- 14 Nov, 2016 2 commits
-
-
Jiri Olsa authored
Adding support to detect jvmti support. It is not plugged into the FEATURE_TESTS machinery, because it's quite rare and will be used separately from perf via feature_check call. Signed-off-by:
Jiri Olsa <jolsa@kernel.org> Tested-by:
Stephane Eranian <eranian@google.com> Cc: Andi Kleen <andi@firstfloor.org> Cc: David Ahern <dsahern@gmail.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Cc: William Cohen <wcohen@redhat.com> Link: http://lkml.kernel.org/r/1478093749-5602-3-git-send-email-jolsa@kernel.orgSigned-off-by:
Arnaldo Carvalho de Melo <acme@redhat.com>
-
Jiri Olsa authored
Adding support to remove options from final CFLAGS for both object file and build target. It's now possible to remove CFLAGS options like: CFLAGS_REMOVE_krava.o += -Wstrict-prototypes Committer notes: This comes from the kernel's kbuild infrastructure, the subset that is supported in tools/ is being documented at tools/build/Documentation/Build.txt. Signed-off-by:
-
- 11 Nov, 2016 1 commit
-
-
Arnaldo Carvalho de Melo authored
Since the unprivileged sched switch event was added in perf, PT doesn't need need perf_event_paranoid=-1 anymore for per cpu decoding. Add a note stating that that is only needed for kernels < 4.2. Reported-by:
Andi Kleen <ak@linux.intel.com> Report-Link: http://lkml.kernel.org/r/http://lkml.kernel.org/n/tip-x2ybghpqxxn3zu0m8o7qi42r@git.kernel.orgAcked-by:
Adrian Hunter <adrian.hunter@intel.com> Fixes: 45ac1403 ("perf: Add PERF_RECORD_SWITCH to indicate context switches") Link: http://lkml.kernel.org/n/tip-x2ybghpqxxn3zu0m8o7qi42r@git.kernel.orgSigned-off-by:
-
- 08 Nov, 2016 1 commit
-
-
Rabin Vincent authored
Since 841e3558 ("perf callchain: Recording 'dwarf' callchains do not need DWARF unwinding support"), --call-graph dwarf is allowed in 'perf record' even without unwind support. A couple of other places don't reflect this yet though: the help text should list dwarf as a valid record mode and the dump_size config should be respected too. Signed-off-by:
Rabin Vincent <rabinv@axis.com> Cc: He Kuang <hekuang@huawei.com> Fixes: 841e3558 ("perf callchain: Recording 'dwarf' callchains do not need DWARF unwinding support") Link: http://lkml.kernel.org/r/1470837148-7642-1-git-send-email-rabin.vincent@axis.comSigned-off-by:
-
- 28 Oct, 2016 9 commits
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-20161028' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/core perf/core improvements and fixes from Arnaldo Carvalho de Melo: New features: - Support matching by topic in 'perf list' (Andi Kleen) User visible: - Apply cpu color only when there was activity in 'perf sched map' (Namhyung Kim) - Always show the task's COMM in 'perf sched map -v' (Namhyung Kim) - Fix hierarchy column counts in the perf hist browser (top, report), avoiding showing nothing after pressing the RIGHT key a number of times (Namhyung Kim) Infrastructure: - Support cascading options in libsubcmd and use it to share common options in 'perf sched' subcommands (Namhyung Kim) - Avoid worker cacheline bouncing in 'perf bench futex' (Davidlohr Bueso) - Sanitize numeric parameters in 'perf bench futex' (Davidlohr Bueso) - Update copies of kernel files (Arnaldo Carvalho de Melo) - Fix scripting (perl, python) setup to avoid leaks (Arnaldo Carvalho de Melo) - Add missing object file to the python binding linkage list (Arnaldo Carvalho de Melo) Signed-off-by:
Ingo Molnar <mingo@kernel.org>
-
Arnaldo Carvalho de Melo authored
In ac12f676 ("perf tools: Implement branch_type event parameter") we started using the parse_branch_str() function from one of the files used in the python binding, which caused this entry in 'perf test' to fail: # perf test -v python 16: Try 'import perf' in python, checking link problems : --- start --- test child forked, pid 16667 Traceback (most recent call last): File "<stdin>", line 1, in <module> ImportError: /tmp/build/perf/python/perf.so: undefined symbol: parse_branch_str test child finished with -1 ---- end ---- Try 'import perf' in python, checking link problems: FAILED! # I must've commited some mistake when running 'perf test' to send the pull request for the perf-core-for-mingo-20161024 tag, to have let this regression to pass, sigh. Just add tools/perf/util/parse-branch-options.c and switch from using ui__warning(), that is not available in the python binding, use pr_warning() instead, which is good enough for this case. Now: # perf test python 16: Try 'import perf' in python, checking link problems : Ok # Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Cc: Andi Kleen <ak@linux.intel.com> Fixes: ac12f676 ("perf tools: Implement branch_type event parameter") Link: http://lkml.kernel.org/n/tip-9kn1ct1cx9ppwqlmzl6z0xhs@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Removing one more set of die() calls. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-6pyil685m5i2tugg56gcy0tg@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Both register_perl_scripting() and register_python_scripting() allocate this variable, fix it by checking if it already was. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Frederic Weisbecker <fweisbec@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Tom Zanussi <tzanussi@gmail.com> Cc: Wang Nan <wangnan0@huawei.com> Fixes: 7e4b21b8 ("perf/scripts: Add Python scripting engine") Signed-off-by:
-
Arnaldo Carvalho de Melo authored
Introduced in commit f9afc619 ("x86: Wire up protection keys system calls") This will make 'perf trace' aware of them on x86_64. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Dave Hansen <dave.hansen@linux.intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-s1ta2ttv2xacecqogmd3a9p1@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
To get the defines introduced in the commit e8c24d3a ("x86/pkeys: Allocation/free syscalls") Silencing this perf build warning: Warning: tools/include/uapi/asm-generic/mman-common.h differs from kernel Need to change 'perf trace' to beautify those syscalls, as soon as booting with a kernel with it. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-yev9rexu02cl7cjeozzmrl9t@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Ignore export.h and EXPORT_SYMBOL in: 784d5699 ("x86: move exports to actual definitions") We're not dragging this stuff, not useful in tools/ This silences the following warnings while building perf: Warning: tools/arch/x86/lib/memcpy_64.S differs from kernel Warning: tools/arch/x86/lib/memset_64.S differs from kernel Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-h9vw3pe0fq79zmyqsfr0s0mo@git.kernel.orgSigned-off-by:
-
Andi Kleen authored
Add support in perf list topic to only show events belonging to a specific vendor events topic. For example the following works now: % perf list frontend List of pre-defined events (to be used in -e): stalled-cycles-frontend OR idle-cycles-frontend [Hardware event] stalled-cycles-frontend OR cpu/stalled-cycles-frontend/ [Kernel PMU event] frontend: dsb2mite_switches.count [Decode Stream Buffer (DSB)-to-MITE switches] dsb2mite_switches.penalty_cycles [Decode Stream Buffer (DSB)-to-MITE switch true penalty cycles] dsb_fill.exceed_dsb_lines [Cycles when Decode Stream Buffer (DSB) fill encounter more than 3 Decode Stream Buffer (DSB) lines] icache.hit [Number of Instruction Cache, Streaming Buffer and Victim Cache Reads. both cacheable and noncacheable, including UC fetches] ... Signed-off-by: -
Namhyung Kim authored
Joonwoo reported that there's a mismatch between timestamps in script and sched commands. This was because of difference in printing the timestamp. Factor out the code and share it so that they can be in sync. Also I found that sched map has similar problem, fix it too. Committer notes: Fixed the max_lat_at bug introduced by Namhyung's original patch, as pointed out by Joonwoo, and made it a function following the scnprintf() model, i.e. returning the number of bytes formatted, and receiving as the first parameter the object from where the data to the formatting is obtained, renaming it from: char *timestamp_in_usec(char *bf, size_t size, u64 timestamp) to int timestamp__scnprintf_usec(u64 timestamp, char *bf, size_t size) Reported-by:
Joonwoo Park <joonwoop@codeaurora.org> Signed-off-by:
Namhyung Kim <namhyung@kernel.org> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Peter Zijlstra <a.p.zijlstra@chello.nl> Link: http://lkml.kernel.org/r/20161024020246.14928-3-namhyung@kernel.orgSigned-off-by:
-
- 25 Oct, 2016 7 commits
-
-
Namhyung Kim authored
I'd like to see the name of tasks with perf sched map, but it only shows name of new tasks and then use short names after all. This is not good for long running tasks since it's hard for users to track the short names. This patch makes it show the names (except the idle task) when -v option is used. Probably we may make it as default behavior. Signed-off-by:
-
Namhyung Kim authored
Applying cpu color always doesn't help readability IMHO. Instead it might be better to applying the color when there's an activity on those CPUs. Signed-off-by:
-
Namhyung Kim authored
The -i and -v options can be used in subcommands so enable cascading the sched_options. This fixes the following inconvenience in 'perf sched': $ perf sched -i perf.data.sched map ... (it works well) ... $ perf sched map -i perf.data.sched Error: unknown switch `i' Usage: perf sched map [<options>] --color-cpus <cpus> highlight given CPUs in map --color-pids <pids> highlight given pids in map --compact map output in compact mode --cpus <cpus> display given CPUs in map With this patch, the second command line works with the perf.data.sched data file. Signed-off-by: -
Namhyung Kim authored
Sometimes subcommand have common options and it can only handled in the upper level command unless it duplicates the options. This patch adds a parent field and fallback to the parent if the given argument was not found in the current options. Signed-off-by:
-
Namhyung Kim authored
The perf report/top on TUI supports horizontal scrolling using LEFT and RIGHT keys. But it calculate the number of columns incorrectly when hierarchy mode is enabled so that keep pressing RIGHT key can make the output disappeared. In the hierarchy mode, all sort keys are collapsed into a single column, so it needs to be applied when calculating column numbers. Reported-and-Tested-by:
Markus Trippelsdorf <markus@trippelsdorf.de> Signed-off-by:
-
Davidlohr Bueso authored
This gets rid of oddities such as: perf bench futex hash -t -4 perf: calloc: Cannot allocate memory Runtime (and many more) are equally busted, i.e. run for bogus amounts of time. Just use the abs, instead of, for example errorring out. Committer note: After the patch: $ perf bench futex hash -t -4 # Running 'futex/hash' benchmark: Run summary [PID 10178]: 4 threads, each operating on 1024 [private] futexes for 10 secs. [thread 0] futexes: 0x34f9fa0 ... 0x34faf9c [ 4702208 ops/sec ] [thread 1] futexes: 0x34fb140 ... 0x34fc13c [ 4707020 ops/sec ] [thread 2] futexes: 0x34fc2e0 ... 0x34fd2dc [ 4711526 ops/sec ] [thread 3] futexes: 0x34fd480 ... 0x34fe47c [ 4709683 ops/sec ] Averaged 4707609 operations/sec (+- 0.04%), total secs = 10 $ Signed-off-by:
Davidlohr Bueso <dbueso@suse.de> Tested-by:
-
Davidlohr Bueso authored
Sebastian noted that overhead for worker thread ops (throughput) accounting was producing 'perf' to appear in the profiles, consuming a non-trivial (i.e. 13%) amount of CPU. This is due to cacheline bouncing due to the increment of w->ops. We can easily fix this by just working on a local copy and updating the actual worker once done running, and ready to show the program summary. There is no danger of the worker being concurrent, so we can trust that no stale value is being seen by another thread. This also gets rid of the unnecessary cache alignment hack; its not worth it. Reported-by:
Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by:
-
- 24 Oct, 2016 20 commits
-
-
Ingo Molnar authored
Merge tag 'perf-core-for-mingo-20161024' 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: New features: - Dynamicly change verbosity level by pressing 'V' in the 'perf top/report' hists TUI browser (Alexis Berlemont) - Implement 'perf trace --delay' in the same fashion as in 'perf record --delay', to skip sampling workload initialization events (Alexis Berlemont) - Make vendor named events case insensitive in 'perf list', i.e. 'perf list LONGEST_LAT' works just the same as 'perf list longest_lat' (Andi Kleen) - Show instruction bytes and lenght in 'perf script' for Intel PT and BTS (Andi Kleen, Adrian Hunter) E.g: % perf record -e intel_pt// foo % perf script --itrace=i0ns -F ip,insn,insnlen ffffffff8101232f ilen: 5 insn: 0f 1f 44 00 00 ffffffff81012334 ilen: 1 insn: 5b ffffffff81012335 ilen: 1 insn: 5d ffffffff81012336 ilen: 1 insn: c3 ffffffff810123e3 ilen: 1 insn: 5b ffffffff810123e4 ilen: 2 insn: 41 5c ffffffff810123e6 ilen: 1 insn: 5d ffffffff810123e7 ilen: 1 insn: c3 ffffffff810124a6 ilen: 2 insn: 31 c0 ffffffff810124a8 ilen: 9 insn: 41 83 bc 24 a8 01 00 00 01 ffffffff810124b1 ilen: 2 insn: 75 87 - Allow enabling the perf_event_attr.branch_type attribute member: (Andi Kleen) perf record -e sched:sched_switch,cpu/cpu-cycles,branch_type=any/ ... - Add unwinding support for jitdump (Stefano Sanfilippo) Fixes: - Use raw_syscall:sys_enter timestamp in 'perf trace' (Arnaldo Carvalho de Melo) Infrastructure: - Allow jitdump to be built without libdwarf (Maciej Debski) - Sync x86's syscall table tools/ copy (Arnaldo Carvalho de Melo) - Fixes to avoid calling die() in library fuctions already propagating other errors (Arnaldo Carvalho de Melo) - Improvements to allow libtraceevent to be properly installed in distro packages (Jiri Olsa) - Removing coresight miscellaneous debug output (Mathieu Poirier) - Cache align the 'perf bench futex' worker struct (Sebastian Andrzej Siewior) Documentation: - Minor improvements on the documentation of event parameters (Andi Kleen) - Add jitdump format specification document (Stephane Eranian) Spelling fixes: - Fix typo "No enough" to "Not enough" (Alexander Alemayhu) Signed-off-by:
-
Mathieu Poirier authored
Printing the full path of the selected link is obviously not needed, hence removing. Signed-off-by:
Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: linux-arm-kernel@lists.infradead.org Link: http://lkml.kernel.org/r/1476913323-6836-1-git-send-email-mathieu.poirier@linaro.orgSigned-off-by:
-
Andi Kleen authored
Make the 'perf list' glob matching for vendor events case insensitive. This allows to use the upper case vendor events with perf list too. Now the following works: % perf list LONGEST_LAT ... cache: longest_lat_cache.miss [Core-originated cacheable demand requests missed LLC] longest_lat_cache.reference [Core-originated cacheable demand requests that refer to LLC] Signed-off-by: -
Arnaldo Carvalho de Melo authored
Instead of the one when another syscall takes place while another is being processed (in another CPU, but we show it serialized, so need to "interrupt" the other), and also when finally showing the sys_enter + sys_exit + duration, where we were showing the sample->time for the sys_exit, duh. Before: # perf trace sleep 1 <SNIP> 0.373 ( 0.001 ms): close(fd: 3 ) = 0 1000.626 (1000.211 ms): nanosleep(rqtp: 0x7ffd6ddddfb0) = 0 1000.653 ( 0.003 ms): close(fd: 1 ) = 0 1000.657 ( 0.002 ms): close(fd: 2 ) = 0 1000.667 ( 0.000 ms): exit_group( ) # After: # perf trace sleep 1 <SNIP> 0.336 ( 0.001 ms): close(fd: 3 ) = 0 0.373 (1000.086 ms): nanosleep(rqtp: 0x7ffe303e9550) = 0 1000.481 ( 0.002 ms): close(fd: 1 ) = 0 1000.485 ( 0.001 ms): close(fd: 2 ) = 0 1000.494 ( 0.000 ms): exit_group( ) [root@jouet linux]# Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-ecbzgmu2ni6glc6zkw8p1zmx@git.kernel.org Fixes: 752fde44 ("perf trace: Support interrupted syscalls") Signed-off-by: -
Arnaldo Carvalho de Melo authored
Not used at all, we need just the entry_time to calculate the syscall duration. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-js6r09zdwlzecvaei7t4l3vd@git.kernel.orgSigned-off-by:
-
Sebastian Andrzej Siewior authored
It popped up in perf testing that the worker consumes some amount of CPU. It boils down to the increment of `ops` which causes cache line bouncing between the individual threads. This patch aligns the struct by 256 bytes to ensure that not a cache line is shared among CPUs. 128 byte is the x86 worst case and grep says that L1_CACHE_SHIFT is set to 8 on s390. Signed-off-by:
-
Arnaldo Carvalho de Melo authored
We already have handling for errors when processing PERF_RECORD_ events, so instead of calling die() when not being able to alloc, propagate the error, so that the normal UI exit sequence can take place, the user be warned and possibly the terminal be properly reset to a sane mode. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Brice Goglin <Brice.Goglin@inria.fr> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-r90je3c009a125dvs3525yge@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
It already returns whatever strbuf_(grow|addch)() returns in case of failure, so just return -ENOSPC in the only case where it was die()ing. When it returns, its only caller will call die() anyway, so no need to be so eager, die later. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-as05b7mbogprlwi8iarwns8e@git.kernel.orgSigned-off-by:
-
Arnaldo Carvalho de Melo authored
Instead of having all tests perform alloc/free, do it in the code that calls the do_cycles() and do_gettimeofday() functions. Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: David Ahern <dsahern@gmail.com> Cc: Hitoshi Mitake <mitake@dcl.info.waseda.ac.jp> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/n/tip-lywj4mbdb1m9x1z9asivwuuy@git.kernel.orgSigned-off-by:
-
Alexis Berlemont authored
In the perf wiki todo-list[1], there is an entry regarding initial-delay and 'perf trace'; the following small patch tries to fulfill this point. It has been generated against the branch tip/perf/core. It has only been implemented in the "trace__run" case. Ex.: $ sudo strace -- ./perf trace --delay 5 sleep 1 2>&1 ... fcntl(7, F_SETFL, O_RDONLY|O_NONBLOCK) = 0 ioctl(7, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0 ioctl(11, PERF_EVENT_IOC_SET_OUTPUT, 0x7) = 0 fcntl(11, F_SETFL, O_RDONLY|O_NONBLOCK) = 0 ioctl(11, PERF_EVENT_IOC_ID, 0x7ffc8fd35718) = 0 write(6, "\0", 1) = 1 close(6) = 0 nanosleep({0, 5000000}, NULL) = 0 # DELAY OF 5 MS BEFORE ENABLING THE EVENTS ioctl(3, PERF_EVENT_IOC_ENABLE, 0) = 0 ioctl(4, PERF_EVENT_IOC_ENABLE, 0) = 0 ioctl(5, PERF_EVENT_IOC_ENABLE, 0) = 0 ioctl(7, PERF_EVENT_IOC_ENABLE, 0) = 0 ... [1]: https://perf.wiki.kernel.org/index.php/TodoSigned-off-by:Alexis Berlemont <alexis.berlemont@gmail.com> Suggested-and-Tested-by:
-
Alexis Berlemont authored
Here is a small patch which tries to fulfill a point in the perf todo list: * Make pressing 'V' multiple times to go on cycling thru various verbosity levels in 'perf top', so that info that is present in 'perf top -v' can be obtained without having to restart the tool (acme). After a small grep in the code, the max verbosity level seems 3; so, we cycle at 4; I did not dare define a MAX_VERBOSE_LEVEL constant. Signed-off-by:
-
Alexander Alemayhu authored
The latter version occurs much more when running git grep. Signed-off-by:
Alexander Alemayhu <alexander@alemayhu.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Wang Nan <wangnan0@huawei.com> Link: http://lkml.kernel.org/r/20161013161811.4939-1-alexander@alemayhu.comSigned-off-by:
-
Andi Kleen authored
With uncore event aliases which are duplicated over multiple PMUs the "Using CPUID" message with -v could be printed many times. Only print it once. Signed-off-by:
-
Stephane Eranian authored
This patch adds a formal specification of the jitdump format. The goal is to help jit runtime developers implement the jitdump support without having to read the jvmti code. Signed-off-by:
-
Stefano Sanfilippo authored
Check the version number when opening a jitdump file. Accept older versions, but not newer ones. Signed-off-by:
Stefano Sanfilippo <ssanfilippo@chromium.org> Signed-off-by:
Ross McIlroy <rmcilroy@chromium.org> Reviewed-by:
-
Stefano Sanfilippo authored
When the jit_buf_desc contains unwinding information, it is emitted as eh_frame unwinding sections in the DSOs generated by perf inject. The unwinding information is required to unwind of JITed code which do not maintain the frame pointer register during function calls. It can be emitted by V8 / Chromium when the --perf_prof_unwinding_info is passed to V8. The eh_frame and eh_frame_hdr sections are emitted immediately after the .text. The .eh_frame is aligned at a 8-byte boundary, and .eh_frame_hdr at a 4-byte one. Since size of the .eh_frame is required to be a multiple of the word size, which means there will never be additional padding between it and the .eh_frame_hdr on machines where the word size is 4 or 8 bytes. However, additional padding might be inserted between .text and .eh_frame to reach the correct alignment, which will always be 8 bytes, also on 32bit machines. The reasoning behind this choice is that 4 extra bytes of padding worst case are not a large cost for the advantage of removing word-size dependent offset calculations when emitting the jitdump. Signed-off-by:
-
Stefano Sanfilippo authored
This record is intended to provide unwinding information in the eh_frame format. This is required to unwind JITed code which does not maintain the frame pointer register during function calls. The eh_frame unwinding information can be emitted by V8 / Chromium when the --perf_prof_unwinding_info is passed. A record of type jr_code_unwinding_info comes before the jr_code_load it referred to and contains both the .eh_frame and .eh_frame_hdr. The fields in the header have the following meaning: * unwinding_size: size of the eh_frame and eh_frame_hdr, necessary for distinguishing the content from the padding. * eh_frame_hdr_size: as the name says. * mapped_size: size of the payload that was in memory at runtime. typically unwinding_size if the .eh_frame_hdr and .eh_frame were mapped, or 0 if they weren't. It should always be the former case, since the .eh_frame is guaranteed to be mapped in memory. However, certain JITs might want to inject an .eh_frame_hdr with an empty LUT to trigger fp-based unwinding fallback in libunwind. The only part of the .eh_frame_hdr that libunwind reads from remote memory is the LUT, and since there is none, mapping the unwinding info in memory is not necessary, and 0 in this field signifies that it wasn't. This practical hack allows to save bytes in code memory for those JIT compilers that might or might not maintain a valid frame pointer. The payload that follows is assumed to contain first the .eh_frame and then the .eh_header_hdr, with no padding between the two. Signed-off-by: -
Stefano Sanfilippo authored
When calculating .eh_frame_hdr base and LUT offsets do not always assume that pgoff is zero. The assumption is false for DSOs built from the jitdump by perf inject, because the ELF header did not exist in memory at sampling time. Signed-off-by:
-
Stefano Sanfilippo authored
The behavior before this commit was to skip the remaining portion of the jitdump in case an unknown record was found, including those records that perf could handle. With this change, parsing a record with an unknown id will cause a warning to be emitted, the record will be skipped and parsing will resume from the next (valid) one. The patch aims at making perf more future proof, by extracting as much information as possible from jitdumps. Signed-off-by:
-
Stephane Eranian authored
This patch removes all the string padding generated in the jitdump file. They are not necessary and were adding unnecessary complexity. Modern processors can handle unaligned accesses quite well. The perf.data/ jitdump file are always post-processed, no need to add extra complexity for no real gain. Signed-off-by:
-
