From db71922217a214e5c9268448e537b54fc1f301ea Mon Sep 17 00:00:00 2001 From: Jan Blunck Date: Sun, 15 Aug 2010 22:51:10 +0200 Subject: BKL: Explicitly add BKL around get_sb/fill_super This patch is a preparation necessary to remove the BKL from do_new_mount(). It explicitly adds calls to lock_kernel()/unlock_kernel() around get_sb/fill_super operations for filesystems that still uses the BKL. I've read through all the code formerly covered by the BKL inside do_kern_mount() and have satisfied myself that it doesn't need the BKL any more. do_kern_mount() is already called without the BKL when mounting the rootfs and in nfsctl. do_kern_mount() calls vfs_kern_mount(), which is called from various places without BKL: simple_pin_fs(), nfs_do_clone_mount() through nfs_follow_mountpoint(), afs_mntpt_do_automount() through afs_mntpt_follow_link(). Both later functions are actually the filesystems follow_link inode operation. vfs_kern_mount() is calling the specified get_sb function and lets the filesystem do its job by calling the given fill_super function. Therefore I think it is safe to push down the BKL from the VFS to the low-level filesystems get_sb/fill_super operation. [arnd: do not add the BKL to those file systems that already don't use it elsewhere] Signed-off-by: Jan Blunck Signed-off-by: Arnd Bergmann Cc: Matthew Wilcox Cc: Christoph Hellwig --- fs/cifs/cifsfs.c | 12 ++++++++++-- 1 file changed, 10 insertions(+), 2 deletions(-) (limited to 'fs/cifs') diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index b7431afdd76d..070bf1aecd2d 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -514,22 +514,30 @@ cifs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt) { int rc; - struct super_block *sb = sget(fs_type, NULL, set_anon_super, NULL); + struct super_block *sb; + + lock_kernel(); + + sb = sget(fs_type, NULL, set_anon_super, NULL); cFYI(1, "Devname: %s flags: %d ", dev_name, flags); - if (IS_ERR(sb)) + if (IS_ERR(sb)) { + unlock_kernel(); return PTR_ERR(sb); + } sb->s_flags = flags; rc = cifs_read_super(sb, data, dev_name, flags & MS_SILENT ? 1 : 0); if (rc) { deactivate_locked_super(sb); + unlock_kernel(); return rc; } sb->s_flags |= MS_ACTIVE; simple_set_mnt(mnt, sb); + unlock_kernel(); return 0; } -- cgit v1.2.3 From b0991aa324b57dca8feef75ed75b24080ee4a9fc Mon Sep 17 00:00:00 2001 From: Jan Blunck Date: Wed, 24 Feb 2010 13:25:29 +0100 Subject: BKL: Remove BKL from CifsFS The BKL is only used in put_super and fill_super that are both protected by the superblocks s_umount rw_semaphore. Therefore it is safe to remove the BKL entirely. Signed-off-by: Jan Blunck Cc: Steve French Signed-off-by: Arnd Bergmann --- fs/cifs/cifsfs.c | 13 +------------ 1 file changed, 1 insertion(+), 12 deletions(-) (limited to 'fs/cifs') diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 070bf1aecd2d..4e273f7793f6 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -35,7 +35,6 @@ #include #include #include -#include #include "cifsfs.h" #include "cifspdu.h" #define DECLARE_GLOBALS_HERE @@ -200,8 +199,6 @@ cifs_put_super(struct super_block *sb) return; } - lock_kernel(); - rc = cifs_umount(sb, cifs_sb); if (rc) cERROR(1, "cifs_umount failed with return code %d", rc); @@ -215,8 +212,6 @@ cifs_put_super(struct super_block *sb) unload_nls(cifs_sb->local_nls); bdi_destroy(&cifs_sb->bdi); kfree(cifs_sb); - - unlock_kernel(); } static int @@ -516,28 +511,22 @@ cifs_get_sb(struct file_system_type *fs_type, int rc; struct super_block *sb; - lock_kernel(); - sb = sget(fs_type, NULL, set_anon_super, NULL); cFYI(1, "Devname: %s flags: %d ", dev_name, flags); - if (IS_ERR(sb)) { - unlock_kernel(); + if (IS_ERR(sb)) return PTR_ERR(sb); - } sb->s_flags = flags; rc = cifs_read_super(sb, data, dev_name, flags & MS_SILENT ? 1 : 0); if (rc) { deactivate_locked_super(sb); - unlock_kernel(); return rc; } sb->s_flags |= MS_ACTIVE; simple_set_mnt(mnt, sb); - unlock_kernel(); return 0; } -- cgit v1.2.3 From b89f432133851a01c0d28822f11cbdcc15781a75 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Sat, 18 Sep 2010 15:09:31 +0200 Subject: fs/locks.c: prepare for BKL removal This prepares the removal of the big kernel lock from the file locking code. We still use the BKL as long as fs/lockd uses it and ceph might sleep, but we can flip the definition to a private spinlock as soon as that's done. All users outside of fs/lockd get converted to use lock_flocks() instead of lock_kernel() where appropriate. Based on an earlier patch to use a spinlock from Matthew Wilcox, who has attempted this a few times before, the earliest patch from over 10 years ago turned it into a semaphore, which ended up being slower than the BKL and was subsequently reverted. Someone should do some serious performance testing when this becomes a spinlock, since this has caused problems before. Using a spinlock should be at least as good as the BKL in theory, but who knows... Signed-off-by: Arnd Bergmann Acked-by: Matthew Wilcox Cc: Christoph Hellwig Cc: Trond Myklebust Cc: "J. Bruce Fields" Cc: Andrew Morton Cc: Miklos Szeredi Cc: Frederic Weisbecker Cc: Ingo Molnar Cc: John Kacur Cc: Sage Weil Cc: linux-kernel@vger.kernel.org Cc: linux-fsdevel@vger.kernel.org --- fs/afs/flock.c | 5 +-- fs/cifs/cifsfs.c | 4 +- fs/gfs2/file.c | 2 + fs/locks.c | 112 +++++++++++++++++++++++++++++++--------------------- fs/nfs/delegation.c | 10 ++--- fs/nfs/nfs4state.c | 10 ++--- fs/nfsd/nfs4state.c | 6 +-- include/linux/fs.h | 14 +++++-- 8 files changed, 97 insertions(+), 66 deletions(-) (limited to 'fs/cifs') diff --git a/fs/afs/flock.c b/fs/afs/flock.c index 0931bc1325eb..757d664575dd 100644 --- a/fs/afs/flock.c +++ b/fs/afs/flock.c @@ -9,7 +9,6 @@ * 2 of the License, or (at your option) any later version. */ -#include #include "internal.h" #define AFS_LOCK_GRANTED 0 @@ -274,7 +273,7 @@ static int afs_do_setlk(struct file *file, struct file_lock *fl) type = (fl->fl_type == F_RDLCK) ? AFS_LOCK_READ : AFS_LOCK_WRITE; - lock_kernel(); + lock_flocks(); /* make sure we've got a callback on this file and that our view of the * data version is up to date */ @@ -421,7 +420,7 @@ given_lock: afs_vnode_fetch_status(vnode, NULL, key); error: - unlock_kernel(); + unlock_flocks(); _leave(" = %d", ret); return ret; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index 4e273f7793f6..50208c15309a 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -562,8 +562,8 @@ static loff_t cifs_llseek(struct file *file, loff_t offset, int origin) static int cifs_setlease(struct file *file, long arg, struct file_lock **lease) { - /* note that this is called by vfs setlease with the BKL held - although I doubt that BKL is needed here in cifs */ + /* note that this is called by vfs setlease with lock_flocks held + to protect *lease from going away */ struct inode *inode = file->f_path.dentry->d_inode; if (!(S_ISREG(inode->i_mode))) diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c index 4edd662c8232..8fcfefb96077 100644 --- a/fs/gfs2/file.c +++ b/fs/gfs2/file.c @@ -620,6 +620,8 @@ static ssize_t gfs2_file_aio_write(struct kiocb *iocb, const struct iovec *iov, * cluster; until we do, disable leases (by just returning -EINVAL), * unless the administrator has requested purely local locking. * + * Locking: called under lock_flocks + * * Returns: errno */ diff --git a/fs/locks.c b/fs/locks.c index ab24d49fc048..8b2b6ad56a09 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -143,6 +143,22 @@ int lease_break_time = 45; static LIST_HEAD(file_lock_list); static LIST_HEAD(blocked_list); +/* + * Protects the two list heads above, plus the inode->i_flock list + * FIXME: should use a spinlock, once lockd and ceph are ready. + */ +void lock_flocks(void) +{ + lock_kernel(); +} +EXPORT_SYMBOL_GPL(lock_flocks); + +void unlock_flocks(void) +{ + unlock_kernel(); +} +EXPORT_SYMBOL_GPL(unlock_flocks); + static struct kmem_cache *filelock_cache __read_mostly; /* Allocate an empty lock structure. */ @@ -511,9 +527,9 @@ static void __locks_delete_block(struct file_lock *waiter) */ static void locks_delete_block(struct file_lock *waiter) { - lock_kernel(); + lock_flocks(); __locks_delete_block(waiter); - unlock_kernel(); + unlock_flocks(); } /* Insert waiter into blocker's block list. @@ -644,7 +660,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; - lock_kernel(); + lock_flocks(); for (cfl = filp->f_path.dentry->d_inode->i_flock; cfl; cfl = cfl->fl_next) { if (!IS_POSIX(cfl)) continue; @@ -657,7 +673,7 @@ posix_test_lock(struct file *filp, struct file_lock *fl) fl->fl_pid = pid_vnr(cfl->fl_nspid); } else fl->fl_type = F_UNLCK; - unlock_kernel(); + unlock_flocks(); return; } EXPORT_SYMBOL(posix_test_lock); @@ -730,18 +746,16 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) int error = 0; int found = 0; - lock_kernel(); - if (request->fl_flags & FL_ACCESS) - goto find_conflict; - - if (request->fl_type != F_UNLCK) { - error = -ENOMEM; + if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) { new_fl = locks_alloc_lock(); - if (new_fl == NULL) - goto out; - error = 0; + if (!new_fl) + return -ENOMEM; } + lock_flocks(); + if (request->fl_flags & FL_ACCESS) + goto find_conflict; + for_each_lock(inode, before) { struct file_lock *fl = *before; if (IS_POSIX(fl)) @@ -767,8 +781,11 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) * If a higher-priority process was blocked on the old file lock, * give it the opportunity to lock the file. */ - if (found) + if (found) { + unlock_flocks(); cond_resched(); + lock_flocks(); + } find_conflict: for_each_lock(inode, before) { @@ -794,7 +811,7 @@ find_conflict: error = 0; out: - unlock_kernel(); + unlock_flocks(); if (new_fl) locks_free_lock(new_fl); return error; @@ -823,7 +840,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str new_fl2 = locks_alloc_lock(); } - lock_kernel(); + lock_flocks(); if (request->fl_type != F_UNLCK) { for_each_lock(inode, before) { fl = *before; @@ -991,7 +1008,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_wake_up_blocks(left); } out: - unlock_kernel(); + unlock_flocks(); /* * Free any unused locks. */ @@ -1066,14 +1083,14 @@ int locks_mandatory_locked(struct inode *inode) /* * Search the lock list for this inode for any POSIX locks. */ - lock_kernel(); + lock_flocks(); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { if (!IS_POSIX(fl)) continue; if (fl->fl_owner != owner) break; } - unlock_kernel(); + unlock_flocks(); return fl ? -EAGAIN : 0; } @@ -1186,7 +1203,7 @@ int __break_lease(struct inode *inode, unsigned int mode) new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK); - lock_kernel(); + lock_flocks(); time_out_leases(inode); @@ -1247,8 +1264,10 @@ restart: break_time++; } locks_insert_block(flock, new_fl); + unlock_flocks(); error = wait_event_interruptible_timeout(new_fl->fl_wait, !new_fl->fl_next, break_time); + lock_flocks(); __locks_delete_block(new_fl); if (error >= 0) { if (error == 0) @@ -1263,7 +1282,7 @@ restart: } out: - unlock_kernel(); + unlock_flocks(); if (!IS_ERR(new_fl)) locks_free_lock(new_fl); return error; @@ -1319,7 +1338,7 @@ int fcntl_getlease(struct file *filp) struct file_lock *fl; int type = F_UNLCK; - lock_kernel(); + lock_flocks(); time_out_leases(filp->f_path.dentry->d_inode); for (fl = filp->f_path.dentry->d_inode->i_flock; fl && IS_LEASE(fl); fl = fl->fl_next) { @@ -1328,7 +1347,7 @@ int fcntl_getlease(struct file *filp) break; } } - unlock_kernel(); + unlock_flocks(); return type; } @@ -1341,7 +1360,7 @@ int fcntl_getlease(struct file *filp) * The (input) flp->fl_lmops->fl_break function is required * by break_lease(). * - * Called with kernel lock held. + * Called with file_lock_lock held. */ int generic_setlease(struct file *filp, long arg, struct file_lock **flp) { @@ -1436,7 +1455,15 @@ out: } EXPORT_SYMBOL(generic_setlease); - /** +static int __vfs_setlease(struct file *filp, long arg, struct file_lock **lease) +{ + if (filp->f_op && filp->f_op->setlease) + return filp->f_op->setlease(filp, arg, lease); + else + return generic_setlease(filp, arg, lease); +} + +/** * vfs_setlease - sets a lease on an open file * @filp: file pointer * @arg: type of lease to obtain @@ -1467,12 +1494,9 @@ int vfs_setlease(struct file *filp, long arg, struct file_lock **lease) { int error; - lock_kernel(); - if (filp->f_op && filp->f_op->setlease) - error = filp->f_op->setlease(filp, arg, lease); - else - error = generic_setlease(filp, arg, lease); - unlock_kernel(); + lock_flocks(); + error = __vfs_setlease(filp, arg, lease); + unlock_flocks(); return error; } @@ -1499,9 +1523,9 @@ int fcntl_setlease(unsigned int fd, struct file *filp, long arg) if (error) return error; - lock_kernel(); + lock_flocks(); - error = vfs_setlease(filp, arg, &flp); + error = __vfs_setlease(filp, arg, &flp); if (error || arg == F_UNLCK) goto out_unlock; @@ -1516,7 +1540,7 @@ int fcntl_setlease(unsigned int fd, struct file *filp, long arg) error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0); out_unlock: - unlock_kernel(); + unlock_flocks(); return error; } @@ -2020,7 +2044,7 @@ void locks_remove_flock(struct file *filp) fl.fl_ops->fl_release_private(&fl); } - lock_kernel(); + lock_flocks(); before = &inode->i_flock; while ((fl = *before) != NULL) { @@ -2038,7 +2062,7 @@ void locks_remove_flock(struct file *filp) } before = &fl->fl_next; } - unlock_kernel(); + unlock_flocks(); } /** @@ -2053,12 +2077,12 @@ posix_unblock_lock(struct file *filp, struct file_lock *waiter) { int status = 0; - lock_kernel(); + lock_flocks(); if (waiter->fl_next) __locks_delete_block(waiter); else status = -ENOENT; - unlock_kernel(); + unlock_flocks(); return status; } @@ -2172,7 +2196,7 @@ static int locks_show(struct seq_file *f, void *v) static void *locks_start(struct seq_file *f, loff_t *pos) { - lock_kernel(); + lock_flocks(); f->private = (void *)1; return seq_list_start(&file_lock_list, *pos); } @@ -2184,7 +2208,7 @@ static void *locks_next(struct seq_file *f, void *v, loff_t *pos) static void locks_stop(struct seq_file *f, void *v) { - unlock_kernel(); + unlock_flocks(); } static const struct seq_operations locks_seq_operations = { @@ -2231,7 +2255,7 @@ int lock_may_read(struct inode *inode, loff_t start, unsigned long len) { struct file_lock *fl; int result = 1; - lock_kernel(); + lock_flocks(); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { if (IS_POSIX(fl)) { if (fl->fl_type == F_RDLCK) @@ -2248,7 +2272,7 @@ int lock_may_read(struct inode *inode, loff_t start, unsigned long len) result = 0; break; } - unlock_kernel(); + unlock_flocks(); return result; } @@ -2271,7 +2295,7 @@ int lock_may_write(struct inode *inode, loff_t start, unsigned long len) { struct file_lock *fl; int result = 1; - lock_kernel(); + lock_flocks(); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { if (IS_POSIX(fl)) { if ((fl->fl_end < start) || (fl->fl_start > (start + len))) @@ -2286,7 +2310,7 @@ int lock_may_write(struct inode *inode, loff_t start, unsigned long len) result = 0; break; } - unlock_kernel(); + unlock_flocks(); return result; } diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index b9c3c43cea1d..232a7eead33a 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -71,20 +71,20 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ if (inode->i_flock == NULL) goto out; - /* Protect inode->i_flock using the BKL */ - lock_kernel(); + /* Protect inode->i_flock using the file locks lock */ + lock_flocks(); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) continue; if (nfs_file_open_context(fl->fl_file) != ctx) continue; - unlock_kernel(); + unlock_flocks(); status = nfs4_lock_delegation_recall(state, fl); if (status < 0) goto out; - lock_kernel(); + lock_flocks(); } - unlock_kernel(); + unlock_flocks(); out: return status; } diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 3e2f19b04c06..96524c5dca6b 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -40,7 +40,7 @@ #include #include -#include +#include #include #include #include @@ -970,13 +970,13 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ /* Guard against delegation returns and new lock/unlock calls */ down_write(&nfsi->rwsem); /* Protect inode->i_flock using the BKL */ - lock_kernel(); + lock_flocks(); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) continue; if (nfs_file_open_context(fl->fl_file)->state != state) continue; - unlock_kernel(); + unlock_flocks(); status = ops->recover_lock(state, fl); switch (status) { case 0: @@ -1003,9 +1003,9 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ /* kill_proc(fl->fl_pid, SIGLOST, 1); */ status = 0; } - lock_kernel(); + lock_flocks(); } - unlock_kernel(); + unlock_flocks(); out: up_write(&nfsi->rwsem); return status; diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index cf0d2ffb3c84..a7292fcf7718 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -33,7 +33,7 @@ */ #include -#include +#include #include #include #include @@ -3895,7 +3895,7 @@ check_for_locks(struct nfs4_file *filp, struct nfs4_stateowner *lowner) struct inode *inode = filp->fi_inode; int status = 0; - lock_kernel(); + lock_flocks(); for (flpp = &inode->i_flock; *flpp != NULL; flpp = &(*flpp)->fl_next) { if ((*flpp)->fl_owner == (fl_owner_t)lowner) { status = 1; @@ -3903,7 +3903,7 @@ check_for_locks(struct nfs4_file *filp, struct nfs4_stateowner *lowner) } } out: - unlock_kernel(); + unlock_flocks(); return status; } diff --git a/include/linux/fs.h b/include/linux/fs.h index 63d069bd80b7..180325268237 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1093,10 +1093,6 @@ struct file_lock { #include -/* temporary stubs for BKL removal */ -#define lock_flocks() lock_kernel() -#define unlock_flocks() unlock_kernel() - extern void send_sigio(struct fown_struct *fown, int fd, int band); #ifdef CONFIG_FILE_LOCKING @@ -1135,6 +1131,8 @@ extern int vfs_setlease(struct file *, long, struct file_lock **); extern int lease_modify(struct file_lock **, int); extern int lock_may_read(struct inode *, loff_t start, unsigned long count); extern int lock_may_write(struct inode *, loff_t start, unsigned long count); +extern void lock_flocks(void); +extern void unlock_flocks(void); #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, struct flock __user *user) { @@ -1277,6 +1275,14 @@ static inline int lock_may_write(struct inode *inode, loff_t start, return 1; } +static inline void lock_flocks(void) +{ +} + +static inline void unlock_flocks(void) +{ +} + #endif /* !CONFIG_FILE_LOCKING */ -- cgit v1.2.3