Merge tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4
Pull ext4 updates from Ted Ts'o:
"Fix a number of bugs, most notably a potential stale data exposure
after a crash and a potential BUG_ON crash if a file has the data
journalling flag enabled while it has dirty delayed allocation blocks
that haven't been written yet. Also fix a potential crash in the new
project quota code and a maliciously corrupted file system.
In addition, fix some DAX-specific bugs, including when there is a
transient ENOSPC situation and races between writes via direct I/O and
an mmap'ed segment that could lead to lost I/O.
Finally the usual set of miscellaneous cleanups"
* tag 'ext4_for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tytso/ext4: (23 commits)
ext4: pre-zero allocated blocks for DAX IO
ext4: refactor direct IO code
ext4: fix race in transient ENOSPC detection
ext4: handle transient ENOSPC properly for DAX
dax: call get_blocks() with create == 1 for write faults to unwritten extents
ext4: remove unmeetable inconsisteny check from ext4_find_extent()
jbd2: remove excess descriptions for handle_s
ext4: remove unnecessary bio get/put
ext4: silence UBSAN in ext4_mb_init()
ext4: address UBSAN warning in mb_find_order_for_block()
ext4: fix oops on corrupted filesystem
ext4: fix check of dqget() return value in ext4_ioctl_setproject()
ext4: clean up error handling when orphan list is corrupted
ext4: fix hang when processing corrupted orphaned inode list
ext4: remove trailing \n from ext4_warning/ext4_error calls
ext4: fix races between changing inode journal mode and ext4_writepages
ext4: handle unwritten or delalloc buffers before enabling data journaling
ext4: fix jbd2 handle extension in ext4_ext_truncate_extend_restart()
ext4: do not ask jbd2 to write data for delalloc buffers
jbd2: add support for avoiding data writes during transaction commits
...
diff --git a/fs/compat.c b/fs/compat.c
index 8754e9a..be6e48b 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -936,6 +936,8 @@
}
dirent = buf->previous;
if (dirent) {
+ if (signal_pending(current))
+ return -EINTR;
if (__put_user(offset, &dirent->d_off))
goto efault;
}
@@ -1020,6 +1022,8 @@
dirent = buf->previous;
if (dirent) {
+ if (signal_pending(current))
+ return -EINTR;
if (__put_user_unaligned(offset, &dirent->d_off))
goto efault;
}
diff --git a/fs/dax.c b/fs/dax.c
index a345c16..7d9df93 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -676,7 +676,7 @@
if (error)
goto unlock_page;
- if (!buffer_mapped(&bh) && !buffer_unwritten(&bh) && !vmf->cow_page) {
+ if (!buffer_mapped(&bh) && !vmf->cow_page) {
if (vmf->flags & FAULT_FLAG_WRITE) {
error = get_block(inode, block, &bh, 1);
count_vm_event(PGMAJFAULT);
diff --git a/fs/ext4/balloc.c b/fs/ext4/balloc.c
index fe1f50f..3020fd7 100644
--- a/fs/ext4/balloc.c
+++ b/fs/ext4/balloc.c
@@ -610,7 +610,8 @@
jbd_debug(1, "%s: retrying operation after ENOSPC\n", sb->s_id);
- return jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+ jbd2_journal_force_commit_nested(EXT4_SB(sb)->s_journal);
+ return 1;
}
/*
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index 5d00bf0..68323e3 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -150,6 +150,11 @@
while (ctx->pos < inode->i_size) {
struct ext4_map_blocks map;
+ if (fatal_signal_pending(current)) {
+ err = -ERESTARTSYS;
+ goto errout;
+ }
+ cond_resched();
map.m_lblk = ctx->pos >> EXT4_BLOCK_SIZE_BITS(sb);
map.m_len = 1;
err = ext4_map_blocks(NULL, inode, &map, 0);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 72f4c9e..b84aa1c 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -33,6 +33,7 @@
#include <linux/ratelimit.h>
#include <crypto/hash.h>
#include <linux/falloc.h>
+#include <linux/percpu-rwsem.h>
#ifdef __KERNEL__
#include <linux/compat.h>
#endif
@@ -581,6 +582,9 @@
#define EXT4_GET_BLOCKS_ZERO 0x0200
#define EXT4_GET_BLOCKS_CREATE_ZERO (EXT4_GET_BLOCKS_CREATE |\
EXT4_GET_BLOCKS_ZERO)
+ /* Caller will submit data before dropping transaction handle. This
+ * allows jbd2 to avoid submitting data before commit. */
+#define EXT4_GET_BLOCKS_IO_SUBMIT 0x0400
/*
* The bit position of these flags must not overlap with any of the
@@ -1505,6 +1509,9 @@
struct ratelimit_state s_err_ratelimit_state;
struct ratelimit_state s_warning_ratelimit_state;
struct ratelimit_state s_msg_ratelimit_state;
+
+ /* Barrier between changing inodes' journal flags and writepages ops. */
+ struct percpu_rw_semaphore s_journal_flag_rwsem;
};
static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1549,7 +1556,6 @@
EXT4_STATE_DIOREAD_LOCK, /* Disable support for dio read
nolocking */
EXT4_STATE_MAY_INLINE_DATA, /* may have in-inode data */
- EXT4_STATE_ORDERED_MODE, /* data=ordered mode */
EXT4_STATE_EXT_PRECACHED, /* extents have been precached */
};
@@ -2521,8 +2527,8 @@
struct buffer_head *ext4_bread(handle_t *, struct inode *, ext4_lblk_t, int);
int ext4_get_block_unwritten(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
-int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create);
+int ext4_dax_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create);
int ext4_get_block(struct inode *inode, sector_t iblock,
struct buffer_head *bh_result, int create);
int ext4_dio_get_block(struct inode *inode, sector_t iblock,
@@ -2581,7 +2587,6 @@
/* indirect.c */
extern int ext4_ind_map_blocks(handle_t *handle, struct inode *inode,
struct ext4_map_blocks *map, int flags);
-extern ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
extern int ext4_ind_calc_metadata_amount(struct inode *inode, sector_t lblock);
extern int ext4_ind_trans_blocks(struct inode *inode, int nrblocks);
extern void ext4_ind_truncate(handle_t *, struct inode *inode);
@@ -3329,6 +3334,13 @@
}
}
+static inline bool ext4_aligned_io(struct inode *inode, loff_t off, loff_t len)
+{
+ int blksize = 1 << inode->i_blkbits;
+
+ return IS_ALIGNED(off, blksize) && IS_ALIGNED(len, blksize);
+}
+
#endif /* __KERNEL__ */
#define EFSBADCRC EBADMSG /* Bad CRC detected */
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 5f58462..09c1ef3 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -359,10 +359,21 @@
return 0;
}
-static inline int ext4_jbd2_file_inode(handle_t *handle, struct inode *inode)
+static inline int ext4_jbd2_inode_add_write(handle_t *handle,
+ struct inode *inode)
{
if (ext4_handle_valid(handle))
- return jbd2_journal_file_inode(handle, EXT4_I(inode)->jinode);
+ return jbd2_journal_inode_add_write(handle,
+ EXT4_I(inode)->jinode);
+ return 0;
+}
+
+static inline int ext4_jbd2_inode_add_wait(handle_t *handle,
+ struct inode *inode)
+{
+ if (ext4_handle_valid(handle))
+ return jbd2_journal_inode_add_wait(handle,
+ EXT4_I(inode)->jinode);
return 0;
}
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 95bf467..2a2eef9 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -120,9 +120,14 @@
if (!ext4_handle_valid(handle))
return 0;
- if (handle->h_buffer_credits > needed)
+ if (handle->h_buffer_credits >= needed)
return 0;
- err = ext4_journal_extend(handle, needed);
+ /*
+ * If we need to extend the journal get a few extra blocks
+ * while we're at it for efficiency's sake.
+ */
+ needed += 3;
+ err = ext4_journal_extend(handle, needed - handle->h_buffer_credits);
if (err <= 0)
return err;
err = ext4_truncate_restart_trans(handle, inode, needed);
@@ -907,13 +912,6 @@
eh = ext_block_hdr(bh);
ppos++;
- if (unlikely(ppos > depth)) {
- put_bh(bh);
- EXT4_ERROR_INODE(inode,
- "ppos %d > depth %d", ppos, depth);
- ret = -EFSCORRUPTED;
- goto err;
- }
path[ppos].p_bh = bh;
path[ppos].p_hdr = eh;
}
@@ -2583,7 +2581,7 @@
}
} else
ext4_error(sbi->s_sb, "strange request: removal(2) "
- "%u-%u from %u:%u\n",
+ "%u-%u from %u:%u",
from, to, le32_to_cpu(ex->ee_block), ee_len);
return 0;
}
@@ -3738,7 +3736,7 @@
if (ee_block != map->m_lblk || ee_len > map->m_len) {
#ifdef EXT4_DEBUG
ext4_warning("Inode (%ld) finished: extent logical block %llu,"
- " len %u; IO logical block %llu, len %u\n",
+ " len %u; IO logical block %llu, len %u",
inode->i_ino, (unsigned long long)ee_block, ee_len,
(unsigned long long)map->m_lblk, map->m_len);
#endif
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index e38b987a..37e0592 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -707,7 +707,7 @@
(status & EXTENT_STATUS_WRITTEN)) {
ext4_warning(inode->i_sb, "Inserting extent [%u/%u] as "
" delayed and written which can potentially "
- " cause data loss.\n", lblk, len);
+ " cause data loss.", lblk, len);
WARN_ON(1);
}
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 00ff691..d478110 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -202,7 +202,7 @@
if (IS_ERR(handle))
result = VM_FAULT_SIGBUS;
else
- result = __dax_fault(vma, vmf, ext4_dax_mmap_get_block, NULL);
+ result = __dax_fault(vma, vmf, ext4_dax_get_block, NULL);
if (write) {
if (!IS_ERR(handle))
@@ -238,7 +238,7 @@
result = VM_FAULT_SIGBUS;
else
result = __dax_pmd_fault(vma, addr, pmd, flags,
- ext4_dax_mmap_get_block, NULL);
+ ext4_dax_get_block, NULL);
if (write) {
if (!IS_ERR(handle))
@@ -373,7 +373,7 @@
if (ext4_encrypted_inode(d_inode(dir)) &&
!ext4_is_child_context_consistent_with_parent(d_inode(dir), inode)) {
ext4_warning(inode->i_sb,
- "Inconsistent encryption contexts: %lu/%lu\n",
+ "Inconsistent encryption contexts: %lu/%lu",
(unsigned long) d_inode(dir)->i_ino,
(unsigned long) inode->i_ino);
dput(dir);
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index 237b877..3da4cf8 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -1150,25 +1150,20 @@
unsigned long max_ino = le32_to_cpu(EXT4_SB(sb)->s_es->s_inodes_count);
ext4_group_t block_group;
int bit;
- struct buffer_head *bitmap_bh;
+ struct buffer_head *bitmap_bh = NULL;
struct inode *inode = NULL;
- long err = -EIO;
+ int err = -EFSCORRUPTED;
- /* Error cases - e2fsck has already cleaned up for us */
- if (ino > max_ino) {
- ext4_warning(sb, "bad orphan ino %lu! e2fsck was run?", ino);
- err = -EFSCORRUPTED;
- goto error;
- }
+ if (ino < EXT4_FIRST_INO(sb) || ino > max_ino)
+ goto bad_orphan;
block_group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
bitmap_bh = ext4_read_inode_bitmap(sb, block_group);
if (IS_ERR(bitmap_bh)) {
- err = PTR_ERR(bitmap_bh);
- ext4_warning(sb, "inode bitmap error %ld for orphan %lu",
- ino, err);
- goto error;
+ ext4_error(sb, "inode bitmap error %ld for orphan %lu",
+ ino, PTR_ERR(bitmap_bh));
+ return (struct inode *) bitmap_bh;
}
/* Having the inode bit set should be a 100% indicator that this
@@ -1179,15 +1174,21 @@
goto bad_orphan;
inode = ext4_iget(sb, ino);
- if (IS_ERR(inode))
- goto iget_failed;
+ if (IS_ERR(inode)) {
+ err = PTR_ERR(inode);
+ ext4_error(sb, "couldn't read orphan inode %lu (err %d)",
+ ino, err);
+ return inode;
+ }
/*
- * If the orphans has i_nlinks > 0 then it should be able to be
- * truncated, otherwise it won't be removed from the orphan list
- * during processing and an infinite loop will result.
+ * If the orphans has i_nlinks > 0 then it should be able to
+ * be truncated, otherwise it won't be removed from the orphan
+ * list during processing and an infinite loop will result.
+ * Similarly, it must not be a bad inode.
*/
- if (inode->i_nlink && !ext4_can_truncate(inode))
+ if ((inode->i_nlink && !ext4_can_truncate(inode)) ||
+ is_bad_inode(inode))
goto bad_orphan;
if (NEXT_ORPHAN(inode) > max_ino)
@@ -1195,29 +1196,25 @@
brelse(bitmap_bh);
return inode;
-iget_failed:
- err = PTR_ERR(inode);
- inode = NULL;
bad_orphan:
- ext4_warning(sb, "bad orphan inode %lu! e2fsck was run?", ino);
- printk(KERN_WARNING "ext4_test_bit(bit=%d, block=%llu) = %d\n",
- bit, (unsigned long long)bitmap_bh->b_blocknr,
- ext4_test_bit(bit, bitmap_bh->b_data));
- printk(KERN_WARNING "inode=%p\n", inode);
+ ext4_error(sb, "bad orphan inode %lu", ino);
+ if (bitmap_bh)
+ printk(KERN_ERR "ext4_test_bit(bit=%d, block=%llu) = %d\n",
+ bit, (unsigned long long)bitmap_bh->b_blocknr,
+ ext4_test_bit(bit, bitmap_bh->b_data));
if (inode) {
- printk(KERN_WARNING "is_bad_inode(inode)=%d\n",
+ printk(KERN_ERR "is_bad_inode(inode)=%d\n",
is_bad_inode(inode));
- printk(KERN_WARNING "NEXT_ORPHAN(inode)=%u\n",
+ printk(KERN_ERR "NEXT_ORPHAN(inode)=%u\n",
NEXT_ORPHAN(inode));
- printk(KERN_WARNING "max_ino=%lu\n", max_ino);
- printk(KERN_WARNING "i_nlink=%u\n", inode->i_nlink);
+ printk(KERN_ERR "max_ino=%lu\n", max_ino);
+ printk(KERN_ERR "i_nlink=%u\n", inode->i_nlink);
/* Avoid freeing blocks if we got a bad deleted inode */
if (inode->i_nlink == 0)
inode->i_blocks = 0;
iput(inode);
}
brelse(bitmap_bh);
-error:
return ERR_PTR(err);
}
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index 627b7e8..bc15c2c 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -649,133 +649,6 @@
}
/*
- * O_DIRECT for ext3 (or indirect map) based files
- *
- * If the O_DIRECT write will extend the file then add this inode to the
- * orphan list. So recovery will truncate it back to the original size
- * if the machine crashes during the write.
- *
- * If the O_DIRECT write is intantiating holes inside i_size and the machine
- * crashes then stale disk data _may_ be exposed inside the file. But current
- * VFS code falls back into buffered path in that case so we are safe.
- */
-ssize_t ext4_ind_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
-{
- struct file *file = iocb->ki_filp;
- struct inode *inode = file->f_mapping->host;
- struct ext4_inode_info *ei = EXT4_I(inode);
- loff_t offset = iocb->ki_pos;
- handle_t *handle;
- ssize_t ret;
- int orphan = 0;
- size_t count = iov_iter_count(iter);
- int retries = 0;
-
- if (iov_iter_rw(iter) == WRITE) {
- loff_t final_size = offset + count;
-
- if (final_size > inode->i_size) {
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
- ret = ext4_orphan_add(handle, inode);
- if (ret) {
- ext4_journal_stop(handle);
- goto out;
- }
- orphan = 1;
- ei->i_disksize = inode->i_size;
- ext4_journal_stop(handle);
- }
- }
-
-retry:
- if (iov_iter_rw(iter) == READ && ext4_should_dioread_nolock(inode)) {
- /*
- * Nolock dioread optimization may be dynamically disabled
- * via ext4_inode_block_unlocked_dio(). Check inode's state
- * while holding extra i_dio_count ref.
- */
- inode_dio_begin(inode);
- smp_mb();
- if (unlikely(ext4_test_inode_state(inode,
- EXT4_STATE_DIOREAD_LOCK))) {
- inode_dio_end(inode);
- goto locked;
- }
- if (IS_DAX(inode))
- ret = dax_do_io(iocb, inode, iter,
- ext4_dio_get_block, NULL, 0);
- else
- ret = __blockdev_direct_IO(iocb, inode,
- inode->i_sb->s_bdev, iter,
- ext4_dio_get_block,
- NULL, NULL, 0);
- inode_dio_end(inode);
- } else {
-locked:
- if (IS_DAX(inode))
- ret = dax_do_io(iocb, inode, iter,
- ext4_dio_get_block, NULL, DIO_LOCKING);
- else
- ret = blockdev_direct_IO(iocb, inode, iter,
- ext4_dio_get_block);
-
- if (unlikely(iov_iter_rw(iter) == WRITE && ret < 0)) {
- loff_t isize = i_size_read(inode);
- loff_t end = offset + count;
-
- if (end > isize)
- ext4_truncate_failed_write(inode);
- }
- }
- if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
- goto retry;
-
- if (orphan) {
- int err;
-
- /* Credits for sb + inode write */
- handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
- if (IS_ERR(handle)) {
- /* This is really bad luck. We've written the data
- * but cannot extend i_size. Bail out and pretend
- * the write failed... */
- ret = PTR_ERR(handle);
- if (inode->i_nlink)
- ext4_orphan_del(NULL, inode);
-
- goto out;
- }
- if (inode->i_nlink)
- ext4_orphan_del(handle, inode);
- if (ret > 0) {
- loff_t end = offset + ret;
- if (end > inode->i_size) {
- ei->i_disksize = end;
- i_size_write(inode, end);
- /*
- * We're going to return a positive `ret'
- * here due to non-zero-length I/O, so there's
- * no way of reporting error returns from
- * ext4_mark_inode_dirty() to userspace. So
- * ignore it.
- */
- ext4_mark_inode_dirty(handle, inode);
- }
- }
- err = ext4_journal_stop(handle);
- if (ret == 0)
- ret = err;
- }
-out:
- return ret;
-}
-
-/*
* Calculate the number of metadata blocks need to reserve
* to allocate a new block at @lblocks for non extent file based file
*/
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 7bc6c85..ff7538c 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -1780,7 +1780,7 @@
ext4_warning(dir->i_sb,
"bad inline directory (dir #%lu) - "
"inode %u, rec_len %u, name_len %d"
- "inline size %d\n",
+ "inline size %d",
dir->i_ino, le32_to_cpu(de->inode),
le16_to_cpu(de->rec_len), de->name_len,
inline_size);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 79b298d..f7140ca6 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -684,6 +684,24 @@
ret = check_block_validity(inode, map);
if (ret != 0)
return ret;
+
+ /*
+ * Inodes with freshly allocated blocks where contents will be
+ * visible after transaction commit must be on transaction's
+ * ordered data list.
+ */
+ if (map->m_flags & EXT4_MAP_NEW &&
+ !(map->m_flags & EXT4_MAP_UNWRITTEN) &&
+ !(flags & EXT4_GET_BLOCKS_ZERO) &&
+ !IS_NOQUOTA(inode) &&
+ ext4_should_order_data(inode)) {
+ if (flags & EXT4_GET_BLOCKS_IO_SUBMIT)
+ ret = ext4_jbd2_inode_add_wait(handle, inode);
+ else
+ ret = ext4_jbd2_inode_add_write(handle, inode);
+ if (ret)
+ return ret;
+ }
}
return retval;
}
@@ -1289,15 +1307,6 @@
int i_size_changed = 0;
trace_ext4_write_end(inode, pos, len, copied);
- if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE)) {
- ret = ext4_jbd2_file_inode(handle, inode);
- if (ret) {
- unlock_page(page);
- put_page(page);
- goto errout;
- }
- }
-
if (ext4_has_inline_data(inode)) {
ret = ext4_write_inline_data_end(inode, pos, len,
copied, page);
@@ -2313,7 +2322,8 @@
* the data was copied into the page cache.
*/
get_blocks_flags = EXT4_GET_BLOCKS_CREATE |
- EXT4_GET_BLOCKS_METADATA_NOFAIL;
+ EXT4_GET_BLOCKS_METADATA_NOFAIL |
+ EXT4_GET_BLOCKS_IO_SUBMIT;
dioread_nolock = ext4_should_dioread_nolock(inode);
if (dioread_nolock)
get_blocks_flags |= EXT4_GET_BLOCKS_IO_CREATE_EXT;
@@ -2602,11 +2612,14 @@
struct blk_plug plug;
bool give_up_on_write = false;
+ percpu_down_read(&sbi->s_journal_flag_rwsem);
trace_ext4_writepages(inode, wbc);
- if (dax_mapping(mapping))
- return dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
- wbc);
+ if (dax_mapping(mapping)) {
+ ret = dax_writeback_mapping_range(mapping, inode->i_sb->s_bdev,
+ wbc);
+ goto out_writepages;
+ }
/*
* No pages to write? This is mainly a kludge to avoid starting
@@ -2776,6 +2789,7 @@
out_writepages:
trace_ext4_writepages_result(inode, wbc, ret,
nr_to_write - wbc->nr_to_write);
+ percpu_up_read(&sbi->s_journal_flag_rwsem);
return ret;
}
@@ -3215,75 +3229,52 @@
}
#ifdef CONFIG_FS_DAX
-int ext4_dax_mmap_get_block(struct inode *inode, sector_t iblock,
- struct buffer_head *bh_result, int create)
+/*
+ * Get block function for DAX IO and mmap faults. It takes care of converting
+ * unwritten extents to written ones and initializes new / converted blocks
+ * to zeros.
+ */
+int ext4_dax_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
{
- int ret, err;
- int credits;
- struct ext4_map_blocks map;
- handle_t *handle = NULL;
- int flags = 0;
+ int ret;
- ext4_debug("ext4_dax_mmap_get_block: inode %lu, create flag %d\n",
- inode->i_ino, create);
- map.m_lblk = iblock;
- map.m_len = bh_result->b_size >> inode->i_blkbits;
- credits = ext4_chunk_trans_blocks(inode, map.m_len);
- if (create) {
- flags |= EXT4_GET_BLOCKS_PRE_IO | EXT4_GET_BLOCKS_CREATE_ZERO;
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
+ ext4_debug("inode %lu, create flag %d\n", inode->i_ino, create);
+ if (!create)
+ return _ext4_get_block(inode, iblock, bh_result, 0);
+
+ ret = ext4_get_block_trans(inode, iblock, bh_result,
+ EXT4_GET_BLOCKS_PRE_IO |
+ EXT4_GET_BLOCKS_CREATE_ZERO);
+ if (ret < 0)
+ return ret;
+
+ if (buffer_unwritten(bh_result)) {
+ /*
+ * We are protected by i_mmap_sem or i_mutex so we know block
+ * cannot go away from under us even though we dropped
+ * i_data_sem. Convert extent to written and write zeros there.
+ */
+ ret = ext4_get_block_trans(inode, iblock, bh_result,
+ EXT4_GET_BLOCKS_CONVERT |
+ EXT4_GET_BLOCKS_CREATE_ZERO);
+ if (ret < 0)
return ret;
- }
}
-
- ret = ext4_map_blocks(handle, inode, &map, flags);
- if (create) {
- err = ext4_journal_stop(handle);
- if (ret >= 0 && err < 0)
- ret = err;
- }
- if (ret <= 0)
- goto out;
- if (map.m_flags & EXT4_MAP_UNWRITTEN) {
- int err2;
-
- /*
- * We are protected by i_mmap_sem so we know block cannot go
- * away from under us even though we dropped i_data_sem.
- * Convert extent to written and write zeros there.
- *
- * Note: We may get here even when create == 0.
- */
- handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits);
- if (IS_ERR(handle)) {
- ret = PTR_ERR(handle);
- goto out;
- }
-
- err = ext4_map_blocks(handle, inode, &map,
- EXT4_GET_BLOCKS_CONVERT | EXT4_GET_BLOCKS_CREATE_ZERO);
- if (err < 0)
- ret = err;
- err2 = ext4_journal_stop(handle);
- if (err2 < 0 && ret > 0)
- ret = err2;
- }
-out:
- WARN_ON_ONCE(ret == 0 && create);
- if (ret > 0) {
- map_bh(bh_result, inode->i_sb, map.m_pblk);
- /*
- * At least for now we have to clear BH_New so that DAX code
- * doesn't attempt to zero blocks again in a racy way.
- */
- map.m_flags &= ~EXT4_MAP_NEW;
- ext4_update_bh_state(bh_result, map.m_flags);
- bh_result->b_size = map.m_len << inode->i_blkbits;
- ret = 0;
- }
- return ret;
+ /*
+ * At least for now we have to clear BH_New so that DAX code
+ * doesn't attempt to zero blocks again in a racy way.
+ */
+ clear_buffer_new(bh_result);
+ return 0;
+}
+#else
+/* Just define empty function, it will never get called. */
+int ext4_dax_get_block(struct inode *inode, sector_t iblock,
+ struct buffer_head *bh_result, int create)
+{
+ BUG();
+ return 0;
}
#endif
@@ -3316,7 +3307,9 @@
}
/*
- * For ext4 extent files, ext4 will do direct-io write to holes,
+ * Handling of direct IO writes.
+ *
+ * For ext4 extent files, ext4 will do direct-io write even to holes,
* preallocated extents, and those write extend the file, no need to
* fall back to buffered IO.
*
@@ -3334,10 +3327,11 @@
* if the machine crashes during the write.
*
*/
-static ssize_t ext4_ext_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
+static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file->f_mapping->host;
+ struct ext4_inode_info *ei = EXT4_I(inode);
ssize_t ret;
loff_t offset = iocb->ki_pos;
size_t count = iov_iter_count(iter);
@@ -3345,10 +3339,25 @@
get_block_t *get_block_func = NULL;
int dio_flags = 0;
loff_t final_size = offset + count;
+ int orphan = 0;
+ handle_t *handle;
- /* Use the old path for reads and writes beyond i_size. */
- if (iov_iter_rw(iter) != WRITE || final_size > inode->i_size)
- return ext4_ind_direct_IO(iocb, iter);
+ if (final_size > inode->i_size) {
+ /* Credits for sb + inode write */
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+ if (IS_ERR(handle)) {
+ ret = PTR_ERR(handle);
+ goto out;
+ }
+ ret = ext4_orphan_add(handle, inode);
+ if (ret) {
+ ext4_journal_stop(handle);
+ goto out;
+ }
+ orphan = 1;
+ ei->i_disksize = inode->i_size;
+ ext4_journal_stop(handle);
+ }
BUG_ON(iocb->private == NULL);
@@ -3357,8 +3366,7 @@
* conversion. This also disallows race between truncate() and
* overwrite DIO as i_dio_count needs to be incremented under i_mutex.
*/
- if (iov_iter_rw(iter) == WRITE)
- inode_dio_begin(inode);
+ inode_dio_begin(inode);
/* If we do a overwrite dio, i_mutex locking can be released */
overwrite = *((int *)iocb->private);
@@ -3367,7 +3375,7 @@
inode_unlock(inode);
/*
- * We could direct write to holes and fallocate.
+ * For extent mapped files we could direct write to holes and fallocate.
*
* Allocated blocks to fill the hole are marked as unwritten to prevent
* parallel buffered read to expose the stale data before DIO complete
@@ -3389,7 +3397,23 @@
iocb->private = NULL;
if (overwrite)
get_block_func = ext4_dio_get_block_overwrite;
- else if (is_sync_kiocb(iocb)) {
+ else if (IS_DAX(inode)) {
+ /*
+ * We can avoid zeroing for aligned DAX writes beyond EOF. Other
+ * writes need zeroing either because they can race with page
+ * faults or because they use partial blocks.
+ */
+ if (round_down(offset, 1<<inode->i_blkbits) >= inode->i_size &&
+ ext4_aligned_io(inode, offset, count))
+ get_block_func = ext4_dio_get_block;
+ else
+ get_block_func = ext4_dax_get_block;
+ dio_flags = DIO_LOCKING;
+ } else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
+ round_down(offset, 1 << inode->i_blkbits) >= inode->i_size) {
+ get_block_func = ext4_dio_get_block;
+ dio_flags = DIO_LOCKING | DIO_SKIP_HOLES;
+ } else if (is_sync_kiocb(iocb)) {
get_block_func = ext4_dio_get_block_unwritten_sync;
dio_flags = DIO_LOCKING;
} else {
@@ -3399,10 +3423,10 @@
#ifdef CONFIG_EXT4_FS_ENCRYPTION
BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
#endif
- if (IS_DAX(inode))
+ if (IS_DAX(inode)) {
ret = dax_do_io(iocb, inode, iter, get_block_func,
ext4_end_io_dio, dio_flags);
- else
+ } else
ret = __blockdev_direct_IO(iocb, inode,
inode->i_sb->s_bdev, iter,
get_block_func,
@@ -3422,12 +3446,86 @@
ext4_clear_inode_state(inode, EXT4_STATE_DIO_UNWRITTEN);
}
- if (iov_iter_rw(iter) == WRITE)
- inode_dio_end(inode);
+ inode_dio_end(inode);
/* take i_mutex locking again if we do a ovewrite dio */
if (overwrite)
inode_lock(inode);
+ if (ret < 0 && final_size > inode->i_size)
+ ext4_truncate_failed_write(inode);
+
+ /* Handle extending of i_size after direct IO write */
+ if (orphan) {
+ int err;
+
+ /* Credits for sb + inode write */
+ handle = ext4_journal_start(inode, EXT4_HT_INODE, 2);
+ if (IS_ERR(handle)) {
+ /* This is really bad luck. We've written the data
+ * but cannot extend i_size. Bail out and pretend
+ * the write failed... */
+ ret = PTR_ERR(handle);
+ if (inode->i_nlink)
+ ext4_orphan_del(NULL, inode);
+
+ goto out;
+ }
+ if (inode->i_nlink)
+ ext4_orphan_del(handle, inode);
+ if (ret > 0) {
+ loff_t end = offset + ret;
+ if (end > inode->i_size) {
+ ei->i_disksize = end;
+ i_size_write(inode, end);
+ /*
+ * We're going to return a positive `ret'
+ * here due to non-zero-length I/O, so there's
+ * no way of reporting error returns from
+ * ext4_mark_inode_dirty() to userspace. So
+ * ignore it.
+ */
+ ext4_mark_inode_dirty(handle, inode);
+ }
+ }
+ err = ext4_journal_stop(handle);
+ if (ret == 0)
+ ret = err;
+ }
+out:
+ return ret;
+}
+
+static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
+{
+ int unlocked = 0;
+ struct inode *inode = iocb->ki_filp->f_mapping->host;
+ ssize_t ret;
+
+ if (ext4_should_dioread_nolock(inode)) {
+ /*
+ * Nolock dioread optimization may be dynamically disabled
+ * via ext4_inode_block_unlocked_dio(). Check inode's state
+ * while holding extra i_dio_count ref.
+ */
+ inode_dio_begin(inode);
+ smp_mb();
+ if (unlikely(ext4_test_inode_state(inode,
+ EXT4_STATE_DIOREAD_LOCK)))
+ inode_dio_end(inode);
+ else
+ unlocked = 1;
+ }
+ if (IS_DAX(inode)) {
+ ret = dax_do_io(iocb, inode, iter, ext4_dio_get_block,
+ NULL, unlocked ? 0 : DIO_LOCKING);
+ } else {
+ ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
+ iter, ext4_dio_get_block,
+ NULL, NULL,
+ unlocked ? 0 : DIO_LOCKING);
+ }
+ if (unlocked)
+ inode_dio_end(inode);
return ret;
}
@@ -3455,10 +3553,10 @@
return 0;
trace_ext4_direct_IO_enter(inode, offset, count, iov_iter_rw(iter));
- if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
- ret = ext4_ext_direct_IO(iocb, iter);
+ if (iov_iter_rw(iter) == READ)
+ ret = ext4_direct_IO_read(iocb, iter);
else
- ret = ext4_ind_direct_IO(iocb, iter);
+ ret = ext4_direct_IO_write(iocb, iter);
trace_ext4_direct_IO_exit(inode, offset, count, iov_iter_rw(iter), ret);
return ret;
}
@@ -3534,10 +3632,7 @@
{
switch (ext4_inode_journal_mode(inode)) {
case EXT4_INODE_ORDERED_DATA_MODE:
- ext4_set_inode_state(inode, EXT4_STATE_ORDERED_MODE);
- break;
case EXT4_INODE_WRITEBACK_DATA_MODE:
- ext4_clear_inode_state(inode, EXT4_STATE_ORDERED_MODE);
break;
case EXT4_INODE_JOURNAL_DATA_MODE:
inode->i_mapping->a_ops = &ext4_journalled_aops;
@@ -3630,8 +3725,8 @@
} else {
err = 0;
mark_buffer_dirty(bh);
- if (ext4_test_inode_state(inode, EXT4_STATE_ORDERED_MODE))
- err = ext4_jbd2_file_inode(handle, inode);
+ if (ext4_should_order_data(inode))
+ err = ext4_jbd2_inode_add_write(handle, inode);
}
unlock:
@@ -5429,6 +5524,7 @@
journal_t *journal;
handle_t *handle;
int err;
+ struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
/*
* We have to be very careful here: changing a data block's
@@ -5445,22 +5541,30 @@
return 0;
if (is_journal_aborted(journal))
return -EROFS;
- /* We have to allocate physical blocks for delalloc blocks
- * before flushing journal. otherwise delalloc blocks can not
- * be allocated any more. even more truncate on delalloc blocks
- * could trigger BUG by flushing delalloc blocks in journal.
- * There is no delalloc block in non-journal data mode.
- */
- if (val && test_opt(inode->i_sb, DELALLOC)) {
- err = ext4_alloc_da_blocks(inode);
- if (err < 0)
- return err;
- }
/* Wait for all existing dio workers */
ext4_inode_block_unlocked_dio(inode);
inode_dio_wait(inode);
+ /*
+ * Before flushing the journal and switching inode's aops, we have
+ * to flush all dirty data the inode has. There can be outstanding
+ * delayed allocations, there can be unwritten extents created by
+ * fallocate or buffered writes in dioread_nolock mode covered by
+ * dirty data which can be converted only after flushing the dirty
+ * data (and journalled aops don't know how to handle these cases).
+ */
+ if (val) {
+ down_write(&EXT4_I(inode)->i_mmap_sem);
+ err = filemap_write_and_wait(inode->i_mapping);
+ if (err < 0) {
+ up_write(&EXT4_I(inode)->i_mmap_sem);
+ ext4_inode_resume_unlocked_dio(inode);
+ return err;
+ }
+ }
+
+ percpu_down_write(&sbi->s_journal_flag_rwsem);
jbd2_journal_lock_updates(journal);
/*
@@ -5477,6 +5581,7 @@
err = jbd2_journal_flush(journal);
if (err < 0) {
jbd2_journal_unlock_updates(journal);
+ percpu_up_write(&sbi->s_journal_flag_rwsem);
ext4_inode_resume_unlocked_dio(inode);
return err;
}
@@ -5485,6 +5590,10 @@
ext4_set_aops(inode);
jbd2_journal_unlock_updates(journal);
+ percpu_up_write(&sbi->s_journal_flag_rwsem);
+
+ if (val)
+ up_write(&EXT4_I(inode)->i_mmap_sem);
ext4_inode_resume_unlocked_dio(inode);
/* Finally we can mark the inode as dirty. */
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 7497f50..28cc412 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -365,7 +365,7 @@
struct dquot *transfer_to[MAXQUOTAS] = { };
transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
- if (transfer_to[PRJQUOTA]) {
+ if (!IS_ERR(transfer_to[PRJQUOTA])) {
err = __dquot_transfer(inode, transfer_to);
dqput(transfer_to[PRJQUOTA]);
if (err)
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index eeeade7..c1ab3ec 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -1266,6 +1266,7 @@
static int mb_find_order_for_block(struct ext4_buddy *e4b, int block)
{
int order = 1;
+ int bb_incr = 1 << (e4b->bd_blkbits - 1);
void *bb;
BUG_ON(e4b->bd_bitmap == e4b->bd_buddy);
@@ -1278,7 +1279,8 @@
/* this block is part of buddy of order 'order' */
return order;
}
- bb += 1 << (e4b->bd_blkbits - order);
+ bb += bb_incr;
+ bb_incr >>= 1;
order++;
}
return 0;
@@ -2583,7 +2585,7 @@
{
struct ext4_sb_info *sbi = EXT4_SB(sb);
unsigned i, j;
- unsigned offset;
+ unsigned offset, offset_incr;
unsigned max;
int ret;
@@ -2612,11 +2614,13 @@
i = 1;
offset = 0;
+ offset_incr = 1 << (sb->s_blocksize_bits - 1);
max = sb->s_blocksize << 2;
do {
sbi->s_mb_offsets[i] = offset;
sbi->s_mb_maxs[i] = max;
- offset += 1 << (sb->s_blocksize_bits - i);
+ offset += offset_incr;
+ offset_incr = offset_incr >> 1;
max = max >> 1;
i++;
} while (i <= sb->s_blocksize_bits + 1);
@@ -4935,7 +4939,7 @@
* boundary.
*/
if (bit + count > EXT4_BLOCKS_PER_GROUP(sb)) {
- ext4_warning(sb, "too much blocks added to group %u\n",
+ ext4_warning(sb, "too much blocks added to group %u",
block_group);
err = -EINVAL;
goto error_return;
diff --git a/fs/ext4/mmp.c b/fs/ext4/mmp.c
index 2444527..23d436d 100644
--- a/fs/ext4/mmp.c
+++ b/fs/ext4/mmp.c
@@ -121,7 +121,7 @@
__ext4_warning(sb, function, line, "%s", msg);
__ext4_warning(sb, function, line,
"MMP failure info: last update time: %llu, last update "
- "node: %s, last update device: %s\n",
+ "node: %s, last update device: %s",
(long long unsigned int) le64_to_cpu(mmp->mmp_time),
mmp->mmp_nodename, mmp->mmp_bdevname);
}
@@ -353,7 +353,7 @@
* wait for MMP interval and check mmp_seq.
*/
if (schedule_timeout_interruptible(HZ * wait_time) != 0) {
- ext4_warning(sb, "MMP startup interrupted, failing mount\n");
+ ext4_warning(sb, "MMP startup interrupted, failing mount");
goto failed;
}
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 325cef4..a920c5d 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -400,7 +400,7 @@
/* Even in case of data=writeback it is reasonable to pin
* inode to transaction, to prevent unexpected data loss */
- *err = ext4_jbd2_file_inode(handle, orig_inode);
+ *err = ext4_jbd2_inode_add_write(handle, orig_inode);
unlock_pages:
unlock_page(pagep[0]);
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 5611ec9..ec4c399 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1107,6 +1107,11 @@
}
while (1) {
+ if (fatal_signal_pending(current)) {
+ err = -ERESTARTSYS;
+ goto errout;
+ }
+ cond_resched();
block = dx_get_block(frame->at);
ret = htree_dirblock_to_tree(dir_file, dir, block, &hinfo,
start_hash, start_minor_hash);
@@ -1613,7 +1618,7 @@
if (nokey)
return ERR_PTR(-ENOKEY);
ext4_warning(inode->i_sb,
- "Inconsistent encryption contexts: %lu/%lu\n",
+ "Inconsistent encryption contexts: %lu/%lu",
(unsigned long) dir->i_ino,
(unsigned long) inode->i_ino);
return ERR_PTR(-EPERM);
@@ -2828,7 +2833,7 @@
* list entries can cause panics at unmount time.
*/
mutex_lock(&sbi->s_orphan_lock);
- list_del(&EXT4_I(inode)->i_orphan);
+ list_del_init(&EXT4_I(inode)->i_orphan);
mutex_unlock(&sbi->s_orphan_lock);
}
}
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index e4fc8ea..2a01df9 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -342,9 +342,7 @@
if (bio) {
int io_op = io->io_wbc->sync_mode == WB_SYNC_ALL ?
WRITE_SYNC : WRITE;
- bio_get(io->io_bio);
submit_bio(io_op, io->io_bio);
- bio_put(io->io_bio);
}
io->io_bio = NULL;
}
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index 34038e3..cf68100 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -41,7 +41,7 @@
*/
if (EXT4_SB(sb)->s_mount_state & EXT4_ERROR_FS) {
ext4_warning(sb, "There are errors in the filesystem, "
- "so online resizing is not allowed\n");
+ "so online resizing is not allowed");
return -EPERM;
}
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 304c712..20c5d52 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -859,6 +859,7 @@
percpu_counter_destroy(&sbi->s_freeinodes_counter);
percpu_counter_destroy(&sbi->s_dirs_counter);
percpu_counter_destroy(&sbi->s_dirtyclusters_counter);
+ percpu_free_rwsem(&sbi->s_journal_flag_rwsem);
brelse(sbi->s_sbh);
#ifdef CONFIG_QUOTA
for (i = 0; i < EXT4_MAXQUOTAS; i++)
@@ -3930,6 +3931,9 @@
if (!err)
err = percpu_counter_init(&sbi->s_dirtyclusters_counter, 0,
GFP_KERNEL);
+ if (!err)
+ err = percpu_init_rwsem(&sbi->s_journal_flag_rwsem);
+
if (err) {
ext4_msg(sb, KERN_ERR, "insufficient memory");
goto failed_mount6;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 2ad98d6..7007809 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -219,6 +219,8 @@
spin_lock(&journal->j_list_lock);
list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+ if (!(jinode->i_flags & JI_WRITE_DATA))
+ continue;
mapping = jinode->i_vfs_inode->i_mapping;
jinode->i_flags |= JI_COMMIT_RUNNING;
spin_unlock(&journal->j_list_lock);
@@ -256,6 +258,8 @@
/* For locking, see the comment in journal_submit_data_buffers() */
spin_lock(&journal->j_list_lock);
list_for_each_entry(jinode, &commit_transaction->t_inode_list, i_list) {
+ if (!(jinode->i_flags & JI_WAIT_DATA))
+ continue;
jinode->i_flags |= JI_COMMIT_RUNNING;
spin_unlock(&journal->j_list_lock);
err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index 435f0b2..b31852f 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -94,7 +94,8 @@
EXPORT_SYMBOL(jbd2_journal_invalidatepage);
EXPORT_SYMBOL(jbd2_journal_try_to_free_buffers);
EXPORT_SYMBOL(jbd2_journal_force_commit);
-EXPORT_SYMBOL(jbd2_journal_file_inode);
+EXPORT_SYMBOL(jbd2_journal_inode_add_write);
+EXPORT_SYMBOL(jbd2_journal_inode_add_wait);
EXPORT_SYMBOL(jbd2_journal_init_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_release_jbd_inode);
EXPORT_SYMBOL(jbd2_journal_begin_ordered_truncate);
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index 2c56c3e..1749519 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -2462,7 +2462,8 @@
/*
* File inode in the inode list of the handle's transaction
*/
-int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode)
+static int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *jinode,
+ unsigned long flags)
{
transaction_t *transaction = handle->h_transaction;
journal_t *journal;
@@ -2487,12 +2488,14 @@
* and if jinode->i_next_transaction == transaction, commit code
* will only file the inode where we want it.
*/
- if (jinode->i_transaction == transaction ||
- jinode->i_next_transaction == transaction)
+ if ((jinode->i_transaction == transaction ||
+ jinode->i_next_transaction == transaction) &&
+ (jinode->i_flags & flags) == flags)
return 0;
spin_lock(&journal->j_list_lock);
-
+ jinode->i_flags |= flags;
+ /* Is inode already attached where we need it? */
if (jinode->i_transaction == transaction ||
jinode->i_next_transaction == transaction)
goto done;
@@ -2523,6 +2526,17 @@
return 0;
}
+int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *jinode)
+{
+ return jbd2_journal_file_inode(handle, jinode,
+ JI_WRITE_DATA | JI_WAIT_DATA);
+}
+
+int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *jinode)
+{
+ return jbd2_journal_file_inode(handle, jinode, JI_WAIT_DATA);
+}
+
/*
* File truncate and transaction commit interact with each other in a
* non-trivial way. If a transaction writing data block A is
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index f4cd3c3..497a4171 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -619,7 +619,7 @@
static inline int ocfs2_jbd2_file_inode(handle_t *handle, struct inode *inode)
{
- return jbd2_journal_file_inode(handle, &OCFS2_I(inode)->ip_jinode);
+ return jbd2_journal_inode_add_write(handle, &OCFS2_I(inode)->ip_jinode);
}
static inline int ocfs2_begin_ordered_truncate(struct inode *inode,
diff --git a/fs/readdir.c b/fs/readdir.c
index a86c6c0..68ef06e 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -182,6 +182,8 @@
}
dirent = buf->previous;
if (dirent) {
+ if (signal_pending(current))
+ return -EINTR;
if (__put_user(offset, &dirent->d_off))
goto efault;
}
@@ -261,6 +263,8 @@
return -EINVAL;
dirent = buf->previous;
if (dirent) {
+ if (signal_pending(current))
+ return -EINTR;
if (__put_user(offset, &dirent->d_off))
goto efault;
}
diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
index fd1083c..efb232c 100644
--- a/include/linux/jbd2.h
+++ b/include/linux/jbd2.h
@@ -403,11 +403,19 @@
/* Flags in jbd_inode->i_flags */
#define __JI_COMMIT_RUNNING 0
-/* Commit of the inode data in progress. We use this flag to protect us from
+#define __JI_WRITE_DATA 1
+#define __JI_WAIT_DATA 2
+
+/*
+ * Commit of the inode data in progress. We use this flag to protect us from
* concurrent deletion of inode. We cannot use reference to inode for this
* since we cannot afford doing last iput() on behalf of kjournald
*/
#define JI_COMMIT_RUNNING (1 << __JI_COMMIT_RUNNING)
+/* Write allocated dirty buffers in this inode before commit */
+#define JI_WRITE_DATA (1 << __JI_WRITE_DATA)
+/* Wait for outstanding data writes for this inode before commit */
+#define JI_WAIT_DATA (1 << __JI_WAIT_DATA)
/**
* struct jbd_inode is the structure linking inodes in ordered mode
@@ -781,9 +789,6 @@
* @j_wbufsize: maximum number of buffer_heads allowed in j_wbuf, the
* number that will fit in j_blocksize
* @j_last_sync_writer: most recent pid which did a synchronous write
- * @j_history: Buffer storing the transactions statistics history
- * @j_history_max: Maximum number of transactions in the statistics history
- * @j_history_cur: Current number of transactions in the statistics history
* @j_history_lock: Protect the transactions statistics history
* @j_proc_entry: procfs entry for the jbd statistics directory
* @j_stats: Overall statistics
@@ -1270,7 +1275,8 @@
extern int jbd2_journal_bmap(journal_t *, unsigned long, unsigned long long *);
extern int jbd2_journal_force_commit(journal_t *);
extern int jbd2_journal_force_commit_nested(journal_t *);
-extern int jbd2_journal_file_inode(handle_t *handle, struct jbd2_inode *inode);
+extern int jbd2_journal_inode_add_write(handle_t *handle, struct jbd2_inode *inode);
+extern int jbd2_journal_inode_add_wait(handle_t *handle, struct jbd2_inode *inode);
extern int jbd2_journal_begin_ordered_truncate(journal_t *journal,
struct jbd2_inode *inode, loff_t new_size);
extern void jbd2_journal_init_jbd_inode(struct jbd2_inode *jinode, struct inode *inode);
diff --git a/kernel/locking/percpu-rwsem.c b/kernel/locking/percpu-rwsem.c
index f231e0b..bec0b64 100644
--- a/kernel/locking/percpu-rwsem.c
+++ b/kernel/locking/percpu-rwsem.c
@@ -37,6 +37,7 @@
free_percpu(brw->fast_read_ctr);
brw->fast_read_ctr = NULL; /* catch use after free bugs */
}
+EXPORT_SYMBOL_GPL(percpu_free_rwsem);
/*
* This is the fast-path for down_read/up_read. If it succeeds we rely