Re: [PATCH 4/6] mm: proc: Invalidate TLB after clearing soft-dirty page state

[Yu Zhao]

On Fri, Nov 20, 2020 at 02:35:55PM +0000, Will Deacon wrote:
> Since commit 0758cd830494 ("asm-generic/tlb: avoid potential double flush"),
> TLB invalidation is elided in tlb_finish_mmu() if no entries were batched
> via the tlb_remove_*() functions. Consequently, the page-table modifications
> performed by clear_refs_write() in response to a write to
> /proc/<pid>/clear_refs do not perform TLB invalidation. Although this is
> fine when simply aging the ptes, in the case of clearing the "soft-dirty"
> state we can end up with entries where pte_write() is false, yet a
> writable mapping remains in the TLB.

I don't think we need a TLB flush in this context, same reason as we
don't have one in copy_present_pte() which uses ptep_set_wrprotect()
to write-protect a src PTE.

ptep_modify_prot_start/commit() and ptep_set_wrprotect() guarantee
either the dirty bit is set (when a PTE is still writable) or a PF
happens (when a PTE has become r/o) when h/w page table walker races
with kernel that modifies a PTE using the two APIs.

> Fix this by calling tlb_remove_tlb_entry() for each entry being
> write-protected when cleating soft-dirty.
> 
> Signed-off-by: Will Deacon <will@xxxxxxxxxx>
> ---
>  fs/proc/task_mmu.c | 18 +++++++++++-------
>  1 file changed, 11 insertions(+), 7 deletions(-)
> 
> diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> index cd03ab9087b0..3308292ee5c5 100644
> --- a/fs/proc/task_mmu.c
> +++ b/fs/proc/task_mmu.c
> @@ -1032,11 +1032,12 @@ enum clear_refs_types {
>  
>  struct clear_refs_private {
>  	enum clear_refs_types type;
> +	struct mmu_gather *tlb;
>  };
>  
>  #ifdef CONFIG_MEM_SOFT_DIRTY
>  static inline void clear_soft_dirty(struct vm_area_struct *vma,
> -		unsigned long addr, pte_t *pte)
> +		unsigned long addr, pte_t *pte, struct mmu_gather *tlb)
>  {
>  	/*
>  	 * The soft-dirty tracker uses #PF-s to catch writes
> @@ -1053,6 +1054,7 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
>  		ptent = pte_wrprotect(old_pte);
>  		ptent = pte_clear_soft_dirty(ptent);
>  		ptep_modify_prot_commit(vma, addr, pte, old_pte, ptent);
> +		tlb_remove_tlb_entry(tlb, pte, addr);
>  	} else if (is_swap_pte(ptent)) {
>  		ptent = pte_swp_clear_soft_dirty(ptent);
>  		set_pte_at(vma->vm_mm, addr, pte, ptent);
> @@ -1060,14 +1062,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
>  }
>  #else
>  static inline void clear_soft_dirty(struct vm_area_struct *vma,
> -		unsigned long addr, pte_t *pte)
> +		unsigned long addr, pte_t *pte, struct mmu_gather *tlb)
>  {
>  }
>  #endif
>  
>  #if defined(CONFIG_MEM_SOFT_DIRTY) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
>  static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
> -		unsigned long addr, pmd_t *pmdp)
> +		unsigned long addr, pmd_t *pmdp, struct mmu_gather *tlb)
>  {
>  	pmd_t old, pmd = *pmdp;
>  
> @@ -1081,6 +1083,7 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
>  
>  		pmd = pmd_wrprotect(pmd);
>  		pmd = pmd_clear_soft_dirty(pmd);
> +		tlb_remove_pmd_tlb_entry(tlb, pmdp, addr);
>  
>  		set_pmd_at(vma->vm_mm, addr, pmdp, pmd);
>  	} else if (is_migration_entry(pmd_to_swp_entry(pmd))) {
> @@ -1090,7 +1093,7 @@ static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
>  }
>  #else
>  static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
> -		unsigned long addr, pmd_t *pmdp)
> +		unsigned long addr, pmd_t *pmdp, struct mmu_gather *tlb)
>  {
>  }
>  #endif
> @@ -1107,7 +1110,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
>  	ptl = pmd_trans_huge_lock(pmd, vma);
>  	if (ptl) {
>  		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
> -			clear_soft_dirty_pmd(vma, addr, pmd);
> +			clear_soft_dirty_pmd(vma, addr, pmd, cp->tlb);
>  			goto out;
>  		}
>  
> @@ -1133,7 +1136,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
>  		ptent = *pte;
>  
>  		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
> -			clear_soft_dirty(vma, addr, pte);
> +			clear_soft_dirty(vma, addr, pte, cp->tlb);
>  			continue;
>  		}
>  
> @@ -1212,7 +1215,8 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
>  	if (mm) {
>  		struct mmu_notifier_range range;
>  		struct clear_refs_private cp = {
> -			.type = type,
> +			.type	= type,
> +			.tlb	= &tlb,
>  		};
>  
>  		if (type == CLEAR_REFS_MM_HIWATER_RSS) {
> -- 
> 2.29.2.454.gaff20da3a2-goog
>