mm/khugepaged: stop swapping in page when VM_FAULT_RETRY occurs

When do_swap_page returns VM_FAULT_RETRY, we do not retry here and thus
swap entry will remain in pagetable.  This will result in later failure. 
So stop swapping in pages in this case to save cpu cycles.  As A further
optimization, mmap_lock is released when __collapse_huge_page_swapin()
fails to avoid relocking mmap_lock.  And "swapped_in++" is moved after
error handling to make it more accurate.

Link: https://lkml.kernel.org/r/20220625092816.4856-3-linmiaohe@huawei.com
Signed-off-by: Miaohe Lin <linmiaohe@huawei.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: NeilBrown <neilb@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Yang Shi <shy828301@gmail.com>
Cc: Zach O'Keefe <zokeefe@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 14 insertions, 18 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 34e6b4604aa1..16e98395f362 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -972,8 +972,8 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
  * Bring missing pages in from swap, to complete THP collapse.
  * Only done if khugepaged_scan_pmd believes it is worthwhile.
  *
- * Called and returns without pte mapped or spinlocks held,
- * but with mmap_lock held to protect against vma changes.
+ * Called and returns without pte mapped or spinlocks held.
+ * Note that if false is returned, mmap_lock will be released.
  */
 
 static bool __collapse_huge_page_swapin(struct mm_struct *mm,
@@ -1000,27 +1000,24 @@ static bool __collapse_huge_page_swapin(struct mm_struct *mm,
 			pte_unmap(vmf.pte);
 			continue;
 		}
-		swapped_in++;
 		ret = do_swap_page(&vmf);
 
-		/* do_swap_page returns VM_FAULT_RETRY with released mmap_lock */
+		/*
+		 * do_swap_page returns VM_FAULT_RETRY with released mmap_lock.
+		 * Note we treat VM_FAULT_RETRY as VM_FAULT_ERROR here because
+		 * we do not retry here and swap entry will remain in pagetable
+		 * resulting in later failure.
+		 */
 		if (ret & VM_FAULT_RETRY) {
-			mmap_read_lock(mm);
-			if (hugepage_vma_revalidate(mm, haddr, &vma)) {
-				/* vma is no longer available, don't continue to swapin */
-				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
-				return false;
-			}
-			/* check if the pmd is still valid */
-			if (mm_find_pmd(mm, haddr) != pmd) {
-				trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
-				return false;
-			}
+			trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
+			return false;
 		}
 		if (ret & VM_FAULT_ERROR) {
+			mmap_read_unlock(mm);
 			trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, 0);
 			return false;
 		}
+		swapped_in++;
 	}
 
 	/* Drain LRU add pagevec to remove extra pin on the swapped in pages */
@@ -1086,13 +1083,12 @@ static void collapse_huge_page(struct mm_struct *mm,
 	}
 
 	/*
-	 * __collapse_huge_page_swapin always returns with mmap_lock locked.
-	 * If it fails, we release mmap_lock and jump out_nolock.
+	 * __collapse_huge_page_swapin will return with mmap_lock released
+	 * when it fails. So we jump out_nolock directly in that case.
 	 * Continuing to collapse causes inconsistency.
 	 */
 	if (unmapped && !__collapse_huge_page_swapin(mm, vma, address,
 						     pmd, referenced)) {
-		mmap_read_unlock(mm);
 		goto out_nolock;
 	}