From 94b83ff0c0a69e42f403b59918529fbca2a89daf Mon Sep 17 00:00:00 2001 From: Fuad Tabba Date: Mon, 13 Jul 2026 08:28:23 +0100 Subject: [PATCH 01/11] tracing/remotes: Fix page_va[] access before counter update in trace_remote_alloc_buffer() page_va[] is annotated __counted_by(nr_page_va), so nr_page_va must cover an index before that element is accessed. The allocation loop writes page_va[id] while nr_page_va is still id and increments it only afterwards, so every write is one element past the declared count. The store is out of bounds with respect to the annotation: a build with CONFIG_UBSAN_BOUNDS on a toolchain that honours __counted_by (clang >= 20.1, gcc >= 15.1) flags it as an array-index overflow. Increment nr_page_va before writing the element it now covers. A failed allocation then leaves the slot counted but NULL; the error path frees it with free_page(0), which is a no-op. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260713072823.2668323-1-fuad.tabba@linux.dev Fixes: 96e43537af546 ("tracing: Introduce trace remotes") Signed-off-by: Fuad Tabba Reviewed-by: Vincent Donnefort Tested-by: Vincent Donnefort Signed-off-by: Steven Rostedt --- kernel/trace/trace_remote.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c index 0f6ef5c36d84..ef42d9c38b37 100644 --- a/kernel/trace/trace_remote.c +++ b/kernel/trace/trace_remote.c @@ -1004,11 +1004,10 @@ int trace_remote_alloc_buffer(struct trace_buffer_desc *desc, size_t desc_size, desc->nr_cpus++; for (id = 0; id < nr_pages; id++) { + rb_desc->nr_page_va++; rb_desc->page_va[id] = (unsigned long)__get_free_page(GFP_KERNEL); if (!rb_desc->page_va[id]) goto err; - - rb_desc->nr_page_va++; } rb_desc = __next_ring_buffer_desc(rb_desc); } From 655111f878a455f724e20122929cf2afa52b76e4 Mon Sep 17 00:00:00 2001 From: Jackie Liu Date: Wed, 15 Jul 2026 15:44:55 +0800 Subject: [PATCH 02/11] tracing: Propagate errors from remote event bulk updates remote_events_dir_enable_write() ignores the return value from trace_remote_enable_event(). If a remote rejects an event state change, the write therefore reports success even though the affected event remains in its previous state. Keep trying all events, but retain and return the first error. This matches __ftrace_set_clr_event_nolock(), which permits partial updates while notifying userspace when an operation fails. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260715074455.3897-1-liu.yun@linux.dev Fixes: 775cb093bc50 ("tracing: Add events/ root files to trace remotes") Assisted-by: Codex:gpt-5.6-sol Signed-off-by: Jackie Liu Reviewed-by: Vincent Donnefort Signed-off-by: Steven Rostedt --- kernel/trace/trace_remote.c | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c index ef42d9c38b37..e6724f947170 100644 --- a/kernel/trace/trace_remote.c +++ b/kernel/trace/trace_remote.c @@ -1149,10 +1149,21 @@ static ssize_t remote_events_dir_enable_write(struct file *filp, const char __us for (i = 0; i < remote->nr_events; i++) { struct remote_event *evt = &remote->events[i]; + int eret; - trace_remote_enable_event(remote, evt, enable); + eret = trace_remote_enable_event(remote, evt, enable); + /* + * Save the first error and return that. Some events + * may still have been enabled, but let the user + * know that something went wrong. + */ + if (!ret && eret) + ret = eret; } + if (ret) + return ret; + return count; } From c1d87e724ae55e781b7cc7ccafb34d9e668582b2 Mon Sep 17 00:00:00 2001 From: deepakraog Date: Wed, 15 Jul 2026 20:06:04 +0530 Subject: [PATCH 03/11] tracing: Fix resource leak on mmiotrace trace_pipe close The mmiotrace tracer was added May 12th 2008. At that time, resources created in pipe_open() could not be freed because there was not pipe_close function pointer of the tracer. The pipe_close function pointer was added in December 7th, 2009, but the mmiotrace tracer was not updated. mmio_pipe_open() allocates a header_iter and takes a pci_dev reference when trace_pipe is opened. mmio_close() frees them, but it was only wired to the tracer's .close callback. tracing_release_pipe() invokes .pipe_close, not .close, when the trace_pipe file is released. As a result, closing trace_pipe with the mmiotrace tracer active leaked the header_iter allocation and left a stale pci_dev reference. Set .pipe_close to mmio_close, matching how function_graph wires both callbacks to the same handler. Note, if the trace_pipe is read to completion, it will clean up the resources, but if one were to run: # head -n 1 /sys/kernel/tracing/trace_pipe VERSION 20070824 Over and over again, it would trigger a massive leak. Cc: stable@vger.kernel.org Fixes: c521efd1700a8 ("tracing: Add pipe_close interface) Link: https://patch.msgid.link/20260715143604.14481-1-gaikwad.dcg@gmail.com Signed-off-by: deepakraog Signed-off-by: Steven Rostedt --- kernel/trace/trace_mmiotrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 226cf66e0d68..20812e7f911f 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -109,7 +109,6 @@ static void mmio_pipe_open(struct trace_iterator *iter) iter->private = hiter; } -/* XXX: This is not called when the pipe is closed! */ static void mmio_close(struct trace_iterator *iter) { struct header_iter *hiter = iter->private; @@ -279,6 +278,7 @@ static struct tracer mmio_tracer __read_mostly = .start = mmio_trace_start, .pipe_open = mmio_pipe_open, .close = mmio_close, + .pipe_close = mmio_close, .read = mmio_read, .print_line = mmio_print_line, .noboot = true, From 144f29e85702234b23d2a62abf723e6a17eb5427 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Tue, 21 Jul 2026 21:11:43 -0400 Subject: [PATCH 04/11] tracing: Fix mmiotrace possible NULL dereferencing of hiter->dev If the mmio_pipe_open() fails to find a PCI device, the hiter->dev will be assigned to NULL. The mmiotrace read() function dereferences the hiter->dev if hiter exists. Change the test of the read to not only check hiter being NULL, but also the hiter->dev before dereferencing it. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260721211143.36dbd559@gandalf.local.home Fixes: f984b51e0779 ("ftrace: add mmiotrace plugin") Reported-by: Sashiko Link: https://sashiko.dev/#/patchset/20260715143604.14481-1-gaikwad.dcg%40gmail.com Signed-off-by: Steven Rostedt --- kernel/trace/trace_mmiotrace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace_mmiotrace.c b/kernel/trace/trace_mmiotrace.c index 20812e7f911f..b88b8d9923ad 100644 --- a/kernel/trace/trace_mmiotrace.c +++ b/kernel/trace/trace_mmiotrace.c @@ -145,7 +145,7 @@ static ssize_t mmio_read(struct trace_iterator *iter, struct file *filp, goto print_out; } - if (!hiter) + if (!hiter || !hiter->dev) return 0; mmio_print_pcidev(s, hiter->dev); From b4eb07bde606c2096b24252be589e735eff6d413 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 17 Jul 2026 11:51:49 +0900 Subject: [PATCH 05/11] tracing: Fix union collision of module and refcnt for dynamic events In 'struct trace_event_call', the 'module' pointer and the 'refcnt' atomic variable share the same memory space in a union. For dynamic events, the union member is 'refcnt', which acts as an active reference counter. When a dynamic event (such as kprobe, uprobe, fprobe, eprobe, or wprobe) has a non-zero reference count (e.g. due to active event triggers or perf attachments), its 'call->module' evaluates to a small non-zero integer instead of NULL. When filtering or setting events for a specific module (e.g., writing ':mod:' to 'set_event'), the code in '__ftrace_set_clr_event_nolock()' and 'update_event_fields()' reads 'call->module' directly without checking whether the event is dynamic. This causes the kernel to treat the small integer (refcnt) as a 'struct module' pointer, leading to a NULL/invalid pointer dereference (Oops) when dereferencing the module name. Fix this by ensuring that the 'TRACE_EVENT_FL_DYNAMIC' flag is checked before treating 'call->module' as a valid pointer in these code paths. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/178425670947.84440.11344393611899824907.stgit@devnote2 Fixes: 4c86bc531e60 ("tracing: Add :mod: command to enabled module events") Assisted-by: Antigravity:gemini-3.5-flash Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt --- kernel/trace/trace_events.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-) diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index c46e623e7e0d..956692856fa8 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1350,7 +1350,9 @@ __ftrace_set_clr_event_nolock(struct trace_array *tr, const char *match, call = file->event_call; /* If a module is specified, skip events that are not that module */ - if (module && (!call->module || strcmp(module_name(call->module), module))) + if (module && + ((call->flags & TRACE_EVENT_FL_DYNAMIC) || + !call->module || strcmp(module_name(call->module), module))) continue; name = trace_event_name(call); From 1a087033a6bad73b4140020b40e819b0933aafc3 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Fri, 17 Jul 2026 11:51:59 +0900 Subject: [PATCH 06/11] selftests/ftrace: Reset triggers at top level before instance loop When running instance tests, 'ftracetest' creates a new ftrace instance and runs the tests inside it. Before starting each test, it executes 'initialize_system()' to reset the ftrace state to initial-state. However, since 'initialize_system()' is executed in the context of the instance directory, it only cleans up triggers and filters of that instance. Any triggers or dynamic events left behind in the top-level instance by previous failed top-level tests, are left completely untouched. These top-level leftovers can cause subsequent instance-based tests to fail or even crash the kernel. Fix this by executing 'initialize_system()' in the top-level tracing directory once before entering the instance loop. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/178425671889.84440.9477850701738666404.stgit@devnote2 Fixes: b5b77be812de ("selftests: ftrace: Allow some tests to be run in a tracing instance") Assisted-by: Antigravity:gemini-3.5-flash Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt --- tools/testing/selftests/ftrace/ftracetest | 1 + 1 file changed, 1 insertion(+) diff --git a/tools/testing/selftests/ftrace/ftracetest b/tools/testing/selftests/ftrace/ftracetest index 0a56bf209f6c..8ad2c385407e 100755 --- a/tools/testing/selftests/ftrace/ftracetest +++ b/tools/testing/selftests/ftrace/ftracetest @@ -503,6 +503,7 @@ for t in $TEST_CASES; do done # Test on instance loop +(cd $TRACING_DIR; initialize_system) INSTANCE=" (instance) " for t in $TEST_CASES; do test_on_instance $t || continue From 8f76afb9b114bee1c1251e0e52553e9dc7c59f20 Mon Sep 17 00:00:00 2001 From: Usama Arif Date: Fri, 17 Jul 2026 10:32:52 -0700 Subject: [PATCH 07/11] tracing: Fix context switch counter truncation trace_user_fault_read() samples nr_context_switches_cpu() before enabling preemption and retries the user copy if the counter changes. The helper returns unsigned long long because rq->nr_switches is u64, but the saved value is unsigned int. Once a CPU has performed 2^32 context switches, assigning the counter to cnt discards its upper bits. The comparison after the copy promotes cnt back to unsigned long long, but the lost bits remain zero, so it reports a change even when the task was never scheduled out. Every retry then fails the same way until the 100-try guard warns and the user copy is abandoned. This affects long-running systems and workloads with high context-switch rates. A CPU switching 1,000 times per second takes about 50 days. Store the sampled count in unsigned long long so the full value is preserved. Cc: stable@vger.kernel.org Fixes: 64cf7d058a00 ("tracing: Have trace_marker use per-cpu data to read user space") Link: https://patch.msgid.link/20260717173252.3431565-1-usama.arif@linux.dev Reported-by: Breno Leitao Signed-off-by: Usama Arif Acked-by: Masami Hiramatsu (Google) Reviewed-by: Breno Leitao Signed-off-by: Steven Rostedt --- kernel/trace/trace.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index 18710c190c92..01a5e87af299 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6187,7 +6187,7 @@ char *trace_user_fault_read(struct trace_user_buf_info *tinfo, { int cpu = smp_processor_id(); char *buffer = per_cpu_ptr(tinfo->tbuf, cpu)->buf; - unsigned int cnt; + unsigned long long cnt; int trys = 0; int ret; From 79097812153b826fc156a2930ec8a90ed9edf4a2 Mon Sep 17 00:00:00 2001 From: David Carlier Date: Fri, 24 Jul 2026 04:05:17 +0100 Subject: [PATCH 08/11] tracing: Fix use-after-free freeing trigger private data Commit 61d445af0a7c ("tracing: Add bulk garbage collection of freeing event_trigger_data") moved the kfree() of event_trigger_data to a kthread that runs tracepoint_synchronize_unregister() before freeing. That removed the synchronization the trigger .free callbacks used to get implicitly and inline from trigger_data_free(). event_hist_trigger_free(), event_hist_trigger_named_free() and event_enable_trigger_free() free their satellite data (hist_data, cmd_ops, enable_data) right after trigger_data_free() returns. With the synchronization now deferred to the kthread, a concurrent tracepoint handler can still reach that data through the list_del_rcu()'d trigger, causing a use-after-free. The histogram teardown must stay synchronous: remove_hist_vars() and unregister_field_var_hists() have to detach a synthetic event from the histogram before the trigger-removal write returns, otherwise a following command races in and the synthetic-event removal fails with -EBUSY, as the trigger-synthetic-eprobe.tc selftest catches. Make those callbacks wait with the correct barrier - tracepoint_synchronize_unregister(), matching the free kthread - before freeing. The enable trigger has no such synchronous requirement, and a blocking synchronize there would re-serialize the path that commit deliberately deferred. Give it an optional private_data_free() callback that the free kthread runs after its grace period, and free enable_data from there. Link: https://patch.msgid.link/20260724030523.19081-1-devnexen@gmail.com Suggested-by: Masami Hiramatsu (Google) Suggested-by: Steven Rostedt Fixes: 61d445af0a7c ("tracing: Add bulk garbage collection of freeing event_trigger_data") Signed-off-by: David Carlier Signed-off-by: Steven Rostedt --- kernel/trace/trace.h | 1 + kernel/trace/trace_events_hist.c | 2 ++ kernel/trace/trace_events_trigger.c | 18 +++++++++++++++--- 3 files changed, 18 insertions(+), 3 deletions(-) diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h index 80fe152af1dd..bf77331f56a4 100644 --- a/kernel/trace/trace.h +++ b/kernel/trace/trace.h @@ -1941,6 +1941,7 @@ struct event_trigger_data { struct list_head named_list; struct event_trigger_data *named_data; struct llist_node llist; + void (*private_data_free)(struct event_trigger_data *data); }; /* Avoid typos */ diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c index 82ce492ab268..58d28cd1afa3 100644 --- a/kernel/trace/trace_events_hist.c +++ b/kernel/trace/trace_events_hist.c @@ -6349,6 +6349,7 @@ static void event_hist_trigger_free(struct event_trigger_data *data) trigger_data_free(data); + tracepoint_synchronize_unregister(); remove_hist_vars(hist_data); unregister_field_var_hists(hist_data); @@ -6388,6 +6389,7 @@ static void event_hist_trigger_named_free(struct event_trigger_data *data) del_named_trigger(data); trigger_data_free(data); + tracepoint_synchronize_unregister(); kfree(cmd_ops); } } diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 655db2e82513..46e60b70a4bb 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -38,6 +38,13 @@ static void trigger_create_kthread_locked(void) } } +static void trigger_data_free_one(struct event_trigger_data *data) +{ + if (data->private_data_free) + data->private_data_free(data); + kfree(data); +} + static void trigger_data_free_queued_locked(void) { struct event_trigger_data *data, *tmp; @@ -52,7 +59,7 @@ static void trigger_data_free_queued_locked(void) tracepoint_synchronize_unregister(); llist_for_each_entry_safe(data, tmp, llnodes, llist) - kfree(data); + trigger_data_free_one(data); } /* Bulk garbage collection of event_trigger_data elements */ @@ -75,7 +82,7 @@ static int trigger_kthread_fn(void *ignore) tracepoint_synchronize_unregister(); llist_for_each_entry_safe(data, tmp, llnodes, llist) - kfree(data); + trigger_data_free_one(data); } return 0; @@ -1717,6 +1724,11 @@ int event_enable_trigger_print(struct seq_file *m, return 0; } +static void enable_trigger_private_data_free(struct event_trigger_data *data) +{ + kfree(data->private_data); +} + void event_enable_trigger_free(struct event_trigger_data *data) { struct enable_trigger_data *enable_data = data->private_data; @@ -1728,9 +1740,9 @@ void event_enable_trigger_free(struct event_trigger_data *data) if (!data->ref) { /* Remove the SOFT_MODE flag */ trace_event_enable_disable(enable_data->file, 0, 1); + data->private_data_free = enable_trigger_private_data_free; trace_event_put_ref(enable_data->file->event_call); trigger_data_free(data); - kfree(enable_data); } } From e091351b38818ef620d27f44f4bfd625f13afbff Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 24 Jul 2026 13:24:15 -0400 Subject: [PATCH 09/11] tracing: Delay module ref count for "enable_event" trigger Triggers are now delayed from freeing, but can still be triggered until after the RCU grace period has ended. The freeing of the enable_event data is put into the private_data_free() callback, but the put of the module refcount is done immediately. It is possible that if a module is removed that has an event that would enable (or disable) it is still active, it can read the data of the module after it is removed causing a use-after-free bug. Move the trace_event_put_ref() that releases the module into the delayed callback so that the module can not be removed until any reference to its events are finished. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260724132415.1b5005db@gandalf.local.home Reported-by: Sashiko Link: https://sashiko.dev/#/patchset/20260724030523.19081-1-devnexen%40gmail.com Fixes: 61d445af0a7c ("tracing: Add bulk garbage collection of freeing event_trigger_data") Signed-off-by: Steven Rostedt --- kernel/trace/trace_events_trigger.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c index 46e60b70a4bb..ad83419cb420 100644 --- a/kernel/trace/trace_events_trigger.c +++ b/kernel/trace/trace_events_trigger.c @@ -1726,7 +1726,10 @@ int event_enable_trigger_print(struct seq_file *m, static void enable_trigger_private_data_free(struct event_trigger_data *data) { - kfree(data->private_data); + struct enable_trigger_data *enable_data = data->private_data; + + trace_event_put_ref(enable_data->file->event_call); + kfree(enable_data); } void event_enable_trigger_free(struct event_trigger_data *data) @@ -1741,7 +1744,6 @@ void event_enable_trigger_free(struct event_trigger_data *data) /* Remove the SOFT_MODE flag */ trace_event_enable_disable(enable_data->file, 0, 1); data->private_data_free = enable_trigger_private_data_free; - trace_event_put_ref(enable_data->file->event_call); trigger_data_free(data); } } From 7720b63bcef3f54c7fe288774b720a227d54a306 Mon Sep 17 00:00:00 2001 From: Tengda Wu Date: Sat, 25 Jul 2026 02:47:21 +0000 Subject: [PATCH 10/11] ftrace: Add global mutex to serialize trace_parser access In ftrace, the trace_parser structure is allocated and initialized when a trace file is opened, and is subsequently used across write and release handlers to parse user input. The affected handler paths and their specific functions are: - Open paths: ftrace_regex_open(), ftrace_graph_open() - Write paths: ftrace_regex_write(), ftrace_graph_write() - Release paths: ftrace_regex_release(), ftrace_graph_release() If userspace opens a trace file descriptor and shares it across multiple threads, concurrent write calls will race on the parser's internal state, specifically the 'idx', 'cont', and 'buffer' fields, leading to corrupted input or undefined behavior. Fix this by adding a global mutex, parser_lock, to serialize all access to trace_parser across write and release paths, preventing concurrent corruption of parser state. Fixes: e704eff3ff51 ("ftrace: Have set_graph_function handle multiple functions in one write") Fixes: 689fd8b65d66 ("tracing: trace parser support for function and graph") Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260725024721.1983675-1-wutengda@huaweicloud.com Signed-off-by: Tengda Wu Signed-off-by: Steven Rostedt --- kernel/trace/ftrace.c | 13 +++++++++++++ 1 file changed, 13 insertions(+) diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c index f93e34dd2328..6c47a94f5924 100644 --- a/kernel/trace/ftrace.c +++ b/kernel/trace/ftrace.c @@ -1097,6 +1097,12 @@ struct ftrace_ops global_ops = { FTRACE_OPS_FL_PID, }; +/* + * parser_lock - Protects trace_parser state against concurrent operations. + * Held across trace_get_user() and subsequent buffer parsing to prevent races. + */ +static DEFINE_MUTEX(parser_lock); + /* * Used by the stack unwinder to know about dynamic ftrace trampolines. */ @@ -5842,6 +5848,8 @@ ftrace_regex_write(struct file *file, const char __user *ubuf, /* iter->hash is a local copy, so we don't need regex_lock */ parser = &iter->parser; + + guard(mutex)(&parser_lock); read = trace_get_user(parser, ubuf, cnt, ppos); if (read >= 0 && trace_parser_loaded(parser) && @@ -6984,12 +6992,14 @@ int ftrace_regex_release(struct inode *inode, struct file *file) iter = file->private_data; parser = &iter->parser; + mutex_lock(&parser_lock); if (trace_parser_loaded(parser)) { int enable = !(iter->flags & FTRACE_ITER_NOTRACE); ftrace_process_regex(iter, parser->buffer, parser->idx, enable); } + mutex_unlock(&parser_lock); trace_parser_put(parser); @@ -7321,10 +7331,12 @@ ftrace_graph_release(struct inode *inode, struct file *file) parser = &fgd->parser; + mutex_lock(&parser_lock); if (trace_parser_loaded((parser))) { ret = ftrace_graph_set_hash(fgd->new_hash, parser->buffer); } + mutex_unlock(&parser_lock); trace_parser_put(parser); @@ -7437,6 +7449,7 @@ ftrace_graph_write(struct file *file, const char __user *ubuf, parser = &fgd->parser; + guard(mutex)(&parser_lock); read = trace_get_user(parser, ubuf, cnt, ppos); if (read >= 0 && trace_parser_loaded(parser) && From 2c2b322acdcc78575b8d6afa64a085cf92e03c12 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Fri, 24 Jul 2026 19:32:10 -0400 Subject: [PATCH 11/11] tracing: perf: Fix stale head for perf syscall tracing The code that can read the user space parameters of a system call may enable preemption and migrate. The head of the per CPU perf events list may be pointing to the wrong CPU event if the code migrates the task. Reassign the head pointer if the system call event called the code that may have caused a migration. Cc: stable@vger.kernel.org Link: https://patch.msgid.link/20260724193210.03fae1d6@gandalf.local.home Reported-by: Sashiko <> Link: https://sashiko.dev/#/patchset/20260717173252.3431565-1-usama.arif%40linux.dev Fixes: edca33a56297d ("tracing: Fix failure to read user space from system call trace events") Signed-off-by: Steven Rostedt --- kernel/trace/trace_syscalls.c | 5 +++++ 1 file changed, 5 insertions(+) diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c index e98ee7e1e66f..8a4f3c75e39f 100644 --- a/kernel/trace/trace_syscalls.c +++ b/kernel/trace/trace_syscalls.c @@ -1451,6 +1451,11 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id) if (syscall_get_data(sys_data, args, &user_ptr, &size, user_sizes, &uargs, buf_size) < 0) return; + + /* The above may have caused a migration */ + head = this_cpu_ptr(sys_data->enter_event->perf_events); + if (hlist_empty(head)) + return; } /* get the size after alignment with the u32 buffer size field */