From 0a663b764dbdf135a126284f454c9f01f95a87d4 Mon Sep 17 00:00:00 2001 From: Huiwen He Date: Tue, 24 Feb 2026 10:35:44 +0800 Subject: tracing: Fix syscall events activation by ensuring refcount hits zero When multiple syscall events are specified in the kernel command line (e.g., trace_event=syscalls:sys_enter_openat,syscalls:sys_enter_close), they are often not captured after boot, even though they appear enabled in the tracing/set_event file. The issue stems from how syscall events are initialized. Syscall tracepoints require the global reference count (sys_tracepoint_refcount) to transition from 0 to 1 to trigger the registration of the syscall work (TIF_SYSCALL_TRACEPOINT) for tasks, including the init process (pid 1). The current implementation of early_enable_events() with disable_first=true used an interleaved sequence of "Disable A -> Enable A -> Disable B -> Enable B". If multiple syscalls are enabled, the refcount never drops to zero, preventing the 0->1 transition that triggers actual registration. Fix this by splitting early_enable_events() into two distinct phases: 1. Disable all events specified in the buffer. 2. Enable all events specified in the buffer. This ensures the refcount hits zero before re-enabling, allowing syscall events to be properly activated during early boot. The code is also refactored to use a helper function to avoid logic duplication between the disable and enable phases. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260224023544.1250787-1-hehuiwen@kylinos.cn Fixes: ce1039bd3a89 ("tracing: Fix enabling of syscall events on the command line") Signed-off-by: Huiwen He Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 52 ++++++++++++++++++++++++++++++++------------- 1 file changed, 37 insertions(+), 15 deletions(-) (limited to 'kernel/trace/trace_events.c') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 9928da636c9d..9c7f26cbe171 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -4668,26 +4668,22 @@ static __init int event_trace_memsetup(void) return 0; } -__init void -early_enable_events(struct trace_array *tr, char *buf, bool disable_first) +/* + * Helper function to enable or disable a comma-separated list of events + * from the bootup buffer. + */ +static __init void __early_set_events(struct trace_array *tr, char *buf, bool enable) { char *token; - int ret; - - while (true) { - token = strsep(&buf, ","); - - if (!token) - break; + while ((token = strsep(&buf, ","))) { if (*token) { - /* Restarting syscalls requires that we stop them first */ - if (disable_first) + if (enable) { + if (ftrace_set_clr_event(tr, token, 1)) + pr_warn("Failed to enable trace event: %s\n", token); + } else { ftrace_set_clr_event(tr, token, 0); - - ret = ftrace_set_clr_event(tr, token, 1); - if (ret) - pr_warn("Failed to enable trace event: %s\n", token); + } } /* Put back the comma to allow this to be called again */ @@ -4696,6 +4692,32 @@ early_enable_events(struct trace_array *tr, char *buf, bool disable_first) } } +/** + * early_enable_events - enable events from the bootup buffer + * @tr: The trace array to enable the events in + * @buf: The buffer containing the comma separated list of events + * @disable_first: If true, disable all events in @buf before enabling them + * + * This function enables events from the bootup buffer. If @disable_first + * is true, it will first disable all events in the buffer before enabling + * them. + * + * For syscall events, which rely on a global refcount to register the + * SYSCALL_WORK_SYSCALL_TRACEPOINT flag (especially for pid 1), we must + * ensure the refcount hits zero before re-enabling them. A simple + * "disable then enable" per-event is not enough if multiple syscalls are + * used, as the refcount will stay above zero. Thus, we need a two-phase + * approach: disable all, then enable all. + */ +__init void +early_enable_events(struct trace_array *tr, char *buf, bool disable_first) +{ + if (disable_first) + __early_set_events(tr, buf, false); + + __early_set_events(tr, buf, true); +} + static __init int event_trace_enable(void) { struct trace_array *tr = top_trace_array(); -- cgit v1.2.3 From a5dd6f58666f22ae16b98a2177bebc3340d38fe9 Mon Sep 17 00:00:00 2001 From: "Masami Hiramatsu (Google)" Date: Tue, 3 Mar 2026 21:57:38 -0500 Subject: tracing: Disable preemption in the tracepoint callbacks handling filtered pids Filtering PIDs for events triggered the following during selftests: [37] event tracing - restricts events based on pid notrace filtering [ 155.874095] [ 155.874869] ============================= [ 155.876037] WARNING: suspicious RCU usage [ 155.877287] 7.0.0-rc1-00004-g8cd473a19bc7 #7 Not tainted [ 155.879263] ----------------------------- [ 155.882839] kernel/trace/trace_events.c:1057 suspicious rcu_dereference_check() usage! [ 155.889281] [ 155.889281] other info that might help us debug this: [ 155.889281] [ 155.894519] [ 155.894519] rcu_scheduler_active = 2, debug_locks = 1 [ 155.898068] no locks held by ftracetest/4364. [ 155.900524] [ 155.900524] stack backtrace: [ 155.902645] CPU: 1 UID: 0 PID: 4364 Comm: ftracetest Not tainted 7.0.0-rc1-00004-g8cd473a19bc7 #7 PREEMPT(lazy) [ 155.902648] Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS 1.17.0-debian-1.17.0-1 04/01/2014 [ 155.902651] Call Trace: [ 155.902655] [ 155.902659] dump_stack_lvl+0x67/0x90 [ 155.902665] lockdep_rcu_suspicious+0x154/0x1a0 [ 155.902672] event_filter_pid_sched_process_fork+0x9a/0xd0 [ 155.902678] kernel_clone+0x367/0x3a0 [ 155.902689] __x64_sys_clone+0x116/0x140 [ 155.902696] do_syscall_64+0x158/0x460 [ 155.902700] ? entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 155.902702] ? trace_irq_disable+0x1d/0xc0 [ 155.902709] entry_SYSCALL_64_after_hwframe+0x77/0x7f [ 155.902711] RIP: 0033:0x4697c3 [ 155.902716] Code: 1f 84 00 00 00 00 00 64 48 8b 04 25 10 00 00 00 45 31 c0 31 d2 31 f6 bf 11 00 20 01 4c 8d 90 d0 02 00 00 b8 38 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 35 89 c2 85 c0 75 2c 64 48 8b 04 25 10 00 00 [ 155.902718] RSP: 002b:00007ffc41150428 EFLAGS: 00000246 ORIG_RAX: 0000000000000038 [ 155.902721] RAX: ffffffffffffffda RBX: 0000000000000000 RCX: 00000000004697c3 [ 155.902722] RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000001200011 [ 155.902724] RBP: 0000000000000000 R08: 0000000000000000 R09: 000000003fccf990 [ 155.902725] R10: 000000003fccd690 R11: 0000000000000246 R12: 0000000000000001 [ 155.902726] R13: 000000003fce8103 R14: 0000000000000001 R15: 0000000000000000 [ 155.902733] [ 155.902747] The tracepoint callbacks recently were changed to allow preemption. The event PID filtering callbacks that were attached to the fork and exit tracepoints expected preemption disabled in order to access the RCU protected PID lists. Add a guard(preempt)() to protect the references to the PID list. Cc: stable@vger.kernel.org Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260303215738.6ab275af@fedora Fixes: a46023d5616e ("tracing: Guard __DECLARE_TRACE() use of __DO_TRACE_CALL() with SRCU-fast") Link: https://patch.msgid.link/20260303131706.96057f61a48a34c43ce1e396@kernel.org Signed-off-by: Masami Hiramatsu (Google) Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 2 ++ 1 file changed, 2 insertions(+) (limited to 'kernel/trace/trace_events.c') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index 9c7f26cbe171..b7343fdfd7b0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -1039,6 +1039,7 @@ event_filter_pid_sched_process_exit(void *data, struct task_struct *task) struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_raw(tr->filtered_pids); trace_filter_add_remove_task(pid_list, NULL, task); @@ -1054,6 +1055,7 @@ event_filter_pid_sched_process_fork(void *data, struct trace_pid_list *pid_list; struct trace_array *tr = data; + guard(preempt)(); pid_list = rcu_dereference_sched(tr->filtered_pids); trace_filter_add_remove_task(pid_list, self, task); -- cgit v1.2.3 From 3b1679e086bb869ca02722f6bd29b3573a6a0e7e Mon Sep 17 00:00:00 2001 From: Andrei-Alexandru Tachici Date: Mon, 2 Mar 2026 11:27:34 +0100 Subject: tracing: Fix enabling multiple events on the kernel command line and bootconfig Multiple events can be enabled on the kernel command line via a comma separator. But if the are specified one at a time, then only the last event is enabled. This is because the event names are saved in a temporary buffer, and each call by the init cmdline code will reset that buffer. This also affects names in the boot config file, as it may call the callback multiple times with an example of: kernel.trace_event = ":mod:rproc_qcom_common", ":mod:qrtr", ":mod:qcom_aoss" Change the cmdline callback function to append a comma and the next value if the temporary buffer already has content. Cc: stable@vger.kernel.org Cc: Masami Hiramatsu Cc: Mathieu Desnoyers Link: https://patch.msgid.link/20260302-trace-events-allow-multiple-modules-v1-1-ce4436e37fb8@oss.qualcomm.com Signed-off-by: Andrei-Alexandru Tachici Signed-off-by: Steven Rostedt (Google) --- kernel/trace/trace_events.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'kernel/trace/trace_events.c') diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c index b7343fdfd7b0..249d1cba72c0 100644 --- a/kernel/trace/trace_events.c +++ b/kernel/trace/trace_events.c @@ -4493,7 +4493,11 @@ static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata; static __init int setup_trace_event(char *str) { - strscpy(bootup_event_buf, str, COMMAND_LINE_SIZE); + if (bootup_event_buf[0] != '\0') + strlcat(bootup_event_buf, ",", COMMAND_LINE_SIZE); + + strlcat(bootup_event_buf, str, COMMAND_LINE_SIZE); + trace_set_ring_buffer_expanded(NULL); disable_tracing_selftest("running event tracing"); -- cgit v1.2.3