summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2017-02-20 18:24:39 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-02-20 18:24:39 -0800
commitcab7076a185e1e27f6879325e4da762424c3f1c9 (patch)
treeeb9274ba3b306bce14c581368579677775814088 /fs/ext4
parent6c24337f22115d669e24ce990842dab667371b4d (diff)
parente9be2ac7c09cabcbbbb12b0869e49b7a715d6fb5 (diff)
downloadlinux-cab7076a185e1e27f6879325e4da762424c3f1c9.tar.bz2
Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 updates from Ted Ts'o: "For this cycle we add support for the shutdown ioctl, which is primarily used for testing, but which can be useful on production systems when a scratch volume is being destroyed and the data on it doesn't need to be saved. This found (and we fixed) a number of bugs with ext4's recovery to corrupted file system --- the bugs increased the amount of data that could be potentially lost, and in the case of the inline data feature, could cause the kernel to BUG. Also included are a number of other bug fixes, including in ext4's fscrypt, DAX, inline data support" * tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (26 commits) ext4: rename EXT4_IOC_GOINGDOWN to EXT4_IOC_SHUTDOWN ext4: fix fencepost in s_first_meta_bg validation ext4: don't BUG when truncating encrypted inodes on the orphan list ext4: do not use stripe_width if it is not set ext4: fix stripe-unaligned allocations dax: assert that i_rwsem is held exclusive for writes ext4: fix DAX write locking ext4: add EXT4_IOC_GOINGDOWN ioctl ext4: add shutdown bit and check for it ext4: rename s_resize_flags to s_ext4_flags ext4: return EROFS if device is r/o and journal replay is needed ext4: preserve the needs_recovery flag when the journal is aborted jbd2: don't leak modified metadata buffers on an aborted journal ext4: fix inline data error paths ext4: move halfmd4 into hash.c directly ext4: fix use-after-iput when fscrypt contexts are inconsistent jbd2: fix use after free in kjournald2() ext4: fix data corruption in data=journal mode ext4: trim allocation requests to group size ext4: replace BUG_ON with WARN_ON in mb_find_extent() ...
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/ext4.h28
-rw-r--r--fs/ext4/ext4_jbd2.c11
-rw-r--r--fs/ext4/extents.c27
-rw-r--r--fs/ext4/file.c22
-rw-r--r--fs/ext4/fsync.c3
-rw-r--r--fs/ext4/hash.c71
-rw-r--r--fs/ext4/ialloc.c3
-rw-r--r--fs/ext4/inline.c123
-rw-r--r--fs/ext4/inode.c79
-rw-r--r--fs/ext4/ioctl.c50
-rw-r--r--fs/ext4/mballoc.c25
-rw-r--r--fs/ext4/namei.c18
-rw-r--r--fs/ext4/page-io.c2
-rw-r--r--fs/ext4/resize.c5
-rw-r--r--fs/ext4/super.c47
-rw-r--r--fs/ext4/xattr.c33
-rw-r--r--fs/ext4/xattr.h32
17 files changed, 446 insertions, 133 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index a5c756b80b7d..01d52b98f9a7 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -683,6 +683,16 @@ struct fsxattr {
#define EXT4_IOC_FSGETXATTR FS_IOC_FSGETXATTR
#define EXT4_IOC_FSSETXATTR FS_IOC_FSSETXATTR
+#define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
+
+/*
+ * Flags for going down operation
+ */
+#define EXT4_GOING_FLAGS_DEFAULT 0x0 /* going down */
+#define EXT4_GOING_FLAGS_LOGFLUSH 0x1 /* flush log but not data */
+#define EXT4_GOING_FLAGS_NOLOGFLUSH 0x2 /* don't flush log nor data */
+
+
#if defined(__KERNEL__) && defined(CONFIG_COMPAT)
/*
* ioctl commands in 32 bit emulation
@@ -1403,8 +1413,7 @@ struct ext4_sb_info {
struct journal_s *s_journal;
struct list_head s_orphan;
struct mutex s_orphan_lock;
- unsigned long s_resize_flags; /* Flags indicating if there
- is a resizer */
+ unsigned long s_ext4_flags; /* Ext4 superblock flags */
unsigned long s_commit_interval;
u32 s_max_batch_time;
u32 s_min_batch_time;
@@ -1838,6 +1847,18 @@ static inline bool ext4_has_incompat_features(struct super_block *sb)
}
/*
+ * Superblock flags
+ */
+#define EXT4_FLAGS_RESIZING 0
+#define EXT4_FLAGS_SHUTDOWN 1
+
+static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
+{
+ return test_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+}
+
+
+/*
* Default values for user and/or group using reserved blocks
*/
#define EXT4_DEF_RESUID 0
@@ -3005,7 +3026,7 @@ extern int ext4_inline_data_fiemap(struct inode *inode,
extern int ext4_try_to_evict_inline_data(handle_t *handle,
struct inode *inode,
int needed);
-extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline);
+extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
extern int ext4_convert_inline_data(struct inode *inode);
@@ -3199,7 +3220,6 @@ static inline void ext4_inode_resume_unlocked_dio(struct inode *inode)
EXT4_WQ_HASH_SZ])
extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
-#define EXT4_RESIZING 0
extern int ext4_resize_begin(struct super_block *sb);
extern void ext4_resize_end(struct super_block *sb);
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index e770c1ee4613..dd106b1d5d89 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -43,6 +43,10 @@ static int ext4_journal_check_start(struct super_block *sb)
journal_t *journal;
might_sleep();
+
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+ return -EIO;
+
if (sb->s_flags & MS_RDONLY)
return -EROFS;
WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
@@ -161,6 +165,13 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
might_sleep();
if (ext4_handle_valid(handle)) {
+ struct super_block *sb;
+
+ sb = handle->h_transaction->t_journal->j_private;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) {
+ jbd2_journal_abort_handle(handle);
+ return -EIO;
+ }
err = jbd2_journal_get_write_access(handle, bh);
if (err)
ext4_journal_abort_handle(where, line, __func__, bh,
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 3e295d3350a9..2a97dff87b96 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -5334,7 +5334,8 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
ext4_lblk_t stop, *iterator, ex_start, ex_end;
/* Let path point to the last extent */
- path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+ EXT4_EX_NOCACHE);
if (IS_ERR(path))
return PTR_ERR(path);
@@ -5343,15 +5344,15 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
if (!extent)
goto out;
- stop = le32_to_cpu(extent->ee_block) +
- ext4_ext_get_actual_len(extent);
+ stop = le32_to_cpu(extent->ee_block);
/*
* In case of left shift, Don't start shifting extents until we make
* sure the hole is big enough to accommodate the shift.
*/
if (SHIFT == SHIFT_LEFT) {
- path = ext4_find_extent(inode, start - 1, &path, 0);
+ path = ext4_find_extent(inode, start - 1, &path,
+ EXT4_EX_NOCACHE);
if (IS_ERR(path))
return PTR_ERR(path);
depth = path->p_depth;
@@ -5383,9 +5384,14 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
else
iterator = &stop;
- /* Its safe to start updating extents */
- while (start < stop) {
- path = ext4_find_extent(inode, *iterator, &path, 0);
+ /*
+ * Its safe to start updating extents. Start and stop are unsigned, so
+ * in case of right shift if extent with 0 block is reached, iterator
+ * becomes NULL to indicate the end of the loop.
+ */
+ while (iterator && start <= stop) {
+ path = ext4_find_extent(inode, *iterator, &path,
+ EXT4_EX_NOCACHE);
if (IS_ERR(path))
return PTR_ERR(path);
depth = path->p_depth;
@@ -5412,8 +5418,11 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
ext4_ext_get_actual_len(extent);
} else {
extent = EXT_FIRST_EXTENT(path[depth].p_hdr);
- *iterator = le32_to_cpu(extent->ee_block) > 0 ?
- le32_to_cpu(extent->ee_block) - 1 : 0;
+ if (le32_to_cpu(extent->ee_block) > 0)
+ *iterator = le32_to_cpu(extent->ee_block) - 1;
+ else
+ /* Beginning is reached, end of the loop */
+ iterator = NULL;
/* Update path extent in case we need to stop */
while (le32_to_cpu(extent->ee_block) < start)
extent++;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d663d3d7c81c..87e11dfe3cde 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -57,6 +57,9 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
+ return -EIO;
+
if (!iov_iter_count(to))
return 0; /* skip atime */
@@ -175,7 +178,6 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
{
struct inode *inode = file_inode(iocb->ki_filp);
ssize_t ret;
- bool overwrite = false;
inode_lock(inode);
ret = ext4_write_checks(iocb, from);
@@ -188,16 +190,9 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
if (ret)
goto out;
- if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
- overwrite = true;
- downgrade_write(&inode->i_rwsem);
- }
ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
out:
- if (!overwrite)
- inode_unlock(inode);
- else
- inode_unlock_shared(inode);
+ inode_unlock(inode);
if (ret > 0)
ret = generic_write_sync(iocb, ret);
return ret;
@@ -213,6 +208,9 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
int overwrite = 0;
ssize_t ret;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
#ifdef CONFIG_FS_DAX
if (IS_DAX(inode))
return ext4_dax_write_iter(iocb, from);
@@ -348,6 +346,9 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
{
struct inode *inode = file->f_mapping->host;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
if (ext4_encrypted_inode(inode)) {
int err = fscrypt_get_encryption_info(inode);
if (err)
@@ -375,6 +376,9 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
char buf[64], *cp;
int ret;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
!(sb->s_flags & MS_RDONLY))) {
sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 88effb1053c7..9d549608fd30 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -100,6 +100,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
tid_t commit_tid;
bool needs_barrier = false;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
J_ASSERT(ext4_journal_current_handle() == NULL);
trace_ext4_sync_file_enter(file, datasync);
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index e026aa941fd5..38b8a96eb97c 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -10,7 +10,8 @@
*/
#include <linux/fs.h>
-#include <linux/cryptohash.h>
+#include <linux/compiler.h>
+#include <linux/bitops.h>
#include "ext4.h"
#define DELTA 0x9E3779B9
@@ -32,6 +33,74 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
buf[1] += b1;
}
+/* F, G and H are basic MD4 functions: selection, majority, parity */
+#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
+#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z)))
+#define H(x, y, z) ((x) ^ (y) ^ (z))
+
+/*
+ * The generic round function. The application is so specific that
+ * we don't bother protecting all the arguments with parens, as is generally
+ * good macro practice, in favor of extra legibility.
+ * Rotation is separate from addition to prevent recomputation
+ */
+#define ROUND(f, a, b, c, d, x, s) \
+ (a += f(b, c, d) + x, a = rol32(a, s))
+#define K1 0
+#define K2 013240474631UL
+#define K3 015666365641UL
+
+/*
+ * Basic cut-down MD4 transform. Returns only 32 bits of result.
+ */
+static __u32 half_md4_transform(__u32 buf[4], __u32 const in[8])
+{
+ __u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3];
+
+ /* Round 1 */
+ ROUND(F, a, b, c, d, in[0] + K1, 3);
+ ROUND(F, d, a, b, c, in[1] + K1, 7);
+ ROUND(F, c, d, a, b, in[2] + K1, 11);
+ ROUND(F, b, c, d, a, in[3] + K1, 19);
+ ROUND(F, a, b, c, d, in[4] + K1, 3);
+ ROUND(F, d, a, b, c, in[5] + K1, 7);
+ ROUND(F, c, d, a, b, in[6] + K1, 11);
+ ROUND(F, b, c, d, a, in[7] + K1, 19);
+
+ /* Round 2 */
+ ROUND(G, a, b, c, d, in[1] + K2, 3);
+ ROUND(G, d, a, b, c, in[3] + K2, 5);
+ ROUND(G, c, d, a, b, in[5] + K2, 9);
+ ROUND(G, b, c, d, a, in[7] + K2, 13);
+ ROUND(G, a, b, c, d, in[0] + K2, 3);
+ ROUND(G, d, a, b, c, in[2] + K2, 5);
+ ROUND(G, c, d, a, b, in[4] + K2, 9);
+ ROUND(G, b, c, d, a, in[6] + K2, 13);
+
+ /* Round 3 */
+ ROUND(H, a, b, c, d, in[3] + K3, 3);
+ ROUND(H, d, a, b, c, in[7] + K3, 9);
+ ROUND(H, c, d, a, b, in[2] + K3, 11);
+ ROUND(H, b, c, d, a, in[6] + K3, 15);
+ ROUND(H, a, b, c, d, in[1] + K3, 3);
+ ROUND(H, d, a, b, c, in[5] + K3, 9);
+ ROUND(H, c, d, a, b, in[0] + K3, 11);
+ ROUND(H, b, c, d, a, in[4] + K3, 15);
+
+ buf[0] += a;
+ buf[1] += b;
+ buf[2] += c;
+ buf[3] += d;
+
+ return buf[1]; /* "most hashed" word */
+}
+#undef ROUND
+#undef K1
+#undef K2
+#undef K3
+#undef F
+#undef G
+#undef H
/* The old legacy hash */
static __u32 dx_hack_hash_unsigned(const char *name, int len)
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index f372fc431b8e..b14bae2598bc 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -764,6 +764,9 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
if (!dir || !dir->i_nlink)
return ERR_PTR(-EPERM);
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+ return ERR_PTR(-EIO);
+
if ((ext4_encrypted_inode(dir) ||
DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) &&
(S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 437df6a1a841..30a9f210d1e3 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -215,6 +215,9 @@ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
struct ext4_inode *raw_inode;
int cp_len = 0;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return;
+
BUG_ON(!EXT4_I(inode)->i_inline_off);
BUG_ON(pos + len > EXT4_I(inode)->i_inline_size);
@@ -381,7 +384,7 @@ out:
static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
unsigned int len)
{
- int ret, size;
+ int ret, size, no_expand;
struct ext4_inode_info *ei = EXT4_I(inode);
if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA))
@@ -391,15 +394,14 @@ static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
if (size < len)
return -ENOSPC;
- down_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_lock_xattr(inode, &no_expand);
if (ei->i_inline_off)
ret = ext4_update_inline_data(handle, inode, len);
else
ret = ext4_create_inline_data(handle, inode, len);
- up_write(&EXT4_I(inode)->xattr_sem);
-
+ ext4_write_unlock_xattr(inode, &no_expand);
return ret;
}
@@ -533,7 +535,7 @@ static int ext4_convert_inline_data_to_extent(struct address_space *mapping,
struct inode *inode,
unsigned flags)
{
- int ret, needed_blocks;
+ int ret, needed_blocks, no_expand;
handle_t *handle = NULL;
int retries = 0, sem_held = 0;
struct page *page = NULL;
@@ -573,7 +575,7 @@ retry:
goto out;
}
- down_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_lock_xattr(inode, &no_expand);
sem_held = 1;
/* If some one has already done this for us, just exit. */
if (!ext4_has_inline_data(inode)) {
@@ -610,7 +612,7 @@ retry:
put_page(page);
page = NULL;
ext4_orphan_add(handle, inode);
- up_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_unlock_xattr(inode, &no_expand);
sem_held = 0;
ext4_journal_stop(handle);
handle = NULL;
@@ -636,7 +638,7 @@ out:
put_page(page);
}
if (sem_held)
- up_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_unlock_xattr(inode, &no_expand);
if (handle)
ext4_journal_stop(handle);
brelse(iloc.bh);
@@ -729,7 +731,7 @@ convert:
int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
unsigned copied, struct page *page)
{
- int ret;
+ int ret, no_expand;
void *kaddr;
struct ext4_iloc iloc;
@@ -747,7 +749,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
goto out;
}
- down_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_lock_xattr(inode, &no_expand);
BUG_ON(!ext4_has_inline_data(inode));
kaddr = kmap_atomic(page);
@@ -757,7 +759,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
/* clear page dirty so that writepages wouldn't work for us. */
ClearPageDirty(page);
- up_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_unlock_xattr(inode, &no_expand);
brelse(iloc.bh);
out:
return copied;
@@ -768,7 +770,7 @@ ext4_journalled_write_inline_data(struct inode *inode,
unsigned len,
struct page *page)
{
- int ret;
+ int ret, no_expand;
void *kaddr;
struct ext4_iloc iloc;
@@ -778,11 +780,11 @@ ext4_journalled_write_inline_data(struct inode *inode,
return NULL;
}
- down_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_lock_xattr(inode, &no_expand);
kaddr = kmap_atomic(page);
ext4_write_inline_data(inode, &iloc, kaddr, 0, len);
kunmap_atomic(kaddr);
- up_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_unlock_xattr(inode, &no_expand);
return iloc.bh;
}
@@ -944,8 +946,15 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
struct page *page)
{
int i_size_changed = 0;
+ int ret;
- copied = ext4_write_inline_data_end(inode, pos, len, copied, page);
+ ret = ext4_write_inline_data_end(inode, pos, len, copied, page);
+ if (ret < 0) {
+ unlock_page(page);
+ put_page(page);
+ return ret;
+ }
+ copied = ret;
/*
* No need to use i_size_read() here, the i_size
@@ -1043,7 +1052,6 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
dir->i_mtime = dir->i_ctime = current_time(dir);
ext4_update_dx_flag(dir);
dir->i_version++;
- ext4_mark_inode_dirty(handle, dir);
return 1;
}
@@ -1259,7 +1267,7 @@ out:
int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
struct inode *dir, struct inode *inode)
{
- int ret, inline_size;
+ int ret, inline_size, no_expand;
void *inline_start;
struct ext4_iloc iloc;
@@ -1267,7 +1275,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
if (ret)
return ret;
- down_write(&EXT4_I(dir)->xattr_sem);
+ ext4_write_lock_xattr(dir, &no_expand);
if (!ext4_has_inline_data(dir))
goto out;
@@ -1312,8 +1320,8 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
ret = ext4_convert_inline_data_nolock(handle, dir, &iloc);
out:
+ ext4_write_unlock_xattr(dir, &no_expand);
ext4_mark_inode_dirty(handle, dir);
- up_write(&EXT4_I(dir)->xattr_sem);
brelse(iloc.bh);
return ret;
}
@@ -1673,7 +1681,7 @@ int ext4_delete_inline_entry(handle_t *handle,
struct buffer_head *bh,
int *has_inline_data)
{
- int err, inline_size;
+ int err, inline_size, no_expand;
struct ext4_iloc iloc;
void *inline_start;
@@ -1681,7 +1689,7 @@ int ext4_delete_inline_entry(handle_t *handle,
if (err)
return err;
- down_write(&EXT4_I(dir)->xattr_sem);
+ ext4_write_lock_xattr(dir, &no_expand);
if (!ext4_has_inline_data(dir)) {
*has_inline_data = 0;
goto out;
@@ -1709,13 +1717,11 @@ int ext4_delete_inline_entry(handle_t *handle,
if (err)
goto out;
- err = ext4_mark_inode_dirty(handle, dir);
- if (unlikely(err))
- goto out;
-
ext4_show_inline_dir(dir, iloc.bh, inline_start, inline_size);
out:
- up_write(&EXT4_I(dir)->xattr_sem);
+ ext4_write_unlock_xattr(dir, &no_expand);
+ if (likely(err == 0))
+ err = ext4_mark_inode_dirty(handle, dir);
brelse(iloc.bh);
if (err != -ENOENT)
ext4_std_error(dir->i_sb, err);
@@ -1814,11 +1820,11 @@ out:
int ext4_destroy_inline_data(handle_t *handle, struct inode *inode)
{
- int ret;
+ int ret, no_expand;
- down_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_lock_xattr(inode, &no_expand);
ret = ext4_destroy_inline_data_nolock(handle, inode);
- up_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_unlock_xattr(inode, &no_expand);
return ret;
}
@@ -1900,10 +1906,10 @@ out:
return error;
}
-void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
+int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
{
handle_t *handle;
- int inline_size, value_len, needed_blocks;
+ int inline_size, value_len, needed_blocks, no_expand, err = 0;
size_t i_size;
void *value = NULL;
struct ext4_xattr_ibody_find is = {
@@ -1918,19 +1924,19 @@ void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
needed_blocks = ext4_writepage_trans_blocks(inode);
handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks);
if (IS_ERR(handle))
- return;
+ return PTR_ERR(handle);
- down_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_lock_xattr(inode, &no_expand);
if (!ext4_has_inline_data(inode)) {
*has_inline = 0;
ext4_journal_stop(handle);
- return;
+ return 0;
}
- if (ext4_orphan_add(handle, inode))
+ if ((err = ext4_orphan_add(handle, inode)) != 0)
goto out;
- if (ext4_get_inode_loc(inode, &is.iloc))
+ if ((err = ext4_get_inode_loc(inode, &is.iloc)) != 0)
goto out;
down_write(&EXT4_I(inode)->i_data_sem);
@@ -1941,24 +1947,29 @@ void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
if (i_size < inline_size) {
/* Clear the content in the xattr space. */
if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) {
- if (ext4_xattr_ibody_find(inode, &i, &is))
+ if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0)
goto out_error;
BUG_ON(is.s.not_found);
value_len = le32_to_cpu(is.s.here->e_value_size);
value = kmalloc(value_len, GFP_NOFS);
- if (!value)
+ if (!value) {
+ err = -ENOMEM;
goto out_error;
+ }
- if (ext4_xattr_ibody_get(inode, i.name_index, i.name,
- value, value_len))
+ err = ext4_xattr_ibody_get(inode, i.name_index,
+ i.name, value, value_len);
+ if (err <= 0)
goto out_error;
i.value = value;
i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ?
i_size - EXT4_MIN_INLINE_DATA_SIZE : 0;
- if (ext4_xattr_ibody_inline_set(handle, inode, &i, &is))
+ err = ext4_xattr_ibody_inline_set(handle, inode,
+ &i, &is);
+ if (err)
goto out_error;
}
@@ -1978,23 +1989,24 @@ out_error:
up_write(&EXT4_I(inode)->i_data_sem);
out:
brelse(is.iloc.bh);
- up_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_unlock_xattr(inode, &no_expand);
kfree(value);
if (inode->i_nlink)
ext4_orphan_del(handle, inode);
- inode->i_mtime = inode->i_ctime = current_time(inode);
- ext4_mark_inode_dirty(handle, inode);
- if (IS_SYNC(inode))
- ext4_handle_sync(handle);
-
+ if (err == 0) {
+ inode->i_mtime = inode->i_ctime = current_time(inode);
+ err = ext4_mark_inode_dirty(handle, inode);
+ if (IS_SYNC(inode))
+ ext4_handle_sync(handle);
+ }
ext4_journal_stop(handle);
- return;
+ return err;
}
int ext4_convert_inline_data(struct inode *inode)
{
- int error, needed_blocks;
+ int error, needed_blocks, no_expand;
handle_t *handle;
struct ext4_iloc iloc;
@@ -2016,15 +2028,10 @@ int ext4_convert_inline_data(struct inode *inode)
goto out_free;
}
- down_write(&EXT4_I(inode)->xattr_sem);
- if (!ext4_has_inline_data(inode)) {
- up_write(&EXT4_I(inode)->xattr_sem);
- goto out;
- }
-
- error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
- up_write(&EXT4_I(inode)->xattr_sem);
-out:
+ ext4_write_lock_xattr(inode, &no_expand);
+ if (ext4_has_inline_data(inode))
+ error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
+ ext4_write_unlock_xattr(inode, &no_expand);
ext4_journal_stop(handle);
out_free:
brelse(iloc.bh);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 88d57af1b516..f622d4a577e3 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1189,6 +1189,9 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
pgoff_t index;
unsigned from, to;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
trace_ext4_write_begin(inode, pos, len, flags);
/*
* Reserve one block more for addition to orphan list in case
@@ -1330,8 +1333,11 @@ static int ext4_write_end(struct file *file,
if (ext4_has_inline_data(inode)) {
ret = ext4_write_inline_data_end(inode, pos, len,
copied, page);
- if (ret < 0)
+ if (ret < 0) {
+ unlock_page(page);
+ put_page(page);
goto errout;
+ }
copied = ret;
} else
copied = block_write_end(file, mapping, pos,
@@ -1385,7 +1391,9 @@ errout:
* set the buffer to be dirty, since in data=journalled mode we need
* to call ext4_handle_dirty_metadata() instead.
*/
-static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
+static void ext4_journalled_zero_new_buffers(handle_t *handle,
+ struct page *page,
+ unsigned from, unsigned to)
{
unsigned int block_start = 0, block_end;
struct buffer_head *head, *bh;
@@ -1402,7 +1410,7 @@ static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
size = min(to, block_end) - start;
zero_user(page, start, size);
- set_buffer_uptodate(bh);
+ write_end_fn(handle, bh);
}
clear_buffer_new(bh);
}
@@ -1431,18 +1439,25 @@ static int ext4_journalled_write_end(struct file *file,
BUG_ON(!ext4_handle_valid(handle));
- if (ext4_has_inline_data(inode))
- copied = ext4_write_inline_data_end(inode, pos, len,
- copied, page);
- else {
- if (copied < len) {
- if (!PageUptodate(page))
- copied = 0;
- zero_new_buffers(page, from+copied, to);
+ if (ext4_has_inline_data(inode)) {
+ ret = ext4_write_inline_data_end(inode, pos, len,
+ copied, page);
+ if (ret < 0) {
+ unlock_page(page);
+ put_page(page);
+ goto errout;
}
-
+ copied = ret;
+ } else if (unlikely(copied < len) && !PageUptodate(page)) {
+ copied = 0;
+ ext4_journalled_zero_new_buffers(handle, page, from, to);
+ } else {
+ if (unlikely(copied < len))
+ ext4_journalled_zero_new_buffers(handle, page,
+ from + copied, to);
ret = ext4_walk_page_buffers(handle, page_buffers(page), from,
- to, &partial, write_end_fn);
+ from + copied, &partial,
+ write_end_fn);
if (!partial)
SetPageUptodate(page);
}
@@ -1468,6 +1483,7 @@ static int ext4_journalled_write_end(struct file *file,
*/
ext4_orphan_add(handle, inode);
+errout:
ret2 = ext4_journal_stop(handle);
if (!ret)
ret = ret2;
@@ -2034,6 +2050,12 @@ static int ext4_writepage(struct page *page,
struct ext4_io_submit io_submit;
bool keep_towrite = false;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) {
+ ext4_invalidatepage(page, 0, PAGE_SIZE);
+ unlock_page(page);
+ return -EIO;
+ }
+
trace_ext4_writepage(page);
size = i_size_read(inode);
if (page->index == size >> PAGE_SHIFT)
@@ -2409,7 +2431,8 @@ static int mpage_map_and_submit_extent(handle_t *handle,
if (err < 0) {
struct super_block *sb = inode->i_sb;
- if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+ if (ext4_forced_shutdown(EXT4_SB(sb)) ||
+ EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
goto invalidate_dirty_pages;
/*
* Let the uper layers retry transient errors.
@@ -2464,8 +2487,8 @@ update_disksize:
disksize = i_size;
if (disksize > EXT4_I(inode)->i_disksize)
EXT4_I(inode)->i_disksize = disksize;
- err2 = ext4_mark_inode_dirty(handle, inode);
up_write(&EXT4_I(inode)->i_data_sem);
+ err2 = ext4_mark_inode_dirty(handle, inode);
if (err2)
ext4_error(inode->i_sb,
"Failed to mark inode %lu dirty",
@@ -2631,6 +2654,9 @@ static int ext4_writepages(struct address_space *mapping,
struct blk_plug plug;
bool give_up_on_write = false;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
percpu_down_read(&sbi->s_journal_flag_rwsem);
trace_ext4_writepages(inode, wbc);
@@ -2667,7 +2693,8 @@ static int ext4_writepages(struct address_space *mapping,
* *never* be called, so if that ever happens, we would want
* the stack trace.
*/
- if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
+ sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
ret = -EROFS;
goto out_writepages;
}
@@ -2892,6 +2919,9 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
struct inode *inode = mapping->host;
handle_t *handle;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
index = pos >> PAGE_SHIFT;
if (ext4_nonda_switch(inode->i_sb) ||
@@ -3914,6 +3944,10 @@ static int ext4_block_truncate_page(handle_t *handle,
unsigned blocksize;
struct inode *inode = mapping->host;
+ /* If we are processing an encrypted inode during orphan list handling */
+ if (ext4_encrypted_inode(inode) && !fscrypt_has_encryption_key(inode))
+ return 0;
+
blocksize = inode->i_sb->s_blocksize;
length = blocksize - (offset & (blocksize - 1));
@@ -4222,7 +4256,9 @@ int ext4_truncate(struct inode *inode)
if (ext4_has_inline_data(inode)) {
int has_inline = 1;
- ext4_inline_data_truncate(inode, &has_inline);
+ err = ext4_inline_data_truncate(inode, &has_inline);
+ if (err)
+ return err;
if (has_inline)
return 0;
}
@@ -5197,6 +5233,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
int orphan = 0;
const unsigned int ia_valid = attr->ia_valid;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
error = setattr_prepare(dentry, attr);
if (error)
return error;
@@ -5483,6 +5522,9 @@ int ext4_mark_iloc_dirty(handle_t *handle,
{
int err = 0;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
if (IS_I_VERSION(inode))
inode_inc_iversion(inode);
@@ -5506,6 +5548,9 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
{
int err;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
err = ext4_get_inode_loc(inode, iloc);
if (!err) {
BUFFER_TRACE(iloc->bh, "get_write_access");
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index d534399cf607..a4273ddb9922 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -16,6 +16,7 @@
#include <linux/quotaops.h>
#include <linux/uuid.h>
#include <linux/uaccess.h>
+#include <linux/delay.h>
#include "ext4_jbd2.h"
#include "ext4.h"
@@ -442,6 +443,52 @@ static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
return iflags;
}
+int ext4_shutdown(struct super_block *sb, unsigned long arg)
+{
+ struct ext4_sb_info *sbi = EXT4_SB(sb);
+ __u32 flags;
+
+ if (!capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ if (get_user(flags, (__u32 __user *)arg))
+ return -EFAULT;
+
+ if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH)
+ return -EINVAL;
+
+ if (ext4_forced_shutdown(sbi))
+ return 0;
+
+ ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags);
+
+ switch (flags) {
+ case EXT4_GOING_FLAGS_DEFAULT:
+ freeze_bdev(sb->s_bdev);
+ set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+ thaw_bdev(sb->s_bdev, sb);
+ break;
+ case EXT4_GOING_FLAGS_LOGFLUSH:
+ set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+ if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
+ (void) ext4_force_commit(sb);
+ jbd2_journal_abort(sbi->s_journal, 0);
+ }
+ break;
+ case EXT4_GOING_FLAGS_NOLOGFLUSH:
+ set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+ if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
+ msleep(100);
+ jbd2_journal_abort(sbi->s_journal, 0);
+ }
+ break;
+ default:
+ return -EINVAL;
+ }
+ clear_opt(sb, DISCARD);
+ return 0;
+}
+
long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
{
struct inode *inode = file_inode(filp);
@@ -893,6 +940,8 @@ resizefs_out:
return 0;
}
+ case EXT4_IOC_SHUTDOWN:
+ return ext4_shutdown(sb, arg);
default:
return -ENOTTY;
}
@@ -959,6 +1008,7 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
case EXT4_IOC_SET_ENCRYPTION_POLICY:
case EXT4_IOC_GET_ENCRYPTION_PWSALT:
case EXT4_IOC_GET_ENCRYPTION_POLICY:
+ case EXT4_IOC_SHUTDOWN:
break;
default:
return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 7ae43c59bc79..10c62de642c6 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1556,7 +1556,17 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block,
ex->fe_len += 1 << order;
}
- BUG_ON(ex->fe_start + ex->fe_len > (1 << (e4b->bd_blkbits + 3)));
+ if (ex->fe_start + ex->fe_len > (1 << (e4b->bd_blkbits + 3))) {
+ /* Should never happen! (but apparently sometimes does?!?) */
+ WARN_ON(1);
+ ext4_error(e4b->bd_sb, "corruption or bug in mb_find_extent "
+ "block=%d, order=%d needed=%d ex=%u/%d/%d@%u",
+ block, order, needed, ex->fe_group, ex->fe_start,
+ ex->fe_len, ex->fe_logical);
+ ex->fe_len = 0;
+ ex->fe_start = 0;
+ ex->fe_group = 0;
+ }
return ex->fe_len;
}
@@ -2136,8 +2146,10 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
* We search using buddy data only if the order of the request
* is greater than equal to the sbi_s_mb_order2_reqs
* You can tune it via /sys/fs/ext4/<partition>/mb_order2_req
+ * We also support searching for power-of-two requests only for
+ * requests upto maximum buddy size we have constructed.
*/
- if (i >= sbi->s_mb_order2_reqs) {
+ if (i >= sbi->s_mb_order2_reqs && i <= sb->s_blocksize_bits + 2) {
/*
* This should tell if fe_len is exactly power of 2
*/
@@ -2207,7 +2219,7 @@ repeat:
}
ac->ac_groups_scanned++;
- if (cr == 0 && ac->ac_2order < sb->s_blocksize_bits+2)
+ if (cr == 0)
ext4_mb_simple_scan_group(ac, &e4b);
else if (cr == 1 && sbi->s_stripe &&
!(ac->ac_g_ex.fe_len % sbi->s_stripe))
@@ -3123,6 +3135,13 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
if (ar->pright && start + size - 1 >= ar->lright)
size -= start + size - ar->lright;
+ /*
+ * Trim allocation request for filesystems with artificially small
+ * groups.
+ */
+ if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb))
+ size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb);
+
end = start + size;
/* check we don't cross already preallocated blocks */
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index bb880c326191..6ad612c576fc 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1618,13 +1618,15 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
!fscrypt_has_permitted_context(dir, inode)) {
int nokey = ext4_encrypted_inode(inode) &&
!fscrypt_has_encryption_key(inode);
- iput(inode);
- if (nokey)
+ if (nokey) {
+ iput(inode);
return ERR_PTR(-ENOKEY);
+ }
ext4_warning(inode->i_sb,
"Inconsistent encryption contexts: %lu/%lu",
(unsigned long) dir->i_ino,
(unsigned long) inode->i_ino);
+ iput(inode);
return ERR_PTR(-EPERM);
}
}
@@ -2937,6 +2939,9 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
struct ext4_dir_entry_2 *de;
handle_t *handle = NULL;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+ return -EIO;
+
/* Initialize quotas before so that eventual writes go in
* separate transaction */
retval = dquot_initialize(dir);
@@ -3010,6 +3015,9 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
struct ext4_dir_entry_2 *de;
handle_t *handle = NULL;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+ return -EIO;
+
trace_ext4_unlink_enter(dir, dentry);
/* Initialize quotas before so that eventual writes go
* in separate transaction */
@@ -3080,6 +3088,9 @@ static int ext4_symlink(struct inode *dir,
struct fscrypt_str disk_link;
struct fscrypt_symlink_data *sd = NULL;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+ return -EIO;
+
disk_link.len = len + 1;
disk_link.name = (char *) symname;
@@ -3872,6 +3883,9 @@ static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry,
struct inode *new_dir, struct dentry *new_dentry,
unsigned int flags)
{
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(old_dir->i_sb))))
+ return -EIO;
+
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index e55624c50898..208241b06662 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -157,7 +157,7 @@ static int ext4_end_io(ext4_io_end_t *io)
io->handle = NULL; /* Following call will use up the handle */
ret = ext4_convert_unwritten_extents(handle, inode, offset, size);
- if (ret < 0) {
+ if (ret < 0 && !ext4_forced_shutdown(EXT4_SB(inode->i_sb))) {
ext4_msg(inode->i_sb, KERN_EMERG,
"failed to convert unwritten extents to written "
"extents -- potential data loss! "
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index cf681004b196..c3ed9021b781 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -45,7 +45,8 @@ int ext4_resize_begin(struct super_block *sb)
return -EPERM;
}
- if (test_and_set_bit_lock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags))
+ if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING,
+ &EXT4_SB(sb)->s_ext4_flags))
ret = -EBUSY;
return ret;
@@ -53,7 +54,7 @@ int ext4_resize_begin(struct super_block *sb)
void ext4_resize_end(struct super_block *sb)
{
- clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags);
+ clear_bit_unlock(EXT4_FLAGS_RESIZING, &EXT4_SB(sb)->s_ext4_flags);
smp_mb__after_atomic();
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 20539c2cd6d8..2e03a0a88d92 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -438,6 +438,9 @@ void __ext4_error(struct super_block *sb, const char *function,
struct va_format vaf;
va_list args;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+ return;
+
if (ext4_error_ratelimit(sb)) {
va_start(args, fmt);
vaf.fmt = fmt;
@@ -459,6 +462,9 @@ void __ext4_error_inode(struct inode *inode, const char *function,
struct va_format vaf;
struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return;
+
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
es->s_last_error_block = cpu_to_le64(block);
if (ext4_error_ratelimit(inode->i_sb)) {
@@ -491,6 +497,9 @@ void __ext4_error_file(struct file *file, const char *function,
struct inode *inode = file_inode(file);
char pathname[80], *path;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return;
+
es = EXT4_SB(inode->i_sb)->s_es;
es->s_last_error_ino = cpu_to_le32(inode->i_ino);
if (ext4_error_ratelimit(inode->i_sb)) {
@@ -567,6 +576,9 @@ void __ext4_std_error(struct super_block *sb, const char *function,
char nbuf[16];
const char *errstr;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+ return;
+
/* Special case: if the error is EROFS, and we're not already
* inside a transaction, then there's really no point in logging
* an error. */
@@ -600,6 +612,9 @@ void __ext4_abort(struct super_block *sb, const char *function,
struct va_format vaf;
va_list args;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+ return;
+
save_error_info(sb, function, line);
va_start(args, fmt);
vaf.fmt = fmt;
@@ -695,6 +710,9 @@ __acquires(bitlock)
va_list args;
struct ext4_super_block *es = EXT4_SB(sb)->s_es;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+ return;
+
es->s_last_error_ino = cpu_to_le32(ino);
es->s_last_error_block = cpu_to_le64(block);
__save_error_info(sb, function, line);
@@ -825,6 +843,7 @@ static void ext4_put_super(struct super_block *sb)
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
struct ext4_super_block *es = sbi->s_es;
+ int aborted = 0;
int i, err;
ext4_unregister_li_request(sb);
@@ -834,9 +853,10 @@ static void ext4_put_super(struct super_block *sb)
destroy_workqueue(sbi->rsv_conversion_wq);
if (sbi->s_journal) {
+ aborted = is_journal_aborted(sbi->s_journal);
err = jbd2_journal_destroy(sbi->s_journal);
sbi->s_journal = NULL;
- if (err < 0)
+ if ((err < 0) && !aborted)
ext4_abort(sb, "Couldn't clean up the journal");
}
@@ -847,7 +867,7 @@ static void ext4_put_super(struct super_block *sb)
ext4_mb_release(sb);
ext4_ext_release(sb);
- if (!(sb->s_flags & MS_RDONLY)) {
+ if (!(sb->s_flags & MS_RDONLY) && !aborted) {
ext4_clear_feature_journal_needs_recovery(sb);
es->s_state = cpu_to_le16(sbi->s_mount_state);
}
@@ -1284,7 +1304,7 @@ enum {
Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
- Opt_lazytime, Opt_nolazytime,
+ Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
Opt_inode_readahead_blks, Opt_journal_ioprio,
Opt_dioread_nolock, Opt_dioread_lock,
@@ -1352,6 +1372,7 @@ static const match_table_t tokens = {
{Opt_delalloc, "delalloc"},
{Opt_lazytime, "lazytime"},
{Opt_nolazytime, "nolazytime"},
+ {Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"},
{Opt_nodelalloc, "nodelalloc"},
{Opt_removed, "mblk_io_submit"},
{Opt_removed, "nomblk_io_submit"},
@@ -1557,6 +1578,7 @@ static const struct mount_opts {
#endif
{Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET},
{Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET},
+ {Opt_debug_want_extra_isize, 0, MOPT_GTE0},
{Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q},
{Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA,
MOPT_SET | MOPT_Q},
@@ -1670,6 +1692,8 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
if (arg == 0)
arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
sbi->s_commit_interval = HZ * arg;
+ } else if (token == Opt_debug_want_extra_isize) {
+ sbi->s_want_extra_isize = arg;
} else if (token == Opt_max_batch_time) {
sbi->s_max_batch_time = arg;
} else if (token == Opt_min_batch_time) {
@@ -2613,9 +2637,9 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
ret = sbi->s_stripe;
- else if (stripe_width <= sbi->s_blocks_per_group)
+ else if (stripe_width && stripe_width <= sbi->s_blocks_per_group)
ret = stripe_width;
- else if (stride <= sbi->s_blocks_per_group)
+ else if (stride && stride <= sbi->s_blocks_per_group)
ret = stride;
else
ret = 0;
@@ -3836,7 +3860,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
EXT4_DESC_PER_BLOCK(sb);
if (ext4_has_feature_meta_bg(sb)) {
- if (le32_to_cpu(es->s_first_meta_bg) >= db_count) {
+ if (le32_to_cpu(es->s_first_meta_bg) > db_count) {
ext4_msg(sb, KERN_WARNING,
"first meta block group too large: %u "
"(group descriptor block count %u)",
@@ -3919,7 +3943,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
* root first: it may be modified in the journal!
*/
if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) {
- if (ext4_load_journal(sb, es, journal_devnum))
+ err = ext4_load_journal(sb, es, journal_devnum);
+ if (err)
goto failed_mount3a;
} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
ext4_has_feature_journal_needs_recovery(sb)) {
@@ -4081,7 +4106,8 @@ no_journal:
sb->s_flags |= MS_RDONLY;
/* determine the minimum size of new large inodes, if present */
- if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
+ if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
+ sbi->s_want_extra_isize == 0) {
sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
EXT4_GOOD_OLD_INODE_SIZE;
if (ext4_has_feature_extra_isize(sb)) {
@@ -4709,6 +4735,9 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
bool needs_barrier = false;
struct ext4_sb_info *sbi = EXT4_SB(sb);
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+ return 0;
+
trace_ext4_sync_fs(sb, wait);
flush_workqueue(sbi->rsv_conversion_wq);
/*
@@ -4792,7 +4821,7 @@ out:
*/
static int ext4_unfreeze(struct super_block *sb)
{
- if (sb->s_flags & MS_RDONLY)
+ if ((sb->s_flags & MS_RDONLY) || ext4_forced_shutdown(EXT4_SB(sb)))
return 0;
if (EXT4_SB(sb)->s_journal) {
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 5a94fa52b74f..67636acf7624 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -411,6 +411,9 @@ ext4_xattr_get(struct inode *inode, int name_index, const char *name,
{
int error;
+ if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+ return -EIO;
+
if (strlen(name) > 255)
return -ERANGE;
@@ -1188,16 +1191,14 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
struct ext4_xattr_block_find bs = {
.s = { .not_found = -ENODATA, },
};
- unsigned long no_expand;
+ int no_expand;
int error;
if (!name)
return -EINVAL;
if (strlen(name) > 255)
return -ERANGE;
- down_write(&EXT4_I(inode)->xattr_sem);
- no_expand = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
- ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+ ext4_write_lock_xattr(inode, &no_expand);
error = ext4_reserve_inode_write(handle, inode, &is.iloc);
if (error)
@@ -1264,7 +1265,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
ext4_xattr_update_super_block(handle, inode->i_sb);
inode->i_ctime = current_time(inode);
if (!value)
- ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+ no_expand = 0;
error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
/*
* The bh is consumed by ext4_mark_iloc_dirty, even with
@@ -1278,9 +1279,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
cleanup:
brelse(is.iloc.bh);
brelse(bs.bh);
- if (no_expand == 0)
- ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
- up_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_unlock_xattr(inode, &no_expand);
return error;
}
@@ -1497,12 +1496,11 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
int error = 0, tried_min_extra_isize = 0;
int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
int isize_diff; /* How much do we need to grow i_extra_isize */
+ int no_expand;
+
+ if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
+ return 0;
- down_write(&EXT4_I(inode)->xattr_sem);
- /*
- * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty
- */
- ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
retry:
isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
@@ -1584,17 +1582,16 @@ shift:
EXT4_I(inode)->i_extra_isize = new_extra_isize;
brelse(bh);
out:
- ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
- up_write(&EXT4_I(inode)->xattr_sem);
+ ext4_write_unlock_xattr(inode, &no_expand);
return 0;
cleanup:
brelse(bh);
/*
- * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
- * size expansion failed.
+ * Inode size expansion failed; don't try again
*/
- up_write(&EXT4_I(inode)->xattr_sem);
+ no_expand = 1;
+ ext4_write_unlock_xattr(inode, &no_expand);
return error;
}
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index a92e783fa057..099c8b670ef5 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -102,6 +102,38 @@ extern const struct xattr_handler ext4_xattr_security_handler;
#define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c"
+/*
+ * The EXT4_STATE_NO_EXPAND is overloaded and used for two purposes.
+ * The first is to signal that there the inline xattrs and data are
+ * taking up so much space that we might as well not keep trying to
+ * expand it. The second is that xattr_sem is taken for writing, so
+ * we shouldn't try to recurse into the inode expansion. For this
+ * second case, we need to make sure that we take save and restore the
+ * NO_EXPAND state flag appropriately.
+ */
+static inline void ext4_write_lock_xattr(struct inode *inode, int *save)
+{
+ down_write(&EXT4_I(inode)->xattr_sem);
+ *save = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+ ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+}
+
+static inline int ext4_write_trylock_xattr(struct inode *inode, int *save)
+{
+ if (down_write_trylock(&EXT4_I(inode)->xattr_sem) == 0)
+ return 0;
+ *save = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+ ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+ return 1;
+}
+
+static inline void ext4_write_unlock_xattr(struct inode *inode, int *save)
+{
+ if (*save == 0)
+ ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+ up_write(&EXT4_I(inode)->xattr_sem);
+}
+
extern ssize_t ext4_listxattr(struct dentry *, char *, size_t);
extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t);