The patch titled Subject: mm/khugepaged: recover from poisoned file-backed memory has been added to the -mm mm-unstable branch. Its filename is mm-khugepaged-recover-from-poisoned-file-backed-memory.patch This patch will shortly appear at https://git.kernel.org/pub/scm/linux/kernel/git/akpm/25-new.git/tree/patches/mm-khugepaged-recover-from-poisoned-file-backed-memory.patch This patch will later appear in the mm-unstable branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/process/submit-checklist.rst when testing your code *** The -mm tree is included into linux-next via the mm-everything branch at git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm and is updated there every 2-3 working days ------------------------------------------------------ From: Jiaqi Yan <jiaqiyan@xxxxxxxxxx> Subject: mm/khugepaged: recover from poisoned file-backed memory Date: Wed, 29 Mar 2023 08:11:21 -0700 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@xxxxxxxxxx Signed-off-by: Jiaqi Yan <jiaqiyan@xxxxxxxxxx> Cc: David Stevens <stevensd@xxxxxxxxxxxx> Cc: Hugh Dickins <hughd@xxxxxxxxxx> Cc: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx> Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx> Cc: "Kirill A. Shutemov" <kirill@xxxxxxxxxxxxx> Cc: Miaohe Lin <linmiaohe@xxxxxxxxxx> Cc: Naoya Horiguchi <naoya.horiguchi@xxxxxxx> Cc: Oscar Salvador <osalvador@xxxxxxx> Cc: Tong Tiangen <tongtiangen@xxxxxxxxxx> Cc: Tony Luck <tony.luck@xxxxxxxxx> Cc: Yang Shi <shy828301@xxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/khugepaged.c | 88 +++++++++++++++++++++++++++++----------------- 1 file changed, 56 insertions(+), 32 deletions(-) --- a/mm/khugepaged.c~mm-khugepaged-recover-from-poisoned-file-backed-memory +++ a/mm/khugepaged.c @@ -1872,6 +1872,9 @@ static int collapse_file(struct mm_struc { 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); @@ -1916,8 +1919,7 @@ static int collapse_file(struct mm_struc 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) { @@ -2097,12 +2099,8 @@ 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 @@ -2113,21 +2111,9 @@ 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); xa_locked: xas_unlock_irq(&xas); xa_unlocked: @@ -2140,21 +2126,36 @@ 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); @@ -2162,12 +2163,23 @@ 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); @@ -2185,8 +2197,6 @@ 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) { @@ -2220,6 +2230,20 @@ 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; _ Patches currently in -mm which might be from jiaqiyan@xxxxxxxxxx are mm-khugepaged-recover-from-poisoned-anonymous-memory.patch mm-hwpoison-introduce-copy_mc_highpage.patch mm-khugepaged-recover-from-poisoned-file-backed-memory.patch