perf bpf-filter: Support filtering on cgroups

The new cgroup filter can take either of '==' or '!=' operator and a
pathname for the target cgroup.

  $ perf record -a --all-cgroups -e cycles --filter 'cgroup == /abc/def' -- sleep 1

Users should have --all-cgroups option in the command line to enable
cgroup filtering.  Technically it doesn't need to have the option as
it can get the current task's cgroup info directly from BPF.  But I want
to follow the convention for the other sample info.

Signed-off-by: Namhyung Kim <namhyung@kernel.org>
Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: Ian Rogers <irogers@google.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Kan Liang <kan.liang@linux.intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Link: https://lore.kernel.org/r/20240826221045.1202305-4-namhyung@kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

diff --git a/tools/perf/util/bpf-filter.c b/tools/perf/util/bpf-filter.c
index 0a1832564dd25c8049a49fe3e5430d50d0425f00..e87b6789eb9ef3b9ce174da383e43d465a07278e 100644 (file)
--- a/tools/perf/util/bpf-filter.c
+++ b/tools/perf/util/bpf-filter.c
@@ -100,6 +100,7 @@ static const struct perf_sample_info {
        PERF_SAMPLE_TYPE(TRANSACTION, "--transaction"),
        PERF_SAMPLE_TYPE(CODE_PAGE_SIZE, "--code-page-size"),
        PERF_SAMPLE_TYPE(DATA_PAGE_SIZE, "--data-page-size"),
+       PERF_SAMPLE_TYPE(CGROUP, "--all-cgroups"),
 };
 
 static int get_pinned_fd(const char *name);

diff --git a/tools/perf/util/bpf-filter.l b/tools/perf/util/bpf-filter.l
index 2a7c839f3fae2b2236c34fbd532664ee6f788016..f313404f95a90d252cdde26b88e0a02950ed490b 100644 (file)
--- a/tools/perf/util/bpf-filter.l
+++ b/tools/perf/util/bpf-filter.l
@@ -9,8 +9,11 @@
 #include "bpf-filter.h"
 #include "bpf-filter-bison.h"
 
+extern int perf_bpf_filter_needs_path;
+
 static int sample(enum perf_bpf_filter_term term)
 {
+       perf_bpf_filter_needs_path = 0;
        perf_bpf_filter_lval.sample.term = term;
        perf_bpf_filter_lval.sample.part = 0;
        return BFT_SAMPLE;
@@ -18,11 +21,20 @@ static int sample(enum perf_bpf_filter_term term)
 
 static int sample_part(enum perf_bpf_filter_term term, int part)
 {
+       perf_bpf_filter_needs_path = 0;
        perf_bpf_filter_lval.sample.term = term;
        perf_bpf_filter_lval.sample.part = part;
        return BFT_SAMPLE;
 }
 
+static int sample_path(enum perf_bpf_filter_term term)
+{
+       perf_bpf_filter_needs_path = 1;
+       perf_bpf_filter_lval.sample.term = term;
+       perf_bpf_filter_lval.sample.part = 0;
+       return BFT_SAMPLE_PATH;
+}
+
 static int operator(enum perf_bpf_filter_op op)
 {
        perf_bpf_filter_lval.op = op;
@@ -48,10 +60,15 @@ static int constant(int val)
        return BFT_NUM;
 }
 
-static int error(const char *str)
+static int path_or_error(void)
 {
-       printf("perf_bpf_filter: Unexpected filter %s: %s\n", str, perf_bpf_filter_text);
-       return BFT_ERROR;
+       if (!perf_bpf_filter_needs_path) {
+               printf("perf_bpf_filter: Error: Unexpected item: %s\n",
+                       perf_bpf_filter_text);
+               return BFT_ERROR;
+       }
+       perf_bpf_filter_lval.path = perf_bpf_filter_text;
+       return BFT_PATH;
 }
 
 %}
@@ -59,6 +76,7 @@ static int error(const char *str)
 num_dec                [0-9]+
 num_hex                0[Xx][0-9a-fA-F]+
 space          [ \t]+
+path           [^ \t\n]+
 ident          [_a-zA-Z][_a-zA-Z0-9]+
 
 %%
@@ -97,6 +115,7 @@ mem_blk              { return sample_part(PBF_TERM_DATA_SRC, 7); }
 mem_hops       { return sample_part(PBF_TERM_DATA_SRC, 8); }
 uid            { return sample(PBF_TERM_UID); }
 gid            { return sample(PBF_TERM_GID); }
+cgroup         { return sample_path(PBF_TERM_CGROUP); }
 
 "=="           { return operator(PBF_OP_EQ); }
 "!="           { return operator(PBF_OP_NEQ); }
@@ -155,7 +174,6 @@ hops3               { return constant(PERF_MEM_HOPS_3); }
 ","            { return ','; }
 "||"           { return BFT_LOGICAL_OR; }
 
-{ident}                { return error("ident"); }
-.              { return error("input"); }
+{path}         { return path_or_error(); }
 
 %%

diff --git a/tools/perf/util/bpf-filter.y b/tools/perf/util/bpf-filter.y
index 0c56fccb8874885ad368a1be2f2ce923e6f62b32..5a79a8e7a45b1a98905dd0b7527d0c5cf514a040 100644 (file)
--- a/tools/perf/util/bpf-filter.y
+++ b/tools/perf/util/bpf-filter.y
@@ -12,9 +12,13 @@
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include "bpf-filter.h"
+#include "cgroup.h"
 
 int perf_bpf_filter_lex(void);
 
+/* To indicate if the current term needs a pathname or not */
+int perf_bpf_filter_needs_path;
+
 static void perf_bpf_filter_error(struct list_head *expr __maybe_unused,
                                  char const *msg)
 {
@@ -26,6 +30,7 @@ static void perf_bpf_filter_error(struct list_head *expr __maybe_unused,
 %union
 {
        unsigned long num;
+       char *path;
        struct {
                enum perf_bpf_filter_term term;
                int part;
@@ -34,12 +39,13 @@ static void perf_bpf_filter_error(struct list_head *expr __maybe_unused,
        struct perf_bpf_filter_expr *expr;
 }
 
-%token BFT_SAMPLE BFT_OP BFT_ERROR BFT_NUM BFT_LOGICAL_OR
+%token BFT_SAMPLE BFT_SAMPLE_PATH BFT_OP BFT_ERROR BFT_NUM BFT_LOGICAL_OR BFT_PATH
 %type <expr> filter_term filter_expr
 %destructor { free ($$); } <expr>
-%type <sample> BFT_SAMPLE
+%type <sample> BFT_SAMPLE BFT_SAMPLE_PATH
 %type <op> BFT_OP
 %type <num> BFT_NUM
+%type <path> BFT_PATH
 
 %%
 
@@ -81,5 +87,23 @@ BFT_SAMPLE BFT_OP BFT_NUM
 {
        $$ = perf_bpf_filter_expr__new($1.term, $1.part, $2, $3);
 }
+|
+BFT_SAMPLE_PATH BFT_OP BFT_PATH
+{
+       struct cgroup *cgrp;
+       unsigned long cgroup_id = 0;
+
+       if ($2 != PBF_OP_EQ && $2 != PBF_OP_NEQ) {
+               printf("perf_bpf_filter: cgroup accepts '==' or '!=' only\n");
+               YYERROR;
+       }
+
+       cgrp = cgroup__new($3, /*do_open=*/false);
+       if (cgrp && read_cgroup_id(cgrp) == 0)
+               cgroup_id = cgrp->id;
+
+       $$ = perf_bpf_filter_expr__new($1.term, $1.part, $2, cgroup_id);
+       cgroup__put(cgrp);
+}
 
 %%

diff --git a/tools/perf/util/bpf_skel/sample-filter.h b/tools/perf/util/bpf_skel/sample-filter.h
index 5f0c8e4e83d3e09b9cfdd496cd14f32f8f44b101..683fec85e71ef3524d69fc9b62b49d27e618cbcf 100644 (file)
--- a/tools/perf/util/bpf_skel/sample-filter.h
+++ b/tools/perf/util/bpf_skel/sample-filter.h
@@ -45,7 +45,7 @@ enum perf_bpf_filter_term {
        __PBF_UNUSED_TERM18     = PBF_TERM_SAMPLE_START + 18, /* SAMPLE_REGS_INTR = 1U << 18 */
        PBF_TERM_PHYS_ADDR      = PBF_TERM_SAMPLE_START + 19, /* SAMPLE_PHYS_ADDR = 1U << 19 */
        __PBF_UNUSED_TERM20     = PBF_TERM_SAMPLE_START + 20, /* SAMPLE_AUX = 1U << 20 */
-       __PBF_UNUSED_TERM21     = PBF_TERM_SAMPLE_START + 21, /* SAMPLE_CGROUP = 1U << 21 */
+       PBF_TERM_CGROUP         = PBF_TERM_SAMPLE_START + 21, /* SAMPLE_CGROUP = 1U << 21 */
        PBF_TERM_DATA_PAGE_SIZE = PBF_TERM_SAMPLE_START + 22, /* SAMPLE_DATA_PAGE_SIZE = 1U << 22 */
        PBF_TERM_CODE_PAGE_SIZE = PBF_TERM_SAMPLE_START + 23, /* SAMPLE_CODE_PAGE_SIZE = 1U << 23 */
        PBF_TERM_WEIGHT_STRUCT  = PBF_TERM_SAMPLE_START + 24, /* SAMPLE_WEIGHT_STRUCT = 1U << 24 */

diff --git a/tools/perf/util/bpf_skel/sample_filter.bpf.c b/tools/perf/util/bpf_skel/sample_filter.bpf.c
index 4872a16eedfd457d3c9dbcd663c446300195529e..b195e6efeb8beb0ed82b959ca149b2f782369809 100644 (file)
--- a/tools/perf/util/bpf_skel/sample_filter.bpf.c
+++ b/tools/perf/util/bpf_skel/sample_filter.bpf.c
@@ -93,6 +93,7 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx,
        BUILD_CHECK_SAMPLE(DATA_SRC);
        BUILD_CHECK_SAMPLE(TRANSACTION);
        BUILD_CHECK_SAMPLE(PHYS_ADDR);
+       BUILD_CHECK_SAMPLE(CGROUP);
        BUILD_CHECK_SAMPLE(DATA_PAGE_SIZE);
        BUILD_CHECK_SAMPLE(CODE_PAGE_SIZE);
        BUILD_CHECK_SAMPLE(WEIGHT_STRUCT);
@@ -135,6 +136,8 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx,
                return kctx->data->weight.full;
        case PBF_TERM_PHYS_ADDR:
                return kctx->data->phys_addr;
+       case PBF_TERM_CGROUP:
+               return kctx->data->cgroup;
        case PBF_TERM_CODE_PAGE_SIZE:
                return kctx->data->code_page_size;
        case PBF_TERM_DATA_PAGE_SIZE:
@@ -183,7 +186,6 @@ static inline __u64 perf_get_sample(struct bpf_perf_event_data_kern *kctx,
        case __PBF_UNUSED_TERM16:
        case __PBF_UNUSED_TERM18:
        case __PBF_UNUSED_TERM20:
-       case __PBF_UNUSED_TERM21:
        default:
                break;
        }

diff --git a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
index 4fa21468487e1bf2f760221a2534d578c6c8c835..4dcad7b682bdee9c0d4f30389a227b97fc2648c2 100644 (file)
--- a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
+++ b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
@@ -171,6 +171,7 @@ struct perf_sample_data {
                u32              cpu;
        } cpu_entry;
        u64                      phys_addr;
+       u64                      cgroup;
        u64                      data_page_size;
        u64                      code_page_size;
 } __attribute__((__aligned__(64))) __attribute__((preserve_access_index));