mm/khugepaged: recover from poisoned file-backed memory

Make collapse_file roll back when copying pages failed. More concretely:
- extract copying operations into a separate loop
- postpone the updates for nr_none until both scanning and copying
  succeeded
- postpone joining small xarray entries until both scanning and copying
  succeeded
- postpone the update operations to NR_XXX_THPS until both scanning and
  copying succeeded
- for non-SHMEM file, roll back filemap_nr_thps_inc if scan succeeded but
  copying failed

Tested manually:
0. Enable khugepaged on system under test. Mount tmpfs at /mnt/ramdisk.
1. Start a two-thread application. Each thread allocates a chunk of
   non-huge memory buffer from /mnt/ramdisk.
2. Pick 4 random buffer address (2 in each thread) and inject
   uncorrectable memory errors at physical addresses.
3. Signal both threads to make their memory buffer collapsible, i.e.
   calling madvise(MADV_HUGEPAGE).
4. Wait and then check kernel log: khugepaged is able to recover from
   poisoned pages by skipping them.
5. Signal both threads to inspect their buffer contents and make sure no
   data corruption.

Link: https://lkml.kernel.org/r/20230329151121.949896-4-jiaqiyan@google.com
Signed-off-by: Jiaqi Yan <jiaqiyan@google.com>
Reviewed-by: Yang Shi <shy828301@gmail.com>
Acked-by: Hugh Dickins <hughd@google.com>
Cc: David Stevens <stevensd@chromium.org>
Cc: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: "Kirill A. Shutemov" <kirill@shutemov.name>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Naoya Horiguchi <naoya.horiguchi@nec.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Tong Tiangen <tongtiangen@huawei.com>
Cc: Tony Luck <tony.luck@intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 56 insertions, 31 deletions

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index c66933d8a8b8..deea5c5cd9e8 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1877,6 +1877,9 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
 {
 	struct address_space *mapping = file->f_mapping;
 	struct page *hpage;
+	struct page *page;
+	struct page *tmp;
+	struct folio *folio;
 	pgoff_t index = 0, end = start + HPAGE_PMD_NR;
 	LIST_HEAD(pagelist);
 	XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
@@ -1921,8 +1924,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
 
 	xas_set(&xas, start);
 	for (index = start; index < end; index++) {
-		struct page *page = xas_next(&xas);
-		struct folio *folio;
+		page = xas_next(&xas);
 
 		VM_BUG_ON(index != xas.xa_index);
 		if (is_shmem) {
@@ -2116,12 +2118,8 @@ out_unlock:
 		put_page(page);
 		goto xa_unlocked;
 	}
-	nr = thp_nr_pages(hpage);
 
-	if (is_shmem)
-		__mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr);
-	else {
-		__mod_lruvec_page_state(hpage, NR_FILE_THPS, nr);
+	if (!is_shmem) {
 		filemap_nr_thps_inc(mapping);
 		/*
 		 * Paired with smp_mb() in do_dentry_open() to ensure
@@ -2132,21 +2130,10 @@ out_unlock:
 		smp_mb();
 		if (inode_is_open_for_write(mapping->host)) {
 			result = SCAN_FAIL;
-			__mod_lruvec_page_state(hpage, NR_FILE_THPS, -nr);
 			filemap_nr_thps_dec(mapping);
-			goto xa_locked;
 		}
 	}
 
-	if (nr_none) {
-		__mod_lruvec_page_state(hpage, NR_FILE_PAGES, nr_none);
-		/* nr_none is always 0 for non-shmem. */
-		__mod_lruvec_page_state(hpage, NR_SHMEM, nr_none);
-	}
-
-	/* Join all the small entries into a single multi-index entry */
-	xas_set_order(&xas, start, HPAGE_PMD_ORDER);
-	xas_store(&xas, hpage);
 	/* Here we can't get an ENOMEM (because entries were
 	 * previously allocated) But let's check for errors
 	 * (XArray implementation can be changed in the future)
@@ -2164,21 +2151,36 @@ xa_unlocked:
 	try_to_unmap_flush();
 
 	if (result == SCAN_SUCCEED) {
-		struct page *page, *tmp;
-		struct folio *folio;
-
 		/*
 		 * Replacing old pages with new one has succeeded, now we
-		 * need to copy the content and free the old pages.
+		 * attempt to copy the contents.
 		 */
 		index = start;
-		list_for_each_entry_safe(page, tmp, &pagelist, lru) {
+		list_for_each_entry(page, &pagelist, lru) {
 			while (index < page->index) {
 				clear_highpage(hpage + (index % HPAGE_PMD_NR));
 				index++;
 			}
-			copy_highpage(hpage + (page->index % HPAGE_PMD_NR),
-				      page);
+			if (copy_mc_highpage(hpage + (page->index % HPAGE_PMD_NR),
+					     page) > 0) {
+				result = SCAN_COPY_MC;
+				break;
+			}
+			index++;
+		}
+		while (result == SCAN_SUCCEED && index < end) {
+			clear_highpage(hpage + (index % HPAGE_PMD_NR));
+			index++;
+		}
+	}
+
+	nr = thp_nr_pages(hpage);
+	if (result == SCAN_SUCCEED) {
+		/*
+		 * Copying old pages to huge one has succeeded, now we
+		 * need to free the old pages.
+		 */
+		list_for_each_entry_safe(page, tmp, &pagelist, lru) {
 			list_del(&page->lru);
 			page->mapping = NULL;
 			page_ref_unfreeze(page, 1);
@@ -2186,12 +2188,23 @@ xa_unlocked:
 			ClearPageUnevictable(page);
 			unlock_page(page);
 			put_page(page);
-			index++;
 		}
-		while (index < end) {
-			clear_highpage(hpage + (index % HPAGE_PMD_NR));
-			index++;
+
+		xas_lock_irq(&xas);
+		if (is_shmem)
+			__mod_lruvec_page_state(hpage, NR_SHMEM_THPS, nr);
+		else
+			__mod_lruvec_page_state(hpage, NR_FILE_THPS, nr);
+
+		if (nr_none) {
+			__mod_lruvec_page_state(hpage, NR_FILE_PAGES, nr_none);
+			/* nr_none is always 0 for non-shmem. */
+			__mod_lruvec_page_state(hpage, NR_SHMEM, nr_none);
 		}
+		/* Join all the small entries into a single multi-index entry. */
+		xas_set_order(&xas, start, HPAGE_PMD_ORDER);
+		xas_store(&xas, hpage);
+		xas_unlock_irq(&xas);
 
 		folio = page_folio(hpage);
 		folio_mark_uptodate(folio);
@@ -2209,8 +2222,6 @@ xa_unlocked:
 		unlock_page(hpage);
 		hpage = NULL;
 	} else {
-		struct page *page;
-
 		/* Something went wrong: roll back page cache changes */
 		xas_lock_irq(&xas);
 		if (nr_none) {
@@ -2244,6 +2255,20 @@ xa_unlocked:
 			xas_lock_irq(&xas);
 		}
 		VM_BUG_ON(nr_none);
+		/*
+		 * Undo the updates of filemap_nr_thps_inc for non-SHMEM
+		 * file only. This undo is not needed unless failure is
+		 * due to SCAN_COPY_MC.
+		 */
+		if (!is_shmem && result == SCAN_COPY_MC) {
+			filemap_nr_thps_dec(mapping);
+			/*
+			 * Paired with smp_mb() in do_dentry_open() to
+			 * ensure the update to nr_thps is visible.
+			 */
+			smp_mb();
+		}
+
 		xas_unlock_irq(&xas);
 
 		hpage->mapping = NULL;