From: Linus Torvalds Date: Mon, 7 May 2007 19:34:24 +0000 (-0700) Subject: Merge branch 'server-cluster-locking-api' of git://linux-nfs.org/~bfields/linux X-Git-Tag: v2.6.22-rc1~818 X-Git-Url: http://git.rot13.org/?a=commitdiff_plain;h=2d56d3c43cc97ae48586745556f5a5b564d61582;hp=-c;p=powerpc.git Merge branch 'server-cluster-locking-api' of git://linux-nfs.org/~bfields/linux * 'server-cluster-locking-api' of git://linux-nfs.org/~bfields/linux: gfs2: nfs lock support for gfs2 lockd: add code to handle deferred lock requests lockd: always preallocate block in nlmsvc_lock() lockd: handle test_lock deferrals lockd: pass cookie in nlmsvc_testlock lockd: handle fl_grant callbacks lockd: save lock state on deferral locks: add fl_grant callback for asynchronous lock return nfsd4: Convert NFSv4 to new lock interface locks: add lock cancel command locks: allow {vfs,posix}_lock_file to return conflicting lock locks: factor out generic/filesystem switch from setlock code locks: factor out generic/filesystem switch from test_lock locks: give posix_test_lock same interface as ->lock locks: make ->lock release private data before returning in GETLK case locks: create posix-to-flock helper functions locks: trivial removal of unnecessary parentheses --- 2d56d3c43cc97ae48586745556f5a5b564d61582 diff --combined fs/locks.c index 3255780747,53b0cd1532..671a034dc9 --- a/fs/locks.c +++ b/fs/locks.c @@@ -203,7 -203,8 +203,7 @@@ static void init_once(void *foo, struc { struct file_lock *lock = (struct file_lock *) foo; - if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) != - SLAB_CTOR_CONSTRUCTOR) + if (!(flags & SLAB_CTOR_CONSTRUCTOR)) return; locks_init_lock(lock); @@@ -665,11 -666,11 +665,11 @@@ static int locks_block_on_timeout(struc } int - posix_test_lock(struct file *filp, struct file_lock *fl, - struct file_lock *conflock) + posix_test_lock(struct file *filp, struct file_lock *fl) { struct file_lock *cfl; + fl->fl_type = F_UNLCK; lock_kernel(); for (cfl = filp->f_path.dentry->d_inode->i_flock; cfl; cfl = cfl->fl_next) { if (!IS_POSIX(cfl)) @@@ -678,7 -679,7 +678,7 @@@ break; } if (cfl) { - __locks_copy_lock(conflock, cfl); + __locks_copy_lock(fl, cfl); unlock_kernel(); return 1; } @@@ -800,7 -801,7 +800,7 @@@ out return error; } - static int __posix_lock_file_conf(struct inode *inode, struct file_lock *request, struct file_lock *conflock) + static int __posix_lock_file(struct inode *inode, struct file_lock *request, struct file_lock *conflock) { struct file_lock *fl; struct file_lock *new_fl = NULL; @@@ -1006,6 -1007,7 +1006,7 @@@ * posix_lock_file - Apply a POSIX-style lock to a file * @filp: The file to apply the lock to * @fl: The lock to be applied + * @conflock: Place to return a copy of the conflicting lock, if found. * * Add a POSIX style lock to a file. * We merge adjacent & overlapping locks whenever possible. @@@ -1015,26 -1017,12 +1016,12 @@@ * whether or not a lock was successfully freed by testing the return * value for -ENOENT. */ - int posix_lock_file(struct file *filp, struct file_lock *fl) - { - return __posix_lock_file_conf(filp->f_path.dentry->d_inode, fl, NULL); - } - EXPORT_SYMBOL(posix_lock_file); - - /** - * posix_lock_file_conf - Apply a POSIX-style lock to a file - * @filp: The file to apply the lock to - * @fl: The lock to be applied - * @conflock: Place to return a copy of the conflicting lock, if found. - * - * Except for the conflock parameter, acts just like posix_lock_file. - */ - int posix_lock_file_conf(struct file *filp, struct file_lock *fl, + int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { - return __posix_lock_file_conf(filp->f_path.dentry->d_inode, fl, conflock); + return __posix_lock_file(filp->f_path.dentry->d_inode, fl, conflock); } - EXPORT_SYMBOL(posix_lock_file_conf); + EXPORT_SYMBOL(posix_lock_file); /** * posix_lock_file_wait - Apply a POSIX-style lock to a file @@@ -1050,7 -1038,7 +1037,7 @@@ int posix_lock_file_wait(struct file *f int error; might_sleep (); for (;;) { - error = posix_lock_file(filp, fl); + error = posix_lock_file(filp, fl, NULL); if ((error != -EAGAIN) || !(fl->fl_flags & FL_SLEEP)) break; error = wait_event_interruptible(fl->fl_wait, !fl->fl_next); @@@ -1122,7 -1110,7 +1109,7 @@@ int locks_mandatory_area(int read_write fl.fl_end = offset + count - 1; for (;;) { - error = __posix_lock_file_conf(inode, &fl, NULL); + error = __posix_lock_file(inode, &fl, NULL); if (error != -EAGAIN) break; if (!(fl.fl_flags & FL_SLEEP)) @@@ -1610,12 -1598,62 +1597,62 @@@ asmlinkage long sys_flock(unsigned int return error; } + /** + * vfs_test_lock - test file byte range lock + * @filp: The file to test lock for + * @fl: The lock to test + * @conf: Place to return a copy of the conflicting lock, if found + * + * Returns -ERRNO on failure. Indicates presence of conflicting lock by + * setting conf->fl_type to something other than F_UNLCK. + */ + int vfs_test_lock(struct file *filp, struct file_lock *fl) + { + if (filp->f_op && filp->f_op->lock) + return filp->f_op->lock(filp, F_GETLK, fl); + posix_test_lock(filp, fl); + return 0; + } + EXPORT_SYMBOL_GPL(vfs_test_lock); + + static int posix_lock_to_flock(struct flock *flock, struct file_lock *fl) + { + flock->l_pid = fl->fl_pid; + #if BITS_PER_LONG == 32 + /* + * Make sure we can represent the posix lock via + * legacy 32bit flock. + */ + if (fl->fl_start > OFFT_OFFSET_MAX) + return -EOVERFLOW; + if (fl->fl_end != OFFSET_MAX && fl->fl_end > OFFT_OFFSET_MAX) + return -EOVERFLOW; + #endif + 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; + return 0; + } + + #if BITS_PER_LONG == 32 + static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl) + { + flock->l_pid = fl->fl_pid; + flock->l_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; + } + #endif + /* Report the first existing lock that would conflict with l. * This implements the F_GETLK command of fcntl(). */ int fcntl_getlk(struct file *filp, struct flock __user *l) { - struct file_lock *fl, cfl, file_lock; + struct file_lock file_lock; struct flock flock; int error; @@@ -1630,38 -1668,15 +1667,15 @@@ if (error) goto out; - if (filp->f_op && filp->f_op->lock) { - error = filp->f_op->lock(filp, F_GETLK, &file_lock); - if (file_lock.fl_ops && file_lock.fl_ops->fl_release_private) - file_lock.fl_ops->fl_release_private(&file_lock); - if (error < 0) - goto out; - else - fl = (file_lock.fl_type == F_UNLCK ? NULL : &file_lock); - } else { - fl = (posix_test_lock(filp, &file_lock, &cfl) ? &cfl : NULL); - } + error = vfs_test_lock(filp, &file_lock); + if (error) + goto out; - flock.l_type = F_UNLCK; - if (fl != NULL) { - flock.l_pid = fl->fl_pid; - #if BITS_PER_LONG == 32 - /* - * Make sure we can represent the posix lock via - * legacy 32bit flock. - */ - error = -EOVERFLOW; - if (fl->fl_start > OFFT_OFFSET_MAX) - goto out; - if ((fl->fl_end != OFFSET_MAX) - && (fl->fl_end > OFFT_OFFSET_MAX)) + flock.l_type = file_lock.fl_type; + if (file_lock.fl_type != F_UNLCK) { + error = posix_lock_to_flock(&flock, &file_lock); + if (error) goto out; - #endif - 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; } error = -EFAULT; if (!copy_to_user(l, &flock, sizeof(flock))) @@@ -1670,6 -1685,48 +1684,48 @@@ out return error; } + /** + * vfs_lock_file - file byte range lock + * @filp: The file to apply the lock to + * @cmd: type of locking operation (F_SETLK, F_GETLK, etc.) + * @fl: The lock to be applied + * @conf: Place to return a copy of the conflicting lock, if found. + * + * A caller that doesn't care about the conflicting lock may pass NULL + * as the final argument. + * + * If the filesystem defines a private ->lock() method, then @conf will + * be left unchanged; so a caller that cares should initialize it to + * some acceptable default. + * + * To avoid blocking kernel daemons, such as lockd, that need to acquire POSIX + * locks, the ->lock() interface may return asynchronously, before the lock has + * been granted or denied by the underlying filesystem, if (and only if) + * fl_grant is set. Callers expecting ->lock() to return asynchronously + * 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 -EINPROGRESS, and call ->fl_grant() when the lock + * request completes. + * If the request is for non-blocking lock the file system should return + * -EINPROGRESS 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 + * nonzero return code and the file system should release the lock. The file + * system is also responsible to keep a corresponding posix lock when it + * grants a lock so the VFS can find out which locks are locally held and do + * the correct lock cleanup when required. + * The underlying filesystem must not drop the kernel lock or call + * ->fl_grant() before returning to the caller with a -EINPROGRESS + * return code. + */ + int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) + { + if (filp->f_op && filp->f_op->lock) + return filp->f_op->lock(filp, cmd, fl); + else + return posix_lock_file(filp, fl, conf); + } + EXPORT_SYMBOL_GPL(vfs_lock_file); + /* Apply the lock described by l to an open file descriptor. * This implements both the F_SETLK and F_SETLKW commands of fcntl(). */ @@@ -1732,21 -1789,17 +1788,17 @@@ again if (error) goto out; - if (filp->f_op && filp->f_op->lock != NULL) - error = filp->f_op->lock(filp, cmd, file_lock); - else { - for (;;) { - error = posix_lock_file(filp, file_lock); - if ((error != -EAGAIN) || (cmd == F_SETLK)) - break; - error = wait_event_interruptible(file_lock->fl_wait, - !file_lock->fl_next); - if (!error) - continue; - - locks_delete_block(file_lock); + for (;;) { + error = vfs_lock_file(filp, cmd, file_lock, NULL); + if (error != -EAGAIN || cmd == F_SETLK) break; - } + error = wait_event_interruptible(file_lock->fl_wait, + !file_lock->fl_next); + if (!error) + continue; + + locks_delete_block(file_lock); + break; } /* @@@ -1769,7 -1822,7 +1821,7 @@@ out */ int fcntl_getlk64(struct file *filp, struct flock64 __user *l) { - struct file_lock *fl, cfl, file_lock; + struct file_lock file_lock; struct flock64 flock; int error; @@@ -1784,27 -1837,14 +1836,14 @@@ if (error) goto out; - if (filp->f_op && filp->f_op->lock) { - error = filp->f_op->lock(filp, F_GETLK, &file_lock); - if (file_lock.fl_ops && file_lock.fl_ops->fl_release_private) - file_lock.fl_ops->fl_release_private(&file_lock); - if (error < 0) - goto out; - else - fl = (file_lock.fl_type == F_UNLCK ? NULL : &file_lock); - } else { - fl = (posix_test_lock(filp, &file_lock, &cfl) ? &cfl : NULL); - } - - flock.l_type = F_UNLCK; - if (fl != NULL) { - flock.l_pid = fl->fl_pid; - flock.l_start = fl->fl_start; - flock.l_len = fl->fl_end == OFFSET_MAX ? 0 : - fl->fl_end - fl->fl_start + 1; - flock.l_whence = 0; - flock.l_type = fl->fl_type; - } + error = vfs_test_lock(filp, &file_lock); + if (error) + goto out; + + flock.l_type = file_lock.fl_type; + if (file_lock.fl_type != F_UNLCK) + posix_lock_to_flock64(&flock, &file_lock); + error = -EFAULT; if (!copy_to_user(l, &flock, sizeof(flock))) error = 0; @@@ -1875,21 -1915,17 +1914,17 @@@ again if (error) goto out; - if (filp->f_op && filp->f_op->lock != NULL) - error = filp->f_op->lock(filp, cmd, file_lock); - else { - for (;;) { - error = posix_lock_file(filp, file_lock); - if ((error != -EAGAIN) || (cmd == F_SETLK64)) - break; - error = wait_event_interruptible(file_lock->fl_wait, - !file_lock->fl_next); - if (!error) - continue; - - locks_delete_block(file_lock); + for (;;) { + error = vfs_lock_file(filp, cmd, file_lock, NULL); + if (error != -EAGAIN || cmd == F_SETLK64) break; - } + error = wait_event_interruptible(file_lock->fl_wait, + !file_lock->fl_next); + if (!error) + continue; + + locks_delete_block(file_lock); + break; } /* @@@ -1934,10 -1970,7 +1969,7 @@@ void locks_remove_posix(struct file *fi lock.fl_ops = NULL; lock.fl_lmops = NULL; - if (filp->f_op && filp->f_op->lock != NULL) - filp->f_op->lock(filp, F_SETLK, &lock); - else - posix_lock_file(filp, &lock); + vfs_lock_file(filp, F_SETLK, &lock, NULL); if (lock.fl_ops && lock.fl_ops->fl_release_private) lock.fl_ops->fl_release_private(&lock); @@@ -2014,6 -2047,22 +2046,22 @@@ posix_unblock_lock(struct file *filp, s EXPORT_SYMBOL(posix_unblock_lock); + /** + * vfs_cancel_lock - file byte range unblock lock + * @filp: The file to apply the unblock to + * @fl: The lock to be unblocked + * + * Used by lock managers to cancel blocked requests + */ + int vfs_cancel_lock(struct file *filp, struct file_lock *fl) + { + if (filp->f_op && filp->f_op->lock) + return filp->f_op->lock(filp, F_CANCELLK, fl); + return 0; + } + + EXPORT_SYMBOL_GPL(vfs_cancel_lock); + static void lock_get_status(char* out, struct file_lock *fl, int id, char *pfx) { struct inode *inode = NULL; diff --combined fs/nfs/nfs4proc.c index 3b5ca1b15f,d9000ec52f..d6a30e9657 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@@ -2647,7 -2647,8 +2647,7 @@@ static int __nfs4_proc_set_acl(struct i nfs_inode_return_delegation(inode); buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase); ret = rpc_call_sync(NFS_CLIENT(inode), &msg, 0); - if (ret == 0) - nfs4_write_cached_acl(inode, buf, buflen); + nfs_zap_caches(inode); return ret; } @@@ -3017,6 -3018,7 +3017,7 @@@ static int _nfs4_proc_getlk(struct nfs4 case -NFS4ERR_DENIED: status = 0; } + request->fl_ops->fl_release_private(request); out: up_read(&clp->cl_sem); return status; diff --combined include/linux/fs.h index 55a74ffa7e,b22991d5f1..bc6d27ceca --- a/include/linux/fs.h +++ b/include/linux/fs.h @@@ -696,13 -696,12 +696,13 @@@ struct file_ra_state unsigned long size; unsigned long flags; /* ra flags RA_FLAG_xxx*/ unsigned long cache_hit; /* cache hit count*/ - unsigned long prev_page; /* Cache last read() position */ + unsigned long prev_index; /* Cache last read() position */ unsigned long ahead_start; /* Ahead window */ unsigned long ahead_size; unsigned long ra_pages; /* Maximum readahead window */ unsigned long mmap_hit; /* Cache hit stat for mmap accesses */ unsigned long mmap_miss; /* Cache miss stat for mmap accesses */ + unsigned int prev_offset; /* Offset where last read() ended in a page */ }; #define RA_FLAG_MISS 0x01 /* a cache miss occured against this file */ #define RA_FLAG_INCACHE 0x02 /* file is already in cache */ @@@ -786,6 -785,7 +786,7 @@@ struct file_lock_operations struct lock_manager_operations { int (*fl_compare_owner)(struct file_lock *, struct file_lock *); void (*fl_notify)(struct file_lock *); /* unblock callback */ + int (*fl_grant)(struct file_lock *, struct file_lock *, int); void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); void (*fl_break)(struct file_lock *); @@@ -844,24 -844,21 +845,26 @@@ extern int fcntl_setlease(unsigned int extern int fcntl_getlease(struct file *filp); /* fs/sync.c */ -extern int do_sync_file_range(struct file *file, loff_t offset, loff_t endbyte, - unsigned int flags); +extern int do_sync_mapping_range(struct address_space *mapping, loff_t offset, + loff_t endbyte, unsigned int flags); +static inline int do_sync_file_range(struct file *file, loff_t offset, + loff_t endbyte, unsigned int flags) +{ + return do_sync_mapping_range(file->f_mapping, offset, endbyte, flags); +} /* fs/locks.c */ extern void locks_init_lock(struct file_lock *); extern void locks_copy_lock(struct file_lock *, struct file_lock *); extern void locks_remove_posix(struct file *, fl_owner_t); extern void locks_remove_flock(struct file *); - extern int posix_test_lock(struct file *, struct file_lock *, struct file_lock *); - extern int posix_lock_file_conf(struct file *, struct file_lock *, struct file_lock *); - extern int posix_lock_file(struct file *, struct file_lock *); + extern int posix_test_lock(struct file *, struct file_lock *); + extern int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); extern int posix_lock_file_wait(struct file *, struct file_lock *); extern int posix_unblock_lock(struct file *, struct file_lock *); + extern int vfs_test_lock(struct file *, struct file_lock *); + extern int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); + extern int vfs_cancel_lock(struct file *filp, struct file_lock *fl); extern int flock_lock_file_wait(struct file *filp, struct file_lock *fl); extern int __break_lease(struct inode *inode, unsigned int flags); extern void lease_get_mtime(struct inode *, struct timespec *time); @@@ -1417,7 -1414,7 +1420,7 @@@ extern void mnt_set_mountpoint(struct v extern int vfs_statfs(struct dentry *, struct kstatfs *); /* /sys/fs */ -extern struct subsystem fs_subsys; +extern struct kset fs_subsys; #define FLOCK_VERIFY_READ 1 #define FLOCK_VERIFY_WRITE 2 diff --combined include/linux/lockd/lockd.h index f6a81e0b1b,424c3de333..05707e2fcc --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@@ -88,7 -88,7 +88,7 @@@ struct nlm_wait /* * Memory chunk for NLM client RPC request. */ -#define NLMCLNT_OHSIZE (sizeof(utsname()->nodename)+10) +#define NLMCLNT_OHSIZE ((__NEW_UTS_LEN) + 10u) struct nlm_rqst { unsigned int a_flags; /* initial RPC task flags */ struct nlm_host * a_host; /* host handle */ @@@ -119,6 -119,9 +119,9 @@@ struct nlm_file * couldn't be granted because of a conflicting lock). */ #define NLM_NEVER (~(unsigned long) 0) + /* timeout on non-blocking call: */ + #define NLM_TIMEOUT (7 * HZ) + struct nlm_block { struct kref b_count; /* Reference count */ struct list_head b_list; /* linked list of all blocks */ @@@ -130,6 -133,13 +133,13 @@@ unsigned int b_id; /* block id */ unsigned char b_granted; /* VFS granted lock */ struct nlm_file * b_file; /* file in question */ + struct cache_req * b_cache_req; /* deferred request handling */ + struct file_lock * b_fl; /* set for GETLK */ + struct cache_deferred_req * b_deferred_req; + unsigned int b_flags; /* block flags */ + #define B_QUEUED 1 /* lock queued */ + #define B_GOT_CALLBACK 2 /* got lock or conflicting lock */ + #define B_TIMED_OUT 4 /* filesystem too slow to respond */ }; /* @@@ -185,8 -195,8 +195,8 @@@ typedef int (*nlm_host_match_fn_t)(st __be32 nlmsvc_lock(struct svc_rqst *, struct nlm_file *, struct nlm_lock *, int, struct nlm_cookie *); __be32 nlmsvc_unlock(struct nlm_file *, struct nlm_lock *); - __be32 nlmsvc_testlock(struct nlm_file *, struct nlm_lock *, - struct nlm_lock *); + __be32 nlmsvc_testlock(struct svc_rqst *, struct nlm_file *, + struct nlm_lock *, struct nlm_lock *, struct nlm_cookie *); __be32 nlmsvc_cancel_blocked(struct nlm_file *, struct nlm_lock *); unsigned long nlmsvc_retry_blocked(void); void nlmsvc_traverse_blocks(struct nlm_host *, struct nlm_file *,