linux-kernel - [patch V3 24/37] rseq: Separate the signal delivery path

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250904185720.650857527@linutronix.de>
Date: Fri,  5 Sep 2025 00:21:19 +0200 (CEST)
From: Thomas Gleixner <tglx@...utronix.de>
To: LKML <linux-kernel@...r.kernel.org>
Cc: Michael Jeanson <mjeanson@...icios.com>,
 Jens Axboe <axboe@...nel.dk>,
 Mathieu Desnoyers <mathieu.desnoyers@...icios.com>,
 Peter Zijlstra <peterz@...radead.org>,
 "Paul E. McKenney" <paulmck@...nel.org>,
 Boqun Feng <boqun.feng@...il.com>,
 Paolo Bonzini <pbonzini@...hat.com>,
 Sean Christopherson <seanjc@...gle.com>,
 Wei Liu <wei.liu@...nel.org>,
 Dexuan Cui <decui@...rosoft.com>,
 x86@...nel.org,
 Arnd Bergmann <arnd@...db.de>,
 Heiko Carstens <hca@...ux.ibm.com>,
 Christian Borntraeger <borntraeger@...ux.ibm.com>,
 Sven Schnelle <svens@...ux.ibm.com>,
 Huacai Chen <chenhuacai@...nel.org>,
 Paul Walmsley <paul.walmsley@...ive.com>,
 Palmer Dabbelt <palmer@...belt.com>
Subject: [patch V3 24/37] 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 <tglx@...utronix.de>
---
V3: Move rseq_update_usr() to the next patch - Mathieu
---
 include/linux/rseq.h |   21 ++++++++++++++++-----
 kernel/rseq.c        |   30 ++++++++++++++++++++++--------
 2 files changed, 38 insertions(+), 13 deletions(-)

--- a/include/linux/rseq.h
+++ b/include/linux/rseq.h
@@ -5,22 +5,33 @@
 #ifdef CONFIG_RSEQ
 #include <linux/sched.h>

-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) {
--- a/kernel/rseq.c
+++ b/kernel/rseq.c
@@ -247,13 +247,12 @@ static bool rseq_handle_cs(struct task_s
  * 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
@@ -272,10 +271,7 @@ void __rseq_handle_notify_resume(struct
 	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
@@ -314,8 +310,26 @@ void __rseq_handle_notify_resume(struct
 	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);
+	}
 }

 void __rseq_debug_syscall_return(struct pt_regs *regs)