summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAgeFilesLines
* Merge tag 'trace-v5.12' of ↵Linus Torvalds2021-02-2240-628/+3083
|\ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace Pull tracing updates from Steven Rostedt: - Update to the way irqs and preemption is tracked via the trace event PC field - Fix handling of unregistering event failing due to allocate memory. This is only triggered by failure injection, as it is pretty much guaranteed to have less than a page allocation succeed. - Do not show the useless "filter" or "enable" files for the "ftrace" trace system, as they have no effect on doing anything. - Add a warning if kprobes are registered more than once. - Synthetic events now have their fields parsed by semicolons. Old formats without semicolons will still work, but new features will require them. - New option to allow trace events to show %p without hashing in trace file. The trace file can only be read by root, and reading the raw event buffer did not have any pointers hashed, so this does not expose anything new. - New directory in tools called tools/tracing, where a new tool that reads sequential latency reports from the ftrace latency tracers. - Other minor fixes and cleanups. * tag 'trace-v5.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (33 commits) kprobes: Fix to delay the kprobes jump optimization tracing/tools: Add the latency-collector to tools directory tracing: Make hash-ptr option default tracing: Add ptr-hash option to show the hashed pointer value tracing: Update the stage 3 of trace event macro comment tracing: Show real address for trace event arguments selftests/ftrace: Add '!event' synthetic event syntax check selftests/ftrace: Update synthetic event syntax errors tracing: Add a backward-compatibility check for synthetic event creation tracing: Update synth command errors tracing: Rework synthetic event command parsing tracing/dynevent: Delegate parsing to create function kprobes: Warn if the kprobe is reregistered ftrace: Remove unused ftrace_force_update() tracepoints: Code clean up tracepoints: Do not punish non static call users tracepoints: Remove unnecessary "data_args" macro parameter tracing: Do not create "enable" or "filter" files for ftrace event subsystem kernel: trace: preemptirq_delay_test: add cpu affinity tracepoint: Do not fail unregistering a probe due to memory failure ...
| * kprobes: Fix to delay the kprobes jump optimizationMasami Hiramatsu2021-02-191-10/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Commit 36dadef23fcc ("kprobes: Init kprobes in early_initcall") moved the kprobe setup in early_initcall(), which includes kprobe jump optimization. The kprobes jump optimizer involves synchronize_rcu_tasks() which depends on the ksoftirqd and rcu_spawn_tasks_*(). However, since those are setup in core_initcall(), kprobes jump optimizer can not run at the early_initcall(). To avoid this issue, make the kprobe optimization disabled in the early_initcall() and enables it in subsys_initcall(). Note that non-optimized kprobes is still available after early_initcall(). Only jump optimization is delayed. Link: https://lkml.kernel.org/r/161365856280.719838.12423085451287256713.stgit@devnote2 Fixes: 36dadef23fcc ("kprobes: Init kprobes in early_initcall") Cc: Ingo Molnar <mingo@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: RCU <rcu@vger.kernel.org> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Andrew Morton <akpm@linux-foundation.org> Cc: Daniel Axtens <dja@axtens.net> Cc: Frederic Weisbecker <frederic@kernel.org> Cc: Neeraj Upadhyay <neeraju@codeaurora.org> Cc: Joel Fernandes <joel@joelfernandes.org> Cc: Michal Hocko <mhocko@suse.com> Cc: "Theodore Y . Ts'o" <tytso@mit.edu> Cc: Oleksiy Avramchenko <oleksiy.avramchenko@sonymobile.com> Cc: stable@vger.kernel.org Reported-by: Paul E. McKenney <paulmck@kernel.org> Reported-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Reported-by: Uladzislau Rezki <urezki@gmail.com> Acked-by: Paul E. McKenney <paulmck@kernel.org> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing/tools: Add the latency-collector to tools directoryViktor Rosendahl2021-02-125-6/+2161
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This is a tool that is intended to work around the fact that the preemptoff, irqsoff, and preemptirqsoff tracers only work in overwrite mode. The idea is to act randomly in such a way that we do not systematically lose any latencies, so that if enough testing is done, all latencies will be captured. If the same burst of latencies is repeated, then sooner or later we will have captured all the latencies. It also works with the wakeup_dl, wakeup_rt, and wakeup tracers. However, in that case it is probably not useful to use the random sleep functionality. The reason why it may be desirable to catch all latencies with a long test campaign is that for some organizations, it's necessary to test the kernel in the field and not practical for developers to work iteratively with field testers. Because of cost and project schedules it is not possible to start a new test campaign every time a latency problem has been fixed. It uses inotify to detect changes to /sys/kernel/tracing/trace. When a latency is detected, it will either sleep or print immediately, depending on a function that act as an unfair coin toss. If immediate print is chosen, it means that we open /sys/kernel/tracing/trace and thereby cause a blackout period that will hide any subsequent latencies. If sleep is chosen, it means that we wait before opening /sys/kernel/tracing/trace, by default for 1000 ms, to see if there is another latency during this period. If there is, then we will lose the previous latency. The coin will be tossed again with a different probability, and we will either print the new latency, or possibly a subsequent one. The probability for the unfair coin toss is chosen so that there is equal probability to obtain any of the latencies in a burst. However, this assumes that we make an assumption of how many latencies there can be. By default the program assumes that there are no more than 2 latencies in a burst, the probability of immediate printout will be: 1/2 and 1 Thus, the probability of getting each of the two latencies will be 1/2. If we ever find that there is more than one latency in a series, meaning that we reach the probability of 1, then the table will be expanded to: 1/3, 1/2, and 1 Thus, we assume that there are no more than three latencies and each with a probability of 1/3 of being captured. If the probability of 1 is reached in the new table, that is we see more than two closely occurring latencies, then the table will again be extended, and so on. On my systems, it seems like this scheme works fairly well, as long as the latencies we trace are long enough, 300 us seems to be enough. This userspace program receive the inotify event at the end of a latency, and it has time until the end of the next latency to react, that is to open /sys/kernel/tracing/trace. Thus, if we trace latencies that are >300 us, then we have at least 300 us to react. The minimum latency will of course not be 300 us on all systems, it will depend on the hardware, kernel version, workload and configuration. Example usage: In one shell, give the following command: sudo latency-collector -rvv -t preemptirqsoff -s 2000 -a 3 This will trace latencies > 2000us with the preemptirqsoff tracer, using random sleep with maximum verbosity, with a probability table initialized to a size of 3. In another shell, generate a few bursts of latencies: root@host:~# modprobe preemptirq_delay_test delay=3000 test_mode=alternate burst_size=3 root@host:~# echo 1 > /sys/kernel/preemptirq_delay_test/trigger root@host:~# echo 1 > /sys/kernel/preemptirq_delay_test/trigger root@host:~# echo 1 > /sys/kernel/preemptirq_delay_test/trigger root@host:~# echo 1 > /sys/kernel/preemptirq_delay_test/trigger If all goes well, you should be getting stack traces that shows all the different latencies, i.e. you should see all the three functions preemptirqtest_0, preemptirqtest_1, preemptirqtest_2 in the stack traces. Link: https://lkml.kernel.org/r/20210212134421.172750-2-Viktor.Rosendahl@bmw.de Signed-off-by: Viktor Rosendahl <Viktor.Rosendahl@bmw.de> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Make hash-ptr option defaultSteven Rostedt (VMware)2021-02-121-1/+2
| | | | | | | | | | | | | | | | | | Since the original behavior of the trace events is to hash the %p pointers, make that the default, and have developers have to enable the option in order to have them unhashed. Cc: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Add ptr-hash option to show the hashed pointer valueMasami Hiramatsu2021-02-113-0/+10
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add tracefs/options/hash-ptr option to show hashed pointer value by %p in event printk format string. For the security reason, normal printk will show the hashed pointer value (encrypted by random number) with %p to printk buffer to hide the real address. But the tracefs/trace always shows real address for debug. To bridge those outputs, add an option to switch the output format. Ftrace users can use it to find the hashed value corresponding to the real address in trace log. Link: https://lkml.kernel.org/r/160277372504.29307.14909828808982012211.stgit@devnote2 Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Update the stage 3 of trace event macro commentMasami Hiramatsu2021-02-111-9/+20
| | | | | | | | | | | | | | | | | | | | | | Update the comment of the 3rd stage of trace event macro expansion code. Now there are 2 macros makes different trace_raw_output_<call>() functions. Link: https://lkml.kernel.org/r/160277371605.29307.8586817119278606720.stgit@devnote2 Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Show real address for trace event argumentsMasami Hiramatsu2021-02-115-3/+88
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | To help debugging kernel, show real address for trace event arguments in tracefs/trace{,pipe} instead of hashed pointer value. Since ftrace human-readable format uses vsprintf(), all %p are translated to hash values instead of pointer address. However, when debugging the kernel, raw address value gives a hint when comparing with the memory mapping in the kernel. (Those are sometimes used with crash log, which is not hashed too) So converting %p with %px when calling trace_seq_printf(). Moreover, this is not improving the security because the tracefs can be used only by root user and the raw address values are readable from tracefs/percpu/cpu*/trace_pipe_raw file. Link: https://lkml.kernel.org/r/160277370703.29307.5134475491761971203.stgit@devnote2 Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * selftests/ftrace: Add '!event' synthetic event syntax checkTom Zanussi2021-02-111-0/+4
| | | | | | | | | | | | | | | | | | | | Add a check confirming that '!event' alone will remove a synthetic event. Link: https://lkml.kernel.org/r/1dff3f03d18542cece08c10d6323d8a8dba11e42.1612208610.git.zanussi@kernel.org Signed-off-by: Tom Zanussi <zanussi@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * selftests/ftrace: Update synthetic event syntax errorsTom Zanussi2021-02-111-8/+27
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Some of the synthetic event errors and positions have changed in the code - update those and add several more tests. Also add a runtime check to ensure that the kernel supports dynamic strings in synthetic events, which these tests require. Link: https://lkml.kernel.org/r/51402656433455baead34f068c6e9466b64df9c0.1612208610.git.zanussi@kernel.org Fixes: 81ff92a93d95 (selftests/ftrace: Add test case for synthetic event syntax errors) Reported-by: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Tom Zanussi <zanussi@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Add a backward-compatibility check for synthetic event creationTom Zanussi2021-02-091-19/+74
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The synthetic event parsing rework now requires semicolons between synthetic event fields. That requirement breaks existing users who might already have used the old synthetic event command format, so this adds an inner loop that can parse more than one field, if present, between semicolons. For each field, parse_synth_field() checks in which version that field was introduced, using check_field_version(). The caller, __create_synth_event() can then use that version information to determine whether or not to enforce the requirement on the command as a whole. In the future, if/when new features are added, the requirement will be that any field/string containing the new feature must use semicolons, and the check_field_version() check can then check for those and enforce it. Using a version number allows this scheme to be extended if necessary. Link: https://lkml.kernel.org/r/74fcc500d561b40ce91c5ee94818c70c6b0c9330.1612208610.git.zanussi@kernel.org [ zanussi: added check_field_version() comment from rostedt@goodmis.org ] Signed-off-by: Tom Zanussi <zanussi@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Update synth command errorsTom Zanussi2021-02-091-11/+19
| | | | | | | | | | | | | | | | | | | | | | | | | | | | Since array types are handled differently, errors referencing them also need to be handled differently. Add and use a new INVALID_ARRAY_SPEC error. Also add INVALID_CMD and INVALID_DYN_CMD to catch and display the correct form for badly-formed commands, which can also be used in place of CMD_INCOMPLETE, which is removed, and remove CMD_TOO_LONG, since it's no longer used. Link: https://lkml.kernel.org/r/b9dd434dc6458dcff11adc6ed616fe93a8794770.1612208610.git.zanussi@kernel.org Signed-off-by: Tom Zanussi <zanussi@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Rework synthetic event command parsingTom Zanussi2021-02-091-102/+143
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Now that command parsing has been delegated to the create functions and we're no longer constrained by argv_split(), we can modify the synthetic event command parser to better match the higher-level structure of the synthetic event commands, which is basically an event name followed by a set of semicolon-separated fields. Since we're also now passed the raw command, we can also save it directly and can get rid of save_cmdstr(). Link: https://lkml.kernel.org/r/cb9e2be92d992ce59f2b4f132264a5d467f3933f.1612208610.git.zanussi@kernel.org Signed-off-by: Tom Zanussi <zanussi@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing/dynevent: Delegate parsing to create functionMasami Hiramatsu2021-02-099-73/+120
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Delegate command parsing to each create function so that the command syntax can be customized. This requires changes to the kprobe/uprobe/synthetic event handling, which are also included here. Link: https://lkml.kernel.org/r/e488726f49cbdbc01568618f8680584306c4c79f.1612208610.git.zanussi@kernel.org Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> [ zanussi@kernel.org: added synthetic event modifications ] Signed-off-by: Tom Zanussi <zanussi@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * kprobes: Warn if the kprobe is reregisteredMasami Hiramatsu2021-02-091-5/+8
| | | | | | | | | | | | | | | | | | | | | | | | | | Warn if the kprobe is reregistered, since there must be a software bug (actively used resource must not be re-registered) and caller must be fixed. Link: https://lkml.kernel.org/r/161236436734.194052.4058506306336814476.stgit@devnote2 Acked-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> Acked-by: Ananth N Mavinakayanahalli <ananth@linux.ibm.com> Signed-off-by: Masami Hiramatsu <mhiramat@kernel.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * ftrace: Remove unused ftrace_force_update()Jinyang He2021-02-091-2/+0
| | | | | | | | | | | | | | | | | | | | | | ftrace_force_update() is committed by Commit e1c08bdd9fa7 ("ftrace: force recording") and removed by Commit cb7be3b2fc2c ("ftrace: remove daemon"). Remove it in header file. Link: https://lkml.kernel.org/r/1612409671-8249-1-git-send-email-hejinyang@loongson.cn Signed-off-by: Jinyang He <hejinyang@loongson.cn> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracepoints: Code clean upSteven Rostedt (VMware)2021-02-092-57/+36
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Restructure the code a bit to make it simpler, fix some formatting problems and add READ_ONCE/WRITE_ONCE to make sure there's no compiler load/store tearing to the variables that can be accessed across CPUs. Started with Mathieu Desnoyers's patch: Link: https://lore.kernel.org/lkml/20210203175741.20665-1-mathieu.desnoyers@efficios.com/ And will keep his signature, but I will take the responsibility of this being correct, and keep the authorship. Link: https://lkml.kernel.org/r/20210204143004.61126582@gandalf.local.home Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracepoints: Do not punish non static call usersSteven Rostedt (VMware)2021-02-091-10/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | With static calls, a tracepoint can call the callback directly if there is only one callback registered to that tracepoint. When there is more than one, the static call will call the tracepoint's "iterator" function, which needs to reload the tracepoint's "funcs" array again, as it could have changed since the first time it was loaded. But an arch without static calls is punished by having to load the tracepoint's "funcs" array twice. Once in the DO_TRACE macro, and once again in the iterator macro. For archs without static calls, there's no reason to load the array macro in the first place, since the iterator function will do it anyway. Change the __DO_TRACE_CALL() macro to do the load and call of the tracepoints funcs array only for architectures with static calls, and just call the iterator function directly for architectures without static calls. Link: https://lkml.kernel.org/r/20210208201050.909329787@goodmis.org Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracepoints: Remove unnecessary "data_args" macro parameterSteven Rostedt (VMware)2021-02-091-20/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | While working on a clean up that would restructure the difference between architectures that have static calls vs those that do not, I was stumbling over the "data_args" parameter that includes "__data" in the arguments. The issue was that one version didn't even need it, while the other one did. Instead of injecting a "__data = NULL;" into the macro for the unneeded version, just remove it completely. The original idea behind data_args is that there may be a case of a tracepoint with no arguments. But this is considered bad practice, and all tracepoints should pass something to that location (that's what tracepoints were created for). Link: https://lkml.kernel.org/r/20210208201050.768074128@goodmis.org Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Do not create "enable" or "filter" files for ftrace event subsystemSteven Rostedt (VMware)2021-02-051-9/+13
| | | | | | | | | | | | | | | | | | | | | | | | | | The ftrace event subsystem is only created for showing the format files of events created by the ftrace tracers, and are not trace events. The ftrace subsystem currently has both the "enable" and "filter" files that in other subsystems are used to enable/disable all events within the subsystem or set a filter for all the subsystem events. As ftrace subsystem events do not use enable or filter operations, these files are useless in the ftrace subsystem. Remove them. Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * kernel: trace: preemptirq_delay_test: add cpu affinitySong Chen2021-02-022-0/+18
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The kernel thread executing test can run on any cpu, which might be different cpu latency tracer is running on, as a result, the big latency caused by preemptirq delay test can't be detected. Therefore, the argument cpu_affinity is added to be passed to test, ensure it's running on the same cpu with latency tracer. e.g. cyclictest -p 90 -m -c 0 -i 1000 -a 3 modprobe preemptirq_delay_test test_mode=preempt delay=500 \ burst_size=3 cpu_affinity=3 Link: https://lkml.kernel.org/r/1611797713-20965-1-git-send-email-chensong_2000@189.cn Signed-off-by: Song Chen <chensong_2000@189.cn> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracepoint: Do not fail unregistering a probe due to memory failureSteven Rostedt (VMware)2021-02-021-16/+64
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The list of tracepoint callbacks is managed by an array that is protected by RCU. To update this array, a new array is allocated, the updates are copied over to the new array, and then the list of functions for the tracepoint is switched over to the new array. After a completion of an RCU grace period, the old array is freed. This process happens for both adding a callback as well as removing one. But on removing a callback, if the new array fails to be allocated, the callback is not removed, and may be used after it is freed by the clients of the tracepoint. There's really no reason to fail if the allocation for a new array fails when removing a function. Instead, the function can simply be replaced by a stub function that could be cleaned up on the next modification of the array. That is, instead of calling the function registered to the tracepoint, it would call a stub function in its place. Link: https://lore.kernel.org/r/20201115055256.65625-1-mmullins@mmlx.us Link: https://lore.kernel.org/r/20201116175107.02db396d@gandalf.local.home Link: https://lore.kernel.org/r/20201117211836.54acaef2@oasis.local.home Link: https://lkml.kernel.org/r/20201118093405.7a6d2290@gandalf.local.home [ Note, this version does use undefined compiler behavior (assuming that a stub function with no parameters or return, can be called by a location that thinks it has parameters but still no return value. Static calls do the same thing, so this trick is not without precedent. There's another solution that uses RCU tricks and is more complex, but can be an alternative if this solution becomes an issue. Link: https://lore.kernel.org/lkml/20210127170721.58bce7cc@gandalf.local.home/ ] Cc: Peter Zijlstra <peterz@infradead.org> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Alexei Starovoitov <ast@kernel.org> Cc: Daniel Borkmann <daniel@iogearbox.net> Cc: Dmitry Vyukov <dvyukov@google.com> Cc: Martin KaFai Lau <kafai@fb.com> Cc: Song Liu <songliubraving@fb.com> Cc: Yonghong Song <yhs@fb.com> Cc: Andrii Nakryiko <andriin@fb.com> Cc: John Fastabend <john.fastabend@gmail.com> Cc: KP Singh <kpsingh@chromium.org> Cc: netdev <netdev@vger.kernel.org> Cc: bpf <bpf@vger.kernel.org> Cc: Kees Cook <keescook@chromium.org> Cc: Florian Weimer <fw@deneb.enyo.de> Fixes: 97e1c18e8d17b ("tracing: Kernel Tracepoints") Reported-by: syzbot+83aa762ef23b6f0d1991@syzkaller.appspotmail.com Reported-by: syzbot+d29e58bb557324e55e5e@syzkaller.appspotmail.com Reported-by: Matt Mullins <mmullins@mmlx.us> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Tested-by: Matt Mullins <mmullins@mmlx.us>
| * tracing: Remove definition of DEBUG in trace_mmiotrace.cTom Rix2021-02-021-2/+0
| | | | | | | | | | | | | | | | | | | | | | Defining DEBUG should only be done in development. So remove DEBUG. Link: https://lkml.kernel.org/r/20210115153348.131791-1-trix@redhat.com Signed-off-by: Tom Rix <trix@redhat.com> Reviewed-by: Karol Herbst <kherbst@redhat.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Fix a kernel doc warningBean Huo2021-02-021-0/+1
| | | | | | | | | | | | | | | | | | | | | | | | Add description for trace_array_put() parameter. kernel/trace/trace.c:464: warning: Function parameter or member 'this_tr' not described in 'trace_array_put' Link: https://lkml.kernel.org/r/20210112111202.23508-1-huobean@gmail.com Signed-off-by: Bean Huo <beanhuo@micron.com> [ Merged as one of the original fixes was already fixed by someone else ] Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Fix spelling of controlling in uprobesBhaskar Chowdhury2021-02-021-1/+1
| | | | | | | | | | | | | | | | | | | | s/controling/controlling/p Link: https://lkml.kernel.org/r/20210112045008.29834-1-unixbhaskar@gmail.com Signed-off-by: Bhaskar Chowdhury <unixbhaskar@gmail.com> Acked-by: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Fix spelling mistake in Kconfig "infinit" -> "infinite"Colin Ian King2021-02-021-1/+1
| | | | | | | | | | | | | | | | | | There is a spelling mistake in the Kconfig help text. Fix it. Link: https://lkml.kernel.org/r/20201216114051.12056-1-colin.king@canonical.com Signed-off-by: Colin Ian King <colin.king@canonical.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Remove NULL check from current in tracing_generic_entry_update().Sebastian Andrzej Siewior2021-02-021-3/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | I can't imagine when or why `current' would return a NULL pointer. This check was added in commit 72829bc3d63cd ("ftrace: move enums to ftrace.h and make helper function global") but it doesn't give me hint why it was needed. Assume `current' never returns a NULL pointer and remove the check. Link: https://lkml.kernel.org/r/20210125194511.3924915-5-bigeasy@linutronix.de Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Use in_serving_softirq() to deduct softirq status.Sebastian Andrzej Siewior2021-02-021-2/+1
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | PREEMPT_RT does not report "serving softirq" because the tracing core looks at the preemption counter while PREEMPT_RT does not update it while processing softirqs in order to remain preemptible. The information is stored somewhere else. The in_serving_softirq() macro and the SOFTIRQ_OFFSET define are still working but not on the preempt-counter. Use in_serving_softirq() macro which works on PREEMPT_RT. On !PREEMPT_RT the compiler (gcc-10 / clang-11) is smart enough to optimize the in_serving_softirq() related read of the preemption counter away. The only difference I noticed by using in_serving_softirq() on !PREEMPT_RT is that gcc-10 implemented tracing_gen_ctx_flags() as reading FLAG, jmp _tracing_gen_ctx_flags(). Without in_serving_softirq() it inlined _tracing_gen_ctx_flags() into tracing_gen_ctx_flags(). Link: https://lkml.kernel.org/r/20210125194511.3924915-4-bigeasy@linutronix.de Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Inline tracing_gen_ctx_flags()Sebastian Andrzej Siewior2021-02-023-58/+53
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Inline tracing_gen_ctx_flags(). This allows to have one ifdef CONFIG_TRACE_IRQFLAGS_SUPPORT. This requires to move `trace_flag_type' so tracing_gen_ctx_flags() can use it. Link: https://lkml.kernel.org/r/20210125194511.3924915-3-bigeasy@linutronix.de Suggested-by: Steven Rostedt <rostedt@goodmis.org> Link: https://lkml.kernel.org/r/20210125140323.6b1ff20c@gandalf.local.home Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Merge irqflags + preempt counter.Sebastian Andrzej Siewior2021-02-0217-308/+287
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The state of the interrupts (irqflags) and the preemption counter are both passed down to tracing_generic_entry_update(). Only one bit of irqflags is actually required: The on/off state. The complete 32bit of the preemption counter isn't needed. Just whether of the upper bits (softirq, hardirq and NMI) are set and the preemption depth is needed. The irqflags and the preemption counter could be evaluated early and the information stored in an integer `trace_ctx'. tracing_generic_entry_update() would use the upper bits as the TRACE_FLAG_* and the lower 8bit as the disabled-preemption depth (considering that one must be substracted from the counter in one special cases). The actual preemption value is not used except for the tracing record. The `irqflags' variable is mostly used only for the tracing record. An exception here is for instance wakeup_tracer_call() or probe_wakeup_sched_switch() which explicilty disable interrupts and use that `irqflags' to save (and restore) the IRQ state and to record the state. Struct trace_event_buffer has also the `pc' and flags' members which can be replaced with `trace_ctx' since their actual value is not used outside of trace recording. This will reduce tracing_generic_entry_update() to simply assign values to struct trace_entry. The evaluation of the TRACE_FLAG_* bits is moved to _tracing_gen_ctx_flags() which replaces preempt_count() and local_save_flags() invocations. As an example, ftrace_syscall_enter() may invoke: - trace_buffer_lock_reserve() -> … -> tracing_generic_entry_update() - event_trigger_unlock_commit() -> ftrace_trace_stack() -> … -> tracing_generic_entry_update() -> ftrace_trace_userstack() -> … -> tracing_generic_entry_update() In this case the TRACE_FLAG_* bits were evaluated three times. By using the `trace_ctx' they are evaluated once and assigned three times. A build with all tracers enabled on x86-64 with and without the patch: text data bss dec hex filename 21970669 17084168 7639260 46694097 2c87ed1 vmlinux.old 21970293 17084168 7639260 46693721 2c87d59 vmlinux.new text shrank by 379 bytes, data remained constant. Link: https://lkml.kernel.org/r/20210125194511.3924915-2-bigeasy@linutronix.de Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * ring-buffer: Drop unneeded check in ring_buffer_resize()Qiujun Huang2021-02-021-5/+1
| | | | | | | | | | | | | | | | | | | | | | Remove the cpumask check, as we has done it at the beginning of the function. Also fix a typo. s/also the on the/also on the/ Link: https://lkml.kernel.org/r/20201224144634.3210-1-hqjagain@gmail.com Signed-off-by: Qiujun Huang <hqjagain@gmail.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * ring-buffer: Remove cpu_buffer argument from the rb_inc_page()Qiujun Huang2021-02-021-19/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | The cpu_buffer argument is not used inside the rb_inc_page() after commit 3adc54fa82a6 ("ring-buffer: make the buffer a true circular link list"). And cpu_buffer argument is not used inside the two functions too, rb_is_head_page/rb_set_list_to_head. Link: https://lkml.kernel.org/r/20201225140356.23008-1-hqjagain@gmail.com Signed-off-by: Qiujun Huang <hqjagain@gmail.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Remove get/put_cpu() from function_trace_initQiujun Huang2021-02-021-2/+1
| | | | | | | | | | | | | | | | | | | | | | Since commit b6f11df26fdc ("trace: Call tracing_reset_online_cpus before tracer->init()"), get/put_cpu() are not needed anymore. We can use raw_smp_processor_id() instead. Link: https://lkml.kernel.org/r/20201230140521.31920-1-hqjagain@gmail.com Signed-off-by: Qiujun Huang <hqjagain@gmail.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Update trace_ignore_this_task() kernel-doc commentQiujun Huang2021-02-021-1/+2
| | | | | | | | | | | | | | | | | | | | | | Update kernel-doc parameter after commit b3b1e6ededa4 ("ftrace: Create set_ftrace_notrace_pid to not trace tasks") added @filtered_no_pids. Link: https://lkml.kernel.org/r/20201231153558.4804-1-hqjagain@gmail.com Signed-off-by: Qiujun Huang <hqjagain@gmail.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
| * tracing: Add printf attribute to log functionTom Rix2021-02-021-1/+2
| | | | | | | | | | | | | | | | | | | | Attributing the function allows the compiler to more thoroughly check the use of the function with -Wformat and similar flags. Link: https://lkml.kernel.org/r/20201221162715.3757291-1-trix@redhat.com Signed-off-by: Tom Rix <trix@redhat.com> Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
* | Merge tag 'perf-tools-for-v5.12-2020-02-19' of ↵Linus Torvalds2021-02-22183-974/+6938
|\ \ | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux Pull perf tool updates from Arnaldo Carvalho de Melo: "New features: - Support instruction latency in 'perf report', with both memory latency (weight) and instruction latency information, users can locate expensive load instructions and understand time spent in different stages. - Extend 'perf c2c' to display the number of loads which were blocked by data or address conflict. - Add 'perf stat' support for L2 topdown events in systems such as Intel's Sapphire rapids server. - Add support for PERF_SAMPLE_CODE_PAGE_SIZE in various tools, as a sort key, for instance: perf report --stdio --sort=comm,symbol,code_page_size - New 'perf daemon' command to run long running sessions while providing a way to control the enablement of events without restarting a traditional 'perf record' session. - Enable counting events for BPF programs in 'perf stat' just like for other targets (tid, cgroup, cpu, etc), e.g.: # perf stat -e ref-cycles,cycles -b 254 -I 1000 1.487903822 115,200 ref-cycles 1.487903822 86,012 cycles 2.489147029 80,560 ref-cycles 2.489147029 73,784 cycles ^C The example above counts 'cycles' and 'ref-cycles' of BPF program of id 254. It is similar to bpftool-prog-profile command, but more flexible. - Support the new layout for PERF_RECORD_MMAP2 to carry the DSO build-id using infrastructure generalised from the eBPF subsystem, removing the need for traversing the perf.data file to collect build-ids at the end of 'perf record' sessions and helping with long running sessions where binaries can get replaced in updates, leading to possible mis-resolution of symbols. - Support filtering by hex address in 'perf script'. - Support DSO filter in 'perf script', like in other perf tools. - Add namespaces support to 'perf inject' - Add support for SDT (Dtrace Style Markers) events on ARM64. perf record: - Fix handling of eventfd() when draining a buffer in 'perf record'. - Improvements to the generation of metadata events for pre-existing threads (mmaps, comm, etc), speeding up the work done at the start of system wide or per CPU 'perf record' sessions. Hardware tracing: - Initial support for tracing KVM with Intel PT. - Intel PT fixes for IPC - Support Intel PT PSB (synchronization packets) events. - Automatically group aux-output events to overcome --filter syntax. - Enable PERF_SAMPLE_DATA_SRC on ARMs SPE. - Update ARM's CoreSight hardware tracing OpenCSD library to v1.0.0. perf annotate TUI: - Fix handling of 'k' ("show line number") hotkey - Fix jump parsing for C++ code. perf probe: - Add protection to avoid endless loop. cgroups: - Avoid reading cgroup mountpoint multiple times, caching it. - Fix handling of cgroup v1/v2 in mixed hierarchy. Symbol resolving: - Add OCaml symbol demangling. - Further fixes for handling PE executables when using perf with Wine and .exe/.dll files. - Fix 'perf unwind' DSO handling. - Resolve symbols against debug file first, to deal with artifacts related to LTO. - Fix gap between kernel end and module start on powerpc. Reporting tools: - The DSO filter shouldn't show samples in unresolved maps. - Improve debuginfod support in various tools. build ids: - Fix 16-byte build ids in 'perf buildid-cache', add a 'perf test' entry for that case. perf test: - Support for PERF_SAMPLE_WEIGHT_STRUCT. - Add test case for PERF_SAMPLE_CODE_PAGE_SIZE. - Shell based tests for 'perf daemon's commands ('start', 'stop, 'reconfig', 'list', etc). - ARM cs-etm 'perf test' fixes. - Add parse-metric memory bandwidth testcase. Compiler related: - Fix 'perf probe' kretprobe issue caused by gcc 11 bug when used with -fpatchable-function-entry. - Fix ARM64 build with gcc 11's -Wformat-overflow. - Fix unaligned access in sample parsing test. - Fix printf conversion specifier for IP addresses on arm64, s390 and powerpc. Arch specific: - Support exposing Performance Monitor Counter SPRs as part of extended regs on powerpc. - Add JSON 'perf stat' metrics for ARM64's imx8mp, imx8mq and imx8mn DDR, fix imx8mm ones. - Fix common and uarch events for ARM64's A76 and Ampere eMag" * tag 'perf-tools-for-v5.12-2020-02-19' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (148 commits) perf buildid-cache: Don't skip 16-byte build-ids perf buildid-cache: Add test for 16-byte build-id perf symbol: Remove redundant libbfd checks perf test: Output the sub testing result in cs-etm perf test: Suppress logs in cs-etm testing perf tools: Fix arm64 build error with gcc-11 perf intel-pt: Add documentation for tracing virtual machines perf intel-pt: Split VM-Entry and VM-Exit branches perf intel-pt: Adjust sample flags for VM-Exit perf intel-pt: Allow for a guest kernel address filter perf intel-pt: Support decoding of guest kernel perf machine: Factor out machine__idle_thread() perf machine: Factor out machines__find_guest() perf intel-pt: Amend decoder to track the NR flag perf intel-pt: Retain the last PIP packet payload as is perf intel_pt: Add vmlaunch and vmresume as branches perf script: Add branch types for VM-Entry and VM-Exit perf auxtrace: Automatically group aux-output events perf test: Fix unaligned access in sample parsing test perf tools: Support arch specific PERF_SAMPLE_WEIGHT_STRUCT processing ...
| * | perf buildid-cache: Don't skip 16-byte build-idsNicholas Fraser2021-02-182-3/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | lsdir_bid_tail_filter() ignored any build-id that wasn't exactly 20 bytes. This worked only for SHA-1 build-ids. The build-id for a PE file is always a 16-byte GUID and ELF files can also have MD5 or UUID build-ids. This fix changes the filter to allow build-ids between 16 and 20 bytes. Signed-off-by: Nicholas Fraser <nfraser@codeweavers.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Huw Davies <huw@codeweavers.com> Cc: Ian Rogers <irogers@google.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Remi Bernon <rbernon@codeweavers.com> Cc: Song Liu <songliubraving@fb.com> Cc: Tommi Rantala <tommi.t.rantala@nokia.com> Cc: Ulrich Czekalla <uczekalla@codeweavers.com> Link: http://lore.kernel.org/lkml/597788e4-661d-633f-857c-3de700115d02@codeweavers.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf buildid-cache: Add test for 16-byte build-idNicholas Fraser2021-02-181-0/+6
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | tests/shell/buildid.sh added an ELF executable with an MD5 build-id to the perf debug cache but did not check whether the object was printed by a subsequent call to "perf buildid-cache -l". It was being omitted from the list. A previous commit fixed the bug that left it out of the list. This adds a test for it. Signed-off-by: Nicholas Fraser <nfraser@codeweavers.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Huw Davies <huw@codeweavers.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Remi Bernon <rbernon@codeweavers.com> Cc: Song Liu <songliubraving@fb.com> Cc: Tommi Rantala <tommi.t.rantala@nokia.com> Cc: Ulrich Czekalla <uczekalla@codeweavers.com> Link: https://lore.kernel.org/r/c08be235-7434-5208-5f21-e8c9a3265464@codeweavers.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf symbol: Remove redundant libbfd checksNicholas Fraser2021-02-181-9/+0
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | This removes the redundant checks bfd_check_format() and bfd_target_elf_flavour. They were previously checking different files. Signed-off-by: Nicholas Fraser <nfraser@codeweavers.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Adrian Hunter <adrian.hunter@intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Arnaldo Carvalho de Melo <acme@kernel.org> Cc: Frank Ch. Eigler <fche@redhat.com> Cc: Huw Davies <huw@codeweavers.com> Cc: Ian Rogers <irogers@google.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Kim Phillips <kim.phillips@amd.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Remi Bernon <rbernon@codeweavers.com> Cc: Song Liu <songliubraving@fb.com> Cc: Tommi Rantala <tommi.t.rantala@nokia.com> Cc: Ulrich Czekalla <uczekalla@codeweavers.com> Link: https://lore.kernel.org/r/94758ca1-0031-d7c6-6c6a-900fd77ef695@codeweavers.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf test: Output the sub testing result in cs-etmLeo Yan2021-02-181-10/+14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The CoreSight testing contains sub cases, e.g. every CPU iterates the possible conntected sinks and tests the paths between the associated ETM with the found sink. Besides the per-thread testing, it also contains system wide testing and snapshot testing. To easier observe results for the sub cases, this patch introduces a new function arm_cs_report(), it outputs the result as "PASS" or "FAIL" for every sub case; and it records the error in the variable "glb_err" which is used as the final return value when exits the testing. Before: # perf test 73 -v 73: Check Arm CoreSight trace data recording and synthesized samples: --- start --- test child forked, pid 17423 Recording trace (only user mode) with path: CPU0 => tmc_etf0 Looking at perf.data file for dumping branch samples: Looking at perf.data file for reporting branch samples: Looking at perf.data file for instruction samples: Recording trace (only user mode) with path: CPU0 => tmc_etr0 Looking at perf.data file for dumping branch samples: Looking at perf.data file for reporting branch samples: Looking at perf.data file for instruction samples: [...] After: # perf test 73 -v 73: Check Arm CoreSight trace data recording and synthesized samples: --- start --- test child forked, pid 17423 Recording trace (only user mode) with path: CPU0 => tmc_etf0 Looking at perf.data file for dumping branch samples: Looking at perf.data file for reporting branch samples: Looking at perf.data file for instruction samples: CoreSight path testing (CPU0 -> tmc_etf0): PASS Recording trace (only user mode) with path: CPU0 => tmc_etr0 Looking at perf.data file for dumping branch samples: Looking at perf.data file for reporting branch samples: Looking at perf.data file for instruction samples: CoreSight path testing (CPU0 -> tmc_etr0): PASS [...] Signed-off-by: Leo Yan <leo.yan@linaro.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Basil Eljuse <basil.eljuse@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naresh Kamboju <naresh.kamboju@linaro.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Link: http://lore.kernel.org/lkml/20210215115944.535986-3-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf test: Suppress logs in cs-etm testingLeo Yan2021-02-181-12/+9
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | With the option '-v' for the verbose logs, "perf test" outputs tons of logs for the CoreSight case, the logs are mainly introduced by the decoding. And it outputs some trivial info from "perf record" command and there have debugging info for CPU number and device name when iterates between ETMs and sinks. For a neat output format, this patch redirects the output logs to "/dev/null", thus can avoid to flood logs. And it removes the redundant log for CPU number and device name, which have already printed out the relevant info in the function record_touch_file(). Signed-off-by: Leo Yan <leo.yan@linaro.org> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Basil Eljuse <basil.eljuse@arm.com> Cc: Jiri Olsa <jolsa@redhat.com> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Mike Leach <mike.leach@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Naresh Kamboju <naresh.kamboju@linaro.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Suzuki Poulouse <suzuki.poulose@arm.com> Cc: Viresh Kumar <viresh.kumar@linaro.org> Link: http://lore.kernel.org/lkml/20210215115944.535986-2-leo.yan@linaro.org Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf tools: Fix arm64 build error with gcc-11Jianlin Lv2021-02-188-7/+14
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | gcc version: 11.0.0 20210208 (experimental) (GCC) Following build error on arm64: ....... In function ‘printf’, inlined from ‘regs_dump__printf’ at util/session.c:1141:3, inlined from ‘regs__printf’ at util/session.c:1169:2: /usr/include/aarch64-linux-gnu/bits/stdio2.h:107:10: \ error: ‘%-5s’ directive argument is null [-Werror=format-overflow=] 107 | return __printf_chk (__USE_FORTIFY_LEVEL - 1, __fmt, \ __va_arg_pack ()); ...... In function ‘fprintf’, inlined from ‘perf_sample__fprintf_regs.isra’ at \ builtin-script.c:622:14: /usr/include/aarch64-linux-gnu/bits/stdio2.h:100:10: \ error: ‘%5s’ directive argument is null [-Werror=format-overflow=] 100 | return __fprintf_chk (__stream, __USE_FORTIFY_LEVEL - 1, __fmt, 101 | __va_arg_pack ()); cc1: all warnings being treated as errors ....... This patch fixes Wformat-overflow warnings. Add helper function to convert NULL to "unknown". Signed-off-by: Jianlin Lv <Jianlin.Lv@arm.com> Reviewed-by: John Garry <john.garry@huawei.com> Acked-by: Jiri Olsa <jolsa@redhat.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Anju T Sudhakar <anju@linux.vnet.ibm.com> Cc: Athira Jajeev <atrajeev@linux.vnet.ibm.com> Cc: Guo Ren <guoren@kernel.org> Cc: Kajol Jain <kjain@linux.ibm.com> Cc: Leo Yan <leo.yan@linaro.org> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Mathieu Poirier <mathieu.poirier@linaro.org> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Ravi Bangoria <ravi.bangoria@linux.ibm.com> Cc: Will Deacon <will@kernel.org> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: iecedge@gmail.com Cc: linux-csky@vger.kernel.org Cc: linux-riscv@lists.infradead.org Link: http://lore.kernel.org/lkml/20210218031245.2078492-1-Jianlin.Lv@arm.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf intel-pt: Add documentation for tracing virtual machinesAdrian Hunter2021-02-181-0/+82
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Add documentation to the perf-intel-pt man page for tracing virtual machines. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: https://lore.kernel.org/r/20210218095801.19576-12-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf intel-pt: Split VM-Entry and VM-Exit branchesAdrian Hunter2021-02-181-1/+21
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Events record a single cpumode so the tools cannot handle a branch from the host machine to a virtual machine, or vice versa. Split it in two so that each branch can have a different cpumode. E.g. host ip -> guest ip becomes: host ip -> 0 0 -> guest ip Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: https://lore.kernel.org/r/20210218095801.19576-11-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf intel-pt: Adjust sample flags for VM-ExitAdrian Hunter2021-02-181-4/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Use the change of NR to detect whether an asynchronous branch is a VM-Exit. Note VM-Entry is determined from the vmlaunch or vmresume instruction, in which case, sample flags will show "VMentry" even if the VM-Entry fails. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: https://lore.kernel.org/r/20210218095801.19576-10-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf intel-pt: Allow for a guest kernel address filterAdrian Hunter2021-02-181-1/+7
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Handling TIP.PGD for an address filter for a guest kernel is the same as a host kernel, but user space decoding, and hence address filters, are not supported. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: https://lore.kernel.org/r/20210218095801.19576-9-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf intel-pt: Support decoding of guest kernelAdrian Hunter2021-02-181-12/+69
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The guest kernel can be found from any guest thread belonging to the guest machine. The guest machine is associated with the current host process pid. An idle thread (pid=tid=0) is created as a vehicle from which to find the guest kernel map. Decoding guest user space is not supported. Synthesized samples just need the cpumode set for the guest. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: https://lore.kernel.org/r/20210218095801.19576-8-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf machine: Factor out machine__idle_thread()Adrian Hunter2021-02-183-22/+22
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Factor out machine__idle_thread() so it can be re-used for guest machines. A thread is needed to find executable code, even for the guest kernel. To avoid possible future pid number conflicts, the idle thread can be used. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: https://lore.kernel.org/r/20210218095801.19576-7-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf machine: Factor out machines__find_guest()Adrian Hunter2021-02-183-6/+11
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Factor out machines__find_guest() so it can be re-used. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: https://lore.kernel.org/r/20210218095801.19576-6-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf intel-pt: Amend decoder to track the NR flagAdrian Hunter2021-02-182-9/+53
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | The PIP packet NR (non-root) flag indicates whether or not a virtual machine is being traced (NR=1 => VM). Add support for tracking its value. In particular note that the PIP packet (outside of PSB+) will be associated with a TIP packet from which address the NR value takes effect. At that point, there is a branch from_ip, to_ip with corresponding from_nr and to_nr. In the event of VM-Entry failure, there should still PIP and TIP packets that can be followed in the same way. Also note that this assumes that a host VMM is not employing VMX controls that affect Intel PT, e.g. to hide the host from a guest using Intel PT. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: https://lore.kernel.org/r/20210218095801.19576-5-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
| * | perf intel-pt: Retain the last PIP packet payload as isAdrian Hunter2021-02-185-18/+16
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | Retain the PIP packet payload as is, instead of just the CR3, because it contains also the VMX NR flag which is needed to track VM-Entry. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Acked-by: Andi Kleen <ak@linux.intel.com> Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com> Cc: Jiri Olsa <jolsa@redhat.com> Link: https://lore.kernel.org/r/20210218095801.19576-4-adrian.hunter@intel.com Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
generated by cgit v1.2.3 (git 2.25.1) at 2024-07-13 10:49:56 +0000