diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2024-11-19 13:34:06 -0800 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2024-11-19 13:34:06 -0800 |
commit | f41dac3efb7582cd3f518fadf7764d424f453788 (patch) | |
tree | da2aee8b82625525adf671911ed862af43a1b60d /arch/x86/events/intel/core.c | |
parent | 9d7d4ad222aea8ab482e78858d03b10221c7fe78 (diff) | |
parent | 2c47e7a74f445426d156278e339b7abb259e50de (diff) |
Merge tag 'perf-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull performance events updates from Ingo Molnar:
"Uprobes:
- Add BPF session support (Jiri Olsa)
- Switch to RCU Tasks Trace flavor for better performance (Andrii
Nakryiko)
- Massively increase uretprobe SMP scalability by SRCU-protecting
the uretprobe lifetime (Andrii Nakryiko)
- Kill xol_area->slot_count (Oleg Nesterov)
Core facilities:
- Implement targeted high-frequency profiling by adding the ability
for an event to "pause" or "resume" AUX area tracing (Adrian
Hunter)
VM profiling/sampling:
- Correct perf sampling with guest VMs (Colton Lewis)
New hardware support:
- x86/intel: Add PMU support for Intel ArrowLake-H CPUs (Dapeng Mi)
Misc fixes and enhancements:
- x86/intel/pt: Fix buffer full but size is 0 case (Adrian Hunter)
- x86/amd: Warn only on new bits set (Breno Leitao)
- x86/amd/uncore: Avoid a false positive warning about snprintf
truncation in amd_uncore_umc_ctx_init (Jean Delvare)
- uprobes: Re-order struct uprobe_task to save some space
(Christophe JAILLET)
- x86/rapl: Move the pmu allocation out of CPU hotplug (Kan Liang)
- x86/rapl: Clean up cpumask and hotplug (Kan Liang)
- uprobes: Deuglify xol_get_insn_slot/xol_free_insn_slot paths (Oleg
Nesterov)"
* tag 'perf-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
perf/core: Correct perf sampling with guest VMs
perf/x86: Refactor misc flag assignments
perf/powerpc: Use perf_arch_instruction_pointer()
perf/core: Hoist perf_instruction_pointer() and perf_misc_flags()
perf/arm: Drop unused functions
uprobes: Re-order struct uprobe_task to save some space
perf/x86/amd/uncore: Avoid a false positive warning about snprintf truncation in amd_uncore_umc_ctx_init
perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
perf/x86/intel/pt: Add support for pause / resume
perf/core: Add aux_pause, aux_resume, aux_start_paused
perf/x86/intel/pt: Fix buffer full but size is 0 case
uprobes: SRCU-protect uretprobe lifetime (with timeout)
uprobes: allow put_uprobe() from non-sleepable softirq context
perf/x86/rapl: Clean up cpumask and hotplug
perf/x86/rapl: Move the pmu allocation out of CPU hotplug
uprobe: Add support for session consumer
uprobe: Add data pointer to consumer handlers
perf/x86/amd: Warn only on new bits set
uprobes: fold xol_take_insn_slot() into xol_get_insn_slot()
uprobes: kill xol_area->slot_count
...
Diffstat (limited to 'arch/x86/events/intel/core.c')
-rw-r--r-- | arch/x86/events/intel/core.c | 137 |
1 files changed, 123 insertions, 14 deletions
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c index d879478db3f5..bb284aff7bfd 100644 --- a/arch/x86/events/intel/core.c +++ b/arch/x86/events/intel/core.c @@ -3962,8 +3962,8 @@ static int intel_pmu_hw_config(struct perf_event *event) if (!(event->attr.freq || (event->attr.wakeup_events && !event->attr.watermark))) { event->hw.flags |= PERF_X86_EVENT_AUTO_RELOAD; - if (!(event->attr.sample_type & - ~intel_pmu_large_pebs_flags(event))) { + if (!(event->attr.sample_type & ~intel_pmu_large_pebs_flags(event)) && + !has_aux_action(event)) { event->hw.flags |= PERF_X86_EVENT_LARGE_PEBS; event->attach_state |= PERF_ATTACH_SCHED_CB; } @@ -4599,6 +4599,28 @@ static inline bool erratum_hsw11(struct perf_event *event) X86_CONFIG(.event=0xc0, .umask=0x01); } +static struct event_constraint * +arl_h_get_event_constraints(struct cpu_hw_events *cpuc, int idx, + struct perf_event *event) +{ + struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); + + if (pmu->pmu_type == hybrid_tiny) + return cmt_get_event_constraints(cpuc, idx, event); + + return mtl_get_event_constraints(cpuc, idx, event); +} + +static int arl_h_hw_config(struct perf_event *event) +{ + struct x86_hybrid_pmu *pmu = hybrid_pmu(event->pmu); + + if (pmu->pmu_type == hybrid_tiny) + return intel_pmu_hw_config(event); + + return adl_hw_config(event); +} + /* * The HSW11 requires a period larger than 100 which is the same as the BDM11. * A minimum period of 128 is enforced as well for the INST_RETIRED.ALL. @@ -4924,17 +4946,26 @@ static struct x86_hybrid_pmu *find_hybrid_pmu_for_cpu(void) /* * This essentially just maps between the 'hybrid_cpu_type' - * and 'hybrid_pmu_type' enums: + * and 'hybrid_pmu_type' enums except for ARL-H processor + * which needs to compare atom uarch native id since ARL-H + * contains two different atom uarchs. */ for (i = 0; i < x86_pmu.num_hybrid_pmus; i++) { enum hybrid_pmu_type pmu_type = x86_pmu.hybrid_pmu[i].pmu_type; + u32 native_id; - if (cpu_type == HYBRID_INTEL_CORE && - pmu_type == hybrid_big) - return &x86_pmu.hybrid_pmu[i]; - if (cpu_type == HYBRID_INTEL_ATOM && - pmu_type == hybrid_small) + if (cpu_type == HYBRID_INTEL_CORE && pmu_type == hybrid_big) return &x86_pmu.hybrid_pmu[i]; + if (cpu_type == HYBRID_INTEL_ATOM) { + if (x86_pmu.num_hybrid_pmus == 2 && pmu_type == hybrid_small) + return &x86_pmu.hybrid_pmu[i]; + + native_id = get_this_hybrid_cpu_native_id(); + if (native_id == skt_native_id && pmu_type == hybrid_small) + return &x86_pmu.hybrid_pmu[i]; + if (native_id == cmt_native_id && pmu_type == hybrid_tiny) + return &x86_pmu.hybrid_pmu[i]; + } } return NULL; @@ -5965,6 +5996,37 @@ static struct attribute *lnl_hybrid_events_attrs[] = { NULL }; +/* The event string must be in PMU IDX order. */ +EVENT_ATTR_STR_HYBRID(topdown-retiring, + td_retiring_arl_h, + "event=0xc2,umask=0x02;event=0x00,umask=0x80;event=0xc2,umask=0x0", + hybrid_big_small_tiny); +EVENT_ATTR_STR_HYBRID(topdown-bad-spec, + td_bad_spec_arl_h, + "event=0x73,umask=0x0;event=0x00,umask=0x81;event=0x73,umask=0x0", + hybrid_big_small_tiny); +EVENT_ATTR_STR_HYBRID(topdown-fe-bound, + td_fe_bound_arl_h, + "event=0x9c,umask=0x01;event=0x00,umask=0x82;event=0x71,umask=0x0", + hybrid_big_small_tiny); +EVENT_ATTR_STR_HYBRID(topdown-be-bound, + td_be_bound_arl_h, + "event=0xa4,umask=0x02;event=0x00,umask=0x83;event=0x74,umask=0x0", + hybrid_big_small_tiny); + +static struct attribute *arl_h_hybrid_events_attrs[] = { + EVENT_PTR(slots_adl), + EVENT_PTR(td_retiring_arl_h), + EVENT_PTR(td_bad_spec_arl_h), + EVENT_PTR(td_fe_bound_arl_h), + EVENT_PTR(td_be_bound_arl_h), + EVENT_PTR(td_heavy_ops_adl), + EVENT_PTR(td_br_mis_adl), + EVENT_PTR(td_fetch_lat_adl), + EVENT_PTR(td_mem_bound_adl), + NULL, +}; + /* Must be in IDX order */ EVENT_ATTR_STR_HYBRID(mem-loads, mem_ld_adl, "event=0xd0,umask=0x5,ldlat=3;event=0xcd,umask=0x1,ldlat=3", hybrid_big_small); EVENT_ATTR_STR_HYBRID(mem-stores, mem_st_adl, "event=0xd0,umask=0x6;event=0xcd,umask=0x2", hybrid_big_small); @@ -5983,6 +6045,21 @@ static struct attribute *mtl_hybrid_mem_attrs[] = { NULL }; +EVENT_ATTR_STR_HYBRID(mem-loads, + mem_ld_arl_h, + "event=0xd0,umask=0x5,ldlat=3;event=0xcd,umask=0x1,ldlat=3;event=0xd0,umask=0x5,ldlat=3", + hybrid_big_small_tiny); +EVENT_ATTR_STR_HYBRID(mem-stores, + mem_st_arl_h, + "event=0xd0,umask=0x6;event=0xcd,umask=0x2;event=0xd0,umask=0x6", + hybrid_big_small_tiny); + +static struct attribute *arl_h_hybrid_mem_attrs[] = { + EVENT_PTR(mem_ld_arl_h), + EVENT_PTR(mem_st_arl_h), + NULL, +}; + EVENT_ATTR_STR_HYBRID(tx-start, tx_start_adl, "event=0xc9,umask=0x1", hybrid_big); EVENT_ATTR_STR_HYBRID(tx-commit, tx_commit_adl, "event=0xc9,umask=0x2", hybrid_big); EVENT_ATTR_STR_HYBRID(tx-abort, tx_abort_adl, "event=0xc9,umask=0x4", hybrid_big); @@ -6006,8 +6083,8 @@ static struct attribute *adl_hybrid_tsx_attrs[] = { FORMAT_ATTR_HYBRID(in_tx, hybrid_big); FORMAT_ATTR_HYBRID(in_tx_cp, hybrid_big); -FORMAT_ATTR_HYBRID(offcore_rsp, hybrid_big_small); -FORMAT_ATTR_HYBRID(ldlat, hybrid_big_small); +FORMAT_ATTR_HYBRID(offcore_rsp, hybrid_big_small_tiny); +FORMAT_ATTR_HYBRID(ldlat, hybrid_big_small_tiny); FORMAT_ATTR_HYBRID(frontend, hybrid_big); #define ADL_HYBRID_RTM_FORMAT_ATTR \ @@ -6030,7 +6107,7 @@ static struct attribute *adl_hybrid_extra_attr[] = { NULL }; -FORMAT_ATTR_HYBRID(snoop_rsp, hybrid_small); +FORMAT_ATTR_HYBRID(snoop_rsp, hybrid_small_tiny); static struct attribute *mtl_hybrid_extra_attr_rtm[] = { ADL_HYBRID_RTM_FORMAT_ATTR, @@ -6238,8 +6315,9 @@ static inline int intel_pmu_v6_addr_offset(int index, bool eventsel) } static const struct { enum hybrid_pmu_type id; char *name; } intel_hybrid_pmu_type_map[] __initconst = { - { hybrid_small, "cpu_atom" }, - { hybrid_big, "cpu_core" }, + { hybrid_small, "cpu_atom" }, + { hybrid_big, "cpu_core" }, + { hybrid_tiny, "cpu_lowpower" }, }; static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus) @@ -6272,7 +6350,7 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus) 0, x86_pmu_num_counters(&pmu->pmu), 0, 0); pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities; - if (pmu->pmu_type & hybrid_small) { + if (pmu->pmu_type & hybrid_small_tiny) { pmu->intel_cap.perf_metrics = 0; pmu->intel_cap.pebs_output_pt_available = 1; pmu->mid_ack = true; @@ -7111,6 +7189,37 @@ __init int intel_pmu_init(void) name = "lunarlake_hybrid"; break; + case INTEL_ARROWLAKE_H: + intel_pmu_init_hybrid(hybrid_big_small_tiny); + + x86_pmu.pebs_latency_data = arl_h_latency_data; + x86_pmu.get_event_constraints = arl_h_get_event_constraints; + x86_pmu.hw_config = arl_h_hw_config; + + td_attr = arl_h_hybrid_events_attrs; + mem_attr = arl_h_hybrid_mem_attrs; + tsx_attr = adl_hybrid_tsx_attrs; + extra_attr = boot_cpu_has(X86_FEATURE_RTM) ? + mtl_hybrid_extra_attr_rtm : mtl_hybrid_extra_attr; + + /* Initialize big core specific PerfMon capabilities. */ + pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX]; + intel_pmu_init_lnc(&pmu->pmu); + + /* Initialize Atom core specific PerfMon capabilities. */ + pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_ATOM_IDX]; + intel_pmu_init_skt(&pmu->pmu); + + /* Initialize Lower Power Atom specific PerfMon capabilities. */ + pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_TINY_IDX]; + intel_pmu_init_grt(&pmu->pmu); + pmu->extra_regs = intel_cmt_extra_regs; + + intel_pmu_pebs_data_source_arl_h(); + pr_cont("ArrowLake-H Hybrid events, "); + name = "arrowlake_h_hybrid"; + break; + default: switch (x86_pmu.version) { case 1: |