[7/7] perf bpf filter: Add data_src sample data support
Commit Message
The data_src has many entries to express memory behaviors. Add each
term separately so that users can combine them for their purpose.
I didn't add prefix for the constants for simplicity as they are mostly
distinguishable but I had to use l1_miss and l2_hit for mem_dtlb since
mem_lvl has different values for the same names. Note that I decided
mem_lvl to be used as an alias of mem_lvlnum as it's deprecated now.
According to the comment in the UAPI header, users should use the mix
of mem_lvlnum, mem_remote and mem_snoop. Also the SNOOPX bits are
concatenated to mem_snoop for simplicity.
The following terms are used for data_src and the corresponding perf
sample data fields:
* mem_op : { load, store, pfetch, exec }
* mem_lvl: { l1, l2, l3, l4, cxl, io, any_cache, lfb, ram, pmem }
* mem_snoop: { none, hit, miss, hitm, fwd, peer }
* mem_remote: { remote }
* mem_lock: { locked }
* mem_dtlb { l1_hit, l1_miss, l2_hit, l2_miss, any_hit, any_miss, walk, fault }
* mem_blk { by_data, by_addr }
* mem_hops { hops0, hops1, hops2, hops3 }
We can now use a filter expression like below:
'bpf: mem_op == load, mem_lvl <= l2, mem_dtlb == l1_hit'
'bpf: mem_dtlb == l2_miss, mem_hops > hops1'
'bpf: mem_lvl == ram, mem_remote == 1'
Note that 'na' is shared among the terms as it has the same value except
for mem_lvl. I don't have a good idea to handle that for now.
Signed-off-by: Namhyung Kim <namhyung@kernel.org>
---
tools/perf/util/bpf-filter.l | 61 ++++++++++++++++++++
tools/perf/util/bpf_skel/sample_filter.bpf.c | 23 ++++++++
2 files changed, 84 insertions(+)
@@ -41,6 +41,12 @@ static int value(int base)
return BFT_NUM;
}
+static int constant(int val)
+{
+ perf_bpf_filter_lval.num = val;
+ return BFT_NUM;
+}
+
%}
num_dec [0-9]+
@@ -70,6 +76,15 @@ retire_lat { return sample_part(PERF_SAMPLE_WEIGHT_STRUCT, 3); } /* alias for we
phys_addr { return sample(PERF_SAMPLE_PHYS_ADDR); }
code_pgsz { return sample(PERF_SAMPLE_CODE_PAGE_SIZE); }
data_pgsz { return sample(PERF_SAMPLE_DATA_PAGE_SIZE); }
+mem_op { return sample_part(PERF_SAMPLE_DATA_SRC, 1); }
+mem_lvlnum { return sample_part(PERF_SAMPLE_DATA_SRC, 2); }
+mem_lvl { return sample_part(PERF_SAMPLE_DATA_SRC, 2); } /* alias for mem_lvlnum */
+mem_snoop { return sample_part(PERF_SAMPLE_DATA_SRC, 3); } /* include snoopx */
+mem_remote { return sample_part(PERF_SAMPLE_DATA_SRC, 4); }
+mem_lock { return sample_part(PERF_SAMPLE_DATA_SRC, 5); }
+mem_dtlb { return sample_part(PERF_SAMPLE_DATA_SRC, 6); }
+mem_blk { return sample_part(PERF_SAMPLE_DATA_SRC, 7); }
+mem_hops { return sample_part(PERF_SAMPLE_DATA_SRC, 8); }
"==" { return operator(PBF_OP_EQ); }
"!=" { return operator(PBF_OP_NEQ); }
@@ -79,6 +94,52 @@ data_pgsz { return sample(PERF_SAMPLE_DATA_PAGE_SIZE); }
"<=" { return operator(PBF_OP_LE); }
"&" { return operator(PBF_OP_AND); }
+na { return constant(PERF_MEM_OP_NA); }
+load { return constant(PERF_MEM_OP_LOAD); }
+store { return constant(PERF_MEM_OP_STORE); }
+pfetch { return constant(PERF_MEM_OP_PFETCH); }
+exec { return constant(PERF_MEM_OP_EXEC); }
+
+l1 { return constant(PERF_MEM_LVLNUM_L1); }
+l2 { return constant(PERF_MEM_LVLNUM_L2); }
+l3 { return constant(PERF_MEM_LVLNUM_L3); }
+l4 { return constant(PERF_MEM_LVLNUM_L4); }
+cxl { return constant(PERF_MEM_LVLNUM_CXL); }
+io { return constant(PERF_MEM_LVLNUM_IO); }
+any_cache { return constant(PERF_MEM_LVLNUM_ANY_CACHE); }
+lfb { return constant(PERF_MEM_LVLNUM_LFB); }
+ram { return constant(PERF_MEM_LVLNUM_RAM); }
+pmem { return constant(PERF_MEM_LVLNUM_PMEM); }
+
+none { return constant(PERF_MEM_SNOOP_NONE); }
+hit { return constant(PERF_MEM_SNOOP_HIT); }
+miss { return constant(PERF_MEM_SNOOP_MISS); }
+hitm { return constant(PERF_MEM_SNOOP_HITM); }
+fwd { return constant(PERF_MEM_SNOOPX_FWD); }
+peer { return constant(PERF_MEM_SNOOPX_PEER); }
+
+remote { return constant(PERF_MEM_REMOTE_REMOTE); }
+
+locked { return constant(PERF_MEM_LOCK_LOCKED); }
+
+l1_hit { return constant(PERF_MEM_TLB_L1 | PERF_MEM_TLB_HIT); }
+l1_miss { return constant(PERF_MEM_TLB_L1 | PERF_MEM_TLB_MISS); }
+l2_hit { return constant(PERF_MEM_TLB_L2 | PERF_MEM_TLB_HIT); }
+l2_miss { return constant(PERF_MEM_TLB_L2 | PERF_MEM_TLB_MISS); }
+any_hit { return constant(PERF_MEM_TLB_HIT); }
+any_miss { return constant(PERF_MEM_TLB_MISS); }
+walk { return constant(PERF_MEM_TLB_WK); }
+os { return constant(PERF_MEM_TLB_OS); }
+fault { return constant(PERF_MEM_TLB_OS); } /* alias for os */
+
+by_data { return constant(PERF_MEM_BLK_DATA); }
+by_addr { return constant(PERF_MEM_BLK_ADDR); }
+
+hops0 { return constant(PERF_MEM_HOPS_0); }
+hops1 { return constant(PERF_MEM_HOPS_1); }
+hops2 { return constant(PERF_MEM_HOPS_2); }
+hops3 { return constant(PERF_MEM_HOPS_3); }
+
"," { return ','; }
. { }
@@ -62,6 +62,29 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx,
return kctx->data->code_page_size;
case PERF_SAMPLE_DATA_PAGE_SIZE:
return kctx->data->data_page_size;
+ case PERF_SAMPLE_DATA_SRC:
+ if (entry->part == 1)
+ return kctx->data->data_src.mem_op;
+ if (entry->part == 2)
+ return kctx->data->data_src.mem_lvl_num;
+ if (entry->part == 3) {
+ __u32 snoop = kctx->data->data_src.mem_snoop;
+ __u32 snoopx = kctx->data->data_src.mem_snoopx;
+
+ return (snoopx << 5) | snoop;
+ }
+ if (entry->part == 4)
+ return kctx->data->data_src.mem_remote;
+ if (entry->part == 5)
+ return kctx->data->data_src.mem_lock;
+ if (entry->part == 6)
+ return kctx->data->data_src.mem_dtlb;
+ if (entry->part == 7)
+ return kctx->data->data_src.mem_blk;
+ if (entry->part == 8)
+ return kctx->data->data_src.mem_hops;
+ /* return the whole word */
+ return kctx->data->data_src.val;
default:
break;
}