summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/ext4.h1
-rw-r--r--fs/ext4/ext4_jbd2.h4
-rw-r--r--fs/ext4/indirect.c9
-rw-r--r--fs/ext4/inode.c27
-rw-r--r--fs/ext4/namei.c9
-rw-r--r--fs/ext4/page-io.c24
-rw-r--r--fs/ext4/super.c1
7 files changed, 60 insertions, 15 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index e717dfd2f2b..b7d7bd0f066 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -175,6 +175,7 @@ struct mpage_da_data {
*/
#define EXT4_IO_END_UNWRITTEN 0x0001
#define EXT4_IO_END_ERROR 0x0002
+#define EXT4_IO_END_QUEUED 0x0004
struct ext4_io_page {
struct page *p_page;
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index bb85757689b..5802fa1dab1 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -289,10 +289,10 @@ static inline int ext4_should_order_data(struct inode *inode)
static inline int ext4_should_writeback_data(struct inode *inode)
{
- if (!S_ISREG(inode->i_mode))
- return 0;
if (EXT4_JOURNAL(inode) == NULL)
return 1;
+ if (!S_ISREG(inode->i_mode))
+ return 0;
if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
return 0;
if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index b8602cde5b5..0962642119c 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -800,12 +800,17 @@ ssize_t ext4_ind_direct_IO(int rw, struct kiocb *iocb,
}
retry:
- if (rw == READ && ext4_should_dioread_nolock(inode))
+ if (rw == READ && ext4_should_dioread_nolock(inode)) {
+ if (unlikely(!list_empty(&ei->i_completed_io_list))) {
+ mutex_lock(&inode->i_mutex);
+ ext4_flush_completed_IO(inode);
+ mutex_unlock(&inode->i_mutex);
+ }
ret = __blockdev_direct_IO(rw, iocb, inode,
inode->i_sb->s_bdev, iov,
offset, nr_segs,
ext4_get_block, NULL, NULL, 0);
- else {
+ } else {
ret = blockdev_direct_IO(rw, iocb, inode, iov,
offset, nr_segs, ext4_get_block);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index d47264cafee..986e2388f03 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -120,6 +120,9 @@ void ext4_evict_inode(struct inode *inode)
int err;
trace_ext4_evict_inode(inode);
+
+ ext4_ioend_wait(inode);
+
if (inode->i_nlink) {
/*
* When journalling data dirty buffers are tracked only in the
@@ -644,7 +647,7 @@ struct buffer_head *ext4_bread(handle_t *handle, struct inode *inode,
return bh;
if (buffer_uptodate(bh))
return bh;
- ll_rw_block(READ_META, 1, &bh);
+ ll_rw_block(READ | REQ_META | REQ_PRIO, 1, &bh);
wait_on_buffer(bh);
if (buffer_uptodate(bh))
return bh;
@@ -983,6 +986,8 @@ static int ext4_journalled_write_end(struct file *file,
from = pos & (PAGE_CACHE_SIZE - 1);
to = from + len;
+ BUG_ON(!ext4_handle_valid(handle));
+
if (copied < len) {
if (!PageUptodate(page))
copied = 0;
@@ -1283,7 +1288,12 @@ static int mpage_da_submit_io(struct mpage_da_data *mpd,
else if (test_opt(inode->i_sb, MBLK_IO_SUBMIT))
err = ext4_bio_write_page(&io_submit, page,
len, mpd->wbc);
- else
+ else if (buffer_uninit(page_bufs)) {
+ ext4_set_bh_endio(page_bufs, inode);
+ err = block_write_full_page_endio(page,
+ noalloc_get_block_write,
+ mpd->wbc, ext4_end_io_buffer_write);
+ } else
err = block_write_full_page(page,
noalloc_get_block_write, mpd->wbc);
@@ -1699,6 +1709,8 @@ static int __ext4_journalled_writepage(struct page *page,
goto out;
}
+ BUG_ON(!ext4_handle_valid(handle));
+
ret = walk_page_buffers(handle, page_bufs, 0, len, NULL,
do_journal_get_write_access);
@@ -2668,8 +2680,15 @@ static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
goto out;
}
- io_end->flag = EXT4_IO_END_UNWRITTEN;
+ /*
+ * It may be over-defensive here to check EXT4_IO_END_UNWRITTEN now,
+ * but being more careful is always safe for the future change.
+ */
inode = io_end->inode;
+ if (!(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+ io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ }
/* Add the io_end to per-inode completed io list*/
spin_lock_irqsave(&EXT4_I(inode)->i_completed_io_lock, flags);
@@ -3279,7 +3298,7 @@ make_io:
trace_ext4_load_inode(inode);
get_bh(bh);
bh->b_end_io = end_buffer_read_sync;
- submit_bh(READ_META, bh);
+ submit_bh(READ | REQ_META | REQ_PRIO, bh);
wait_on_buffer(bh);
if (!buffer_uptodate(bh)) {
EXT4_ERROR_INODE_BLOCK(inode, block,
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 565a154e22d..1c924faeb6c 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -922,7 +922,8 @@ restart:
bh = ext4_getblk(NULL, dir, b++, 0, &err);
bh_use[ra_max] = bh;
if (bh)
- ll_rw_block(READ_META, 1, &bh);
+ ll_rw_block(READ | REQ_META | REQ_PRIO,
+ 1, &bh);
}
}
if ((bh = bh_use[ra_ptr++]) == NULL)
@@ -2253,9 +2254,11 @@ static int ext4_symlink(struct inode *dir,
/*
* For non-fast symlinks, we just allocate inode and put it on
* orphan list in the first transaction => we need bitmap,
- * group descriptor, sb, inode block, quota blocks.
+ * group descriptor, sb, inode block, quota blocks, and
+ * possibly selinux xattr blocks.
*/
- credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb);
+ credits = 4 + EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
+ EXT4_XATTR_TRANS_BLOCKS;
} else {
/*
* Fast symlink. We have to add entry to directory
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 430c401d089..92f38ee13f8 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -142,7 +142,23 @@ static void ext4_end_io_work(struct work_struct *work)
unsigned long flags;
int ret;
- mutex_lock(&inode->i_mutex);
+ if (!mutex_trylock(&inode->i_mutex)) {
+ /*
+ * Requeue the work instead of waiting so that the work
+ * items queued after this can be processed.
+ */
+ queue_work(EXT4_SB(inode->i_sb)->dio_unwritten_wq, &io->work);
+ /*
+ * To prevent the ext4-dio-unwritten thread from keeping
+ * requeueing end_io requests and occupying cpu for too long,
+ * yield the cpu if it sees an end_io request that has already
+ * been requeued.
+ */
+ if (io->flag & EXT4_IO_END_QUEUED)
+ yield();
+ io->flag |= EXT4_IO_END_QUEUED;
+ return;
+ }
ret = ext4_end_io_nolock(io);
if (ret < 0) {
mutex_unlock(&inode->i_mutex);
@@ -334,8 +350,10 @@ submit_and_retry:
if ((io_end->num_io_pages >= MAX_IO_PAGES) &&
(io_end->pages[io_end->num_io_pages-1] != io_page))
goto submit_and_retry;
- if (buffer_uninit(bh))
- io->io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ if (buffer_uninit(bh) && !(io_end->flag & EXT4_IO_END_UNWRITTEN)) {
+ io_end->flag |= EXT4_IO_END_UNWRITTEN;
+ atomic_inc(&EXT4_I(inode)->i_aiodio_unwritten);
+ }
io->io_end->size += bh->b_size;
io->io_next_block++;
ret = bio_add_page(io->io_bio, bh->b_page, bh->b_size, bh_offset(bh));
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 4687fea0c00..44d0c8db223 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -919,7 +919,6 @@ static void ext4_i_callback(struct rcu_head *head)
static void ext4_destroy_inode(struct inode *inode)
{
- ext4_ioend_wait(inode);
if (!list_empty(&(EXT4_I(inode)->i_orphan))) {
ext4_msg(inode->i_sb, KERN_ERR,
"Inode %lu (%p): orphan list check failed!",