mm: proc: Invalidate TLB after clearing soft-dirty page state

Since commit 0758cd8304 ("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.

Fix this by avoiding the mmu_gather API altogether: managing both the
'tlb_flush_pending' flag on the 'mm_struct' and explicit TLB
invalidation for the sort-dirty path, much like mprotect() does already.

Fixes: 0758cd8304 ("asm-generic/tlb: avoid potential double flush”)
Signed-off-by: Will Deacon <[email protected]>
Signed-off-by: Peter Zijlstra (Intel) <[email protected]>
Reviewed-by: Yu Zhao <[email protected]>
Acked-by: Peter Zijlstra (Intel) <[email protected]>
Acked-by: Linus Torvalds <[email protected]>
Link: https://lkml.kernel.org/r/[email protected]

fs/proc/task_mmu.c

@@ -1210,7 +1210,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 	struct mm_struct *mm;
 	struct vm_area_struct *vma;
 	enum clear_refs_types type;
-	struct mmu_gather tlb;
 	int itype;
 	int rv;
 
@@ -1249,7 +1248,6 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			goto out_unlock;
 		}
 
-		tlb_gather_mmu(&tlb, mm, 0, -1);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			for (vma = mm->mmap; vma; vma = vma->vm_next) {
 				if (!(vma->vm_flags & VM_SOFTDIRTY))
@@ -1258,15 +1256,18 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				vma_set_page_prot(vma);
 			}
 
+			inc_tlb_flush_pending(mm);
 			mmu_notifier_range_init(&range, MMU_NOTIFY_SOFT_DIRTY,
 						0, NULL, mm, 0, -1UL);
 			mmu_notifier_invalidate_range_start(&range);
 		}
 		walk_page_range(mm, 0, mm->highest_vm_end, &clear_refs_walk_ops,
 				&cp);
-		if (type == CLEAR_REFS_SOFT_DIRTY)
+		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			mmu_notifier_invalidate_range_end(&range);
-		tlb_finish_mmu(&tlb, 0, -1);
+			flush_tlb_mm(mm);
+			dec_tlb_flush_pending(mm);
+		}
 out_unlock:
 		mmap_write_unlock(mm);
 out_mm: