From 9f6ffd4cebda86841700775de3213f22bb0ea22d Mon Sep 17 00:00:00 2001 From: Thomas Gleixner Date: Mon, 27 Oct 2025 09:45:10 +0100 Subject: [PATCH] rseq: Separate the signal delivery path Completely separate the signal delivery path from the notify handler as they have different semantics versus the event handling. The signal delivery only needs to ensure that the interrupted user context was not in a critical section or the section is aborted before it switches to the signal frame context. The signal frame context does not have the original instruction pointer anymore, so that can't be handled on exit to user space. No point in updating the CPU/CID ids as they might change again before the task returns to user space for real. The fast path optimization, which checks for the 'entry from user via interrupt' condition is only available for architectures which use the generic entry code. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Mathieu Desnoyers Link: https://patch.msgid.link/20251027084307.455429038@linutronix.de --- include/linux/rseq.h | 21 ++++++++++++++++----- kernel/rseq.c | 30 ++++++++++++++++++++++-------- 2 files changed, 38 insertions(+), 13 deletions(-) diff --git a/include/linux/rseq.h b/include/linux/rseq.h index 92f9cd49489bc..f5a43188023fa 100644 --- a/include/linux/rseq.h +++ b/include/linux/rseq.h @@ -7,22 +7,33 @@ #include -void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); +void __rseq_handle_notify_resume(struct pt_regs *regs); static inline void rseq_handle_notify_resume(struct pt_regs *regs) { if (current->rseq.event.has_rseq) - __rseq_handle_notify_resume(NULL, regs); + __rseq_handle_notify_resume(regs); } +void __rseq_signal_deliver(int sig, struct pt_regs *regs); + +/* + * Invoked from signal delivery to fixup based on the register context before + * switching to the signal delivery context. + */ static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { - if (current->rseq.event.has_rseq) { - current->rseq.event.sched_switch = true; - __rseq_handle_notify_resume(ksig, regs); + if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) { + /* '&' is intentional to spare one conditional branch */ + if (current->rseq.event.has_rseq & current->rseq.event.user_irq) + __rseq_signal_deliver(ksig->sig, regs); + } else { + if (current->rseq.event.has_rseq) + __rseq_signal_deliver(ksig->sig, regs); } } +/* Raised from context switch and exevce to force evaluation on exit to user */ static inline void rseq_sched_switch_event(struct task_struct *t) { if (t->rseq.event.has_rseq) { diff --git a/kernel/rseq.c b/kernel/rseq.c index 1e4f1d2cdfe57..13faadc737ad6 100644 --- a/kernel/rseq.c +++ b/kernel/rseq.c @@ -250,13 +250,12 @@ efault: * respect to other threads scheduled on the same CPU, and with respect * to signal handlers. */ -void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) +void __rseq_handle_notify_resume(struct pt_regs *regs) { struct task_struct *t = current; struct rseq_ids ids; u32 node_id; bool event; - int sig; /* * If invoked from hypervisors before entering the guest via @@ -275,10 +274,7 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) if (unlikely(t->flags & PF_EXITING)) return; - if (ksig) - rseq_stat_inc(rseq_stats.signal); - else - rseq_stat_inc(rseq_stats.slowpath); + rseq_stat_inc(rseq_stats.slowpath); /* * Read and clear the event pending bit first. If the task @@ -317,8 +313,26 @@ void __rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) return; error: - sig = ksig ? ksig->sig : 0; - force_sigsegv(sig); + force_sig(SIGSEGV); +} + +void __rseq_signal_deliver(int sig, struct pt_regs *regs) +{ + rseq_stat_inc(rseq_stats.signal); + /* + * Don't update IDs, they are handled on exit to user if + * necessary. The important thing is to abort a critical section of + * the interrupted context as after this point the instruction + * pointer in @regs points to the signal handler. + */ + if (unlikely(!rseq_handle_cs(current, regs))) { + /* + * Clear the errors just in case this might survive + * magically, but leave the rest intact. + */ + current->rseq.event.error = 0; + force_sigsegv(sig); + } } /* -- 2.47.3