- 27 Mar, 2015 4 commits
-
-
Andi Kleen authored
On Broadwell INST_RETIRED.ALL cannot be used with any period that doesn't have the lowest 6 bits cleared. And the period should not be smaller than 128. This is erratum BDM11 and BDM55: http://www.intel.com/content/dam/www/public/us/en/documents/specification-updates/5th-gen-core-family-spec-update.pdf BDM11: When using a period < 100; we may get incorrect PEBS/PMI interrupts and/or an invalid counter state. BDM55: When bit0-5 of the period are !0 we may get redundant PEBS records on overflow. Add a new callback to enforce this, and set it for Broadwell. How does this handle the case when an app requests a specific period with some of the bottom bits set? Short answer: Any useful instruction sampling period needs to be 4-6 orders of magnitude larger than 128, as an PMI every 128 instructions would instantly overwhelm the system and be throttled. So the +-64 error from this is really small compared to the period, much smaller than normal system jitter. Long answer (by Peterz): IFF we guarantee perf_event_attr::sample_period >= 128. Suppose we start out with sample_period=192; then we'll set period_left to 192, we'll end up with left = 128 (we truncate the lower bits). We get an interrupt, find that period_left = 64 (>0 so we return 0 and don't get an overflow handler), up that to 128. Then we trigger again, at n=256. Then we find period_left = -64 (<=0 so we return 1 and do get an overflow). We increment with sample_period so we get left = 128. We fire again, at n=384, period_left = 0 (<=0 so we return 1 and get an overflow). And on and on. So while the individual interrupts are 'wrong' we get then with interval=256,128 in exactly the right ratio to average out at 192. And this works for everything >=128. So the num_samples*fixed_period thing is still entirely correct +- 127, which is good enough I'd say, as you already have that error anyhow. So no need to 'fix' the tools, al we need to do is refuse to create INST_RETIRED:ALL events with sample_period < 128. Signed-off-by:
Andi Kleen <ak@linux.intel.com> [ Updated comments and changelog a bit. ] Signed-off-by:
Peter Zijlstra (Intel) <peterz@infradead.org> Link: http://lkml.kernel.org/r/1424225886-18652-3-git-send-email-andi@firstfloor.orgSigned-off-by:
Ingo Molnar <mingo@kernel.org>
-
Andi Kleen authored
Add Broadwell support for Broadwell to perf. The basic support is very similar to Haswell. We use the new cache event list added for Haswell earlier. The only differences are a few bits related to remote nodes. To avoid an extra, mostly identical, table these are patched up in the initialization code. The constraint list has one new event that needs to be handled over Haswell. Includes code and testing from Kan Liang. Signed-off-by:
-
Andi Kleen authored
Haswell offcore events are quite different from Sandy Bridge. Add a new table to handle Haswell properly. Note that the offcore bits listed in the SDM are not quite correct (this is currently being fixed). An uptodate list of bits is in the patch. The basic setup is similar to Sandy Bridge. The prefetch columns have been removed, as prefetch counting is not very reliable on Haswell. One L1 event that is not in the event list anymore has been also removed. - data reads do not include code reads (comparable to earlier Sandy Bridge tables) - data counts include speculative execution (except L1 write, dtlb, bpu) - remote node access includes both remote memory, remote cache, remote mmio. - prefetches are not included in the counts for consistency (different from Sandy Bridge, which includes prefetches in the remote node) 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: - Show the first event with an invalid filter (David Ahern, Arnaldo Carvalho de Melo) - Fix garbage output when intermixing syscalls from different threads in 'perf trace' (Arnaldo Carvalho de Melo) - Fix 'perf timechart' SIBGUS error on sparc64 (David Ahern) Infrastructure changes: - Set JOBS based on CPU or processor, making it work on SPARC, where /proc/cpuinfo has "CPU", not "processor" (David Ahern) - Zero should not be considered "not found" in libtraceevent's eval_flag() (Steven Rostedt) Signed-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by:
-
- 26 Mar, 2015 6 commits
-
-
Steven Rostedt authored
Guilherme Cox found that: There is, however, a potential bug if there is an item with code zero that is not the first one in the symbol list, since eval_flag(..) returns 0 when it doesn't find anything. That is, if you have the following enums: enum { FOO_START = 0, FOO_GO = 1, FOO_END = 2 } and then have: __print_symbolic(foo, FOO_GO, "go", FOO_START, "start", FOO_END, "end") If none of the enums are known to pevent, then eval_flag() will return zero, and it will match it to the first item in the list, which would be FOO_GO, which is not zero. Luckily, in most cases, the first element would be zero, and the parsing would match out of sheer luck. Reported-by:Guilherme Cox <cox@computer.org> Signed-off-by:
Steven Rostedt <rostedt@goodmis.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/20150324145813.0bfe95ba@gandalf.local.homeSigned-off-by:
-
Arnaldo Carvalho de Melo authored
commit e596663e Author: Arnaldo Carvalho de Melo <acme@redhat.com> Date: Fri Feb 13 13:22:21 2015 -0300 perf trace: Handle multiple threads better wrt syscalls being intermixed Introduced a bug where it considered the number of bytes output directly to the output file when formatting the syscall entry buffer that is stored to be finally printed at syscall exit, ending up leaving garbage at the start of syscalls that appeared while another syscall was being processed, in another thread. Fix it. Example of garbage in the output before this patch: 4280.102 ( 0.000 ms): lsmd/763 ... [continued]: select()) = 0 Timeout 4280.107 (275.250 ms): tuned/852 select(tvp: 0x7f41f7ffde50 ) ... 4280.109 ( 0.002 ms): lsmd/763 Xl�� ) = -10 4639.197 ( 0.000 ms): systemd-journa/542 ... [continued]: epoll_wait()) = 1 4639.202 (359.088 ms): lsmd/763 select(n: 6, inp: 0x7ffff21daad0, tvp: 0x7ffff21daac0) ... 4639.207 ( 0.005 ms): systemd-journa/542 Hn�� ) = 106 4639.221 ( 0.002 ms): systemd-journa/542 uname(name: 0x7ffdbaed8e00) = 0 4639.271 ( 0.008 ms): systemd-journa/542 ftruncate(fd: 11</run/log/journal/60cd52417cf440a4a80107518bbd3c20/system.journal>, length: 50331648) = 0 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: Namhyung Kim <namhyung@kernel.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-9ckfe8mvsedgkg6y80gz1ul8@git.kernel.orgSigned-off-by:
-
David Ahern authored
Number of JOBS to use is set automatically to the number of processors found in /proc/cpuinfo. SPARC uses 'CPU' lines rather than 'processor'. Update the check in perf's Makefile to work for SPARC. Signed-off-by:
David Ahern <david.ahern@oracle.com> Acked-by:
Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Link: http://lkml.kernel.org/r/1427213455-127249-1-git-send-email-david.ahern@oracle.comSigned-off-by:
-
David Ahern authored
SPARC based systems currently support up to 1024 cpus (e.g. T5-8). Allow perf to work on those systems. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Use of a bad filter currently generates the message: Error: failed to set filter with 22 (Invalid argument) Add the event name to make it clear to which event the filter failed to apply: Error: Failed to set filter "foo" on event sched:sg_lb_stats: 22: Invalid argument To test it use something like: # perf record -e sched:sched_switch -e sched:*fork --filter parent_pid==1 -e sched:*wait* --filter bla usleep 1 Error: failed to set filter "bla" on event sched:sched_stat_iowait with 22 (Invalid argument) # Based-on-a-patch-by:
David Ahern <dsahern@gmail.com> Acked-by:
-
David Ahern authored
perf timechart -T on sparc64 is terminating due to SIGBUS. Backtrace: Program received signal SIGBUS, Bus error. 0x0000000000173d7c in perf_evsel__intval (evsel=<value optimized out>, sample=0x7feffffda28, name=0x289b28 "prev_state") at util/evsel.c:1918 1918 util/evsel.c: No such file or directory. in util/evsel.c Missing separate debuginfos, use: debuginfo-install audit-libs-2.3.7-1.0.1.el6.sparc64 bzip2-libs-1.0.5-7.el6_0.sparc64 elfutils-libelf-0.155-2.0.3.el6.sparc64 elfutils-libs-0.155-2.0.3.el6.sparc64 glibc-2.12-1.132.0.8.el6_5.sparc64 numactl-2.0.7-8.el6.sparc64 python-libs-2.6.6-52.0.2.el6.sparc64 slang-2.2.1-1.el6.sparc64 xz-libs-4.999.9-0.3.beta.20091007git.el6.sparc64 zlib-1.2.3-29.el6.sparc64 (gdb) bt 0 0x0000000000173d7c in perf_evsel__intval (evsel=<value optimized out>, sample=0x7feffffda28, name=0x289b28 "prev_state") at util/evsel.c:1918 1 0x0000000000123b94 in process_sample_sched_switch (tchart=0x7feffffe040, evsel=0x4ca850, sample=0x7feffffda28, backtrace=0xc39010 "") at builtin-timechart.c:627 2 0x0000000000122828 in process_sample_event (tool=0x7feffffe040, event=<value optimized out>, sample=0x7feffffda28, evsel=0x4ca850, machine=0x4c9c88) at builtin-timechart.c:569 Another extended load on unaligned pointer. As before fix by copying to a temporary variable using memcpy. Signed-off-by:
-
- 24 Mar, 2015 19 commits
-
-
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: - Improve support of compressed kernel modules (Jiri Olsa) - Add --kallsyms option to 'perf diff' (David Ahern) - Add pid/tid filtering to 'report' and 'script' commands (David Ahern) - Add support for __print_array() in libtraceevent (Javi Merino) - Save DSO loading errno to better report errors (Arnaldo Carvalho de Melo) - Fix 'probe' to get ummapped symbol address on kernel (Masami Hiramatsu) - Print big numbers using thousands' group in 'kmem' (Namhyung Kim) - Remove (null) value of "Sort order" for perf mem report (Yunlong Song) Infrastructure changes: - Handle NULL comm name in libtracevent (Josef Bacik) - Libtraceevent synchronization with trace-cmd repo (Steven Rostedt) - Work around lack of sched_getcpu() in glibc < 2.6. (Vinson Lee) Signed-off-by:
-
David Ahern authored
The 'record' and 'top' tools already allow a user to specify a CSV of pids and/or tids of tasks to collect data. Add those options to the 'report' and 'script' analysis commands to only consider samples related to the given pids/tids. This is also inline with the existing comm option. Signed-off-by:
-
David Ahern authored
Required for off-box analysis to convert kernel addresses. Signed-off-by:
-
Javi Merino authored
Since 6ea22486 ("tracing: Add array printing helper") trace can generate traces with variable element size arrays. Add support to parse them. Signed-off-by:
Javi Merino <javi.merino@arm.com> Acked-by:
Namhyung Kim <namhyung@kernel.org> Acked-by:
-
Steven Rostedt (Red Hat) authored
valgrind showed that the filter token wasn't being freed properly in process_filter(). Signed-off-by:
-
Steven Rostedt (Red Hat) authored
For debugging purposes, it may be helpful for the kbuffer library to flag when crossing a sub buffer. Signed-off-by:
-
Steven Rostedt (Red Hat) authored
When a event PADDING is hit (a deleted event that is still in the ring buffer), translate_data() sets the length of the padding and also updates the data pointer which is passed back to the caller. This is unneeded because the caller also updates the data pointer with the passed back length. translate_data() should not update the pointer, only set the length. Signed-off-by:
-
Steven Rostedt authored
When a plugin option is defined, by default it is a boolean (true or false). If the option is something else, then it needs to set its "value" field to a default string other than NULL (can be just ""). If the value is not set then the option is considered boolean, and the updating of the option value will be handled accordingly. Signed-off-by:
-
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 (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: -
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:
-
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:
-
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 2 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:
-
