summaryrefslogtreecommitdiff
path: root/kernel/events
AgeCommit message (Collapse)AuthorFilesLines
2024-09-05perf/core: Fix small negative period being ignoredLuo Gengkun1-1/+5
In perf_adjust_period, we will first calculate period, and then use this period to calculate delta. However, when delta is less than 0, there will be a deviation compared to when delta is greater than or equal to 0. For example, when delta is in the range of [-14,-1], the range of delta = delta + 7 is between [-7,6], so the final value of delta/8 is 0. Therefore, the impact of -1 and -2 will be ignored. This is unacceptable when the target period is very short, because we will lose a lot of samples. Here are some tests and analyzes: before: # perf record -e cs -F 1000 ./a.out [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.022 MB perf.data (518 samples) ] # perf script ... a.out 396 257.956048: 23 cs: ffffffff81f4eeec schedul> a.out 396 257.957891: 23 cs: ffffffff81f4eeec schedul> a.out 396 257.959730: 23 cs: ffffffff81f4eeec schedul> a.out 396 257.961545: 23 cs: ffffffff81f4eeec schedul> a.out 396 257.963355: 23 cs: ffffffff81f4eeec schedul> a.out 396 257.965163: 23 cs: ffffffff81f4eeec schedul> a.out 396 257.966973: 23 cs: ffffffff81f4eeec schedul> a.out 396 257.968785: 23 cs: ffffffff81f4eeec schedul> a.out 396 257.970593: 23 cs: ffffffff81f4eeec schedul> ... after: # perf record -e cs -F 1000 ./a.out [ perf record: Woken up 1 times to write data ] [ perf record: Captured and wrote 0.058 MB perf.data (1466 samples) ] # perf script ... a.out 395 59.338813: 11 cs: ffffffff81f4eeec schedul> a.out 395 59.339707: 12 cs: ffffffff81f4eeec schedul> a.out 395 59.340682: 13 cs: ffffffff81f4eeec schedul> a.out 395 59.341751: 13 cs: ffffffff81f4eeec schedul> a.out 395 59.342799: 12 cs: ffffffff81f4eeec schedul> a.out 395 59.343765: 11 cs: ffffffff81f4eeec schedul> a.out 395 59.344651: 11 cs: ffffffff81f4eeec schedul> a.out 395 59.345539: 12 cs: ffffffff81f4eeec schedul> a.out 395 59.346502: 13 cs: ffffffff81f4eeec schedul> ... test.c int main() { for (int i = 0; i < 20000; i++) usleep(10); return 0; } # time ./a.out real 0m1.583s user 0m0.040s sys 0m0.298s The above results were tested on x86-64 qemu with KVM enabled using test.c as test program. Ideally, we should have around 1500 samples, but the previous algorithm had only about 500, whereas the modified algorithm now has about 1400. Further more, the new version shows 1 sample per 0.001s, while the previous one is 1 sample per 0.002s.This indicates that the new algorithm is more sensitive to small negative values compared to old algorithm. Fixes: bd2b5b12849a ("perf_counter: More aggressive frequency adjustment") Signed-off-by: Luo Gengkun <luogengkun@huaweicloud.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Adrian Hunter <adrian.hunter@intel.com> Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Cc: stable@vger.kernel.org Link: https://lkml.kernel.org/r/20240831074316.2106159-2-luogengkun@huaweicloud.com
2024-09-05Merge branch 'perf/urgent' into perf/core, to pick up fixesIngo Molnar4-9/+18
This also refreshes the -rc1 based branch to -rc5. Signed-off-by: Ingo Molnar <mingo@kernel.org>
2024-09-04perf/aux: Fix AUX buffer serializationPeter Zijlstra3-6/+15
Ole reported that event->mmap_mutex is strictly insufficient to serialize the AUX buffer, add a per RB mutex to fully serialize it. Note that in the lock order comment the perf_event::mmap_mutex order was already wrong, that is, it nesting under mmap_lock is not new with this patch. Fixes: 45bfb2e50471 ("perf: Add AUX area to ring buffer for raw data streams") Reported-by: Ole <ole@binarygecko.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org>
2024-09-03uprobes: Use kzalloc to allocate xol areaSven Schnelle1-2/+1
To prevent unitialized members, use kzalloc to allocate the xol area. Fixes: b059a453b1cf1 ("x86/vdso: Add mremap hook to vm_special_mapping") Signed-off-by: Sven Schnelle <svens@linux.ibm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Acked-by: Oleg Nesterov <oleg@redhat.com> Link: https://lore.kernel.org/r/20240903102313.3402529-1-svens@linux.ibm.com
2024-08-30drivers/perf: arm_spe: Use perf_allow_kernel() for permissionsJames Clark1-0/+9
Use perf_allow_kernel() for 'pa_enable' (physical addresses), 'pct_enable' (physical timestamps) and context IDs. This means that perf_event_paranoid is now taken into account and LSM hooks can be used, which is more consistent with other perf_event_open calls. For example PERF_SAMPLE_PHYS_ADDR uses perf_allow_kernel() rather than just perfmon_capable(). This also indirectly fixes the following error message which is misleading because perf_event_paranoid is not taken into account by perfmon_capable(): $ perf record -e arm_spe/pa_enable/ Error: Access to performance monitoring and observability operations is limited. Consider adjusting /proc/sys/kernel/perf_event_paranoid setting ... Suggested-by: Al Grant <al.grant@arm.com> Signed-off-by: James Clark <james.clark@linaro.org> Link: https://lore.kernel.org/r/20240827145113.1224604-1-james.clark@linaro.org Link: https://lore.kernel.org/all/20240807120039.GD37996@noisy.programming.kicks-ass.net/ Signed-off-by: Will Deacon <will@kernel.org>
2024-08-14perf: Really fix event_function_call() lockingNamhyung Kim1-5/+8
Commit 558abc7e3f89 ("perf: Fix event_function_call() locking") lost IRQ disabling by mistake. Fixes: 558abc7e3f89 ("perf: Fix event_function_call() locking") Reported-by: Pengfei Xu <pengfei.xu@intel.com> Reported-by: Naresh Kamboju <naresh.kamboju@linaro.org> Tested-by: Pengfei Xu <pengfei.xu@intel.com> Signed-off-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
2024-08-13perf/bpf: Don't call bpf_overflow_handler() for tracing eventsKyle Huey1-1/+2
The regressing commit is new in 6.10. It assumed that anytime event->prog is set bpf_overflow_handler() should be invoked to execute the attached bpf program. This assumption is false for tracing events, and as a result the regressing commit broke bpftrace by invoking the bpf handler with garbage inputs on overflow. Prior to the regression the overflow handlers formed a chain (of length 0, 1, or 2) and perf_event_set_bpf_handler() (the !tracing case) added bpf_overflow_handler() to that chain, while perf_event_attach_bpf_prog() (the tracing case) did not. Both set event->prog. The chain of overflow handlers was replaced by a single overflow handler slot and a fixed call to bpf_overflow_handler() when appropriate. This modifies the condition there to check event->prog->type == BPF_PROG_TYPE_PERF_EVENT, restoring the previous behavior and fixing bpftrace. Signed-off-by: Kyle Huey <khuey@kylehuey.com> Suggested-by: Andrii Nakryiko <andrii.nakryiko@gmail.com> Reported-by: Joe Damato <jdamato@fastly.com> Closes: https://lore.kernel.org/lkml/ZpFfocvyF3KHaSzF@LQ3V64L9R2/ Fixes: f11f10bfa1ca ("perf/bpf: Call BPF handler directly, not through overflow machinery") Cc: stable@vger.kernel.org Tested-by: Joe Damato <jdamato@fastly.com> # bpftrace Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/r/20240813151727.28797-1-jdamato@fastly.com Signed-off-by: Alexei Starovoitov <ast@kernel.org>
2024-08-12struct fd: representation changeAl Viro1-1/+1
We want the compiler to see that fdput() on empty instance is a no-op. The emptiness check is that file reference is NULL, while fdput() is "fput() if FDPUT_FPUT is present in flags". The reason why fdput() on empty instance is a no-op is something compiler can't see - it's that we never generate instances with NULL file reference combined with non-zero flags. It's not that hard to deal with - the real primitives behind fdget() et.al. are returning an unsigned long value, unpacked by (inlined) __to_fd() into the current struct file * + int. The lower bits are used to store flags, while the rest encodes the pointer. Linus suggested that keeping this unsigned long around with the extractions done by inlined accessors should generate a sane code and that turns out to be the case. Namely, turning struct fd into a struct-wrapped unsinged long, with fd_empty(f) => unlikely(f.word == 0) fd_file(f) => (struct file *)(f.word & ~3) fdput(f) => if (f.word & 1) fput(fd_file(f)) ends up with compiler doing the right thing. The cost is the patch footprint, of course - we need to switch f.file to fd_file(f) all over the tree, and it's not doable with simple search and replace; there are false positives, etc. Note that the sole member of that structure is an opaque unsigned long - all accesses should be done via wrappers and I don't want to use a name that would invite manual casts to file pointers, etc. The value of that member is equal either to (unsigned long)p | flags, p being an address of some struct file instance, or to 0 for an empty fd. For now the new predicate (fd_empty(f)) has no users; all the existing checks have form (!fd_file(f)). We will convert to fd_empty() use later; here we only define it (and tell the compiler that it's unlikely to return true). This commit only deals with representation change; there will be followups. Reviewed-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2024-08-12introduce fd_file(), convert all accessors to it.Al Viro1-6/+6
For any changes of struct fd representation we need to turn existing accesses to fields into calls of wrappers. Accesses to struct fd::flags are very few (3 in linux/file.h, 1 in net/socket.c, 3 in fs/overlayfs/file.c and 3 more in explicit initializers). Those can be dealt with in the commit converting to new layout; accesses to struct fd::file are too many for that. This commit converts (almost) all of f.file to fd_file(f). It's not entirely mechanical ('file' is used as a member name more than just in struct fd) and it does not even attempt to distinguish the uses in pointer context from those in boolean context; the latter will be eventually turned into a separate helper (fd_empty()). NOTE: mass conversion to fd_empty(), tempting as it might be, is a bad idea; better do that piecewise in commit that convert from fdget...() to CLASS(...). [conflicts in fs/fhandle.c, kernel/bpf/syscall.c, mm/memcontrol.c caught by git; fs/stat.c one got caught by git grep] [fs/xattr.c conflict] Reviewed-by: Christian Brauner <brauner@kernel.org> Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
2024-08-08perf: Optimize __pmu_ctx_sched_out()Peter Zijlstra1-1/+1
There is is no point in doing the perf_pmu_disable() dance just to do nothing. This happens for ctx_sched_out(.type = EVENT_TIME) for instance. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Reviewed-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240807115550.392851915@infradead.org
2024-08-08perf: Add context time freezePeter Zijlstra1-42/+86
Many of the the context reschedule users are of the form: ctx_sched_out(.type = EVENT_TIME); ... modify context ctx_resched(); With the idea that the whole reschedule happens with a single time-stamp, rather than with each ctx_sched_out() advancing time and ctx_sched_in() re-starting time, creating a non-atomic experience. However, Kan noticed that since this completely stops time, it actually looses a bit of time between the stop and start. Worse, now that we can do partial (per PMU) reschedules, the PMUs that are not scheduled out still observe the time glitch. Replace this with: ctx_time_freeze(); ... modify context ctx_resched(); With the assumption that this happens in a perf_ctx_lock() / perf_ctx_unlock() pair. The new ctx_time_freeze() will update time and sets EVENT_FROZEN, and ensures EVENT_TIME and EVENT_FROZEN remain set, this avoids perf_event_time_now() from observing a time wobble from not seeing EVENT_TIME for a little while. Additionally, this avoids loosing time between ctx_sched_out(EVENT_TIME) and ctx_sched_in(), which would re-set the timestamp. Reported-by: Kan Liang <kan.liang@linux.intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Reviewed-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240807115550.250637571@infradead.org
2024-08-08perf: Fix event_function_call() lockingPeter Zijlstra1-4/+5
All the event_function/@func call context already uses perf_ctx_lock() except for the !ctx->is_active case. Make it all consistent. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Reviewed-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240807115550.138301094@infradead.org
2024-08-08perf: Extract a few helpersPeter Zijlstra1-17/+22
The context time update code is repeated verbatim a few times. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Reviewed-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240807115550.031212518@infradead.org
2024-08-08perf: Optimize context reschedule for single PMU casesPeter Zijlstra1-76/+88
Currently re-scheduling a context will reschedule all active PMUs for that context, even if it is known only a single event is added. Namhyung reported that changing this to only reschedule the affected PMU when possible provides significant performance gains under certain conditions. Therefore, allow partial context reschedules for a specific PMU, that of the event modified. While the patch looks somewhat noisy, it mostly just propagates a new @pmu argument through the callchain and modifies the epc loop to only pick the 'epc->pmu == @pmu' case. Reported-by: Namhyung Kim <namhyung@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Kan Liang <kan.liang@linux.intel.com> Reviewed-by: Namhyung Kim <namhyung@kernel.org> Link: https://lore.kernel.org/r/20240807115549.920950699@infradead.org
2024-08-02uprobes: shift put_uprobe() from delete_uprobe() to uprobe_unregister()Oleg Nesterov1-5/+9
Kill the extra get_uprobe() + put_uprobe() in uprobe_unregister() and move the possibly final put_uprobe() from delete_uprobe() to its only caller, uprobe_unregister(). Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: "Masami Hiramatsu (Google)" <mhiramat@kernel.org> Link: https://lore.kernel.org/r/20240801132749.GA8817@redhat.com
2024-08-02uprobes: fold __uprobe_unregister() into uprobe_unregister()Oleg Nesterov1-15/+10
Fold __uprobe_unregister() into its single caller, uprobe_unregister(). A separate patch to simplify the next change. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: "Masami Hiramatsu (Google)" <mhiramat@kernel.org> Link: https://lore.kernel.org/r/20240801132744.GA8814@redhat.com
2024-08-02uprobes: change uprobe_register() to use uprobe_unregister() instead of ↵Oleg Nesterov1-5/+7
__uprobe_unregister() If register_for_each_vma() fails uprobe_register() can safely drop uprobe->register_rwsem and use uprobe_unregister(). There is no worry about the races with another register/unregister, consumer_add() was already called so this case doesn't differ from _unregister() right after the successful _register(). Yes this means the extra up_write() + down_write(), but this is the slow and unlikely case anyway. Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: "Masami Hiramatsu (Google)" <mhiramat@kernel.org> Link: https://lore.kernel.org/r/20240801132739.GA8809@redhat.com
2024-08-02uprobes: make uprobe_register() return struct uprobe *Oleg Nesterov1-34/+22
This way uprobe_unregister() and uprobe_apply() can use "struct uprobe *" rather than inode + offset. This simplifies the code and allows to avoid the unnecessary find_uprobe() + put_uprobe() in these functions. TODO: uprobe_unregister() still needs get_uprobe/put_uprobe to ensure that this uprobe can't be freed before up_write(&uprobe->register_rwsem). Co-developed-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20240801132734.GA8803@redhat.com
2024-08-02uprobes: kill uprobe_register_refctr()Oleg Nesterov1-18/+6
It doesn't make any sense to have 2 versions of _register(). Note that trace_uprobe_enable(), the only user of uprobe_register(), doesn't need to check tu->ref_ctr_offset to decide which one should be used, it could safely pass ref_ctr_offset == 0 to uprobe_register_refctr(). Add this argument to uprobe_register(), update the callers, and kill uprobe_register_refctr(). Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/r/20240801132728.GA8800@redhat.com
2024-08-02uprobes: simplify error handling for alloc_uprobe()Andrii Nakryiko1-3/+1
Return -ENOMEM instead of NULL, which makes caller's error handling just a touch simpler. Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: "Masami Hiramatsu (Google)" <mhiramat@kernel.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/r/20240801132719.GA8788@redhat.com
2024-08-02uprobes: is_trap_at_addr: don't use get_user_pages_remote()Oleg Nesterov1-7/+1
get_user_pages_remote() and the comment above it make no sense. There is no task_struct passed into get_user_pages_remote() anymore, and nowadays mm_account_fault() increments the current->min/maj_flt counters regardless of FAULT_FLAG_REMOTE. Reported-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Link: https://lore.kernel.org/r/20240801132714.GA8783@redhat.com
2024-08-02uprobes: document the usage of mm->mmap_lockOleg Nesterov1-2/+8
The comment above uprobe_write_opcode() is wrong, unapply_uprobe() calls it under mmap_read_lock() and this is correct. And it is completely unclear why register_for_each_vma() takes mmap_lock for writing, add a comment to explain that mmap_write_lock() is needed to avoid the following race: - A task T hits the bp installed by uprobe and calls find_active_uprobe() - uprobe_unregister() removes this uprobe/bp - T calls find_uprobe() which returns NULL - another uprobe_register() installs the bp at the same address - T calls is_trap_at_addr() which returns true - T returns to handle_swbp() and gets SIGTRAP. Reported-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Oleg Nesterov <oleg@redhat.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Acked-by: Andrii Nakryiko <andrii@kernel.org> Acked-by: "Masami Hiramatsu (Google)" <mhiramat@kernel.org> Link: https://lore.kernel.org/r/20240801132709.GA8780@redhat.com
2024-08-02perf,x86: avoid missing caller address in stack traces captured in uprobeAndrii Nakryiko1-0/+2
When tracing user functions with uprobe functionality, it's common to install the probe (e.g., a BPF program) at the first instruction of the function. This is often going to be `push %rbp` instruction in function preamble, which means that within that function frame pointer hasn't been established yet. This leads to consistently missing an actual caller of the traced function, because perf_callchain_user() only records current IP (capturing traced function) and then following frame pointer chain (which would be caller's frame, containing the address of caller's caller). So when we have target_1 -> target_2 -> target_3 call chain and we are tracing an entry to target_3, captured stack trace will report target_1 -> target_3 call chain, which is wrong and confusing. This patch proposes a x86-64-specific heuristic to detect `push %rbp` (`push %ebp` on 32-bit architecture) instruction being traced. Given entire kernel implementation of user space stack trace capturing works under assumption that user space code was compiled with frame pointer register (%rbp/%ebp) preservation, it seems pretty reasonable to use this instruction as a strong indicator that this is the entry to the function. In that case, return address is still pointed to by %rsp/%esp, so we fetch it and add to stack trace before proceeding to unwind the rest using frame pointer-based logic. We also check for `endbr64` (for 64-bit modes) as another common pattern for function entry, as suggested by Josh Poimboeuf. Even if we get this wrong sometimes for uprobes attached not at the function entry, it's OK because stack trace will still be overall meaningful, just with one extra bogus entry. If we don't detect this, we end up with guaranteed to be missing caller function entry in the stack trace, which is worse overall. Signed-off-by: Andrii Nakryiko <andrii@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20240729175223.23914-1-andrii@kernel.org
2024-08-02perf: Support PERF_SAMPLE_READ with inheritBen Gainey1-14/+41
This change allows events to use PERF_SAMPLE_READ with inherit so long as PERF_SAMPLE_TID is also set. This enables sample based profiling of a group of counters over a hierarchy of processes or threads. This is useful, for example, for collecting per-thread counters/metrics, event based sampling of multiple counters as a unit, access to the enabled and running time when using multiplexing and so on. Prior to this, users were restricted to either collecting aggregate statistics for a multi-threaded/-process application (e.g. with "perf stat"), or to sample individual threads, or to profile the entire system (which requires root or CAP_PERFMON, and may produce much more data than is required). Theoretically a tool could poll for or otherwise monitor thread/process creation and construct whatever events the user is interested in using perf_event_open, for each new thread or process, but this is racy, can lead to file-descriptor exhaustion, and ultimately just replicates the behaviour of inherit, but in userspace. This configuration differs from inherit without PERF_SAMPLE_READ in that the accumulated event count, and consequently any sample (such as if triggered by overflow of sample_period) will be on a per-thread rather than on an aggregate basis. The meaning of read_format::value field of both PERF_RECORD_READ and PERF_RECORD_SAMPLE is changed such that if the sampled event uses this new configuration then the values reported will be per-thread rather than the global aggregate value. This is a change from the existing semantics of read_format (where PERF_SAMPLE_READ is used without inherit), but it is necessary to expose the per-thread counter values, and it avoids reinventing a separate "read_format_thread" field that otherwise replicates the same behaviour. This change should not break existing tools, since this configuration was not previously valid and was rejected by the kernel. Tools that opt into this new mode will need to account for this when calculating the counter delta for a given sample. Tools that wish to have both the per-thread and aggregate value can perform the global aggregation themselves from the per-thread values. The change to read_format::value does not affect existing valid perf_event_attr configurations, nor does it change the behaviour of calls to "read" on an event descriptor. Both continue to report the aggregate value for the entire thread/process hierarchy. The difference between the results reported by "read" and PERF_RECORD_SAMPLE in this new configuration is justified on the basis that it is not (easily) possible for "read" to target a specific thread (the caller only has the fd for the original parent event). Signed-off-by: Ben Gainey <ben.gainey@arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20240730084417.7693-3-ben.gainey@arm.com
2024-08-02perf: Rename perf_event_context.nr_pending to nr_no_switch_fast.Ben Gainey1-6/+6
nr_pending counts the number of events in the context that either pending_sigtrap or pending_work, but it is used to prevent taking the fast path in perf_event_context_sched_out. Renamed to reflect what it is used for, rather than what it counts. This change allows using the field to track other event properties that also require skipping the fast path without possible confusion over the name. Signed-off-by: Ben Gainey <ben.gainey@arm.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20240730084417.7693-2-ben.gainey@arm.com
2024-07-25Merge tag 'net-6.11-rc1' of ↵Linus Torvalds1-15/+13
git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net Pull networking fixes from Jakub Kicinski: "Including fixes from bpf and netfilter. A lot of networking people were at a conference last week, busy catching COVID, so relatively short PR. Current release - regressions: - tcp: process the 3rd ACK with sk_socket for TFO and MPTCP Current release - new code bugs: - l2tp: protect session IDR and tunnel session list with one lock, make sure the state is coherent to avoid a warning - eth: bnxt_en: update xdp_rxq_info in queue restart logic - eth: airoha: fix location of the MBI_RX_AGE_SEL_MASK field Previous releases - regressions: - xsk: require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len, the field reuses previously un-validated pad Previous releases - always broken: - tap/tun: drop short frames to prevent crashes later in the stack - eth: ice: add a per-VF limit on number of FDIR filters - af_unix: disable MSG_OOB handling for sockets in sockmap/sockhash" * tag 'net-6.11-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (34 commits) tun: add missing verification for short frame tap: add missing verification for short frame mISDN: Fix a use after free in hfcmulti_tx() gve: Fix an edge case for TSO skb validity check bnxt_en: update xdp_rxq_info in queue restart logic tcp: process the 3rd ACK with sk_socket for TFO/MPTCP selftests/bpf: Add XDP_UMEM_TX_METADATA_LEN to XSK TX metadata test xsk: Require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len bpf: Fix a segment issue when downgrading gso_size net: mediatek: Fix potential NULL pointer dereference in dummy net_device handling MAINTAINERS: make Breno the netconsole maintainer MAINTAINERS: Update bonding entry net: nexthop: Initialize all fields in dumped nexthops net: stmmac: Correct byte order of perfect_match selftests: forwarding: skip if kernel not support setting bridge fdb learning limit tipc: Return non-zero value from tipc_udp_addr2str() on error netfilter: nft_set_pipapo_avx2: disable softinterrupts ice: Fix recipe read procedure ice: Add a per-VF limit on number of FDIR filters net: bonding: correctly annotate RCU in bond_should_notify_peers() ...
2024-07-25Merge tag 'for-netdev' of ↵Jakub Kicinski1-15/+13
https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf Daniel Borkmann says: ==================== pull-request: bpf 2024-07-25 We've added 14 non-merge commits during the last 8 day(s) which contain a total of 19 files changed, 177 insertions(+), 70 deletions(-). The main changes are: 1) Fix af_unix to disable MSG_OOB handling for sockets in BPF sockmap and BPF sockhash. Also add test coverage for this case, from Michal Luczaj. 2) Fix a segmentation issue when downgrading gso_size in the BPF helper bpf_skb_adjust_room(), from Fred Li. 3) Fix a compiler warning in resolve_btfids due to a missing type cast, from Liwei Song. 4) Fix stack allocation for arm64 to align the stack pointer at a 16 byte boundary in the fexit_sleep BPF selftest, from Puranjay Mohan. 5) Fix a xsk regression to require a flag when actuating tx_metadata_len, from Stanislav Fomichev. 6) Fix function prototype BTF dumping in libbpf for prototypes that have no input arguments, from Andrii Nakryiko. 7) Fix stacktrace symbol resolution in perf script for BPF programs containing subprograms, from Hou Tao. * tag 'for-netdev' of https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf: selftests/bpf: Add XDP_UMEM_TX_METADATA_LEN to XSK TX metadata test xsk: Require XDP_UMEM_TX_METADATA_LEN to actuate tx_metadata_len bpf: Fix a segment issue when downgrading gso_size tools/resolve_btfids: Fix comparison of distinct pointer types warning in resolve_btfids bpf, events: Use prog to emit ksymbol event for main program selftests/bpf: Test sockmap redirect for AF_UNIX MSG_OOB selftests/bpf: Parametrize AF_UNIX redir functions to accept send() flags selftests/bpf: Support SOCK_STREAM in unix_inet_redir_to_connected() af_unix: Disable MSG_OOB handling for sockets in sockmap/sockhash bpftool: Fix typo in usage help libbpf: Fix no-args func prototype BTF dumping syntax MAINTAINERS: Update powerpc BPF JIT maintainers MAINTAINERS: Update email address of Naveen selftests/bpf: fexit_sleep: Fix stack allocation for arm64 ==================== Link: https://patch.msgid.link/20240725114312.32197-1-daniel@iogearbox.net Signed-off-by: Jakub Kicinski <kuba@kernel.org>
2024-07-24sysctl: treewide: constify the ctl_table argument of proc_handlersJoel Granados2-3/+3
const qualify the struct ctl_table argument in the proc_handler function signatures. This is a prerequisite to moving the static ctl_table structs into .rodata data which will ensure that proc_handler function pointers cannot be modified. This patch has been generated by the following coccinelle script: ``` virtual patch @r1@ identifier ctl, write, buffer, lenp, ppos; identifier func !~ "appldata_(timer|interval)_handler|sched_(rt|rr)_handler|rds_tcp_skbuf_handler|proc_sctp_do_(hmac_alg|rto_min|rto_max|udp_port|alpha_beta|auth|probe_interval)"; @@ int func( - struct ctl_table *ctl + const struct ctl_table *ctl ,int write, void *buffer, size_t *lenp, loff_t *ppos); @r2@ identifier func, ctl, write, buffer, lenp, ppos; @@ int func( - struct ctl_table *ctl + const struct ctl_table *ctl ,int write, void *buffer, size_t *lenp, loff_t *ppos) { ... } @r3@ identifier func; @@ int func( - struct ctl_table * + const struct ctl_table * ,int , void *, size_t *, loff_t *); @r4@ identifier func, ctl; @@ int func( - struct ctl_table *ctl + const struct ctl_table *ctl ,int , void *, size_t *, loff_t *); @r5@ identifier func, write, buffer, lenp, ppos; @@ int func( - struct ctl_table * + const struct ctl_table * ,int write, void *buffer, size_t *lenp, loff_t *ppos); ``` * Code formatting was adjusted in xfs_sysctl.c to comply with code conventions. The xfs_stats_clear_proc_handler, xfs_panic_mask_proc_handler and xfs_deprecated_dointvec_minmax where adjusted. * The ctl_table argument in proc_watchdog_common was const qualified. This is called from a proc_handler itself and is calling back into another proc_handler, making it necessary to change it as part of the proc_handler migration. Co-developed-by: Thomas Weißschuh <linux@weissschuh.net> Signed-off-by: Thomas Weißschuh <linux@weissschuh.net> Co-developed-by: Joel Granados <j.granados@samsung.com> Signed-off-by: Joel Granados <j.granados@samsung.com>
2024-07-21Merge tag 'mm-nonmm-stable-2024-07-21-15-07' of ↵Linus Torvalds1-14/+15
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Pull non-MM updates from Andrew Morton: - In the series "treewide: Refactor heap related implementation", Kuan-Wei Chiu has significantly reworked the min_heap library code and has taught bcachefs to use the new more generic implementation. - Yury Norov's series "Cleanup cpumask.h inclusion in core headers" reworks the cpumask and nodemask headers to make things generally more rational. - Kuan-Wei Chiu has sent along some maintenance work against our sorting library code in the series "lib/sort: Optimizations and cleanups". - More library maintainance work from Christophe Jaillet in the series "Remove usage of the deprecated ida_simple_xx() API". - Ryusuke Konishi continues with the nilfs2 fixes and clanups in the series "nilfs2: eliminate the call to inode_attach_wb()". - Kuan-Ying Lee has some fixes to the gdb scripts in the series "Fix GDB command error". - Plus the usual shower of singleton patches all over the place. Please see the relevant changelogs for details. * tag 'mm-nonmm-stable-2024-07-21-15-07' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (98 commits) ia64: scrub ia64 from poison.h watchdog/perf: properly initialize the turbo mode timestamp and rearm counter tsacct: replace strncpy() with strscpy() lib/bch.c: use swap() to improve code test_bpf: convert comma to semicolon init/modpost: conditionally check section mismatch to __meminit* init: remove unused __MEMINIT* macros nilfs2: Constify struct kobj_type nilfs2: avoid undefined behavior in nilfs_cnt32_ge macro math: rational: add missing MODULE_DESCRIPTION() macro lib/zlib: add missing MODULE_DESCRIPTION() macro fs: ufs: add MODULE_DESCRIPTION() lib/rbtree.c: fix the example typo ocfs2: add bounds checking to ocfs2_check_dir_entry() fs: add kernel-doc comments to ocfs2_prepare_orphan_dir() coredump: simplify zap_process() selftests/fpu: add missing MODULE_DESCRIPTION() macro compiler.h: simplify data_race() macro build-id: require program headers to be right after ELF header resource: add missing MODULE_DESCRIPTION() ...
2024-07-21Merge tag 'mm-stable-2024-07-21-14-50' of ↵Linus Torvalds2-2/+2
git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Pull MM updates from Andrew Morton: - In the series "mm: Avoid possible overflows in dirty throttling" Jan Kara addresses a couple of issues in the writeback throttling code. These fixes are also targetted at -stable kernels. - Ryusuke Konishi's series "nilfs2: fix potential issues related to reserved inodes" does that. This should actually be in the mm-nonmm-stable tree, along with the many other nilfs2 patches. My bad. - More folio conversions from Kefeng Wang in the series "mm: convert to folio_alloc_mpol()" - Kemeng Shi has sent some cleanups to the writeback code in the series "Add helper functions to remove repeated code and improve readability of cgroup writeback" - Kairui Song has made the swap code a little smaller and a little faster in the series "mm/swap: clean up and optimize swap cache index". - In the series "mm/memory: cleanly support zeropage in vm_insert_page*(), vm_map_pages*() and vmf_insert_mixed()" David Hildenbrand has reworked the rather sketchy handling of the use of the zeropage in MAP_SHARED mappings. I don't see any runtime effects here - more a cleanup/understandability/maintainablity thing. - Dev Jain has improved selftests/mm/va_high_addr_switch.c's handling of higher addresses, for aarch64. The (poorly named) series is "Restructure va_high_addr_switch". - The core TLB handling code gets some cleanups and possible slight optimizations in Bang Li's series "Add update_mmu_tlb_range() to simplify code". - Jane Chu has improved the handling of our fake-an-unrecoverable-memory-error testing feature MADV_HWPOISON in the series "Enhance soft hwpoison handling and injection". - Jeff Johnson has sent a billion patches everywhere to add MODULE_DESCRIPTION() to everything. Some landed in this pull. - In the series "mm: cleanup MIGRATE_SYNC_NO_COPY mode", Kefeng Wang has simplified migration's use of hardware-offload memory copying. - Yosry Ahmed performs more folio API conversions in his series "mm: zswap: trivial folio conversions". - In the series "large folios swap-in: handle refault cases first", Chuanhua Han inches us forward in the handling of large pages in the swap code. This is a cleanup and optimization, working toward the end objective of full support of large folio swapin/out. - In the series "mm,swap: cleanup VMA based swap readahead window calculation", Huang Ying has contributed some cleanups and a possible fixlet to his VMA based swap readahead code. - In the series "add mTHP support for anonymous shmem" Baolin Wang has taught anonymous shmem mappings to use multisize THP. By default this is a no-op - users must opt in vis sysfs controls. Dramatic improvements in pagefault latency are realized. - David Hildenbrand has some cleanups to our remaining use of page_mapcount() in the series "fs/proc: move page_mapcount() to fs/proc/internal.h". - David also has some highmem accounting cleanups in the series "mm/highmem: don't track highmem pages manually". - Build-time fixes and cleanups from John Hubbard in the series "cleanups, fixes, and progress towards avoiding "make headers"". - Cleanups and consolidation of the core pagemap handling from Barry Song in the series "mm: introduce pmd|pte_needs_soft_dirty_wp helpers and utilize them". - Lance Yang's series "Reclaim lazyfree THP without splitting" has reduced the latency of the reclaim of pmd-mapped THPs under fairly common circumstances. A 10x speedup is seen in a microbenchmark. It does this by punting to aother CPU but I guess that's a win unless all CPUs are pegged. - hugetlb_cgroup cleanups from Xiu Jianfeng in the series "mm/hugetlb_cgroup: rework on cftypes". - Miaohe Lin's series "Some cleanups for memory-failure" does just that thing. - Someone other than SeongJae has developed a DAMON feature in Honggyu Kim's series "DAMON based tiered memory management for CXL memory". This adds DAMON features which may be used to help determine the efficiency of our placement of CXL/PCIe attached DRAM. - DAMON user API centralization and simplificatio work in SeongJae Park's series "mm/damon: introduce DAMON parameters online commit function". - In the series "mm: page_type, zsmalloc and page_mapcount_reset()" David Hildenbrand does some maintenance work on zsmalloc - partially modernizing its use of pageframe fields. - Kefeng Wang provides more folio conversions in the series "mm: remove page_maybe_dma_pinned() and page_mkclean()". - More cleanup from David Hildenbrand, this time in the series "mm/memory_hotplug: use PageOffline() instead of PageReserved() for !ZONE_DEVICE". It "enlightens memory hotplug more about PageOffline() pages" and permits the removal of some virtio-mem hacks. - Barry Song's series "mm: clarify folio_add_new_anon_rmap() and __folio_add_anon_rmap()" is a cleanup to the anon folio handling in preparation for mTHP (multisize THP) swapin. - Kefeng Wang's series "mm: improve clear and copy user folio" implements more folio conversions, this time in the area of large folio userspace copying. - The series "Docs/mm/damon/maintaier-profile: document a mailing tool and community meetup series" tells people how to get better involved with other DAMON developers. From SeongJae Park. - A large series ("kmsan: Enable on s390") from Ilya Leoshkevich does that. - David Hildenbrand sends along more cleanups, this time against the migration code. The series is "mm/migrate: move NUMA hinting fault folio isolation + checks under PTL". - Jan Kara has found quite a lot of strangenesses and minor errors in the readahead code. He addresses this in the series "mm: Fix various readahead quirks". - SeongJae Park's series "selftests/damon: test DAMOS tried regions and {min,max}_nr_regions" adds features and addresses errors in DAMON's self testing code. - Gavin Shan has found a userspace-triggerable WARN in the pagecache code. The series "mm/filemap: Limit page cache size to that supported by xarray" addresses this. The series is marked cc:stable. - Chengming Zhou's series "mm/ksm: cmp_and_merge_page() optimizations and cleanup" cleans up and slightly optimizes KSM. - Roman Gushchin has separated the memcg-v1 and memcg-v2 code - lots of code motion. The series (which also makes the memcg-v1 code Kconfigurable) are "mm: memcg: separate legacy cgroup v1 code and put under config option" and "mm: memcg: put cgroup v1-specific memcg data under CONFIG_MEMCG_V1" - Dan Schatzberg's series "Add swappiness argument to memory.reclaim" adds an additional feature to this cgroup-v2 control file. - The series "Userspace controls soft-offline pages" from Jiaqi Yan permits userspace to stop the kernel's automatic treatment of excessive correctable memory errors. In order to permit userspace to monitor and handle this situation. - Kefeng Wang's series "mm: migrate: support poison recover from migrate folio" teaches the kernel to appropriately handle migration from poisoned source folios rather than simply panicing. - SeongJae Park's series "Docs/damon: minor fixups and improvements" does those things. - In the series "mm/zsmalloc: change back to per-size_class lock" Chengming Zhou improves zsmalloc's scalability and memory utilization. - Vivek Kasireddy's series "mm/gup: Introduce memfd_pin_folios() for pinning memfd folios" makes the GUP code use FOLL_PIN rather than bare refcount increments. So these paes can first be moved aside if they reside in the movable zone or a CMA block. - Andrii Nakryiko has added a binary ioctl()-based API to /proc/pid/maps for much faster reading of vma information. The series is "query VMAs from /proc/<pid>/maps". - In the series "mm: introduce per-order mTHP split counters" Lance Yang improves the kernel's presentation of developer information related to multisize THP splitting. - Michael Ellerman has developed the series "Reimplement huge pages without hugepd on powerpc (8xx, e500, book3s/64)". This permits userspace to use all available huge page sizes. - In the series "revert unconditional slab and page allocator fault injection calls" Vlastimil Babka removes a performance-affecting and not very useful feature from slab fault injection. * tag 'mm-stable-2024-07-21-14-50' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (411 commits) mm/mglru: fix ineffective protection calculation mm/zswap: fix a white space issue mm/hugetlb: fix kernel NULL pointer dereference when migrating hugetlb folio mm/hugetlb: fix possible recursive locking detected warning mm/gup: clear the LRU flag of a page before adding to LRU batch mm/numa_balancing: teach mpol_to_str about the balancing mode mm: memcg1: convert charge move flags to unsigned long long alloc_tag: fix page_ext_get/page_ext_put sequence during page splitting lib: reuse page_ext_data() to obtain codetag_ref lib: add missing newline character in the warning message mm/mglru: fix overshooting shrinker memory mm/mglru: fix div-by-zero in vmpressure_calc_level() mm/kmemleak: replace strncpy() with strscpy() mm, page_alloc: put should_fail_alloc_page() back behing CONFIG_FAIL_PAGE_ALLOC mm, slab: put should_failslab() back behind CONFIG_SHOULD_FAILSLAB mm: ignore data-race in __swap_writepage hugetlbfs: ensure generic_hugetlb_get_unmapped_area() returns higher address than mmap_min_addr mm: shmem: rename mTHP shmem counters mm: swap_state: use folio_alloc_mpol() in __read_swap_cache_async() mm/migrate: putback split folios when numa hint migration fails ...
2024-07-19bpf, events: Use prog to emit ksymbol event for main programHou Tao1-15/+13
Since commit 0108a4e9f358 ("bpf: ensure main program has an extable"), prog->aux->func[0]->kallsyms is left as uninitialized. For BPF programs with subprogs, the symbol for the main program is missing just as shown in the output of perf script below: ffffffff81284b69 qp_trie_lookup_elem+0xb9 ([kernel.kallsyms]) ffffffffc0011125 bpf_prog_a4a0eb0651e6af8b_lookup_qp_trie+0x5d (bpf...) ffffffff8127bc2b bpf_for_each_array_elem+0x7b ([kernel.kallsyms]) ffffffffc00110a1 +0x25 () ffffffff8121a89a trace_call_bpf+0xca ([kernel.kallsyms]) Fix it by always using prog instead prog->aux->func[0] to emit ksymbol event for the main program. After the fix, the output of perf script will be correct: ffffffff81284b96 qp_trie_lookup_elem+0xe6 ([kernel.kallsyms]) ffffffffc001382d bpf_prog_a4a0eb0651e6af8b_lookup_qp_trie+0x5d (bpf...) ffffffff8127bc2b bpf_for_each_array_elem+0x7b ([kernel.kallsyms]) ffffffffc0013779 bpf_prog_245c55ab25cfcf40_qp_trie_lookup+0x25 (bpf...) ffffffff8121a89a trace_call_bpf+0xca ([kernel.kallsyms]) Fixes: 0108a4e9f358 ("bpf: ensure main program has an extable") Signed-off-by: Hou Tao <houtao1@huawei.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net> Tested-by: Yonghong Song <yonghong.song@linux.dev> Reviewed-by: Krister Johansen <kjlx@templeofstupid.com> Reviewed-by: Jiri Olsa <jolsa@kernel.org> Link: https://lore.kernel.org/bpf/20240714065533.1112616-1-houtao@huaweicloud.com
2024-07-18Merge tag 'probes-v6.11' of ↵Linus Torvalds2-8/+68
git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace Pull probes updates from Masami Hiramatsu: "Uprobes: - x86/shstk: Make return uprobe work with shadow stack - Add uretprobe syscall which speeds up the uretprobe 10-30% faster. This syscall is automatically used from user-space trampolines which are generated by the uretprobe. If this syscall is used by normal user program, it will cause SIGILL. Note that this is currently only implemented on x86_64. (This also has two fixes for adjusting the syscall number to avoid conflict with new *attrat syscalls.) - uprobes/perf: fix user stack traces in the presence of pending uretprobe. This corrects the uretprobe's trampoline address in the stacktrace with correct return address - selftests/x86: Add a return uprobe with shadow stack test - selftests/bpf: Add uretprobe syscall related tests. - test case for register integrity check - test case with register changing case - test case for uretprobe syscall without uprobes (expected to fail) - test case for uretprobe with shadow stack - selftests/bpf: add test validating uprobe/uretprobe stack traces - MAINTAINERS: Add uprobes entry. This does not specify the tree but to clarify who maintains and reviews the uprobes Kprobes: - tracing/kprobes: Test case cleanups. Replace redundant WARN_ON_ONCE() + pr_warn() with WARN_ONCE() and remove unnecessary code from selftest - tracing/kprobes: Add symbol counting check when module loads. This checks the uniqueness of the probed symbol on modules. The same check has already done for kernel symbols (This also has a fix for build error with CONFIG_MODULES=n) Cleanup: - Add MODULE_DESCRIPTION() macros for fprobe and kprobe examples" * tag 'probes-v6.11' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: MAINTAINERS: Add uprobes entry selftests/bpf: Change uretprobe syscall number in uprobe_syscall test uprobe: Change uretprobe syscall scope and number tracing/kprobes: Fix build error when find_module() is not available tracing/kprobes: Add symbol counting check when module loads selftests/bpf: add test validating uprobe/uretprobe stack traces perf,uprobes: fix user stack traces in the presence of pending uretprobes tracing/kprobe: Remove cleanup code unrelated to selftest tracing/kprobe: Integrate test warnings into WARN_ONCE selftests/bpf: Add uretprobe shadow stack test selftests/bpf: Add uretprobe syscall call from user space test selftests/bpf: Add uretprobe syscall test for regs changes selftests/bpf: Add uretprobe syscall test for regs integrity selftests/x86: Add return uprobe shadow stack test uprobe: Add uretprobe syscall to speed up return probe uprobe: Wire up uretprobe system call x86/shstk: Make return uprobe work with shadow stack samples: kprobes: add missing MODULE_DESCRIPTION() macros fprobe: add missing MODULE_DESCRIPTION() macro
2024-07-16Merge tag 'perf-core-2024-07-16' of ↵Linus Torvalds4-55/+85
git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull performance events updates from Ingo Molnar: - Intel PT support enhancements & fixes - Fix leaked SIGTRAP events - Improve and fix the Intel uncore driver - Add support for Intel HBM and CXL uncore counters - Add Intel Lake and Arrow Lake support - AMD uncore driver fixes - Make SIGTRAP and __perf_pending_irq() work on RT - Micro-optimizations - Misc cleanups and fixes * tag 'perf-core-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits) perf/x86/intel: Add a distinct name for Granite Rapids perf/x86/intel/ds: Fix non 0 retire latency on Raptorlake perf/x86/intel: Hide Topdown metrics events if the feature is not enumerated perf/x86/intel/uncore: Fix the bits of the CHA extended umask for SPR perf: Split __perf_pending_irq() out of perf_pending_irq() perf: Don't disable preemption in perf_pending_task(). perf: Move swevent_htable::recursion into task_struct. perf: Shrink the size of the recursion counter. perf: Enqueue SIGTRAP always via task_work. task_work: Add TWA_NMI_CURRENT as an additional notify mode. perf: Move irq_work_queue() where the event is prepared. perf: Fix event leak upon exec and file release perf: Fix event leak upon exit task_work: Introduce task_work_cancel() again task_work: s/task_work_cancel()/task_work_cancel_func()/ perf/x86/amd/uncore: Fix DF and UMC domain identification perf/x86/amd/uncore: Avoid PMU registration if counters are unavailable perf/x86/intel: Support Perfmon MSRs aliasing perf/x86/intel: Support PERFEVTSEL extension perf/x86: Add config_mask to represent EVENTSEL bitmask ...
2024-07-12mm: define __pte_leaf_size() to also take a PMD entryChristophe Leroy1-1/+1
On powerpc 8xx, when a page is 8M size, the information is in the PMD entry. So allow architectures to provide __pte_leaf_size() instead of pte_leaf_size() and provide the PMD entry to that function. When __pte_leaf_size() is not defined, define it as a pte_leaf_size() so that architectures not interested in the PMD arguments are not impacted. Only define a default pte_leaf_size() when __pte_leaf_size() is not defined to make sure nobody adds new calls to pte_leaf_size() in the core. Link: https://lkml.kernel.org/r/c7c008f0a314bf8029ad7288fdc908db1ec7e449.1719928057.git.christophe.leroy@csgroup.eu Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Jason Gunthorpe <jgg@nvidia.com> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Peter Xu <peterx@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-07-09perf: Split __perf_pending_irq() out of perf_pending_irq()Sebastian Andrzej Siewior1-7/+22
perf_pending_irq() invokes perf_event_wakeup() and __perf_pending_irq(). The former is in charge of waking any tasks which waits to be woken up while the latter disables perf-events. The irq_work perf_pending_irq(), while this an irq_work, the callback is invoked in thread context on PREEMPT_RT. This is needed because all the waking functions (wake_up_all(), kill_fasync()) acquire sleep locks which must not be used with disabled interrupts. Disabling events, as done by __perf_pending_irq(), expects a hardirq context and disabled interrupts. This requirement is not fulfilled on PREEMPT_RT. Split functionality based on perf_event::pending_disable into irq_work named `pending_disable_irq' and invoke it in hardirq context on PREEMPT_RT. Rename the split out callback to perf_pending_disable(). Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Marco Elver <elver@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: https://lore.kernel.org/r/20240704170424.1466941-8-bigeasy@linutronix.de
2024-07-09perf: Don't disable preemption in perf_pending_task().Sebastian Andrzej Siewior1-6/+5
perf_pending_task() is invoked in task context and disables preemption because perf_swevent_get_recursion_context() used to access per-CPU variables. The other reason is to create a RCU read section while accessing the perf_event. The recursion counter is no longer a per-CPU accounter so disabling preemption is no longer required. The RCU section is needed and must be created explicit. Replace the preemption-disable section with a explicit RCU-read section. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Marco Elver <elver@google.com> Link: https://lore.kernel.org/r/20240704170424.1466941-7-bigeasy@linutronix.de
2024-07-09perf: Move swevent_htable::recursion into task_struct.Sebastian Andrzej Siewior2-11/+4
The swevent_htable::recursion counter is used to avoid creating an swevent while an event is processed to avoid recursion. The counter is per-CPU and preemption must be disabled to have a stable counter. perf_pending_task() disables preemption to access the counter and then signal. This is problematic on PREEMPT_RT because sending a signal uses a spinlock_t which must not be acquired in atomic on PREEMPT_RT because it becomes a sleeping lock. The atomic context can be avoided by moving the counter into the task_struct. There is a 4 byte hole between futex_state (usually always on) and the following perf pointer (perf_event_ctxp). After the recursion lost some weight it fits perfectly. Move swevent_htable::recursion into task_struct. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Marco Elver <elver@google.com> Link: https://lore.kernel.org/r/20240704170424.1466941-6-bigeasy@linutronix.de
2024-07-09perf: Shrink the size of the recursion counter.Sebastian Andrzej Siewior3-4/+4
There are four recursion counter, one for each context. The type of the counter is `int' but the counter is used as `bool' since it is only incremented if zero. The main goal here is to shrink the whole struct into 32bit int which can later be added task_struct into an existing hole. Reduce the type of the recursion counter to an unsigned char, keep the increment/ decrement operation. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Marco Elver <elver@google.com> Link: https://lore.kernel.org/r/20240704170424.1466941-5-bigeasy@linutronix.de
2024-07-09perf: Enqueue SIGTRAP always via task_work.Sebastian Andrzej Siewior1-21/+10
A signal is delivered by raising irq_work() which works from any context including NMI. irq_work() can be delayed if the architecture does not provide an interrupt vector. In order not to lose a signal, the signal is injected via task_work during event_sched_out(). Instead going via irq_work, the signal could be added directly via task_work. The signal is sent to current and can be enqueued on its return path to userland. Queue signal via task_work and consider possible NMI context. Remove perf_event::pending_sigtrap and and use perf_event::pending_work instead. Reported-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Marco Elver <elver@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: https://lore.kernel.org/r/20240704170424.1466941-4-bigeasy@linutronix.de
2024-07-09perf: Move irq_work_queue() where the event is prepared.Sebastian Andrzej Siewior1-5/+5
Only if perf_event::pending_sigtrap is zero, the irq_work accounted by increminging perf_event::nr_pending. The member perf_event::pending_addr might be overwritten by a subsequent event if the signal was not yet delivered and is expected. The irq_work will not be enqeueued again because it has a check to be only enqueued once. Move irq_work_queue() to where the counter is incremented and perf_event::pending_sigtrap is set to make it more obvious that the irq_work is scheduled once. Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Tested-by: Marco Elver <elver@google.com> Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com> Link: https://lore.kernel.org/r/20240704170424.1466941-2-bigeasy@linutronix.de
2024-07-09perf: Fix event leak upon exec and file releaseFrederic Weisbecker1-4/+34
The perf pending task work is never waited upon the matching event release. In the case of a child event, released via free_event() directly, this can potentially result in a leaked event, such as in the following scenario that doesn't even require a weak IRQ work implementation to trigger: schedule() prepare_task_switch() =======> <NMI> perf_event_overflow() event->pending_sigtrap = ... irq_work_queue(&event->pending_irq) <======= </NMI> perf_event_task_sched_out() event_sched_out() event->pending_sigtrap = 0; atomic_long_inc_not_zero(&event->refcount) task_work_add(&event->pending_task) finish_lock_switch() =======> <IRQ> perf_pending_irq() //do nothing, rely on pending task work <======= </IRQ> begin_new_exec() perf_event_exit_task() perf_event_exit_event() // If is child event free_event() WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1) // event is leaked Similar scenarios can also happen with perf_event_remove_on_exec() or simply against concurrent perf_event_release(). Fix this with synchonizing against the possibly remaining pending task work while freeing the event, just like is done with remaining pending IRQ work. This means that the pending task callback neither need nor should hold a reference to the event, preventing it from ever beeing freed. Fixes: 517e6a301f34 ("perf: Fix perf_pending_task() UaF") Signed-off-by: Frederic Weisbecker <frederic@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240621091601.18227-5-frederic@kernel.org
2024-07-09perf: Fix event leak upon exitFrederic Weisbecker1-8/+5
When a task is scheduled out, pending sigtrap deliveries are deferred to the target task upon resume to userspace via task_work. However failures while adding an event's callback to the task_work engine are ignored. And since the last call for events exit happen after task work is eventually closed, there is a small window during which pending sigtrap can be queued though ignored, leaking the event refcount addition such as in the following scenario: TASK A ----- do_exit() exit_task_work(tsk); <IRQ> perf_event_overflow() event->pending_sigtrap = pending_id; irq_work_queue(&event->pending_irq); </IRQ> =========> PREEMPTION: TASK A -> TASK B event_sched_out() event->pending_sigtrap = 0; atomic_long_inc_not_zero(&event->refcount) // FAILS: task work has exited task_work_add(&event->pending_task) [...] <IRQ WORK> perf_pending_irq() // early return: event->oncpu = -1 </IRQ WORK> [...] =========> TASK B -> TASK A perf_event_exit_task(tsk) perf_event_exit_event() free_event() WARN(atomic_long_cmpxchg(&event->refcount, 1, 0) != 1) // leak event due to unexpected refcount == 2 As a result the event is never released while the task exits. Fix this with appropriate task_work_add()'s error handling. Fixes: 517e6a301f34 ("perf: Fix perf_pending_task() UaF") Signed-off-by: Frederic Weisbecker <frederic@kernel.org> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/20240621091601.18227-4-frederic@kernel.org
2024-07-04Merge branch 'tip/x86/cpu'Peter Zijlstra2-16/+16
The Lunarlake patches rely on the new VFM stuff. Signed-off-by: Peter Zijlstra <peterz@infradead.org>
2024-07-04perf: Make rb_alloc_aux() return an error immediately if nr_pages <= 0Adrian Hunter1-0/+3
rb_alloc_aux() should not be called with nr_pages <= 0. Make it more robust and readable by returning an error immediately in that case. Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20240624201101.60186-8-adrian.hunter@intel.com
2024-07-04perf: Fix default aux_watermark calculationAdrian Hunter1-1/+3
The default aux_watermark is half the AUX area buffer size. In general, on a 64-bit architecture, the AUX area buffer size could be a bigger than fits in a 32-bit type, but the calculation does not allow for that possibility. However the aux_watermark value is recorded in a u32, so should not be more than U32_MAX either. Fix by doing the calculation in a correctly sized type, and limiting the result to U32_MAX. Fixes: d68e6799a5c8 ("perf: Cap allocation order at aux_watermark") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20240624201101.60186-7-adrian.hunter@intel.com
2024-07-04perf: Prevent passing zero nr_pages to rb_alloc_aux()Adrian Hunter1-0/+2
nr_pages is unsigned long but gets passed to rb_alloc_aux() as an int, and is stored as an int. Only power-of-2 values are accepted, so if nr_pages is a 64_bit value, it will be passed to rb_alloc_aux() as zero. That is not ideal because: 1. the value is incorrect 2. rb_alloc_aux() is at risk of misbehaving, although it manages to return -ENOMEM in that case, it is a result of passing zero to get_order() even though the get_order() result is documented to be undefined in that case. Fix by simply validating the maximum supported value in the first place. Use -ENOMEM error code for consistency with the current error code that is returned in that case. Fixes: 45bfb2e50471 ("perf: Add AUX area to ring buffer for raw data streams") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20240624201101.60186-6-adrian.hunter@intel.com
2024-07-04perf: Fix perf_aux_size() for greater-than 32-bit sizeAdrian Hunter1-1/+1
perf_buffer->aux_nr_pages uses a 32-bit type, so a cast is needed to calculate a 64-bit size. Fixes: 45bfb2e50471 ("perf: Add AUX area to ring buffer for raw data streams") Signed-off-by: Adrian Hunter <adrian.hunter@intel.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lore.kernel.org/r/20240624201101.60186-5-adrian.hunter@intel.com
2024-07-03mm: extend rmap flags arguments for folio_add_new_anon_rmapBarry Song1-1/+1
Patch series "mm: clarify folio_add_new_anon_rmap() and __folio_add_anon_rmap()", v2. This patchset is preparatory work for mTHP swapin. folio_add_new_anon_rmap() assumes that new anon rmaps are always exclusive. However, this assumption doesn’t hold true for cases like do_swap_page(), where a new anon might be added to the swapcache and is not necessarily exclusive. The patchset extends the rmap flags to allow folio_add_new_anon_rmap() to handle both exclusive and non-exclusive new anon folios. The do_swap_page() function is updated to use this extended API with rmap flags. Consequently, all new anon folios now consistently use folio_add_new_anon_rmap(). The special case for !folio_test_anon() in __folio_add_anon_rmap() can be safely removed. In conclusion, new anon folios always use folio_add_new_anon_rmap(), regardless of exclusivity. Old anon folios continue to use __folio_add_anon_rmap() via folio_add_anon_rmap_pmd() and folio_add_anon_rmap_ptes(). This patch (of 3): In the case of a swap-in, a new anonymous folio is not necessarily exclusive. This patch updates the rmap flags to allow a new anonymous folio to be treated as either exclusive or non-exclusive. To maintain the existing behavior, we always use EXCLUSIVE as the default setting. [akpm@linux-foundation.org: cleanup and constifications per David and akpm] [v-songbaohua@oppo.com: fix missing doc for flags of folio_add_new_anon_rmap()] Link: https://lkml.kernel.org/r/20240619210641.62542-1-21cnbao@gmail.com [v-songbaohua@oppo.com: enhance doc for extend rmap flags arguments for folio_add_new_anon_rmap] Link: https://lkml.kernel.org/r/20240622030256.43775-1-21cnbao@gmail.com Link: https://lkml.kernel.org/r/20240617231137.80726-1-21cnbao@gmail.com Link: https://lkml.kernel.org/r/20240617231137.80726-2-21cnbao@gmail.com Signed-off-by: Barry Song <v-songbaohua@oppo.com> Suggested-by: David Hildenbrand <david@redhat.com> Tested-by: Shuai Yuan <yuanshuai@oppo.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Baolin Wang <baolin.wang@linux.alibaba.com> Cc: Chris Li <chrisl@kernel.org> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Ryan Roberts <ryan.roberts@arm.com> Cc: Suren Baghdasaryan <surenb@google.com> Cc: Yang Shi <shy828301@gmail.com> Cc: Yosry Ahmed <yosryahmed@google.com> Cc: Yu Zhao <yuzhao@google.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-06-24lib min_heap: rename min_heapify() to min_heap_sift_down()Kuan-Wei Chiu1-1/+1
After adding min_heap_sift_up(), the naming convention has been adjusted to maintain consistency with the min_heap_sift_up(). Consequently, min_heapify() has been renamed to min_heap_sift_down(). Link: https://lkml.kernel.org/CAP-5=fVcBAxt8Mw72=NCJPRJfjDaJcqk4rjbadgouAEAHz_q1A@mail.gmail.com Link: https://lkml.kernel.org/r/20240524152958.919343-13-visitorckw@gmail.com Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com> Reviewed-by: Ian Rogers <irogers@google.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: Bagas Sanjaya <bagasdotme@gmail.com> Cc: Brian Foster <bfoster@redhat.com> Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw> Cc: Coly Li <colyli@suse.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kent Overstreet <kent.overstreet@linux.dev> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Sakai <msakai@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
2024-06-24lib min_heap: add args for min_heap_callbacksKuan-Wei Chiu1-5/+5
Add a third parameter 'args' for the 'less' and 'swp' functions in the 'struct min_heap_callbacks'. This additional parameter allows these comparison and swap functions to handle extra arguments when necessary. Link: https://lkml.kernel.org/r/20240524152958.919343-9-visitorckw@gmail.com Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com> Reviewed-by: Ian Rogers <irogers@google.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: Bagas Sanjaya <bagasdotme@gmail.com> Cc: Brian Foster <bfoster@redhat.com> Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw> Cc: Coly Li <colyli@suse.de> Cc: Ingo Molnar <mingo@redhat.com> Cc: Jiri Olsa <jolsa@kernel.org> Cc: Kent Overstreet <kent.overstreet@linux.dev> Cc: Mark Rutland <mark.rutland@arm.com> Cc: Matthew Sakai <msakai@redhat.com> Cc: Namhyung Kim <namhyung@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Randy Dunlap <rdunlap@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>