All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jiaqi Yan <jiaqiyan@google.com>
To: shy828301@gmail.com, tongtiangen@huawei.com
Cc: tony.luck@intel.com, naoya.horiguchi@nec.com,
	 kirill.shutemov@linux.intel.com, linmiaohe@huawei.com,
	juew@google.com,  linux-mm@kvack.org,
	Jiaqi Yan <jiaqiyan@google.com>
Subject: [RFC v2 2/2] mm: khugepaged: recover from poisoned file-backed memory
Date: Wed,  6 Apr 2022 15:23:51 -0700	[thread overview]
Message-ID: <20220406222351.949927-3-jiaqiyan@google.com> (raw)
In-Reply-To: <20220406222351.949927-1-jiaqiyan@google.com>

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
* for non-SHMEM file, roll back filemap_nr_thps_inc if scan
  succeeded but copying failed

Signed-off-by: Jiaqi Yan <jiaqiyan@google.com>
---
 mm/khugepaged.c | 77 ++++++++++++++++++++++++++++++-------------------
 1 file changed, 48 insertions(+), 29 deletions(-)

diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 8e69a0640e551..08f93f2ea9712 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1710,7 +1710,7 @@ static void collapse_file(struct mm_struct *mm,
 {
 	struct address_space *mapping = file->f_mapping;
 	gfp_t gfp;
-	struct page *new_page;
+	struct page *new_page, *page, *tmp;
 	pgoff_t index, end = start + HPAGE_PMD_NR;
 	LIST_HEAD(pagelist);
 	XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER);
@@ -1766,7 +1766,7 @@ static void collapse_file(struct mm_struct *mm,
 
 	xas_set(&xas, start);
 	for (index = start; index < end; index++) {
-		struct page *page = xas_next(&xas);
+		page = xas_next(&xas);
 
 		VM_BUG_ON(index != xas.xa_index);
 		if (is_shmem) {
@@ -1938,10 +1938,7 @@ static void collapse_file(struct mm_struct *mm,
 	}
 	nr = thp_nr_pages(new_page);
 
-	if (is_shmem)
-		__mod_lruvec_page_state(new_page, NR_SHMEM_THPS, nr);
-	else {
-		__mod_lruvec_page_state(new_page, NR_FILE_THPS, nr);
+	if (!is_shmem) {
 		filemap_nr_thps_inc(mapping);
 		/*
 		 * Paired with smp_mb() in do_dentry_open() to ensure
@@ -1952,40 +1949,44 @@ static void collapse_file(struct mm_struct *mm,
 		smp_mb();
 		if (inode_is_open_for_write(mapping->host)) {
 			result = SCAN_FAIL;
-			__mod_lruvec_page_state(new_page, NR_FILE_THPS, -nr);
 			filemap_nr_thps_dec(mapping);
 			goto xa_locked;
 		}
 	}
 
-	if (nr_none) {
-		__mod_lruvec_page_state(new_page, NR_FILE_PAGES, nr_none);
-		if (is_shmem)
-			__mod_lruvec_page_state(new_page, 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, new_page);
 xa_locked:
 	xas_unlock_irq(&xas);
 xa_unlocked:
 
 	if (result == SCAN_SUCCEED) {
-		struct page *page, *tmp;
-
 		/*
 		 * 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(new_page + (index % HPAGE_PMD_NR));
 				index++;
 			}
-			copy_highpage(new_page + (page->index % HPAGE_PMD_NR),
-					page);
+			if (copy_highpage_mc(new_page + (page->index % HPAGE_PMD_NR), page)) {
+				result = SCAN_COPY_MC;
+				break;
+			}
+			index++;
+		}
+		while (result == SCAN_SUCCEED && index < end) {
+			clear_highpage(new_page + (page->index % HPAGE_PMD_NR));
+			index++;
+		}
+	}
+
+	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);
@@ -1993,12 +1994,23 @@ static void collapse_file(struct mm_struct *mm,
 			ClearPageUnevictable(page);
 			unlock_page(page);
 			put_page(page);
-			index++;
 		}
-		while (index < end) {
-			clear_highpage(new_page + (index % HPAGE_PMD_NR));
-			index++;
+
+		xas_lock_irq(&xas);
+		if (is_shmem)
+			__mod_lruvec_page_state(new_page, NR_SHMEM_THPS, nr);
+		else
+			__mod_lruvec_page_state(new_page, NR_FILE_THPS, nr);
+
+		if (nr_none) {
+			__mod_lruvec_page_state(new_page, NR_FILE_PAGES, nr_none);
+			if (is_shmem)
+				__mod_lruvec_page_state(new_page, 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, new_page);
+		xas_unlock_irq(&xas);
 
 		SetPageUptodate(new_page);
 		page_ref_add(new_page, HPAGE_PMD_NR - 1);
@@ -2014,9 +2026,9 @@ static void collapse_file(struct mm_struct *mm,
 
 		khugepaged_pages_collapsed++;
 	} else {
-		struct page *page;
-
-		/* Something went wrong: roll back page cache changes */
+		/*
+		 * Something went wrong: roll back page cache changes
+		 */
 		xas_lock_irq(&xas);
 		mapping->nrpages -= nr_none;
 
@@ -2049,6 +2061,13 @@ static void collapse_file(struct mm_struct *mm,
 			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);
+
 		xas_unlock_irq(&xas);
 
 		new_page->mapping = NULL;
-- 
2.35.1.1178.g4f1659d476-goog



  parent reply	other threads:[~2022-04-06 22:25 UTC|newest]

Thread overview: 5+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2022-04-06 22:23 [RFC v2 0/2] Memory poison recovery in khugepaged collapsing Jiaqi Yan
2022-04-06 22:23 ` [RFC v2 1/2] mm: khugepaged: recover from poisoned anonymous memory Jiaqi Yan
2022-04-06 22:23 ` Jiaqi Yan [this message]
  -- strict thread matches above, loose matches on Subject: below --
2022-04-29  0:09 [RFC v2 0/2] Memory poison recovery in khugepaged collapsing Jiaqi Yan
2022-04-29  0:09 ` [RFC v2 2/2] mm: khugepaged: recover from poisoned file-backed memory Jiaqi Yan
2022-04-05 20:51 [RFC v2 0/2] Memory poison recovery in khugepaged collapsing Jiaqi Yan
2022-04-05 20:51 ` [RFC v2 2/2] mm: khugepaged: recover from poisoned file-backed memory Jiaqi Yan

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20220406222351.949927-3-jiaqiyan@google.com \
    --to=jiaqiyan@google.com \
    --cc=juew@google.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linmiaohe@huawei.com \
    --cc=linux-mm@kvack.org \
    --cc=naoya.horiguchi@nec.com \
    --cc=shy828301@gmail.com \
    --cc=tongtiangen@huawei.com \
    --cc=tony.luck@intel.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.