +} + +void __init intel_pmu_pebs_data_source_arl_h(void) +{ + u64 *data_source; + + intel_pmu_pebs_data_source_lnl(); + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_TINY_IDX].pebs_data_source; + memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); + __intel_pmu_pebs_data_source_cmt(data_source); +} + +void __init intel_pmu_pebs_data_source_cmt(void) +{ + __intel_pmu_pebs_data_source_cmt(pebs_data_source); +} + +/* Version for Lion Cove and later */ +static u64 lnc_pebs_data_source[PERF_PEBS_DATA_SOURCE_MAX] = { + P(OP, LOAD) | P(LVL, MISS) | LEVEL(L3) | P(SNOOP, NA), /* 0x00: ukn L3 */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x01: L1 hit */ + OP_LH | P(LVL, L1) | LEVEL(L1) | P(SNOOP, NONE), /* 0x02: L1 hit */ + OP_LH | P(LVL, LFB) | LEVEL(LFB) | P(SNOOP, NONE), /* 0x03: LFB/L1 Miss Handling Buffer hit */ + 0, /* 0x04: Reserved */ + OP_LH | P(LVL, L2) | LEVEL(L2) | P(SNOOP, NONE), /* 0x05: L2 Hit */ + OP_LH | LEVEL(L2_MHB) | P(SNOOP, NONE), /* 0x06: L2 Miss Handling Buffer Hit */ + 0, /* 0x07: Reserved */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, NONE), /* 0x08: L3 Hit */ + 0, /* 0x09: Reserved */ + 0, /* 0x0a: Reserved */ + 0, /* 0x0b: Reserved */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOPX, FWD), /* 0x0c: L3 Hit Snoop Fwd */ + OP_LH | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x0d: L3 Hit Snoop HitM */ + 0, /* 0x0e: Reserved */ + P(OP, LOAD) | P(LVL, MISS) | P(LVL, L3) | LEVEL(L3) | P(SNOOP, HITM), /* 0x0f: L3 Miss Snoop HitM */ + OP_LH | LEVEL(MSC) | P(SNOOP, NONE), /* 0x10: Memory-side Cache Hit */ + OP_LH | P(LVL, LOC_RAM) | LEVEL(RAM) | P(SNOOP, NONE), /* 0x11: Local Memory Hit */ +}; + +void __init intel_pmu_pebs_data_source_lnl(void) +{ + u64 *data_source; + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX].pebs_data_source; + memcpy(data_source, lnc_pebs_data_source, sizeof(lnc_pebs_data_source)); + + data_source = x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX].pebs_data_source; + memcpy(data_source, pebs_data_source, sizeof(pebs_data_source)); + __intel_pmu_pebs_data_source_cmt(data_source); } static u64 precise_store_data(u64 status) @@ -171,7 +294,124 @@ static u64 precise_datala_hsw(struct perf_event *event, u64 status) return dse.val; } -static u64 load_latency_data(u64 status) +static inline void pebs_set_tlb_lock(u64 *val, bool tlb, bool lock) +{ + /* + * TLB access + * 0 = did not miss 2nd level TLB + * 1 = missed 2nd level TLB + */ + if (tlb) + *val |= P(TLB, MISS) | P(TLB, L2); + else + *val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); + + /* locked prefix */ + if (lock) + *val |= P(LOCK, LOCKED); +} + +/* Retrieve the latency data for e-core of ADL */ +static u64 __grt_latency_data(struct perf_event *event, u64 status, + u8 dse, bool tlb, bool lock, bool blk) +{ + u64 val; + + WARN_ON_ONCE(is_hybrid() && + hybrid_pmu(event->pmu)->pmu_type == hybrid_big); + + dse &= PERF_PEBS_DATA_SOURCE_GRT_MASK; + val = hybrid_var(event->pmu, pebs_data_source)[dse]; + + pebs_set_tlb_lock(&val, tlb, lock); + + if (blk) + val |= P(BLK, DATA); + else + val |= P(BLK, NA); + + return val; +} + +u64 grt_latency_data(struct perf_event *event, u64 status) +{ + union intel_x86_pebs_dse dse; + + dse.val = status; + + return __grt_latency_data(event, status, dse.ld_dse, + dse.ld_locked, dse.ld_stlb_miss, + dse.ld_data_blk); +} + +/* Retrieve the latency data for e-core of MTL */ +u64 cmt_latency_data(struct perf_event *event, u64 status) +{ + union intel_x86_pebs_dse dse; + + dse.val = status; + + return __grt_latency_data(event, status, dse.mtl_dse, + dse.mtl_stlb_miss, dse.mtl_locked, + dse.mtl_fwd_blk); +} + +static u64 lnc_latency_data(struct perf_event *event, u64 status) +{ + union intel_x86_pebs_dse dse; + union perf_mem_data_src src; + u64 val; + + dse.val = status; + + /* LNC core latency data */ + val = hybrid_var(event->pmu, pebs_data_source)[status & PERF_PEBS_DATA_SOURCE_MASK]; + if (!val) + val = P(OP, LOAD) | LEVEL(NA) | P(SNOOP, NA); + + if (dse.lnc_stlb_miss) + val |= P(TLB, MISS) | P(TLB, L2); + else + val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); + + if (dse.lnc_locked) + val |= P(LOCK, LOCKED); + + if (dse.lnc_data_blk) + val |= P(BLK, DATA); + if (dse.lnc_addr_blk) + val |= P(BLK, ADDR); + if (!dse.lnc_data_blk && !dse.lnc_addr_blk) + val |= P(BLK, NA); + + src.val = val; + if (event->hw.flags & PERF_X86_EVENT_PEBS_ST_HSW) + src.mem_op = P(OP, STORE); + + return src.val; +} + +u64 lnl_latency_data(struct perf_event *event, u64 status) +{ + struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); + + if (pmu->pmu_type == hybrid_small) + return cmt_latency_data(event, status); + + return lnc_latency_data(event, status); +} + +u64 arl_h_latency_data(struct perf_event *event, u64 status) +{ + struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); + + if (pmu->pmu_type == hybrid_tiny) + return cmt_latency_data(event, status); + + return lnl_latency_data(event, status); +} + +static u64 load_latency_data(struct perf_event *event, u64 status) { union intel_x86_pebs_dse dse; u64 val; @@ -181,7 +421,7 @@ static u64 load_latency_data(u64 status) /* * use the mapping table for bit 0-3 */ - val = pebs_data_source[dse.ld_dse]; + val = hybrid_var(event->pmu, pebs_data_source)[dse.ld_dse]; /* * Nehalem models do not support TLB, Lock infos @@ -190,21 +430,8 @@ static u64 load_latency_data(u64 status) val |= P(TLB, NA) | P(LOCK, NA); return val; } - /* - * bit 4: TLB access - * 0 = did not miss 2nd level TLB - * 1 = missed 2nd level TLB - */ - if (dse.ld_stlb_miss) - val |= P(TLB, MISS) | P(TLB, L2); - else - val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); - /* - * bit 5: locked prefix - */ - if (dse.ld_locked) - val |= P(LOCK, LOCKED); + pebs_set_tlb_lock(&val, dse.ld_stlb_miss, dse.ld_locked); /* * Ice Lake and earlier models do not support block infos. @@ -233,9 +460,10 @@ static u64 load_latency_data(u64 status) return val; } -static u64 store_latency_data(u64 status) +static u64 store_latency_data(struct perf_event *event, u64 status) { union intel_x86_pebs_dse dse; + union perf_mem_data_src src; u64 val; dse.val = status; @@ -243,27 +471,20 @@ static u64 store_latency_data(u64 status) /* * use the mapping table for bit 0-3 */ - val = pebs_data_source[dse.st_lat_dse]; + val = hybrid_var(event->pmu, pebs_data_source)[dse.st_lat_dse]; - /* - * bit 4: TLB access - * 0 = did not miss 2nd level TLB - * 1 = missed 2nd level TLB - */ - if (dse.st_lat_stlb_miss) - val |= P(TLB, MISS) | P(TLB, L2); - else - val |= P(TLB, HIT) | P(TLB, L1) | P(TLB, L2); + pebs_set_tlb_lock(&val, dse.st_lat_stlb_miss, dse.st_lat_locked); + + val |= P(BLK, NA); /* - * bit 5: locked prefix + * the pebs_data_source table is only for loads + * so override the mem_op to say STORE instead */ - if (dse.st_lat_locked) - val |= P(LOCK, LOCKED); + src.val = val; + src.mem_op = P(OP,STORE); - val |= P(BLK, NA); - - return val; + return src.val; } struct pebs_record_core { @@ -405,13 +626,18 @@ static int alloc_pebs_buffer(int cpu) int max, node = cpu_to_node(cpu); void *buffer, *insn_buff, *cea; - if (!x86_pmu.pebs) + if (!intel_pmu_has_pebs()) return 0; buffer = dsalloc_pages(bsiz, GFP_KERNEL, cpu); if (unlikely(!buffer)) return -ENOMEM; + if (x86_pmu.arch_pebs) { + hwev->pebs_vaddr = buffer; + return 0; + } + /* * HSW+ already provides us the eventing ip; no need to allocate this * buffer then. @@ -424,7 +650,7 @@ static int alloc_pebs_buffer(int cpu) } per_cpu(insn_buffer, cpu) = insn_buff; } - hwev->ds_pebs_vaddr = buffer; + hwev->pebs_vaddr = buffer; /* Update the cpu entry area mapping */ cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer; ds->pebs_buffer_base = (unsigned long) cea; @@ -440,17 +666,20 @@ static void release_pebs_buffer(int cpu) struct cpu_hw_events *hwev = per_cpu_ptr(&cpu_hw_events, cpu); void *cea; - if (!x86_pmu.pebs) + if (!intel_pmu_has_pebs()) return; - kfree(per_cpu(insn_buffer, cpu)); - per_cpu(insn_buffer, cpu) = NULL; + if (x86_pmu.ds_pebs) { + kfree(per_cpu(insn_buffer, cpu)); + per_cpu(insn_buffer, cpu) = NULL; - /* Clear the fixmap */ - cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer; - ds_clear_cea(cea, x86_pmu.pebs_buffer_size); - dsfree_pages(hwev->ds_pebs_vaddr, x86_pmu.pebs_buffer_size); - hwev->ds_pebs_vaddr = NULL; + /* Clear the fixmap */ + cea = &get_cpu_entry_area(cpu)->cpu_debug_buffers.pebs_buffer; + ds_clear_cea(cea, x86_pmu.pebs_buffer_size); + } + + dsfree_pages(hwev->pebs_vaddr, x86_pmu.pebs_buffer_size); + hwev->pebs_vaddr = NULL; } static int alloc_bts_buffer(int cpu) @@ -515,7 +744,7 @@ void release_ds_buffers(void) { int cpu; - if (!x86_pmu.bts && !x86_pmu.pebs) + if (!x86_pmu.bts && !x86_pmu.ds_pebs) return; for_each_possible_cpu(cpu) @@ -531,7 +760,8 @@ void release_ds_buffers(void) } for_each_possible_cpu(cpu) { - release_pebs_buffer(cpu); + if (x86_pmu.ds_pebs) + release_pebs_buffer(cpu); release_bts_buffer(cpu); } } @@ -542,15 +772,17 @@ void reserve_ds_buffers(void) int cpu; x86_pmu.bts_active = 0; - x86_pmu.pebs_active = 0; - if (!x86_pmu.bts && !x86_pmu.pebs) + if (x86_pmu.ds_pebs) + x86_pmu.pebs_active = 0; + + if (!x86_pmu.bts && !x86_pmu.ds_pebs) return; if (!x86_pmu.bts) bts_err = 1; - if (!x86_pmu.pebs) + if (!x86_pmu.ds_pebs) pebs_err = 1; for_each_possible_cpu(cpu) { @@ -562,7 +794,8 @@ void reserve_ds_buffers(void) if (!bts_err && alloc_bts_buffer(cpu)) bts_err = 1; - if (!pebs_err && alloc_pebs_buffer(cpu)) + if (x86_pmu.ds_pebs && !pebs_err && + alloc_pebs_buffer(cpu)) pebs_err = 1; if (bts_err && pebs_err) @@ -574,7 +807,7 @@ void reserve_ds_buffers(void) release_bts_buffer(cpu); } - if (pebs_err) { + if (x86_pmu.ds_pebs && pebs_err) { for_each_possible_cpu(cpu) release_pebs_buffer(cpu); } @@ -586,7 +819,7 @@ void reserve_ds_buffers(void) if (x86_pmu.bts && !bts_err) x86_pmu.bts_active = 1; - if (x86_pmu.pebs && !pebs_err) + if (x86_pmu.ds_pebs && !pebs_err) x86_pmu.pebs_active = 1; for_each_possible_cpu(cpu) { @@ -599,6 +832,56 @@ void reserve_ds_buffers(void) } } +inline int alloc_arch_pebs_buf_on_cpu(int cpu) +{ + if (!x86_pmu.arch_pebs) + return 0; + + return alloc_pebs_buffer(cpu); +} + +inline void release_arch_pebs_buf_on_cpu(int cpu) +{ + if (!x86_pmu.arch_pebs) + return; + + release_pebs_buffer(cpu); +} + +void init_arch_pebs_on_cpu(int cpu) +{ + struct cpu_hw_events *cpuc = per_cpu_ptr(&cpu_hw_events, cpu); + u64 arch_pebs_base; + + if (!x86_pmu.arch_pebs) + return; + + if (!cpuc->pebs_vaddr) { + WARN(1, "Fail to allocate PEBS buffer on CPU %d\n", cpu); + x86_pmu.pebs_active = 0; + return; + } + + /* + * 4KB-aligned pointer of the output buffer + * (__alloc_pages_node() return page aligned address) + * Buffer Size = 4KB * 2^SIZE + * contiguous physical buffer (__alloc_pages_node() with order) + */ + arch_pebs_base = virt_to_phys(cpuc->pebs_vaddr) | PEBS_BUFFER_SHIFT; + wrmsr_on_cpu(cpu, MSR_IA32_PEBS_BASE, (u32)arch_pebs_base, + (u32)(arch_pebs_base >> 32)); + x86_pmu.pebs_active = 1; +} + +inline void fini_arch_pebs_on_cpu(int cpu) +{ + if (!x86_pmu.arch_pebs) + return; + + wrmsr_on_cpu(cpu, MSR_IA32_PEBS_BASE, 0, 0); +} + /* * BTS */ @@ -705,7 +988,8 @@ int intel_pmu_drain_bts_buffer(void) * the sample. */ rcu_read_lock(); - perf_prepare_sample(&header, &data, event, ®s); + perf_prepare_sample(&data, event, ®s); + perf_prepare_header(&header, &data, event, ®s); if (perf_output_begin(&handle, &data, event, header.size * (top - base - skip))) @@ -733,11 +1017,11 @@ unlock: return 1; } -static inline void intel_pmu_drain_pebs_buffer(void) +void intel_pmu_drain_pebs_buffer(void) { struct perf_sample_data data; - x86_pmu.drain_pebs(NULL, &data); + static_call(x86_pmu_drain_pebs)(NULL, &data); } /* @@ -781,8 +1065,8 @@ struct event_constraint intel_glm_pebs_event_constraints[] = { struct event_constraint intel_grt_pebs_event_constraints[] = { /* Allow all events as PEBS with no flags */ - INTEL_PLD_CONSTRAINT(0x5d0, 0xf), - INTEL_PSD_CONSTRAINT(0x6d0, 0xf), + INTEL_HYBRID_LAT_CONSTRAINT(0x5d0, 0x3), + INTEL_HYBRID_LAT_CONSTRAINT(0x6d0, 0xf), EVENT_CONSTRAINT_END }; @@ -923,12 +1207,18 @@ struct event_constraint intel_skl_pebs_event_constraints[] = { }; struct event_constraint intel_icl_pebs_event_constraints[] = { - INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x01c0, 0x100000000ULL), /* old INST_RETIRED.PREC_DIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x0100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), /* SLOTS */ INTEL_PLD_CONSTRAINT(0x1cd, 0xff), /* MEM_TRANS_RETIRED.LOAD_LATENCY */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), /* MEM_INST_RETIRED.LOAD */ - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), /* MEM_INST_RETIRED.STORE */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), /* MEM_LOAD_*_RETIRED.* */ @@ -942,15 +1232,46 @@ struct event_constraint intel_icl_pebs_event_constraints[] = { EVENT_CONSTRAINT_END }; -struct event_constraint intel_spr_pebs_event_constraints[] = { - INTEL_FLAGS_UEVENT_CONSTRAINT(0x1c0, 0x100000000ULL), +struct event_constraint intel_glc_pebs_event_constraints[] = { + INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), INTEL_FLAGS_EVENT_CONSTRAINT(0xc0, 0xfe), INTEL_PLD_CONSTRAINT(0x1cd, 0xfe), INTEL_PSD_CONSTRAINT(0x2cd, 0x1), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x1d0, 0xf), - INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x2d0, 0xf), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ + + INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), + + INTEL_FLAGS_EVENT_CONSTRAINT(0xd0, 0xf), + + /* + * Everything else is handled by PMU_FL_PEBS_ALL, because we + * need the full constraints from the main table. + */ + + EVENT_CONSTRAINT_END +}; + +struct event_constraint intel_lnc_pebs_event_constraints[] = { + INTEL_FLAGS_UEVENT_CONSTRAINT(0x100, 0x100000000ULL), /* INST_RETIRED.PREC_DIST */ + INTEL_FLAGS_UEVENT_CONSTRAINT(0x0400, 0x800000000ULL), + + INTEL_HYBRID_LDLAT_CONSTRAINT(0x1cd, 0x3fc), + INTEL_HYBRID_STLAT_CONSTRAINT(0x2cd, 0x3), + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x11d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x12d0, 0xf), /* MEM_INST_RETIRED.STLB_MISS_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x21d0, 0xf), /* MEM_INST_RETIRED.LOCK_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x41d0, 0xf), /* MEM_INST_RETIRED.SPLIT_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x42d0, 0xf), /* MEM_INST_RETIRED.SPLIT_STORES */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_LD(0x81d0, 0xf), /* MEM_INST_RETIRED.ALL_LOADS */ + INTEL_FLAGS_UEVENT_CONSTRAINT_DATALA_ST(0x82d0, 0xf), /* MEM_INST_RETIRED.ALL_STORES */ INTEL_FLAGS_EVENT_CONSTRAINT_DATALA_LD_RANGE(0xd1, 0xd4, 0xf), @@ -1004,7 +1325,7 @@ static inline bool pebs_needs_sched_cb(struct cpu_hw_events *cpuc) return cpuc->n_pebs && (cpuc->n_pebs == cpuc->n_large_pebs); } -void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) +void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sched_in) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1015,8 +1336,7 @@ void intel_pmu_pebs_sched_task(struct perf_event_context *ctx, bool sched_in) static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) { struct debug_store *ds = cpuc->ds; - int max_pebs_events = hybrid(cpuc->pmu, max_pebs_events); - int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed); + int max_pebs_events = intel_pmu_max_num_pebs(cpuc->pmu); u64 threshold; int reserved; @@ -1024,7 +1344,7 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) return; if (x86_pmu.flags & PMU_FL_PEBS_ALL) - reserved = max_pebs_events + num_counters_fixed; + reserved = max_pebs_events + x86_pmu_max_num_counters_fixed(cpuc->pmu); else reserved = max_pebs_events; @@ -1038,6 +1358,19 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc) ds->pebs_interrupt_threshold = threshold; } +#define PEBS_DATACFG_CNTRS(x) \ + ((x >> PEBS_DATACFG_CNTR_SHIFT) & PEBS_DATACFG_CNTR_MASK) + +#define PEBS_DATACFG_CNTR_BIT(x) \ + (((1ULL << x) & PEBS_DATACFG_CNTR_MASK) << PEBS_DATACFG_CNTR_SHIFT) + +#define PEBS_DATACFG_FIX(x) \ + ((x >> PEBS_DATACFG_FIX_SHIFT) & PEBS_DATACFG_FIX_MASK) + +#define PEBS_DATACFG_FIX_BIT(x) \ + (((1ULL << (x)) & PEBS_DATACFG_FIX_MASK) \ + << PEBS_DATACFG_FIX_SHIFT) + static void adaptive_pebs_record_size_update(void) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1052,10 +1385,57 @@ static void adaptive_pebs_record_size_update(void) sz += sizeof(struct pebs_xmm); if (pebs_data_cfg & PEBS_DATACFG_LBRS) sz += x86_pmu.lbr_nr * sizeof(struct lbr_entry); + if (pebs_data_cfg & (PEBS_DATACFG_METRICS | PEBS_DATACFG_CNTR)) { + sz += sizeof(struct pebs_cntr_header); + + /* Metrics base and Metrics Data */ + if (pebs_data_cfg & PEBS_DATACFG_METRICS) + sz += 2 * sizeof(u64); + + if (pebs_data_cfg & PEBS_DATACFG_CNTR) { + sz += (hweight64(PEBS_DATACFG_CNTRS(pebs_data_cfg)) + + hweight64(PEBS_DATACFG_FIX(pebs_data_cfg))) * + sizeof(u64); + } + } cpuc->pebs_record_size = sz; } +static void __intel_pmu_pebs_update_cfg(struct perf_event *event, + int idx, u64 *pebs_data_cfg) +{ + if (is_metric_event(event)) { + *pebs_data_cfg |= PEBS_DATACFG_METRICS; + return; + } + + *pebs_data_cfg |= PEBS_DATACFG_CNTR; + + if (idx >= INTEL_PMC_IDX_FIXED) + *pebs_data_cfg |= PEBS_DATACFG_FIX_BIT(idx - INTEL_PMC_IDX_FIXED); + else + *pebs_data_cfg |= PEBS_DATACFG_CNTR_BIT(idx); +} + + +void intel_pmu_pebs_late_setup(struct cpu_hw_events *cpuc) +{ + struct perf_event *event; + u64 pebs_data_cfg = 0; + int i; + + for (i = 0; i < cpuc->n_events; i++) { + event = cpuc->event_list[i]; + if (!is_pebs_counter_event_group(event)) + continue; + __intel_pmu_pebs_update_cfg(event, cpuc->assign[i], &pebs_data_cfg); + } + + if (pebs_data_cfg & ~cpuc->pebs_data_cfg) + cpuc->pebs_data_cfg |= pebs_data_cfg | PEBS_UPDATE_DS_SW; +} + #define PERF_PEBS_MEMINFO_TYPE (PERF_SAMPLE_ADDR | PERF_SAMPLE_DATA_SRC | \ PERF_SAMPLE_PHYS_ADDR | \ PERF_SAMPLE_WEIGHT_TYPE | \ @@ -1082,8 +1462,10 @@ static u64 pebs_update_adaptive_cfg(struct perf_event *event) * + precise_ip < 2 for the non event IP * + For RTM TSX weight we need GPRs for the abort code. */ - gprs = (sample_type & PERF_SAMPLE_REGS_INTR) && - (attr->sample_regs_intr & PEBS_GP_REGS); + gprs = ((sample_type & PERF_SAMPLE_REGS_INTR) && + (attr->sample_regs_intr & PEBS_GP_REGS)) || + ((sample_type & PERF_SAMPLE_REGS_USER) && + (attr->sample_regs_user & PEBS_GP_REGS)); tsx_weight = (sample_type & PERF_SAMPLE_WEIGHT_TYPE) && ((attr->config & INTEL_ARCH_EVENT_MASK) == @@ -1112,13 +1494,15 @@ static void pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, struct perf_event *event, bool add) { - struct pmu *pmu = event->ctx->pmu; + struct pmu *pmu = event->pmu; + /* - * Make sure we get updated with the first PEBS - * event. It will trigger also during removal, but - * that does not hurt: + * Make sure we get updated with the first PEBS event. + * During removal, ->pebs_data_cfg is still valid for + * the last PEBS event. Don't clear it. */ - bool update = cpuc->n_pebs == 1; + if ((cpuc->n_pebs == 1) && add) + cpuc->pebs_data_cfg = PEBS_UPDATE_DS_SW; if (needed_cb != pebs_needs_sched_cb(cpuc)) { if (!needed_cb) @@ -1126,7 +1510,7 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, else perf_sched_cb_dec(pmu); - update = true; + cpuc->pebs_data_cfg |= PEBS_UPDATE_DS_SW; } /* @@ -1136,24 +1520,32 @@ pebs_update_state(bool needed_cb, struct cpu_hw_events *cpuc, if (x86_pmu.intel_cap.pebs_baseline && add) { u64 pebs_data_cfg; - /* Clear pebs_data_cfg and pebs_record_size for first PEBS. */ - if (cpuc->n_pebs == 1) { - cpuc->pebs_data_cfg = 0; - cpuc->pebs_record_size = sizeof(struct pebs_basic); - } - pebs_data_cfg = pebs_update_adaptive_cfg(event); - - /* Update pebs_record_size if new event requires more data. */ - if (pebs_data_cfg & ~cpuc->pebs_data_cfg) { - cpuc->pebs_data_cfg |= pebs_data_cfg; - adaptive_pebs_record_size_update(); - update = true; - } + /* + * Be sure to update the thresholds when we change the record. + */ + if (pebs_data_cfg & ~cpuc->pebs_data_cfg) + cpuc->pebs_data_cfg |= pebs_data_cfg | PEBS_UPDATE_DS_SW; } +} - if (update) - pebs_update_threshold(cpuc); +u64 intel_get_arch_pebs_data_config(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 pebs_data_cfg = 0; + u64 cntr_mask; + + if (WARN_ON(event->hw.idx < 0 || event->hw.idx >= X86_PMC_IDX_MAX)) + return 0; + + pebs_data_cfg |= pebs_update_adaptive_cfg(event); + + cntr_mask = (PEBS_DATACFG_CNTR_MASK << PEBS_DATACFG_CNTR_SHIFT) | + (PEBS_DATACFG_FIX_MASK << PEBS_DATACFG_FIX_SHIFT) | + PEBS_DATACFG_CNTR | PEBS_DATACFG_METRICS; + pebs_data_cfg |= cpuc->pebs_data_cfg & cntr_mask; + + return pebs_data_cfg; } void intel_pmu_pebs_add(struct perf_event *event) @@ -1202,21 +1594,39 @@ static void intel_pmu_pebs_via_pt_enable(struct perf_event *event) if (hwc->idx >= INTEL_PMC_IDX_FIXED) { base = MSR_RELOAD_FIXED_CTR0; idx = hwc->idx - INTEL_PMC_IDX_FIXED; - value = ds->pebs_event_reset[MAX_PEBS_EVENTS + idx]; + if (x86_pmu.intel_cap.pebs_format < 5) + value = ds->pebs_event_reset[MAX_PEBS_EVENTS_FMT4 + idx]; + else + value = ds->pebs_event_reset[MAX_PEBS_EVENTS + idx]; } - wrmsrl(base + idx, value); + wrmsrq(base + idx, value); +} + +static inline void intel_pmu_drain_large_pebs(struct cpu_hw_events *cpuc) +{ + if (cpuc->n_pebs == cpuc->n_large_pebs && + cpuc->n_pebs != cpuc->n_pebs_via_pt) + intel_pmu_drain_pebs_buffer(); +} + +static void __intel_pmu_pebs_enable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + + hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; + cpuc->pebs_enabled |= 1ULL << hwc->idx; } void intel_pmu_pebs_enable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 pebs_data_cfg = cpuc->pebs_data_cfg & ~PEBS_UPDATE_DS_SW; struct hw_perf_event *hwc = &event->hw; struct debug_store *ds = cpuc->ds; unsigned int idx = hwc->idx; - hwc->config &= ~ARCH_PERFMON_EVENTSEL_INT; - - cpuc->pebs_enabled |= 1ULL << hwc->idx; + __intel_pmu_pebs_enable(event); if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5)) cpuc->pebs_enabled |= 1ULL << (hwc->idx + 32); @@ -1225,14 +1635,29 @@ void intel_pmu_pebs_enable(struct perf_event *event) if (x86_pmu.intel_cap.pebs_baseline) { hwc->config |= ICL_EVENTSEL_ADAPTIVE; - if (cpuc->pebs_data_cfg != cpuc->active_pebs_data_cfg) { - wrmsrl(MSR_PEBS_DATA_CFG, cpuc->pebs_data_cfg); - cpuc->active_pebs_data_cfg = cpuc->pebs_data_cfg; + if (pebs_data_cfg != cpuc->active_pebs_data_cfg) { + /* + * drain_pebs() assumes uniform record size; + * hence we need to drain when changing said + * size. + */ + intel_pmu_drain_pebs_buffer(); + adaptive_pebs_record_size_update(); + wrmsrq(MSR_PEBS_DATA_CFG, pebs_data_cfg); + cpuc->active_pebs_data_cfg = pebs_data_cfg; } } + if (cpuc->pebs_data_cfg & PEBS_UPDATE_DS_SW) { + cpuc->pebs_data_cfg = pebs_data_cfg; + pebs_update_threshold(cpuc); + } - if (idx >= INTEL_PMC_IDX_FIXED) - idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED); + if (idx >= INTEL_PMC_IDX_FIXED) { + if (x86_pmu.intel_cap.pebs_format < 5) + idx = MAX_PEBS_EVENTS_FMT4 + (idx - INTEL_PMC_IDX_FIXED); + else + idx = MAX_PEBS_EVENTS + (idx - INTEL_PMC_IDX_FIXED); + } /* * Use auto-reload if possible to save a MSR write in the PMI. @@ -1263,16 +1688,22 @@ void intel_pmu_pebs_del(struct perf_event *event) pebs_update_state(needed_cb, cpuc, event, false); } -void intel_pmu_pebs_disable(struct perf_event *event) +static void __intel_pmu_pebs_disable(struct perf_event *event) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); struct hw_perf_event *hwc = &event->hw; - if (cpuc->n_pebs == cpuc->n_large_pebs && - cpuc->n_pebs != cpuc->n_pebs_via_pt) - intel_pmu_drain_pebs_buffer(); - + intel_pmu_drain_large_pebs(cpuc); cpuc->pebs_enabled &= ~(1ULL << hwc->idx); + hwc->config |= ARCH_PERFMON_EVENTSEL_INT; +} + +void intel_pmu_pebs_disable(struct perf_event *event) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct hw_perf_event *hwc = &event->hw; + + __intel_pmu_pebs_disable(event); if ((event->hw.flags & PERF_X86_EVENT_PEBS_LDLAT) && (x86_pmu.version < 5)) @@ -1283,9 +1714,7 @@ void intel_pmu_pebs_disable(struct perf_event *event) intel_pmu_pebs_via_pt_disable(event); if (cpuc->enabled) - wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); - - hwc->config |= ARCH_PERFMON_EVENTSEL_INT; + wrmsrq(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); } void intel_pmu_pebs_enable_all(void) @@ -1293,7 +1722,7 @@ void intel_pmu_pebs_enable_all(void) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->pebs_enabled) - wrmsrl(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); + wrmsrq(MSR_IA32_PEBS_ENABLE, cpuc->pebs_enabled); } void intel_pmu_pebs_disable_all(void) @@ -1301,7 +1730,7 @@ void intel_pmu_pebs_disable_all(void) struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); if (cpuc->pebs_enabled) - wrmsrl(MSR_IA32_PEBS_ENABLE, 0); + __intel_pmu_pebs_disable_all(); } static int intel_pmu_pebs_fixup_ip(struct pt_regs *regs) @@ -1435,9 +1864,11 @@ static u64 get_data_src(struct perf_event *event, u64 aux) bool fst = fl & (PERF_X86_EVENT_PEBS_ST | PERF_X86_EVENT_PEBS_HSW_PREC); if (fl & PERF_X86_EVENT_PEBS_LDLAT) - val = load_latency_data(aux); + val = load_latency_data(event, aux); else if (fl & PERF_X86_EVENT_PEBS_STLAT) - val = store_latency_data(aux); + val = store_latency_data(event, aux); + else if (fl & PERF_X86_EVENT_PEBS_LAT_HYBRID) + val = x86_pmu.pebs_latency_data(event, aux); else if (fst && (fl & PERF_X86_EVENT_PEBS_HSW_PREC)) val = precise_datala_hsw(event, aux); else if (fst) @@ -1445,6 +1876,27 @@ static u64 get_data_src(struct perf_event *event, u64 aux) return val; } +static void setup_pebs_time(struct perf_event *event, + struct perf_sample_data *data, + u64 tsc) +{ + /* Converting to a user-defined clock is not supported yet. */ + if (event->attr.use_clockid != 0) + return; + + /* + * Doesn't support the conversion when the TSC is unstable. + * The TSC unstable case is a corner case and very unlikely to + * happen. If it happens, the TSC in a PEBS record will be + * dropped and fall back to perf_event_clock(). + */ + if (!using_native_sched_clock() || !sched_clock_stable()) + return; + + data->time = native_sched_clock_from_tsc(tsc) + __sched_clock_offset; + data->sample_flags |= PERF_SAMPLE_TIME; +} + #define PERF_SAMPLE_ADDR_TYPE (PERF_SAMPLE_ADDR | \ PERF_SAMPLE_PHYS_ADDR | \ PERF_SAMPLE_DATA_PAGE_SIZE) @@ -1471,19 +1923,21 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, perf_sample_data_init(data, 0, event->hw.last_period); - data->period = event->hw.last_period; - /* * Use latency for weight (only avail with PEBS-LL) */ - if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE)) + if (fll && (sample_type & PERF_SAMPLE_WEIGHT_TYPE)) { data->weight.full = pebs->lat; + data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE; + } /* * data.data_src encodes the data source */ - if (sample_type & PERF_SAMPLE_DATA_SRC) + if (sample_type & PERF_SAMPLE_DATA_SRC) { data->data_src.val = get_data_src(event, pebs->dse); + data->sample_flags |= PERF_SAMPLE_DATA_SRC; + } /* * We must however always use iregs for the unwinder to stay sane; the @@ -1491,8 +1945,7 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, * previous PMI context or an (I)RET happened between the record and * PMI. */ - if (sample_type & PERF_SAMPLE_CALLCHAIN) - data->callchain = perf_callchain(event, iregs); + perf_sample_save_callchain(data, event, iregs); /* * We use the interrupt regs as a base because the PEBS record does not @@ -1564,17 +2017,22 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, if ((sample_type & PERF_SAMPLE_ADDR_TYPE) && - x86_pmu.intel_cap.pebs_format >= 1) + x86_pmu.intel_cap.pebs_format >= 1) { data->addr = pebs->dla; + data->sample_flags |= PERF_SAMPLE_ADDR; + } if (x86_pmu.intel_cap.pebs_format >= 2) { /* Only set the TSX weight when no memory weight. */ - if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll) + if ((sample_type & PERF_SAMPLE_WEIGHT_TYPE) && !fll) { data->weight.full = intel_get_tsx_weight(pebs->tsx_tuning); - - if (sample_type & PERF_SAMPLE_TRANSACTION) + data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE; + } + if (sample_type & PERF_SAMPLE_TRANSACTION) { data->txn = intel_get_tsx_transaction(pebs->tsx_tuning, pebs->ax); + data->sample_flags |= PERF_SAMPLE_TRANSACTION; + } } /* @@ -1583,12 +2041,10 @@ static void setup_pebs_fixed_sample_data(struct perf_event *event, * * We can only do this for the default trace clock. */ - if (x86_pmu.intel_cap.pebs_format >= 3 && - event->attr.use_clockid == 0) - data->time = native_sched_clock_from_tsc(pebs->tsc); + if (x86_pmu.intel_cap.pebs_format >= 3) + setup_pebs_time(event, data, pebs->tsc); - if (has_branch_stack(event)) - data->br_stack = &cpuc->lbr_stack; + perf_sample_save_brstack(data, event, &cpuc->lbr_stack, NULL); } static void adaptive_pebs_save_regs(struct pt_regs *regs, @@ -1614,26 +2070,187 @@ static void adaptive_pebs_save_regs(struct pt_regs *regs, #endif } +static void intel_perf_event_update_pmc(struct perf_event *event, u64 pmc) +{ + int shift = 64 - x86_pmu.cntval_bits; + struct hw_perf_event *hwc; + u64 delta, prev_pmc; + + /* + * A recorded counter may not have an assigned event in the + * following cases. The value should be dropped. + * - An event is deleted. There is still an active PEBS event. + * The PEBS record doesn't shrink on pmu::del(). + * If the counter of the deleted event once occurred in a PEBS + * record, PEBS still records the counter until the counter is + * reassigned. + * - An event is stopped for some reason, e.g., throttled. + * During this period, another event is added and takes the + * counter of the stopped event. The stopped event is assigned + * to another new and uninitialized counter, since the + * x86_pmu_start(RELOAD) is not invoked for a stopped event. + * The PEBS__DATA_CFG is updated regardless of the event state. + * The uninitialized counter can be recorded in a PEBS record. + * But the cpuc->events[uninitialized_counter] is always NULL, + * because the event is stopped. The uninitialized value is + * safely dropped. + */ + if (!event) + return; + + hwc = &event->hw; + prev_pmc = local64_read(&hwc->prev_count); + + /* Only update the count when the PMU is disabled */ + WARN_ON(this_cpu_read(cpu_hw_events.enabled)); + local64_set(&hwc->prev_count, pmc); + + delta = (pmc << shift) - (prev_pmc << shift); + delta >>= shift; + + local64_add(delta, &event->count); + local64_sub(delta, &hwc->period_left); +} + +static inline void __setup_pebs_counter_group(struct cpu_hw_events *cpuc, + struct perf_event *event, + struct pebs_cntr_header *cntr, + void *next_record) +{ + int bit; + + for_each_set_bit(bit, (unsigned long *)&cntr->cntr, INTEL_PMC_MAX_GENERIC) { + intel_perf_event_update_pmc(cpuc->events[bit], *(u64 *)next_record); + next_record += sizeof(u64); + } + + for_each_set_bit(bit, (unsigned long *)&cntr->fixed, INTEL_PMC_MAX_FIXED) { + /* The slots event will be handled with perf_metric later */ + if ((cntr->metrics == INTEL_CNTR_METRICS) && + (bit + INTEL_PMC_IDX_FIXED == INTEL_PMC_IDX_FIXED_SLOTS)) { + next_record += sizeof(u64); + continue; + } + intel_perf_event_update_pmc(cpuc->events[bit + INTEL_PMC_IDX_FIXED], + *(u64 *)next_record); + next_record += sizeof(u64); + } + + /* HW will reload the value right after the overflow. */ + if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) + local64_set(&event->hw.prev_count, (u64)-event->hw.sample_period); + + if (cntr->metrics == INTEL_CNTR_METRICS) { + static_call(intel_pmu_update_topdown_event) + (cpuc->events[INTEL_PMC_IDX_FIXED_SLOTS], + (u64 *)next_record); + next_record += 2 * sizeof(u64); + } +} + #define PEBS_LATENCY_MASK 0xffff -#define PEBS_CACHE_LATENCY_OFFSET 32 + +static inline void __setup_perf_sample_data(struct perf_event *event, + struct pt_regs *iregs, + struct perf_sample_data *data) +{ + perf_sample_data_init(data, 0, event->hw.last_period); + + /* + * We must however always use iregs for the unwinder to stay sane; the + * record BP,SP,IP can point into thin air when the record is from a + * previous PMI context or an (I)RET happened between the record and + * PMI. + */ + perf_sample_save_callchain(data, event, iregs); +} + +static inline void __setup_pebs_basic_group(struct perf_event *event, + struct pt_regs *regs, + struct perf_sample_data *data, + u64 sample_type, u64 ip, + u64 tsc, u16 retire) +{ + /* The ip in basic is EventingIP */ + set_linear_ip(regs, ip); + regs->flags = PERF_EFLAGS_EXACT; + setup_pebs_time(event, data, tsc); + + if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) + data->weight.var3_w = retire; +} + +static inline void __setup_pebs_gpr_group(struct perf_event *event, + struct pt_regs *regs, + struct pebs_gprs *gprs, + u64 sample_type) +{ + if (event->attr.precise_ip < 2) { + set_linear_ip(regs, gprs->ip); + regs->flags &= ~PERF_EFLAGS_EXACT; + } + + if (sample_type & (PERF_SAMPLE_REGS_INTR | PERF_SAMPLE_REGS_USER)) + adaptive_pebs_save_regs(regs, gprs); +} + +static inline void __setup_pebs_meminfo_group(struct perf_event *event, + struct perf_sample_data *data, + u64 sample_type, u64 latency, + u16 instr_latency, u64 address, + u64 aux, u64 tsx_tuning, u64 ax) +{ + if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) { + u64 tsx_latency = intel_get_tsx_weight(tsx_tuning); + + data->weight.var2_w = instr_latency; + + /* + * Although meminfo::latency is defined as a u64, + * only the lower 32 bits include the valid data + * in practice on Ice Lake and earlier platforms. + */ + if (sample_type & PERF_SAMPLE_WEIGHT) + data->weight.full = latency ?: tsx_latency; + else + data->weight.var1_dw = (u32)latency ?: tsx_latency; + + data->sample_flags |= PERF_SAMPLE_WEIGHT_TYPE; + } + + if (sample_type & PERF_SAMPLE_DATA_SRC) { + data->data_src.val = get_data_src(event, aux); + data->sample_flags |= PERF_SAMPLE_DATA_SRC; + } + + if (sample_type & PERF_SAMPLE_ADDR_TYPE) { + data->addr = address; + data->sample_flags |= PERF_SAMPLE_ADDR; + } + + if (sample_type & PERF_SAMPLE_TRANSACTION) { + data->txn = intel_get_tsx_transaction(tsx_tuning, ax); + data->sample_flags |= PERF_SAMPLE_TRANSACTION; + } +} /* * With adaptive PEBS the layout depends on what fields are configured. */ - static void setup_pebs_adaptive_sample_data(struct perf_event *event, struct pt_regs *iregs, void *__pebs, struct perf_sample_data *data, struct pt_regs *regs) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 sample_type = event->attr.sample_type; struct pebs_basic *basic = __pebs; void *next_record = basic + 1; - u64 sample_type; - u64 format_size; struct pebs_meminfo *meminfo = NULL; struct pebs_gprs *gprs = NULL; struct x86_perf_regs *perf_regs; + u64 format_group; + u16 retire; if (basic == NULL) return; @@ -1641,109 +2258,223 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event, perf_regs = container_of(regs, struct x86_perf_regs, regs); perf_regs->xmm_regs = NULL; - sample_type = event->attr.sample_type; - format_size = basic->format_size; - perf_sample_data_init(data, 0, event->hw.last_period); - data->period = event->hw.last_period; + format_group = basic->format_group; - if (event->attr.use_clockid == 0) - data->time = native_sched_clock_from_tsc(basic->tsc); - - /* - * We must however always use iregs for the unwinder to stay sane; the - * record BP,SP,IP can point into thin air when the record is from a - * previous PMI context or an (I)RET happened between the record and - * PMI. - */ - if (sample_type & PERF_SAMPLE_CALLCHAIN) - data->callchain = perf_callchain(event, iregs); + __setup_perf_sample_data(event, iregs, data); *regs = *iregs; - /* The ip in basic is EventingIP */ - set_linear_ip(regs, basic->ip); - regs->flags = PERF_EFLAGS_EXACT; + + /* basic group */ + retire = x86_pmu.flags & PMU_FL_RETIRE_LATENCY ? + basic->retire_latency : 0; + __setup_pebs_basic_group(event, regs, data, sample_type, + basic->ip, basic->tsc, retire); /* * The record for MEMINFO is in front of GP * But PERF_SAMPLE_TRANSACTION needs gprs->ax. * Save the pointer here but process later. */ - if (format_size & PEBS_DATACFG_MEMINFO) { + if (format_group & PEBS_DATACFG_MEMINFO) { meminfo = next_record; next_record = meminfo + 1; } - if (format_size & PEBS_DATACFG_GP) { + if (format_group & PEBS_DATACFG_GP) { gprs = next_record; next_record = gprs + 1; - if (event->attr.precise_ip < 2) { - set_linear_ip(regs, gprs->ip); - regs->flags &= ~PERF_EFLAGS_EXACT; - } + __setup_pebs_gpr_group(event, regs, gprs, sample_type); + } - if (sample_type & PERF_SAMPLE_REGS_INTR) - adaptive_pebs_save_regs(regs, gprs); + if (format_group & PEBS_DATACFG_MEMINFO) { + u64 latency = x86_pmu.flags & PMU_FL_INSTR_LATENCY ? + meminfo->cache_latency : meminfo->mem_latency; + u64 instr_latency = x86_pmu.flags & PMU_FL_INSTR_LATENCY ? + meminfo->instr_latency : 0; + u64 ax = gprs ? gprs->ax : 0; + + __setup_pebs_meminfo_group(event, data, sample_type, latency, + instr_latency, meminfo->address, + meminfo->aux, meminfo->tsx_tuning, + ax); } - if (format_size & PEBS_DATACFG_MEMINFO) { - if (sample_type & PERF_SAMPLE_WEIGHT_TYPE) { - u64 weight = meminfo->latency; + if (format_group & PEBS_DATACFG_XMMS) { + struct pebs_xmm *xmm = next_record; - if (x86_pmu.flags & PMU_FL_INSTR_LATENCY) { - data->weight.var2_w = weight & PEBS_LATENCY_MASK; - weight >>= PEBS_CACHE_LATENCY_OFFSET; - } + next_record = xmm + 1; + perf_regs->xmm_regs = xmm->xmm; + } - /* - * Although meminfo::latency is defined as a u64, - * only the lower 32 bits include the valid data - * in practice on Ice Lake and earlier platforms. - */ - if (sample_type & PERF_SAMPLE_WEIGHT) { - data->weight.full = weight ?: - intel_get_tsx_weight(meminfo->tsx_tuning); - } else { - data->weight.var1_dw = (u32)(weight & PEBS_LATENCY_MASK) ?: - intel_get_tsx_weight(meminfo->tsx_tuning); - } + if (format_group & PEBS_DATACFG_LBRS) { + struct lbr_entry *lbr = next_record; + int num_lbr = ((format_group >> PEBS_DATACFG_LBR_SHIFT) + & 0xff) + 1; + next_record = next_record + num_lbr * sizeof(struct lbr_entry); + + if (has_branch_stack(event)) { + intel_pmu_store_pebs_lbrs(lbr); + intel_pmu_lbr_save_brstack(data, cpuc, event); } + } - if (sample_type & PERF_SAMPLE_DATA_SRC) - data->data_src.val = get_data_src(event, meminfo->aux); + if (format_group & (PEBS_DATACFG_CNTR | PEBS_DATACFG_METRICS)) { + struct pebs_cntr_header *cntr = next_record; + unsigned int nr; - if (sample_type & PERF_SAMPLE_ADDR_TYPE) - data->addr = meminfo->address; + next_record += sizeof(struct pebs_cntr_header); + /* + * The PEBS_DATA_CFG is a global register, which is the + * superset configuration for all PEBS events. + * For the PEBS record of non-sample-read group, ignore + * the counter snapshot fields. + */ + if (is_pebs_counter_event_group(event)) { + __setup_pebs_counter_group(cpuc, event, cntr, next_record); + data->sample_flags |= PERF_SAMPLE_READ; + } - if (sample_type & PERF_SAMPLE_TRANSACTION) - data->txn = intel_get_tsx_transaction(meminfo->tsx_tuning, - gprs ? gprs->ax : 0); + nr = hweight32(cntr->cntr) + hweight32(cntr->fixed); + if (cntr->metrics == INTEL_CNTR_METRICS) + nr += 2; + next_record += nr * sizeof(u64); } - if (format_size & PEBS_DATACFG_XMMS) { - struct pebs_xmm *xmm = next_record; + WARN_ONCE(next_record != __pebs + basic->format_size, + "PEBS record size %u, expected %llu, config %llx\n", + basic->format_size, + (u64)(next_record - __pebs), + format_group); +} - next_record = xmm + 1; +static inline bool arch_pebs_record_continued(struct arch_pebs_header *header) +{ + /* Continue bit or null PEBS record indicates fragment follows. */ + return header->cont || !(header->format & GENMASK_ULL(63, 16)); +} + +static void setup_arch_pebs_sample_data(struct perf_event *event, + struct pt_regs *iregs, + void *__pebs, + struct perf_sample_data *data, + struct pt_regs *regs) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + u64 sample_type = event->attr.sample_type; + struct arch_pebs_header *header = NULL; + struct arch_pebs_aux *meminfo = NULL; + struct arch_pebs_gprs *gprs = NULL; + struct x86_perf_regs *perf_regs; + void *next_record; + void *at = __pebs; + + if (at == NULL) + return; + + perf_regs = container_of(regs, struct x86_perf_regs, regs); + perf_regs->xmm_regs = NULL; + + __setup_perf_sample_data(event, iregs, data); + + *regs = *iregs; + +again: + header = at; + next_record = at + sizeof(struct arch_pebs_header); + if (header->basic) { + struct arch_pebs_basic *basic = next_record; + u16 retire = 0; + + next_record = basic + 1; + + if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) + retire = basic->valid ? basic->retire : 0; + __setup_pebs_basic_group(event, regs, data, sample_type, + basic->ip, basic->tsc, retire); + } + + /* + * The record for MEMINFO is in front of GP + * But PERF_SAMPLE_TRANSACTION needs gprs->ax. + * Save the pointer here but process later. + */ + if (header->aux) { + meminfo = next_record; + next_record = meminfo + 1; + } + + if (header->gpr) { + gprs = next_record; + next_record = gprs + 1; + + __setup_pebs_gpr_group(event, regs, + (struct pebs_gprs *)gprs, + sample_type); + } + + if (header->aux) { + u64 ax = gprs ? gprs->ax : 0; + + __setup_pebs_meminfo_group(event, data, sample_type, + meminfo->cache_latency, + meminfo->instr_latency, + meminfo->address, meminfo->aux, + meminfo->tsx_tuning, ax); + } + + if (header->xmm) { + struct pebs_xmm *xmm; + + next_record += sizeof(struct arch_pebs_xer_header); + + xmm = next_record; perf_regs->xmm_regs = xmm->xmm; + next_record = xmm + 1; } - if (format_size & PEBS_DATACFG_LBRS) { - struct lbr_entry *lbr = next_record; - int num_lbr = ((format_size >> PEBS_DATACFG_LBR_SHIFT) - & 0xff) + 1; - next_record = next_record + num_lbr * sizeof(struct lbr_entry); + if (header->lbr) { + struct arch_pebs_lbr_header *lbr_header = next_record; + struct lbr_entry *lbr; + int num_lbr; + + next_record = lbr_header + 1; + lbr = next_record; + + num_lbr = header->lbr == ARCH_PEBS_LBR_NUM_VAR ? + lbr_header->depth : + header->lbr * ARCH_PEBS_BASE_LBR_ENTRIES; + next_record += num_lbr * sizeof(struct lbr_entry); if (has_branch_stack(event)) { intel_pmu_store_pebs_lbrs(lbr); - data->br_stack = &cpuc->lbr_stack; + intel_pmu_lbr_save_brstack(data, cpuc, event); } } - WARN_ONCE(next_record != __pebs + (format_size >> 48), - "PEBS record size %llu, expected %llu, config %llx\n", - format_size >> 48, - (u64)(next_record - __pebs), - basic->format_size); + if (header->cntr) { + struct arch_pebs_cntr_header *cntr = next_record; + unsigned int nr; + + next_record += sizeof(struct arch_pebs_cntr_header); + + if (is_pebs_counter_event_group(event)) { + __setup_pebs_counter_group(cpuc, event, + (struct pebs_cntr_header *)cntr, next_record); + data->sample_flags |= PERF_SAMPLE_READ; + } + + nr = hweight32(cntr->cntr) + hweight32(cntr->fixed); + if (cntr->metrics == INTEL_CNTR_METRICS) + nr += 2; + next_record += nr * sizeof(u64); + } + + /* Parse followed fragments if there are. */ + if (arch_pebs_record_continued(header)) { + at = at + header->size; + goto again; + } } static inline void * @@ -1784,15 +2515,6 @@ get_next_pebs_record_by_bit(void *base, void *top, int bit) return NULL; } -void intel_pmu_auto_reload_read(struct perf_event *event) -{ - WARN_ON(!(event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD)); - - perf_pmu_disable(event->pmu); - intel_pmu_drain_pebs_buffer(); - perf_pmu_enable(event->pmu); -} - /* * Special variant of intel_pmu_save_and_restart() for auto-reload. */ @@ -1813,7 +2535,7 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) WARN_ON(this_cpu_read(cpu_hw_events.enabled)); prev_raw_count = local64_read(&hwc->prev_count); - rdpmcl(hwc->event_base_rdpmc, new_raw_count); + new_raw_count = rdpmc(hwc->event_base_rdpmc); local64_set(&hwc->prev_count, new_raw_count); /* @@ -1854,46 +2576,33 @@ intel_pmu_save_and_restart_reload(struct perf_event *event, int count) return 0; } +typedef void (*setup_fn)(struct perf_event *, struct pt_regs *, void *, + struct perf_sample_data *, struct pt_regs *); + +static struct pt_regs dummy_iregs; + static __always_inline void __intel_pmu_pebs_event(struct perf_event *event, struct pt_regs *iregs, + struct pt_regs *regs, struct perf_sample_data *data, - void *base, void *top, - int bit, int count, - void (*setup_sample)(struct perf_event *, - struct pt_regs *, - void *, - struct perf_sample_data *, - struct pt_regs *)) + void *at, + setup_fn setup_sample) { - struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - struct hw_perf_event *hwc = &event->hw; - struct x86_perf_regs perf_regs; - struct pt_regs *regs = &perf_regs.regs; - void *at = get_next_pebs_record_by_bit(base, top, bit); - static struct pt_regs dummy_iregs; - - if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { - /* - * Now, auto-reload is only enabled in fixed period mode. - * The reload value is always hwc->sample_period. - * May need to change it, if auto-reload is enabled in - * freq mode later. - */ - intel_pmu_save_and_restart_reload(event, count); - } else if (!intel_pmu_save_and_restart(event)) - return; - - if (!iregs) - iregs = &dummy_iregs; + setup_sample(event, iregs, at, data, regs); + perf_event_output(event, data, regs); +} - while (count > 1) { - setup_sample(event, iregs, at, data, regs); - perf_event_output(event, data, regs); - at += cpuc->pebs_record_size; - at = get_next_pebs_record_by_bit(at, top, bit); - count--; - } +static __always_inline void +__intel_pmu_pebs_last_event(struct perf_event *event, + struct pt_regs *iregs, + struct pt_regs *regs, + struct perf_sample_data *data, + void *at, + int count, + setup_fn setup_sample) +{ + struct hw_perf_event *hwc = &event->hw; setup_sample(event, iregs, at, data, regs); if (iregs == &dummy_iregs) { @@ -1909,11 +2618,73 @@ __intel_pmu_pebs_event(struct perf_event *event, * All but the last records are processed. * The last one is left to be able to call the overflow handler. */ - if (perf_event_overflow(event, data, regs)) - x86_pmu_stop(event, 0); + perf_event_overflow(event, data, regs); + } + + if (hwc->flags & PERF_X86_EVENT_AUTO_RELOAD) { + if ((is_pebs_counter_event_group(event))) { + /* + * The value of each sample has been updated when setup + * the corresponding sample data. + */ + perf_event_update_userpage(event); + } else { + /* + * Now, auto-reload is only enabled in fixed period mode. + * The reload value is always hwc->sample_period. + * May need to change it, if auto-reload is enabled in + * freq mode later. + */ + intel_pmu_save_and_restart_reload(event, count); + } + } else { + /* + * For a non-precise event, it's possible the + * counters-snapshotting records a positive value for the + * overflowed event. Then the HW auto-reload mechanism + * reset the counter to 0 immediately, because the + * pebs_event_reset is cleared if the PERF_X86_EVENT_AUTO_RELOAD + * is not set. The counter backwards may be observed in a + * PMI handler. + * + * Since the event value has been updated when processing the + * counters-snapshotting record, only needs to set the new + * period for the counter. + */ + if (is_pebs_counter_event_group(event)) + static_call(x86_pmu_set_period)(event); + else + intel_pmu_save_and_restart(event); } } +static __always_inline void +__intel_pmu_pebs_events(struct perf_event *event, + struct pt_regs *iregs, + struct perf_sample_data *data, + void *base, void *top, + int bit, int count, + setup_fn setup_sample) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct x86_perf_regs perf_regs; + struct pt_regs *regs = &perf_regs.regs; + void *at = get_next_pebs_record_by_bit(base, top, bit); + int cnt = count; + + if (!iregs) + iregs = &dummy_iregs; + + while (cnt > 1) { + __intel_pmu_pebs_event(event, iregs, regs, data, at, setup_sample); + at += cpuc->pebs_record_size; + at = get_next_pebs_record_by_bit(at, top, bit); + cnt--; + } + + __intel_pmu_pebs_last_event(event, iregs, regs, data, at, count, setup_sample); +} + static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_data *data) { struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); @@ -1948,12 +2719,13 @@ static void intel_pmu_drain_pebs_core(struct pt_regs *iregs, struct perf_sample_ return; } - __intel_pmu_pebs_event(event, iregs, data, at, top, 0, n, - setup_pebs_fixed_sample_data); + __intel_pmu_pebs_events(event, iregs, data, at, top, 0, n, + setup_pebs_fixed_sample_data); } -static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int size) +static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, u64 mask) { + u64 pebs_enabled = cpuc->pebs_enabled & mask; struct perf_event *event; int bit; @@ -1964,7 +2736,7 @@ static void intel_pmu_pebs_event_update_no_drain(struct cpu_hw_events *cpuc, int * It needs to call intel_pmu_save_and_restart_reload() to * update the event->count for this case. */ - for_each_set_bit(bit, (unsigned long *)&cpuc->pebs_enabled, size) { + for_each_set_bit(bit, (unsigned long *)&pebs_enabled, X86_PMC_IDX_MAX) { event = cpuc->events[bit]; if (event->hw.flags & PERF_X86_EVENT_AUTO_RELOAD) intel_pmu_save_and_restart_reload(event, 0); @@ -1979,6 +2751,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d void *base, *at, *top; short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + int max_pebs_events = intel_pmu_max_num_pebs(NULL); int bit, i, size; u64 mask; @@ -1990,15 +2763,15 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d ds->pebs_index = ds->pebs_buffer_base; - mask = (1ULL << x86_pmu.max_pebs_events) - 1; - size = x86_pmu.max_pebs_events; + mask = x86_pmu.pebs_events_mask; + size = max_pebs_events; if (x86_pmu.flags & PMU_FL_PEBS_ALL) { - mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED; - size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed; + mask |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED; + size = INTEL_PMC_IDX_FIXED + x86_pmu_max_num_counters_fixed(NULL); } if (unlikely(base >= top)) { - intel_pmu_pebs_event_update_no_drain(cpuc, size); + intel_pmu_pebs_event_update_no_drain(cpuc, mask); return; } @@ -2030,8 +2803,9 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d pebs_status = p->status = cpuc->pebs_enabled; bit = find_first_bit((unsigned long *)&pebs_status, - x86_pmu.max_pebs_events); - if (bit >= x86_pmu.max_pebs_events) + max_pebs_events); + + if (!(x86_pmu.pebs_events_mask & (1 << bit))) continue; /* @@ -2073,28 +2847,79 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d if (error[bit]) { perf_log_lost_samples(event, error[bit]); - if (iregs && perf_event_account_interrupt(event)) - x86_pmu_stop(event, 0); + if (iregs) + perf_event_account_interrupt(event); } if (counts[bit]) { - __intel_pmu_pebs_event(event, iregs, data, base, - top, bit, counts[bit], - setup_pebs_fixed_sample_data); + __intel_pmu_pebs_events(event, iregs, data, base, + top, bit, counts[bit], + setup_pebs_fixed_sample_data); } } } +static __always_inline void +__intel_pmu_handle_pebs_record(struct pt_regs *iregs, + struct pt_regs *regs, + struct perf_sample_data *data, + void *at, u64 pebs_status, + short *counts, void **last, + setup_fn setup_sample) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct perf_event *event; + int bit; + + for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX) { + event = cpuc->events[bit]; + + if (WARN_ON_ONCE(!event) || + WARN_ON_ONCE(!event->attr.precise_ip)) + continue; + + if (counts[bit]++) { + __intel_pmu_pebs_event(event, iregs, regs, data, + last[bit], setup_sample); + } + + last[bit] = at; + } +} + +static __always_inline void +__intel_pmu_handle_last_pebs_record(struct pt_regs *iregs, + struct pt_regs *regs, + struct perf_sample_data *data, + u64 mask, short *counts, void **last, + setup_fn setup_sample) +{ + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + struct perf_event *event; + int bit; + + for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) { + if (!counts[bit]) + continue; + + event = cpuc->events[bit]; + + __intel_pmu_pebs_last_event(event, iregs, regs, data, last[bit], + counts[bit], setup_sample); + } + +} + static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_data *data) { short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + void *last[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS]; struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); - int max_pebs_events = hybrid(cpuc->pmu, max_pebs_events); - int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed); struct debug_store *ds = cpuc->ds; - struct perf_event *event; + struct x86_perf_regs perf_regs; + struct pt_regs *regs = &perf_regs.regs; + struct pebs_basic *basic; void *base, *at, *top; - int bit, size; u64 mask; if (!x86_pmu.pebs_active) @@ -2105,47 +2930,134 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d ds->pebs_index = ds->pebs_buffer_base; - mask = ((1ULL << max_pebs_events) - 1) | - (((1ULL << num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED); - size = INTEL_PMC_IDX_FIXED + num_counters_fixed; + mask = hybrid(cpuc->pmu, pebs_events_mask) | + (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED); + mask &= cpuc->pebs_enabled; if (unlikely(base >= top)) { - intel_pmu_pebs_event_update_no_drain(cpuc, size); + intel_pmu_pebs_event_update_no_drain(cpuc, mask); return; } - for (at = base; at < top; at += cpuc->pebs_record_size) { + if (!iregs) + iregs = &dummy_iregs; + + /* Process all but the last event for each counter. */ + for (at = base; at < top; at += basic->format_size) { u64 pebs_status; - pebs_status = get_pebs_status(at) & cpuc->pebs_enabled; - pebs_status &= mask; + basic = at; + if (basic->format_size != cpuc->pebs_record_size) + continue; - for_each_set_bit(bit, (unsigned long *)&pebs_status, size) - counts[bit]++; + pebs_status = mask & basic->applicable_counters; + __intel_pmu_handle_pebs_record(iregs, regs, data, at, + pebs_status, counts, last, + setup_pebs_adaptive_sample_data); } - for_each_set_bit(bit, (unsigned long *)&mask, size) { - if (counts[bit] == 0) - continue; + __intel_pmu_handle_last_pebs_record(iregs, regs, data, mask, counts, last, + setup_pebs_adaptive_sample_data); +} - event = cpuc->events[bit]; - if (WARN_ON_ONCE(!event)) - continue; +static void intel_pmu_drain_arch_pebs(struct pt_regs *iregs, + struct perf_sample_data *data) +{ + short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {}; + void *last[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS]; + struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events); + union arch_pebs_index index; + struct x86_perf_regs perf_regs; + struct pt_regs *regs = &perf_regs.regs; + void *base, *at, *top; + u64 mask; - if (WARN_ON_ONCE(!event->attr.precise_ip)) + rdmsrq(MSR_IA32_PEBS_INDEX, index.whole); + + if (unlikely(!index.wr)) { + intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX); + return; + } + + base = cpuc->pebs_vaddr; + top = cpuc->pebs_vaddr + (index.wr << ARCH_PEBS_INDEX_WR_SHIFT); + + index.wr = 0; + index.full = 0; + index.en = 1; + if (cpuc->n_pebs == cpuc->n_large_pebs) + index.thresh = ARCH_PEBS_THRESH_MULTI; + else + index.thresh = ARCH_PEBS_THRESH_SINGLE; + wrmsrq(MSR_IA32_PEBS_INDEX, index.whole); + + mask = hybrid(cpuc->pmu, arch_pebs_cap).counters & cpuc->pebs_enabled; + + if (!iregs) + iregs = &dummy_iregs; + + /* Process all but the last event for each counter. */ + for (at = base; at < top;) { + struct arch_pebs_header *header; + struct arch_pebs_basic *basic; + u64 pebs_status; + + header = at; + + if (WARN_ON_ONCE(!header->size)) + break; + + /* 1st fragment or single record must have basic group */ + if (!header->basic) { + at += header->size; continue; + } + + basic = at + sizeof(struct arch_pebs_header); + pebs_status = mask & basic->applicable_counters; + __intel_pmu_handle_pebs_record(iregs, regs, data, at, + pebs_status, counts, last, + setup_arch_pebs_sample_data); + + /* Skip non-last fragments */ + while (arch_pebs_record_continued(header)) { + if (!header->size) + break; + at += header->size; + header = at; + } - __intel_pmu_pebs_event(event, iregs, data, base, - top, bit, counts[bit], - setup_pebs_adaptive_sample_data); + /* Skip last fragment or the single record */ + at += header->size; } + + __intel_pmu_handle_last_pebs_record(iregs, regs, data, mask, + counts, last, + setup_arch_pebs_sample_data); +} + +static void __init intel_arch_pebs_init(void) +{ + /* + * Current hybrid platforms always both support arch-PEBS or not + * on all kinds of cores. So directly set x86_pmu.arch_pebs flag + * if boot cpu supports arch-PEBS. + */ + x86_pmu.arch_pebs = 1; + x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; + x86_pmu.drain_pebs = intel_pmu_drain_arch_pebs; + x86_pmu.pebs_capable = ~0ULL; + x86_pmu.flags |= PMU_FL_PEBS_ALL; + + x86_pmu.pebs_enable = __intel_pmu_pebs_enable; + x86_pmu.pebs_disable = __intel_pmu_pebs_disable; } /* - * BTS, PEBS probe and setup + * PEBS probe and setup */ -void __init intel_ds_init(void) +static void __init intel_ds_pebs_init(void) { /* * No support for 32bit formats @@ -2153,13 +3065,12 @@ void __init intel_ds_init(void) if (!boot_cpu_has(X86_FEATURE_DTES64)) return; - x86_pmu.bts = boot_cpu_has(X86_FEATURE_BTS); - x86_pmu.pebs = boot_cpu_has(X86_FEATURE_PEBS); + x86_pmu.ds_pebs = boot_cpu_has(X86_FEATURE_PEBS); x86_pmu.pebs_buffer_size = PEBS_BUFFER_SIZE; if (x86_pmu.version <= 4) x86_pmu.pebs_no_isolation = 1; - if (x86_pmu.pebs) { + if (x86_pmu.ds_pebs) { char pebs_type = x86_pmu.intel_cap.pebs_trap ? '+' : '-'; char *pebs_qual = ""; int format = x86_pmu.intel_cap.pebs_format; @@ -2167,6 +3078,11 @@ void __init intel_ds_init(void) if (format < 4) x86_pmu.intel_cap.pebs_baseline = 0; + x86_pmu.pebs_enable = intel_pmu_pebs_enable; + x86_pmu.pebs_disable = intel_pmu_pebs_disable; + x86_pmu.pebs_enable_all = intel_pmu_pebs_enable_all; + x86_pmu.pebs_disable_all = intel_pmu_pebs_disable_all; + switch (format) { case 0: pr_cont("PEBS fmt0%c, ", pebs_type); @@ -2202,6 +3118,13 @@ void __init intel_ds_init(void) x86_pmu.large_pebs_flags |= PERF_SAMPLE_TIME; break; + case 6: + if (x86_pmu.intel_cap.pebs_baseline) + x86_pmu.large_pebs_flags |= PERF_SAMPLE_READ; + fallthrough; + case 5: + x86_pmu.pebs_ept = 1; + fallthrough; case 4: x86_pmu.drain_pebs = intel_pmu_drain_pebs_icl; x86_pmu.pebs_record_size = sizeof(struct pebs_basic); @@ -2210,6 +3133,7 @@ void __init intel_ds_init(void) PERF_SAMPLE_BRANCH_STACK | PERF_SAMPLE_TIME; x86_pmu.flags |= PMU_FL_PEBS_ALL; + x86_pmu.pebs_capable = ~0ULL; pebs_qual = "-baseline"; x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_EXTENDED_REGS; } else { @@ -2222,9 +3146,17 @@ void __init intel_ds_init(void) PERF_SAMPLE_REGS_USER | PERF_SAMPLE_REGS_INTR); } - pr_cont("PEBS fmt4%c%s, ", pebs_type, pebs_qual); + pr_cont("PEBS fmt%d%c%s, ", format, pebs_type, pebs_qual); - if (!is_hybrid() && x86_pmu.intel_cap.pebs_output_pt_available) { + /* + * The PEBS-via-PT is not supported on hybrid platforms, + * because not all CPUs of a hybrid machine support it. + * The global x86_pmu.intel_cap, which only contains the + * common capabilities, is used to check the availability + * of the feature. The per-PMU pebs_output_pt_available + * in a hybrid machine should be ignored. + */ + if (x86_pmu.intel_cap.pebs_output_pt_available) { pr_cont("PEBS-via-PT, "); x86_get_pmu(smp_processor_id())->capabilities |= PERF_PMU_CAP_AUX_OUTPUT; } @@ -2233,17 +3165,25 @@ void __init intel_ds_init(void) default: pr_cont("no PEBS fmt%d%c, ", format, pebs_type); - x86_pmu.pebs = 0; + x86_pmu.ds_pebs = 0; } } } +void __init intel_pebs_init(void) +{ + if (x86_pmu.intel_cap.pebs_format == 0xf) + intel_arch_pebs_init(); + else + intel_ds_pebs_init(); +} + void perf_restore_debug_store(void) { struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds); - if (!x86_pmu.bts && !x86_pmu.pebs) + if (!x86_pmu.bts && !x86_pmu.ds_pebs) return; - wrmsrl(MSR_IA32_DS_AREA, (unsigned long)ds); + wrmsrq(MSR_IA32_DS_AREA, (unsigned long)ds); } |