Re: [PATCH 4/4] mmu_gather: Force tlb-flush VM_PFNMAP vmas

[Will Deacon <will@kernel.org>]

On Fri, Jul 08, 2022 at 09:18:06AM +0200, Peter Zijlstra wrote:
> Jann reported a race between munmap() and unmap_mapping_range(), where
> unmap_mapping_range() will no-op once unmap_vmas() has unlinked the
> VMA; however munmap() will not yet have invalidated the TLBs.
> 
> Therefore unmap_mapping_range() will complete while there are still
> (stale) TLB entries for the specified range.
> 
> Mitigate this by force flushing TLBs for VM_PFNMAP ranges.
> 
> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
> ---
>  include/asm-generic/tlb.h |   33 +++++++++++++++++----------------
>  1 file changed, 17 insertions(+), 16 deletions(-)
> 
> --- a/include/asm-generic/tlb.h
> +++ b/include/asm-generic/tlb.h
> @@ -303,6 +303,7 @@ struct mmu_gather {
>  	 */
>  	unsigned int		vma_exec : 1;
>  	unsigned int		vma_huge : 1;
> +	unsigned int		vma_pfn  : 1;
>  
>  	unsigned int		batch_count;
>  
> @@ -373,7 +374,6 @@ tlb_update_vma_flags(struct mmu_gather *
>  #else /* CONFIG_MMU_GATHER_NO_RANGE */
>  
>  #ifndef tlb_flush
> -
>  /*
>   * When an architecture does not provide its own tlb_flush() implementation
>   * but does have a reasonably efficient flush_vma_range() implementation
> @@ -393,6 +393,9 @@ static inline void tlb_flush(struct mmu_
>  		flush_tlb_range(&vma, tlb->start, tlb->end);
>  	}
>  }
> +#endif
> +
> +#endif /* CONFIG_MMU_GATHER_NO_RANGE */
>  
>  static inline void
>  tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma)
> @@ -410,17 +413,9 @@ tlb_update_vma_flags(struct mmu_gather *
>  	 */
>  	tlb->vma_huge = is_vm_hugetlb_page(vma);
>  	tlb->vma_exec = !!(vma->vm_flags & VM_EXEC);
> +	tlb->vma_pfn  = !!(vma->vm_flags & VM_PFNMAP);
>  }
>  
> -#else
> -
> -static inline void
> -tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { }
> -
> -#endif
> -
> -#endif /* CONFIG_MMU_GATHER_NO_RANGE */
> -
>  static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb)
>  {
>  	/*
> @@ -507,16 +502,22 @@ static inline void tlb_start_vma(struct
>  
>  static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma)
>  {
> -	if (tlb->fullmm || IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS))
> +	if (tlb->fullmm)
>  		return;
>  
>  	/*
> -	 * Do a TLB flush and reset the range at VMA boundaries; this avoids
> -	 * the ranges growing with the unused space between consecutive VMAs,
> -	 * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on
> -	 * this.
> +	 * VM_PFNMAP is more fragile because the core mm will not track the
> +	 * page mapcount -- there might not be page-frames for these PFNs after
> +	 * all. Force flush TLBs for such ranges to avoid munmap() vs
> +	 * unmap_mapping_range() races.
>  	 */
> -	tlb_flush_mmu_tlbonly(tlb);
> +	if (tlb->vma_pfn || !IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS)) {
> +		/*
> +		 * Do a TLB flush and reset the range at VMA boundaries; this avoids
> +		 * the ranges growing with the unused space between consecutive VMAs.
> +		 */
> +		tlb_flush_mmu_tlbonly(tlb);
> +	}

We already have the vma here, so I'm not sure how much the new 'vma_pfn'
field really buys us over checking the 'vm_flags', but perhaps that's
cleanup for another day.

Acked-by: Will Deacon <will@kernel.org>

Will