On Fri, Mar 08, 2024 at 10:07:19AM -0500, Mathieu Desnoyers wrote:
> diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
> index 35389b2af88e..0d5e54201eb2 100644
> --- a/arch/x86/include/asm/barrier.h
> +++ b/arch/x86/include/asm/barrier.h
> @@ -79,6 +79,9 @@ do { \
> #define __smp_mb__before_atomic() do { } while (0)
> #define __smp_mb__after_atomic() do { } while (0)
>
> +/* Writing to CR3 provides a full memory barrier in switch_mm(). */
> +#define smp_mb__after_switch_mm() do { } while (0)
> +
> #include <asm-generic/barrier.h>
>
> /*
> diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h
> index 961f4d88f9ef..5a6c94d7a598 100644
> --- a/include/asm-generic/barrier.h
> +++ b/include/asm-generic/barrier.h
> @@ -296,5 +296,13 @@ do { \
> #define io_stop_wc() do { } while (0)
> #endif
>
> +/*
> + * Architectures that guarantee an implicit smp_mb() in switch_mm()
> + * can override smp_mb__after_switch_mm.
> + */
> +#ifndef smp_mb__after_switch_mm
> +#define smp_mb__after_switch_mm() smp_mb()
> +#endif
> +
> #endif /* !__ASSEMBLY__ */
> #endif /* __ASM_GENERIC_BARRIER_H */
> diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
> index 2e5a95486a42..044d842c696c 100644
> --- a/kernel/sched/sched.h
> +++ b/kernel/sched/sched.h
> @@ -79,6 +79,8 @@
> # include <asm/paravirt_api_clock.h>
> #endif
>
> +#include <asm/barrier.h>
> +
> #include "cpupri.h"
> #include "cpudeadline.h"
>
> @@ -3481,13 +3483,19 @@ static inline void switch_mm_cid(struct rq *rq,
> * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu].
> * Provide it here.
> */
> - if (!prev->mm) // from kernel
> + if (!prev->mm) { // from kernel
> smp_mb();
> - /*
> - * user -> user transition guarantees a memory barrier through
> - * switch_mm() when current->mm changes. If current->mm is
> - * unchanged, no barrier is needed.
> - */
> + } else { // from user
> + /*
> + * user -> user transition relies on an implicit
> + * memory barrier in switch_mm() when
> + * current->mm changes. If the architecture
> + * switch_mm() does not have an implicit memory
> + * barrier, it is emitted here. If current->mm
> + * is unchanged, no barrier is needed.
> + */
> + smp_mb__after_switch_mm();
> + }
I'm fine with the change from the arm64 perspective but I guess we need
an ack from the x86 and sched maintainers. FWIW:
Reviewed-by: Catalin Marinas <catalin.marinas@xxxxxxx>
--
Catalin
