rseq: Simplify the event notification

Since commit 0190e4198e47 ("rseq: Deprecate RSEQ_CS_FLAG_NO_RESTART_ON_*
flags") the bits in task::rseq_event_mask are meaningless and just extra
work in terms of setting them individually.

Aside of that the only relevant point where an event has to be raised is
context switch. Neither the CPU nor MM CID can change without going through
a context switch.

Collapse them all into a single boolean which simplifies the code a lot and
remove the pointless invocations which have been sprinkled all over the
place for no value.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://patch.msgid.link/20251027084306.336978188@linutronix.de

1 files changed, 17 insertions, 11 deletions

diff --git a/kernel/rseq.c b/kernel/rseq.c
index 80af48a972f0..59adc1a7183b 100644
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -78,6 +78,12 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/rseq.h>
 
+#ifdef CONFIG_MEMBARRIER
+# define RSEQ_EVENT_GUARD	irq
+#else
+# define RSEQ_EVENT_GUARD	preempt
+#endif
+
 /* The original rseq structure size (including padding) is 32 bytes. */
 #define ORIG_RSEQ_SIZE		32
 
@@ -430,11 +436,11 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
 	 */
 	if (regs) {
 		/*
-		 * Read and clear the event mask first. If the task was not
-		 * preempted or migrated or a signal is on the way, there
-		 * is no point in doing any of the heavy lifting here on
-		 * production kernels. In that case TIF_NOTIFY_RESUME was
-		 * raised by some other functionality.
+		 * Read and clear the event pending bit first. If the task
+		 * was not preempted or migrated or a signal is on the way,
+		 * there is no point in doing any of the heavy lifting here
+		 * on production kernels. In that case TIF_NOTIFY_RESUME
+		 * was raised by some other functionality.
 		 *
 		 * This is correct because the read/clear operation is
 		 * guarded against scheduler preemption, which makes it CPU
@@ -447,15 +453,15 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs)
 		 * with the result handed in to allow the detection of
 		 * inconsistencies.
 		 */
-		u32 event_mask;
+		bool event;
 
 		scoped_guard(RSEQ_EVENT_GUARD) {
-			event_mask = t->rseq_event_mask;
-			t->rseq_event_mask = 0;
+			event = t->rseq_event_pending;
+			t->rseq_event_pending = false;
 		}
 
-		if (IS_ENABLED(CONFIG_DEBUG_RSEQ) || event_mask) {
-			ret = rseq_ip_fixup(regs, !!event_mask);
+		if (IS_ENABLED(CONFIG_DEBUG_RSEQ) || event) {
+			ret = rseq_ip_fixup(regs, event);
 			if (unlikely(ret < 0))
 				goto error;
 		}
@@ -584,7 +590,7 @@ SYSCALL_DEFINE4(rseq, struct rseq __user *, rseq, u32, rseq_len, int, flags, u32
 	 * registered, ensure the cpu_id_start and cpu_id fields
 	 * are updated before returning to user-space.
 	 */
-	rseq_set_notify_resume(current);
+	rseq_sched_switch_event(current);
 
 	return 0;
 }