Re: [PATCH v4 12/12] mm: bail out of lazy_mmu_mode_* in interrupt context

[Ryan Roberts <ryan.roberts@xxxxxxx>]

On 29/10/2025 10:09, Kevin Brodsky wrote:
> The lazy MMU mode cannot be used in interrupt context. This is
> documented in <linux/pgtable.h>, but isn't consistently handled
> across architectures.
> 
> arm64 ensures that calls to lazy_mmu_mode_* have no effect in
> interrupt context, because such calls do occur in certain
> configurations - see commit b81c688426a9 ("arm64/mm: Disable barrier
> batching in interrupt contexts"). Other architectures do not check
> this situation, most likely because it hasn't occurred so far.
> 
> Both arm64 and x86/Xen also ensure that any lazy MMU optimisation is
> disabled while in interrupt mode (see queue_pte_barriers() and
> xen_get_lazy_mode() respectively).
> 
> Let's handle this in the new generic lazy_mmu layer, in the same
> fashion as arm64: bail out of lazy_mmu_mode_* if in_interrupt(), and
> have in_lazy_mmu_mode() return false to disable any optimisation.
> Also remove the arm64 handling that is now redundant; x86/Xen has
> its own internal tracking so it is left unchanged.
> 
> Signed-off-by: Kevin Brodsky <kevin.brodsky@xxxxxxx>
> ---
>  arch/arm64/include/asm/pgtable.h | 17 +----------------
>  include/linux/pgtable.h          | 16 ++++++++++++++--
>  include/linux/sched.h            |  3 +++
>  3 files changed, 18 insertions(+), 18 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/pgtable.h 
> b/arch/arm64/include/asm/pgtable.h
> index 61ca88f94551..96987a49e83b 100644
> --- a/arch/arm64/include/asm/pgtable.h
> +++ b/arch/arm64/include/asm/pgtable.h
> @@ -62,37 +62,22 @@ static inline void emit_pte_barriers(void)
>  
>  static inline void queue_pte_barriers(void)
>  {
> -     if (in_interrupt()) {
> -             emit_pte_barriers();
> -             return;
> -     }
> -
>       if (in_lazy_mmu_mode())
>               test_and_set_thread_flag(TIF_LAZY_MMU_PENDING);
>       else
>               emit_pte_barriers();
>  }
>  
> -static inline void arch_enter_lazy_mmu_mode(void)
> -{
> -     if (in_interrupt())
> -             return;
> -}
> +static inline void arch_enter_lazy_mmu_mode(void) {}
>  
>  static inline void arch_flush_lazy_mmu_mode(void)
>  {
> -     if (in_interrupt())
> -             return;
> -
>       if (test_and_clear_thread_flag(TIF_LAZY_MMU_PENDING))
>               emit_pte_barriers();
>  }
>  
>  static inline void arch_leave_lazy_mmu_mode(void)
>  {
> -     if (in_interrupt())
> -             return;
> -
>       arch_flush_lazy_mmu_mode();
>  }

Ahh ok, by the time you get to the final state, I think a most of my
comments/concerns are solved. Certainly this now looks safe for the interrupt
case, whereas I think the intermediate state when you initially introduce
nesting is broken. So perhaps you want to look at how to rework it to prevent 
that.

Thanks,
Ryan


>  
> diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
> index e6064e00b22d..e6069ce4ec83 100644
> --- a/include/linux/pgtable.h
> +++ b/include/linux/pgtable.h
> @@ -228,8 +228,8 @@ static inline int pmd_dirty(pmd_t pmd)
>   * of the lazy mode. So the implementation must assume preemption may be 
> enabled
>   * and cpu migration is possible; it must take steps to be robust against 
> this.
>   * (In practice, for user PTE updates, the appropriate page table lock(s) are
> - * held, but for kernel PTE updates, no lock is held). The mode cannot be 
> used
> - * in interrupt context.
> + * held, but for kernel PTE updates, no lock is held). The mode is disabled
> + * in interrupt context and calls to the lazy_mmu API have no effect.
>   *
>   * The lazy MMU mode is enabled for a given block of code using:
>   *
> @@ -265,6 +265,9 @@ static inline void lazy_mmu_mode_enable(void)
>  {
>       struct lazy_mmu_state *state = &current->lazy_mmu_state;
>  
> +     if (in_interrupt())
> +             return;
> +
>       VM_WARN_ON_ONCE(state->nesting_level == U8_MAX);
>       /* enable() must not be called while paused */
>       VM_WARN_ON(state->nesting_level > 0 && !state->active);
> @@ -279,6 +282,9 @@ static inline void lazy_mmu_mode_disable(void)
>  {
>       struct lazy_mmu_state *state = &current->lazy_mmu_state;
>  
> +     if (in_interrupt())
> +             return;
> +
>       VM_WARN_ON_ONCE(state->nesting_level == 0);
>       VM_WARN_ON(!state->active);
>  
> @@ -295,6 +301,9 @@ static inline void lazy_mmu_mode_pause(void)
>  {
>       struct lazy_mmu_state *state = &current->lazy_mmu_state;
>  
> +     if (in_interrupt())
> +             return;
> +
>       VM_WARN_ON(state->nesting_level == 0 || !state->active);
>  
>       state->active = false;
> @@ -305,6 +314,9 @@ static inline void lazy_mmu_mode_resume(void)
>  {
>       struct lazy_mmu_state *state = &current->lazy_mmu_state;
>  
> +     if (in_interrupt())
> +             return;
> +
>       VM_WARN_ON(state->nesting_level == 0 || state->active);
>  
>       state->active = true;
> diff --git a/include/linux/sched.h b/include/linux/sched.h
> index 11566d973f42..bb873016ffcf 100644
> --- a/include/linux/sched.h
> +++ b/include/linux/sched.h
> @@ -1731,6 +1731,9 @@ static inline char task_state_to_char(struct 
> task_struct *tsk)
>  #ifdef CONFIG_ARCH_HAS_LAZY_MMU_MODE
>  static inline bool in_lazy_mmu_mode(void)
>  {
> +     if (in_interrupt())
> +             return false;
> +
>       return current->lazy_mmu_state.active;
>  }
>  #else