perf script: Add API for filtering via dynamically loaded shared object
Adrian Hunter
reviewercover perf script: Add API for filtering via dynamically loaded shared object
Hi
In some cases, users want to filter very large amounts of data (e.g. from AUX area tracing like Intel PT) looking for something specific. While scripting such as Python can be used, Python is 10 to 20 times slower than C. So define a C API so that custom filters can be written and loaded.
There are 3 preparation patches. The main patch is patch 4.
The other patches add more functionality, except for patch 6 which installs the C API header file.
Adrian Hunter (11):
perf script: Move filter_cpu() earlier
perf script: Move filtering before scripting
perf script: Share addr_al between functions
perf script: Add API for filtering via dynamically loaded shared object perf script: Add dlfilter__filter_event_early()
perf build: Install perf_dlfilter.h
perf dlfilter: Add resolve_address() to perf_dlfilter_fns perf dlfilter: Add insn() to perf_dlfilter_fns
perf dlfilter: Add srcline() to perf_dlfilter_fns
perf dlfilter: Add attr() to perf_dlfilter_fns
perf dlfilter: Add object_code() to perf_dlfilter_fns
tools/perf/Documentation/perf-dlfilter.txt | 235 +++++++++++++++ tools/perf/Documentation/perf-script.txt | 7 +- tools/perf/Makefile.config | 3 + tools/perf/Makefile.perf | 4 +- tools/perf/builtin-script.c | 93 ++++-- tools/perf/util/Build | 1 + tools/perf/util/dlfilter.c | 469 +++++++++++++++++++++++++++++ tools/perf/util/dlfilter.h | 91 ++++++ tools/perf/util/perf_dlfilter.h | 139 +++++++++ 9 files changed, 1015 insertions(+), 27 deletions(-) create mode 100644 tools/perf/Documentation/perf-dlfilter.txt create mode 100644 tools/perf/util/dlfilter.c create mode 100644 tools/perf/util/dlfilter.h create mode 100644 tools/perf/util/perf_dlfilter.h
Regards
Adrian
Adrian Hunter
reviewerRFC PATCH 1/11 perf script: Move filter_cpu() earlier
Generally, it should be more efficient if filter_cpu() comes before machine__resolve() because filter_cpu() is much less code than machine__resolve().
Example:
$ perf record --sample-cpu -- make -C tools/perf >/dev/null
Before:
$ perf stat -- perf script -C 0 >/dev/null
Performance counter stats for 'perf script -C 0':
116.94 msec task-clock # 0.992 CPUs utilized
2 context-switches # 17.103 /sec
0 cpu-migrations # 0.000 /sec
8,187 page-faults # 70.011 K/sec
478,351,812 cycles # 4.091 GHz
564,785,464 instructions # 1.18 insn per cycle
114,341,105 branches # 977.789 M/sec
2,615,495 branch-misses # 2.29% of all branches 0.117840576 seconds time elapsed
0.085040000 seconds user
0.032396000 seconds sysAfter:
$ perf stat -- perf script -C 0 >/dev/null
Performance counter stats for 'perf script -C 0':
107.45 msec task-clock # 0.992 CPUs utilized
3 context-switches # 27.919 /sec
0 cpu-migrations # 0.000 /sec
7,964 page-faults # 74.117 K/sec
438,417,260 cycles # 4.080 GHz
522,571,855 instructions # 1.19 insn per cycle
105,187,488 branches # 978.921 M/sec
2,356,261 branch-misses # 2.24% of all branches 0.108282546 seconds time elapsed
0.095935000 seconds user
0.011991000 seconds sys--- tools/perf/builtin-script.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
tools/perf/builtin-script.c +3 -3
@@ -2191,6 +2191,9 @@ static int process_sample_event(struct perf_tool *tool,return 0 ; } +if (filter_cpu (sample)) +return 0 ; +if (machine__resolve (machine, &al, sample) <0 ) {pr_err ("problem processing %d event, skipping it.\n" , event->header.type);
@@ -2200,9 +2203,6 @@ static int process_sample_event(struct perf_tool *tool,if (al.filtered) goto out_put; -if (filter_cpu (sample)) - goto out_put; -if (scripting_ops) {struct addr_location *addr_al_ptr =NULL ;struct addr_location addr_al;
Signature · 1 line
2.17.1
Arnaldo Carvalho de Melo
maintainerRe: [PATCH RFC 01/11] perf script: Move filter_cpu() earlier
Em Mon, Jun 21, 2021 at 06:05:04PM +0300, Adrian Hunter escreveu:
Quoted 3 lines
Generally, it should be more efficient if
filter_cpu()comes beforemachine__resolve()becausefilter_cpu()is much less code thanmachine__resolve().
Simple patch, I like it, applied.
- Arnaldo
Quoted 76 lines
Example:
$ perf record --sample-cpu -- make -C tools/perf >/dev/nullBefore:
$ perf stat -- perf script -C 0 >/dev/nullPerformance counter stats for 'perf script -C 0':
116.94 msec task-clock # 0.992 CPUs utilized 2 context-switches # 17.103 /sec 0 cpu-migrations # 0.000 /sec 8,187 page-faults # 70.011 K/sec 478,351,812 cycles # 4.091 GHz 564,785,464 instructions # 1.18 insn per cycle 114,341,105 branches # 977.789 M/sec 2,615,495 branch-misses # 2.29% of all branches0.117840576 seconds time elapsed 0.085040000 seconds user 0.032396000 seconds sysAfter:
$ perf stat -- perf script -C 0 >/dev/nullPerformance counter stats for 'perf script -C 0':
107.45 msec task-clock # 0.992 CPUs utilized 3 context-switches # 27.919 /sec 0 cpu-migrations # 0.000 /sec 7,964 page-faults # 74.117 K/sec 438,417,260 cycles # 4.080 GHz 522,571,855 instructions # 1.19 insn per cycle 105,187,488 branches # 978.921 M/sec 2,356,261 branch-misses # 2.24% of all branches0.108282546 seconds time elapsed 0.095935000 seconds user 0.011991000 seconds sysSigned-off-by Adrian Hunter <[email protected]>--- tools/perf/builtin-script.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)tools/perf/builtin-script.c +3
-3@@ -2191,6 +2191,9 @@ static int process_sample_event(struct perf_tool *tool,return 0 ; } +if (filter_cpu (sample)) +return 0 ; +if (machine__resolve (machine, &al, sample) <0 ) {pr_err ("problem processing %d event, skipping it.\n" , event->header.type);@@ -2200,9 +2203,6 @@ static int process_sample_event(struct perf_tool *tool,if (al.filtered) goto out_put; -if (filter_cpu (sample)) - goto out_put; -if (scripting_ops) {struct addr_location *addr_al_ptr =NULL ;struct addr_location addr_al;Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
Adrian Hunter
reviewerRFC PATCH 2/11 perf script: Move filtering before scripting
In reply to Adrian HunterTo make it possible to use filtering with scripts, move filtering before scripting.
--- tools/perf/builtin-script.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)
tools/perf/builtin-script.c +6 -6
@@ -1984,12 +1984,6 @@ static void process_event(struct perf_script *script,if (output[type].fields ==0 )return ; -if (!show_event (sample, evsel, thread, al)) -return ; - -if (evswitch__discard (&script->evswitch, evsel)) -return ; - ++es->samples; perf_sample__fprintf_start(script, sample, thread, evsel,
@@ -2203,6 +2197,12 @@ static int process_sample_event(struct perf_tool *tool,if (al.filtered) goto out_put; +if (!show_event (sample, evsel, al.thread, &al)) + goto out_put; + +if (evswitch__discard (&scr->evswitch, evsel)) + goto out_put; +if (scripting_ops) {struct addr_location *addr_al_ptr =NULL ;struct addr_location addr_al;
Signature · 1 line
2.17.1
Re: [PATCH RFC 02/11] perf script: Move filtering before scripting
Em Mon, Jun 21, 2021 at 06:05:05PM +0300, Adrian Hunter escreveu:
Quoted 2 lines
To make it possible to use filtering with scripts, move filtering before scripting.
Thanks, applied.
- Arnaldo
Quoted 38 lines
Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/builtin-script.c | 12 ++++++------ 1 file changed, 6 insertions(+), 6 deletions(-)tools/perf/builtin-script.c +6
-6@@ -1984,12 +1984,6 @@ static void process_event(struct perf_script *script,if (output[type].fields ==0 )return ; -if (!show_event (sample, evsel, thread, al)) -return ; - -if (evswitch__discard (&script->evswitch, evsel)) -return ; - ++es->samples; perf_sample__fprintf_start(script, sample, thread, evsel,@@ -2203,6 +2197,12 @@ static int process_sample_event(struct perf_tool *tool,if (al.filtered) goto out_put; +if (!show_event (sample, evsel, al.thread, &al)) + goto out_put; + +if (evswitch__discard (&scr->evswitch, evsel)) + goto out_put; +if (scripting_ops) {struct addr_location *addr_al_ptr =NULL ;struct addr_location addr_al;Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
Adrian Hunter
reviewerRFC PATCH 3/11 perf script: Share addr_al between functions
In reply to Adrian HunterShare the addr_location of 'addr' so that it need not be resolved more than once.
--- tools/perf/builtin-script.c | 38 +++++++++++++++++++++++-------------- 1 file changed, 24 insertions(+), 14 deletions(-)
tools/perf/builtin-script.c +24 -14
@@ -1337,17 +1337,18 @@ static const char *resolve_branch_sym(struct perf_sample *sample,struct evsel *evsel, struct thread *thread, struct addr_location *al, + struct addr_location *addr_al, u64 *ip) { - struct addr_location addr_al; struct perf_event_attr *attr = &evsel->core.attr;const char *name =NULL ;if (sample->flags & (PERF_IP_FLAG_CALL |PERF_IP_FLAG_TRACE_BEGIN )) {if (sample_addr_correlates_sym (attr)) { -thread__resolve (thread, &addr_al, sample); -if (addr_al.sym) - name = addr_al.sym->name; +if (!addr_al->thread) +thread__resolve (thread, addr_al, sample); +if (addr_al->sym) + name = addr_al->sym->name;else *ip = sample->addr; }else {
@@ -1365,7 +1366,9 @@ static const char *resolve_branch_sym(struct perf_sample *sample,static int perf_sample__fprintf_callindent (struct perf_sample *sample,struct evsel *evsel,struct thread *thread, -struct addr_location *al,FILE *fp) +struct addr_location *al, +struct addr_location *addr_al, +FILE *fp) {struct perf_event_attr *attr = &evsel->core.attr;size_t depth =thread_stack__depth (thread, sample->cpu);
@@ -1382,7 +1385,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,if (thread->ts && sample->flags &PERF_IP_FLAG_RETURN ) depth +=1 ; - name =resolve_branch_sym (sample, evsel, thread, al, &ip); + name =resolve_branch_sym (sample, evsel, thread, al, addr_al, &ip);if (PRINT_FIELD (DSO ) && !(PRINT_FIELD (IP ) ||PRINT_FIELD (ADDR ))) { dlen +=fprintf (fp,"(" );
@@ -1466,6 +1469,7 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample,struct evsel *evsel, struct thread *thread, struct addr_location *al, + struct addr_location *addr_al, struct machine *machine, FILE *fp) { struct perf_event_attr *attr = &evsel->core.attr;
@@ -1474,7 +1478,7 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample,int printed =0 ;if (PRINT_FIELD (CALLINDENT )) - printed +=perf_sample__fprintf_callindent (sample, evsel, thread, al, fp); + printed +=perf_sample__fprintf_callindent (sample, evsel, thread, al, addr_al, fp);/* print branch_from information */ if (PRINT_FIELD (IP )) {
@@ -1931,7 +1935,8 @@ static void perf_sample__fprint_metric(struct perf_script *script,static bool show_event (struct perf_sample *sample,struct evsel *evsel,struct thread *thread, -struct addr_location *al) +struct addr_location *al, +struct addr_location *addr_al) {int depth =thread_stack__depth (thread, sample->cpu);
@@ -1947,7 +1952,7 @@ static bool show_event(struct perf_sample *sample, }else {const char *s = symbol_conf.graph_function;u64 ip; -const char *name =resolve_branch_sym (sample, evsel, thread, al, +const char *name =resolve_branch_sym (sample, evsel, thread, al, addr_al, &ip);unsigned nlen;
@@ -1972,6 +1977,7 @@ static bool show_event(struct perf_sample *sample,static void process_event (struct perf_script *script,struct perf_sample *sample,struct evsel *evsel,struct addr_location *al, +struct addr_location *addr_al,struct machine *machine) {struct thread *thread = al->thread;
@@ -2005,7 +2011,7 @@ static void process_event(struct perf_script *script,perf_sample__fprintf_flags (sample->flags, fp);if (is_bts_event (attr)) { -perf_sample__fprintf_bts (sample, evsel, thread, al, machine, fp); +perf_sample__fprintf_bts (sample, evsel, thread, al, addr_al, machine, fp);return ; }
@@ -2168,6 +2174,7 @@ static int process_sample_event(struct perf_tool *tool, { struct perf_script *scr = container_of(tool, struct perf_script, tool);struct addr_location al; +struct addr_location addr_al;if (perf_time__ranges_skip_sample (scr->ptime_range, scr->range_num, sample->time)) {
@@ -2197,7 +2204,10 @@ static int process_sample_event(struct perf_tool *tool,if (al.filtered) goto out_put; -if (!show_event (sample, evsel, al.thread, &al)) +/* Set thread to NULL to indicate addr_al is not initialized */ + addr_al.thread =NULL ; + +if (!show_event (sample, evsel, al.thread, &al, &addr_al)) goto out_put;if (evswitch__discard (&scr->evswitch, evsel))
@@ -2205,16 +2215,16 @@ static int process_sample_event(struct perf_tool *tool,if (scripting_ops) {struct addr_location *addr_al_ptr =NULL ; -struct addr_location addr_al;if ((evsel->core.attr.sample_type &PERF_SAMPLE_ADDR ) &&sample_addr_correlates_sym (&evsel->core.attr)) { -thread__resolve (al.thread, &addr_al, sample); +if (!addr_al.thread) +thread__resolve (al.thread, &addr_al, sample); addr_al_ptr = &addr_al; } scripting_ops->process_event (event, sample, evsel, &al, addr_al_ptr); }else { -process_event (scr, sample, evsel, &al, machine); +process_event (scr, sample, evsel, &al, &addr_al, machine); } out_put:
Signature · 1 line
2.17.1
Arnaldo Carvalho de Melo
maintainerRe: [PATCH RFC 03/11] perf script: Share addr_al between functions
Em Mon, Jun 21, 2021 at 06:05:06PM +0300, Adrian Hunter escreveu:
Quoted 2 lines
Share the
addr_locationof 'addr' so that it need not be resolved more than once.
Another nice patch, i.e. don't resolve it unconditionally, let the first function that needs it under a callchain to do it, then reuse if another needs it.
Looks ok, applied.
- Arnaldo
Quoted 148 lines
Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/builtin-script.c | 38 +++++++++++++++++++++++-------------- 1 file changed, 24 insertions(+), 14 deletions(-)tools/perf/builtin-script.c +24
-14@@ -1337,17 +1337,18 @@ static const char *resolve_branch_sym(struct perf_sample *sample,struct evsel *evsel, struct thread *thread, struct addr_location *al, + struct addr_location *addr_al, u64 *ip) { - struct addr_location addr_al; struct perf_event_attr *attr = &evsel->core.attr;const char *name =NULL ;if (sample->flags & (PERF_IP_FLAG_CALL |PERF_IP_FLAG_TRACE_BEGIN )) {if (sample_addr_correlates_sym (attr)) { -thread__resolve (thread, &addr_al, sample); -if (addr_al.sym) - name = addr_al.sym->name; +if (!addr_al->thread) +thread__resolve (thread, addr_al, sample); +if (addr_al->sym) + name = addr_al->sym->name;else *ip = sample->addr; }else {@@ -1365,7 +1366,9 @@ static const char *resolve_branch_sym(struct perf_sample *sample,static int perf_sample__fprintf_callindent (struct perf_sample *sample,struct evsel *evsel,struct thread *thread, -struct addr_location *al,FILE *fp) +struct addr_location *al, +struct addr_location *addr_al, +FILE *fp) {struct perf_event_attr *attr = &evsel->core.attr;size_t depth =thread_stack__depth (thread, sample->cpu);@@ -1382,7 +1385,7 @@ static int perf_sample__fprintf_callindent(struct perf_sample *sample,if (thread->ts && sample->flags &PERF_IP_FLAG_RETURN ) depth +=1 ; - name =resolve_branch_sym (sample, evsel, thread, al, &ip); + name =resolve_branch_sym (sample, evsel, thread, al, addr_al, &ip);if (PRINT_FIELD (DSO ) && !(PRINT_FIELD (IP ) ||PRINT_FIELD (ADDR ))) { dlen +=fprintf (fp,"(" );@@ -1466,6 +1469,7 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample,struct evsel *evsel, struct thread *thread, struct addr_location *al, + struct addr_location *addr_al, struct machine *machine, FILE *fp) { struct perf_event_attr *attr = &evsel->core.attr;@@ -1474,7 +1478,7 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample,int printed =0 ;if (PRINT_FIELD (CALLINDENT )) - printed +=perf_sample__fprintf_callindent (sample, evsel, thread, al, fp); + printed +=perf_sample__fprintf_callindent (sample, evsel, thread, al, addr_al, fp);/* print branch_from information */ if (PRINT_FIELD (IP )) {@@ -1931,7 +1935,8 @@ static void perf_sample__fprint_metric(struct perf_script *script,static bool show_event (struct perf_sample *sample,struct evsel *evsel,struct thread *thread, -struct addr_location *al) +struct addr_location *al, +struct addr_location *addr_al) {int depth =thread_stack__depth (thread, sample->cpu);@@ -1947,7 +1952,7 @@ static bool show_event(struct perf_sample *sample, }else {const char *s = symbol_conf.graph_function;u64 ip; -const char *name =resolve_branch_sym (sample, evsel, thread, al, +const char *name =resolve_branch_sym (sample, evsel, thread, al, addr_al, &ip);unsigned nlen;@@ -1972,6 +1977,7 @@ static bool show_event(struct perf_sample *sample,static void process_event (struct perf_script *script,struct perf_sample *sample,struct evsel *evsel,struct addr_location *al, +struct addr_location *addr_al,struct machine *machine) {struct thread *thread = al->thread;@@ -2005,7 +2011,7 @@ static void process_event(struct perf_script *script,perf_sample__fprintf_flags (sample->flags, fp);if (is_bts_event (attr)) { -perf_sample__fprintf_bts (sample, evsel, thread, al, machine, fp); +perf_sample__fprintf_bts (sample, evsel, thread, al, addr_al, machine, fp);return ; }@@ -2168,6 +2174,7 @@ static int process_sample_event(struct perf_tool *tool, { struct perf_script *scr = container_of(tool, struct perf_script, tool);struct addr_location al; +struct addr_location addr_al;if (perf_time__ranges_skip_sample (scr->ptime_range, scr->range_num, sample->time)) {@@ -2197,7 +2204,10 @@ static int process_sample_event(struct perf_tool *tool,if (al.filtered) goto out_put; -if (!show_event (sample, evsel, al.thread, &al)) +/* Set thread to NULL to indicate addr_al is not initialized */ + addr_al.thread =NULL ; + +if (!show_event (sample, evsel, al.thread, &al, &addr_al)) goto out_put;if (evswitch__discard (&scr->evswitch, evsel))@@ -2205,16 +2215,16 @@ static int process_sample_event(struct perf_tool *tool,if (scripting_ops) {struct addr_location *addr_al_ptr =NULL ; -struct addr_location addr_al;if ((evsel->core.attr.sample_type &PERF_SAMPLE_ADDR ) &&sample_addr_correlates_sym (&evsel->core.attr)) { -thread__resolve (al.thread, &addr_al, sample); +if (!addr_al.thread) +thread__resolve (al.thread, &addr_al, sample); addr_al_ptr = &addr_al; } scripting_ops->process_event (event, sample, evsel, &al, addr_al_ptr); }else { -process_event (scr, sample, evsel, &al, machine); +process_event (scr, sample, evsel, &al, &addr_al, machine); } out_put:Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
Adrian Hunter
reviewerRFC PATCH 4/11 perf script: Add API for filtering via dynamically loaded shared object
In reply to Adrian HunterIn some cases, users want to filter very large amounts of data (e.g. from AUX area tracing like Intel PT) looking for something specific. While scripting such as Python can be used, Python is 10 to 20 times slower than C. So define a C API so that custom filters can be written and loaded.
--- tools/perf/Documentation/perf-dlfilter.txt | 214 +++++++++++++ tools/perf/Documentation/perf-script.txt | 7 +- tools/perf/builtin-script.c | 25 +- tools/perf/util/Build | 1 + tools/perf/util/dlfilter.c | 330 +++++++++++++++++++++ tools/perf/util/dlfilter.h | 74 +++++ tools/perf/util/perf_dlfilter.h | 120 ++++++++ 7 files changed, 769 insertions(+), 2 deletions(-) create mode 100644 tools/perf/Documentation/perf-dlfilter.txt create mode 100644 tools/perf/util/dlfilter.c create mode 100644 tools/perf/util/dlfilter.h create mode 100644 tools/perf/util/perf_dlfilter.h
tools/perf/Documentation/perf-dlfilter.txt new file +214 -0
@@ -0,0 +1,214 @@ +perf-dlfilter(1) +================ + +NAME +---- +perf-dlfilter - Filter sample events using a dynamically loaded shared +object file + +SYNOPSIS +-------- +[verse] +'perf script' [--dlfilter file.so ] + +DESCRIPTION +----------- + +This option is used to process data through a custom filter provided by a +dynamically loaded shared object file. + +API +--- + +The API for filtering consists of the following: + +[source,c] +---- +#include <perf/perf_dlfilter.h> + +const struct perf_dlfilter_fns perf_dlfilter_fns; + +int start(void **data); +int stop(void *data); +int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx); +---- + +If implemented, 'start' will be called at the beginning, before any +calls to 'filter_event' . Return 0 to indicate success, +or return a negative error code. '*data' can be assigned for use by other +functions. + +If implemented, 'stop' will be called at the end, after any calls to +'filter_event'. Return 0 to indicate success, or +return a negative error code. 'data' is set by 'start'. + +If implemented, 'filter_event' will be called for each sample event. +Return 0 to keep the sample event, 1 to filter it out, or return a negative +error code. 'data' is set by 'start'. 'ctx' is needed for calls to +'perf_dlfilter_fns'. + +The perf_dlfilter_sample structure +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +'filter_event' is passed a perf_dlfilter_sample +structure, which contains the following fields: +[source,c] +---- +/* + * perf sample event information (as per perf script and <linux/perf_event.h>) + */ +struct perf_dlfilter_sample { + __u32 size; /* Size of this structure (for compatibility checking) */ + __u64 ip; + __s32 pid; + __s32 tid; + __u64 time; + __u64 addr; + __u64 id; + __u64 stream_id; + __u64 period; + __u64 weight; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ + __u16 ins_lat; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ + __u16 p_stage_cyc; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ + __u64 transaction; /* Refer PERF_SAMPLE_TRANSACTION in <linux/perf_event.h> */ + __u64 insn_cnt; /* For instructions-per-cycle (IPC) */ + __u64 cyc_cnt; /* For instructions-per-cycle (IPC) */ + __s32 cpu; + __u32 flags; /* Refer PERF_DLFILTER_FLAG_* above */ + __u64 data_src; /* Refer PERF_SAMPLE_DATA_SRC in <linux/perf_event.h> */ + __u64 phys_addr; /* Refer PERF_SAMPLE_PHYS_ADDR in <linux/perf_event.h> */ + __u64 data_page_size; /* Refer PERF_SAMPLE_DATA_PAGE_SIZE in <linux/perf_event.h> */ + __u64 code_page_size; /* Refer PERF_SAMPLE_CODE_PAGE_SIZE in <linux/perf_event.h> */ + __u64 cgroup; /* Refer PERF_SAMPLE_CGROUP in <linux/perf_event.h> */ + __u8 cpumode; /* Refer CPUMODE_MASK etc in <linux/perf_event.h> */ + __u8 addr_correlates_sym; /* True => resolve_addr() can be called */ + __u16 misc; /* Refer perf_event_header in <linux/perf_event.h> */ + __u32 raw_size; /* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ + const void *raw_data; /* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ + __u64 brstack_nr; /* Number of brstack entries */ + const struct perf_branch_entry *brstack; /* Refer <linux/perf_event.h> */ + __u64 raw_callchain_nr; /* Number of raw_callchain entries */ + const __u64 *raw_callchain; /* Refer <linux/perf_event.h> */ + const char *event; +}; +---- + +The perf_dlfilter_fns structure +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The 'perf_dlfilter_fns' structure is populated with function pointers when the +file is loaded. The functions can be called by 'filter_event'. + +[source,c] +---- +struct perf_dlfilter_fns { + const struct perf_dlfilter_al *(*resolve_ip)(void *ctx); + const struct perf_dlfilter_al *(*resolve_addr)(void *ctx); + void *(*reserved[126])(void *); +}; +---- + +'resolve_ip' returns information about ip. + +'resolve_addr' returns information about addr (if addr_correlates_sym). + +The perf_dlfilter_al structure +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The 'perf_dlfilter_al' structure contains information about an address. + +[source,c] +---- +/* + * Address location (as per perf script) + */ +struct perf_dlfilter_al { + __u32 size; /* Size of this structure (for compatibility checking) */ + __u32 symoff; + const char *sym; + __u64 addr; /* Mapped address (from dso) */ + __u64 sym_start; + __u64 sym_end; + const char *dso; + __u8 sym_binding; /* STB_LOCAL, STB_GLOBAL or STB_WEAK, refer <elf.h> */ + __u8 is_64_bit; /* Only valid if dso is not NULL */ + __u8 is_kernel_ip; /* True if in kernel space */ + __u32 buildid_size; + __u8 *buildid; + /* Below members are only populated by resolve_ip() */ + __u8 filtered; /* true if this sample event will be filtered out */ + const char *comm; +}; +---- + +perf_dlfilter_sample flags +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The 'flags' member of 'perf_dlfilter_sample' corresponds with the flags field +of perf script. The bits of the flags are as follows: + +[source,c] +---- +/* Definitions for perf_dlfilter_sample flags */ +enum { + PERF_DLFILTER_FLAG_BRANCH = 1ULL << 0, + PERF_DLFILTER_FLAG_CALL = 1ULL << 1, + PERF_DLFILTER_FLAG_RETURN = 1ULL << 2, + PERF_DLFILTER_FLAG_CONDITIONAL = 1ULL << 3, + PERF_DLFILTER_FLAG_SYSCALLRET = 1ULL << 4, + PERF_DLFILTER_FLAG_ASYNC = 1ULL << 5, + PERF_DLFILTER_FLAG_INTERRUPT = 1ULL << 6, + PERF_DLFILTER_FLAG_TX_ABORT = 1ULL << 7, + PERF_DLFILTER_FLAG_TRACE_BEGIN = 1ULL << 8, + PERF_DLFILTER_FLAG_TRACE_END = 1ULL << 9, + PERF_DLFILTER_FLAG_IN_TX = 1ULL << 10, + PERF_DLFILTER_FLAG_VMENTRY = 1ULL << 11, + PERF_DLFILTER_FLAG_VMEXIT = 1ULL << 12, +}; +---- + +EXAMPLE +------- + +Filter out everything except branches from "foo" to "bar": + +[source,c] +---- +#include <perf/perf_dlfilter.h> +#include <string.h> + +const struct perf_dlfilter_fns perf_dlfilter_fns; + +int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx) +{ + const struct perf_dlfilter_al *al; + const struct perf_dlfilter_al *addr_al; + + if (!sample->ip || !sample->addr_correlates_sym) + return 1; + + al = perf_dlfilter_fns.resolve_ip(ctx); + if (!al || !al->sym || strcmp(al->sym, "foo")) + return 1; + + addr_al = perf_dlfilter_fns.resolve_addr(ctx); + if (!addr_al || !addr_al->sym || strcmp(addr_al->sym, "bar")) + return 1; + + return 0; +} +---- + +To build the shared object, assuming perf has been installed for the local user +i.e. perf_dlfilter.h is in ~/include/perf : + + gcc -c -I ~/include -fpic dlfilter-example.c + gcc -shared -o dlfilter-example.so dlfilter-example.o + +To use the filter with perf script: + + perf script --dlfilter ./dlfilter-example.so + +SEE ALSO +-------- +linkperf:perf-script[1]
tools/perf/Documentation/perf-script.txt +6 -1
@@ -98,6 +98,10 @@ OPTIONS Generate perf-script.[ext] starter script for given language, using current perf.data. +--dlfilter=<file>:: + Filter sample events using the given shared object file. + Refer linkperf:perf-dlfilter[1] + -a:: Force system-wide collection. Scripts run without a <command> normally use -a by default, while scripts run with a <command>
@@ -483,4 +487,5 @@ include::itrace.txt[] SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], -linkperf:perf-script-python[1], linkperf:perf-intel-pt[1] +linkperf:perf-script-python[1], linkperf:perf-intel-pt[1], +linkperf:perf-dlfilter[1]
tools/perf/builtin-script.c +24 -1
@@ -55,6 +55,7 @@#include <subcmd/pager.h> #include <perf/evlist.h> #include <linux/err.h> +#include "util/dlfilter.h" #include "util/record.h" #include "util/util.h" #include "perf.h"
@@ -79,6 +80,7 @@ static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);static struct perf_stat_config stat_config;static int max_blocks;static bool native_arch; +static struct dlfilter *dlfilter;unsigned int scripting_max_stack =PERF_MAX_STACK_DEPTH ;
@@ -2175,6 +2177,7 @@ static int process_sample_event(struct perf_tool *tool, struct perf_script *scr = container_of(tool, struct perf_script, tool);struct addr_location al;struct addr_location addr_al; +int ret =0 ;if (perf_time__ranges_skip_sample (scr->ptime_range, scr->range_num, sample->time)) {
@@ -2213,6 +2216,13 @@ static int process_sample_event(struct perf_tool *tool,if (evswitch__discard (&scr->evswitch, evsel)) goto out_put; + ret =dlfilter__filter_event (dlfilter, event, sample, evsel, machine, &al, &addr_al); +if (ret) { +if (ret >0 ) + ret =0 ; + goto out_put; + } +if (scripting_ops) {struct addr_location *addr_al_ptr =NULL ;
@@ -2229,7 +2239,7 @@ static int process_sample_event(struct perf_tool *tool, out_put:addr_location__put (&al); -return 0 ; +return ret; } static int process_attr(struct perf_tool *tool, union perf_event *event,
@@ -3568,6 +3578,7 @@ int cmd_script(int argc, const char **argv) };struct utsname uts;char *script_path =NULL ; +const char *dlfilter_file =NULL ;const char **__argv;int i, j, err =0 ;struct perf_script script = {
@@ -3615,6 +3626,7 @@ int cmd_script(int argc, const char **argv) parse_scriptname),OPT_STRING ('g' ,"gen-script" , &generate_script_lang,"lang" ,"generate perf-script.xx script in specified language" ), +OPT_STRING (0 ,"dlfilter" , &dlfilter_file,"file" ,"filter .so file name" ),OPT_STRING ('i' ,"input" , &input_name,"file" ,"input file name" ),OPT_BOOLEAN ('d' ,"debug-mode" , &debug_mode, "do various checks like samples ordering and lost events"),
@@ -3933,6 +3945,12 @@ int cmd_script(int argc, const char **argv)exit (-1 ); } +if (dlfilter_file) { + dlfilter =dlfilter__new (dlfilter_file); +if (!dlfilter) +return -1 ; + } +if (!script_name) {setup_pager (); use_browser =0 ;
@@ -4032,6 +4050,10 @@ int cmd_script(int argc, const char **argv) goto out_delete; } + err =dlfilter__start (dlfilter, session); +if (err) + goto out_delete; +if (script_name) { err = scripting_ops->start_script (script_name, argc, argv, session);if (err)
@@ -4081,6 +4103,7 @@ int cmd_script(int argc, const char **argv)if (script_started)cleanup_scripting (); +dlfilter__cleanup (dlfilter); out:return err; }
tools/perf/util/Build +1 -0
@@ -126,6 +126,7 @@ perf-y += parse-regs-options.o perf-y += parse-sublevel-options.o perf-y += term.o perf-y += help-unknown-cmd.o +perf-y += dlfilter.o perf-y += mem-events.o perf-y += vsprintf.o perf-y += units.o
tools/perf/util/dlfilter.c new file +330 -0
330 lines not on this page · raw message
tools/perf/util/dlfilter.h new file +74 -0
74 lines not on this page · raw message
tools/perf/util/perf_dlfilter.h new file +120 -0
120 lines not on this page · raw message
Signature · 1 line
2.17.1
Arnaldo Carvalho de Melo
maintainerEm Mon, Jun 21, 2021 at 06:05:07PM +0300, Adrian Hunter escreveu:
Quoted 4 lines
In some cases, users want to filter very large amounts of data (e.g. from AUX area tracing like Intel PT) looking for something specific. While scripting such as Python can be used, Python is 10 to 20 times slower than C. So define a C API so that custom filters can be written and loaded.
Statically linking with perf would be even faster 8-) But yeah, I think its something useful, some notes below
A first question, can this be combined with pre-existing filters? I.e.
perf script -C 0 --dlfilter file.so
?
Also in the docs we can state that after these custom filters get polished and mature, it would be interesting to send them to be merged upstream, where they could even be statically linked with perf, if a profile session with it linked statically proves that.
Having a collection of such filters upstream we could then have a similar interface as for the script collection to describe filters, i.e. the .so file would have to have a description and perhaps a man page:
⬢[acme@toolbox perf]$ perf script -l
List of available trace scripts:
compaction-times [-h] [-u] [-p|-pv] [-t | [-m] [-fs] [-ms]] [pid|pid-range|comm-regex] display time taken by mm compaction
event_analyzing_sample analyze all perf samples
export-to-postgresql [database name] [columns] [calls] export perf data to a postgresql database export-to-sqlite [database name] [columns] [calls] export perf data to a sqlite3 database
failed-syscalls-by-pid [comm] system-wide failed syscalls, by pid flamegraph create flame graphs futex-contention futext contention measurement intel-pt-events print Intel PT Events including Power Events and PTWRITE mem-phys-addr resolve physical address samples net_dropmonitor display a table of dropped frames netdev-times [tx] [rx] [dev=] [debug] display a process of packet and processing time powerpc-hcalls sched-migration sched migration overview sctop [comm] [interval] syscall top stackcollapse produce callgraphs in short form for scripting use syscall-counts-by-pid [comm] system-wide syscall counts, by pid syscall-counts [comm] system-wide syscall counts failed-syscalls [comm] system-wide failed syscalls rw-by-file <comm> r/w activity for a program, by file rw-by-pid system-wide r/w activity rwtop [interval] system-wide r/w top wakeup-latency system-wide min/max/avg wakeup latency
⬢[acme@toolbox perf]$
I.e. some 'perf script --list-dlfilters'
Quoted 72 lines
Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/Documentation/perf-dlfilter.txt | 214 +++++++++++++ tools/perf/Documentation/perf-script.txt | 7 +- tools/perf/builtin-script.c | 25 +- tools/perf/util/Build | 1 + tools/perf/util/dlfilter.c | 330 +++++++++++++++++++++ tools/perf/util/dlfilter.h | 74 +++++ tools/perf/util/perf_dlfilter.h | 120 ++++++++ 7 files changed, 769 insertions(+), 2 deletions(-) create mode 100644 tools/perf/Documentation/perf-dlfilter.txt create mode 100644 tools/perf/util/dlfilter.c create mode 100644 tools/perf/util/dlfilter.h create mode 100644 tools/perf/util/perf_dlfilter.htools/perf/Documentation/perf-dlfilter.txt new file +51
-0@@ -0,0 +1,214 @@ +perf-dlfilter(1) +================ + +NAME +---- +perf-dlfilter - Filter sample events using a dynamically loaded shared +object file + +SYNOPSIS +-------- +[verse] +'perf script' [--dlfilter file.so ] + +DESCRIPTION +----------- + +This option is used to process data through a custom filter provided by a +dynamically loaded shared object file. + +API +--- + +The API for filtering consists of the following: + +[source,c] +---- +#include <perf/perf_dlfilter.h> + +const struct perf_dlfilter_fns perf_dlfilter_fns; + +int start(void **data); +int stop(void *data); +int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx); +---- + +If implemented, 'start' will be called at the beginning, before any +calls to 'filter_event' . Return 0 to indicate success, +or return a negative error code. '*data' can be assigned for use by other +functions. + +If implemented, 'stop' will be called at the end, after any calls to +'filter_event'. Return 0 to indicate success, or +return a negative error code. 'data' is set by 'start'. + +If implemented, 'filter_event' will be called for each sample event. +Return 0 to keep the sample event, 1 to filter it out, or return a negative +error code. 'data' is set by 'start'. 'ctx' is needed for calls to +'perf_dlfilter_fns'. + +The perf_dlfilter_sample structure +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tools/perf/Documentation/perf-dlfilter.txt line 61
Quoted 10 lines
tools/perf/Documentation/perf-dlfilter.txt new file +10
-0+ +'filter_event' is passed a perf_dlfilter_sample +structure, which contains the following fields: +[source,c] +---- +/* + * perf sample event information (as per perf script and <linux/perf_event.h>) + */ +struct perf_dlfilter_sample { + __u32 size; /* Size of this structure (for compatibility checking) */
There is a 4-byte hole here,
tools/perf/Documentation/perf-dlfilter.txt line 72
Quoted 11 lines
tools/perf/Documentation/perf-dlfilter.txt new file +11
-0+ __u64 ip; + __s32 pid; + __s32 tid; + __u64 time; + __u64 addr; + __u64 id; + __u64 stream_id; + __u64 period; + __u64 weight; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ + __u16 ins_lat; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ + __u16 p_stage_cyc; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */
Another
Can you move these last two __u16 to right after the 'size' field?
Quoted 820 lines
tools/perf/Documentation/perf-dlfilter.txt new file +142
-0+ __u64 transaction; /* Refer PERF_SAMPLE_TRANSACTION in <linux/perf_event.h> */ + __u64 insn_cnt; /* For instructions-per-cycle (IPC) */ + __u64 cyc_cnt; /* For instructions-per-cycle (IPC) */ + __s32 cpu; + __u32 flags; /* Refer PERF_DLFILTER_FLAG_* above */ + __u64 data_src; /* Refer PERF_SAMPLE_DATA_SRC in <linux/perf_event.h> */ + __u64 phys_addr; /* Refer PERF_SAMPLE_PHYS_ADDR in <linux/perf_event.h> */ + __u64 data_page_size; /* Refer PERF_SAMPLE_DATA_PAGE_SIZE in <linux/perf_event.h> */ + __u64 code_page_size; /* Refer PERF_SAMPLE_CODE_PAGE_SIZE in <linux/perf_event.h> */ + __u64 cgroup; /* Refer PERF_SAMPLE_CGROUP in <linux/perf_event.h> */ + __u8 cpumode; /* Refer CPUMODE_MASK etc in <linux/perf_event.h> */ + __u8 addr_correlates_sym; /* True => resolve_addr() can be called */ + __u16 misc; /* Refer perf_event_header in <linux/perf_event.h> */ + __u32 raw_size; /* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ + const void *raw_data; /* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ + __u64 brstack_nr; /* Number of brstack entries */ + const struct perf_branch_entry *brstack; /* Refer <linux/perf_event.h> */ + __u64 raw_callchain_nr; /* Number of raw_callchain entries */ + const __u64 *raw_callchain; /* Refer <linux/perf_event.h> */ + const char *event; +}; +---- + +The perf_dlfilter_fns structure +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The 'perf_dlfilter_fns' structure is populated with function pointers when the +file is loaded. The functions can be called by 'filter_event'. + +[source,c] +---- +struct perf_dlfilter_fns { + const struct perf_dlfilter_al *(*resolve_ip)(void *ctx); + const struct perf_dlfilter_al *(*resolve_addr)(void *ctx); + void *(*reserved[126])(void *); +}; +---- + +'resolve_ip' returns information about ip. + +'resolve_addr' returns information about addr (if addr_correlates_sym). + +The perf_dlfilter_al structure +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The 'perf_dlfilter_al' structure contains information about an address. + +[source,c] +---- +/* + * Address location (as per perf script) + */ +struct perf_dlfilter_al { + __u32 size; /* Size of this structure (for compatibility checking) */ + __u32 symoff; + const char *sym; + __u64 addr; /* Mapped address (from dso) */ + __u64 sym_start; + __u64 sym_end; + const char *dso; + __u8 sym_binding; /* STB_LOCAL, STB_GLOBAL or STB_WEAK, refer <elf.h> */ + __u8 is_64_bit; /* Only valid if dso is not NULL */ + __u8 is_kernel_ip; /* True if in kernel space */ + __u32 buildid_size; + __u8 *buildid; + /* Below members are only populated by resolve_ip() */ + __u8 filtered; /* true if this sample event will be filtered out */ + const char *comm; +}; +---- + +perf_dlfilter_sample flags +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The 'flags' member of 'perf_dlfilter_sample' corresponds with the flags field +of perf script. The bits of the flags are as follows: + +[source,c] +---- +/* Definitions for perf_dlfilter_sample flags */ +enum { + PERF_DLFILTER_FLAG_BRANCH = 1ULL << 0, + PERF_DLFILTER_FLAG_CALL = 1ULL << 1, + PERF_DLFILTER_FLAG_RETURN = 1ULL << 2, + PERF_DLFILTER_FLAG_CONDITIONAL = 1ULL << 3, + PERF_DLFILTER_FLAG_SYSCALLRET = 1ULL << 4, + PERF_DLFILTER_FLAG_ASYNC = 1ULL << 5, + PERF_DLFILTER_FLAG_INTERRUPT = 1ULL << 6, + PERF_DLFILTER_FLAG_TX_ABORT = 1ULL << 7, + PERF_DLFILTER_FLAG_TRACE_BEGIN = 1ULL << 8, + PERF_DLFILTER_FLAG_TRACE_END = 1ULL << 9, + PERF_DLFILTER_FLAG_IN_TX = 1ULL << 10, + PERF_DLFILTER_FLAG_VMENTRY = 1ULL << 11, + PERF_DLFILTER_FLAG_VMEXIT = 1ULL << 12, +}; +---- + +EXAMPLE +------- + +Filter out everything except branches from "foo" to "bar": + +[source,c] +---- +#include <perf/perf_dlfilter.h> +#include <string.h> + +const struct perf_dlfilter_fns perf_dlfilter_fns; + +int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx) +{ + const struct perf_dlfilter_al *al; + const struct perf_dlfilter_al *addr_al; + + if (!sample->ip || !sample->addr_correlates_sym) + return 1; + + al = perf_dlfilter_fns.resolve_ip(ctx); + if (!al || !al->sym || strcmp(al->sym, "foo")) + return 1; + + addr_al = perf_dlfilter_fns.resolve_addr(ctx); + if (!addr_al || !addr_al->sym || strcmp(addr_al->sym, "bar")) + return 1; + + return 0; +} +---- + +To build the shared object, assuming perf has been installed for the local user +i.e. perf_dlfilter.h is in ~/include/perf : + + gcc -c -I ~/include -fpic dlfilter-example.c + gcc -shared -o dlfilter-example.so dlfilter-example.o + +To use the filter with perf script: + + perf script --dlfilter ./dlfilter-example.so + +SEE ALSO +-------- +linkperf:perf-script[1]tools/perf/Documentation/perf-script.txt +6
-1@@ -98,6 +98,10 @@ OPTIONS Generate perf-script.[ext] starter script for given language, using current perf.data. +--dlfilter=<file>:: + Filter sample events using the given shared object file. + Refer linkperf:perf-dlfilter[1] + -a:: Force system-wide collection. Scripts run without a <command> normally use -a by default, while scripts run with a <command>@@ -483,4 +487,5 @@ include::itrace.txt[] SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], -linkperf:perf-script-python[1], linkperf:perf-intel-pt[1] +linkperf:perf-script-python[1], linkperf:perf-intel-pt[1], +linkperf:perf-dlfilter[1]tools/perf/builtin-script.c +24
-1@@ -55,6 +55,7 @@#include <subcmd/pager.h> #include <perf/evlist.h> #include <linux/err.h> +#include "util/dlfilter.h" #include "util/record.h" #include "util/util.h" #include "perf.h" @@ -79,6 +80,7 @@ static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);static struct perf_stat_config stat_config;static int max_blocks;static bool native_arch; +static struct dlfilter *dlfilter;unsigned int scripting_max_stack =PERF_MAX_STACK_DEPTH ;@@ -2175,6 +2177,7 @@ static int process_sample_event(struct perf_tool *tool, struct perf_script *scr = container_of(tool, struct perf_script, tool);struct addr_location al;struct addr_location addr_al; +int ret =0 ;if (perf_time__ranges_skip_sample (scr->ptime_range, scr->range_num, sample->time)) {@@ -2213,6 +2216,13 @@ static int process_sample_event(struct perf_tool *tool,if (evswitch__discard (&scr->evswitch, evsel)) goto out_put; + ret =dlfilter__filter_event (dlfilter, event, sample, evsel, machine, &al, &addr_al); +if (ret) { +if (ret >0 ) + ret =0 ; + goto out_put; + } +if (scripting_ops) {struct addr_location *addr_al_ptr =NULL ;@@ -2229,7 +2239,7 @@ static int process_sample_event(struct perf_tool *tool, out_put:addr_location__put (&al); -return 0 ; +return ret; } static int process_attr(struct perf_tool *tool, union perf_event *event,@@ -3568,6 +3578,7 @@ int cmd_script(int argc, const char **argv) };struct utsname uts;char *script_path =NULL ; +const char *dlfilter_file =NULL ;const char **__argv;int i, j, err =0 ;struct perf_script script = {@@ -3615,6 +3626,7 @@ int cmd_script(int argc, const char **argv) parse_scriptname),OPT_STRING ('g' ,"gen-script" , &generate_script_lang,"lang" ,"generate perf-script.xx script in specified language" ), +OPT_STRING (0 ,"dlfilter" , &dlfilter_file,"file" ,"filter .so file name" ),OPT_STRING ('i' ,"input" , &input_name,"file" ,"input file name" ),OPT_BOOLEAN ('d' ,"debug-mode" , &debug_mode, "do various checks like samples ordering and lost events"),@@ -3933,6 +3945,12 @@ int cmd_script(int argc, const char **argv)exit (-1 ); } +if (dlfilter_file) { + dlfilter =dlfilter__new (dlfilter_file); +if (!dlfilter) +return -1 ; + } +if (!script_name) {setup_pager (); use_browser =0 ;@@ -4032,6 +4050,10 @@ int cmd_script(int argc, const char **argv) goto out_delete; } + err =dlfilter__start (dlfilter, session); +if (err) + goto out_delete; +if (script_name) { err = scripting_ops->start_script (script_name, argc, argv, session);if (err)@@ -4081,6 +4103,7 @@ int cmd_script(int argc, const char **argv)if (script_started)cleanup_scripting (); +dlfilter__cleanup (dlfilter); out:return err; }tools/perf/util/Build +1
-0@@ -126,6 +126,7 @@ perf-y += parse-regs-options.o perf-y += parse-sublevel-options.o perf-y += term.o perf-y += help-unknown-cmd.o +perf-y += dlfilter.o perf-y += mem-events.o perf-y += vsprintf.o perf-y += units.otools/perf/util/dlfilter.c new file +330
-0@@ -0,0 +1,330 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* dlfilter.c: Interface to perf script --dlfilter shared object +* Copyright (c) 2021, Intel Corporation. +*/ +#include <dlfcn.h> +#include <stdlib.h> +#include <string.h> +#include <linux/zalloc.h> +#include <linux/build_bug.h> + +#include "debug.h" +#include "event.h" +#include "evsel.h" +#include "dso.h" +#include "map.h" +#include "thread.h" +#include "symbol.h" +#include "dlfilter.h" +#include "perf_dlfilter.h" + +static void al_to_d_al (struct addr_location *al,struct perf_dlfilter_al *d_al) +{ +struct symbol *sym = al->sym; + + d_al->size =sizeof (*d_al); +if (al->map) { +struct dso *dso = al->map->dso; + +if (symbol_conf.show_kernel_path && dso->long_name) + d_al->dso = dso->long_name; +else + d_al->dso = dso->name; + d_al->is_64_bit = dso->is_64_bit; + d_al->buildid_size = dso->bid.size; + d_al->buildid = dso->bid.data; + }else { + d_al->dso =NULL ; + d_al->is_64_bit =0 ; + d_al->buildid_size =0 ; + d_al->buildid =NULL ; + } +if (sym) { + d_al->sym = sym->name; + d_al->sym_start = sym->start; + d_al->sym_end = sym->end; +if (al->addr < sym->end) + d_al->symoff = al->addr - sym->start; +else + d_al->symoff = al->addr - al->map->start - sym->start; + d_al->sym_binding = sym->binding; + }else { + d_al->sym =NULL ; + d_al->sym_start =0 ; + d_al->sym_end =0 ; + d_al->symoff =0 ; + d_al->sym_binding =0 ; + } + d_al->addr = al->addr; + d_al->comm =NULL ; + d_al->filtered =0 ; +} + +static struct addr_location *get_al (struct dlfilter *d) +{ +struct addr_location *al = d->al; + +if (!al->thread &&machine__resolve (d->machine, al, d->sample) <0 ) +return NULL ; +return al; +} + +static struct thread *get_thread (struct dlfilter *d) +{ +struct addr_location *al =get_al (d); + +return al ? al->thread :NULL ; +} + +static const struct perf_dlfilter_al *dlfilter__resolve_ip (void *ctx) +{ +struct dlfilter *d = (struct dlfilter *)ctx; +struct perf_dlfilter_al *d_al = d->d_ip_al; +struct addr_location *al; + +if (!d->ctx_valid) +return NULL ; + +/* 'size' is also used to indicate already initialized */ +if (d_al->size) +return d_al; + + al =get_al (d); +if (!al) +return NULL ; + +al_to_d_al (al, d_al); + + d_al->is_kernel_ip =machine__kernel_ip (d->machine, d->sample->ip); + d_al->comm = al->thread ?thread__comm_str (al->thread) :":-1" ; + d_al->filtered = al->filtered; + +return d_al; +} + +static const struct perf_dlfilter_al *dlfilter__resolve_addr (void *ctx) +{ +struct dlfilter *d = (struct dlfilter *)ctx; +struct perf_dlfilter_al *d_addr_al = d->d_addr_al; +struct addr_location *addr_al = d->addr_al; + +if (!d->ctx_valid || !d->d_sample->addr_correlates_sym) +return NULL ; + +/* 'size' is also used to indicate already initialized */ +if (d_addr_al->size) +return d_addr_al; + +if (!addr_al->thread) { +struct thread *thread =get_thread (d); + +if (!thread) +return NULL ; +thread__resolve (thread, addr_al, d->sample); + } + +al_to_d_al (addr_al, d_addr_al); + + d_addr_al->is_kernel_ip =machine__kernel_ip (d->machine, d->sample->addr); + +return d_addr_al; +} + +static const struct perf_dlfilter_fns perf_dlfilter_fns = { + .resolve_ip = dlfilter__resolve_ip, + .resolve_addr = dlfilter__resolve_addr, +}; + +#define CHECK_FLAG (x) BUILD_BUG_ON((u64)PERF_DLFILTER_FLAG_ ## x != (u64)PERF_IP_FLAG_ ## x) + +static int dlfilter__init (struct dlfilter *d,const char *file) +{ +CHECK_FLAG (BRANCH ); +CHECK_FLAG (CALL ); +CHECK_FLAG (RETURN ); +CHECK_FLAG (CONDITIONAL ); +CHECK_FLAG (SYSCALLRET ); +CHECK_FLAG (ASYNC ); +CHECK_FLAG (INTERRUPT ); +CHECK_FLAG (TX_ABORT ); +CHECK_FLAG (TRACE_BEGIN ); +CHECK_FLAG (TRACE_END ); +CHECK_FLAG (IN_TX ); +CHECK_FLAG (VMENTRY ); +CHECK_FLAG (VMEXIT ); + +memset (d,0 ,sizeof (*d)); + d->file =strdup (file); +if (!d->file) +return -1 ; +return 0 ; +} + +static void dlfilter__exit (struct dlfilter *d) +{ +zfree (&d->file); +} + +static int dlfilter__open (struct dlfilter *d) +{ + d->handle =dlopen (d->file,RTLD_NOW ); +if (!d->handle) { +pr_err ("dlopen failed for: '%s'\n" , d->file); +return -1 ; + } + d->start =dlsym (d->handle,"start" ); + d->filter_event =dlsym (d->handle,"filter_event" ); + d->stop =dlsym (d->handle,"stop" ); + d->fns =dlsym (d->handle,"perf_dlfilter_fns" ); +if (d->fns) +memcpy (d->fns, &perf_dlfilter_fns,sizeof (struct perf_dlfilter_fns )); +return 0 ; +} + +static int dlfilter__close (struct dlfilter *d) +{ +return dlclose (d->handle); +} + +struct dlfilter *dlfilter__new (const char *file) +{ +struct dlfilter *d =malloc (sizeof (*d)); + +if (!d) +return NULL ; + +if (dlfilter__init (d, file)) + goto err_free; + +if (dlfilter__open (d)) + goto err_exit; + +return d; + +err_exit: +dlfilter__exit (d); +err_free: +free (d); +return NULL ; +} + +static void dlfilter__free (struct dlfilter *d) +{ +if (d) { +dlfilter__exit (d); +free (d); + } +} + +int dlfilter__start (struct dlfilter *d,struct perf_session *session) +{ +if (d) { + d->session = session; +if (d->start) +return d->start (&d->data); + } +return 0 ; +} + +static int dlfilter__stop (struct dlfilter *d) +{ +if (d && d->stop) +return d->stop (d->data); +return 0 ; +} + +void dlfilter__cleanup (struct dlfilter *d) +{ +if (d) { +dlfilter__stop (d); +dlfilter__close (d); +dlfilter__free (d); + } +} + +#define ASSIGN (x) d_sample.x = sample->x + +int dlfilter__do_filter_event (struct dlfilter *d, +union perf_event *event, +struct perf_sample *sample, +struct evsel *evsel, +struct machine *machine, +struct addr_location *al, +struct addr_location *addr_al) +{ +struct perf_dlfilter_sample d_sample; +struct perf_dlfilter_al d_ip_al; +struct perf_dlfilter_al d_addr_al; +int ret; + + d->event = event; + d->sample = sample; + d->evsel = evsel; + d->machine = machine; + d->al = al; + d->addr_al = addr_al; + d->d_sample = &d_sample; + d->d_ip_al = &d_ip_al; + d->d_addr_al = &d_addr_al; + + d_sample.size =sizeof (d_sample); + d_ip_al.size =0 ;/* To indicate d_ip_al is not initialized */ + d_addr_al.size =0 ;/* To indicate d_addr_al is not initialized */ + +ASSIGN (ip); +ASSIGN (pid); +ASSIGN (tid); +ASSIGN (time); +ASSIGN (addr); +ASSIGN (id); +ASSIGN (stream_id); +ASSIGN (period); +ASSIGN (weight); +ASSIGN (ins_lat); +ASSIGN (p_stage_cyc); +ASSIGN (transaction); +ASSIGN (insn_cnt); +ASSIGN (cyc_cnt); +ASSIGN (cpu); +ASSIGN (flags); +ASSIGN (data_src); +ASSIGN (phys_addr); +ASSIGN (data_page_size); +ASSIGN (code_page_size); +ASSIGN (cgroup); +ASSIGN (cpumode); +ASSIGN (misc); +ASSIGN (raw_size); +ASSIGN (raw_data); + +if (sample->branch_stack) { + d_sample.brstack_nr = sample->branch_stack->nr; + d_sample.brstack = (struct perf_branch_entry *)perf_sample__branch_entries (sample); + }else { + d_sample.brstack_nr =0 ; + d_sample.brstack =NULL ; + } + +if (sample->callchain) { + d_sample.raw_callchain_nr = sample->callchain->nr; + d_sample.raw_callchain = (__u64 *)sample->callchain->ips; + }else { + d_sample.raw_callchain_nr =0 ; + d_sample.raw_callchain =NULL ; + } + + d_sample.addr_correlates_sym = + (evsel->core.attr.sample_type &PERF_SAMPLE_ADDR ) && +sample_addr_correlates_sym (&evsel->core.attr); + + d_sample.event =evsel__name (evsel); + + d->ctx_valid = true; + + ret = d->filter_event (d->data, &d_sample, d); + + d->ctx_valid = false; + +return ret; +}tools/perf/util/dlfilter.h new file +74
-0@@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* +* dlfilter.h: Interface to perf script --dlfilter shared object +* Copyright (c) 2021, Intel Corporation. +*/ + +#ifndef PERF_UTIL_DLFILTER_H +#define PERF_UTIL_DLFILTER_H + +struct perf_session ; +union perf_event ; +struct perf_sample ; +struct evsel ; +struct machine ; +struct addr_location ; +struct perf_dlfilter_fns ; +struct perf_dlfilter_sample ; +struct perf_dlfilter_al ; + +struct dlfilter { +char *file; +void *handle; +void *data; +struct perf_session *session; +bool ctx_valid; + +union perf_event *event; +struct perf_sample *sample; +struct evsel *evsel; +struct machine *machine; +struct addr_location *al; +struct addr_location *addr_al; +struct perf_dlfilter_sample *d_sample; +struct perf_dlfilter_al *d_ip_al; +struct perf_dlfilter_al *d_addr_al; + +int (*start)(void **data); +int (*stop)(void *data); + +int (*filter_event)(void *data, +const struct perf_dlfilter_sample *sample, +void *ctx); + +struct perf_dlfilter_fns *fns; +}; + +struct dlfilter *dlfilter__new (const char *file); + +int dlfilter__start (struct dlfilter *d,struct perf_session *session); + +int dlfilter__do_filter_event (struct dlfilter *d, +union perf_event *event, +struct perf_sample *sample, +struct evsel *evsel, +struct machine *machine, +struct addr_location *al, +struct addr_location *addr_al); + +void dlfilter__cleanup (struct dlfilter *d); + +static inline int dlfilter__filter_event (struct dlfilter *d, +union perf_event *event, +struct perf_sample *sample, +struct evsel *evsel, +struct machine *machine, +struct addr_location *al, +struct addr_location *addr_al) +{ +if (!d || !d->filter_event) +return 0 ; +return dlfilter__do_filter_event (d, event, sample, evsel, machine, al, addr_al); +} + +#endif tools/perf/util/perf_dlfilter.h new file +120
-0@@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* +* perf_dlfilter.h: API for perf --dlfilter shared object +* Copyright (c) 2021, Intel Corporation. +*/ +#ifndef _LINUX_PERF_DLFILTER_H +#define _LINUX_PERF_DLFILTER_H + +#include <linux/perf_event.h> +#include <linux/types.h> + +/* Definitions for perf_dlfilter_sample flags */ +enum { +PERF_DLFILTER_FLAG_BRANCH =1ULL <<0 , +PERF_DLFILTER_FLAG_CALL =1ULL <<1 , +PERF_DLFILTER_FLAG_RETURN =1ULL <<2 , +PERF_DLFILTER_FLAG_CONDITIONAL =1ULL <<3 , +PERF_DLFILTER_FLAG_SYSCALLRET =1ULL <<4 , +PERF_DLFILTER_FLAG_ASYNC =1ULL <<5 , +PERF_DLFILTER_FLAG_INTERRUPT =1ULL <<6 , +PERF_DLFILTER_FLAG_TX_ABORT =1ULL <<7 , +PERF_DLFILTER_FLAG_TRACE_BEGIN =1ULL <<8 , +PERF_DLFILTER_FLAG_TRACE_END =1ULL <<9 , +PERF_DLFILTER_FLAG_IN_TX =1ULL <<10 , +PERF_DLFILTER_FLAG_VMENTRY =1ULL <<11 , +PERF_DLFILTER_FLAG_VMEXIT =1ULL <<12 , +}; + +/* +* perf sample event information (as per perf script and <linux/perf_event.h>) +*/ +struct perf_dlfilter_sample { +__u32 size;/* Size of this structure (for compatibility checking) */ +__u64 ip; +__s32 pid; +__s32 tid; +__u64 time; +__u64 addr; +__u64 id; +__u64 stream_id; +__u64 period; +__u64 weight;/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ +__u16 ins_lat;/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ +__u16 p_stage_cyc;/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ +__u64 transaction;/* Refer PERF_SAMPLE_TRANSACTION in <linux/perf_event.h> */ +__u64 insn_cnt;/* For instructions-per-cycle (IPC) */ +__u64 cyc_cnt;/* For instructions-per-cycle (IPC) */ +__s32 cpu; +__u32 flags;/* Refer PERF_DLFILTER_FLAG_* above */ +__u64 data_src;/* Refer PERF_SAMPLE_DATA_SRC in <linux/perf_event.h> */ +__u64 phys_addr;/* Refer PERF_SAMPLE_PHYS_ADDR in <linux/perf_event.h> */ +__u64 data_page_size;/* Refer PERF_SAMPLE_DATA_PAGE_SIZE in <linux/perf_event.h> */ +__u64 code_page_size;/* Refer PERF_SAMPLE_CODE_PAGE_SIZE in <linux/perf_event.h> */ +__u64 cgroup;/* Refer PERF_SAMPLE_CGROUP in <linux/perf_event.h> */ +__u8 cpumode;/* Refer CPUMODE_MASK etc in <linux/perf_event.h> */ +__u8 addr_correlates_sym;/* True => resolve_addr() can be called */ +__u16 misc;/* Refer perf_event_header in <linux/perf_event.h> */ +__u32 raw_size;/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ +const void *raw_data;/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ +__u64 brstack_nr;/* Number of brstack entries */ +const struct perf_branch_entry *brstack;/* Refer <linux/perf_event.h> */ +__u64 raw_callchain_nr;/* Number of raw_callchain entries */ +const __u64 *raw_callchain;/* Refer <linux/perf_event.h> */ +const char *event; +}; + +/* +* Address location (as per perf script) +*/ +struct perf_dlfilter_al { +__u32 size;/* Size of this structure (for compatibility checking) */ +__u32 symoff; +const char *sym; +__u64 addr;/* Mapped address (from dso) */ +__u64 sym_start; +__u64 sym_end; +const char *dso; +__u8 sym_binding;/* STB_LOCAL, STB_GLOBAL or STB_WEAK, refer <elf.h> */ +__u8 is_64_bit;/* Only valid if dso is not NULL */ +__u8 is_kernel_ip;/* True if in kernel space */ +__u32 buildid_size; +__u8 *buildid; +/* Below members are only populated by resolve_ip() */ +__u8 filtered;/* True if this sample event will be filtered out */ +const char *comm; +}; + +struct perf_dlfilter_fns { +/* Return information about ip */ +const struct perf_dlfilter_al *(*resolve_ip)(void *ctx); +/* Return information about addr (if addr_correlates_sym) */ +const struct perf_dlfilter_al *(*resolve_addr)(void *ctx); +/* Reserved */ +void *(*reserved[126 ])(void *); +}; + +/* +* If implemented, 'start' will be called at the beginning, +* before any calls to 'filter_event'. Return 0 to indicate success, +* or return a negative error code. '*data' can be assigned for use +* by other functions. +*/ +int start (void **data); + +/* +* If implemented, 'stop' will be called at the end, +* after any calls to 'filter_event'. Return 0 to indicate success, or +* return a negative error code. 'data' is set by start(). +*/ +int stop (void *data); + +/* +* If implemented, 'filter_event' will be called for each sample +* event. Return 0 to keep the sample event, 1 to filter it out, or +* return a negative error code. 'data' is set by start(). 'ctx' is +* needed for calls to perf_dlfilter_fns. +*/ +int filter_event (void *data,const struct perf_dlfilter_sample *sample,void *ctx); + +#endif Signature · 1 line
2.17.1
Signature · 1 line
- Arnaldo
Adrian Hunter
reviewerQuoted 6 lines · Arnaldo Carvalho de Melo
Em Mon, Jun 21, 2021 at 06:05:07PM +0300, Adrian Hunter escreveu:
Quoted 4 lines
In some cases, users want to filter very large amounts of data (e.g. from AUX area tracing like Intel PT) looking for something specific. While scripting such as Python can be used, Python is 10 to 20 times slower than C. So define a C API so that custom filters can be written and loaded.
Quoted 8 lines
Statically linking with perf would be even faster 8-) But yeah, I think its something useful, some notes below
A first question, can this be combined with pre-existing filters? I.e.
perf script -C 0 --dlfilter file.so?
Thanks for looking at the patches.
Yes. The filter_event() callback is called after internal filtering. Patch 5 introduces filter_event_early() which is called before internal filtering, but in either case all internal filtering is still done.
Quoted 35 lines
Also in the docs we can state that after these custom filters get polished and mature, it would be interesting to send them to be merged upstream, where they could even be statically linked with perf, if a profile session with it linked statically proves that.
Having a collection of such filters upstream we could then have a similar interface as for the script collection to describe filters, i.e. the .so file would have to have a description and perhaps a man page:
⬢[acme@toolbox perf]$ perf script -l
List of available trace scripts:
compaction-times [-h] [-u] [-p|-pv] [-t | [-m] [-fs] [-ms]] [pid|pid-range|comm-regex] display time taken by mm compaction
event_analyzing_sampleanalyze all perf samples
export-to-postgresql [database name] [columns] [calls] export perf data to a postgresql database export-to-sqlite [database name] [columns] [calls] export perf data to a sqlite3 databasefailed-syscalls-by-pid [comm] system-wide failed syscalls, by pid flamegraph create flame graphs futex-contention futext contention measurement intel-pt-events print Intel PT Events including Power Events and PTWRITE mem-phys-addr resolve physical address samples net_dropmonitor display a table of dropped frames netdev-times [tx] [rx] [dev=] [debug] display a process of packet and processing time powerpc-hcalls sched-migration sched migration overview sctop [comm] [interval] syscall top stackcollapse produce callgraphs in short form for scripting use syscall-counts-by-pid [comm] system-wide syscall counts, by pid syscall-counts [comm] system-wide syscall counts failed-syscalls [comm] system-wide failed syscalls rw-by-file <comm> r/w activity for a program, by file rw-by-pid system-wide r/w activity rwtop [interval] system-wide r/w top wakeup-latency system-wide min/max/avg wakeup latency
Quoted 3 lines
⬢[acme@toolbox perf]$
I.e. some 'perf script --list-dlfilters'
Yes but we would also need some way to store and retrieve a description of the filter otherwise all we have is the file name. I guess it could be another API function so the filter .so could be loaded and the "const char* filter_description(const char **title)" function called to get the description.
Quoted 100 lines
Quoted 73 lines
Signed-off-by Adrian Hunter <[email protected]>--- tools/perf/Documentation/perf-dlfilter.txt | 214 +++++++++++++ tools/perf/Documentation/perf-script.txt | 7 +- tools/perf/builtin-script.c | 25 +- tools/perf/util/Build | 1 + tools/perf/util/dlfilter.c | 330 +++++++++++++++++++++ tools/perf/util/dlfilter.h | 74 +++++ tools/perf/util/perf_dlfilter.h | 120 ++++++++ 7 files changed, 769 insertions(+), 2 deletions(-) create mode 100644 tools/perf/Documentation/perf-dlfilter.txt create mode 100644 tools/perf/util/dlfilter.c create mode 100644 tools/perf/util/dlfilter.h create mode 100644 tools/perf/util/perf_dlfilter.htools/perf/Documentation/perf-dlfilter.txt new file +51
-0@@ -0,0 +1,214 @@ +perf-dlfilter(1) +================ + +NAME +---- +perf-dlfilter - Filter sample events using a dynamically loaded shared +object file + +SYNOPSIS +-------- +[verse] +'perf script' [--dlfilter file.so ] + +DESCRIPTION +----------- + +This option is used to process data through a custom filter provided by a +dynamically loaded shared object file. + +API +--- + +The API for filtering consists of the following: + +[source,c] +---- +#include <perf/perf_dlfilter.h> + +const struct perf_dlfilter_fns perf_dlfilter_fns; + +int start(void **data); +int stop(void *data); +int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx); +---- + +If implemented, 'start' will be called at the beginning, before any +calls to 'filter_event' . Return 0 to indicate success, +or return a negative error code. '*data' can be assigned for use by other +functions. + +If implemented, 'stop' will be called at the end, after any calls to +'filter_event'. Return 0 to indicate success, or +return a negative error code. 'data' is set by 'start'. + +If implemented, 'filter_event' will be called for each sample event. +Return 0 to keep the sample event, 1 to filter it out, or return a negative +error code. 'data' is set by 'start'. 'ctx' is needed for calls to +'perf_dlfilter_fns'. + +The perf_dlfilter_sample structure +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~tools/perf/Documentation/perf-dlfilter.txt line 61
Quoted 10 lines
tools/perf/Documentation/perf-dlfilter.txt new file +10
-0+ +'filter_event' is passed a perf_dlfilter_sample +structure, which contains the following fields: +[source,c] +---- +/* + * perf sample event information (as per perf script and <linux/perf_event.h>) + */ +struct perf_dlfilter_sample { + __u32 size; /* Size of this structure (for compatibility checking) */There is a 4-byte hole here,
tools/perf/Documentation/perf-dlfilter.txt line 72
Quoted 11 lines
tools/perf/Documentation/perf-dlfilter.txt new file +11
-0+ __u64 ip; + __s32 pid; + __s32 tid; + __u64 time; + __u64 addr; + __u64 id; + __u64 stream_id; + __u64 period; + __u64 weight; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ + __u16 ins_lat; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ + __u16 p_stage_cyc; /* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */Another
Quoted 1 line
Can you move these last two
__u16to right after the 'size' field?
Sure
Quoted 822 lines
Quoted 821 lines
tools/perf/Documentation/perf-dlfilter.txt new file +142
-0+ __u64 transaction; /* Refer PERF_SAMPLE_TRANSACTION in <linux/perf_event.h> */ + __u64 insn_cnt; /* For instructions-per-cycle (IPC) */ + __u64 cyc_cnt; /* For instructions-per-cycle (IPC) */ + __s32 cpu; + __u32 flags; /* Refer PERF_DLFILTER_FLAG_* above */ + __u64 data_src; /* Refer PERF_SAMPLE_DATA_SRC in <linux/perf_event.h> */ + __u64 phys_addr; /* Refer PERF_SAMPLE_PHYS_ADDR in <linux/perf_event.h> */ + __u64 data_page_size; /* Refer PERF_SAMPLE_DATA_PAGE_SIZE in <linux/perf_event.h> */ + __u64 code_page_size; /* Refer PERF_SAMPLE_CODE_PAGE_SIZE in <linux/perf_event.h> */ + __u64 cgroup; /* Refer PERF_SAMPLE_CGROUP in <linux/perf_event.h> */ + __u8 cpumode; /* Refer CPUMODE_MASK etc in <linux/perf_event.h> */ + __u8 addr_correlates_sym; /* True => resolve_addr() can be called */ + __u16 misc; /* Refer perf_event_header in <linux/perf_event.h> */ + __u32 raw_size; /* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ + const void *raw_data; /* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ + __u64 brstack_nr; /* Number of brstack entries */ + const struct perf_branch_entry *brstack; /* Refer <linux/perf_event.h> */ + __u64 raw_callchain_nr; /* Number of raw_callchain entries */ + const __u64 *raw_callchain; /* Refer <linux/perf_event.h> */ + const char *event; +}; +---- + +The perf_dlfilter_fns structure +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The 'perf_dlfilter_fns' structure is populated with function pointers when the +file is loaded. The functions can be called by 'filter_event'. + +[source,c] +---- +struct perf_dlfilter_fns { + const struct perf_dlfilter_al *(*resolve_ip)(void *ctx); + const struct perf_dlfilter_al *(*resolve_addr)(void *ctx); + void *(*reserved[126])(void *); +}; +---- + +'resolve_ip' returns information about ip. + +'resolve_addr' returns information about addr (if addr_correlates_sym). + +The perf_dlfilter_al structure +~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The 'perf_dlfilter_al' structure contains information about an address. + +[source,c] +---- +/* + * Address location (as per perf script) + */ +struct perf_dlfilter_al { + __u32 size; /* Size of this structure (for compatibility checking) */ + __u32 symoff; + const char *sym; + __u64 addr; /* Mapped address (from dso) */ + __u64 sym_start; + __u64 sym_end; + const char *dso; + __u8 sym_binding; /* STB_LOCAL, STB_GLOBAL or STB_WEAK, refer <elf.h> */ + __u8 is_64_bit; /* Only valid if dso is not NULL */ + __u8 is_kernel_ip; /* True if in kernel space */ + __u32 buildid_size; + __u8 *buildid; + /* Below members are only populated by resolve_ip() */ + __u8 filtered; /* true if this sample event will be filtered out */ + const char *comm; +}; +---- + +perf_dlfilter_sample flags +~~~~~~~~~~~~~~~~~~~~~~~~~~ + +The 'flags' member of 'perf_dlfilter_sample' corresponds with the flags field +of perf script. The bits of the flags are as follows: + +[source,c] +---- +/* Definitions for perf_dlfilter_sample flags */ +enum { + PERF_DLFILTER_FLAG_BRANCH = 1ULL << 0, + PERF_DLFILTER_FLAG_CALL = 1ULL << 1, + PERF_DLFILTER_FLAG_RETURN = 1ULL << 2, + PERF_DLFILTER_FLAG_CONDITIONAL = 1ULL << 3, + PERF_DLFILTER_FLAG_SYSCALLRET = 1ULL << 4, + PERF_DLFILTER_FLAG_ASYNC = 1ULL << 5, + PERF_DLFILTER_FLAG_INTERRUPT = 1ULL << 6, + PERF_DLFILTER_FLAG_TX_ABORT = 1ULL << 7, + PERF_DLFILTER_FLAG_TRACE_BEGIN = 1ULL << 8, + PERF_DLFILTER_FLAG_TRACE_END = 1ULL << 9, + PERF_DLFILTER_FLAG_IN_TX = 1ULL << 10, + PERF_DLFILTER_FLAG_VMENTRY = 1ULL << 11, + PERF_DLFILTER_FLAG_VMEXIT = 1ULL << 12, +}; +---- + +EXAMPLE +------- + +Filter out everything except branches from "foo" to "bar": + +[source,c] +---- +#include <perf/perf_dlfilter.h> +#include <string.h> + +const struct perf_dlfilter_fns perf_dlfilter_fns; + +int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx) +{ + const struct perf_dlfilter_al *al; + const struct perf_dlfilter_al *addr_al; + + if (!sample->ip || !sample->addr_correlates_sym) + return 1; + + al = perf_dlfilter_fns.resolve_ip(ctx); + if (!al || !al->sym || strcmp(al->sym, "foo")) + return 1; + + addr_al = perf_dlfilter_fns.resolve_addr(ctx); + if (!addr_al || !addr_al->sym || strcmp(addr_al->sym, "bar")) + return 1; + + return 0; +} +---- + +To build the shared object, assuming perf has been installed for the local user +i.e. perf_dlfilter.h is in ~/include/perf : + + gcc -c -I ~/include -fpic dlfilter-example.c + gcc -shared -o dlfilter-example.so dlfilter-example.o + +To use the filter with perf script: + + perf script --dlfilter ./dlfilter-example.so + +SEE ALSO +-------- +linkperf:perf-script[1]tools/perf/Documentation/perf-script.txt +6
-1@@ -98,6 +98,10 @@ OPTIONS Generate perf-script.[ext] starter script for given language, using current perf.data. +--dlfilter=<file>:: + Filter sample events using the given shared object file. + Refer linkperf:perf-dlfilter[1] + -a:: Force system-wide collection. Scripts run without a <command> normally use -a by default, while scripts run with a <command>@@ -483,4 +487,5 @@ include::itrace.txt[] SEE ALSO -------- linkperf:perf-record[1], linkperf:perf-script-perl[1], -linkperf:perf-script-python[1], linkperf:perf-intel-pt[1] +linkperf:perf-script-python[1], linkperf:perf-intel-pt[1], +linkperf:perf-dlfilter[1]tools/perf/builtin-script.c +24
-1@@ -55,6 +55,7 @@#include <subcmd/pager.h> #include <perf/evlist.h> #include <linux/err.h> +#include "util/dlfilter.h" #include "util/record.h" #include "util/util.h" #include "perf.h" @@ -79,6 +80,7 @@ static DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);static struct perf_stat_config stat_config;static int max_blocks;static bool native_arch; +static struct dlfilter *dlfilter;unsigned int scripting_max_stack =PERF_MAX_STACK_DEPTH ;@@ -2175,6 +2177,7 @@ static int process_sample_event(struct perf_tool *tool, struct perf_script *scr = container_of(tool, struct perf_script, tool);struct addr_location al;struct addr_location addr_al; +int ret =0 ;if (perf_time__ranges_skip_sample (scr->ptime_range, scr->range_num, sample->time)) {@@ -2213,6 +2216,13 @@ static int process_sample_event(struct perf_tool *tool,if (evswitch__discard (&scr->evswitch, evsel)) goto out_put; + ret =dlfilter__filter_event (dlfilter, event, sample, evsel, machine, &al, &addr_al); +if (ret) { +if (ret >0 ) + ret =0 ; + goto out_put; + } +if (scripting_ops) {struct addr_location *addr_al_ptr =NULL ;@@ -2229,7 +2239,7 @@ static int process_sample_event(struct perf_tool *tool, out_put:addr_location__put (&al); -return 0 ; +return ret; } static int process_attr(struct perf_tool *tool, union perf_event *event,@@ -3568,6 +3578,7 @@ int cmd_script(int argc, const char **argv) };struct utsname uts;char *script_path =NULL ; +const char *dlfilter_file =NULL ;const char **__argv;int i, j, err =0 ;struct perf_script script = {@@ -3615,6 +3626,7 @@ int cmd_script(int argc, const char **argv) parse_scriptname),OPT_STRING ('g' ,"gen-script" , &generate_script_lang,"lang" ,"generate perf-script.xx script in specified language" ), +OPT_STRING (0 ,"dlfilter" , &dlfilter_file,"file" ,"filter .so file name" ),OPT_STRING ('i' ,"input" , &input_name,"file" ,"input file name" ),OPT_BOOLEAN ('d' ,"debug-mode" , &debug_mode, "do various checks like samples ordering and lost events"),@@ -3933,6 +3945,12 @@ int cmd_script(int argc, const char **argv)exit (-1 ); } +if (dlfilter_file) { + dlfilter =dlfilter__new (dlfilter_file); +if (!dlfilter) +return -1 ; + } +if (!script_name) {setup_pager (); use_browser =0 ;@@ -4032,6 +4050,10 @@ int cmd_script(int argc, const char **argv) goto out_delete; } + err =dlfilter__start (dlfilter, session); +if (err) + goto out_delete; +if (script_name) { err = scripting_ops->start_script (script_name, argc, argv, session);if (err)@@ -4081,6 +4103,7 @@ int cmd_script(int argc, const char **argv)if (script_started)cleanup_scripting (); +dlfilter__cleanup (dlfilter); out:return err; }tools/perf/util/Build +1
-0@@ -126,6 +126,7 @@ perf-y += parse-regs-options.o perf-y += parse-sublevel-options.o perf-y += term.o perf-y += help-unknown-cmd.o +perf-y += dlfilter.o perf-y += mem-events.o perf-y += vsprintf.o perf-y += units.otools/perf/util/dlfilter.c new file +330
-0@@ -0,0 +1,330 @@ +// SPDX-License-Identifier: GPL-2.0 +/* +* dlfilter.c: Interface to perf script --dlfilter shared object +* Copyright (c) 2021, Intel Corporation. +*/ +#include <dlfcn.h> +#include <stdlib.h> +#include <string.h> +#include <linux/zalloc.h> +#include <linux/build_bug.h> + +#include "debug.h" +#include "event.h" +#include "evsel.h" +#include "dso.h" +#include "map.h" +#include "thread.h" +#include "symbol.h" +#include "dlfilter.h" +#include "perf_dlfilter.h" + +static void al_to_d_al (struct addr_location *al,struct perf_dlfilter_al *d_al) +{ +struct symbol *sym = al->sym; + + d_al->size =sizeof (*d_al); +if (al->map) { +struct dso *dso = al->map->dso; + +if (symbol_conf.show_kernel_path && dso->long_name) + d_al->dso = dso->long_name; +else + d_al->dso = dso->name; + d_al->is_64_bit = dso->is_64_bit; + d_al->buildid_size = dso->bid.size; + d_al->buildid = dso->bid.data; + }else { + d_al->dso =NULL ; + d_al->is_64_bit =0 ; + d_al->buildid_size =0 ; + d_al->buildid =NULL ; + } +if (sym) { + d_al->sym = sym->name; + d_al->sym_start = sym->start; + d_al->sym_end = sym->end; +if (al->addr < sym->end) + d_al->symoff = al->addr - sym->start; +else + d_al->symoff = al->addr - al->map->start - sym->start; + d_al->sym_binding = sym->binding; + }else { + d_al->sym =NULL ; + d_al->sym_start =0 ; + d_al->sym_end =0 ; + d_al->symoff =0 ; + d_al->sym_binding =0 ; + } + d_al->addr = al->addr; + d_al->comm =NULL ; + d_al->filtered =0 ; +} + +static struct addr_location *get_al (struct dlfilter *d) +{ +struct addr_location *al = d->al; + +if (!al->thread &&machine__resolve (d->machine, al, d->sample) <0 ) +return NULL ; +return al; +} + +static struct thread *get_thread (struct dlfilter *d) +{ +struct addr_location *al =get_al (d); + +return al ? al->thread :NULL ; +} + +static const struct perf_dlfilter_al *dlfilter__resolve_ip (void *ctx) +{ +struct dlfilter *d = (struct dlfilter *)ctx; +struct perf_dlfilter_al *d_al = d->d_ip_al; +struct addr_location *al; + +if (!d->ctx_valid) +return NULL ; + +/* 'size' is also used to indicate already initialized */ +if (d_al->size) +return d_al; + + al =get_al (d); +if (!al) +return NULL ; + +al_to_d_al (al, d_al); + + d_al->is_kernel_ip =machine__kernel_ip (d->machine, d->sample->ip); + d_al->comm = al->thread ?thread__comm_str (al->thread) :":-1" ; + d_al->filtered = al->filtered; + +return d_al; +} + +static const struct perf_dlfilter_al *dlfilter__resolve_addr (void *ctx) +{ +struct dlfilter *d = (struct dlfilter *)ctx; +struct perf_dlfilter_al *d_addr_al = d->d_addr_al; +struct addr_location *addr_al = d->addr_al; + +if (!d->ctx_valid || !d->d_sample->addr_correlates_sym) +return NULL ; + +/* 'size' is also used to indicate already initialized */ +if (d_addr_al->size) +return d_addr_al; + +if (!addr_al->thread) { +struct thread *thread =get_thread (d); + +if (!thread) +return NULL ; +thread__resolve (thread, addr_al, d->sample); + } + +al_to_d_al (addr_al, d_addr_al); + + d_addr_al->is_kernel_ip =machine__kernel_ip (d->machine, d->sample->addr); + +return d_addr_al; +} + +static const struct perf_dlfilter_fns perf_dlfilter_fns = { + .resolve_ip = dlfilter__resolve_ip, + .resolve_addr = dlfilter__resolve_addr, +}; + +#define CHECK_FLAG (x) BUILD_BUG_ON((u64)PERF_DLFILTER_FLAG_ ## x != (u64)PERF_IP_FLAG_ ## x) + +static int dlfilter__init (struct dlfilter *d,const char *file) +{ +CHECK_FLAG (BRANCH ); +CHECK_FLAG (CALL ); +CHECK_FLAG (RETURN ); +CHECK_FLAG (CONDITIONAL ); +CHECK_FLAG (SYSCALLRET ); +CHECK_FLAG (ASYNC ); +CHECK_FLAG (INTERRUPT ); +CHECK_FLAG (TX_ABORT ); +CHECK_FLAG (TRACE_BEGIN ); +CHECK_FLAG (TRACE_END ); +CHECK_FLAG (IN_TX ); +CHECK_FLAG (VMENTRY ); +CHECK_FLAG (VMEXIT ); + +memset (d,0 ,sizeof (*d)); + d->file =strdup (file); +if (!d->file) +return -1 ; +return 0 ; +} + +static void dlfilter__exit (struct dlfilter *d) +{ +zfree (&d->file); +} + +static int dlfilter__open (struct dlfilter *d) +{ + d->handle =dlopen (d->file,RTLD_NOW ); +if (!d->handle) { +pr_err ("dlopen failed for: '%s'\n" , d->file); +return -1 ; + } + d->start =dlsym (d->handle,"start" ); + d->filter_event =dlsym (d->handle,"filter_event" ); + d->stop =dlsym (d->handle,"stop" ); + d->fns =dlsym (d->handle,"perf_dlfilter_fns" ); +if (d->fns) +memcpy (d->fns, &perf_dlfilter_fns,sizeof (struct perf_dlfilter_fns )); +return 0 ; +} + +static int dlfilter__close (struct dlfilter *d) +{ +return dlclose (d->handle); +} + +struct dlfilter *dlfilter__new (const char *file) +{ +struct dlfilter *d =malloc (sizeof (*d)); + +if (!d) +return NULL ; + +if (dlfilter__init (d, file)) + goto err_free; + +if (dlfilter__open (d)) + goto err_exit; + +return d; + +err_exit: +dlfilter__exit (d); +err_free: +free (d); +return NULL ; +} + +static void dlfilter__free (struct dlfilter *d) +{ +if (d) { +dlfilter__exit (d); +free (d); + } +} + +int dlfilter__start (struct dlfilter *d,struct perf_session *session) +{ +if (d) { + d->session = session; +if (d->start) +return d->start (&d->data); + } +return 0 ; +} + +static int dlfilter__stop (struct dlfilter *d) +{ +if (d && d->stop) +return d->stop (d->data); +return 0 ; +} + +void dlfilter__cleanup (struct dlfilter *d) +{ +if (d) { +dlfilter__stop (d); +dlfilter__close (d); +dlfilter__free (d); + } +} + +#define ASSIGN (x) d_sample.x = sample->x + +int dlfilter__do_filter_event (struct dlfilter *d, +union perf_event *event, +struct perf_sample *sample, +struct evsel *evsel, +struct machine *machine, +struct addr_location *al, +struct addr_location *addr_al) +{ +struct perf_dlfilter_sample d_sample; +struct perf_dlfilter_al d_ip_al; +struct perf_dlfilter_al d_addr_al; +int ret; + + d->event = event; + d->sample = sample; + d->evsel = evsel; + d->machine = machine; + d->al = al; + d->addr_al = addr_al; + d->d_sample = &d_sample; + d->d_ip_al = &d_ip_al; + d->d_addr_al = &d_addr_al; + + d_sample.size =sizeof (d_sample); + d_ip_al.size =0 ;/* To indicate d_ip_al is not initialized */ + d_addr_al.size =0 ;/* To indicate d_addr_al is not initialized */ + +ASSIGN (ip); +ASSIGN (pid); +ASSIGN (tid); +ASSIGN (time); +ASSIGN (addr); +ASSIGN (id); +ASSIGN (stream_id); +ASSIGN (period); +ASSIGN (weight); +ASSIGN (ins_lat); +ASSIGN (p_stage_cyc); +ASSIGN (transaction); +ASSIGN (insn_cnt); +ASSIGN (cyc_cnt); +ASSIGN (cpu); +ASSIGN (flags); +ASSIGN (data_src); +ASSIGN (phys_addr); +ASSIGN (data_page_size); +ASSIGN (code_page_size); +ASSIGN (cgroup); +ASSIGN (cpumode); +ASSIGN (misc); +ASSIGN (raw_size); +ASSIGN (raw_data); + +if (sample->branch_stack) { + d_sample.brstack_nr = sample->branch_stack->nr; + d_sample.brstack = (struct perf_branch_entry *)perf_sample__branch_entries (sample); + }else { + d_sample.brstack_nr =0 ; + d_sample.brstack =NULL ; + } + +if (sample->callchain) { + d_sample.raw_callchain_nr = sample->callchain->nr; + d_sample.raw_callchain = (__u64 *)sample->callchain->ips; + }else { + d_sample.raw_callchain_nr =0 ; + d_sample.raw_callchain =NULL ; + } + + d_sample.addr_correlates_sym = + (evsel->core.attr.sample_type &PERF_SAMPLE_ADDR ) && +sample_addr_correlates_sym (&evsel->core.attr); + + d_sample.event =evsel__name (evsel); + + d->ctx_valid = true; + + ret = d->filter_event (d->data, &d_sample, d); + + d->ctx_valid = false; + +return ret; +}tools/perf/util/dlfilter.h new file +74
-0@@ -0,0 +1,74 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* +* dlfilter.h: Interface to perf script --dlfilter shared object +* Copyright (c) 2021, Intel Corporation. +*/ + +#ifndef PERF_UTIL_DLFILTER_H +#define PERF_UTIL_DLFILTER_H + +struct perf_session ; +union perf_event ; +struct perf_sample ; +struct evsel ; +struct machine ; +struct addr_location ; +struct perf_dlfilter_fns ; +struct perf_dlfilter_sample ; +struct perf_dlfilter_al ; + +struct dlfilter { +char *file; +void *handle; +void *data; +struct perf_session *session; +bool ctx_valid; + +union perf_event *event; +struct perf_sample *sample; +struct evsel *evsel; +struct machine *machine; +struct addr_location *al; +struct addr_location *addr_al; +struct perf_dlfilter_sample *d_sample; +struct perf_dlfilter_al *d_ip_al; +struct perf_dlfilter_al *d_addr_al; + +int (*start)(void **data); +int (*stop)(void *data); + +int (*filter_event)(void *data, +const struct perf_dlfilter_sample *sample, +void *ctx); + +struct perf_dlfilter_fns *fns; +}; + +struct dlfilter *dlfilter__new (const char *file); + +int dlfilter__start (struct dlfilter *d,struct perf_session *session); + +int dlfilter__do_filter_event (struct dlfilter *d, +union perf_event *event, +struct perf_sample *sample, +struct evsel *evsel, +struct machine *machine, +struct addr_location *al, +struct addr_location *addr_al); + +void dlfilter__cleanup (struct dlfilter *d); + +static inline int dlfilter__filter_event (struct dlfilter *d, +union perf_event *event, +struct perf_sample *sample, +struct evsel *evsel, +struct machine *machine, +struct addr_location *al, +struct addr_location *addr_al) +{ +if (!d || !d->filter_event) +return 0 ; +return dlfilter__do_filter_event (d, event, sample, evsel, machine, al, addr_al); +} + +#endif tools/perf/util/perf_dlfilter.h new file +120
-0@@ -0,0 +1,120 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* +* perf_dlfilter.h: API for perf --dlfilter shared object +* Copyright (c) 2021, Intel Corporation. +*/ +#ifndef _LINUX_PERF_DLFILTER_H +#define _LINUX_PERF_DLFILTER_H + +#include <linux/perf_event.h> +#include <linux/types.h> + +/* Definitions for perf_dlfilter_sample flags */ +enum { +PERF_DLFILTER_FLAG_BRANCH =1ULL <<0 , +PERF_DLFILTER_FLAG_CALL =1ULL <<1 , +PERF_DLFILTER_FLAG_RETURN =1ULL <<2 , +PERF_DLFILTER_FLAG_CONDITIONAL =1ULL <<3 , +PERF_DLFILTER_FLAG_SYSCALLRET =1ULL <<4 , +PERF_DLFILTER_FLAG_ASYNC =1ULL <<5 , +PERF_DLFILTER_FLAG_INTERRUPT =1ULL <<6 , +PERF_DLFILTER_FLAG_TX_ABORT =1ULL <<7 , +PERF_DLFILTER_FLAG_TRACE_BEGIN =1ULL <<8 , +PERF_DLFILTER_FLAG_TRACE_END =1ULL <<9 , +PERF_DLFILTER_FLAG_IN_TX =1ULL <<10 , +PERF_DLFILTER_FLAG_VMENTRY =1ULL <<11 , +PERF_DLFILTER_FLAG_VMEXIT =1ULL <<12 , +}; + +/* +* perf sample event information (as per perf script and <linux/perf_event.h>) +*/ +struct perf_dlfilter_sample { +__u32 size;/* Size of this structure (for compatibility checking) */ +__u64 ip; +__s32 pid; +__s32 tid; +__u64 time; +__u64 addr; +__u64 id; +__u64 stream_id; +__u64 period; +__u64 weight;/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ +__u16 ins_lat;/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ +__u16 p_stage_cyc;/* Refer PERF_SAMPLE_WEIGHT_TYPE in <linux/perf_event.h> */ +__u64 transaction;/* Refer PERF_SAMPLE_TRANSACTION in <linux/perf_event.h> */ +__u64 insn_cnt;/* For instructions-per-cycle (IPC) */ +__u64 cyc_cnt;/* For instructions-per-cycle (IPC) */ +__s32 cpu; +__u32 flags;/* Refer PERF_DLFILTER_FLAG_* above */ +__u64 data_src;/* Refer PERF_SAMPLE_DATA_SRC in <linux/perf_event.h> */ +__u64 phys_addr;/* Refer PERF_SAMPLE_PHYS_ADDR in <linux/perf_event.h> */ +__u64 data_page_size;/* Refer PERF_SAMPLE_DATA_PAGE_SIZE in <linux/perf_event.h> */ +__u64 code_page_size;/* Refer PERF_SAMPLE_CODE_PAGE_SIZE in <linux/perf_event.h> */ +__u64 cgroup;/* Refer PERF_SAMPLE_CGROUP in <linux/perf_event.h> */ +__u8 cpumode;/* Refer CPUMODE_MASK etc in <linux/perf_event.h> */ +__u8 addr_correlates_sym;/* True => resolve_addr() can be called */ +__u16 misc;/* Refer perf_event_header in <linux/perf_event.h> */ +__u32 raw_size;/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ +const void *raw_data;/* Refer PERF_SAMPLE_RAW in <linux/perf_event.h> */ +__u64 brstack_nr;/* Number of brstack entries */ +const struct perf_branch_entry *brstack;/* Refer <linux/perf_event.h> */ +__u64 raw_callchain_nr;/* Number of raw_callchain entries */ +const __u64 *raw_callchain;/* Refer <linux/perf_event.h> */ +const char *event; +}; + +/* +* Address location (as per perf script) +*/ +struct perf_dlfilter_al { +__u32 size;/* Size of this structure (for compatibility checking) */ +__u32 symoff; +const char *sym; +__u64 addr;/* Mapped address (from dso) */ +__u64 sym_start; +__u64 sym_end; +const char *dso; +__u8 sym_binding;/* STB_LOCAL, STB_GLOBAL or STB_WEAK, refer <elf.h> */ +__u8 is_64_bit;/* Only valid if dso is not NULL */ +__u8 is_kernel_ip;/* True if in kernel space */ +__u32 buildid_size; +__u8 *buildid; +/* Below members are only populated by resolve_ip() */ +__u8 filtered;/* True if this sample event will be filtered out */ +const char *comm; +}; + +struct perf_dlfilter_fns { +/* Return information about ip */ +const struct perf_dlfilter_al *(*resolve_ip)(void *ctx); +/* Return information about addr (if addr_correlates_sym) */ +const struct perf_dlfilter_al *(*resolve_addr)(void *ctx); +/* Reserved */ +void *(*reserved[126 ])(void *); +}; + +/* +* If implemented, 'start' will be called at the beginning, +* before any calls to 'filter_event'. Return 0 to indicate success, +* or return a negative error code. '*data' can be assigned for use +* by other functions. +*/ +int start (void **data); + +/* +* If implemented, 'stop' will be called at the end, +* after any calls to 'filter_event'. Return 0 to indicate success, or +* return a negative error code. 'data' is set by start(). +*/ +int stop (void *data); + +/* +* If implemented, 'filter_event' will be called for each sample +* event. Return 0 to keep the sample event, 1 to filter it out, or +* return a negative error code. 'data' is set by start(). 'ctx' is +* needed for calls to perf_dlfilter_fns. +*/ +int filter_event (void *data,const struct perf_dlfilter_sample *sample,void *ctx); + +#endif Signature · 1 line
2.17.1
Adrian Hunter
reviewerRFC PATCH 5/11 perf script: Add dlfilter__filter_event_early()
In reply to Adrian Hunterfilter_event_early() can be more than 30% faster than filter_event() because it is called before internal filtering. In other respects it is the same as filter_event(), except that it will be passed events that have yet to be filtered out.
--- tools/perf/Documentation/perf-dlfilter.txt | 13 +++++++---- tools/perf/builtin-script.c | 26 +++++++++++++++------- tools/perf/util/dlfilter.c | 9 ++++++-- tools/perf/util/dlfilter.h | 21 +++++++++++++++-- tools/perf/util/perf_dlfilter.h | 6 +++++ 5 files changed, 59 insertions(+), 16 deletions(-)
tools/perf/Documentation/perf-dlfilter.txt +9 -4
@@ -31,15 +31,16 @@ const struct perf_dlfilter_fns perf_dlfilter_fns; int start(void **data); int stop(void *data); int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx); +int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, void *ctx); ---- If implemented, 'start' will be called at the beginning, before any -calls to 'filter_event' . Return 0 to indicate success, +calls to 'filter_event' or 'filter_event_early'. Return 0 to indicate success, or return a negative error code. '*data' can be assigned for use by other functions. If implemented, 'stop' will be called at the end, after any calls to -'filter_event'. Return 0 to indicate success, or +'filter_event' or 'filter_event_early'. Return 0 to indicate success, or return a negative error code. 'data' is set by 'start'. If implemented, 'filter_event' will be called for each sample event.
@@ -47,10 +48,13 @@ Return 0 to keep the sample event, 1 to filter it out, or return a negative error code. 'data' is set by 'start'. 'ctx' is needed for calls to 'perf_dlfilter_fns'. +'filter_event_early' is the same as 'filter_event' except it is called before +internal filtering. + The perf_dlfilter_sample structure ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ -'filter_event' is passed a perf_dlfilter_sample +'filter_event' and 'filter_event_early' are passed a perf_dlfilter_sample structure, which contains the following fields: [source,c] ----
@@ -97,7 +101,8 @@ The perf_dlfilter_fns structure ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ The 'perf_dlfilter_fns' structure is populated with function pointers when the -file is loaded. The functions can be called by 'filter_event'. +file is loaded. The functions can be called by 'filter_event' or +'filter_event_early'. [source,c] ----
tools/perf/builtin-script.c +18 -8
@@ -2179,9 +2179,20 @@ static int process_sample_event(struct perf_tool *tool,struct addr_location addr_al;int ret =0 ; +/* Set thread to NULL to indicate addr_al and al are not initialized */ + addr_al.thread =NULL ; + al.thread =NULL ; + + ret =dlfilter__filter_event_early (dlfilter, event, sample, evsel, machine, &al, &addr_al); +if (ret) { +if (ret >0 ) + ret =0 ; + goto out_put; + } +if (perf_time__ranges_skip_sample (scr->ptime_range, scr->range_num, sample->time)) { -return 0 ; + goto out_put; }if (debug_mode) {
@@ -2192,24 +2203,22 @@ static int process_sample_event(struct perf_tool *tool, nr_unordered++; } last_timestamp = sample->time; -return 0 ; + goto out_put; }if (filter_cpu (sample)) -return 0 ; + goto out_put;if (machine__resolve (machine, &al, sample) <0 ) {pr_err ("problem processing %d event, skipping it.\n" , event->header.type); -return -1 ; + ret =-1 ; + goto out_put; }if (al.filtered) goto out_put; -/* Set thread to NULL to indicate addr_al is not initialized */ - addr_al.thread =NULL ; -if (!show_event (sample, evsel, al.thread, &al, &addr_al)) goto out_put;
@@ -2238,7 +2247,8 @@ static int process_sample_event(struct perf_tool *tool, } out_put: -addr_location__put (&al); +if (al.thread) +addr_location__put (&al);return ret; }
tools/perf/util/dlfilter.c +7 -2
@@ -175,6 +175,7 @@ static int dlfilter__open(struct dlfilter *d) } d->start =dlsym (d->handle,"start" ); d->filter_event =dlsym (d->handle,"filter_event" ); + d->filter_event_early =dlsym (d->handle,"filter_event_early" ); d->stop =dlsym (d->handle,"stop" ); d->fns =dlsym (d->handle,"perf_dlfilter_fns" );if (d->fns)
@@ -251,7 +252,8 @@ int dlfilter__do_filter_event(struct dlfilter *d,struct evsel *evsel, struct machine *machine, struct addr_location *al, - struct addr_location *addr_al) + struct addr_location *addr_al, + bool early) { struct perf_dlfilter_sample d_sample;struct perf_dlfilter_al d_ip_al;
@@ -322,7 +324,10 @@ int dlfilter__do_filter_event(struct dlfilter *d, d->ctx_valid = true; - ret = d->filter_event (d->data, &d_sample, d); +if (early) + ret = d->filter_event_early (d->data, &d_sample, d); +else + ret = d->filter_event (d->data, &d_sample, d); d->ctx_valid = false;
tools/perf/util/dlfilter.h +19 -2
@@ -40,6 +40,9 @@ struct dlfilter {int (*filter_event)(void *data,const struct perf_dlfilter_sample *sample,void *ctx); +int (*filter_event_early)(void *data, +const struct perf_dlfilter_sample *sample, +void *ctx);struct perf_dlfilter_fns *fns; };
@@ -54,7 +57,8 @@ int dlfilter__do_filter_event(struct dlfilter *d,struct evsel *evsel, struct machine *machine, struct addr_location *al, - struct addr_location *addr_al); + struct addr_location *addr_al, + bool early);void dlfilter__cleanup (struct dlfilter *d);
@@ -68,7 +72,20 @@ static inline int dlfilter__filter_event(struct dlfilter *d, {if (!d || !d->filter_event)return 0 ; -return dlfilter__do_filter_event (d, event, sample, evsel, machine, al, addr_al); +return dlfilter__do_filter_event (d, event, sample, evsel, machine, al, addr_al, false); +} + +static inline int dlfilter__filter_event_early (struct dlfilter *d, +union perf_event *event, +struct perf_sample *sample, +struct evsel *evsel, +struct machine *machine, +struct addr_location *al, +struct addr_location *addr_al) +{ +if (!d || !d->filter_event_early) +return 0 ; +return dlfilter__do_filter_event (d, event, sample, evsel, machine, al, addr_al, true); }#endif
tools/perf/util/perf_dlfilter.h +6 -0
@@ -117,4 +117,10 @@ int stop(void *data);*/ int filter_event (void *data,const struct perf_dlfilter_sample *sample,void *ctx); +/* +* The same as 'filter_event' except it is called before internal +* filtering. +*/ +int filter_event_early (void *data,const struct perf_dlfilter_sample *sample,void *ctx); +#endif
Signature · 1 line
2.17.1
Adrian Hunter
reviewerRFC PATCH 6/11 perf build: Install perf_dlfilter.h
In reply to Adrian HunterUsers of the --dlfilter option need to include perf_dlfilter.h in their filters. Install it to the include path.
--- tools/perf/Makefile.config | 3 +++ tools/perf/Makefile.perf | 4 +++- 2 files changed, 6 insertions(+), 1 deletion(-)
tools/perf/Makefile.config +3 -0
@@ -1118,6 +1118,8 @@ prefix ?= $(HOME) endif bindir_relative = bin bindir = $(abspath $(prefix)/$(bindir_relative)) +includedir_relative = include +includedir = $(abspath $(prefix)/$(includedir_relative)) mandir = share/man infodir = share/info perfexecdir = libexec/perf-core
@@ -1150,6 +1152,7 @@ ETC_PERFCONFIG_SQ = $(subst ','\'',$(ETC_PERFCONFIG)) STRACE_GROUPS_DIR_SQ = $(subst ','\'',$(STRACE_GROUPS_DIR)) DESTDIR_SQ = $(subst ','\'',$(DESTDIR)) bindir_SQ = $(subst ','\'',$(bindir)) +includedir_SQ = $(subst ','\'',$(includedir)) mandir_SQ = $(subst ','\'',$(mandir)) infodir_SQ = $(subst ','\'',$(infodir)) perfexecdir_SQ = $(subst ','\'',$(perfexecdir))
tools/perf/Makefile.perf +3 -1
@@ -923,7 +923,9 @@ install-tools: all install-gtk $(call QUIET_INSTALL, binaries) \ $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'; \ $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'; \ - $(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(bindir_SQ)/trace' + $(LN) '$(DESTDIR_SQ)$(bindir_SQ)/perf' '$(DESTDIR_SQ)$(dir_SQ)/trace'; \ + $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(includedir_SQ)/perf'; \ + $(INSTALL) util/perf_dlfilter.h -t '$(DESTDIR_SQ)$(includedir_SQ)/perf' ifndef NO_PERF_READ_VDSO32 $(call QUIET_INSTALL, perf-read-vdso32) \ $(INSTALL) $(OUTPUT)perf-read-vdso32 '$(DESTDIR_SQ)$(bindir_SQ)';
Signature · 1 line
2.17.1
Adrian Hunter
reviewerRFC PATCH 7/11 perf dlfilter: Add resolve_address() to perf_dlfilter_fns
In reply to Adrian HunterAdd a function, for use by dlfilters, to resolve addresses from branch stacks or callchains.
--- tools/perf/Documentation/perf-dlfilter.txt | 6 ++++- tools/perf/util/dlfilter.c | 29 ++++++++++++++++++++++ tools/perf/util/perf_dlfilter.h | 7 +++++- 3 files changed, 40 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-dlfilter.txt +5 -1
@@ -109,7 +109,8 @@ file is loaded. The functions can be called by 'filter_event' or struct perf_dlfilter_fns { const struct perf_dlfilter_al *(*resolve_ip)(void *ctx); const struct perf_dlfilter_al *(*resolve_addr)(void *ctx); - void *(*reserved[126])(void *); + __s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al); + void *(*reserved[125])(void *); }; ----
@@ -117,6 +118,9 @@ struct perf_dlfilter_fns { 'resolve_addr' returns information about addr (if addr_correlates_sym). +'resolve_address' provides information about 'address'. al->size must be set +before calling. Returns 0 on success, -1 otherwise. + The perf_dlfilter_al structure ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tools/perf/util/dlfilter.c +29 -0
@@ -131,9 +131,38 @@ static const struct perf_dlfilter_al *dlfilter__resolve_addr(void *ctx)return d_addr_al; } +static __s32 dlfilter__resolve_address (void *ctx,__u64 address,struct perf_dlfilter_al *d_al_p) +{ +struct dlfilter *d = (struct dlfilter *)ctx; +struct perf_dlfilter_al d_al; +struct addr_location al; +struct thread *thread; +__u32 sz; + +if (!d->ctx_valid || !d_al_p) +return -1 ; + + thread =get_thread (d); +if (!thread) +return -1 ; + +thread__find_symbol_fb (thread, d->sample->cpumode, address, &al); + +al_to_d_al (&al, &d_al); + + d_al.is_kernel_ip =machine__kernel_ip (d->machine, address); + + sz = d_al_p->size; +memcpy (d_al_p, &d_al,min ((size_t )sz,sizeof (d_al))); + d_al_p->size = sz; + +return 0 ; +} +static const struct perf_dlfilter_fns perf_dlfilter_fns = { .resolve_ip = dlfilter__resolve_ip, .resolve_addr = dlfilter__resolve_addr, + .resolve_address = dlfilter__resolve_address, };#define CHECK_FLAG (x) BUILD_BUG_ON((u64)PERF_DLFILTER_FLAG_ ## x != (u64)PERF_IP_FLAG_ ## x)
tools/perf/util/perf_dlfilter.h +6 -1
@@ -90,8 +90,13 @@ struct perf_dlfilter_fns {const struct perf_dlfilter_al *(*resolve_ip)(void *ctx);/* Return information about addr (if addr_correlates_sym) */ const struct perf_dlfilter_al *(*resolve_addr)(void *ctx); +/* +* Return information about address (al->size must be set before +* calling). Returns 0 on success, -1 otherwise. +*/ +__s32 (*resolve_address)(void *ctx,__u64 address,struct perf_dlfilter_al *al);/* Reserved */ -void *(*reserved[126 ])(void *); +void *(*reserved[125 ])(void *); };/*
Signature · 1 line
2.17.1
Adrian Hunter
reviewerRFC PATCH 8/11 perf dlfilter: Add insn() to perf_dlfilter_fns
In reply to Adrian HunterAdd a function, for use by dlfilters, to return instruction bytes.
--- tools/perf/Documentation/perf-dlfilter.txt | 5 +++- tools/perf/util/dlfilter.c | 32 ++++++++++++++++++++++ tools/perf/util/perf_dlfilter.h | 4 ++- 3 files changed, 39 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-dlfilter.txt +4 -1
@@ -110,7 +110,8 @@ struct perf_dlfilter_fns { const struct perf_dlfilter_al *(*resolve_ip)(void *ctx); const struct perf_dlfilter_al *(*resolve_addr)(void *ctx); __s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al); - void *(*reserved[125])(void *); + const __u8 *(*insn)(void *ctx, __u32 *length); + void *(*reserved[124])(void *); }; ----
@@ -121,6 +122,8 @@ struct perf_dlfilter_fns { 'resolve_address' provides information about 'address'. al->size must be set before calling. Returns 0 on success, -1 otherwise. +'insn' returns instruction bytes and length. + The perf_dlfilter_al structure ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tools/perf/util/dlfilter.c +32 -0
@@ -15,6 +15,7 @@#include "dso.h" #include "map.h" #include "thread.h" +#include "trace-event.h" #include "symbol.h" #include "dlfilter.h" #include "perf_dlfilter.h"
@@ -159,10 +160,41 @@ static __s32 dlfilter__resolve_address(void *ctx, __u64 address, struct perf_dlfreturn 0 ; } +static const __u8 *dlfilter__insn (void *ctx,__u32 *len) +{ +struct dlfilter *d = (struct dlfilter *)ctx; + +if (!len) +return NULL ; + + *len =0 ; + +if (!d->ctx_valid) +return NULL ; + +if (d->sample->ip && !d->sample->insn_len) { +struct addr_location *al = d->al; + +if (!al->thread &&machine__resolve (d->machine, al, d->sample) <0 ) +return NULL ; + +if (al->thread->maps && al->thread->maps->machine) +script_fetch_insn (d->sample, al->thread, al->thread->maps->machine); + } + +if (!d->sample->insn_len) +return NULL ; + + *len = d->sample->insn_len; + +return (__u8 *)d->sample->insn; +} +static const struct perf_dlfilter_fns perf_dlfilter_fns = { .resolve_ip = dlfilter__resolve_ip, .resolve_addr = dlfilter__resolve_addr, .resolve_address = dlfilter__resolve_address, + .insn = dlfilter__insn, };#define CHECK_FLAG (x) BUILD_BUG_ON((u64)PERF_DLFILTER_FLAG_ ## x != (u64)PERF_IP_FLAG_ ## x)
tools/perf/util/perf_dlfilter.h +3 -1
@@ -95,8 +95,10 @@ struct perf_dlfilter_fns {* calling). Returns 0 on success, -1 otherwise. */ __s32 (*resolve_address)(void *ctx,__u64 address,struct perf_dlfilter_al *al); +/* Return instruction bytes and length */ +const __u8 *(*insn)(void *ctx,__u32 *length);/* Reserved */ -void *(*reserved[125 ])(void *); +void *(*reserved[124 ])(void *); };/*
Signature · 1 line
2.17.1
Adrian Hunter
reviewerRFC PATCH 9/11 perf dlfilter: Add srcline() to perf_dlfilter_fns
In reply to Adrian HunterAdd a function, for use by dlfilters, to return source code file name and line number.
--- tools/perf/Documentation/perf-dlfilter.txt | 5 +++- tools/perf/util/dlfilter.c | 28 ++++++++++++++++++++++ tools/perf/util/perf_dlfilter.h | 4 +++- 3 files changed, 35 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-dlfilter.txt +4 -1
@@ -111,7 +111,8 @@ struct perf_dlfilter_fns { const struct perf_dlfilter_al *(*resolve_addr)(void *ctx); __s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al); const __u8 *(*insn)(void *ctx, __u32 *length); - void *(*reserved[124])(void *); + const char *(*srcline)(void *ctx, __u32 *line_number); + void *(*reserved[123])(void *); }; ----
@@ -124,6 +125,8 @@ before calling. Returns 0 on success, -1 otherwise. 'insn' returns instruction bytes and length. +'srcline' return source file name and line number. + The perf_dlfilter_al structure ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tools/perf/util/dlfilter.c +28 -0
@@ -17,6 +17,7 @@#include "thread.h" #include "trace-event.h" #include "symbol.h" +#include "srcline.h" #include "dlfilter.h" #include "perf_dlfilter.h"
@@ -190,11 +191,38 @@ static const __u8 *dlfilter__insn(void *ctx, __u32 *len)return (__u8 *)d->sample->insn; } +static const char *dlfilter__srcline (void *ctx,__u32 *line_no) +{ +struct dlfilter *d = (struct dlfilter *)ctx; +struct addr_location *al; +unsigned int line =0 ; +char *srcfile =NULL ; +struct map *map; +u64 addr; + +if (!d->ctx_valid || !line_no) +return NULL ; + + al =get_al (d); +if (!al) +return NULL ; + + map = al->map; + addr = al->addr; + +if (map && map->dso) + srcfile =get_srcline_split (map->dso,map__rip_2objdump (map, addr), &line); + + *line_no = line; +return srcfile; +} +static const struct perf_dlfilter_fns perf_dlfilter_fns = { .resolve_ip = dlfilter__resolve_ip, .resolve_addr = dlfilter__resolve_addr, .resolve_address = dlfilter__resolve_address, .insn = dlfilter__insn, + .srcline = dlfilter__srcline, };#define CHECK_FLAG (x) BUILD_BUG_ON((u64)PERF_DLFILTER_FLAG_ ## x != (u64)PERF_IP_FLAG_ ## x)
tools/perf/util/perf_dlfilter.h +3 -1
@@ -97,8 +97,10 @@ struct perf_dlfilter_fns {__s32 (*resolve_address)(void *ctx,__u64 address,struct perf_dlfilter_al *al);/* Return instruction bytes and length */ const __u8 *(*insn)(void *ctx,__u32 *length); +/* Return source file name and line number */ +const char *(*srcline)(void *ctx,__u32 *line_number);/* Reserved */ -void *(*reserved[124 ])(void *); +void *(*reserved[123 ])(void *); };/*
Signature · 1 line
2.17.1
Adrian Hunter
reviewerRFC PATCH 10/11 perf dlfilter: Add attr() to perf_dlfilter_fns
In reply to Adrian HunterAdd a function, for use by dlfilters, to return the perf_event_attr structure.
--- tools/perf/Documentation/perf-dlfilter.txt | 5 ++++- tools/perf/util/dlfilter.c | 11 +++++++++++ tools/perf/util/perf_dlfilter.h | 4 +++- 3 files changed, 18 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-dlfilter.txt +4 -1
@@ -112,7 +112,8 @@ struct perf_dlfilter_fns { __s32 (*resolve_address)(void *ctx, __u64 address, struct perf_dlfilter_al *al); const __u8 *(*insn)(void *ctx, __u32 *length); const char *(*srcline)(void *ctx, __u32 *line_number); - void *(*reserved[123])(void *); + struct perf_event_attr *(*attr)(void *ctx); + void *(*reserved[122])(void *); }; ----
@@ -127,6 +128,8 @@ before calling. Returns 0 on success, -1 otherwise. 'srcline' return source file name and line number. +'attr' returns perf_event_attr, refer <linux/perf_event.h>. + The perf_dlfilter_al structure ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tools/perf/util/dlfilter.c +11 -0
@@ -217,12 +217,23 @@ static const char *dlfilter__srcline(void *ctx, __u32 *line_no)return srcfile; } +static struct perf_event_attr *dlfilter__attr (void *ctx) +{ +struct dlfilter *d = (struct dlfilter *)ctx; + +if (!d->ctx_valid) +return NULL ; + +return &d->evsel->core.attr; +} +static const struct perf_dlfilter_fns perf_dlfilter_fns = { .resolve_ip = dlfilter__resolve_ip, .resolve_addr = dlfilter__resolve_addr, .resolve_address = dlfilter__resolve_address, .insn = dlfilter__insn, .srcline = dlfilter__srcline, + .attr = dlfilter__attr, };#define CHECK_FLAG (x) BUILD_BUG_ON((u64)PERF_DLFILTER_FLAG_ ## x != (u64)PERF_IP_FLAG_ ## x)
tools/perf/util/perf_dlfilter.h +3 -1
@@ -99,8 +99,10 @@ struct perf_dlfilter_fns {const __u8 *(*insn)(void *ctx,__u32 *length);/* Return source file name and line number */ const char *(*srcline)(void *ctx,__u32 *line_number); +/* Return perf_event_attr, refer <linux/perf_event.h> */ +struct perf_event_attr *(*attr)(void *ctx);/* Reserved */ -void *(*reserved[123 ])(void *); +void *(*reserved[122 ])(void *); };/*
Signature · 1 line
2.17.1
Adrian Hunter
reviewerRFC PATCH 11/11 perf dlfilter: Add object_code() to perf_dlfilter_fns
In reply to Adrian HunterAdd a function, for use by dlfilters, to read object code.
--- tools/perf/Documentation/perf-dlfilter.txt | 5 +++- tools/perf/util/dlfilter.c | 34 ++++++++++++++++++++++ tools/perf/util/perf_dlfilter.h | 4 ++- 3 files changed, 41 insertions(+), 2 deletions(-)
tools/perf/Documentation/perf-dlfilter.txt +4 -1
@@ -113,7 +113,8 @@ struct perf_dlfilter_fns { const __u8 *(*insn)(void *ctx, __u32 *length); const char *(*srcline)(void *ctx, __u32 *line_number); struct perf_event_attr *(*attr)(void *ctx); - void *(*reserved[122])(void *); + __s32 (*object_code)(void *ctx, __u64 ip, void *buf, __u32 len); + void *(*reserved[121])(void *); }; ----
@@ -130,6 +131,8 @@ before calling. Returns 0 on success, -1 otherwise. 'attr' returns perf_event_attr, refer <linux/perf_event.h>. +'object_code' reads object code and returns the number of bytes read. + The perf_dlfilter_al structure ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
tools/perf/util/dlfilter.c +34 -0
@@ -227,6 +227,39 @@ static struct perf_event_attr *dlfilter__attr(void *ctx)return &d->evsel->core.attr; } +static __s32 dlfilter__object_code (void *ctx,__u64 ip,void *buf,__u32 len) +{ +struct dlfilter *d = (struct dlfilter *)ctx; +struct addr_location *al; +struct addr_location a; +struct map *map; +u64 offset; + +if (!d->ctx_valid) +return -1 ; + + al =get_al (d); +if (!al) +return -1 ; + + map = al->map; + +if (map && ip >= map->start && ip < map->end && +machine__kernel_ip (d->machine, ip) ==machine__kernel_ip (d->machine, d->sample->ip)) + goto have_map; + +thread__find_map_fb (al->thread, d->sample->cpumode, ip, &a); +if (!a.map) +return -1 ; + + map = a.map; +have_map: + offset = map->map_ip (map, ip); +if (ip + len >= map->end) + len = map->end - ip; +return dso__data_read_offset (map->dso, d->machine, offset, buf, len); +} +static const struct perf_dlfilter_fns perf_dlfilter_fns = { .resolve_ip = dlfilter__resolve_ip, .resolve_addr = dlfilter__resolve_addr,
@@ -234,6 +267,7 @@ static const struct perf_dlfilter_fns perf_dlfilter_fns = { .insn = dlfilter__insn, .srcline = dlfilter__srcline, .attr = dlfilter__attr, + .object_code = dlfilter__object_code, };#define CHECK_FLAG (x) BUILD_BUG_ON((u64)PERF_DLFILTER_FLAG_ ## x != (u64)PERF_IP_FLAG_ ## x)
tools/perf/util/perf_dlfilter.h +3 -1
@@ -101,8 +101,10 @@ struct perf_dlfilter_fns {const char *(*srcline)(void *ctx,__u32 *line_number);/* Return perf_event_attr, refer <linux/perf_event.h> */ struct perf_event_attr *(*attr)(void *ctx); +/* Read object code, return numbers of bytes read */ +__s32 (*object_code)(void *ctx,__u64 ip,void *buf,__u32 len);/* Reserved */ -void *(*reserved[122 ])(void *); +void *(*reserved[121 ])(void *); };/*
Signature · 1 line
2.17.1