| H A D | thread-stack.c | 3c0cd952 Wed Jan 09 03:18:35 CST 2019 Adrian Hunter <adrian.hunter@intel.com> perf thread-stack: Hide x86 retpolines
x86 retpoline functions pollute the call graph by showing up everywhere
there is an indirect branch, but they do not really mean anything. Make
changes so that the default retpoline functions will no longer appear in
the call graph. Note this only affects the call graph, since all the
original branches are left unchanged.
This does not handle function return thunks, nor is there any
improvement for the handling of inline thunks or extern thunks.
Example:
$ cat simple-retpoline.c
__attribute__((noinline)) int bar(void)
{
return -1;
}
int foo(void)
{
return bar() + 1;
}
__attribute__((indirect_branch("thunk"))) int main()
{
int (*volatile fn)(void) = foo;
fn();
return fn();
}
$ gcc -ggdb3 -Wall -Wextra -O2 -o simple-retpoline simple-retpoline.c
$ objdump -d simple-retpoline
<SNIP>
0000000000001040 <main>:
1040: 48 83 ec 18 sub $0x18,%rsp
1044: 48 8d 05 25 01 00 00 lea 0x125(%rip),%rax # 1170 <foo>
104b: 48 89 44 24 08 mov %rax,0x8(%rsp)
1050: 48 8b 44 24 08 mov 0x8(%rsp),%rax
1055: e8 1f 01 00 00 callq 1179 <__x86_indirect_thunk_rax>
105a: 48 8b 44 24 08 mov 0x8(%rsp),%rax
105f: 48 83 c4 18 add $0x18,%rsp
1063: e9 11 01 00 00 jmpq 1179 <__x86_indirect_thunk_rax>
<SNIP>
0000000000001160 <bar>:
1160: b8 ff ff ff ff mov $0xffffffff,%eax
1165: c3 retq
<SNIP>
0000000000001170 <foo>:
1170: e8 eb ff ff ff callq 1160 <bar>
1175: 83 c0 01 add $0x1,%eax
1178: c3 retq
0000000000001179 <__x86_indirect_thunk_rax>:
1179: e8 07 00 00 00 callq 1185 <__x86_indirect_thunk_rax+0xc>
117e: f3 90 pause
1180: 0f ae e8 lfence
1183: eb f9 jmp 117e <__x86_indirect_thunk_rax+0x5>
1185: 48 89 04 24 mov %rax,(%rsp)
1189: c3 retq
<SNIP>
$ perf record -o simple-retpoline.perf.data -e intel_pt/cyc/u ./simple-retpoline
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0,017 MB simple-retpoline.perf.data ]
$ perf script -i simple-retpoline.perf.data --itrace=be -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py simple-retpoline.db branches calls
2019-01-08 14:03:37.851655 Creating database...
2019-01-08 14:03:37.863256 Writing records...
2019-01-08 14:03:38.069750 Adding indexes
2019-01-08 14:03:38.078799 Done
$ ~/libexec/perf-core/scripts/python/exported-sql-viewer.py simple-retpoline.db
Before:
main
-> __x86_indirect_thunk_rax
-> __x86_indirect_thunk_rax
-> foo
-> bar
After:
main
-> foo
-> bar
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/20190109091835.5570-7-adrian.hunter@intel.com
[ Remove (sym->name != NULL) test, this is not a pointer and breaks the build with clang version 7.0.1 (Fedora 7.0.1-2.fc30) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
3c0cd952 Wed Jan 09 03:18:35 CST 2019 Adrian Hunter <adrian.hunter@intel.com> perf thread-stack: Hide x86 retpolines
x86 retpoline functions pollute the call graph by showing up everywhere
there is an indirect branch, but they do not really mean anything. Make
changes so that the default retpoline functions will no longer appear in
the call graph. Note this only affects the call graph, since all the
original branches are left unchanged.
This does not handle function return thunks, nor is there any
improvement for the handling of inline thunks or extern thunks.
Example:
$ cat simple-retpoline.c
__attribute__((noinline)) int bar(void)
{
return -1;
}
int foo(void)
{
return bar() + 1;
}
__attribute__((indirect_branch("thunk"))) int main()
{
int (*volatile fn)(void) = foo;
fn();
return fn();
}
$ gcc -ggdb3 -Wall -Wextra -O2 -o simple-retpoline simple-retpoline.c
$ objdump -d simple-retpoline
<SNIP>
0000000000001040 <main>:
1040: 48 83 ec 18 sub $0x18,%rsp
1044: 48 8d 05 25 01 00 00 lea 0x125(%rip),%rax # 1170 <foo>
104b: 48 89 44 24 08 mov %rax,0x8(%rsp)
1050: 48 8b 44 24 08 mov 0x8(%rsp),%rax
1055: e8 1f 01 00 00 callq 1179 <__x86_indirect_thunk_rax>
105a: 48 8b 44 24 08 mov 0x8(%rsp),%rax
105f: 48 83 c4 18 add $0x18,%rsp
1063: e9 11 01 00 00 jmpq 1179 <__x86_indirect_thunk_rax>
<SNIP>
0000000000001160 <bar>:
1160: b8 ff ff ff ff mov $0xffffffff,%eax
1165: c3 retq
<SNIP>
0000000000001170 <foo>:
1170: e8 eb ff ff ff callq 1160 <bar>
1175: 83 c0 01 add $0x1,%eax
1178: c3 retq
0000000000001179 <__x86_indirect_thunk_rax>:
1179: e8 07 00 00 00 callq 1185 <__x86_indirect_thunk_rax+0xc>
117e: f3 90 pause
1180: 0f ae e8 lfence
1183: eb f9 jmp 117e <__x86_indirect_thunk_rax+0x5>
1185: 48 89 04 24 mov %rax,(%rsp)
1189: c3 retq
<SNIP>
$ perf record -o simple-retpoline.perf.data -e intel_pt/cyc/u ./simple-retpoline
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0,017 MB simple-retpoline.perf.data ]
$ perf script -i simple-retpoline.perf.data --itrace=be -s ~/libexec/perf-core/scripts/python/export-to-sqlite.py simple-retpoline.db branches calls
2019-01-08 14:03:37.851655 Creating database...
2019-01-08 14:03:37.863256 Writing records...
2019-01-08 14:03:38.069750 Adding indexes
2019-01-08 14:03:38.078799 Done
$ ~/libexec/perf-core/scripts/python/exported-sql-viewer.py simple-retpoline.db
Before:
main
-> __x86_indirect_thunk_rax
-> __x86_indirect_thunk_rax
-> foo
-> bar
After:
main
-> foo
-> bar
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/20190109091835.5570-7-adrian.hunter@intel.com
[ Remove (sym->name != NULL) test, this is not a pointer and breaks the build with clang version 7.0.1 (Fedora 7.0.1-2.fc30) ]
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
|