From: Yang Shi shy828301@gmail.com
commit a7605426666196c5a460dd3de6f8dac1d3c21f00 upstream.
The current behavior of memory failure is to truncate the page cache regardless of dirty or clean. If the page is dirty the later access will get the obsolete data from disk without any notification to the users. This may cause silent data loss. It is even worse for shmem since shmem is in-memory filesystem, truncating page cache means discarding data blocks. The later read would return all zero.
The right approach is to keep the corrupted page in page cache, any later access would return error for syscalls or SIGBUS for page fault, until the file is truncated, hole punched or removed. The regular storage backed filesystems would be more complicated so this patch is focused on shmem. This also unblock the support for soft offlining shmem THP.
[akpm@linux-foundation.org: coding style fixes] [arnd@arndb.de: fix uninitialized variable use in me_pagecache_clean()] Link: https://lkml.kernel.org/r/20211022064748.4173718-1-arnd@kernel.org [Fix invalid pointer dereference in shmem_read_mapping_page_gfp() with a slight different implementation from what Ajay Garg ajaygargnsit@gmail.com and Muchun Song songmuchun@bytedance.com proposed and reworked the error handling of shmem_write_begin() suggested by Linus] Link: https://lore.kernel.org/linux-mm/20211111084617.6746-1-ajaygargnsit@gmail.co...
Link: https://lkml.kernel.org/r/20211020210755.23964-6-shy828301@gmail.com Link: https://lkml.kernel.org/r/20211116193247.21102-1-shy828301@gmail.com Signed-off-by: Yang Shi shy828301@gmail.com Signed-off-by: Arnd Bergmann arnd@arndb.de Cc: Hugh Dickins hughd@google.com Cc: Kirill A. Shutemov kirill.shutemov@linux.intel.com Cc: Matthew Wilcox willy@infradead.org Cc: Naoya Horiguchi naoya.horiguchi@nec.com Cc: Oscar Salvador osalvador@suse.de Cc: Peter Xu peterx@redhat.com Cc: Ajay Garg ajaygargnsit@gmail.com Cc: Muchun Song songmuchun@bytedance.com Cc: Andy Lavr andy.lavr@gmail.com Signed-off-by: Andrew Morton akpm@linux-foundation.org Signed-off-by: Linus Torvalds torvalds@linux-foundation.org Signed-off-by: Mike Kravetz mike.kravetz@oracle.com --- mm/memory-failure.c | 10 ++++++++- mm/shmem.c | 51 +++++++++++++++++++++++++++++++++++++++------ 2 files changed, 54 insertions(+), 7 deletions(-)
diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 1d37de089008..7d96be8e93b7 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -56,6 +56,7 @@ #include <linux/kfifo.h> #include <linux/ratelimit.h> #include <linux/page-isolation.h> +#include <linux/shmem_fs.h> #include "internal.h" #include "ras/ras_event.h"
@@ -705,6 +706,7 @@ static int me_unknown(struct page_state *ps, struct page *p) static int me_pagecache_clean(struct page_state *ps, struct page *p) { struct address_space *mapping; + bool extra_pins; int ret;
delete_from_lru_cache(p); @@ -731,6 +733,12 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p) return MF_FAILED; }
+ /* + * The shmem page is kept in page cache instead of truncating + * so is expected to have an extra refcount after error-handling. + */ + extra_pins = shmem_mapping(mapping); + /* * Truncation is a bit tricky. Enable it per file system for now. * @@ -738,7 +746,7 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p) */ ret = truncate_error_page(p, page_to_pfn(p), mapping);
- if (has_extra_refcount(ps, p, false)) + if (has_extra_refcount(ps, p, extra_pins)) ret = MF_FAILED;
return ret; diff --git a/mm/shmem.c b/mm/shmem.c index d3d8c5e7a296..8b539033dfe2 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2521,6 +2521,7 @@ shmem_write_begin(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; struct shmem_inode_info *info = SHMEM_I(inode); pgoff_t index = pos >> PAGE_SHIFT; + int ret = 0;
/* i_mutex is held by caller */ if (unlikely(info->seals & (F_SEAL_GROW | @@ -2531,7 +2532,19 @@ shmem_write_begin(struct file *file, struct address_space *mapping, return -EPERM; }
- return shmem_getpage(inode, index, pagep, SGP_WRITE); + ret = shmem_getpage(inode, index, pagep, SGP_WRITE); + + if (ret) + return ret; + + if (PageHWPoison(*pagep)) { + unlock_page(*pagep); + put_page(*pagep); + *pagep = NULL; + return -EIO; + } + + return 0; }
static int @@ -2618,6 +2631,12 @@ static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to) if (sgp == SGP_CACHE) set_page_dirty(page); unlock_page(page); + + if (PageHWPoison(page)) { + put_page(page); + error = -EIO; + break; + } }
/* @@ -3210,7 +3229,8 @@ static const char *shmem_get_link(struct dentry *dentry, page = find_get_page(inode->i_mapping, 0); if (!page) return ERR_PTR(-ECHILD); - if (!PageUptodate(page)) { + if (PageHWPoison(page) || + !PageUptodate(page)) { put_page(page); return ERR_PTR(-ECHILD); } @@ -3218,6 +3238,13 @@ static const char *shmem_get_link(struct dentry *dentry, error = shmem_getpage(inode, 0, &page, SGP_READ); if (error) return ERR_PTR(error); + if (!page) + return ERR_PTR(-ECHILD); + if (PageHWPoison(page)) { + unlock_page(page); + put_page(page); + return ERR_PTR(-ECHILD); + } unlock_page(page); } set_delayed_call(done, shmem_put_link, page); @@ -3866,6 +3893,13 @@ static void shmem_destroy_inodecache(void) kmem_cache_destroy(shmem_inode_cachep); }
+/* Keep the page in page cache instead of truncating it */ +static int shmem_error_remove_page(struct address_space *mapping, + struct page *page) +{ + return 0; +} + static const struct address_space_operations shmem_aops = { .writepage = shmem_writepage, .set_page_dirty = __set_page_dirty_no_writeback, @@ -3876,7 +3910,7 @@ static const struct address_space_operations shmem_aops = { #ifdef CONFIG_MIGRATION .migratepage = migrate_page, #endif - .error_remove_page = generic_error_remove_page, + .error_remove_page = shmem_error_remove_page, };
static const struct file_operations shmem_file_operations = { @@ -4316,9 +4350,14 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping, error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE, gfp, NULL, NULL, NULL); if (error) - page = ERR_PTR(error); - else - unlock_page(page); + return ERR_PTR(error); + + unlock_page(page); + if (PageHWPoison(page)) { + put_page(page); + return ERR_PTR(-EIO); + } + return page; #else /*