perf: arm-spe: Decode SPE source and use for perf c2c
Subsystems (2)
v4 cover perf: arm-spe: Decode SPE source and use for perf c2c
When synthesizing data from SPE, augment the type with source information for Arm Neoverse cores so we can detect situtions like cache line contention and transfers on Arm platforms.
This changes enables future changes to c2c on a system with SPE where lines that are shared among multiple cores show up in perf c2c output.
Changes in v7:
* Minor change requested by Leo Yan
Changes in v6:
* Drop changes to c2c command which will come from Leo Yan
Changes in v5:
* Add a new snooping type to disambiguate cache-to-cache transfers where we don't know if the data is clean or dirty.
* Set snoop flags on all the data-source cases
* Special case stores as we have no information on them
Changes in v4:
* Bring-in the kernel's arch/arm64/include/asm/cputype.h into tools/
* Add neoverse-v1 to the neoverse cores list
Ali Saidi (4):
tools: arm64: Import cputype.h
perf arm-spe: Use SPE data source for neoverse cores perf mem: Support mem_lvl_num in c2c command perf mem: Support HITM for when mem_lvl_num is any
tools/arch/arm64/include/asm/cputype.h | 258 ++++++++++++++++++ .../util/arm-spe-decoder/arm-spe-decoder.c | 1 + .../util/arm-spe-decoder/arm-spe-decoder.h | 12 + tools/perf/util/arm-spe.c | 110 +++++++- tools/perf/util/mem-events.c | 20 +- 5 files changed, 383 insertions(+), 18 deletions(-) create mode 100644 tools/arch/arm64/include/asm/cputype.h
Signature · 1 line
2.32.0
PATCH v7 1/5 perf: Add SNOOP_PEER flag to perf mem data struct
Add a flag to the perf mem data struct to signal that a request caused a cache-to-cache transfer of a line from a peer of the requestor and wasn't sourced from a lower cache level. The line being moved from one peer cache to another has latency and performance implications. On Arm64 Neoverse systems the data source can indicate a cache-to-cache transfer but not if the line is dirty or clean, so instead of overloading HITM define a new flag that indicates this type of transfer.
--- include/uapi/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
include/uapi/linux/perf_event.h +1 -1
@@ -1310,7 +1310,7 @@ union perf_mem_data_src {#define PERF_MEM_SNOOP_SHIFT 19#define PERF_MEM_SNOOPX_FWD 0x01/* forward */ -/* 1 free */ +#define PERF_MEM_SNOOPX_PEER 0x02/* xfer from peer */ #define PERF_MEM_SNOOPX_SHIFT 38/* locked instruction */
Signature · 1 line
2.32.0
PATCH v7 2/5 perf tools: sync addition of PERF_MEM_SNOOPX_PEER
In reply to Ali SaidiAdd a flag to the perf mem data struct to signal that a request caused a cache-to-cache transfer of a line from a peer of the requestor and wasn't sourced from a lower cache level. The line being moved from one peer cache to another has latency and performance implications. On Arm64 Neoverse systems the data source can indicate a cache-to-cache transfer but not if the line is dirty or clean, so instead of overloading HITM define a new flag that indicates this type of transfer.
--- tools/include/uapi/linux/perf_event.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
tools/include/uapi/linux/perf_event.h +1 -1
@@ -1310,7 +1310,7 @@ union perf_mem_data_src {#define PERF_MEM_SNOOP_SHIFT 19#define PERF_MEM_SNOOPX_FWD 0x01/* forward */ -/* 1 free */ +#define PERF_MEM_SNOOPX_PEER 0x02/* xfer from peer */ #define PERF_MEM_SNOOPX_SHIFT 38/* locked instruction */
Signature · 1 line
2.32.0
PATCH v7 3/5 perf mem: Print snoop peer flag
In reply to Ali SaidiFrom: Leo Yan <[email protected]>
Since PERF_MEM_SNOOPX_PEER flag is a new snoop type, print this flag if it is set.
Before:
memstress 3603 [020] 122.463754: 1 l1d-miss: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP N/A|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)
memstress 3603 [020] 122.463754: 1 l1d-access: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP N/A|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)
memstress 3603 [020] 122.463754: 1 llc-miss: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP N/A|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)
memstress 3603 [020] 122.463754: 1 llc-access: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP N/A|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)
memstress 3603 [020] 122.463754: 1 tlb-access: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP N/A|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)
memstress 3603 [020] 122.463754: 1 memory: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP N/A|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)After:
memstress 3603 [020] 122.463754: 1 l1d-miss: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP Peer|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)
memstress 3603 [020] 122.463754: 1 l1d-access: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP Peer|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)
memstress 3603 [020] 122.463754: 1 llc-miss: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP Peer|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)
memstress 3603 [020] 122.463754: 1 llc-access: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP Peer|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)
memstress 3603 [020] 122.463754: 1 tlb-access: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP Peer|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)
memstress 3603 [020] 122.463754: 1 memory: 8688000842 |OP LOAD|LVL L3 or L3 hit|SNP Peer|TLB Walker hit|LCK No|BLK N/A aaaac17c3e88 [unknown] (/home/ubuntu/memstress)--- tools/perf/util/mem-events.c | 18 +++++++++++++++--- 1 file changed, 15 insertions(+), 3 deletions(-)
tools/perf/util/mem-events.c +15 -3
@@ -410,6 +410,11 @@ static const char * const snoop_access[] = { "HitM", }; +static const char *const snoopx_access[] = { +"Fwd" , +"Peer" , +}; +int perf_mem__snp_scnprintf (char *out,size_t sz,struct mem_info *mem_info) {size_t i, l =0 ;
@@ -430,13 +435,20 @@ int perf_mem__snp_scnprintf(char *out, size_t sz, struct mem_info *mem_info) } l +=scnprintf (out + l, sz - l, snoop_access[i]); } -if (mem_info && - (mem_info->data_src.mem_snoopx &PERF_MEM_SNOOPX_FWD )) { + + m =0 ; +if (mem_info) + m = mem_info->data_src.mem_snoopx; + +for (i =0 ; m && i <ARRAY_SIZE (snoopx_access); i++, m >>=1 ) { +if (!(m &0x1 )) +continue ; +if (l) {strcat (out," or " ); l +=4 ; } - l +=scnprintf (out + l, sz - l,"Fwd" ); + l +=scnprintf (out + l, sz - l, snoopx_access[i]); }if (*out =='\0' )
Signature · 1 line
2.32.0
PATCH v7 4/5 perf arm-spe: Don't set data source if it's not a memory operation
In reply to Ali SaidiFrom: Leo Yan <[email protected]>
Except memory load and store operations, Arm SPE records also can support other operation types, bug when set the data source field the current code assumes a record is a either load operation or store operation, this leads to wrongly synthesize memory samples.
This patch strictly checks the record operation type, it only sets data source only for the operation types ARM_SPE_LD and ARM_SPE_ST, otherwise, returns zero for data source. Therefore, we can synthesize memory samples only when data source is a non-zero value, the function arm_spe__is_memory_event() is useless and removed.
--- tools/perf/util/arm-spe.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-)
tools/perf/util/arm-spe.c +8 -14
@@ -387,26 +387,16 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,return arm_spe_deliver_synth_event (spe, speq, event, &sample); } -#define SPE_MEM_TYPE (ARM_SPE_L1D_ACCESS | ARM_SPE_L1D_MISS | \ - ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS | \ - ARM_SPE_REMOTE_ACCESS) - -static bool arm_spe__is_memory_event (enum arm_spe_sample_type type) -{ -if (type &SPE_MEM_TYPE ) -return true; - -return false; -} -static u64 arm_spe__synth_data_source (const struct arm_spe_record *record) {union perf_mem_data_src data_src = {0 };if (record->op ==ARM_SPE_LD ) data_src.mem_op =PERF_MEM_OP_LOAD ; -else +else if (record->op ==ARM_SPE_ST ) data_src.mem_op =PERF_MEM_OP_STORE ; +else +return 0 ;if (record->type & (ARM_SPE_LLC_ACCESS |ARM_SPE_LLC_MISS )) { data_src.mem_lvl =PERF_MEM_LVL_L3 ;
@@ -510,7 +500,11 @@ static int arm_spe_sample(struct arm_spe_queue *speq)return err; } -if (spe->sample_memory &&arm_spe__is_memory_event (record->type)) { +/* +* When data_src is zero it means the record is not a memory operation, +* skip to synthesize memory sample for this case. +*/ +if (spe->sample_memory && data_src) { err =arm_spe__synth_mem_sample (speq, spe->memory_id, data_src);if (err)return err;
Signature · 1 line
2.32.0
Re: [PATCH v7 4/5] perf arm-spe: Don't set data source if it's not a memory operation
Quoted 13 lines · Ali Saidi
From: Leo Yan <[email protected]>
Except memory load and store operations, Arm SPE records also can support other operation types, bug when set the data source field the current code assumes a record is a either load operation or store operation, this leads to wrongly synthesize memory samples.
This patch strictly checks the record operation type, it only sets data source only for the operation types
ARM_SPE_LDandARM_SPE_ST, otherwise, returns zero for data source. Therefore, we can synthesize memory samples only when data source is a non-zero value, the functionarm_spe__is_memory_event()is useless and removed.
Quoted 3 lines
Signed-off-by Leo Yan <[email protected]>Reviewed-by Ali Saidi <[email protected]>Tested-by Ali Saidi <[email protected]>
I think the Fixes tag is missing, right?
Thanks,
German
Quoted 51 lines
--- tools/perf/util/arm-spe.c | 22 ++++++++-------------- 1 file changed, 8 insertions(+), 14 deletions(-)tools/perf/util/arm-spe.c +8
-14@@ -387,26 +387,16 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,return arm_spe_deliver_synth_event (spe, speq, event, &sample); } -#define SPE_MEM_TYPE (ARM_SPE_L1D_ACCESS | ARM_SPE_L1D_MISS | \ - ARM_SPE_LLC_ACCESS | ARM_SPE_LLC_MISS | \ - ARM_SPE_REMOTE_ACCESS) - -static bool arm_spe__is_memory_event (enum arm_spe_sample_type type) -{ -if (type &SPE_MEM_TYPE ) -return true; - -return false; -} -static u64 arm_spe__synth_data_source (const struct arm_spe_record *record) {union perf_mem_data_src data_src = {0 };if (record->op ==ARM_SPE_LD ) data_src.mem_op =PERF_MEM_OP_LOAD ; -else +else if (record->op ==ARM_SPE_ST ) data_src.mem_op =PERF_MEM_OP_STORE ; +else +return 0 ;if (record->type & (ARM_SPE_LLC_ACCESS |ARM_SPE_LLC_MISS )) { data_src.mem_lvl =PERF_MEM_LVL_L3 ;@@ -510,7 +500,11 @@ static int arm_spe_sample(struct arm_spe_queue *speq)return err; } -if (spe->sample_memory &&arm_spe__is_memory_event (record->type)) { +/* +* When data_src is zero it means the record is not a memory operation, +* skip to synthesize memory sample for this case. +*/ +if (spe->sample_memory && data_src) { err =arm_spe__synth_mem_sample (speq, spe->memory_id, data_src);if (err)return err;
PATCH v7 5/5 perf arm-spe: Use SPE data source for neoverse cores
In reply to Ali SaidiWhen synthesizing data from SPE, augment the type with source information for Arm Neoverse cores. The field is IMPLDEF but the Neoverse cores all use the same encoding. I can't find encoding information for any other SPE implementations to unify their choices with Arm's thus that is left for future work.
This change populates the mem_lvl_num for Neoverse cores as well as the deprecated mem_lvl namespace.
--- .../util/arm-spe-decoder/arm-spe-decoder.c | 1 + .../util/arm-spe-decoder/arm-spe-decoder.h | 12 ++ tools/perf/util/arm-spe.c | 130 +++++++++++++++--- 3 files changed, 127 insertions(+), 16 deletions(-)
tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +1 -0
@@ -220,6 +220,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)break ;case ARM_SPE_DATA_SOURCE : + decoder->record.source = payload;break ;case ARM_SPE_BAD :break ;
tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +12 -0
@@ -29,6 +29,17 @@ enum arm_spe_op_type { ARM_SPE_ST = 1 << 1, }; +enum arm_spe_neoverse_data_source { +ARM_SPE_NV_L1D =0x0 , +ARM_SPE_NV_L2 =0x8 , +ARM_SPE_NV_PEER_CORE =0x9 , +ARM_SPE_NV_LOCAL_CLUSTER =0xa , +ARM_SPE_NV_SYS_CACHE =0xb , +ARM_SPE_NV_PEER_CLUSTER =0xc , +ARM_SPE_NV_REMOTE =0xd , +ARM_SPE_NV_DRAM =0xe , +}; +struct arm_spe_record {enum arm_spe_sample_type type;int err;
@@ -40,6 +51,7 @@ struct arm_spe_record {u64 virt_addr;u64 phys_addr;u64 context_id; +u16 source; };struct arm_spe_insn ;
tools/perf/util/arm-spe.c +114 -16
180 lines not on this page · raw message
Signature · 1 line
2.32.0
Re: [PATCH v7 5/5] perf arm-spe: Use SPE data source for neoverse cores
Quoted 10 lines · Ali Saidi
When synthesizing data from SPE, augment the type with source information for Arm Neoverse cores. The field is IMPLDEF but the Neoverse cores all use the same encoding. I can't find encoding information for any other SPE implementations to unify their choices with Arm's thus that is left for future work.
This change populates the
mem_lvl_numfor Neoverse cores as well as the deprecatedmem_lvlnamespace.Signed-off-by Ali Saidi <[email protected]>
I tested this patch and also did the integration testing with perf ć2c tool, this patch looks good to me:
James, German, it's better if this patch set can get the green light from you. So please take a look, thanks!
Leo
Re: [PATCH v7 5/5] perf arm-spe: Use SPE data source for neoverse cores
In reply to Ali SaidiHi Ali, Leo
Some minor comments below.
Quoted 105 lines · Ali Saidi
When synthesizing data from SPE, augment the type with source information for Arm Neoverse cores. The field is IMPLDEF but the Neoverse cores all use the same encoding. I can't find encoding information for any other SPE implementations to unify their choices with Arm's thus that is left for future work.
This change populates the
mem_lvl_numfor Neoverse cores as well as the deprecatedmem_lvlnamespace.Signed-off-by Ali Saidi <[email protected]>--- .../util/arm-spe-decoder/arm-spe-decoder.c | 1 + .../util/arm-spe-decoder/arm-spe-decoder.h | 12 ++ tools/perf/util/arm-spe.c | 130 +++++++++++++++--- 3 files changed, 127 insertions(+), 16 deletions(-)tools/perf/util/arm-spe-decoder/arm-spe-decoder.c +1
-0@@ -220,6 +220,7 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)break ;case ARM_SPE_DATA_SOURCE : + decoder->record.source = payload;break ;case ARM_SPE_BAD :break ;tools/perf/util/arm-spe-decoder/arm-spe-decoder.h +12
-0@@ -29,6 +29,17 @@ enum arm_spe_op_type { ARM_SPE_ST = 1 << 1, }; +enum arm_spe_neoverse_data_source { +ARM_SPE_NV_L1D =0x0 , +ARM_SPE_NV_L2 =0x8 , +ARM_SPE_NV_PEER_CORE =0x9 , +ARM_SPE_NV_LOCAL_CLUSTER =0xa , +ARM_SPE_NV_SYS_CACHE =0xb , +ARM_SPE_NV_PEER_CLUSTER =0xc , +ARM_SPE_NV_REMOTE =0xd , +ARM_SPE_NV_DRAM =0xe , +}; +struct arm_spe_record {enum arm_spe_sample_type type;int err;@@ -40,6 +51,7 @@ struct arm_spe_record {u64 virt_addr;u64 phys_addr;u64 context_id; +u16 source; };struct arm_spe_insn ;tools/perf/util/arm-spe.c +18
-5@@ -34,6 +34,7 @@#include "arm-spe-decoder/arm-spe-decoder.h" #include "arm-spe-decoder/arm-spe-pkt-decoder.h" +#include "../../arch/arm64/include/asm/cputype.h" #define MAX_TIMESTAMP (~0ULL)struct arm_spe {@@ -45,6 +46,7 @@ struct arm_spe {struct perf_session *session;struct machine *machine;u32 pmu_type; +u64 midr;struct perf_tsc_conversion tc;@@ -387,35 +389,128 @@ static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,return arm_spe_deliver_synth_event (spe, speq, event, &sample); } -static u64 arm_spe__synth_data_source (const struct arm_spe_record *record) +static const struct midr_range neoverse_spe[] = { +MIDR_ALL_VERSIONS (MIDR_NEOVERSE_N1 ), +MIDR_ALL_VERSIONS (MIDR_NEOVERSE_N2 ), +MIDR_ALL_VERSIONS (MIDR_NEOVERSE_V1 ), + {}, +}; + +static void arm_spe__synth_data_source_neoverse (const struct arm_spe_record *record, +union perf_mem_data_src *data_src) { -union perf_mem_data_src data_src = {0 }; +/* +* Even though four levels of cache hierarchy are possible, no known +* production Neoverse systems currently include more than three levels +* so for the time being we assume three exist. If a production system +* is built with four the this function would have to be changed to +* detect the number of levels for reporting. +*/ -if (record->op ==ARM_SPE_LD ) - data_src.mem_op =PERF_MEM_OP_LOAD ; -else if (record->op ==ARM_SPE_ST )
tools/perf/util/arm-spe.c static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, · line 416
Quoted 10 lines
tools/perf/util/arm-spe.c +7
-3- data_src.mem_op =PERF_MEM_OP_STORE ; - else - return 0; +/* +* We have no data on the hit level or data source for stores in the +* Neoverse SPE records. +*/ +if (record->op &ARM_SPE_ST ) { + data_src->mem_lvl =PERF_MEM_LVL_NA ; + data_src->mem_lvl_num =PERF_MEM_LVLNUM_ANY_CACHE ;
Is it correct to use ANY_CACHE as the NA value? The LVLNUM_* enum begins at 1, so it looks like this should be set to 0 instead (like in HOPS_*).
Quoted 54 lines
tools/perf/util/arm-spe.c +54
-0+ data_src->mem_snoop =PERF_MEM_SNOOP_NA ; +return ; + } + +switch (record->source) { +case ARM_SPE_NV_L1D : + data_src->mem_lvl =PERF_MEM_LVL_L1 |PERF_MEM_LVL_HIT ; + data_src->mem_lvl_num =PERF_MEM_LVLNUM_L1 ; + data_src->mem_snoop =PERF_MEM_SNOOP_NONE ; +break ; +case ARM_SPE_NV_L2 : + data_src->mem_lvl =PERF_MEM_LVL_L2 |PERF_MEM_LVL_HIT ; + data_src->mem_lvl_num =PERF_MEM_LVLNUM_L2 ; + data_src->mem_snoop =PERF_MEM_SNOOP_NONE ; +break ; +case ARM_SPE_NV_PEER_CORE : + data_src->mem_lvl =PERF_MEM_LVL_L2 |PERF_MEM_LVL_HIT ; + data_src->mem_lvl_num =PERF_MEM_LVLNUM_L2 ; + data_src->mem_snoopx =PERF_MEM_SNOOPX_PEER ; +break ; +/* +* We don't know if this is L1, L2 but we do know it was a cache-2-cache +* transfer, so set SNOOPX_PEER +*/ +case ARM_SPE_NV_LOCAL_CLUSTER : +case ARM_SPE_NV_PEER_CLUSTER : + data_src->mem_lvl =PERF_MEM_LVL_L3 |PERF_MEM_LVL_HIT ; + data_src->mem_lvl_num =PERF_MEM_LVLNUM_L3 ; + data_src->mem_snoopx =PERF_MEM_SNOOPX_PEER ; +break ; +/* +* System cache is assumed to be L3 +*/ +case ARM_SPE_NV_SYS_CACHE : + data_src->mem_lvl =PERF_MEM_LVL_L3 |PERF_MEM_LVL_HIT ; + data_src->mem_lvl_num =PERF_MEM_LVLNUM_L3 ; + data_src->mem_snoop =PERF_MEM_SNOOP_HIT ; +break ; +/* +* We don't know what level it hit in, except it came from the other +* socket +*/ +case ARM_SPE_NV_REMOTE : + data_src->mem_lvl =PERF_MEM_LVL_REM_RAM1 |PERF_MEM_LVL_HIT ; + data_src->mem_lvl_num =PERF_MEM_LVLNUM_RAM ; + data_src->mem_remote =PERF_MEM_REMOTE_REMOTE ; + data_src->mem_snoop =PERF_MEM_SNOOP_NA ; +break ; +case ARM_SPE_NV_DRAM : + data_src->mem_lvl =PERF_MEM_LVL_LOC_RAM |PERF_MEM_LVL_HIT ; + data_src->mem_lvl_num =PERF_MEM_LVLNUM_RAM ; + data_src->mem_snoop =PERF_MEM_SNOOP_NONE ; +break ; +default :
tools/perf/util/arm-spe.c static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, · line 479
Quoted 10 lines
tools/perf/util/arm-spe.c +7
-1+break ; + } +} +static void arm_spe__synth_data_source_generic (const struct arm_spe_record *record, +union perf_mem_data_src *data_src) +{if (record->type & (ARM_SPE_LLC_ACCESS |ARM_SPE_LLC_MISS )) { - data_src.mem_lvl =PERF_MEM_LVL_L3 ; + data_src->mem_lvl =PERF_MEM_LVL_L3 ;
Thanks for addressing my previous comment about filling both mem_lvl and mem_lvl_num.
I wonder if it's also worth updating for the non-Neoverse cores as well while we're at it. I'll let Leo decide since this patchset is only focused on Neoverse.
Aside from these comments, this change also looks good to me. Thanks for catching the things I missed in my previous review.
Quoted 69 lines
tools/perf/util/arm-spe.c +28
-7if (record->type &ARM_SPE_LLC_MISS ) - data_src.mem_lvl |=PERF_MEM_LVL_MISS ; + data_src->mem_lvl |=PERF_MEM_LVL_MISS ;else - data_src.mem_lvl |=PERF_MEM_LVL_HIT ; + data_src->mem_lvl |=PERF_MEM_LVL_HIT ; }else if (record->type & (ARM_SPE_L1D_ACCESS |ARM_SPE_L1D_MISS )) { - data_src.mem_lvl =PERF_MEM_LVL_L1 ; + data_src->mem_lvl =PERF_MEM_LVL_L1 ;if (record->type &ARM_SPE_L1D_MISS ) - data_src.mem_lvl |=PERF_MEM_LVL_MISS ; + data_src->mem_lvl |=PERF_MEM_LVL_MISS ;else - data_src.mem_lvl |=PERF_MEM_LVL_HIT ; + data_src->mem_lvl |=PERF_MEM_LVL_HIT ; }if (record->type &ARM_SPE_REMOTE_ACCESS ) - data_src.mem_lvl |=PERF_MEM_LVL_REM_CCE1 ; + data_src->mem_lvl |=PERF_MEM_LVL_REM_CCE1 ; +} + +static u64 arm_spe__synth_data_source (const struct arm_spe_record *record,u64 midr) +{ +union perf_mem_data_src data_src = {0 }; +bool is_neoverse =is_midr_in_range (midr, neoverse_spe); + +if (record->op ==ARM_SPE_LD ) + data_src.mem_op =PERF_MEM_OP_LOAD ; +else if (record->op ==ARM_SPE_ST ) + data_src.mem_op =PERF_MEM_OP_STORE ; +else +return 0 ; + +if (is_neoverse) +arm_spe__synth_data_source_neoverse (record, &data_src); +else +arm_spe__synth_data_source_generic (record, &data_src);if (record->type & (ARM_SPE_TLB_ACCESS |ARM_SPE_TLB_MISS )) { data_src.mem_dtlb =PERF_MEM_TLB_WK ;@@ -436,7 +531,7 @@ static int arm_spe_sample(struct arm_spe_queue *speq)u64 data_src;int err; - data_src =arm_spe__synth_data_source (record); + data_src =arm_spe__synth_data_source (record, spe->midr);if (spe->sample_flc) {if (record->type &ARM_SPE_L1D_MISS ) {@@ -1177,6 +1272,8 @@ int arm_spe_process_auxtrace_info(union perf_event *event,struct perf_record_auxtrace_info *auxtrace_info = &event->auxtrace_info;size_t min_sz =sizeof (u64) *ARM_SPE_AUXTRACE_PRIV_MAX ;struct perf_record_time_conv *tc = &session->time_conv; +const char *cpuid =perf_env__cpuid (session->evlist->env); +u64 midr =strtol (cpuid,NULL ,16 );struct arm_spe *spe;int err;@@ -1196,6 +1293,7 @@ int arm_spe_process_auxtrace_info(union perf_event *event, spe->machine = &session->machines.host;/* No kvm support */ spe->auxtrace_type = auxtrace_info->type; spe->pmu_type = auxtrace_info->priv[ARM_SPE_PMU_TYPE ]; + spe->midr = midr; spe->timeless_decoding =arm_spe__is_timeless_decoding (spe);
Re: [PATCH v7 5/5] perf arm-spe: Use SPE data source for neoverse cores
Hi German,
Thanks for taking another look!
Quoted 22 lines · German Gomez
Hi Ali, Leo
Some minor comments below.
Quoted 16 lines · Ali Saidi
When synthesizing data from SPE, augment the type with source information for Arm Neoverse cores. The field is IMPLDEF but the Neoverse cores all use the same encoding. I can't find encoding information for any other SPE implementations to unify their choices with Arm's thus that is left for future work.
This change populates the
mem_lvl_numfor Neoverse cores as well as the deprecatedmem_lvlnamespace.Signed-off-by Ali Saidi <[email protected]>--- .../util/arm-spe-decoder/arm-spe-decoder.c | 1 + .../util/arm-spe-decoder/arm-spe-decoder.h | 12 ++ tools/perf/util/arm-spe.c | 130 +++++++++++++++--- 3 files changed, 127 insertions(+), 16 deletions(-)[snip]
Quoted 9 lines
tools/perf/util/arm-spe.c static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, · line 416
Quoted 7 lines
tools/perf/util/arm-spe.c +7
-0+/* +* We have no data on the hit level or data source for stores in the +* Neoverse SPE records. +*/ +if (record->op &ARM_SPE_ST ) { + data_src->mem_lvl =PERF_MEM_LVL_NA ; + data_src->mem_lvl_num =PERF_MEM_LVLNUM_ANY_CACHE ;Is it correct to use
ANY_CACHEas the NA value? The LVLNUM_* enum begins at 1, so it looks like this should be set to 0 instead (like in HOPS_*).
I think you're making a good point here. To be consistent we should set mem_lvl_num to PERF_MEM_LVLNUM_NA just like mem_lvl.
Thanks,
Ali
Re: [PATCH v7 5/5] perf arm-spe: Use SPE data source for neoverse cores
In reply to German GomezOn Tue, May 03, 2022 at 10:58:15AM +0100, German Gomez wrote:
[...]
Quoted 10 lines
tools/perf/util/arm-spe.c static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq, · line 479
Quoted 6 lines
tools/perf/util/arm-spe.c +4
-1+static void arm_spe__synth_data_source_generic (const struct arm_spe_record *record, +union perf_mem_data_src *data_src) +{if (record->type & (ARM_SPE_LLC_ACCESS |ARM_SPE_LLC_MISS )) { - data_src.mem_lvl =PERF_MEM_LVL_L3 ; + data_src->mem_lvl =PERF_MEM_LVL_L3 ;Thanks for addressing my previous comment about filling both
mem_lvlandmem_lvl_num.I wonder if it's also worth updating for the non-Neoverse cores as well while we're at it. I'll let Leo decide since this patchset is only focused on Neoverse.
Thanks for pointing out this. Yeah, Let's use this patch set for enabling Neoverse data source.
We can use a new patch to updating cache level for non-Neoverse cores (it's better also set store cache level as LVL_NA for non-Neoverse cores).
Thanks,
Leo