* [PATCH 0/5] perf record: Put a copy of kcore into the perf.data directory @ 2019-10-04 8:31 Adrian Hunter 2019-10-04 8:31 ` [PATCH 1/5] perf data: Correctly identify directory data files Adrian Hunter ` (6 more replies) 0 siblings, 7 replies; 24+ messages in thread From: Adrian Hunter @ 2019-10-04 8:31 UTC (permalink / raw) To: Arnaldo Carvalho de Melo, Jiri Olsa; +Cc: linux-kernel Hi Here are patches to add a new 'perf record' option '--kcore' which will put a copy of /proc/kcore, kallsyms and modules into a perf.data directory. Note, that without the --kcore option, output goes to a file as previously. The tools' -o and -i options work with either a file name or directory name. Example: $ sudo perf record --kcore uname $ sudo tree perf.data perf.data ├── kcore_dir │ ├── kallsyms │ ├── kcore │ └── modules └── data $ sudo perf script -v build id event received for vmlinux: 1eaa285996affce2d74d8e66dcea09a80c9941de build id event received for [vdso]: 8bbaf5dc62a9b644b4d4e4539737e104e4a84541 Samples for 'cycles' event do not have CPU attribute set. Skipping 'cpu' field. Using CPUID GenuineIntel-6-8E-A Using perf.data/kcore_dir/kcore for kernel data Using perf.data/kcore_dir/kallsyms for symbols perf 19058 506778.423729: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423733: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423734: 7 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423736: 117 cycles: ffffffffa2caa54a native_write_msr+0xa (vmlinux) perf 19058 506778.423738: 2092 cycles: ffffffffa2c9b7b0 native_apic_msr_write+0x0 (vmlinux) perf 19058 506778.423740: 37380 cycles: ffffffffa2f121d0 perf_event_addr_filters_exec+0x0 (vmlinux) uname 19058 506778.423751: 582673 cycles: ffffffffa303a407 propagate_protected_usage+0x147 (vmlinux) uname 19058 506778.423892: 2241841 cycles: ffffffffa2cae0c9 unwind_next_frame.part.5+0x79 (vmlinux) uname 19058 506778.424430: 2457397 cycles: ffffffffa3019232 check_memory_region+0x52 (vmlinux) Adrian Hunter (5): perf data: Correctly identify directory data files perf data: Move perf_dir_version into data.h perf data: Rename directory "header" file to "data" perf tools: Support single perf.data file directory perf record: Put a copy of kcore into the perf.data directory tools/perf/Documentation/perf-record.txt | 3 ++ .../Documentation/perf.data-directory-format.txt | 63 ++++++++++++++++++++++ tools/perf/builtin-record.c | 54 ++++++++++++++++++- tools/perf/util/data.c | 46 ++++++++++++++-- tools/perf/util/data.h | 12 +++++ tools/perf/util/header.h | 4 -- tools/perf/util/record.h | 1 + tools/perf/util/session.c | 4 ++ tools/perf/util/util.c | 19 ++++++- 9 files changed, 197 insertions(+), 9 deletions(-) create mode 100644 tools/perf/Documentation/perf.data-directory-format.txt Regards Adrian ^ permalink raw reply [flat|nested] 24+ messages in thread
* [PATCH 1/5] perf data: Correctly identify directory data files 2019-10-04 8:31 [PATCH 0/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter @ 2019-10-04 8:31 ` Adrian Hunter 2019-11-12 11:18 ` [tip: perf/core] " tip-bot2 for Adrian Hunter 2019-10-04 8:31 ` [PATCH 2/5] perf data: Move perf_dir_version into data.h Adrian Hunter ` (5 subsequent siblings) 6 siblings, 1 reply; 24+ messages in thread From: Adrian Hunter @ 2019-10-04 8:31 UTC (permalink / raw) To: Arnaldo Carvalho de Melo, Jiri Olsa; +Cc: linux-kernel In order to rename the "header" file to "data" without conflicting, correctly identify the non-header files as starting with "data." Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> --- tools/perf/util/data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 88fba2ba549f..8993253c5564 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -96,7 +96,7 @@ int perf_data__open_dir(struct perf_data *data) if (stat(path, &st)) continue; - if (!S_ISREG(st.st_mode) || strncmp(dent->d_name, "data", 4)) + if (!S_ISREG(st.st_mode) || strncmp(dent->d_name, "data.", 5)) continue; ret = -ENOMEM; -- 2.17.1 ^ permalink raw reply related [flat|nested] 24+ messages in thread
* [tip: perf/core] perf data: Correctly identify directory data files 2019-10-04 8:31 ` [PATCH 1/5] perf data: Correctly identify directory data files Adrian Hunter @ 2019-11-12 11:18 ` tip-bot2 for Adrian Hunter 0 siblings, 0 replies; 24+ messages in thread From: tip-bot2 for Adrian Hunter @ 2019-11-12 11:18 UTC (permalink / raw) To: linux-tip-commits Cc: Adrian Hunter, Jiri Olsa, Arnaldo Carvalho de Melo, Ingo Molnar, Borislav Petkov, linux-kernel The following commit has been merged into the perf/core branch of tip: Commit-ID: 490e6db09a9035d7b40a328a2a004ef70b6bdee6 Gitweb: https://git.kernel.org/tip/490e6db09a9035d7b40a328a2a004ef70b6bdee6 Author: Adrian Hunter <adrian.hunter@intel.com> AuthorDate: Fri, 04 Oct 2019 11:31:17 +03:00 Committer: Arnaldo Carvalho de Melo <acme@redhat.com> CommitterDate: Wed, 06 Nov 2019 15:43:05 -03:00 perf data: Correctly identify directory data files In order to rename the "header" file to "data" without conflicting, correctly identify the non-header files as starting with "data." Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Link: http://lore.kernel.org/lkml/20191004083121.12182-2-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/util/data.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 88fba2b..8993253 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -96,7 +96,7 @@ int perf_data__open_dir(struct perf_data *data) if (stat(path, &st)) continue; - if (!S_ISREG(st.st_mode) || strncmp(dent->d_name, "data", 4)) + if (!S_ISREG(st.st_mode) || strncmp(dent->d_name, "data.", 5)) continue; ret = -ENOMEM; ^ permalink raw reply related [flat|nested] 24+ messages in thread
* [PATCH 2/5] perf data: Move perf_dir_version into data.h 2019-10-04 8:31 [PATCH 0/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter 2019-10-04 8:31 ` [PATCH 1/5] perf data: Correctly identify directory data files Adrian Hunter @ 2019-10-04 8:31 ` Adrian Hunter 2019-11-12 11:18 ` [tip: perf/core] " tip-bot2 for Adrian Hunter 2019-10-04 8:31 ` [PATCH 3/5] perf data: Rename directory "header" file to "data" Adrian Hunter ` (4 subsequent siblings) 6 siblings, 1 reply; 24+ messages in thread From: Adrian Hunter @ 2019-10-04 8:31 UTC (permalink / raw) To: Arnaldo Carvalho de Melo, Jiri Olsa; +Cc: linux-kernel perf_dir_version belongs to struct perf_data which is declared in data.h. To allow its use in inline perf_data functions, move perf_dir_version to data.h Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> --- tools/perf/util/data.h | 4 ++++ tools/perf/util/header.h | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 259868a39019..218fe9a16801 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -9,6 +9,10 @@ enum perf_data_mode { PERF_DATA_MODE_READ, }; +enum perf_dir_version { + PERF_DIR_VERSION = 1, +}; + struct perf_data_file { char *path; int fd; diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index ca53a929e9fd..840f95cee349 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -52,10 +52,6 @@ enum perf_header_version { PERF_HEADER_VERSION_2, }; -enum perf_dir_version { - PERF_DIR_VERSION = 1, -}; - struct perf_file_section { u64 offset; u64 size; -- 2.17.1 ^ permalink raw reply related [flat|nested] 24+ messages in thread
* [tip: perf/core] perf data: Move perf_dir_version into data.h 2019-10-04 8:31 ` [PATCH 2/5] perf data: Move perf_dir_version into data.h Adrian Hunter @ 2019-11-12 11:18 ` tip-bot2 for Adrian Hunter 0 siblings, 0 replies; 24+ messages in thread From: tip-bot2 for Adrian Hunter @ 2019-11-12 11:18 UTC (permalink / raw) To: linux-tip-commits Cc: Adrian Hunter, Jiri Olsa, Arnaldo Carvalho de Melo, Ingo Molnar, Borislav Petkov, linux-kernel The following commit has been merged into the perf/core branch of tip: Commit-ID: 3dedec4f5ccc8048b9a2cfe89838c3b3275b6b2b Gitweb: https://git.kernel.org/tip/3dedec4f5ccc8048b9a2cfe89838c3b3275b6b2b Author: Adrian Hunter <adrian.hunter@intel.com> AuthorDate: Fri, 04 Oct 2019 11:31:18 +03:00 Committer: Arnaldo Carvalho de Melo <acme@redhat.com> CommitterDate: Wed, 06 Nov 2019 15:43:05 -03:00 perf data: Move perf_dir_version into data.h perf_dir_version belongs to struct perf_data which is declared in data.h. To allow its use in inline perf_data functions, move perf_dir_version to data.h Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Link: http://lore.kernel.org/lkml/20191004083121.12182-3-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/util/data.h | 4 ++++ tools/perf/util/header.h | 4 ---- 2 files changed, 4 insertions(+), 4 deletions(-) diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 259868a..218fe9a 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -9,6 +9,10 @@ enum perf_data_mode { PERF_DATA_MODE_READ, }; +enum perf_dir_version { + PERF_DIR_VERSION = 1, +}; + struct perf_data_file { char *path; int fd; diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h index ca53a92..840f95c 100644 --- a/tools/perf/util/header.h +++ b/tools/perf/util/header.h @@ -52,10 +52,6 @@ enum perf_header_version { PERF_HEADER_VERSION_2, }; -enum perf_dir_version { - PERF_DIR_VERSION = 1, -}; - struct perf_file_section { u64 offset; u64 size; ^ permalink raw reply related [flat|nested] 24+ messages in thread
* [PATCH 3/5] perf data: Rename directory "header" file to "data" 2019-10-04 8:31 [PATCH 0/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter 2019-10-04 8:31 ` [PATCH 1/5] perf data: Correctly identify directory data files Adrian Hunter 2019-10-04 8:31 ` [PATCH 2/5] perf data: Move perf_dir_version into data.h Adrian Hunter @ 2019-10-04 8:31 ` Adrian Hunter 2019-11-12 11:18 ` [tip: perf/core] " tip-bot2 for Adrian Hunter 2019-10-04 8:31 ` [PATCH 4/5] perf tools: Support single perf.data file directory Adrian Hunter ` (3 subsequent siblings) 6 siblings, 1 reply; 24+ messages in thread From: Adrian Hunter @ 2019-10-04 8:31 UTC (permalink / raw) To: Arnaldo Carvalho de Melo, Jiri Olsa; +Cc: linux-kernel In preparation to support a single file directory format, rename "header" to "data" because "header" is a mis-leading name when there is only 1 file. Note, in the multi-file case, the "header" file also contains data. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> --- tools/perf/util/data.c | 2 +- tools/perf/util/util.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 8993253c5564..df173f0bf654 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -306,7 +306,7 @@ static int open_dir(struct perf_data *data) * So far we open only the header, so we can read the data version and * layout. */ - if (asprintf(&data->file.path, "%s/header", data->path) < 0) + if (asprintf(&data->file.path, "%s/data", data->path) < 0) return -1; if (perf_data__is_write(data) && diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 5eda6e19c947..56f30ad29ca7 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -183,7 +183,7 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat) int rm_rf_perf_data(const char *path) { const char *pat[] = { - "header", + "data", "data.*", NULL, }; -- 2.17.1 ^ permalink raw reply related [flat|nested] 24+ messages in thread
* [tip: perf/core] perf data: Rename directory "header" file to "data" 2019-10-04 8:31 ` [PATCH 3/5] perf data: Rename directory "header" file to "data" Adrian Hunter @ 2019-11-12 11:18 ` tip-bot2 for Adrian Hunter 0 siblings, 0 replies; 24+ messages in thread From: tip-bot2 for Adrian Hunter @ 2019-11-12 11:18 UTC (permalink / raw) To: linux-tip-commits Cc: Adrian Hunter, Jiri Olsa, Arnaldo Carvalho de Melo, Ingo Molnar, Borislav Petkov, linux-kernel The following commit has been merged into the perf/core branch of tip: Commit-ID: 9b70b9db4e0cc03d224795a18088fdb916dec823 Gitweb: https://git.kernel.org/tip/9b70b9db4e0cc03d224795a18088fdb916dec823 Author: Adrian Hunter <adrian.hunter@intel.com> AuthorDate: Fri, 04 Oct 2019 11:31:19 +03:00 Committer: Arnaldo Carvalho de Melo <acme@redhat.com> CommitterDate: Wed, 06 Nov 2019 15:43:05 -03:00 perf data: Rename directory "header" file to "data" In preparation to support a single file directory format, rename "header" to "data" because "header" is a mis-leading name when there is only 1 file. Note, in the multi-file case, the "header" file also contains data. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Link: http://lore.kernel.org/lkml/20191004083121.12182-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/util/data.c | 2 +- tools/perf/util/util.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 8993253..df173f0 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -306,7 +306,7 @@ static int open_dir(struct perf_data *data) * So far we open only the header, so we can read the data version and * layout. */ - if (asprintf(&data->file.path, "%s/header", data->path) < 0) + if (asprintf(&data->file.path, "%s/data", data->path) < 0) return -1; if (perf_data__is_write(data) && diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index ae56c76..3096654 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -185,7 +185,7 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat) int rm_rf_perf_data(const char *path) { const char *pat[] = { - "header", + "data", "data.*", NULL, }; ^ permalink raw reply related [flat|nested] 24+ messages in thread
* [PATCH 4/5] perf tools: Support single perf.data file directory 2019-10-04 8:31 [PATCH 0/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter ` (2 preceding siblings ...) 2019-10-04 8:31 ` [PATCH 3/5] perf data: Rename directory "header" file to "data" Adrian Hunter @ 2019-10-04 8:31 ` Adrian Hunter 2019-10-07 11:20 ` Jiri Olsa 2019-11-12 11:18 ` [tip: perf/core] perf data: Support single perf.data file directory tip-bot2 for Adrian Hunter 2019-10-04 8:31 ` [PATCH 5/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter ` (2 subsequent siblings) 6 siblings, 2 replies; 24+ messages in thread From: Adrian Hunter @ 2019-10-04 8:31 UTC (permalink / raw) To: Arnaldo Carvalho de Melo, Jiri Olsa; +Cc: linux-kernel Support directory output that contains a regular perf.data file, named "data". By default the directory is named perf.data i.e. perf.data └── data Most of the infrastucture to support a directory is already there. This patch makes the changes needed to support the format above. Presently there is no 'perf record' option to output a directory. This is preparation for adding support for putting a copy of /proc/kcore in the directory. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> --- .../perf.data-directory-format.txt | 28 +++++++++++++++++++ tools/perf/builtin-record.c | 2 +- tools/perf/util/data.c | 9 +++++- tools/perf/util/data.h | 6 ++++ 4 files changed, 43 insertions(+), 2 deletions(-) create mode 100644 tools/perf/Documentation/perf.data-directory-format.txt diff --git a/tools/perf/Documentation/perf.data-directory-format.txt b/tools/perf/Documentation/perf.data-directory-format.txt new file mode 100644 index 000000000000..4bf08908178d --- /dev/null +++ b/tools/perf/Documentation/perf.data-directory-format.txt @@ -0,0 +1,28 @@ +perf.data directory format + +DISCLAIMER This is not ABI yet and is subject to possible change + in following versions of perf. We will remove this + disclaimer once the directory format soaks in. + + +This document describes the on-disk perf.data directory format. + +The layout is described by HEADER_DIR_FORMAT feature. +Currently it holds only version number (0): + + HEADER_DIR_FORMAT = 24 + + struct { + uint64_t version; + } + +The current only version value 0 means that: + - there is a single perf.data file named 'data' within the directory. + e.g. + + $ tree -ps perf.data + perf.data + └── [-rw------- 25912] data + +Future versions are expected to describe different data files +layout according to special needs. diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 23332861de6e..fceac9d42b4e 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -537,7 +537,7 @@ static int record__process_auxtrace(struct perf_tool *tool, size_t padding; u8 pad[8] = {0}; - if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) { + if (!perf_data__is_pipe(data) && perf_data__is_single_file(data)) { off_t file_offset; int fd = perf_data__fd(data); int err; diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index df173f0bf654..964ea101dba6 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -76,6 +76,13 @@ int perf_data__open_dir(struct perf_data *data) DIR *dir; int nr = 0; + /* + * Directory containing a single regular perf data file which is already + * open, means there is nothing more to do here. + */ + if (perf_data__is_single_file(data)) + return 0; + if (WARN_ON(!data->is_dir)) return -EINVAL; @@ -406,7 +413,7 @@ unsigned long perf_data__size(struct perf_data *data) u64 size = data->file.size; int i; - if (!data->is_dir) + if (perf_data__is_single_file(data)) return size; for (i = 0; i < data->dir.nr; i++) { diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 218fe9a16801..f68815f7e428 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -10,6 +10,7 @@ enum perf_data_mode { }; enum perf_dir_version { + PERF_DIR_SINGLE_FILE = 0, PERF_DIR_VERSION = 1, }; @@ -54,6 +55,11 @@ static inline bool perf_data__is_dir(struct perf_data *data) return data->is_dir; } +static inline bool perf_data__is_single_file(struct perf_data *data) +{ + return data->dir.version == PERF_DIR_SINGLE_FILE; +} + static inline int perf_data__fd(struct perf_data *data) { return data->file.fd; -- 2.17.1 ^ permalink raw reply related [flat|nested] 24+ messages in thread
* Re: [PATCH 4/5] perf tools: Support single perf.data file directory 2019-10-04 8:31 ` [PATCH 4/5] perf tools: Support single perf.data file directory Adrian Hunter @ 2019-10-07 11:20 ` Jiri Olsa 2019-10-07 12:06 ` Adrian Hunter 2019-11-12 11:18 ` [tip: perf/core] perf session: Fix indent in perf_session__new()" tip-bot2 for Jiri Olsa 2019-11-12 11:18 ` [tip: perf/core] perf data: Support single perf.data file directory tip-bot2 for Adrian Hunter 1 sibling, 2 replies; 24+ messages in thread From: Jiri Olsa @ 2019-10-07 11:20 UTC (permalink / raw) To: Adrian Hunter; +Cc: Arnaldo Carvalho de Melo, linux-kernel On Fri, Oct 04, 2019 at 11:31:20AM +0300, Adrian Hunter wrote: SNIP > u8 pad[8] = {0}; > > - if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) { > + if (!perf_data__is_pipe(data) && perf_data__is_single_file(data)) { > off_t file_offset; > int fd = perf_data__fd(data); > int err; > diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c > index df173f0bf654..964ea101dba6 100644 > --- a/tools/perf/util/data.c > +++ b/tools/perf/util/data.c > @@ -76,6 +76,13 @@ int perf_data__open_dir(struct perf_data *data) > DIR *dir; > int nr = 0; > > + /* > + * Directory containing a single regular perf data file which is already > + * open, means there is nothing more to do here. > + */ > + if (perf_data__is_single_file(data)) > + return 0; > + cool, I like this approach much more than the previous flag any change you (if there's repost) or Arnaldo could squeeze in indent change below? thanks, jirka --- diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index bfa80fe8d369..7f567a521cea 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -227,8 +227,8 @@ struct perf_session *perf_session__new(struct perf_data *data, /* Open the directory data. */ if (data->is_dir) { ret = perf_data__open_dir(data); - if (ret) - goto out_delete; + if (ret) + goto out_delete; } if (!symbol_conf.kallsyms_name && ^ permalink raw reply related [flat|nested] 24+ messages in thread
* Re: [PATCH 4/5] perf tools: Support single perf.data file directory 2019-10-07 11:20 ` Jiri Olsa @ 2019-10-07 12:06 ` Adrian Hunter 2019-10-21 12:42 ` Adrian Hunter 2019-11-12 11:18 ` [tip: perf/core] perf session: Fix indent in perf_session__new()" tip-bot2 for Jiri Olsa 1 sibling, 1 reply; 24+ messages in thread From: Adrian Hunter @ 2019-10-07 12:06 UTC (permalink / raw) To: Jiri Olsa; +Cc: Arnaldo Carvalho de Melo, linux-kernel On 7/10/19 2:20 PM, Jiri Olsa wrote: > On Fri, Oct 04, 2019 at 11:31:20AM +0300, Adrian Hunter wrote: > > SNIP > >> u8 pad[8] = {0}; >> >> - if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) { >> + if (!perf_data__is_pipe(data) && perf_data__is_single_file(data)) { >> off_t file_offset; >> int fd = perf_data__fd(data); >> int err; >> diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c >> index df173f0bf654..964ea101dba6 100644 >> --- a/tools/perf/util/data.c >> +++ b/tools/perf/util/data.c >> @@ -76,6 +76,13 @@ int perf_data__open_dir(struct perf_data *data) >> DIR *dir; >> int nr = 0; >> >> + /* >> + * Directory containing a single regular perf data file which is already >> + * open, means there is nothing more to do here. >> + */ >> + if (perf_data__is_single_file(data)) >> + return 0; >> + > > cool, I like this approach much more than the previous flag Yes it is much nicer. Thanks for your direction on that. > > any change you (if there's repost) or Arnaldo > could squeeze in indent change below? Sent a patch, to be applied before these. > > thanks, > jirka > > > --- > diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c > index bfa80fe8d369..7f567a521cea 100644 > --- a/tools/perf/util/session.c > +++ b/tools/perf/util/session.c > @@ -227,8 +227,8 @@ struct perf_session *perf_session__new(struct perf_data *data, > /* Open the directory data. */ > if (data->is_dir) { > ret = perf_data__open_dir(data); > - if (ret) > - goto out_delete; > + if (ret) > + goto out_delete; > } > > if (!symbol_conf.kallsyms_name && > ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 4/5] perf tools: Support single perf.data file directory 2019-10-07 12:06 ` Adrian Hunter @ 2019-10-21 12:42 ` Adrian Hunter 2019-10-21 13:46 ` Arnaldo Carvalho de Melo 2019-10-21 14:03 ` Arnaldo Carvalho de Melo 0 siblings, 2 replies; 24+ messages in thread From: Adrian Hunter @ 2019-10-21 12:42 UTC (permalink / raw) To: Jiri Olsa; +Cc: Arnaldo Carvalho de Melo, linux-kernel On 7/10/19 3:06 PM, Adrian Hunter wrote: > On 7/10/19 2:20 PM, Jiri Olsa wrote: >> On Fri, Oct 04, 2019 at 11:31:20AM +0300, Adrian Hunter wrote: >> >> SNIP >> >>> u8 pad[8] = {0}; >>> >>> - if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) { >>> + if (!perf_data__is_pipe(data) && perf_data__is_single_file(data)) { >>> off_t file_offset; >>> int fd = perf_data__fd(data); >>> int err; >>> diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c >>> index df173f0bf654..964ea101dba6 100644 >>> --- a/tools/perf/util/data.c >>> +++ b/tools/perf/util/data.c >>> @@ -76,6 +76,13 @@ int perf_data__open_dir(struct perf_data *data) >>> DIR *dir; >>> int nr = 0; >>> >>> + /* >>> + * Directory containing a single regular perf data file which is already >>> + * open, means there is nothing more to do here. >>> + */ >>> + if (perf_data__is_single_file(data)) >>> + return 0; >>> + >> >> cool, I like this approach much more than the previous flag > > Yes it is much nicer. Thanks for your direction on that. > >> >> any change you (if there's repost) or Arnaldo >> could squeeze in indent change below? > > Sent a patch, to be applied before these. > That is: "[PATCH] perf session: Fix indent in perf_session__new()" Any comments on this patch set Arnaldo? ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 4/5] perf tools: Support single perf.data file directory 2019-10-21 12:42 ` Adrian Hunter @ 2019-10-21 13:46 ` Arnaldo Carvalho de Melo 2019-10-21 13:52 ` Jiri Olsa 2019-10-21 14:03 ` Arnaldo Carvalho de Melo 1 sibling, 1 reply; 24+ messages in thread From: Arnaldo Carvalho de Melo @ 2019-10-21 13:46 UTC (permalink / raw) To: Adrian Hunter; +Cc: Jiri Olsa, linux-kernel Em Mon, Oct 21, 2019 at 03:42:39PM +0300, Adrian Hunter escreveu: > On 7/10/19 3:06 PM, Adrian Hunter wrote: > > On 7/10/19 2:20 PM, Jiri Olsa wrote: > >> On Fri, Oct 04, 2019 at 11:31:20AM +0300, Adrian Hunter wrote: > >> > >> SNIP > >> > >>> u8 pad[8] = {0}; > >>> > >>> - if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) { > >>> + if (!perf_data__is_pipe(data) && perf_data__is_single_file(data)) { > >>> off_t file_offset; > >>> int fd = perf_data__fd(data); > >>> int err; > >>> diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c > >>> index df173f0bf654..964ea101dba6 100644 > >>> --- a/tools/perf/util/data.c > >>> +++ b/tools/perf/util/data.c > >>> @@ -76,6 +76,13 @@ int perf_data__open_dir(struct perf_data *data) > >>> DIR *dir; > >>> int nr = 0; > >>> > >>> + /* > >>> + * Directory containing a single regular perf data file which is already > >>> + * open, means there is nothing more to do here. > >>> + */ > >>> + if (perf_data__is_single_file(data)) > >>> + return 0; > >>> + > >> > >> cool, I like this approach much more than the previous flag > > > > Yes it is much nicer. Thanks for your direction on that. > > > >> > >> any change you (if there's repost) or Arnaldo > >> could squeeze in indent change below? > > > > Sent a patch, to be applied before these. > > > > That is: > > "[PATCH] perf session: Fix indent in perf_session__new()" > > Any comments on this patch set Arnaldo? I'll take a look at it later, I think Jiri is ok with it already? - Arnaldo ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 4/5] perf tools: Support single perf.data file directory 2019-10-21 13:46 ` Arnaldo Carvalho de Melo @ 2019-10-21 13:52 ` Jiri Olsa 0 siblings, 0 replies; 24+ messages in thread From: Jiri Olsa @ 2019-10-21 13:52 UTC (permalink / raw) To: Arnaldo Carvalho de Melo; +Cc: Adrian Hunter, linux-kernel On Mon, Oct 21, 2019 at 10:46:11AM -0300, Arnaldo Carvalho de Melo wrote: > Em Mon, Oct 21, 2019 at 03:42:39PM +0300, Adrian Hunter escreveu: > > On 7/10/19 3:06 PM, Adrian Hunter wrote: > > > On 7/10/19 2:20 PM, Jiri Olsa wrote: > > >> On Fri, Oct 04, 2019 at 11:31:20AM +0300, Adrian Hunter wrote: > > >> > > >> SNIP > > >> > > >>> u8 pad[8] = {0}; > > >>> > > >>> - if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) { > > >>> + if (!perf_data__is_pipe(data) && perf_data__is_single_file(data)) { > > >>> off_t file_offset; > > >>> int fd = perf_data__fd(data); > > >>> int err; > > >>> diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c > > >>> index df173f0bf654..964ea101dba6 100644 > > >>> --- a/tools/perf/util/data.c > > >>> +++ b/tools/perf/util/data.c > > >>> @@ -76,6 +76,13 @@ int perf_data__open_dir(struct perf_data *data) > > >>> DIR *dir; > > >>> int nr = 0; > > >>> > > >>> + /* > > >>> + * Directory containing a single regular perf data file which is already > > >>> + * open, means there is nothing more to do here. > > >>> + */ > > >>> + if (perf_data__is_single_file(data)) > > >>> + return 0; > > >>> + > > >> > > >> cool, I like this approach much more than the previous flag > > > > > > Yes it is much nicer. Thanks for your direction on that. > > > > > >> > > >> any change you (if there's repost) or Arnaldo > > >> could squeeze in indent change below? > > > > > > Sent a patch, to be applied before these. > > > > > > > That is: > > > > "[PATCH] perf session: Fix indent in perf_session__new()" > > > > Any comments on this patch set Arnaldo? > > I'll take a look at it later, I think Jiri is ok with it already? yes, it's just indent fix jirka ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 4/5] perf tools: Support single perf.data file directory 2019-10-21 12:42 ` Adrian Hunter 2019-10-21 13:46 ` Arnaldo Carvalho de Melo @ 2019-10-21 14:03 ` Arnaldo Carvalho de Melo 1 sibling, 0 replies; 24+ messages in thread From: Arnaldo Carvalho de Melo @ 2019-10-21 14:03 UTC (permalink / raw) To: Adrian Hunter; +Cc: Jiri Olsa, linux-kernel Em Mon, Oct 21, 2019 at 03:42:39PM +0300, Adrian Hunter escreveu: > On 7/10/19 3:06 PM, Adrian Hunter wrote: > > On 7/10/19 2:20 PM, Jiri Olsa wrote: > >> On Fri, Oct 04, 2019 at 11:31:20AM +0300, Adrian Hunter wrote: > >> > >> SNIP > >> > >>> u8 pad[8] = {0}; > >>> > >>> - if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) { > >>> + if (!perf_data__is_pipe(data) && perf_data__is_single_file(data)) { > >>> off_t file_offset; > >>> int fd = perf_data__fd(data); > >>> int err; > >>> diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c > >>> index df173f0bf654..964ea101dba6 100644 > >>> --- a/tools/perf/util/data.c > >>> +++ b/tools/perf/util/data.c > >>> @@ -76,6 +76,13 @@ int perf_data__open_dir(struct perf_data *data) > >>> DIR *dir; > >>> int nr = 0; > >>> > >>> + /* > >>> + * Directory containing a single regular perf data file which is already > >>> + * open, means there is nothing more to do here. > >>> + */ > >>> + if (perf_data__is_single_file(data)) > >>> + return 0; > >>> + > >> > >> cool, I like this approach much more than the previous flag > > > > Yes it is much nicer. Thanks for your direction on that. > > > >> > >> any change you (if there's repost) or Arnaldo > >> could squeeze in indent change below? > > > > Sent a patch, to be applied before these. > > > > That is: > > "[PATCH] perf session: Fix indent in perf_session__new()" Done it as a separate patch, etc. > Any comments on this patch set Arnaldo? -- - Arnaldo ^ permalink raw reply [flat|nested] 24+ messages in thread
* [tip: perf/core] perf session: Fix indent in perf_session__new()" 2019-10-07 11:20 ` Jiri Olsa 2019-10-07 12:06 ` Adrian Hunter @ 2019-11-12 11:18 ` tip-bot2 for Jiri Olsa 1 sibling, 0 replies; 24+ messages in thread From: tip-bot2 for Jiri Olsa @ 2019-11-12 11:18 UTC (permalink / raw) To: linux-tip-commits Cc: Jiri Olsa, Adrian Hunter, Arnaldo Carvalho de Melo, Ingo Molnar, Borislav Petkov, linux-kernel The following commit has been merged into the perf/core branch of tip: Commit-ID: 01e97a59ea3e071e5c60ad46c40b4db748bfe928 Gitweb: https://git.kernel.org/tip/01e97a59ea3e071e5c60ad46c40b4db748bfe928 Author: Jiri Olsa <jolsa@redhat.com> AuthorDate: Mon, 07 Oct 2019 13:20:27 +02:00 Committer: Arnaldo Carvalho de Melo <acme@redhat.com> CommitterDate: Wed, 06 Nov 2019 15:43:05 -03:00 perf session: Fix indent in perf_session__new()" Fix up indentation. Signed-off-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Adrian Hunter <adrian.hunter@intel.com> Link: http://lore.kernel.org/lkml/20191007112027.GD6919@krava Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/util/session.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 6cc32f5..0266604 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -227,8 +227,8 @@ struct perf_session *perf_session__new(struct perf_data *data, /* Open the directory data. */ if (data->is_dir) { ret = perf_data__open_dir(data); - if (ret) - goto out_delete; + if (ret) + goto out_delete; } } } else { ^ permalink raw reply related [flat|nested] 24+ messages in thread
* [tip: perf/core] perf data: Support single perf.data file directory 2019-10-04 8:31 ` [PATCH 4/5] perf tools: Support single perf.data file directory Adrian Hunter 2019-10-07 11:20 ` Jiri Olsa @ 2019-11-12 11:18 ` tip-bot2 for Adrian Hunter 1 sibling, 0 replies; 24+ messages in thread From: tip-bot2 for Adrian Hunter @ 2019-11-12 11:18 UTC (permalink / raw) To: linux-tip-commits Cc: Adrian Hunter, Jiri Olsa, Arnaldo Carvalho de Melo, Ingo Molnar, Borislav Petkov, linux-kernel The following commit has been merged into the perf/core branch of tip: Commit-ID: 46e201efa15b70ec39df5237116fddebb4f5057c Gitweb: https://git.kernel.org/tip/46e201efa15b70ec39df5237116fddebb4f5057c Author: Adrian Hunter <adrian.hunter@intel.com> AuthorDate: Fri, 04 Oct 2019 11:31:20 +03:00 Committer: Arnaldo Carvalho de Melo <acme@redhat.com> CommitterDate: Wed, 06 Nov 2019 15:43:05 -03:00 perf data: Support single perf.data file directory Support directory output that contains a regular perf.data file, named "data". By default the directory is named perf.data i.e. perf.data └── data Most of the infrastructure to support a directory is already there. This patch makes the changes needed to support the format above. Presently there is no 'perf record' option to output a directory. This is preparation for adding support for putting a copy of /proc/kcore in the directory. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Link: http://lore.kernel.org/lkml/20191004083121.12182-5-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/Documentation/perf.data-directory-format.txt | 28 ++++++++- tools/perf/builtin-record.c | 2 +- tools/perf/util/data.c | 9 ++- tools/perf/util/data.h | 6 ++- 4 files changed, 43 insertions(+), 2 deletions(-) create mode 100644 tools/perf/Documentation/perf.data-directory-format.txt diff --git a/tools/perf/Documentation/perf.data-directory-format.txt b/tools/perf/Documentation/perf.data-directory-format.txt new file mode 100644 index 0000000..4bf0890 --- /dev/null +++ b/tools/perf/Documentation/perf.data-directory-format.txt @@ -0,0 +1,28 @@ +perf.data directory format + +DISCLAIMER This is not ABI yet and is subject to possible change + in following versions of perf. We will remove this + disclaimer once the directory format soaks in. + + +This document describes the on-disk perf.data directory format. + +The layout is described by HEADER_DIR_FORMAT feature. +Currently it holds only version number (0): + + HEADER_DIR_FORMAT = 24 + + struct { + uint64_t version; + } + +The current only version value 0 means that: + - there is a single perf.data file named 'data' within the directory. + e.g. + + $ tree -ps perf.data + perf.data + └── [-rw------- 25912] data + +Future versions are expected to describe different data files +layout according to special needs. diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index 2fb83aa..e402459 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -537,7 +537,7 @@ static int record__process_auxtrace(struct perf_tool *tool, size_t padding; u8 pad[8] = {0}; - if (!perf_data__is_pipe(data) && !perf_data__is_dir(data)) { + if (!perf_data__is_pipe(data) && perf_data__is_single_file(data)) { off_t file_offset; int fd = perf_data__fd(data); int err; diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index df173f0..964ea10 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -76,6 +76,13 @@ int perf_data__open_dir(struct perf_data *data) DIR *dir; int nr = 0; + /* + * Directory containing a single regular perf data file which is already + * open, means there is nothing more to do here. + */ + if (perf_data__is_single_file(data)) + return 0; + if (WARN_ON(!data->is_dir)) return -EINVAL; @@ -406,7 +413,7 @@ unsigned long perf_data__size(struct perf_data *data) u64 size = data->file.size; int i; - if (!data->is_dir) + if (perf_data__is_single_file(data)) return size; for (i = 0; i < data->dir.nr; i++) { diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index 218fe9a..f68815f 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -10,6 +10,7 @@ enum perf_data_mode { }; enum perf_dir_version { + PERF_DIR_SINGLE_FILE = 0, PERF_DIR_VERSION = 1, }; @@ -54,6 +55,11 @@ static inline bool perf_data__is_dir(struct perf_data *data) return data->is_dir; } +static inline bool perf_data__is_single_file(struct perf_data *data) +{ + return data->dir.version == PERF_DIR_SINGLE_FILE; +} + static inline int perf_data__fd(struct perf_data *data) { return data->file.fd; ^ permalink raw reply related [flat|nested] 24+ messages in thread
* [PATCH 5/5] perf record: Put a copy of kcore into the perf.data directory 2019-10-04 8:31 [PATCH 0/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter ` (3 preceding siblings ...) 2019-10-04 8:31 ` [PATCH 4/5] perf tools: Support single perf.data file directory Adrian Hunter @ 2019-10-04 8:31 ` Adrian Hunter 2019-10-07 11:20 ` Jiri Olsa ` (2 more replies) 2019-10-07 12:55 ` [PATCH 0/5] " Jiri Olsa 2019-10-21 14:36 ` Arnaldo Carvalho de Melo 6 siblings, 3 replies; 24+ messages in thread From: Adrian Hunter @ 2019-10-04 8:31 UTC (permalink / raw) To: Arnaldo Carvalho de Melo, Jiri Olsa; +Cc: linux-kernel Add a new 'perf record' option '--kcore' which will put a copy of /proc/kcore, kallsyms and modules into a perf.data directory. Note, that without the --kcore option, output goes to a file as previously. The tools' -o and -i options work with either a file name or directory name. Example: $ sudo perf record --kcore uname $ sudo tree perf.data perf.data ├── kcore_dir │ ├── kallsyms │ ├── kcore │ └── modules └── data $ sudo perf script -v build id event received for vmlinux: 1eaa285996affce2d74d8e66dcea09a80c9941de build id event received for [vdso]: 8bbaf5dc62a9b644b4d4e4539737e104e4a84541 Samples for 'cycles' event do not have CPU attribute set. Skipping 'cpu' field. Using CPUID GenuineIntel-6-8E-A Using perf.data/kcore_dir/kcore for kernel data Using perf.data/kcore_dir/kallsyms for symbols perf 19058 506778.423729: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423733: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423734: 7 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423736: 117 cycles: ffffffffa2caa54a native_write_msr+0xa (vmlinux) perf 19058 506778.423738: 2092 cycles: ffffffffa2c9b7b0 native_apic_msr_write+0x0 (vmlinux) perf 19058 506778.423740: 37380 cycles: ffffffffa2f121d0 perf_event_addr_filters_exec+0x0 (vmlinux) uname 19058 506778.423751: 582673 cycles: ffffffffa303a407 propagate_protected_usage+0x147 (vmlinux) uname 19058 506778.423892: 2241841 cycles: ffffffffa2cae0c9 unwind_next_frame.part.5+0x79 (vmlinux) uname 19058 506778.424430: 2457397 cycles: ffffffffa3019232 check_memory_region+0x52 (vmlinux) Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> --- tools/perf/Documentation/perf-record.txt | 3 ++ .../perf.data-directory-format.txt | 35 +++++++++++++ tools/perf/builtin-record.c | 52 +++++++++++++++++++ tools/perf/util/data.c | 33 ++++++++++++ tools/perf/util/data.h | 2 + tools/perf/util/record.h | 1 + tools/perf/util/session.c | 4 ++ tools/perf/util/util.c | 17 ++++++ 8 files changed, 147 insertions(+) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index c6f9f31b6039..8a4506113d9f 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -571,6 +571,9 @@ config terms. For example: 'cycles/overwrite/' and 'instructions/no-overwrite/'. Implies --tail-synthesize. +--kcore:: +Make a copy of /proc/kcore and place it into a directory with the perf data file. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf.data-directory-format.txt b/tools/perf/Documentation/perf.data-directory-format.txt index 4bf08908178d..f37fbd29112e 100644 --- a/tools/perf/Documentation/perf.data-directory-format.txt +++ b/tools/perf/Documentation/perf.data-directory-format.txt @@ -26,3 +26,38 @@ The current only version value 0 means that: Future versions are expected to describe different data files layout according to special needs. + +Currently the only 'perf record' option to output to a directory is +the --kcore option which puts a copy of /proc/kcore into the directory. +e.g. + + $ sudo perf record --kcore uname + Linux + [ perf record: Woken up 1 times to write data ] + [ perf record: Captured and wrote 0.015 MB perf.data (9 samples) ] + $ sudo tree -ps perf.data + perf.data + ├── [-rw------- 23744] data + └── [drwx------ 4096] kcore_dir + ├── [-r-------- 6731125] kallsyms + ├── [-r-------- 40230912] kcore + └── [-r-------- 5419] modules + + 1 directory, 4 files + $ sudo perf script -v + build id event received for vmlinux: 1eaa285996affce2d74d8e66dcea09a80c9941de + build id event received for [vdso]: 8bbaf5dc62a9b644b4d4e4539737e104e4a84541 + build id event received for /lib/x86_64-linux-gnu/libc-2.28.so: 5b157f49586a3ca84d55837f97ff466767dd3445 + Samples for 'cycles' event do not have CPU attribute set. Skipping 'cpu' field. + Using CPUID GenuineIntel-6-8E-A + Using perf.data/kcore_dir/kcore for kernel data + Using perf.data/kcore_dir/kallsyms for symbols + perf 15316 2060795.480902: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) + perf 15316 2060795.480906: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) + perf 15316 2060795.480908: 7 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) + perf 15316 2060795.480910: 119 cycles: ffffffffa2caa54a native_write_msr+0xa (vmlinux) + perf 15316 2060795.480912: 2109 cycles: ffffffffa2c9b7b0 native_apic_msr_write+0x0 (vmlinux) + perf 15316 2060795.480914: 37606 cycles: ffffffffa2f121fe perf_event_addr_filters_exec+0x2e (vmlinux) + uname 15316 2060795.480924: 588287 cycles: ffffffffa303a56d page_counter_try_charge+0x6d (vmlinux) + uname 15316 2060795.481067: 2261945 cycles: ffffffffa301438f kmem_cache_free+0x4f (vmlinux) + uname 15316 2060795.481643: 2172167 cycles: 7f1a48c393c0 _IO_un_link+0x0 (/lib/x86_64-linux-gnu/libc-2.28.so) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index fceac9d42b4e..ca9bf249cfb2 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -55,6 +55,9 @@ #include <signal.h> #include <sys/mman.h> #include <sys/wait.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> #include <linux/err.h> #include <linux/string.h> #include <linux/time64.h> @@ -699,6 +702,37 @@ static int record__auxtrace_init(struct record *rec __maybe_unused) #endif +static bool record__kcore_readable(struct machine *machine) +{ + char kcore[PATH_MAX]; + int fd; + + scnprintf(kcore, sizeof(kcore), "%s/proc/kcore", machine->root_dir); + + fd = open(kcore, O_RDONLY); + if (fd < 0) + return false; + + close(fd); + + return true; +} + +static int record__kcore_copy(struct machine *machine, struct perf_data *data) +{ + char from_dir[PATH_MAX]; + char kcore_dir[PATH_MAX]; + int ret; + + snprintf(from_dir, sizeof(from_dir), "%s/proc", machine->root_dir); + + ret = perf_data__make_kcore_dir(data, kcore_dir, sizeof(kcore_dir)); + if (ret) + return ret; + + return kcore_copy(from_dir, kcore_dir); +} + static int record__mmap_evlist(struct record *rec, struct evlist *evlist) { @@ -1383,6 +1417,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) session->header.env.comp_type = PERF_COMP_ZSTD; session->header.env.comp_level = rec->opts.comp_level; + if (rec->opts.kcore && + !record__kcore_readable(&session->machines.host)) { + pr_err("ERROR: kcore is not readable.\n"); + return -1; + } + record__init_features(rec); if (rec->opts.use_clockid && rec->opts.clockid_res_ns) @@ -1414,6 +1454,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } session->header.env.comp_mmap_len = session->evlist->core.mmap_len; + if (rec->opts.kcore) { + err = record__kcore_copy(&session->machines.host, data); + if (err) { + pr_err("ERROR: Failed to copy kcore\n"); + goto out_child; + } + } + err = bpf__apply_obj_config(); if (err) { char errbuf[BUFSIZ]; @@ -2184,6 +2232,7 @@ static struct option __record_options[] = { parse_cgroups), OPT_UINTEGER('D', "delay", &record.opts.initial_delay, "ms to wait before starting measurement after program start"), + OPT_BOOLEAN(0, "kcore", &record.opts.kcore, "copy /proc/kcore"), OPT_STRING('u', "uid", &record.opts.target.uid_str, "user", "user to profile"), @@ -2322,6 +2371,9 @@ int cmd_record(int argc, const char **argv) } + if (rec->opts.kcore) + rec->data.is_dir = true; + if (rec->opts.comp_level != 0) { pr_debug("Compression enabled, disabling build id collection at the end of the session.\n"); rec->no_buildid = true; diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 964ea101dba6..c47aa34fdc0a 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -424,3 +424,36 @@ unsigned long perf_data__size(struct perf_data *data) return size; } + +int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz) +{ + int ret; + + if (!data->is_dir) + return -1; + + ret = snprintf(buf, buf_sz, "%s/kcore_dir", data->path); + if (ret < 0 || (size_t)ret >= buf_sz) + return -1; + + return mkdir(buf, S_IRWXU); +} + +char *perf_data__kallsyms_name(struct perf_data *data) +{ + char *kallsyms_name; + struct stat st; + + if (!data->is_dir) + return NULL; + + if (asprintf(&kallsyms_name, "%s/kcore_dir/kallsyms", data->path) < 0) + return NULL; + + if (stat(kallsyms_name, &st)) { + free(kallsyms_name); + return NULL; + } + + return kallsyms_name; +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index f68815f7e428..75947ef6bc17 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -87,4 +87,6 @@ int perf_data__open_dir(struct perf_data *data); void perf_data__close_dir(struct perf_data *data); int perf_data__update_dir(struct perf_data *data); unsigned long perf_data__size(struct perf_data *data); +int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz); +char *perf_data__kallsyms_name(struct perf_data *data); #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 00275afc524d..948bbcf9aef3 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -44,6 +44,7 @@ struct record_opts { bool strict_freq; bool sample_id; bool no_bpf_event; + bool kcore; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 061bb4d6a3f5..bfa80fe8d369 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -230,6 +230,10 @@ struct perf_session *perf_session__new(struct perf_data *data, if (ret) goto out_delete; } + + if (!symbol_conf.kallsyms_name && + !symbol_conf.vmlinux_name) + symbol_conf.kallsyms_name = perf_data__kallsyms_name(data); } } else { session->machines.host.env = &perf_env; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 56f30ad29ca7..16f81a0a9208 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -180,6 +180,21 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat) return rmdir(path); } +static int rm_rf_kcore_dir(const char *path) +{ + char kcore_dir_path[PATH_MAX]; + const char *pat[] = { + "kcore", + "kallsyms", + "modules", + NULL, + }; + + snprintf(kcore_dir_path, sizeof(kcore_dir_path), "%s/kcore_dir", path); + + return rm_rf_depth_pat(kcore_dir_path, 0, pat); +} + int rm_rf_perf_data(const char *path) { const char *pat[] = { @@ -188,6 +203,8 @@ int rm_rf_perf_data(const char *path) NULL, }; + rm_rf_kcore_dir(path); + return rm_rf_depth_pat(path, 0, pat); } -- 2.17.1 ^ permalink raw reply related [flat|nested] 24+ messages in thread
* Re: [PATCH 5/5] perf record: Put a copy of kcore into the perf.data directory 2019-10-04 8:31 ` [PATCH 5/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter @ 2019-10-07 11:20 ` Jiri Olsa 2019-10-07 12:06 ` Adrian Hunter 2019-10-07 11:20 ` Jiri Olsa 2019-11-12 11:18 ` [tip: perf/core] " tip-bot2 for Adrian Hunter 2 siblings, 1 reply; 24+ messages in thread From: Jiri Olsa @ 2019-10-07 11:20 UTC (permalink / raw) To: Adrian Hunter; +Cc: Arnaldo Carvalho de Melo, linux-kernel On Fri, Oct 04, 2019 at 11:31:21AM +0300, Adrian Hunter wrote: SNIP > +} > + > static int record__mmap_evlist(struct record *rec, > struct evlist *evlist) > { > @@ -1383,6 +1417,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) > session->header.env.comp_type = PERF_COMP_ZSTD; > session->header.env.comp_level = rec->opts.comp_level; > > + if (rec->opts.kcore && > + !record__kcore_readable(&session->machines.host)) { > + pr_err("ERROR: kcore is not readable.\n"); > + return -1; > + } > + is there any reason why this change is not merged with the change below? > record__init_features(rec); > > if (rec->opts.use_clockid && rec->opts.clockid_res_ns) > @@ -1414,6 +1454,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) > } > session->header.env.comp_mmap_len = session->evlist->core.mmap_len; > > + if (rec->opts.kcore) { > + err = record__kcore_copy(&session->machines.host, data); > + if (err) { > + pr_err("ERROR: Failed to copy kcore\n"); > + goto out_child; > + } > + } > + thanks, jirka ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 5/5] perf record: Put a copy of kcore into the perf.data directory 2019-10-07 11:20 ` Jiri Olsa @ 2019-10-07 12:06 ` Adrian Hunter 0 siblings, 0 replies; 24+ messages in thread From: Adrian Hunter @ 2019-10-07 12:06 UTC (permalink / raw) To: Jiri Olsa; +Cc: Arnaldo Carvalho de Melo, linux-kernel On 7/10/19 2:20 PM, Jiri Olsa wrote: > On Fri, Oct 04, 2019 at 11:31:21AM +0300, Adrian Hunter wrote: > > SNIP > >> +} >> + >> static int record__mmap_evlist(struct record *rec, >> struct evlist *evlist) >> { >> @@ -1383,6 +1417,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) >> session->header.env.comp_type = PERF_COMP_ZSTD; >> session->header.env.comp_level = rec->opts.comp_level; >> >> + if (rec->opts.kcore && >> + !record__kcore_readable(&session->machines.host)) { >> + pr_err("ERROR: kcore is not readable.\n"); >> + return -1; >> + } >> + > > is there any reason why this change is not merged with the change below? It seemed better to do the validation before opening all the events. > > >> record__init_features(rec); >> >> if (rec->opts.use_clockid && rec->opts.clockid_res_ns) >> @@ -1414,6 +1454,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) >> } >> session->header.env.comp_mmap_len = session->evlist->core.mmap_len; >> >> + if (rec->opts.kcore) { >> + err = record__kcore_copy(&session->machines.host, data); >> + if (err) { >> + pr_err("ERROR: Failed to copy kcore\n"); >> + goto out_child; >> + } >> + } >> + > > thanks, > jirka > ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 5/5] perf record: Put a copy of kcore into the perf.data directory 2019-10-04 8:31 ` [PATCH 5/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter 2019-10-07 11:20 ` Jiri Olsa @ 2019-10-07 11:20 ` Jiri Olsa 2019-10-07 12:14 ` Adrian Hunter 2019-11-12 11:18 ` [tip: perf/core] " tip-bot2 for Adrian Hunter 2 siblings, 1 reply; 24+ messages in thread From: Jiri Olsa @ 2019-10-07 11:20 UTC (permalink / raw) To: Adrian Hunter; +Cc: Arnaldo Carvalho de Melo, linux-kernel On Fri, Oct 04, 2019 at 11:31:21AM +0300, Adrian Hunter wrote: SNIP > bool strict_freq; > bool sample_id; > bool no_bpf_event; > + bool kcore; > unsigned int freq; > unsigned int mmap_pages; > unsigned int auxtrace_mmap_pages; > diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c > index 061bb4d6a3f5..bfa80fe8d369 100644 > --- a/tools/perf/util/session.c > +++ b/tools/perf/util/session.c > @@ -230,6 +230,10 @@ struct perf_session *perf_session__new(struct perf_data *data, > if (ret) > goto out_delete; > } > + > + if (!symbol_conf.kallsyms_name && > + !symbol_conf.vmlinux_name) > + symbol_conf.kallsyms_name = perf_data__kallsyms_name(data); hum, should this also depend on rec->opts.kcore ? jirka ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 5/5] perf record: Put a copy of kcore into the perf.data directory 2019-10-07 11:20 ` Jiri Olsa @ 2019-10-07 12:14 ` Adrian Hunter 0 siblings, 0 replies; 24+ messages in thread From: Adrian Hunter @ 2019-10-07 12:14 UTC (permalink / raw) To: Jiri Olsa; +Cc: Arnaldo Carvalho de Melo, linux-kernel On 7/10/19 2:20 PM, Jiri Olsa wrote: > On Fri, Oct 04, 2019 at 11:31:21AM +0300, Adrian Hunter wrote: > > SNIP > >> bool strict_freq; >> bool sample_id; >> bool no_bpf_event; >> + bool kcore; >> unsigned int freq; >> unsigned int mmap_pages; >> unsigned int auxtrace_mmap_pages; >> diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c >> index 061bb4d6a3f5..bfa80fe8d369 100644 >> --- a/tools/perf/util/session.c >> +++ b/tools/perf/util/session.c >> @@ -230,6 +230,10 @@ struct perf_session *perf_session__new(struct perf_data *data, >> if (ret) >> goto out_delete; >> } >> + >> + if (!symbol_conf.kallsyms_name && >> + !symbol_conf.vmlinux_name) >> + symbol_conf.kallsyms_name = perf_data__kallsyms_name(data); > > hum, should this also depend on rec->opts.kcore ? This is the bit that makes 'perf script' work. It has the same affect as though the --kallsyms option was used. i.e. it makes 'perf script' behave the same as: perf script --kallsyms perf.data/kcore_dir/kallsyms Which works because perf looks for kcore in the same directory as kallsyms. ^ permalink raw reply [flat|nested] 24+ messages in thread
* [tip: perf/core] perf record: Put a copy of kcore into the perf.data directory 2019-10-04 8:31 ` [PATCH 5/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter 2019-10-07 11:20 ` Jiri Olsa 2019-10-07 11:20 ` Jiri Olsa @ 2019-11-12 11:18 ` tip-bot2 for Adrian Hunter 2 siblings, 0 replies; 24+ messages in thread From: tip-bot2 for Adrian Hunter @ 2019-11-12 11:18 UTC (permalink / raw) To: linux-tip-commits Cc: Adrian Hunter, Jiri Olsa, Arnaldo Carvalho de Melo, Ingo Molnar, Borislav Petkov, linux-kernel The following commit has been merged into the perf/core branch of tip: Commit-ID: eeb399b531a1576e36016f8a7f0c50d10194e190 Gitweb: https://git.kernel.org/tip/eeb399b531a1576e36016f8a7f0c50d10194e190 Author: Adrian Hunter <adrian.hunter@intel.com> AuthorDate: Fri, 04 Oct 2019 11:31:21 +03:00 Committer: Arnaldo Carvalho de Melo <acme@redhat.com> CommitterDate: Wed, 06 Nov 2019 15:43:05 -03:00 perf record: Put a copy of kcore into the perf.data directory Add a new 'perf record' option '--kcore' which will put a copy of /proc/kcore, kallsyms and modules into a perf.data directory. Note, that without the --kcore option, output goes to a file as previously. The tools' -o and -i options work with either a file name or directory name. Example: $ sudo perf record --kcore uname $ sudo tree perf.data perf.data ├── kcore_dir │ ├── kallsyms │ ├── kcore │ └── modules └── data $ sudo perf script -v build id event received for vmlinux: 1eaa285996affce2d74d8e66dcea09a80c9941de build id event received for [vdso]: 8bbaf5dc62a9b644b4d4e4539737e104e4a84541 Samples for 'cycles' event do not have CPU attribute set. Skipping 'cpu' field. Using CPUID GenuineIntel-6-8E-A Using perf.data/kcore_dir/kcore for kernel data Using perf.data/kcore_dir/kallsyms for symbols perf 19058 506778.423729: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423733: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423734: 7 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) perf 19058 506778.423736: 117 cycles: ffffffffa2caa54a native_write_msr+0xa (vmlinux) perf 19058 506778.423738: 2092 cycles: ffffffffa2c9b7b0 native_apic_msr_write+0x0 (vmlinux) perf 19058 506778.423740: 37380 cycles: ffffffffa2f121d0 perf_event_addr_filters_exec+0x0 (vmlinux) uname 19058 506778.423751: 582673 cycles: ffffffffa303a407 propagate_protected_usage+0x147 (vmlinux) uname 19058 506778.423892: 2241841 cycles: ffffffffa2cae0c9 unwind_next_frame.part.5+0x79 (vmlinux) uname 19058 506778.424430: 2457397 cycles: ffffffffa3019232 check_memory_region+0x52 (vmlinux) Committer testing: # rm -rf perf.data* # perf record sleep 1 [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.024 MB perf.data (7 samples) ] # ls -l perf.data -rw-------. 1 root root 34772 Oct 21 11:08 perf.data # perf record --kcore uname Linux [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.024 MB perf.data (7 samples) ] ls[root@quaco ~]# ls -lad perf.data* drwx------. 3 root root 4096 Oct 21 11:08 perf.data -rw-------. 1 root root 34772 Oct 21 11:08 perf.data.old # perf evlist -v cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1 # perf evlist -v -i perf.data/data cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type: IP|TID|TIME|PERIOD, read_format: ID, disabled: 1, inherit: 1, mmap: 1, comm: 1, freq: 1, enable_on_exec: 1, task: 1, precise_ip: 3, sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol: 1, bpf_event: 1 # Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: http://lore.kernel.org/lkml/20191004083121.12182-6-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> --- tools/perf/Documentation/perf-record.txt | 3 +- tools/perf/Documentation/perf.data-directory-format.txt | 35 +++++- tools/perf/builtin-record.c | 52 ++++++++- tools/perf/util/data.c | 33 +++++- tools/perf/util/data.h | 2 +- tools/perf/util/record.h | 1 +- tools/perf/util/session.c | 4 +- tools/perf/util/util.c | 17 +++- 8 files changed, 147 insertions(+) diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt index c6f9f31..8a45061 100644 --- a/tools/perf/Documentation/perf-record.txt +++ b/tools/perf/Documentation/perf-record.txt @@ -571,6 +571,9 @@ config terms. For example: 'cycles/overwrite/' and 'instructions/no-overwrite/'. Implies --tail-synthesize. +--kcore:: +Make a copy of /proc/kcore and place it into a directory with the perf data file. + SEE ALSO -------- linkperf:perf-stat[1], linkperf:perf-list[1] diff --git a/tools/perf/Documentation/perf.data-directory-format.txt b/tools/perf/Documentation/perf.data-directory-format.txt index 4bf0890..f37fbd2 100644 --- a/tools/perf/Documentation/perf.data-directory-format.txt +++ b/tools/perf/Documentation/perf.data-directory-format.txt @@ -26,3 +26,38 @@ The current only version value 0 means that: Future versions are expected to describe different data files layout according to special needs. + +Currently the only 'perf record' option to output to a directory is +the --kcore option which puts a copy of /proc/kcore into the directory. +e.g. + + $ sudo perf record --kcore uname + Linux + [ perf record: Woken up 1 times to write data ] + [ perf record: Captured and wrote 0.015 MB perf.data (9 samples) ] + $ sudo tree -ps perf.data + perf.data + ├── [-rw------- 23744] data + └── [drwx------ 4096] kcore_dir + ├── [-r-------- 6731125] kallsyms + ├── [-r-------- 40230912] kcore + └── [-r-------- 5419] modules + + 1 directory, 4 files + $ sudo perf script -v + build id event received for vmlinux: 1eaa285996affce2d74d8e66dcea09a80c9941de + build id event received for [vdso]: 8bbaf5dc62a9b644b4d4e4539737e104e4a84541 + build id event received for /lib/x86_64-linux-gnu/libc-2.28.so: 5b157f49586a3ca84d55837f97ff466767dd3445 + Samples for 'cycles' event do not have CPU attribute set. Skipping 'cpu' field. + Using CPUID GenuineIntel-6-8E-A + Using perf.data/kcore_dir/kcore for kernel data + Using perf.data/kcore_dir/kallsyms for symbols + perf 15316 2060795.480902: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) + perf 15316 2060795.480906: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) + perf 15316 2060795.480908: 7 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) + perf 15316 2060795.480910: 119 cycles: ffffffffa2caa54a native_write_msr+0xa (vmlinux) + perf 15316 2060795.480912: 2109 cycles: ffffffffa2c9b7b0 native_apic_msr_write+0x0 (vmlinux) + perf 15316 2060795.480914: 37606 cycles: ffffffffa2f121fe perf_event_addr_filters_exec+0x2e (vmlinux) + uname 15316 2060795.480924: 588287 cycles: ffffffffa303a56d page_counter_try_charge+0x6d (vmlinux) + uname 15316 2060795.481067: 2261945 cycles: ffffffffa301438f kmem_cache_free+0x4f (vmlinux) + uname 15316 2060795.481643: 2172167 cycles: 7f1a48c393c0 _IO_un_link+0x0 (/lib/x86_64-linux-gnu/libc-2.28.so) diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c index e402459..f6664bb 100644 --- a/tools/perf/builtin-record.c +++ b/tools/perf/builtin-record.c @@ -55,6 +55,9 @@ #include <signal.h> #include <sys/mman.h> #include <sys/wait.h> +#include <sys/types.h> +#include <sys/stat.h> +#include <fcntl.h> #include <linux/err.h> #include <linux/string.h> #include <linux/time64.h> @@ -699,6 +702,37 @@ static int record__auxtrace_init(struct record *rec __maybe_unused) #endif +static bool record__kcore_readable(struct machine *machine) +{ + char kcore[PATH_MAX]; + int fd; + + scnprintf(kcore, sizeof(kcore), "%s/proc/kcore", machine->root_dir); + + fd = open(kcore, O_RDONLY); + if (fd < 0) + return false; + + close(fd); + + return true; +} + +static int record__kcore_copy(struct machine *machine, struct perf_data *data) +{ + char from_dir[PATH_MAX]; + char kcore_dir[PATH_MAX]; + int ret; + + snprintf(from_dir, sizeof(from_dir), "%s/proc", machine->root_dir); + + ret = perf_data__make_kcore_dir(data, kcore_dir, sizeof(kcore_dir)); + if (ret) + return ret; + + return kcore_copy(from_dir, kcore_dir); +} + static int record__mmap_evlist(struct record *rec, struct evlist *evlist) { @@ -1383,6 +1417,12 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) session->header.env.comp_type = PERF_COMP_ZSTD; session->header.env.comp_level = rec->opts.comp_level; + if (rec->opts.kcore && + !record__kcore_readable(&session->machines.host)) { + pr_err("ERROR: kcore is not readable.\n"); + return -1; + } + record__init_features(rec); if (rec->opts.use_clockid && rec->opts.clockid_res_ns) @@ -1414,6 +1454,14 @@ static int __cmd_record(struct record *rec, int argc, const char **argv) } session->header.env.comp_mmap_len = session->evlist->core.mmap_len; + if (rec->opts.kcore) { + err = record__kcore_copy(&session->machines.host, data); + if (err) { + pr_err("ERROR: Failed to copy kcore\n"); + goto out_child; + } + } + err = bpf__apply_obj_config(); if (err) { char errbuf[BUFSIZ]; @@ -2184,6 +2232,7 @@ static struct option __record_options[] = { parse_cgroups), OPT_UINTEGER('D', "delay", &record.opts.initial_delay, "ms to wait before starting measurement after program start"), + OPT_BOOLEAN(0, "kcore", &record.opts.kcore, "copy /proc/kcore"), OPT_STRING('u', "uid", &record.opts.target.uid_str, "user", "user to profile"), @@ -2322,6 +2371,9 @@ int cmd_record(int argc, const char **argv) } + if (rec->opts.kcore) + rec->data.is_dir = true; + if (rec->opts.comp_level != 0) { pr_debug("Compression enabled, disabling build id collection at the end of the session.\n"); rec->no_buildid = true; diff --git a/tools/perf/util/data.c b/tools/perf/util/data.c index 964ea10..c47aa34 100644 --- a/tools/perf/util/data.c +++ b/tools/perf/util/data.c @@ -424,3 +424,36 @@ unsigned long perf_data__size(struct perf_data *data) return size; } + +int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz) +{ + int ret; + + if (!data->is_dir) + return -1; + + ret = snprintf(buf, buf_sz, "%s/kcore_dir", data->path); + if (ret < 0 || (size_t)ret >= buf_sz) + return -1; + + return mkdir(buf, S_IRWXU); +} + +char *perf_data__kallsyms_name(struct perf_data *data) +{ + char *kallsyms_name; + struct stat st; + + if (!data->is_dir) + return NULL; + + if (asprintf(&kallsyms_name, "%s/kcore_dir/kallsyms", data->path) < 0) + return NULL; + + if (stat(kallsyms_name, &st)) { + free(kallsyms_name); + return NULL; + } + + return kallsyms_name; +} diff --git a/tools/perf/util/data.h b/tools/perf/util/data.h index f68815f..75947ef 100644 --- a/tools/perf/util/data.h +++ b/tools/perf/util/data.h @@ -87,4 +87,6 @@ int perf_data__open_dir(struct perf_data *data); void perf_data__close_dir(struct perf_data *data); int perf_data__update_dir(struct perf_data *data); unsigned long perf_data__size(struct perf_data *data); +int perf_data__make_kcore_dir(struct perf_data *data, char *buf, size_t buf_sz); +char *perf_data__kallsyms_name(struct perf_data *data); #endif /* __PERF_DATA_H */ diff --git a/tools/perf/util/record.h b/tools/perf/util/record.h index 00275af..948bbcf 100644 --- a/tools/perf/util/record.h +++ b/tools/perf/util/record.h @@ -44,6 +44,7 @@ struct record_opts { bool strict_freq; bool sample_id; bool no_bpf_event; + bool kcore; unsigned int freq; unsigned int mmap_pages; unsigned int auxtrace_mmap_pages; diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c index 0266604..f07b8ec 100644 --- a/tools/perf/util/session.c +++ b/tools/perf/util/session.c @@ -230,6 +230,10 @@ struct perf_session *perf_session__new(struct perf_data *data, if (ret) goto out_delete; } + + if (!symbol_conf.kallsyms_name && + !symbol_conf.vmlinux_name) + symbol_conf.kallsyms_name = perf_data__kallsyms_name(data); } } else { session->machines.host.env = &perf_env; diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c index 3096654..969ae56 100644 --- a/tools/perf/util/util.c +++ b/tools/perf/util/util.c @@ -182,6 +182,21 @@ static int rm_rf_depth_pat(const char *path, int depth, const char **pat) return rmdir(path); } +static int rm_rf_kcore_dir(const char *path) +{ + char kcore_dir_path[PATH_MAX]; + const char *pat[] = { + "kcore", + "kallsyms", + "modules", + NULL, + }; + + snprintf(kcore_dir_path, sizeof(kcore_dir_path), "%s/kcore_dir", path); + + return rm_rf_depth_pat(kcore_dir_path, 0, pat); +} + int rm_rf_perf_data(const char *path) { const char *pat[] = { @@ -190,6 +205,8 @@ int rm_rf_perf_data(const char *path) NULL, }; + rm_rf_kcore_dir(path); + return rm_rf_depth_pat(path, 0, pat); } ^ permalink raw reply related [flat|nested] 24+ messages in thread
* Re: [PATCH 0/5] perf record: Put a copy of kcore into the perf.data directory 2019-10-04 8:31 [PATCH 0/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter ` (4 preceding siblings ...) 2019-10-04 8:31 ` [PATCH 5/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter @ 2019-10-07 12:55 ` Jiri Olsa 2019-10-21 14:36 ` Arnaldo Carvalho de Melo 6 siblings, 0 replies; 24+ messages in thread From: Jiri Olsa @ 2019-10-07 12:55 UTC (permalink / raw) To: Adrian Hunter; +Cc: Arnaldo Carvalho de Melo, linux-kernel On Fri, Oct 04, 2019 at 11:31:16AM +0300, Adrian Hunter wrote: > Hi > > Here are patches to add a new 'perf record' option '--kcore' which will put > a copy of /proc/kcore, kallsyms and modules into a perf.data directory. > Note, that without the --kcore option, output goes to a file as previously. > The tools' -o and -i options work with either a file name or directory > name. > > Example: > > $ sudo perf record --kcore uname > > $ sudo tree perf.data > perf.data > ├── kcore_dir > │ ├── kallsyms > │ ├── kcore > │ └── modules > └── data > > $ sudo perf script -v > build id event received for vmlinux: 1eaa285996affce2d74d8e66dcea09a80c9941de > build id event received for [vdso]: 8bbaf5dc62a9b644b4d4e4539737e104e4a84541 > Samples for 'cycles' event do not have CPU attribute set. Skipping 'cpu' field. > Using CPUID GenuineIntel-6-8E-A > Using perf.data/kcore_dir/kcore for kernel data > Using perf.data/kcore_dir/kallsyms for symbols > perf 19058 506778.423729: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) > perf 19058 506778.423733: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) > perf 19058 506778.423734: 7 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) > perf 19058 506778.423736: 117 cycles: ffffffffa2caa54a native_write_msr+0xa (vmlinux) > perf 19058 506778.423738: 2092 cycles: ffffffffa2c9b7b0 native_apic_msr_write+0x0 (vmlinux) > perf 19058 506778.423740: 37380 cycles: ffffffffa2f121d0 perf_event_addr_filters_exec+0x0 (vmlinux) > uname 19058 506778.423751: 582673 cycles: ffffffffa303a407 propagate_protected_usage+0x147 (vmlinux) > uname 19058 506778.423892: 2241841 cycles: ffffffffa2cae0c9 unwind_next_frame.part.5+0x79 (vmlinux) > uname 19058 506778.424430: 2457397 cycles: ffffffffa3019232 check_memory_region+0x52 (vmlinux) > > > Adrian Hunter (5): > perf data: Correctly identify directory data files > perf data: Move perf_dir_version into data.h > perf data: Rename directory "header" file to "data" > perf tools: Support single perf.data file directory > perf record: Put a copy of kcore into the perf.data directory Reviewed-by: Jiri Olsa <jolsa@kernel.org> thanks, jirka > > tools/perf/Documentation/perf-record.txt | 3 ++ > .../Documentation/perf.data-directory-format.txt | 63 ++++++++++++++++++++++ > tools/perf/builtin-record.c | 54 ++++++++++++++++++- > tools/perf/util/data.c | 46 ++++++++++++++-- > tools/perf/util/data.h | 12 +++++ > tools/perf/util/header.h | 4 -- > tools/perf/util/record.h | 1 + > tools/perf/util/session.c | 4 ++ > tools/perf/util/util.c | 19 ++++++- > 9 files changed, 197 insertions(+), 9 deletions(-) > create mode 100644 tools/perf/Documentation/perf.data-directory-format.txt > > > Regards > Adrian ^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 0/5] perf record: Put a copy of kcore into the perf.data directory 2019-10-04 8:31 [PATCH 0/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter ` (5 preceding siblings ...) 2019-10-07 12:55 ` [PATCH 0/5] " Jiri Olsa @ 2019-10-21 14:36 ` Arnaldo Carvalho de Melo 6 siblings, 0 replies; 24+ messages in thread From: Arnaldo Carvalho de Melo @ 2019-10-21 14:36 UTC (permalink / raw) To: Adrian Hunter Cc: Jiri Olsa, Namhyung Kim, Ingo Molnar, Thomas Gleixner, linux-kernel Em Fri, Oct 04, 2019 at 11:31:16AM +0300, Adrian Hunter escreveu: > Hi > > Here are patches to add a new 'perf record' option '--kcore' which will put > a copy of /proc/kcore, kallsyms and modules into a perf.data directory. > Note, that without the --kcore option, output goes to a file as previously. > The tools' -o and -i options work with either a file name or directory > name. Its great that you two got in agreement about adding the new feature using the infrastructure that is being put in place for perf.data as a directory, great team work. Applied, thanks a lot, - Arnaldo > Example: > > $ sudo perf record --kcore uname > > $ sudo tree perf.data > perf.data > ├── kcore_dir > │ ├── kallsyms > │ ├── kcore > │ └── modules > └── data > > $ sudo perf script -v > build id event received for vmlinux: 1eaa285996affce2d74d8e66dcea09a80c9941de > build id event received for [vdso]: 8bbaf5dc62a9b644b4d4e4539737e104e4a84541 > Samples for 'cycles' event do not have CPU attribute set. Skipping 'cpu' field. > Using CPUID GenuineIntel-6-8E-A > Using perf.data/kcore_dir/kcore for kernel data > Using perf.data/kcore_dir/kallsyms for symbols > perf 19058 506778.423729: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) > perf 19058 506778.423733: 1 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) > perf 19058 506778.423734: 7 cycles: ffffffffa2caa548 native_write_msr+0x8 (vmlinux) > perf 19058 506778.423736: 117 cycles: ffffffffa2caa54a native_write_msr+0xa (vmlinux) > perf 19058 506778.423738: 2092 cycles: ffffffffa2c9b7b0 native_apic_msr_write+0x0 (vmlinux) > perf 19058 506778.423740: 37380 cycles: ffffffffa2f121d0 perf_event_addr_filters_exec+0x0 (vmlinux) > uname 19058 506778.423751: 582673 cycles: ffffffffa303a407 propagate_protected_usage+0x147 (vmlinux) > uname 19058 506778.423892: 2241841 cycles: ffffffffa2cae0c9 unwind_next_frame.part.5+0x79 (vmlinux) > uname 19058 506778.424430: 2457397 cycles: ffffffffa3019232 check_memory_region+0x52 (vmlinux) > > > Adrian Hunter (5): > perf data: Correctly identify directory data files > perf data: Move perf_dir_version into data.h > perf data: Rename directory "header" file to "data" > perf tools: Support single perf.data file directory > perf record: Put a copy of kcore into the perf.data directory > > tools/perf/Documentation/perf-record.txt | 3 ++ > .../Documentation/perf.data-directory-format.txt | 63 ++++++++++++++++++++++ > tools/perf/builtin-record.c | 54 ++++++++++++++++++- > tools/perf/util/data.c | 46 ++++++++++++++-- > tools/perf/util/data.h | 12 +++++ > tools/perf/util/header.h | 4 -- > tools/perf/util/record.h | 1 + > tools/perf/util/session.c | 4 ++ > tools/perf/util/util.c | 19 ++++++- > 9 files changed, 197 insertions(+), 9 deletions(-) > create mode 100644 tools/perf/Documentation/perf.data-directory-format.txt > > > Regards > Adrian -- - Arnaldo ^ permalink raw reply [flat|nested] 24+ messages in thread
end of thread, other threads:[~2019-11-12 11:20 UTC | newest] Thread overview: 24+ messages (download: mbox.gz / follow: Atom feed) -- links below jump to the message on this page -- 2019-10-04 8:31 [PATCH 0/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter 2019-10-04 8:31 ` [PATCH 1/5] perf data: Correctly identify directory data files Adrian Hunter 2019-11-12 11:18 ` [tip: perf/core] " tip-bot2 for Adrian Hunter 2019-10-04 8:31 ` [PATCH 2/5] perf data: Move perf_dir_version into data.h Adrian Hunter 2019-11-12 11:18 ` [tip: perf/core] " tip-bot2 for Adrian Hunter 2019-10-04 8:31 ` [PATCH 3/5] perf data: Rename directory "header" file to "data" Adrian Hunter 2019-11-12 11:18 ` [tip: perf/core] " tip-bot2 for Adrian Hunter 2019-10-04 8:31 ` [PATCH 4/5] perf tools: Support single perf.data file directory Adrian Hunter 2019-10-07 11:20 ` Jiri Olsa 2019-10-07 12:06 ` Adrian Hunter 2019-10-21 12:42 ` Adrian Hunter 2019-10-21 13:46 ` Arnaldo Carvalho de Melo 2019-10-21 13:52 ` Jiri Olsa 2019-10-21 14:03 ` Arnaldo Carvalho de Melo 2019-11-12 11:18 ` [tip: perf/core] perf session: Fix indent in perf_session__new()" tip-bot2 for Jiri Olsa 2019-11-12 11:18 ` [tip: perf/core] perf data: Support single perf.data file directory tip-bot2 for Adrian Hunter 2019-10-04 8:31 ` [PATCH 5/5] perf record: Put a copy of kcore into the perf.data directory Adrian Hunter 2019-10-07 11:20 ` Jiri Olsa 2019-10-07 12:06 ` Adrian Hunter 2019-10-07 11:20 ` Jiri Olsa 2019-10-07 12:14 ` Adrian Hunter 2019-11-12 11:18 ` [tip: perf/core] " tip-bot2 for Adrian Hunter 2019-10-07 12:55 ` [PATCH 0/5] " Jiri Olsa 2019-10-21 14:36 ` Arnaldo Carvalho de Melo
This is a public inbox, see mirroring instructions for how to clone and mirror all data and code used for this inbox; as well as URLs for NNTP newsgroup(s).