diff options
Diffstat (limited to 'fs/locks.c')
| -rw-r--r-- | fs/locks.c | 1759 |
1 files changed, 952 insertions, 807 deletions
diff --git a/fs/locks.c b/fs/locks.c index ff6af2c32601..9f565802a88c 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -1,117 +1,12 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/locks.c * - * Provide support for fcntl()'s F_GETLK, F_SETLK, and F_SETLKW calls. - * Doug Evans (dje@spiff.uucp), August 07, 1992 + * We implement four types of file locks: BSD locks, posix locks, open + * file description locks, and leases. For details about BSD locks, + * see the flock(2) man page; for details about the other three, see + * fcntl(2). * - * Deadlock detection added. - * FIXME: one thing isn't handled yet: - * - mandatory locks (requires lots of changes elsewhere) - * Kelly Carmichael (kelly@[142.24.8.65]), September 17, 1994. - * - * Miscellaneous edits, and a total rewrite of posix_lock_file() code. - * Kai Petzke (wpp@marie.physik.tu-berlin.de), 1994 - * - * Converted file_lock_table to a linked list from an array, which eliminates - * the limits on how many active file locks are open. - * Chad Page (pageone@netcom.com), November 27, 1994 - * - * Removed dependency on file descriptors. dup()'ed file descriptors now - * get the same locks as the original file descriptors, and a close() on - * any file descriptor removes ALL the locks on the file for the current - * process. Since locks still depend on the process id, locks are inherited - * after an exec() but not after a fork(). This agrees with POSIX, and both - * BSD and SVR4 practice. - * Andy Walker (andy@lysaker.kvaerner.no), February 14, 1995 - * - * Scrapped free list which is redundant now that we allocate locks - * dynamically with kmalloc()/kfree(). - * Andy Walker (andy@lysaker.kvaerner.no), February 21, 1995 - * - * Implemented two lock personalities - FL_FLOCK and FL_POSIX. - * - * FL_POSIX locks are created with calls to fcntl() and lockf() through the - * fcntl() system call. They have the semantics described above. - * - * FL_FLOCK locks are created with calls to flock(), through the flock() - * system call, which is new. Old C libraries implement flock() via fcntl() - * and will continue to use the old, broken implementation. - * - * FL_FLOCK locks follow the 4.4 BSD flock() semantics. They are associated - * with a file pointer (filp). As a result they can be shared by a parent - * process and its children after a fork(). They are removed when the last - * file descriptor referring to the file pointer is closed (unless explicitly - * unlocked). - * - * FL_FLOCK locks never deadlock, an existing lock is always removed before - * upgrading from shared to exclusive (or vice versa). When this happens - * any processes blocked by the current lock are woken up and allowed to - * run before the new lock is applied. - * Andy Walker (andy@lysaker.kvaerner.no), June 09, 1995 - * - * Removed some race conditions in flock_lock_file(), marked other possible - * races. Just grep for FIXME to see them. - * Dmitry Gorodchanin (pgmdsg@ibi.com), February 09, 1996. - * - * Addressed Dmitry's concerns. Deadlock checking no longer recursive. - * Lock allocation changed to GFP_ATOMIC as we can't afford to sleep - * once we've checked for blocking and deadlocking. - * Andy Walker (andy@lysaker.kvaerner.no), April 03, 1996. - * - * Initial implementation of mandatory locks. SunOS turned out to be - * a rotten model, so I implemented the "obvious" semantics. - * 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 - * check if a file has mandatory locks, used by mmap(), open() and creat() to - * see if system call should be rejected. Ref. HP-UX/SunOS/Solaris Reference - * Manual, Section 2. - * Andy Walker (andy@lysaker.kvaerner.no), April 09, 1996. - * - * Tidied up block list handling. Added '/proc/locks' interface. - * Andy Walker (andy@lysaker.kvaerner.no), April 24, 1996. - * - * Fixed deadlock condition for pathological code that mixes calls to - * flock() and fcntl(). - * Andy Walker (andy@lysaker.kvaerner.no), April 29, 1996. - * - * Allow only one type of locking scheme (FL_POSIX or FL_FLOCK) to be in use - * for a given file at a time. Changed the CONFIG_LOCK_MANDATORY scheme to - * guarantee sensible behaviour in the case where file system modules might - * be compiled with different options than the kernel itself. - * Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996. - * - * Added a couple of missing wake_up() calls. Thanks to Thomas Meckel - * (Thomas.Meckel@mni.fh-giessen.de) for spotting this. - * Andy Walker (andy@lysaker.kvaerner.no), May 15, 1996. - * - * Changed FL_POSIX locks to use the block list in the same way as FL_FLOCK - * locks. Changed process synchronisation to avoid dereferencing locks that - * have already been freed. - * Andy Walker (andy@lysaker.kvaerner.no), Sep 21, 1996. - * - * Made the block list a circular list to minimise searching in the list. - * Andy Walker (andy@lysaker.kvaerner.no), Sep 25, 1996. - * - * Made mandatory locking a mount option. Default is not to allow mandatory - * locking. - * Andy Walker (andy@lysaker.kvaerner.no), Oct 04, 1996. - * - * Some adaptations for NFS support. - * Olaf Kirch (okir@monad.swb.de), Dec 1996, - * - * Fixed /proc/locks interface so that we can't overrun the buffer we are handed. - * Andy Walker (andy@lysaker.kvaerner.no), May 12, 1997. - * - * Use slab allocator instead of kmalloc/kfree. - * Use generic list implementation from <linux/list.h>. - * Sped up posix_locks_deadlock by only considering blocked locks. - * Matthew Wilcox <willy@debian.org>, March, 2000. - * - * Leases and LOCK_MAND - * Matthew Wilcox <willy@debian.org>, June, 2000. - * Stephen Rothwell <sfr@canb.auug.org.au>, June, 2000. * * Locking conflicts and dependencies: * If multiple threads attempt to lock the same byte (or flock the same file) @@ -153,10 +48,10 @@ * children. * */ - #include <linux/capability.h> #include <linux/file.h> #include <linux/fdtable.h> +#include <linux/filelock.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/security.h> @@ -167,34 +62,67 @@ #include <linux/pid_namespace.h> #include <linux/hashtable.h> #include <linux/percpu.h> +#include <linux/sysctl.h> #define CREATE_TRACE_POINTS #include <trace/events/filelock.h> #include <linux/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|FL_DELEG|FL_LAYOUT)) -#define IS_OFDLCK(fl) (fl->fl_flags & FL_OFDLCK) -#define IS_REMOTELCK(fl) (fl->fl_pid <= 0) +static struct file_lock *file_lock(struct file_lock_core *flc) +{ + return container_of(flc, struct file_lock, c); +} -static bool lease_breaking(struct file_lock *fl) +static struct file_lease *file_lease(struct file_lock_core *flc) { - return fl->fl_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING); + return container_of(flc, struct file_lease, c); } -static int target_leasetype(struct file_lock *fl) +static bool lease_breaking(struct file_lease *fl) { - if (fl->fl_flags & FL_UNLOCK_PENDING) + return fl->c.flc_flags & (FL_UNLOCK_PENDING | FL_DOWNGRADE_PENDING); +} + +static int target_leasetype(struct file_lease *fl) +{ + if (fl->c.flc_flags & FL_UNLOCK_PENDING) return F_UNLCK; - if (fl->fl_flags & FL_DOWNGRADE_PENDING) + if (fl->c.flc_flags & FL_DOWNGRADE_PENDING) return F_RDLCK; - return fl->fl_type; -} + return fl->c.flc_type; +} + +static int leases_enable = 1; +static int lease_break_time = 45; + +#ifdef CONFIG_SYSCTL +static const struct ctl_table locks_sysctls[] = { + { + .procname = "leases-enable", + .data = &leases_enable, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#ifdef CONFIG_MMU + { + .procname = "lease-break-time", + .data = &lease_break_time, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif /* CONFIG_MMU */ +}; -int leases_enable = 1; -int lease_break_time = 45; +static int __init init_fs_locks_sysctls(void) +{ + register_sysctl_init("fs", locks_sysctls); + return 0; +} +early_initcall(init_fs_locks_sysctls); +#endif /* CONFIG_SYSCTL */ /* * The global file_lock_list is only used for displaying /proc/locks, so we @@ -211,6 +139,7 @@ struct file_lock_list_struct { static DEFINE_PER_CPU(struct file_lock_list_struct, file_lock_list); DEFINE_STATIC_PERCPU_RWSEM(file_rwsem); + /* * The blocked_hash is used to find POSIX lock loops for deadlock detection. * It is protected by blocked_lock_lock. @@ -240,8 +169,9 @@ static DEFINE_HASHTABLE(blocked_hash, BLOCKED_HASH_BITS); */ static DEFINE_SPINLOCK(blocked_lock_lock); -static struct kmem_cache *flctx_cache __read_mostly; -static struct kmem_cache *filelock_cache __read_mostly; +static struct kmem_cache *flctx_cache __ro_after_init; +static struct kmem_cache *filelock_cache __ro_after_init; +static struct kmem_cache *filelease_cache __ro_after_init; static struct file_lock_context * locks_get_lock_context(struct inode *inode, int type) @@ -249,7 +179,7 @@ locks_get_lock_context(struct inode *inode, int type) struct file_lock_context *ctx; /* paired with cmpxchg() below */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (likely(ctx) || type == F_UNLCK) goto out; @@ -268,7 +198,7 @@ locks_get_lock_context(struct inode *inode, int type) */ if (cmpxchg(&inode->i_flctx, NULL, ctx)) { kmem_cache_free(flctx_cache, ctx); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); } out: trace_locks_get_lock_context(inode, type, ctx); @@ -278,11 +208,12 @@ out: static void locks_dump_ctx_list(struct list_head *list, char *list_type) { - struct file_lock *fl; + struct file_lock_core *flc; - list_for_each_entry(fl, list, fl_list) { - pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid); - } + list_for_each_entry(flc, list, flc_list) + pr_warn("%s: fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", + list_type, flc->flc_owner, flc->flc_flags, + flc->flc_type, flc->flc_pid); } static void @@ -303,25 +234,25 @@ locks_check_ctx_lists(struct inode *inode) } static void -locks_check_ctx_file_list(struct file *filp, struct list_head *list, - char *list_type) +locks_check_ctx_file_list(struct file *filp, struct list_head *list, char *list_type) { - struct file_lock *fl; - struct inode *inode = locks_inode(filp); + struct file_lock_core *flc; + struct inode *inode = file_inode(filp); - list_for_each_entry(fl, list, fl_list) - if (fl->fl_file == filp) + list_for_each_entry(flc, list, flc_list) + if (flc->flc_file == filp) pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%lx " " fl_owner=%p fl_flags=0x%x fl_type=0x%x fl_pid=%u\n", list_type, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino, - fl->fl_owner, fl->fl_flags, fl->fl_type, fl->fl_pid); + flc->flc_owner, flc->flc_flags, + flc->flc_type, flc->flc_pid); } void locks_free_lock_context(struct inode *inode) { - struct file_lock_context *ctx = inode->i_flctx; + struct file_lock_context *ctx = locks_inode_context(inode); if (unlikely(ctx)) { locks_check_ctx_lists(inode); @@ -329,13 +260,13 @@ locks_free_lock_context(struct inode *inode) } } -static void locks_init_lock_heads(struct file_lock *fl) +static void locks_init_lock_heads(struct file_lock_core *flc) { - INIT_HLIST_NODE(&fl->fl_link); - INIT_LIST_HEAD(&fl->fl_list); - INIT_LIST_HEAD(&fl->fl_blocked_requests); - INIT_LIST_HEAD(&fl->fl_blocked_member); - init_waitqueue_head(&fl->fl_wait); + INIT_HLIST_NODE(&flc->flc_link); + INIT_LIST_HEAD(&flc->flc_list); + INIT_LIST_HEAD(&flc->flc_blocked_requests); + INIT_LIST_HEAD(&flc->flc_blocked_member); + init_waitqueue_head(&flc->flc_wait); } /* Allocate an empty lock structure. */ @@ -344,14 +275,34 @@ struct file_lock *locks_alloc_lock(void) struct file_lock *fl = kmem_cache_zalloc(filelock_cache, GFP_KERNEL); if (fl) - locks_init_lock_heads(fl); + locks_init_lock_heads(&fl->c); return fl; } EXPORT_SYMBOL_GPL(locks_alloc_lock); +/* Allocate an empty lock structure. */ +struct file_lease *locks_alloc_lease(void) +{ + struct file_lease *fl = kmem_cache_zalloc(filelease_cache, GFP_KERNEL); + + if (fl) + locks_init_lock_heads(&fl->c); + + return fl; +} +EXPORT_SYMBOL_GPL(locks_alloc_lease); + void locks_release_private(struct file_lock *fl) { + struct file_lock_core *flc = &fl->c; + + BUG_ON(waitqueue_active(&flc->flc_wait)); + BUG_ON(!list_empty(&flc->flc_list)); + BUG_ON(!list_empty(&flc->flc_blocked_requests)); + BUG_ON(!list_empty(&flc->flc_blocked_member)); + BUG_ON(!hlist_unhashed(&flc->flc_link)); + if (fl->fl_ops) { if (fl->fl_ops->fl_release_private) fl->fl_ops->fl_release_private(fl); @@ -360,57 +311,95 @@ void locks_release_private(struct file_lock *fl) if (fl->fl_lmops) { if (fl->fl_lmops->lm_put_owner) { - fl->fl_lmops->lm_put_owner(fl->fl_owner); - fl->fl_owner = NULL; + fl->fl_lmops->lm_put_owner(flc->flc_owner); + flc->flc_owner = NULL; } fl->fl_lmops = NULL; } } EXPORT_SYMBOL_GPL(locks_release_private); +/** + * locks_owner_has_blockers - Check for blocking lock requests + * @flctx: file lock context + * @owner: lock owner + * + * Return values: + * %true: @owner has at least one blocker + * %false: @owner has no blockers + */ +bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) +{ + struct file_lock_core *flc; + + spin_lock(&flctx->flc_lock); + list_for_each_entry(flc, &flctx->flc_posix, flc_list) { + if (flc->flc_owner != owner) + continue; + if (!list_empty(&flc->flc_blocked_requests)) { + spin_unlock(&flctx->flc_lock); + return true; + } + } + spin_unlock(&flctx->flc_lock); + return false; +} +EXPORT_SYMBOL_GPL(locks_owner_has_blockers); + /* Free a lock which is not in use. */ void locks_free_lock(struct file_lock *fl) { - BUG_ON(waitqueue_active(&fl->fl_wait)); - BUG_ON(!list_empty(&fl->fl_list)); - BUG_ON(!list_empty(&fl->fl_blocked_requests)); - BUG_ON(!list_empty(&fl->fl_blocked_member)); - BUG_ON(!hlist_unhashed(&fl->fl_link)); - locks_release_private(fl); kmem_cache_free(filelock_cache, fl); } EXPORT_SYMBOL(locks_free_lock); +/* Free a lease which is not in use. */ +void locks_free_lease(struct file_lease *fl) +{ + kmem_cache_free(filelease_cache, fl); +} +EXPORT_SYMBOL(locks_free_lease); + static void locks_dispose_list(struct list_head *dispose) { - struct file_lock *fl; + struct file_lock_core *flc; while (!list_empty(dispose)) { - fl = list_first_entry(dispose, struct file_lock, fl_list); - list_del_init(&fl->fl_list); - locks_free_lock(fl); + flc = list_first_entry(dispose, struct file_lock_core, flc_list); + list_del_init(&flc->flc_list); + if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) + locks_free_lease(file_lease(flc)); + else + locks_free_lock(file_lock(flc)); } } void locks_init_lock(struct file_lock *fl) { memset(fl, 0, sizeof(struct file_lock)); - locks_init_lock_heads(fl); + locks_init_lock_heads(&fl->c); } EXPORT_SYMBOL(locks_init_lock); +void locks_init_lease(struct file_lease *fl) +{ + memset(fl, 0, sizeof(*fl)); + locks_init_lock_heads(&fl->c); +} +EXPORT_SYMBOL(locks_init_lease); + /* * Initialize a new lock from an existing file_lock structure. */ void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { - new->fl_owner = fl->fl_owner; - new->fl_pid = fl->fl_pid; - new->fl_file = NULL; - new->fl_flags = fl->fl_flags; - new->fl_type = fl->fl_type; + new->c.flc_owner = fl->c.flc_owner; + new->c.flc_pid = fl->c.flc_pid; + new->c.flc_file = NULL; + new->c.flc_flags = fl->c.flc_flags; + new->c.flc_type = fl->c.flc_type; new->fl_start = fl->fl_start; new->fl_end = fl->fl_end; new->fl_lmops = fl->fl_lmops; @@ -418,7 +407,7 @@ void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) if (fl->fl_lmops) { if (fl->fl_lmops->lm_get_owner) - fl->fl_lmops->lm_get_owner(fl->fl_owner); + fl->fl_lmops->lm_get_owner(fl->c.flc_owner); } } EXPORT_SYMBOL(locks_copy_conflock); @@ -430,7 +419,7 @@ void locks_copy_lock(struct file_lock *new, struct file_lock *fl) locks_copy_conflock(new, fl); - new->fl_file = fl->fl_file; + new->c.flc_file = fl->c.flc_file; new->fl_ops = fl->fl_ops; if (fl->fl_ops) { @@ -446,21 +435,21 @@ static void locks_move_blocks(struct file_lock *new, struct file_lock *fl) /* * As ctx->flc_lock is held, new requests cannot be added to - * ->fl_blocked_requests, so we don't need a lock to check if it + * ->flc_blocked_requests, so we don't need a lock to check if it * is empty. */ - if (list_empty(&fl->fl_blocked_requests)) + if (list_empty(&fl->c.flc_blocked_requests)) return; spin_lock(&blocked_lock_lock); - list_splice_init(&fl->fl_blocked_requests, &new->fl_blocked_requests); - list_for_each_entry(f, &new->fl_blocked_requests, fl_blocked_member) - f->fl_blocker = new; + list_splice_init(&fl->c.flc_blocked_requests, + &new->c.flc_blocked_requests); + list_for_each_entry(f, &new->c.flc_blocked_requests, + c.flc_blocked_member) + f->c.flc_blocker = &new->c; spin_unlock(&blocked_lock_lock); } static inline int flock_translate_cmd(int cmd) { - if (cmd & LOCK_MAND) - return cmd & (LOCK_MAND | LOCK_RW); switch (cmd) { case LOCK_SH: return F_RDLCK; @@ -473,39 +462,25 @@ static inline int flock_translate_cmd(int cmd) { } /* Fill in a file_lock structure with an appropriate FLOCK lock. */ -static struct file_lock * -flock_make_lock(struct file *filp, unsigned int cmd, struct file_lock *fl) +static void flock_make_lock(struct file *filp, struct file_lock *fl, int type) { - int type = flock_translate_cmd(cmd); + locks_init_lock(fl); - if (type < 0) - return ERR_PTR(type); - - if (fl == NULL) { - fl = locks_alloc_lock(); - if (fl == NULL) - return ERR_PTR(-ENOMEM); - } else { - locks_init_lock(fl); - } - - fl->fl_file = filp; - fl->fl_owner = filp; - fl->fl_pid = current->tgid; - fl->fl_flags = FL_FLOCK; - fl->fl_type = type; + fl->c.flc_file = filp; + fl->c.flc_owner = filp; + fl->c.flc_pid = current->tgid; + fl->c.flc_flags = FL_FLOCK; + fl->c.flc_type = type; fl->fl_end = OFFSET_MAX; - - return fl; } -static int assign_type(struct file_lock *fl, long type) +static int assign_type(struct file_lock_core *flc, int type) { switch (type) { case F_RDLCK: case F_WRLCK: case F_UNLCK: - fl->fl_type = type; + flc->flc_type = type; break; default: return -EINVAL; @@ -540,7 +515,7 @@ static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl, if (l->l_len > 0) { if (l->l_len - 1 > OFFSET_MAX - fl->fl_start) return -EOVERFLOW; - fl->fl_end = fl->fl_start + l->l_len - 1; + fl->fl_end = fl->fl_start + (l->l_len - 1); } else if (l->l_len < 0) { if (fl->fl_start + l->l_len < 0) @@ -550,14 +525,14 @@ static int flock64_to_posix_lock(struct file *filp, struct file_lock *fl, } else fl->fl_end = OFFSET_MAX; - fl->fl_owner = current->files; - fl->fl_pid = current->tgid; - fl->fl_file = filp; - fl->fl_flags = FL_POSIX; + fl->c.flc_owner = current->files; + fl->c.flc_pid = current->tgid; + fl->c.flc_file = filp; + fl->c.flc_flags = FL_POSIX; fl->fl_ops = NULL; fl->fl_lmops = NULL; - return assign_type(fl, l->l_type); + return assign_type(&fl->c, l->l_type); } /* Verify a "struct flock" and copy it to a "struct file_lock" as a POSIX @@ -578,16 +553,16 @@ static int flock_to_posix_lock(struct file *filp, struct file_lock *fl, /* default lease lock manager operations */ static bool -lease_break_callback(struct file_lock *fl) +lease_break_callback(struct file_lease *fl) { kill_fasync(&fl->fl_fasync, SIGIO, POLL_MSG); return false; } static void -lease_setup(struct file_lock *fl, void **priv) +lease_setup(struct file_lease *fl, void **priv) { - struct file *filp = fl->fl_file; + struct file *filp = fl->c.flc_file; struct fasync_struct *fa = *priv; /* @@ -601,7 +576,7 @@ lease_setup(struct file_lock *fl, void **priv) __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); } -static const struct lock_manager_operations lease_manager_ops = { +static const struct lease_manager_operations lease_manager_ops = { .lm_break = lease_break_callback, .lm_change = lease_modify, .lm_setup = lease_setup, @@ -610,35 +585,32 @@ static const struct lock_manager_operations lease_manager_ops = { /* * Initialize a lease, use the default lock manager operations */ -static int lease_init(struct file *filp, long type, struct file_lock *fl) +static int lease_init(struct file *filp, unsigned int flags, int type, struct file_lease *fl) { - if (assign_type(fl, type) != 0) + if (assign_type(&fl->c, type) != 0) return -EINVAL; - fl->fl_owner = filp; - fl->fl_pid = current->tgid; + fl->c.flc_owner = filp; + fl->c.flc_pid = current->tgid; - fl->fl_file = filp; - fl->fl_flags = FL_LEASE; - fl->fl_start = 0; - fl->fl_end = OFFSET_MAX; - fl->fl_ops = NULL; + fl->c.flc_file = filp; + fl->c.flc_flags = flags; fl->fl_lmops = &lease_manager_ops; return 0; } /* Allocate a file_lock initialised to this type of lease */ -static struct file_lock *lease_alloc(struct file *filp, long type) +static struct file_lease *lease_alloc(struct file *filp, unsigned int flags, int type) { - struct file_lock *fl = locks_alloc_lock(); + struct file_lease *fl = locks_alloc_lease(); int error = -ENOMEM; if (fl == NULL) return ERR_PTR(error); - error = lease_init(filp, type, fl); + error = lease_init(filp, flags, type, fl); if (error) { - locks_free_lock(fl); + locks_free_lease(fl); return ERR_PTR(error); } return fl; @@ -655,29 +627,26 @@ static inline int locks_overlap(struct file_lock *fl1, struct file_lock *fl2) /* * Check whether two locks have the same owner. */ -static int posix_same_owner(struct file_lock *fl1, struct file_lock *fl2) +static int posix_same_owner(struct file_lock_core *fl1, struct file_lock_core *fl2) { - if (fl1->fl_lmops && fl1->fl_lmops->lm_compare_owner) - return fl2->fl_lmops == fl1->fl_lmops && - fl1->fl_lmops->lm_compare_owner(fl1, fl2); - return fl1->fl_owner == fl2->fl_owner; + return fl1->flc_owner == fl2->flc_owner; } /* Must be called with the flc_lock held! */ -static void locks_insert_global_locks(struct file_lock *fl) +static void locks_insert_global_locks(struct file_lock_core *flc) { struct file_lock_list_struct *fll = this_cpu_ptr(&file_lock_list); percpu_rwsem_assert_held(&file_rwsem); spin_lock(&fll->lock); - fl->fl_link_cpu = smp_processor_id(); - hlist_add_head(&fl->fl_link, &fll->hlist); + flc->flc_link_cpu = smp_processor_id(); + hlist_add_head(&flc->flc_link, &fll->hlist); spin_unlock(&fll->lock); } /* Must be called with the flc_lock held! */ -static void locks_delete_global_locks(struct file_lock *fl) +static void locks_delete_global_locks(struct file_lock_core *flc) { struct file_lock_list_struct *fll; @@ -688,35 +657,33 @@ static void locks_delete_global_locks(struct file_lock *fl) * is done while holding the flc_lock, and new insertions into the list * also require that it be held. */ - if (hlist_unhashed(&fl->fl_link)) + if (hlist_unhashed(&flc->flc_link)) return; - fll = per_cpu_ptr(&file_lock_list, fl->fl_link_cpu); + fll = per_cpu_ptr(&file_lock_list, flc->flc_link_cpu); spin_lock(&fll->lock); - hlist_del_init(&fl->fl_link); + hlist_del_init(&flc->flc_link); spin_unlock(&fll->lock); } static unsigned long -posix_owner_key(struct file_lock *fl) +posix_owner_key(struct file_lock_core *flc) { - if (fl->fl_lmops && fl->fl_lmops->lm_owner_key) - return fl->fl_lmops->lm_owner_key(fl); - return (unsigned long)fl->fl_owner; + return (unsigned long) flc->flc_owner; } -static void locks_insert_global_blocked(struct file_lock *waiter) +static void locks_insert_global_blocked(struct file_lock_core *waiter) { lockdep_assert_held(&blocked_lock_lock); - hash_add(blocked_hash, &waiter->fl_link, posix_owner_key(waiter)); + hash_add(blocked_hash, &waiter->flc_link, posix_owner_key(waiter)); } -static void locks_delete_global_blocked(struct file_lock *waiter) +static void locks_delete_global_blocked(struct file_lock_core *waiter) { lockdep_assert_held(&blocked_lock_lock); - hash_del(&waiter->fl_link); + hash_del(&waiter->flc_link); } /* Remove waiter from blocker's block list. @@ -724,60 +691,92 @@ static void locks_delete_global_blocked(struct file_lock *waiter) * * Must be called with blocked_lock_lock held. */ -static void __locks_delete_block(struct file_lock *waiter) +static void __locks_unlink_block(struct file_lock_core *waiter) { locks_delete_global_blocked(waiter); - list_del_init(&waiter->fl_blocked_member); - waiter->fl_blocker = NULL; + list_del_init(&waiter->flc_blocked_member); } -static void __locks_wake_up_blocks(struct file_lock *blocker) +static void __locks_wake_up_blocks(struct file_lock_core *blocker) { - while (!list_empty(&blocker->fl_blocked_requests)) { - struct file_lock *waiter; + while (!list_empty(&blocker->flc_blocked_requests)) { + struct file_lock_core *waiter; + struct file_lock *fl; - waiter = list_first_entry(&blocker->fl_blocked_requests, - struct file_lock, fl_blocked_member); - __locks_delete_block(waiter); - if (waiter->fl_lmops && waiter->fl_lmops->lm_notify) - waiter->fl_lmops->lm_notify(waiter); + waiter = list_first_entry(&blocker->flc_blocked_requests, + struct file_lock_core, flc_blocked_member); + + fl = file_lock(waiter); + __locks_unlink_block(waiter); + if ((waiter->flc_flags & (FL_POSIX | FL_FLOCK)) && + fl->fl_lmops && fl->fl_lmops->lm_notify) + fl->fl_lmops->lm_notify(fl); else - wake_up(&waiter->fl_wait); + locks_wake_up_waiter(waiter); + + /* + * The setting of flc_blocker to NULL marks the "done" + * point in deleting a block. Paired with acquire at the top + * of locks_delete_block(). + */ + smp_store_release(&waiter->flc_blocker, NULL); } } -/** - * locks_delete_lock - stop waiting for a file lock - * @waiter: the lock which was waiting - * - * lockd/nfsd need to disconnect the lock while working on it. - */ -int locks_delete_block(struct file_lock *waiter) +static int __locks_delete_block(struct file_lock_core *waiter) { int status = -ENOENT; /* - * If fl_blocker is NULL, it won't be set again as this thread - * "owns" the lock and is the only one that might try to claim - * the lock. So it is safe to test fl_blocker locklessly. - * Also if fl_blocker is NULL, this waiter is not listed on - * fl_blocked_requests for some lock, so no other request can - * be added to the list of fl_blocked_requests for this - * request. So if fl_blocker is NULL, it is safe to - * locklessly check if fl_blocked_requests is empty. If both - * of these checks succeed, there is no need to take the lock. + * If fl_blocker is NULL, it won't be set again as this thread "owns" + * the lock and is the only one that might try to claim the lock. + * + * We use acquire/release to manage fl_blocker so that we can + * optimize away taking the blocked_lock_lock in many cases. + * + * The smp_load_acquire guarantees two things: + * + * 1/ that fl_blocked_requests can be tested locklessly. If something + * was recently added to that list it must have been in a locked region + * *before* the locked region when fl_blocker was set to NULL. + * + * 2/ that no other thread is accessing 'waiter', so it is safe to free + * it. __locks_wake_up_blocks is careful not to touch waiter after + * fl_blocker is released. + * + * If a lockless check of fl_blocker shows it to be NULL, we know that + * no new locks can be inserted into its fl_blocked_requests list, and + * can avoid doing anything further if the list is empty. */ - if (waiter->fl_blocker == NULL && - list_empty(&waiter->fl_blocked_requests)) + if (!smp_load_acquire(&waiter->flc_blocker) && + list_empty(&waiter->flc_blocked_requests)) return status; + spin_lock(&blocked_lock_lock); - if (waiter->fl_blocker) + if (waiter->flc_blocker) status = 0; __locks_wake_up_blocks(waiter); - __locks_delete_block(waiter); + __locks_unlink_block(waiter); + + /* + * The setting of fl_blocker to NULL marks the "done" point in deleting + * a block. Paired with acquire at the top of this function. + */ + smp_store_release(&waiter->flc_blocker, NULL); spin_unlock(&blocked_lock_lock); return status; } + +/** + * locks_delete_block - stop waiting for a file lock + * @waiter: the lock which was waiting + * + * lockd/nfsd need to disconnect the lock while working on it. + */ +int locks_delete_block(struct file_lock *waiter) +{ + return __locks_delete_block(&waiter->c); +} EXPORT_SYMBOL(locks_delete_block); /* Insert waiter into blocker's block list. @@ -795,26 +794,28 @@ EXPORT_SYMBOL(locks_delete_block); * waiters, and add beneath any waiter that blocks the new waiter. * Thus wakeups don't happen until needed. */ -static void __locks_insert_block(struct file_lock *blocker, - struct file_lock *waiter, - bool conflict(struct file_lock *, - struct file_lock *)) +static void __locks_insert_block(struct file_lock_core *blocker, + struct file_lock_core *waiter, + bool conflict(struct file_lock_core *, + struct file_lock_core *)) { - struct file_lock *fl; - BUG_ON(!list_empty(&waiter->fl_blocked_member)); + struct file_lock_core *flc; + BUG_ON(!list_empty(&waiter->flc_blocked_member)); new_blocker: - list_for_each_entry(fl, &blocker->fl_blocked_requests, fl_blocked_member) - if (conflict(fl, waiter)) { - blocker = fl; + list_for_each_entry(flc, &blocker->flc_blocked_requests, flc_blocked_member) + if (conflict(flc, waiter)) { + blocker = flc; goto new_blocker; } - waiter->fl_blocker = blocker; - list_add_tail(&waiter->fl_blocked_member, &blocker->fl_blocked_requests); - if (IS_POSIX(blocker) && !IS_OFDLCK(blocker)) + waiter->flc_blocker = blocker; + list_add_tail(&waiter->flc_blocked_member, + &blocker->flc_blocked_requests); + + if ((blocker->flc_flags & (FL_POSIX|FL_OFDLCK)) == FL_POSIX) locks_insert_global_blocked(waiter); - /* The requests in waiter->fl_blocked are known to conflict with + /* The requests in waiter->flc_blocked are known to conflict with * waiter, but might not conflict with blocker, or the requests * and lock which block it. So they all need to be woken. */ @@ -822,10 +823,10 @@ new_blocker: } /* Must be called with flc_lock held. */ -static void locks_insert_block(struct file_lock *blocker, - struct file_lock *waiter, - bool conflict(struct file_lock *, - struct file_lock *)) +static void locks_insert_block(struct file_lock_core *blocker, + struct file_lock_core *waiter, + bool conflict(struct file_lock_core *, + struct file_lock_core *)) { spin_lock(&blocked_lock_lock); __locks_insert_block(blocker, waiter, conflict); @@ -837,7 +838,7 @@ static void locks_insert_block(struct file_lock *blocker, * * Must be called with the inode->flc_lock held! */ -static void locks_wake_up_blocks(struct file_lock *blocker) +static void locks_wake_up_blocks(struct file_lock_core *blocker) { /* * Avoid taking global lock if list is empty. This is safe since new @@ -846,7 +847,7 @@ static void locks_wake_up_blocks(struct file_lock *blocker) * fl_blocked_requests list does not require the flc_lock, so we must * recheck list_empty() after acquiring the blocked_lock_lock. */ - if (list_empty(&blocker->fl_blocked_requests)) + if (list_empty(&blocker->flc_blocked_requests)) return; spin_lock(&blocked_lock_lock); @@ -855,39 +856,39 @@ static void locks_wake_up_blocks(struct file_lock *blocker) } static void -locks_insert_lock_ctx(struct file_lock *fl, struct list_head *before) +locks_insert_lock_ctx(struct file_lock_core *fl, struct list_head *before) { - list_add_tail(&fl->fl_list, before); + list_add_tail(&fl->flc_list, before); locks_insert_global_locks(fl); } static void -locks_unlink_lock_ctx(struct file_lock *fl) +locks_unlink_lock_ctx(struct file_lock_core *fl) { locks_delete_global_locks(fl); - list_del_init(&fl->fl_list); + list_del_init(&fl->flc_list); locks_wake_up_blocks(fl); } static void -locks_delete_lock_ctx(struct file_lock *fl, struct list_head *dispose) +locks_delete_lock_ctx(struct file_lock_core *fl, struct list_head *dispose) { locks_unlink_lock_ctx(fl); if (dispose) - list_add(&fl->fl_list, dispose); + list_add(&fl->flc_list, dispose); else - locks_free_lock(fl); + locks_free_lock(file_lock(fl)); } /* Determine if lock sys_fl blocks lock caller_fl. Common functionality * checks for shared/exclusive status of overlapping locks. */ -static bool locks_conflict(struct file_lock *caller_fl, - struct file_lock *sys_fl) +static bool locks_conflict(struct file_lock_core *caller_flc, + struct file_lock_core *sys_flc) { - if (sys_fl->fl_type == F_WRLCK) + if (sys_flc->flc_type == F_WRLCK) return true; - if (caller_fl->fl_type == F_WRLCK) + if (caller_flc->flc_type == F_WRLCK) return true; return false; } @@ -895,37 +896,56 @@ static bool locks_conflict(struct file_lock *caller_fl, /* Determine if lock sys_fl blocks lock caller_fl. POSIX specific * checking before calling the locks_conflict(). */ -static bool posix_locks_conflict(struct file_lock *caller_fl, - struct file_lock *sys_fl) +static bool posix_locks_conflict(struct file_lock_core *caller_flc, + struct file_lock_core *sys_flc) { + struct file_lock *caller_fl = file_lock(caller_flc); + struct file_lock *sys_fl = file_lock(sys_flc); + /* POSIX locks owned by the same process do not conflict with * each other. */ - if (posix_same_owner(caller_fl, sys_fl)) + if (posix_same_owner(caller_flc, sys_flc)) return false; /* Check whether they overlap */ if (!locks_overlap(caller_fl, sys_fl)) return false; - return locks_conflict(caller_fl, sys_fl); + return locks_conflict(caller_flc, sys_flc); +} + +/* Determine if lock sys_fl blocks lock caller_fl. Used on xx_GETLK + * path so checks for additional GETLK-specific things like F_UNLCK. + */ +static bool posix_test_locks_conflict(struct file_lock *caller_fl, + struct file_lock *sys_fl) +{ + struct file_lock_core *caller = &caller_fl->c; + struct file_lock_core *sys = &sys_fl->c; + + /* F_UNLCK checks any locks on the same fd. */ + if (lock_is_unlock(caller_fl)) { + if (!posix_same_owner(caller, sys)) + return false; + return locks_overlap(caller_fl, sys_fl); + } + return posix_locks_conflict(caller, sys); } /* Determine if lock sys_fl blocks lock caller_fl. FLOCK specific * checking before calling the locks_conflict(). */ -static bool flock_locks_conflict(struct file_lock *caller_fl, - struct file_lock *sys_fl) +static bool flock_locks_conflict(struct file_lock_core *caller_flc, + struct file_lock_core *sys_flc) { /* FLOCK locks referring to the same filp do not conflict with * each other. */ - if (caller_fl->fl_file == sys_fl->fl_file) - return false; - if ((caller_fl->fl_type & LOCK_MAND) || (sys_fl->fl_type & LOCK_MAND)) + if (caller_flc->flc_file == sys_flc->flc_file) return false; - return locks_conflict(caller_fl, sys_fl); + return locks_conflict(caller_flc, sys_flc); } void @@ -933,22 +953,35 @@ posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; struct file_lock_context *ctx; - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); + void *owner; + void (*func)(void); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx || list_empty_careful(&ctx->flc_posix)) { - fl->fl_type = F_UNLCK; + fl->c.flc_type = F_UNLCK; return; } +retry: spin_lock(&ctx->flc_lock); - list_for_each_entry(cfl, &ctx->flc_posix, fl_list) { - if (posix_locks_conflict(fl, cfl)) { - locks_copy_conflock(fl, cfl); - goto out; + list_for_each_entry(cfl, &ctx->flc_posix, c.flc_list) { + if (!posix_test_locks_conflict(fl, cfl)) + continue; + if (cfl->fl_lmops && cfl->fl_lmops->lm_lock_expirable + && (*cfl->fl_lmops->lm_lock_expirable)(cfl)) { + owner = cfl->fl_lmops->lm_mod_owner; + func = cfl->fl_lmops->lm_expire_lock; + __module_get(owner); + spin_unlock(&ctx->flc_lock); + (*func)(); + module_put(owner); + goto retry; } + locks_copy_conflock(fl, cfl); + goto out; } - fl->fl_type = F_UNLCK; + fl->c.flc_type = F_UNLCK; out: spin_unlock(&ctx->flc_lock); return; @@ -990,25 +1023,27 @@ EXPORT_SYMBOL(posix_test_lock); #define MAX_DEADLK_ITERATIONS 10 -/* Find a lock that the owner of the given block_fl is blocking on. */ -static struct file_lock *what_owner_is_waiting_for(struct file_lock *block_fl) +/* Find a lock that the owner of the given @blocker is blocking on. */ +static struct file_lock_core *what_owner_is_waiting_for(struct file_lock_core *blocker) { - struct file_lock *fl; + struct file_lock_core *flc; - hash_for_each_possible(blocked_hash, fl, fl_link, posix_owner_key(block_fl)) { - if (posix_same_owner(fl, block_fl)) { - while (fl->fl_blocker) - fl = fl->fl_blocker; - return fl; + hash_for_each_possible(blocked_hash, flc, flc_link, posix_owner_key(blocker)) { + if (posix_same_owner(flc, blocker)) { + while (flc->flc_blocker) + flc = flc->flc_blocker; + return flc; } } 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) +static bool posix_locks_deadlock(struct file_lock *caller_fl, + struct file_lock *block_fl) { + struct file_lock_core *caller = &caller_fl->c; + struct file_lock_core *blocker = &block_fl->c; int i = 0; lockdep_assert_held(&blocked_lock_lock); @@ -1017,16 +1052,16 @@ static int posix_locks_deadlock(struct file_lock *caller_fl, * 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; + if (caller->flc_flags & FL_OFDLCK) + return false; - while ((block_fl = what_owner_is_waiting_for(block_fl))) { + while ((blocker = what_owner_is_waiting_for(blocker))) { if (i++ > MAX_DEADLK_ITERATIONS) - return 0; - if (posix_same_owner(caller_fl, block_fl)) - return 1; + return false; + if (posix_same_owner(caller, blocker)) + return true; } - return 0; + return false; } /* Try to create a FLOCK lock on filp. We always insert new FLOCK locks @@ -1045,62 +1080,62 @@ static int flock_lock_inode(struct inode *inode, struct file_lock *request) bool found = false; LIST_HEAD(dispose); - ctx = locks_get_lock_context(inode, request->fl_type); + ctx = locks_get_lock_context(inode, request->c.flc_type); if (!ctx) { - if (request->fl_type != F_UNLCK) + if (request->c.flc_type != F_UNLCK) return -ENOMEM; - return (request->fl_flags & FL_EXISTS) ? -ENOENT : 0; + return (request->c.flc_flags & FL_EXISTS) ? -ENOENT : 0; } - if (!(request->fl_flags & FL_ACCESS) && (request->fl_type != F_UNLCK)) { + if (!(request->c.flc_flags & FL_ACCESS) && (request->c.flc_type != F_UNLCK)) { new_fl = locks_alloc_lock(); if (!new_fl) return -ENOMEM; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); - if (request->fl_flags & FL_ACCESS) + if (request->c.flc_flags & FL_ACCESS) goto find_conflict; - list_for_each_entry(fl, &ctx->flc_flock, fl_list) { - if (request->fl_file != fl->fl_file) + list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) { + if (request->c.flc_file != fl->c.flc_file) continue; - if (request->fl_type == fl->fl_type) + if (request->c.flc_type == fl->c.flc_type) goto out; found = true; - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(&fl->c, &dispose); break; } - if (request->fl_type == F_UNLCK) { - if ((request->fl_flags & FL_EXISTS) && !found) + if (lock_is_unlock(request)) { + if ((request->c.flc_flags & FL_EXISTS) && !found) error = -ENOENT; goto out; } find_conflict: - list_for_each_entry(fl, &ctx->flc_flock, fl_list) { - if (!flock_locks_conflict(request, fl)) + list_for_each_entry(fl, &ctx->flc_flock, c.flc_list) { + if (!flock_locks_conflict(&request->c, &fl->c)) continue; error = -EAGAIN; - if (!(request->fl_flags & FL_SLEEP)) + if (!(request->c.flc_flags & FL_SLEEP)) goto out; error = FILE_LOCK_DEFERRED; - locks_insert_block(fl, request, flock_locks_conflict); + locks_insert_block(&fl->c, &request->c, flock_locks_conflict); goto out; } - if (request->fl_flags & FL_ACCESS) + if (request->c.flc_flags & FL_ACCESS) goto out; locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); - locks_insert_lock_ctx(new_fl, &ctx->flc_flock); + locks_insert_lock_ctx(&new_fl->c, &ctx->flc_flock); new_fl = NULL; error = 0; out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); if (new_fl) locks_free_lock(new_fl); locks_dispose_list(&dispose); @@ -1120,10 +1155,12 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, int error; bool added = false; LIST_HEAD(dispose); + void *owner; + void (*func)(void); - ctx = locks_get_lock_context(inode, request->fl_type); + ctx = locks_get_lock_context(inode, request->c.flc_type); if (!ctx) - return (request->fl_type == F_UNLCK) ? 0 : -ENOMEM; + return lock_is_unlock(request) ? 0 : -ENOMEM; /* * We may need two file_lock structures for this operation, @@ -1131,28 +1168,40 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, * * In some cases we can be sure, that no new locks will be needed */ - if (!(request->fl_flags & FL_ACCESS) && - (request->fl_type != F_UNLCK || + if (!(request->c.flc_flags & FL_ACCESS) && + (request->c.flc_type != F_UNLCK || request->fl_start != 0 || request->fl_end != OFFSET_MAX)) { new_fl = locks_alloc_lock(); new_fl2 = locks_alloc_lock(); } - percpu_down_read_preempt_disable(&file_rwsem); +retry: + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_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) { - list_for_each_entry(fl, &ctx->flc_posix, fl_list) { - if (!posix_locks_conflict(request, fl)) + if (request->c.flc_type != F_UNLCK) { + list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) { + if (!posix_locks_conflict(&request->c, &fl->c)) continue; + if (fl->fl_lmops && fl->fl_lmops->lm_lock_expirable + && (*fl->fl_lmops->lm_lock_expirable)(fl)) { + owner = fl->fl_lmops->lm_mod_owner; + func = fl->fl_lmops->lm_expire_lock; + __module_get(owner); + spin_unlock(&ctx->flc_lock); + percpu_up_read(&file_rwsem); + (*func)(); + module_put(owner); + goto retry; + } if (conflock) locks_copy_conflock(conflock, fl); error = -EAGAIN; - if (!(request->fl_flags & FL_SLEEP)) + if (!(request->c.flc_flags & FL_SLEEP)) goto out; /* * Deadlock detection and insertion into the blocked @@ -1160,9 +1209,14 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, */ error = -EDEADLK; spin_lock(&blocked_lock_lock); + /* + * Ensure that we don't find any locks blocked on this + * request during deadlock detection. + */ + __locks_wake_up_blocks(&request->c); if (likely(!posix_locks_deadlock(request, fl))) { error = FILE_LOCK_DEFERRED; - __locks_insert_block(fl, request, + __locks_insert_block(&fl->c, &request->c, posix_locks_conflict); } spin_unlock(&blocked_lock_lock); @@ -1172,22 +1226,22 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, /* If we're just looking for a conflict, we're done. */ error = 0; - if (request->fl_flags & FL_ACCESS) + if (request->c.flc_flags & FL_ACCESS) goto out; /* Find the first old lock with the same owner as the new lock */ - list_for_each_entry(fl, &ctx->flc_posix, fl_list) { - if (posix_same_owner(request, fl)) + list_for_each_entry(fl, &ctx->flc_posix, c.flc_list) { + if (posix_same_owner(&request->c, &fl->c)) break; } /* Process locks with this owner. */ - list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, fl_list) { - if (!posix_same_owner(request, fl)) + list_for_each_entry_safe_from(fl, tmp, &ctx->flc_posix, c.flc_list) { + if (!posix_same_owner(&request->c, &fl->c)) break; /* Detect adjacent or overlapping regions (if same lock type) */ - if (request->fl_type == fl->fl_type) { + if (request->c.flc_type == fl->c.flc_type) { /* In all comparisons of start vs end, use * "start - 1" rather than "end + 1". If end * is OFFSET_MAX, end + 1 will become negative. @@ -1214,7 +1268,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, else request->fl_end = fl->fl_end; if (added) { - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(&fl->c, &dispose); continue; } request = fl; @@ -1227,7 +1281,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, continue; if (fl->fl_start > request->fl_end) break; - if (request->fl_type == F_UNLCK) + if (lock_is_unlock(request)) added = true; if (fl->fl_start < request->fl_start) left = fl; @@ -1243,7 +1297,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, * one (This may happen several times). */ if (added) { - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(&fl->c, &dispose); continue; } /* @@ -1257,10 +1311,12 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, if (!new_fl) goto out; locks_copy_lock(new_fl, request); + locks_move_blocks(new_fl, request); request = new_fl; new_fl = NULL; - locks_insert_lock_ctx(request, &fl->fl_list); - locks_delete_lock_ctx(fl, &dispose); + locks_insert_lock_ctx(&request->c, + &fl->c.flc_list); + locks_delete_lock_ctx(&fl->c, &dispose); added = true; } } @@ -1277,8 +1333,8 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, error = 0; if (!added) { - if (request->fl_type == F_UNLCK) { - if (request->fl_flags & FL_EXISTS) + if (lock_is_unlock(request)) { + if (request->c.flc_flags & FL_EXISTS) error = -ENOENT; goto out; } @@ -1289,7 +1345,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, } locks_copy_lock(new_fl, request); locks_move_blocks(new_fl, request); - locks_insert_lock_ctx(new_fl, &fl->fl_list); + locks_insert_lock_ctx(&new_fl->c, &fl->c.flc_list); fl = new_fl; new_fl = NULL; } @@ -1301,18 +1357,19 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, left = new_fl2; new_fl2 = NULL; locks_copy_lock(left, right); - locks_insert_lock_ctx(left, &fl->fl_list); + locks_insert_lock_ctx(&left->c, &fl->c.flc_list); } right->fl_start = request->fl_end + 1; - locks_wake_up_blocks(right); + locks_wake_up_blocks(&right->c); } if (left) { left->fl_end = request->fl_start - 1; - locks_wake_up_blocks(left); + locks_wake_up_blocks(&left->c); } out: + trace_posix_lock_inode(inode, request, error); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); /* * Free any unused locks. */ @@ -1321,7 +1378,6 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, if (new_fl2) locks_free_lock(new_fl2); locks_dispose_list(&dispose); - trace_posix_lock_inode(inode, request, error); return error; } @@ -1343,7 +1399,7 @@ static int posix_lock_inode(struct inode *inode, struct file_lock *request, int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { - return posix_lock_inode(locks_inode(filp), fl, conflock); + return posix_lock_inode(file_inode(filp), fl, conflock); } EXPORT_SYMBOL(posix_lock_file); @@ -1362,7 +1418,8 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) error = posix_lock_inode(inode, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; - error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker); + error = wait_event_interruptible(fl->c.flc_wait, + list_empty(&fl->c.flc_blocked_member)); if (error) break; } @@ -1370,133 +1427,37 @@ static int posix_lock_inode_wait(struct inode *inode, struct file_lock *fl) return error; } -#ifdef CONFIG_MANDATORY_FILE_LOCKING -/** - * locks_mandatory_locked - Check for an active lock - * @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 file *file) -{ - int ret; - struct inode *inode = locks_inode(file); - struct file_lock_context *ctx; - struct file_lock *fl; - - ctx = smp_load_acquire(&inode->i_flctx); - if (!ctx || list_empty_careful(&ctx->flc_posix)) - return 0; - - /* - * Search the lock list for this inode for any POSIX locks. - */ - spin_lock(&ctx->flc_lock); - ret = 0; - list_for_each_entry(fl, &ctx->flc_posix, fl_list) { - if (fl->fl_owner != current->files && - fl->fl_owner != file) { - ret = -EAGAIN; - break; - } - } - spin_unlock(&ctx->flc_lock); - return ret; -} - -/** - * locks_mandatory_area - Check for a conflicting lock - * @inode: the file to check - * @filp: how the file was opened (if it was) - * @start: first byte in the file to check - * @end: lastbyte in the file to check - * @type: %F_WRLCK for a write lock, else %F_RDLCK - * - * Searches the inode's list of locks to find any POSIX locks which conflict. - */ -int locks_mandatory_area(struct inode *inode, struct file *filp, loff_t start, - loff_t end, unsigned char type) -{ - struct file_lock fl; - int error; - bool sleep = false; - - locks_init_lock(&fl); - fl.fl_pid = current->tgid; - fl.fl_file = filp; - fl.fl_flags = FL_POSIX | FL_ACCESS; - if (filp && !(filp->f_flags & O_NONBLOCK)) - sleep = true; - fl.fl_type = type; - fl.fl_start = start; - fl.fl_end = end; - - for (;;) { - if (filp) { - fl.fl_owner = filp; - fl.fl_flags &= ~FL_SLEEP; - error = posix_lock_inode(inode, &fl, NULL); - if (!error) - break; - } - - if (sleep) - fl.fl_flags |= FL_SLEEP; - fl.fl_owner = current->files; - error = posix_lock_inode(inode, &fl, NULL); - if (error != FILE_LOCK_DEFERRED) - break; - error = wait_event_interruptible(fl.fl_wait, !fl.fl_blocker); - if (!error) { - /* - * If we've been sleeping someone might have - * changed the permissions behind our back. - */ - if (__mandatory_lock(inode)) - continue; - } - - break; - } - locks_delete_block(&fl); - - return error; -} -EXPORT_SYMBOL(locks_mandatory_area); -#endif /* CONFIG_MANDATORY_FILE_LOCKING */ - -static void lease_clear_pending(struct file_lock *fl, int arg) +static void lease_clear_pending(struct file_lease *fl, int arg) { switch (arg) { case F_UNLCK: - fl->fl_flags &= ~FL_UNLOCK_PENDING; - /* fall through: */ + fl->c.flc_flags &= ~FL_UNLOCK_PENDING; + fallthrough; case F_RDLCK: - fl->fl_flags &= ~FL_DOWNGRADE_PENDING; + fl->c.flc_flags &= ~FL_DOWNGRADE_PENDING; } } /* We already had a lease on this file; just change its type */ -int lease_modify(struct file_lock *fl, int arg, struct list_head *dispose) +int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { - int error = assign_type(fl, arg); + int error = assign_type(&fl->c, arg); if (error) return error; lease_clear_pending(fl, arg); - locks_wake_up_blocks(fl); + locks_wake_up_blocks(&fl->c); if (arg == F_UNLCK) { - struct file *filp = fl->fl_file; + struct file *filp = fl->c.flc_file; f_delown(filp); - filp->f_owner.signum = 0; - fasync_helper(0, fl->fl_file, 0, &fl->fl_fasync); + file_f_owner(filp)->signum = 0; + fasync_helper(0, fl->c.flc_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_ctx(fl, dispose); + locks_delete_lock_ctx(&fl->c, dispose); } return 0; } @@ -1513,11 +1474,11 @@ static bool past_time(unsigned long then) static void time_out_leases(struct inode *inode, struct list_head *dispose) { struct file_lock_context *ctx = inode->i_flctx; - struct file_lock *fl, *tmp; + struct file_lease *fl, *tmp; lockdep_assert_held(&ctx->flc_lock); - list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) { trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) lease_modify(fl, F_RDLCK, dispose); @@ -1526,25 +1487,40 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose) } } -static bool leases_conflict(struct file_lock *lease, struct file_lock *breaker) +static bool leases_conflict(struct file_lock_core *lc, struct file_lock_core *bc) { - if ((breaker->fl_flags & FL_LAYOUT) != (lease->fl_flags & FL_LAYOUT)) - return false; - if ((breaker->fl_flags & FL_DELEG) && (lease->fl_flags & FL_LEASE)) + bool rc; + struct file_lease *lease = file_lease(lc); + struct file_lease *breaker = file_lease(bc); + + if (lease->fl_lmops->lm_breaker_owns_lease + && lease->fl_lmops->lm_breaker_owns_lease(lease)) return false; - return locks_conflict(breaker, lease); + if ((bc->flc_flags & FL_LAYOUT) != (lc->flc_flags & FL_LAYOUT)) { + rc = false; + goto trace; + } + if ((bc->flc_flags & FL_DELEG) && (lc->flc_flags & FL_LEASE)) { + rc = false; + goto trace; + } + + rc = locks_conflict(bc, lc); +trace: + trace_leases_conflict(rc, lease, breaker); + return rc; } static bool -any_leases_conflict(struct inode *inode, struct file_lock *breaker) +any_leases_conflict(struct inode *inode, struct file_lease *breaker) { struct file_lock_context *ctx = inode->i_flctx; - struct file_lock *fl; + struct file_lock_core *flc; lockdep_assert_held(&ctx->flc_lock); - list_for_each_entry(fl, &ctx->flc_lease, fl_list) { - if (leases_conflict(fl, breaker)) + list_for_each_entry(flc, &ctx->flc_lease, flc_list) { + if (leases_conflict(flc, &breaker->c)) return true; } return false; @@ -1553,38 +1529,44 @@ any_leases_conflict(struct inode *inode, struct file_lock *breaker) /** * __break_lease - revoke all outstanding leases on file * @inode: the inode of the file to return - * @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 + * @flags: LEASE_BREAK_* flags * * 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(). + * a call to open() or truncate(). This function can block waiting for the + * lease break unless you specify LEASE_BREAK_NONBLOCK. */ -int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) +int __break_lease(struct inode *inode, unsigned int flags) { - int error = 0; + struct file_lease *new_fl, *fl, *tmp; struct file_lock_context *ctx; - struct file_lock *new_fl, *fl, *tmp; unsigned long break_time; - int want_write = (mode & O_ACCMODE) != O_RDONLY; + unsigned int type; LIST_HEAD(dispose); + bool want_write = !(flags & LEASE_BREAK_OPEN_RDONLY); + int error = 0; - new_fl = lease_alloc(NULL, want_write ? F_WRLCK : F_RDLCK); + if (flags & LEASE_BREAK_LEASE) + type = FL_LEASE; + else if (flags & LEASE_BREAK_DELEG) + type = FL_DELEG; + else if (flags & LEASE_BREAK_LAYOUT) + type = FL_LAYOUT; + else + return -EINVAL; + + new_fl = lease_alloc(NULL, type, want_write ? F_WRLCK : F_RDLCK); if (IS_ERR(new_fl)) return PTR_ERR(new_fl); - new_fl->fl_flags = type; /* typically we will check that ctx is non-NULL before calling */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) { WARN_ON_ONCE(1); - return error; + goto free_lock; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); @@ -1599,53 +1581,54 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) break_time++; /* so that 0 means no break time */ } - list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) { - if (!leases_conflict(fl, new_fl)) + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) { + if (!leases_conflict(&fl->c, &new_fl->c)) continue; if (want_write) { - if (fl->fl_flags & FL_UNLOCK_PENDING) + if (fl->c.flc_flags & FL_UNLOCK_PENDING) continue; - fl->fl_flags |= FL_UNLOCK_PENDING; + fl->c.flc_flags |= FL_UNLOCK_PENDING; fl->fl_break_time = break_time; } else { if (lease_breaking(fl)) continue; - fl->fl_flags |= FL_DOWNGRADE_PENDING; + fl->c.flc_flags |= FL_DOWNGRADE_PENDING; fl->fl_downgrade_time = break_time; } if (fl->fl_lmops->lm_break(fl)) - locks_delete_lock_ctx(fl, &dispose); + locks_delete_lock_ctx(&fl->c, &dispose); } if (list_empty(&ctx->flc_lease)) goto out; - if (mode & O_NONBLOCK) { + if (flags & LEASE_BREAK_NONBLOCK) { trace_break_lease_noblock(inode, new_fl); error = -EWOULDBLOCK; goto out; } restart: - fl = list_first_entry(&ctx->flc_lease, struct file_lock, fl_list); + fl = list_first_entry(&ctx->flc_lease, struct file_lease, c.flc_list); break_time = fl->fl_break_time; if (break_time != 0) break_time -= jiffies; if (break_time == 0) break_time++; - locks_insert_block(fl, new_fl, leases_conflict); + locks_insert_block(&fl->c, &new_fl->c, leases_conflict); trace_break_lease_block(inode, new_fl); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); - error = wait_event_interruptible_timeout(new_fl->fl_wait, - !new_fl->fl_blocker, break_time); + error = wait_event_interruptible_timeout(new_fl->c.flc_wait, + list_empty(&new_fl->c.flc_blocked_member), + break_time); - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); trace_break_lease_unblock(inode, new_fl); - locks_delete_block(new_fl); + __locks_delete_block(&new_fl->c); if (error >= 0) { /* * Wait for the next conflicting lease that has not been @@ -1659,9 +1642,10 @@ restart: } out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); - locks_free_lock(new_fl); +free_lock: + locks_free_lease(new_fl); return error; } EXPORT_SYMBOL(__break_lease); @@ -1679,14 +1663,14 @@ void lease_get_mtime(struct inode *inode, struct timespec64 *time) { bool has_lease = false; struct file_lock_context *ctx; - struct file_lock *fl; + struct file_lock_core *flc; - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { spin_lock(&ctx->flc_lock); - fl = list_first_entry_or_null(&ctx->flc_lease, - struct file_lock, fl_list); - if (fl && (fl->fl_type == F_WRLCK)) + flc = list_first_entry_or_null(&ctx->flc_lease, + struct file_lock_core, flc_list); + if (flc && flc->flc_type == F_WRLCK) has_lease = true; spin_unlock(&ctx->flc_lock); } @@ -1697,8 +1681,9 @@ void lease_get_mtime(struct inode *inode, struct timespec64 *time) EXPORT_SYMBOL(lease_get_mtime); /** - * fcntl_getlease - Enquire what lease is currently active + * __fcntl_getlease - Enquire what lease is currently active * @filp: the file + * @flavor: type of lease flags to check * * The value returned by this function will be one of * (if no lease break is pending): @@ -1719,38 +1704,52 @@ EXPORT_SYMBOL(lease_get_mtime); * XXX: sfr & willy disagree over whether F_INPROGRESS * should be returned to userspace. */ -int fcntl_getlease(struct file *filp) +static int __fcntl_getlease(struct file *filp, unsigned int flavor) { - struct file_lock *fl; - struct inode *inode = locks_inode(filp); + struct file_lease *fl; + struct inode *inode = file_inode(filp); struct file_lock_context *ctx; int type = F_UNLCK; LIST_HEAD(dispose); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (ctx && !list_empty_careful(&ctx->flc_lease)) { - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); - list_for_each_entry(fl, &ctx->flc_lease, fl_list) { - if (fl->fl_file != filp) + list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { + if (fl->c.flc_file != filp) continue; - type = target_leasetype(fl); + if (fl->c.flc_flags & flavor) + type = target_leasetype(fl); break; } spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } return type; } +int fcntl_getlease(struct file *filp) +{ + return __fcntl_getlease(filp, FL_LEASE); +} + +int fcntl_getdeleg(struct file *filp, struct delegation *deleg) +{ + if (deleg->d_flags != 0 || deleg->__pad != 0) + return -EINVAL; + deleg->d_type = __fcntl_getlease(filp, FL_DELEG); + return 0; +} + /** - * check_conflicting_open - see if the given dentry points to a file that has + * check_conflicting_open - see if the given file points to an inode that has * an existing open that would conflict with the * desired lease. - * @dentry: dentry to check + * @filp: file to check * @arg: type of lease that we're trying to acquire * @flags: current lock flags * @@ -1758,38 +1757,57 @@ int fcntl_getlease(struct file *filp) * conflict with the lease we're trying to set. */ static int -check_conflicting_open(const struct dentry *dentry, const long arg, int flags) +check_conflicting_open(struct file *filp, const int arg, int flags) { - int ret = 0; - struct inode *inode = dentry->d_inode; + struct inode *inode = file_inode(filp); + int self_wcount = 0, self_rcount = 0; if (flags & FL_LAYOUT) return 0; + if (flags & FL_DELEG) + /* We leave these checks to the caller */ + return 0; - if ((arg == F_RDLCK) && inode_is_open_for_write(inode)) - return -EAGAIN; + if (arg == F_RDLCK) + return inode_is_open_for_write(inode) ? -EAGAIN : 0; + else if (arg != F_WRLCK) + return 0; - if ((arg == F_WRLCK) && ((d_count(dentry) > 1) || - (atomic_read(&inode->i_count) > 1))) - ret = -EAGAIN; + /* + * Make sure that only read/write count is from lease requestor. + * Note that this will result in denying write leases when i_writecount + * is negative, which is what we want. (We shouldn't grant write leases + * on files open for execution.) + */ + if (filp->f_mode & FMODE_WRITE) + self_wcount = 1; + else if (filp->f_mode & FMODE_READ) + self_rcount = 1; - return ret; + if (atomic_read(&inode->i_writecount) != self_wcount || + atomic_read(&inode->i_readcount) != self_rcount) + return -EAGAIN; + + return 0; } static int -generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **priv) +generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **priv) { - struct file_lock *fl, *my_fl = NULL, *lease; - struct dentry *dentry = filp->f_path.dentry; - struct inode *inode = dentry->d_inode; + struct file_lease *fl, *my_fl = NULL, *lease; + struct inode *inode = file_inode(filp); struct file_lock_context *ctx; - bool is_deleg = (*flp)->fl_flags & FL_DELEG; + bool is_deleg = (*flp)->c.flc_flags & FL_DELEG; int error; LIST_HEAD(dispose); lease = *flp; trace_generic_add_lease(inode, lease); + error = file_f_owner_allocate(filp); + if (error) + return error; + /* Note that arg is never F_UNLCK here */ ctx = locks_get_lock_context(inode, arg); if (!ctx) @@ -1797,7 +1815,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr /* * In the delegation case we need mutual exclusion with - * a number of operations that take the i_mutex. We trylock + * a number of operations that take the i_rwsem. 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 @@ -1806,17 +1824,10 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr if (is_deleg && !inode_trylock(inode)) return -EAGAIN; - if (is_deleg && arg == F_WRLCK) { - /* Write delegations are not currently supported: */ - inode_unlock(inode); - WARN_ON_ONCE(1); - return -EINVAL; - } - - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); - error = check_conflicting_open(dentry, arg, lease->fl_flags); + error = check_conflicting_open(filp, arg, lease->c.flc_flags); if (error) goto out; @@ -1829,9 +1840,9 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr * except for this filp. */ error = -EAGAIN; - list_for_each_entry(fl, &ctx->flc_lease, fl_list) { - if (fl->fl_file == filp && - fl->fl_owner == lease->fl_owner) { + list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { + if (fl->c.flc_file == filp && + fl->c.flc_owner == lease->c.flc_owner) { my_fl = fl; continue; } @@ -1846,7 +1857,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr * 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) + if (fl->c.flc_flags & FL_UNLOCK_PENDING) goto out; } @@ -1862,7 +1873,7 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr if (!leases_enable) goto out; - locks_insert_lock_ctx(lease, &ctx->flc_lease); + locks_insert_lock_ctx(&lease->c, &ctx->flc_lease); /* * 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 @@ -1873,9 +1884,9 @@ generic_add_lease(struct file *filp, long arg, struct file_lock **flp, void **pr * precedes these checks. */ smp_mb(); - error = check_conflicting_open(dentry, arg, lease->fl_flags); + error = check_conflicting_open(filp, arg, lease->c.flc_flags); if (error) { - locks_unlink_lock_ctx(lease); + locks_unlink_lock_ctx(&lease->c); goto out; } @@ -1884,7 +1895,7 @@ out_setup: lease->fl_lmops->lm_setup(lease, priv); out: spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); @@ -1896,22 +1907,22 @@ out: static int generic_delete_lease(struct file *filp, void *owner) { int error = -EAGAIN; - struct file_lock *fl, *victim = NULL; - struct inode *inode = locks_inode(filp); + struct file_lease *fl, *victim = NULL; + struct inode *inode = file_inode(filp); struct file_lock_context *ctx; LIST_HEAD(dispose); - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) { trace_generic_delete_lease(inode, NULL); return error; } - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); - list_for_each_entry(fl, &ctx->flc_lease, fl_list) { - if (fl->fl_file == filp && - fl->fl_owner == owner) { + list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) { + if (fl->c.flc_file == filp && + fl->c.flc_owner == owner) { victim = fl; break; } @@ -1920,7 +1931,7 @@ static int generic_delete_lease(struct file *filp, void *owner) if (victim) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); return error; } @@ -1936,25 +1947,22 @@ static int generic_delete_lease(struct file *filp, void *owner) * The (input) flp->fl_lmops->lm_break function is required * by break_lease(). */ -int generic_setlease(struct file *filp, long arg, struct file_lock **flp, +int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { - struct inode *inode = locks_inode(filp); - int error; + struct inode *inode = file_inode(filp); - if ((!uid_eq(current_fsuid(), inode->i_uid)) && !capable(CAP_LEASE)) - return -EACCES; - if (!S_ISREG(inode->i_mode)) + if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EINVAL; - error = security_file_lock(filp, arg); - if (error) - return error; switch (arg) { case F_UNLCK: return generic_delete_lease(filp, *priv); - case F_RDLCK: case F_WRLCK: + if (S_ISDIR(inode->i_mode)) + return -EINVAL; + fallthrough; + case F_RDLCK: if (!(*flp)->fl_lmops->lm_break) { WARN_ON_ONCE(1); return -ENOLCK; @@ -1967,6 +1975,52 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp, } EXPORT_SYMBOL(generic_setlease); +/* + * Kernel subsystems can register to be notified on any attempt to set + * a new lease with the lease_notifier_chain. This is used by (e.g.) nfsd + * to close files that it may have cached when there is an attempt to set a + * conflicting lease. + */ +static struct srcu_notifier_head lease_notifier_chain; + +static inline void +lease_notifier_chain_init(void) +{ + srcu_init_notifier_head(&lease_notifier_chain); +} + +static inline void +setlease_notifier(int arg, struct file_lease *lease) +{ + if (arg != F_UNLCK) + srcu_notifier_call_chain(&lease_notifier_chain, arg, lease); +} + +int lease_register_notifier(struct notifier_block *nb) +{ + return srcu_notifier_chain_register(&lease_notifier_chain, nb); +} +EXPORT_SYMBOL_GPL(lease_register_notifier); + +void lease_unregister_notifier(struct notifier_block *nb) +{ + srcu_notifier_chain_unregister(&lease_notifier_chain, nb); +} +EXPORT_SYMBOL_GPL(lease_unregister_notifier); + + +int +kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) +{ + if (lease) + setlease_notifier(arg, *lease); + if (filp->f_op->setlease) + return filp->f_op->setlease(filp, arg, lease, priv); + else + return generic_setlease(filp, arg, lease, priv); +} +EXPORT_SYMBOL_GPL(kernel_setlease); + /** * vfs_setlease - sets a lease on an open file * @filp: file pointer @@ -1985,35 +2039,41 @@ EXPORT_SYMBOL(generic_setlease); * may be NULL if the lm_setup operation doesn't require it. */ int -vfs_setlease(struct file *filp, long arg, struct file_lock **lease, void **priv) +vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { - if (filp->f_op->setlease) - return filp->f_op->setlease(filp, arg, lease, priv); - else - return generic_setlease(filp, arg, lease, priv); + struct inode *inode = file_inode(filp); + vfsuid_t vfsuid = i_uid_into_vfsuid(file_mnt_idmap(filp), inode); + int error; + + if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE)) + return -EACCES; + error = security_file_lock(filp, arg); + if (error) + return error; + return kernel_setlease(filp, arg, lease, priv); } EXPORT_SYMBOL_GPL(vfs_setlease); -static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg) +static int do_fcntl_add_lease(unsigned int fd, struct file *filp, unsigned int flavor, int arg) { - struct file_lock *fl; + struct file_lease *fl; struct fasync_struct *new; int error; - fl = lease_alloc(filp, arg); + fl = lease_alloc(filp, flavor, arg); if (IS_ERR(fl)) return PTR_ERR(fl); new = fasync_alloc(); if (!new) { - locks_free_lock(fl); + locks_free_lease(fl); return -ENOMEM; } new->fa_fd = fd; error = vfs_setlease(filp, arg, &fl, (void **)&new); if (fl) - locks_free_lock(fl); + locks_free_lease(fl); if (new) fasync_free(new); return error; @@ -2029,11 +2089,35 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, long arg) * Note that you also need to call %F_SETSIG to * receive a signal when the lease is broken. */ -int fcntl_setlease(unsigned int fd, struct file *filp, long arg) +int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { + if (S_ISDIR(file_inode(filp)->i_mode)) + return -EINVAL; + if (arg == F_UNLCK) return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp); - return do_fcntl_add_lease(fd, filp, arg); + return do_fcntl_add_lease(fd, filp, FL_LEASE, arg); +} + +/** + * fcntl_setdeleg - sets a delegation on an open file + * @fd: open file descriptor + * @filp: file pointer + * @deleg: delegation request from userland + * + * Call this fcntl to establish a delegation on the file. + * Note that you also need to call %F_SETSIG to + * receive a signal when the lease is broken. + */ +int fcntl_setdeleg(unsigned int fd, struct file *filp, struct delegation *deleg) +{ + /* For now, no flags are supported */ + if (deleg->d_flags != 0 || deleg->__pad != 0) + return -EINVAL; + + if (deleg->d_type == F_UNLCK) + return vfs_setlease(filp, F_UNLCK, NULL, (void **)&filp); + return do_fcntl_add_lease(fd, filp, FL_DELEG, deleg->d_type); } /** @@ -2051,7 +2135,8 @@ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) error = flock_lock_inode(inode, fl); if (error != FILE_LOCK_DEFERRED) break; - error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker); + error = wait_event_interruptible(fl->c.flc_wait, + list_empty(&fl->c.flc_blocked_member)); if (error) break; } @@ -2069,7 +2154,7 @@ static int flock_lock_inode_wait(struct inode *inode, struct file_lock *fl) int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { int res = 0; - switch (fl->fl_flags & (FL_POSIX|FL_FLOCK)) { + switch (fl->c.flc_flags & (FL_POSIX|FL_FLOCK)) { case FL_POSIX: res = posix_lock_inode_wait(inode, fl); break; @@ -2094,57 +2179,57 @@ EXPORT_SYMBOL(locks_lock_inode_wait); * - %LOCK_SH -- a shared lock. * - %LOCK_EX -- an exclusive lock. * - %LOCK_UN -- remove an existing lock. - * - %LOCK_MAND -- a 'mandatory' flock. - * This exists to emulate Windows Share Modes. + * - %LOCK_MAND -- a 'mandatory' flock. (DEPRECATED) * - * %LOCK_MAND can be combined with %LOCK_READ or %LOCK_WRITE to allow other - * processes read and write access respectively. + * %LOCK_MAND support has been removed from the kernel. */ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) { - struct fd f = fdget(fd); - struct file_lock *lock; - int can_sleep, unlock; - int error; + int can_sleep, error, type; + struct file_lock fl; - error = -EBADF; - if (!f.file) - goto out; + /* + * LOCK_MAND locks were broken for a long time in that they never + * conflicted with one another and didn't prevent any sort of open, + * read or write activity. + * + * Just ignore these requests now, to preserve legacy behavior, but + * throw a warning to let people know that they don't actually work. + */ + if (cmd & LOCK_MAND) { + pr_warn_once("%s(%d): Attempt to set a LOCK_MAND lock via flock(2). This support has been removed and the request ignored.\n", current->comm, current->pid); + return 0; + } - can_sleep = !(cmd & LOCK_NB); - cmd &= ~LOCK_NB; - unlock = (cmd == LOCK_UN); + type = flock_translate_cmd(cmd & ~LOCK_NB); + if (type < 0) + return type; - if (!unlock && !(cmd & LOCK_MAND) && - !(f.file->f_mode & (FMODE_READ|FMODE_WRITE))) - goto out_putf; + CLASS(fd, f)(fd); + if (fd_empty(f)) + return -EBADF; - lock = flock_make_lock(f.file, cmd, NULL); - if (IS_ERR(lock)) { - error = PTR_ERR(lock); - goto out_putf; - } + if (type != F_UNLCK && !(fd_file(f)->f_mode & (FMODE_READ | FMODE_WRITE))) + return -EBADF; - if (can_sleep) - lock->fl_flags |= FL_SLEEP; + flock_make_lock(fd_file(f), &fl, type); - error = security_file_lock(f.file, lock->fl_type); + error = security_file_lock(fd_file(f), fl.c.flc_type); if (error) - goto out_free; + return error; - if (f.file->f_op->flock) - error = f.file->f_op->flock(f.file, - (can_sleep) ? F_SETLKW : F_SETLK, - lock); - else - error = locks_lock_file_wait(f.file, lock); + can_sleep = !(cmd & LOCK_NB); + if (can_sleep) + fl.c.flc_flags |= FL_SLEEP; - out_free: - locks_free_lock(lock); + if (fd_file(f)->f_op->flock) + error = fd_file(f)->f_op->flock(fd_file(f), + (can_sleep) ? F_SETLKW : F_SETLK, + &fl); + else + error = locks_lock_file_wait(fd_file(f), &fl); - out_putf: - fdput(f); - out: + locks_release_private(&fl); return error; } @@ -2158,6 +2243,7 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { + WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, F_GETLK, fl); posix_test_lock(filp, fl); @@ -2170,27 +2256,30 @@ EXPORT_SYMBOL_GPL(vfs_test_lock); * @fl: The file_lock who's fl_pid should be translated * @ns: The namespace into which the pid should be translated * - * Used to tranlate a fl_pid into a namespace virtual pid number + * Used to translate a fl_pid into a namespace virtual pid number */ -static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns) +static pid_t locks_translate_pid(struct file_lock_core *fl, struct pid_namespace *ns) { pid_t vnr; struct pid *pid; - if (IS_OFDLCK(fl)) + if (fl->flc_flags & FL_OFDLCK) return -1; - if (IS_REMOTELCK(fl)) - return fl->fl_pid; + + /* Remote locks report a negative pid value */ + if (fl->flc_pid <= 0) + return fl->flc_pid; + /* * If the flock owner process is dead and its pid has been already * freed, the translation below won't work, but we still want to show * flock owner pid number in init pidns. */ if (ns == &init_pid_ns) - return (pid_t)fl->fl_pid; + return (pid_t) fl->flc_pid; rcu_read_lock(); - pid = find_pid_ns(fl->fl_pid, &init_pid_ns); + pid = find_pid_ns(fl->flc_pid, &init_pid_ns); vnr = pid_nr_ns(pid, ns); rcu_read_unlock(); return vnr; @@ -2198,7 +2287,7 @@ static pid_t locks_translate_pid(struct file_lock *fl, struct pid_namespace *ns) static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) { - flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current)); + flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current)); #if BITS_PER_LONG == 32 /* * Make sure we can represent the posix lock via @@ -2213,19 +2302,19 @@ static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; - flock->l_type = fl->fl_type; + flock->l_type = fl->c.flc_type; return 0; } #if BITS_PER_LONG == 32 static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) { - flock->l_pid = locks_translate_pid(fl, task_active_pid_ns(current)); + flock->l_pid = locks_translate_pid(&fl->c, task_active_pid_ns(current)); flock->l_start = fl->fl_start; flock->l_len = fl->fl_end == OFFSET_MAX ? 0 : fl->fl_end - fl->fl_start + 1; flock->l_whence = 0; - flock->l_type = fl->fl_type; + flock->l_type = fl->c.flc_type; } #endif @@ -2241,7 +2330,8 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock) if (fl == NULL) return -ENOMEM; error = -EINVAL; - if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) + if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK + && flock->l_type != F_WRLCK) goto out; error = flock_to_posix_lock(filp, fl, flock); @@ -2253,17 +2343,16 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock) if (flock->l_pid != 0) goto out; - cmd = F_GETLK; - fl->fl_flags |= FL_OFDLCK; - fl->fl_owner = filp; + fl->c.flc_flags |= FL_OFDLCK; + fl->c.flc_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; - flock->l_type = fl->fl_type; - if (fl->fl_type != F_UNLCK) { + flock->l_type = fl->c.flc_type; + if (fl->c.flc_type != F_UNLCK) { error = posix_lock_to_flock(flock, fl); if (error) goto out; @@ -2290,11 +2379,13 @@ 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) - * 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 ->lm_grant() when the lock - * request completes. + * lm_grant is set. Additionally FOP_ASYNC_LOCK in file_operations fop_flags + * need to be 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 ->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 * with the result. If the request timed out the callback routine will return a @@ -2308,6 +2399,7 @@ out: */ int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { + WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, cmd, fl); else @@ -2320,7 +2412,7 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd, { int error; - error = security_file_lock(filp, fl->fl_type); + error = security_file_lock(filp, fl->c.flc_type); if (error) return error; @@ -2328,7 +2420,8 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd, error = vfs_lock_file(filp, cmd, fl, NULL); if (error != FILE_LOCK_DEFERRED) break; - error = wait_event_interruptible(fl->fl_wait, !fl->fl_blocker); + error = wait_event_interruptible(fl->c.flc_wait, + list_empty(&fl->c.flc_blocked_member)); if (error) break; } @@ -2341,13 +2434,13 @@ static int do_lock_file_wait(struct file *filp, unsigned int cmd, static int check_fmode_for_setlk(struct file_lock *fl) { - switch (fl->fl_type) { + switch (fl->c.flc_type) { case F_RDLCK: - if (!(fl->fl_file->f_mode & FMODE_READ)) + if (!(fl->c.flc_file->f_mode & FMODE_READ)) return -EBADF; break; case F_WRLCK: - if (!(fl->fl_file->f_mode & FMODE_WRITE)) + if (!(fl->c.flc_file->f_mode & FMODE_WRITE)) return -EBADF; } return 0; @@ -2360,21 +2453,13 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, struct flock *flock) { struct file_lock *file_lock = locks_alloc_lock(); - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; - /* Don't allow mandatory locks on files that may be memory mapped - * and shared. - */ - if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) { - error = -EAGAIN; - goto out; - } - error = flock_to_posix_lock(filp, file_lock, flock); if (error) goto out; @@ -2394,8 +2479,8 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, goto out; cmd = F_SETLK; - file_lock->fl_flags |= FL_OFDLCK; - file_lock->fl_owner = filp; + file_lock->c.flc_flags |= FL_OFDLCK; + file_lock->c.flc_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; @@ -2403,34 +2488,34 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd, goto out; cmd = F_SETLKW; - file_lock->fl_flags |= FL_OFDLCK; - file_lock->fl_owner = filp; - /* Fallthrough */ + file_lock->c.flc_flags |= FL_OFDLCK; + file_lock->c.flc_owner = filp; + fallthrough; case F_SETLKW: - file_lock->fl_flags |= FL_SLEEP; + file_lock->c.flc_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* - * Attempt to detect a close/fcntl race and recover by releasing the - * lock that was just acquired. There is no need to do that when we're + * Detect close/fcntl races and recover by zapping all POSIX locks + * associated with this file and our files_struct, just like on + * filp_flush(). There is no need to do that when we're * unlocking though, or for OFD locks. */ - if (!error && file_lock->fl_type != F_UNLCK && - !(file_lock->fl_flags & FL_OFDLCK)) { + if (!error && file_lock->c.flc_type != F_UNLCK && + !(file_lock->c.flc_flags & FL_OFDLCK)) { + struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); + spin_lock(&files->file_lock); + f = files_lookup_fd_locked(files, fd); + spin_unlock(&files->file_lock); if (f != filp) { - file_lock->fl_type = F_UNLCK; - error = do_lock_file_wait(filp, cmd, file_lock); - WARN_ON_ONCE(error); + locks_remove_posix(filp, files); error = -EBADF; } } @@ -2454,7 +2539,8 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock) return -ENOMEM; error = -EINVAL; - if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK) + if (cmd != F_OFD_GETLK && flock->l_type != F_RDLCK + && flock->l_type != F_WRLCK) goto out; error = flock64_to_posix_lock(filp, fl, flock); @@ -2466,17 +2552,16 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock) if (flock->l_pid != 0) goto out; - cmd = F_GETLK64; - fl->fl_flags |= FL_OFDLCK; - fl->fl_owner = filp; + fl->c.flc_flags |= FL_OFDLCK; + fl->c.flc_owner = filp; } error = vfs_test_lock(filp, fl); if (error) goto out; - flock->l_type = fl->fl_type; - if (fl->fl_type != F_UNLCK) + flock->l_type = fl->c.flc_type; + if (fl->c.flc_type != F_UNLCK) posix_lock_to_flock64(flock, fl); out: @@ -2491,21 +2576,12 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, struct flock64 *flock) { struct file_lock *file_lock = locks_alloc_lock(); - struct inode *inode = locks_inode(filp); struct file *f; int error; if (file_lock == NULL) return -ENOLCK; - /* Don't allow mandatory locks on files that may be memory mapped - * and shared. - */ - if (mandatory_lock(inode) && mapping_writably_mapped(filp->f_mapping)) { - error = -EAGAIN; - goto out; - } - error = flock64_to_posix_lock(filp, file_lock, flock); if (error) goto out; @@ -2525,8 +2601,8 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, goto out; cmd = F_SETLK64; - file_lock->fl_flags |= FL_OFDLCK; - file_lock->fl_owner = filp; + file_lock->c.flc_flags |= FL_OFDLCK; + file_lock->c.flc_owner = filp; break; case F_OFD_SETLKW: error = -EINVAL; @@ -2534,34 +2610,34 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd, goto out; cmd = F_SETLKW64; - file_lock->fl_flags |= FL_OFDLCK; - file_lock->fl_owner = filp; - /* Fallthrough */ + file_lock->c.flc_flags |= FL_OFDLCK; + file_lock->c.flc_owner = filp; + fallthrough; case F_SETLKW64: - file_lock->fl_flags |= FL_SLEEP; + file_lock->c.flc_flags |= FL_SLEEP; } error = do_lock_file_wait(filp, cmd, file_lock); /* - * Attempt to detect a close/fcntl race and recover by releasing the - * lock that was just acquired. There is no need to do that when we're + * Detect close/fcntl races and recover by zapping all POSIX locks + * associated with this file and our files_struct, just like on + * filp_flush(). There is no need to do that when we're * unlocking though, or for OFD locks. */ - if (!error && file_lock->fl_type != F_UNLCK && - !(file_lock->fl_flags & FL_OFDLCK)) { + if (!error && file_lock->c.flc_type != F_UNLCK && + !(file_lock->c.flc_flags & FL_OFDLCK)) { + struct files_struct *files = current->files; /* * We need that spin_lock here - it prevents reordering between * update of i_flctx->flc_posix and check for it done in * close(). rcu_read_lock() wouldn't do. */ - spin_lock(¤t->files->file_lock); - f = fcheck(fd); - spin_unlock(¤t->files->file_lock); + spin_lock(&files->file_lock); + f = files_lookup_fd_locked(files, fd); + spin_unlock(&files->file_lock); if (f != filp) { - file_lock->fl_type = F_UNLCK; - error = do_lock_file_wait(filp, cmd, file_lock); - WARN_ON_ONCE(error); + locks_remove_posix(filp, files); error = -EBADF; } } @@ -2579,7 +2655,7 @@ out: void locks_remove_posix(struct file *filp, fl_owner_t owner) { int error; - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); struct file_lock lock; struct file_lock_context *ctx; @@ -2588,18 +2664,18 @@ 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. */ - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx || list_empty(&ctx->flc_posix)) return; locks_init_lock(&lock); - lock.fl_type = F_UNLCK; - lock.fl_flags = FL_POSIX | FL_CLOSE; + lock.c.flc_type = F_UNLCK; + lock.c.flc_flags = FL_POSIX | FL_CLOSE; lock.fl_start = 0; lock.fl_end = OFFSET_MAX; - lock.fl_owner = owner; - lock.fl_pid = current->tgid; - lock.fl_file = filp; + lock.c.flc_owner = owner; + lock.c.flc_pid = current->tgid; + lock.c.flc_file = filp; lock.fl_ops = NULL; lock.fl_lmops = NULL; @@ -2616,13 +2692,13 @@ static void locks_remove_flock(struct file *filp, struct file_lock_context *flctx) { struct file_lock fl; - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); if (list_empty(&flctx->flc_flock)) return; - flock_make_lock(filp, LOCK_UN, &fl); - fl.fl_flags |= FL_CLOSE; + flock_make_lock(filp, &fl, F_UNLCK); + fl.c.flc_flags |= FL_CLOSE; if (filp->f_op->flock) filp->f_op->flock(filp, F_SETLKW, &fl); @@ -2637,19 +2713,19 @@ locks_remove_flock(struct file *filp, struct file_lock_context *flctx) static void locks_remove_lease(struct file *filp, struct file_lock_context *ctx) { - struct file_lock *fl, *tmp; + struct file_lease *fl, *tmp; LIST_HEAD(dispose); if (list_empty(&ctx->flc_lease)) return; - percpu_down_read_preempt_disable(&file_rwsem); + percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); - list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, fl_list) - if (filp == fl->fl_file) + list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) + if (filp == fl->c.flc_file) lease_modify(fl, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); - percpu_up_read_preempt_enable(&file_rwsem); + percpu_up_read(&file_rwsem); locks_dispose_list(&dispose); } @@ -2661,7 +2737,7 @@ void locks_remove_file(struct file *filp) { struct file_lock_context *ctx; - ctx = smp_load_acquire(&locks_inode(filp)->i_flctx); + ctx = locks_inode_context(file_inode(filp)); if (!ctx) return; @@ -2690,12 +2766,36 @@ void locks_remove_file(struct file *filp) */ int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { + WARN_ON_ONCE(filp != fl->c.flc_file); if (filp->f_op->lock) return filp->f_op->lock(filp, F_CANCELLK, fl); return 0; } EXPORT_SYMBOL_GPL(vfs_cancel_lock); +/** + * vfs_inode_has_locks - are any file locks held on @inode? + * @inode: inode to check for locks + * + * Return true if there are any FL_POSIX or FL_FLOCK locks currently + * set on @inode. + */ +bool vfs_inode_has_locks(struct inode *inode) +{ + struct file_lock_context *ctx; + bool ret; + + ctx = locks_inode_context(inode); + if (!ctx) + return false; + + spin_lock(&ctx->flc_lock); + ret = !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_flock); + spin_unlock(&ctx->flc_lock); + return ret; +} +EXPORT_SYMBOL_GPL(vfs_inode_has_locks); + #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -2705,76 +2805,73 @@ struct locks_iterator { loff_t li_pos; }; -static void lock_get_status(struct seq_file *f, struct file_lock *fl, - loff_t id, char *pfx) +static void lock_get_status(struct seq_file *f, struct file_lock_core *flc, + loff_t id, char *pfx, int repeat) { struct inode *inode = NULL; - unsigned int fl_pid; - struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info; + unsigned int pid; + struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); + int type = flc->flc_type; + struct file_lock *fl = file_lock(flc); + + pid = locks_translate_pid(flc, proc_pidns); - fl_pid = locks_translate_pid(fl, proc_pidns); /* * If lock owner is dead (and pid is freed) or not visible in current * pidns, zero is shown as a pid value. Check lock info from * init_pid_ns to get saved lock pid value. */ + if (flc->flc_file != NULL) + inode = file_inode(flc->flc_file); + + seq_printf(f, "%lld: ", id); - if (fl->fl_file != NULL) - inode = locks_inode(fl->fl_file); + if (repeat) + seq_printf(f, "%*s", repeat - 1 + (int)strlen(pfx), pfx); - seq_printf(f, "%lld:%s ", id, pfx); - if (IS_POSIX(fl)) { - if (fl->fl_flags & FL_ACCESS) + if (flc->flc_flags & FL_POSIX) { + if (flc->flc_flags & FL_ACCESS) seq_puts(f, "ACCESS"); - else if (IS_OFDLCK(fl)) + else if (flc->flc_flags & FL_OFDLCK) 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_puts(f, "FLOCK MSNFS "); - } else { - seq_puts(f, "FLOCK ADVISORY "); - } - } else if (IS_LEASE(fl)) { - if (fl->fl_flags & FL_DELEG) + (inode == NULL) ? "*NOINODE*" : "ADVISORY "); + } else if (flc->flc_flags & FL_FLOCK) { + seq_puts(f, "FLOCK ADVISORY "); + } else if (flc->flc_flags & (FL_LEASE|FL_DELEG|FL_LAYOUT)) { + struct file_lease *lease = file_lease(flc); + + type = target_leasetype(lease); + + if (flc->flc_flags & FL_DELEG) seq_puts(f, "DELEG "); else seq_puts(f, "LEASE "); - if (lease_breaking(fl)) + if (lease_breaking(lease)) seq_puts(f, "BREAKING "); - else if (fl->fl_file) + else if (flc->flc_file) seq_puts(f, "ACTIVE "); else seq_puts(f, "BREAKER "); } else { seq_puts(f, "UNKNOWN UNKNOWN "); } - if (fl->fl_type & LOCK_MAND) { - seq_printf(f, "%s ", - (fl->fl_type & LOCK_READ) - ? (fl->fl_type & LOCK_WRITE) ? "RW " : "READ " - : (fl->fl_type & LOCK_WRITE) ? "WRITE" : "NONE "); - } else { - seq_printf(f, "%s ", - (lease_breaking(fl)) - ? (fl->fl_type == F_UNLCK) ? "UNLCK" : "READ " - : (fl->fl_type == F_WRLCK) ? "WRITE" : "READ "); - } + + seq_printf(f, "%s ", (type == F_WRLCK) ? "WRITE" : + (type == F_RDLCK) ? "READ" : "UNLCK"); if (inode) { /* userspace relies on this representation of dev_t */ - seq_printf(f, "%d %02x:%02x:%ld ", fl_pid, + seq_printf(f, "%d %02x:%02x:%lu ", pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } else { - seq_printf(f, "%d <none>:0 ", fl_pid); + seq_printf(f, "%d <none>:0 ", pid); } - if (IS_POSIX(fl)) { + if (flc->flc_flags & FL_POSIX) { if (fl->fl_end == OFFSET_MAX) seq_printf(f, "%Ld EOF\n", fl->fl_start); else @@ -2784,21 +2881,66 @@ static void lock_get_status(struct seq_file *f, struct file_lock *fl, } } +static struct file_lock_core *get_next_blocked_member(struct file_lock_core *node) +{ + struct file_lock_core *tmp; + + /* NULL node or root node */ + if (node == NULL || node->flc_blocker == NULL) + return NULL; + + /* Next member in the linked list could be itself */ + tmp = list_next_entry(node, flc_blocked_member); + if (list_entry_is_head(tmp, &node->flc_blocker->flc_blocked_requests, + flc_blocked_member) + || tmp == node) { + return NULL; + } + + return tmp; +} + static int locks_show(struct seq_file *f, void *v) { struct locks_iterator *iter = f->private; - struct file_lock *fl, *bfl; - struct pid_namespace *proc_pidns = file_inode(f->file)->i_sb->s_fs_info; + struct file_lock_core *cur, *tmp; + struct pid_namespace *proc_pidns = proc_pid_ns(file_inode(f->file)->i_sb); + int level = 0; - fl = hlist_entry(v, struct file_lock, fl_link); + cur = hlist_entry(v, struct file_lock_core, flc_link); - if (locks_translate_pid(fl, proc_pidns) == 0) + if (locks_translate_pid(cur, proc_pidns) == 0) return 0; - lock_get_status(f, fl, iter->li_pos, ""); - - list_for_each_entry(bfl, &fl->fl_blocked_requests, fl_blocked_member) - lock_get_status(f, bfl, iter->li_pos, " ->"); + /* View this crossed linked list as a binary tree, the first member of flc_blocked_requests + * is the left child of current node, the next silibing in flc_blocked_member is the + * right child, we can alse get the parent of current node from flc_blocker, so this + * question becomes traversal of a binary tree + */ + while (cur != NULL) { + if (level) + lock_get_status(f, cur, iter->li_pos, "-> ", level); + else + lock_get_status(f, cur, iter->li_pos, "", level); + + if (!list_empty(&cur->flc_blocked_requests)) { + /* Turn left */ + cur = list_first_entry_or_null(&cur->flc_blocked_requests, + struct file_lock_core, + flc_blocked_member); + level++; + } else { + /* Turn right */ + tmp = get_next_blocked_member(cur); + /* Fall back to parent node */ + while (tmp == NULL && cur->flc_blocker != NULL) { + cur = cur->flc_blocker; + level--; + tmp = get_next_blocked_member(cur); + } + cur = tmp; + } + } return 0; } @@ -2807,30 +2949,29 @@ static void __show_fd_locks(struct seq_file *f, struct list_head *head, int *id, struct file *filp, struct files_struct *files) { - struct file_lock *fl; + struct file_lock_core *fl; - list_for_each_entry(fl, head, fl_list) { + list_for_each_entry(fl, head, flc_list) { - if (filp != fl->fl_file) + if (filp != fl->flc_file) continue; - if (fl->fl_owner != files && - fl->fl_owner != filp) + if (fl->flc_owner != files && fl->flc_owner != filp) continue; (*id)++; seq_puts(f, "lock:\t"); - lock_get_status(f, fl, *id, ""); + lock_get_status(f, fl, *id, "", 0); } } void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) { - struct inode *inode = locks_inode(filp); + struct inode *inode = file_inode(filp); struct file_lock_context *ctx; int id = 0; - ctx = smp_load_acquire(&inode->i_flctx); + ctx = locks_inode_context(inode); if (!ctx) return; @@ -2893,6 +3034,9 @@ static int __init filelock_init(void) filelock_cache = kmem_cache_create("file_lock_cache", sizeof(struct file_lock), 0, SLAB_PANIC, NULL); + filelease_cache = kmem_cache_create("file_lease_cache", + sizeof(struct file_lease), 0, SLAB_PANIC, NULL); + for_each_possible_cpu(i) { struct file_lock_list_struct *fll = per_cpu_ptr(&file_lock_list, i); @@ -2900,6 +3044,7 @@ static int __init filelock_init(void) INIT_HLIST_HEAD(&fll->hlist); } + lease_notifier_chain_init(); return 0; } core_initcall(filelock_init); |