summaryrefslogtreecommitdiffstats
path: root/fs/ext4
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-07-23 12:27:27 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-07-23 12:27:27 -0700
commita66d2c8f7ec1284206ca7c14569e2a607583f1e3 (patch)
tree08cf68bcef3559b370843cab8191e5cc0f740bde /fs/ext4
parenta6be1fcbc57f95bb47ef3c8e4ee3d83731b8f21e (diff)
parent8cae6f7158ec1fa44c8a04a43db7d8020ec60437 (diff)
Merge branch 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs
Pull the big VFS changes from Al Viro: "This one is *big* and changes quite a few things around VFS. What's in there: - the first of two really major architecture changes - death to open intents. The former is finally there; it was very long in making, but with Miklos getting through really hard and messy final push in fs/namei.c, we finally have it. Unlike his variant, this one doesn't introduce struct opendata; what we have instead is ->atomic_open() taking preallocated struct file * and passing everything via its fields. Instead of returning struct file *, it returns -E... on error, 0 on success and 1 in "deal with it yourself" case (e.g. symlink found on server, etc.). See comments before fs/namei.c:atomic_open(). That made a lot of goodies finally possible and quite a few are in that pile: ->lookup(), ->d_revalidate() and ->create() do not get struct nameidata * anymore; ->lookup() and ->d_revalidate() get lookup flags instead, ->create() gets "do we want it exclusive" flag. With the introduction of new helper (kern_path_locked()) we are rid of all struct nameidata instances outside of fs/namei.c; it's still visible in namei.h, but not for long. Come the next cycle, declaration will move either to fs/internal.h or to fs/namei.c itself. [me, miklos, hch] - The second major change: behaviour of final fput(). Now we have __fput() done without any locks held by caller *and* not from deep in call stack. That obviously lifts a lot of constraints on the locking in there. Moreover, it's legal now to call fput() from atomic contexts (which has immediately simplified life for aio.c). We also don't need anti-recursion logics in __scm_destroy() anymore. There is a price, though - the damn thing has become partially asynchronous. For fput() from normal process we are guaranteed that pending __fput() will be done before the caller returns to userland, exits or gets stopped for ptrace. For kernel threads and atomic contexts it's done via schedule_work(), so theoretically we might need a way to make sure it's finished; so far only one such place had been found, but there might be more. There's flush_delayed_fput() (do all pending __fput()) and there's __fput_sync() (fput() analog doing __fput() immediately). I hope we won't need them often; see warnings in fs/file_table.c for details. [me, based on task_work series from Oleg merged last cycle] - sync series from Jan - large part of "death to sync_supers()" work from Artem; the only bits missing here are exofs and ext4 ones. As far as I understand, those are going via the exofs and ext4 trees resp.; once they are in, we can put ->write_super() to the rest, along with the thread calling it. - preparatory bits from unionmount series (from dhowells). - assorted cleanups and fixes all over the place, as usual. This is not the last pile for this cycle; there's at least jlayton's ESTALE work and fsfreeze series (the latter - in dire need of fixes, so I'm not sure it'll make the cut this cycle). I'll probably throw symlink/hardlink restrictions stuff from Kees into the next pile, too. Plus there's a lot of misc patches I hadn't thrown into that one - it's large enough as it is..." * 'for-linus-2' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (127 commits) ext4: switch EXT4_IOC_RESIZE_FS to mnt_want_write_file() btrfs: switch btrfs_ioctl_balance() to mnt_want_write_file() switch dentry_open() to struct path, make it grab references itself spufs: shift dget/mntget towards dentry_open() zoran: don't bother with struct file * in zoran_map ecryptfs: don't reinvent the wheels, please - use struct completion don't expose I_NEW inodes via dentry->d_inode tidy up namei.c a bit unobfuscate follow_up() a bit ext3: pass custom EOF to generic_file_llseek_size() ext4: use core vfs llseek code for dir seeks vfs: allow custom EOF in generic_file_llseek code vfs: Avoid unnecessary WB_SYNC_NONE writeback during sys_sync and reorder sync passes vfs: Remove unnecessary flushing of block devices vfs: Make sys_sync writeout also block device inodes vfs: Create function for iterating over block devices vfs: Reorder operations during sys_sync quota: Move quota syncing to ->sync_fs method quota: Split dquot_quota_sync() to writeback and cache flushing part vfs: Move noop_backing_dev_info check from sync into writeback ...
Diffstat (limited to 'fs/ext4')
-rw-r--r--fs/ext4/dir.c75
-rw-r--r--fs/ext4/file.c9
-rw-r--r--fs/ext4/fsync.c11
-rw-r--r--fs/ext4/ioctl.c4
-rw-r--r--fs/ext4/namei.c8
-rw-r--r--fs/ext4/super.c5
6 files changed, 32 insertions, 80 deletions
diff --git a/fs/ext4/dir.c b/fs/ext4/dir.c
index aa39e600d15..8e07d2a5a13 100644
--- a/fs/ext4/dir.c
+++ b/fs/ext4/dir.c
@@ -324,74 +324,27 @@ static inline loff_t ext4_get_htree_eof(struct file *filp)
/*
- * ext4_dir_llseek() based on generic_file_llseek() to handle both
- * non-htree and htree directories, where the "offset" is in terms
- * of the filename hash value instead of the byte offset.
+ * ext4_dir_llseek() calls generic_file_llseek_size to handle htree
+ * directories, where the "offset" is in terms of the filename hash
+ * value instead of the byte offset.
*
- * NOTE: offsets obtained *before* ext4_set_inode_flag(dir, EXT4_INODE_INDEX)
- * will be invalid once the directory was converted into a dx directory
+ * Because we may return a 64-bit hash that is well beyond offset limits,
+ * we need to pass the max hash as the maximum allowable offset in
+ * the htree directory case.
+ *
+ * For non-htree, ext4_llseek already chooses the proper max offset.
*/
loff_t ext4_dir_llseek(struct file *file, loff_t offset, int origin)
{
struct inode *inode = file->f_mapping->host;
- loff_t ret = -EINVAL;
int dx_dir = is_dx_dir(inode);
+ loff_t htree_max = ext4_get_htree_eof(file);
- mutex_lock(&inode->i_mutex);
-
- /* NOTE: relative offsets with dx directories might not work
- * as expected, as it is difficult to figure out the
- * correct offset between dx hashes */
-
- switch (origin) {
- case SEEK_END:
- if (unlikely(offset > 0))
- goto out_err; /* not supported for directories */
-
- /* so only negative offsets are left, does that have a
- * meaning for directories at all? */
- if (dx_dir)
- offset += ext4_get_htree_eof(file);
- else
- offset += inode->i_size;
- break;
- case SEEK_CUR:
- /*
- * Here we special-case the lseek(fd, 0, SEEK_CUR)
- * position-querying operation. Avoid rewriting the "same"
- * f_pos value back to the file because a concurrent read(),
- * write() or lseek() might have altered it
- */
- if (offset == 0) {
- offset = file->f_pos;
- goto out_ok;
- }
-
- offset += file->f_pos;
- break;
- }
-
- if (unlikely(offset < 0))
- goto out_err;
-
- if (!dx_dir) {
- if (offset > inode->i_sb->s_maxbytes)
- goto out_err;
- } else if (offset > ext4_get_htree_eof(file))
- goto out_err;
-
- /* Special lock needed here? */
- if (offset != file->f_pos) {
- file->f_pos = offset;
- file->f_version = 0;
- }
-
-out_ok:
- ret = offset;
-out_err:
- mutex_unlock(&inode->i_mutex);
-
- return ret;
+ if (likely(dx_dir))
+ return generic_file_llseek_size(file, offset, origin,
+ htree_max, htree_max);
+ else
+ return ext4_llseek(file, offset, origin);
}
/*
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 8c7642a0005..782eecb57e4 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -211,9 +211,9 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
}
/*
- * ext4_llseek() copied from generic_file_llseek() to handle both
- * block-mapped and extent-mapped maxbytes values. This should
- * otherwise be identical with generic_file_llseek().
+ * ext4_llseek() handles both block-mapped and extent-mapped maxbytes values
+ * by calling generic_file_llseek_size() with the appropriate maxbytes
+ * value for each.
*/
loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
{
@@ -225,7 +225,8 @@ loff_t ext4_llseek(struct file *file, loff_t offset, int origin)
else
maxbytes = inode->i_sb->s_maxbytes;
- return generic_file_llseek_size(file, offset, origin, maxbytes);
+ return generic_file_llseek_size(file, offset, origin,
+ maxbytes, i_size_read(inode));
}
const struct file_operations ext4_file_operations = {
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index bb6c7d81131..2a1dcea4f12 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -135,14 +135,7 @@ static int ext4_sync_parent(struct inode *inode)
inode = igrab(inode);
while (ext4_test_inode_state(inode, EXT4_STATE_NEWENTRY)) {
ext4_clear_inode_state(inode, EXT4_STATE_NEWENTRY);
- dentry = NULL;
- spin_lock(&inode->i_lock);
- if (!list_empty(&inode->i_dentry)) {
- dentry = list_first_entry(&inode->i_dentry,
- struct dentry, d_alias);
- dget(dentry);
- }
- spin_unlock(&inode->i_lock);
+ dentry = d_find_any_alias(inode);
if (!dentry)
break;
next = igrab(dentry->d_parent->d_inode);
@@ -232,7 +225,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
if (!journal) {
ret = __sync_inode(inode, datasync);
- if (!ret && !list_empty(&inode->i_dentry))
+ if (!ret && !hlist_empty(&inode->i_dentry))
ret = ext4_sync_parent(inode);
goto out;
}
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 6ec6f9ee2fe..7f7dad78760 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -389,7 +389,7 @@ group_add_out:
if (err)
return err;
- err = mnt_want_write(filp->f_path.mnt);
+ err = mnt_want_write_file(filp);
if (err)
goto resizefs_out;
@@ -401,7 +401,7 @@ group_add_out:
}
if (err == 0)
err = err2;
- mnt_drop_write(filp->f_path.mnt);
+ mnt_drop_write_file(filp);
resizefs_out:
ext4_resize_end(sb);
return err;
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index 5845cd97bf8..d0d3f0e87f9 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -1312,7 +1312,7 @@ errout:
return NULL;
}
-static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
+static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
struct inode *inode;
struct ext4_dir_entry_2 *de;
@@ -2072,8 +2072,8 @@ static int ext4_add_nondir(handle_t *handle,
int err = ext4_add_entry(handle, dentry, inode);
if (!err) {
ext4_mark_inode_dirty(handle, inode);
- d_instantiate(dentry, inode);
unlock_new_inode(inode);
+ d_instantiate(dentry, inode);
return 0;
}
drop_nlink(inode);
@@ -2091,7 +2091,7 @@ static int ext4_add_nondir(handle_t *handle,
* with d_instantiate().
*/
static int ext4_create(struct inode *dir, struct dentry *dentry, umode_t mode,
- struct nameidata *nd)
+ bool excl)
{
handle_t *handle;
struct inode *inode;
@@ -2249,8 +2249,8 @@ out_clear_inode:
err = ext4_mark_inode_dirty(handle, dir);
if (err)
goto out_clear_inode;
- d_instantiate(dentry, inode);
unlock_new_inode(inode);
+ d_instantiate(dentry, inode);
out_stop:
brelse(dir_block);
ext4_journal_stop(handle);
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index eb7aa3e4ef0..d8759401eca 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -4325,6 +4325,11 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
trace_ext4_sync_fs(sb, wait);
flush_workqueue(sbi->dio_unwritten_wq);
+ /*
+ * Writeback quota in non-journalled quota case - journalled quota has
+ * no dirty dquots
+ */
+ dquot_writeback_dquots(sb, -1);
if (jbd2_journal_start_commit(sbi->s_journal, &target)) {
if (wait)
jbd2_log_wait_commit(sbi->s_journal, target);