From edca33a56297d5741ccf867669debec116681987 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Mon, 16 Mar 2026 13:07:34 -0400 Subject: tracing: Fix failure to read user space from system call trace events The system call trace events call trace_user_fault_read() to read the user space part of some system calls. This is done by grabbing a per-cpu buffer, disabling migration, enabling preemption, calling copy_from_user(), disabling preemption, enabling migration and checking if the task was preempted while preemption was enabled. If it was, the buffer is considered corrupted and it tries again. There's a safety mechanism that will fail out of this loop if it fails 100 times (with a warning). That warning message was triggered in some pi_futex stress tests. Enabling the sched_switch trace event and traceoff_on_warning, showed the problem: pi_mutex_hammer-1375 [006] d..21 138.981648: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981651: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 pi_mutex_hammer-1375 [006] d..21 138.981656: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981659: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 pi_mutex_hammer-1375 [006] d..21 138.981664: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981667: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 pi_mutex_hammer-1375 [006] d..21 138.981671: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981675: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 pi_mutex_hammer-1375 [006] d..21 138.981679: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981682: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 pi_mutex_hammer-1375 [006] d..21 138.981687: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981690: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 pi_mutex_hammer-1375 [006] d..21 138.981695: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981698: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 pi_mutex_hammer-1375 [006] d..21 138.981703: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981706: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 pi_mutex_hammer-1375 [006] d..21 138.981711: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981714: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 pi_mutex_hammer-1375 [006] d..21 138.981719: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981722: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 pi_mutex_hammer-1375 [006] d..21 138.981727: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981730: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 pi_mutex_hammer-1375 [006] d..21 138.981735: sched_switch: prev_comm=pi_mutex_hammer prev_pid=1375 prev_prio=95 prev_state=R+ ==> next_comm=migration/6 next_pid=47 next_prio=0 migration/6-47 [006] d..2. 138.981738: sched_switch: prev_comm=migration/6 prev_pid=47 prev_prio=0 prev_state=S ==> next_comm=pi_mutex_hammer next_pid=1375 next_prio=95 What happened was the task 1375 was flagged to be migrated. When preemption was enabled, the migration thread woke up to migrate that task, but failed because migration for that task was disabled. This caused the loop to fail to exit because the task scheduled out while trying to read user space. Every time the task enabled preemption the migration thread would schedule in, try to migrate the task, fail and let the task continue. But because the loop would only enable preemption with migration disabled, it would always fail because each time it enabled preemption to read user space, the migration thread would try to migrate it. To solve this, when the loop fails to read user space without being scheduled out, enabled and disable preemption with migration enabled. This will allow the migration task to successfully migrate the task and the next loop should succeed to read user space without being scheduled out. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260316130734.1858a998@gandalf.local.home Fixes: 64cf7d058a005 ("tracing: Have trace_marker use per-cpu data to read user space") Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 17 +++++++++++++++++ 1 file changed, 17 insertions(+) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index ebd996f8710e..bb4a62f4b953 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -6783,6 +6783,23 @@ char *trace_user_fault_read(struct trace_user_buf_info *tinfo, */ do { + /* + * It is possible that something is trying to migrate this + * task. What happens then, is when preemption is enabled, + * the migration thread will preempt this task, try to + * migrate it, fail, then let it run again. That will + * cause this to loop again and never succeed. + * On failures, enabled and disable preemption with + * migration enabled, to allow the migration thread to + * migrate this task. + */ + if (trys) { + preempt_enable_notrace(); + preempt_disable_notrace(); + cpu = smp_processor_id(); + buffer = per_cpu_ptr(tinfo->tbuf, cpu)->buf; + } + /* * If for some reason, copy_from_user() always causes a context * switch, this would then cause an infinite loop. -- cgit v1.2.3 From 07183aac4a6828e474f00b37c9d795d0d99e18a7 Mon Sep 17 00:00:00 2001 From: Steven Rostedt Date: Wed, 18 Mar 2026 18:55:12 -0400 Subject: tracing: Fix trace_marker copy link list updates When the "copy_trace_marker" option is enabled for an instance, anything written into /sys/kernel/tracing/trace_marker is also copied into that instances buffer. When the option is set, that instance's trace_array descriptor is added to the marker_copies link list. This list is protected by RCU, as all iterations uses an RCU protected list traversal. When the instance is deleted, all the flags that were enabled are cleared. This also clears the copy_trace_marker flag and removes the trace_array descriptor from the list. The issue is after the flags are called, a direct call to update_marker_trace() is performed to clear the flag. This function returns true if the state of the flag changed and false otherwise. If it returns true here, synchronize_rcu() is called to make sure all readers see that its removed from the list. But since the flag was already cleared, the state does not change and the synchronization is never called, leaving a possible UAF bug. Move the clearing of all flags below the updating of the copy_trace_marker option which then makes sure the synchronization is performed. Also use the flag for checking the state in update_marker_trace() instead of looking at if the list is empty. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260318185512.1b6c7db4@gandalf.local.home Fixes: 7b382efd5e8a ("tracing: Allow the top level trace_marker to write into another instances") Reported-by: Sasha Levin Closes: https://lore.kernel.org/all/20260225133122.237275-1-sashal@kernel.org/ Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace.c | 19 ++++++++++--------- 1 file changed, 10 insertions(+), 9 deletions(-) (limited to 'kernel/trace/trace.c') diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c index bb4a62f4b953..a626211ceb9a 100644 --- a/kernel/trace/trace.c +++ b/kernel/trace/trace.c @@ -555,7 +555,7 @@ static bool update_marker_trace(struct trace_array *tr, int enabled) lockdep_assert_held(&event_mutex); if (enabled) { - if (!list_empty(&tr->marker_list)) + if (tr->trace_flags & TRACE_ITER(COPY_MARKER)) return false; list_add_rcu(&tr->marker_list, &marker_copies); @@ -563,10 +563,10 @@ static bool update_marker_trace(struct trace_array *tr, int enabled) return true; } - if (list_empty(&tr->marker_list)) + if (!(tr->trace_flags & TRACE_ITER(COPY_MARKER))) return false; - list_del_init(&tr->marker_list); + list_del_rcu(&tr->marker_list); tr->trace_flags &= ~TRACE_ITER(COPY_MARKER); return true; } @@ -9761,18 +9761,19 @@ static int __remove_instance(struct trace_array *tr) list_del(&tr->list); - /* Disable all the flags that were enabled coming in */ - for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) { - if ((1ULL << i) & ZEROED_TRACE_FLAGS) - set_tracer_flag(tr, 1ULL << i, 0); - } - if (printk_trace == tr) update_printk_trace(&global_trace); + /* Must be done before disabling all the flags */ if (update_marker_trace(tr, 0)) synchronize_rcu(); + /* Disable all the flags that were enabled coming in */ + for (i = 0; i < TRACE_FLAGS_MAX_SIZE; i++) { + if ((1ULL << i) & ZEROED_TRACE_FLAGS) + set_tracer_flag(tr, 1ULL << i, 0); + } + tracing_set_nop(tr); clear_ftrace_function_probes(tr); event_trace_del_tracer(tr); -- cgit v1.2.3