On 2025-08-23 12:40, Thomas Gleixner wrote:
> Seperate the interrupt and syscall exit handling. Syscall exit does not
Separate
> 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.
Reviewed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
>
> Signed-off-by: Thomas Gleixner <tglx@linutronix.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 = ¤t->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 = ¤t->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 */
>
>
--
Mathieu Desnoyers
EfficiOS Inc.
https://www.efficios.com