linux/tools/perf, branch v4.2

perf top: Show backtrace when handling a SIGSEGV on --stdio mode

2015-08-19T18:16:08Z

It was just freezing instead of informing about the SEGV, fix it and also print a backtrace, just like in the TUI mode and in 'perf trace'. Tested by provoking a NULL deref when pressing 'z': 0.31% libc-2.20.so [.] malloc_consolidate 0.31% ld-2.20.so [.] _dl_relocate_object 0.28% cc1 [.] ht_lookup 0.28% cc1 [.] ira_init_register_move_cost perf: Segmentation fault Obtained 7 stack frames. perf(dump_stack+0x32) [0x4d69f2] perf(sighandler_dump_stack+0x29) [0x4d6a89] /lib64/libc.so.6(+0x34960) [0x7f5064333960] perf() [0x438790] /lib64/libpthread.so.0(+0x752a) [0x7f50663dd52a] /lib64/libc.so.6(clone+0x6d) [0x7f50643ff22d] # Reported-by: Linus Torvalds Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-pewrpzqd29rgmhu2wkk7fhww@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Fix buildid processing

2015-08-19T17:15:26Z

After recording, 'perf record' post-processes the data to determine which buildids are needed. That processing must process the data in time order, if possible, because otherwise dependent events, like forks and mmaps, will not make sense. Signed-off-by: Adrian Hunter Tested-by: Jiri Olsa Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1439994561-27436-4-git-send-email-adrian.hunter@intel.com [ Moved the sample_id_add to after trying to open the events, use pr_warning ] Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Make fork event processing more resilient

2015-08-19T17:15:25Z

When processing a fork event, the tools lookup the parent thread by its tid. In a couple of cases, it is possible for that thread to have the wrong pid. That can happen if the data is being processed out of order, or if the (fork) event that would have removed the erroneous thread was lost. Assume the latter case, print a dump message, remove the erroneous thread, create a new one with the correct pid, and keep going. Reported-by: Arnaldo Carvalho de Melo Signed-off-by: Adrian Hunter Tested-by: Jiri Olsa Cc: Linus Torvalds Link: http://lkml.kernel.org/r/1439994561-27436-3-git-send-email-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Avoid deadlock when map_groups are broken

2015-08-19T17:15:09Z

Attempting to clone map groups onto themselves will deadlock. It only happens because of other bugs, but the code should protect itself anyway. Reported-by: Linus Torvalds Signed-off-by: Adrian Hunter Tested-by: Jiri Olsa Link: http://lkml.kernel.org/r/1439994561-27436-2-git-send-email-adrian.hunter@intel.com [ Use pr_debug() instead of dump_fprintf() ] Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Fix test build error when bindir contains double slash

2015-07-28T16:03:49Z

When building with a prefix ending with a slash, for example: $ make prefix=/usr/local/ one of the perf tests fail to compile due to BUILD_STR macro mishandling bindir_SQ string containing with two slashes: -DBINDIR="BUILD_STR(/usr/local//bin)" with the following error: CC tests/attr.o tests/attr.c: In function ‘test__attr’: tests/attr.c:168:50: error: expected ‘)’ before ‘;’ token snprintf(path_perf, PATH_MAX, "%s/perf", BINDIR); ^ tests/attr.c:176:1: error: expected ‘;’ before ‘}’ token } ^ tests/attr.c:176:1: error: control reaches end of non-void function [-Werror=return-type] } ^ cc1: all warnings being treated as errors This patch works around the problem by "cleaning" the bindir string using make's abspath function. Signed-off-by: Pawel Moll Acked-by: Jiri Olsa Cc: Adrian Hunter Cc: Namhyung Kim Cc: Peter Zijlstra Link: http://lkml.kernel.org/r/1438092613-21014-1-git-send-email-pawel.moll@arm.com Signed-off-by: Arnaldo Carvalho de Melo

perf stat: Fix transaction lenght metrics

2015-07-28T15:05:04Z

The transaction length metrics in perf stat -T broke recently. It would not match the metric correctly and always print K/sec. This was caused by a incorrect update of the cycles_in_tx statistics. Update the correct variable. Also the check for zero division was reversed, which resulted in K/sec being printed for no transactions. Fix this also up. Signed-off-by: Andi Kleen Acked-by: Jiri Olsa Link: http://lkml.kernel.org/r/1438039491-22091-1-git-send-email-andi@firstfloor.org Signed-off-by: Arnaldo Carvalho de Melo

perf tools: Really allow to specify custom CC, AR or LD

2015-07-15T14:57:28Z

Commit 5ef7bbb09f7b ("perf tools: Allow to specify custom linker command") was meant to enable usage non $(CROSS_COMPILE)ld linker during perf building. But implementation didn't take into account the fact that LD is a pre-defined variable in GNU Make. I.e. it is always defined. Which means there's no point to check "LD ?= ..." because it will never succeed. And so LD will be either that explicitly passed to make like this: ------->8------- make LD=path_to_my_ld ... ------->8------- or default value, which is host's "ld". Latter leads to failure of cross-linkage because instead of cross linker "$(CROSS_COMPILE)ld" host's "ld" is used. Fortunately there's a way to do correct substitution of $(CROSS_COMPILE)ld with user defined LD on command-line. As a reference was used implementation in "tools/lib/traceevent/Makefile". Build tested for x86_64 and ARC. Thanks Jiri for this hint. Signed-off-by: Alexey Brodkin Fixes: 5ef7bbb09f7b ("perf tools: Allow to specify custom linker command") Cc: Aaro Koskinen Cc: Jiri Olsa Cc: Paul Mackerras Cc: Peter Zijlstra Cc: Vineet Gupta Cc: Vineet Gupta Cc: linux-arch@vger.kernel.org Link: http://lkml.kernel.org/r/1436864720-26316-1-git-send-email-abrodkin@synopsys.com Signed-off-by: Arnaldo Carvalho de Melo

perf auxtrace: Fix misplaced check for HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT

2015-07-15T14:57:28Z

Move the checking for HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT for AUX area mmaps until after checking if such mmaps are used anyway. Reported-by: Alexey Brodkin Signed-off-by: Adrian Hunter Tested-by: Alexey Brodkin Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Peter Zijlstra Cc: Stephane Eranian Cc: Vineet Gupta Cc: linux-arch@vger.kernel.org Link: http://lkml.kernel.org/r/55A5023C.7020907@intel.com Signed-off-by: Arnaldo Carvalho de Melo

perf hists browser: Take the --comm, --dsos, etc filters into account

2015-07-13T19:06:09Z

At some point: commit 2c86c7ca7606 Author: Namhyung Kim Date: Mon Mar 17 18:18:54 2014 -0300 perf report: Merge al->filtered with hist_entry->filtered We stopped dropping samples for things filtered via the --comms, --dsos, --symbols, etc, i.e. things marked as filtered in the symbol resolution routines (thread__find_addr_map(), perf_event__preprocess_sample(), etc). But then, in: commit 268397cb2a47 Author: Namhyung Kim Date: Tue Apr 22 14:49:31 2014 +0900 perf top/tui: Update nr_entries properly after a filter is applied We don't take into account entries that were filtered in perf_event__preprocess_sample() and friends, which leads to inconsistency in the browser seek routines, that expects the number of hist_entry->filtered entries to match what it thinks is the number of unfiltered, browsable entries. So, for instance, when we do: perf top --symbols ___non_existent_symbol___ the hist_browser__nr_entries() routine thinks there are no filters in place, uses the hists->nr_entries but all entries are filtered, leading to a segfault. Tested with: perf top --symbols malloc,free --percentage=relative Freezing, by pressing 'f', at any time and doing the math on the percentages ends up with 100%, ditto for: perf top --dsos libpthread-2.20.so,libxul.so --percentage=relative Both were segfaulting, all fixed now. More work needed to do away with checking if filters are in place, we should just use the nr_non_filtered_samples counter, no need to conditionally use it or hists.nr_filter, as what the browser does is just show unfiltered stuff. An audit of how it is being accounted is needed, this is the minimal fix. Reported-by: Michael Petlan Fixes: 268397cb2a47 ("perf top/tui: Update nr_entries properly after a filter is applied") Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-6w01d5q97qk0d64kuojme5in@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo

perf symbols: Store if there is a filter in place

2015-07-13T11:21:57Z

When setting yup the symbols library we setup several filter lists, for dsos, comms, symbols, etc, and there is code that, if there are filters, do certain operations, like recalculate the number of non filtered histogram entries in the top/report TUI. But they were considering just the "Zoom" filters, when they need to take into account as well the above mentioned filters (perf top --comms, --dsos, etc). So store in symbol_conf.has_filter true if any of those filters is in place. Cc: Adrian Hunter Cc: Borislav Petkov Cc: David Ahern Cc: Frederic Weisbecker Cc: Jiri Olsa Cc: Namhyung Kim Cc: Stephane Eranian Link: http://lkml.kernel.org/n/tip-f5edfmhq69vfvs1kmikq1wep@git.kernel.org Signed-off-by: Arnaldo Carvalho de Melo