diff options
Diffstat (limited to 'fs/locks.c')
| -rw-r--r-- | fs/locks.c | 298 |
1 files changed, 198 insertions, 100 deletions
diff --git a/fs/locks.c b/fs/locks.c index 1619cddfa7a4..fead53474c30 100644 --- a/fs/locks.c +++ b/fs/locks.c @@ -178,7 +178,6 @@ locks_get_lock_context(struct inode *inode, int type) { struct file_lock_context *ctx; - /* paired with cmpxchg() below */ ctx = locks_inode_context(inode); if (likely(ctx) || type == F_UNLCK) goto out; @@ -196,7 +195,18 @@ locks_get_lock_context(struct inode *inode, int type) * Assign the pointer if it's not already assigned. If it is, then * free the context we just allocated. */ - if (cmpxchg(&inode->i_flctx, NULL, ctx)) { + spin_lock(&inode->i_lock); + if (!(inode->i_opflags & IOP_FLCTX)) { + VFS_BUG_ON_INODE(inode->i_flctx, inode); + WRITE_ONCE(inode->i_flctx, ctx); + /* + * Paired with locks_inode_context(). + */ + smp_store_release(&inode->i_opflags, inode->i_opflags | IOP_FLCTX); + spin_unlock(&inode->i_lock); + } else { + VFS_BUG_ON_INODE(!inode->i_flctx, inode); + spin_unlock(&inode->i_lock); kmem_cache_free(flctx_cache, ctx); ctx = locks_inode_context(inode); } @@ -224,7 +234,7 @@ locks_check_ctx_lists(struct inode *inode) if (unlikely(!list_empty(&ctx->flc_flock) || !list_empty(&ctx->flc_posix) || !list_empty(&ctx->flc_lease))) { - pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%lx:\n", + pr_warn("Leaked locks on dev=0x%x:0x%x ino=0x%llx:\n", MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); locks_dump_ctx_list(&ctx->flc_flock, "FLOCK"); @@ -241,7 +251,7 @@ locks_check_ctx_file_list(struct file *filp, struct list_head *list, char *list_ 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 " + pr_warn("Leaked %s lock on dev=0x%x:0x%x ino=0x%llx " " 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, @@ -369,10 +379,19 @@ locks_dispose_list(struct list_head *dispose) while (!list_empty(dispose)) { 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)); + locks_free_lock(file_lock(flc)); + } +} + +static void +lease_dispose_list(struct list_head *dispose) +{ + struct file_lock_core *flc; + + while (!list_empty(dispose)) { + flc = list_first_entry(dispose, struct file_lock_core, flc_list); + list_del_init(&flc->flc_list); + locks_free_lease(file_lease(flc)); } } @@ -576,16 +595,56 @@ lease_setup(struct file_lease *fl, void **priv) __f_setown(filp, task_pid(current), PIDTYPE_TGID, 0); } +/** + * lease_open_conflict - see if the given file points to an inode that has + * an existing open that would conflict with the + * desired lease. + * @filp: file to check + * @arg: type of lease that we're trying to acquire + * + * Check to see if there's an existing open fd on this file that would + * conflict with the lease we're trying to set. + */ +static int +lease_open_conflict(struct file *filp, const int arg) +{ + struct inode *inode = file_inode(filp); + int self_wcount = 0, self_rcount = 0; + + if (arg == F_RDLCK) + return inode_is_open_for_write(inode) ? -EAGAIN : 0; + else if (arg != F_WRLCK) + return 0; + + /* + * 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; + + if (atomic_read(&inode->i_writecount) != self_wcount || + atomic_read(&inode->i_readcount) != self_rcount) + return -EAGAIN; + + return 0; +} + static const struct lease_manager_operations lease_manager_ops = { .lm_break = lease_break_callback, .lm_change = lease_modify, .lm_setup = lease_setup, + .lm_open_conflict = lease_open_conflict, }; /* * Initialize a lease, use the default lock manager operations */ -static int lease_init(struct file *filp, int type, struct file_lease *fl) +static int lease_init(struct file *filp, unsigned int flags, int type, struct file_lease *fl) { if (assign_type(&fl->c, type) != 0) return -EINVAL; @@ -594,13 +653,13 @@ static int lease_init(struct file *filp, int type, struct file_lease *fl) fl->c.flc_pid = current->tgid; fl->c.flc_file = filp; - fl->c.flc_flags = FL_LEASE; + 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_lease *lease_alloc(struct file *filp, int type) +static struct file_lease *lease_alloc(struct file *filp, unsigned int flags, int type) { struct file_lease *fl = locks_alloc_lease(); int error = -ENOMEM; @@ -608,7 +667,7 @@ static struct file_lease *lease_alloc(struct file *filp, int type) if (fl == NULL) return ERR_PTR(error); - error = lease_init(filp, type, fl); + error = lease_init(filp, flags, type, fl); if (error) { locks_free_lease(fl); return ERR_PTR(error); @@ -712,7 +771,7 @@ static void __locks_wake_up_blocks(struct file_lock_core *blocker) fl->fl_lmops && fl->fl_lmops->lm_notify) fl->fl_lmops->lm_notify(fl); else - locks_wake_up(fl); + locks_wake_up_waiter(waiter); /* * The setting of flc_blocker to NULL marks the "done" @@ -1475,6 +1534,7 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose) { struct file_lock_context *ctx = inode->i_flctx; struct file_lease *fl, *tmp; + bool remove; lockdep_assert_held(&ctx->flc_lock); @@ -1482,8 +1542,19 @@ static void time_out_leases(struct inode *inode, struct list_head *dispose) trace_time_out_leases(inode, fl); if (past_time(fl->fl_downgrade_time)) lease_modify(fl, F_RDLCK, dispose); - if (past_time(fl->fl_break_time)) - lease_modify(fl, F_UNLCK, dispose); + + remove = true; + if (past_time(fl->fl_break_time)) { + /* + * Consult the lease manager when a lease break times + * out to determine whether the lease should be disposed + * of. + */ + if (fl->fl_lmops && fl->fl_lmops->lm_breaker_timedout) + remove = fl->fl_lmops->lm_breaker_timedout(fl); + if (remove) + lease_modify(fl, F_UNLCK, dispose); + } } } @@ -1529,29 +1600,35 @@ any_leases_conflict(struct inode *inode, struct file_lease *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_lock_context *ctx; struct file_lease *new_fl, *fl, *tmp; + struct file_lock_context *ctx; 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->c.flc_flags = type; /* typically we will check that ctx is non-NULL before calling */ ctx = locks_inode_context(inode); @@ -1596,7 +1673,7 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) 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; @@ -1605,16 +1682,20 @@ int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) restart: 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) + if (break_time != 0) { + if (time_after(jiffies, break_time)) { + fl->fl_break_time = jiffies + lease_break_time * HZ; + break_time = lease_break_time * HZ; + } else + break_time -= jiffies; + } else break_time++; 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(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); error = wait_event_interruptible_timeout(new_fl->c.flc_wait, list_empty(&new_fl->c.flc_blocked_member), break_time); @@ -1637,7 +1718,7 @@ restart: out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); free_lock: locks_free_lease(new_fl); return error; @@ -1675,8 +1756,9 @@ 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): @@ -1697,7 +1779,7 @@ 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_lease *fl; struct inode *inode = file_inode(filp); @@ -1713,60 +1795,28 @@ int fcntl_getlease(struct 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(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); } return type; } -/** - * check_conflicting_open - see if the given file points to an inode that has - * an existing open that would conflict with the - * desired lease. - * @filp: file to check - * @arg: type of lease that we're trying to acquire - * @flags: current lock flags - * - * Check to see if there's an existing open fd on this file that would - * conflict with the lease we're trying to set. - */ -static int -check_conflicting_open(struct file *filp, const int arg, int flags) +int fcntl_getlease(struct file *filp) { - 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) - return inode_is_open_for_write(inode) ? -EAGAIN : 0; - else if (arg != F_WRLCK) - return 0; - - /* - * 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; - - if (atomic_read(&inode->i_writecount) != self_wcount || - atomic_read(&inode->i_readcount) != self_rcount) - return -EAGAIN; + 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; } @@ -1794,7 +1844,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **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 @@ -1806,7 +1856,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr percpu_down_read(&file_rwsem); spin_lock(&ctx->flc_lock); time_out_leases(inode, &dispose); - error = check_conflicting_open(filp, arg, lease->c.flc_flags); + error = lease->fl_lmops->lm_open_conflict(filp, arg); if (error) goto out; @@ -1863,7 +1913,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr * precedes these checks. */ smp_mb(); - error = check_conflicting_open(filp, arg, lease->c.flc_flags); + error = lease->fl_lmops->lm_open_conflict(filp, arg); if (error) { locks_unlink_lock_ctx(&lease->c); goto out; @@ -1875,7 +1925,7 @@ out_setup: out: spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); if (is_deleg) inode_unlock(inode); if (!error && !my_fl) @@ -1911,7 +1961,7 @@ static int generic_delete_lease(struct file *filp, void *owner) error = fl->fl_lmops->lm_change(victim, F_UNLCK, &dispose); spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); return error; } @@ -1929,11 +1979,19 @@ static int generic_delete_lease(struct file *filp, void *owner) int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { + struct inode *inode = file_inode(filp); + + if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) + return -EINVAL; + 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; @@ -1987,8 +2045,7 @@ kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **pr 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); + return -EINVAL; } EXPORT_SYMBOL_GPL(kernel_setlease); @@ -2018,8 +2075,6 @@ vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE)) return -EACCES; - if (!S_ISREG(inode->i_mode)) - return -EINVAL; error = security_file_lock(filp, arg); if (error) return error; @@ -2027,13 +2082,13 @@ vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) } EXPORT_SYMBOL_GPL(vfs_setlease); -static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int arg) +static int do_fcntl_add_lease(unsigned int fd, struct file *filp, unsigned int flavor, int arg) { 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); @@ -2064,9 +2119,33 @@ static int do_fcntl_add_lease(unsigned int fd, struct file *filp, int 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); } /** @@ -2185,18 +2264,37 @@ SYSCALL_DEFINE2(flock, unsigned int, fd, unsigned int, cmd) /** * vfs_test_lock - test file byte range lock * @filp: The file to test lock for - * @fl: The lock to test; also used to hold result + * @fl: The byte-range in the file to test; also used to hold result * + * On entry, @fl does not contain a lock, but identifies a range (fl_start, fl_end) + * in the file (c.flc_file), and an owner (c.flc_owner) for whom existing locks + * should be ignored. c.flc_type and c.flc_flags are ignored. + * Both fl_lmops and fl_ops in @fl must be NULL. * Returns -ERRNO on failure. Indicates presence of conflicting lock by - * setting conf->fl_type to something other than F_UNLCK. + * setting fl->fl_type to something other than F_UNLCK. + * + * If vfs_test_lock() does find a lock and return it, the caller must + * use locks_free_lock() or locks_release_private() on the returned lock. */ int vfs_test_lock(struct file *filp, struct file_lock *fl) { + int error = 0; + + WARN_ON_ONCE(fl->fl_ops || fl->fl_lmops); 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); - return 0; + error = filp->f_op->lock(filp, F_GETLK, fl); + else + posix_test_lock(filp, fl); + + /* + * We don't expect FILE_LOCK_DEFERRED and callers cannot + * handle it. + */ + if (WARN_ON_ONCE(error == FILE_LOCK_DEFERRED)) + error = -EIO; + + return error; } EXPORT_SYMBOL_GPL(vfs_test_lock); @@ -2328,8 +2426,8 @@ 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. Additionally EXPORT_OP_ASYNC_LOCK in export_operations - * flags need to be set. + * 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 @@ -2676,7 +2774,7 @@ locks_remove_lease(struct file *filp, struct file_lock_context *ctx) spin_unlock(&ctx->flc_lock); percpu_up_read(&file_rwsem); - locks_dispose_list(&dispose); + lease_dispose_list(&dispose); } /* @@ -2814,7 +2912,7 @@ static void lock_get_status(struct seq_file *f, struct file_lock_core *flc, (type == F_RDLCK) ? "READ" : "UNLCK"); if (inode) { /* userspace relies on this representation of dev_t */ - seq_printf(f, "%d %02x:%02x:%lu ", pid, + seq_printf(f, "%d %02x:%02x:%llu ", pid, MAJOR(inode->i_sb->s_dev), MINOR(inode->i_sb->s_dev), inode->i_ino); } else { |
