Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Yang Shi <shy828301@gmail.com>
To:     naoya.horiguchi@nec.com, hughd@google.com,
        kirill.shutemov@linux.intel.com, willy@infradead.org,
        peterx@redhat.com, osalvador@suse.de, akpm@linux-foundation.org
Cc:     shy828301@gmail.com, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org, linux-kernel@vger.kernel.org
Subject: [v5 PATCH 5/6] mm: shmem: don't truncate page if memory failure happens
Date:   Wed, 20 Oct 2021 14:07:54 -0700
Message-Id: <20211020210755.23964-6-shy828301@gmail.com>
In-Reply-To: <20211020210755.23964-1-shy828301@gmail.com>
References: <20211020210755.23964-1-shy828301@gmail.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

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.

Signed-off-by: Yang Shi <shy828301@gmail.com>
---
 mm/memory-failure.c | 10 +++++++++-
 mm/shmem.c          | 38 +++++++++++++++++++++++++++++++++++---
 mm/userfaultfd.c    |  5 +++++
 3 files changed, 49 insertions(+), 4 deletions(-)

diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index aaeda93d26fb..3603a3acf7b3 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -57,6 +57,7 @@
 #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"
 
@@ -866,6 +867,7 @@ 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);
 
@@ -894,6 +896,12 @@ 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.
 	 *
@@ -903,7 +911,7 @@ static int me_pagecache_clean(struct page_state *ps, struct page *p)
 out:
 	unlock_page(p);
 
-	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 b5860f4a2738..89062ce85db8 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -2456,6 +2456,7 @@ 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 |
@@ -2466,7 +2467,15 @@ 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
@@ -2553,6 +2562,12 @@ 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;
+			}
 		}
 
 		/*
@@ -3114,7 +3129,8 @@ 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);
 		}
@@ -3122,6 +3138,11 @@ 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);
@@ -3772,6 +3793,13 @@ 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,
@@ -3782,7 +3810,7 @@ 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);
 
@@ -4193,6 +4221,10 @@ 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
 	/*
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 7a9008415534..b688d5327177 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -233,6 +233,11 @@ 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)
-- 
2.26.2