mm: shmem: don't truncate page if memory failure happens

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.

[arnd@arndb.de: fix uninitialized variable use in me_pagecache_clean()]
  Link: https://lkml.kernel.org/r/20211022064748.4173718-1-arnd@kernel.org

Link: https://lkml.kernel.org/r/20211020210755.23964-6-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>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

mm/memory-failure.c

@@ -58,6 +58,7 @@
 #include <linux/ratelimit.h>
 #include <linux/page-isolation.h>
 #include <linux/pagewalk.h>
+#include <linux/shmem_fs.h>
 #include "internal.h"
 #include "ras/ras_event.h"
 
@@ -867,6 +868,7 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p)
 {
 	int ret;
 	struct address_space *mapping;
+	bool extra_pins;
 
 	delete_from_lru_cache(p);
 
@@ -895,18 +897,24 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p)
 		goto out;
 	}
 
+	/*
+	 * 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.
 	 *
 	 * Open: to take i_rwsem or not for this? Right now we don't.
 	 */
 	ret = truncate_error_page(p, page_to_pfn(p), mapping);
+	if (has_extra_refcount(ps, p, extra_pins))
+		ret = MF_FAILED;
+
 out:
 	unlock_page(p);
 
-	if (has_extra_refcount(ps, p, false))
-		ret = MF_FAILED;
-
 	return ret;
 }
 

mm/shmem.c

@@ -2454,6 +2454,7 @@ 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_rwsem is held by caller */
 	if (unlikely(info->seals & (F_SEAL_GROW |
@@ -2464,7 +2465,15 @@ 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 (*pagep && PageHWPoison(*pagep)) {
+		unlock_page(*pagep);
+		put_page(*pagep);
+		ret = -EIO;
+	}
+
+	return ret;
 }
 
 static int
@@ -2551,6 +2560,12 @@ 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;
+			}
 		}
 
 		/*
@@ -3112,7 +3127,8 @@ 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);
 		}
@@ -3120,6 +3136,11 @@ 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 && PageHWPoison(page)) {
+			unlock_page(page);
+			put_page(page);
+			return ERR_PTR(-ECHILD);
+		}
 		unlock_page(page);
 	}
 	set_delayed_call(done, shmem_put_link, page);
@@ -3770,6 +3791,13 @@ 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;
+}
+
 const struct address_space_operations shmem_aops = {
 	.writepage	= shmem_writepage,
 	.set_page_dirty	= __set_page_dirty_no_writeback,
@@ -3780,7 +3808,7 @@ 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,
 };
 EXPORT_SYMBOL(shmem_aops);
 
@@ -4191,6 +4219,10 @@ struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 		page = ERR_PTR(error);
 	else
 		unlock_page(page);
+
+	if (PageHWPoison(page))
+		page = ERR_PTR(-EIO);
+
 	return page;
 #else
 	/*

mm/userfaultfd.c

@@ -232,6 +232,11 @@ static int mcontinue_atomic_pte(struct mm_struct *dst_mm,
 		goto out;
 	}
 
+	if (PageHWPoison(page)) {
+		ret = -EIO;
+		goto out_release;
+	}
+
 	ret = mfill_atomic_install_pte(dst_mm, dst_pmd, dst_vma, dst_addr,
 				       page, false, wp_copy);
 	if (ret)