Re: [PATCH RFC 1/3] mm/tlb: allow architectures to skip redundant TLB sync IPIs

[Lance Yang <lance.yang@linux.dev>]

On 2025/12/13 16:00, Lance Yang wrote:
> From: Lance Yang <lance.yang@linux.dev>
> 
> When unsharing hugetlb PMD page tables, we currently send two IPIs:
> one for TLB invalidation, and another to synchronize with concurrent
> GUP-fast walkers.
> 
> However, if the TLB flush already reaches all CPUs, the second IPI is
> redundant. GUP-fast runs with IRQs disabled, so when the TLB flush IPI
> completes, any concurrent GUP-fast must have finished.
> 
> Add tlb_table_flush_implies_ipi_broadcast() to let architectures indicate
> their TLB flush provides full synchronization, enabling the redundant IPI
> to be skipped.
> 
> The default implementation returns false to maintain current behavior.
> 
> Suggested-by: David Hildenbrand (Red Hat) <david@kernel.org>
> Signed-off-by: Lance Yang <lance.yang@linux.dev>
> ---
>   include/asm-generic/tlb.h | 22 +++++++++++++++++++++-
>   1 file changed, 21 insertions(+), 1 deletion(-)
> 
> diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h
> index 324a21f53b64..3f0add95604f 100644
> --- a/include/asm-generic/tlb.h
> +++ b/include/asm-generic/tlb.h
> @@ -248,6 +248,21 @@ static inline void tlb_remove_table(struct mmu_gather *tlb, void *table)
>   #define tlb_needs_table_invalidate() (true)
>   #endif
>   
> +/*
> + * Architectures can override if their TLB flush already broadcasts IPIs to all
> + * CPUs when freeing or unsharing page tables.
> + *
> + * Return true only when the flush guarantees:
> + * - IPIs reach all CPUs with potentially stale paging-structure cache entries
> + * - Synchronization with IRQ-disabled code like GUP-fast
> + */
> +#ifndef tlb_table_flush_implies_ipi_broadcast
> +static inline bool tlb_table_flush_implies_ipi_broadcast(void)
> +{
> +	return false;
> +}
> +#endif

As the kernel test robot reported[1][2], the compiler is unhappy with
patch #3:

```
    mm/khugepaged.c: In function 'collapse_huge_page':
>> >> mm/khugepaged.c:1185:14: error: implicit declaration of function 'tlb_table_flush_implies_ipi_broadcast' [-Werror=implicit-function-declaration]
     1185 |         if (!tlb_table_flush_implies_ipi_broadcast())
          |              ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    cc1: some warnings being treated as errors
```

I'll move tlb_table_flush_implies_ipi_broadcast() outside of
CONFIG_MMU_GATHER_RCU_TABLE_FREE in next version, making the complier
happy on architectures that don't enable that config ;)

[1] 
https://lore.kernel.org/oe-kbuild-all/202512142105.NXwq6dfP-lkp@intel.com/

[2] 
https://lore.kernel.org/oe-kbuild-all/202512142156.cShiu6PU-lkp@intel.com/
> +
>   void tlb_remove_table_sync_one(void);
>   
>   #else
> @@ -829,12 +844,17 @@ static inline void tlb_flush_unshared_tables(struct mmu_gather *tlb)
>   	 * We only perform this when we are the last sharer of a page table,
>   	 * as the IPI will reach all CPUs: any GUP-fast.
>   	 *
> +	 * However, if the TLB flush already synchronized with other CPUs
> +	 * (indicated by tlb_table_flush_implies_ipi_broadcast()), we can skip
> +	 * the additional IPI.
> +	 *
>   	 * Note that on configs where tlb_remove_table_sync_one() is a NOP,
>   	 * the expectation is that the tlb_flush_mmu_tlbonly() would have issued
>   	 * required IPIs already for us.
>   	 */
>   	if (tlb->fully_unshared_tables) {
> -		tlb_remove_table_sync_one();
> +		if (!tlb_table_flush_implies_ipi_broadcast())
> +			tlb_remove_table_sync_one();
>   		tlb->fully_unshared_tables = false;
>   	}
>   }