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

1534 lines
35 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 <asm/bug.h>
#include <linux/kernel.h>
#include <sys/time.h>
#include <sys/resource.h>
#include <sys/types.h>
#include <sys/stat.h>
#include <unistd.h>
#include <errno.h>
#include <fcntl.h>
#include <libgen.h>
#include "compress.h"
#include "namespaces.h"
#include "path.h"
#include "map.h"
#include "symbol.h"
#include "srcline.h"
#include "dso.h"
#include "machine.h"
#include "auxtrace.h"
#include "util.h"
#include "debug.h"
#include "string2.h"
#include "vdso.h"
perf unwind: Fix looking up dwarf unwind stack info Using perf with call graph method dwarf fails to provide backtrace support for stripped binary even though .gnu_debuglink points to *.dbg flavor with properly populated debug symbols. Problem is reproduced on ARM (v7, v8), kernels 3.14.y, 4.4.y and 4.10.rc3. Perf is configured with libunwind, and unwind dwarf support [1]. Test code (stress_bt.c) can be found on [2]. Running (explicitly disable other unwinding methods): $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ perf record -N --call-graph dwarf ./stress_bt $ perf report results in properly generated call graph. Stripping the binary and running it results with missing call graph. Expected result is to have call graph: $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ objcopy --only-keep-debug stress_bt stress_bt.dbg $ objcopy --strip-debug stress_bt $ objcopy --add-gnu-debuglink=stress_bt.dbg stress_bt $ perf record -N --call-graph dwarf ./stress_bt $ perf report Problem is that perf doesn't try to read symbols pointed by gnu debuglink. Patch adds checking, and reading of the symbols from debuglink and symsrc. Order of the check is to first check within dso, then check whether symsrc is defined and try to read from it. Finally, debuglink is checked. Default locations of debug files are discussed in [3] and [4]. Comments on RFC are on [5]. [1] https://wiki.linaro.org/LEG/Engineering/TOOLS/perf-callstack-unwinding [2] [1]#Backtrace_stress_application [3] https://sourceware.org/gdb/onlinedocs/gdb/Separate-Debug-Files.html [4] https://sourceware.org/binutils/docs/binutils/objcopy.html [5] https://lkml.org/lkml/2016/8/22/473 Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Sverdlin <alexander.sverdlin@nokia.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/d309d40a-463f-482b-68e1-1465326efdc1@nokia.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-17 22:50:35 +08:00
static const char * const debuglink_paths[] = {
"%.0s%s",
"%s/%s",
"%s/.debug/%s",
"/usr/lib/debug%s/%s"
};
char dso__symtab_origin(const struct dso *dso)
{
static const char origin[] = {
[DSO_BINARY_TYPE__KALLSYMS] = 'k',
[DSO_BINARY_TYPE__VMLINUX] = 'v',
[DSO_BINARY_TYPE__JAVA_JIT] = 'j',
[DSO_BINARY_TYPE__DEBUGLINK] = 'l',
[DSO_BINARY_TYPE__BUILD_ID_CACHE] = 'B',
[DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO] = 'D',
[DSO_BINARY_TYPE__FEDORA_DEBUGINFO] = 'f',
[DSO_BINARY_TYPE__UBUNTU_DEBUGINFO] = 'u',
[DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO] = 'o',
[DSO_BINARY_TYPE__BUILDID_DEBUGINFO] = 'b',
[DSO_BINARY_TYPE__SYSTEM_PATH_DSO] = 'd',
[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE] = 'K',
[DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP] = 'm',
[DSO_BINARY_TYPE__GUEST_KALLSYMS] = 'g',
[DSO_BINARY_TYPE__GUEST_KMODULE] = 'G',
[DSO_BINARY_TYPE__GUEST_KMODULE_COMP] = 'M',
[DSO_BINARY_TYPE__GUEST_VMLINUX] = 'V',
};
if (dso == NULL || dso->symtab_type == DSO_BINARY_TYPE__NOT_FOUND)
return '!';
return origin[dso->symtab_type];
}
int dso__read_binary_type_filename(const struct dso *dso,
enum dso_binary_type type,
char *root_dir, char *filename, size_t size)
{
char build_id_hex[SBUILD_ID_SIZE];
int ret = 0;
size_t len;
switch (type) {
perf unwind: Fix looking up dwarf unwind stack info Using perf with call graph method dwarf fails to provide backtrace support for stripped binary even though .gnu_debuglink points to *.dbg flavor with properly populated debug symbols. Problem is reproduced on ARM (v7, v8), kernels 3.14.y, 4.4.y and 4.10.rc3. Perf is configured with libunwind, and unwind dwarf support [1]. Test code (stress_bt.c) can be found on [2]. Running (explicitly disable other unwinding methods): $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ perf record -N --call-graph dwarf ./stress_bt $ perf report results in properly generated call graph. Stripping the binary and running it results with missing call graph. Expected result is to have call graph: $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ objcopy --only-keep-debug stress_bt stress_bt.dbg $ objcopy --strip-debug stress_bt $ objcopy --add-gnu-debuglink=stress_bt.dbg stress_bt $ perf record -N --call-graph dwarf ./stress_bt $ perf report Problem is that perf doesn't try to read symbols pointed by gnu debuglink. Patch adds checking, and reading of the symbols from debuglink and symsrc. Order of the check is to first check within dso, then check whether symsrc is defined and try to read from it. Finally, debuglink is checked. Default locations of debug files are discussed in [3] and [4]. Comments on RFC are on [5]. [1] https://wiki.linaro.org/LEG/Engineering/TOOLS/perf-callstack-unwinding [2] [1]#Backtrace_stress_application [3] https://sourceware.org/gdb/onlinedocs/gdb/Separate-Debug-Files.html [4] https://sourceware.org/binutils/docs/binutils/objcopy.html [5] https://lkml.org/lkml/2016/8/22/473 Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Sverdlin <alexander.sverdlin@nokia.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/d309d40a-463f-482b-68e1-1465326efdc1@nokia.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-17 22:50:35 +08:00
case DSO_BINARY_TYPE__DEBUGLINK:
{
const char *last_slash;
char dso_dir[PATH_MAX];
char symfile[PATH_MAX];
unsigned int i;
len = __symbol__join_symfs(filename, size, dso->long_name);
perf unwind: Fix looking up dwarf unwind stack info Using perf with call graph method dwarf fails to provide backtrace support for stripped binary even though .gnu_debuglink points to *.dbg flavor with properly populated debug symbols. Problem is reproduced on ARM (v7, v8), kernels 3.14.y, 4.4.y and 4.10.rc3. Perf is configured with libunwind, and unwind dwarf support [1]. Test code (stress_bt.c) can be found on [2]. Running (explicitly disable other unwinding methods): $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ perf record -N --call-graph dwarf ./stress_bt $ perf report results in properly generated call graph. Stripping the binary and running it results with missing call graph. Expected result is to have call graph: $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ objcopy --only-keep-debug stress_bt stress_bt.dbg $ objcopy --strip-debug stress_bt $ objcopy --add-gnu-debuglink=stress_bt.dbg stress_bt $ perf record -N --call-graph dwarf ./stress_bt $ perf report Problem is that perf doesn't try to read symbols pointed by gnu debuglink. Patch adds checking, and reading of the symbols from debuglink and symsrc. Order of the check is to first check within dso, then check whether symsrc is defined and try to read from it. Finally, debuglink is checked. Default locations of debug files are discussed in [3] and [4]. Comments on RFC are on [5]. [1] https://wiki.linaro.org/LEG/Engineering/TOOLS/perf-callstack-unwinding [2] [1]#Backtrace_stress_application [3] https://sourceware.org/gdb/onlinedocs/gdb/Separate-Debug-Files.html [4] https://sourceware.org/binutils/docs/binutils/objcopy.html [5] https://lkml.org/lkml/2016/8/22/473 Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Sverdlin <alexander.sverdlin@nokia.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/d309d40a-463f-482b-68e1-1465326efdc1@nokia.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-17 22:50:35 +08:00
last_slash = filename + len;
while (last_slash != filename && *last_slash != '/')
last_slash--;
perf unwind: Fix looking up dwarf unwind stack info Using perf with call graph method dwarf fails to provide backtrace support for stripped binary even though .gnu_debuglink points to *.dbg flavor with properly populated debug symbols. Problem is reproduced on ARM (v7, v8), kernels 3.14.y, 4.4.y and 4.10.rc3. Perf is configured with libunwind, and unwind dwarf support [1]. Test code (stress_bt.c) can be found on [2]. Running (explicitly disable other unwinding methods): $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ perf record -N --call-graph dwarf ./stress_bt $ perf report results in properly generated call graph. Stripping the binary and running it results with missing call graph. Expected result is to have call graph: $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ objcopy --only-keep-debug stress_bt stress_bt.dbg $ objcopy --strip-debug stress_bt $ objcopy --add-gnu-debuglink=stress_bt.dbg stress_bt $ perf record -N --call-graph dwarf ./stress_bt $ perf report Problem is that perf doesn't try to read symbols pointed by gnu debuglink. Patch adds checking, and reading of the symbols from debuglink and symsrc. Order of the check is to first check within dso, then check whether symsrc is defined and try to read from it. Finally, debuglink is checked. Default locations of debug files are discussed in [3] and [4]. Comments on RFC are on [5]. [1] https://wiki.linaro.org/LEG/Engineering/TOOLS/perf-callstack-unwinding [2] [1]#Backtrace_stress_application [3] https://sourceware.org/gdb/onlinedocs/gdb/Separate-Debug-Files.html [4] https://sourceware.org/binutils/docs/binutils/objcopy.html [5] https://lkml.org/lkml/2016/8/22/473 Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Sverdlin <alexander.sverdlin@nokia.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/d309d40a-463f-482b-68e1-1465326efdc1@nokia.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-17 22:50:35 +08:00
strncpy(dso_dir, filename, last_slash - filename);
dso_dir[last_slash-filename] = '\0';
if (!is_regular_file(filename)) {
ret = -1;
break;
perf unwind: Fix looking up dwarf unwind stack info Using perf with call graph method dwarf fails to provide backtrace support for stripped binary even though .gnu_debuglink points to *.dbg flavor with properly populated debug symbols. Problem is reproduced on ARM (v7, v8), kernels 3.14.y, 4.4.y and 4.10.rc3. Perf is configured with libunwind, and unwind dwarf support [1]. Test code (stress_bt.c) can be found on [2]. Running (explicitly disable other unwinding methods): $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ perf record -N --call-graph dwarf ./stress_bt $ perf report results in properly generated call graph. Stripping the binary and running it results with missing call graph. Expected result is to have call graph: $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ objcopy --only-keep-debug stress_bt stress_bt.dbg $ objcopy --strip-debug stress_bt $ objcopy --add-gnu-debuglink=stress_bt.dbg stress_bt $ perf record -N --call-graph dwarf ./stress_bt $ perf report Problem is that perf doesn't try to read symbols pointed by gnu debuglink. Patch adds checking, and reading of the symbols from debuglink and symsrc. Order of the check is to first check within dso, then check whether symsrc is defined and try to read from it. Finally, debuglink is checked. Default locations of debug files are discussed in [3] and [4]. Comments on RFC are on [5]. [1] https://wiki.linaro.org/LEG/Engineering/TOOLS/perf-callstack-unwinding [2] [1]#Backtrace_stress_application [3] https://sourceware.org/gdb/onlinedocs/gdb/Separate-Debug-Files.html [4] https://sourceware.org/binutils/docs/binutils/objcopy.html [5] https://lkml.org/lkml/2016/8/22/473 Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Sverdlin <alexander.sverdlin@nokia.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/d309d40a-463f-482b-68e1-1465326efdc1@nokia.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-17 22:50:35 +08:00
}
perf unwind: Fix looking up dwarf unwind stack info Using perf with call graph method dwarf fails to provide backtrace support for stripped binary even though .gnu_debuglink points to *.dbg flavor with properly populated debug symbols. Problem is reproduced on ARM (v7, v8), kernels 3.14.y, 4.4.y and 4.10.rc3. Perf is configured with libunwind, and unwind dwarf support [1]. Test code (stress_bt.c) can be found on [2]. Running (explicitly disable other unwinding methods): $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ perf record -N --call-graph dwarf ./stress_bt $ perf report results in properly generated call graph. Stripping the binary and running it results with missing call graph. Expected result is to have call graph: $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ objcopy --only-keep-debug stress_bt stress_bt.dbg $ objcopy --strip-debug stress_bt $ objcopy --add-gnu-debuglink=stress_bt.dbg stress_bt $ perf record -N --call-graph dwarf ./stress_bt $ perf report Problem is that perf doesn't try to read symbols pointed by gnu debuglink. Patch adds checking, and reading of the symbols from debuglink and symsrc. Order of the check is to first check within dso, then check whether symsrc is defined and try to read from it. Finally, debuglink is checked. Default locations of debug files are discussed in [3] and [4]. Comments on RFC are on [5]. [1] https://wiki.linaro.org/LEG/Engineering/TOOLS/perf-callstack-unwinding [2] [1]#Backtrace_stress_application [3] https://sourceware.org/gdb/onlinedocs/gdb/Separate-Debug-Files.html [4] https://sourceware.org/binutils/docs/binutils/objcopy.html [5] https://lkml.org/lkml/2016/8/22/473 Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Sverdlin <alexander.sverdlin@nokia.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/d309d40a-463f-482b-68e1-1465326efdc1@nokia.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-17 22:50:35 +08:00
ret = filename__read_debuglink(filename, symfile, PATH_MAX);
if (ret)
break;
/* Check predefined locations where debug file might reside */
ret = -1;
for (i = 0; i < ARRAY_SIZE(debuglink_paths); i++) {
snprintf(filename, size,
debuglink_paths[i], dso_dir, symfile);
if (is_regular_file(filename)) {
ret = 0;
break;
}
}
perf unwind: Fix looking up dwarf unwind stack info Using perf with call graph method dwarf fails to provide backtrace support for stripped binary even though .gnu_debuglink points to *.dbg flavor with properly populated debug symbols. Problem is reproduced on ARM (v7, v8), kernels 3.14.y, 4.4.y and 4.10.rc3. Perf is configured with libunwind, and unwind dwarf support [1]. Test code (stress_bt.c) can be found on [2]. Running (explicitly disable other unwinding methods): $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ perf record -N --call-graph dwarf ./stress_bt $ perf report results in properly generated call graph. Stripping the binary and running it results with missing call graph. Expected result is to have call graph: $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ objcopy --only-keep-debug stress_bt stress_bt.dbg $ objcopy --strip-debug stress_bt $ objcopy --add-gnu-debuglink=stress_bt.dbg stress_bt $ perf record -N --call-graph dwarf ./stress_bt $ perf report Problem is that perf doesn't try to read symbols pointed by gnu debuglink. Patch adds checking, and reading of the symbols from debuglink and symsrc. Order of the check is to first check within dso, then check whether symsrc is defined and try to read from it. Finally, debuglink is checked. Default locations of debug files are discussed in [3] and [4]. Comments on RFC are on [5]. [1] https://wiki.linaro.org/LEG/Engineering/TOOLS/perf-callstack-unwinding [2] [1]#Backtrace_stress_application [3] https://sourceware.org/gdb/onlinedocs/gdb/Separate-Debug-Files.html [4] https://sourceware.org/binutils/docs/binutils/objcopy.html [5] https://lkml.org/lkml/2016/8/22/473 Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Sverdlin <alexander.sverdlin@nokia.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/d309d40a-463f-482b-68e1-1465326efdc1@nokia.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-17 22:50:35 +08:00
break;
perf unwind: Fix looking up dwarf unwind stack info Using perf with call graph method dwarf fails to provide backtrace support for stripped binary even though .gnu_debuglink points to *.dbg flavor with properly populated debug symbols. Problem is reproduced on ARM (v7, v8), kernels 3.14.y, 4.4.y and 4.10.rc3. Perf is configured with libunwind, and unwind dwarf support [1]. Test code (stress_bt.c) can be found on [2]. Running (explicitly disable other unwinding methods): $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ perf record -N --call-graph dwarf ./stress_bt $ perf report results in properly generated call graph. Stripping the binary and running it results with missing call graph. Expected result is to have call graph: $ gcc -g -o stress_bt -fomit-frame-pointer -fno-unwind-tables \ -fno-asynchronous-unwind-tables stress_bt.c $ objcopy --only-keep-debug stress_bt stress_bt.dbg $ objcopy --strip-debug stress_bt $ objcopy --add-gnu-debuglink=stress_bt.dbg stress_bt $ perf record -N --call-graph dwarf ./stress_bt $ perf report Problem is that perf doesn't try to read symbols pointed by gnu debuglink. Patch adds checking, and reading of the symbols from debuglink and symsrc. Order of the check is to first check within dso, then check whether symsrc is defined and try to read from it. Finally, debuglink is checked. Default locations of debug files are discussed in [3] and [4]. Comments on RFC are on [5]. [1] https://wiki.linaro.org/LEG/Engineering/TOOLS/perf-callstack-unwinding [2] [1]#Backtrace_stress_application [3] https://sourceware.org/gdb/onlinedocs/gdb/Separate-Debug-Files.html [4] https://sourceware.org/binutils/docs/binutils/objcopy.html [5] https://lkml.org/lkml/2016/8/22/473 Signed-off-by: Matija Glavinic Pecotic <matija.glavinic-pecotic.ext@nokia.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Sverdlin <alexander.sverdlin@nokia.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/d309d40a-463f-482b-68e1-1465326efdc1@nokia.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-01-17 22:50:35 +08:00
}
case DSO_BINARY_TYPE__BUILD_ID_CACHE:
if (dso__build_id_filename(dso, filename, size, false) == NULL)
ret = -1;
break;
case DSO_BINARY_TYPE__BUILD_ID_CACHE_DEBUGINFO:
if (dso__build_id_filename(dso, filename, size, true) == NULL)
ret = -1;
break;
case DSO_BINARY_TYPE__FEDORA_DEBUGINFO:
len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
snprintf(filename + len, size - len, "%s.debug", dso->long_name);
break;
case DSO_BINARY_TYPE__UBUNTU_DEBUGINFO:
len = __symbol__join_symfs(filename, size, "/usr/lib/debug");
snprintf(filename + len, size - len, "%s", dso->long_name);
break;
case DSO_BINARY_TYPE__OPENEMBEDDED_DEBUGINFO:
{
const char *last_slash;
size_t dir_size;
last_slash = dso->long_name + dso->long_name_len;
while (last_slash != dso->long_name && *last_slash != '/')
last_slash--;
len = __symbol__join_symfs(filename, size, "");
dir_size = last_slash - dso->long_name + 2;
if (dir_size > (size - len)) {
ret = -1;
break;
}
len += scnprintf(filename + len, dir_size, "%s", dso->long_name);
len += scnprintf(filename + len , size - len, ".debug%s",
last_slash);
break;
}
case DSO_BINARY_TYPE__BUILDID_DEBUGINFO:
if (!dso->has_build_id) {
ret = -1;
break;
}
build_id__sprintf(dso->build_id,
sizeof(dso->build_id),
build_id_hex);
len = __symbol__join_symfs(filename, size, "/usr/lib/debug/.build-id/");
snprintf(filename + len, size - len, "%.2s/%s.debug",
build_id_hex, build_id_hex + 2);
break;
case DSO_BINARY_TYPE__VMLINUX:
case DSO_BINARY_TYPE__GUEST_VMLINUX:
case DSO_BINARY_TYPE__SYSTEM_PATH_DSO:
__symbol__join_symfs(filename, size, dso->long_name);
break;
case DSO_BINARY_TYPE__GUEST_KMODULE:
case DSO_BINARY_TYPE__GUEST_KMODULE_COMP:
path__join3(filename, size, symbol_conf.symfs,
root_dir, dso->long_name);
break;
case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE:
case DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP:
__symbol__join_symfs(filename, size, dso->long_name);
break;
case DSO_BINARY_TYPE__KCORE:
case DSO_BINARY_TYPE__GUEST_KCORE:
snprintf(filename, size, "%s", dso->long_name);
break;
default:
case DSO_BINARY_TYPE__KALLSYMS:
case DSO_BINARY_TYPE__GUEST_KALLSYMS:
case DSO_BINARY_TYPE__JAVA_JIT:
perf symbols: Introduce DSO_BINARY_TYPE__BPF_PROG_INFO Introduce a new dso type DSO_BINARY_TYPE__BPF_PROG_INFO for BPF programs. In symbol__disassemble(), DSO_BINARY_TYPE__BPF_PROG_INFO dso will call into a new function symbol__disassemble_bpf() in an upcoming patch, where annotation line information is filled based bpf_prog_info and btf saved in given perf_env. Committer notes: Removed the unnamed union with 'bpf_prog' and 'cache' in 'struct dso', to fix this bug when exiting 'perf top': # perf top perf: Segmentation fault -------- backtrace -------- perf[0x5a785a] /lib64/libc.so.6(+0x385bf)[0x7fd68443c5bf] perf(rb_first+0x2b)[0x4d6eeb] perf(dso__delete+0xb7)[0x4dffb7] perf[0x4f9e37] perf(perf_session__delete+0x64)[0x504df4] perf(cmd_top+0x1957)[0x454467] perf[0x4aad18] perf(main+0x61c)[0x42ec7c] /lib64/libc.so.6(__libc_start_main+0xf2)[0x7fd684428412] perf(_start+0x2d)[0x42eead] # # addr2line -fe ~/bin/perf 0x4dffb7 dso_cache__free /home/acme/git/perf/tools/perf/util/dso.c:713 That is trying to access the dso->data.cache, and that is not used with BPF programs, so we end up accessing what is in bpf_prog.first_member, b00m. Signed-off-by: Song Liu <songliubraving@fb.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stanislav Fomichev <sdf@google.com> Cc: kernel-team@fb.com Link: http://lkml.kernel.org/r/20190312053051.2690567-13-songliubraving@fb.com [ split from a larger patch ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2019-03-12 13:30:48 +08:00
case DSO_BINARY_TYPE__BPF_PROG_INFO:
case DSO_BINARY_TYPE__NOT_FOUND:
ret = -1;
break;
}
return ret;
}
perf tools: Add compression id into 'struct kmod_path' Store a decompression ID in 'struct kmod_path', so it can be later stored in 'struct dso'. Switch 'struct kmod_path's 'comp' from 'bool' to 'int' to return the compressions array index. Add 0 index item into compressions array, so that the comp usage stays as it was: 0 - no compression, != 0 compression index. Update the kmod_path tests. Committer notes: Use a designated initializer + terminating comma, e.g. { .fmt = NULL, }, to fix the build in several distros: centos:6: util/dso.c:201: error: missing initializer centos:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') debian:9: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:25: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:26: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:27: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] oraclelinux:6: util/dso.c:201: error: missing initializer oraclelinux:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') ubuntu:12.04.5: util/dso.c:201:2: error: missing initializer [-Werror=missing-field-initializers] ubuntu:12.04.5: util/dso.c:201:2: error: (near initialization for 'compressions[0].decompress') [-Werror=missing-field-initializers] ubuntu:16.04: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:17.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20180817094813.15086-7-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-17 17:48:06 +08:00
enum {
COMP_ID__NONE = 0,
};
static const struct {
const char *fmt;
int (*decompress)(const char *input, int output);
bool (*is_compressed)(const char *input);
} compressions[] = {
perf tools: Add compression id into 'struct kmod_path' Store a decompression ID in 'struct kmod_path', so it can be later stored in 'struct dso'. Switch 'struct kmod_path's 'comp' from 'bool' to 'int' to return the compressions array index. Add 0 index item into compressions array, so that the comp usage stays as it was: 0 - no compression, != 0 compression index. Update the kmod_path tests. Committer notes: Use a designated initializer + terminating comma, e.g. { .fmt = NULL, }, to fix the build in several distros: centos:6: util/dso.c:201: error: missing initializer centos:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') debian:9: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:25: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:26: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:27: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] oraclelinux:6: util/dso.c:201: error: missing initializer oraclelinux:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') ubuntu:12.04.5: util/dso.c:201:2: error: missing initializer [-Werror=missing-field-initializers] ubuntu:12.04.5: util/dso.c:201:2: error: (near initialization for 'compressions[0].decompress') [-Werror=missing-field-initializers] ubuntu:16.04: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:17.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20180817094813.15086-7-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-17 17:48:06 +08:00
[COMP_ID__NONE] = { .fmt = NULL, },
perf tools: Add gzip decompression support for kernel module Now my Archlinux box shows module symbols correctly. Before: $ perf report --stdio Failed to open /tmp/perf-3477.map, continuing without symbols no symbols found in /usr/bin/date, maybe install a debug package? No kallsyms or vmlinux with build-id 7b4ea0a49ae2111925857099aaf05c3246ff33e0 was found [drm] with build id 7b4ea0a49ae2111925857099aaf05c3246ff33e0 not found, continuing without symbols No kallsyms or vmlinux with build-id edd931629094b660ca9dec09a1b635c8d87aa2ee was found [jbd2] with build id edd931629094b660ca9dec09a1b635c8d87aa2ee not found, continuing without symbols No kallsyms or vmlinux with build-id a7b1eada671c34933e5610bb920b2ca4945a82c3 was found [ext4] with build id a7b1eada671c34933e5610bb920b2ca4945a82c3 not found, continuing without symbols No kallsyms or vmlinux with build-id d69511fa3e5840e770336ef45b06c83fef8d74e3 was found [scsi_mod] with build id d69511fa3e5840e770336ef45b06c83fef8d74e3 not found, continuing without symbols No kallsyms or vmlinux with build-id af0430af13461af058770ee9b87afc07922c2e77 was found [libata] with build id af0430af13461af058770ee9b87afc07922c2e77 not found, continuing without symbols No kallsyms or vmlinux with build-id aaeedff8160ce631a5f0333591c6ff291201d29f was found [libahci] with build id aaeedff8160ce631a5f0333591c6ff291201d29f not found, continuing without symbols No kallsyms or vmlinux with build-id c57907712becaf662dc4981824bb372c0441d605 was found [mac80211] with build id c57907712becaf662dc4981824bb372c0441d605 not found, continuing without symbols No kallsyms or vmlinux with build-id e0589077cc0ec8c3e4c40eb9f2d9e69d236bee8f was found [iwldvm] with build id e0589077cc0ec8c3e4c40eb9f2d9e69d236bee8f not found, continuing without symbols No kallsyms or vmlinux with build-id 2d86086bf136bf374a2f029cf85a48194f9b950b was found [cfg80211] with build id 2d86086bf136bf374a2f029cf85a48194f9b950b not found, continuing without symbols No kallsyms or vmlinux with build-id 4493c48599bdb3d91d0f8db5150e0be33fdd9221 was found [iwlwifi] with build id 4493c48599bdb3d91d0f8db5150e0be33fdd9221 not found, continuing without symbols ... # # Overhead Command Shared Object Symbol # ........ ............... ....................... ........................................................ # 0.03% swapper [ext4] [k] 0x000000000000fe2e 0.03% swapper [kernel.kallsyms] [k] account_entity_enqueue 0.03% swapper [ext4] [k] 0x000000000000fc2b 0.03% irq/50-iwlwifi [iwlwifi] [k] 0x000000000000200b 0.03% swapper [kernel.kallsyms] [k] ktime_add_safe 0.03% swapper [kernel.kallsyms] [k] elv_completed_request 0.03% swapper [libata] [k] 0x0000000000003997 0.03% swapper [libahci] [k] 0x0000000000001f25 0.03% swapper [kernel.kallsyms] [k] rb_next 0.03% swapper [kernel.kallsyms] [k] blk_finish_request 0.03% swapper [ext4] [k] 0x0000000000010248 0.00% perf [kernel.kallsyms] [k] native_write_msr_safe After: $ perf report --stdio Failed to open /tmp/perf-3477.map, continuing without symbols no symbols found in /usr/bin/tr, maybe install a debug package? ... # # Overhead Command Shared Object Symbol # ........ ............... ........................... ...................................................... # 0.04% kworker/u16:3 [ext4] [k] ext4_read_block_bitmap 0.03% kworker/u16:0 [mac80211] [k] ieee80211_sta_reset_beacon_monitor 0.02% irq/50-iwlwifi [mac80211] [k] ieee80211_get_bssid 0.02% firefox [e1000e] [k] __ew32_prepare 0.02% swapper [libahci] [k] ahci_handle_port_interrupt 0.02% emacs libglib-2.0.so.0.4000.0 [.] g_mutex_unlock 0.02% swapper [e1000e] [k] e1000_clean_tx_irq 0.02% dwm [kernel.kallsyms] [k] __schedule 0.02% gnome-terminal- [vdso] [.] __vdso_clock_gettime 0.02% swapper [e1000e] [k] e1000_alloc_rx_buffers 0.02% irq/50-iwlwifi [mac80211] [k] ieee80211_rx 0.01% firefox [vdso] [.] __vdso_gettimeofday 0.01% irq/50-iwlwifi [iwlwifi] [k] iwl_pcie_rxq_restock.part.13 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/87h9yexshi.fsf@sejong.aot.lge.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-31 15:51:38 +08:00
#ifdef HAVE_ZLIB_SUPPORT
{ "gz", gzip_decompress_to_file, gzip_is_compressed },
#endif
#ifdef HAVE_LZMA_SUPPORT
{ "xz", lzma_decompress_to_file, lzma_is_compressed },
perf tools: Add gzip decompression support for kernel module Now my Archlinux box shows module symbols correctly. Before: $ perf report --stdio Failed to open /tmp/perf-3477.map, continuing without symbols no symbols found in /usr/bin/date, maybe install a debug package? No kallsyms or vmlinux with build-id 7b4ea0a49ae2111925857099aaf05c3246ff33e0 was found [drm] with build id 7b4ea0a49ae2111925857099aaf05c3246ff33e0 not found, continuing without symbols No kallsyms or vmlinux with build-id edd931629094b660ca9dec09a1b635c8d87aa2ee was found [jbd2] with build id edd931629094b660ca9dec09a1b635c8d87aa2ee not found, continuing without symbols No kallsyms or vmlinux with build-id a7b1eada671c34933e5610bb920b2ca4945a82c3 was found [ext4] with build id a7b1eada671c34933e5610bb920b2ca4945a82c3 not found, continuing without symbols No kallsyms or vmlinux with build-id d69511fa3e5840e770336ef45b06c83fef8d74e3 was found [scsi_mod] with build id d69511fa3e5840e770336ef45b06c83fef8d74e3 not found, continuing without symbols No kallsyms or vmlinux with build-id af0430af13461af058770ee9b87afc07922c2e77 was found [libata] with build id af0430af13461af058770ee9b87afc07922c2e77 not found, continuing without symbols No kallsyms or vmlinux with build-id aaeedff8160ce631a5f0333591c6ff291201d29f was found [libahci] with build id aaeedff8160ce631a5f0333591c6ff291201d29f not found, continuing without symbols No kallsyms or vmlinux with build-id c57907712becaf662dc4981824bb372c0441d605 was found [mac80211] with build id c57907712becaf662dc4981824bb372c0441d605 not found, continuing without symbols No kallsyms or vmlinux with build-id e0589077cc0ec8c3e4c40eb9f2d9e69d236bee8f was found [iwldvm] with build id e0589077cc0ec8c3e4c40eb9f2d9e69d236bee8f not found, continuing without symbols No kallsyms or vmlinux with build-id 2d86086bf136bf374a2f029cf85a48194f9b950b was found [cfg80211] with build id 2d86086bf136bf374a2f029cf85a48194f9b950b not found, continuing without symbols No kallsyms or vmlinux with build-id 4493c48599bdb3d91d0f8db5150e0be33fdd9221 was found [iwlwifi] with build id 4493c48599bdb3d91d0f8db5150e0be33fdd9221 not found, continuing without symbols ... # # Overhead Command Shared Object Symbol # ........ ............... ....................... ........................................................ # 0.03% swapper [ext4] [k] 0x000000000000fe2e 0.03% swapper [kernel.kallsyms] [k] account_entity_enqueue 0.03% swapper [ext4] [k] 0x000000000000fc2b 0.03% irq/50-iwlwifi [iwlwifi] [k] 0x000000000000200b 0.03% swapper [kernel.kallsyms] [k] ktime_add_safe 0.03% swapper [kernel.kallsyms] [k] elv_completed_request 0.03% swapper [libata] [k] 0x0000000000003997 0.03% swapper [libahci] [k] 0x0000000000001f25 0.03% swapper [kernel.kallsyms] [k] rb_next 0.03% swapper [kernel.kallsyms] [k] blk_finish_request 0.03% swapper [ext4] [k] 0x0000000000010248 0.00% perf [kernel.kallsyms] [k] native_write_msr_safe After: $ perf report --stdio Failed to open /tmp/perf-3477.map, continuing without symbols no symbols found in /usr/bin/tr, maybe install a debug package? ... # # Overhead Command Shared Object Symbol # ........ ............... ........................... ...................................................... # 0.04% kworker/u16:3 [ext4] [k] ext4_read_block_bitmap 0.03% kworker/u16:0 [mac80211] [k] ieee80211_sta_reset_beacon_monitor 0.02% irq/50-iwlwifi [mac80211] [k] ieee80211_get_bssid 0.02% firefox [e1000e] [k] __ew32_prepare 0.02% swapper [libahci] [k] ahci_handle_port_interrupt 0.02% emacs libglib-2.0.so.0.4000.0 [.] g_mutex_unlock 0.02% swapper [e1000e] [k] e1000_clean_tx_irq 0.02% dwm [kernel.kallsyms] [k] __schedule 0.02% gnome-terminal- [vdso] [.] __vdso_clock_gettime 0.02% swapper [e1000e] [k] e1000_alloc_rx_buffers 0.02% irq/50-iwlwifi [mac80211] [k] ieee80211_rx 0.01% firefox [vdso] [.] __vdso_gettimeofday 0.01% irq/50-iwlwifi [iwlwifi] [k] iwl_pcie_rxq_restock.part.13 Signed-off-by: Namhyung Kim <namhyung@kernel.org> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Ingo Molnar <mingo@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Namhyung Kim <namhyung.kim@lge.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/87h9yexshi.fsf@sejong.aot.lge.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-31 15:51:38 +08:00
#endif
{ NULL, NULL, NULL },
};
perf tools: Add compression id into 'struct kmod_path' Store a decompression ID in 'struct kmod_path', so it can be later stored in 'struct dso'. Switch 'struct kmod_path's 'comp' from 'bool' to 'int' to return the compressions array index. Add 0 index item into compressions array, so that the comp usage stays as it was: 0 - no compression, != 0 compression index. Update the kmod_path tests. Committer notes: Use a designated initializer + terminating comma, e.g. { .fmt = NULL, }, to fix the build in several distros: centos:6: util/dso.c:201: error: missing initializer centos:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') debian:9: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:25: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:26: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:27: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] oraclelinux:6: util/dso.c:201: error: missing initializer oraclelinux:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') ubuntu:12.04.5: util/dso.c:201:2: error: missing initializer [-Werror=missing-field-initializers] ubuntu:12.04.5: util/dso.c:201:2: error: (near initialization for 'compressions[0].decompress') [-Werror=missing-field-initializers] ubuntu:16.04: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:17.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20180817094813.15086-7-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-17 17:48:06 +08:00
static int is_supported_compression(const char *ext)
{
unsigned i;
perf tools: Add compression id into 'struct kmod_path' Store a decompression ID in 'struct kmod_path', so it can be later stored in 'struct dso'. Switch 'struct kmod_path's 'comp' from 'bool' to 'int' to return the compressions array index. Add 0 index item into compressions array, so that the comp usage stays as it was: 0 - no compression, != 0 compression index. Update the kmod_path tests. Committer notes: Use a designated initializer + terminating comma, e.g. { .fmt = NULL, }, to fix the build in several distros: centos:6: util/dso.c:201: error: missing initializer centos:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') debian:9: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:25: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:26: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:27: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] oraclelinux:6: util/dso.c:201: error: missing initializer oraclelinux:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') ubuntu:12.04.5: util/dso.c:201:2: error: missing initializer [-Werror=missing-field-initializers] ubuntu:12.04.5: util/dso.c:201:2: error: (near initialization for 'compressions[0].decompress') [-Werror=missing-field-initializers] ubuntu:16.04: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:17.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20180817094813.15086-7-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-17 17:48:06 +08:00
for (i = 1; compressions[i].fmt; i++) {
if (!strcmp(ext, compressions[i].fmt))
perf tools: Add compression id into 'struct kmod_path' Store a decompression ID in 'struct kmod_path', so it can be later stored in 'struct dso'. Switch 'struct kmod_path's 'comp' from 'bool' to 'int' to return the compressions array index. Add 0 index item into compressions array, so that the comp usage stays as it was: 0 - no compression, != 0 compression index. Update the kmod_path tests. Committer notes: Use a designated initializer + terminating comma, e.g. { .fmt = NULL, }, to fix the build in several distros: centos:6: util/dso.c:201: error: missing initializer centos:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') debian:9: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:25: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:26: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:27: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] oraclelinux:6: util/dso.c:201: error: missing initializer oraclelinux:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') ubuntu:12.04.5: util/dso.c:201:2: error: missing initializer [-Werror=missing-field-initializers] ubuntu:12.04.5: util/dso.c:201:2: error: (near initialization for 'compressions[0].decompress') [-Werror=missing-field-initializers] ubuntu:16.04: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:17.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20180817094813.15086-7-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-17 17:48:06 +08:00
return i;
}
perf tools: Add compression id into 'struct kmod_path' Store a decompression ID in 'struct kmod_path', so it can be later stored in 'struct dso'. Switch 'struct kmod_path's 'comp' from 'bool' to 'int' to return the compressions array index. Add 0 index item into compressions array, so that the comp usage stays as it was: 0 - no compression, != 0 compression index. Update the kmod_path tests. Committer notes: Use a designated initializer + terminating comma, e.g. { .fmt = NULL, }, to fix the build in several distros: centos:6: util/dso.c:201: error: missing initializer centos:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') debian:9: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:25: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:26: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:27: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] oraclelinux:6: util/dso.c:201: error: missing initializer oraclelinux:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') ubuntu:12.04.5: util/dso.c:201:2: error: missing initializer [-Werror=missing-field-initializers] ubuntu:12.04.5: util/dso.c:201:2: error: (near initialization for 'compressions[0].decompress') [-Werror=missing-field-initializers] ubuntu:16.04: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:17.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20180817094813.15086-7-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-17 17:48:06 +08:00
return COMP_ID__NONE;
}
perf tools: Deal with kernel module names in '[]' correctly Before patch ba92732e9808 ('perf kmaps: Check kmaps to make code more robust'), 'perf report' and 'perf annotate' will segfault if trace data contains kernel module information like this: # perf report -D -i ./perf.data ... 0 0 0x188 [0x50]: PERF_RECORD_MMAP -1/0: [0xffffffbff1018000(0xf068000) @ 0]: x [test_module] ... # perf report -i ./perf.data --objdump=/path/to/objdump --kallsyms=/path/to/kallsyms perf: Segmentation fault -------- backtrace -------- /path/to/perf[0x503478] /lib64/libc.so.6(+0x3545f)[0x7fb201f3745f] /path/to/perf[0x499b56] /path/to/perf(dso__load_kallsyms+0x13c)[0x49b56c] /path/to/perf(dso__load+0x72e)[0x49c21e] /path/to/perf(map__load+0x6e)[0x4ae9ee] /path/to/perf(thread__find_addr_map+0x24c)[0x47deec] /path/to/perf(perf_event__preprocess_sample+0x88)[0x47e238] /path/to/perf[0x43ad02] /path/to/perf[0x4b55bc] /path/to/perf(ordered_events__flush+0xca)[0x4b57ea] /path/to/perf[0x4b1a01] /path/to/perf(perf_session__process_events+0x3be)[0x4b428e] /path/to/perf(cmd_report+0xf11)[0x43bfc1] /path/to/perf[0x474702] /path/to/perf(main+0x5f5)[0x42de95] /lib64/libc.so.6(__libc_start_main+0xf4)[0x7fb201f23bd4] /path/to/perf[0x42dfc4] This is because __kmod_path__parse treats '[' leading names as kernel name instead of names of kernel module. If perf.data contains build information and the buildid of such modules can be found, the dso->kernel of it will be set to DSO_TYPE_KERNEL by __event_process_build_id(), not kernel module. It will then be passed to dso__load() -> dso__load_kernel_sym() -> dso__load_kcore() if --kallsyms is provided. The refered patch adds NULL pointer checker to avoid segfault. However, such kernel modules are still processed incorrectly. This patch fixes __kmod_path__parse, makes it treat names like '[test_module]' as kernel modules. kmod-path.c is also update to reflect the above changes. Signed-off-by: Wang Nan <wangnan0@huawei.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/r/1433321541-170245-1-git-send-email-wangnan0@huawei.com [ Fixed the merged with 0443f36b0de0 ("perf machine: Fix the search for the kernel DSO on the unified list" ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-03 16:52:21 +08:00
bool is_kernel_module(const char *pathname, int cpumode)
{
struct kmod_path m;
perf tools: Deal with kernel module names in '[]' correctly Before patch ba92732e9808 ('perf kmaps: Check kmaps to make code more robust'), 'perf report' and 'perf annotate' will segfault if trace data contains kernel module information like this: # perf report -D -i ./perf.data ... 0 0 0x188 [0x50]: PERF_RECORD_MMAP -1/0: [0xffffffbff1018000(0xf068000) @ 0]: x [test_module] ... # perf report -i ./perf.data --objdump=/path/to/objdump --kallsyms=/path/to/kallsyms perf: Segmentation fault -------- backtrace -------- /path/to/perf[0x503478] /lib64/libc.so.6(+0x3545f)[0x7fb201f3745f] /path/to/perf[0x499b56] /path/to/perf(dso__load_kallsyms+0x13c)[0x49b56c] /path/to/perf(dso__load+0x72e)[0x49c21e] /path/to/perf(map__load+0x6e)[0x4ae9ee] /path/to/perf(thread__find_addr_map+0x24c)[0x47deec] /path/to/perf(perf_event__preprocess_sample+0x88)[0x47e238] /path/to/perf[0x43ad02] /path/to/perf[0x4b55bc] /path/to/perf(ordered_events__flush+0xca)[0x4b57ea] /path/to/perf[0x4b1a01] /path/to/perf(perf_session__process_events+0x3be)[0x4b428e] /path/to/perf(cmd_report+0xf11)[0x43bfc1] /path/to/perf[0x474702] /path/to/perf(main+0x5f5)[0x42de95] /lib64/libc.so.6(__libc_start_main+0xf4)[0x7fb201f23bd4] /path/to/perf[0x42dfc4] This is because __kmod_path__parse treats '[' leading names as kernel name instead of names of kernel module. If perf.data contains build information and the buildid of such modules can be found, the dso->kernel of it will be set to DSO_TYPE_KERNEL by __event_process_build_id(), not kernel module. It will then be passed to dso__load() -> dso__load_kernel_sym() -> dso__load_kcore() if --kallsyms is provided. The refered patch adds NULL pointer checker to avoid segfault. However, such kernel modules are still processed incorrectly. This patch fixes __kmod_path__parse, makes it treat names like '[test_module]' as kernel modules. kmod-path.c is also update to reflect the above changes. Signed-off-by: Wang Nan <wangnan0@huawei.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/r/1433321541-170245-1-git-send-email-wangnan0@huawei.com [ Fixed the merged with 0443f36b0de0 ("perf machine: Fix the search for the kernel DSO on the unified list" ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-03 16:52:21 +08:00
int mode = cpumode & PERF_RECORD_MISC_CPUMODE_MASK;
WARN_ONCE(mode != cpumode,
"Internal error: passing unmasked cpumode (%x) to is_kernel_module",
cpumode);
switch (mode) {
case PERF_RECORD_MISC_USER:
case PERF_RECORD_MISC_HYPERVISOR:
case PERF_RECORD_MISC_GUEST_USER:
return false;
/* Treat PERF_RECORD_MISC_CPUMODE_UNKNOWN as kernel */
default:
if (kmod_path__parse(&m, pathname)) {
pr_err("Failed to check whether %s is a kernel module or not. Assume it is.",
pathname);
return true;
}
}
return m.kmod;
}
bool dso__needs_decompress(struct dso *dso)
{
return dso->symtab_type == DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE_COMP ||
dso->symtab_type == DSO_BINARY_TYPE__GUEST_KMODULE_COMP;
}
static int decompress_kmodule(struct dso *dso, const char *name,
char *pathname, size_t len)
{
char tmpbuf[] = KMOD_DECOMP_NAME;
int fd = -1;
if (!dso__needs_decompress(dso))
return -1;
if (dso->comp == COMP_ID__NONE)
return -1;
/*
* We have proper compression id for DSO and yet the file
* behind the 'name' can still be plain uncompressed object.
*
* The reason is behind the logic we open the DSO object files,
* when we try all possible 'debug' objects until we find the
* data. So even if the DSO is represented by 'krava.xz' module,
* we can end up here opening ~/.debug/....23432432/debug' file
* which is not compressed.
*
* To keep this transparent, we detect this and return the file
* descriptor to the uncompressed file.
*/
if (!compressions[dso->comp].is_compressed(name))
return open(name, O_RDONLY);
fd = mkstemp(tmpbuf);
if (fd < 0) {
dso->load_errno = errno;
return -1;
}
if (compressions[dso->comp].decompress(name, fd)) {
dso->load_errno = DSO_LOAD_ERRNO__DECOMPRESSION_FAILURE;
close(fd);
fd = -1;
}
if (!pathname || (fd < 0))
unlink(tmpbuf);
if (pathname && (fd >= 0))
strlcpy(pathname, tmpbuf, len);
return fd;
}
int dso__decompress_kmodule_fd(struct dso *dso, const char *name)
{
return decompress_kmodule(dso, name, NULL, 0);
}
int dso__decompress_kmodule_path(struct dso *dso, const char *name,
char *pathname, size_t len)
{
int fd = decompress_kmodule(dso, name, pathname, len);
close(fd);
return fd >= 0 ? 0 : -1;
}
perf tools: Add kmod_path__parse function Provides united way of parsing kernel module path into several components. The new kmod_path__parse function and few defines: int __kmod_path__parse(struct kmod_path *m, const char *path, bool alloc_name, bool alloc_ext); #define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false, false) #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) #define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) parse kernel module @path and updates @m argument like: @comp - true if @path contains supported compression suffix, false otherwise @kmod - true if @path contains '.ko' suffix in right position, false otherwise @name - if (@alloc_name && @kmod) is true, it contains strdup-ed base name of the kernel module without suffixes, otherwise strudup-ed base name of @path @ext - if (@alloc_ext && @comp) is true, it contains strdup-ed string the compression suffix It returns 0 if there's no strdup error, -ENOMEM otherwise. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@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/n/tip-9t6eqg8j610r94l743hkntiv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-05 22:40:25 +08:00
/*
* Parses kernel module specified in @path and updates
* @m argument like:
*
* @comp - true if @path contains supported compression suffix,
* false otherwise
* @kmod - true if @path contains '.ko' suffix in right position,
* false otherwise
* @name - if (@alloc_name && @kmod) is true, it contains strdup-ed base name
* of the kernel module without suffixes, otherwise strudup-ed
* base name of @path
* @ext - if (@alloc_ext && @comp) is true, it contains strdup-ed string
* the compression suffix
*
* Returns 0 if there's no strdup error, -ENOMEM otherwise.
*/
int __kmod_path__parse(struct kmod_path *m, const char *path,
bool alloc_name)
perf tools: Add kmod_path__parse function Provides united way of parsing kernel module path into several components. The new kmod_path__parse function and few defines: int __kmod_path__parse(struct kmod_path *m, const char *path, bool alloc_name, bool alloc_ext); #define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false, false) #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) #define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) parse kernel module @path and updates @m argument like: @comp - true if @path contains supported compression suffix, false otherwise @kmod - true if @path contains '.ko' suffix in right position, false otherwise @name - if (@alloc_name && @kmod) is true, it contains strdup-ed base name of the kernel module without suffixes, otherwise strudup-ed base name of @path @ext - if (@alloc_ext && @comp) is true, it contains strdup-ed string the compression suffix It returns 0 if there's no strdup error, -ENOMEM otherwise. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@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/n/tip-9t6eqg8j610r94l743hkntiv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-05 22:40:25 +08:00
{
const char *name = strrchr(path, '/');
const char *ext = strrchr(path, '.');
perf tools: Deal with kernel module names in '[]' correctly Before patch ba92732e9808 ('perf kmaps: Check kmaps to make code more robust'), 'perf report' and 'perf annotate' will segfault if trace data contains kernel module information like this: # perf report -D -i ./perf.data ... 0 0 0x188 [0x50]: PERF_RECORD_MMAP -1/0: [0xffffffbff1018000(0xf068000) @ 0]: x [test_module] ... # perf report -i ./perf.data --objdump=/path/to/objdump --kallsyms=/path/to/kallsyms perf: Segmentation fault -------- backtrace -------- /path/to/perf[0x503478] /lib64/libc.so.6(+0x3545f)[0x7fb201f3745f] /path/to/perf[0x499b56] /path/to/perf(dso__load_kallsyms+0x13c)[0x49b56c] /path/to/perf(dso__load+0x72e)[0x49c21e] /path/to/perf(map__load+0x6e)[0x4ae9ee] /path/to/perf(thread__find_addr_map+0x24c)[0x47deec] /path/to/perf(perf_event__preprocess_sample+0x88)[0x47e238] /path/to/perf[0x43ad02] /path/to/perf[0x4b55bc] /path/to/perf(ordered_events__flush+0xca)[0x4b57ea] /path/to/perf[0x4b1a01] /path/to/perf(perf_session__process_events+0x3be)[0x4b428e] /path/to/perf(cmd_report+0xf11)[0x43bfc1] /path/to/perf[0x474702] /path/to/perf(main+0x5f5)[0x42de95] /lib64/libc.so.6(__libc_start_main+0xf4)[0x7fb201f23bd4] /path/to/perf[0x42dfc4] This is because __kmod_path__parse treats '[' leading names as kernel name instead of names of kernel module. If perf.data contains build information and the buildid of such modules can be found, the dso->kernel of it will be set to DSO_TYPE_KERNEL by __event_process_build_id(), not kernel module. It will then be passed to dso__load() -> dso__load_kernel_sym() -> dso__load_kcore() if --kallsyms is provided. The refered patch adds NULL pointer checker to avoid segfault. However, such kernel modules are still processed incorrectly. This patch fixes __kmod_path__parse, makes it treat names like '[test_module]' as kernel modules. kmod-path.c is also update to reflect the above changes. Signed-off-by: Wang Nan <wangnan0@huawei.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/r/1433321541-170245-1-git-send-email-wangnan0@huawei.com [ Fixed the merged with 0443f36b0de0 ("perf machine: Fix the search for the kernel DSO on the unified list" ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-03 16:52:21 +08:00
bool is_simple_name = false;
perf tools: Add kmod_path__parse function Provides united way of parsing kernel module path into several components. The new kmod_path__parse function and few defines: int __kmod_path__parse(struct kmod_path *m, const char *path, bool alloc_name, bool alloc_ext); #define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false, false) #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) #define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) parse kernel module @path and updates @m argument like: @comp - true if @path contains supported compression suffix, false otherwise @kmod - true if @path contains '.ko' suffix in right position, false otherwise @name - if (@alloc_name && @kmod) is true, it contains strdup-ed base name of the kernel module without suffixes, otherwise strudup-ed base name of @path @ext - if (@alloc_ext && @comp) is true, it contains strdup-ed string the compression suffix It returns 0 if there's no strdup error, -ENOMEM otherwise. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@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/n/tip-9t6eqg8j610r94l743hkntiv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-05 22:40:25 +08:00
memset(m, 0x0, sizeof(*m));
name = name ? name + 1 : path;
perf tools: Deal with kernel module names in '[]' correctly Before patch ba92732e9808 ('perf kmaps: Check kmaps to make code more robust'), 'perf report' and 'perf annotate' will segfault if trace data contains kernel module information like this: # perf report -D -i ./perf.data ... 0 0 0x188 [0x50]: PERF_RECORD_MMAP -1/0: [0xffffffbff1018000(0xf068000) @ 0]: x [test_module] ... # perf report -i ./perf.data --objdump=/path/to/objdump --kallsyms=/path/to/kallsyms perf: Segmentation fault -------- backtrace -------- /path/to/perf[0x503478] /lib64/libc.so.6(+0x3545f)[0x7fb201f3745f] /path/to/perf[0x499b56] /path/to/perf(dso__load_kallsyms+0x13c)[0x49b56c] /path/to/perf(dso__load+0x72e)[0x49c21e] /path/to/perf(map__load+0x6e)[0x4ae9ee] /path/to/perf(thread__find_addr_map+0x24c)[0x47deec] /path/to/perf(perf_event__preprocess_sample+0x88)[0x47e238] /path/to/perf[0x43ad02] /path/to/perf[0x4b55bc] /path/to/perf(ordered_events__flush+0xca)[0x4b57ea] /path/to/perf[0x4b1a01] /path/to/perf(perf_session__process_events+0x3be)[0x4b428e] /path/to/perf(cmd_report+0xf11)[0x43bfc1] /path/to/perf[0x474702] /path/to/perf(main+0x5f5)[0x42de95] /lib64/libc.so.6(__libc_start_main+0xf4)[0x7fb201f23bd4] /path/to/perf[0x42dfc4] This is because __kmod_path__parse treats '[' leading names as kernel name instead of names of kernel module. If perf.data contains build information and the buildid of such modules can be found, the dso->kernel of it will be set to DSO_TYPE_KERNEL by __event_process_build_id(), not kernel module. It will then be passed to dso__load() -> dso__load_kernel_sym() -> dso__load_kcore() if --kallsyms is provided. The refered patch adds NULL pointer checker to avoid segfault. However, such kernel modules are still processed incorrectly. This patch fixes __kmod_path__parse, makes it treat names like '[test_module]' as kernel modules. kmod-path.c is also update to reflect the above changes. Signed-off-by: Wang Nan <wangnan0@huawei.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/r/1433321541-170245-1-git-send-email-wangnan0@huawei.com [ Fixed the merged with 0443f36b0de0 ("perf machine: Fix the search for the kernel DSO on the unified list" ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-03 16:52:21 +08:00
/*
* '.' is also a valid character for module name. For example:
* [aaa.bbb] is a valid module name. '[' should have higher
* priority than '.ko' suffix.
*
* The kernel names are from machine__mmap_name. Such
* name should belong to kernel itself, not kernel module.
*/
if (name[0] == '[') {
is_simple_name = true;
if ((strncmp(name, "[kernel.kallsyms]", 17) == 0) ||
(strncmp(name, "[guest.kernel.kallsyms", 22) == 0) ||
(strncmp(name, "[vdso]", 6) == 0) ||
(strncmp(name, "[vdso32]", 8) == 0) ||
(strncmp(name, "[vdsox32]", 9) == 0) ||
perf tools: Deal with kernel module names in '[]' correctly Before patch ba92732e9808 ('perf kmaps: Check kmaps to make code more robust'), 'perf report' and 'perf annotate' will segfault if trace data contains kernel module information like this: # perf report -D -i ./perf.data ... 0 0 0x188 [0x50]: PERF_RECORD_MMAP -1/0: [0xffffffbff1018000(0xf068000) @ 0]: x [test_module] ... # perf report -i ./perf.data --objdump=/path/to/objdump --kallsyms=/path/to/kallsyms perf: Segmentation fault -------- backtrace -------- /path/to/perf[0x503478] /lib64/libc.so.6(+0x3545f)[0x7fb201f3745f] /path/to/perf[0x499b56] /path/to/perf(dso__load_kallsyms+0x13c)[0x49b56c] /path/to/perf(dso__load+0x72e)[0x49c21e] /path/to/perf(map__load+0x6e)[0x4ae9ee] /path/to/perf(thread__find_addr_map+0x24c)[0x47deec] /path/to/perf(perf_event__preprocess_sample+0x88)[0x47e238] /path/to/perf[0x43ad02] /path/to/perf[0x4b55bc] /path/to/perf(ordered_events__flush+0xca)[0x4b57ea] /path/to/perf[0x4b1a01] /path/to/perf(perf_session__process_events+0x3be)[0x4b428e] /path/to/perf(cmd_report+0xf11)[0x43bfc1] /path/to/perf[0x474702] /path/to/perf(main+0x5f5)[0x42de95] /lib64/libc.so.6(__libc_start_main+0xf4)[0x7fb201f23bd4] /path/to/perf[0x42dfc4] This is because __kmod_path__parse treats '[' leading names as kernel name instead of names of kernel module. If perf.data contains build information and the buildid of such modules can be found, the dso->kernel of it will be set to DSO_TYPE_KERNEL by __event_process_build_id(), not kernel module. It will then be passed to dso__load() -> dso__load_kernel_sym() -> dso__load_kcore() if --kallsyms is provided. The refered patch adds NULL pointer checker to avoid segfault. However, such kernel modules are still processed incorrectly. This patch fixes __kmod_path__parse, makes it treat names like '[test_module]' as kernel modules. kmod-path.c is also update to reflect the above changes. Signed-off-by: Wang Nan <wangnan0@huawei.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/r/1433321541-170245-1-git-send-email-wangnan0@huawei.com [ Fixed the merged with 0443f36b0de0 ("perf machine: Fix the search for the kernel DSO on the unified list" ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-03 16:52:21 +08:00
(strncmp(name, "[vsyscall]", 10) == 0)) {
m->kmod = false;
} else
m->kmod = true;
}
perf tools: Add kmod_path__parse function Provides united way of parsing kernel module path into several components. The new kmod_path__parse function and few defines: int __kmod_path__parse(struct kmod_path *m, const char *path, bool alloc_name, bool alloc_ext); #define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false, false) #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) #define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) parse kernel module @path and updates @m argument like: @comp - true if @path contains supported compression suffix, false otherwise @kmod - true if @path contains '.ko' suffix in right position, false otherwise @name - if (@alloc_name && @kmod) is true, it contains strdup-ed base name of the kernel module without suffixes, otherwise strudup-ed base name of @path @ext - if (@alloc_ext && @comp) is true, it contains strdup-ed string the compression suffix It returns 0 if there's no strdup error, -ENOMEM otherwise. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@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/n/tip-9t6eqg8j610r94l743hkntiv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-05 22:40:25 +08:00
/* No extension, just return name. */
perf tools: Deal with kernel module names in '[]' correctly Before patch ba92732e9808 ('perf kmaps: Check kmaps to make code more robust'), 'perf report' and 'perf annotate' will segfault if trace data contains kernel module information like this: # perf report -D -i ./perf.data ... 0 0 0x188 [0x50]: PERF_RECORD_MMAP -1/0: [0xffffffbff1018000(0xf068000) @ 0]: x [test_module] ... # perf report -i ./perf.data --objdump=/path/to/objdump --kallsyms=/path/to/kallsyms perf: Segmentation fault -------- backtrace -------- /path/to/perf[0x503478] /lib64/libc.so.6(+0x3545f)[0x7fb201f3745f] /path/to/perf[0x499b56] /path/to/perf(dso__load_kallsyms+0x13c)[0x49b56c] /path/to/perf(dso__load+0x72e)[0x49c21e] /path/to/perf(map__load+0x6e)[0x4ae9ee] /path/to/perf(thread__find_addr_map+0x24c)[0x47deec] /path/to/perf(perf_event__preprocess_sample+0x88)[0x47e238] /path/to/perf[0x43ad02] /path/to/perf[0x4b55bc] /path/to/perf(ordered_events__flush+0xca)[0x4b57ea] /path/to/perf[0x4b1a01] /path/to/perf(perf_session__process_events+0x3be)[0x4b428e] /path/to/perf(cmd_report+0xf11)[0x43bfc1] /path/to/perf[0x474702] /path/to/perf(main+0x5f5)[0x42de95] /lib64/libc.so.6(__libc_start_main+0xf4)[0x7fb201f23bd4] /path/to/perf[0x42dfc4] This is because __kmod_path__parse treats '[' leading names as kernel name instead of names of kernel module. If perf.data contains build information and the buildid of such modules can be found, the dso->kernel of it will be set to DSO_TYPE_KERNEL by __event_process_build_id(), not kernel module. It will then be passed to dso__load() -> dso__load_kernel_sym() -> dso__load_kcore() if --kallsyms is provided. The refered patch adds NULL pointer checker to avoid segfault. However, such kernel modules are still processed incorrectly. This patch fixes __kmod_path__parse, makes it treat names like '[test_module]' as kernel modules. kmod-path.c is also update to reflect the above changes. Signed-off-by: Wang Nan <wangnan0@huawei.com> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Zefan Li <lizefan@huawei.com> Link: http://lkml.kernel.org/r/1433321541-170245-1-git-send-email-wangnan0@huawei.com [ Fixed the merged with 0443f36b0de0 ("perf machine: Fix the search for the kernel DSO on the unified list" ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-06-03 16:52:21 +08:00
if ((ext == NULL) || is_simple_name) {
perf tools: Add kmod_path__parse function Provides united way of parsing kernel module path into several components. The new kmod_path__parse function and few defines: int __kmod_path__parse(struct kmod_path *m, const char *path, bool alloc_name, bool alloc_ext); #define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false, false) #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) #define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) parse kernel module @path and updates @m argument like: @comp - true if @path contains supported compression suffix, false otherwise @kmod - true if @path contains '.ko' suffix in right position, false otherwise @name - if (@alloc_name && @kmod) is true, it contains strdup-ed base name of the kernel module without suffixes, otherwise strudup-ed base name of @path @ext - if (@alloc_ext && @comp) is true, it contains strdup-ed string the compression suffix It returns 0 if there's no strdup error, -ENOMEM otherwise. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@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/n/tip-9t6eqg8j610r94l743hkntiv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-05 22:40:25 +08:00
if (alloc_name) {
m->name = strdup(name);
return m->name ? 0 : -ENOMEM;
}
return 0;
}
perf tools: Add compression id into 'struct kmod_path' Store a decompression ID in 'struct kmod_path', so it can be later stored in 'struct dso'. Switch 'struct kmod_path's 'comp' from 'bool' to 'int' to return the compressions array index. Add 0 index item into compressions array, so that the comp usage stays as it was: 0 - no compression, != 0 compression index. Update the kmod_path tests. Committer notes: Use a designated initializer + terminating comma, e.g. { .fmt = NULL, }, to fix the build in several distros: centos:6: util/dso.c:201: error: missing initializer centos:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') debian:9: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:25: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:26: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] fedora:27: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] oraclelinux:6: util/dso.c:201: error: missing initializer oraclelinux:6: util/dso.c:201: error: (near initialization for 'compressions[0].decompress') ubuntu:12.04.5: util/dso.c:201:2: error: missing initializer [-Werror=missing-field-initializers] ubuntu:12.04.5: util/dso.c:201:2: error: (near initialization for 'compressions[0].decompress') [-Werror=missing-field-initializers] ubuntu:16.04: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:16.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] ubuntu:17.10: util/dso.c:201:24: error: missing field 'decompress' initializer [-Werror,-Wmissing-field-initializers] Signed-off-by: Jiri Olsa <jolsa@kernel.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Michael Petlan <mpetlan@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20180817094813.15086-7-jolsa@kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2018-08-17 17:48:06 +08:00
m->comp = is_supported_compression(ext + 1);
if (m->comp > COMP_ID__NONE)
perf tools: Add kmod_path__parse function Provides united way of parsing kernel module path into several components. The new kmod_path__parse function and few defines: int __kmod_path__parse(struct kmod_path *m, const char *path, bool alloc_name, bool alloc_ext); #define kmod_path__parse(__m, __p) __kmod_path__parse(__m, __p, false, false) #define kmod_path__parse_name(__m, __p) __kmod_path__parse(__m, __p, true , false) #define kmod_path__parse_ext(__m, __p) __kmod_path__parse(__m, __p, false, true) parse kernel module @path and updates @m argument like: @comp - true if @path contains supported compression suffix, false otherwise @kmod - true if @path contains '.ko' suffix in right position, false otherwise @name - if (@alloc_name && @kmod) is true, it contains strdup-ed base name of the kernel module without suffixes, otherwise strudup-ed base name of @path @ext - if (@alloc_ext && @comp) is true, it contains strdup-ed string the compression suffix It returns 0 if there's no strdup error, -ENOMEM otherwise. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Namhyung Kim <namhyung@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@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/n/tip-9t6eqg8j610r94l743hkntiv@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-02-05 22:40:25 +08:00
ext -= 3;
/* Check .ko extension only if there's enough name left. */
if (ext > name)
m->kmod = !strncmp(ext, ".ko", 3);
if (alloc_name) {
if (m->kmod) {
if (asprintf(&m->name, "[%.*s]", (int) (ext - name), name) == -1)
return -ENOMEM;
} else {
if (asprintf(&m->name, "%s", name) == -1)
return -ENOMEM;
}
strxfrchar(m->name, '-', '_');
}
return 0;
}
void dso__set_module_info(struct dso *dso, struct kmod_path *m,
struct machine *machine)
{
if (machine__is_host(machine))
dso->symtab_type = DSO_BINARY_TYPE__SYSTEM_PATH_KMODULE;
else
dso->symtab_type = DSO_BINARY_TYPE__GUEST_KMODULE;
/* _KMODULE_COMP should be next to _KMODULE */
if (m->kmod && m->comp) {
dso->symtab_type++;
dso->comp = m->comp;
}
dso__set_short_name(dso, strdup(m->name), true);
}
/*
* Global list of open DSOs and the counter.
*/
static LIST_HEAD(dso__data_open);
static long dso__data_open_cnt;
static pthread_mutex_t dso__data_open_lock = PTHREAD_MUTEX_INITIALIZER;
static void dso__list_add(struct dso *dso)
{
list_add_tail(&dso->data.open_entry, &dso__data_open);
dso__data_open_cnt++;
}
static void dso__list_del(struct dso *dso)
{
list_del(&dso->data.open_entry);
WARN_ONCE(dso__data_open_cnt <= 0,
"DSO data fd counter out of bounds.");
dso__data_open_cnt--;
}
static void close_first_dso(void);
static int do_open(char *name)
{
int fd;
char sbuf[STRERR_BUFSIZE];
do {
fd = open(name, O_RDONLY|O_CLOEXEC);
if (fd >= 0)
return fd;
pr_debug("dso open failed: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
if (!dso__data_open_cnt || errno != EMFILE)
break;
close_first_dso();
} while (1);
return -1;
}
static int __open_dso(struct dso *dso, struct machine *machine)
{
int fd = -EINVAL;
char *root_dir = (char *)"";
char *name = malloc(PATH_MAX);
bool decomp = false;
if (!name)
return -ENOMEM;
if (machine)
root_dir = machine->root_dir;
if (dso__read_binary_type_filename(dso, dso->binary_type,
root_dir, name, PATH_MAX))
goto out;
if (!is_regular_file(name))
goto out;
if (dso__needs_decompress(dso)) {
char newpath[KMOD_DECOMP_LEN];
size_t len = sizeof(newpath);
if (dso__decompress_kmodule_path(dso, name, newpath, len) < 0) {
fd = -dso->load_errno;
goto out;
}
decomp = true;
strcpy(name, newpath);
}
fd = do_open(name);
if (decomp)
unlink(name);
out:
free(name);
return fd;
}
static void check_data_close(void);
/**
* dso_close - Open DSO data file
* @dso: dso object
*
* Open @dso's data file descriptor and updates
* list/count of open DSO objects.
*/
static int open_dso(struct dso *dso, struct machine *machine)
{
int fd;
struct nscookie nsc;
if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
nsinfo__mountns_enter(dso->nsinfo, &nsc);
fd = __open_dso(dso, machine);
if (dso->binary_type != DSO_BINARY_TYPE__BUILD_ID_CACHE)
nsinfo__mountns_exit(&nsc);
if (fd >= 0) {
dso__list_add(dso);
/*
* Check if we crossed the allowed number
* of opened DSOs and close one if needed.
*/
check_data_close();
}
return fd;
}
static void close_data_fd(struct dso *dso)
{
if (dso->data.fd >= 0) {
close(dso->data.fd);
dso->data.fd = -1;
dso->data.file_size = 0;
dso__list_del(dso);
}
}
/**
* dso_close - Close DSO data file
* @dso: dso object
*
* Close @dso's data file descriptor and updates
* list/count of open DSO objects.
*/
static void close_dso(struct dso *dso)
{
close_data_fd(dso);
}
static void close_first_dso(void)
{
struct dso *dso;
dso = list_first_entry(&dso__data_open, struct dso, data.open_entry);
close_dso(dso);
}
static rlim_t get_fd_limit(void)
{
struct rlimit l;
rlim_t limit = 0;
/* Allow half of the current open fd limit. */
if (getrlimit(RLIMIT_NOFILE, &l) == 0) {
if (l.rlim_cur == RLIM_INFINITY)
limit = l.rlim_cur;
else
limit = l.rlim_cur / 2;
} else {
pr_err("failed to get fd limit\n");
limit = 1;
}
return limit;
}
static rlim_t fd_limit;
/*
* Used only by tests/dso-data.c to reset the environment
* for tests. I dont expect we should change this during
* standard runtime.
*/
void reset_fd_limit(void)
{
fd_limit = 0;
}
static bool may_cache_fd(void)
{
if (!fd_limit)
fd_limit = get_fd_limit();
if (fd_limit == RLIM_INFINITY)
return true;
return fd_limit > (rlim_t) dso__data_open_cnt;
}
/*
* Check and close LRU dso if we crossed allowed limit
* for opened dso file descriptors. The limit is half
* of the RLIMIT_NOFILE files opened.
*/
static void check_data_close(void)
{
bool cache_fd = may_cache_fd();
if (!cache_fd)
close_first_dso();
}
/**
* dso__data_close - Close DSO data file
* @dso: dso object
*
* External interface to close @dso's data file descriptor.
*/
void dso__data_close(struct dso *dso)
{
pthread_mutex_lock(&dso__data_open_lock);
close_dso(dso);
pthread_mutex_unlock(&dso__data_open_lock);
}
static void try_to_open_dso(struct dso *dso, struct machine *machine)
{
enum dso_binary_type binary_type_data[] = {
DSO_BINARY_TYPE__BUILD_ID_CACHE,
DSO_BINARY_TYPE__SYSTEM_PATH_DSO,
DSO_BINARY_TYPE__NOT_FOUND,
};
int i = 0;
if (dso->data.fd >= 0)
return;
if (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND) {
dso->data.fd = open_dso(dso, machine);
goto out;
}
do {
dso->binary_type = binary_type_data[i++];
dso->data.fd = open_dso(dso, machine);
if (dso->data.fd >= 0)
goto out;
} while (dso->binary_type != DSO_BINARY_TYPE__NOT_FOUND);
out:
if (dso->data.fd >= 0)
dso->data.status = DSO_DATA_STATUS_OK;
else
dso->data.status = DSO_DATA_STATUS_ERROR;
}
/**
* dso__data_get_fd - Get dso's data file descriptor
* @dso: dso object
* @machine: machine object
*
* External interface to find dso's file, open it and
* returns file descriptor. It should be paired with
* dso__data_put_fd() if it returns non-negative value.
*/
int dso__data_get_fd(struct dso *dso, struct machine *machine)
{
if (dso->data.status == DSO_DATA_STATUS_ERROR)
return -1;
if (pthread_mutex_lock(&dso__data_open_lock) < 0)
return -1;
try_to_open_dso(dso, machine);
if (dso->data.fd < 0)
pthread_mutex_unlock(&dso__data_open_lock);
return dso->data.fd;
}
void dso__data_put_fd(struct dso *dso __maybe_unused)
{
pthread_mutex_unlock(&dso__data_open_lock);
}
bool dso__data_status_seen(struct dso *dso, enum dso_data_status_seen by)
{
u32 flag = 1 << by;
if (dso->data.status_seen & flag)
return true;
dso->data.status_seen |= flag;
return false;
}
static void
dso_cache__free(struct dso *dso)
{
struct rb_root *root = &dso->data.cache;
struct rb_node *next = rb_first(root);
pthread_mutex_lock(&dso->lock);
while (next) {
struct dso_cache *cache;
cache = rb_entry(next, struct dso_cache, rb_node);
next = rb_next(&cache->rb_node);
rb_erase(&cache->rb_node, root);
free(cache);
}
pthread_mutex_unlock(&dso->lock);
}
static struct dso_cache *dso_cache__find(struct dso *dso, u64 offset)
{
const struct rb_root *root = &dso->data.cache;
struct rb_node * const *p = &root->rb_node;
const struct rb_node *parent = NULL;
struct dso_cache *cache;
while (*p != NULL) {
u64 end;
parent = *p;
cache = rb_entry(parent, struct dso_cache, rb_node);
end = cache->offset + DSO__DATA_CACHE_SIZE;
if (offset < cache->offset)
p = &(*p)->rb_left;
else if (offset >= end)
p = &(*p)->rb_right;
else
return cache;
}
return NULL;
}
static struct dso_cache *
dso_cache__insert(struct dso *dso, struct dso_cache *new)
{
struct rb_root *root = &dso->data.cache;
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
struct dso_cache *cache;
u64 offset = new->offset;
pthread_mutex_lock(&dso->lock);
while (*p != NULL) {
u64 end;
parent = *p;
cache = rb_entry(parent, struct dso_cache, rb_node);
end = cache->offset + DSO__DATA_CACHE_SIZE;
if (offset < cache->offset)
p = &(*p)->rb_left;
else if (offset >= end)
p = &(*p)->rb_right;
else
goto out;
}
rb_link_node(&new->rb_node, parent, p);
rb_insert_color(&new->rb_node, root);
cache = NULL;
out:
pthread_mutex_unlock(&dso->lock);
return cache;
}
static ssize_t
dso_cache__memcpy(struct dso_cache *cache, u64 offset,
u8 *data, u64 size)
{
u64 cache_offset = offset - cache->offset;
u64 cache_size = min(cache->size - cache_offset, size);
memcpy(data, cache->data + cache_offset, cache_size);
return cache_size;
}
static ssize_t
dso_cache__read(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size)
{
struct dso_cache *cache;
struct dso_cache *old;
ssize_t ret;
do {
u64 cache_offset;
cache = zalloc(sizeof(*cache) + DSO__DATA_CACHE_SIZE);
if (!cache)
return -ENOMEM;
pthread_mutex_lock(&dso__data_open_lock);
/*
* dso->data.fd might be closed if other thread opened another
* file (dso) due to open file limit (RLIMIT_NOFILE).
*/
try_to_open_dso(dso, machine);
if (dso->data.fd < 0) {
ret = -errno;
dso->data.status = DSO_DATA_STATUS_ERROR;
break;
}
cache_offset = offset & DSO__DATA_CACHE_MASK;
ret = pread(dso->data.fd, cache->data, DSO__DATA_CACHE_SIZE, cache_offset);
if (ret <= 0)
break;
cache->offset = cache_offset;
cache->size = ret;
} while (0);
pthread_mutex_unlock(&dso__data_open_lock);
if (ret > 0) {
old = dso_cache__insert(dso, cache);
if (old) {
/* we lose the race */
free(cache);
cache = old;
}
ret = dso_cache__memcpy(cache, offset, data, size);
}
if (ret <= 0)
free(cache);
return ret;
}
static ssize_t dso_cache_read(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size)
{
struct dso_cache *cache;
cache = dso_cache__find(dso, offset);
if (cache)
return dso_cache__memcpy(cache, offset, data, size);
else
return dso_cache__read(dso, machine, offset, data, size);
}
/*
* Reads and caches dso data DSO__DATA_CACHE_SIZE size chunks
* in the rb_tree. Any read to already cached data is served
* by cached data.
*/
static ssize_t cached_read(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size)
{
ssize_t r = 0;
u8 *p = data;
do {
ssize_t ret;
ret = dso_cache_read(dso, machine, offset, p, size);
if (ret < 0)
return ret;
/* Reached EOF, return what we have. */
if (!ret)
break;
BUG_ON(ret > size);
r += ret;
p += ret;
offset += ret;
size -= ret;
} while (size);
return r;
}
int dso__data_file_size(struct dso *dso, struct machine *machine)
{
int ret = 0;
struct stat st;
char sbuf[STRERR_BUFSIZE];
if (dso->data.file_size)
return 0;
if (dso->data.status == DSO_DATA_STATUS_ERROR)
return -1;
pthread_mutex_lock(&dso__data_open_lock);
/*
* dso->data.fd might be closed if other thread opened another
* file (dso) due to open file limit (RLIMIT_NOFILE).
*/
try_to_open_dso(dso, machine);
if (dso->data.fd < 0) {
ret = -errno;
dso->data.status = DSO_DATA_STATUS_ERROR;
goto out;
}
if (fstat(dso->data.fd, &st) < 0) {
ret = -errno;
pr_err("dso cache fstat failed: %s\n",
str_error_r(errno, sbuf, sizeof(sbuf)));
dso->data.status = DSO_DATA_STATUS_ERROR;
goto out;
}
dso->data.file_size = st.st_size;
out:
pthread_mutex_unlock(&dso__data_open_lock);
return ret;
}
/**
* dso__data_size - Return dso data size
* @dso: dso object
* @machine: machine object
*
* Return: dso data size
*/
off_t dso__data_size(struct dso *dso, struct machine *machine)
{
if (dso__data_file_size(dso, machine))
return -1;
/* For now just estimate dso data size is close to file size */
return dso->data.file_size;
}
static ssize_t data_read_offset(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size)
{
if (dso__data_file_size(dso, machine))
return -1;
/* Check the offset sanity. */
if (offset > dso->data.file_size)
return -1;
if (offset + size < offset)
return -1;
return cached_read(dso, machine, offset, data, size);
}
/**
* dso__data_read_offset - Read data from dso file offset
* @dso: dso object
* @machine: machine object
* @offset: file offset
* @data: buffer to store data
* @size: size of the @data buffer
*
* External interface to read data from dso file offset. Open
* dso data file and use cached_read to get the data.
*/
ssize_t dso__data_read_offset(struct dso *dso, struct machine *machine,
u64 offset, u8 *data, ssize_t size)
{
if (dso->data.status == DSO_DATA_STATUS_ERROR)
return -1;
return data_read_offset(dso, machine, offset, data, size);
}
/**
* dso__data_read_addr - Read data from dso address
* @dso: dso object
* @machine: machine object
* @add: virtual memory address
* @data: buffer to store data
* @size: size of the @data buffer
*
* External interface to read data from dso address.
*/
ssize_t dso__data_read_addr(struct dso *dso, struct map *map,
struct machine *machine, u64 addr,
u8 *data, ssize_t size)
{
u64 offset = map->map_ip(map, addr);
return dso__data_read_offset(dso, machine, offset, data, size);
}
struct map *dso__new_map(const char *name)
{
struct map *map = NULL;
struct dso *dso = dso__new(name);
if (dso)
map = map__new2(0, dso);
return map;
}
struct dso *machine__findnew_kernel(struct machine *machine, const char *name,
const char *short_name, int dso_type)
{
/*
* The kernel dso could be created by build_id processing.
*/
struct dso *dso = machine__findnew_dso(machine, name);
/*
* We need to run this in all cases, since during the build_id
* processing we had no idea this was the kernel dso.
*/
if (dso != NULL) {
dso__set_short_name(dso, short_name, false);
dso->kernel = dso_type;
}
return dso;
}
perf symbols: Improve DSO long names lookup speed with rbtree With workload that spawns and destroys many threads and processes, it was found that perf-mem could took a long time to post-process the perf data after the target workload had completed its operation. The performance bottleneck was found to be the lookup and insertion of the new DSO structures (thousands of them in this case). In a dual-socket Ivy-Bridge E7-4890 v2 machine (30-core, 60-thread), the perf profile below shows what perf was doing after the profiled AIM7 shared workload completed: - 83.94% perf libc-2.11.3.so [.] __strcmp_sse42 - __strcmp_sse42 - 99.82% map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main - 13.17% perf perf [.] __dsos__findnew __dsos__findnew map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main So about 97% of CPU times were spent in the map__new() function trying to insert new DSO entry into the DSO linked list. The whole post-processing step took about 9 minutes. The DSO structures are currently searched linearly. So the total processing time will be proportional to n^2. To overcome this performance problem, the DSO code is modified to also put the DSO structures in a RB tree sorted by its long name in additional to being in a simple linked list. With this change, the processing time will become proportional to n*log(n) which will be much quicker for large n. However, the short name will still be searched using the old linear searching method. With that patch in place, the same perf-mem post-processing step took less than 30 seconds to complete. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Link: http://lkml.kernel.org/r/1412098575-27863-3-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-01 01:36:15 +08:00
/*
* Find a matching entry and/or link current entry to RB tree.
* Either one of the dso or name parameter must be non-NULL or the
* function will not work.
*/
static struct dso *__dso__findlink_by_longname(struct rb_root *root,
struct dso *dso, const char *name)
perf symbols: Improve DSO long names lookup speed with rbtree With workload that spawns and destroys many threads and processes, it was found that perf-mem could took a long time to post-process the perf data after the target workload had completed its operation. The performance bottleneck was found to be the lookup and insertion of the new DSO structures (thousands of them in this case). In a dual-socket Ivy-Bridge E7-4890 v2 machine (30-core, 60-thread), the perf profile below shows what perf was doing after the profiled AIM7 shared workload completed: - 83.94% perf libc-2.11.3.so [.] __strcmp_sse42 - __strcmp_sse42 - 99.82% map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main - 13.17% perf perf [.] __dsos__findnew __dsos__findnew map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main So about 97% of CPU times were spent in the map__new() function trying to insert new DSO entry into the DSO linked list. The whole post-processing step took about 9 minutes. The DSO structures are currently searched linearly. So the total processing time will be proportional to n^2. To overcome this performance problem, the DSO code is modified to also put the DSO structures in a RB tree sorted by its long name in additional to being in a simple linked list. With this change, the processing time will become proportional to n*log(n) which will be much quicker for large n. However, the short name will still be searched using the old linear searching method. With that patch in place, the same perf-mem post-processing step took less than 30 seconds to complete. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Link: http://lkml.kernel.org/r/1412098575-27863-3-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-01 01:36:15 +08:00
{
struct rb_node **p = &root->rb_node;
struct rb_node *parent = NULL;
if (!name)
name = dso->long_name;
/*
* Find node with the matching name
*/
while (*p) {
struct dso *this = rb_entry(*p, struct dso, rb_node);
int rc = strcmp(name, this->long_name);
parent = *p;
if (rc == 0) {
/*
* In case the new DSO is a duplicate of an existing
* one, print a one-time warning & put the new entry
perf symbols: Improve DSO long names lookup speed with rbtree With workload that spawns and destroys many threads and processes, it was found that perf-mem could took a long time to post-process the perf data after the target workload had completed its operation. The performance bottleneck was found to be the lookup and insertion of the new DSO structures (thousands of them in this case). In a dual-socket Ivy-Bridge E7-4890 v2 machine (30-core, 60-thread), the perf profile below shows what perf was doing after the profiled AIM7 shared workload completed: - 83.94% perf libc-2.11.3.so [.] __strcmp_sse42 - __strcmp_sse42 - 99.82% map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main - 13.17% perf perf [.] __dsos__findnew __dsos__findnew map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main So about 97% of CPU times were spent in the map__new() function trying to insert new DSO entry into the DSO linked list. The whole post-processing step took about 9 minutes. The DSO structures are currently searched linearly. So the total processing time will be proportional to n^2. To overcome this performance problem, the DSO code is modified to also put the DSO structures in a RB tree sorted by its long name in additional to being in a simple linked list. With this change, the processing time will become proportional to n*log(n) which will be much quicker for large n. However, the short name will still be searched using the old linear searching method. With that patch in place, the same perf-mem post-processing step took less than 30 seconds to complete. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Link: http://lkml.kernel.org/r/1412098575-27863-3-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-01 01:36:15 +08:00
* at the end of the list of duplicates.
*/
if (!dso || (dso == this))
return this; /* Find matching dso */
/*
* The core kernel DSOs may have duplicated long name.
* In this case, the short name should be different.
* Comparing the short names to differentiate the DSOs.
*/
rc = strcmp(dso->short_name, this->short_name);
if (rc == 0) {
pr_err("Duplicated dso name: %s\n", name);
return NULL;
}
}
if (rc < 0)
p = &parent->rb_left;
else
p = &parent->rb_right;
}
if (dso) {
/* Add new node and rebalance tree */
rb_link_node(&dso->rb_node, parent, p);
rb_insert_color(&dso->rb_node, root);
perf symbols: Fix dso lookup by long name and missing buildids Commit 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed with rbtree") Added a tree to lookup dsos by long name. That tree gets corrupted whenever a dso long name is changed because the tree is not updated. One effect of that is buildid-list does not work with the 'with-hits' option because dso lookup fails and results in two structs for the same dso. The first has the buildid but no hits, the second has hits but no buildid. e.g. Before: $ tools/perf/perf record ls arch certs CREDITS Documentation firmware include ipc Kconfig lib Makefile net REPORTING-BUGS scripts sound usr block COPYING crypto drivers fs init Kbuild kernel MAINTAINERS mm README samples security tools virt [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.012 MB perf.data (11 samples) ] $ tools/perf/perf buildid-list 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so $ tools/perf/perf buildid-list -H 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 0000000000000000000000000000000000000000 /lib/x86_64-linux-gnu/libc-2.19.so After: $ tools/perf/perf buildid-list -H 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so The fix is to record the root of the tree on the dso so that dso__set_long_name() can update the tree when the long name changes. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Cc: Waiman Long <Waiman.Long@hp.com> Fixes: 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed with rbtree") Link: http://lkml.kernel.org/r/1447408112-1920-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-13 17:48:30 +08:00
dso->root = root;
perf symbols: Improve DSO long names lookup speed with rbtree With workload that spawns and destroys many threads and processes, it was found that perf-mem could took a long time to post-process the perf data after the target workload had completed its operation. The performance bottleneck was found to be the lookup and insertion of the new DSO structures (thousands of them in this case). In a dual-socket Ivy-Bridge E7-4890 v2 machine (30-core, 60-thread), the perf profile below shows what perf was doing after the profiled AIM7 shared workload completed: - 83.94% perf libc-2.11.3.so [.] __strcmp_sse42 - __strcmp_sse42 - 99.82% map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main - 13.17% perf perf [.] __dsos__findnew __dsos__findnew map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main So about 97% of CPU times were spent in the map__new() function trying to insert new DSO entry into the DSO linked list. The whole post-processing step took about 9 minutes. The DSO structures are currently searched linearly. So the total processing time will be proportional to n^2. To overcome this performance problem, the DSO code is modified to also put the DSO structures in a RB tree sorted by its long name in additional to being in a simple linked list. With this change, the processing time will become proportional to n*log(n) which will be much quicker for large n. However, the short name will still be searched using the old linear searching method. With that patch in place, the same perf-mem post-processing step took less than 30 seconds to complete. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Link: http://lkml.kernel.org/r/1412098575-27863-3-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-01 01:36:15 +08:00
}
return NULL;
}
static inline struct dso *__dso__find_by_longname(struct rb_root *root,
const char *name)
perf symbols: Improve DSO long names lookup speed with rbtree With workload that spawns and destroys many threads and processes, it was found that perf-mem could took a long time to post-process the perf data after the target workload had completed its operation. The performance bottleneck was found to be the lookup and insertion of the new DSO structures (thousands of them in this case). In a dual-socket Ivy-Bridge E7-4890 v2 machine (30-core, 60-thread), the perf profile below shows what perf was doing after the profiled AIM7 shared workload completed: - 83.94% perf libc-2.11.3.so [.] __strcmp_sse42 - __strcmp_sse42 - 99.82% map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main - 13.17% perf perf [.] __dsos__findnew __dsos__findnew map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main So about 97% of CPU times were spent in the map__new() function trying to insert new DSO entry into the DSO linked list. The whole post-processing step took about 9 minutes. The DSO structures are currently searched linearly. So the total processing time will be proportional to n^2. To overcome this performance problem, the DSO code is modified to also put the DSO structures in a RB tree sorted by its long name in additional to being in a simple linked list. With this change, the processing time will become proportional to n*log(n) which will be much quicker for large n. However, the short name will still be searched using the old linear searching method. With that patch in place, the same perf-mem post-processing step took less than 30 seconds to complete. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Link: http://lkml.kernel.org/r/1412098575-27863-3-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-01 01:36:15 +08:00
{
return __dso__findlink_by_longname(root, NULL, name);
perf symbols: Improve DSO long names lookup speed with rbtree With workload that spawns and destroys many threads and processes, it was found that perf-mem could took a long time to post-process the perf data after the target workload had completed its operation. The performance bottleneck was found to be the lookup and insertion of the new DSO structures (thousands of them in this case). In a dual-socket Ivy-Bridge E7-4890 v2 machine (30-core, 60-thread), the perf profile below shows what perf was doing after the profiled AIM7 shared workload completed: - 83.94% perf libc-2.11.3.so [.] __strcmp_sse42 - __strcmp_sse42 - 99.82% map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main - 13.17% perf perf [.] __dsos__findnew __dsos__findnew map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main So about 97% of CPU times were spent in the map__new() function trying to insert new DSO entry into the DSO linked list. The whole post-processing step took about 9 minutes. The DSO structures are currently searched linearly. So the total processing time will be proportional to n^2. To overcome this performance problem, the DSO code is modified to also put the DSO structures in a RB tree sorted by its long name in additional to being in a simple linked list. With this change, the processing time will become proportional to n*log(n) which will be much quicker for large n. However, the short name will still be searched using the old linear searching method. With that patch in place, the same perf-mem post-processing step took less than 30 seconds to complete. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Link: http://lkml.kernel.org/r/1412098575-27863-3-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-01 01:36:15 +08:00
}
void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
{
perf symbols: Fix dso lookup by long name and missing buildids Commit 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed with rbtree") Added a tree to lookup dsos by long name. That tree gets corrupted whenever a dso long name is changed because the tree is not updated. One effect of that is buildid-list does not work with the 'with-hits' option because dso lookup fails and results in two structs for the same dso. The first has the buildid but no hits, the second has hits but no buildid. e.g. Before: $ tools/perf/perf record ls arch certs CREDITS Documentation firmware include ipc Kconfig lib Makefile net REPORTING-BUGS scripts sound usr block COPYING crypto drivers fs init Kbuild kernel MAINTAINERS mm README samples security tools virt [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.012 MB perf.data (11 samples) ] $ tools/perf/perf buildid-list 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so $ tools/perf/perf buildid-list -H 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 0000000000000000000000000000000000000000 /lib/x86_64-linux-gnu/libc-2.19.so After: $ tools/perf/perf buildid-list -H 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so The fix is to record the root of the tree on the dso so that dso__set_long_name() can update the tree when the long name changes. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Cc: Waiman Long <Waiman.Long@hp.com> Fixes: 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed with rbtree") Link: http://lkml.kernel.org/r/1447408112-1920-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-13 17:48:30 +08:00
struct rb_root *root = dso->root;
if (name == NULL)
return;
if (dso->long_name_allocated)
free((char *)dso->long_name);
perf symbols: Fix dso lookup by long name and missing buildids Commit 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed with rbtree") Added a tree to lookup dsos by long name. That tree gets corrupted whenever a dso long name is changed because the tree is not updated. One effect of that is buildid-list does not work with the 'with-hits' option because dso lookup fails and results in two structs for the same dso. The first has the buildid but no hits, the second has hits but no buildid. e.g. Before: $ tools/perf/perf record ls arch certs CREDITS Documentation firmware include ipc Kconfig lib Makefile net REPORTING-BUGS scripts sound usr block COPYING crypto drivers fs init Kbuild kernel MAINTAINERS mm README samples security tools virt [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.012 MB perf.data (11 samples) ] $ tools/perf/perf buildid-list 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so $ tools/perf/perf buildid-list -H 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 0000000000000000000000000000000000000000 /lib/x86_64-linux-gnu/libc-2.19.so After: $ tools/perf/perf buildid-list -H 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so The fix is to record the root of the tree on the dso so that dso__set_long_name() can update the tree when the long name changes. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Cc: Waiman Long <Waiman.Long@hp.com> Fixes: 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed with rbtree") Link: http://lkml.kernel.org/r/1447408112-1920-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-13 17:48:30 +08:00
if (root) {
rb_erase(&dso->rb_node, root);
/*
* __dso__findlink_by_longname() isn't guaranteed to add it
* back, so a clean removal is required here.
*/
RB_CLEAR_NODE(&dso->rb_node);
dso->root = NULL;
}
dso->long_name = name;
dso->long_name_len = strlen(name);
dso->long_name_allocated = name_allocated;
perf symbols: Fix dso lookup by long name and missing buildids Commit 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed with rbtree") Added a tree to lookup dsos by long name. That tree gets corrupted whenever a dso long name is changed because the tree is not updated. One effect of that is buildid-list does not work with the 'with-hits' option because dso lookup fails and results in two structs for the same dso. The first has the buildid but no hits, the second has hits but no buildid. e.g. Before: $ tools/perf/perf record ls arch certs CREDITS Documentation firmware include ipc Kconfig lib Makefile net REPORTING-BUGS scripts sound usr block COPYING crypto drivers fs init Kbuild kernel MAINTAINERS mm README samples security tools virt [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.012 MB perf.data (11 samples) ] $ tools/perf/perf buildid-list 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so $ tools/perf/perf buildid-list -H 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 0000000000000000000000000000000000000000 /lib/x86_64-linux-gnu/libc-2.19.so After: $ tools/perf/perf buildid-list -H 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so The fix is to record the root of the tree on the dso so that dso__set_long_name() can update the tree when the long name changes. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Cc: Waiman Long <Waiman.Long@hp.com> Fixes: 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed with rbtree") Link: http://lkml.kernel.org/r/1447408112-1920-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-13 17:48:30 +08:00
if (root)
__dso__findlink_by_longname(root, dso, NULL);
}
void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated)
{
if (name == NULL)
return;
if (dso->short_name_allocated)
free((char *)dso->short_name);
dso->short_name = name;
dso->short_name_len = strlen(name);
dso->short_name_allocated = name_allocated;
}
static void dso__set_basename(struct dso *dso)
{
char *base, *lname;
int tid;
if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) {
if (asprintf(&base, "[JIT] tid %d", tid) < 0)
return;
} else {
/*
* basename() may modify path buffer, so we must pass
* a copy.
*/
lname = strdup(dso->long_name);
if (!lname)
return;
/*
* basename() may return a pointer to internal
* storage which is reused in subsequent calls
* so copy the result.
*/
base = strdup(basename(lname));
free(lname);
if (!base)
return;
}
dso__set_short_name(dso, base, true);
}
int dso__name_len(const struct dso *dso)
{
if (!dso)
return strlen("[unknown]");
if (verbose > 0)
return dso->long_name_len;
return dso->short_name_len;
}
bool dso__loaded(const struct dso *dso)
{
return dso->loaded;
}
bool dso__sorted_by_name(const struct dso *dso)
{
return dso->sorted_by_name;
}
void dso__set_sorted_by_name(struct dso *dso)
{
dso->sorted_by_name = true;
}
struct dso *dso__new(const char *name)
{
struct dso *dso = calloc(1, sizeof(*dso) + strlen(name) + 1);
if (dso != NULL) {
strcpy(dso->name, name);
dso__set_long_name(dso, dso->name, false);
dso__set_short_name(dso, dso->name, false);
dso->symbols = dso->symbol_names = RB_ROOT_CACHED;
dso->data.cache = RB_ROOT;
dso->inlined_nodes = RB_ROOT_CACHED;
dso->srclines = RB_ROOT_CACHED;
dso->data.fd = -1;
dso->data.status = DSO_DATA_STATUS_UNKNOWN;
dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
dso->binary_type = DSO_BINARY_TYPE__NOT_FOUND;
dso->is_64_bit = (sizeof(void *) == 8);
dso->loaded = 0;
dso->rel = 0;
dso->sorted_by_name = 0;
dso->has_build_id = 0;
dso->has_srcline = 1;
dso->a2l_fails = 1;
dso->kernel = DSO_TYPE_USER;
dso->needs_swap = DSO_SWAP__UNSET;
dso->comp = COMP_ID__NONE;
perf symbols: Improve DSO long names lookup speed with rbtree With workload that spawns and destroys many threads and processes, it was found that perf-mem could took a long time to post-process the perf data after the target workload had completed its operation. The performance bottleneck was found to be the lookup and insertion of the new DSO structures (thousands of them in this case). In a dual-socket Ivy-Bridge E7-4890 v2 machine (30-core, 60-thread), the perf profile below shows what perf was doing after the profiled AIM7 shared workload completed: - 83.94% perf libc-2.11.3.so [.] __strcmp_sse42 - __strcmp_sse42 - 99.82% map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main - 13.17% perf perf [.] __dsos__findnew __dsos__findnew map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main So about 97% of CPU times were spent in the map__new() function trying to insert new DSO entry into the DSO linked list. The whole post-processing step took about 9 minutes. The DSO structures are currently searched linearly. So the total processing time will be proportional to n^2. To overcome this performance problem, the DSO code is modified to also put the DSO structures in a RB tree sorted by its long name in additional to being in a simple linked list. With this change, the processing time will become proportional to n*log(n) which will be much quicker for large n. However, the short name will still be searched using the old linear searching method. With that patch in place, the same perf-mem post-processing step took less than 30 seconds to complete. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Link: http://lkml.kernel.org/r/1412098575-27863-3-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-01 01:36:15 +08:00
RB_CLEAR_NODE(&dso->rb_node);
perf symbols: Fix dso lookup by long name and missing buildids Commit 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed with rbtree") Added a tree to lookup dsos by long name. That tree gets corrupted whenever a dso long name is changed because the tree is not updated. One effect of that is buildid-list does not work with the 'with-hits' option because dso lookup fails and results in two structs for the same dso. The first has the buildid but no hits, the second has hits but no buildid. e.g. Before: $ tools/perf/perf record ls arch certs CREDITS Documentation firmware include ipc Kconfig lib Makefile net REPORTING-BUGS scripts sound usr block COPYING crypto drivers fs init Kbuild kernel MAINTAINERS mm README samples security tools virt [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.012 MB perf.data (11 samples) ] $ tools/perf/perf buildid-list 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so $ tools/perf/perf buildid-list -H 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 0000000000000000000000000000000000000000 /lib/x86_64-linux-gnu/libc-2.19.so After: $ tools/perf/perf buildid-list -H 574da826c66538a8d9060d393a8866289bd06005 [kernel.kallsyms] 30c94dc66a1fe95180c3d68d2b89e576d5ae213c /lib/x86_64-linux-gnu/libc-2.19.so The fix is to record the root of the tree on the dso so that dso__set_long_name() can update the tree when the long name changes. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Cc: Waiman Long <Waiman.Long@hp.com> Fixes: 4598a0a6d22f ("perf symbols: Improve DSO long names lookup speed with rbtree") Link: http://lkml.kernel.org/r/1447408112-1920-2-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-13 17:48:30 +08:00
dso->root = NULL;
INIT_LIST_HEAD(&dso->node);
INIT_LIST_HEAD(&dso->data.open_entry);
pthread_mutex_init(&dso->lock, NULL);
refcount_set(&dso->refcnt, 1);
}
return dso;
}
void dso__delete(struct dso *dso)
{
perf symbols: Improve DSO long names lookup speed with rbtree With workload that spawns and destroys many threads and processes, it was found that perf-mem could took a long time to post-process the perf data after the target workload had completed its operation. The performance bottleneck was found to be the lookup and insertion of the new DSO structures (thousands of them in this case). In a dual-socket Ivy-Bridge E7-4890 v2 machine (30-core, 60-thread), the perf profile below shows what perf was doing after the profiled AIM7 shared workload completed: - 83.94% perf libc-2.11.3.so [.] __strcmp_sse42 - __strcmp_sse42 - 99.82% map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main - 13.17% perf perf [.] __dsos__findnew __dsos__findnew map__new machine__process_mmap_event perf_session_deliver_event perf_session__process_event __perf_session__process_events cmd_record cmd_mem run_builtin main __libc_start_main So about 97% of CPU times were spent in the map__new() function trying to insert new DSO entry into the DSO linked list. The whole post-processing step took about 9 minutes. The DSO structures are currently searched linearly. So the total processing time will be proportional to n^2. To overcome this performance problem, the DSO code is modified to also put the DSO structures in a RB tree sorted by its long name in additional to being in a simple linked list. With this change, the processing time will become proportional to n*log(n) which will be much quicker for large n. However, the short name will still be searched using the old linear searching method. With that patch in place, the same perf-mem post-processing step took less than 30 seconds to complete. Signed-off-by: Waiman Long <Waiman.Long@hp.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Douglas Hatch <doug.hatch@hp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Scott J Norton <scott.norton@hp.com> Link: http://lkml.kernel.org/r/1412098575-27863-3-git-send-email-Waiman.Long@hp.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2014-10-01 01:36:15 +08:00
if (!RB_EMPTY_NODE(&dso->rb_node))
pr_err("DSO %s is still in rbtree when being deleted!\n",
dso->long_name);
/* free inlines first, as they reference symbols */
inlines__tree_delete(&dso->inlined_nodes);
perf report: Cache srclines for callchain nodes On one hand this ensures that the memory is properly freed when the DSO gets freed. On the other hand this significantly speeds up the processing of the callchain nodes when lots of srclines are requested. For one of my data files e.g.: Before: Performance counter stats for 'perf report -s srcline -g srcline --stdio': 52496.495043 task-clock (msec) # 0.999 CPUs utilized 634 context-switches # 0.012 K/sec 2 cpu-migrations # 0.000 K/sec 191,561 page-faults # 0.004 M/sec 165,074,498,235 cycles # 3.144 GHz 334,170,832,408 instructions # 2.02 insn per cycle 90,220,029,745 branches # 1718.591 M/sec 654,525,177 branch-misses # 0.73% of all branches 52.533273822 seconds time elapsedProcessed 236605 events and lost 40 chunks! After: Performance counter stats for 'perf report -s srcline -g srcline --stdio': 22606.323706 task-clock (msec) # 1.000 CPUs utilized 31 context-switches # 0.001 K/sec 0 cpu-migrations # 0.000 K/sec 185,471 page-faults # 0.008 M/sec 71,188,113,681 cycles # 3.149 GHz 133,204,943,083 instructions # 1.87 insn per cycle 34,886,384,979 branches # 1543.214 M/sec 278,214,495 branch-misses # 0.80% of all branches 22.609857253 seconds time elapsed Note that the difference is only this large when `--inline` is not passed. In such situations, we would use the inliner cache and thus do not run this code path that often. I think that this cache should actually be used in other places, too. When looking at the valgrind leak report for perf report, we see tons of srclines being leaked, most notably from calls to hist_entry__get_srcline. The problem is that get_srcline has many different formatting options (show_sym, show_addr, potentially even unwind_inlines when calling __get_srcline directly). As such, the srcline cannot easily be cached for all calls, or we'd have to add caches for all formatting combinations (6 so far). An alternative would be to remove the formatting options and handle that on a different level - i.e. print the sym/addr on demand wherever we actually output something. And the unwind_inlines could be moved into a separate function that does not return the srcline. Signed-off-by: Milian Wolff <milian.wolff@kdab.com> Reviewed-by: Andi Kleen <ak@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jin Yao <yao.jin@linux.intel.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20171019113836.5548-4-milian.wolff@kdab.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2017-10-19 19:38:34 +08:00
srcline__tree_delete(&dso->srclines);
symbols__delete(&dso->symbols);
if (dso->short_name_allocated) {
zfree((char **)&dso->short_name);
dso->short_name_allocated = false;
}
if (dso->long_name_allocated) {
zfree((char **)&dso->long_name);
dso->long_name_allocated = false;
}
dso__data_close(dso);
auxtrace_cache__free(dso->auxtrace_cache);
dso_cache__free(dso);
dso__free_a2l(dso);
zfree(&dso->symsrc_filename);
nsinfo__zput(dso->nsinfo);
pthread_mutex_destroy(&dso->lock);
free(dso);
}
struct dso *dso__get(struct dso *dso)
{
if (dso)
refcount_inc(&dso->refcnt);
return dso;
}
void dso__put(struct dso *dso)
{
if (dso && refcount_dec_and_test(&dso->refcnt))
dso__delete(dso);
}
void dso__set_build_id(struct dso *dso, void *build_id)
{
memcpy(dso->build_id, build_id, sizeof(dso->build_id));
dso->has_build_id = 1;
}
bool dso__build_id_equal(const struct dso *dso, u8 *build_id)
{
return memcmp(dso->build_id, build_id, sizeof(dso->build_id)) == 0;
}
void dso__read_running_kernel_build_id(struct dso *dso, struct machine *machine)
{
char path[PATH_MAX];
if (machine__is_default_guest(machine))
return;
sprintf(path, "%s/sys/kernel/notes", machine->root_dir);
if (sysfs__read_build_id(path, dso->build_id,
sizeof(dso->build_id)) == 0)
dso->has_build_id = true;
}
int dso__kernel_module_get_build_id(struct dso *dso,
const char *root_dir)
{
char filename[PATH_MAX];
/*
* kernel module short names are of the form "[module]" and
* we need just "module" here.
*/
const char *name = dso->short_name + 1;
snprintf(filename, sizeof(filename),
"%s/sys/module/%.*s/notes/.note.gnu.build-id",
root_dir, (int)strlen(name) - 1, name);
if (sysfs__read_build_id(filename, dso->build_id,
sizeof(dso->build_id)) == 0)
dso->has_build_id = true;
return 0;
}
bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
{
bool have_build_id = false;
struct dso *pos;
struct nscookie nsc;
list_for_each_entry(pos, head, node) {
if (with_hits && !pos->hit && !dso__is_vdso(pos))
continue;
if (pos->has_build_id) {
have_build_id = true;
continue;
}
nsinfo__mountns_enter(pos->nsinfo, &nsc);
if (filename__read_build_id(pos->long_name, pos->build_id,
sizeof(pos->build_id)) > 0) {
have_build_id = true;
pos->has_build_id = true;
}
nsinfo__mountns_exit(&nsc);
}
return have_build_id;
}
void __dsos__add(struct dsos *dsos, struct dso *dso)
{
list_add_tail(&dso->node, &dsos->head);
__dso__findlink_by_longname(&dsos->root, dso, NULL);
/*
* It is now in the linked list, grab a reference, then garbage collect
* this when needing memory, by looking at LRU dso instances in the
* list with atomic_read(&dso->refcnt) == 1, i.e. no references
* anywhere besides the one for the list, do, under a lock for the
* list: remove it from the list, then a dso__put(), that probably will
* be the last and will then call dso__delete(), end of life.
*
* That, or at the end of the 'struct machine' lifetime, when all
* 'struct dso' instances will be removed from the list, in
* dsos__exit(), if they have no other reference from some other data
* structure.
*
* E.g.: after processing a 'perf.data' file and storing references
* to objects instantiated while processing events, we will have
* references to the 'thread', 'map', 'dso' structs all from 'struct
* hist_entry' instances, but we may not need anything not referenced,
* so we might as well call machines__exit()/machines__delete() and
* garbage collect it.
*/
dso__get(dso);
}
void dsos__add(struct dsos *dsos, struct dso *dso)
{
down_write(&dsos->lock);
__dsos__add(dsos, dso);
up_write(&dsos->lock);
}
struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
{
struct dso *pos;
perf symbols: Fix vdso list searching When "perf record" was used on a large machine with a lot of CPUs, the perf post-processing time (the time after the workload was done until the perf command itself exited) could take a lot of minutes and even hours depending on how large the resulting perf.data file was. While running AIM7 1500-user high_systime workload on a 80-core x86-64 system with a 3.9 kernel (with only the -s -a options used), the workload itself took about 2 minutes to run and the perf.data file had a size of 1108.746 MB. However, the post-processing step took more than 10 minutes. With a gprof-profiled perf binary, the time spent by perf was as follows: % cumulative self self total time seconds seconds calls s/call s/call name 96.90 822.10 822.10 192156 0.00 0.00 dsos__find 0.81 828.96 6.86 172089958 0.00 0.00 rb_next 0.41 832.44 3.48 48539289 0.00 0.00 rb_erase So 97% (822 seconds) of the time was spent in a single dsos_find() function. After analyzing the call-graph data below: ----------------------------------------------- 0.00 822.12 192156/192156 map__new [6] [7] 96.9 0.00 822.12 192156 vdso__dso_findnew [7] 822.10 0.00 192156/192156 dsos__find [8] 0.01 0.00 192156/192156 dsos__add [62] 0.01 0.00 192156/192366 dso__new [61] 0.00 0.00 1/45282525 memdup [31] 0.00 0.00 192156/192230 dso__set_long_name [91] ----------------------------------------------- 822.10 0.00 192156/192156 vdso__dso_findnew [7] [8] 96.9 822.10 0.00 192156 dsos__find [8] ----------------------------------------------- It was found that the vdso__dso_findnew() function failed to locate VDSO__MAP_NAME ("[vdso]") in the dso list and have to insert a new entry at the end for 192156 times. This problem is due to the fact that there are 2 types of name in the dso entry - short name and long name. The initial dso__new() adds "[vdso]" to both the short and long names. After that, vdso__dso_findnew() modifies the long name to something like /tmp/perf-vdso.so-NoXkDj. The dsos__find() function only compares the long name. As a result, the same vdso entry is duplicated many time in the dso list. This bug increases memory consumption as well as slows the symbol processing time to a crawl. To resolve this problem, the dsos__find() function interface was modified to enable searching either the long name or the short name. The vdso__dso_findnew() will now search only the short name while the other call sites search for the long name as before. With this change, the cpu time of perf was reduced from 848.38s to 15.77s and dsos__find() only accounted for 0.06% of the total time. 0.06 15.73 0.01 192151 0.00 0.00 dsos__find Signed-off-by: Waiman Long <Waiman.Long@hp.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: "Chandramouleeswaran, Aswin" <aswin@hp.com> Cc: "Norton, Scott J" <scott.norton@hp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@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/1368110568-64714-1-git-send-email-Waiman.Long@hp.com [ replaced TRUE/FALSE with stdbool.h equivalents, fixing builds where those macros are not present (NO_LIBPYTHON=1 NO_LIBPERL=1), fix from Jiri Olsa ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-05-09 22:42:48 +08:00
if (cmp_short) {
list_for_each_entry(pos, &dsos->head, node)
perf symbols: Fix vdso list searching When "perf record" was used on a large machine with a lot of CPUs, the perf post-processing time (the time after the workload was done until the perf command itself exited) could take a lot of minutes and even hours depending on how large the resulting perf.data file was. While running AIM7 1500-user high_systime workload on a 80-core x86-64 system with a 3.9 kernel (with only the -s -a options used), the workload itself took about 2 minutes to run and the perf.data file had a size of 1108.746 MB. However, the post-processing step took more than 10 minutes. With a gprof-profiled perf binary, the time spent by perf was as follows: % cumulative self self total time seconds seconds calls s/call s/call name 96.90 822.10 822.10 192156 0.00 0.00 dsos__find 0.81 828.96 6.86 172089958 0.00 0.00 rb_next 0.41 832.44 3.48 48539289 0.00 0.00 rb_erase So 97% (822 seconds) of the time was spent in a single dsos_find() function. After analyzing the call-graph data below: ----------------------------------------------- 0.00 822.12 192156/192156 map__new [6] [7] 96.9 0.00 822.12 192156 vdso__dso_findnew [7] 822.10 0.00 192156/192156 dsos__find [8] 0.01 0.00 192156/192156 dsos__add [62] 0.01 0.00 192156/192366 dso__new [61] 0.00 0.00 1/45282525 memdup [31] 0.00 0.00 192156/192230 dso__set_long_name [91] ----------------------------------------------- 822.10 0.00 192156/192156 vdso__dso_findnew [7] [8] 96.9 822.10 0.00 192156 dsos__find [8] ----------------------------------------------- It was found that the vdso__dso_findnew() function failed to locate VDSO__MAP_NAME ("[vdso]") in the dso list and have to insert a new entry at the end for 192156 times. This problem is due to the fact that there are 2 types of name in the dso entry - short name and long name. The initial dso__new() adds "[vdso]" to both the short and long names. After that, vdso__dso_findnew() modifies the long name to something like /tmp/perf-vdso.so-NoXkDj. The dsos__find() function only compares the long name. As a result, the same vdso entry is duplicated many time in the dso list. This bug increases memory consumption as well as slows the symbol processing time to a crawl. To resolve this problem, the dsos__find() function interface was modified to enable searching either the long name or the short name. The vdso__dso_findnew() will now search only the short name while the other call sites search for the long name as before. With this change, the cpu time of perf was reduced from 848.38s to 15.77s and dsos__find() only accounted for 0.06% of the total time. 0.06 15.73 0.01 192151 0.00 0.00 dsos__find Signed-off-by: Waiman Long <Waiman.Long@hp.com> Acked-by: Ingo Molnar <mingo@kernel.org> Cc: "Chandramouleeswaran, Aswin" <aswin@hp.com> Cc: "Norton, Scott J" <scott.norton@hp.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@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/1368110568-64714-1-git-send-email-Waiman.Long@hp.com [ replaced TRUE/FALSE with stdbool.h equivalents, fixing builds where those macros are not present (NO_LIBPYTHON=1 NO_LIBPERL=1), fix from Jiri Olsa ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2013-05-09 22:42:48 +08:00
if (strcmp(pos->short_name, name) == 0)
return pos;
return NULL;
}
return __dso__find_by_longname(&dsos->root, name);
}
struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
{
struct dso *dso;
down_read(&dsos->lock);
dso = __dsos__find(dsos, name, cmp_short);
up_read(&dsos->lock);
return dso;
}
struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
{
struct dso *dso = dso__new(name);
if (dso != NULL) {
__dsos__add(dsos, dso);
dso__set_basename(dso);
perf tools: Fix __dsos__addnew to put dso after adding it to the list __dsos__addnew should drop the constructor reference to dso after adding it to the list, because __dsos__add() will get a reference that will be kept while it is in the list. This fixes DSO leaks when entries are removed to the list and the refcount never gets to zero. Refcnt debugger shows: ==== [0] ==== Unreclaimed dso: 0x2fccab0 Refcount +1 => 1 at ./perf(dso__new+0x1ff) [0x4a62df] ./perf(__dsos__addnew+0x29) [0x4a6e19] ./perf(dsos__findnew+0xd1) [0x4a7281] ./perf(machine__findnew_kernel+0x27) [0x4a5e17] ./perf() [0x4b8df2] ./perf(machine__create_kernel_maps+0x28) [0x4bb528] ./perf(machine__new_host+0xfa) [0x4bb84a] ./perf(init_probe_symbol_maps+0x93) [0x506713] ./perf() [0x455ffa] ./perf(cmd_probe+0x6c) [0x4566bc] ./perf() [0x47abc5] ./perf(main+0x610) [0x421f90] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f46df132af5] ./perf() [0x4220a9] Refcount +1 => 2 at ./perf(__dsos__addnew+0xfb) [0x4a6eeb] ./perf(dsos__findnew+0xd1) [0x4a7281] ./perf(machine__findnew_kernel+0x27) [0x4a5e17] ./perf() [0x4b8df2] ./perf(machine__create_kernel_maps+0x28) [0x4bb528] ./perf(machine__new_host+0xfa) [0x4bb84a] ./perf(init_probe_symbol_maps+0x93) [0x506713] ./perf() [0x455ffa] ./perf(cmd_probe+0x6c) [0x4566bc] ./perf() [0x47abc5] ./perf(main+0x610) [0x421f90] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f46df132af5] ./perf() [0x4220a9] Refcount +1 => 3 at ./perf(dsos__findnew+0x7e) [0x4a722e] ./perf(machine__findnew_kernel+0x27) [0x4a5e17] ./perf() [0x4b8df2] ./perf(machine__create_kernel_maps+0x28) [0x4bb528] ./perf(machine__new_host+0xfa) [0x4bb84a] ./perf(init_probe_symbol_maps+0x93) [0x506713] ./perf() [0x455ffa] ./perf(cmd_probe+0x6c) [0x4566bc] ./perf() [0x47abc5] ./perf(main+0x610) [0x421f90] /lib64/libc.so.6(__libc_start_main+0xf5) [0x7f46df132af5] ./perf() [0x4220a9] [snip] 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/20151118064031.30709.81460.stgit@localhost.localdomain Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-11-18 14:40:31 +08:00
/* Put dso here because __dsos_add already got it */
dso__put(dso);
}
return dso;
}
struct dso *__dsos__findnew(struct dsos *dsos, const char *name)
{
struct dso *dso = __dsos__find(dsos, name, false);
return dso ? dso : __dsos__addnew(dsos, name);
}
struct dso *dsos__findnew(struct dsos *dsos, const char *name)
{
struct dso *dso;
down_write(&dsos->lock);
dso = dso__get(__dsos__findnew(dsos, name));
up_write(&dsos->lock);
return dso;
}
size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
bool (skip)(struct dso *dso, int parm), int parm)
{
struct dso *pos;
size_t ret = 0;
list_for_each_entry(pos, head, node) {
if (skip && skip(pos, parm))
continue;
ret += dso__fprintf_buildid(pos, fp);
ret += fprintf(fp, " %s\n", pos->long_name);
}
return ret;
}
size_t __dsos__fprintf(struct list_head *head, FILE *fp)
{
struct dso *pos;
size_t ret = 0;
list_for_each_entry(pos, head, node) {
ret += dso__fprintf(pos, fp);
}
return ret;
}
size_t dso__fprintf_buildid(struct dso *dso, FILE *fp)
{
char sbuild_id[SBUILD_ID_SIZE];
build_id__sprintf(dso->build_id, sizeof(dso->build_id), sbuild_id);
return fprintf(fp, "%s", sbuild_id);
}
size_t dso__fprintf(struct dso *dso, FILE *fp)
{
struct rb_node *nd;
size_t ret = fprintf(fp, "dso: %s (", dso->short_name);
if (dso->short_name != dso->long_name)
ret += fprintf(fp, "%s, ", dso->long_name);
ret += fprintf(fp, "%sloaded, ", dso__loaded(dso) ? "" : "NOT ");
ret += dso__fprintf_buildid(dso, fp);
ret += fprintf(fp, ")\n");
for (nd = rb_first_cached(&dso->symbols); nd; nd = rb_next(nd)) {
struct symbol *pos = rb_entry(nd, struct symbol, rb_node);
ret += symbol__fprintf(pos, fp);
}
return ret;
}
enum dso_type dso__type(struct dso *dso, struct machine *machine)
{
int fd;
enum dso_type type = DSO__TYPE_UNKNOWN;
fd = dso__data_get_fd(dso, machine);
if (fd >= 0) {
type = dso__type_fd(fd);
dso__data_put_fd(dso);
}
return type;
}
perf symbols: Save DSO loading errno to better report errors Before, when some problem happened while trying to load the kernel symtab, 'perf top' would show: ┌─Warning:───────────────────────────┐ │The vmlinux file can't be used. │ │Kernel samples will not be resolved.│ │ │ │ │ │Press any key... │ └────────────────────────────────────┘ Now, it reports: # perf top --vmlinux /dev/null ┌─Warning:───────────────────────────────────────────┐ │The /tmp/passwd file can't be used: Invalid ELF file│ │Kernel samples will not be resolved. │ │ │ │ │ │Press any key... │ └────────────────────────────────────────────────────┘ This is possible because we now register the reason for not being able to load the symtab in the dso->load_errno member, and provide a dso__strerror_load() routine to format this error into a strerror like string with a short reason for the error while loading. That can be just forwarding the dso__strerror_load() call to strerror_r(), or, for a separate errno range providing a custom message. Reported-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-u5rb5uq63xqhkfb8uv2lxd5u@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-03-24 22:49:02 +08:00
int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
{
int idx, errnum = dso->load_errno;
/*
* This must have a same ordering as the enum dso_load_errno.
*/
static const char *dso_load__error_str[] = {
"Internal tools/perf/ library error",
"Invalid ELF file",
"Can not read build id",
"Mismatching build id",
"Decompression failure",
};
BUG_ON(buflen == 0);
if (errnum >= 0) {
const char *err = str_error_r(errnum, buf, buflen);
perf symbols: Save DSO loading errno to better report errors Before, when some problem happened while trying to load the kernel symtab, 'perf top' would show: ┌─Warning:───────────────────────────┐ │The vmlinux file can't be used. │ │Kernel samples will not be resolved.│ │ │ │ │ │Press any key... │ └────────────────────────────────────┘ Now, it reports: # perf top --vmlinux /dev/null ┌─Warning:───────────────────────────────────────────┐ │The /tmp/passwd file can't be used: Invalid ELF file│ │Kernel samples will not be resolved. │ │ │ │ │ │Press any key... │ └────────────────────────────────────────────────────┘ This is possible because we now register the reason for not being able to load the symtab in the dso->load_errno member, and provide a dso__strerror_load() routine to format this error into a strerror like string with a short reason for the error while loading. That can be just forwarding the dso__strerror_load() call to strerror_r(), or, for a separate errno range providing a custom message. Reported-by: Ingo Molnar <mingo@kernel.org> Acked-by: Jiri Olsa <jolsa@kernel.org> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Borislav Petkov <bp@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Don Zickus <dzickus@redhat.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-u5rb5uq63xqhkfb8uv2lxd5u@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2015-03-24 22:49:02 +08:00
if (err != buf)
scnprintf(buf, buflen, "%s", err);
return 0;
}
if (errnum < __DSO_LOAD_ERRNO__START || errnum >= __DSO_LOAD_ERRNO__END)
return -1;
idx = errnum - __DSO_LOAD_ERRNO__START;
scnprintf(buf, buflen, "%s", dso_load__error_str[idx]);
return 0;
}