From 2a6c6b7d7ad346f0679d0963cb19b3f0ea7ef32c Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 28 Jan 2021 14:40:07 -0800 Subject: perf/core: Add PERF_SAMPLE_WEIGHT_STRUCT Current PERF_SAMPLE_WEIGHT sample type is very useful to expresses the cost of an action represented by the sample. This allows the profiler to scale the samples to be more informative to the programmer. It could also help to locate a hotspot, e.g., when profiling by memory latencies, the expensive load appear higher up in the histograms. But current PERF_SAMPLE_WEIGHT sample type is solely determined by one factor. This could be a problem, if users want two or more factors to contribute to the weight. For example, Golden Cove core PMU can provide both the instruction latency and the cache Latency information as factors for the memory profiling. For current X86 platforms, although meminfo::latency is defined as a u64, only the lower 32 bits include the valid data in practice (No memory access could last than 4G cycles). The higher 32 bits can be used to store new factors. Add a new sample type, PERF_SAMPLE_WEIGHT_STRUCT, to indicate the new sample weight structure. It shares the same space as the PERF_SAMPLE_WEIGHT sample type. Users can apply either the PERF_SAMPLE_WEIGHT sample type or the PERF_SAMPLE_WEIGHT_STRUCT sample type to retrieve the sample weight, but they cannot apply both sample types simultaneously. Currently, only X86 and PowerPC use the PERF_SAMPLE_WEIGHT sample type. - For PowerPC, there is nothing changed for the PERF_SAMPLE_WEIGHT sample type. There is no effect for the new PERF_SAMPLE_WEIGHT_STRUCT sample type. PowerPC can re-struct the weight field similarly later. - For X86, the same value will be dumped for the PERF_SAMPLE_WEIGHT sample type or the PERF_SAMPLE_WEIGHT_STRUCT sample type for now. The following patches will apply the new factors for the PERF_SAMPLE_WEIGHT_STRUCT sample type. The field in the union perf_sample_weight should be shared among different architectures. A generic name is required, but it's hard to abstract a name that applies to all architectures. For example, on X86, the fields are to store all kinds of latency. While on PowerPC, it stores MMCRA[TECX/TECM], which should not be latency. So a general name prefix 'var$NUM' is used here. Suggested-by: Peter Zijlstra (Intel) Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1611873611-156687-2-git-send-email-kan.liang@linux.intel.com --- include/uapi/linux/perf_event.h | 42 +++++++++++++++++++++++++++++++++++++++-- 1 file changed, 40 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b15e3447cd9f..b2cc246ec119 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -145,12 +145,14 @@ enum perf_event_sample_format { PERF_SAMPLE_CGROUP = 1U << 21, PERF_SAMPLE_DATA_PAGE_SIZE = 1U << 22, PERF_SAMPLE_CODE_PAGE_SIZE = 1U << 23, + PERF_SAMPLE_WEIGHT_STRUCT = 1U << 24, - PERF_SAMPLE_MAX = 1U << 24, /* non-ABI */ + PERF_SAMPLE_MAX = 1U << 25, /* non-ABI */ __PERF_SAMPLE_CALLCHAIN_EARLY = 1ULL << 63, /* non-ABI; internal use */ }; +#define PERF_SAMPLE_WEIGHT_TYPE (PERF_SAMPLE_WEIGHT | PERF_SAMPLE_WEIGHT_STRUCT) /* * values to program into branch_sample_type when PERF_SAMPLE_BRANCH is set * @@ -890,7 +892,24 @@ enum perf_event_type { * char data[size]; * u64 dyn_size; } && PERF_SAMPLE_STACK_USER * - * { u64 weight; } && PERF_SAMPLE_WEIGHT + * { union perf_sample_weight + * { + * u64 full; && PERF_SAMPLE_WEIGHT + * #if defined(__LITTLE_ENDIAN_BITFIELD) + * struct { + * u32 var1_dw; + * u16 var2_w; + * u16 var3_w; + * } && PERF_SAMPLE_WEIGHT_STRUCT + * #elif defined(__BIG_ENDIAN_BITFIELD) + * struct { + * u16 var3_w; + * u16 var2_w; + * u32 var1_dw; + * } && PERF_SAMPLE_WEIGHT_STRUCT + * #endif + * } + * } * { u64 data_src; } && PERF_SAMPLE_DATA_SRC * { u64 transaction; } && PERF_SAMPLE_TRANSACTION * { u64 abi; # enum perf_sample_regs_abi @@ -1248,4 +1267,23 @@ struct perf_branch_entry { reserved:40; }; +union perf_sample_weight { + __u64 full; +#if defined(__LITTLE_ENDIAN_BITFIELD) + struct { + __u32 var1_dw; + __u16 var2_w; + __u16 var3_w; + }; +#elif defined(__BIG_ENDIAN_BITFIELD) + struct { + __u16 var3_w; + __u16 var2_w; + __u32 var1_dw; + }; +#else +#error "Unknown endianness" +#endif +}; + #endif /* _UAPI_LINUX_PERF_EVENT_H */ -- cgit v1.2.3 From 61b985e3e775a3a75fda04ce7ef1b1aefc4758bc Mon Sep 17 00:00:00 2001 From: Kan Liang Date: Thu, 28 Jan 2021 14:40:10 -0800 Subject: perf/x86/intel: Add perf core PMU support for Sapphire Rapids Add perf core PMU support for the Intel Sapphire Rapids server, which is the successor of the Intel Ice Lake server. The enabling code is based on Ice Lake, but there are several new features introduced. The event encoding is changed and simplified, e.g., the event codes which are below 0x90 are restricted to counters 0-3. The event codes which above 0x90 are likely to have no restrictions. The event constraints, extra_regs(), and hardware cache events table are changed accordingly. A new Precise Distribution (PDist) facility is introduced, which further minimizes the skid when a precise event is programmed on the GP counter 0. Enable the Precise Distribution (PDist) facility with :ppp event. For this facility to work, the period must be initialized with a value larger than 127. Add spr_limit_period() to apply the limit for :ppp event. Two new data source fields, data block & address block, are added in the PEBS Memory Info Record for the load latency event. To enable the feature, - An auxiliary event has to be enabled together with the load latency event on Sapphire Rapids. A new flag PMU_FL_MEM_LOADS_AUX is introduced to indicate the case. A new event, mem-loads-aux, is exposed to sysfs for the user tool. Add a check in hw_config(). If the auxiliary event is not detected, return an unique error -ENODATA. - The union perf_mem_data_src is extended to support the new fields. - Ice Lake and earlier models do not support block information, but the fields may be set by HW on some machines. Add pebs_no_block to explicitly indicate the previous platforms which don't support the new block fields. Accessing the new block fields are ignored on those platforms. A new store Latency facility is introduced, which leverages the PEBS facility where it can provide additional information about sampled stores. The additional information includes the data address, memory auxiliary info (e.g. Data Source, STLB miss) and the latency of the store access. To enable the facility, the new event (0x02cd) has to be programed on the GP counter 0. A new flag PERF_X86_EVENT_PEBS_STLAT is introduced to indicate the event. The store_latency_data() is introduced to parse the memory auxiliary info. The layout of access latency field of PEBS Memory Info Record has been changed. Two latency, instruction latency (bit 15:0) and cache access latency (bit 47:32) are recorded. - The cache access latency is similar to previous memory access latency. For loads, the latency starts by the actual cache access until the data is returned by the memory subsystem. For stores, the latency starts when the demand write accesses the L1 data cache and lasts until the cacheline write is completed in the memory subsystem. The cache access latency is stored in low 32bits of the sample type PERF_SAMPLE_WEIGHT_STRUCT. - The instruction latency starts by the dispatch of the load operation for execution and lasts until completion of the instruction it belongs to. Add a new flag PMU_FL_INSTR_LATENCY to indicate the instruction latency support. The instruction latency is stored in the bit 47:32 of the sample type PERF_SAMPLE_WEIGHT_STRUCT. Extends the PERF_METRICS MSR to feature TMA method level 2 metrics. The lower half of the register is the TMA level 1 metrics (legacy). The upper half is also divided into four 8-bit fields for the new level 2 metrics. Expose all eight Topdown metrics events to user space. The full description for the SPR features can be found at Intel Architecture Instruction Set Extensions and Future Features Programming Reference, 319433-041. Signed-off-by: Kan Liang Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/1611873611-156687-5-git-send-email-kan.liang@linux.intel.com --- include/uapi/linux/perf_event.h | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'include/uapi/linux') diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h index b2cc246ec119..7d292de51410 100644 --- a/include/uapi/linux/perf_event.h +++ b/include/uapi/linux/perf_event.h @@ -1146,14 +1146,16 @@ union perf_mem_data_src { mem_lvl_num:4, /* memory hierarchy level number */ mem_remote:1, /* remote */ mem_snoopx:2, /* snoop mode, ext */ - mem_rsvd:24; + mem_blk:3, /* access blocked */ + mem_rsvd:21; }; }; #elif defined(__BIG_ENDIAN_BITFIELD) union perf_mem_data_src { __u64 val; struct { - __u64 mem_rsvd:24, + __u64 mem_rsvd:21, + mem_blk:3, /* access blocked */ mem_snoopx:2, /* snoop mode, ext */ mem_remote:1, /* remote */ mem_lvl_num:4, /* memory hierarchy level number */ @@ -1236,6 +1238,12 @@ union perf_mem_data_src { #define PERF_MEM_TLB_OS 0x40 /* OS fault handler */ #define PERF_MEM_TLB_SHIFT 26 +/* Access blocked */ +#define PERF_MEM_BLK_NA 0x01 /* not available */ +#define PERF_MEM_BLK_DATA 0x02 /* data could not be forwarded */ +#define PERF_MEM_BLK_ADDR 0x04 /* address conflict */ +#define PERF_MEM_BLK_SHIFT 40 + #define PERF_MEM_S(a, s) \ (((__u64)PERF_MEM_##a##_##s) << PERF_MEM_##a##_SHIFT) -- cgit v1.2.3