diff mbox series

[07/10] perf bpf filter: Add data_src sample data support

Message ID 20230314234237.3008956-8-namhyung@kernel.org (mailing list archive)
State Handled Elsewhere
Delegated to: BPF
Headers show
Series perf record: Implement BPF sample filter (v5) | expand

Checks

Context Check Description
netdev/tree_selection success Not a local patch
bpf/vmtest-bpf-PR fail merge-conflict
bpf/vmtest-bpf-VM_Test-1 success Logs for ShellCheck
bpf/vmtest-bpf-VM_Test-2 success Logs for build for aarch64 with gcc
bpf/vmtest-bpf-VM_Test-3 success Logs for build for aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-4 success Logs for build for s390x with gcc
bpf/vmtest-bpf-VM_Test-5 success Logs for build for x86_64 with gcc
bpf/vmtest-bpf-VM_Test-6 success Logs for build for x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-7 success Logs for llvm-toolchain
bpf/vmtest-bpf-VM_Test-8 success Logs for set-matrix
bpf/vmtest-bpf-VM_Test-9 success Logs for test_maps on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-10 success Logs for test_maps on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-11 success Logs for test_maps on s390x with gcc
bpf/vmtest-bpf-VM_Test-12 success Logs for test_maps on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-13 success Logs for test_maps on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-14 fail Logs for test_progs on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-15 fail Logs for test_progs on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-16 fail Logs for test_progs on s390x with gcc
bpf/vmtest-bpf-VM_Test-17 fail Logs for test_progs on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-18 fail Logs for test_progs on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-19 fail Logs for test_progs_no_alu32 on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-20 fail Logs for test_progs_no_alu32 on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-21 fail Logs for test_progs_no_alu32 on s390x with gcc
bpf/vmtest-bpf-VM_Test-22 fail Logs for test_progs_no_alu32 on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-23 fail Logs for test_progs_no_alu32 on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-24 success Logs for test_progs_no_alu32_parallel on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-25 success Logs for test_progs_no_alu32_parallel on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-26 success Logs for test_progs_no_alu32_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-27 success Logs for test_progs_no_alu32_parallel on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-28 success Logs for test_progs_parallel on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-29 success Logs for test_progs_parallel on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-30 success Logs for test_progs_parallel on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-31 success Logs for test_progs_parallel on x86_64 with llvm-17
bpf/vmtest-bpf-VM_Test-32 success Logs for test_verifier on aarch64 with gcc
bpf/vmtest-bpf-VM_Test-33 success Logs for test_verifier on aarch64 with llvm-17
bpf/vmtest-bpf-VM_Test-34 success Logs for test_verifier on s390x with gcc
bpf/vmtest-bpf-VM_Test-35 success Logs for test_verifier on x86_64 with gcc
bpf/vmtest-bpf-VM_Test-36 success Logs for test_verifier on x86_64 with llvm-17

Commit Message

Namhyung Kim March 14, 2023, 11:42 p.m. UTC
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:

  'mem_op == load, mem_lvl <= l2, mem_dtlb == l1_hit'
  'mem_dtlb == l2_miss, mem_hops > hops1'
  '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.

Acked-by: Jiri Olsa <jolsa@kernel.org>
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(+)
diff mbox series

Patch

diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l
index 419f923b35c0..3e66b7a0215e 100644
--- a/tools/perf/util/bpf-filter.l
+++ b/tools/perf/util/bpf-filter.l
@@ -42,6 +42,12 @@  static int value(int base)
 	return BFT_NUM;
 }
 
+static int constant(int val)
+{
+	perf_bpf_filter_lval.num = val;
+	return BFT_NUM;
+}
+
 static int error(const char *str)
 {
 	printf("perf_bpf_filter: Unexpected filter %s: %s\n", str, perf_bpf_filter_text);
@@ -80,6 +86,15 @@  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); }
@@ -89,6 +104,52 @@  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 ','; }
 
 {ident}		{ return error("ident"); }
diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c
index d930401c5bfc..88dbc788d257 100644
--- a/tools/perf/util/bpf_skel/sample_filter.bpf.c
+++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c
@@ -70,6 +70,29 @@  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;
 	}