linux_dsm_epyc7002/tools/perf/util/thread-stack.h

103 lines
3.0 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* thread-stack.h: Synthesize a thread's stack using call / return events
* Copyright (c) 2014, Intel Corporation.
*/
#ifndef __PERF_THREAD_STACK_H
#define __PERF_THREAD_STACK_H
#include <sys/types.h>
#include <linux/types.h>
struct thread;
struct comm;
struct ip_callchain;
struct symbol;
struct dso;
struct comm;
struct perf_sample;
struct addr_location;
struct call_path;
/*
* Call/Return flags.
*
* CALL_RETURN_NO_CALL: 'return' but no matching 'call'
* CALL_RETURN_NO_RETURN: 'call' but no matching 'return'
perf thread-stack: Represent jmps to the start of a different symbol The compiler might optimize a call/ret combination by making it a jmp. However the thread-stack does not presently cater for that, so that such control flow is not visible in the call graph. Make it visible by recording on the stack a branch to the start of a different symbol. Note, that means when a ret pops the stack, all jmps must be popped off first. Example: $ cat jmp-to-fn.c __attribute__((noinline)) int bar(void) { return -1; } __attribute__((noinline)) int foo(void) { return bar() + 1; } int main() { return foo(); } $ gcc -ggdb3 -Wall -Wextra -O2 -o jmp-to-fn jmp-to-fn.c $ objdump -d jmp-to-fn <SNIP> 0000000000001040 <main>: 1040: 31 c0 xor %eax,%eax 1042: e9 09 01 00 00 jmpq 1150 <foo> <SNIP> 0000000000001140 <bar>: 1140: b8 ff ff ff ff mov $0xffffffff,%eax 1145: c3 retq <SNIP> 0000000000001150 <foo>: 1150: 31 c0 xor %eax,%eax 1152: e8 e9 ff ff ff callq 1140 <bar> 1157: 83 c0 01 add $0x1,%eax 115a: c3 retq <SNIP> $ perf record -o jmp-to-fn.perf.data -e intel_pt/cyc/u ./jmp-to-fn [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0,017 MB jmp-to-fn.perf.data ] $ perf script -i jmp-to-fn.perf.data --itrace=be -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py jmp-to-fn.db branches calls 2019-01-08 13:24:58.783069 Creating database... 2019-01-08 13:24:58.794650 Writing records... 2019-01-08 13:24:59.008050 Adding indexes 2019-01-08 13:24:59.015802 Done $ ~/libexec/perf-core/scripts/python/exported-sql-viewer.py jmp-to-fn.db Before: main -> bar After: main -> foo -> bar Committer testing: Install the python2-pyside package, then select these menu options on the GUI: "Reports" "Context sensitive callgraphs" Then go on expanding the symbols, to get, full picture when doing this on a fedora:29 with gcc version 8.2.1 20181215 (Red Hat 8.2.1-6) (GCC): jmp-to-fn PID:TID _start (ld-2.28.so) __libc_start_main main foo bar To verify that indeed, this fixes the problem. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20190109091835.5570-5-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-09 16:18:33 +07:00
* CALL_RETURN_NON_CALL: a branch but not a 'call' to the start of a different
* symbol
*/
enum {
CALL_RETURN_NO_CALL = 1 << 0,
CALL_RETURN_NO_RETURN = 1 << 1,
perf thread-stack: Represent jmps to the start of a different symbol The compiler might optimize a call/ret combination by making it a jmp. However the thread-stack does not presently cater for that, so that such control flow is not visible in the call graph. Make it visible by recording on the stack a branch to the start of a different symbol. Note, that means when a ret pops the stack, all jmps must be popped off first. Example: $ cat jmp-to-fn.c __attribute__((noinline)) int bar(void) { return -1; } __attribute__((noinline)) int foo(void) { return bar() + 1; } int main() { return foo(); } $ gcc -ggdb3 -Wall -Wextra -O2 -o jmp-to-fn jmp-to-fn.c $ objdump -d jmp-to-fn <SNIP> 0000000000001040 <main>: 1040: 31 c0 xor %eax,%eax 1042: e9 09 01 00 00 jmpq 1150 <foo> <SNIP> 0000000000001140 <bar>: 1140: b8 ff ff ff ff mov $0xffffffff,%eax 1145: c3 retq <SNIP> 0000000000001150 <foo>: 1150: 31 c0 xor %eax,%eax 1152: e8 e9 ff ff ff callq 1140 <bar> 1157: 83 c0 01 add $0x1,%eax 115a: c3 retq <SNIP> $ perf record -o jmp-to-fn.perf.data -e intel_pt/cyc/u ./jmp-to-fn [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0,017 MB jmp-to-fn.perf.data ] $ perf script -i jmp-to-fn.perf.data --itrace=be -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py jmp-to-fn.db branches calls 2019-01-08 13:24:58.783069 Creating database... 2019-01-08 13:24:58.794650 Writing records... 2019-01-08 13:24:59.008050 Adding indexes 2019-01-08 13:24:59.015802 Done $ ~/libexec/perf-core/scripts/python/exported-sql-viewer.py jmp-to-fn.db Before: main -> bar After: main -> foo -> bar Committer testing: Install the python2-pyside package, then select these menu options on the GUI: "Reports" "Context sensitive callgraphs" Then go on expanding the symbols, to get, full picture when doing this on a fedora:29 with gcc version 8.2.1 20181215 (Red Hat 8.2.1-6) (GCC): jmp-to-fn PID:TID _start (ld-2.28.so) __libc_start_main main foo bar To verify that indeed, this fixes the problem. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20190109091835.5570-5-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-01-09 16:18:33 +07:00
CALL_RETURN_NON_CALL = 1 << 2,
};
/**
* struct call_return - paired call/return information.
* @thread: thread in which call/return occurred
* @comm: comm in which call/return occurred
* @cp: call path
* @call_time: timestamp of call (if known)
* @return_time: timestamp of return (if known)
* @branch_count: number of branches seen between call and return
* @insn_count: approx. number of instructions between call and return
* @cyc_count: approx. number of cycles between call and return
* @call_ref: external reference to 'call' sample (e.g. db_id)
* @return_ref: external reference to 'return' sample (e.g. db_id)
* @db_id: id used for db-export
* @parent_db_id: id of parent call used for db-export
* @flags: Call/Return flags
*/
struct call_return {
struct thread *thread;
struct comm *comm;
struct call_path *cp;
u64 call_time;
u64 return_time;
u64 branch_count;
u64 insn_count;
u64 cyc_count;
u64 call_ref;
u64 return_ref;
u64 db_id;
u64 parent_db_id;
u32 flags;
};
perf script: Expose usage of the callchain db export via the python api This change allows python scripts to be able to utilize the recent changes to the db export api allowing the export of call_paths derived from sampled callchains. These call paths are also now associated with the samples from which they were derived. - This feature is enabled by setting "perf_db_export_callchains" to true - When enabled, samples that have callchain information will have the callchains exported via call_path_table - The call_path_id field is added to sample_table to enable association of samples with the corresponding callchain stored in the call paths table. A call_path_id of 0 will be exported if there is no corresponding callchain. - When "perf_db_export_callchains" and "perf_db_export_calls" are both set to True, the call path root data structure will be shared. This prevents duplicating of data and call path ids that would result from building two separate call path trees in memory. - The call_return_processor structure definition was relocated to the header file to make its contents visible to db-export.c. This enables the sharing of call path trees between the two features, as mentioned above. This change is visible to python scripts using the python db export api. The change is backwards compatible with scripts written against the previous API, assuming that the scripts model the sample_table function after the one in export-to-postgresql.py script by allowing for additional arguments to be added in the future. ie. using *x as the final argument of the sample_table function. Signed-off-by: Chris Phlipot <cphlipot0@gmail.com> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1461831551-12213-6-git-send-email-cphlipot0@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-28 15:19:10 +07:00
/**
* struct call_return_processor - provides a call-back to consume call-return
* information.
* @cpr: call path root
* @process: call-back that accepts call/return information
* @data: anonymous data for call-back
*/
struct call_return_processor {
struct call_path_root *cpr;
int (*process)(struct call_return *cr, u64 *parent_db_id, void *data);
perf script: Expose usage of the callchain db export via the python api This change allows python scripts to be able to utilize the recent changes to the db export api allowing the export of call_paths derived from sampled callchains. These call paths are also now associated with the samples from which they were derived. - This feature is enabled by setting "perf_db_export_callchains" to true - When enabled, samples that have callchain information will have the callchains exported via call_path_table - The call_path_id field is added to sample_table to enable association of samples with the corresponding callchain stored in the call paths table. A call_path_id of 0 will be exported if there is no corresponding callchain. - When "perf_db_export_callchains" and "perf_db_export_calls" are both set to True, the call path root data structure will be shared. This prevents duplicating of data and call path ids that would result from building two separate call path trees in memory. - The call_return_processor structure definition was relocated to the header file to make its contents visible to db-export.c. This enables the sharing of call path trees between the two features, as mentioned above. This change is visible to python scripts using the python db export api. The change is backwards compatible with scripts written against the previous API, assuming that the scripts model the sample_table function after the one in export-to-postgresql.py script by allowing for additional arguments to be added in the future. ie. using *x as the final argument of the sample_table function. Signed-off-by: Chris Phlipot <cphlipot0@gmail.com> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/1461831551-12213-6-git-send-email-cphlipot0@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2016-04-28 15:19:10 +07:00
void *data;
};
int thread_stack__event(struct thread *thread, int cpu, u32 flags, u64 from_ip,
u64 to_ip, u16 insn_len, u64 trace_nr);
void thread_stack__set_trace_nr(struct thread *thread, int cpu, u64 trace_nr);
void thread_stack__sample(struct thread *thread, int cpu, struct ip_callchain *chain,
size_t sz, u64 ip, u64 kernel_start);
int thread_stack__flush(struct thread *thread);
void thread_stack__free(struct thread *thread);
size_t thread_stack__depth(struct thread *thread, int cpu);
struct call_return_processor *
call_return_processor__new(int (*process)(struct call_return *cr, u64 *parent_db_id, void *data),
void *data);
void call_return_processor__free(struct call_return_processor *crp);
int thread_stack__process(struct thread *thread, struct comm *comm,
struct perf_sample *sample,
struct addr_location *from_al,
struct addr_location *to_al, u64 ref,
struct call_return_processor *crp);
#endif