[RFC 06/20] fs/task_mmu: use mmu_gather interface of clear-soft-dirty

[Nadav Amit]

From: Nadav Amit <namit@xxxxxxxxxx>

Use mmu_gather interface in task_mmu instead of
{inc|dec}_tlb_flush_pending(). This would allow to consolidate the code
and to avoid potential bugs.

Signed-off-by: Nadav Amit <namit@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Yu Zhao <yuzhao@xxxxxxxxxx>
Cc: Nick Piggin <npiggin@xxxxxxxxx>
Cc: x86@xxxxxxxxxx
---
 fs/proc/task_mmu.c | 27 ++++++++++++++++++++++++---
 1 file changed, 24 insertions(+), 3 deletions(-)

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 3cec6fbef725..4cd048ffa0f6 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1032,8 +1032,25 @@ enum clear_refs_types {
 
 struct clear_refs_private {
 	enum clear_refs_types type;
+	struct mmu_gather tlb;
 };
 
+static int tlb_pre_vma(unsigned long start, unsigned long end,
+		       struct mm_walk *walk)
+{
+	struct clear_refs_private *cp = walk->private;
+
+	tlb_start_vma(&cp->tlb, walk->vma);
+	return 0;
+}
+
+static void tlb_post_vma(struct mm_walk *walk)
+{
+	struct clear_refs_private *cp = walk->private;
+
+	tlb_end_vma(&cp->tlb, walk->vma);
+}
+
 #ifdef CONFIG_MEM_SOFT_DIRTY
 
 #define is_cow_mapping(flags) (((flags) & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE)
@@ -1140,6 +1157,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 		/* Clear accessed and referenced bits. */
 		pmdp_test_and_clear_young(vma, addr, pmd);
 		test_and_clear_page_young(page);
+		tlb_flush_pmd_range(&cp->tlb, addr, HPAGE_PMD_SIZE);
 		ClearPageReferenced(page);
 out:
 		spin_unlock(ptl);
@@ -1155,6 +1173,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 
 		if (cp->type == CLEAR_REFS_SOFT_DIRTY) {
 			clear_soft_dirty(vma, addr, pte);
+			tlb_flush_pte_range(&cp->tlb, addr, PAGE_SIZE);
 			continue;
 		}
 
@@ -1168,6 +1187,7 @@ static int clear_refs_pte_range(pmd_t *pmd, unsigned long addr,
 		/* Clear accessed and referenced bits. */
 		ptep_test_and_clear_young(vma, addr, pte);
 		test_and_clear_page_young(page);
+		tlb_flush_pte_range(&cp->tlb, addr, PAGE_SIZE);
 		ClearPageReferenced(page);
 	}
 	pte_unmap_unlock(pte - 1, ptl);
@@ -1198,6 +1218,8 @@ static int clear_refs_test_walk(unsigned long start, unsigned long end,
 }
 
 static const struct mm_walk_ops clear_refs_walk_ops = {
+	.pre_vma		= tlb_pre_vma,
+	.post_vma		= tlb_post_vma,
 	.pmd_entry		= clear_refs_pte_range,
 	.test_walk		= clear_refs_test_walk,
 };
@@ -1248,6 +1270,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 			goto out_unlock;
 		}
 
+		tlb_gather_mmu(&cp.tlb, mm);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			for (vma = mm->mmap; vma; vma = vma->vm_next) {
 				if (!(vma->vm_flags & VM_SOFTDIRTY))
@@ -1256,7 +1279,6 @@ 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);
@@ -1265,10 +1287,9 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 				&cp);
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			mmu_notifier_invalidate_range_end(&range);
-			flush_tlb_mm(mm);
-			dec_tlb_flush_pending(mm);
 		}
 out_unlock:
+		tlb_finish_mmu(&cp.tlb);
 		mmap_write_unlock(mm);
 out_mm:
 		mmput(mm);
-- 
2.25.1