- 24 Mar, 2015 11 commits
-
-
Steven Rostedt (Red Hat) authored
There is a pevent_data_comm_from_pid() that returns the cmdline stored for a given pid in order for users to map pids to comms, but there's no method to convert a comm back to a pid. This is useful for filters that specify a comm instead of a PID (it's faster than searching each individual event). Add a way to retrieve a comm from a pid. Since there can be more than one pid associated to a comm, it returns a data structure that lets the user iterate over all the saved comms for a given pid. Signed-off-by:
Steven Rostedt <rostedt@goodmis.org> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/20150324135923.001103479@goodmis.orgSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Steven Rostedt (Red Hat) authored
The %z printf specifier was not handled making trace_printk()s in the kernel that used this break on output. Reported-by:
Shawn Bohrer <shawn.bohrer@gmail.com> Signed-off-by:
-
Steven Rostedt (Red Hat) authored
The pevent->trace_clock should not be a direct pointer to what was given. It should be copied and freed. Note, valgrind pointed this out when a caller passed in a pointer that needed to be freed and it never was. Ideally, pevent should copy it (which this change does), and free the copy. It's up to the caller to free the clock string passed in. Signed-off-by:
-
Josef Bacik authored
It is possible that a pid has no associated comm attached to it, although it can still be passed to pevent_register_comm(). But if comm is NULL, it will cause strdup() to segfault. To prevent this from happening, if comm is NULL use the default "<...>" name for the pid. Signed-off-by:
Josef Bacik <jbacik@fb.com> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/20150324135922.549965495@goodmis.org Link: http://lkml.kernel.org/p/1403799732-30308-1-git-send-email-jbacik@fb.comSigned-off-by:
-
Arnaldo Carvalho de Melo authored
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.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To deal with forwarding the strerror_r (GNU) return we need to check if the returned value is the buffer we passed or maybe some constant (unknown error), simplify that action by using scnprintf, that will do all the buflen size checks, trimming if needed. Acked-by:
Jiri Olsa <jolsa@redhat.com> Acked-by:
Namhyung Kim <namhyung@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: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-d0ik6i5gjew56j0qphql28ou@git.kernel.orgSigned-off-by:
-
Vinson Lee authored
This patch fixes this build error with glibc < 2.6. CC util/cloexec.o cc1: warnings being treated as errors util/cloexec.c: In function ‘perf_flag_probe’: util/cloexec.c:24: error: implicit declaration of function ‘sched_getcpu’ util/cloexec.c:24: error: nested extern declaration of ‘sched_getcpu’ make: *** [util/cloexec.o] Error 1 Signed-off-by:
Vinson Lee <vlee@twitter.com> Acked-by:
-
Namhyung Kim authored
Like perf stat, this makes easy to read the numbers on stat like below: # perf kmem stat SUMMARY ======= Total bytes requested: 9,770,900 Total bytes allocated: 9,782,712 Total bytes wasted on internal fragmentation: 11,812 Internal fragmentation: 0.120744% Cross CPU allocations: 74/152,819 Suggested-by:
-
Javi Merino authored
The sequence of allocating the print_arg field, calling process_arg() and verifying that the next event delimiter is repeated twice in process_hex() and will also be used for process_int_array(). Factor it out to a function to avoid writing the same code again and again. Signed-off-by:
Javi Merino <javi.merino@arm.com> Acked-by:
-
Masami Hiramatsu authored
Fix to get correctly unmapped symbol address on kernel. This allows us to probe on syscall symbols which are aliases of SyS_ functions with using debuginfo. Without this fix: ---- # ./perf probe -a sys_write Failed to find debug information for address 3b0100 Probe point 'sys_write' not found. Error: Failed to add events. ---- The address 0x3b0100 is a mapped address, and not usable in debuginfo. With this fix: ---- # ./perf probe -a sys_write Added new event: probe:sys_write (on sys_write) You can now use it in all perf tools, such as: perf record -e probe:sys_write -aR sleep 1 ---- Signed-off-by:Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: He Kuang <hekuang@huawei.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/20150322114022.32639.19096.stgit@localhost.localdomainSigned-off-by:
-
Yunlong Song authored
When '--sort' is not set, 'perf mem report" will print a null pointer as the output value of sort order, so fix it. Example: Before this patch: $ perf mem report # To display the perf.data header info, please use --header/--header-only options. # # Samples: 18 of event 'cpu/mem-loads/pp' # Total weight : 188 # Sort order : (null) # ... After this patch: $ perf mem report # To display the perf.data header info, please use --header/--header-only options. # # Samples: 18 of event 'cpu/mem-loads/pp' # Total weight : 188 # Sort order : local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked # ... Signed-off-by:
Yunlong Song <yunlong.song@huawei.com> Acked-by:
-
- 23 Mar, 2015 7 commits
-
-
Jiri Olsa authored
Decompressing kernel module file for objdump command if needed. Annotation commands now display annotation for compressed kernel modules. Signed-off-by:
-
Jiri Olsa authored
Currently we assume machine__new_module is called only once for each module so we create its map&dso unconditionally. However it's possible that it's called multiple times for same module. Like for perf record: 1) via machine__create_module during machine init 2) via kernel MMAP event processing Trying to lookup kernel module map before creating one. Signed-off-by:
-
Jiri Olsa authored
Because it's no longer needed. Signed-off-by:
-
Jiri Olsa authored
We no longer need the 'compressed' argument, because all current users use 'NULL' for it. Signed-off-by:
-
Jiri Olsa authored
Replacing the current parsing code with kmod_path__parse function call. Signed-off-by:
-
Jiri Olsa authored
Replacing the file name parsing with kmod_path__parse. Signed-off-by:
-
Jiri Olsa authored
Replacing the file name parsing with kmod_path__parse and moving the dso update into new separate function. Signed-off-by:
-
- 22 Mar, 2015 2 commits
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-2' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: - Handle legacy syscalls tracepoints (David Ahern, Arnaldo Carvalho de Melo) - Indicate which callchain entries are annotated in the TUI hists browser (report/top) (Arnaldo Carvalho de Melo) - Fix failure to add multiple probes without debuginfo (He Kuang) - Fix 'trace' summary_only option (David Ahern) - Fix race in build_id_cache__add_s() in 'buildid-cache' (Milos Vyletel) - Don't allow empty argument for field-separator, fixing segfault (Wang Nan) Infrastructure: - Add destructor for format_field in libtraceevent (David Ahern) - Prep work for support lzma compressed kernel modules (Jiri Olsa) - Update .gitignore with recently added/renamed feature detection files (Yunlong Song) Signed-off-by:
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core Pull perf/core improvements and fixes from Arnaldo Carvalho de Melo: User visible changes: - Bash completion for subcommands (Yunlong Song) - Allow annotating entries in callchains in the hists browser (top/report). TODO: give some visual cue to what entries in callchains have samples and thus can be annotated and/or allow showing the source code for functions without samples (Arnaldo Carvalho de Melo) - Don't allow empty argument for '-t' in perf report, fixing segfault (Wang Nan) Infrastructure: - Prep work for moving the perf feature tests build system to tools/build (Jiri Olsa) - Fix perf-read-vdsox32 not building and lib64 install dir (H.J. Lu) - ARM64: fix building error and eh/debug frame offset cache fixes (Wang Nan) Signed-off-by:
-
- 21 Mar, 2015 15 commits
-
-
Jiri Olsa authored
Using kmod_path__parse to get the module name and update the dso short name within machine__new_dso function. This way it's done only first time when dso is created, unlike the current way when we update it all the time we process memory map of the kernel module. Signed-off-by:
-
Jiri Olsa authored
Separate the dso object addition and update when adding new kernel module. Currently we update dso's symtab_type any time we find it in the list, because we can't distinguish between new and found dso from __dsos__findnew function. Adding machine__module_dso that separates finding and adding new dso objects, so there's no superfluous update of dso. Signed-off-by:
-
Jiri Olsa authored
Separate the creation of new dso object and its addition to the dsos list. It will be used in following patch. Signed-off-by:
-
Jiri Olsa authored
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 authored
In short, Fedora compresses kernel modules now (since version 21) with lzma compression. Adding lzma decompress support into the dso.c:compressions array introduced by Namhyung earlier. Signed-off-by:
-
Jiri Olsa authored
Will be used to decompress 'xz' objects. The check detects the liblzma.so devel library normally delivered by xz package. Signed-off-by:
-
David Ahern authored
Move the calls that frees the resources allocated for a struct format_field to a separate routine. Signed-off-by:
David Ahern <dsahern@gmail.com> Acked-by:
-
Arnaldo Carvalho de Melo authored
Now that we can annotate entries in a callchain, show which ones have an associated symbol and samples, by adding a right arrow just before the symbol name when in verbose mode. To toggle verbose mode press 'V'. 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: Jiri Olsa <jolsa@redhat.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-d2rf1p3h5gdp7hdl2gf2bozl@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Currently the code skips the first field with the expectation that it is 'nr'. But older kernels do not have the 'nr' field: field:int nr; offset:8; size:4; signed:1; Change perf-trace to drop the field if it exists after parsing the format file. This fixes the off-by-one problem with older kernels (e.g., RHEL6). e.g, perf-trace shows this for write: 1.515 ( 0.006 ms): dd/4245 write(buf: 2</dev/pts/0>, count: 140733837536224 ) = 26 where 2 is really the fd, the huge number is really the buf address, etc. With this patch you get the more appropriate: 1.813 ( 0.003 ms): dd/6330 write(fd: 2</dev/pts/0>, buf: 0x7fff22fc81f0, count: 25) = 25 Based-on-a-patch-by: -
Jiri Olsa authored
Moving feature checks code under tools/build directory. Changing also $feature_dir to point to new feature directory location and perf Makefiles to include Makefile.feature from new location. Signed-off-by:
-
Jiri Olsa authored
Putting feature checks directory into $feature_dir, so it's easy to configure when we move it to bools/build later. Signed-off-by:
-
Jiri Olsa authored
Move feature related code into separate makefile. The new Makefile.feature is included from config/Makefile. It will be moved later into tools/build. Signed-off-by:
-
Jiri Olsa authored
We have 2 feature_check functions, which conflict with each other. Fixing it by renaming the latter to feature_display_check. Signed-off-by:
-
David Ahern authored
The intent of the -s/--summary-only option is to just show a summary of the system calls and statistics without any of the individual events. Commit e596663e broke that by showing the interrupted lines: perf trace -i perf.data -s ... 0.741 ( 0.000 ms): sleep/31316 fstat(fd: 4, statbuf: 0x7ffc75ceb830 ) ... 0.744 ( 0.000 ms): sleep/31316 mmap(len: 100244, prot: READ, flags: PRIVATE, fd: 4 ) ... 0.747 ( 0.000 ms): perf/31315 write(fd: 3, buf: 0x7d4bb0, count: 8 ) ... ... Fix by checking for the summary only option. Signed-off-by:
-
He Kuang authored
Perf tries to find probe function addresses from map when debuginfo could not be found. To the first added function, the value of ref_reloc_sym was set in maps__set_kallsyms_ref_reloc_sym() and can be obtained from host_machine->kmaps->maps. After that, new maps are added to host_machine->kmaps->maps in dso__load_kcore(), all these new added maps do not have a valid ref_reloc_sym. When adding a second function, get_target_map() may get a map without valid ref_reloc_sym, and raise the error "Relocated base symbol is not found". Fix this by using kernel_get_ref_reloc_sym() to get ref_reloc_sym. This problem can be reproduced as following: $ perf probe --add='sys_write' --add='sys_open' Relocated base symbol is not found! Error: Failed to add events. After this patch: $ perf probe --add='sys_write' --add='sys_open' Added new event: probe:sys_write (on sys_write) You can now use it in all perf tools, such as: perf record -e probe:sys_write -aR sleep 1 Added new event: probe:sys_open (on sys_open) You can now use it in all perf tools, such as: perf record -e probe:sys_open -aR sleep 1 Signed-off-by:He Kuang <hekuang@huawei.com> Tested-by:
-
- 20 Mar, 2015 4 commits
-
-
Yunlong Song authored
They are all auto-generated files during the perf building. Before this patch: $ git status Untracked files: (use "git add <file>..." to include in what will be committed) config/feature-checks/test-all.make.output config/feature-checks/test-backtrace.make.output config/feature-checks/test-bionic.make.output config/feature-checks/test-dwarf.make.output config/feature-checks/test-fortify-source.make.output config/feature-checks/test-glibc.make.output config/feature-checks/test-gtk2-infobar.make.output config/feature-checks/test-gtk2.make.output config/feature-checks/test-libaudit.make.output config/feature-checks/test-libbabeltrace.make.output config/feature-checks/test-libbfd.make.output config/feature-checks/test-libdw-dwarf-unwind.make.output config/feature-checks/test-libelf-getphdrnum.make.output config/feature-checks/test-libelf-mmap.make.output config/feature-checks/test-libelf.make.output config/feature-checks/test-libnuma.make.output config/feature-checks/test-libperl.make.output config/feature-checks/test-libpython-version.make.output config/feature-checks/test-libpython.make.output config/feature-checks/test-libslang.make.output config/feature-checks/test-libunwind.make.output config/feature-checks/test-pthread-attr-setaffinity-np.make.output config/feature-checks/test-stackprotector-all.make.output config/feature-checks/test-sync-compare-and-swap.make.output config/feature-checks/test-timerfd.make.output config/feature-checks/test-zlib.make.output After this patch: $ git status nothing to commit, working directory clean Signed-off-by:
-
Yunlong Song authored
Since commit 4ae61202 ("perf build: Rename PERF-FEATURES into FEATURE-DUMP") renames PERF-FEATURES into FEATURE-DUMP, the .gitignore file should also do this thing for consistency. Signed-off-by:
-
Wang Nan authored
Both 'perf diff' and 'perf mem' have 'field-separator' option, which causes segfault if passed with empty string. This patch uses previously introduced 'OPT_STRING_NOEMPTY' option macro to prevent fault. Signed-off-by:
Wang Nan <wangnan0@huawei.com> Tested-by:
-
Milos Vyletel authored
int build_id_cache__add_s(const char *sbuild_id, const char *debugdir, const char *name, bool is_kallsyms, bool is_vdso) { ... if (access(filename, F_OK)) { ^--------------------------------------------------------- [1] if (is_kallsyms) { if (copyfile("/proc/kallsyms", filename)) goto out_free; } else if (link(realname, filename) && copyfile(name, filename)) ^-----------------------------^------------- [2] \------------ [3] goto out_free; } ... When multiple instances of perf record get to [1] at more or less same time and run access() one or more may get failure because the file does not exist yet (since the first instance did not have chance to link it yet). At this point the race moves to link() at [2] where first thread to get there links file and goes on but second one gets -EEXIST so it runs copyfile [3] which truncates the file. reproducer: rm -rf /root/.debug for cpu in $(awk '/processor/ {print $3}' /proc/cpuinfo); do perf record -a -v -T -F 1000 -C $cpu \ -o perf-${cpu}.data sleep 5 2> /dev/null & done wait and simply search for empty files by: find /lib/modules/`uname -r`/kernel/* -size 0 Signed-off-by:Milos Vyletel <milos@redhat.com> Acked-by:
-
- 19 Mar, 2015 1 commit
-
-
Wang Nan authored
Without this patch, perf report cause segfault if pass "" as '-t': $ perf report -t "" # To display the perf.data header info, please use --header/--header-only options. # # Samples: 37 of event 'syscalls:sys_enter_write' # Event count (approx.): 37 # # Children SelfCommand Shared Object Symbol Segmentation fault Since -t is used to add field-separator for generate table, -t "" is actually meanless. This patch defines a new OPT_STRING_NOEMPTY() option generator to ensure user never pass empty string to that option. Signed-off-by:
-
