aboutsummaryrefslogtreecommitdiff
path: root/tools/perf/util
AgeCommit message (Collapse)Author
2012-04-20perf symbols: Read plt symbols from proper symtab_type binaryJiri Olsa
When loading symbols from DSO we check multiple paths of DSO binary until we succeed to load symbols ('.symtab' section). Once symbols are read we try to load also plt symbols. During the reading of plt symbols, the dso file is reopened from location given by dso->long_name. This could be wrong in case we want process buildid binaries. The change is to make the plt symbols being read from the DSO path, that normal symbols were read from. Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1334756818-6631-1-git-send-email-jolsa@redhat.com [ committer note: moved dso to be the first parameter of that function ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-04-17perf tools: Add 'G' and 'H' modifiers to event parsingGleb Natapov
They were dropped during conversion of event parser. Add test case to make sure this will not happen again. Signed-off-by: Gleb Natapov <gleb@redhat.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Avi Kivity <avi@redhat.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/r/20120417111345.GK11918@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-04-12perf session: Skip event correctly for unknown id/machineJiri Olsa
In case the perf_session__process_event function fails, we estimate the next event offset. This is not necessary for sample event failing on unknown ID or machine. In such case we know proper size of the event, so we dont need to guess. Also failure statistics are updated correctly so we don't miss any information. Forcing perf_session__process_event to return 0 in case of unknown ID or machine. Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1334233262-5679-3-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-04-11perf kvm: Finding struct machine fails for PERF_RECORD_MMAPNikunj A. Dadhania
Running 'perf kvm --host --guest --guestmount /tmp/guestmount record -a -g -- sleep 2' Was resulting in a segfault. For event type PERF_RECORD_MMAP, event->ip.pid is being used in perf_session__find_machine_for_cpumode, which is not correct. The event->ip.pid field happens to be 0 in this case and results in returning a NULL machine object. Finally, access to self->pid in machine__mmap_name, results in a segfault later. For PERF_RECORD_MMAP type, pass event->mmap.pid. Signed-off-by: Nikunj A. Dadhania <nikunj@linux.vnet.ibm.com> Reviewed-by: David Ahern <dsahern@gmail.com> Tested-by: David Ahern <dsahern@gmail.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Stephane Eranian <eranian@google.com> Cc: Nikunj A. Dadhania <nikunj@linux.vnet.ibm.com> Link: http://lkml.kernel.org/r/20120409081835.10576.22018.stgit@abhimanyu.in.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-04-05perf annotate: Validate addr in symbol__inc_addr_samplesArnaldo Carvalho de Melo
This routine was checking only if the provided address was after sym->end, not if it was before sym->start. Fix that by checking for both and return in both cases -ERANGE, so that tools can communicate this to the user properly, or if they chose so, to abort. This problem was reported previously but the fixes involved either doing what was being done for the > end case, i.e. silently drop the sample, returning 0, or aborting at this function, which is in a lib (or better, is slated to be at some point) and shouldn't abort. The 'report' tool already checks this value and uses pr_debug to warn the user. This patch makes the 'top' tool check it too and warn once per map where such range problem takes place. Reported-by: David Miller <davem@davemloft.net> Reported-by: Sorin Dumitru <dumitru.sorin87@gmail.com> Reported-by: Stephane Eranian <eranian@google.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/n/tip-lw8gs7p9i9nhldilo82tzpne@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-04-05perf hists browser: Fix NULL deref in hists browsing codeJiri Olsa
If there's an event with no samples in data file, the perf report command can segfault after entering the event details menu. Following steps reproduce the issue: # ./perf record -e syscalls:sys_enter_kexec_load,syscalls:sys_enter_mmap ls # ./perf report # enter '0 syscalls:sys_enter_kexec_load' menu # pres ENTER twice Above steps are valid assuming ls wont run kexec.. ;) The check for sellection to be NULL is missing. The fix makes sure it's being check. Above steps now endup with menu being displayed allowing 'Exit' as the only option. Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1333570898-10505-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-04-05perf hists: Catch and handle out-of-date hist entry maps.David Miller
When a process exec()'s, all the maps are retired, but we keep the hist entries around which hold references to those outdated maps. If the same library gets mapped in for which we have hist entries, a new map will be created. But when we take a perf entry hit within that map, we'll find the existing hist entry with the older map. This causes symbol translations to be done incorrectly. For example, the perf entry processing will lookup the correct uptodate map entry and use that to calculate the symbol and DSO relative address. But later when we update the histogram we'll translate the address using the outdated map file instead leading to conditions such as out-of-range offsets in symbol__inc_addr_samples(). Therefore, update the map of the hist_entry dynamically at lookup/ creation time. Signed-off-by: David S. Miller <davem@davemloft.net> Cc: stable@kernel.org Link: http://lkml.kernel.org/r/20120327.031418.1220315351537060808.davem@davemloft.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-04-05perf annotate: Fix hist decayArnaldo Carvalho de Melo
We were only decaying the entries for the offsets that were associated with an objdump line. That way, when we accrued the whole instruction addr range, more than 100% was appearing in some cases in the live annotation TUI. Fix it by not traversing the source code line at all, just iterate thru the complete addr range decaying each one. Reported-by: Mike Galbraith <mgalbraith@suse.de> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-hcae5oxa22syjrnalsxz7s6n@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-31Merge branch 'perf/urgent' of ↵Ingo Molnar
git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent
2012-03-30perf tools: Remove auto-generated bison/flex filesIngo Molnar
These should not be in the Git history - they are auto-generated. Extend the Makefile rules of the parser files to include the generation run. Signed-off-by: Ingo Molnar <mingo@elte.hu> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20120327183335.GA27621@gmail.com [ committer note: Fixed up O= handling ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-29perf annotate: Fix off by one symbol hist size allocation and hit accountingArnaldo Carvalho de Melo
We were not noticing it because symbol__inc_addr_samples was erroneously dropping samples that hit the last byte in a function. Working on a fix for a problem reported by David Miller, Stephane Eranian and Sorin Dumitru, where addresses < sym->start were causing problems, I noticed this other problem. Cc: David Ahern <dsahern@gmail.com> Cc: David Miller <davem@davemloft.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Sorin Dumitru <dumitru.sorin87@gmail.com> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/n/tip-pqjaq4cr1xs2xen73pjhbav4@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-29perf tools: Add missing ref-cycles event back to event parserNamhyung Kim
The commit 89812fc81f8d ("perf tools: Add parser generator for events parsing") changed event parsing engine but missed the ref-cycles event. Add it. Signed-off-by: Namhyung Kim <namhyung.kim@lge.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1333016517-10591-1-git-send-email-namhyung.kim@lge.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-28perf annotate: addr2line wants addresses in same format as objdumpDavid Miller
Therefore, in symbol__get_source_line(), use map__rip_2objdump instead of calling map->unmap_ip() unconditionally. Link: http://lkml.kernel.org/r/20120325.162812.59519424882536855.davem@davemloft.net Signed-off-by: David S. Miller <davem@davemloft.net> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-28perf probe: Finder fails to resolve function name to addressPrashanth Nageshappa
If DIE entries corresponding to declarations appear before definition entry, probe finder returns error instead of continuing to look further for a definition entry. This patch ensures we reach to the DIE entry corresponding to the definition and get the function address. V2: A simpler solution based on Masami's suggestion. Signed-off-by: Prashanth Nageshappa <prashanth@linux.vnet.ibm.com> Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com> Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com> Cc: Steven Rostedt <rostedt@goodmis.org> Link: http://lkml.kernel.org/r/4F703FB9.9020407@linux.vnet.ibm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-27perf symbols: Handle NULL dso in dso__name_lenDavid Miller
We should use "[unknown]" in this case, in concert with the code in _hist_entry__dso_snprintf(). Otherwise we'll crash when recomputing the histogram column lengths in hists__calc_col_len(). Signed-off-by: David S. Miller <davem@davemloft.net> Link: http://lkml.kernel.org/r/20120325.162822.2267799792062571623.davem@davemloft.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-27perf symbols: Do not include libgen.hDavid Miller
That causes us to end up using the XPG version of basename which can modify it's argument. Signed-off-by: David S. Miller <davem@davemloft.net> Link: http://lkml.kernel.org/r/20120327.000301.1122788061724345175.davem@davemloft.net Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-26perf tools: Fix bug in raw sample parsingStephane Eranian
In perf_event__parse_sample(), the array variable was not incremented by the amount of data used by the raw_data. That was okay until we added PERF_SAMPLE_BRANCH_STACK which depends on the array variable pointing to the beginning of the branch stack data. But that was not the case if branch stack was combined with raw mode sampling. That led to bogus branch stack addresses and count. The bug would show up with: $ perf record -R -b foo This patch fixes the problem by correctly moving the array pointer forward for RAW samples. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Peter Zijlstra <peterz@infradead.org> Link: http://lkml.kernel.org/r/20120317222317.GA8803@quad [ committer note: Fix also later submitted by Jiri Olsa ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-26perf tools: Fix display of first level of callchainsFrederic Weisbecker
The callchain stdio mode display was written using a sorted by symbol report. In this mode we have only one callchain root per hist so we forgot to handle cases where we have multiple callchain root, as in per dso sorting for example. Fix this by handling these roots like any other branch, with the hist as the parent. Before: 1.97% libpthread-2.12.1.so | --- __libc_write create_worker bench_sched_messaging cmd_bench run_builtin main __libc_start_main | --- __libc_read create_worker bench_sched_messaging cmd_bench run_builtin main __libc_start_main After: 1.97% libpthread-2.12.1.so | |--36.97%-- __libc_write | create_worker | bench_sched_messaging | cmd_bench | run_builtin | main | __libc_start_main | |--31.47%-- __libc_read | create_worker | bench_sched_messaging | cmd_bench | run_builtin | main | __libc_start_main ... Single roots keep their entry without percentage because they have the same overhead than the hist they refer to. ie: 100% in fractal mode and the percentage of the hist in graph mode: 0.00% [k] reschedule_interrupt | --- default_idle amd_e400_idle cpu_idle start_secondary Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org> Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: David Ahern <dsahern@gmail.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Link: http://lkml.kernel.org/r/1332526010-15400-1-git-send-email-fweisbec@gmail.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-26perf tools: Switch module.h into export.hJiri Olsa
When merged to Linus's latest tree the perf build is broken due to following change in lib/rbtree.c object: lib: reduce the use of module.h wherever possible commit 8bc3bcc93a2b4e47d5d410146f6546bca6171663 Author: Paul Gortmaker <paul.gortmaker@windriver.com> Date: Wed Nov 16 21:29:17 2011 -0500 We need to move module.h header into export.h. Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: acme@redhat.com Cc: a.p.zijlstra@chello.nl Cc: paulus@samba.org Cc: cjashfor@linux.vnet.ibm.com Cc: fweisbec@gmail.com Link: http://lkml.kernel.org/r/1332753425-3299-1-git-send-email-jolsa@redhat.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
2012-03-26Merge branch 'linus' into perf/urgentIngo Molnar
Merge reason: we need to fix a non-trivial merge conflict. Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-03-23bitops: rename for_each_set_bit_cont() in favor of analogous list.h functionAkinobu Mita
This renames for_each_set_bit_cont() to for_each_set_bit_from() because it is analogous to list_for_each_entry_from() in list.h rather than list_for_each_entry_continue(). This doesn't remove for_each_set_bit_cont() for now. Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com> Cc: Robert Richter <robert.richter@amd.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: "H. Peter Anvin" <hpa@zytor.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
2012-03-22perf diff: Fix to work with new hists designJiri Olsa
The perf diff command is broken since: perf hists: Threaded addition and sorting of entries commit 1980c2ebd7020d82c024b8c4046849b38e78e7da Several places were broken: - hists data need to be collected into opened sessions instead of into events - session's hists data need to be initialized properly when the session is created - hist_entry__pcnt_snprintf: the percentage and displacement buffer preparation must not use 'ret' because it's used as a pointer to the final buffer Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20120322133726.GB1601@m.brq.redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-22perf tools: Fix modifier to be applied on correct eventsJiri Olsa
The event modifier needs to be applied only on the event definition it is attached to. The current state is that in case of multiple events definition (in single '-e' option, separated by ',') all will get modifier of the last one. Fixing this by adding separated list for each event definition, so the modifier is applied only to proper event(s). Added automated test to catch this, plus some other modifier tests. Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1332267341-26338-3-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-22perf tools: Fix various casting issues for 32 bitsJiri Olsa
- util/parse-events.c(parse_events_add_breakpoint) need to use unsigned long instead of u64, otherwise we get following gcc error on 32 bits: error: cast from pointer to integer of different size - util/header.c(print_event_desc) cannot retype to signed type, otherwise we get following gcc error on 32 bits: error: comparison between signed and unsigned integer expressions Signed-off-by: Jiri Olsa <jolsa@redhat.com> Cc: Corey Ashford <cjashfor@linux.vnet.ibm.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1332267341-26338-2-git-send-email-jolsa@redhat.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-22perf tools: Simplify event_read_id exit pathBorislav Petkov
We're freeing the token in any case so simplify the exit path by unifying it. No functional change. Signed-off-by: Borislav Petkov <bp@amd64.org> Link: http://lkml.kernel.org/r/1332339347-21342-1-git-send-email-bp@amd64.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-22Merge branch 'perf/urgent' into perf/coreArnaldo Carvalho de Melo
Merge Reason: to pick the fix: commit e7f01d1 perf tools: Use scnprintf where applicable Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-20Merge branch 'perf-core-for-linus' of ↵Linus Torvalds
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull perf events changes for v3.4 from Ingo Molnar: - New "hardware based branch profiling" feature both on the kernel and the tooling side, on CPUs that support it. (modern x86 Intel CPUs with the 'LBR' hardware feature currently.) This new feature is basically a sophisticated 'magnifying glass' for branch execution - something that is pretty difficult to extract from regular, function histogram centric profiles. The simplest mode is activated via 'perf record -b', and the result looks like this in perf report: $ perf record -b any_call,u -e cycles:u branchy $ perf report -b --sort=symbol 52.34% [.] main [.] f1 24.04% [.] f1 [.] f3 23.60% [.] f1 [.] f2 0.01% [k] _IO_new_file_xsputn [k] _IO_file_overflow 0.01% [k] _IO_vfprintf_internal [k] _IO_new_file_xsputn 0.01% [k] _IO_vfprintf_internal [k] strchrnul 0.01% [k] __printf [k] _IO_vfprintf_internal 0.01% [k] main [k] __printf This output shows from/to branch columns and shows the highest percentage (from,to) jump combinations - i.e. the most likely taken branches in the system. "branches" can also include function calls and any other synchronous and asynchronous transitions of the instruction pointer that are not 'next instruction' - such as system calls, traps, interrupts, etc. This feature comes with (hopefully intuitive) flat ascii and TUI support in perf report. - Various 'perf annotate' visual improvements for us assembly junkies. It will now recognize function calls in the TUI and by hitting enter you can follow the call (recursively) and back, amongst other improvements. - Multiple threads/processes recording support in perf record, perf stat, perf top - which is activated via a comma-list of PIDs: perf top -p 21483,21485 perf stat -p 21483,21485 -ddd perf record -p 21483,21485 - Support for per UID views, via the --uid paramter to perf top, perf report, etc. For example 'perf top --uid mingo' will only show the tasks that I am running, excluding other users, root, etc. - Jump label restructurings and improvements - this includes the factoring out of the (hopefully much clearer) include/linux/static_key.h generic facility: struct static_key key = STATIC_KEY_INIT_FALSE; ... if (static_key_false(&key)) do unlikely code else do likely code ... static_key_slow_inc(); ... static_key_slow_inc(); ... The static_key_false() branch will be generated into the code with as little impact to the likely code path as possible. the static_key_slow_*() APIs flip the branch via live kernel code patching. This facility can now be used more widely within the kernel to micro-optimize hot branches whose likelihood matches the static-key usage and fast/slow cost patterns. - SW function tracer improvements: perf support and filtering support. - Various hardenings of the perf.data ABI, to make older perf.data's smoother on newer tool versions, to make new features integrate more smoothly, to support cross-endian recording/analyzing workflows better, etc. - Restructuring of the kprobes code, the splitting out of 'optprobes', and a corner case bugfix. - Allow the tracing of kernel console output (printk). - Improvements/fixes to user-space RDPMC support, allowing user-space self-profiling code to extract PMU counts without performing any system calls, while playing nice with the kernel side. - 'perf bench' improvements - ... and lots of internal restructurings, cleanups and fixes that made these features possible. And, as usual this list is incomplete as there were also lots of other improvements * 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (120 commits) perf report: Fix annotate double quit issue in branch view mode perf report: Remove duplicate annotate choice in branch view mode perf/x86: Prettify pmu config literals perf report: Enable TUI in branch view mode perf report: Auto-detect branch stack sampling mode perf record: Add HEADER_BRANCH_STACK tag perf record: Provide default branch stack sampling mode option perf tools: Make perf able to read files from older ABIs perf tools: Fix ABI compatibility bug in print_event_desc() perf tools: Enable reading of perf.data files from different ABI rev perf: Add ABI reference sizes perf report: Add support for taken branch sampling perf record: Add support for sampling taken branch perf tools: Add code to support PERF_SAMPLE_BRANCH_STACK x86/kprobes: Split out optprobe related code to kprobes-opt.c x86/kprobes: Fix a bug which can modify kernel code permanently x86/kprobes: Fix instruction recovery on optimized path perf: Add callback to flush branch_stack on context switch perf: Disable PERF_SAMPLE_BRANCH_* when not supported perf/x86: Add LBR software filter support for Intel CPUs ...
2012-03-19perf report: Add a simple GTK2-based 'perf report' browserPekka Enberg
This patch adds a simple GTK2-based browser to 'perf report' that's based on the TTY-based browser in builtin-report.c. To launch "perf report" using the new GTK interface just type: $ perf report --gtk The interface is somewhat limited in features at the moment: - No callgraph support - No KVM guest profiling support - No color coding for percentages - No sorting from the UI - ..and many, many more! That said, I think this patch a reasonable start to build future features on. Signed-off-by: Pekka Enberg <penberg@kernel.org> Cc: Colin Walters <walters@verbum.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Paul Mackerras <paulus@samba.org> Cc: Ingo Molnar <mingo@kernel.org> Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1202231952410.6689@tux.localdomain [ committer note: Added #pragma to make gtk no strict prototype problem go away as suggested by Colin Walters modulo avoiding push/pop ] Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-19perf ui browser: Clean lines inside of the input windowNamhyung Kim
As Arnaldo pointed out, it should be cleared to prevent the window from displaying overlapped strings on the region. Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Namhyung Kim <namhyung.kim@lge.com> Cc: Ingo Molnar <mingo@kernel.org> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1332125180-23041-1-git-send-email-namhyung.kim@lge.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-16perf ui browser: Add 's' key to filter by symbol nameNamhyung Kim
Now user can enter symbol name interested via ui_browser__input_window, and perf can process it using hists__filter_by_symbol(). Giving empty symbol (by pressing 's' followed by ENTER) will disable the filtering. Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1331887855-874-3-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim <namhyung.kim@lge.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-16perf ui browser: Introduce ui_browser__input_windowNamhyung Kim
The ui_browser__input_window() function is to get user's key input. Current implementation can handle maximum 49 characters. Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1331887855-874-2-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim <namhyung.kim@lge.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-16perf hists: Add hists__filter_by_symbolNamhyung Kim
This function will be used for simple (sub-)string matching filter based on user input. Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1331887855-874-1-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim <namhyung.kim@lge.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-16perf tools: Do not disable members of group eventNamhyung Kim
When event group is enabled for forked task (i.e. no target task/cpu was specified) all events were disabled and marked ->enable_on_exec. However they wouldn't be counted at all since only group leader will be enabled on exec actually. In contrast to perf stat, perf record doesn't have a real problem as it enables all the event before proceeding. But it needs to be fixed anyway IMHO. Cc: Ingo Molnar <mingo@elte.hu> Cc: Namhyung Kim <namhyung@gmail.com> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/1331887340-32448-2-git-send-email-namhyung.kim@lge.com Signed-off-by: Namhyung Kim <namhyung.kim@lge.com> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-16perf tools: Add support to specify pmu style eventJiri Olsa
Added new event rule to the event definition grammar: event_def: event_pmu | ... event_pmu: PE_NAME '/' event_config '/' Using this rule, event could be now specified like: cpu/config=1,config1=2,config2=3/u where pmu name 'cpu' is looked up via following path: ${sysfs_mount}/bus/event_source/devices/${pmu} and config options are bound to the pmu's format definiton: ${sysfs_mount}/bus/event_source/devices/${pmu}/format The hardcoded config options still stays and have precedence over any format field defined with same name. Acked-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/n/tip-50d8nr94f8k4wkezutrxvthe@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-16perf tools: Add perf pmu object to access pmu format definitionJiri Olsa
Adding pmu object which provides interface to pmu's sysfs event format definition located at: ${sysfs_mount}/bus/event_source/devices/${pmu}/format Following interface is exported: struct perf_pmu* perf_pmu__find(char *name); - this function returns pmu object, which is then passed as a handle to other interface functions int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr, struct list_head *head_terms); - this function configures perf_event_attr struct based on pmu's format definitions and config terms data, containined in head_terms list. Parser generator is used to retrive the pmu's format definition. The generated parser is part of the patch. Added makefile rule 'pmu-parser' to generate the parser code out of the bison/flex sources. Added builtin test 'Test perf pmu format parsing', which could be run like: perf test pmu Acked-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/n/tip-errz96u1668gj9wlop1zhpht@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-16perf tools: Add config options support for event parsingJiri Olsa
Adding a new rule to the event grammar to be able to specify values of additional attributes of symbolic event. The new syntax for event symbolic definition is: event_legacy_symbol: PE_NAME_SYM '/' event_config '/' | PE_NAME_SYM sep_slash_dc event_config: event_config ',' event_term | event_term event_term: PE_NAME '=' PE_NAME | PE_NAME '=' PE_VALUE PE_NAME sep_slash_dc: '/' | ':' | At the moment the config options are hardcoded to be used for legacy symbol events to define several perf_event_attr fields. It is: 'config' to define perf_event_attr::config 'config1' to define perf_event_attr::config1 'config2' to define perf_event_attr::config2 'period' to define perf_event_attr::sample_period Legacy events could be now specified as: cycles/period=100000/ If term is specified without the value assignment, then 1 is assigned by default. Acked-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/n/tip-mgkavww9790jbt2jdkooyv4q@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-16perf tools: Add parser generator for events parsingJiri Olsa
Changing event parsing to use flex/bison parse generator. The event syntax stays as it was. grammar description: events: events ',' event | event event: event_def PE_MODIFIER_EVENT | event_def event_def: event_legacy_symbol sep_dc | event_legacy_cache sep_dc | event_legacy_breakpoint sep_dc | event_legacy_tracepoint sep_dc | event_legacy_numeric sep_dc | event_legacy_raw sep_dc event_legacy_symbol: PE_NAME_SYM event_legacy_cache: PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT '-' PE_NAME_CACHE_OP_RESULT | PE_NAME_CACHE_TYPE '-' PE_NAME_CACHE_OP_RESULT | PE_NAME_CACHE_TYPE event_legacy_raw: PE_SEP_RAW PE_VALUE event_legacy_numeric: PE_VALUE ':' PE_VALUE event_legacy_breakpoint: PE_SEP_BP ':' PE_VALUE ':' PE_MODIFIER_BP event_breakpoint_type: PE_MODIFIER_BPTYPE | empty PE_NAME_SYM: cpu-cycles|cycles | stalled-cycles-frontend|idle-cycles-frontend | stalled-cycles-backend|idle-cycles-backend | instructions | cache-references | cache-misses | branch-instructions|branches | branch-misses | bus-cycles | cpu-clock | task-clock | page-faults|faults | minor-faults | major-faults | context-switches|cs | cpu-migrations|migrations | alignment-faults | emulation-faults PE_NAME_CACHE_TYPE: L1-dcache|l1-d|l1d|L1-data | L1-icache|l1-i|l1i|L1-instruction | LLC|L2 | dTLB|d-tlb|Data-TLB | iTLB|i-tlb|Instruction-TLB | branch|branches|bpu|btb|bpc | node PE_NAME_CACHE_OP_RESULT: load|loads|read | store|stores|write | prefetch|prefetches | speculative-read|speculative-load | refs|Reference|ops|access | misses|miss PE_MODIFIER_EVENT: [ukhp]{0,5} PE_MODIFIER_BP: [rwx] PE_SEP_BP: 'mem' PE_SEP_RAW: 'r' sep_dc: ':' | Added flex/bison files for event grammar parsing. The generated parser is part of the patch. Added makefile rule 'event-parser' to generate the parser code out of the bison/flex sources. Acked-by: Peter Zijlstra <peterz@infradead.org> Signed-off-by: Jiri Olsa <jolsa@redhat.com> Link: http://lkml.kernel.org/n/tip-u4pfig5waq3ll2bfcdex8fgi@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-14perf tools, x86: Build perf on older user-space as wellIngo Molnar
On ancient systems I get this build failure: util/../../../arch/x86/include/asm/unistd.h:67:29: error: asm/unistd_64.h: No such file or directory In file included from util/cache.h:7, from builtin-test.c:8: util/../perf.h: In function ‘sys_perf_event_open’:In file included from util/../perf.h:16 perf.h:170: error: ‘__NR_perf_event_open’ undeclared (first use in this function) The reason is that this old system does not have the split unistd.h headers yet, from which to pick up the syscall definitions. Add the syscall numbers to the already existing i386 and x86_64 blocks in perf.h, and also provide empty include file stubs. With this patch perf builds and works fine on 5 years old user-space as well. Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: Arnaldo Carvalho de Melo <acme@redhat.com> Link: http://lkml.kernel.org/n/tip-jctwg64le1w47tuaoeyftsg9@git.kernel.org Signed-off-by: Ingo Molnar <mingo@elte.hu> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-14perf tools: Use scnprintf where applicableArnaldo Carvalho de Melo
Several places were expecting that the value returned was the number of characters printed, not what would be printed if there was space. Fix it by using the scnprintf and vscnprintf variants we inherited from the kernel sources. Some corner cases where the number of printed characters were not accounted were fixed too. Reported-by: Anton Blanchard <anton@samba.org> Cc: Anton Blanchard <anton@samba.org> Cc: Eric B Munson <emunson@mgebm.net> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Mike Galbraith <efault@gmx.de> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Stephane Eranian <eranian@google.com> Cc: Yanmin Zhang <yanmin_zhang@linux.intel.com> Cc: stable@kernel.org Link: http://lkml.kernel.org/n/tip-kwxo2eh29cxmd8ilixi2005x@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-14perf tools: Incorrect use of snprintf results in SEGVAnton Blanchard
I have a workload where perf top scribbles over the stack and we SEGV. What makes it interesting is that an snprintf is causing this. The workload is a c++ gem that has method names over 3000 characters long, but snprintf is designed to avoid overrunning buffers. So what went wrong? The problem is we assume snprintf returns the number of characters written: ret += repsep_snprintf(bf + ret, size - ret, "[%c] ", self->level); ... ret += repsep_snprintf(bf + ret, size - ret, "%s", self->ms.sym->name); Unfortunately this is not how snprintf works. snprintf returns the number of characters that would have been written if there was enough space. In the above case, if the first snprintf returns a value larger than size, we pass a negative size into the second snprintf and happily scribble over the stack. If you have 3000 character c++ methods thats a lot of stack to trample. This patch fixes repsep_snprintf by clamping the value at size - 1 which is the maximum snprintf can write before adding the NULL terminator. I get the sinking feeling that there are a lot of other uses of snprintf that have this same bug, we should audit them all. Cc: David Ahern <dsahern@gmail.com> Cc: Eric B Munson <emunson@mgebm.net> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Ingo Molnar <mingo@elte.hu> Cc: Paul Mackerras <paulus@samba.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Yanmin Zhang <yanmin_zhang@linux.intel.com> Cc: stable@kernel.org Link: http://lkml.kernel.org/r/20120307114249.44275ca3@kryten Signed-off-by: Anton Blanchard <anton@samba.org> Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
2012-03-13perf record: Fix buffer overrun bug in tracepoint_id_to_path()Stephane Eranian
This patch fixes a buffer overrun bug in tracepoint_id_to_path(). The bug manisfested itself as a memory error reported by perf record. I ran into it with perf sched: $ perf sched rec noploop 2 noploop for 2 seconds [ perf record: Woken up 14 times to write data ] [ perf record: Captured and wrote 42.701 MB perf.data (~1865622 samples) ] Fatal: No memory to alloc tracepoints list It turned out that tracepoint_id_to_path() was reading the tracepoint id using read() but the buffer was not large enough to include the \n terminator for id with 4 digits or more. The patch fixes the problem by extending the buffer to a more reasonable size covering all possible id length include \n terminator. Note that atoll() stops at the first non digit character, thus it is not necessary to clear the buffer between each read. Signed-off-by: Stephane Eranian <eranian@google.com> Acked-by: Arnaldo Carvalho de Melo <acme@redhat.com> Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: fweisbec@gmail.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/20120313155102.GA6465@quad Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-03-12Merge branch 'perf/hw-branch-sampling' into perf/coreIngo Molnar
Merge reason: The 'perf record -b' hardware branch sampling feature is ready for upstream. Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-03-12perf report: Fix annotate double quit issue in branch view modeStephane Eranian
This patch fixes perf report to not go back two levels when pressing the 'q' key while annotating in branch view mode. When pressing 'q' in annotate mode and if the branch source and target belong to different functions, perf now brings up the annotation popup menu again to offer the option to annotate the other branch source or target. As part of the code restructuring in perf_evsel__hists_browse() we also fix a memory leak on options[] in case of error. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1331565210-10865-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-03-12perf report: Remove duplicate annotate choice in branch view modeStephane Eranian
This patch removes the duplicated annotate selection when browsing in branch view mode. If the sym and dso oof the branch source and target are the same, then only one annotate choice is proposed. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1331565210-10865-2-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-03-09perf report: Enable TUI in branch view modeStephane Eranian
This patch updates perf report to support TUI mode when the perf.data file contains samples with branch stacks. For each row in the report, it is possible to annotate either the source or target of each branch. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1331246868-19905-5-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-03-09perf report: Auto-detect branch stack sampling modeStephane Eranian
This patch enhances perf report to auto-detect when the perf.data file contains samples with branch stacks. That way it is not necessary to use the -b option. To force branch view mode to off, simply use --no-branch-stack. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1331246868-19905-4-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-03-09perf record: Add HEADER_BRANCH_STACK tagStephane Eranian
This patch adds a new feature bit, namely, HEADER_BRANCH_STACK. When present, it indicates that sample records may contain branch stack. This could be useful to a viewer to switch to branch mode without having to parse all the samples or without a specific cmdline option. This will be used in a subsequent patch to enhance perf report with branch stacks. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1331246868-19905-3-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-03-09perf tools: Make perf able to read files from older ABIsStephane Eranian
This patches provides a way to handle legacy perf.data files. Legacy files are those using the older PERFFILE signature. For those, it is still necessary to detect endianness but without comparing their header->attr_size with the tool's own version as it may be different. Instead, we use a reference table for all known sizes from the legacy era. We try all the combinations for sizes and endianness. If we find a match, we proceed, otherwise we return: "incompatible file format". This is also done for the pipe-mode file format. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-19-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-03-09perf tools: Fix ABI compatibility bug in print_event_desc()Stephane Eranian
This patches cleans up local variable types for msz and ret. They need to be size_t and ssize_t respectively. It also fixes a bug whereby perf would not read attr struct with a different size than what it knows about. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-18-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>
2012-03-09perf tools: Enable reading of perf.data files from different ABI revStephane Eranian
This patch allows perf to process perf.data files generated using an ABI that has a different perf_event_attr struct size, i.e., a different ABI version. The perf_event_attr can be extended, yet perf needs to cope with older perf.data files. Similarly, perf must be able to cope with a perf.data file which is using a newer version of the ABI than what it knows about. This patch adds read_attr(), a routine that reads a perf_event_attr struct from a file incrementally based on its advertised size. If the on-file struct is smaller than what perf knows, then the extra fields are zeroed. If the on-file struct is bigger, then perf only uses what it knows about, the rest is skipped. Signed-off-by: Stephane Eranian <eranian@google.com> Cc: peterz@infradead.org Cc: acme@redhat.com Cc: robert.richter@amd.com Cc: ming.m.lin@intel.com Cc: andi@firstfloor.org Cc: asharma@fb.com Cc: ravitillo@lbl.gov Cc: vweaver1@eecs.utk.edu Cc: khandual@linux.vnet.ibm.com Cc: dsahern@gmail.com Link: http://lkml.kernel.org/r/1328826068-11713-17-git-send-email-eranian@google.com Signed-off-by: Ingo Molnar <mingo@elte.hu>