diff options
Diffstat (limited to 'fs/locks.c')
| -rw-r--r-- | fs/locks.c | 1182 |
1 files changed, 748 insertions, 434 deletions
diff --git a/fs/locks.c b/fs/locks.c index 0e62dd35d08..717fbc404e6 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -60,7 +60,7 @@ * * Initial implementation of mandatory locks. SunOS turned out to be * a rotten model, so I implemented the "obvious" semantics. - * See 'Documentation/mandatory.txt' for details. + * See 'Documentation/filesystems/mandatory-locking.txt' for details. * Andy Walker (andy@lysaker.kvaerner.no), April 06, 1996. * * Don't allow mandatory locks on mmap()'ed files. Added simple functions to @@ -122,17 +122,37 @@ #include <linux/module.h> #include <linux/security.h> #include <linux/slab.h> -#include <linux/smp_lock.h> #include <linux/syscalls.h> #include <linux/time.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> +#include <linux/hashtable.h> +#include <linux/percpu.h> +#include <linux/lglock.h> + +#define CREATE_TRACE_POINTS +#include <trace/events/filelock.h> #include <asm/uaccess.h> #define IS_POSIX(fl) (fl->fl_flags & FL_POSIX) #define IS_FLOCK(fl) (fl->fl_flags & FL_FLOCK) -#define IS_LEASE(fl) (fl->fl_flags & FL_LEASE) +#define IS_LEASE(fl) (fl->fl_flags & (FL_LEASE|FL_DELEG)) +#define IS_OFDLCK(fl) (fl->fl_flags & FL_OFDLCK) + +static bool lease_breaking(struct file_lock *fl) +{ + return fl->fl_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING); +} + +static int target_leasetype(struct file_lock *fl) +{ + if (fl->fl_flags & FL_UNLOCK_PENDING) + return F_UNLCK; + if (fl->fl_flags & FL_DOWNGRADE_PENDING) + return F_RDLCK; + return fl->fl_type; +} int leases_enable = 1; int lease_break_time = 45; @@ -140,32 +160,66 @@ int lease_break_time = 45; #define for_each_lock(inode, lockp) \ for (lockp = &inode->i_flock; *lockp != NULL; lockp = &(*lockp)->fl_next) -static LIST_HEAD(file_lock_list); -static LIST_HEAD(blocked_list); -static DEFINE_SPINLOCK(file_lock_lock); +/* + * The global file_lock_list is only used for displaying /proc/locks, so we + * keep a list on each CPU, with each list protected by its own spinlock via + * the file_lock_lglock. Note that alterations to the list also require that + * the relevant i_lock is held. + */ +DEFINE_STATIC_LGLOCK(file_lock_lglock); +static DEFINE_PER_CPU(struct hlist_head, file_lock_list); /* - * Protects the two list heads above, plus the inode->i_flock list - * FIXME: should use a spinlock, once lockd and ceph are ready. + * The blocked_hash is used to find POSIX lock loops for deadlock detection. + * It is protected by blocked_lock_lock. + * + * We hash locks by lockowner in order to optimize searching for the lock a + * particular lockowner is waiting on. + * + * FIXME: make this value scale via some heuristic? We generally will want more + * buckets when we have more lockowners holding locks, but that's a little + * difficult to determine without knowing what the workload will look like. */ -void lock_flocks(void) -{ - spin_lock(&file_lock_lock); -} -EXPORT_SYMBOL_GPL(lock_flocks); +#define BLOCKED_HASH_BITS 7 +static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); -void unlock_flocks(void) -{ - spin_unlock(&file_lock_lock); -} -EXPORT_SYMBOL_GPL(unlock_flocks); +/* + * This lock protects the blocked_hash. Generally, if you're accessing it, you + * want to be holding this lock. + * + * In addition, it also protects the fl->fl_block list, and the fl->fl_next + * pointer for file_lock structures that are acting as lock requests (in + * contrast to those that are acting as records of acquired locks). + * + * Note that when we acquire this lock in order to change the above fields, + * we often hold the i_lock as well. In certain cases, when reading the fields + * protected by this lock, we can skip acquiring it iff we already hold the + * i_lock. + * + * In particular, adding an entry to the fl_block list requires that you hold + * both the i_lock and the blocked_lock_lock (acquired in that order). Deleting + * an entry from the list however only requires the file_lock_lock. + */ +static DEFINE_SPINLOCK(blocked_lock_lock); static struct kmem_cache *filelock_cache __read_mostly; +static void locks_init_lock_heads(struct file_lock *fl) +{ + INIT_HLIST_NODE(&fl->fl_link); + INIT_LIST_HEAD(&fl->fl_block); + init_waitqueue_head(&fl->fl_wait); +} + /* Allocate an empty lock structure. */ struct file_lock *locks_alloc_lock(void) { - return kmem_cache_alloc(filelock_cache, GFP_KERNEL); + struct file_lock *fl = kmem_cache_zalloc(filelock_cache, GFP_KERNEL); + + if (fl) + locks_init_lock_heads(fl); + + return fl; } EXPORT_SYMBOL_GPL(locks_alloc_lock); @@ -176,11 +230,7 @@ void locks_release_private(struct file_lock *fl) fl->fl_ops->fl_release_private(fl); fl->fl_ops = NULL; } - if (fl->fl_lmops) { - if (fl->fl_lmops->fl_release_private) - fl->fl_lmops->fl_release_private(fl); - fl->fl_lmops = NULL; - } + fl->fl_lmops = NULL; } EXPORT_SYMBOL_GPL(locks_release_private); @@ -190,7 +240,7 @@ void locks_free_lock(struct file_lock *fl) { BUG_ON(waitqueue_active(&fl->fl_wait)); BUG_ON(!list_empty(&fl->fl_block)); - BUG_ON(!list_empty(&fl->fl_link)); + BUG_ON(!hlist_unhashed(&fl->fl_link)); locks_release_private(fl); kmem_cache_free(filelock_cache, fl); @@ -199,35 +249,12 @@ EXPORT_SYMBOL(locks_free_lock); void locks_init_lock(struct file_lock *fl) { - INIT_LIST_HEAD(&fl->fl_link); - INIT_LIST_HEAD(&fl->fl_block); - init_waitqueue_head(&fl->fl_wait); - fl->fl_next = NULL; - fl->fl_fasync = NULL; - fl->fl_owner = NULL; - fl->fl_pid = 0; - fl->fl_nspid = NULL; - fl->fl_file = NULL; - fl->fl_flags = 0; - fl->fl_type = 0; - fl->fl_start = fl->fl_end = 0; - fl->fl_ops = NULL; - fl->fl_lmops = NULL; + memset(fl, 0, sizeof(struct file_lock)); + locks_init_lock_heads(fl); } EXPORT_SYMBOL(locks_init_lock); -/* - * Initialises the fields of the file lock which are invariant for - * free file_locks. - */ -static void init_once(void *foo) -{ - struct file_lock *lock = (struct file_lock *) foo; - - locks_init_lock(lock); -} - static void locks_copy_private(struct file_lock *new, struct file_lock *fl) { if (fl->fl_ops) { @@ -298,6 +325,7 @@ static int flock_make_lock(struct file *filp, struct file_lock **lock, return -ENOMEM; fl->fl_file = filp; + fl->fl_owner = (fl_owner_t)filp; fl->fl_pid = current->tgid; fl->fl_flags = FL_FLOCK; fl->fl_type = type; @@ -307,7 +335,7 @@ static int flock_make_lock(struct file *filp, struct file_lock **lock, return 0; } -static int assign_type(struct file_lock *fl, int type) +static int assign_type(struct file_lock *fl, long type) { switch (type) { case F_RDLCK: @@ -321,48 +349,43 @@ static int assign_type(struct file_lock *fl, int type) return 0; } -/* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX - * style lock. - */ -static int flock_to_posix_lock(struct file *filp, struct file_lock *fl, - struct flock *l) +static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl, + struct flock64 *l) { - off_t start, end; - switch (l->l_whence) { case SEEK_SET: - start = 0; + fl->fl_start = 0; break; case SEEK_CUR: - start = filp->f_pos; + fl->fl_start = filp->f_pos; break; case SEEK_END: - start = i_size_read(filp->f_path.dentry->d_inode); + fl->fl_start = i_size_read(file_inode(filp)); break; default: return -EINVAL; } + if (l->l_start > OFFSET_MAX - fl->fl_start) + return -EOVERFLOW; + fl->fl_start += l->l_start; + if (fl->fl_start < 0) + return -EINVAL; /* POSIX-1996 leaves the case l->l_len < 0 undefined; POSIX-2001 defines it. */ - start += l->l_start; - if (start < 0) - return -EINVAL; - fl->fl_end = OFFSET_MAX; if (l->l_len > 0) { - end = start + l->l_len - 1; - fl->fl_end = end; + if (l->l_len - 1 > OFFSET_MAX - fl->fl_start) + return -EOVERFLOW; + fl->fl_end = fl->fl_start + l->l_len - 1; + } else if (l->l_len < 0) { - end = start - 1; - fl->fl_end = end; - start += l->l_len; - if (start < 0) + if (fl->fl_start + l->l_len < 0) return -EINVAL; - } - fl->fl_start = start; /* we record the absolute position */ - if (fl->fl_end < fl->fl_start) - return -EOVERFLOW; - + fl->fl_end = fl->fl_start - 1; + fl->fl_start += l->l_len; + } else + fl->fl_end = OFFSET_MAX; + fl->fl_owner = current->files; fl->fl_pid = current->tgid; fl->fl_file = filp; @@ -373,62 +396,21 @@ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl, return assign_type(fl, l->l_type); } -#if BITS_PER_LONG == 32 -static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl, - struct flock64 *l) +/* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX + * style lock. + */ +static int flock_to_posix_lock(struct file *filp, struct file_lock *fl, + struct flock *l) { - loff_t start; + struct flock64 ll = { + .l_type = l->l_type, + .l_whence = l->l_whence, + .l_start = l->l_start, + .l_len = l->l_len, + }; - switch (l->l_whence) { - case SEEK_SET: - start = 0; - break; - case SEEK_CUR: - start = filp->f_pos; - break; - case SEEK_END: - start = i_size_read(filp->f_path.dentry->d_inode); - break; - default: - return -EINVAL; - } - - start += l->l_start; - if (start < 0) - return -EINVAL; - fl->fl_end = OFFSET_MAX; - if (l->l_len > 0) { - fl->fl_end = start + l->l_len - 1; - } else if (l->l_len < 0) { - fl->fl_end = start - 1; - start += l->l_len; - if (start < 0) - return -EINVAL; - } - fl->fl_start = start; /* we record the absolute position */ - if (fl->fl_end < fl->fl_start) - return -EOVERFLOW; - - fl->fl_owner = current->files; - fl->fl_pid = current->tgid; - fl->fl_file = filp; - fl->fl_flags = FL_POSIX; - fl->fl_ops = NULL; - fl->fl_lmops = NULL; - - switch (l->l_type) { - case F_RDLCK: - case F_WRLCK: - case F_UNLCK: - fl->fl_type = l->l_type; - break; - default: - return -EINVAL; - } - - return (0); + return flock64_to_posix_lock(filp, fl, &ll); } -#endif /* default lease lock manager operations */ static void lease_break_callback(struct file_lock *fl) @@ -436,36 +418,20 @@ static void lease_break_callback(struct file_lock *fl) kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG); } -static void lease_release_private_callback(struct file_lock *fl) -{ - if (!fl->fl_file) - return; - - f_delown(fl->fl_file); - fl->fl_file->f_owner.signum = 0; -} - -static int lease_mylease_callback(struct file_lock *fl, struct file_lock *try) -{ - return fl->fl_file == try->fl_file; -} - static const struct lock_manager_operations lease_manager_ops = { - .fl_break = lease_break_callback, - .fl_release_private = lease_release_private_callback, - .fl_mylease = lease_mylease_callback, - .fl_change = lease_modify, + .lm_break = lease_break_callback, + .lm_change = lease_modify, }; /* * Initialize a lease, use the default lock manager operations */ -static int lease_init(struct file *filp, int type, struct file_lock *fl) +static int lease_init(struct file *filp, long type, struct file_lock *fl) { if (assign_type(fl, type) != 0) return -EINVAL; - fl->fl_owner = current->files; + fl->fl_owner = (fl_owner_t)current->files; fl->fl_pid = current->tgid; fl->fl_file = filp; @@ -478,7 +444,7 @@ static int lease_init(struct file *filp, int type, struct file_lock *fl) } /* Allocate a file_lock initialised to this type of lease */ -static struct file_lock *lease_alloc(struct file *filp, int type) +static struct file_lock *lease_alloc(struct file *filp, long type) { struct file_lock *fl = locks_alloc_lock(); int error = -ENOMEM; @@ -507,98 +473,169 @@ static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2) */ static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2) { - if (fl1->fl_lmops && fl1->fl_lmops->fl_compare_owner) + if (fl1->fl_lmops && fl1->fl_lmops->lm_compare_owner) return fl2->fl_lmops == fl1->fl_lmops && - fl1->fl_lmops->fl_compare_owner(fl1, fl2); + fl1->fl_lmops->lm_compare_owner(fl1, fl2); return fl1->fl_owner == fl2->fl_owner; } +/* Must be called with the i_lock held! */ +static void locks_insert_global_locks(struct file_lock *fl) +{ + lg_local_lock(&file_lock_lglock); + fl->fl_link_cpu = smp_processor_id(); + hlist_add_head(&fl->fl_link, this_cpu_ptr(&file_lock_list)); + lg_local_unlock(&file_lock_lglock); +} + +/* Must be called with the i_lock held! */ +static void locks_delete_global_locks(struct file_lock *fl) +{ + /* + * Avoid taking lock if already unhashed. This is safe since this check + * is done while holding the i_lock, and new insertions into the list + * also require that it be held. + */ + if (hlist_unhashed(&fl->fl_link)) + return; + lg_local_lock_cpu(&file_lock_lglock, fl->fl_link_cpu); + hlist_del_init(&fl->fl_link); + lg_local_unlock_cpu(&file_lock_lglock, fl->fl_link_cpu); +} + +static unsigned long +posix_owner_key(struct file_lock *fl) +{ + if (fl->fl_lmops && fl->fl_lmops->lm_owner_key) + return fl->fl_lmops->lm_owner_key(fl); + return (unsigned long)fl->fl_owner; +} + +static void locks_insert_global_blocked(struct file_lock *waiter) +{ + hash_add(blocked_hash, &waiter->fl_link, posix_owner_key(waiter)); +} + +static void locks_delete_global_blocked(struct file_lock *waiter) +{ + hash_del(&waiter->fl_link); +} + /* Remove waiter from blocker's block list. * When blocker ends up pointing to itself then the list is empty. + * + * Must be called with blocked_lock_lock held. */ static void __locks_delete_block(struct file_lock *waiter) { + locks_delete_global_blocked(waiter); list_del_init(&waiter->fl_block); - list_del_init(&waiter->fl_link); waiter->fl_next = NULL; } -/* - */ static void locks_delete_block(struct file_lock *waiter) { - lock_flocks(); + spin_lock(&blocked_lock_lock); __locks_delete_block(waiter); - unlock_flocks(); + spin_unlock(&blocked_lock_lock); } /* Insert waiter into blocker's block list. * We use a circular list so that processes can be easily woken up in * the order they blocked. The documentation doesn't require this but * it seems like the reasonable thing to do. + * + * Must be called with both the i_lock and blocked_lock_lock held. The fl_block + * list itself is protected by the blocked_lock_lock, but by ensuring that the + * i_lock is also held on insertions we can avoid taking the blocked_lock_lock + * in some cases when we see that the fl_block list is empty. */ -static void locks_insert_block(struct file_lock *blocker, - struct file_lock *waiter) +static void __locks_insert_block(struct file_lock *blocker, + struct file_lock *waiter) { BUG_ON(!list_empty(&waiter->fl_block)); - list_add_tail(&waiter->fl_block, &blocker->fl_block); waiter->fl_next = blocker; - if (IS_POSIX(blocker)) - list_add(&waiter->fl_link, &blocked_list); + list_add_tail(&waiter->fl_block, &blocker->fl_block); + if (IS_POSIX(blocker) && !IS_OFDLCK(blocker)) + locks_insert_global_blocked(waiter); +} + +/* Must be called with i_lock held. */ +static void locks_insert_block(struct file_lock *blocker, + struct file_lock *waiter) +{ + spin_lock(&blocked_lock_lock); + __locks_insert_block(blocker, waiter); + spin_unlock(&blocked_lock_lock); } -/* Wake up processes blocked waiting for blocker. - * If told to wait then schedule the processes until the block list - * is empty, otherwise empty the block list ourselves. +/* + * Wake up processes blocked waiting for blocker. + * + * Must be called with the inode->i_lock held! */ static void locks_wake_up_blocks(struct file_lock *blocker) { + /* + * Avoid taking global lock if list is empty. This is safe since new + * blocked requests are only added to the list under the i_lock, and + * the i_lock is always held here. Note that removal from the fl_block + * list does not require the i_lock, so we must recheck list_empty() + * after acquiring the blocked_lock_lock. + */ + if (list_empty(&blocker->fl_block)) + return; + + spin_lock(&blocked_lock_lock); while (!list_empty(&blocker->fl_block)) { struct file_lock *waiter; waiter = list_first_entry(&blocker->fl_block, struct file_lock, fl_block); __locks_delete_block(waiter); - if (waiter->fl_lmops && waiter->fl_lmops->fl_notify) - waiter->fl_lmops->fl_notify(waiter); + if (waiter->fl_lmops && waiter->fl_lmops->lm_notify) + waiter->fl_lmops->lm_notify(waiter); else wake_up(&waiter->fl_wait); } + spin_unlock(&blocked_lock_lock); } /* Insert file lock fl into an inode's lock list at the position indicated * by pos. At the same time add the lock to the global file lock list. + * + * Must be called with the i_lock held! */ static void locks_insert_lock(struct file_lock **pos, struct file_lock *fl) { - list_add(&fl->fl_link, &file_lock_list); - fl->fl_nspid = get_pid(task_tgid(current)); /* insert into file's list */ fl->fl_next = *pos; *pos = fl; + + locks_insert_global_locks(fl); } -/* - * Delete a lock and then free it. - * Wake up processes that are blocked waiting for this lock, - * notify the FS that the lock has been cleared and - * finally free the lock. +/** + * locks_delete_lock - Delete a lock and then free it. + * @thisfl_p: pointer that points to the fl_next field of the previous + * inode->i_flock list entry + * + * Unlink a lock from all lists and free the namespace reference, but don't + * free it yet. Wake up processes that are blocked waiting for this lock and + * notify the FS that the lock has been cleared. + * + * Must be called with the i_lock held! */ -static void locks_delete_lock(struct file_lock **thisfl_p) +static void locks_unlink_lock(struct file_lock **thisfl_p) { struct file_lock *fl = *thisfl_p; + locks_delete_global_locks(fl); + *thisfl_p = fl->fl_next; fl->fl_next = NULL; - list_del_init(&fl->fl_link); - - fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync); - if (fl->fl_fasync != NULL) { - printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); - fl->fl_fasync = NULL; - } if (fl->fl_nspid) { put_pid(fl->fl_nspid); @@ -606,6 +643,18 @@ static void locks_delete_lock(struct file_lock **thisfl_p) } locks_wake_up_blocks(fl); +} + +/* + * Unlink a lock from all lists and free it. + * + * Must be called with i_lock held! + */ +static void locks_delete_lock(struct file_lock **thisfl_p) +{ + struct file_lock *fl = *thisfl_p; + + locks_unlink_lock(thisfl_p); locks_free_lock(fl); } @@ -659,9 +708,10 @@ void posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; + struct inode *inode = file_inode(filp); - lock_flocks(); - for (cfl = filp->f_path.dentry->d_inode->i_flock; cfl; cfl = cfl->fl_next) { + spin_lock(&inode->i_lock); + for (cfl = file_inode(filp)->i_flock; cfl; cfl = cfl->fl_next) { if (!IS_POSIX(cfl)) continue; if (posix_locks_conflict(fl, cfl)) @@ -673,7 +723,7 @@ 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_flocks(); + spin_unlock(&inode->i_lock); return; } EXPORT_SYMBOL(posix_test_lock); @@ -699,8 +749,16 @@ EXPORT_SYMBOL(posix_test_lock); * Note: the above assumption may not be true when handling lock * requests from a broken NFS client. It may also fail in the presence * of tasks (such as posix threads) sharing the same open file table. - * * To handle those cases, we just bail out after a few iterations. + * + * For FL_OFDLCK locks, the owner is the filp, not the files_struct. + * Because the owner is not even nominally tied to a thread of + * execution, the deadlock detection below can't reasonably work well. Just + * skip it for those. + * + * In principle, we could do a more limited deadlock detection on FL_OFDLCK + * locks that just checks for the case where two tasks are attempting to + * upgrade from read to write locks on the same inode. */ #define MAX_DEADLK_ITERATIONS 10 @@ -710,18 +768,26 @@ static struct file_lock *what_owner_is_waiting_for(struct file_lock *block_fl) { struct file_lock *fl; - list_for_each_entry(fl, &blocked_list, fl_link) { + hash_for_each_possible(blocked_hash, fl, fl_link, posix_owner_key(block_fl)) { if (posix_same_owner(fl, block_fl)) return fl->fl_next; } return NULL; } +/* Must be called with the blocked_lock_lock held! */ static int posix_locks_deadlock(struct file_lock *caller_fl, struct file_lock *block_fl) { int i = 0; + /* + * This deadlock detector can't reasonably detect deadlocks with + * FL_OFDLCK locks, since they aren't owned by a process, per-se. + */ + if (IS_OFDLCK(caller_fl)) + return 0; + while ((block_fl = what_owner_is_waiting_for(block_fl))) { if (i++ > MAX_DEADLK_ITERATIONS) return 0; @@ -742,7 +808,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) { struct file_lock *new_fl = NULL; struct file_lock **before; - struct inode * inode = filp->f_path.dentry->d_inode; + struct inode * inode = file_inode(filp); int error = 0; int found = 0; @@ -752,7 +818,7 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) return -ENOMEM; } - lock_flocks(); + spin_lock(&inode->i_lock); if (request->fl_flags & FL_ACCESS) goto find_conflict; @@ -782,9 +848,9 @@ static int flock_lock_file(struct file *filp, struct file_lock *request) * give it the opportunity to lock the file. */ if (found) { - unlock_flocks(); + spin_unlock(&inode->i_lock); cond_resched(); - lock_flocks(); + spin_lock(&inode->i_lock); } find_conflict: @@ -811,7 +877,7 @@ find_conflict: error = 0; out: - unlock_flocks(); + spin_unlock(&inode->i_lock); if (new_fl) locks_free_lock(new_fl); return error; @@ -825,7 +891,8 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str struct file_lock *left = NULL; struct file_lock *right = NULL; struct file_lock **before; - int error, added = 0; + int error; + bool added = false; /* * We may need two file_lock structures for this operation, @@ -840,7 +907,12 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str new_fl2 = locks_alloc_lock(); } - lock_flocks(); + spin_lock(&inode->i_lock); + /* + * New lock request. Walk all POSIX locks and look for conflicts. If + * there are any, either return error or put the request on the + * blocker's list of waiters and the global blocked_hash. + */ if (request->fl_type != F_UNLCK) { for_each_lock(inode, before) { fl = *before; @@ -853,11 +925,17 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str error = -EAGAIN; if (!(request->fl_flags & FL_SLEEP)) goto out; + /* + * Deadlock detection and insertion into the blocked + * locks list must be done while holding the same lock! + */ error = -EDEADLK; - if (posix_locks_deadlock(request, fl)) - goto out; - error = FILE_LOCK_DEFERRED; - locks_insert_block(fl, request); + spin_lock(&blocked_lock_lock); + if (likely(!posix_locks_deadlock(request, fl))) { + error = FILE_LOCK_DEFERRED; + __locks_insert_block(fl, request); + } + spin_unlock(&blocked_lock_lock); goto out; } } @@ -879,7 +957,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str before = &fl->fl_next; } - /* Process locks with this owner. */ + /* Process locks with this owner. */ while ((fl = *before) && posix_same_owner(request, fl)) { /* Detect adjacent or overlapping regions (if same lock type) */ @@ -914,7 +992,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str continue; } request = fl; - added = 1; + added = true; } else { /* Processing for different lock types is a bit @@ -925,7 +1003,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str if (fl->fl_start > request->fl_end) break; if (request->fl_type == F_UNLCK) - added = 1; + added = true; if (fl->fl_start < request->fl_start) left = fl; /* If the next lock in the list has a higher end @@ -955,7 +1033,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_release_private(fl); locks_copy_private(fl, request); request = fl; - added = 1; + added = true; } } /* Go on to next lock. @@ -965,10 +1043,9 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str } /* - * The above code only modifies existing locks in case of - * merging or replacing. If new lock(s) need to be inserted - * all modifications are done bellow this, so it's safe yet to - * bail out. + * The above code only modifies existing locks in case of merging or + * replacing. If new lock(s) need to be inserted all modifications are + * done below this, so it's safe yet to bail out. */ error = -ENOLCK; /* "no luck" */ if (right && left == right && !new_fl2) @@ -1008,7 +1085,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str locks_wake_up_blocks(left); } out: - unlock_flocks(); + spin_unlock(&inode->i_lock); /* * Free any unused locks. */ @@ -1036,7 +1113,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { - return __posix_lock_file(filp->f_path.dentry->d_inode, fl, conflock); + return __posix_lock_file(file_inode(filp), fl, conflock); } EXPORT_SYMBOL(posix_lock_file); @@ -1070,27 +1147,28 @@ EXPORT_SYMBOL(posix_lock_file_wait); /** * locks_mandatory_locked - Check for an active lock - * @inode: the file to check + * @file: the file to check * * Searches the inode's list of locks to find any POSIX locks which conflict. * This function is called from locks_verify_locked() only. */ -int locks_mandatory_locked(struct inode *inode) +int locks_mandatory_locked(struct file *file) { + struct inode *inode = file_inode(file); fl_owner_t owner = current->files; struct file_lock *fl; /* * Search the lock list for this inode for any POSIX locks. */ - lock_flocks(); + spin_lock(&inode->i_lock); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { if (!IS_POSIX(fl)) continue; - if (fl->fl_owner != owner) + if (fl->fl_owner != owner && fl->fl_owner != (fl_owner_t)file) break; } - unlock_flocks(); + spin_unlock(&inode->i_lock); return fl ? -EAGAIN : 0; } @@ -1113,19 +1191,30 @@ int locks_mandatory_area(int read_write, struct inode *inode, { struct file_lock fl; int error; + bool sleep = false; locks_init_lock(&fl); - fl.fl_owner = current->files; fl.fl_pid = current->tgid; fl.fl_file = filp; fl.fl_flags = FL_POSIX | FL_ACCESS; if (filp && !(filp->f_flags & O_NONBLOCK)) - fl.fl_flags |= FL_SLEEP; + sleep = true; fl.fl_type = (read_write == FLOCK_VERIFY_WRITE) ? F_WRLCK : F_RDLCK; fl.fl_start = offset; fl.fl_end = offset + count - 1; for (;;) { + if (filp) { + fl.fl_owner = (fl_owner_t)filp; + fl.fl_flags &= ~FL_SLEEP; + error = __posix_lock_file(inode, &fl, NULL); + if (!error) + break; + } + + if (sleep) + fl.fl_flags |= FL_SLEEP; + fl.fl_owner = current->files; error = __posix_lock_file(inode, &fl, NULL); if (error != FILE_LOCK_DEFERRED) break; @@ -1148,6 +1237,17 @@ int locks_mandatory_area(int read_write, struct inode *inode, EXPORT_SYMBOL(locks_mandatory_area); +static void lease_clear_pending(struct file_lock *fl, int arg) +{ + switch (arg) { + case F_UNLCK: + fl->fl_flags &= ~FL_UNLOCK_PENDING; + /* fall through: */ + case F_RDLCK: + fl->fl_flags &= ~FL_DOWNGRADE_PENDING; + } +} + /* We already had a lease on this file; just change its type */ int lease_modify(struct file_lock **before, int arg) { @@ -1156,54 +1256,86 @@ int lease_modify(struct file_lock **before, int arg) if (error) return error; + lease_clear_pending(fl, arg); locks_wake_up_blocks(fl); - if (arg == F_UNLCK) + if (arg == F_UNLCK) { + struct file *filp = fl->fl_file; + + f_delown(filp); + filp->f_owner.signum = 0; + fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync); + if (fl->fl_fasync != NULL) { + printk(KERN_ERR "locks_delete_lock: fasync == %p\n", fl->fl_fasync); + fl->fl_fasync = NULL; + } locks_delete_lock(before); + } return 0; } EXPORT_SYMBOL(lease_modify); +static bool past_time(unsigned long then) +{ + if (!then) + /* 0 is a special value meaning "this never expires": */ + return false; + return time_after(jiffies, then); +} + static void time_out_leases(struct inode *inode) { struct file_lock **before; struct file_lock *fl; before = &inode->i_flock; - while ((fl = *before) && IS_LEASE(fl) && (fl->fl_type & F_INPROGRESS)) { - if ((fl->fl_break_time == 0) - || time_before(jiffies, fl->fl_break_time)) { - before = &fl->fl_next; - continue; - } - lease_modify(before, fl->fl_type & ~F_INPROGRESS); + while ((fl = *before) && IS_LEASE(fl) && lease_breaking(fl)) { + trace_time_out_leases(inode, fl); + if (past_time(fl->fl_downgrade_time)) + lease_modify(before, F_RDLCK); + if (past_time(fl->fl_break_time)) + lease_modify(before, F_UNLCK); if (fl == *before) /* lease_modify may have freed fl */ before = &fl->fl_next; } } +static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker) +{ + if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE)) + return false; + return locks_conflict(breaker, lease); +} + /** * __break_lease - revoke all outstanding leases on file * @inode: the inode of the file to return - * @mode: the open mode (read or write) + * @mode: O_RDONLY: break only write leases; O_WRONLY or O_RDWR: + * break all leases + * @type: FL_LEASE: break leases and delegations; FL_DELEG: break + * only delegations * * break_lease (inlined for speed) has checked there already is at least * some kind of lock (maybe a lease) on this file. Leases are broken on * a call to open() or truncate(). This function can sleep unless you * specified %O_NONBLOCK to your open(). */ -int __break_lease(struct inode *inode, unsigned int mode) +int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { - int error = 0, future; + int error = 0; struct file_lock *new_fl, *flock; struct file_lock *fl; unsigned long break_time; int i_have_this_lease = 0; + bool lease_conflict = false; int want_write = (mode & O_ACCMODE) != O_RDONLY; new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK); + if (IS_ERR(new_fl)) + return PTR_ERR(new_fl); + new_fl->fl_flags = type; - lock_flocks(); + spin_lock(&inode->i_lock); time_out_leases(inode); @@ -1211,29 +1343,15 @@ int __break_lease(struct inode *inode, unsigned int mode) if ((flock == NULL) || !IS_LEASE(flock)) goto out; - for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) - if (fl->fl_owner == current->files) - i_have_this_lease = 1; - - if (want_write) { - /* If we want write access, we have to revoke any lease. */ - future = F_UNLCK | F_INPROGRESS; - } else if (flock->fl_type & F_INPROGRESS) { - /* If the lease is already being broken, we just leave it */ - future = flock->fl_type; - } else if (flock->fl_type & F_WRLCK) { - /* Downgrade the exclusive lease to a read-only lease. */ - future = F_RDLCK | F_INPROGRESS; - } else { - /* the existing lease was read-only, so we can read too. */ - goto out; + for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) { + if (leases_conflict(fl, new_fl)) { + lease_conflict = true; + if (fl->fl_owner == current->files) + i_have_this_lease = 1; + } } - - if (IS_ERR(new_fl) && !i_have_this_lease - && ((mode & O_NONBLOCK) == 0)) { - error = PTR_ERR(new_fl); + if (!lease_conflict) goto out; - } break_time = 0; if (lease_break_time > 0) { @@ -1243,48 +1361,60 @@ int __break_lease(struct inode *inode, unsigned int mode) } for (fl = flock; fl && IS_LEASE(fl); fl = fl->fl_next) { - if (fl->fl_type != future) { - fl->fl_type = future; + if (!leases_conflict(fl, new_fl)) + continue; + if (want_write) { + if (fl->fl_flags & FL_UNLOCK_PENDING) + continue; + fl->fl_flags |= FL_UNLOCK_PENDING; fl->fl_break_time = break_time; - /* lease must have lmops break callback */ - fl->fl_lmops->fl_break(fl); + } else { + if (lease_breaking(flock)) + continue; + fl->fl_flags |= FL_DOWNGRADE_PENDING; + fl->fl_downgrade_time = break_time; } + fl->fl_lmops->lm_break(fl); } if (i_have_this_lease || (mode & O_NONBLOCK)) { + trace_break_lease_noblock(inode, new_fl); error = -EWOULDBLOCK; goto out; } restart: break_time = flock->fl_break_time; - if (break_time != 0) { + if (break_time != 0) break_time -= jiffies; - if (break_time == 0) - break_time++; - } + if (break_time == 0) + break_time++; locks_insert_block(flock, new_fl); - unlock_flocks(); + trace_break_lease_block(inode, new_fl); + spin_unlock(&inode->i_lock); error = wait_event_interruptible_timeout(new_fl->fl_wait, !new_fl->fl_next, break_time); - lock_flocks(); - __locks_delete_block(new_fl); + spin_lock(&inode->i_lock); + trace_break_lease_unblock(inode, new_fl); + locks_delete_block(new_fl); if (error >= 0) { if (error == 0) time_out_leases(inode); - /* Wait for the next lease that has not been broken yet */ + /* + * Wait for the next conflicting lease that has not been + * broken yet + */ for (flock = inode->i_flock; flock && IS_LEASE(flock); flock = flock->fl_next) { - if (flock->fl_type & F_INPROGRESS) + if (leases_conflict(new_fl, flock)) goto restart; } error = 0; } out: - unlock_flocks(); - if (!IS_ERR(new_fl)) - locks_free_lock(new_fl); + spin_unlock(&inode->i_lock); + locks_free_lock(new_fl); return error; } @@ -1302,7 +1432,7 @@ EXPORT_SYMBOL(__break_lease); void lease_get_mtime(struct inode *inode, struct timespec *time) { struct file_lock *flock = inode->i_flock; - if (flock && IS_LEASE(flock) && (flock->fl_type & F_WRLCK)) + if (flock && IS_LEASE(flock) && (flock->fl_type == F_WRLCK)) *time = current_fs_time(inode->i_sb); else *time = inode->i_mtime; @@ -1336,65 +1466,81 @@ EXPORT_SYMBOL(lease_get_mtime); int fcntl_getlease(struct file *filp) { struct file_lock *fl; + struct inode *inode = file_inode(filp); int type = F_UNLCK; - 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); + spin_lock(&inode->i_lock); + time_out_leases(file_inode(filp)); + for (fl = file_inode(filp)->i_flock; fl && IS_LEASE(fl); fl = fl->fl_next) { if (fl->fl_file == filp) { - type = fl->fl_type & ~F_INPROGRESS; + type = target_leasetype(fl); break; } } - unlock_flocks(); + spin_unlock(&inode->i_lock); return type; } /** - * generic_setlease - sets a lease on an open file - * @filp: file pointer - * @arg: type of lease to obtain - * @flp: input - file_lock to use, output - file_lock inserted - * - * The (input) flp->fl_lmops->fl_break function is required - * by break_lease(). - * - * Called with file_lock_lock held. + * check_conflicting_open - see if the given dentry points to a file that has + * an existing open that would conflict with the + * desired lease. + * @dentry: dentry to check + * @arg: type of lease that we're trying to acquire + * + * Check to see if there's an existing open fd on this file that would + * conflict with the lease we're trying to set. */ -int generic_setlease(struct file *filp, long arg, struct file_lock **flp) +static int +check_conflicting_open(const struct dentry *dentry, const long arg) +{ + int ret = 0; + struct inode *inode = dentry->d_inode; + + if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0)) + return -EAGAIN; + + if ((arg == F_WRLCK) && ((d_count(dentry) > 1) || + (atomic_read(&inode->i_count) > 1))) + ret = -EAGAIN; + + return ret; +} + +static int generic_add_lease(struct file *filp, long arg, struct file_lock **flp) { struct file_lock *fl, **before, **my_before = NULL, *lease; struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; - int error, rdlease_count = 0, wrlease_count = 0; + bool is_deleg = (*flp)->fl_flags & FL_DELEG; + int error; lease = *flp; + trace_generic_add_lease(inode, lease); - error = -EACCES; - if ((current_fsuid() != inode->i_uid) && !capable(CAP_LEASE)) - goto out; - error = -EINVAL; - if (!S_ISREG(inode->i_mode)) - goto out; - error = security_file_lock(filp, arg); - if (error) - goto out; - - time_out_leases(inode); - - BUG_ON(!(*flp)->fl_lmops->fl_break); + /* + * In the delegation case we need mutual exclusion with + * a number of operations that take the i_mutex. We trylock + * because delegations are an optional optimization, and if + * there's some chance of a conflict--we'd rather not + * bother, maybe that's a sign this just isn't a good file to + * hand out a delegation on. + */ + if (is_deleg && !mutex_trylock(&inode->i_mutex)) + return -EAGAIN; - if (arg != F_UNLCK) { - error = -EAGAIN; - if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0)) - goto out; - if ((arg == F_WRLCK) - && ((atomic_read(&dentry->d_count) > 1) - || (atomic_read(&inode->i_count) > 1))) - goto out; + if (is_deleg && arg == F_WRLCK) { + /* Write delegations are not currently supported: */ + mutex_unlock(&inode->i_mutex); + WARN_ON_ONCE(1); + return -EINVAL; } + error = check_conflicting_open(dentry, arg); + if (error) + goto out; + /* * At this point, we know that if there is an exclusive * lease on this file, then we hold it on this filp @@ -1403,52 +1549,121 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp) * then the file is not open by anyone (including us) * except for this filp. */ + error = -EAGAIN; for (before = &inode->i_flock; ((fl = *before) != NULL) && IS_LEASE(fl); before = &fl->fl_next) { - if (lease->fl_lmops->fl_mylease(fl, lease)) + if (fl->fl_file == filp) { my_before = before; - else if (fl->fl_type == (F_INPROGRESS | F_UNLCK)) - /* - * Someone is in the process of opening this - * file for writing so we may not take an - * exclusive lease on it. - */ - wrlease_count++; - else - rdlease_count++; + continue; + } + /* + * No exclusive leases if someone else has a lease on + * this file: + */ + if (arg == F_WRLCK) + goto out; + /* + * Modifying our existing lease is OK, but no getting a + * new lease if someone else is opening for write: + */ + if (fl->fl_flags & FL_UNLOCK_PENDING) + goto out; } - error = -EAGAIN; - if ((arg == F_RDLCK && (wrlease_count > 0)) || - (arg == F_WRLCK && ((rdlease_count + wrlease_count) > 0))) - goto out; - if (my_before != NULL) { - error = lease->fl_lmops->fl_change(my_before, arg); + error = lease->fl_lmops->lm_change(my_before, arg); if (!error) *flp = *my_before; goto out; } - if (arg == F_UNLCK) - goto out; - error = -EINVAL; if (!leases_enable) goto out; locks_insert_lock(before, lease); - return 0; - + /* + * The check in break_lease() is lockless. It's possible for another + * open to race in after we did the earlier check for a conflicting + * open but before the lease was inserted. Check again for a + * conflicting open and cancel the lease if there is one. + * + * We also add a barrier here to ensure that the insertion of the lock + * precedes these checks. + */ + smp_mb(); + error = check_conflicting_open(dentry, arg); + if (error) + locks_unlink_lock(flp); out: + if (is_deleg) + mutex_unlock(&inode->i_mutex); return error; } + +static int generic_delete_lease(struct file *filp, struct file_lock **flp) +{ + struct file_lock *fl, **before; + struct dentry *dentry = filp->f_path.dentry; + struct inode *inode = dentry->d_inode; + + trace_generic_delete_lease(inode, *flp); + + for (before = &inode->i_flock; + ((fl = *before) != NULL) && IS_LEASE(fl); + before = &fl->fl_next) { + if (fl->fl_file != filp) + continue; + return (*flp)->fl_lmops->lm_change(before, F_UNLCK); + } + return -EAGAIN; +} + +/** + * generic_setlease - sets a lease on an open file + * @filp: file pointer + * @arg: type of lease to obtain + * @flp: input - file_lock to use, output - file_lock inserted + * + * The (input) flp->fl_lmops->lm_break function is required + * by break_lease(). + * + * Called with inode->i_lock held. + */ +int generic_setlease(struct file *filp, long arg, struct file_lock **flp) +{ + struct dentry *dentry = filp->f_path.dentry; + struct inode *inode = dentry->d_inode; + int error; + + if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE)) + return -EACCES; + if (!S_ISREG(inode->i_mode)) + return -EINVAL; + error = security_file_lock(filp, arg); + if (error) + return error; + + time_out_leases(inode); + + BUG_ON(!(*flp)->fl_lmops->lm_break); + + switch (arg) { + case F_UNLCK: + return generic_delete_lease(filp, flp); + case F_RDLCK: + case F_WRLCK: + return generic_add_lease(filp, arg, flp); + default: + return -EINVAL; + } +} 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) + if (filp->f_op->setlease) return filp->f_op->setlease(filp, arg, lease); else return generic_setlease(filp, arg, lease); @@ -1461,7 +1676,7 @@ static int __vfs_setlease(struct file *filp, long arg, struct file_lock **lease) * @lease: file_lock to use * * Call this to establish a lease on the file. - * The (*lease)->fl_lmops->fl_break operation must be set; if not, + * The (*lease)->fl_lmops->lm_break operation must be set; if not, * break_lease will oops! * * This will call the filesystem's setlease file method, if @@ -1483,11 +1698,12 @@ static int __vfs_setlease(struct file *filp, long arg, struct file_lock **lease) int vfs_setlease(struct file *filp, long arg, struct file_lock **lease) { + struct inode *inode = file_inode(filp); int error; - lock_flocks(); + spin_lock(&inode->i_lock); error = __vfs_setlease(filp, arg, lease); - unlock_flocks(); + spin_unlock(&inode->i_lock); return error; } @@ -1505,6 +1721,7 @@ static int do_fcntl_delete_lease(struct file *filp) static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg) { struct file_lock *fl, *ret; + struct inode *inode = file_inode(filp); struct fasync_struct *new; int error; @@ -1518,10 +1735,10 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg) return -ENOMEM; } ret = fl; - lock_flocks(); + spin_lock(&inode->i_lock); error = __vfs_setlease(filp, arg, &ret); if (error) { - unlock_flocks(); + spin_unlock(&inode->i_lock); locks_free_lock(fl); goto out_free_fasync; } @@ -1538,7 +1755,7 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg) new = NULL; error = __f_setown(filp, task_pid(current), PIDTYPE_PID, 0); - unlock_flocks(); + spin_unlock(&inode->i_lock); out_free_fasync: if (new) @@ -1611,14 +1828,13 @@ EXPORT_SYMBOL(flock_lock_file_wait); */ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) { - struct file *filp; + struct fd f = fdget(fd); struct file_lock *lock; int can_sleep, unlock; int error; error = -EBADF; - filp = fget(fd); - if (!filp) + if (!f.file) goto out; can_sleep = !(cmd & LOCK_NB); @@ -1626,31 +1842,31 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) unlock = (cmd == LOCK_UN); if (!unlock && !(cmd & LOCK_MAND) && - !(filp->f_mode & (FMODE_READ|FMODE_WRITE))) + !(f.file->f_mode & (FMODE_READ|FMODE_WRITE))) goto out_putf; - error = flock_make_lock(filp, &lock, cmd); + error = flock_make_lock(f.file, &lock, cmd); if (error) goto out_putf; if (can_sleep) lock->fl_flags |= FL_SLEEP; - error = security_file_lock(filp, lock->fl_type); + error = security_file_lock(f.file, lock->fl_type); if (error) goto out_free; - if (filp->f_op && filp->f_op->flock) - error = filp->f_op->flock(filp, + if (f.file->f_op->flock) + error = f.file->f_op->flock(f.file, (can_sleep) ? F_SETLKW : F_SETLK, lock); else - error = flock_lock_file_wait(filp, lock); + error = flock_lock_file_wait(f.file, lock); out_free: locks_free_lock(lock); out_putf: - fput(filp); + fdput(f); out: return error; } @@ -1665,7 +1881,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { - if (filp->f_op && filp->f_op->lock) + if (filp->f_op->lock) return filp->f_op->lock(filp, F_GETLK, fl); posix_test_lock(filp, fl); return 0; @@ -1674,7 +1890,7 @@ EXPORT_SYMBOL_GPL(vfs_test_lock); static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) { - flock->l_pid = fl->fl_pid; + flock->l_pid = IS_OFDLCK(fl) ? -1 : fl->fl_pid; #if BITS_PER_LONG == 32 /* * Make sure we can represent the posix lock via @@ -1696,7 +1912,7 @@ static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) #if BITS_PER_LONG == 32 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) { - flock->l_pid = fl->fl_pid; + flock->l_pid = IS_OFDLCK(fl) ? -1 : fl->fl_pid; flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; @@ -1708,7 +1924,7 @@ static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ -int fcntl_getlk(struct file *filp, struct flock __user *l) +int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l) { struct file_lock file_lock; struct flock flock; @@ -1725,6 +1941,16 @@ int fcntl_getlk(struct file *filp, struct flock __user *l) if (error) goto out; + if (cmd == F_OFD_GETLK) { + error = -EINVAL; + if (flock.l_pid != 0) + goto out; + + cmd = F_GETLK; + file_lock.fl_flags |= FL_OFDLCK; + file_lock.fl_owner = (fl_owner_t)filp; + } + error = vfs_test_lock(filp, &file_lock); if (error) goto out; @@ -1759,10 +1985,10 @@ out: * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX * locks, the ->lock() interface may return asynchronously, before the lock has * been granted or denied by the underlying filesystem, if (and only if) - * fl_grant is set. Callers expecting ->lock() to return asynchronously + * lm_grant is set. Callers expecting ->lock() to return asynchronously * will only use F_SETLK, not F_SETLKW; they will set FL_SLEEP if (and only if) * the request is for a blocking lock. When ->lock() does return asynchronously, - * it must return FILE_LOCK_DEFERRED, and call ->fl_grant() when the lock + * it must return FILE_LOCK_DEFERRED, and call ->lm_grant() when the lock * request completes. * If the request is for non-blocking lock the file system should return * FILE_LOCK_DEFERRED then try to get the lock and call the callback routine @@ -1772,12 +1998,12 @@ out: * grants a lock so the VFS can find out which locks are locally held and do * the correct lock cleanup when required. * The underlying filesystem must not drop the kernel lock or call - * ->fl_grant() before returning to the caller with a FILE_LOCK_DEFERRED + * ->lm_grant() before returning to the caller with a FILE_LOCK_DEFERRED * return code. */ int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { - if (filp->f_op && filp->f_op->lock) + if (filp->f_op->lock) return filp->f_op->lock(filp, cmd, fl); else return posix_lock_file(filp, fl, conf); @@ -1808,6 +2034,22 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd, return error; } +/* Ensure that fl->fl_filp has compatible f_mode for F_SETLK calls */ +static int +check_fmode_for_setlk(struct file_lock *fl) +{ + switch (fl->fl_type) { + case F_RDLCK: + if (!(fl->fl_file->f_mode & FMODE_READ)) + return -EBADF; + break; + case F_WRLCK: + if (!(fl->fl_file->f_mode & FMODE_WRITE)) + return -EBADF; + } + return 0; +} + /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ @@ -1830,7 +2072,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, if (copy_from_user(&flock, l, sizeof(flock))) goto out; - inode = filp->f_path.dentry->d_inode; + inode = file_inode(filp); /* Don't allow mandatory locks on files that may be memory mapped * and shared. @@ -1844,25 +2086,36 @@ again: error = flock_to_posix_lock(filp, file_lock, &flock); if (error) goto out; - if (cmd == F_SETLKW) { - file_lock->fl_flags |= FL_SLEEP; - } - - error = -EBADF; - switch (flock.l_type) { - case F_RDLCK: - if (!(filp->f_mode & FMODE_READ)) - goto out; - break; - case F_WRLCK: - if (!(filp->f_mode & FMODE_WRITE)) + + error = check_fmode_for_setlk(file_lock); + if (error) + goto out; + + /* + * If the cmd is requesting file-private locks, then set the + * FL_OFDLCK flag and override the owner. + */ + switch (cmd) { + case F_OFD_SETLK: + error = -EINVAL; + if (flock.l_pid != 0) goto out; + + cmd = F_SETLK; + file_lock->fl_flags |= FL_OFDLCK; + file_lock->fl_owner = (fl_owner_t)filp; break; - case F_UNLCK: - break; - default: + case F_OFD_SETLKW: error = -EINVAL; - goto out; + if (flock.l_pid != 0) + goto out; + + cmd = F_SETLKW; + file_lock->fl_flags |= FL_OFDLCK; + file_lock->fl_owner = (fl_owner_t)filp; + /* Fallthrough */ + case F_SETLKW: + file_lock->fl_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); @@ -1893,7 +2146,7 @@ out: /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ -int fcntl_getlk64(struct file *filp, struct flock64 __user *l) +int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l) { struct file_lock file_lock; struct flock64 flock; @@ -1910,6 +2163,16 @@ int fcntl_getlk64(struct file *filp, struct flock64 __user *l) if (error) goto out; + if (cmd == F_OFD_GETLK) { + error = -EINVAL; + if (flock.l_pid != 0) + goto out; + + cmd = F_GETLK64; + file_lock.fl_flags |= FL_OFDLCK; + file_lock.fl_owner = (fl_owner_t)filp; + } + error = vfs_test_lock(filp, &file_lock); if (error) goto out; @@ -1948,7 +2211,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, if (copy_from_user(&flock, l, sizeof(flock))) goto out; - inode = filp->f_path.dentry->d_inode; + inode = file_inode(filp); /* Don't allow mandatory locks on files that may be memory mapped * and shared. @@ -1962,25 +2225,36 @@ again: error = flock64_to_posix_lock(filp, file_lock, &flock); if (error) goto out; - if (cmd == F_SETLKW64) { - file_lock->fl_flags |= FL_SLEEP; - } - - error = -EBADF; - switch (flock.l_type) { - case F_RDLCK: - if (!(filp->f_mode & FMODE_READ)) - goto out; - break; - case F_WRLCK: - if (!(filp->f_mode & FMODE_WRITE)) + + error = check_fmode_for_setlk(file_lock); + if (error) + goto out; + + /* + * If the cmd is requesting file-private locks, then set the + * FL_OFDLCK flag and override the owner. + */ + switch (cmd) { + case F_OFD_SETLK: + error = -EINVAL; + if (flock.l_pid != 0) goto out; + + cmd = F_SETLK64; + file_lock->fl_flags |= FL_OFDLCK; + file_lock->fl_owner = (fl_owner_t)filp; break; - case F_UNLCK: - break; - default: + case F_OFD_SETLKW: error = -EINVAL; - goto out; + if (flock.l_pid != 0) + goto out; + + cmd = F_SETLKW64; + file_lock->fl_flags |= FL_OFDLCK; + file_lock->fl_owner = (fl_owner_t)filp; + /* Fallthrough */ + case F_SETLKW64: + file_lock->fl_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); @@ -2017,7 +2291,7 @@ void locks_remove_posix(struct file *filp, fl_owner_t owner) * posix_lock_file(). Another process could be setting a lock on this * file at the same time, but we wouldn't remove that lock anyway. */ - if (!filp->f_path.dentry->d_inode->i_flock) + if (!file_inode(filp)->i_flock) return; lock.fl_type = F_UNLCK; @@ -2041,17 +2315,20 @@ EXPORT_SYMBOL(locks_remove_posix); /* * This function is called on the last close of an open file. */ -void locks_remove_flock(struct file *filp) +void locks_remove_file(struct file *filp) { - struct inode * inode = filp->f_path.dentry->d_inode; + struct inode * inode = file_inode(filp); struct file_lock *fl; struct file_lock **before; if (!inode->i_flock) return; - if (filp->f_op && filp->f_op->flock) { + locks_remove_posix(filp, (fl_owner_t)filp); + + if (filp->f_op->flock) { struct file_lock fl = { + .fl_owner = (fl_owner_t)filp, .fl_pid = current->tgid, .fl_file = filp, .fl_flags = FL_FLOCK, @@ -2063,48 +2340,58 @@ void locks_remove_flock(struct file *filp) fl.fl_ops->fl_release_private(&fl); } - lock_flocks(); + spin_lock(&inode->i_lock); before = &inode->i_flock; while ((fl = *before) != NULL) { if (fl->fl_file == filp) { - if (IS_FLOCK(fl)) { - locks_delete_lock(before); - continue; - } if (IS_LEASE(fl)) { lease_modify(before, F_UNLCK); continue; } - /* What? */ - BUG(); + + /* + * There's a leftover lock on the list of a type that + * we didn't expect to see. Most likely a classic + * POSIX lock that ended up not getting released + * properly, or that raced onto the list somehow. Log + * some info about it and then just remove it from + * the list. + */ + WARN(!IS_FLOCK(fl), + "leftover lock: dev=%u:%u ino=%lu type=%hhd flags=0x%x start=%lld end=%lld\n", + MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), inode->i_ino, + fl->fl_type, fl->fl_flags, + fl->fl_start, fl->fl_end); + + locks_delete_lock(before); + continue; } before = &fl->fl_next; } - unlock_flocks(); + spin_unlock(&inode->i_lock); } /** * posix_unblock_lock - stop waiting for a file lock - * @filp: how the file was opened * @waiter: the lock which was waiting * * lockd needs to block waiting for locks. */ int -posix_unblock_lock(struct file *filp, struct file_lock *waiter) +posix_unblock_lock(struct file_lock *waiter) { int status = 0; - lock_flocks(); + spin_lock(&blocked_lock_lock); if (waiter->fl_next) __locks_delete_block(waiter); else status = -ENOENT; - unlock_flocks(); + spin_unlock(&blocked_lock_lock); return status; } - EXPORT_SYMBOL(posix_unblock_lock); /** @@ -2116,7 +2403,7 @@ EXPORT_SYMBOL(posix_unblock_lock); */ int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { - if (filp->f_op && filp->f_op->lock) + if (filp->f_op->lock) return filp->f_op->lock(filp, F_CANCELLK, fl); return 0; } @@ -2127,6 +2414,11 @@ EXPORT_SYMBOL_GPL(vfs_cancel_lock); #include <linux/proc_fs.h> #include <linux/seq_file.h> +struct locks_iterator { + int li_cpu; + loff_t li_pos; +}; + static void lock_get_status(struct seq_file *f, struct file_lock *fl, loff_t id, char *pfx) { @@ -2139,30 +2431,36 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, fl_pid = fl->fl_pid; if (fl->fl_file != NULL) - inode = fl->fl_file->f_path.dentry->d_inode; + inode = file_inode(fl->fl_file); seq_printf(f, "%lld:%s ", id, pfx); if (IS_POSIX(fl)) { - seq_printf(f, "%6s %s ", - (fl->fl_flags & FL_ACCESS) ? "ACCESS" : "POSIX ", + if (fl->fl_flags & FL_ACCESS) + seq_puts(f, "ACCESS"); + else if (IS_OFDLCK(fl)) + seq_puts(f, "OFDLCK"); + else + seq_puts(f, "POSIX "); + + seq_printf(f, " %s ", (inode == NULL) ? "*NOINODE*" : mandatory_lock(inode) ? "MANDATORY" : "ADVISORY "); } else if (IS_FLOCK(fl)) { if (fl->fl_type & LOCK_MAND) { - seq_printf(f, "FLOCK MSNFS "); + seq_puts(f, "FLOCK MSNFS "); } else { - seq_printf(f, "FLOCK ADVISORY "); + seq_puts(f, "FLOCK ADVISORY "); } } else if (IS_LEASE(fl)) { - seq_printf(f, "LEASE "); - if (fl->fl_type & F_INPROGRESS) - seq_printf(f, "BREAKING "); + seq_puts(f, "LEASE "); + if (lease_breaking(fl)) + seq_puts(f, "BREAKING "); else if (fl->fl_file) - seq_printf(f, "ACTIVE "); + seq_puts(f, "ACTIVE "); else - seq_printf(f, "BREAKER "); + seq_puts(f, "BREAKER "); } else { - seq_printf(f, "UNKNOWN UNKNOWN "); + seq_puts(f, "UNKNOWN UNKNOWN "); } if (fl->fl_type & LOCK_MAND) { seq_printf(f, "%s ", @@ -2171,9 +2469,9 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, : (fl->fl_type & LOCK_WRITE) ? "WRITE" : "NONE "); } else { seq_printf(f, "%s ", - (fl->fl_type & F_INPROGRESS) - ? (fl->fl_type & F_UNLCK) ? "UNLCK" : "READ " - : (fl->fl_type & F_WRLCK) ? "WRITE" : "READ "); + (lease_breaking(fl)) + ? (fl->fl_type == F_UNLCK) ? "UNLCK" : "READ " + : (fl->fl_type == F_WRLCK) ? "WRITE" : "READ "); } if (inode) { #ifdef WE_CAN_BREAK_LSLK_NOW @@ -2194,43 +2492,49 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, else seq_printf(f, "%Ld %Ld\n", fl->fl_start, fl->fl_end); } else { - seq_printf(f, "0 EOF\n"); + seq_puts(f, "0 EOF\n"); } } static int locks_show(struct seq_file *f, void *v) { + struct locks_iterator *iter = f->private; struct file_lock *fl, *bfl; - fl = list_entry(v, struct file_lock, fl_link); + fl = hlist_entry(v, struct file_lock, fl_link); - lock_get_status(f, fl, *((loff_t *)f->private), ""); + lock_get_status(f, fl, iter->li_pos, ""); list_for_each_entry(bfl, &fl->fl_block, fl_block) - lock_get_status(f, bfl, *((loff_t *)f->private), " ->"); + lock_get_status(f, bfl, iter->li_pos, " ->"); return 0; } static void *locks_start(struct seq_file *f, loff_t *pos) + __acquires(&blocked_lock_lock) { - loff_t *p = f->private; + struct locks_iterator *iter = f->private; - lock_flocks(); - *p = (*pos + 1); - return seq_list_start(&file_lock_list, *pos); + iter->li_pos = *pos + 1; + lg_global_lock(&file_lock_lglock); + spin_lock(&blocked_lock_lock); + return seq_hlist_start_percpu(&file_lock_list, &iter->li_cpu, *pos); } static void *locks_next(struct seq_file *f, void *v, loff_t *pos) { - loff_t *p = f->private; - ++*p; - return seq_list_next(v, &file_lock_list, pos); + struct locks_iterator *iter = f->private; + + ++iter->li_pos; + return seq_hlist_next_percpu(v, &file_lock_list, &iter->li_cpu, pos); } static void locks_stop(struct seq_file *f, void *v) + __releases(&blocked_lock_lock) { - unlock_flocks(); + spin_unlock(&blocked_lock_lock); + lg_global_unlock(&file_lock_lglock); } static const struct seq_operations locks_seq_operations = { @@ -2242,7 +2546,8 @@ static const struct seq_operations locks_seq_operations = { static int locks_open(struct inode *inode, struct file *filp) { - return seq_open_private(filp, &locks_seq_operations, sizeof(loff_t)); + return seq_open_private(filp, &locks_seq_operations, + sizeof(struct locks_iterator)); } static const struct file_operations proc_locks_operations = { @@ -2277,7 +2582,8 @@ int lock_may_read(struct inode *inode, loff_t start, unsigned long len) { struct file_lock *fl; int result = 1; - lock_flocks(); + + spin_lock(&inode->i_lock); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { if (IS_POSIX(fl)) { if (fl->fl_type == F_RDLCK) @@ -2294,7 +2600,7 @@ int lock_may_read(struct inode *inode, loff_t start, unsigned long len) result = 0; break; } - unlock_flocks(); + spin_unlock(&inode->i_lock); return result; } @@ -2317,7 +2623,8 @@ int lock_may_write(struct inode *inode, loff_t start, unsigned long len) { struct file_lock *fl; int result = 1; - lock_flocks(); + + spin_lock(&inode->i_lock); 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))) @@ -2332,7 +2639,7 @@ int lock_may_write(struct inode *inode, loff_t start, unsigned long len) result = 0; break; } - unlock_flocks(); + spin_unlock(&inode->i_lock); return result; } @@ -2340,9 +2647,16 @@ EXPORT_SYMBOL(lock_may_write); static int __init filelock_init(void) { + int i; + filelock_cache = kmem_cache_create("file_lock_cache", - sizeof(struct file_lock), 0, SLAB_PANIC, - init_once); + sizeof(struct file_lock), 0, SLAB_PANIC, NULL); + + lg_lock_init(&file_lock_lglock, "file_lock_lglock"); + + for_each_possible_cpu(i) + INIT_HLIST_HEAD(per_cpu_ptr(&file_lock_list, i)); + return 0; } |