From: Jiaqi Yan <jiaqiyan@google.com>
To: kirill.shutemov@linux.intel.com, kirill@shutemov.name,
shy828301@gmail.com, tongtiangen@huawei.com,
tony.luck@intel.com, akpm@linux-foundation.org
Cc: naoya.horiguchi@nec.com, linmiaohe@huawei.com,
jiaqiyan@google.com, linux-mm@kvack.org, osalvador@suse.de,
wangkefeng.wang@huawei.com
Subject: [PATCH v10 3/3] mm/khugepaged: recover from poisoned file-backed memory
Date: Sat, 4 Mar 2023 22:51:12 -0800 [thread overview]
Message-ID: <20230305065112.1932255-4-jiaqiyan@google.com> (raw)
In-Reply-To: <20230305065112.1932255-1-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 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.
Signed-off-by: Jiaqi Yan <jiaqiyan@google.com>
---
mm/khugepaged.c | 78 ++++++++++++++++++++++++++++++-------------------
1 file changed, 48 insertions(+), 30 deletions(-)
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index c3c217f6ebc6e..3ea2aa55c2c52 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -1890,6 +1890,9 @@ 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);
@@ -1934,8 +1937,7 @@ 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) {
@@ -2117,10 +2119,7 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
}
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
@@ -2131,21 +2130,10 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
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);
xa_locked:
xas_unlock_irq(&xas);
xa_unlocked:
@@ -2158,21 +2146,35 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
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++;
+ }
+ }
+
+ 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);
@@ -2180,12 +2182,23 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
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);
@@ -2203,8 +2216,6 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
unlock_page(hpage);
hpage = NULL;
} else {
- struct page *page;
-
/* Something went wrong: roll back page cache changes */
xas_lock_irq(&xas);
if (nr_none) {
@@ -2238,6 +2249,13 @@ static int collapse_file(struct mm_struct *mm, unsigned long addr,
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);
hpage->mapping = NULL;
--
2.40.0.rc0.216.gc4246ad0f0-goog
next prev parent reply other threads:[~2023-03-05 6:51 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-03-05 6:51 [PATCH v10 0/3] Memory poison recovery in khugepaged collapsing Jiaqi Yan
2023-03-05 6:51 ` [PATCH v10 1/3] mm/khugepaged: recover from poisoned anonymous memory Jiaqi Yan
2023-03-20 14:42 ` Jiaqi Yan
2023-03-21 0:12 ` Yang Shi
2023-03-23 21:37 ` Yang Shi
2023-03-24 15:34 ` Jiaqi Yan
2023-03-24 20:11 ` Yang Shi
2023-03-24 22:31 ` Jiaqi Yan
2023-03-27 20:46 ` Jiaqi Yan
2023-03-05 6:51 ` [PATCH v10 2/3] mm/hwpoison: introduce copy_mc_highpage Jiaqi Yan
2023-03-05 6:56 ` Jiaqi Yan
2023-03-24 20:24 ` Yang Shi
2023-03-05 6:51 ` Jiaqi Yan [this message]
2023-03-24 21:15 ` [PATCH v10 3/3] mm/khugepaged: recover from poisoned file-backed memory Yang Shi
2023-03-24 22:54 ` Jiaqi Yan
2023-03-25 0:39 ` Hugh Dickins
2023-03-27 21:15 ` 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=20230305065112.1932255-4-jiaqiyan@google.com \
--to=jiaqiyan@google.com \
--cc=akpm@linux-foundation.org \
--cc=kirill.shutemov@linux.intel.com \
--cc=kirill@shutemov.name \
--cc=linmiaohe@huawei.com \
--cc=linux-mm@kvack.org \
--cc=naoya.horiguchi@nec.com \
--cc=osalvador@suse.de \
--cc=shy828301@gmail.com \
--cc=tongtiangen@huawei.com \
--cc=tony.luck@intel.com \
--cc=wangkefeng.wang@huawei.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).