OpenCloudOS-Kernel/tools/perf/util/map.c

975 lines
21 KiB
C
Raw Normal View History

License cleanup: add SPDX GPL-2.0 license identifier to files with no license Many source files in the tree are missing licensing information, which makes it harder for compliance tools to determine the correct license. By default all files without license information are under the default license of the kernel, which is GPL version 2. Update the files which contain no license information with the 'GPL-2.0' SPDX license identifier. The SPDX identifier is a legally binding shorthand, which can be used instead of the full boiler plate text. This patch is based on work done by Thomas Gleixner and Kate Stewart and Philippe Ombredanne. How this work was done: Patches were generated and checked against linux-4.14-rc6 for a subset of the use cases: - file had no licensing information it it. - file was a */uapi/* one with no licensing information in it, - file was a */uapi/* one with existing licensing information, Further patches will be generated in subsequent months to fix up cases where non-standard license headers were used, and references to license had to be inferred by heuristics based on keywords. The analysis to determine which SPDX License Identifier to be applied to a file was done in a spreadsheet of side by side results from of the output of two independent scanners (ScanCode & Windriver) producing SPDX tag:value files created by Philippe Ombredanne. Philippe prepared the base worksheet, and did an initial spot review of a few 1000 files. The 4.13 kernel was the starting point of the analysis with 60,537 files assessed. Kate Stewart did a file by file comparison of the scanner results in the spreadsheet to determine which SPDX license identifier(s) to be applied to the file. She confirmed any determination that was not immediately clear with lawyers working with the Linux Foundation. Criteria used to select files for SPDX license identifier tagging was: - Files considered eligible had to be source code files. - Make and config files were included as candidates if they contained >5 lines of source - File already had some variant of a license header in it (even if <5 lines). All documentation files were explicitly excluded. The following heuristics were used to determine which SPDX license identifiers to apply. - when both scanners couldn't find any license traces, file was considered to have no license information in it, and the top level COPYING file license applied. For non */uapi/* files that summary was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 11139 and resulted in the first patch in this series. If that file was a */uapi/* path one, it was "GPL-2.0 WITH Linux-syscall-note" otherwise it was "GPL-2.0". Results of that was: SPDX license identifier # files ---------------------------------------------------|------- GPL-2.0 WITH Linux-syscall-note 930 and resulted in the second patch in this series. - if a file had some form of licensing information in it, and was one of the */uapi/* ones, it was denoted with the Linux-syscall-note if any GPL family license was found in the file or had no licensing in it (per prior point). Results summary: SPDX license identifier # files ---------------------------------------------------|------ GPL-2.0 WITH Linux-syscall-note 270 GPL-2.0+ WITH Linux-syscall-note 169 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-2-Clause) 21 ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) 17 LGPL-2.1+ WITH Linux-syscall-note 15 GPL-1.0+ WITH Linux-syscall-note 14 ((GPL-2.0+ WITH Linux-syscall-note) OR BSD-3-Clause) 5 LGPL-2.0+ WITH Linux-syscall-note 4 LGPL-2.1 WITH Linux-syscall-note 3 ((GPL-2.0 WITH Linux-syscall-note) OR MIT) 3 ((GPL-2.0 WITH Linux-syscall-note) AND MIT) 1 and that resulted in the third patch in this series. - when the two scanners agreed on the detected license(s), that became the concluded license(s). - when there was disagreement between the two scanners (one detected a license but the other didn't, or they both detected different licenses) a manual inspection of the file occurred. - In most cases a manual inspection of the information in the file resulted in a clear resolution of the license that should apply (and which scanner probably needed to revisit its heuristics). - When it was not immediately clear, the license identifier was confirmed with lawyers working with the Linux Foundation. - If there was any question as to the appropriate license identifier, the file was flagged for further research and to be revisited later in time. In total, over 70 hours of logged manual review was done on the spreadsheet to determine the SPDX license identifiers to apply to the source files by Kate, Philippe, Thomas and, in some cases, confirmation by lawyers working with the Linux Foundation. Kate also obtained a third independent scan of the 4.13 code base from FOSSology, and compared selected files where the other two scanners disagreed against that SPDX file, to see if there was new insights. The Windriver scanner is based on an older version of FOSSology in part, so they are related. Thomas did random spot checks in about 500 files from the spreadsheets for the uapi headers and agreed with SPDX license identifier in the files he inspected. For the non-uapi files Thomas did random spot checks in about 15000 files. In initial set of patches against 4.14-rc6, 3 files were found to have copy/paste license identifier errors, and have been fixed to reflect the correct identifier. Additionally Philippe spent 10 hours this week doing a detailed manual inspection and review of the 12,461 patched files from the initial patch version early this week with: - a full scancode scan run, collecting the matched texts, detected license ids and scores - reviewing anything where there was a license detected (about 500+ files) to ensure that the applied SPDX license was correct - reviewing anything where there was no detection but the patch license was not GPL-2.0 WITH Linux-syscall-note to ensure that the applied SPDX license was correct This produced a worksheet with 20 files needing minor correction. This worksheet was then exported into 3 different .csv files for the different types of files to be modified. These .csv files were then reviewed by Greg. Thomas wrote a script to parse the csv files and add the proper SPDX tag to the file, in the format that the file expected. This script was further refined by Greg based on the output to detect more types of files automatically and to distinguish between header and source .c files (which need different comment types.) Finally Greg ran the script using the .csv files to generate the patches. Reviewed-by: Kate Stewart <kstewart@linuxfoundation.org> Reviewed-by: Philippe Ombredanne <pombredanne@nexb.com> Reviewed-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2017-11-01 22:07:57 +08:00
// SPDX-License-Identifier: GPL-2.0
#include "symbol.h"
perf map: Fix overlapped map handling Whenever an mmap/mmap2 event occurs, the map tree must be updated to add a new entry. If a new map overlaps a previous map, the overlapped section of the previous map is effectively unmapped, but the non-overlapping sections are still valid. maps__fixup_overlappings() is responsible for creating any new map entries from the previously overlapped map. It optionally creates a before and an after map. When creating the after map the existing code failed to adjust the map.pgoff. This meant the new after map would incorrectly calculate the file offset for the ip. This results in incorrect symbol name resolution for any ip in the after region. Make maps__fixup_overlappings() correctly populate map.pgoff. Add an assert that new mapping matches old mapping at the beginning of the after map. Committer-testing: Validated correct parsing of libcoreclr.so symbols from .NET Core 3.0 preview9 (which didn't strip symbols). Preparation: ~/dotnet3.0-preview9/dotnet new webapi -o perfSymbol cd perfSymbol ~/dotnet3.0-preview9/dotnet publish perf record ~/dotnet3.0-preview9/dotnet \ bin/Debug/netcoreapp3.0/publish/perfSymbol.dll ^C Before: perf script --show-mmap-events 2>&1 | grep -e MMAP -e unknown |\ grep libcoreclr.so | head -n 4 dotnet 1907 373352.698780: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615726000(0x768000) @ 0 08:02 5510620 765057155]: \ r-xp .../3.0.0-preview9-19423-09/libcoreclr.so dotnet 1907 373352.701091: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615974000(0x1000) @ 0x24e000 08:02 5510620 765057155]: \ rwxp .../3.0.0-preview9-19423-09/libcoreclr.so dotnet 1907 373352.701241: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615c42000(0x1000) @ 0x51c000 08:02 5510620 765057155]: \ rwxp .../3.0.0-preview9-19423-09/libcoreclr.so dotnet 1907 373352.705249: 250000 cpu-clock: \ 7fe6159a1f99 [unknown] \ (.../3.0.0-preview9-19423-09/libcoreclr.so) After: perf script --show-mmap-events 2>&1 | grep -e MMAP -e unknown |\ grep libcoreclr.so | head -n 4 dotnet 1907 373352.698780: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615726000(0x768000) @ 0 08:02 5510620 765057155]: \ r-xp .../3.0.0-preview9-19423-09/libcoreclr.so dotnet 1907 373352.701091: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615974000(0x1000) @ 0x24e000 08:02 5510620 765057155]: \ rwxp .../3.0.0-preview9-19423-09/libcoreclr.so dotnet 1907 373352.701241: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615c42000(0x1000) @ 0x51c000 08:02 5510620 765057155]: \ rwxp .../3.0.0-preview9-19423-09/libcoreclr.so All the [unknown] symbols were resolved. Signed-off-by: Steve MacLean <Steve.MacLean@Microsoft.com> Tested-by: Brian Robbins <brianrob@microsoft.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Eric Saint-Etienne <eric.saint.etienne@oracle.com> Cc: John Keeping <john@metanate.com> Cc: John Salem <josalem@microsoft.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tom McDonald <thomas.mcdonald@microsoft.com> Link: http://lore.kernel.org/lkml/BN8PR21MB136270949F22A6A02335C238F7800@BN8PR21MB1362.namprd21.prod.outlook.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-28 09:39:00 +08:00
#include <assert.h>
#include <errno.h>
#include <inttypes.h>
#include <limits.h>
#include <stdlib.h>
#include <string.h>
#include <stdio.h>
#include <unistd.h>
#include <uapi/linux/mman.h> /* To get things like MAP_HUGETLB even on older libc headers */
#include "dso.h"
#include "map.h"
#include "map_symbol.h"
#include "thread.h"
perf tools: Back [vdso] DSO with real data Storing data for VDSO shared object, because we need it for the post unwind processing. The VDSO shared object is same for all process on a running system, so it makes no difference when we store it inside the tracer - perf. When [vdso] map memory is hit, we retrieve [vdso] DSO image and store it into temporary file. During the build-id processing phase, the [vdso] DSO image is stored in build-id db, and build-id reference is made inside perf.data. The build-id vdso file object is called '[vdso]'. We don't use temporary file name which gets removed when record is finished. During report phase the vdso build-id object is treated as any other build-id DSO object. Adding following API for vdso object: bool is_vdso_map(const char *filename) - returns true if the filename matches vdso map name struct dso *vdso__dso_findnew(struct list_head *head) - find/create proper vdso DSO object vdso__exit(void) - removes temporary VDSO image if there's any This change makes backtrace dwarf post unwind possible from [vdso] maps. Following output is current report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00007fff3ace89af | --- 0x7fff3ace89af Following output is new report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00000000000009af | --- 0x7fff3ace89af main __libc_start_main _start Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1347295819-23177-5-git-send-email-jolsa@redhat.com [ committer note: s/ALIGN/PERF_ALIGN/g to cope with the android build changes ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:50:19 +08:00
#include "vdso.h"
#include "build-id.h"
#include "debug.h"
#include "machine.h"
#include <linux/string.h>
#include <linux/zalloc.h>
#include "srcline.h"
#include "namespaces.h"
#include "unwind.h"
perf tools: Support 'srccode' output When looking at PT or brstackinsn traces with 'perf script' it can be very useful to see the source code. This adds a simple facility to print them with 'perf script', if the information is available through dwarf % perf record ... % perf script -F insn,ip,sym,srccode ... 4004c6 main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004c6 main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004b3 main 6 v++; % perf record -b ... % perf script -F insn,ip,sym,srccode,brstackinsn ... main+22: 0000000000400543 insn: e8 ca ff ff ff # PRED |18 f1(); f1: 0000000000400512 insn: 55 |10 { 0000000000400513 insn: 48 89 e5 0000000000400516 insn: b8 00 00 00 00 |11 f2(); 000000000040051b insn: e8 d6 ff ff ff # PRED f2: 00000000004004f6 insn: 55 |5 { 00000000004004f7 insn: 48 89 e5 00000000004004fa insn: 8b 05 2c 0b 20 00 |6 c = a / b; 0000000000400500 insn: 8b 0d 2a 0b 20 00 0000000000400506 insn: 99 0000000000400507 insn: f7 f9 0000000000400509 insn: 89 05 29 0b 20 00 000000000040050f insn: 90 |7 } 0000000000400510 insn: 5d 0000000000400511 insn: c3 # PRED f1+14: 0000000000400520 insn: b8 00 00 00 00 |12 f2(); 0000000000400525 insn: e8 cc ff ff ff # PRED f2: 00000000004004f6 insn: 55 |5 { 00000000004004f7 insn: 48 89 e5 00000000004004fa insn: 8b 05 2c 0b 20 00 |6 c = a / b; Not supported for callchains currently, would need some layout changes there. Committer notes: Fixed the build on Alpine Linux (3.4 .. 3.8) by addressing this warning: In file included from util/srccode.c:19:0: /usr/include/sys/fcntl.h:1:2: error: #warning redirecting incorrect #include <sys/fcntl.h> to <fcntl.h> [-Werror=cpp] #warning redirecting incorrect #include <sys/fcntl.h> to <fcntl.h> ^~~~~~~ cc1: all warnings being treated as errors Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20181204001848.24769-1-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-04 08:18:48 +08:00
#include "srccode.h"
#include "ui/ui.h"
static void __maps__insert(struct maps *maps, struct map *map);
static inline int is_anon_memory(const char *filename, u32 flags)
{
return flags & MAP_HUGETLB ||
!strcmp(filename, "//anon") ||
!strncmp(filename, "/dev/zero", sizeof("/dev/zero") - 1) ||
!strncmp(filename, "/anon_hugepage", sizeof("/anon_hugepage") - 1);
}
static inline int is_no_dso_memory(const char *filename)
{
perf tools: Fix detection of stack area Output of /proc/<pid>/maps contains helpful information to anonymous mappings like stack, heap, ... For the case of stack, it can show multiple stack area for each thread in the process: $ cat /proc/$(pidof gnome-shell)/maps | grep stack 7fe019946000-7fe01a146000 rw-p 00000000 00:00 0 [stack:1624] 7fe040e32000-7fe041632000 rw-p 00000000 00:00 0 [stack:1451] 7fe041643000-7fe041e43000 rw-p 00000000 00:00 0 [stack:1450] 7fe04204b000-7fe04284b000 rw-p 00000000 00:00 0 [stack:1449] 7fe042a7e000-7fe04327e000 rw-p 00000000 00:00 0 [stack:1446] 7fe0432ff000-7fe043aff000 rw-p 00000000 00:00 0 [stack:1445] 7fe043b00000-7fe044300000 rw-p 00000000 00:00 0 [stack:1444] 7fe044301000-7fe044b01000 rw-p 00000000 00:00 0 [stack:1443] 7fe044b02000-7fe045302000 rw-p 00000000 00:00 0 [stack:1442] 7fe045303000-7fe045b03000 rw-p 00000000 00:00 0 [stack:1441] 7fe045b04000-7fe046304000 rw-p 00000000 00:00 0 [stack:1440] 7fe046305000-7fe046b05000 rw-p 00000000 00:00 0 [stack:1439] 7fe046b06000-7fe047306000 rw-p 00000000 00:00 0 [stack:1438] 7fff4b16f000-7fff4b190000 rw-p 00000000 00:00 0 [stack] However perf only knew about the main thread's. Fix it. Signed-off-by: Namhyung Kim <namhyung@kernel.org> Cc: Andi Kleen <ak@linux.intel.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1352273234-28912-4-git-send-email-namhyung@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-11-07 15:27:11 +08:00
return !strncmp(filename, "[stack", 6) ||
!strncmp(filename, "/SYSV",5) ||
!strcmp(filename, "[heap]");
}
static inline int is_android_lib(const char *filename)
{
return strstarts(filename, "/data/app-lib/") ||
strstarts(filename, "/system/lib/");
}
static inline bool replace_android_lib(const char *filename, char *newfilename)
{
const char *libname;
char *app_abi;
size_t app_abi_length, new_length;
size_t lib_length = 0;
libname = strrchr(filename, '/');
if (libname)
lib_length = strlen(libname);
app_abi = getenv("APP_ABI");
if (!app_abi)
return false;
app_abi_length = strlen(app_abi);
if (strstarts(filename, "/data/app-lib/")) {
char *apk_path;
if (!app_abi_length)
return false;
new_length = 7 + app_abi_length + lib_length;
apk_path = getenv("APK_PATH");
if (apk_path) {
new_length += strlen(apk_path) + 1;
if (new_length > PATH_MAX)
return false;
snprintf(newfilename, new_length,
"%s/libs/%s/%s", apk_path, app_abi, libname);
} else {
if (new_length > PATH_MAX)
return false;
snprintf(newfilename, new_length,
"libs/%s/%s", app_abi, libname);
}
return true;
}
if (strstarts(filename, "/system/lib/")) {
char *ndk, *app;
const char *arch;
size_t ndk_length;
size_t app_length;
ndk = getenv("NDK_ROOT");
app = getenv("APP_PLATFORM");
if (!(ndk && app))
return false;
ndk_length = strlen(ndk);
app_length = strlen(app);
if (!(ndk_length && app_length && app_abi_length))
return false;
arch = !strncmp(app_abi, "arm", 3) ? "arm" :
!strncmp(app_abi, "mips", 4) ? "mips" :
!strncmp(app_abi, "x86", 3) ? "x86" : NULL;
if (!arch)
return false;
new_length = 27 + ndk_length +
app_length + lib_length
+ strlen(arch);
if (new_length > PATH_MAX)
return false;
snprintf(newfilename, new_length,
"%s/platforms/%s/arch-%s/usr/lib/%s",
ndk, app, arch, libname);
return true;
}
return false;
}
void map__init(struct map *map, u64 start, u64 end, u64 pgoff, struct dso *dso)
{
map->start = start;
map->end = end;
map->pgoff = pgoff;
map->reloc = 0;
map->dso = dso__get(dso);
map->map_ip = map__map_ip;
map->unmap_ip = map__unmap_ip;
RB_CLEAR_NODE(&map->rb_node);
map->erange_warned = false;
refcount_set(&map->refcnt, 1);
}
struct map *map__new(struct machine *machine, u64 start, u64 len,
u64 pgoff, struct dso_id *id,
u32 prot, u32 flags, char *filename,
struct thread *thread)
{
struct map *map = malloc(sizeof(*map));
struct nsinfo *nsi = NULL;
struct nsinfo *nnsi;
if (map != NULL) {
char newfilename[PATH_MAX];
struct dso *dso;
int anon, no_dso, vdso, android;
android = is_android_lib(filename);
anon = is_anon_memory(filename, flags);
perf tools: Back [vdso] DSO with real data Storing data for VDSO shared object, because we need it for the post unwind processing. The VDSO shared object is same for all process on a running system, so it makes no difference when we store it inside the tracer - perf. When [vdso] map memory is hit, we retrieve [vdso] DSO image and store it into temporary file. During the build-id processing phase, the [vdso] DSO image is stored in build-id db, and build-id reference is made inside perf.data. The build-id vdso file object is called '[vdso]'. We don't use temporary file name which gets removed when record is finished. During report phase the vdso build-id object is treated as any other build-id DSO object. Adding following API for vdso object: bool is_vdso_map(const char *filename) - returns true if the filename matches vdso map name struct dso *vdso__dso_findnew(struct list_head *head) - find/create proper vdso DSO object vdso__exit(void) - removes temporary VDSO image if there's any This change makes backtrace dwarf post unwind possible from [vdso] maps. Following output is current report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00007fff3ace89af | --- 0x7fff3ace89af Following output is new report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00000000000009af | --- 0x7fff3ace89af main __libc_start_main _start Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1347295819-23177-5-git-send-email-jolsa@redhat.com [ committer note: s/ALIGN/PERF_ALIGN/g to cope with the android build changes ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:50:19 +08:00
vdso = is_vdso_map(filename);
no_dso = is_no_dso_memory(filename);
map->prot = prot;
map->flags = flags;
nsi = nsinfo__get(thread->nsinfo);
if ((anon || no_dso) && nsi && (prot & PROT_EXEC)) {
snprintf(newfilename, sizeof(newfilename),
"/tmp/perf-%d.map", nsi->pid);
filename = newfilename;
}
if (android) {
if (replace_android_lib(filename, newfilename))
filename = newfilename;
}
perf tools: Back [vdso] DSO with real data Storing data for VDSO shared object, because we need it for the post unwind processing. The VDSO shared object is same for all process on a running system, so it makes no difference when we store it inside the tracer - perf. When [vdso] map memory is hit, we retrieve [vdso] DSO image and store it into temporary file. During the build-id processing phase, the [vdso] DSO image is stored in build-id db, and build-id reference is made inside perf.data. The build-id vdso file object is called '[vdso]'. We don't use temporary file name which gets removed when record is finished. During report phase the vdso build-id object is treated as any other build-id DSO object. Adding following API for vdso object: bool is_vdso_map(const char *filename) - returns true if the filename matches vdso map name struct dso *vdso__dso_findnew(struct list_head *head) - find/create proper vdso DSO object vdso__exit(void) - removes temporary VDSO image if there's any This change makes backtrace dwarf post unwind possible from [vdso] maps. Following output is current report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00007fff3ace89af | --- 0x7fff3ace89af Following output is new report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00000000000009af | --- 0x7fff3ace89af main __libc_start_main _start Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1347295819-23177-5-git-send-email-jolsa@redhat.com [ committer note: s/ALIGN/PERF_ALIGN/g to cope with the android build changes ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:50:19 +08:00
if (vdso) {
/* The vdso maps are always on the host and not the
* container. Ensure that we don't use setns to look
* them up.
*/
nnsi = nsinfo__copy(nsi);
if (nnsi) {
nsinfo__put(nsi);
nnsi->need_setns = false;
nsi = nnsi;
}
perf tools: Back [vdso] DSO with real data Storing data for VDSO shared object, because we need it for the post unwind processing. The VDSO shared object is same for all process on a running system, so it makes no difference when we store it inside the tracer - perf. When [vdso] map memory is hit, we retrieve [vdso] DSO image and store it into temporary file. During the build-id processing phase, the [vdso] DSO image is stored in build-id db, and build-id reference is made inside perf.data. The build-id vdso file object is called '[vdso]'. We don't use temporary file name which gets removed when record is finished. During report phase the vdso build-id object is treated as any other build-id DSO object. Adding following API for vdso object: bool is_vdso_map(const char *filename) - returns true if the filename matches vdso map name struct dso *vdso__dso_findnew(struct list_head *head) - find/create proper vdso DSO object vdso__exit(void) - removes temporary VDSO image if there's any This change makes backtrace dwarf post unwind possible from [vdso] maps. Following output is current report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00007fff3ace89af | --- 0x7fff3ace89af Following output is new report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00000000000009af | --- 0x7fff3ace89af main __libc_start_main _start Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1347295819-23177-5-git-send-email-jolsa@redhat.com [ committer note: s/ALIGN/PERF_ALIGN/g to cope with the android build changes ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:50:19 +08:00
pgoff = 0;
dso = machine__findnew_vdso(machine, thread);
perf tools: Back [vdso] DSO with real data Storing data for VDSO shared object, because we need it for the post unwind processing. The VDSO shared object is same for all process on a running system, so it makes no difference when we store it inside the tracer - perf. When [vdso] map memory is hit, we retrieve [vdso] DSO image and store it into temporary file. During the build-id processing phase, the [vdso] DSO image is stored in build-id db, and build-id reference is made inside perf.data. The build-id vdso file object is called '[vdso]'. We don't use temporary file name which gets removed when record is finished. During report phase the vdso build-id object is treated as any other build-id DSO object. Adding following API for vdso object: bool is_vdso_map(const char *filename) - returns true if the filename matches vdso map name struct dso *vdso__dso_findnew(struct list_head *head) - find/create proper vdso DSO object vdso__exit(void) - removes temporary VDSO image if there's any This change makes backtrace dwarf post unwind possible from [vdso] maps. Following output is current report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00007fff3ace89af | --- 0x7fff3ace89af Following output is new report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00000000000009af | --- 0x7fff3ace89af main __libc_start_main _start Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1347295819-23177-5-git-send-email-jolsa@redhat.com [ committer note: s/ALIGN/PERF_ALIGN/g to cope with the android build changes ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:50:19 +08:00
} else
perf dso: Move dso_id from 'struct map' to 'struct dso' And take it into account when looking up DSOs when we have the dso_id fields obtained from somewhere, like from PERF_RECORD_MMAP2 records. Instances of struct map pointing to the same DSO pathname but with anything in dso_id different are in fact different DSOs, so better have different 'struct dso' instances to reflect that. At some point we may want to get copies of the contents of the different objects if we want to do correct annotation or other analysis. With this we get 'struct map' 24 bytes leaner: $ pahole -C map ~/bin/perf struct map { union { struct rb_node rb_node __attribute__((__aligned__(8))); /* 0 24 */ struct list_head node; /* 0 16 */ } __attribute__((__aligned__(8))); /* 0 24 */ u64 start; /* 24 8 */ u64 end; /* 32 8 */ _Bool erange_warned:1; /* 40: 0 1 */ _Bool priv:1; /* 40: 1 1 */ /* XXX 6 bits hole, try to pack */ /* XXX 3 bytes hole, try to pack */ u32 prot; /* 44 4 */ u64 pgoff; /* 48 8 */ u64 reloc; /* 56 8 */ /* --- cacheline 1 boundary (64 bytes) --- */ u64 (*map_ip)(struct map *, u64); /* 64 8 */ u64 (*unmap_ip)(struct map *, u64); /* 72 8 */ struct dso * dso; /* 80 8 */ refcount_t refcnt; /* 88 4 */ u32 flags; /* 92 4 */ /* size: 96, cachelines: 2, members: 13 */ /* sum members: 92, holes: 1, sum holes: 3 */ /* sum bitfield members: 2 bits, bit holes: 1, sum bit holes: 6 bits */ /* forced alignments: 1 */ /* last cacheline: 32 bytes */ } __attribute__((__aligned__(8))); $ Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-g4hxxmraplo7wfjmk384mfsb@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-20 05:44:22 +08:00
dso = machine__findnew_dso_id(machine, filename, id);
perf tools: Back [vdso] DSO with real data Storing data for VDSO shared object, because we need it for the post unwind processing. The VDSO shared object is same for all process on a running system, so it makes no difference when we store it inside the tracer - perf. When [vdso] map memory is hit, we retrieve [vdso] DSO image and store it into temporary file. During the build-id processing phase, the [vdso] DSO image is stored in build-id db, and build-id reference is made inside perf.data. The build-id vdso file object is called '[vdso]'. We don't use temporary file name which gets removed when record is finished. During report phase the vdso build-id object is treated as any other build-id DSO object. Adding following API for vdso object: bool is_vdso_map(const char *filename) - returns true if the filename matches vdso map name struct dso *vdso__dso_findnew(struct list_head *head) - find/create proper vdso DSO object vdso__exit(void) - removes temporary VDSO image if there's any This change makes backtrace dwarf post unwind possible from [vdso] maps. Following output is current report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00007fff3ace89af | --- 0x7fff3ace89af Following output is new report of [vdso] sample dwarf backtrace: # Overhead Command Shared Object Symbol # ........ ....... ................. ............................. # 99.52% ex [vdso] [.] 0x00000000000009af | --- 0x7fff3ace89af main __libc_start_main _start Signed-off-by: Jiri Olsa <jolsa@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1347295819-23177-5-git-send-email-jolsa@redhat.com [ committer note: s/ALIGN/PERF_ALIGN/g to cope with the android build changes ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-09-11 00:50:19 +08:00
if (dso == NULL)
goto out_delete;
map__init(map, start, start + len, pgoff, dso);
if (anon || no_dso) {
map->map_ip = map->unmap_ip = identity__map_ip;
/*
* Set memory without DSO as loaded. All map__find_*
* functions still return NULL, and we avoid the
* unnecessary map__load warning.
*/
if (!(prot & PROT_EXEC))
dso__set_loaded(dso);
}
dso->nsinfo = nsi;
dso__put(dso);
}
return map;
out_delete:
nsinfo__put(nsi);
free(map);
return NULL;
}
/*
* Constructor variant for modules (where we know from /proc/modules where
* they are loaded) and for vmlinux, where only after we load all the
* symbols we'll know where it starts and ends.
*/
struct map *map__new2(u64 start, struct dso *dso)
{
struct map *map = calloc(1, (sizeof(*map) +
(dso->kernel ? sizeof(struct kmap) : 0)));
if (map != NULL) {
/*
* ->end will be filled after we load all the symbols
*/
map__init(map, start, 0, 0, dso);
}
return map;
}
bool __map__is_kernel(const struct map *map)
{
if (!map->dso->kernel)
return false;
return machine__kernel_map(map__kmaps((struct map *)map)->machine) == map;
}
bool __map__is_extra_kernel_map(const struct map *map)
{
struct kmap *kmap = __map__kmap((struct map *)map);
return kmap && kmap->name[0];
}
bool __map__is_bpf_prog(const struct map *map)
{
const char *name;
if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO)
return true;
/*
* If PERF_RECORD_BPF_EVENT is not included, the dso will not have
* type of DSO_BINARY_TYPE__BPF_PROG_INFO. In such cases, we can
* guess the type based on name.
*/
name = map->dso->short_name;
return name && (strstr(name, "bpf_prog_") == name);
}
bool __map__is_bpf_image(const struct map *map)
{
const char *name;
if (map->dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE)
return true;
/*
* If PERF_RECORD_KSYMBOL is not included, the dso will not have
* type of DSO_BINARY_TYPE__BPF_IMAGE. In such cases, we can
* guess the type based on name.
*/
name = map->dso->short_name;
return name && is_bpf_image(name);
}
bool __map__is_ool(const struct map *map)
{
return map->dso && map->dso->binary_type == DSO_BINARY_TYPE__OOL;
}
bool map__has_symbols(const struct map *map)
{
return dso__has_symbols(map->dso);
}
static void map__exit(struct map *map)
{
BUG_ON(refcount_read(&map->refcnt) != 0);
dso__zput(map->dso);
}
void map__delete(struct map *map)
{
map__exit(map);
free(map);
}
void map__put(struct map *map)
{
if (map && refcount_dec_and_test(&map->refcnt))
map__delete(map);
}
void map__fixup_start(struct map *map)
{
struct rb_root_cached *symbols = &map->dso->symbols;
struct rb_node *nd = rb_first_cached(symbols);
if (nd != NULL) {
struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
map->start = sym->start;
}
}
void map__fixup_end(struct map *map)
{
struct rb_root_cached *symbols = &map->dso->symbols;
struct rb_node *nd = rb_last(&symbols->rb_root);
if (nd != NULL) {
struct symbol *sym = rb_entry(nd, struct symbol, rb_node);
map->end = sym->end;
}
}
#define DSO__DELETED "(deleted)"
int map__load(struct map *map)
{
const char *name = map->dso->long_name;
int nr;
if (dso__loaded(map->dso))
return 0;
nr = dso__load(map->dso, map);
if (nr < 0) {
if (map->dso->has_build_id) {
char sbuild_id[SBUILD_ID_SIZE];
build_id__sprintf(map->dso->build_id,
sizeof(map->dso->build_id),
sbuild_id);
pr_debug("%s with build id %s not found", name, sbuild_id);
} else
pr_debug("Failed to open %s", name);
pr_debug(", continuing without symbols\n");
return -1;
} else if (nr == 0) {
#ifdef HAVE_LIBELF_SUPPORT
const size_t len = strlen(name);
const size_t real_len = len - sizeof(DSO__DELETED);
if (len > sizeof(DSO__DELETED) &&
strcmp(name + real_len + 1, DSO__DELETED) == 0) {
pr_debug("%.*s was updated (is prelink enabled?). "
"Restart the long running apps that use it!\n",
(int)real_len, name);
} else {
pr_debug("no symbols found in %s, maybe install a debug package?\n", name);
}
#endif
return -1;
}
return 0;
}
struct symbol *map__find_symbol(struct map *map, u64 addr)
{
if (map__load(map) < 0)
return NULL;
return dso__find_symbol(map->dso, addr);
}
struct symbol *map__find_symbol_by_name(struct map *map, const char *name)
{
if (map__load(map) < 0)
return NULL;
if (!dso__sorted_by_name(map->dso))
dso__sort_by_name(map->dso);
return dso__find_symbol_by_name(map->dso, name);
}
struct map *map__clone(struct map *from)
{
size_t size = sizeof(struct map);
struct map *map;
if (from->dso && from->dso->kernel)
size += sizeof(struct kmap);
map = memdup(from, size);
if (map != NULL) {
refcount_set(&map->refcnt, 1);
RB_CLEAR_NODE(&map->rb_node);
dso__get(map->dso);
}
return map;
}
size_t map__fprintf(struct map *map, FILE *fp)
{
return fprintf(fp, " %" PRIx64 "-%" PRIx64 " %" PRIx64 " %s\n",
map->start, map->end, map->pgoff, map->dso->name);
}
perf annotate: Fix it for non-prelinked *.so The problem was we were incorrectly calculating objdump addresses for sym->start and sym->end, look: For simple ET_DYN type DSO (*.so) with one function, objdump -dS output is something like this: 000004ac <my_strlen>: int my_strlen(const char *s) 4ac: 55 push %ebp 4ad: 89 e5 mov %esp,%ebp 4af: 83 ec 10 sub $0x10,%esp { i.e. we have relative-to-dso-mapping IPs (=RIP) there. For ET_EXEC type and probably for prelinked libs as well (sorry can't test - I don't use prelink) objdump outputs absolute IPs, e.g. 08048604 <zz_strlen>: extern "C" int zz_strlen(const char *s) 8048604: 55 push %ebp 8048605: 89 e5 mov %esp,%ebp 8048607: 83 ec 10 sub $0x10,%esp { So, if sym->start is always relative to dso mapping(*), we'll have to unmap it for ET_EXEC like cases, and leave as is for ET_DYN cases. (*) and it is - we've explicitely made it relative. Look for adjust_symbols handling in dso__load_sym() Previously we were always unmapping sym->start and for ET_DYN dsos resulting addresses were wrong, and so objdump output was empty. The end result was that perf annotate output for symbols from non-prelinked *.so had always 0.00% percents only, which is wrong. To fix it, let's introduce a helper for converting rip to objdump address, and also let's document what map_ip() and unmap_ip() do -- I had to study sources for several hours to understand it. Signed-off-by: Kirill Smelkov <kirr@landau.phys.spbu.ru> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1265223128-11786-8-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-04 02:52:07 +08:00
size_t map__fprintf_dsoname(struct map *map, FILE *fp)
{
perf script: Pad DSO name for --call-trace Pad the DSO name in --call-trace so we don't have the indent screwed by different DSO name lengths, as now for kernel there's also BPF code displayed. # perf-with-kcore record pt -e intel_pt//ku -- sleep 1 # perf-core/perf-with-kcore script pt --call-trace Before: sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) kretprobe_perf_func sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) trace_call_bpf sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_get_current_pid_tgid sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_ktime_get_ns sleep 3660 [16] 57036.806464725: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806465045: (bpf_prog_da4fe6b3d2c29b25_trace_return) __htab_map_lookup_elem sleep 3660 [16] 57036.806465366: ([kernel.kallsyms]) memcmp sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_get_current_uid_gid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms]) from_kgid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms]) from_kuid sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) perf_prepare_sample sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) perf_misc_flags sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806466328: ([kvm]) kvm_is_in_guest sleep 3660 [16] 57036.806466649: ([kernel.kallsyms]) __perf_event_header__init_id.isra.0 sleep 3660 [16] 57036.806466649: ([kernel.kallsyms]) perf_output_begin After: sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) kretprobe_perf_func sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) trace_call_bpf sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_get_current_pid_tgid sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_ktime_get_ns sleep 3660 [16] 57036.806464725: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806465045: (bpf_prog_da4fe6b3d2c29b25_trace_return ) __htab_map_lookup_elem sleep 3660 [16] 57036.806465366: ([kernel.kallsyms] ) memcmp sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_get_current_uid_gid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms] ) from_kgid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms] ) from_kuid sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) perf_prepare_sample sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) perf_misc_flags sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) __x86_indirect_thunk_rax Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stanislav Fomichev <sdf@google.com> Link: http://lkml.kernel.org/r/20190508132010.14512-8-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-05-08 21:20:05 +08:00
char buf[symbol_conf.pad_output_len_dso + 1];
const char *dsoname = "[unknown]";
if (map && map->dso) {
if (symbol_conf.show_kernel_path && map->dso->long_name)
dsoname = map->dso->long_name;
else
dsoname = map->dso->name;
}
perf script: Pad DSO name for --call-trace Pad the DSO name in --call-trace so we don't have the indent screwed by different DSO name lengths, as now for kernel there's also BPF code displayed. # perf-with-kcore record pt -e intel_pt//ku -- sleep 1 # perf-core/perf-with-kcore script pt --call-trace Before: sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) kretprobe_perf_func sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) trace_call_bpf sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464404: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_get_current_pid_tgid sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_ktime_get_ns sleep 3660 [16] 57036.806464725: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806465045: (bpf_prog_da4fe6b3d2c29b25_trace_return) __htab_map_lookup_elem sleep 3660 [16] 57036.806465366: ([kernel.kallsyms]) memcmp sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms]) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_get_current_uid_gid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms]) from_kgid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms]) from_kuid sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return) bpf_perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) perf_prepare_sample sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) perf_misc_flags sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806466328: ([kernel.kallsyms]) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806466328: ([kvm]) kvm_is_in_guest sleep 3660 [16] 57036.806466649: ([kernel.kallsyms]) __perf_event_header__init_id.isra.0 sleep 3660 [16] 57036.806466649: ([kernel.kallsyms]) perf_output_begin After: sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) kretprobe_perf_func sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) trace_call_bpf sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464404: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_get_current_pid_tgid sleep 3660 [16] 57036.806464725: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_ktime_get_ns sleep 3660 [16] 57036.806464725: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806464725: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806465045: (bpf_prog_da4fe6b3d2c29b25_trace_return ) __htab_map_lookup_elem sleep 3660 [16] 57036.806465366: ([kernel.kallsyms] ) memcmp sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806465687: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_probe_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) probe_kernel_read sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) __check_object_size sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) check_stack_object sleep 3660 [16] 57036.806465687: ([kernel.kallsyms] ) copy_user_enhanced_fast_string sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_get_current_uid_gid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms] ) from_kgid sleep 3660 [16] 57036.806466008: ([kernel.kallsyms] ) from_kuid sleep 3660 [16] 57036.806466008: (bpf_prog_da4fe6b3d2c29b25_trace_return ) bpf_perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) perf_event_output sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) perf_prepare_sample sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) perf_misc_flags sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) __x86_indirect_thunk_rax sleep 3660 [16] 57036.806466328: ([kernel.kallsyms] ) __x86_indirect_thunk_rax Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Song Liu <songliubraving@fb.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stanislav Fomichev <sdf@google.com> Link: http://lkml.kernel.org/r/20190508132010.14512-8-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-05-08 21:20:05 +08:00
if (symbol_conf.pad_output_len_dso) {
scnprintf_pad(buf, symbol_conf.pad_output_len_dso, "%s", dsoname);
dsoname = buf;
}
return fprintf(fp, "%s", dsoname);
}
char *map__srcline(struct map *map, u64 addr, struct symbol *sym)
{
if (map == NULL)
return SRCLINE_UNKNOWN;
return get_srcline(map->dso, map__rip_2objdump(map, addr), sym, true, true, addr);
}
perf script: Add an option to print the source line number Add field 'srcline' that displays the source file name and line number associated with the sample ip. The information displayed is the same as from addr2line. $ perf script -f comm,tid,pid,time,ip,sym,dso,symoff,srcline grep 10701/10701 2497321.421013: ffffffff81043ffa native_write_msr_safe+0xa ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/arch/x86/include/asm/msr.h:95 grep 10701/10701 2497321.421984: ffffffff8165b6b3 _raw_spin_lock+0x13 ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/arch/x86/include/asm/spinlock.h:54 grep 10701/10701 2497321.421990: ffffffff810b64b3 tick_sched_timer+0x53 ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/kernel/time/tick-sched.c:840 grep 10701/10701 2497321.421992: ffffffff8106f63f run_timer_softirq+0x2f ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/kernel/timer.c:1372 Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1386315778-11633-3-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-12-06 15:42:57 +08:00
int map__fprintf_srcline(struct map *map, u64 addr, const char *prefix,
FILE *fp)
{
int ret = 0;
if (map && map->dso) {
char *srcline = map__srcline(map, addr, NULL);
perf diff: Fix undefined string comparison spotted by clang's -Wstring-compare clang warns: util/block-info.c:298:18: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:51: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:18: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/block-info.c:298:51: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if ((start_line != SRCLINE_UNKNOWN) && (end_line != SRCLINE_UNKNOWN)) { ^ ~~~~~~~~~~~~~~~ util/map.c:434:15: error: result of comparison against a string literal is unspecified (use an explicit string comparison function instead) [-Werror,-Wstring-compare] if (srcline != SRCLINE_UNKNOWN) ^ ~~~~~~~~~~~~~~~ Reviewer Notes: Looks good to me. Some more context: https://clang.llvm.org/docs/DiagnosticsReference.html#wstring-compare The spec says: J.1 Unspecified behavior The following are unspecified: .. Whether two string literals result in distinct arrays (6.4.5). Signed-off-by: Nick Desaulniers <nick.desaulniers@gmail.com> Reviewed-by: Ian Rogers <irogers@google.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Changbin Du <changbin.du@intel.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: John Keeping <john@metanate.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: clang-built-linux@googlegroups.com Link: https://github.com/ClangBuiltLinux/linux/issues/900 Link: http://lore.kernel.org/lkml/20200223193456.25291-1-nick.desaulniers@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2020-02-24 03:34:49 +08:00
if (strncmp(srcline, SRCLINE_UNKNOWN, strlen(SRCLINE_UNKNOWN)) != 0)
perf script: Add an option to print the source line number Add field 'srcline' that displays the source file name and line number associated with the sample ip. The information displayed is the same as from addr2line. $ perf script -f comm,tid,pid,time,ip,sym,dso,symoff,srcline grep 10701/10701 2497321.421013: ffffffff81043ffa native_write_msr_safe+0xa ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/arch/x86/include/asm/msr.h:95 grep 10701/10701 2497321.421984: ffffffff8165b6b3 _raw_spin_lock+0x13 ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/arch/x86/include/asm/spinlock.h:54 grep 10701/10701 2497321.421990: ffffffff810b64b3 tick_sched_timer+0x53 ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/kernel/time/tick-sched.c:840 grep 10701/10701 2497321.421992: ffffffff8106f63f run_timer_softirq+0x2f ([kernel.kallsyms]) /usr/src/debug/kernel-3.9.fc17/linux-3.9.10-100.fc17.x86_64/kernel/timer.c:1372 Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1386315778-11633-3-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-12-06 15:42:57 +08:00
ret = fprintf(fp, "%s%s", prefix, srcline);
free_srcline(srcline);
}
return ret;
}
perf tools: Support 'srccode' output When looking at PT or brstackinsn traces with 'perf script' it can be very useful to see the source code. This adds a simple facility to print them with 'perf script', if the information is available through dwarf % perf record ... % perf script -F insn,ip,sym,srccode ... 4004c6 main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004c6 main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004cd main 5 for (i = 0; i < 10000000; i++) 4004b3 main 6 v++; % perf record -b ... % perf script -F insn,ip,sym,srccode,brstackinsn ... main+22: 0000000000400543 insn: e8 ca ff ff ff # PRED |18 f1(); f1: 0000000000400512 insn: 55 |10 { 0000000000400513 insn: 48 89 e5 0000000000400516 insn: b8 00 00 00 00 |11 f2(); 000000000040051b insn: e8 d6 ff ff ff # PRED f2: 00000000004004f6 insn: 55 |5 { 00000000004004f7 insn: 48 89 e5 00000000004004fa insn: 8b 05 2c 0b 20 00 |6 c = a / b; 0000000000400500 insn: 8b 0d 2a 0b 20 00 0000000000400506 insn: 99 0000000000400507 insn: f7 f9 0000000000400509 insn: 89 05 29 0b 20 00 000000000040050f insn: 90 |7 } 0000000000400510 insn: 5d 0000000000400511 insn: c3 # PRED f1+14: 0000000000400520 insn: b8 00 00 00 00 |12 f2(); 0000000000400525 insn: e8 cc ff ff ff # PRED f2: 00000000004004f6 insn: 55 |5 { 00000000004004f7 insn: 48 89 e5 00000000004004fa insn: 8b 05 2c 0b 20 00 |6 c = a / b; Not supported for callchains currently, would need some layout changes there. Committer notes: Fixed the build on Alpine Linux (3.4 .. 3.8) by addressing this warning: In file included from util/srccode.c:19:0: /usr/include/sys/fcntl.h:1:2: error: #warning redirecting incorrect #include <sys/fcntl.h> to <fcntl.h> [-Werror=cpp] #warning redirecting incorrect #include <sys/fcntl.h> to <fcntl.h> ^~~~~~~ cc1: all warnings being treated as errors Signed-off-by: Andi Kleen <ak@linux.intel.com> Tested-by: Jiri Olsa <jolsa@kernel.org> Link: http://lkml.kernel.org/r/20181204001848.24769-1-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-12-04 08:18:48 +08:00
void srccode_state_free(struct srccode_state *state)
{
zfree(&state->srcfile);
state->line = 0;
}
/**
* map__rip_2objdump - convert symbol start address to objdump address.
* @map: memory map
* @rip: symbol start address
*
perf annotate: Fix it for non-prelinked *.so The problem was we were incorrectly calculating objdump addresses for sym->start and sym->end, look: For simple ET_DYN type DSO (*.so) with one function, objdump -dS output is something like this: 000004ac <my_strlen>: int my_strlen(const char *s) 4ac: 55 push %ebp 4ad: 89 e5 mov %esp,%ebp 4af: 83 ec 10 sub $0x10,%esp { i.e. we have relative-to-dso-mapping IPs (=RIP) there. For ET_EXEC type and probably for prelinked libs as well (sorry can't test - I don't use prelink) objdump outputs absolute IPs, e.g. 08048604 <zz_strlen>: extern "C" int zz_strlen(const char *s) 8048604: 55 push %ebp 8048605: 89 e5 mov %esp,%ebp 8048607: 83 ec 10 sub $0x10,%esp { So, if sym->start is always relative to dso mapping(*), we'll have to unmap it for ET_EXEC like cases, and leave as is for ET_DYN cases. (*) and it is - we've explicitely made it relative. Look for adjust_symbols handling in dso__load_sym() Previously we were always unmapping sym->start and for ET_DYN dsos resulting addresses were wrong, and so objdump output was empty. The end result was that perf annotate output for symbols from non-prelinked *.so had always 0.00% percents only, which is wrong. To fix it, let's introduce a helper for converting rip to objdump address, and also let's document what map_ip() and unmap_ip() do -- I had to study sources for several hours to understand it. Signed-off-by: Kirill Smelkov <kirr@landau.phys.spbu.ru> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1265223128-11786-8-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-04 02:52:07 +08:00
* objdump wants/reports absolute IPs for ET_EXEC, and RIPs for ET_DYN.
* map->dso->adjust_symbols==1 for ET_EXEC-like cases except ET_REL which is
* relative to section start.
*
* Return: Address suitable for passing to "objdump --start-address="
perf annotate: Fix it for non-prelinked *.so The problem was we were incorrectly calculating objdump addresses for sym->start and sym->end, look: For simple ET_DYN type DSO (*.so) with one function, objdump -dS output is something like this: 000004ac <my_strlen>: int my_strlen(const char *s) 4ac: 55 push %ebp 4ad: 89 e5 mov %esp,%ebp 4af: 83 ec 10 sub $0x10,%esp { i.e. we have relative-to-dso-mapping IPs (=RIP) there. For ET_EXEC type and probably for prelinked libs as well (sorry can't test - I don't use prelink) objdump outputs absolute IPs, e.g. 08048604 <zz_strlen>: extern "C" int zz_strlen(const char *s) 8048604: 55 push %ebp 8048605: 89 e5 mov %esp,%ebp 8048607: 83 ec 10 sub $0x10,%esp { So, if sym->start is always relative to dso mapping(*), we'll have to unmap it for ET_EXEC like cases, and leave as is for ET_DYN cases. (*) and it is - we've explicitely made it relative. Look for adjust_symbols handling in dso__load_sym() Previously we were always unmapping sym->start and for ET_DYN dsos resulting addresses were wrong, and so objdump output was empty. The end result was that perf annotate output for symbols from non-prelinked *.so had always 0.00% percents only, which is wrong. To fix it, let's introduce a helper for converting rip to objdump address, and also let's document what map_ip() and unmap_ip() do -- I had to study sources for several hours to understand it. Signed-off-by: Kirill Smelkov <kirr@landau.phys.spbu.ru> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1265223128-11786-8-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-04 02:52:07 +08:00
*/
u64 map__rip_2objdump(struct map *map, u64 rip)
{
struct kmap *kmap = __map__kmap(map);
/*
* vmlinux does not have program headers for PTI entry trampolines and
* kcore may not either. However the trampoline object code is on the
* main kernel map, so just use that instead.
*/
if (kmap && is_entry_trampoline(kmap->name) && kmap->kmaps && kmap->kmaps->machine) {
struct map *kernel_map = machine__kernel_map(kmap->kmaps->machine);
if (kernel_map)
map = kernel_map;
}
if (!map->dso->adjust_symbols)
return rip;
if (map->dso->rel)
return rip - map->pgoff;
/*
* kernel modules also have DSO_TYPE_USER in dso->kernel,
* but all kernel modules are ET_REL, so won't get here.
*/
if (map->dso->kernel == DSO_SPACE__USER)
return rip + map->dso->text_offset;
return map->unmap_ip(map, rip) - map->reloc;
perf annotate: Fix it for non-prelinked *.so The problem was we were incorrectly calculating objdump addresses for sym->start and sym->end, look: For simple ET_DYN type DSO (*.so) with one function, objdump -dS output is something like this: 000004ac <my_strlen>: int my_strlen(const char *s) 4ac: 55 push %ebp 4ad: 89 e5 mov %esp,%ebp 4af: 83 ec 10 sub $0x10,%esp { i.e. we have relative-to-dso-mapping IPs (=RIP) there. For ET_EXEC type and probably for prelinked libs as well (sorry can't test - I don't use prelink) objdump outputs absolute IPs, e.g. 08048604 <zz_strlen>: extern "C" int zz_strlen(const char *s) 8048604: 55 push %ebp 8048605: 89 e5 mov %esp,%ebp 8048607: 83 ec 10 sub $0x10,%esp { So, if sym->start is always relative to dso mapping(*), we'll have to unmap it for ET_EXEC like cases, and leave as is for ET_DYN cases. (*) and it is - we've explicitely made it relative. Look for adjust_symbols handling in dso__load_sym() Previously we were always unmapping sym->start and for ET_DYN dsos resulting addresses were wrong, and so objdump output was empty. The end result was that perf annotate output for symbols from non-prelinked *.so had always 0.00% percents only, which is wrong. To fix it, let's introduce a helper for converting rip to objdump address, and also let's document what map_ip() and unmap_ip() do -- I had to study sources for several hours to understand it. Signed-off-by: Kirill Smelkov <kirr@landau.phys.spbu.ru> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1265223128-11786-8-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-04 02:52:07 +08:00
}
perf top: Fix annotate for userspace First, for programs and prelinked libraries, annotate code was fooled by objdump output IPs (src->eip in the code) being wrongly converted to absolute IPs. In such case there were no conversion needed, but in src->eip = strtoull(src->line, NULL, 16); src->eip = map->unmap_ip(map, src->eip); // = eip + map->start - map->pgoff we were reading absolute address from objdump (e.g. 8048604) and then almost doubling it, because eip & map->start are approximately close for small programs. Needless to say, that later, in record_precise_ip() there was no matching with real runtime IPs. And second, like with `perf annotate` the problem with non-prelinked *.so was that we were doing rip -> objdump address conversion wrong. Also, because unlike `perf annotate`, `perf top` code does annotation based on absolute IPs for performance reasons(*), new helper for mapping objdump addresse to IP is introduced. (*) we get samples info in absolute IPs, and since we do lots of hit-testing on absolute IPs at runtime in record_precise_ip(), it's better to convert objdump addresses to IPs once and do no conversion at runtime. I also had to fix how objdump output is parsed (with hardcoded 8/16 characters format, which was inappropriate for ET_DYN dsos with small addresses like '4ac') Also note, that not all objdump output lines has associtated IPs, e.g. look at source lines here: 000004ac <my_strlen>: extern "C" int my_strlen(const char *s) 4ac: 55 push %ebp 4ad: 89 e5 mov %esp,%ebp 4af: 83 ec 10 sub $0x10,%esp { int len = 0; 4b2: c7 45 fc 00 00 00 00 movl $0x0,-0x4(%ebp) 4b9: eb 08 jmp 4c3 <my_strlen+0x17> while (*s) { ++len; 4bb: 83 45 fc 01 addl $0x1,-0x4(%ebp) ++s; 4bf: 83 45 08 01 addl $0x1,0x8(%ebp) So we mark them with eip=0, and ignore such lines in annotate lookup code. Signed-off-by: Kirill Smelkov <kirr@landau.phys.spbu.ru> [ Note: one hunk of this patch was applied by Mike in 57d8188 ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Mike Galbraith <efault@gmx.de> LKML-Reference: <1265550376-12665-1-git-send-email-acme@infradead.org> Signed-off-by: Ingo Molnar <mingo@elte.hu>
2010-02-07 21:46:15 +08:00
/**
* map__objdump_2mem - convert objdump address to a memory address.
* @map: memory map
* @ip: objdump address
*
* Closely related to map__rip_2objdump(), this function takes an address from
* objdump and converts it to a memory address. Note this assumes that @map
* contains the address. To be sure the result is valid, check it forwards
* e.g. map__rip_2objdump(map->map_ip(map, map__objdump_2mem(map, ip))) == ip
*
* Return: Memory address.
*/
u64 map__objdump_2mem(struct map *map, u64 ip)
{
if (!map->dso->adjust_symbols)
return map->unmap_ip(map, ip);
if (map->dso->rel)
return map->unmap_ip(map, ip + map->pgoff);
/*
* kernel modules also have DSO_TYPE_USER in dso->kernel,
* but all kernel modules are ET_REL, so won't get here.
*/
if (map->dso->kernel == DSO_SPACE__USER)
return map->unmap_ip(map, ip - map->dso->text_offset);
return ip + map->reloc;
}
void maps__init(struct maps *maps, struct machine *machine)
{
maps->entries = RB_ROOT;
init_rwsem(&maps->lock);
maps->machine = machine;
maps->last_search_by_name = NULL;
maps->nr_maps = 0;
maps->maps_by_name = NULL;
refcount_set(&maps->refcnt, 1);
}
static void __maps__free_maps_by_name(struct maps *maps)
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
{
/*
* Free everything to try to do it from the rbtree in the next search
*/
zfree(&maps->maps_by_name);
maps->nr_maps_allocated = 0;
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
}
void maps__insert(struct maps *maps, struct map *map)
{
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
down_write(&maps->lock);
__maps__insert(maps, map);
++maps->nr_maps;
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
if (map->dso && map->dso->kernel) {
struct kmap *kmap = map__kmap(map);
if (kmap)
kmap->kmaps = maps;
else
pr_err("Internal error: kernel dso with non kernel map\n");
}
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
/*
* If we already performed some search by name, then we need to add the just
* inserted map and resort.
*/
if (maps->maps_by_name) {
if (maps->nr_maps > maps->nr_maps_allocated) {
int nr_allocate = maps->nr_maps * 2;
struct map **maps_by_name = realloc(maps->maps_by_name, nr_allocate * sizeof(map));
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
if (maps_by_name == NULL) {
__maps__free_maps_by_name(maps);
up_write(&maps->lock);
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
return;
}
maps->maps_by_name = maps_by_name;
maps->nr_maps_allocated = nr_allocate;
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
}
maps->maps_by_name[maps->nr_maps - 1] = map;
__maps__sort_by_name(maps);
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
}
up_write(&maps->lock);
}
static void __maps__remove(struct maps *maps, struct map *map)
{
rb_erase_init(&map->rb_node, &maps->entries);
map__put(map);
}
void maps__remove(struct maps *maps, struct map *map)
perf map_groups: Add a front end cache for map lookups by name Lets see if it helps: First look at the probeable lines for the function that does lookups by name in a map_groups struct: # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } 12 maps__for_each_entry(maps, map) 13 if (strcmp(map->dso->short_name, name) == 0) { 14 mg->last_search_by_name = map; 15 goto out_unlock; } 18 map = NULL; out_unlock: 21 up_read(&maps->lock); 22 return map; 23 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # Now add a probe to the place where we reuse the last search: # perf probe -x ~/bin/perf map_groups__find_by_name:8 Added new event: probe_perf:map_groups__find_by_name (on map_groups__find_by_name:8 in /home/acme/bin/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:map_groups__find_by_name -aR sleep 1 # Now lets do a system wide 'perf stat' counting those events: # perf stat -e probe_perf:* Leave it running and lets do a 'perf top', then, after a while, stop the 'perf stat': # perf stat -e probe_perf:* ^C Performance counter stats for 'system wide': 3,603 probe_perf:map_groups__find_by_name 44.565253139 seconds time elapsed # yeah, good to have. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-tcz37g3nxv3tvxw3q90vga3p@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-14 03:33:33 +08:00
{
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
down_write(&maps->lock);
if (maps->last_search_by_name == map)
maps->last_search_by_name = NULL;
perf map_groups: Add a front end cache for map lookups by name Lets see if it helps: First look at the probeable lines for the function that does lookups by name in a map_groups struct: # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } 12 maps__for_each_entry(maps, map) 13 if (strcmp(map->dso->short_name, name) == 0) { 14 mg->last_search_by_name = map; 15 goto out_unlock; } 18 map = NULL; out_unlock: 21 up_read(&maps->lock); 22 return map; 23 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # Now add a probe to the place where we reuse the last search: # perf probe -x ~/bin/perf map_groups__find_by_name:8 Added new event: probe_perf:map_groups__find_by_name (on map_groups__find_by_name:8 in /home/acme/bin/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:map_groups__find_by_name -aR sleep 1 # Now lets do a system wide 'perf stat' counting those events: # perf stat -e probe_perf:* Leave it running and lets do a 'perf top', then, after a while, stop the 'perf stat': # perf stat -e probe_perf:* ^C Performance counter stats for 'system wide': 3,603 probe_perf:map_groups__find_by_name 44.565253139 seconds time elapsed # yeah, good to have. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-tcz37g3nxv3tvxw3q90vga3p@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-14 03:33:33 +08:00
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
__maps__remove(maps, map);
--maps->nr_maps;
if (maps->maps_by_name)
__maps__free_maps_by_name(maps);
perf map_groups: Auto sort maps by name, if needed There are still lots of lookups by name, even if just when loading vmlinux, till that code is studied to figure out if its possible to do away with those map lookup by names, provide a way to sort it using libc's qsort/bsearch. Doing it at the first lookup defers the sorting a bit, and as the code stands now, is never done for user maps, just for the kernel ones. # perf probe -l # perf probe -x ~/bin/perf -L __map_groups__find_by_name <__map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 static struct map *__map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { struct map **mapp; 4 if (mg->maps_by_name == NULL && 5 map__groups__sort_by_name_from_rbtree(mg)) 6 return NULL; 8 mapp = bsearch(name, mg->maps_by_name, mg->nr_maps, sizeof(*mapp), map__strcmp_name); 9 if (mapp) 10 return *mapp; 11 return NULL; 12 } struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) { # perf probe -x ~/bin/perf 'found=__map_groups__find_by_name:10 name:string' Added new event: probe_perf:found (on __map_groups__find_by_name:10 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:found -aR sleep 1 # # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } /* * If we have mg->maps_by_name, then the name isn't in the rbtree, * as mg->maps_by_name mirrors the rbtree when lookups by name are * made. */ 16 map = __map_groups__find_by_name(mg, name); 17 if (map || mg->maps_by_name != NULL) 18 goto out_unlock; /* Fallback to traversing the rbtree... */ 21 maps__for_each_entry(maps, map) 22 if (strcmp(map->dso->short_name, name) == 0) { 23 mg->last_search_by_name = map; 24 goto out_unlock; } 27 map = NULL; out_unlock: 30 up_read(&maps->lock); 31 return map; 32 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # perf probe -x ~/bin/perf 'fallback=map_groups__find_by_name:21 name:string' Added new events: probe_perf:fallback (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) probe_perf:fallback_1 (on map_groups__find_by_name:21 in /home/acme/bin/perf with name:string) You can now use it in all perf tools, such as: perf record -e probe_perf:fallback_1 -aR sleep 1 # # perf probe -l probe_perf:fallback (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:fallback_1 (on map_groups__find_by_name:21@util/symbol.c in /home/acme/bin/perf with name_string) probe_perf:found (on __map_groups__find_by_name:10@util/symbol.c in /home/acme/bin/perf with name_string) # # perf stat -e probe_perf:* Now run 'perf top' in another term and then, after a while, stop 'perf stat': Furthermore, if we ask for interval printing, we can see that that is done just at the start of the workload: # perf stat -I1000 -e probe_perf:* # time counts unit events 1.000319513 0 probe_perf:found 1.000319513 0 probe_perf:fallback_1 1.000319513 0 probe_perf:fallback 2.001868092 23,251 probe_perf:found 2.001868092 0 probe_perf:fallback_1 2.001868092 0 probe_perf:fallback 3.002901597 0 probe_perf:found 3.002901597 0 probe_perf:fallback_1 3.002901597 0 probe_perf:fallback 4.003358591 0 probe_perf:found 4.003358591 0 probe_perf:fallback_1 4.003358591 0 probe_perf:fallback ^C # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-c5lmbyr14x448rcfii7y6t3k@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-17 22:38:13 +08:00
up_write(&maps->lock);
perf map_groups: Add a front end cache for map lookups by name Lets see if it helps: First look at the probeable lines for the function that does lookups by name in a map_groups struct: # perf probe -x ~/bin/perf -L map_groups__find_by_name <map_groups__find_by_name@/home/acme/git/perf/tools/perf/util/symbol.c:0> 0 struct map *map_groups__find_by_name(struct map_groups *mg, const char *name) 1 { 2 struct maps *maps = &mg->maps; struct map *map; 5 down_read(&maps->lock); 7 if (mg->last_search_by_name && strcmp(mg->last_search_by_name->dso->short_name, name) == 0) { 8 map = mg->last_search_by_name; 9 goto out_unlock; } 12 maps__for_each_entry(maps, map) 13 if (strcmp(map->dso->short_name, name) == 0) { 14 mg->last_search_by_name = map; 15 goto out_unlock; } 18 map = NULL; out_unlock: 21 up_read(&maps->lock); 22 return map; 23 } int dso__load_vmlinux(struct dso *dso, struct map *map, const char *vmlinux, bool vmlinux_allocated) # Now add a probe to the place where we reuse the last search: # perf probe -x ~/bin/perf map_groups__find_by_name:8 Added new event: probe_perf:map_groups__find_by_name (on map_groups__find_by_name:8 in /home/acme/bin/perf) You can now use it in all perf tools, such as: perf record -e probe_perf:map_groups__find_by_name -aR sleep 1 # Now lets do a system wide 'perf stat' counting those events: # perf stat -e probe_perf:* Leave it running and lets do a 'perf top', then, after a while, stop the 'perf stat': # perf stat -e probe_perf:* ^C Performance counter stats for 'system wide': 3,603 probe_perf:map_groups__find_by_name 44.565253139 seconds time elapsed # yeah, good to have. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: https://lkml.kernel.org/n/tip-tcz37g3nxv3tvxw3q90vga3p@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-11-14 03:33:33 +08:00
}
static void __maps__purge(struct maps *maps)
{
struct map *pos, *next;
maps__for_each_entry_safe(maps, pos, next) {
rb_erase_init(&pos->rb_node, &maps->entries);
map__put(pos);
}
}
void maps__exit(struct maps *maps)
{
down_write(&maps->lock);
__maps__purge(maps);
up_write(&maps->lock);
}
bool maps__empty(struct maps *maps)
{
return !maps__first(maps);
}
struct maps *maps__new(struct machine *machine)
{
struct maps *maps = zalloc(sizeof(*maps));
if (maps != NULL)
maps__init(maps, machine);
return maps;
}
void maps__delete(struct maps *maps)
{
maps__exit(maps);
unwind__finish_access(maps);
free(maps);
}
void maps__put(struct maps *maps)
{
if (maps && refcount_dec_and_test(&maps->refcnt))
maps__delete(maps);
}
struct symbol *maps__find_symbol(struct maps *maps, u64 addr, struct map **mapp)
{
struct map *map = maps__find(maps, addr);
/* Ensure map is loaded before using map->map_ip */
if (map != NULL && map__load(map) >= 0) {
if (mapp != NULL)
*mapp = map;
return map__find_symbol(map, map->map_ip(map, addr));
}
return NULL;
}
static bool map__contains_symbol(struct map *map, struct symbol *sym)
{
u64 ip = map->unmap_ip(map, sym->start);
return ip >= map->start && ip < map->end;
}
struct symbol *maps__find_symbol_by_name(struct maps *maps, const char *name, struct map **mapp)
{
struct symbol *sym;
struct map *pos;
down_read(&maps->lock);
maps__for_each_entry(maps, pos) {
sym = map__find_symbol_by_name(pos, name);
if (sym == NULL)
continue;
if (!map__contains_symbol(pos, sym)) {
sym = NULL;
continue;
}
if (mapp != NULL)
*mapp = pos;
goto out;
}
sym = NULL;
out:
up_read(&maps->lock);
return sym;
}
int maps__find_ams(struct maps *maps, struct addr_map_symbol *ams)
{
if (ams->addr < ams->ms.map->start || ams->addr >= ams->ms.map->end) {
if (maps == NULL)
return -1;
ams->ms.map = maps__find(maps, ams->addr);
if (ams->ms.map == NULL)
return -1;
}
ams->al_addr = ams->ms.map->map_ip(ams->ms.map, ams->addr);
ams->ms.sym = map__find_symbol(ams->ms.map, ams->al_addr);
return ams->ms.sym ? 0 : -1;
}
size_t maps__fprintf(struct maps *maps, FILE *fp)
{
size_t printed = 0;
struct map *pos;
down_read(&maps->lock);
maps__for_each_entry(maps, pos) {
printed += fprintf(fp, "Map:");
printed += map__fprintf(pos, fp);
if (verbose > 2) {
printed += dso__fprintf(pos->dso, fp);
printed += fprintf(fp, "--\n");
}
}
up_read(&maps->lock);
return printed;
}
int maps__fixup_overlappings(struct maps *maps, struct map *map, FILE *fp)
{
struct rb_root *root;
struct rb_node *next, *first;
int err = 0;
down_write(&maps->lock);
root = &maps->entries;
/*
* Find first map where end > map->start.
* Same as find_vma() in kernel.
*/
next = root->rb_node;
first = NULL;
while (next) {
struct map *pos = rb_entry(next, struct map, rb_node);
if (pos->end > map->start) {
first = next;
if (pos->start <= map->start)
break;
next = next->rb_left;
} else
next = next->rb_right;
}
next = first;
while (next) {
struct map *pos = rb_entry(next, struct map, rb_node);
next = rb_next(&pos->rb_node);
/*
* Stop if current map starts after map->end.
* Maps are ordered by start: next will not overlap for sure.
*/
if (pos->start >= map->end)
break;
if (verbose >= 2) {
if (use_browser) {
pr_debug("overlapping maps in %s (disable tui for more info)\n",
map->dso->name);
} else {
fputs("overlapping maps:\n", fp);
map__fprintf(map, fp);
map__fprintf(pos, fp);
}
}
rb_erase_init(&pos->rb_node, root);
/*
* Now check if we need to create new maps for areas not
* overlapped by the new map:
*/
if (map->start > pos->start) {
struct map *before = map__clone(pos);
if (before == NULL) {
err = -ENOMEM;
goto put_map;
}
before->end = map->start;
__maps__insert(maps, before);
if (verbose >= 2 && !use_browser)
map__fprintf(before, fp);
perf tools: Fix maps__fixup_overlappings to put used maps Since the __map_groups__insert got the given map, we don't need to keep it. So put the maps. Refcnt debugger shows that map_groups__fixup_overlappings() got a map twice but the group released it just once. This pattern usually indicates the leak happens in caller site. ---- ==== [0] ==== Unreclaimed map@0x39d3ae0 Refcount +1 => 1 at ./perf(map_groups__fixup_overlappings+0x335) [0x4c1865] ./perf(thread__insert_map+0x30) [0x4c8e00] ./perf(machine__process_mmap2_event+0x106) [0x4bd876] ./perf() [0x4c378e] ./perf() [0x4c4393] ./perf(perf_session__process_events+0x38a) [0x4c654a] ./perf(cmd_record+0xe24) [0x42fc94] ./perf() [0x47b745] ./perf(main+0x617) [0x422547] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f2eca2deaf5] ./perf() [0x4226bd] Refcount +1 => 2 at ./perf(map_groups__fixup_overlappings+0x3c5) [0x4c18f5] ./perf(thread__insert_map+0x30) [0x4c8e00] ./perf(machine__process_mmap2_event+0x106) [0x4bd876] ./perf() [0x4c378e] ./perf() [0x4c4393] ./perf(perf_session__process_events+0x38a) [0x4c654a] ./perf(cmd_record+0xe24) [0x42fc94] ./perf() [0x47b745] ./perf(main+0x617) [0x422547] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f2eca2deaf5] ./perf() [0x4226bd] Refcount -1 => 1 at ./perf(map_groups__exit+0x92) [0x4c0962] ./perf(map_groups__put+0x60) [0x4c0bc0] ./perf(thread__put+0x90) [0x4c8a40] ./perf(machine__delete_threads+0x7e) [0x4bad9e] ./perf(perf_session__delete+0x4f) [0x4c499f] ./perf(cmd_record+0xb6d) [0x42f9dd] ./perf() [0x47b745] ./perf(main+0x617) [0x422547] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f2eca2deaf5] ./perf() [0x4226bd] ---- Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20151209021131.10245.41485.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-12-09 10:11:31 +08:00
map__put(before);
}
if (map->end < pos->end) {
struct map *after = map__clone(pos);
if (after == NULL) {
err = -ENOMEM;
goto put_map;
}
after->start = map->end;
perf map: Fix overlapped map handling Whenever an mmap/mmap2 event occurs, the map tree must be updated to add a new entry. If a new map overlaps a previous map, the overlapped section of the previous map is effectively unmapped, but the non-overlapping sections are still valid. maps__fixup_overlappings() is responsible for creating any new map entries from the previously overlapped map. It optionally creates a before and an after map. When creating the after map the existing code failed to adjust the map.pgoff. This meant the new after map would incorrectly calculate the file offset for the ip. This results in incorrect symbol name resolution for any ip in the after region. Make maps__fixup_overlappings() correctly populate map.pgoff. Add an assert that new mapping matches old mapping at the beginning of the after map. Committer-testing: Validated correct parsing of libcoreclr.so symbols from .NET Core 3.0 preview9 (which didn't strip symbols). Preparation: ~/dotnet3.0-preview9/dotnet new webapi -o perfSymbol cd perfSymbol ~/dotnet3.0-preview9/dotnet publish perf record ~/dotnet3.0-preview9/dotnet \ bin/Debug/netcoreapp3.0/publish/perfSymbol.dll ^C Before: perf script --show-mmap-events 2>&1 | grep -e MMAP -e unknown |\ grep libcoreclr.so | head -n 4 dotnet 1907 373352.698780: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615726000(0x768000) @ 0 08:02 5510620 765057155]: \ r-xp .../3.0.0-preview9-19423-09/libcoreclr.so dotnet 1907 373352.701091: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615974000(0x1000) @ 0x24e000 08:02 5510620 765057155]: \ rwxp .../3.0.0-preview9-19423-09/libcoreclr.so dotnet 1907 373352.701241: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615c42000(0x1000) @ 0x51c000 08:02 5510620 765057155]: \ rwxp .../3.0.0-preview9-19423-09/libcoreclr.so dotnet 1907 373352.705249: 250000 cpu-clock: \ 7fe6159a1f99 [unknown] \ (.../3.0.0-preview9-19423-09/libcoreclr.so) After: perf script --show-mmap-events 2>&1 | grep -e MMAP -e unknown |\ grep libcoreclr.so | head -n 4 dotnet 1907 373352.698780: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615726000(0x768000) @ 0 08:02 5510620 765057155]: \ r-xp .../3.0.0-preview9-19423-09/libcoreclr.so dotnet 1907 373352.701091: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615974000(0x1000) @ 0x24e000 08:02 5510620 765057155]: \ rwxp .../3.0.0-preview9-19423-09/libcoreclr.so dotnet 1907 373352.701241: PERF_RECORD_MMAP2 1907/1907: \ [0x7fe615c42000(0x1000) @ 0x51c000 08:02 5510620 765057155]: \ rwxp .../3.0.0-preview9-19423-09/libcoreclr.so All the [unknown] symbols were resolved. Signed-off-by: Steve MacLean <Steve.MacLean@Microsoft.com> Tested-by: Brian Robbins <brianrob@microsoft.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Andi Kleen <ak@linux.intel.com> Cc: Davidlohr Bueso <dave@stgolabs.net> Cc: Eric Saint-Etienne <eric.saint.etienne@oracle.com> Cc: John Keeping <john@metanate.com> Cc: John Salem <josalem@microsoft.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Song Liu <songliubraving@fb.com> Cc: Stephane Eranian <eranian@google.com> Cc: Tom McDonald <thomas.mcdonald@microsoft.com> Link: http://lore.kernel.org/lkml/BN8PR21MB136270949F22A6A02335C238F7800@BN8PR21MB1362.namprd21.prod.outlook.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-09-28 09:39:00 +08:00
after->pgoff += map->end - pos->start;
assert(pos->map_ip(pos, map->end) == after->map_ip(after, map->end));
__maps__insert(maps, after);
if (verbose >= 2 && !use_browser)
map__fprintf(after, fp);
perf tools: Fix maps__fixup_overlappings to put used maps Since the __map_groups__insert got the given map, we don't need to keep it. So put the maps. Refcnt debugger shows that map_groups__fixup_overlappings() got a map twice but the group released it just once. This pattern usually indicates the leak happens in caller site. ---- ==== [0] ==== Unreclaimed map@0x39d3ae0 Refcount +1 => 1 at ./perf(map_groups__fixup_overlappings+0x335) [0x4c1865] ./perf(thread__insert_map+0x30) [0x4c8e00] ./perf(machine__process_mmap2_event+0x106) [0x4bd876] ./perf() [0x4c378e] ./perf() [0x4c4393] ./perf(perf_session__process_events+0x38a) [0x4c654a] ./perf(cmd_record+0xe24) [0x42fc94] ./perf() [0x47b745] ./perf(main+0x617) [0x422547] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f2eca2deaf5] ./perf() [0x4226bd] Refcount +1 => 2 at ./perf(map_groups__fixup_overlappings+0x3c5) [0x4c18f5] ./perf(thread__insert_map+0x30) [0x4c8e00] ./perf(machine__process_mmap2_event+0x106) [0x4bd876] ./perf() [0x4c378e] ./perf() [0x4c4393] ./perf(perf_session__process_events+0x38a) [0x4c654a] ./perf(cmd_record+0xe24) [0x42fc94] ./perf() [0x47b745] ./perf(main+0x617) [0x422547] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f2eca2deaf5] ./perf() [0x4226bd] Refcount -1 => 1 at ./perf(map_groups__exit+0x92) [0x4c0962] ./perf(map_groups__put+0x60) [0x4c0bc0] ./perf(thread__put+0x90) [0x4c8a40] ./perf(machine__delete_threads+0x7e) [0x4bad9e] ./perf(perf_session__delete+0x4f) [0x4c499f] ./perf(cmd_record+0xb6d) [0x42f9dd] ./perf() [0x47b745] ./perf(main+0x617) [0x422547] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f2eca2deaf5] ./perf() [0x4226bd] ---- Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20151209021131.10245.41485.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-12-09 10:11:31 +08:00
map__put(after);
}
put_map:
map__put(pos);
if (err)
goto out;
}
err = 0;
out:
up_write(&maps->lock);
return err;
}
/*
* XXX This should not really _copy_ te maps, but refcount them.
*/
int maps__clone(struct thread *thread, struct maps *parent)
{
struct maps *maps = thread->maps;
int err = -ENOMEM;
struct map *map;
down_read(&parent->lock);
maps__for_each_entry(parent, map) {
struct map *new = map__clone(map);
if (new == NULL)
goto out_unlock;
err = unwind__prepare_access(maps, new, NULL);
if (err)
goto out_unlock;
maps__insert(maps, new);
perf tools: Fix map_groups__clone to put cloned map Fix map_groups__clone to put cloned map after inserting it to the map_groups. Refcnt debugger shows: ---- ==== [0] ==== Unreclaimed map: 0x2a27ee0 Refcount +1 => 1 at ./perf(map_groups__clone+0x8d) [0x4bb7ed] ./perf(thread__fork+0xbe) [0x4c1f9e] ./perf(machine__process_fork_event+0x216) [0x4b79a6] ./perf(perf_event__synthesize_threads+0x38b) [0x48135b] ./perf(cmd_top+0xdc6) [0x43cb76] ./perf() [0x477223] ./perf(main+0x617) [0x422077] /lib64/libc.so.6(__libc_start_main+0xf0) [0x7ff806af8fe0] ./perf() [0x4221ed] Refcount +1 => 2 at ./perf(map_groups__clone+0x128) [0x4bb888] ./perf(thread__fork+0xbe) [0x4c1f9e] ./perf(machine__process_fork_event+0x216) [0x4b79a6] ./perf(perf_event__synthesize_threads+0x38b) [0x48135b] ./perf(cmd_top+0xdc6) [0x43cb76] ./perf() [0x477223] ./perf(main+0x617) [0x422077] /lib64/libc.so.6(__libc_start_main+0xf0) [0x7ff806af8fe0] ./perf() [0x4221ed] Refcount -1 => 1 at ./perf(map_groups__exit+0x87) [0x4ba757] ./perf(map_groups__put+0x68) [0x4ba9a8] ./perf(thread__put+0x8b) [0x4c1aeb] ./perf(machine__delete_threads+0x81) [0x4b48f1] ./perf(perf_session__delete+0x4f) [0x4be63f] ./perf(cmd_top+0x1094) [0x43ce44] ./perf() [0x477223] ./perf(main+0x617) [0x422077] /lib64/libc.so.6(__libc_start_main+0xf0) [0x7ff806af8fe0] ./perf() [0x4221ed] ---- This shows map_groups__clone get the map twice and put it when map_groups__exit. Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20151209021120.10245.95388.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-12-09 10:11:20 +08:00
map__put(new);
}
err = 0;
out_unlock:
up_read(&parent->lock);
return err;
}
static void __maps__insert(struct maps *maps, struct map *map)
{
struct rb_node **p = &maps->entries.rb_node;
struct rb_node *parent = NULL;
const u64 ip = map->start;
struct map *m;
while (*p != NULL) {
parent = *p;
m = rb_entry(parent, struct map, rb_node);
if (ip < m->start)
p = &(*p)->rb_left;
else
p = &(*p)->rb_right;
}
rb_link_node(&map->rb_node, parent, p);
rb_insert_color(&map->rb_node, &maps->entries);
map__get(map);
}
struct map *maps__find(struct maps *maps, u64 ip)
{
struct rb_node *p;
struct map *m;
down_read(&maps->lock);
p = maps->entries.rb_node;
while (p != NULL) {
m = rb_entry(p, struct map, rb_node);
if (ip < m->start)
p = p->rb_left;
else if (ip >= m->end)
p = p->rb_right;
else
goto out;
}
m = NULL;
out:
up_read(&maps->lock);
return m;
}
struct map *maps__first(struct maps *maps)
{
struct rb_node *first = rb_first(&maps->entries);
if (first)
return rb_entry(first, struct map, rb_node);
return NULL;
}
static struct map *__map__next(struct map *map)
{
struct rb_node *next = rb_next(&map->rb_node);
if (next)
return rb_entry(next, struct map, rb_node);
return NULL;
}
struct map *map__next(struct map *map)
{
return map ? __map__next(map) : NULL;
}
struct kmap *__map__kmap(struct map *map)
{
if (!map->dso || !map->dso->kernel)
return NULL;
return (struct kmap *)(map + 1);
}
struct kmap *map__kmap(struct map *map)
{
struct kmap *kmap = __map__kmap(map);
if (!kmap)
pr_err("Internal error: map__kmap with a non-kernel map\n");
return kmap;
}
struct maps *map__kmaps(struct map *map)
{
struct kmap *kmap = map__kmap(map);
if (!kmap || !kmap->kmaps) {
pr_err("Internal error: map__kmaps with a non-kernel map\n");
return NULL;
}
return kmap->kmaps;
}