From 1eb2cbb6d5efe129cd006691267ce513c0aa59da Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 27 May 2010 11:11:06 -0400 Subject: [PATCH 01/17] Revert "anon_inode: set S_IFREG on the anon_inode" This reverts commit a7cf4145bb86aaf85d4d4d29a69b50b688e2e49d. --- fs/anon_inodes.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c index 9bd4b3876c99..e4b75d6eda83 100644 --- a/fs/anon_inodes.c +++ b/fs/anon_inodes.c @@ -205,7 +205,7 @@ static struct inode *anon_inode_mkinode(void) * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; - inode->i_mode = S_IFREG | S_IRUSR | S_IWUSR; + inode->i_mode = S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_flags |= S_PRIVATE; From 176306f59ac7a35369cbba87aff13e14c5916074 Mon Sep 17 00:00:00 2001 From: Neil Brown Date: Mon, 24 May 2010 16:57:56 +1000 Subject: [PATCH 02/17] VFS: fix recent breakage of FS_REVAL_DOT Commit 1f36f774b22a0ceb7dd33eca626746c81a97b6a5 broke FS_REVAL_DOT semantics. In particular, before this patch, the command ls -l in an NFS mounted directory would always check if the directory on the server had changed and if so would flush and refill the pagecache for the dir. After this patch, the same "ls -l" will repeatedly return stale date until the cached attributes for the directory time out. The following patch fixes this by ensuring the d_revalidate is called by do_last when "." is being looked-up. link_path_walk has already called d_revalidate, but in that case LOOKUP_OPEN is not set so nfs_lookup_verify_inode chooses not to do any validation. The following patch restores the original behaviour. Cc: stable@kernel.org Signed-off-by: NeilBrown Signed-off-by: Al Viro --- fs/namei.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/namei.c b/fs/namei.c index 48e1f60520ea..868d0cb9d473 100644 --- a/fs/namei.c +++ b/fs/namei.c @@ -1621,6 +1621,7 @@ static struct file *do_last(struct nameidata *nd, struct path *path, case LAST_DOTDOT: follow_dotdot(nd); dir = nd->path.dentry; + case LAST_DOT: if (nd->path.mnt->mnt_sb->s_type->fs_flags & FS_REVAL_DOT) { if (!dir->d_op->d_revalidate(dir, nd)) { error = -ESTALE; @@ -1628,7 +1629,6 @@ static struct file *do_last(struct nameidata *nd, struct path *path, } } /* fallthrough */ - case LAST_DOT: case LAST_ROOT: if (open_flag & O_CREAT) goto exit; From d7065da038227a4d09a244e6014e0186a6bd21d0 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 26 May 2010 15:13:55 -0400 Subject: [PATCH 03/17] get rid of the magic around f_count in aio __aio_put_req() plays sick games with file refcount. What it wants is fput() from atomic context; it's almost always done with f_count > 1, so they only have to deal with delayed work in rare cases when their reference happens to be the last one. Current code decrements f_count and if it hasn't hit 0, everything is fine. Otherwise it keeps a pointer to struct file (with zero f_count!) around and has delayed work do __fput() on it. Better way to do it: use atomic_long_add_unless( , -1, 1) instead of !atomic_long_dec_and_test(). IOW, decrement it only if it's not the last reference, leave refcount alone if it was. And use normal fput() in delayed work. I've made that atomic_long_add_unless call a new helper - fput_atomic(). Drops a reference to file if it's safe to do in atomic (i.e. if that's not the last one), tells if it had been able to do that. aio.c converted to it, __fput() use is gone. req->ki_file *always* contributes to refcount now. And __fput() became static. Signed-off-by: Al Viro --- fs/aio.c | 6 +++--- fs/file_table.c | 21 ++++++++++----------- include/linux/file.h | 1 - include/linux/fs.h | 1 + 4 files changed, 14 insertions(+), 15 deletions(-) diff --git a/fs/aio.c b/fs/aio.c index 48fdeebdb544..1ccf25cef1f0 100644 --- a/fs/aio.c +++ b/fs/aio.c @@ -527,7 +527,7 @@ static void aio_fput_routine(struct work_struct *data) /* Complete the fput(s) */ if (req->ki_filp != NULL) - __fput(req->ki_filp); + fput(req->ki_filp); /* Link the iocb into the context's free list */ spin_lock_irq(&ctx->ctx_lock); @@ -560,11 +560,11 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req) /* * Try to optimize the aio and eventfd file* puts, by avoiding to - * schedule work in case it is not __fput() time. In normal cases, + * schedule work in case it is not final fput() time. In normal cases, * we would not be holding the last reference to the file*, so * this function will be executed w/out any aio kthread wakeup. */ - if (unlikely(atomic_long_dec_and_test(&req->ki_filp->f_count))) { + if (unlikely(!fput_atomic(req->ki_filp))) { get_ioctx(ctx); spin_lock(&fput_lock); list_add(&req->ki_list, &fput_head); diff --git a/fs/file_table.c b/fs/file_table.c index 32d12b78bac8..5c7d10ead4ad 100644 --- a/fs/file_table.c +++ b/fs/file_table.c @@ -194,14 +194,6 @@ struct file *alloc_file(struct path *path, fmode_t mode, } EXPORT_SYMBOL(alloc_file); -void fput(struct file *file) -{ - if (atomic_long_dec_and_test(&file->f_count)) - __fput(file); -} - -EXPORT_SYMBOL(fput); - /** * drop_file_write_access - give up ability to write to a file * @file: the file to which we will stop writing @@ -227,10 +219,9 @@ void drop_file_write_access(struct file *file) } EXPORT_SYMBOL_GPL(drop_file_write_access); -/* __fput is called from task context when aio completion releases the last - * last use of a struct file *. Do not use otherwise. +/* the real guts of fput() - releasing the last reference to file */ -void __fput(struct file *file) +static void __fput(struct file *file) { struct dentry *dentry = file->f_path.dentry; struct vfsmount *mnt = file->f_path.mnt; @@ -268,6 +259,14 @@ void __fput(struct file *file) mntput(mnt); } +void fput(struct file *file) +{ + if (atomic_long_dec_and_test(&file->f_count)) + __fput(file); +} + +EXPORT_SYMBOL(fput); + struct file *fget(unsigned int fd) { struct file *file; diff --git a/include/linux/file.h b/include/linux/file.h index 5555508fd517..b1e12970f617 100644 --- a/include/linux/file.h +++ b/include/linux/file.h @@ -11,7 +11,6 @@ struct file; -extern void __fput(struct file *); extern void fput(struct file *); extern void drop_file_write_access(struct file *file); diff --git a/include/linux/fs.h b/include/linux/fs.h index 85e823adcd4a..3d9ed8302402 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -954,6 +954,7 @@ extern spinlock_t files_lock; #define file_list_unlock() spin_unlock(&files_lock); #define get_file(x) atomic_long_inc(&(x)->f_count) +#define fput_atomic(x) atomic_long_add_unless(&(x)->f_count, -1, 1) #define file_count(x) atomic_long_read(&(x)->f_count) #ifdef CONFIG_DEBUG_WRITECOUNT From ea635c64e007061f6468ece5cc9cc62d41d4ecf2 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Wed, 26 May 2010 17:40:29 -0400 Subject: [PATCH 04/17] Fix racy use of anon_inode_getfd() in perf_event.c once anon_inode_getfd() is called, you can't expect *anything* about struct file that descriptor points to - another thread might be doing whatever it likes with descriptor table at that point. Cc: stable Signed-off-by: Al Viro --- kernel/perf_event.c | 44 ++++++++++++++++++++++++-------------------- 1 file changed, 24 insertions(+), 20 deletions(-) diff --git a/kernel/perf_event.c b/kernel/perf_event.c index e099650cd249..bd7ce8ca5bb9 100644 --- a/kernel/perf_event.c +++ b/kernel/perf_event.c @@ -4999,8 +4999,8 @@ SYSCALL_DEFINE5(perf_event_open, struct perf_event_context *ctx; struct file *event_file = NULL; struct file *group_file = NULL; + int event_fd; int fput_needed = 0; - int fput_needed2 = 0; int err; /* for future expandability... */ @@ -5021,12 +5021,18 @@ SYSCALL_DEFINE5(perf_event_open, return -EINVAL; } + event_fd = get_unused_fd_flags(O_RDWR); + if (event_fd < 0) + return event_fd; + /* * Get the target context (task or percpu): */ ctx = find_get_context(pid, cpu); - if (IS_ERR(ctx)) - return PTR_ERR(ctx); + if (IS_ERR(ctx)) { + err = PTR_ERR(ctx); + goto err_fd; + } /* * Look up the group leader (we will attach this event to it): @@ -5066,13 +5072,11 @@ SYSCALL_DEFINE5(perf_event_open, if (IS_ERR(event)) goto err_put_context; - err = anon_inode_getfd("[perf_event]", &perf_fops, event, O_RDWR); - if (err < 0) - goto err_free_put_context; - - event_file = fget_light(err, &fput_needed2); - if (!event_file) + event_file = anon_inode_getfile("[perf_event]", &perf_fops, event, O_RDWR); + if (IS_ERR(event_file)) { + err = PTR_ERR(event_file); goto err_free_put_context; + } if (flags & PERF_FLAG_FD_OUTPUT) { err = perf_event_set_output(event, group_fd); @@ -5093,19 +5097,19 @@ SYSCALL_DEFINE5(perf_event_open, list_add_tail(&event->owner_entry, ¤t->perf_event_list); mutex_unlock(¤t->perf_event_mutex); -err_fput_free_put_context: - fput_light(event_file, fput_needed2); - -err_free_put_context: - if (err < 0) - free_event(event); - -err_put_context: - if (err < 0) - put_ctx(ctx); - fput_light(group_file, fput_needed); + fd_install(event_fd, event_file); + return event_fd; +err_fput_free_put_context: + fput(event_file); +err_free_put_context: + free_event(event); +err_put_context: + fput_light(group_file, fput_needed); + put_ctx(ctx); +err_fd: + put_unused_fd(event_fd); return err; } From cc967be54710d97c05229b2e5ba2d00df84ddd64 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Wed, 26 May 2010 17:54:39 +0200 Subject: [PATCH 05/17] fs: Add missing mutex_unlock Add a mutex_unlock missing on the error path. At other exists from the function that return an error flag, the mutex is unlocked, so do the same here. The semantic match that finds this problem is as follows: (http://coccinelle.lip6.fr/) // @@ expression E1; @@ * mutex_lock(E1,...); <+... when != E1 if (...) { ... when != E1 * return ...; } ...+> * mutex_unlock(E1,...); // Signed-off-by: Julia Lawall Signed-off-by: Al Viro --- fs/pipe.c | 13 +++++++++---- 1 file changed, 9 insertions(+), 4 deletions(-) diff --git a/fs/pipe.c b/fs/pipe.c index d79872eba09a..60da077400f1 100644 --- a/fs/pipe.c +++ b/fs/pipe.c @@ -1169,14 +1169,18 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) switch (cmd) { case F_SETPIPE_SZ: - if (!capable(CAP_SYS_ADMIN) && arg > pipe_max_pages) - return -EINVAL; + if (!capable(CAP_SYS_ADMIN) && arg > pipe_max_pages) { + ret = -EINVAL; + goto out; + } /* * The pipe needs to be at least 2 pages large to * guarantee POSIX behaviour. */ - if (arg < 2) - return -EINVAL; + if (arg < 2) { + ret = -EINVAL; + goto out; + } ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: @@ -1187,6 +1191,7 @@ long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) break; } +out: mutex_unlock(&pipe->inode->i_mutex); return ret; } From 7ea8085910ef3dd4f3cad6845aaa2b580d39b115 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 May 2010 17:53:25 +0200 Subject: [PATCH 06/17] drop unused dentry argument to ->fsync Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- Documentation/filesystems/Locking | 2 +- Documentation/filesystems/vfs.txt | 2 +- arch/powerpc/platforms/cell/spufs/file.c | 3 +-- drivers/char/ps3flash.c | 3 +-- drivers/mtd/ubi/cdev.c | 3 +-- drivers/staging/pohmelfs/inode.c | 2 +- drivers/usb/gadget/printer.c | 2 +- drivers/video/fb_defio.c | 2 +- fs/9p/vfs_file.c | 6 ++---- fs/affs/affs.h | 2 +- fs/affs/file.c | 4 ++-- fs/afs/internal.h | 2 +- fs/afs/write.c | 3 ++- fs/bad_inode.c | 3 +-- fs/block_dev.c | 7 +------ fs/btrfs/ctree.h | 2 +- fs/btrfs/file.c | 3 ++- fs/ceph/caps.c | 4 ++-- fs/ceph/dir.c | 5 ++--- fs/ceph/super.h | 2 +- fs/cifs/cifsfs.h | 2 +- fs/cifs/file.c | 4 ++-- fs/coda/coda_int.h | 3 +-- fs/coda/file.c | 4 ++-- fs/ecryptfs/file.c | 2 +- fs/exofs/file.c | 7 +++---- fs/ext2/ext2.h | 2 +- fs/ext2/file.c | 6 +++--- fs/ext3/fsync.c | 4 ++-- fs/ext4/ext4.h | 2 +- fs/ext4/fsync.c | 8 ++++---- fs/fat/fat.h | 3 +-- fs/fat/file.c | 6 +++--- fs/fuse/dir.c | 5 ++--- fs/fuse/file.c | 9 ++++----- fs/fuse/fuse_i.h | 3 +-- fs/gfs2/file.c | 4 ++-- fs/hostfs/hostfs_kern.c | 4 ++-- fs/hpfs/file.c | 4 ++-- fs/hpfs/hpfs_fn.h | 2 +- fs/hppfs/hppfs.c | 2 +- fs/jffs2/file.c | 4 ++-- fs/jffs2/os-linux.h | 2 +- fs/jfs/file.c | 4 ++-- fs/jfs/jfs_inode.h | 2 +- fs/libfs.c | 6 +++--- fs/logfs/file.c | 4 ++-- fs/logfs/logfs.h | 2 +- fs/ncpfs/file.c | 2 +- fs/nfs/dir.c | 6 ++++-- fs/nfs/file.c | 5 +++-- fs/nilfs2/file.c | 4 ++-- fs/nilfs2/nilfs.h | 2 +- fs/ntfs/dir.c | 5 ++--- fs/ntfs/file.c | 9 ++------- fs/ocfs2/file.c | 7 +++---- fs/reiserfs/dir.c | 8 +++----- fs/reiserfs/file.c | 5 ++--- fs/smbfs/file.c | 3 ++- fs/sync.c | 8 +++----- fs/ubifs/file.c | 4 ++-- fs/ubifs/ubifs.h | 2 +- fs/xfs/linux-2.6/xfs_file.c | 10 +++++----- include/linux/buffer_head.h | 2 +- include/linux/ext3_fs.h | 2 +- include/linux/fb.h | 5 +---- include/linux/fs.h | 8 ++++---- include/trace/events/ext4.h | 6 ++++-- ipc/shm.c | 11 ++++------- 69 files changed, 129 insertions(+), 157 deletions(-) diff --git a/Documentation/filesystems/Locking b/Documentation/filesystems/Locking index 61c98f03baa1..96d4293607ec 100644 --- a/Documentation/filesystems/Locking +++ b/Documentation/filesystems/Locking @@ -380,7 +380,7 @@ prototypes: int (*open) (struct inode *, struct file *); int (*flush) (struct file *); int (*release) (struct inode *, struct file *); - int (*fsync) (struct file *, struct dentry *, int datasync); + int (*fsync) (struct file *, int datasync); int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index b66858538df5..d4f5731dcbbb 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -729,7 +729,7 @@ struct file_operations { int (*open) (struct inode *, struct file *); int (*flush) (struct file *); int (*release) (struct inode *, struct file *); - int (*fsync) (struct file *, struct dentry *, int datasync); + int (*fsync) (struct file *, int datasync); int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); diff --git a/arch/powerpc/platforms/cell/spufs/file.c b/arch/powerpc/platforms/cell/spufs/file.c index 5c2808252516..1a40da92154c 100644 --- a/arch/powerpc/platforms/cell/spufs/file.c +++ b/arch/powerpc/platforms/cell/spufs/file.c @@ -1849,8 +1849,7 @@ out: return ret; } -static int spufs_mfc_fsync(struct file *file, struct dentry *dentry, - int datasync) +static int spufs_mfc_fsync(struct file *file, int datasync) { return spufs_mfc_flush(file, NULL); } diff --git a/drivers/char/ps3flash.c b/drivers/char/ps3flash.c index 606048b72bcf..85c004a518ee 100644 --- a/drivers/char/ps3flash.c +++ b/drivers/char/ps3flash.c @@ -305,8 +305,7 @@ static int ps3flash_flush(struct file *file, fl_owner_t id) return ps3flash_writeback(ps3flash_dev); } -static int ps3flash_fsync(struct file *file, struct dentry *dentry, - int datasync) +static int ps3flash_fsync(struct file *file, int datasync) { return ps3flash_writeback(ps3flash_dev); } diff --git a/drivers/mtd/ubi/cdev.c b/drivers/mtd/ubi/cdev.c index 72ebb3f06b86..4dfa6b90c21c 100644 --- a/drivers/mtd/ubi/cdev.c +++ b/drivers/mtd/ubi/cdev.c @@ -189,8 +189,7 @@ static loff_t vol_cdev_llseek(struct file *file, loff_t offset, int origin) return new_offset; } -static int vol_cdev_fsync(struct file *file, struct dentry *dentry, - int datasync) +static int vol_cdev_fsync(struct file *file, int datasync) { struct ubi_volume_desc *desc = file->private_data; struct ubi_device *ubi = desc->vol->ubi; diff --git a/drivers/staging/pohmelfs/inode.c b/drivers/staging/pohmelfs/inode.c index 9286e863b0e7..e92595eff1b8 100644 --- a/drivers/staging/pohmelfs/inode.c +++ b/drivers/staging/pohmelfs/inode.c @@ -880,7 +880,7 @@ static struct inode *pohmelfs_alloc_inode(struct super_block *sb) /* * We want fsync() to work on POHMELFS. */ -static int pohmelfs_fsync(struct file *file, struct dentry *dentry, int datasync) +static int pohmelfs_fsync(struct file *file, int datasync) { struct inode *inode = file->f_mapping->host; struct writeback_control wbc = { diff --git a/drivers/usb/gadget/printer.c b/drivers/usb/gadget/printer.c index 6b8bf8c781c4..43abf55d8c60 100644 --- a/drivers/usb/gadget/printer.c +++ b/drivers/usb/gadget/printer.c @@ -794,7 +794,7 @@ printer_write(struct file *fd, const char __user *buf, size_t len, loff_t *ptr) } static int -printer_fsync(struct file *fd, struct dentry *dentry, int datasync) +printer_fsync(struct file *fd, int datasync) { struct printer_dev *dev = fd->private_data; unsigned long flags; diff --git a/drivers/video/fb_defio.c b/drivers/video/fb_defio.c index 1105a591dcc1..073c9b408cf7 100644 --- a/drivers/video/fb_defio.c +++ b/drivers/video/fb_defio.c @@ -66,7 +66,7 @@ static int fb_deferred_io_fault(struct vm_area_struct *vma, return 0; } -int fb_deferred_io_fsync(struct file *file, struct dentry *dentry, int datasync) +int fb_deferred_io_fsync(struct file *file, int datasync) { struct fb_info *info = file->private_data; diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index 25b300e1c9d7..2bedc6c94fc2 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -257,15 +257,13 @@ v9fs_file_write(struct file *filp, const char __user * data, return total; } -static int v9fs_file_fsync(struct file *filp, struct dentry *dentry, - int datasync) +static int v9fs_file_fsync(struct file *filp, int datasync) { struct p9_fid *fid; struct p9_wstat wstat; int retval; - P9_DPRINTK(P9_DEBUG_VFS, "filp %p dentry %p datasync %x\n", filp, - dentry, datasync); + P9_DPRINTK(P9_DEBUG_VFS, "filp %p datasync %x\n", filp, datasync); fid = filp->private_data; v9fs_blank_wstat(&wstat); diff --git a/fs/affs/affs.h b/fs/affs/affs.h index 861dae68ac12..f05b6155ccc8 100644 --- a/fs/affs/affs.h +++ b/fs/affs/affs.h @@ -183,7 +183,7 @@ extern int affs_add_entry(struct inode *dir, struct inode *inode, struct dent void affs_free_prealloc(struct inode *inode); extern void affs_truncate(struct inode *); -int affs_file_fsync(struct file *, struct dentry *, int); +int affs_file_fsync(struct file *, int); /* dir.c */ diff --git a/fs/affs/file.c b/fs/affs/file.c index 184e55c1c9ba..322710c3eedf 100644 --- a/fs/affs/file.c +++ b/fs/affs/file.c @@ -916,9 +916,9 @@ affs_truncate(struct inode *inode) affs_free_prealloc(inode); } -int affs_file_fsync(struct file *filp, struct dentry *dentry, int datasync) +int affs_file_fsync(struct file *filp, int datasync) { - struct inode * inode = dentry->d_inode; + struct inode *inode = filp->f_mapping->host; int ret, err; ret = write_inode_now(inode, 0); diff --git a/fs/afs/internal.h b/fs/afs/internal.h index 807f284cc75e..5f679b77ce24 100644 --- a/fs/afs/internal.h +++ b/fs/afs/internal.h @@ -740,7 +740,7 @@ extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *); extern ssize_t afs_file_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); extern int afs_writeback_all(struct afs_vnode *); -extern int afs_fsync(struct file *, struct dentry *, int); +extern int afs_fsync(struct file *, int); /*****************************************************************************/ diff --git a/fs/afs/write.c b/fs/afs/write.c index 3bed54a294d4..3dab9e9948d0 100644 --- a/fs/afs/write.c +++ b/fs/afs/write.c @@ -701,8 +701,9 @@ int afs_writeback_all(struct afs_vnode *vnode) * - the return status from this call provides a reliable indication of * whether any write errors occurred for this process. */ -int afs_fsync(struct file *file, struct dentry *dentry, int datasync) +int afs_fsync(struct file *file, int datasync) { + struct dentry *dentry = file->f_path.dentry; struct afs_writeback *wb, *xwb; struct afs_vnode *vnode = AFS_FS_I(dentry->d_inode); int ret; diff --git a/fs/bad_inode.c b/fs/bad_inode.c index a05287a23f62..52e59bf4aa5f 100644 --- a/fs/bad_inode.c +++ b/fs/bad_inode.c @@ -93,8 +93,7 @@ static int bad_file_release(struct inode *inode, struct file *filp) return -EIO; } -static int bad_file_fsync(struct file *file, struct dentry *dentry, - int datasync) +static int bad_file_fsync(struct file *file, int datasync) { return -EIO; } diff --git a/fs/block_dev.c b/fs/block_dev.c index 26e5f5026620..d0b37e626a1a 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -358,12 +358,7 @@ static loff_t block_llseek(struct file *file, loff_t offset, int origin) return retval; } -/* - * Filp is never NULL; the only case when ->fsync() is called with - * NULL first argument is nfsd_sync_dir() and that's not a directory. - */ - -int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync) +int blkdev_fsync(struct file *filp, int datasync) { struct inode *bd_inode = filp->f_mapping->host; struct block_device *bdev = I_BDEV(bd_inode); diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h index e9bf86415e86..29c20092847e 100644 --- a/fs/btrfs/ctree.h +++ b/fs/btrfs/ctree.h @@ -2434,7 +2434,7 @@ void btrfs_update_iflags(struct inode *inode); void btrfs_inherit_iflags(struct inode *inode, struct inode *dir); /* file.c */ -int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync); +int btrfs_sync_file(struct file *file, int datasync); int btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end, int skip_pinned); int btrfs_check_file(struct btrfs_root *root, struct inode *inode); diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c index 79437c5eeb1e..787b50a16a14 100644 --- a/fs/btrfs/file.c +++ b/fs/btrfs/file.c @@ -1101,8 +1101,9 @@ int btrfs_release_file(struct inode *inode, struct file *filp) * important optimization for directories because holding the mutex prevents * new operations on the dir while we write to disk. */ -int btrfs_sync_file(struct file *file, struct dentry *dentry, int datasync) +int btrfs_sync_file(struct file *file, int datasync) { + struct dentry *dentry = file->f_path.dentry; struct inode *inode = dentry->d_inode; struct btrfs_root *root = BTRFS_I(inode)->root; int ret = 0; diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c index 0dd0b81e64f7..ae3e3a306445 100644 --- a/fs/ceph/caps.c +++ b/fs/ceph/caps.c @@ -1776,9 +1776,9 @@ out: spin_unlock(&ci->i_unsafe_lock); } -int ceph_fsync(struct file *file, struct dentry *dentry, int datasync) +int ceph_fsync(struct file *file, int datasync) { - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_mapping->host; struct ceph_inode_info *ci = ceph_inode(inode); unsigned flush_tid; int ret; diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c index 4fd30900eff7..0057f4a07347 100644 --- a/fs/ceph/dir.c +++ b/fs/ceph/dir.c @@ -1107,10 +1107,9 @@ static ssize_t ceph_read_dir(struct file *file, char __user *buf, size_t size, * an fsync() on a dir will wait for any uncommitted directory * operations to commit. */ -static int ceph_dir_fsync(struct file *file, struct dentry *dentry, - int datasync) +static int ceph_dir_fsync(struct file *file, int datasync) { - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_path.dentry->d_inode; struct ceph_inode_info *ci = ceph_inode(inode); struct list_head *head = &ci->i_unsafe_dirops; struct ceph_mds_request *req; diff --git a/fs/ceph/super.h b/fs/ceph/super.h index 3725c9ee9d08..dd1e7add656b 100644 --- a/fs/ceph/super.h +++ b/fs/ceph/super.h @@ -811,7 +811,7 @@ extern void ceph_put_cap(struct ceph_cap *cap); extern void ceph_queue_caps_release(struct inode *inode); extern int ceph_write_inode(struct inode *inode, struct writeback_control *wbc); -extern int ceph_fsync(struct file *file, struct dentry *dentry, int datasync); +extern int ceph_fsync(struct file *file, int datasync); extern void ceph_kick_flushing_caps(struct ceph_mds_client *mdsc, struct ceph_mds_session *session); extern int ceph_get_cap_mds(struct inode *inode); diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index 0242ff9cbf41..a7eb65c84b1c 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -84,7 +84,7 @@ extern ssize_t cifs_user_read(struct file *file, char __user *read_data, extern ssize_t cifs_user_write(struct file *file, const char __user *write_data, size_t write_size, loff_t *poffset); extern int cifs_lock(struct file *, int, struct file_lock *); -extern int cifs_fsync(struct file *, struct dentry *, int); +extern int cifs_fsync(struct file *, int); extern int cifs_flush(struct file *, fl_owner_t id); extern int cifs_file_mmap(struct file * , struct vm_area_struct *); extern const struct file_operations cifs_dir_ops; diff --git a/fs/cifs/file.c b/fs/cifs/file.c index a83541ec9713..f1ff785b2292 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1676,7 +1676,7 @@ static int cifs_write_end(struct file *file, struct address_space *mapping, return rc; } -int cifs_fsync(struct file *file, struct dentry *dentry, int datasync) +int cifs_fsync(struct file *file, int datasync) { int xid; int rc = 0; @@ -1688,7 +1688,7 @@ int cifs_fsync(struct file *file, struct dentry *dentry, int datasync) xid = GetXid(); cFYI(1, "Sync file - name: %s datasync: 0x%x", - dentry->d_name.name, datasync); + file->f_path.dentry->d_name.name, datasync); rc = filemap_write_and_wait(inode->i_mapping); if (rc == 0) { diff --git a/fs/coda/coda_int.h b/fs/coda/coda_int.h index d99860a33890..6b443ff43a19 100644 --- a/fs/coda/coda_int.h +++ b/fs/coda/coda_int.h @@ -11,8 +11,7 @@ extern int coda_fake_statfs; void coda_destroy_inodecache(void); int coda_init_inodecache(void); -int coda_fsync(struct file *coda_file, struct dentry *coda_dentry, - int datasync); +int coda_fsync(struct file *coda_file, int datasync); void coda_sysctl_init(void); void coda_sysctl_clean(void); diff --git a/fs/coda/file.c b/fs/coda/file.c index 7196077b1688..ad3cd2abeeb4 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -202,10 +202,10 @@ int coda_release(struct inode *coda_inode, struct file *coda_file) return 0; } -int coda_fsync(struct file *coda_file, struct dentry *coda_dentry, int datasync) +int coda_fsync(struct file *coda_file, int datasync) { struct file *host_file; - struct inode *coda_inode = coda_dentry->d_inode; + struct inode *coda_inode = coda_file->f_path.dentry->d_inode; struct coda_file_info *cfi; int err = 0; diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c index 3bdddbcc785f..e8fcf4e2ed7d 100644 --- a/fs/ecryptfs/file.c +++ b/fs/ecryptfs/file.c @@ -274,7 +274,7 @@ static int ecryptfs_release(struct inode *inode, struct file *file) } static int -ecryptfs_fsync(struct file *file, struct dentry *dentry, int datasync) +ecryptfs_fsync(struct file *file, int datasync) { return vfs_fsync(ecryptfs_file_to_lower(file), datasync); } diff --git a/fs/exofs/file.c b/fs/exofs/file.c index 839b9dc1e70f..fef6899be397 100644 --- a/fs/exofs/file.c +++ b/fs/exofs/file.c @@ -40,12 +40,11 @@ static int exofs_release_file(struct inode *inode, struct file *filp) return 0; } -static int exofs_file_fsync(struct file *filp, struct dentry *dentry, - int datasync) +static int exofs_file_fsync(struct file *filp, int datasync) { int ret; struct address_space *mapping = filp->f_mapping; - struct inode *inode = dentry->d_inode; + struct inode *inode = mapping->host; struct super_block *sb; ret = filemap_write_and_wait(mapping); @@ -66,7 +65,7 @@ static int exofs_file_fsync(struct file *filp, struct dentry *dentry, static int exofs_flush(struct file *file, fl_owner_t id) { - exofs_file_fsync(file, file->f_path.dentry, 1); + exofs_file_fsync(file, 1); /* TODO: Flush the OSD target */ return 0; } diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 0b038e47ad2f..8e917b686510 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -155,7 +155,7 @@ extern void ext2_write_super (struct super_block *); extern const struct file_operations ext2_dir_operations; /* file.c */ -extern int ext2_fsync(struct file *file, struct dentry *dentry, int datasync); +extern int ext2_fsync(struct file *file, int datasync); extern const struct inode_operations ext2_file_inode_operations; extern const struct file_operations ext2_file_operations; extern const struct file_operations ext2_xip_file_operations; diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 5d198d0697fb..48bcfc327014 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -40,13 +40,13 @@ static int ext2_release_file (struct inode * inode, struct file * filp) return 0; } -int ext2_fsync(struct file *file, struct dentry *dentry, int datasync) +int ext2_fsync(struct file *file, int datasync) { int ret; - struct super_block *sb = dentry->d_inode->i_sb; + struct super_block *sb = file->f_mapping->host->i_sb; struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; - ret = simple_fsync(file, dentry, datasync); + ret = simple_fsync(file, datasync); if (ret == -EIO || test_and_clear_bit(AS_EIO, &mapping->flags)) { /* We don't really know where the IO error happened... */ ext2_error(sb, __func__, diff --git a/fs/ext3/fsync.c b/fs/ext3/fsync.c index fcf7487734b6..d7e9f74dc3a6 100644 --- a/fs/ext3/fsync.c +++ b/fs/ext3/fsync.c @@ -43,9 +43,9 @@ * inode to disk. */ -int ext3_sync_file(struct file * file, struct dentry *dentry, int datasync) +int ext3_sync_file(struct file *file, int datasync) { - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_mapping->host; struct ext3_inode_info *ei = EXT3_I(inode); journal_t *journal = EXT3_SB(inode->i_sb)->s_journal; int ret, needs_barrier = 0; diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h index 60bd31026e7c..19a4de57128a 100644 --- a/fs/ext4/ext4.h +++ b/fs/ext4/ext4.h @@ -1519,7 +1519,7 @@ extern int ext4_htree_store_dirent(struct file *dir_file, __u32 hash, extern void ext4_htree_free_dir_info(struct dir_private_info *p); /* fsync.c */ -extern int ext4_sync_file(struct file *, struct dentry *, int); +extern int ext4_sync_file(struct file *, int); /* hash.c */ extern int ext4fs_dirhash(const char *name, int len, struct diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index b6a74f991bf4..40f345201737 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -71,9 +71,9 @@ static void ext4_sync_parent(struct inode *inode) * i_mutex lock is held when entering and exiting this function */ -int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) +int ext4_sync_file(struct file *file, int datasync) { - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_mapping->host; struct ext4_inode_info *ei = EXT4_I(inode); journal_t *journal = EXT4_SB(inode->i_sb)->s_journal; int ret; @@ -81,7 +81,7 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) J_ASSERT(ext4_journal_current_handle() == NULL); - trace_ext4_sync_file(file, dentry, datasync); + trace_ext4_sync_file(file, datasync); if (inode->i_sb->s_flags & MS_RDONLY) return 0; @@ -91,7 +91,7 @@ int ext4_sync_file(struct file *file, struct dentry *dentry, int datasync) return ret; if (!journal) { - ret = simple_fsync(file, dentry, datasync); + ret = simple_fsync(file, datasync); if (!ret && !list_empty(&inode->i_dentry)) ext4_sync_parent(inode); return ret; diff --git a/fs/fat/fat.h b/fs/fat/fat.h index 53dba57b49a1..a1c8c4b44fdb 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -309,8 +309,7 @@ extern int fat_setattr(struct dentry * dentry, struct iattr * attr); extern void fat_truncate(struct inode *inode); extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); -extern int fat_file_fsync(struct file *file, struct dentry *dentry, - int datasync); +extern int fat_file_fsync(struct file *file, int datasync); /* fat/inode.c */ extern void fat_attach(struct inode *inode, loff_t i_pos); diff --git a/fs/fat/file.c b/fs/fat/file.c index a14c2f6a489e..29a576944374 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -149,12 +149,12 @@ static int fat_file_release(struct inode *inode, struct file *filp) return 0; } -int fat_file_fsync(struct file *filp, struct dentry *dentry, int datasync) +int fat_file_fsync(struct file *filp, int datasync) { - struct inode *inode = dentry->d_inode; + struct inode *inode = filp->f_mapping->host; int res, err; - res = simple_fsync(filp, dentry, datasync); + res = simple_fsync(filp, datasync); err = sync_mapping_buffers(MSDOS_SB(inode->i_sb)->fat_inode->i_mapping); return res ? res : err; diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c index 4787ae6c5c1c..3cdc5f78a406 100644 --- a/fs/fuse/dir.c +++ b/fs/fuse/dir.c @@ -1156,10 +1156,9 @@ static int fuse_dir_release(struct inode *inode, struct file *file) return 0; } -static int fuse_dir_fsync(struct file *file, struct dentry *de, int datasync) +static int fuse_dir_fsync(struct file *file, int datasync) { - /* nfsd can call this with no file */ - return file ? fuse_fsync_common(file, de, datasync, 1) : 0; + return fuse_fsync_common(file, datasync, 1); } static bool update_mtime(unsigned ivalid) diff --git a/fs/fuse/file.c b/fs/fuse/file.c index a9f5e137f1d3..b5fd6f9905e4 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -351,10 +351,9 @@ static void fuse_sync_writes(struct inode *inode) fuse_release_nowrite(inode); } -int fuse_fsync_common(struct file *file, struct dentry *de, int datasync, - int isdir) +int fuse_fsync_common(struct file *file, int datasync, int isdir) { - struct inode *inode = de->d_inode; + struct inode *inode = file->f_mapping->host; struct fuse_conn *fc = get_fuse_conn(inode); struct fuse_file *ff = file->private_data; struct fuse_req *req; @@ -403,9 +402,9 @@ int fuse_fsync_common(struct file *file, struct dentry *de, int datasync, return err; } -static int fuse_fsync(struct file *file, struct dentry *de, int datasync) +static int fuse_fsync(struct file *file, int datasync) { - return fuse_fsync_common(file, de, datasync, 0); + return fuse_fsync_common(file, datasync, 0); } void fuse_read_fill(struct fuse_req *req, struct file *file, loff_t pos, diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h index 01cc462ff45d..2c0d14a86779 100644 --- a/fs/fuse/fuse_i.h +++ b/fs/fuse/fuse_i.h @@ -568,8 +568,7 @@ void fuse_release_common(struct file *file, int opcode); /** * Send FSYNC or FSYNCDIR request */ -int fuse_fsync_common(struct file *file, struct dentry *de, int datasync, - int isdir); +int fuse_fsync_common(struct file *file, int datasync, int isdir); /** * Notify poll wakeup diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index b20bfcc9fa2d..ed9a94f0ef15 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -554,9 +554,9 @@ static int gfs2_close(struct inode *inode, struct file *file) * Returns: errno */ -static int gfs2_fsync(struct file *file, struct dentry *dentry, int datasync) +static int gfs2_fsync(struct file *file, int datasync) { - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_mapping->host; int sync_state = inode->i_state & (I_DIRTY_SYNC|I_DIRTY_DATASYNC); int ret = 0; diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 3a029d8f4cf1..87ac1891a185 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -411,9 +411,9 @@ int hostfs_file_open(struct inode *ino, struct file *file) return 0; } -int hostfs_fsync(struct file *file, struct dentry *dentry, int datasync) +int hostfs_fsync(struct file *file, int datasync) { - return fsync_file(HOSTFS_I(dentry->d_inode)->fd, datasync); + return fsync_file(HOSTFS_I(file->f_mapping->host)->fd, datasync); } static const struct file_operations hostfs_file_fops = { diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c index 3efabff00367..a9ae9bfa752f 100644 --- a/fs/hpfs/file.c +++ b/fs/hpfs/file.c @@ -19,9 +19,9 @@ static int hpfs_file_release(struct inode *inode, struct file *file) return 0; } -int hpfs_file_fsync(struct file *file, struct dentry *dentry, int datasync) +int hpfs_file_fsync(struct file *file, int datasync) { - /*return file_fsync(file, dentry);*/ + /*return file_fsync(file, datasync);*/ return 0; /* Don't fsync :-) */ } diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h index 97bf738cd5d6..75f9d4324851 100644 --- a/fs/hpfs/hpfs_fn.h +++ b/fs/hpfs/hpfs_fn.h @@ -268,7 +268,7 @@ void hpfs_set_ea(struct inode *, struct fnode *, const char *, /* file.c */ -int hpfs_file_fsync(struct file *, struct dentry *, int); +int hpfs_file_fsync(struct file *, int); extern const struct file_operations hpfs_file_ops; extern const struct inode_operations hpfs_file_iops; extern const struct address_space_operations hpfs_aops; diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c index 2e4dfa8593da..826c3f9d29ac 100644 --- a/fs/hppfs/hppfs.c +++ b/fs/hppfs/hppfs.c @@ -587,7 +587,7 @@ static int hppfs_readdir(struct file *file, void *ent, filldir_t filldir) return err; } -static int hppfs_fsync(struct file *file, struct dentry *dentry, int datasync) +static int hppfs_fsync(struct file *file, int datasync) { return 0; } diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c index e7291c161a19..813497024437 100644 --- a/fs/jffs2/file.c +++ b/fs/jffs2/file.c @@ -26,9 +26,9 @@ static int jffs2_write_begin(struct file *filp, struct address_space *mapping, struct page **pagep, void **fsdata); static int jffs2_readpage (struct file *filp, struct page *pg); -int jffs2_fsync(struct file *filp, struct dentry *dentry, int datasync) +int jffs2_fsync(struct file *filp, int datasync) { - struct inode *inode = dentry->d_inode; + struct inode *inode = filp->f_mapping->host; struct jffs2_sb_info *c = JFFS2_SB_INFO(inode->i_sb); /* Trigger GC to flush any pending writes for this inode */ diff --git a/fs/jffs2/os-linux.h b/fs/jffs2/os-linux.h index 035a767f958b..4791aacf3084 100644 --- a/fs/jffs2/os-linux.h +++ b/fs/jffs2/os-linux.h @@ -158,7 +158,7 @@ extern const struct inode_operations jffs2_dir_inode_operations; extern const struct file_operations jffs2_file_operations; extern const struct inode_operations jffs2_file_inode_operations; extern const struct address_space_operations jffs2_file_address_operations; -int jffs2_fsync(struct file *, struct dentry *, int); +int jffs2_fsync(struct file *, int); int jffs2_do_readpage_unlock (struct inode *inode, struct page *pg); /* ioctl.c */ diff --git a/fs/jfs/file.c b/fs/jfs/file.c index 85d9ec659225..127263cc8657 100644 --- a/fs/jfs/file.c +++ b/fs/jfs/file.c @@ -27,9 +27,9 @@ #include "jfs_acl.h" #include "jfs_debug.h" -int jfs_fsync(struct file *file, struct dentry *dentry, int datasync) +int jfs_fsync(struct file *file, int datasync) { - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_mapping->host; int rc = 0; if (!(inode->i_state & I_DIRTY) || diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h index 9e6bda30a6e8..11042b1f44b5 100644 --- a/fs/jfs/jfs_inode.h +++ b/fs/jfs/jfs_inode.h @@ -21,7 +21,7 @@ struct fid; extern struct inode *ialloc(struct inode *, umode_t); -extern int jfs_fsync(struct file *, struct dentry *, int); +extern int jfs_fsync(struct file *, int); extern long jfs_ioctl(struct file *, unsigned int, unsigned long); extern long jfs_compat_ioctl(struct file *, unsigned int, unsigned long); extern struct inode *jfs_iget(struct super_block *, unsigned long); diff --git a/fs/libfs.c b/fs/libfs.c index 232bea425b09..e57ea58bda68 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -58,7 +58,7 @@ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, struct na return NULL; } -int simple_sync_file(struct file * file, struct dentry *dentry, int datasync) +int simple_sync_file(struct file *file, int datasync) { return 0; } @@ -851,13 +851,13 @@ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, } EXPORT_SYMBOL_GPL(generic_fh_to_parent); -int simple_fsync(struct file *file, struct dentry *dentry, int datasync) +int simple_fsync(struct file *file, int datasync) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, .nr_to_write = 0, /* metadata-only; caller takes care of data */ }; - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_mapping->host; int err; int ret; diff --git a/fs/logfs/file.c b/fs/logfs/file.c index 0de524071870..abe1cafbd4c2 100644 --- a/fs/logfs/file.c +++ b/fs/logfs/file.c @@ -219,9 +219,9 @@ int logfs_ioctl(struct inode *inode, struct file *file, unsigned int cmd, } } -int logfs_fsync(struct file *file, struct dentry *dentry, int datasync) +int logfs_fsync(struct file *file, int datasync) { - struct super_block *sb = dentry->d_inode->i_sb; + struct super_block *sb = file->f_mapping->host->i_sb; logfs_write_anchor(sb); return 0; diff --git a/fs/logfs/logfs.h b/fs/logfs/logfs.h index 1a9db84f8d8f..c838c4d72111 100644 --- a/fs/logfs/logfs.h +++ b/fs/logfs/logfs.h @@ -506,7 +506,7 @@ extern const struct address_space_operations logfs_reg_aops; int logfs_readpage(struct file *file, struct page *page); int logfs_ioctl(struct inode *inode, struct file *file, unsigned int cmd, unsigned long arg); -int logfs_fsync(struct file *file, struct dentry *dentry, int datasync); +int logfs_fsync(struct file *file, int datasync); /* gc.c */ u32 get_best_cand(struct super_block *sb, struct candidate_list *list, u32 *ec); diff --git a/fs/ncpfs/file.c b/fs/ncpfs/file.c index b93870892892..3639cc5cbdae 100644 --- a/fs/ncpfs/file.c +++ b/fs/ncpfs/file.c @@ -22,7 +22,7 @@ #include #include "ncplib_kernel.h" -static int ncp_fsync(struct file *file, struct dentry *dentry, int datasync) +static int ncp_fsync(struct file *file, int datasync) { return 0; } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index db64854b7b09..782b431ef91c 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -53,7 +53,7 @@ static int nfs_link(struct dentry *, struct inode *, struct dentry *); static int nfs_mknod(struct inode *, struct dentry *, int, dev_t); static int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); -static int nfs_fsync_dir(struct file *, struct dentry *, int); +static int nfs_fsync_dir(struct file *, int); static loff_t nfs_llseek_dir(struct file *, loff_t, int); const struct file_operations nfs_dir_operations = { @@ -641,8 +641,10 @@ out: * All directory operations under NFS are synchronous, so fsync() * is a dummy operation. */ -static int nfs_fsync_dir(struct file *filp, struct dentry *dentry, int datasync) +static int nfs_fsync_dir(struct file *filp, int datasync) { + struct dentry *dentry = filp->f_path.dentry; + dfprintk(FILE, "NFS: fsync dir(%s/%s) datasync %d\n", dentry->d_parent->d_name.name, dentry->d_name.name, datasync); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index cac96bcc91e4..36a5e74f51b4 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -53,7 +53,7 @@ static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe, static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov, unsigned long nr_segs, loff_t pos); static int nfs_file_flush(struct file *, fl_owner_t id); -static int nfs_file_fsync(struct file *, struct dentry *dentry, int datasync); +static int nfs_file_fsync(struct file *, int datasync); static int nfs_check_flags(int flags); static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl); static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl); @@ -322,8 +322,9 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma) * whether any write errors occurred for this process. */ static int -nfs_file_fsync(struct file *file, struct dentry *dentry, int datasync) +nfs_file_fsync(struct file *file, int datasync) { + struct dentry *dentry = file->f_path.dentry; struct nfs_open_context *ctx = nfs_file_open_context(file); struct inode *inode = dentry->d_inode; diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c index 30292df443ce..c9a30d7ff6fc 100644 --- a/fs/nilfs2/file.c +++ b/fs/nilfs2/file.c @@ -27,7 +27,7 @@ #include "nilfs.h" #include "segment.h" -int nilfs_sync_file(struct file *file, struct dentry *dentry, int datasync) +int nilfs_sync_file(struct file *file, int datasync) { /* * Called from fsync() system call @@ -37,7 +37,7 @@ int nilfs_sync_file(struct file *file, struct dentry *dentry, int datasync) * This function should be implemented when the writeback function * will be implemented. */ - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_mapping->host; int err; if (!nilfs_inode_dirty(inode)) diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h index 8723e5bfd071..47d6d7928122 100644 --- a/fs/nilfs2/nilfs.h +++ b/fs/nilfs2/nilfs.h @@ -228,7 +228,7 @@ extern void nilfs_set_link(struct inode *, struct nilfs_dir_entry *, struct page *, struct inode *); /* file.c */ -extern int nilfs_sync_file(struct file *, struct dentry *, int); +extern int nilfs_sync_file(struct file *, int); /* ioctl.c */ long nilfs_ioctl(struct file *, unsigned int, unsigned long); diff --git a/fs/ntfs/dir.c b/fs/ntfs/dir.c index fe44d3feee4a..0f48e7c5d9e1 100644 --- a/fs/ntfs/dir.c +++ b/fs/ntfs/dir.c @@ -1527,10 +1527,9 @@ static int ntfs_dir_open(struct inode *vi, struct file *filp) * this problem for now. We do write the $BITMAP attribute if it is present * which is the important one for a directory so things are not too bad. */ -static int ntfs_dir_fsync(struct file *filp, struct dentry *dentry, - int datasync) +static int ntfs_dir_fsync(struct file *filp, int datasync) { - struct inode *bmp_vi, *vi = dentry->d_inode; + struct inode *bmp_vi, *vi = filp->f_mapping->host; int err, ret; ntfs_attr na; diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c index a1924a0d2ab0..113ebd9f25a4 100644 --- a/fs/ntfs/file.c +++ b/fs/ntfs/file.c @@ -2133,7 +2133,6 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, /** * ntfs_file_fsync - sync a file to disk * @filp: file to be synced - * @dentry: dentry describing the file to sync * @datasync: if non-zero only flush user data and not metadata * * Data integrity sync of a file to disk. Used for fsync, fdatasync, and msync @@ -2149,19 +2148,15 @@ static ssize_t ntfs_file_aio_write(struct kiocb *iocb, const struct iovec *iov, * Also, if @datasync is true, we do not wait on the inode to be written out * but we always wait on the page cache pages to be written out. * - * Note: In the past @filp could be NULL so we ignore it as we don't need it - * anyway. - * * Locking: Caller must hold i_mutex on the inode. * * TODO: We should probably also write all attribute/index inodes associated * with this inode but since we have no simple way of getting to them we ignore * this problem for now. */ -static int ntfs_file_fsync(struct file *filp, struct dentry *dentry, - int datasync) +static int ntfs_file_fsync(struct file *filp, int datasync) { - struct inode *vi = dentry->d_inode; + struct inode *vi = filp->f_mapping->host; int err, ret = 0; ntfs_debug("Entering for inode 0x%lx.", vi->i_ino); diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 97e54b9e654b..1c6220a8e072 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -175,13 +175,12 @@ static int ocfs2_dir_release(struct inode *inode, struct file *file) return 0; } -static int ocfs2_sync_file(struct file *file, - struct dentry *dentry, - int datasync) +static int ocfs2_sync_file(struct file *file, int datasync) { int err = 0; journal_t *journal; - struct inode *inode = dentry->d_inode; + struct dentry *dentry = file->f_path.dentry; + struct inode *inode = file->f_mapping->host; struct ocfs2_super *osb = OCFS2_SB(inode->i_sb); mlog_entry("(0x%p, 0x%p, %d, '%.*s')\n", file, dentry, datasync, diff --git a/fs/reiserfs/dir.c b/fs/reiserfs/dir.c index 4455fbe269a3..198dabf1b2bb 100644 --- a/fs/reiserfs/dir.c +++ b/fs/reiserfs/dir.c @@ -14,8 +14,7 @@ extern const struct reiserfs_key MIN_KEY; static int reiserfs_readdir(struct file *, void *, filldir_t); -static int reiserfs_dir_fsync(struct file *filp, struct dentry *dentry, - int datasync); +static int reiserfs_dir_fsync(struct file *filp, int datasync); const struct file_operations reiserfs_dir_operations = { .llseek = generic_file_llseek, @@ -28,10 +27,9 @@ const struct file_operations reiserfs_dir_operations = { #endif }; -static int reiserfs_dir_fsync(struct file *filp, struct dentry *dentry, - int datasync) +static int reiserfs_dir_fsync(struct file *filp, int datasync) { - struct inode *inode = dentry->d_inode; + struct inode *inode = filp->f_mapping->host; int err; reiserfs_write_lock(inode->i_sb); err = reiserfs_commit_for_inode(inode); diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 9977df9f3a54..b82cdd8a45dd 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -134,10 +134,9 @@ static void reiserfs_vfs_truncate_file(struct inode *inode) * be removed... */ -static int reiserfs_sync_file(struct file *filp, - struct dentry *dentry, int datasync) +static int reiserfs_sync_file(struct file *filp, int datasync) { - struct inode *inode = dentry->d_inode; + struct inode *inode = filp->f_mapping->host; int err; int barrier_done; diff --git a/fs/smbfs/file.c b/fs/smbfs/file.c index 84ecf0e43f91..8e187a0f94bb 100644 --- a/fs/smbfs/file.c +++ b/fs/smbfs/file.c @@ -28,8 +28,9 @@ #include "proto.h" static int -smb_fsync(struct file *file, struct dentry * dentry, int datasync) +smb_fsync(struct file *file, int datasync) { + struct dentry *dentry = file->f_path.dentry; struct smb_sb_info *server = server_from_dentry(dentry); int result; diff --git a/fs/sync.c b/fs/sync.c index e8cbd415e50a..c9f83f480ec5 100644 --- a/fs/sync.c +++ b/fs/sync.c @@ -130,12 +130,10 @@ void emergency_sync(void) /* * Generic function to fsync a file. - * - * filp may be NULL if called via the msync of a vma. */ -int file_fsync(struct file *filp, struct dentry *dentry, int datasync) +int file_fsync(struct file *filp, int datasync) { - struct inode * inode = dentry->d_inode; + struct inode *inode = filp->f_mapping->host; struct super_block * sb; int ret, err; @@ -183,7 +181,7 @@ int vfs_fsync_range(struct file *file, loff_t start, loff_t end, int datasync) * livelocks in fsync_buffers_list(). */ mutex_lock(&mapping->host->i_mutex); - err = file->f_op->fsync(file, file->f_path.dentry, datasync); + err = file->f_op->fsync(file, datasync); if (!ret) ret = err; mutex_unlock(&mapping->host->i_mutex); diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index 5692cf72b807..c726da68e6be 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -1304,9 +1304,9 @@ static void *ubifs_follow_link(struct dentry *dentry, struct nameidata *nd) return NULL; } -int ubifs_fsync(struct file *file, struct dentry *dentry, int datasync) +int ubifs_fsync(struct file *file, int datasync) { - struct inode *inode = dentry->d_inode; + struct inode *inode = file->f_mapping->host; struct ubifs_info *c = inode->i_sb->s_fs_info; int err; diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index bd2542dad014..b0904536cc1c 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -1678,7 +1678,7 @@ const struct ubifs_lprops *ubifs_fast_find_frdi_idx(struct ubifs_info *c); int ubifs_calc_dark(const struct ubifs_info *c, int spc); /* file.c */ -int ubifs_fsync(struct file *file, struct dentry *dentry, int datasync); +int ubifs_fsync(struct file *file, int datasync); int ubifs_setattr(struct dentry *dentry, struct iattr *attr); /* dir.c */ diff --git a/fs/xfs/linux-2.6/xfs_file.c b/fs/xfs/linux-2.6/xfs_file.c index d8fb1b5d6cb5..257a56b127cf 100644 --- a/fs/xfs/linux-2.6/xfs_file.c +++ b/fs/xfs/linux-2.6/xfs_file.c @@ -100,10 +100,10 @@ xfs_iozero( STATIC int xfs_file_fsync( struct file *file, - struct dentry *dentry, int datasync) { - struct xfs_inode *ip = XFS_I(dentry->d_inode); + struct inode *inode = file->f_mapping->host; + struct xfs_inode *ip = XFS_I(inode); struct xfs_trans *tp; int error = 0; int log_flushed = 0; @@ -140,8 +140,8 @@ xfs_file_fsync( * might gets cleared when the inode gets written out via the AIL * or xfs_iflush_cluster. */ - if (((dentry->d_inode->i_state & I_DIRTY_DATASYNC) || - ((dentry->d_inode->i_state & I_DIRTY_SYNC) && !datasync)) && + if (((inode->i_state & I_DIRTY_DATASYNC) || + ((inode->i_state & I_DIRTY_SYNC) && !datasync)) && ip->i_update_core) { /* * Kick off a transaction to log the inode core to get the @@ -868,7 +868,7 @@ write_retry: mutex_lock(&inode->i_mutex); xfs_ilock(ip, iolock); - error2 = -xfs_file_fsync(file, file->f_path.dentry, + error2 = -xfs_file_fsync(file, (file->f_flags & __O_SYNC) ? 0 : 1); if (!error) error = error2; diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 16ed0284d780..05e5f5996216 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -224,7 +224,7 @@ int block_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf, void block_sync_page(struct page *); sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); -int file_fsync(struct file *, struct dentry *, int); +int file_fsync(struct file *, int); int nobh_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h index 5f494b465097..7fc62d4550b2 100644 --- a/include/linux/ext3_fs.h +++ b/include/linux/ext3_fs.h @@ -868,7 +868,7 @@ extern int ext3_htree_store_dirent(struct file *dir_file, __u32 hash, extern void ext3_htree_free_dir_info(struct dir_private_info *p); /* fsync.c */ -extern int ext3_sync_file (struct file *, struct dentry *, int); +extern int ext3_sync_file(struct file *, int); /* hash.c */ extern int ext3fs_dirhash(const char *name, int len, struct diff --git a/include/linux/fb.h b/include/linux/fb.h index f3793ebc241c..907ace3a64c8 100644 --- a/include/linux/fb.h +++ b/include/linux/fb.h @@ -4,8 +4,6 @@ #include #include -struct dentry; - /* Definitions of frame buffers */ #define FB_MAX 32 /* sufficient for now */ @@ -1017,8 +1015,7 @@ extern void fb_deferred_io_open(struct fb_info *info, struct inode *inode, struct file *file); extern void fb_deferred_io_cleanup(struct fb_info *info); -extern int fb_deferred_io_fsync(struct file *file, struct dentry *dentry, - int datasync); +extern int fb_deferred_io_fsync(struct file *file, int datasync); static inline bool fb_be_math(struct fb_info *info) { diff --git a/include/linux/fs.h b/include/linux/fs.h index 3d9ed8302402..eb39e5eb77f5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1498,7 +1498,7 @@ struct file_operations { int (*open) (struct inode *, struct file *); int (*flush) (struct file *, fl_owner_t id); int (*release) (struct inode *, struct file *); - int (*fsync) (struct file *, struct dentry *, int datasync); + int (*fsync) (struct file *, int datasync); int (*aio_fsync) (struct kiocb *, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); @@ -2213,7 +2213,7 @@ extern int generic_segment_checks(const struct iovec *iov, /* fs/block_dev.c */ extern ssize_t blkdev_aio_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos); -extern int blkdev_fsync(struct file *filp, struct dentry *dentry, int datasync); +extern int blkdev_fsync(struct file *filp, int datasync); /* fs/splice.c */ extern ssize_t generic_file_splice_read(struct file *, loff_t *, @@ -2348,7 +2348,7 @@ extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); -extern int simple_sync_file(struct file *, struct dentry *, int); +extern int simple_sync_file(struct file *, int); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, @@ -2373,7 +2373,7 @@ extern ssize_t simple_read_from_buffer(void __user *to, size_t count, extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); -extern int simple_fsync(struct file *, struct dentry *, int); +extern int simple_fsync(struct file *, int); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, diff --git a/include/trace/events/ext4.h b/include/trace/events/ext4.h index 5d60ad4ebf78..f5b1ba90e952 100644 --- a/include/trace/events/ext4.h +++ b/include/trace/events/ext4.h @@ -606,9 +606,9 @@ TRACE_EVENT(ext4_free_blocks, ); TRACE_EVENT(ext4_sync_file, - TP_PROTO(struct file *file, struct dentry *dentry, int datasync), + TP_PROTO(struct file *file, int datasync), - TP_ARGS(file, dentry, datasync), + TP_ARGS(file, datasync), TP_STRUCT__entry( __field( dev_t, dev ) @@ -618,6 +618,8 @@ TRACE_EVENT(ext4_sync_file, ), TP_fast_assign( + struct dentry *dentry = file->f_path.dentry; + __entry->dev = dentry->d_inode->i_sb->s_dev; __entry->ino = dentry->d_inode->i_ino; __entry->datasync = datasync; diff --git a/ipc/shm.c b/ipc/shm.c index 1a314c89f93c..52ed77eb9713 100644 --- a/ipc/shm.c +++ b/ipc/shm.c @@ -273,16 +273,13 @@ static int shm_release(struct inode *ino, struct file *file) return 0; } -static int shm_fsync(struct file *file, struct dentry *dentry, int datasync) +static int shm_fsync(struct file *file, int datasync) { - int (*fsync) (struct file *, struct dentry *, int datasync); struct shm_file_data *sfd = shm_file_data(file); - int ret = -EINVAL; - fsync = sfd->file->f_op->fsync; - if (fsync) - ret = fsync(sfd->file, sfd->file->f_path.dentry, datasync); - return ret; + if (!sfd->file->f_op->fsync) + return -EINVAL; + return sfd->file->f_op->fsync(sfd->file, datasync); } static unsigned long shm_get_unmapped_area(struct file *file, From 1b061d9247f71cd15edc4c4c4600191a903642c0 Mon Sep 17 00:00:00 2001 From: Christoph Hellwig Date: Wed, 26 May 2010 17:53:41 +0200 Subject: [PATCH 07/17] rename the generic fsync implementations We don't name our generic fsync implementations very well currently. The no-op implementation for in-memory filesystems currently is called simple_sync_file which doesn't make too much sense to start with, the the generic one for simple filesystems is called simple_fsync which can lead to some confusion. This patch renames the generic file fsync method to generic_file_fsync to match the other generic_file_* routines it is supposed to be used with, and the no-op implementation to noop_fsync to make it obvious what to expect. In addition add some documentation for both methods. Signed-off-by: Christoph Hellwig Signed-off-by: Al Viro --- arch/powerpc/platforms/cell/spufs/inode.c | 2 +- fs/adfs/dir.c | 2 +- fs/adfs/file.c | 2 +- fs/bfs/dir.c | 2 +- fs/ext2/file.c | 2 +- fs/ext4/fsync.c | 2 +- fs/fat/file.c | 2 +- fs/hugetlbfs/inode.c | 2 +- fs/libfs.c | 30 ++++++++++++++++------- fs/minix/dir.c | 2 +- fs/minix/file.c | 2 +- fs/omfs/file.c | 2 +- fs/qnx4/dir.c | 2 +- fs/ramfs/file-mmu.c | 2 +- fs/ramfs/file-nommu.c | 2 +- fs/sysv/dir.c | 2 +- fs/sysv/file.c | 2 +- fs/udf/dir.c | 2 +- fs/udf/file.c | 2 +- fs/ufs/dir.c | 2 +- fs/ufs/file.c | 2 +- include/linux/fs.h | 4 +-- mm/shmem.c | 2 +- 23 files changed, 44 insertions(+), 32 deletions(-) diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c index fc1b1c42b1dc..e5e5f823d687 100644 --- a/arch/powerpc/platforms/cell/spufs/inode.c +++ b/arch/powerpc/platforms/cell/spufs/inode.c @@ -251,7 +251,7 @@ const struct file_operations spufs_context_fops = { .llseek = dcache_dir_lseek, .read = generic_read_dir, .readdir = dcache_readdir, - .fsync = simple_sync_file, + .fsync = noop_fsync, }; EXPORT_SYMBOL_GPL(spufs_context_fops); diff --git a/fs/adfs/dir.c b/fs/adfs/dir.c index 23aa52f548a0..f4287e4de744 100644 --- a/fs/adfs/dir.c +++ b/fs/adfs/dir.c @@ -197,7 +197,7 @@ const struct file_operations adfs_dir_operations = { .read = generic_read_dir, .llseek = generic_file_llseek, .readdir = adfs_readdir, - .fsync = simple_fsync, + .fsync = generic_file_fsync, }; static int diff --git a/fs/adfs/file.c b/fs/adfs/file.c index 005ea34d1758..a36da5382b40 100644 --- a/fs/adfs/file.c +++ b/fs/adfs/file.c @@ -26,7 +26,7 @@ const struct file_operations adfs_file_operations = { .read = do_sync_read, .aio_read = generic_file_aio_read, .mmap = generic_file_mmap, - .fsync = simple_fsync, + .fsync = generic_file_fsync, .write = do_sync_write, .aio_write = generic_file_aio_write, .splice_read = generic_file_splice_read, diff --git a/fs/bfs/dir.c b/fs/bfs/dir.c index 8f73841fc974..d967e052b779 100644 --- a/fs/bfs/dir.c +++ b/fs/bfs/dir.c @@ -78,7 +78,7 @@ static int bfs_readdir(struct file *f, void *dirent, filldir_t filldir) const struct file_operations bfs_dir_operations = { .read = generic_read_dir, .readdir = bfs_readdir, - .fsync = simple_fsync, + .fsync = generic_file_fsync, .llseek = generic_file_llseek, }; diff --git a/fs/ext2/file.c b/fs/ext2/file.c index 48bcfc327014..d82e7ca93455 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -46,7 +46,7 @@ int ext2_fsync(struct file *file, int datasync) struct super_block *sb = file->f_mapping->host->i_sb; struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping; - ret = simple_fsync(file, datasync); + ret = generic_file_fsync(file, datasync); if (ret == -EIO || test_and_clear_bit(AS_EIO, &mapping->flags)) { /* We don't really know where the IO error happened... */ ext2_error(sb, __func__, diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c index 40f345201737..592adf2e546e 100644 --- a/fs/ext4/fsync.c +++ b/fs/ext4/fsync.c @@ -91,7 +91,7 @@ int ext4_sync_file(struct file *file, int datasync) return ret; if (!journal) { - ret = simple_fsync(file, datasync); + ret = generic_file_fsync(file, datasync); if (!ret && !list_empty(&inode->i_dentry)) ext4_sync_parent(inode); return ret; diff --git a/fs/fat/file.c b/fs/fat/file.c index 29a576944374..8c13b8acfd2f 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -154,7 +154,7 @@ int fat_file_fsync(struct file *filp, int datasync) struct inode *inode = filp->f_mapping->host; int res, err; - res = simple_fsync(filp, datasync); + res = generic_file_fsync(filp, datasync); err = sync_mapping_buffers(MSDOS_SB(inode->i_sb)->fat_inode->i_mapping); return res ? res : err; diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c index a0bbd3d1b41a..a4e9a7ec3691 100644 --- a/fs/hugetlbfs/inode.c +++ b/fs/hugetlbfs/inode.c @@ -688,7 +688,7 @@ static void init_once(void *foo) const struct file_operations hugetlbfs_file_operations = { .read = hugetlbfs_read, .mmap = hugetlbfs_file_mmap, - .fsync = simple_sync_file, + .fsync = noop_fsync, .get_unmapped_area = hugetlb_get_unmapped_area, }; diff --git a/fs/libfs.c b/fs/libfs.c index e57ea58bda68..b84d0a7a2204 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -58,11 +58,6 @@ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, struct na return NULL; } -int simple_sync_file(struct file *file, int datasync) -{ - return 0; -} - int dcache_dir_open(struct inode *inode, struct file *file) { static struct qstr cursor_name = {.len = 1, .name = "."}; @@ -190,7 +185,7 @@ const struct file_operations simple_dir_operations = { .llseek = dcache_dir_lseek, .read = generic_read_dir, .readdir = dcache_readdir, - .fsync = simple_sync_file, + .fsync = noop_fsync, }; const struct inode_operations simple_dir_inode_operations = { @@ -851,7 +846,16 @@ struct dentry *generic_fh_to_parent(struct super_block *sb, struct fid *fid, } EXPORT_SYMBOL_GPL(generic_fh_to_parent); -int simple_fsync(struct file *file, int datasync) +/** + * generic_file_fsync - generic fsync implementation for simple filesystems + * @file: file to synchronize + * @datasync: only synchronize essential metadata if true + * + * This is a generic implementation of the fsync method for simple + * filesystems which track all non-inode metadata in the buffers list + * hanging off the address_space structure. + */ +int generic_file_fsync(struct file *file, int datasync) { struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, @@ -872,7 +876,15 @@ int simple_fsync(struct file *file, int datasync) ret = err; return ret; } -EXPORT_SYMBOL(simple_fsync); +EXPORT_SYMBOL(generic_file_fsync); + +/* + * No-op implementation of ->fsync for in-memory filesystems. + */ +int noop_fsync(struct file *file, int datasync) +{ + return 0; +} EXPORT_SYMBOL(dcache_dir_close); EXPORT_SYMBOL(dcache_dir_lseek); @@ -895,7 +907,7 @@ EXPORT_SYMBOL(simple_release_fs); EXPORT_SYMBOL(simple_rename); EXPORT_SYMBOL(simple_rmdir); EXPORT_SYMBOL(simple_statfs); -EXPORT_SYMBOL(simple_sync_file); +EXPORT_SYMBOL(noop_fsync); EXPORT_SYMBOL(simple_unlink); EXPORT_SYMBOL(simple_read_from_buffer); EXPORT_SYMBOL(simple_write_to_buffer); diff --git a/fs/minix/dir.c b/fs/minix/dir.c index 6198731d7fcd..aaab97ec5bc0 100644 --- a/fs/minix/dir.c +++ b/fs/minix/dir.c @@ -22,7 +22,7 @@ const struct file_operations minix_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .readdir = minix_readdir, - .fsync = simple_fsync, + .fsync = generic_file_fsync, }; static inline void dir_put_page(struct page *page) diff --git a/fs/minix/file.c b/fs/minix/file.c index 3eec3e607a87..d5320ff23faf 100644 --- a/fs/minix/file.c +++ b/fs/minix/file.c @@ -19,7 +19,7 @@ const struct file_operations minix_file_operations = { .write = do_sync_write, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, - .fsync = simple_fsync, + .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, }; diff --git a/fs/omfs/file.c b/fs/omfs/file.c index 399487c09364..6e7a3291bbe8 100644 --- a/fs/omfs/file.c +++ b/fs/omfs/file.c @@ -329,7 +329,7 @@ const struct file_operations omfs_file_operations = { .aio_read = generic_file_aio_read, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, - .fsync = simple_fsync, + .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, }; diff --git a/fs/qnx4/dir.c b/fs/qnx4/dir.c index 3d3fd4692133..6e8fc62b40a8 100644 --- a/fs/qnx4/dir.c +++ b/fs/qnx4/dir.c @@ -80,7 +80,7 @@ const struct file_operations qnx4_dir_operations = .llseek = generic_file_llseek, .read = generic_read_dir, .readdir = qnx4_readdir, - .fsync = simple_fsync, + .fsync = generic_file_fsync, }; const struct inode_operations qnx4_dir_inode_operations = diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 78f613cb9c76..50020501c5eb 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -43,7 +43,7 @@ const struct file_operations ramfs_file_operations = { .write = do_sync_write, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, - .fsync = simple_sync_file, + .fsync = noop_fsync, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, .llseek = generic_file_llseek, diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 5ea4ad81a429..869f2d80183d 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -42,7 +42,7 @@ const struct file_operations ramfs_file_operations = { .aio_read = generic_file_aio_read, .write = do_sync_write, .aio_write = generic_file_aio_write, - .fsync = simple_sync_file, + .fsync = noop_fsync, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, .llseek = generic_file_llseek, diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c index 1dabed286b4c..79941e4964a4 100644 --- a/fs/sysv/dir.c +++ b/fs/sysv/dir.c @@ -24,7 +24,7 @@ const struct file_operations sysv_dir_operations = { .llseek = generic_file_llseek, .read = generic_read_dir, .readdir = sysv_readdir, - .fsync = simple_fsync, + .fsync = generic_file_fsync, }; static inline void dir_put_page(struct page *page) diff --git a/fs/sysv/file.c b/fs/sysv/file.c index 96340c01f4a7..750cc22349bd 100644 --- a/fs/sysv/file.c +++ b/fs/sysv/file.c @@ -26,7 +26,7 @@ const struct file_operations sysv_file_operations = { .write = do_sync_write, .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, - .fsync = simple_fsync, + .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, }; diff --git a/fs/udf/dir.c b/fs/udf/dir.c index 1660c81ffa3d..51552bf50225 100644 --- a/fs/udf/dir.c +++ b/fs/udf/dir.c @@ -211,5 +211,5 @@ const struct file_operations udf_dir_operations = { .read = generic_read_dir, .readdir = udf_readdir, .unlocked_ioctl = udf_ioctl, - .fsync = simple_fsync, + .fsync = generic_file_fsync, }; diff --git a/fs/udf/file.c b/fs/udf/file.c index baae3a723946..0660280aa180 100644 --- a/fs/udf/file.c +++ b/fs/udf/file.c @@ -224,7 +224,7 @@ const struct file_operations udf_file_operations = { .write = do_sync_write, .aio_write = udf_file_aio_write, .release = udf_release_file, - .fsync = simple_fsync, + .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, .llseek = generic_file_llseek, }; diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c index 317a0d444f6b..ec784756dc65 100644 --- a/fs/ufs/dir.c +++ b/fs/ufs/dir.c @@ -666,6 +666,6 @@ not_empty: const struct file_operations ufs_dir_operations = { .read = generic_read_dir, .readdir = ufs_readdir, - .fsync = simple_fsync, + .fsync = generic_file_fsync, .llseek = generic_file_llseek, }; diff --git a/fs/ufs/file.c b/fs/ufs/file.c index a8962cecde5b..d4c30d1bef86 100644 --- a/fs/ufs/file.c +++ b/fs/ufs/file.c @@ -42,6 +42,6 @@ const struct file_operations ufs_file_operations = { .aio_write = generic_file_aio_write, .mmap = generic_file_mmap, .open = dquot_file_open, - .fsync = simple_fsync, + .fsync = generic_file_fsync, .splice_read = generic_file_splice_read, }; diff --git a/include/linux/fs.h b/include/linux/fs.h index eb39e5eb77f5..acf6c52a50dd 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2348,7 +2348,7 @@ extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); -extern int simple_sync_file(struct file *, int); +extern int noop_fsync(struct file *, int); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); extern int simple_write_begin(struct file *file, struct address_space *mapping, @@ -2373,7 +2373,7 @@ extern ssize_t simple_read_from_buffer(void __user *to, size_t count, extern ssize_t simple_write_to_buffer(void *to, size_t available, loff_t *ppos, const void __user *from, size_t count); -extern int simple_fsync(struct file *, int); +extern int generic_file_fsync(struct file *, int); #ifdef CONFIG_MIGRATION extern int buffer_migrate_page(struct address_space *, diff --git a/mm/shmem.c b/mm/shmem.c index 855eaf5b8d5b..4daf8cecf422 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -2433,7 +2433,7 @@ static const struct file_operations shmem_file_operations = { .write = do_sync_write, .aio_read = shmem_file_aio_read, .aio_write = generic_file_aio_write, - .fsync = simple_sync_file, + .fsync = noop_fsync, .splice_read = generic_file_splice_read, .splice_write = generic_file_splice_write, #endif From 0ab7620a0cefe6982b914a830a41f65ecccd74bd Mon Sep 17 00:00:00 2001 From: Erik van der Kouwe Date: Wed, 26 May 2010 12:03:23 +0200 Subject: [PATCH 08/17] fs/minix: bugfix, number of indirect block ptrs per block depends on block size The MINIX filesystem driver used a constant number of indirect block pointers in an indirect block. This worked only for filesystems with 1kb block, while the MINIX default block size is now 4kb. As a consequence, large files were read incorrectly on such filesystems and writing a large file would cause the filesystem to become corrupted. This patch computes the number of indirect block pointers based on the block size, making the driver work for each block size. I would like to thank Feiran Zheng ('Fam') for pointing out the cause of the corruption. Signed-off-by: Erik van der Kouwe Signed-off-by: Al Viro --- fs/minix/itree_v2.c | 27 +++++++++++++++------------ 1 file changed, 15 insertions(+), 12 deletions(-) diff --git a/fs/minix/itree_v2.c b/fs/minix/itree_v2.c index f23010969369..13487ad16894 100644 --- a/fs/minix/itree_v2.c +++ b/fs/minix/itree_v2.c @@ -20,6 +20,9 @@ static inline block_t *i_data(struct inode *inode) return (block_t *)minix_i(inode)->u.i2_data; } +#define DIRCOUNT 7 +#define INDIRCOUNT(sb) (1 << ((sb)->s_blocksize_bits - 2)) + static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) { int n = 0; @@ -34,21 +37,21 @@ static int block_to_path(struct inode * inode, long block, int offsets[DEPTH]) printk("MINIX-fs: block_to_path: " "block %ld too big on dev %s\n", block, bdevname(sb->s_bdev, b)); - } else if (block < 7) { + } else if (block < DIRCOUNT) { offsets[n++] = block; - } else if ((block -= 7) < 256) { - offsets[n++] = 7; + } else if ((block -= DIRCOUNT) < INDIRCOUNT(sb)) { + offsets[n++] = DIRCOUNT; offsets[n++] = block; - } else if ((block -= 256) < 256*256) { - offsets[n++] = 8; - offsets[n++] = block>>8; - offsets[n++] = block & 255; + } else if ((block -= INDIRCOUNT(sb)) < INDIRCOUNT(sb) * INDIRCOUNT(sb)) { + offsets[n++] = DIRCOUNT + 1; + offsets[n++] = block / INDIRCOUNT(sb); + offsets[n++] = block % INDIRCOUNT(sb); } else { - block -= 256*256; - offsets[n++] = 9; - offsets[n++] = block>>16; - offsets[n++] = (block>>8) & 255; - offsets[n++] = block & 255; + block -= INDIRCOUNT(sb) * INDIRCOUNT(sb); + offsets[n++] = DIRCOUNT + 2; + offsets[n++] = (block / INDIRCOUNT(sb)) / INDIRCOUNT(sb); + offsets[n++] = (block / INDIRCOUNT(sb)) % INDIRCOUNT(sb); + offsets[n++] = block % INDIRCOUNT(sb); } return n; } From 7000d3c424e5bb350e502a477fb0e1ed42f8b10e Mon Sep 17 00:00:00 2001 From: Randy Dunlap Date: Mon, 24 May 2010 22:22:34 -0700 Subject: [PATCH 09/17] fs/super: fix kernel-doc warning Fix fs/super.c kernel-doc warning and function notation: Warning(fs/super.c:957): No description found for parameter 'sb' Signed-off-by: Randy Dunlap Cc: Alexander Viro Signed-off-by: Al Viro --- fs/super.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/fs/super.c b/fs/super.c index 69688b15f1fa..a67409e5ad94 100644 --- a/fs/super.c +++ b/fs/super.c @@ -946,8 +946,8 @@ out: EXPORT_SYMBOL_GPL(vfs_kern_mount); /** - * freeze_super -- lock the filesystem and force it into a consistent state - * @super: the super to lock + * freeze_super - lock the filesystem and force it into a consistent state + * @sb: the super to lock * * Syncs the super to make sure the filesystem is consistent and calls the fs's * freeze_fs. Subsequent calls to this without first thawing the fs will return From 7bb46a6734a7e1ad4beaecc11cae7ed3ff81d30f Mon Sep 17 00:00:00 2001 From: "npiggin@suse.de" Date: Thu, 27 May 2010 01:05:33 +1000 Subject: [PATCH 10/17] fs: introduce new truncate sequence Introduce a new truncate calling sequence into fs/mm subsystems. Rather than setattr > vmtruncate > truncate, have filesystems call their truncate sequence from ->setattr if filesystem specific operations are required. vmtruncate is deprecated, and truncate_pagecache and inode_newsize_ok helpers introduced previously should be used. simple_setattr is introduced for simple in-ram filesystems to implement the new truncate sequence. Eventually all filesystems should be converted to implement a setattr, and the default code in notify_change should go away. simple_setsize is also introduced to perform just the ATTR_SIZE portion of simple_setattr (ie. changing i_size and trimming pagecache). To implement the new truncate sequence: - filesystem specific manipulations (eg freeing blocks) must be done in the setattr method rather than ->truncate. - vmtruncate can not be used by core code to trim blocks past i_size in the event of write failure after allocation, so this must be performed in the fs code. - convert usage of helpers block_write_begin, nobh_write_begin, cont_write_begin, and *blockdev_direct_IO* to use _newtrunc postfixed variants. These avoid calling vmtruncate to trim blocks (see previous). - inode_setattr should not be used. generic_setattr is a new function to be used to copy simple attributes into the generic inode. - make use of the better opportunity to handle errors with the new sequence. Big problem with the previous calling sequence: the filesystem is not called until i_size has already changed. This means it is not allowed to fail the call, and also it does not know what the previous i_size was. Also, generic code calling vmtruncate to truncate allocated blocks in case of error had no good way to return a meaningful error (or, for example, atomically handle block deallocation). Cc: Christoph Hellwig Acked-by: Jan Kara Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- Documentation/filesystems/vfs.txt | 7 +- fs/attr.c | 50 +++++++++--- fs/buffer.c | 123 ++++++++++++++++++++++++------ fs/direct-io.c | 61 ++++++++++----- fs/libfs.c | 76 ++++++++++++++++++ include/linux/buffer_head.h | 9 +++ include/linux/fs.h | 27 ++++++- mm/truncate.c | 10 +-- 8 files changed, 300 insertions(+), 63 deletions(-) diff --git a/Documentation/filesystems/vfs.txt b/Documentation/filesystems/vfs.txt index d4f5731dcbbb..94677e7dcb13 100644 --- a/Documentation/filesystems/vfs.txt +++ b/Documentation/filesystems/vfs.txt @@ -401,11 +401,16 @@ otherwise noted. started might not be in the page cache at the end of the walk). - truncate: called by the VFS to change the size of a file. The + truncate: Deprecated. This will not be called if ->setsize is defined. + Called by the VFS to change the size of a file. The i_size field of the inode is set to the desired size by the VFS before this method is called. This method is called by the truncate(2) system call and related functionality. + Note: ->truncate and vmtruncate are deprecated. Do not add new + instances/calls of these. Filesystems should be converted to do their + truncate sequence via ->setattr(). + permission: called by the VFS to check for access rights on a POSIX-like filesystem. diff --git a/fs/attr.c b/fs/attr.c index 0815e93bb487..b4fa3b0aa596 100644 --- a/fs/attr.c +++ b/fs/attr.c @@ -67,14 +67,14 @@ EXPORT_SYMBOL(inode_change_ok); * @offset: the new size to assign to the inode * @Returns: 0 on success, -ve errno on failure * + * inode_newsize_ok must be called with i_mutex held. + * * inode_newsize_ok will check filesystem limits and ulimits to check that the * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ * when necessary. Caller must not proceed with inode size change if failure is * returned. @inode must be a file (not directory), with appropriate * permissions to allow truncate (inode_newsize_ok does NOT check these * conditions). - * - * inode_newsize_ok must be called with i_mutex held. */ int inode_newsize_ok(const struct inode *inode, loff_t offset) { @@ -104,17 +104,25 @@ out_big: } EXPORT_SYMBOL(inode_newsize_ok); -int inode_setattr(struct inode * inode, struct iattr * attr) +/** + * generic_setattr - copy simple metadata updates into the generic inode + * @inode: the inode to be updated + * @attr: the new attributes + * + * generic_setattr must be called with i_mutex held. + * + * generic_setattr updates the inode's metadata with that specified + * in attr. Noticably missing is inode size update, which is more complex + * as it requires pagecache updates. See simple_setsize. + * + * The inode is not marked as dirty after this operation. The rationale is + * that for "simple" filesystems, the struct inode is the inode storage. + * The caller is free to mark the inode dirty afterwards if needed. + */ +void generic_setattr(struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; - if (ia_valid & ATTR_SIZE && - attr->ia_size != i_size_read(inode)) { - int error = vmtruncate(inode, attr->ia_size); - if (error) - return error; - } - if (ia_valid & ATTR_UID) inode->i_uid = attr->ia_uid; if (ia_valid & ATTR_GID) @@ -135,6 +143,28 @@ int inode_setattr(struct inode * inode, struct iattr * attr) mode &= ~S_ISGID; inode->i_mode = mode; } +} +EXPORT_SYMBOL(generic_setattr); + +/* + * note this function is deprecated, the new truncate sequence should be + * used instead -- see eg. simple_setsize, generic_setattr. + */ +int inode_setattr(struct inode *inode, const struct iattr *attr) +{ + unsigned int ia_valid = attr->ia_valid; + + if (ia_valid & ATTR_SIZE && + attr->ia_size != i_size_read(inode)) { + int error; + + error = vmtruncate(inode, attr->ia_size); + if (error) + return error; + } + + generic_setattr(inode, attr); + mark_inode_dirty(inode); return 0; diff --git a/fs/buffer.c b/fs/buffer.c index e8aa7081d25c..d54812b198e9 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -1949,14 +1949,11 @@ static int __block_commit_write(struct inode *inode, struct page *page, } /* - * block_write_begin takes care of the basic task of block allocation and - * bringing partial write blocks uptodate first. - * - * If *pagep is not NULL, then block_write_begin uses the locked page - * at *pagep rather than allocating its own. In this case, the page will - * not be unlocked or deallocated on failure. + * Filesystems implementing the new truncate sequence should use the + * _newtrunc postfix variant which won't incorrectly call vmtruncate. + * The filesystem needs to handle block truncation upon failure. */ -int block_write_begin(struct file *file, struct address_space *mapping, +int block_write_begin_newtrunc(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block) @@ -1992,20 +1989,50 @@ int block_write_begin(struct file *file, struct address_space *mapping, unlock_page(page); page_cache_release(page); *pagep = NULL; - - /* - * prepare_write() may have instantiated a few blocks - * outside i_size. Trim these off again. Don't need - * i_size_read because we hold i_mutex. - */ - if (pos + len > inode->i_size) - vmtruncate(inode, inode->i_size); } } out: return status; } +EXPORT_SYMBOL(block_write_begin_newtrunc); + +/* + * block_write_begin takes care of the basic task of block allocation and + * bringing partial write blocks uptodate first. + * + * If *pagep is not NULL, then block_write_begin uses the locked page + * at *pagep rather than allocating its own. In this case, the page will + * not be unlocked or deallocated on failure. + */ +int block_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata, + get_block_t *get_block) +{ + int ret; + + ret = block_write_begin_newtrunc(file, mapping, pos, len, flags, + pagep, fsdata, get_block); + + /* + * prepare_write() may have instantiated a few blocks + * outside i_size. Trim these off again. Don't need + * i_size_read because we hold i_mutex. + * + * Filesystems which pass down their own page also cannot + * call into vmtruncate here because it would lead to lock + * inversion problems (*pagep is locked). This is a further + * example of where the old truncate sequence is inadequate. + */ + if (unlikely(ret) && *pagep == NULL) { + loff_t isize = mapping->host->i_size; + if (pos + len > isize) + vmtruncate(mapping->host, isize); + } + + return ret; +} EXPORT_SYMBOL(block_write_begin); int block_write_end(struct file *file, struct address_space *mapping, @@ -2324,7 +2351,7 @@ out: * For moronic filesystems that do not allow holes in file. * We may have to extend the file. */ -int cont_write_begin(struct file *file, struct address_space *mapping, +int cont_write_begin_newtrunc(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block, loff_t *bytes) @@ -2345,11 +2372,30 @@ int cont_write_begin(struct file *file, struct address_space *mapping, } *pagep = NULL; - err = block_write_begin(file, mapping, pos, len, + err = block_write_begin_newtrunc(file, mapping, pos, len, flags, pagep, fsdata, get_block); out: return err; } +EXPORT_SYMBOL(cont_write_begin_newtrunc); + +int cont_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata, + get_block_t *get_block, loff_t *bytes) +{ + int ret; + + ret = cont_write_begin_newtrunc(file, mapping, pos, len, flags, + pagep, fsdata, get_block, bytes); + if (unlikely(ret)) { + loff_t isize = mapping->host->i_size; + if (pos + len > isize) + vmtruncate(mapping->host, isize); + } + + return ret; +} EXPORT_SYMBOL(cont_write_begin); int block_prepare_write(struct page *page, unsigned from, unsigned to, @@ -2381,7 +2427,7 @@ EXPORT_SYMBOL(block_commit_write); * * We are not allowed to take the i_mutex here so we have to play games to * protect against truncate races as the page could now be beyond EOF. Because - * vmtruncate() writes the inode size before removing pages, once we have the + * truncate writes the inode size before removing pages, once we have the * page lock we can determine safely if the page is beyond EOF. If it is not * beyond EOF, then the page is guaranteed safe against truncation until we * unlock the page. @@ -2464,10 +2510,11 @@ static void attach_nobh_buffers(struct page *page, struct buffer_head *head) } /* - * On entry, the page is fully not uptodate. - * On exit the page is fully uptodate in the areas outside (from,to) + * Filesystems implementing the new truncate sequence should use the + * _newtrunc postfix variant which won't incorrectly call vmtruncate. + * The filesystem needs to handle block truncation upon failure. */ -int nobh_write_begin(struct file *file, struct address_space *mapping, +int nobh_write_begin_newtrunc(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata, get_block_t *get_block) @@ -2500,8 +2547,8 @@ int nobh_write_begin(struct file *file, struct address_space *mapping, unlock_page(page); page_cache_release(page); *pagep = NULL; - return block_write_begin(file, mapping, pos, len, flags, pagep, - fsdata, get_block); + return block_write_begin_newtrunc(file, mapping, pos, len, + flags, pagep, fsdata, get_block); } if (PageMappedToDisk(page)) @@ -2605,8 +2652,34 @@ out_release: page_cache_release(page); *pagep = NULL; - if (pos + len > inode->i_size) - vmtruncate(inode, inode->i_size); + return ret; +} +EXPORT_SYMBOL(nobh_write_begin_newtrunc); + +/* + * On entry, the page is fully not uptodate. + * On exit the page is fully uptodate in the areas outside (from,to) + */ +int nobh_write_begin(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned flags, + struct page **pagep, void **fsdata, + get_block_t *get_block) +{ + int ret; + + ret = nobh_write_begin_newtrunc(file, mapping, pos, len, flags, + pagep, fsdata, get_block); + + /* + * prepare_write() may have instantiated a few blocks + * outside i_size. Trim these off again. Don't need + * i_size_read because we hold i_mutex. + */ + if (unlikely(ret)) { + loff_t isize = mapping->host->i_size; + if (pos + len > isize) + vmtruncate(mapping->host, isize); + } return ret; } diff --git a/fs/direct-io.c b/fs/direct-io.c index da111aacb46e..7600aacf531d 100644 --- a/fs/direct-io.c +++ b/fs/direct-io.c @@ -1134,27 +1134,8 @@ direct_io_worker(int rw, struct kiocb *iocb, struct inode *inode, return ret; } -/* - * This is a library function for use by filesystem drivers. - * - * The locking rules are governed by the flags parameter: - * - if the flags value contains DIO_LOCKING we use a fancy locking - * scheme for dumb filesystems. - * For writes this function is called under i_mutex and returns with - * i_mutex held, for reads, i_mutex is not held on entry, but it is - * taken and dropped again before returning. - * For reads and writes i_alloc_sem is taken in shared mode and released - * on I/O completion (which may happen asynchronously after returning to - * the caller). - * - * - if the flags value does NOT contain DIO_LOCKING we don't use any - * internal locking but rather rely on the filesystem to synchronize - * direct I/O reads/writes versus each other and truncate. - * For reads and writes both i_mutex and i_alloc_sem are not held on - * entry and are never taken. - */ ssize_t -__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, +__blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, dio_submit_t submit_io, int flags) @@ -1247,9 +1228,46 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, nr_segs, blkbits, get_block, end_io, submit_io, dio); +out: + return retval; +} +EXPORT_SYMBOL(__blockdev_direct_IO_newtrunc); + +/* + * This is a library function for use by filesystem drivers. + * + * The locking rules are governed by the flags parameter: + * - if the flags value contains DIO_LOCKING we use a fancy locking + * scheme for dumb filesystems. + * For writes this function is called under i_mutex and returns with + * i_mutex held, for reads, i_mutex is not held on entry, but it is + * taken and dropped again before returning. + * For reads and writes i_alloc_sem is taken in shared mode and released + * on I/O completion (which may happen asynchronously after returning to + * the caller). + * + * - if the flags value does NOT contain DIO_LOCKING we don't use any + * internal locking but rather rely on the filesystem to synchronize + * direct I/O reads/writes versus each other and truncate. + * For reads and writes both i_mutex and i_alloc_sem are not held on + * entry and are never taken. + */ +ssize_t +__blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, const struct iovec *iov, loff_t offset, + unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, + dio_submit_t submit_io, int flags) +{ + ssize_t retval; + + retval = __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov, + offset, nr_segs, get_block, end_io, submit_io, flags); /* * In case of error extending write may have instantiated a few * blocks outside i_size. Trim these off again for DIO_LOCKING. + * NOTE: DIO_NO_LOCK/DIO_OWN_LOCK callers have to handle this in + * their own manner. This is a further example of where the old + * truncate sequence is inadequate. * * NOTE: filesystems with their own locking have to handle this * on their own. @@ -1257,12 +1275,13 @@ __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, if (flags & DIO_LOCKING) { if (unlikely((rw & WRITE) && retval < 0)) { loff_t isize = i_size_read(inode); + loff_t end = offset + iov_length(iov, nr_segs); + if (end > isize) vmtruncate(inode, isize); } } -out: return retval; } EXPORT_SYMBOL(__blockdev_direct_IO); diff --git a/fs/libfs.c b/fs/libfs.c index b84d0a7a2204..09e1016eb774 100644 --- a/fs/libfs.c +++ b/fs/libfs.c @@ -8,6 +8,7 @@ #include #include #include +#include #include #include #include @@ -325,6 +326,81 @@ int simple_rename(struct inode *old_dir, struct dentry *old_dentry, return 0; } +/** + * simple_setsize - handle core mm and vfs requirements for file size change + * @inode: inode + * @newsize: new file size + * + * Returns 0 on success, -error on failure. + * + * simple_setsize must be called with inode_mutex held. + * + * simple_setsize will check that the requested new size is OK (see + * inode_newsize_ok), and then will perform the necessary i_size update + * and pagecache truncation (if necessary). It will be typically be called + * from the filesystem's setattr function when ATTR_SIZE is passed in. + * + * The inode itself must have correct permissions and attributes to allow + * i_size to be changed, this function then just checks that the new size + * requested is valid. + * + * In the case of simple in-memory filesystems with inodes stored solely + * in the inode cache, and file data in the pagecache, nothing more needs + * to be done to satisfy a truncate request. Filesystems with on-disk + * blocks for example will need to free them in the case of truncate, in + * that case it may be easier not to use simple_setsize (but each of its + * components will likely be required at some point to update pagecache + * and inode etc). + */ +int simple_setsize(struct inode *inode, loff_t newsize) +{ + loff_t oldsize; + int error; + + error = inode_newsize_ok(inode, newsize); + if (error) + return error; + + oldsize = inode->i_size; + i_size_write(inode, newsize); + truncate_pagecache(inode, oldsize, newsize); + + return error; +} +EXPORT_SYMBOL(simple_setsize); + +/** + * simple_setattr - setattr for simple in-memory filesystem + * @dentry: dentry + * @iattr: iattr structure + * + * Returns 0 on success, -error on failure. + * + * simple_setattr implements setattr for an in-memory filesystem which + * does not store its own file data or metadata (eg. uses the page cache + * and inode cache as its data store). + */ +int simple_setattr(struct dentry *dentry, struct iattr *iattr) +{ + struct inode *inode = dentry->d_inode; + int error; + + error = inode_change_ok(inode, iattr); + if (error) + return error; + + if (iattr->ia_valid & ATTR_SIZE) { + error = simple_setsize(inode, iattr->ia_size); + if (error) + return error; + } + + generic_setattr(inode, iattr); + + return error; +} +EXPORT_SYMBOL(simple_setattr); + int simple_readpage(struct file *file, struct page *page) { clear_highpage(page); diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h index 05e5f5996216..1b9ba193b789 100644 --- a/include/linux/buffer_head.h +++ b/include/linux/buffer_head.h @@ -203,6 +203,9 @@ int block_write_full_page_endio(struct page *page, get_block_t *get_block, int block_read_full_page(struct page*, get_block_t*); int block_is_partially_uptodate(struct page *page, read_descriptor_t *desc, unsigned long from); +int block_write_begin_newtrunc(struct file *, struct address_space *, + loff_t, unsigned, unsigned, + struct page **, void **, get_block_t*); int block_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); @@ -214,6 +217,9 @@ int generic_write_end(struct file *, struct address_space *, struct page *, void *); void page_zero_new_buffers(struct page *page, unsigned from, unsigned to); int block_prepare_write(struct page*, unsigned, unsigned, get_block_t*); +int cont_write_begin_newtrunc(struct file *, struct address_space *, loff_t, + unsigned, unsigned, struct page **, void **, + get_block_t *, loff_t *); int cont_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t *, loff_t *); @@ -225,6 +231,9 @@ void block_sync_page(struct page *); sector_t generic_block_bmap(struct address_space *, sector_t, get_block_t *); int block_truncate_page(struct address_space *, loff_t, get_block_t *); int file_fsync(struct file *, int); +int nobh_write_begin_newtrunc(struct file *, struct address_space *, + loff_t, unsigned, unsigned, + struct page **, void **, get_block_t*); int nobh_write_begin(struct file *, struct address_space *, loff_t, unsigned, unsigned, struct page **, void **, get_block_t*); diff --git a/include/linux/fs.h b/include/linux/fs.h index acf6c52a50dd..3428393942a6 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -2257,6 +2257,10 @@ typedef void (dio_submit_t)(int rw, struct bio *bio, struct inode *inode, loff_t file_offset); void dio_end_io(struct bio *bio, int error); +ssize_t __blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb, struct inode *inode, + struct block_device *bdev, const struct iovec *iov, loff_t offset, + unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, + dio_submit_t submit_io, int lock_type); ssize_t __blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, unsigned long nr_segs, get_block_t get_block, dio_iodone_t end_io, @@ -2270,6 +2274,24 @@ enum { DIO_SKIP_HOLES = 0x02, }; +static inline ssize_t blockdev_direct_IO_newtrunc(int rw, struct kiocb *iocb, + struct inode *inode, struct block_device *bdev, const struct iovec *iov, + loff_t offset, unsigned long nr_segs, get_block_t get_block, + dio_iodone_t end_io) +{ + return __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov, offset, + nr_segs, get_block, end_io, NULL, + DIO_LOCKING | DIO_SKIP_HOLES); +} + +static inline ssize_t blockdev_direct_IO_no_locking_newtrunc(int rw, struct kiocb *iocb, + struct inode *inode, struct block_device *bdev, const struct iovec *iov, + loff_t offset, unsigned long nr_segs, get_block_t get_block, + dio_iodone_t end_io) +{ + return __blockdev_direct_IO_newtrunc(rw, iocb, inode, bdev, iov, offset, + nr_segs, get_block, end_io, NULL, 0); +} static inline ssize_t blockdev_direct_IO(int rw, struct kiocb *iocb, struct inode *inode, struct block_device *bdev, const struct iovec *iov, loff_t offset, unsigned long nr_segs, get_block_t get_block, @@ -2342,12 +2364,14 @@ extern int dcache_dir_open(struct inode *, struct file *); extern int dcache_dir_close(struct inode *, struct file *); extern loff_t dcache_dir_lseek(struct file *, loff_t, int); extern int dcache_readdir(struct file *, void *, filldir_t); +extern int simple_setattr(struct dentry *, struct iattr *); extern int simple_getattr(struct vfsmount *, struct dentry *, struct kstat *); extern int simple_statfs(struct dentry *, struct kstatfs *); extern int simple_link(struct dentry *, struct inode *, struct dentry *); extern int simple_unlink(struct inode *, struct dentry *); extern int simple_rmdir(struct inode *, struct dentry *); extern int simple_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); +extern int simple_setsize(struct inode *, loff_t); extern int noop_fsync(struct file *, int); extern int simple_empty(struct dentry *); extern int simple_readpage(struct file *file, struct page *page); @@ -2384,7 +2408,8 @@ extern int buffer_migrate_page(struct address_space *, extern int inode_change_ok(const struct inode *, struct iattr *); extern int inode_newsize_ok(const struct inode *, loff_t offset); -extern int __must_check inode_setattr(struct inode *, struct iattr *); +extern int __must_check inode_setattr(struct inode *, const struct iattr *); +extern void generic_setattr(struct inode *inode, const struct iattr *attr); extern void file_update_time(struct file *file); diff --git a/mm/truncate.c b/mm/truncate.c index f42675a3615d..937571b8b233 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -548,18 +548,18 @@ EXPORT_SYMBOL(truncate_pagecache); * NOTE! We have to be ready to update the memory sharing * between the file and the memory map for a potential last * incomplete page. Ugly, but necessary. + * + * This function is deprecated and simple_setsize or truncate_pagecache + * should be used instead. */ int vmtruncate(struct inode *inode, loff_t offset) { - loff_t oldsize; int error; - error = inode_newsize_ok(inode, offset); + error = simple_setsize(inode, offset); if (error) return error; - oldsize = inode->i_size; - i_size_write(inode, offset); - truncate_pagecache(inode, oldsize, offset); + if (inode->i_op->truncate) inode->i_op->truncate(inode); From 15c6fd9786dfaab43547bf60df6fa63170fb64fc Mon Sep 17 00:00:00 2001 From: "npiggin@suse.de" Date: Thu, 27 May 2010 01:05:34 +1000 Subject: [PATCH 11/17] kill spurious reference to vmtruncate Lots of filesystems calls vmtruncate despite not implementing the old ->truncate method. Switch them to use simple_setsize and add some comments about the truncate code where it seems fitting. Signed-off-by: Christoph Hellwig Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- fs/adfs/inode.c | 3 ++- fs/ecryptfs/inode.c | 4 ++-- fs/gfs2/aops.c | 8 +++++++- fs/gfs2/ops_inode.c | 5 ++++- fs/jffs2/fs.c | 4 ++-- fs/ocfs2/file.c | 8 ++++++-- fs/smbfs/inode.c | 2 +- fs/ubifs/file.c | 13 ++++++++----- fs/ubifs/ubifs.h | 2 +- fs/ufs/truncate.c | 10 ++++------ 10 files changed, 37 insertions(+), 22 deletions(-) diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c index 0f5e30978135..6f850b06ab62 100644 --- a/fs/adfs/inode.c +++ b/fs/adfs/inode.c @@ -322,8 +322,9 @@ adfs_notify_change(struct dentry *dentry, struct iattr *attr) if (error) goto out; + /* XXX: this is missing some actual on-disk truncation.. */ if (ia_valid & ATTR_SIZE) - error = vmtruncate(inode, attr->ia_size); + error = simple_setsize(inode, attr->ia_size); if (error) goto out; diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c index 65dee2f336ae..31ef5252f0fe 100644 --- a/fs/ecryptfs/inode.c +++ b/fs/ecryptfs/inode.c @@ -805,7 +805,7 @@ static int truncate_upper(struct dentry *dentry, struct iattr *ia, - (ia->ia_size & ~PAGE_CACHE_MASK)); if (!(crypt_stat->flags & ECRYPTFS_ENCRYPTED)) { - rc = vmtruncate(inode, ia->ia_size); + rc = simple_setsize(inode, ia->ia_size); if (rc) goto out; lower_ia->ia_size = ia->ia_size; @@ -830,7 +830,7 @@ static int truncate_upper(struct dentry *dentry, struct iattr *ia, goto out; } } - vmtruncate(inode, ia->ia_size); + simple_setsize(inode, ia->ia_size); rc = ecryptfs_write_inode_size_to_metadata(inode); if (rc) { printk(KERN_ERR "Problem with " diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c index a739a0a48067..9f8b52500d63 100644 --- a/fs/gfs2/aops.c +++ b/fs/gfs2/aops.c @@ -700,8 +700,14 @@ out: return 0; page_cache_release(page); + + /* + * XXX(hch): the call below should probably be replaced with + * a call to the gfs2-specific truncate blocks helper to actually + * release disk blocks.. + */ if (pos + len > ip->i_inode.i_size) - vmtruncate(&ip->i_inode, ip->i_inode.i_size); + simple_setsize(&ip->i_inode, ip->i_inode.i_size); out_endtrans: gfs2_trans_end(sdp); out_trans_fail: diff --git a/fs/gfs2/ops_inode.c b/fs/gfs2/ops_inode.c index 4e64352d49de..98cdd05f3316 100644 --- a/fs/gfs2/ops_inode.c +++ b/fs/gfs2/ops_inode.c @@ -1071,6 +1071,9 @@ int gfs2_permission(struct inode *inode, int mask) return error; } +/* + * XXX: should be changed to have proper ordering by opencoding simple_setsize + */ static int setattr_size(struct inode *inode, struct iattr *attr) { struct gfs2_inode *ip = GFS2_I(inode); @@ -1081,7 +1084,7 @@ static int setattr_size(struct inode *inode, struct iattr *attr) error = gfs2_trans_begin(sdp, 0, sdp->sd_jdesc->jd_blocks); if (error) return error; - error = vmtruncate(inode, attr->ia_size); + error = simple_setsize(inode, attr->ia_size); gfs2_trans_end(sdp); if (error) return error; diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c index 86e0821fc989..8bc2c80ab159 100644 --- a/fs/jffs2/fs.c +++ b/fs/jffs2/fs.c @@ -169,13 +169,13 @@ int jffs2_do_setattr (struct inode *inode, struct iattr *iattr) mutex_unlock(&f->sem); jffs2_complete_reservation(c); - /* We have to do the vmtruncate() without f->sem held, since + /* We have to do the simple_setsize() without f->sem held, since some pages may be locked and waiting for it in readpage(). We are protected from a simultaneous write() extending i_size back past iattr->ia_size, because do_truncate() holds the generic inode semaphore. */ if (ivalid & ATTR_SIZE && inode->i_size > iattr->ia_size) { - vmtruncate(inode, iattr->ia_size); + simple_setsize(inode, iattr->ia_size); inode->i_blocks = (inode->i_size + 511) >> 9; } diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c index 1c6220a8e072..6a13ea64c447 100644 --- a/fs/ocfs2/file.c +++ b/fs/ocfs2/file.c @@ -1052,7 +1052,7 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr) } /* - * This will intentionally not wind up calling vmtruncate(), + * This will intentionally not wind up calling simple_setsize(), * since all the work for a size change has been done above. * Otherwise, we could get into problems with truncate as * ip_alloc_sem is used there to protect against i_size @@ -2118,9 +2118,13 @@ relock: * direct write may have instantiated a few * blocks outside i_size. Trim these off again. * Don't need i_size_read because we hold i_mutex. + * + * XXX(hch): this looks buggy because ocfs2 did not + * actually implement ->truncate. Take a look at + * the new truncate sequence and update this accordingly */ if (*ppos + count > inode->i_size) - vmtruncate(inode, inode->i_size); + simple_setsize(inode, inode->i_size); ret = written; goto out_dio; } diff --git a/fs/smbfs/inode.c b/fs/smbfs/inode.c index dfa1d67f8fca..9551cb6f7fe4 100644 --- a/fs/smbfs/inode.c +++ b/fs/smbfs/inode.c @@ -714,7 +714,7 @@ smb_notify_change(struct dentry *dentry, struct iattr *attr) error = server->ops->truncate(inode, attr->ia_size); if (error) goto out; - error = vmtruncate(inode, attr->ia_size); + error = simple_setsize(inode, attr->ia_size); if (error) goto out; refresh = 1; diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c index c726da68e6be..12f445cee9f7 100644 --- a/fs/ubifs/file.c +++ b/fs/ubifs/file.c @@ -967,12 +967,15 @@ static int do_writepage(struct page *page, int len) * the page locked, and it locks @ui_mutex. However, write-back does take inode * @i_mutex, which means other VFS operations may be run on this inode at the * same time. And the problematic one is truncation to smaller size, from where - * we have to call 'vmtruncate()', which first changes @inode->i_size, then + * we have to call 'simple_setsize()', which first changes @inode->i_size, then * drops the truncated pages. And while dropping the pages, it takes the page - * lock. This means that 'do_truncation()' cannot call 'vmtruncate()' with + * lock. This means that 'do_truncation()' cannot call 'simple_setsize()' with * @ui_mutex locked, because it would deadlock with 'ubifs_writepage()'. This * means that @inode->i_size is changed while @ui_mutex is unlocked. * + * XXX: with the new truncate the above is not true anymore, the simple_setsize + * calls can be replaced with the individual components. + * * But in 'ubifs_writepage()' we have to guarantee that we do not write beyond * inode size. How do we do this if @inode->i_size may became smaller while we * are in the middle of 'ubifs_writepage()'? The UBIFS solution is the @@ -1125,7 +1128,7 @@ static int do_truncation(struct ubifs_info *c, struct inode *inode, budgeted = 0; } - err = vmtruncate(inode, new_size); + err = simple_setsize(inode, new_size); if (err) goto out_budg; @@ -1214,7 +1217,7 @@ static int do_setattr(struct ubifs_info *c, struct inode *inode, if (attr->ia_valid & ATTR_SIZE) { dbg_gen("size %lld -> %lld", inode->i_size, new_size); - err = vmtruncate(inode, new_size); + err = simple_setsize(inode, new_size); if (err) goto out; } @@ -1223,7 +1226,7 @@ static int do_setattr(struct ubifs_info *c, struct inode *inode, if (attr->ia_valid & ATTR_SIZE) { /* Truncation changes inode [mc]time */ inode->i_mtime = inode->i_ctime = ubifs_current_time(inode); - /* 'vmtruncate()' changed @i_size, update @ui_size */ + /* 'simple_setsize()' changed @i_size, update @ui_size */ ui->ui_size = inode->i_size; } diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h index b0904536cc1c..2eef553d50c8 100644 --- a/fs/ubifs/ubifs.h +++ b/fs/ubifs/ubifs.h @@ -379,7 +379,7 @@ struct ubifs_gced_idx_leb { * The @ui_size is a "shadow" variable for @inode->i_size and UBIFS uses * @ui_size instead of @inode->i_size. The reason for this is that UBIFS cannot * make sure @inode->i_size is always changed under @ui_mutex, because it - * cannot call 'vmtruncate()' with @ui_mutex locked, because it would deadlock + * cannot call 'simple_setsize()' with @ui_mutex locked, because it would deadlock * with 'ubifs_writepage()' (see file.c). All the other inode fields are * changed under @ui_mutex, so they do not need "shadow" fields. Note, one * could consider to rework locking and base it on "shadow" fields. diff --git a/fs/ufs/truncate.c b/fs/ufs/truncate.c index f294c44577dc..3733057e7833 100644 --- a/fs/ufs/truncate.c +++ b/fs/ufs/truncate.c @@ -501,12 +501,10 @@ out: return err; } - /* - * We don't define our `inode->i_op->truncate', and call it here, - * because of: - * - there is no way to know old size - * - there is no way inform user about error, if it happens in `truncate' + * TODO: + * - truncate case should use proper ordering instead of using + * simple_setsize */ int ufs_setattr(struct dentry *dentry, struct iattr *attr) { @@ -530,7 +528,7 @@ int ufs_setattr(struct dentry *dentry, struct iattr *attr) if (ia_valid & ATTR_SIZE && attr->ia_size != inode->i_size) { loff_t old_i_size = inode->i_size; - error = vmtruncate(inode, attr->ia_size); + error = simple_setsize(inode, attr->ia_size); if (error) return error; error = ufs_truncate(inode, old_i_size); From 3322e79a3860fd0d50e3c1879b2e98ac582c0ff6 Mon Sep 17 00:00:00 2001 From: Nick Piggin Date: Thu, 27 May 2010 22:42:19 +1000 Subject: [PATCH 12/17] fs: convert simple fs to new truncate Convert simple filesystems: ramfs, configfs, sysfs, block_dev to new truncate sequence. Cc: Christoph Hellwig Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- fs/block_dev.c | 9 +++++---- fs/configfs/inode.c | 13 ++++--------- fs/ramfs/file-mmu.c | 1 + fs/ramfs/file-nommu.c | 7 ++++--- fs/sysfs/inode.c | 8 +++----- 5 files changed, 17 insertions(+), 21 deletions(-) diff --git a/fs/block_dev.c b/fs/block_dev.c index d0b37e626a1a..7346c96308a5 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -172,8 +172,9 @@ blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, struct file *file = iocb->ki_filp; struct inode *inode = file->f_mapping->host; - return blockdev_direct_IO_no_locking(rw, iocb, inode, I_BDEV(inode), - iov, offset, nr_segs, blkdev_get_blocks, NULL); + return blockdev_direct_IO_no_locking_newtrunc(rw, iocb, inode, + I_BDEV(inode), iov, offset, nr_segs, + blkdev_get_blocks, NULL); } int __sync_blockdev(struct block_device *bdev, int wait) @@ -309,8 +310,8 @@ static int blkdev_write_begin(struct file *file, struct address_space *mapping, struct page **pagep, void **fsdata) { *pagep = NULL; - return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, - blkdev_get_block); + return block_write_begin_newtrunc(file, mapping, pos, len, flags, + pagep, fsdata, blkdev_get_block); } static int blkdev_write_end(struct file *file, struct address_space *mapping, diff --git a/fs/configfs/inode.c b/fs/configfs/inode.c index c8af2d91174b..41645142b88b 100644 --- a/fs/configfs/inode.c +++ b/fs/configfs/inode.c @@ -72,16 +72,11 @@ int configfs_setattr(struct dentry * dentry, struct iattr * iattr) if (!sd) return -EINVAL; + error = simple_setattr(dentry, iattr); + if (error) + return error; + sd_iattr = sd->s_iattr; - - error = inode_change_ok(inode, iattr); - if (error) - return error; - - error = inode_setattr(inode, iattr); - if (error) - return error; - if (!sd_iattr) { /* setting attributes for the first time, allocate now */ sd_iattr = kzalloc(sizeof(struct iattr), GFP_KERNEL); diff --git a/fs/ramfs/file-mmu.c b/fs/ramfs/file-mmu.c index 50020501c5eb..4884ac5ae9be 100644 --- a/fs/ramfs/file-mmu.c +++ b/fs/ramfs/file-mmu.c @@ -50,5 +50,6 @@ const struct file_operations ramfs_file_operations = { }; const struct inode_operations ramfs_file_inode_operations = { + .setattr = simple_setattr, .getattr = simple_getattr, }; diff --git a/fs/ramfs/file-nommu.c b/fs/ramfs/file-nommu.c index 869f2d80183d..d532c20fc179 100644 --- a/fs/ramfs/file-nommu.c +++ b/fs/ramfs/file-nommu.c @@ -146,7 +146,7 @@ static int ramfs_nommu_resize(struct inode *inode, loff_t newsize, loff_t size) return ret; } - ret = vmtruncate(inode, newsize); + ret = simple_setsize(inode, newsize); return ret; } @@ -169,7 +169,8 @@ static int ramfs_nommu_setattr(struct dentry *dentry, struct iattr *ia) /* pick out size-changing events */ if (ia->ia_valid & ATTR_SIZE) { - loff_t size = i_size_read(inode); + loff_t size = inode->i_size; + if (ia->ia_size != size) { ret = ramfs_nommu_resize(inode, ia->ia_size, size); if (ret < 0 || ia->ia_valid == ATTR_SIZE) @@ -182,7 +183,7 @@ static int ramfs_nommu_setattr(struct dentry *dentry, struct iattr *ia) } } - ret = inode_setattr(inode, ia); + generic_setattr(inode, ia); out: ia->ia_valid = old_ia_valid; return ret; diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index bbd77e95cf7f..bde1a4c3679a 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -117,13 +117,11 @@ int sysfs_setattr(struct dentry *dentry, struct iattr *iattr) if (error) goto out; - iattr->ia_valid &= ~ATTR_SIZE; /* ignore size changes */ - - error = inode_setattr(inode, iattr); - if (error) - goto out; + /* this ignores size changes */ + generic_setattr(inode, iattr); error = sysfs_sd_setattr(sd, iattr); + out: mutex_unlock(&sysfs_mutex); return error; From 3889e6e76f66b7de208a1709d0fe530b21a2d384 Mon Sep 17 00:00:00 2001 From: "npiggin@suse.de" Date: Thu, 27 May 2010 01:05:36 +1000 Subject: [PATCH 13/17] tmpfs: convert to use the new truncate convention Cc: Christoph Hellwig Acked-by: Hugh Dickins Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- mm/shmem.c | 43 ++++++++++++++++++++++--------------------- 1 file changed, 22 insertions(+), 21 deletions(-) diff --git a/mm/shmem.c b/mm/shmem.c index 4daf8cecf422..7e5030ae18ff 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -727,10 +727,11 @@ done2: if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) { /* * Call truncate_inode_pages again: racing shmem_unuse_inode - * may have swizzled a page in from swap since vmtruncate or - * generic_delete_inode did it, before we lowered next_index. - * Also, though shmem_getpage checks i_size before adding to - * cache, no recheck after: so fix the narrow window there too. + * may have swizzled a page in from swap since + * truncate_pagecache or generic_delete_inode did it, before we + * lowered next_index. Also, though shmem_getpage checks + * i_size before adding to cache, no recheck after: so fix the + * narrow window there too. * * Recalling truncate_inode_pages_range and unmap_mapping_range * every time for punch_hole (which never got a chance to clear @@ -760,19 +761,16 @@ done2: } } -static void shmem_truncate(struct inode *inode) -{ - shmem_truncate_range(inode, inode->i_size, (loff_t)-1); -} - static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) { struct inode *inode = dentry->d_inode; - struct page *page = NULL; int error; if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) { - if (attr->ia_size < inode->i_size) { + loff_t newsize = attr->ia_size; + struct page *page = NULL; + + if (newsize < inode->i_size) { /* * If truncating down to a partial page, then * if that page is already allocated, hold it @@ -780,9 +778,9 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) * truncate_partial_page cannnot miss it were * it assigned to swap. */ - if (attr->ia_size & (PAGE_CACHE_SIZE-1)) { + if (newsize & (PAGE_CACHE_SIZE-1)) { (void) shmem_getpage(inode, - attr->ia_size>>PAGE_CACHE_SHIFT, + newsize >> PAGE_CACHE_SHIFT, &page, SGP_READ, NULL); if (page) unlock_page(page); @@ -794,24 +792,29 @@ static int shmem_notify_change(struct dentry *dentry, struct iattr *attr) * if it's being fully truncated to zero-length: the * nrpages check is efficient enough in that case. */ - if (attr->ia_size) { + if (newsize) { struct shmem_inode_info *info = SHMEM_I(inode); spin_lock(&info->lock); info->flags &= ~SHMEM_PAGEIN; spin_unlock(&info->lock); } } + + error = simple_setsize(inode, newsize); + if (page) + page_cache_release(page); + if (error) + return error; + shmem_truncate_range(inode, newsize, (loff_t)-1); } error = inode_change_ok(inode, attr); if (!error) - error = inode_setattr(inode, attr); + generic_setattr(inode, attr); #ifdef CONFIG_TMPFS_POSIX_ACL if (!error && (attr->ia_valid & ATTR_MODE)) error = generic_acl_chmod(inode); #endif - if (page) - page_cache_release(page); return error; } @@ -819,11 +822,11 @@ static void shmem_delete_inode(struct inode *inode) { struct shmem_inode_info *info = SHMEM_I(inode); - if (inode->i_op->truncate == shmem_truncate) { + if (inode->i_mapping->a_ops == &shmem_aops) { truncate_inode_pages(inode->i_mapping, 0); shmem_unacct_size(info->flags, inode->i_size); inode->i_size = 0; - shmem_truncate(inode); + shmem_truncate_range(inode, 0, (loff_t)-1); if (!list_empty(&info->swaplist)) { mutex_lock(&shmem_swaplist_mutex); list_del_init(&info->swaplist); @@ -2022,7 +2025,6 @@ static const struct inode_operations shmem_symlink_inline_operations = { }; static const struct inode_operations shmem_symlink_inode_operations = { - .truncate = shmem_truncate, .readlink = generic_readlink, .follow_link = shmem_follow_link, .put_link = shmem_put_link, @@ -2440,7 +2442,6 @@ static const struct file_operations shmem_file_operations = { }; static const struct inode_operations shmem_inode_operations = { - .truncate = shmem_truncate, .setattr = shmem_notify_change, .truncate_range = shmem_truncate_range, #ifdef CONFIG_TMPFS_POSIX_ACL From 737f2e93b9724a3554f9d0b248c22cd407313f86 Mon Sep 17 00:00:00 2001 From: "npiggin@suse.de" Date: Thu, 27 May 2010 01:05:37 +1000 Subject: [PATCH 14/17] ext2: convert to use the new truncate convention. I also have commented a possible bug in existing ext2 code, marked with XXX. Cc: linux-ext4@vger.kernel.org Cc: Christoph Hellwig Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- fs/ext2/ext2.h | 1 - fs/ext2/file.c | 1 - fs/ext2/inode.c | 151 +++++++++++++++++++++++++++++++++++++----------- 3 files changed, 118 insertions(+), 35 deletions(-) diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h index 8e917b686510..52b34f1d2738 100644 --- a/fs/ext2/ext2.h +++ b/fs/ext2/ext2.h @@ -122,7 +122,6 @@ extern int ext2_write_inode (struct inode *, struct writeback_control *); extern void ext2_delete_inode (struct inode *); extern int ext2_sync_inode (struct inode *); extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int); -extern void ext2_truncate (struct inode *); extern int ext2_setattr (struct dentry *, struct iattr *); extern void ext2_set_inode_flags(struct inode *inode); extern void ext2_get_inode_flags(struct ext2_inode_info *); diff --git a/fs/ext2/file.c b/fs/ext2/file.c index d82e7ca93455..49eec9456c5b 100644 --- a/fs/ext2/file.c +++ b/fs/ext2/file.c @@ -95,7 +95,6 @@ const struct file_operations ext2_xip_file_operations = { #endif const struct inode_operations ext2_file_inode_operations = { - .truncate = ext2_truncate, #ifdef CONFIG_EXT2_FS_XATTR .setxattr = generic_setxattr, .getxattr = generic_getxattr, diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c index 527c46d9bc1f..19214435b752 100644 --- a/fs/ext2/inode.c +++ b/fs/ext2/inode.c @@ -54,6 +54,18 @@ static inline int ext2_inode_is_fast_symlink(struct inode *inode) inode->i_blocks - ea_blocks == 0); } +static void ext2_truncate_blocks(struct inode *inode, loff_t offset); + +static void ext2_write_failed(struct address_space *mapping, loff_t to) +{ + struct inode *inode = mapping->host; + + if (to > inode->i_size) { + truncate_pagecache(inode, to, inode->i_size); + ext2_truncate_blocks(inode, inode->i_size); + } +} + /* * Called at the last iput() if i_nlink is zero. */ @@ -71,7 +83,7 @@ void ext2_delete_inode (struct inode * inode) inode->i_size = 0; if (inode->i_blocks) - ext2_truncate (inode); + ext2_truncate_blocks(inode, 0); ext2_free_inode (inode); return; @@ -757,8 +769,8 @@ int __ext2_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { - return block_write_begin(file, mapping, pos, len, flags, pagep, fsdata, - ext2_get_block); + return block_write_begin_newtrunc(file, mapping, pos, len, flags, + pagep, fsdata, ext2_get_block); } static int @@ -766,8 +778,25 @@ ext2_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { + int ret; + *pagep = NULL; - return __ext2_write_begin(file, mapping, pos, len, flags, pagep,fsdata); + ret = __ext2_write_begin(file, mapping, pos, len, flags, pagep, fsdata); + if (ret < 0) + ext2_write_failed(mapping, pos + len); + return ret; +} + +static int ext2_write_end(struct file *file, struct address_space *mapping, + loff_t pos, unsigned len, unsigned copied, + struct page *page, void *fsdata) +{ + int ret; + + ret = generic_write_end(file, mapping, pos, len, copied, page, fsdata); + if (ret < len) + ext2_write_failed(mapping, pos + len); + return ret; } static int @@ -775,13 +804,18 @@ ext2_nobh_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { + int ret; + /* * Dir-in-pagecache still uses ext2_write_begin. Would have to rework * directory handling code to pass around offsets rather than struct * pages in order to make this work easily. */ - return nobh_write_begin(file, mapping, pos, len, flags, pagep, fsdata, - ext2_get_block); + ret = nobh_write_begin_newtrunc(file, mapping, pos, len, flags, pagep, + fsdata, ext2_get_block); + if (ret < 0) + ext2_write_failed(mapping, pos + len); + return ret; } static int ext2_nobh_writepage(struct page *page, @@ -800,10 +834,15 @@ ext2_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t offset, unsigned long nr_segs) { struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + ssize_t ret; - return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, ext2_get_block, NULL); + ret = blockdev_direct_IO_newtrunc(rw, iocb, inode, inode->i_sb->s_bdev, + iov, offset, nr_segs, ext2_get_block, NULL); + if (ret < 0 && (rw & WRITE)) + ext2_write_failed(mapping, offset + iov_length(iov, nr_segs)); + return ret; } static int @@ -818,7 +857,7 @@ const struct address_space_operations ext2_aops = { .writepage = ext2_writepage, .sync_page = block_sync_page, .write_begin = ext2_write_begin, - .write_end = generic_write_end, + .write_end = ext2_write_end, .bmap = ext2_bmap, .direct_IO = ext2_direct_IO, .writepages = ext2_writepages, @@ -1027,7 +1066,7 @@ static void ext2_free_branches(struct inode *inode, __le32 *p, __le32 *q, int de ext2_free_data(inode, p, q); } -void ext2_truncate(struct inode *inode) +static void __ext2_truncate_blocks(struct inode *inode, loff_t offset) { __le32 *i_data = EXT2_I(inode)->i_data; struct ext2_inode_info *ei = EXT2_I(inode); @@ -1039,27 +1078,8 @@ void ext2_truncate(struct inode *inode) int n; long iblock; unsigned blocksize; - - if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || - S_ISLNK(inode->i_mode))) - return; - if (ext2_inode_is_fast_symlink(inode)) - return; - if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) - return; - blocksize = inode->i_sb->s_blocksize; - iblock = (inode->i_size + blocksize-1) - >> EXT2_BLOCK_SIZE_BITS(inode->i_sb); - - if (mapping_is_xip(inode->i_mapping)) - xip_truncate_page(inode->i_mapping, inode->i_size); - else if (test_opt(inode->i_sb, NOBH)) - nobh_truncate_page(inode->i_mapping, - inode->i_size, ext2_get_block); - else - block_truncate_page(inode->i_mapping, - inode->i_size, ext2_get_block); + iblock = (offset + blocksize-1) >> EXT2_BLOCK_SIZE_BITS(inode->i_sb); n = ext2_block_to_path(inode, iblock, offsets, NULL); if (n == 0) @@ -1127,6 +1147,62 @@ do_indirects: ext2_discard_reservation(inode); mutex_unlock(&ei->truncate_mutex); +} + +static void ext2_truncate_blocks(struct inode *inode, loff_t offset) +{ + /* + * XXX: it seems like a bug here that we don't allow + * IS_APPEND inode to have blocks-past-i_size trimmed off. + * review and fix this. + * + * Also would be nice to be able to handle IO errors and such, + * but that's probably too much to ask. + */ + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode))) + return; + if (ext2_inode_is_fast_symlink(inode)) + return; + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + return; + __ext2_truncate_blocks(inode, offset); +} + +int ext2_setsize(struct inode *inode, loff_t newsize) +{ + loff_t oldsize; + int error; + + error = inode_newsize_ok(inode, newsize); + if (error) + return error; + + if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || + S_ISLNK(inode->i_mode))) + return -EINVAL; + if (ext2_inode_is_fast_symlink(inode)) + return -EINVAL; + if (IS_APPEND(inode) || IS_IMMUTABLE(inode)) + return -EPERM; + + if (mapping_is_xip(inode->i_mapping)) + error = xip_truncate_page(inode->i_mapping, newsize); + else if (test_opt(inode->i_sb, NOBH)) + error = nobh_truncate_page(inode->i_mapping, + newsize, ext2_get_block); + else + error = block_truncate_page(inode->i_mapping, + newsize, ext2_get_block); + if (error) + return error; + + oldsize = inode->i_size; + i_size_write(inode, newsize); + truncate_pagecache(inode, oldsize, newsize); + + __ext2_truncate_blocks(inode, newsize); + inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; if (inode_needs_sync(inode)) { sync_mapping_buffers(inode->i_mapping); @@ -1134,6 +1210,8 @@ do_indirects: } else { mark_inode_dirty(inode); } + + return 0; } static struct ext2_inode *ext2_get_inode(struct super_block *sb, ino_t ino, @@ -1474,8 +1552,15 @@ int ext2_setattr(struct dentry *dentry, struct iattr *iattr) if (error) return error; } - error = inode_setattr(inode, iattr); - if (!error && (iattr->ia_valid & ATTR_MODE)) + if (iattr->ia_valid & ATTR_SIZE) { + error = ext2_setsize(inode, iattr->ia_size); + if (error) + return error; + } + generic_setattr(inode, iattr); + if (iattr->ia_valid & ATTR_MODE) error = ext2_acl_chmod(inode); + mark_inode_dirty(inode); + return error; } From 459f6ed3b8c74cedeb64e5a854394c0d40eda9cd Mon Sep 17 00:00:00 2001 From: "npiggin@suse.de" Date: Thu, 27 May 2010 01:05:38 +1000 Subject: [PATCH 15/17] fat: convert to use the new truncate convention. Cc: OGAWA Hirofumi Cc: Christoph Hellwig Signed-off-by: Nick Piggin Signed-off-by: Al Viro --- fs/fat/fat.h | 3 ++- fs/fat/file.c | 34 ++++++++++++++++++++++++++-------- fs/fat/inode.c | 35 +++++++++++++++++++++++++++++------ 3 files changed, 57 insertions(+), 15 deletions(-) diff --git a/fs/fat/fat.h b/fs/fat/fat.h index a1c8c4b44fdb..27ac25725954 100644 --- a/fs/fat/fat.h +++ b/fs/fat/fat.h @@ -306,7 +306,8 @@ extern long fat_generic_ioctl(struct file *filp, unsigned int cmd, extern const struct file_operations fat_file_operations; extern const struct inode_operations fat_file_inode_operations; extern int fat_setattr(struct dentry * dentry, struct iattr * attr); -extern void fat_truncate(struct inode *inode); +extern int fat_setsize(struct inode *inode, loff_t offset); +extern void fat_truncate_blocks(struct inode *inode, loff_t offset); extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat); extern int fat_file_fsync(struct file *file, int datasync); diff --git a/fs/fat/file.c b/fs/fat/file.c index 8c13b8acfd2f..990dfae022e5 100644 --- a/fs/fat/file.c +++ b/fs/fat/file.c @@ -283,7 +283,7 @@ static int fat_free(struct inode *inode, int skip) return fat_free_clusters(inode, free_start); } -void fat_truncate(struct inode *inode) +void fat_truncate_blocks(struct inode *inode, loff_t offset) { struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb); const unsigned int cluster_size = sbi->cluster_size; @@ -293,10 +293,10 @@ void fat_truncate(struct inode *inode) * This protects against truncating a file bigger than it was then * trying to write into the hole. */ - if (MSDOS_I(inode)->mmu_private > inode->i_size) - MSDOS_I(inode)->mmu_private = inode->i_size; + if (MSDOS_I(inode)->mmu_private > offset) + MSDOS_I(inode)->mmu_private = offset; - nr_clusters = (inode->i_size + (cluster_size - 1)) >> sbi->cluster_bits; + nr_clusters = (offset + (cluster_size - 1)) >> sbi->cluster_bits; fat_free(inode, nr_clusters); fat_flush_inodes(inode->i_sb, inode, NULL); @@ -364,6 +364,18 @@ static int fat_allow_set_time(struct msdos_sb_info *sbi, struct inode *inode) return 0; } +int fat_setsize(struct inode *inode, loff_t offset) +{ + int error; + + error = simple_setsize(inode, offset); + if (error) + return error; + fat_truncate_blocks(inode, offset); + + return error; +} + #define TIMES_SET_FLAGS (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET) /* valid file mode bits */ #define FAT_VALID_MODE (S_IFREG | S_IFDIR | S_IRWXUGO) @@ -378,7 +390,8 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) /* * Expand the file. Since inode_setattr() updates ->i_size * before calling the ->truncate(), but FAT needs to fill the - * hole before it. + * hole before it. XXX: this is no longer true with new truncate + * sequence. */ if (attr->ia_valid & ATTR_SIZE) { if (attr->ia_size > inode->i_size) { @@ -427,15 +440,20 @@ int fat_setattr(struct dentry *dentry, struct iattr *attr) attr->ia_valid &= ~ATTR_MODE; } - if (attr->ia_valid) - error = inode_setattr(inode, attr); + if (attr->ia_valid & ATTR_SIZE) { + error = fat_setsize(inode, attr->ia_size); + if (error) + goto out; + } + + generic_setattr(inode, attr); + mark_inode_dirty(inode); out: return error; } EXPORT_SYMBOL_GPL(fat_setattr); const struct inode_operations fat_file_inode_operations = { - .truncate = fat_truncate, .setattr = fat_setattr, .getattr = fat_getattr, }; diff --git a/fs/fat/inode.c b/fs/fat/inode.c index ed33904926ee..7bf45aee56d7 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -142,14 +142,29 @@ static int fat_readpages(struct file *file, struct address_space *mapping, return mpage_readpages(mapping, pages, nr_pages, fat_get_block); } +static void fat_write_failed(struct address_space *mapping, loff_t to) +{ + struct inode *inode = mapping->host; + + if (to > inode->i_size) { + truncate_pagecache(inode, to, inode->i_size); + fat_truncate_blocks(inode, inode->i_size); + } +} + static int fat_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, struct page **pagep, void **fsdata) { + int err; + *pagep = NULL; - return cont_write_begin(file, mapping, pos, len, flags, pagep, fsdata, - fat_get_block, + err = cont_write_begin_newtrunc(file, mapping, pos, len, flags, + pagep, fsdata, fat_get_block, &MSDOS_I(mapping->host)->mmu_private); + if (err < 0) + fat_write_failed(mapping, pos + len); + return err; } static int fat_write_end(struct file *file, struct address_space *mapping, @@ -159,6 +174,8 @@ static int fat_write_end(struct file *file, struct address_space *mapping, struct inode *inode = mapping->host; int err; err = generic_write_end(file, mapping, pos, len, copied, pagep, fsdata); + if (err < len) + fat_write_failed(mapping, pos + len); if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) { inode->i_mtime = inode->i_ctime = CURRENT_TIME_SEC; MSDOS_I(inode)->i_attrs |= ATTR_ARCH; @@ -172,7 +189,9 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, loff_t offset, unsigned long nr_segs) { struct file *file = iocb->ki_filp; - struct inode *inode = file->f_mapping->host; + struct address_space *mapping = file->f_mapping; + struct inode *inode = mapping->host; + ssize_t ret; if (rw == WRITE) { /* @@ -193,8 +212,12 @@ static ssize_t fat_direct_IO(int rw, struct kiocb *iocb, * FAT need to use the DIO_LOCKING for avoiding the race * condition of fat_get_block() and ->truncate(). */ - return blockdev_direct_IO(rw, iocb, inode, inode->i_sb->s_bdev, iov, - offset, nr_segs, fat_get_block, NULL); + ret = blockdev_direct_IO_newtrunc(rw, iocb, inode, inode->i_sb->s_bdev, + iov, offset, nr_segs, fat_get_block, NULL); + if (ret < 0 && (rw & WRITE)) + fat_write_failed(mapping, offset + iov_length(iov, nr_segs)); + + return ret; } static sector_t _fat_bmap(struct address_space *mapping, sector_t block) @@ -429,7 +452,7 @@ static void fat_delete_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); inode->i_size = 0; - fat_truncate(inode); + fat_truncate_blocks(inode, 0); clear_inode(inode); } From 4c9002de329c9ae825f10eb9044c928434a4d230 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Thu, 27 May 2010 09:04:07 -0400 Subject: [PATCH 16/17] fix fs/sysv s_dirt handling got broken on ->sync_fs() conversion a year ago, nobody noticed... Signed-off-by: Al Viro --- fs/sysv/inode.c | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c index 4573734d723d..d4a5380b5669 100644 --- a/fs/sysv/inode.c +++ b/fs/sysv/inode.c @@ -43,6 +43,7 @@ static int sysv_sync_fs(struct super_block *sb, int wait) * then attach current time stamp. * But if the filesystem was marked clean, keep it clean. */ + sb->s_dirt = 0; old_time = fs32_to_cpu(sbi, *sbi->s_sb_time); if (sbi->s_type == FSTYPE_SYSV4) { if (*sbi->s_sb_state == cpu_to_fs32(sbi, 0x7c269d38 - old_time)) From 49837a80b38b79a7c06217b2c40842aeb6fa13b9 Mon Sep 17 00:00:00 2001 From: Al Viro Date: Fri, 28 May 2010 11:34:50 -0400 Subject: [PATCH 17/17] remove detritus left by "mm: make read_cache_page synchronous" gets minix get_dir_page() in sync with its analogs; back in 2007 Nick has switched read_cache_page() and friends to sync behaviour (i.e. they wait for the page to get unlocked, check if it's uptodate and if it isn't return ERR_PTR(-EIO) instead) and removed the duplicate logics from the callers. In case of fs/minix/dir.c he'd removed only half of that... Signed-off-by: Al Viro --- fs/minix/dir.c | 5 +---- 1 file changed, 1 insertion(+), 4 deletions(-) diff --git a/fs/minix/dir.c b/fs/minix/dir.c index aaab97ec5bc0..91969589131c 100644 --- a/fs/minix/dir.c +++ b/fs/minix/dir.c @@ -72,11 +72,8 @@ static struct page * dir_get_page(struct inode *dir, unsigned long n) { struct address_space *mapping = dir->i_mapping; struct page *page = read_mapping_page(mapping, n, NULL); - if (!IS_ERR(page)) { + if (!IS_ERR(page)) kmap(page); - if (!PageUptodate(page)) - goto fail; - } return page; fail: