From 454e2398be9b9fa30433fccc548db34d19aa9958 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 23 Jun 2006 02:02:57 -0700 Subject: [PATCH] VFS: Permit filesystem to override root dentry on mount Extend the get_sb() filesystem operation to take an extra argument that permits the VFS to pass in the target vfsmount that defines the mountpoint. The filesystem is then required to manually set the superblock and root dentry pointers. For most filesystems, this should be done with simple_set_mnt() which will set the superblock pointer and then set the root dentry to the superblock's s_root (as per the old default behaviour). The get_sb() op now returns an integer as there's now no need to return the superblock pointer. This patch permits a superblock to be implicitly shared amongst several mount points, such as can be done with NFS to avoid potential inode aliasing. In such a case, simple_set_mnt() would not be called, and instead the mnt_root and mnt_sb would be set directly. The patch also makes the following changes: (*) the get_sb_*() convenience functions in the core kernel now take a vfsmount pointer argument and return an integer, so most filesystems have to change very little. (*) If one of the convenience function is not used, then get_sb() should normally call simple_set_mnt() to instantiate the vfsmount. This will always return 0, and so can be tail-called from get_sb(). (*) generic_shutdown_super() now calls shrink_dcache_sb() to clean up the dcache upon superblock destruction rather than shrink_dcache_anon(). This is required because the superblock may now have multiple trees that aren't actually bound to s_root, but that still need to be cleaned up. The currently called functions assume that the whole tree is rooted at s_root, and that anonymous dentries are not the roots of trees which results in dentries being left unculled. However, with the way NFS superblock sharing are currently set to be implemented, these assumptions are violated: the root of the filesystem is simply a dummy dentry and inode (the real inode for '/' may well be inaccessible), and all the vfsmounts are rooted on anonymous[*] dentries with child trees. [*] Anonymous until discovered from another tree. (*) The documentation has been adjusted, including the additional bit of changing ext2_* into foo_* in the documentation. [akpm@osdl.org: convert ipath_fs, do other stuff] Signed-off-by: David Howells Acked-by: Al Viro Cc: Nathan Scott Cc: Roland Dreier Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- ipc/mqueue.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'ipc/mqueue.c') diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 1511714a958..0a2a24b6ebe 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -205,11 +205,11 @@ static int mqueue_fill_super(struct super_block *sb, void *data, int silent) return 0; } -static struct super_block *mqueue_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, - void *data) +static int mqueue_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, + void *data, struct vfsmount *mnt) { - return get_sb_single(fs_type, flags, data, mqueue_fill_super); + return get_sb_single(fs_type, flags, data, mqueue_fill_super, mnt); } static void init_once(void *foo, kmem_cache_t * cachep, unsigned long flags) -- cgit v1.2.3-70-g09d2 From 75e1fcc0b18df0a65ab113198e9dc0e98999a08c Mon Sep 17 00:00:00 2001 From: Miklos Szeredi Date: Fri, 23 Jun 2006 02:05:12 -0700 Subject: [PATCH] vfs: add lock owner argument to flush operation Pass the POSIX lock owner ID to the flush operation. This is useful for filesystems which don't want to store any locking state in inode->i_flock but want to handle locking/unlocking POSIX locks internally. FUSE is one such filesystem but I think it possible that some network filesystems would need this also. Also add a flag to indicate that a POSIX locking request was generated by close(), so filesystems using the above feature won't send an extra locking request in this case. Signed-off-by: Miklos Szeredi Cc: Trond Myklebust Cc: Al Viro Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- arch/ia64/kernel/perfmon.c | 3 +-- drivers/input/evdev.c | 2 +- drivers/scsi/osst.c | 2 +- drivers/scsi/st.c | 2 +- fs/cifs/cifsfs.h | 2 +- fs/cifs/file.c | 2 +- fs/coda/file.c | 2 +- fs/fuse/file.c | 2 +- fs/locks.c | 2 +- fs/nfs/file.c | 4 ++-- fs/open.c | 2 +- include/linux/coda_linux.h | 2 +- include/linux/fs.h | 3 ++- ipc/mqueue.c | 2 +- 14 files changed, 16 insertions(+), 16 deletions(-) (limited to 'ipc/mqueue.c') diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c index 2359e2809f5..6d7bc8ff7b3 100644 --- a/arch/ia64/kernel/perfmon.c +++ b/arch/ia64/kernel/perfmon.c @@ -532,7 +532,6 @@ static ctl_table pfm_sysctl_root[] = { static struct ctl_table_header *pfm_sysctl_header; static int pfm_context_unload(pfm_context_t *ctx, void *arg, int count, struct pt_regs *regs); -static int pfm_flush(struct file *filp); #define pfm_get_cpu_var(v) __ia64_per_cpu_var(v) #define pfm_get_cpu_data(a,b) per_cpu(a, b) @@ -1774,7 +1773,7 @@ pfm_syswide_cleanup_other_cpu(pfm_context_t *ctx) * When caller is self-monitoring, the context is unloaded. */ static int -pfm_flush(struct file *filp) +pfm_flush(struct file *filp, fl_owner_t id) { pfm_context_t *ctx; struct task_struct *task; diff --git a/drivers/input/evdev.c b/drivers/input/evdev.c index ba325f16d07..5f561fce32d 100644 --- a/drivers/input/evdev.c +++ b/drivers/input/evdev.c @@ -82,7 +82,7 @@ static int evdev_fasync(int fd, struct file *file, int on) return retval < 0 ? retval : 0; } -static int evdev_flush(struct file * file) +static int evdev_flush(struct file * file, fl_owner_t id) { struct evdev_list *list = file->private_data; if (!list->evdev->exist) return -ENODEV; diff --git a/drivers/scsi/osst.c b/drivers/scsi/osst.c index ce0ba3a174f..4a2fed350d4 100644 --- a/drivers/scsi/osst.c +++ b/drivers/scsi/osst.c @@ -4724,7 +4724,7 @@ err_out: /* Flush the tape buffer before close */ -static int os_scsi_tape_flush(struct file * filp) +static int os_scsi_tape_flush(struct file * filp, fl_owner_t id) { int result = 0, result2; struct osst_tape * STp = filp->private_data; diff --git a/drivers/scsi/st.c b/drivers/scsi/st.c index ad87d73f88e..1272dd249af 100644 --- a/drivers/scsi/st.c +++ b/drivers/scsi/st.c @@ -1193,7 +1193,7 @@ static int st_open(struct inode *inode, struct file *filp) /* Flush the tape buffer before close */ -static int st_flush(struct file *filp) +static int st_flush(struct file *filp, fl_owner_t id) { int result = 0, result2; unsigned char cmd[MAX_COMMAND_SIZE]; diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index c98755dca86..d56c0577c71 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -74,7 +74,7 @@ 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_flush(struct file *); +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; extern int cifs_dir_open(struct inode *inode, struct file *file); diff --git a/fs/cifs/file.c b/fs/cifs/file.c index 487ea8b3baa..b4a18c1cab0 100644 --- a/fs/cifs/file.c +++ b/fs/cifs/file.c @@ -1417,7 +1417,7 @@ int cifs_fsync(struct file *file, struct dentry *dentry, int datasync) * As file closes, flush all cached write data for this inode checking * for write behind errors. */ -int cifs_flush(struct file *file) +int cifs_flush(struct file *file, fl_owner_t id) { struct inode * inode = file->f_dentry->d_inode; int rc = 0; diff --git a/fs/coda/file.c b/fs/coda/file.c index 7c2642431fa..cc66c681bd1 100644 --- a/fs/coda/file.c +++ b/fs/coda/file.c @@ -164,7 +164,7 @@ int coda_open(struct inode *coda_inode, struct file *coda_file) return 0; } -int coda_flush(struct file *coda_file) +int coda_flush(struct file *coda_file, fl_owner_t id) { unsigned short flags = coda_file->f_flags & ~O_EXCL; unsigned short coda_flags = coda_flags_to_cflags(flags); diff --git a/fs/fuse/file.c b/fs/fuse/file.c index fc342cf7c2c..087f3b734f4 100644 --- a/fs/fuse/file.c +++ b/fs/fuse/file.c @@ -169,7 +169,7 @@ static int fuse_release(struct inode *inode, struct file *file) return fuse_release_common(inode, file, 0); } -static int fuse_flush(struct file *file) +static int fuse_flush(struct file *file, fl_owner_t id) { struct inode *inode = file->f_dentry->d_inode; struct fuse_conn *fc = get_fuse_conn(inode); diff --git a/fs/locks.c b/fs/locks.c index e588e1c265f..f8a634ac112 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1907,7 +1907,7 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) return; lock.fl_type = F_UNLCK; - lock.fl_flags = FL_POSIX; + lock.fl_flags = FL_POSIX | FL_CLOSE; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; lock.fl_owner = owner; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index fade02c15e6..fa05c027ea1 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -43,7 +43,7 @@ static int nfs_file_mmap(struct file *, struct vm_area_struct *); static ssize_t nfs_file_sendfile(struct file *, loff_t *, size_t, read_actor_t, void *); static ssize_t nfs_file_read(struct kiocb *, char __user *, size_t, loff_t); static ssize_t nfs_file_write(struct kiocb *, const char __user *, size_t, loff_t); -static int nfs_file_flush(struct file *); +static int nfs_file_flush(struct file *, fl_owner_t id); static int nfs_fsync(struct file *, struct dentry *dentry, int datasync); static int nfs_check_flags(int flags); static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl); @@ -188,7 +188,7 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin) * */ static int -nfs_file_flush(struct file *file) +nfs_file_flush(struct file *file, fl_owner_t id) { struct nfs_open_context *ctx = (struct nfs_open_context *)file->private_data; struct inode *inode = file->f_dentry->d_inode; diff --git a/fs/open.c b/fs/open.c index a37ff861108..5fb16e5267d 100644 --- a/fs/open.c +++ b/fs/open.c @@ -1152,7 +1152,7 @@ int filp_close(struct file *filp, fl_owner_t id) } if (filp->f_op && filp->f_op->flush) - retval = filp->f_op->flush(filp); + retval = filp->f_op->flush(filp, id); dnotify_flush(filp, id); locks_remove_posix(filp, id); diff --git a/include/linux/coda_linux.h b/include/linux/coda_linux.h index b3ecf8f71d9..7b5c5df5cb6 100644 --- a/include/linux/coda_linux.h +++ b/include/linux/coda_linux.h @@ -36,7 +36,7 @@ extern const struct file_operations coda_ioctl_operations; /* operations shared over more than one file */ int coda_open(struct inode *i, struct file *f); -int coda_flush(struct file *f); +int coda_flush(struct file *f, fl_owner_t id); int coda_release(struct inode *i, struct file *f); int coda_permission(struct inode *inode, int mask, struct nameidata *nd); int coda_revalidate_inode(struct dentry *); diff --git a/include/linux/fs.h b/include/linux/fs.h index e917403f4d5..56d8bf0d0a7 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -683,6 +683,7 @@ extern spinlock_t files_lock; #define FL_FLOCK 2 #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_LEASE 32 /* lease held on this file */ +#define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ /* @@ -1025,7 +1026,7 @@ struct file_operations { long (*compat_ioctl) (struct file *, unsigned int, unsigned long); int (*mmap) (struct file *, struct vm_area_struct *); int (*open) (struct inode *, struct file *); - int (*flush) (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 (*aio_fsync) (struct kiocb *, int datasync); diff --git a/ipc/mqueue.c b/ipc/mqueue.c index 0a2a24b6ebe..02e6f679897 100644 --- a/ipc/mqueue.c +++ b/ipc/mqueue.c @@ -359,7 +359,7 @@ static ssize_t mqueue_read_file(struct file *filp, char __user *u_data, return count; } -static int mqueue_flush_file(struct file *filp) +static int mqueue_flush_file(struct file *filp, fl_owner_t id) { struct mqueue_inode_info *info = MQUEUE_I(filp->f_dentry->d_inode); -- cgit v1.2.3-70-g09d2