linux-kernel - [patch V2 30/37] rseq: Split up rseq_exit_to_user

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 for Android: free password hash cracker in your pocket

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

Message-ID: <20250823161655.191313426@linutronix.de>
Date: Sat, 23 Aug 2025 18:40:22 +0200 (CEST)
From: Thomas Gleixner <tglx@...utronix.de>
To: LKML <linux-kernel@...r.kernel.org>
Cc: 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 V2 30/37] rseq: Split up rseq_exit_to_user_mode()

Seperate the interrupt and syscall exit handling. Syscall exit does not
require to clear the user_irq bit as it can't be set. On interrupt exit it
can be set when the interrupt did not result in a scheduling event and
therefore the return path did not invoke the TIF work handling, which would
have cleared it.

The debug check for the event state is also not really required even when
debug mode is enabled via the static key. Debug mode is largely aiding user
space by enabling a larger amount of validation checks, which cause a
segfault when a malformed critical section is detected. In production mode
the critical section handling takes the content mostly as is and lets user
space keep the pieces when it screwed up.

On kernel changes in that area the state check is useful, but that can be
done when lockdep is enabled, which is anyway a required test scenario for
fundamental changes.

Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
---
 include/linux/irq-entry-common.h |    4 ++--
 include/linux/rseq_entry.h       |   21 +++++++++++++++++----
 2 files changed, 19 insertions(+), 6 deletions(-)

--- a/include/linux/irq-entry-common.h
+++ b/include/linux/irq-entry-common.h
@@ -247,7 +247,7 @@ static __always_inline void __exit_to_us
 static __always_inline void syscall_exit_to_user_mode_prepare(struct pt_regs *regs)
 {
 	__exit_to_user_mode_prepare(regs);
-	rseq_exit_to_user_mode();
+	rseq_syscall_exit_to_user_mode();
 	__exit_to_user_mode_validate();
 }

@@ -261,7 +261,7 @@ static __always_inline void syscall_exit
 static __always_inline void irqentry_exit_to_user_mode_prepare(struct pt_regs *regs)
 {
 	__exit_to_user_mode_prepare(regs);
-	rseq_exit_to_user_mode();
+	rseq_irqentry_exit_to_user_mode();
 	__exit_to_user_mode_validate();
 }

--- a/include/linux/rseq_entry.h
+++ b/include/linux/rseq_entry.h
@@ -519,19 +519,31 @@ rseq_exit_to_user_mode_work(struct pt_re

 #endif /* !CONFIG_GENERIC_ENTRY */

-static __always_inline void rseq_exit_to_user_mode(void)
+static __always_inline void rseq_syscall_exit_to_user_mode(void)
 {
 	struct rseq_event *ev = &current->rseq_event;

 	rseq_stat_inc(rseq_stats.exit);

-	if (static_branch_unlikely(&rseq_debug_enabled))
+	/* Needed to remove the store for the !lockdep case */
+	if (IS_ENABLED(CONFIG_LOCKDEP)) {
 		WARN_ON_ONCE(ev->sched_switch);
+		ev->events = 0;
+	}
+}
+
+static __always_inline void rseq_irqentry_exit_to_user_mode(void)
+{
+	struct rseq_event *ev = &current->rseq_event;
+
+	rseq_stat_inc(rseq_stats.exit);
+
+	lockdep_assert_once(!ev->sched_switch);

 	/*
 	 * Ensure that event (especially user_irq) is cleared when the
 	 * interrupt did not result in a schedule and therefore the
-	 * rseq processing did not clear it.
+	 * rseq processing could not clear it.
 	 */
 	ev->events = 0;
 }
@@ -551,7 +563,8 @@ static inline unsigned long rseq_exit_to
 	return ti_work;
 }
 static inline void rseq_note_user_irq_entry(void) { }
-static inline void rseq_exit_to_user_mode(void) { }
+static inline void rseq_syscall_exit_to_user_mode(void) { }
+static inline void rseq_irqentry_exit_to_user_mode(void) { }
 static inline void rseq_debug_syscall_return(struct pt_regs *regs) { }
 #endif /* !CONFIG_RSEQ */