diff options
Diffstat (limited to 'fs')
-rw-r--r-- | fs/Kconfig | 30 | ||||
-rw-r--r-- | fs/Makefile | 3 | ||||
-rw-r--r-- | fs/binfmt_flat.c | 4 | ||||
-rw-r--r-- | fs/binfmt_misc.c | 4 | ||||
-rw-r--r-- | fs/coda/psdev.c | 5 | ||||
-rw-r--r-- | fs/cramfs/inode.c | 84 | ||||
-rw-r--r-- | fs/fat/inode.c | 10 | ||||
-rw-r--r-- | fs/ioprio.c | 8 | ||||
-rw-r--r-- | fs/lockd/svc.c | 33 | ||||
-rw-r--r-- | fs/nfs/callback.c | 3 | ||||
-rw-r--r-- | fs/nfsd/nfs3proc.c | 8 | ||||
-rw-r--r-- | fs/nfsd/nfs4callback.c | 3 | ||||
-rw-r--r-- | fs/nfsd/nfs4xdr.c | 171 | ||||
-rw-r--r-- | fs/nfsd/nfsfh.c | 30 | ||||
-rw-r--r-- | fs/nfsd/nfsproc.c | 6 | ||||
-rw-r--r-- | fs/nfsd/nfssvc.c | 1 | ||||
-rw-r--r-- | fs/nfsd/vfs.c | 63 | ||||
-rw-r--r-- | fs/proc/nommu.c | 4 | ||||
-rw-r--r-- | fs/proc/proc_misc.c | 4 | ||||
-rw-r--r-- | fs/proc/task_mmu.c | 4 | ||||
-rw-r--r-- | fs/sysfs/dir.c | 245 | ||||
-rw-r--r-- | fs/sysfs/file.c | 88 | ||||
-rw-r--r-- | fs/sysfs/inode.c | 23 | ||||
-rw-r--r-- | fs/sysfs/mount.c | 94 | ||||
-rw-r--r-- | fs/sysfs/sysfs.h | 20 | ||||
-rw-r--r-- | fs/xfs/linux-2.6/xfs_super.c | 11 | ||||
-rw-r--r-- | fs/xfs/xfs_mount.h | 1 |
27 files changed, 633 insertions, 327 deletions
diff --git a/fs/Kconfig b/fs/Kconfig index d3873583360b..d752ce1e48c6 100644 --- a/fs/Kconfig +++ b/fs/Kconfig @@ -419,6 +419,14 @@ config FS_POSIX_ACL bool default n +config FILE_LOCKING + bool "Enable POSIX file locking API" if EMBEDDED + default y + help + This option enables standard file locking support, required + for filesystems like NFS and for the flock() system + call. Disabling this option saves about 11k. + source "fs/xfs/Kconfig" source "fs/gfs2/Kconfig" @@ -1765,6 +1773,28 @@ config SUNRPC_XPRT_RDMA If unsure, say N. +config SUNRPC_REGISTER_V4 + bool "Register local RPC services via rpcbind v4 (EXPERIMENTAL)" + depends on SUNRPC && EXPERIMENTAL + default n + help + Sun added support for registering RPC services at an IPv6 + address by creating two new versions of the rpcbind protocol + (RFC 1833). + + This option enables support in the kernel RPC server for + registering kernel RPC services via version 4 of the rpcbind + protocol. If you enable this option, you must run a portmapper + daemon that supports rpcbind protocol version 4. + + Serving NFS over IPv6 from knfsd (the kernel's NFS server) + requires that you enable this option and use a portmapper that + supports rpcbind version 4. + + If unsure, say N to get traditional behavior (register kernel + RPC services using only rpcbind version 2). Distributions + using the legacy Linux portmapper daemon must say N here. + config RPCSEC_GSS_KRB5 tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)" depends on SUNRPC && EXPERIMENTAL diff --git a/fs/Makefile b/fs/Makefile index a1482a5eff15..4b86d433baaf 100644 --- a/fs/Makefile +++ b/fs/Makefile @@ -7,7 +7,7 @@ obj-y := open.o read_write.o file_table.o super.o \ char_dev.o stat.o exec.o pipe.o namei.o fcntl.o \ - ioctl.o readdir.o select.o fifo.o locks.o dcache.o inode.o \ + ioctl.o readdir.o select.o fifo.o dcache.o inode.o \ attr.o bad_inode.o file.o filesystems.o namespace.o aio.o \ seq_file.o xattr.o libfs.o fs-writeback.o \ pnode.o drop_caches.o splice.o sync.o utimes.o \ @@ -27,6 +27,7 @@ obj-$(CONFIG_ANON_INODES) += anon_inodes.o obj-$(CONFIG_SIGNALFD) += signalfd.o obj-$(CONFIG_TIMERFD) += timerfd.o obj-$(CONFIG_EVENTFD) += eventfd.o +obj-$(CONFIG_FILE_LOCKING) += locks.o obj-$(CONFIG_COMPAT) += compat.o compat_ioctl.o nfsd-$(CONFIG_NFSD) := nfsctl.o diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c index 56372ecf1690..dfc0197905ca 100644 --- a/fs/binfmt_flat.c +++ b/fs/binfmt_flat.c @@ -914,7 +914,9 @@ static int load_flat_binary(struct linux_binprm * bprm, struct pt_regs * regs) /* Stash our initial stack pointer into the mm structure */ current->mm->start_stack = (unsigned long )sp; - +#ifdef FLAT_PLAT_INIT + FLAT_PLAT_INIT(regs); +#endif DBG_FLT("start_thread(regs=0x%x, entry=0x%x, start_stack=0x%x)\n", (int)regs, (int)start_addr, (int)current->mm->start_stack); diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index 756205314c24..8d7e88e02e0f 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -120,8 +120,6 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs) if (bprm->misc_bang) goto _ret; - bprm->misc_bang = 1; - /* to keep locking time low, we copy the interpreter string */ read_lock(&entries_lock); fmt = check_file(bprm); @@ -199,6 +197,8 @@ static int load_misc_binary(struct linux_binprm *bprm, struct pt_regs *regs) if (retval < 0) goto _error; + bprm->misc_bang = 1; + retval = search_binary_handler (bprm, regs); if (retval < 0) goto _error; diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c index 0d9b80ec689c..cfd29da714d1 100644 --- a/fs/coda/psdev.c +++ b/fs/coda/psdev.c @@ -362,9 +362,8 @@ static int init_coda_psdev(void) goto out_chrdev; } for (i = 0; i < MAX_CODADEVS; i++) - device_create_drvdata(coda_psdev_class, NULL, - MKDEV(CODA_PSDEV_MAJOR, i), - NULL, "cfs%d", i); + device_create(coda_psdev_class, NULL, + MKDEV(CODA_PSDEV_MAJOR, i), NULL, "cfs%d", i); coda_sysctl_init(); goto out; diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c index 0c3b618c15b3..f40423eb1a14 100644 --- a/fs/cramfs/inode.c +++ b/fs/cramfs/inode.c @@ -43,58 +43,13 @@ static DEFINE_MUTEX(read_mutex); static int cramfs_iget5_test(struct inode *inode, void *opaque) { struct cramfs_inode *cramfs_inode = opaque; - - if (inode->i_ino != CRAMINO(cramfs_inode)) - return 0; /* does not match */ - - if (inode->i_ino != 1) - return 1; - - /* all empty directories, char, block, pipe, and sock, share inode #1 */ - - if ((inode->i_mode != cramfs_inode->mode) || - (inode->i_gid != cramfs_inode->gid) || - (inode->i_uid != cramfs_inode->uid)) - return 0; /* does not match */ - - if ((S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) && - (inode->i_rdev != old_decode_dev(cramfs_inode->size))) - return 0; /* does not match */ - - return 1; /* matches */ + return inode->i_ino == CRAMINO(cramfs_inode) && inode->i_ino != 1; } static int cramfs_iget5_set(struct inode *inode, void *opaque) { - static struct timespec zerotime; struct cramfs_inode *cramfs_inode = opaque; - inode->i_mode = cramfs_inode->mode; - inode->i_uid = cramfs_inode->uid; - inode->i_size = cramfs_inode->size; - inode->i_blocks = (cramfs_inode->size - 1) / 512 + 1; - inode->i_gid = cramfs_inode->gid; - /* Struct copy intentional */ - inode->i_mtime = inode->i_atime = inode->i_ctime = zerotime; inode->i_ino = CRAMINO(cramfs_inode); - /* inode->i_nlink is left 1 - arguably wrong for directories, - but it's the best we can do without reading the directory - contents. 1 yields the right result in GNU find, even - without -noleaf option. */ - if (S_ISREG(inode->i_mode)) { - inode->i_fop = &generic_ro_fops; - inode->i_data.a_ops = &cramfs_aops; - } else if (S_ISDIR(inode->i_mode)) { - inode->i_op = &cramfs_dir_inode_operations; - inode->i_fop = &cramfs_directory_operations; - } else if (S_ISLNK(inode->i_mode)) { - inode->i_op = &page_symlink_inode_operations; - inode->i_data.a_ops = &cramfs_aops; - } else { - inode->i_size = 0; - inode->i_blocks = 0; - init_special_inode(inode, inode->i_mode, - old_decode_dev(cramfs_inode->size)); - } return 0; } @@ -104,12 +59,48 @@ static struct inode *get_cramfs_inode(struct super_block *sb, struct inode *inode = iget5_locked(sb, CRAMINO(cramfs_inode), cramfs_iget5_test, cramfs_iget5_set, cramfs_inode); + static struct timespec zerotime; + if (inode && (inode->i_state & I_NEW)) { + inode->i_mode = cramfs_inode->mode; + inode->i_uid = cramfs_inode->uid; + inode->i_size = cramfs_inode->size; + inode->i_blocks = (cramfs_inode->size - 1) / 512 + 1; + inode->i_gid = cramfs_inode->gid; + /* Struct copy intentional */ + inode->i_mtime = inode->i_atime = inode->i_ctime = zerotime; + /* inode->i_nlink is left 1 - arguably wrong for directories, + but it's the best we can do without reading the directory + contents. 1 yields the right result in GNU find, even + without -noleaf option. */ + if (S_ISREG(inode->i_mode)) { + inode->i_fop = &generic_ro_fops; + inode->i_data.a_ops = &cramfs_aops; + } else if (S_ISDIR(inode->i_mode)) { + inode->i_op = &cramfs_dir_inode_operations; + inode->i_fop = &cramfs_directory_operations; + } else if (S_ISLNK(inode->i_mode)) { + inode->i_op = &page_symlink_inode_operations; + inode->i_data.a_ops = &cramfs_aops; + } else { + inode->i_size = 0; + inode->i_blocks = 0; + init_special_inode(inode, inode->i_mode, + old_decode_dev(cramfs_inode->size)); + } unlock_new_inode(inode); } return inode; } +static void cramfs_drop_inode(struct inode *inode) +{ + if (inode->i_ino == 1) + generic_delete_inode(inode); + else + generic_drop_inode(inode); +} + /* * We have our own block cache: don't fill up the buffer cache * with the rom-image, because the way the filesystem is set @@ -534,6 +525,7 @@ static const struct super_operations cramfs_ops = { .put_super = cramfs_put_super, .remount_fs = cramfs_remount, .statfs = cramfs_statfs, + .drop_inode = cramfs_drop_inode, }; static int cramfs_get_sb(struct file_system_type *fs_type, diff --git a/fs/fat/inode.c b/fs/fat/inode.c index 6d266d793e2c..80ff3381fa21 100644 --- a/fs/fat/inode.c +++ b/fs/fat/inode.c @@ -562,26 +562,23 @@ static int fat_write_inode(struct inode *inode, int wait) struct buffer_head *bh; struct msdos_dir_entry *raw_entry; loff_t i_pos; - int err = 0; + int err; retry: i_pos = MSDOS_I(inode)->i_pos; if (inode->i_ino == MSDOS_ROOT_INO || !i_pos) return 0; - lock_super(sb); bh = sb_bread(sb, i_pos >> sbi->dir_per_block_bits); if (!bh) { printk(KERN_ERR "FAT: unable to read inode block " "for updating (i_pos %lld)\n", i_pos); - err = -EIO; - goto out; + return -EIO; } spin_lock(&sbi->inode_hash_lock); if (i_pos != MSDOS_I(inode)->i_pos) { spin_unlock(&sbi->inode_hash_lock); brelse(bh); - unlock_super(sb); goto retry; } @@ -607,11 +604,10 @@ retry: } spin_unlock(&sbi->inode_hash_lock); mark_buffer_dirty(bh); + err = 0; if (wait) err = sync_dirty_buffer(bh); brelse(bh); -out: - unlock_super(sb); return err; } diff --git a/fs/ioprio.c b/fs/ioprio.c index c4a1c3c65aac..da3cc460d4df 100644 --- a/fs/ioprio.c +++ b/fs/ioprio.c @@ -115,11 +115,11 @@ asmlinkage long sys_ioprio_set(int which, int who, int ioprio) pgrp = task_pgrp(current); else pgrp = find_vpid(who); - do_each_pid_task(pgrp, PIDTYPE_PGID, p) { + do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { ret = set_task_ioprio(p, ioprio); if (ret) break; - } while_each_pid_task(pgrp, PIDTYPE_PGID, p); + } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case IOPRIO_WHO_USER: if (!who) @@ -204,7 +204,7 @@ asmlinkage long sys_ioprio_get(int which, int who) pgrp = task_pgrp(current); else pgrp = find_vpid(who); - do_each_pid_task(pgrp, PIDTYPE_PGID, p) { + do_each_pid_thread(pgrp, PIDTYPE_PGID, p) { tmpio = get_task_ioprio(p); if (tmpio < 0) continue; @@ -212,7 +212,7 @@ asmlinkage long sys_ioprio_get(int which, int who) ret = tmpio; else ret = ioprio_best(ret, tmpio); - } while_each_pid_task(pgrp, PIDTYPE_PGID, p); + } while_each_pid_thread(pgrp, PIDTYPE_PGID, p); break; case IOPRIO_WHO_USER: if (!who) diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c index 5bd9bf0fa9df..450a3fa87941 100644 --- a/fs/lockd/svc.c +++ b/fs/lockd/svc.c @@ -97,15 +97,19 @@ unsigned long get_nfs_grace_period(void) } EXPORT_SYMBOL(get_nfs_grace_period); -static unsigned long set_grace_period(void) +static void grace_ender(struct work_struct *not_used) { - nlmsvc_grace_period = 1; - return get_nfs_grace_period() + jiffies; + nlmsvc_grace_period = 0; } -static inline void clear_grace_period(void) +static DECLARE_DELAYED_WORK(grace_period_end, grace_ender); + +static void set_grace_period(void) { - nlmsvc_grace_period = 0; + unsigned long grace_period = get_nfs_grace_period() + jiffies; + + nlmsvc_grace_period = 1; + schedule_delayed_work(&grace_period_end, grace_period); } /* @@ -116,7 +120,6 @@ lockd(void *vrqstp) { int err = 0, preverr = 0; struct svc_rqst *rqstp = vrqstp; - unsigned long grace_period_expire; /* try_to_freeze() is called from svc_recv() */ set_freezable(); @@ -139,7 +142,7 @@ lockd(void *vrqstp) nlm_timeout = LOCKD_DFLT_TIMEO; nlmsvc_timeout = nlm_timeout * HZ; - grace_period_expire = set_grace_period(); + set_grace_period(); /* * The main request loop. We don't terminate until the last @@ -153,21 +156,12 @@ lockd(void *vrqstp) flush_signals(current); if (nlmsvc_ops) { nlmsvc_invalidate_all(); - grace_period_expire = set_grace_period(); + set_grace_period(); } continue; } - /* - * Retry any blocked locks that have been notified by - * the VFS. Don't do this during grace period. - * (Theoretically, there shouldn't even be blocked locks - * during grace period). - */ - if (!nlmsvc_grace_period) { - timeout = nlmsvc_retry_blocked(); - } else if (time_before(grace_period_expire, jiffies)) - clear_grace_period(); + timeout = nlmsvc_retry_blocked(); /* * Find a socket with data available and call its @@ -195,6 +189,7 @@ lockd(void *vrqstp) svc_process(rqstp); } flush_signals(current); + cancel_delayed_work_sync(&grace_period_end); if (nlmsvc_ops) nlmsvc_invalidate_all(); nlm_shutdown_hosts(); @@ -266,7 +261,7 @@ lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */ "lockd_up: no pid, %d users??\n", nlmsvc_users); error = -ENOMEM; - serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, NULL); + serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, AF_INET, NULL); if (!serv) { printk(KERN_WARNING "lockd_up: create service failed\n"); goto out; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index f447f4b4476c..6a09760c5960 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -105,7 +105,8 @@ int nfs_callback_up(void) mutex_lock(&nfs_callback_mutex); if (nfs_callback_info.users++ || nfs_callback_info.task != NULL) goto out; - serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL); + serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, + AF_INET, NULL); ret = -ENOMEM; if (!serv) goto out_err; diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index 4d617ea28cfc..9dbd2eb91281 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -63,7 +63,8 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, SVCFH_fmt(&argp->fh)); fh_copy(&resp->fh, &argp->fh); - nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP); + nfserr = fh_verify(rqstp, &resp->fh, 0, + NFSD_MAY_NOP | NFSD_MAY_BYPASS_GSS_ON_ROOT); if (nfserr) RETURN_STATUS(nfserr); @@ -530,7 +531,7 @@ nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, dprintk("nfsd: FSSTAT(3) %s\n", SVCFH_fmt(&argp->fh)); - nfserr = nfsd_statfs(rqstp, &argp->fh, &resp->stats); + nfserr = nfsd_statfs(rqstp, &argp->fh, &resp->stats, 0); fh_put(&argp->fh); RETURN_STATUS(nfserr); } @@ -558,7 +559,8 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, resp->f_maxfilesize = ~(u32) 0; resp->f_properties = NFS3_FSF_DEFAULT; - nfserr = fh_verify(rqstp, &argp->fh, 0, NFSD_MAY_NOP); + nfserr = fh_verify(rqstp, &argp->fh, 0, + NFSD_MAY_NOP | NFSD_MAY_BYPASS_GSS_ON_ROOT); /* Check special features of the file system. May request * different read/write sizes for file systems known to have diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c index 702fa577aa6e..ab13e02c5683 100644 --- a/fs/nfsd/nfs4callback.c +++ b/fs/nfsd/nfs4callback.c @@ -225,7 +225,8 @@ encode_cb_recall(struct xdr_stream *xdr, struct nfs4_cb_recall *cb_rec) RESERVE_SPACE(12+sizeof(cb_rec->cbr_stateid) + len); WRITE32(OP_CB_RECALL); - WRITEMEM(&cb_rec->cbr_stateid, sizeof(stateid_t)); + WRITE32(cb_rec->cbr_stateid.si_generation); + WRITEMEM(&cb_rec->cbr_stateid.si_opaque, sizeof(stateid_opaque_t)); WRITE32(cb_rec->cbr_trunc); WRITE32(len); WRITEMEM(cb_rec->cbr_fhval, len); diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 14ba4d9b2859..afcdf4b76843 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -413,6 +413,18 @@ out_nfserr: } static __be32 +nfsd4_decode_stateid(struct nfsd4_compoundargs *argp, stateid_t *sid) +{ + DECODE_HEAD; + + READ_BUF(sizeof(stateid_t)); + READ32(sid->si_generation); + COPYMEM(&sid->si_opaque, sizeof(stateid_opaque_t)); + + DECODE_TAIL; +} + +static __be32 nfsd4_decode_access(struct nfsd4_compoundargs *argp, struct nfsd4_access *access) { DECODE_HEAD; @@ -429,10 +441,9 @@ nfsd4_decode_close(struct nfsd4_compoundargs *argp, struct nfsd4_close *close) DECODE_HEAD; close->cl_stateowner = NULL; - READ_BUF(4 + sizeof(stateid_t)); + READ_BUF(4); READ32(close->cl_seqid); - READ32(close->cl_stateid.si_generation); - COPYMEM(&close->cl_stateid.si_opaque, sizeof(stateid_opaque_t)); + return nfsd4_decode_stateid(argp, &close->cl_stateid); DECODE_TAIL; } @@ -493,13 +504,7 @@ nfsd4_decode_create(struct nfsd4_compoundargs *argp, struct nfsd4_create *create static inline __be32 nfsd4_decode_delegreturn(struct nfsd4_compoundargs *argp, struct nfsd4_delegreturn *dr) { - DECODE_HEAD; - - READ_BUF(sizeof(stateid_t)); - READ32(dr->dr_stateid.si_generation); - COPYMEM(&dr->dr_stateid.si_opaque, sizeof(stateid_opaque_t)); - - DECODE_TAIL; + return nfsd4_decode_stateid(argp, &dr->dr_stateid); } static inline __be32 @@ -542,20 +547,22 @@ nfsd4_decode_lock(struct nfsd4_compoundargs *argp, struct nfsd4_lock *lock) READ32(lock->lk_is_new); if (lock->lk_is_new) { - READ_BUF(36); + READ_BUF(4); READ32(lock->lk_new_open_seqid); - READ32(lock->lk_new_open_stateid.si_generation); - - COPYMEM(&lock->lk_new_open_stateid.si_opaque, sizeof(stateid_opaque_t)); + status = nfsd4_decode_stateid(argp, &lock->lk_new_open_stateid); + if (status) + return status; + READ_BUF(8 + sizeof(clientid_t)); READ32(lock->lk_new_lock_seqid); COPYMEM(&lock->lk_new_clientid, sizeof(clientid_t)); READ32(lock->lk_new_owner.len); READ_BUF(lock->lk_new_owner.len); READMEM(lock->lk_new_owner.data, lock->lk_new_owner.len); } else { - READ_BUF(20); - READ32(lock->lk_old_lock_stateid.si_generation); - COPYMEM(&lock->lk_old_lock_stateid.si_opaque, sizeof(stateid_opaque_t)); + status = nfsd4_decode_stateid(argp, &lock->lk_old_lock_stateid); + if (status) + return status; + READ_BUF(4); READ32(lock->lk_old_lock_seqid); } @@ -587,13 +594,15 @@ nfsd4_decode_locku(struct nfsd4_compoundargs *argp, struct nfsd4_locku *locku) DECODE_HEAD; locku->lu_stateowner = NULL; - READ_BUF(24 + sizeof(stateid_t)); + READ_BUF(8); READ32(locku->lu_type); if ((locku->lu_type < NFS4_READ_LT) || (locku->lu_type > NFS4_WRITEW_LT)) goto xdr_error; READ32(locku->lu_seqid); - READ32(locku->lu_stateid.si_generation); - COPYMEM(&locku->lu_stateid.si_opaque, sizeof(stateid_opaque_t)); + status = nfsd4_decode_stateid(argp, &locku->lu_stateid); + if (status) + return status; + READ_BUF(16); READ64(locku->lu_offset); READ64(locku->lu_length); @@ -678,8 +687,10 @@ nfsd4_decode_open(struct nfsd4_compoundargs *argp, struct nfsd4_open *open) READ32(open->op_delegate_type); break; case NFS4_OPEN_CLAIM_DELEGATE_CUR: - READ_BUF(sizeof(stateid_t) + 4); - COPYMEM(&open->op_delegate_stateid, sizeof(stateid_t)); + status = nfsd4_decode_stateid(argp, &open->op_delegate_stateid); + if (status) + return status; + READ_BUF(4); READ32(open->op_fname.len); READ_BUF(open->op_fname.len); SAVEMEM(open->op_fname.data, open->op_fname.len); @@ -699,9 +710,10 @@ nfsd4_decode_open_confirm(struct nfsd4_compoundargs *argp, struct nfsd4_open_con DECODE_HEAD; open_conf->oc_stateowner = NULL; - READ_BUF(4 + sizeof(stateid_t)); - READ32(open_conf->oc_req_stateid.si_generation); - COPYMEM(&open_conf->oc_req_stateid.si_opaque, sizeof(stateid_opaque_t)); + status = nfsd4_decode_stateid(argp, &open_conf->oc_req_stateid); + if (status) + return status; + READ_BUF(4); READ32(open_conf->oc_seqid); DECODE_TAIL; @@ -713,9 +725,10 @@ nfsd4_decode_open_downgrade(struct nfsd4_compoundargs *argp, struct nfsd4_open_d DECODE_HEAD; open_down->od_stateowner = NULL; - READ_BUF(12 + sizeof(stateid_t)); - READ32(open_down->od_stateid.si_generation); - COPYMEM(&open_down->od_stateid.si_opaque, sizeof(stateid_opaque_t)); + status = nfsd4_decode_stateid(argp, &open_down->od_stateid); + if (status) + return status; + READ_BUF(12); READ32(open_down->od_seqid); READ32(open_down->od_share_access); READ32(open_down->od_share_deny); @@ -743,9 +756,10 @@ nfsd4_decode_read(struct nfsd4_compoundargs *argp, struct nfsd4_read *read) { DECODE_HEAD; - READ_BUF(sizeof(stateid_t) + 12); - READ32(read->rd_stateid.si_generation); - COPYMEM(&read->rd_stateid.si_opaque, sizeof(stateid_opaque_t)); + status = nfsd4_decode_stateid(argp, &read->rd_stateid); + if (status) + return status; + READ_BUF(12); READ64(read->rd_offset); READ32(read->rd_length); @@ -834,15 +848,13 @@ nfsd4_decode_secinfo(struct nfsd4_compoundargs *argp, static __be32 nfsd4_decode_setattr(struct nfsd4_compoundargs *argp, struct nfsd4_setattr *setattr) { - DECODE_HEAD; - - READ_BUF(sizeof(stateid_t)); - READ32(setattr->sa_stateid.si_generation); - COPYMEM(&setattr->sa_stateid.si_opaque, sizeof(stateid_opaque_t)); - if ((status = nfsd4_decode_fattr(argp, setattr->sa_bmval, &setattr->sa_iattr, &setattr->sa_acl))) - goto out; + __be32 status; - DECODE_TAIL; + status = nfsd4_decode_stateid(argp, &setattr->sa_stateid); + if (status) + return status; + return nfsd4_decode_fattr(argp, setattr->sa_bmval, + &setattr->sa_iattr, &setattr->sa_acl); } static __be32 @@ -927,9 +939,10 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write) int len; DECODE_HEAD; - READ_BUF(sizeof(stateid_opaque_t) + 20); - READ32(write->wr_stateid.si_generation); - COPYMEM(&write->wr_stateid.si_opaque, sizeof(stateid_opaque_t)); + status = nfsd4_decode_stateid(argp, &write->wr_stateid); + if (status) + return status; + READ_BUF(16); READ64(write->wr_offset); READ32(write->wr_stable_how); if (write->wr_stable_how > 2) @@ -1183,7 +1196,6 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) * Header routine to setup seqid operation replay cache */ #define ENCODE_SEQID_OP_HEAD \ - __be32 *p; \ __be32 *save; \ \ save = resp->p; @@ -1950,6 +1962,17 @@ fail: return -EINVAL; } +static void +nfsd4_encode_stateid(struct nfsd4_compoundres *resp, stateid_t *sid) +{ + ENCODE_HEAD; + + RESERVE_SPACE(sizeof(stateid_t)); + WRITE32(sid->si_generation); + WRITEMEM(&sid->si_opaque, sizeof(stateid_opaque_t)); + ADJUST_ARGS(); +} + static __be32 nfsd4_encode_access(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_access *access) { @@ -1969,12 +1992,9 @@ nfsd4_encode_close(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_c { ENCODE_SEQID_OP_HEAD; - if (!nfserr) { - RESERVE_SPACE(sizeof(stateid_t)); - WRITE32(close->cl_stateid.si_generation); - WRITEMEM(&close->cl_stateid.si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); - } + if (!nfserr) + nfsd4_encode_stateid(resp, &close->cl_stateid); + ENCODE_SEQID_OP_TAIL(close->cl_stateowner); return nfserr; } @@ -2074,12 +2094,9 @@ nfsd4_encode_lock(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_lo { ENCODE_SEQID_OP_HEAD; - if (!nfserr) { - RESERVE_SPACE(4 + sizeof(stateid_t)); - WRITE32(lock->lk_resp_stateid.si_generation); - WRITEMEM(&lock->lk_resp_stateid.si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); - } else if (nfserr == nfserr_denied) + if (!nfserr) + nfsd4_encode_stateid(resp, &lock->lk_resp_stateid); + else if (nfserr == nfserr_denied) nfsd4_encode_lock_denied(resp, &lock->lk_denied); ENCODE_SEQID_OP_TAIL(lock->lk_replay_owner); @@ -2099,13 +2116,9 @@ nfsd4_encode_locku(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_l { ENCODE_SEQID_OP_HEAD; - if (!nfserr) { - RESERVE_SPACE(sizeof(stateid_t)); - WRITE32(locku->lu_stateid.si_generation); - WRITEMEM(&locku->lu_stateid.si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); - } - + if (!nfserr) + nfsd4_encode_stateid(resp, &locku->lu_stateid); + ENCODE_SEQID_OP_TAIL(locku->lu_stateowner); return nfserr; } @@ -2128,14 +2141,14 @@ nfsd4_encode_link(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_li static __be32 nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open *open) { + ENCODE_HEAD; ENCODE_SEQID_OP_HEAD; if (nfserr) goto out; - RESERVE_SPACE(36 + sizeof(stateid_t)); - WRITE32(open->op_stateid.si_generation); - WRITEMEM(&open->op_stateid.si_opaque, sizeof(stateid_opaque_t)); + nfsd4_encode_stateid(resp, &open->op_stateid); + RESERVE_SPACE(40); WRITECINFO(open->op_cinfo); WRITE32(open->op_rflags); WRITE32(2); @@ -2148,8 +2161,8 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op case NFS4_OPEN_DELEGATE_NONE: break; case NFS4_OPEN_DELEGATE_READ: - RESERVE_SPACE(20 + sizeof(stateid_t)); - WRITEMEM(&open->op_delegate_stateid, sizeof(stateid_t)); + nfsd4_encode_stateid(resp, &open->op_delegate_stateid); + RESERVE_SPACE(20); WRITE32(open->op_recall); /* @@ -2162,8 +2175,8 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op ADJUST_ARGS(); break; case NFS4_OPEN_DELEGATE_WRITE: - RESERVE_SPACE(32 + sizeof(stateid_t)); - WRITEMEM(&open->op_delegate_stateid, sizeof(stateid_t)); + nfsd4_encode_stateid(resp, &open->op_delegate_stateid); + RESERVE_SPACE(32); WRITE32(0); /* @@ -2195,13 +2208,9 @@ static __be32 nfsd4_encode_open_confirm(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_confirm *oc) { ENCODE_SEQID_OP_HEAD; - - if (!nfserr) { - RESERVE_SPACE(sizeof(stateid_t)); - WRITE32(oc->oc_resp_stateid.si_generation); - WRITEMEM(&oc->oc_resp_stateid.si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); - } + + if (!nfserr) + nfsd4_encode_stateid(resp, &oc->oc_resp_stateid); ENCODE_SEQID_OP_TAIL(oc->oc_stateowner); return nfserr; @@ -2211,13 +2220,9 @@ static __be32 nfsd4_encode_open_downgrade(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_open_downgrade *od) { ENCODE_SEQID_OP_HEAD; - - if (!nfserr) { - RESERVE_SPACE(sizeof(stateid_t)); - WRITE32(od->od_stateid.si_generation); - WRITEMEM(&od->od_stateid.si_opaque, sizeof(stateid_opaque_t)); - ADJUST_ARGS(); - } + + if (!nfserr) + nfsd4_encode_stateid(resp, &od->od_stateid); ENCODE_SEQID_OP_TAIL(od->od_stateowner); return nfserr; diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index ea37c96f0445..cd25d91895a1 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -302,17 +302,27 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) if (error) goto out; - if (!(access & NFSD_MAY_LOCK)) { - /* - * pseudoflavor restrictions are not enforced on NLM, - * which clients virtually always use auth_sys for, - * even while using RPCSEC_GSS for NFS. - */ - error = check_nfsd_access(exp, rqstp); - if (error) - goto out; - } + /* + * pseudoflavor restrictions are not enforced on NLM, + * which clients virtually always use auth_sys for, + * even while using RPCSEC_GSS for NFS. + */ + if (access & NFSD_MAY_LOCK) + goto skip_pseudoflavor_check; + /* + * Clients may expect to be able to use auth_sys during mount, + * even if they use gss for everything else; see section 2.3.2 + * of rfc 2623. + */ + if (access & NFSD_MAY_BYPASS_GSS_ON_ROOT + && exp->ex_path.dentry == dentry) + goto skip_pseudoflavor_check; + + error = check_nfsd_access(exp, rqstp); + if (error) + goto out; +skip_pseudoflavor_check: /* Finally, check access permissions. */ error = nfsd_permission(rqstp, exp, dentry, access); diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index 0766f95d236a..5cffeca7acef 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -65,7 +65,8 @@ nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle *argp, dprintk("nfsd: GETATTR %s\n", SVCFH_fmt(&argp->fh)); fh_copy(&resp->fh, &argp->fh); - nfserr = fh_verify(rqstp, &resp->fh, 0, NFSD_MAY_NOP); + nfserr = fh_verify(rqstp, &resp->fh, 0, + NFSD_MAY_NOP | NFSD_MAY_BYPASS_GSS_ON_ROOT); return nfsd_return_attrs(nfserr, resp); } @@ -521,7 +522,8 @@ nfsd_proc_statfs(struct svc_rqst * rqstp, struct nfsd_fhandle *argp, dprintk("nfsd: STATFS %s\n", SVCFH_fmt(&argp->fh)); - nfserr = nfsd_statfs(rqstp, &argp->fh, &resp->stats); + nfserr = nfsd_statfs(rqstp, &argp->fh, &resp->stats, + NFSD_MAY_BYPASS_GSS_ON_ROOT); fh_put(&argp->fh); return nfserr; } diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 80292ff5e924..7f3d76a7839d 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -229,6 +229,7 @@ int nfsd_create_serv(void) atomic_set(&nfsd_busy, 0); nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize, + AF_INET, nfsd_last_thread, nfsd, THIS_MODULE); if (nfsd_serv == NULL) err = -ENOMEM; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 18060bed5267..aa1d0d6489a1 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -83,7 +83,6 @@ struct raparm_hbucket { spinlock_t pb_lock; } ____cacheline_aligned_in_smp; -static struct raparms * raparml; #define RAPARM_HASH_BITS 4 #define RAPARM_HASH_SIZE (1<<RAPARM_HASH_BITS) #define RAPARM_HASH_MASK (RAPARM_HASH_SIZE-1) @@ -1866,9 +1865,9 @@ out: * N.B. After this call fhp needs an fh_put */ __be32 -nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat) +nfsd_statfs(struct svc_rqst *rqstp, struct svc_fh *fhp, struct kstatfs *stat, int access) { - __be32 err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP); + __be32 err = fh_verify(rqstp, fhp, 0, NFSD_MAY_NOP | access); if (!err && vfs_statfs(fhp->fh_dentry,stat)) err = nfserr_io; return err; @@ -1966,11 +1965,20 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, void nfsd_racache_shutdown(void) { - if (!raparml) - return; + struct raparms *raparm, *last_raparm; + unsigned int i; + dprintk("nfsd: freeing readahead buffers.\n"); - kfree(raparml); - raparml = NULL; + + for (i = 0; i < RAPARM_HASH_SIZE; i++) { + raparm = raparm_hash[i].pb_head; + while(raparm) { + last_raparm = raparm; + raparm = raparm->p_next; + kfree(last_raparm); + } + raparm_hash[i].pb_head = NULL; + } } /* * Initialize readahead param cache @@ -1981,35 +1989,38 @@ nfsd_racache_init(int cache_size) int i; int j = 0; int nperbucket; + struct raparms **raparm = NULL; - if (raparml) + if (raparm_hash[0].pb_head) return 0; - if (cache_size < 2*RAPARM_HASH_SIZE) - cache_size = 2*RAPARM_HASH_SIZE; - raparml = kcalloc(cache_size, sizeof(struct raparms), GFP_KERNEL); - - if (!raparml) { - printk(KERN_WARNING - "nfsd: Could not allocate memory read-ahead cache.\n"); - return -ENOMEM; - } + nperbucket = DIV_ROUND_UP(cache_size, RAPARM_HASH_SIZE); + if (nperbucket < 2) + nperbucket = 2; + cache_size = nperbucket * RAPARM_HASH_SIZE; dprintk("nfsd: allocating %d readahead buffers.\n", cache_size); - for (i = 0 ; i < RAPARM_HASH_SIZE ; i++) { - raparm_hash[i].pb_head = NULL; + + for (i = 0; i < RAPARM_HASH_SIZE; i++) { spin_lock_init(&raparm_hash[i].pb_lock); - } - nperbucket = DIV_ROUND_UP(cache_size, RAPARM_HASH_SIZE); - for (i = 0; i < cache_size - 1; i++) { - if (i % nperbucket == 0) - raparm_hash[j++].pb_head = raparml + i; - if (i % nperbucket < nperbucket-1) - raparml[i].p_next = raparml + i + 1; + + raparm = &raparm_hash[i].pb_head; + for (j = 0; j < nperbucket; j++) { + *raparm = kzalloc(sizeof(struct raparms), GFP_KERNEL); + if (!*raparm) + goto out_nomem; + raparm = &(*raparm)->p_next; + } + *raparm = NULL; } nfsdstats.ra_size = cache_size; return 0; + +out_nomem: + dprintk("nfsd: kmalloc failed, freeing readahead buffers\n"); + nfsd_racache_shutdown(); + return -ENOMEM; } #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c index 79ecd281d2cb..3f87d2632947 100644 --- a/fs/proc/nommu.c +++ b/fs/proc/nommu.c @@ -52,14 +52,14 @@ int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma) } seq_printf(m, - "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n", + "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n", vma->vm_start, vma->vm_end, flags & VM_READ ? 'r' : '-', flags & VM_WRITE ? 'w' : '-', flags & VM_EXEC ? 'x' : '-', flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p', - vma->vm_pgoff << PAGE_SHIFT, + ((loff_t)vma->vm_pgoff) << PAGE_SHIFT, MAJOR(dev), MINOR(dev), ino, &len); if (file) { diff --git a/fs/proc/proc_misc.c b/fs/proc/proc_misc.c index ded969862960..486b13a9e4e7 100644 --- a/fs/proc/proc_misc.c +++ b/fs/proc/proc_misc.c @@ -677,6 +677,7 @@ static int cmdline_read_proc(char *page, char **start, off_t off, return proc_calc_metrics(page, start, off, count, eof, len); } +#ifdef CONFIG_FILE_LOCKING static int locks_open(struct inode *inode, struct file *filp) { return seq_open(filp, &locks_seq_operations); @@ -688,6 +689,7 @@ static const struct file_operations proc_locks_operations = { .llseek = seq_lseek, .release = seq_release, }; +#endif /* CONFIG_FILE_LOCKING */ static int execdomains_read_proc(char *page, char **start, off_t off, int count, int *eof, void *data) @@ -881,7 +883,9 @@ void __init proc_misc_init(void) #ifdef CONFIG_PRINTK proc_create("kmsg", S_IRUSR, NULL, &proc_kmsg_operations); #endif +#ifdef CONFIG_FILE_LOCKING proc_create("locks", 0, NULL, &proc_locks_operations); +#endif proc_create("devices", 0, NULL, &proc_devinfo_operations); proc_create("cpuinfo", 0, NULL, &proc_cpuinfo_operations); #ifdef CONFIG_BLOCK diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c index 7546a918f790..73d1891ee625 100644 --- a/fs/proc/task_mmu.c +++ b/fs/proc/task_mmu.c @@ -219,14 +219,14 @@ static int show_map(struct seq_file *m, void *v) ino = inode->i_ino; } - seq_printf(m, "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n", + seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n", vma->vm_start, vma->vm_end, flags & VM_READ ? 'r' : '-', flags & VM_WRITE ? 'w' : '-', flags & VM_EXEC ? 'x' : '-', flags & VM_MAYSHARE ? 's' : 'p', - vma->vm_pgoff << PAGE_SHIFT, + ((loff_t)vma->vm_pgoff) << PAGE_SHIFT, MAJOR(dev), MINOR(dev), ino, &len); /* diff --git a/fs/sysfs/dir.c b/fs/sysfs/dir.c index aedaeba82ae5..4ffcfd2d5ea0 100644 --- a/fs/sysfs/dir.c +++ b/fs/sysfs/dir.c @@ -85,6 +85,7 @@ static void sysfs_unlink_sibling(struct sysfs_dirent *sd) /** * sysfs_get_dentry - get dentry for the given sysfs_dirent + * @sb: superblock of the dentry to return * @sd: sysfs_dirent of interest * * Get dentry for @sd. Dentry is looked up if currently not @@ -97,9 +98,10 @@ static void sysfs_unlink_sibling(struct sysfs_dirent *sd) * RETURNS: * Pointer to found dentry on success, ERR_PTR() value on error. */ -struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd) +struct dentry *sysfs_get_dentry(struct super_block *sb, + struct sysfs_dirent *sd) { - struct dentry *dentry = dget(sysfs_sb->s_root); + struct dentry *dentry = dget(sb->s_root); while (dentry->d_fsdata != sd) { struct sysfs_dirent *cur; @@ -636,6 +638,7 @@ struct sysfs_dirent *sysfs_get_dirent(struct sysfs_dirent *parent_sd, return sd; } +EXPORT_SYMBOL_GPL(sysfs_get_dirent); static int create_dir(struct kobject *kobj, struct sysfs_dirent *parent_sd, const char *name, struct sysfs_dirent **p_sd) @@ -792,68 +795,177 @@ void sysfs_remove_dir(struct kobject * kobj) __sysfs_remove_dir(sd); } +/** + * __sysfs_get_dentry - get dentry for the given sysfs_dirent + * @sb: superblock of the dentry to return + * @sd: sysfs_dirent of interest + * + * Get dentry for @sd. Only return a dentry if one currently + * exists. + * + * LOCKING: + * Kernel thread context (may sleep) + * + * RETURNS: + * Pointer to found dentry on success, NULL on failure. + */ +static struct dentry *__sysfs_get_dentry(struct super_block *sb, + struct sysfs_dirent *sd) +{ + struct inode *inode; + struct dentry *dentry = NULL; + + inode = ilookup5_nowait(sysfs_sb, sd->s_ino, sysfs_ilookup_test, sd); + if (inode && !(inode->i_state & I_NEW)) { + struct dentry *alias; + spin_lock(&dcache_lock); + list_for_each_entry(alias, &inode->i_dentry, d_alias) { + if (!IS_ROOT(alias) && d_unhashed(alias)) + continue; + if (alias->d_sb != sb) + continue; + dentry = alias; + dget_locked(dentry); + break; + } + spin_unlock(&dcache_lock); + } + iput(inode); + return dentry; +} + +struct sysfs_rename_struct { + struct list_head list; + struct dentry *old_dentry; + struct dentry *new_dentry; + struct dentry *old_parent; + struct dentry *new_parent; +}; + +static void post_rename(struct list_head *head) +{ + struct sysfs_rename_struct *srs; + while (!list_empty(head)) { + srs = list_entry(head->next, struct sysfs_rename_struct, list); + dput(srs->old_dentry); + dput(srs->new_dentry); + dput(srs->old_parent); + dput(srs->new_parent); + list_del(&srs->list); + kfree(srs); + } +} + +static int prep_rename(struct list_head *head, + struct sysfs_dirent *sd, struct sysfs_dirent *new_parent_sd, + const char *name) +{ + struct sysfs_rename_struct *srs; + struct super_block *sb; + struct dentry *dentry; + int error; + + list_for_each_entry(sb, &sysfs_fs_type.fs_supers, s_instances) { + dentry = sysfs_get_dentry(sb, sd); + if (dentry == ERR_PTR(-EXDEV)) + continue; + if (IS_ERR(dentry)) { + error = PTR_ERR(dentry); + goto err_out; + } + + srs = kzalloc(sizeof(*srs), GFP_KERNEL); + if (!srs) { + error = -ENOMEM; + dput(dentry); + goto err_out; + } + + INIT_LIST_HEAD(&srs->list); + list_add(head, &srs->list); + srs->old_dentry = dentry; + srs->old_parent = dget(dentry->d_parent); + + dentry = sysfs_get_dentry(sb, new_parent_sd); + if (IS_ERR(dentry)) { + error = PTR_ERR(dentry); + goto err_out; + } + srs->new_parent = dentry; + + error = -ENOMEM; + dentry = d_alloc_name(srs->new_parent, name); + if (!dentry) + goto err_out; + srs->new_dentry = dentry; + } + return 0; + +err_out: + post_rename(head); + return error; +} + int sysfs_rename_dir(struct kobject * kobj, const char *new_name) { struct sysfs_dirent *sd = kobj->sd; - struct dentry *parent = NULL; - struct dentry *old_dentry = NULL, *new_dentry = NULL; + struct list_head todo; + struct sysfs_rename_struct *srs; + struct inode *parent_inode = NULL; const char *dup_name = NULL; int error; + INIT_LIST_HEAD(&todo); mutex_lock(&sysfs_rename_mutex); error = 0; if (strcmp(sd->s_name, new_name) == 0) goto out; /* nothing to rename */ - /* get the original dentry */ - old_dentry = sysfs_get_dentry(sd); - if (IS_ERR(old_dentry)) { - error = PTR_ERR(old_dentry); - old_dentry = NULL; - goto out; - } + sysfs_grab_supers(); + error = prep_rename(&todo, sd, sd->s_parent, new_name); + if (error) + goto out_release; - parent = old_dentry->d_parent; + error = -ENOMEM; + mutex_lock(&sysfs_mutex); + parent_inode = sysfs_get_inode(sd->s_parent); + mutex_unlock(&sysfs_mutex); + if (!parent_inode) + goto out_release; - /* lock parent and get dentry for new name */ - mutex_lock(&parent->d_inode->i_mutex); + mutex_lock(&parent_inode->i_mutex); mutex_lock(&sysfs_mutex); error = -EEXIST; if (sysfs_find_dirent(sd->s_parent, new_name)) goto out_unlock; - error = -ENOMEM; - new_dentry = d_alloc_name(parent, new_name); - if (!new_dentry) - goto out_unlock; - - /* rename kobject and sysfs_dirent */ + /* rename sysfs_dirent */ error = -ENOMEM; new_name = dup_name = kstrdup(new_name, GFP_KERNEL); if (!new_name) goto out_unlock; - error = kobject_set_name(kobj, "%s", new_name); - if (error) - goto out_unlock; - dup_name = sd->s_name; sd->s_name = new_name; /* rename */ - d_add(new_dentry, NULL); - d_move(old_dentry, new_dentry); + list_for_each_entry(srs, &todo, list) { + d_add(srs->new_dentry, NULL); + d_move(srs->old_dentry, srs->new_dentry); + } error = 0; - out_unlock: +out_unlock: mutex_unlock(&sysfs_mutex); - mutex_unlock(&parent->d_inode->i_mutex); + mutex_unlock(&parent_inode->i_mutex); kfree(dup_name); - dput(old_dentry); - dput(new_dentry); - out: +out_release: + iput(parent_inode); + post_rename(&todo); + sysfs_release_supers(); +out: mutex_unlock(&sysfs_rename_mutex); return error; } @@ -862,10 +974,12 @@ int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj) { struct sysfs_dirent *sd = kobj->sd; struct sysfs_dirent *new_parent_sd; - struct dentry *old_parent, *new_parent = NULL; - struct dentry *old_dentry = NULL, *new_dentry = NULL; + struct list_head todo; + struct sysfs_rename_struct *srs; + struct inode *old_parent_inode = NULL, *new_parent_inode = NULL; int error; + INIT_LIST_HEAD(&todo); mutex_lock(&sysfs_rename_mutex); BUG_ON(!sd->s_parent); new_parent_sd = new_parent_kobj->sd ? new_parent_kobj->sd : &sysfs_root; @@ -874,26 +988,29 @@ int sysfs_move_dir(struct kobject *kobj, struct kobject *new_parent_kobj) if (sd->s_parent == new_parent_sd) goto out; /* nothing to move */ - /* get dentries */ - old_dentry = sysfs_get_dentry(sd); - if (IS_ERR(old_dentry)) { - error = PTR_ERR(old_dentry); - old_dentry = NULL; - goto out; - } - old_parent = old_dentry->d_parent; + sysfs_grab_supers(); + error = prep_rename(&todo, sd, new_parent_sd, sd->s_name); + if (error) + goto out_release; - new_parent = sysfs_get_dentry(new_parent_sd); - if (IS_ERR(new_parent)) { - error = PTR_ERR(new_parent); - new_parent = NULL; - goto out; - } + error = -ENOMEM; + mutex_lock(&sysfs_mutex); + old_parent_inode = sysfs_get_inode(sd->s_parent); + mutex_unlock(&sysfs_mutex); + if (!old_parent_inode) + goto out_release; + + error = -ENOMEM; + mutex_lock(&sysfs_mutex); + new_parent_inode = sysfs_get_inode(new_parent_sd); + mutex_unlock(&sysfs_mutex); + if (!new_parent_inode) + goto out_release; again: - mutex_lock(&old_parent->d_inode->i_mutex); - if (!mutex_trylock(&new_parent->d_inode->i_mutex)) { - mutex_unlock(&old_parent->d_inode->i_mutex); + mutex_lock(&old_parent_inode->i_mutex); + if (!mutex_trylock(&new_parent_inode->i_mutex)) { + mutex_unlock(&old_parent_inode->i_mutex); goto again; } mutex_lock(&sysfs_mutex); @@ -902,14 +1019,11 @@ again: if (sysfs_find_dirent(new_parent_sd, sd->s_name)) goto out_unlock; - error = -ENOMEM; - new_dentry = d_alloc_name(new_parent, sd->s_name); - if (!new_dentry) - goto out_unlock; - error = 0; - d_add(new_dentry, NULL); - d_move(old_dentry, new_dentry); + list_for_each_entry(srs, &todo, list) { + d_add(srs->new_dentry, NULL); + d_move(srs->old_dentry, srs->new_dentry); + } /* Remove from old parent's list and insert into new parent's list. */ sysfs_unlink_sibling(sd); @@ -918,14 +1032,17 @@ again: sd->s_parent = new_parent_sd; sysfs_link_sibling(sd); - out_unlock: +out_unlock: mutex_unlock(&sysfs_mutex); - mutex_unlock(&new_parent->d_inode->i_mutex); - mutex_unlock(&old_parent->d_inode->i_mutex); - out: - dput(new_parent); - dput(old_dentry); - dput(new_dentry); + mutex_unlock(&new_parent_inode->i_mutex); + mutex_unlock(&old_parent_inode->i_mutex); + +out_release: + iput(new_parent_inode); + iput(old_parent_inode); + post_rename(&todo); + sysfs_release_supers(); +out: mutex_unlock(&sysfs_rename_mutex); return error; } diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c index c9e4e5091da1..61c34768e7b2 100644 --- a/fs/sysfs/file.c +++ b/fs/sysfs/file.c @@ -19,10 +19,18 @@ #include <linux/poll.h> #include <linux/list.h> #include <linux/mutex.h> +#include <linux/limits.h> #include <asm/uaccess.h> #include "sysfs.h" +/* used in crash dumps to help with debugging */ +static char last_sysfs_file[PATH_MAX]; +void sysfs_printk_last_file(void) +{ + printk(KERN_EMERG "last sysfs file: %s\n", last_sysfs_file); +} + /* * There's one sysfs_buffer for each open file and one * sysfs_open_dirent for each sysfs_dirent with one or more open @@ -328,6 +336,11 @@ static int sysfs_open_file(struct inode *inode, struct file *file) struct sysfs_buffer *buffer; struct sysfs_ops *ops; int error = -EACCES; + char *p; + + p = d_path(&file->f_path, last_sysfs_file, sizeof(last_sysfs_file)); + if (p) + memmove(last_sysfs_file, p, strlen(p) + 1); /* need attr_sd for attr and ops, its parent for kobj */ if (!sysfs_get_active_two(attr_sd)) @@ -440,6 +453,22 @@ static unsigned int sysfs_poll(struct file *filp, poll_table *wait) return POLLERR|POLLPRI; } +void sysfs_notify_dirent(struct sysfs_dirent *sd) +{ + struct sysfs_open_dirent *od; + + spin_lock(&sysfs_open_dirent_lock); + + od = sd->s_attr.open; + if (od) { + atomic_inc(&od->event); + wake_up_interruptible(&od->poll); + } + + spin_unlock(&sysfs_open_dirent_lock); +} +EXPORT_SYMBOL_GPL(sysfs_notify_dirent); + void sysfs_notify(struct kobject *k, char *dir, char *attr) { struct sysfs_dirent *sd = k->sd; @@ -450,19 +479,8 @@ void sysfs_notify(struct kobject *k, char *dir, char *attr) sd = sysfs_find_dirent(sd, dir); if (sd && attr) sd = sysfs_find_dirent(sd, attr); - if (sd) { - struct sysfs_open_dirent *od; - - spin_lock(&sysfs_open_dirent_lock); - - od = sd->s_attr.open; - if (od) { - atomic_inc(&od->event); - wake_up_interruptible(&od->poll); - } - - spin_unlock(&sysfs_open_dirent_lock); - } + if (sd) + sysfs_notify_dirent(sd); mutex_unlock(&sysfs_mutex); } @@ -560,8 +578,8 @@ EXPORT_SYMBOL_GPL(sysfs_add_file_to_group); int sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode) { struct sysfs_dirent *victim_sd = NULL; - struct dentry *victim = NULL; - struct inode * inode; + struct super_block *sb; + struct inode * inode = NULL; struct iattr newattrs; int rc; @@ -570,34 +588,42 @@ int sysfs_chmod_file(struct kobject *kobj, struct attribute *attr, mode_t mode) if (!victim_sd) goto out; - mutex_lock(&sysfs_rename_mutex); - victim = sysfs_get_dentry(victim_sd); - mutex_unlock(&sysfs_rename_mutex); - if (IS_ERR(victim)) { - rc = PTR_ERR(victim); - victim = NULL; - goto out; - } - - inode = victim->d_inode; + rc = -ENOENT; + mutex_lock(&sysfs_mutex); + inode = sysfs_get_inode(victim_sd); + mutex_unlock(&sysfs_mutex); + if (!inode) + goto out; + mutex_lock(&sysfs_rename_mutex); + sysfs_grab_supers(); mutex_lock(&inode->i_mutex); newattrs.ia_mode = (mode & S_IALLUGO) | (inode->i_mode & ~S_IALLUGO); newattrs.ia_valid = ATTR_MODE | ATTR_CTIME; newattrs.ia_ctime = current_fs_time(inode->i_sb); - rc = sysfs_setattr(victim, &newattrs); + rc = sysfs_sd_setattr(victim_sd, inode, &newattrs); + if (rc) + goto out_unlock; + + list_for_each_entry(sb, &sysfs_fs_type.fs_supers, s_instances) { + /* Ignore it when the dentry does not exist on the + * target superblock. + */ + struct dentry * victim = sysfs_get_dentry(sb, victim_sd); + if (IS_ERR(victim)) + continue; - if (rc == 0) { fsnotify_change(victim, newattrs.ia_valid); - mutex_lock(&sysfs_mutex); - victim_sd->s_mode = newattrs.ia_mode; - mutex_unlock(&sysfs_mutex); + dput(victim); } + out_unlock: mutex_unlock(&inode->i_mutex); + sysfs_release_supers(); + mutex_unlock(&sysfs_rename_mutex); out: - dput(victim); + iput(inode); sysfs_put(victim_sd); return rc; } diff --git a/fs/sysfs/inode.c b/fs/sysfs/inode.c index eb53c632f856..80f8fd4b2f92 100644 --- a/fs/sysfs/inode.c +++ b/fs/sysfs/inode.c @@ -42,10 +42,9 @@ int __init sysfs_inode_init(void) return bdi_init(&sysfs_backing_dev_info); } -int sysfs_setattr(struct dentry * dentry, struct iattr * iattr) +int sysfs_sd_setattr(struct sysfs_dirent *sd, struct inode *inode, + struct iattr * iattr) { - struct inode * inode = dentry->d_inode; - struct sysfs_dirent * sd = dentry->d_fsdata; struct iattr * sd_iattr; unsigned int ia_valid = iattr->ia_valid; int error; @@ -55,10 +54,6 @@ int sysfs_setattr(struct dentry * dentry, struct iattr * iattr) sd_iattr = sd->s_iattr; - error = inode_change_ok(inode, iattr); - if (error) - return error; - iattr->ia_valid &= ~ATTR_SIZE; /* ignore size changes */ error = inode_setattr(inode, iattr); @@ -104,6 +99,20 @@ int sysfs_setattr(struct dentry * dentry, struct iattr * iattr) return error; } +int sysfs_setattr(struct dentry *dentry, struct iattr *iattr) +{ + struct inode * inode = dentry->d_inode; + struct sysfs_dirent * sd = dentry->d_fsdata; + int error; + + error = inode_change_ok(inode, iattr); + if (error) + return error; + + return sysfs_sd_setattr(sd, inode, iattr); +} + + static inline void set_default_inode_attr(struct inode * inode, mode_t mode) { inode->i_mode = mode; diff --git a/fs/sysfs/mount.c b/fs/sysfs/mount.c index 14f0023984d7..6ebda1a40918 100644 --- a/fs/sysfs/mount.c +++ b/fs/sysfs/mount.c @@ -16,6 +16,7 @@ #include <linux/mount.h> #include <linux/pagemap.h> #include <linux/init.h> +#include <linux/module.h> #include "sysfs.h" @@ -41,47 +42,110 @@ struct sysfs_dirent sysfs_root = { static int sysfs_fill_super(struct super_block *sb, void *data, int silent) { - struct inode *inode; - struct dentry *root; + struct sysfs_super_info *info = NULL; + struct inode *inode = NULL; + struct dentry *root = NULL; + int error; sb->s_blocksize = PAGE_CACHE_SIZE; sb->s_blocksize_bits = PAGE_CACHE_SHIFT; sb->s_magic = SYSFS_MAGIC; sb->s_op = &sysfs_ops; sb->s_time_gran = 1; - sysfs_sb = sb; + if (!sysfs_sb) + sysfs_sb = sb; + + error = -ENOMEM; + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + goto out_err; /* get root inode, initialize and unlock it */ + error = -ENOMEM; inode = sysfs_get_inode(&sysfs_root); if (!inode) { pr_debug("sysfs: could not get root inode\n"); - return -ENOMEM; + goto out_err; } /* instantiate and link root dentry */ + error = -ENOMEM; root = d_alloc_root(inode); if (!root) { pr_debug("%s: could not get root dentry!\n",__func__); - iput(inode); - return -ENOMEM; + goto out_err; } root->d_fsdata = &sysfs_root; sb->s_root = root; + sb->s_fs_info = info; return 0; + +out_err: + dput(root); + iput(inode); + kfree(info); + if (sysfs_sb == sb) + sysfs_sb = NULL; + return error; } static int sysfs_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, struct vfsmount *mnt) { - return get_sb_single(fs_type, flags, data, sysfs_fill_super, mnt); + int rc; + mutex_lock(&sysfs_rename_mutex); + rc = get_sb_single(fs_type, flags, data, sysfs_fill_super, mnt); + mutex_unlock(&sysfs_rename_mutex); + return rc; } -static struct file_system_type sysfs_fs_type = { +struct file_system_type sysfs_fs_type = { .name = "sysfs", .get_sb = sysfs_get_sb, .kill_sb = kill_anon_super, }; +void sysfs_grab_supers(void) +{ + /* must hold sysfs_rename_mutex */ + struct super_block *sb; + /* Loop until I have taken s_umount on all sysfs superblocks */ +restart: + spin_lock(&sb_lock); + list_for_each_entry(sb, &sysfs_fs_type.fs_supers, s_instances) { + if (sysfs_info(sb)->grabbed) + continue; + /* Wait for unmount activity to complete. */ + if (sb->s_count < S_BIAS) { + sb->s_count += 1; + spin_unlock(&sb_lock); + down_read(&sb->s_umount); + drop_super(sb); + goto restart; + } + atomic_inc(&sb->s_active); + sysfs_info(sb)->grabbed = 1; + } + spin_unlock(&sb_lock); +} + +void sysfs_release_supers(void) +{ + /* must hold sysfs_rename_mutex */ + struct super_block *sb; +restart: + spin_lock(&sb_lock); + list_for_each_entry(sb, &sysfs_fs_type.fs_supers, s_instances) { + if (!sysfs_info(sb)->grabbed) + continue; + sysfs_info(sb)->grabbed = 0; + spin_unlock(&sb_lock); + deactivate_super(sb); + goto restart; + } + spin_unlock(&sb_lock); +} + int __init sysfs_init(void) { int err = -ENOMEM; @@ -115,3 +179,17 @@ out_err: sysfs_dir_cachep = NULL; goto out; } + +#undef sysfs_get +struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd) +{ + return __sysfs_get(sd); +} +EXPORT_SYMBOL_GPL(sysfs_get); + +#undef sysfs_put +void sysfs_put(struct sysfs_dirent *sd) +{ + __sysfs_put(sd); +} +EXPORT_SYMBOL_GPL(sysfs_put); diff --git a/fs/sysfs/sysfs.h b/fs/sysfs/sysfs.h index a5db496f71c7..f0e5ecb38b6e 100644 --- a/fs/sysfs/sysfs.h +++ b/fs/sysfs/sysfs.h @@ -85,12 +85,22 @@ struct sysfs_addrm_cxt { int cnt; }; +struct sysfs_super_info { + int grabbed; +}; + +#define sysfs_info(SB) ((struct sysfs_super_info *)(SB)->s_fs_info) + /* * mount.c */ extern struct sysfs_dirent sysfs_root; extern struct super_block *sysfs_sb; extern struct kmem_cache *sysfs_dir_cachep; +extern struct file_system_type sysfs_fs_type; + +void sysfs_grab_supers(void); +void sysfs_release_supers(void); /* * dir.c @@ -102,7 +112,8 @@ extern spinlock_t sysfs_assoc_lock; extern const struct file_operations sysfs_dir_operations; extern const struct inode_operations sysfs_dir_inode_operations; -struct dentry *sysfs_get_dentry(struct sysfs_dirent *sd); +struct dentry *sysfs_get_dentry(struct super_block *sb, + struct sysfs_dirent *sd); struct sysfs_dirent *sysfs_get_active_two(struct sysfs_dirent *sd); void sysfs_put_active_two(struct sysfs_dirent *sd); void sysfs_addrm_start(struct sysfs_addrm_cxt *acxt, @@ -124,7 +135,7 @@ int sysfs_create_subdir(struct kobject *kobj, const char *name, struct sysfs_dirent **p_sd); void sysfs_remove_subdir(struct sysfs_dirent *sd); -static inline struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd) +static inline struct sysfs_dirent *__sysfs_get(struct sysfs_dirent *sd) { if (sd) { WARN_ON(!atomic_read(&sd->s_count)); @@ -132,17 +143,20 @@ static inline struct sysfs_dirent *sysfs_get(struct sysfs_dirent *sd) } return sd; } +#define sysfs_get(sd) __sysfs_get(sd) -static inline void sysfs_put(struct sysfs_dirent *sd) +static inline void __sysfs_put(struct sysfs_dirent *sd) { if (sd && atomic_dec_and_test(&sd->s_count)) release_sysfs_dirent(sd); } +#define sysfs_put(sd) __sysfs_put(sd) /* * inode.c */ struct inode *sysfs_get_inode(struct sysfs_dirent *sd); +int sysfs_sd_setattr(struct sysfs_dirent *sd, struct inode *inode, struct iattr *iattr); int sysfs_setattr(struct dentry *dentry, struct iattr *iattr); int sysfs_hash_and_remove(struct sysfs_dirent *dir_sd, const char *name); int sysfs_inode_init(void); diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c index 73c65f19e549..7d4bdfdd7853 100644 --- a/fs/xfs/linux-2.6/xfs_super.c +++ b/fs/xfs/linux-2.6/xfs_super.c @@ -1815,8 +1815,17 @@ xfs_fs_get_sb( void *data, struct vfsmount *mnt) { - return get_sb_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super, + int error; + + error = get_sb_bdev(fs_type, flags, dev_name, data, xfs_fs_fill_super, mnt); + if (!error) { + xfs_mount_t *mp = XFS_M(mnt->mnt_sb); + + mp->m_vfsmount = mnt; + } + + return error; } static struct super_operations xfs_super_operations = { diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h index f3c1024b1241..64116b58329c 100644 --- a/fs/xfs/xfs_mount.h +++ b/fs/xfs/xfs_mount.h @@ -341,6 +341,7 @@ typedef struct xfs_mount { spinlock_t m_sync_lock; /* work item list lock */ int m_sync_seq; /* sync thread generation no. */ wait_queue_head_t m_wait_single_sync_task; + struct vfsmount *m_vfsmount; } xfs_mount_t; /* |