summaryrefslogtreecommitdiff
path: root/fs/ext4
diff options
context:
space:
mode:
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/ext4.h2
-rw-r--r--fs/ext4/ext4_jbd2.h56
-rw-r--r--fs/ext4/extents.c2
-rw-r--r--fs/ext4/fsync.c2
-rw-r--r--fs/ext4/inode.c46
-rw-r--r--fs/ext4/page-io.c11
6 files changed, 71 insertions, 48 deletions
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 5b0e26a1272d..dbae4d98dab0 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -184,6 +184,8 @@ struct mpage_da_data {
#define EXT4_IO_END_UNWRITTEN 0x0001
#define EXT4_IO_END_ERROR 0x0002
#define EXT4_IO_END_QUEUED 0x0004
+#define EXT4_IO_END_DIRECT 0x0008
+#define EXT4_IO_END_IN_FSYNC 0x0010
struct ext4_io_page {
struct page *p_page;
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index 5802fa1dab18..95af6f878501 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -261,43 +261,45 @@ static inline void ext4_update_inode_fsync_trans(handle_t *handle,
/* super.c */
int ext4_force_commit(struct super_block *sb);
-static inline int ext4_should_journal_data(struct inode *inode)
+/*
+ * Ext4 inode journal modes
+ */
+#define EXT4_INODE_JOURNAL_DATA_MODE 0x01 /* journal data mode */
+#define EXT4_INODE_ORDERED_DATA_MODE 0x02 /* ordered data mode */
+#define EXT4_INODE_WRITEBACK_DATA_MODE 0x04 /* writeback data mode */
+
+static inline int ext4_inode_journal_mode(struct inode *inode)
{
if (EXT4_JOURNAL(inode) == NULL)
- return 0;
- if (!S_ISREG(inode->i_mode))
- return 1;
- if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
- return 1;
- if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA))
- return 1;
- return 0;
+ return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
+ /* We do not support data journalling with delayed allocation */
+ if (!S_ISREG(inode->i_mode) ||
+ test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_JOURNAL_DATA)
+ return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
+ if (ext4_test_inode_flag(inode, EXT4_INODE_JOURNAL_DATA) &&
+ !test_opt(inode->i_sb, DELALLOC))
+ return EXT4_INODE_JOURNAL_DATA_MODE; /* journal data */
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_ORDERED_DATA)
+ return EXT4_INODE_ORDERED_DATA_MODE; /* ordered */
+ if (test_opt(inode->i_sb, DATA_FLAGS) == EXT4_MOUNT_WRITEBACK_DATA)
+ return EXT4_INODE_WRITEBACK_DATA_MODE; /* writeback */
+ else
+ BUG();
+}
+
+static inline int ext4_should_journal_data(struct inode *inode)
+{
+ return ext4_inode_journal_mode(inode) & EXT4_INODE_JOURNAL_DATA_MODE;
}
static inline int ext4_should_order_data(struct inode *inode)
{
- if (EXT4_JOURNAL(inode) == NULL)
- return 0;
- 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_ORDERED_DATA)
- return 1;
- return 0;
+ return ext4_inode_journal_mode(inode) & EXT4_INODE_ORDERED_DATA_MODE;
}
static inline int ext4_should_writeback_data(struct inode *inode)
{
- 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)
- return 1;
- return 0;
+ return ext4_inode_journal_mode(inode) & EXT4_INODE_WRITEBACK_DATA_MODE;
}
/*
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 607b1557d292..75070365f479 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -301,6 +301,8 @@ static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext)
ext4_fsblk_t block = ext4_ext_pblock(ext);
int len = ext4_ext_get_actual_len(ext);
+ if (len == 0)
+ return 0;
return ext4_data_block_valid(EXT4_SB(inode->i_sb), block, len);
}
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 00a2cb753efd..bb6c7d811313 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -89,6 +89,7 @@ int ext4_flush_completed_IO(struct inode *inode)
io = list_entry(ei->i_completed_io_list.next,
ext4_io_end_t, list);
list_del_init(&io->list);
+ io->flag |= EXT4_IO_END_IN_FSYNC;
/*
* Calling ext4_end_io_nolock() to convert completed
* IO to written.
@@ -108,6 +109,7 @@ int ext4_flush_completed_IO(struct inode *inode)
if (ret < 0)
ret2 = ret;
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ io->flag &= ~EXT4_IO_END_IN_FSYNC;
}
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
return (ret2 < 0) ? ret2 : 0;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 92655fd89657..3ce761373241 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -2480,13 +2480,14 @@ static int ext4_da_write_end(struct file *file,
int write_mode = (int)(unsigned long)fsdata;
if (write_mode == FALL_BACK_TO_NONDELALLOC) {
- if (ext4_should_order_data(inode)) {
+ switch (ext4_inode_journal_mode(inode)) {
+ case EXT4_INODE_ORDERED_DATA_MODE:
return ext4_ordered_write_end(file, mapping, pos,
len, copied, page, fsdata);
- } else if (ext4_should_writeback_data(inode)) {
+ case EXT4_INODE_WRITEBACK_DATA_MODE:
return ext4_writeback_write_end(file, mapping, pos,
len, copied, page, fsdata);
- } else {
+ default:
BUG();
}
}
@@ -2793,9 +2794,6 @@ out:
/* queue the work to convert unwritten extents to written */
queue_work(wq, &io_end->work);
-
- /* XXX: probably should move into the real I/O completion handler */
- inode_dio_done(inode);
}
static void ext4_end_io_buffer_write(struct buffer_head *bh, int uptodate)
@@ -2919,9 +2917,12 @@ static ssize_t ext4_ext_direct_IO(int rw, struct kiocb *iocb,
iocb->private = NULL;
EXT4_I(inode)->cur_aio_dio = NULL;
if (!is_sync_kiocb(iocb)) {
- iocb->private = ext4_init_io_end(inode, GFP_NOFS);
- if (!iocb->private)
+ ext4_io_end_t *io_end =
+ ext4_init_io_end(inode, GFP_NOFS);
+ if (!io_end)
return -ENOMEM;
+ io_end->flag |= EXT4_IO_END_DIRECT;
+ iocb->private = io_end;
/*
* we save the io structure for current async
* direct IO, so that later ext4_map_blocks()
@@ -3084,18 +3085,25 @@ static const struct address_space_operations ext4_da_aops = {
void ext4_set_aops(struct inode *inode)
{
- if (ext4_should_order_data(inode) &&
- test_opt(inode->i_sb, DELALLOC))
- inode->i_mapping->a_ops = &ext4_da_aops;
- else if (ext4_should_order_data(inode))
- inode->i_mapping->a_ops = &ext4_ordered_aops;
- else if (ext4_should_writeback_data(inode) &&
- test_opt(inode->i_sb, DELALLOC))
- inode->i_mapping->a_ops = &ext4_da_aops;
- else if (ext4_should_writeback_data(inode))
- inode->i_mapping->a_ops = &ext4_writeback_aops;
- else
+ switch (ext4_inode_journal_mode(inode)) {
+ case EXT4_INODE_ORDERED_DATA_MODE:
+ if (test_opt(inode->i_sb, DELALLOC))
+ inode->i_mapping->a_ops = &ext4_da_aops;
+ else
+ inode->i_mapping->a_ops = &ext4_ordered_aops;
+ break;
+ case EXT4_INODE_WRITEBACK_DATA_MODE:
+ if (test_opt(inode->i_sb, DELALLOC))
+ inode->i_mapping->a_ops = &ext4_da_aops;
+ else
+ inode->i_mapping->a_ops = &ext4_writeback_aops;
+ break;
+ case EXT4_INODE_JOURNAL_DATA_MODE:
inode->i_mapping->a_ops = &ext4_journalled_aops;
+ break;
+ default:
+ BUG();
+ }
}
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index 7e106c810c62..24feb1ced3fd 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -111,6 +111,8 @@ int ext4_end_io_nolock(ext4_io_end_t *io)
if (io->iocb)
aio_complete(io->iocb, io->result, 0);
+ if (io->flag & EXT4_IO_END_DIRECT)
+ inode_dio_done(inode);
/* Wake up anyone waiting on unwritten extent conversion */
if (atomic_dec_and_test(&EXT4_I(inode)->i_aiodio_unwritten))
wake_up_all(ext4_ioend_wq(io->inode));
@@ -128,12 +130,18 @@ static void ext4_end_io_work(struct work_struct *work)
unsigned long flags;
spin_lock_irqsave(&ei->i_completed_io_lock, flags);
+ if (io->flag & EXT4_IO_END_IN_FSYNC)
+ goto requeue;
if (list_empty(&io->list)) {
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
goto free;
}
if (!mutex_trylock(&inode->i_mutex)) {
+ bool was_queued;
+requeue:
+ was_queued = !!(io->flag & EXT4_IO_END_QUEUED);
+ io->flag |= EXT4_IO_END_QUEUED;
spin_unlock_irqrestore(&ei->i_completed_io_lock, flags);
/*
* Requeue the work instead of waiting so that the work
@@ -146,9 +154,8 @@ static void ext4_end_io_work(struct work_struct *work)
* yield the cpu if it sees an end_io request that has already
* been requeued.
*/
- if (io->flag & EXT4_IO_END_QUEUED)
+ if (was_queued)
yield();
- io->flag |= EXT4_IO_END_QUEUED;
return;
}
list_del_init(&io->list);