diff options
59 files changed, 3029 insertions, 1489 deletions
diff --git a/Documentation/filesystems/automount-support.txt b/Documentation/filesystems/automount-support.txt index 58c65a1..7cac200 100644 --- a/Documentation/filesystems/automount-support.txt +++ b/Documentation/filesystems/automount-support.txt @@ -19,7 +19,7 @@ following procedure: (2) Have the follow_link() op do the following steps: - (a) Call do_kern_mount() to call the appropriate filesystem to set up a + (a) Call vfs_kern_mount() to call the appropriate filesystem to set up a superblock and gain a vfsmount structure representing it. (b) Copy the nameidata provided as an argument and substitute the dentry diff --git a/drivers/usb/core/inode.c b/drivers/usb/core/inode.c index 3cf945c..695b90a 100644 --- a/drivers/usb/core/inode.c +++ b/drivers/usb/core/inode.c @@ -569,7 +569,7 @@ static int create_special_files (void) ignore_mount = 1; /* create the devices special file */ - retval = simple_pin_fs("usbfs", &usbfs_mount, &usbfs_mount_count); + retval = simple_pin_fs(&usb_fs_type, &usbfs_mount, &usbfs_mount_count); if (retval) { err ("Unable to get usbfs mount"); goto exit; diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c index 61c599b..00c1f6b 100644 --- a/fs/9p/vfs_super.c +++ b/fs/9p/vfs_super.c @@ -253,11 +253,12 @@ static int v9fs_show_options(struct seq_file *m, struct vfsmount *mnt) } static void -v9fs_umount_begin(struct super_block *sb) +v9fs_umount_begin(struct vfsmount *vfsmnt, int flags) { - struct v9fs_session_info *v9ses = sb->s_fs_info; + struct v9fs_session_info *v9ses = vfsmnt->mnt_sb->s_fs_info; - v9fs_session_cancel(v9ses); + if (flags & MNT_FORCE) + v9fs_session_cancel(v9ses); } static struct super_operations v9fs_super_ops = { diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c index 4e6eeb5..7b6dc03 100644 --- a/fs/afs/mntpt.c +++ b/fs/afs/mntpt.c @@ -210,7 +210,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt) /* try and do the mount */ kdebug("--- attempting mount %s -o %s ---", devname, options); - mnt = do_kern_mount("afs", 0, devname, options); + mnt = vfs_kern_mount(&afs_fs_type, 0, devname, options); kdebug("--- mount result %p ---", mnt); free_page((unsigned long) devname); diff --git a/fs/afs/super.c b/fs/afs/super.c index 53c56e7..93a7821 100644 --- a/fs/afs/super.c +++ b/fs/afs/super.c @@ -48,7 +48,7 @@ static void afs_put_super(struct super_block *sb); static void afs_destroy_inode(struct inode *inode); -static struct file_system_type afs_fs_type = { +struct file_system_type afs_fs_type = { .owner = THIS_MODULE, .name = "afs", .get_sb = afs_get_sb, diff --git a/fs/afs/super.h b/fs/afs/super.h index ac11362..32de8cc 100644 --- a/fs/afs/super.h +++ b/fs/afs/super.h @@ -38,6 +38,8 @@ static inline struct afs_super_info *AFS_FS_S(struct super_block *sb) return sb->s_fs_info; } +extern struct file_system_type afs_fs_type; + #endif /* __KERNEL__ */ #endif /* _LINUX_AFS_SUPER_H */ diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c index d73d755..c0a909e 100644 --- a/fs/binfmt_misc.c +++ b/fs/binfmt_misc.c @@ -55,6 +55,7 @@ typedef struct { } Node; static DEFINE_RWLOCK(entries_lock); +static struct file_system_type bm_fs_type; static struct vfsmount *bm_mnt; static int entry_count; @@ -638,7 +639,7 @@ static ssize_t bm_register_write(struct file *file, const char __user *buffer, if (!inode) goto out2; - err = simple_pin_fs("binfmt_misc", &bm_mnt, &entry_count); + err = simple_pin_fs(&bm_fs_type, &bm_mnt, &entry_count); if (err) { iput(inode); inode = NULL; diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c index c262d88..3fdc225 100644 --- a/fs/cifs/cifsfs.c +++ b/fs/cifs/cifsfs.c @@ -402,12 +402,14 @@ static struct quotactl_ops cifs_quotactl_ops = { #endif #ifdef CONFIG_CIFS_EXPERIMENTAL -static void cifs_umount_begin(struct super_block * sblock) +static void cifs_umount_begin(struct vfsmount * vfsmnt, int flags) { struct cifs_sb_info *cifs_sb; struct cifsTconInfo * tcon; - cifs_sb = CIFS_SB(sblock); + if (!(flags & MNT_FORCE)) + return; + cifs_sb = CIFS_SB(vfsmnt->mnt_sb); if(cifs_sb == NULL) return; diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c index f920d30..be5d86a 100644 --- a/fs/configfs/mount.c +++ b/fs/configfs/mount.c @@ -118,7 +118,7 @@ static struct file_system_type configfs_fs_type = { int configfs_pin_fs(void) { - return simple_pin_fs("configfs", &configfs_mount, + return simple_pin_fs(&configfs_fs_type, &configfs_mount, &configfs_mnt_count); } diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c index b55b4ea..90f9417 100644 --- a/fs/debugfs/inode.c +++ b/fs/debugfs/inode.c @@ -199,7 +199,7 @@ struct dentry *debugfs_create_file(const char *name, mode_t mode, pr_debug("debugfs: creating file '%s'\n",name); - error = simple_pin_fs("debugfs", &debugfs_mount, &debugfs_mount_count); + error = simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); if (error) goto exit; diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c index 7627022..13ebe57 100644 --- a/fs/fuse/inode.c +++ b/fs/fuse/inode.c @@ -195,9 +195,10 @@ struct inode *fuse_iget(struct super_block *sb, unsigned long nodeid, return inode; } -static void fuse_umount_begin(struct super_block *sb) +static void fuse_umount_begin(struct vfsmount *vfsmnt, int flags) { - fuse_abort_conn(get_fuse_conn_super(sb)); + if (flags & MNT_FORCE) + fuse_abort_conn(get_fuse_conn_super(vfsmnt->mnt_sb)); } static void fuse_put_super(struct super_block *sb) @@ -424,13 +424,13 @@ out: static DEFINE_SPINLOCK(pin_fs_lock); -int simple_pin_fs(char *name, struct vfsmount **mount, int *count) +int simple_pin_fs(struct file_system_type *type, struct vfsmount **mount, int *count) { struct vfsmount *mnt = NULL; spin_lock(&pin_fs_lock); if (unlikely(!*mount)) { spin_unlock(&pin_fs_lock); - mnt = do_kern_mount(name, 0, name, NULL); + mnt = vfs_kern_mount(type, 0, type->name, NULL); if (IS_ERR(mnt)) return PTR_ERR(mnt); spin_lock(&pin_fs_lock); diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index bce7444..52774fe 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -147,11 +147,10 @@ u32 nlmclnt_grant(const struct sockaddr_in *addr, const struct nlm_lock *lock) * Someone has sent us an SM_NOTIFY. Ensure we bind to the new port number, * that we mark locks for reclaiming, and that we bump the pseudo NSM state. */ -static inline -void nlmclnt_prepare_reclaim(struct nlm_host *host, u32 newstate) +static void nlmclnt_prepare_reclaim(struct nlm_host *host) { + down_write(&host->h_rwsem); host->h_monitored = 0; - host->h_nsmstate = newstate; host->h_state++; host->h_nextrebind = 0; nlm_rebind_host(host); @@ -164,6 +163,13 @@ void nlmclnt_prepare_reclaim(struct nlm_host *host, u32 newstate) dprintk("NLM: reclaiming locks for host %s", host->h_name); } +static void nlmclnt_finish_reclaim(struct nlm_host *host) +{ + host->h_reclaiming = 0; + up_write(&host->h_rwsem); + dprintk("NLM: done reclaiming locks for host %s", host->h_name); +} + /* * Reclaim all locks on server host. We do this by spawning a separate * reclaimer thread. @@ -171,12 +177,10 @@ void nlmclnt_prepare_reclaim(struct nlm_host *host, u32 newstate) void nlmclnt_recovery(struct nlm_host *host, u32 newstate) { - if (host->h_reclaiming++) { - if (host->h_nsmstate == newstate) - return; - nlmclnt_prepare_reclaim(host, newstate); - } else { - nlmclnt_prepare_reclaim(host, newstate); + if (host->h_nsmstate == newstate) + return; + host->h_nsmstate = newstate; + if (!host->h_reclaiming++) { nlm_get_host(host); __module_get(THIS_MODULE); if (kernel_thread(reclaimer, host, CLONE_KERNEL) < 0) @@ -190,6 +194,7 @@ reclaimer(void *ptr) struct nlm_host *host = (struct nlm_host *) ptr; struct nlm_wait *block; struct file_lock *fl, *next; + u32 nsmstate; daemonize("%s-reclaim", host->h_name); allow_signal(SIGKILL); @@ -199,19 +204,25 @@ reclaimer(void *ptr) lock_kernel(); lockd_up(); + nlmclnt_prepare_reclaim(host); /* First, reclaim all locks that have been marked. */ restart: + nsmstate = host->h_nsmstate; list_for_each_entry_safe(fl, next, &host->h_reclaim, fl_u.nfs_fl.list) { list_del_init(&fl->fl_u.nfs_fl.list); if (signalled()) continue; - if (nlmclnt_reclaim(host, fl) == 0) - list_add_tail(&fl->fl_u.nfs_fl.list, &host->h_granted); - goto restart; + if (nlmclnt_reclaim(host, fl) != 0) + continue; + list_add_tail(&fl->fl_u.nfs_fl.list, &host->h_granted); + if (host->h_nsmstate != nsmstate) { + /* Argh! The server rebooted again! */ + list_splice_init(&host->h_granted, &host->h_reclaim); + goto restart; + } } - - host->h_reclaiming = 0; + nlmclnt_finish_reclaim(host); /* Now, wake up all processes that sleep on a blocked lock */ list_for_each_entry(block, &nlm_blocked, b_list) { diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c index f96e381..4db6209 100644 --- a/fs/lockd/clntproc.c +++ b/fs/lockd/clntproc.c @@ -508,7 +508,10 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl) } block = nlmclnt_prepare_block(host, fl); +again: for(;;) { + /* Reboot protection */ + fl->fl_u.nfs_fl.state = host->h_state; status = nlmclnt_call(req, NLMPROC_LOCK); if (status < 0) goto out_unblock; @@ -531,10 +534,16 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl) } if (resp->status == NLM_LCK_GRANTED) { - fl->fl_u.nfs_fl.state = host->h_state; + down_read(&host->h_rwsem); + /* Check whether or not the server has rebooted */ + if (fl->fl_u.nfs_fl.state != host->h_state) { + up_read(&host->h_rwsem); + goto again; + } fl->fl_flags |= FL_SLEEP; /* Ensure the resulting lock will get added to granted list */ do_vfs_lock(fl); + up_read(&host->h_rwsem); } status = nlm_stat_to_errno(resp->status); out_unblock: @@ -596,6 +605,7 @@ nlmclnt_reclaim(struct nlm_host *host, struct file_lock *fl) static int nlmclnt_unlock(struct nlm_rqst *req, struct file_lock *fl) { + struct nlm_host *host = req->a_host; struct nlm_res *resp = &req->a_res; int status; @@ -604,7 +614,9 @@ nlmclnt_unlock(struct nlm_rqst *req, struct file_lock *fl) * request, or to deny it with NLM_LCK_DENIED_GRACE_PERIOD. In either * case, we want to unlock. */ + down_read(&host->h_rwsem); do_vfs_lock(fl); + up_read(&host->h_rwsem); if (req->a_flags & RPC_TASK_ASYNC) return nlm_async_call(req, NLMPROC_UNLOCK, &nlmclnt_unlock_ops); diff --git a/fs/lockd/host.c b/fs/lockd/host.c index 729ac42..38b0e8a 100644 --- a/fs/lockd/host.c +++ b/fs/lockd/host.c @@ -112,11 +112,12 @@ nlm_lookup_host(int server, struct sockaddr_in *sin, host->h_version = version; host->h_proto = proto; host->h_rpcclnt = NULL; - init_MUTEX(&host->h_sema); + mutex_init(&host->h_mutex); host->h_nextrebind = jiffies + NLM_HOST_REBIND; host->h_expires = jiffies + NLM_HOST_EXPIRE; atomic_set(&host->h_count, 1); init_waitqueue_head(&host->h_gracewait); + init_rwsem(&host->h_rwsem); host->h_state = 0; /* pseudo NSM state */ host->h_nsmstate = 0; /* real NSM state */ host->h_server = server; @@ -172,7 +173,7 @@ nlm_bind_host(struct nlm_host *host) (unsigned)ntohl(host->h_addr.sin_addr.s_addr)); /* Lock host handle */ - down(&host->h_sema); + mutex_lock(&host->h_mutex); /* If we've already created an RPC client, check whether * RPC rebind is required @@ -204,12 +205,12 @@ nlm_bind_host(struct nlm_host *host) host->h_rpcclnt = clnt; } - up(&host->h_sema); + mutex_unlock(&host->h_mutex); return clnt; forgetit: printk("lockd: couldn't create RPC handle for %s\n", host->h_name); - up(&host->h_sema); + mutex_unlock(&host->h_mutex); return NULL; } diff --git a/fs/namespace.c b/fs/namespace.c index bf478ad..6bb0b85 100644 --- a/fs/namespace.c +++ b/fs/namespace.c @@ -576,8 +576,8 @@ static int do_umount(struct vfsmount *mnt, int flags) */ lock_kernel(); - if ((flags & MNT_FORCE) && sb->s_op->umount_begin) - sb->s_op->umount_begin(sb); + if (sb->s_op->umount_begin) + sb->s_op->umount_begin(mnt, flags); unlock_kernel(); /* @@ -1163,13 +1163,46 @@ static void expire_mount(struct vfsmount *mnt, struct list_head *mounts, } /* + * go through the vfsmounts we've just consigned to the graveyard to + * - check that they're still dead + * - delete the vfsmount from the appropriate namespace under lock + * - dispose of the corpse + */ +static void expire_mount_list(struct list_head *graveyard, struct list_head *mounts) +{ + struct namespace *namespace; + struct vfsmount *mnt; + + while (!list_empty(graveyard)) { + LIST_HEAD(umounts); + mnt = list_entry(graveyard->next, struct vfsmount, mnt_expire); + list_del_init(&mnt->mnt_expire); + + /* don't do anything if the namespace is dead - all the + * vfsmounts from it are going away anyway */ + namespace = mnt->mnt_namespace; + if (!namespace || !namespace->root) + continue; + get_namespace(namespace); + + spin_unlock(&vfsmount_lock); + down_write(&namespace_sem); + expire_mount(mnt, mounts, &umounts); + up_write(&namespace_sem); + release_mounts(&umounts); + mntput(mnt); + put_namespace(namespace); + spin_lock(&vfsmount_lock); + } +} + +/* * process a list of expirable mountpoints with the intent of discarding any * mountpoints that aren't in use and haven't been touched since last we came * here */ void mark_mounts_for_expiry(struct list_head *mounts) { - struct namespace *namespace; struct vfsmount *mnt, *next; LIST_HEAD(graveyard); @@ -1193,38 +1226,79 @@ void mark_mounts_for_expiry(struct list_head *mounts) list_move(&mnt->mnt_expire, &graveyard); } - /* - * go through the vfsmounts we've just consigned to the graveyard to - * - check that they're still dead - * - delete the vfsmount from the appropriate namespace under lock - * - dispose of the corpse - */ - while (!list_empty(&graveyard)) { - LIST_HEAD(umounts); - mnt = list_entry(graveyard.next, struct vfsmount, mnt_expire); - list_del_init(&mnt->mnt_expire); + expire_mount_list(&graveyard, mounts); - /* don't do anything if the namespace is dead - all the - * vfsmounts from it are going away anyway */ - namespace = mnt->mnt_namespace; - if (!namespace || !namespace->root) + spin_unlock(&vfsmount_lock); +} + +EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); + +/* + * Ripoff of 'select_parent()' + * + * search the list of submounts for a given mountpoint, and move any + * shrinkable submounts to the 'graveyard' list. + */ +static int select_submounts(struct vfsmount *parent, struct list_head *graveyard) +{ + struct vfsmount *this_parent = parent; + struct list_head *next; + int found = 0; + +repeat: + next = this_parent->mnt_mounts.next; +resume: + while (next != &this_parent->mnt_mounts) { + struct list_head *tmp = next; + struct vfsmount *mnt = list_entry(tmp, struct vfsmount, mnt_child); + + next = tmp->next; + if (!(mnt->mnt_flags & MNT_SHRINKABLE)) continue; - get_namespace(namespace); + /* + * Descend a level if the d_mounts list is non-empty. + */ + if (!list_empty(&mnt->mnt_mounts)) { + this_parent = mnt; + goto repeat; + } - spin_unlock(&vfsmount_lock); - down_write(&namespace_sem); - expire_mount(mnt, mounts, &umounts); - up_write(&namespace_sem); - release_mounts(&umounts); - mntput(mnt); - put_namespace(namespace); - spin_lock(&vfsmount_lock); + if (!propagate_mount_busy(mnt, 1)) { + mntget(mnt); + list_move_tail(&mnt->mnt_expire, graveyard); + found++; + } } + /* + * All done at this level ... ascend and resume the search + */ + if (this_parent != parent) { + next = this_parent->mnt_child.next; + this_parent = this_parent->mnt_parent; + goto resume; + } + return found; +} + +/* + * process a list of expirable mountpoints with the intent of discarding any + * submounts of a specific parent mountpoint + */ +void shrink_submounts(struct vfsmount *mountpoint, struct list_head *mounts) +{ + LIST_HEAD(graveyard); + int found; + + spin_lock(&vfsmount_lock); + + /* extract submounts of 'mountpoint' from the expiration list */ + while ((found = select_submounts(mountpoint, &graveyard)) != 0) + expire_mount_list(&graveyard, mounts); spin_unlock(&vfsmount_lock); } -EXPORT_SYMBOL_GPL(mark_mounts_for_expiry); +EXPORT_SYMBOL_GPL(shrink_submounts); /* * Some copy_from_user() implementations do not return the exact number of diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index ec61fd5..0b572a0 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -4,14 +4,16 @@ obj-$(CONFIG_NFS_FS) += nfs.o -nfs-y := dir.o file.o inode.o nfs2xdr.o pagelist.o \ - proc.o read.o symlink.o unlink.o write.o +nfs-y := dir.o file.o inode.o super.o nfs2xdr.o pagelist.o \ + proc.o read.o symlink.o unlink.o write.o \ + namespace.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o mount_clnt.o nfs-$(CONFIG_NFS_V3) += nfs3proc.o nfs3xdr.o nfs-$(CONFIG_NFS_V3_ACL) += nfs3acl.o nfs-$(CONFIG_NFS_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \ delegation.o idmap.o \ - callback.o callback_xdr.o callback_proc.o + callback.o callback_xdr.o callback_proc.o \ + nfs4namespace.o nfs-$(CONFIG_NFS_DIRECTIO) += direct.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-objs := $(nfs-y) diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 90c95ad..d53f8c6 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -182,8 +182,6 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp) /* * Define NFS4 callback program */ -extern struct svc_version nfs4_callback_version1; - static struct svc_version *nfs4_callback_version[] = { [1] = &nfs4_callback_version1, }; diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index 05c38cf..c929913 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -202,7 +202,7 @@ static unsigned decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xd status = decode_fh(xdr, &args->fh); out: dprintk("%s: exit with status = %d\n", __FUNCTION__, status); - return 0; + return status; } static unsigned encode_string(struct xdr_stream *xdr, unsigned int len, const char *str) diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index cae74dd..3ddda6f 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -528,7 +528,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) lock_kernel(); - res = nfs_revalidate_inode(NFS_SERVER(inode), inode); + res = nfs_revalidate_mapping(inode, filp->f_mapping); if (res < 0) { unlock_kernel(); return res; @@ -868,6 +868,17 @@ int nfs_is_exclusive_create(struct inode *dir, struct nameidata *nd) return (nd->intent.open.flags & O_EXCL) != 0; } +static inline int nfs_reval_fsid(struct inode *dir, + struct nfs_fh *fh, struct nfs_fattr *fattr) +{ + struct nfs_server *server = NFS_SERVER(dir); + + if (!nfs_fsid_equal(&server->fsid, &fattr->fsid)) + /* Revalidate fsid on root dir */ + return __nfs_revalidate_inode(server, dir->i_sb->s_root->d_inode); + return 0; +} + static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, struct nameidata *nd) { struct dentry *res; @@ -900,6 +911,11 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru res = ERR_PTR(error); goto out_unlock; } + error = nfs_reval_fsid(dir, &fhandle, &fattr); + if (error < 0) { + res = ERR_PTR(error); + goto out_unlock; + } inode = nfs_fhget(dentry->d_sb, &fhandle, &fattr); res = (struct dentry *)inode; if (IS_ERR(res)) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 3c72b0c..402005c 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -892,7 +892,7 @@ out: * nfs_init_directcache - create a slab cache for nfs_direct_req structures * */ -int nfs_init_directcache(void) +int __init nfs_init_directcache(void) { nfs_direct_cachep = kmem_cache_create("nfs_direct_cache", sizeof(struct nfs_direct_req), @@ -906,10 +906,10 @@ int nfs_init_directcache(void) } /** - * nfs_init_directcache - destroy the slab cache for nfs_direct_req structures + * nfs_destroy_directcache - destroy the slab cache for nfs_direct_req structures * */ -void nfs_destroy_directcache(void) +void __exit nfs_destroy_directcache(void) { if (kmem_cache_destroy(nfs_direct_cachep)) printk(KERN_INFO "nfs_direct_cache: not all structures were freed\n"); diff --git a/fs/nfs/file.c b/fs/nfs/file.c index fade02c..106ef0d 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -127,23 +127,6 @@ nfs_file_release(struct inode *inode, struct file *filp) } /** - * nfs_revalidate_file - Revalidate the page cache & related metadata - * @inode - pointer to inode struct - * @file - pointer to file - */ -static int nfs_revalidate_file(struct inode *inode, struct file *filp) -{ - struct nfs_inode *nfsi = NFS_I(inode); - int retval = 0; - - if ((nfsi->cache_validity & (NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_ATTR)) - || nfs_attribute_timeout(inode)) - retval = __nfs_revalidate_inode(NFS_SERVER(inode), inode); - nfs_revalidate_mapping(inode, filp->f_mapping); - return 0; -} - -/** * nfs_revalidate_size - Revalidate the file size * @inode - pointer to inode struct * @file - pointer to struct file @@ -228,7 +211,7 @@ nfs_file_read(struct kiocb *iocb, char __user * buf, size_t count, loff_t pos) dentry->d_parent->d_name.name, dentry->d_name.name, (unsigned long) count, (unsigned long) pos); - result = nfs_revalidate_file(inode, iocb->ki_filp); + result = nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping); nfs_add_stats(inode, NFSIOS_NORMALREADBYTES, count); if (!result) result = generic_file_aio_read(iocb, buf, count, pos); @@ -247,7 +230,7 @@ nfs_file_sendfile(struct file *filp, loff_t *ppos, size_t count, dentry->d_parent->d_name.name, dentry->d_name.name, (unsigned long) count, (unsigned long long) *ppos); - res = nfs_revalidate_file(inode, filp); + res = nfs_revalidate_mapping(inode, filp->f_mapping); if (!res) res = generic_file_sendfile(filp, ppos, count, actor, target); return res; @@ -263,7 +246,7 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma) dfprintk(VFS, "nfs: mmap(%s/%s)\n", dentry->d_parent->d_name.name, dentry->d_name.name); - status = nfs_revalidate_file(inode, file); + status = nfs_revalidate_mapping(inode, file->f_mapping); if (!status) status = generic_file_mmap(file, vma); return status; @@ -320,7 +303,11 @@ static int nfs_commit_write(struct file *file, struct page *page, unsigned offse static void nfs_invalidate_page(struct page *page, unsigned long offset) { - /* FIXME: we really should cancel any unstarted writes on this page */ + struct inode *inode = page->mapping->host; + + /* Cancel any unstarted writes on this page */ + if (offset == 0) + nfs_sync_inode_wait(inode, page->index, 1, FLUSH_INVALIDATE); } static int nfs_release_page(struct page *page, gfp_t gfp) @@ -373,7 +360,6 @@ nfs_file_write(struct kiocb *iocb, const char __user *buf, size_t count, loff_t if (result) goto out; } - nfs_revalidate_mapping(inode, iocb->ki_filp->f_mapping); result = count; if (!count) diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 3fab5b0..b81e7ed 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -47,7 +47,6 @@ #include <linux/workqueue.h> #include <linux/sunrpc/rpc_pipe_fs.h> -#include <linux/nfs_fs_sb.h> #include <linux/nfs_fs.h> #include <linux/nfs_idmap.h> diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index d0b991a..24a7139 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -36,6 +36,8 @@ #include <linux/mount.h> #include <linux/nfs_idmap.h> #include <linux/vfs.h> +#include <linux/inet.h> +#include <linux/nfs_xdr.h> #include <asm/system.h> #include <asm/uaccess.h> @@ -44,89 +46,17 @@ #include "callback.h" #include "delegation.h" #include "iostat.h" +#include "internal.h" #define NFSDBG_FACILITY NFSDBG_VFS #define NFS_PARANOIA 1 -/* Maximum number of readahead requests - * FIXME: this should really be a sysctl so that users may tune it to suit - * their needs. People that do NFS over a slow network, might for - * instance want to reduce it to something closer to 1 for improved - * interactive response. - */ -#define NFS_MAX_READAHEAD (RPC_DEF_SLOT_TABLE - 1) - static void nfs_invalidate_inode(struct inode *); static int nfs_update_inode(struct inode *, struct nfs_fattr *); -static struct inode *nfs_alloc_inode(struct super_block *sb); -static void nfs_destroy_inode(struct inode *); -static int nfs_write_inode(struct inode *,int); -static void nfs_delete_inode(struct inode *); -static void nfs_clear_inode(struct inode *); -static void nfs_umount_begin(struct super_block *); -static int nfs_statfs(struct super_block *, struct kstatfs *); -static int nfs_show_options(struct seq_file *, struct vfsmount *); -static int nfs_show_stats(struct seq_file *, struct vfsmount *); static void nfs_zap_acl_cache(struct inode *); -static struct rpc_program nfs_program; - -static struct super_operations nfs_sops = { - .alloc_inode = nfs_alloc_inode, - .destroy_inode = nfs_destroy_inode, - .write_inode = nfs_write_inode, - .delete_inode = nfs_delete_inode, - .statfs = nfs_statfs, - .clear_inode = nfs_clear_inode, - .umount_begin = nfs_umount_begin, - .show_options = nfs_show_options, - .show_stats = nfs_show_stats, -}; - -/* - * RPC cruft for NFS - */ -static struct rpc_stat nfs_rpcstat = { - .program = &nfs_program -}; -static struct rpc_version * nfs_version[] = { - NULL, - NULL, - &nfs_version2, -#if defined(CONFIG_NFS_V3) - &nfs_version3, -#elif defined(CONFIG_NFS_V4) - NULL, -#endif -#if defined(CONFIG_NFS_V4) - &nfs_version4, -#endif -}; - -static struct rpc_program nfs_program = { - .name = "nfs", - .number = NFS_PROGRAM, - .nrvers = ARRAY_SIZE(nfs_version), - .version = nfs_version, - .stats = &nfs_rpcstat, - .pipe_dir_name = "/nfs", -}; - -#ifdef CONFIG_NFS_V3_ACL -static struct rpc_stat nfsacl_rpcstat = { &nfsacl_program }; -static struct rpc_version * nfsacl_version[] = { - [3] = &nfsacl_version3, -}; - -struct rpc_program nfsacl_program = { - .name = "nfsacl", - .number = NFS_ACL_PROGRAM, - .nrvers = ARRAY_SIZE(nfsacl_version), - .version = nfsacl_version, - .stats = &nfsacl_rpcstat, -}; -#endif /* CONFIG_NFS_V3_ACL */ +static kmem_cache_t * nfs_inode_cachep; static inline unsigned long nfs_fattr_to_ino_t(struct nfs_fattr *fattr) @@ -134,8 +64,7 @@ nfs_fattr_to_ino_t(struct nfs_fattr *fattr) return nfs_fileid_to_ino_t(fattr->fileid); } -static int -nfs_write_inode(struct inode *inode, int sync) +int nfs_write_inode(struct inode *inode, int sync) { int flags = sync ? FLUSH_SYNC : 0; int ret; @@ -146,31 +75,15 @@ nfs_write_inode(struct inode *inode, int sync) return 0; } -static void -nfs_delete_inode(struct inode * inode) +void nfs_clear_inode(struct inode *inode) { - dprintk("NFS: delete_inode(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino); - - truncate_inode_pages(&inode->i_data, 0); + struct nfs_inode *nfsi = NFS_I(inode); + struct rpc_cred *cred; - nfs_wb_all(inode); /* * The following should never happen... */ - if (nfs_have_writebacks(inode)) { - printk(KERN_ERR "nfs_delete_inode: inode %ld has pending RPC requests\n", inode->i_ino); - } - - clear_inode(inode); -} - -static void -nfs_clear_inode(struct inode *inode) -{ - struct nfs_inode *nfsi = NFS_I(inode); - struct rpc_cred *cred; - - nfs_wb_all(inode); + BUG_ON(nfs_have_writebacks(inode)); BUG_ON (!list_empty(&nfsi->open_files)); nfs_zap_acl_cache(inode); cred = nfsi->cache_access.cred; @@ -179,554 +92,6 @@ nfs_clear_inode(struct inode *inode) BUG_ON(atomic_read(&nfsi->data_updates) != 0); } -void -nfs_umount_begin(struct super_block *sb) -{ - struct rpc_clnt *rpc = NFS_SB(sb)->client; - - /* -EIO all pending I/O */ - if (!IS_ERR(rpc)) - rpc_killall_tasks(rpc); - rpc = NFS_SB(sb)->client_acl; - if (!IS_ERR(rpc)) - rpc_killall_tasks(rpc); -} - - -static inline unsigned long -nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp) -{ - /* make sure blocksize is a power of two */ - if ((bsize & (bsize - 1)) || nrbitsp) { - unsigned char nrbits; - - for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--) - ; - bsize = 1 << nrbits; - if (nrbitsp) - *nrbitsp = nrbits; - } - - return bsize; -} - -/* - * Calculate the number of 512byte blocks used. - */ -static inline unsigned long -nfs_calc_block_size(u64 tsize) -{ - loff_t used = (tsize + 511) >> 9; - return (used > ULONG_MAX) ? ULONG_MAX : used; -} - -/* - * Compute and set NFS server blocksize - */ -static inline unsigned long -nfs_block_size(unsigned long bsize, unsigned char *nrbitsp) -{ - if (bsize < NFS_MIN_FILE_IO_SIZE) - bsize = NFS_DEF_FILE_IO_SIZE; - else if (bsize >= NFS_MAX_FILE_IO_SIZE) - bsize = NFS_MAX_FILE_IO_SIZE; - - return nfs_block_bits(bsize, nrbitsp); -} - -/* - * Obtain the root inode of the file system. - */ -static struct inode * -nfs_get_root(struct super_block *sb, struct nfs_fh *rootfh, struct nfs_fsinfo *fsinfo) -{ - struct nfs_server *server = NFS_SB(sb); - int error; - - error = server->rpc_ops->getroot(server, rootfh, fsinfo); - if (error < 0) { - dprintk("nfs_get_root: getattr error = %d\n", -error); - return ERR_PTR(error); - } - - return nfs_fhget(sb, rootfh, fsinfo->fattr); -} - -/* - * Do NFS version-independent mount processing, and sanity checking - */ -static int -nfs_sb_init(struct super_block *sb, rpc_authflavor_t authflavor) -{ - struct nfs_server *server; - struct inode *root_inode; - struct nfs_fattr fattr; - struct nfs_fsinfo fsinfo = { - .fattr = &fattr, - }; - struct nfs_pathconf pathinfo = { - .fattr = &fattr, - }; - int no_root_error = 0; - unsigned long max_rpc_payload; - - /* We probably want something more informative here */ - snprintf(sb->s_id, sizeof(sb->s_id), "%x:%x", MAJOR(sb->s_dev), MINOR(sb->s_dev)); - - server = NFS_SB(sb); - - sb->s_magic = NFS_SUPER_MAGIC; - - server->io_stats = nfs_alloc_iostats(); - if (server->io_stats == NULL) - return -ENOMEM; - - root_inode = nfs_get_root(sb, &server->fh, &fsinfo); - /* Did getting the root inode fail? */ - if (IS_ERR(root_inode)) { - no_root_error = PTR_ERR(root_inode); - goto out_no_root; - } - sb->s_root = d_alloc_root(root_inode); - if (!sb->s_root) { - no_root_error = -ENOMEM; - goto out_no_root; - } - sb->s_root->d_op = server->rpc_ops->dentry_ops; - - /* mount time stamp, in seconds */ - server->mount_time = jiffies; - - /* Get some general file system info */ - if (server->namelen == 0 && - server->rpc_ops->pathconf(server, &server->fh, &pathinfo) >= 0) - server->namelen = pathinfo.max_namelen; - /* Work out a lot of parameters */ - if (server->rsize == 0) - server->rsize = nfs_block_size(fsinfo.rtpref, NULL); - if (server->wsize == 0) - server->wsize = nfs_block_size(fsinfo.wtpref, NULL); - - if (fsinfo.rtmax >= 512 && server->rsize > fsinfo.rtmax) - server->rsize = nfs_block_size(fsinfo.rtmax, NULL); - if (fsinfo.wtmax >= 512 && server->wsize > fsinfo.wtmax) - server->wsize = nfs_block_size(fsinfo.wtmax, NULL); - - max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL); - if (server->rsize > max_rpc_payload) - server->rsize = max_rpc_payload; - if (server->rsize > NFS_MAX_FILE_IO_SIZE) - server->rsize = NFS_MAX_FILE_IO_SIZE; - server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - - if (server->wsize > max_rpc_payload) - server->wsize = max_rpc_payload; - if (server->wsize > NFS_MAX_FILE_IO_SIZE) - server->wsize = NFS_MAX_FILE_IO_SIZE; - server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - - if (sb->s_blocksize == 0) - sb->s_blocksize = nfs_block_bits(server->wsize, - &sb->s_blocksize_bits); - server->wtmult = nfs_block_bits(fsinfo.wtmult, NULL); - - server->dtsize = nfs_block_size(fsinfo.dtpref, NULL); - if (server->dtsize > PAGE_CACHE_SIZE) - server->dtsize = PAGE_CACHE_SIZE; - if (server->dtsize > server->rsize) - server->dtsize = server->rsize; - - if (server->flags & NFS_MOUNT_NOAC) { - server->acregmin = server->acregmax = 0; - server->acdirmin = server->acdirmax = 0; - sb->s_flags |= MS_SYNCHRONOUS; - } - server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD; - - sb->s_maxbytes = fsinfo.maxfilesize; - if (sb->s_maxbytes > MAX_LFS_FILESIZE) - sb->s_maxbytes = MAX_LFS_FILESIZE; - - server->client->cl_intr = (server->flags & NFS_MOUNT_INTR) ? 1 : 0; - server->client->cl_softrtry = (server->flags & NFS_MOUNT_SOFT) ? 1 : 0; - - /* We're airborne Set socket buffersize */ - rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100); - return 0; - /* Yargs. It didn't work out. */ -out_no_root: - dprintk("nfs_sb_init: get root inode failed: errno %d\n", -no_root_error); - if (!IS_ERR(root_inode)) - iput(root_inode); - return no_root_error; -} - -static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, unsigned int timeo, unsigned int retrans) -{ - to->to_initval = timeo * HZ / 10; - to->to_retries = retrans; - if (!to->to_retries) - to->to_retries = 2; - - switch (proto) { - case IPPROTO_TCP: - if (!to->to_initval) - to->to_initval = 60 * HZ; - if (to->to_initval > NFS_MAX_TCP_TIMEOUT) - to->to_initval = NFS_MAX_TCP_TIMEOUT; - to->to_increment = to->to_initval; - to->to_maxval = to->to_initval + (to->to_increment * to->to_retries); - to->to_exponential = 0; - break; - case IPPROTO_UDP: - default: - if (!to->to_initval) - to->to_initval = 11 * HZ / 10; - if (to->to_initval > NFS_MAX_UDP_TIMEOUT) - to->to_initval = NFS_MAX_UDP_TIMEOUT; - to->to_maxval = NFS_MAX_UDP_TIMEOUT; - to->to_exponential = 1; - break; - } -} - -/* - * Create an RPC client handle. - */ -static struct rpc_clnt * -nfs_create_client(struct nfs_server *server, const struct nfs_mount_data *data) -{ - struct rpc_timeout timeparms; - struct rpc_xprt *xprt = NULL; - struct rpc_clnt *clnt = NULL; - int proto = (data->flags & NFS_MOUNT_TCP) ? IPPROTO_TCP : IPPROTO_UDP; - - nfs_init_timeout_values(&timeparms, proto, data->timeo, data->retrans); - - server->retrans_timeo = timeparms.to_initval; - server->retrans_count = timeparms.to_retries; - - /* create transport and client */ - xprt = xprt_create_proto(proto, &server->addr, &timeparms); - if (IS_ERR(xprt)) { - dprintk("%s: cannot create RPC transport. Error = %ld\n", - __FUNCTION__, PTR_ERR(xprt)); - return (struct rpc_clnt *)xprt; - } - clnt = rpc_create_client(xprt, server->hostname, &nfs_program, - server->rpc_ops->version, data->pseudoflavor); - if (IS_ERR(clnt)) { - dprintk("%s: cannot create RPC client. Error = %ld\n", - __FUNCTION__, PTR_ERR(xprt)); - goto out_fail; - } - - clnt->cl_intr = 1; - clnt->cl_softrtry = 1; - - return clnt; - -out_fail: - return clnt; -} - -/* - * The way this works is that the mount process passes a structure - * in the data argument which contains the server's IP address - * and the root file handle obtained from the server's mount - * daemon. We stash these away in the private superblock fields. - */ -static int -nfs_fill_super(struct super_block *sb, struct nfs_mount_data *data, int silent) -{ - struct nfs_server *server; - rpc_authflavor_t authflavor; - - server = NFS_SB(sb); - sb->s_blocksize_bits = 0; - sb->s_blocksize = 0; - if (data->bsize) - sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits); - if (data->rsize) - server->rsize = nfs_block_size(data->rsize, NULL); - if (data->wsize) - server->wsize = nfs_block_size(data->wsize, NULL); - server->flags = data->flags & NFS_MOUNT_FLAGMASK; - - server->acregmin = data->acregmin*HZ; - server->acregmax = data->acregmax*HZ; - server->acdirmin = data->acdirmin*HZ; - server->acdirmax = data->acdirmax*HZ; - - /* Start lockd here, before we might error out */ - if (!(server->flags & NFS_MOUNT_NONLM)) - lockd_up(); - - server->namelen = data->namlen; - server->hostname = kmalloc(strlen(data->hostname) + 1, GFP_KERNEL); - if (!server->hostname) - return -ENOMEM; - strcpy(server->hostname, data->hostname); - - /* Check NFS protocol revision and initialize RPC op vector - * and file handle pool. */ -#ifdef CONFIG_NFS_V3 - if (server->flags & NFS_MOUNT_VER3) { - server->rpc_ops = &nfs_v3_clientops; - server->caps |= NFS_CAP_READDIRPLUS; - } else { - server->rpc_ops = &nfs_v2_clientops; - } -#else - server->rpc_ops = &nfs_v2_clientops; -#endif - - /* Fill in pseudoflavor for mount version < 5 */ - if (!(data->flags & NFS_MOUNT_SECFLAVOUR)) - data->pseudoflavor = RPC_AUTH_UNIX; - authflavor = data->pseudoflavor; /* save for sb_init() */ - /* XXX maybe we want to add a server->pseudoflavor field */ - - /* Create RPC client handles */ - server->client = nfs_create_client(server, data); - if (IS_ERR(server->client)) - return PTR_ERR(server->client); - /* RFC 2623, sec 2.3.2 */ - if (authflavor != RPC_AUTH_UNIX) { - struct rpc_auth *auth; - - server->client_sys = rpc_clone_client(server->client); - if (IS_ERR(server->client_sys)) - return PTR_ERR(server->client_sys); - auth = rpcauth_create(RPC_AUTH_UNIX, server->client_sys); - if (IS_ERR(auth)) - return PTR_ERR(auth); - } else { - atomic_inc(&server->client->cl_count); - server->client_sys = server->client; - } - if (server->flags & NFS_MOUNT_VER3) { -#ifdef CONFIG_NFS_V3_ACL - if (!(server->flags & NFS_MOUNT_NOACL)) { - server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3); - /* No errors! Assume that Sun nfsacls are supported */ - if (!IS_ERR(server->client_acl)) - server->caps |= NFS_CAP_ACLS; - } -#else - server->flags &= ~NFS_MOUNT_NOACL; -#endif /* CONFIG_NFS_V3_ACL */ - /* - * The VFS shouldn't apply the umask to mode bits. We will - * do so ourselves when necessary. - */ - sb->s_flags |= MS_POSIXACL; - if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN) - server->namelen = NFS3_MAXNAMLEN; - sb->s_time_gran = 1; - } else { - if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN) - server->namelen = NFS2_MAXNAMLEN; - } - - sb->s_op = &nfs_sops; - return nfs_sb_init(sb, authflavor); -} - -static int -nfs_statfs(struct super_block *sb, struct kstatfs *buf) -{ - struct nfs_server *server = NFS_SB(sb); - unsigned char blockbits; - unsigned long blockres; - struct nfs_fh *rootfh = NFS_FH(sb->s_root->d_inode); - struct nfs_fattr fattr; - struct nfs_fsstat res = { - .fattr = &fattr, - }; - int error; - - lock_kernel(); - - error = server->rpc_ops->statfs(server, rootfh, &res); - buf->f_type = NFS_SUPER_MAGIC; - if (error < 0) - goto out_err; - - /* - * Current versions of glibc do not correctly handle the - * case where f_frsize != f_bsize. Eventually we want to - * report the value of wtmult in this field. - */ - buf->f_frsize = sb->s_blocksize; - - /* - * On most *nix systems, f_blocks, f_bfree, and f_bavail - * are reported in units of f_frsize. Linux hasn't had - * an f_frsize field in its statfs struct until recently, - * thus historically Linux's sys_statfs reports these - * fields in units of f_bsize. - */ - buf->f_bsize = sb->s_blocksize; - blockbits = sb->s_blocksize_bits; - blockres = (1 << blockbits) - 1; - buf->f_blocks = (res.tbytes + blockres) >> blockbits; - buf->f_bfree = (res.fbytes + blockres) >> blockbits; - buf->f_bavail = (res.abytes + blockres) >> blockbits; - - buf->f_files = res.tfiles; - buf->f_ffree = res.afiles; - - buf->f_namelen = server->namelen; - out: - unlock_kernel(); - return 0; - - out_err: - dprintk("%s: statfs error = %d\n", __FUNCTION__, -error); - buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1; - goto out; - -} - -static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, int showdefaults) -{ - static struct proc_nfs_info { - int flag; - char *str; - char *nostr; - } nfs_info[] = { - { NFS_MOUNT_SOFT, ",soft", ",hard" }, - { NFS_MOUNT_INTR, ",intr", "" }, - { NFS_MOUNT_NOCTO, ",nocto", "" }, - { NFS_MOUNT_NOAC, ",noac", "" }, - { NFS_MOUNT_NONLM, ",nolock", "" }, - { NFS_MOUNT_NOACL, ",noacl", "" }, - { 0, NULL, NULL } - }; - struct proc_nfs_info *nfs_infop; - char buf[12]; - char *proto; - - seq_printf(m, ",vers=%d", nfss->rpc_ops->version); - seq_printf(m, ",rsize=%d", nfss->rsize); - seq_printf(m, ",wsize=%d", nfss->wsize); - if (nfss->acregmin != 3*HZ || showdefaults) - seq_printf(m, ",acregmin=%d", nfss->acregmin/HZ); - if (nfss->acregmax != 60*HZ || showdefaults) - seq_printf(m, ",acregmax=%d", nfss->acregmax/HZ); - if (nfss->acdirmin != 30*HZ || showdefaults) - seq_printf(m, ",acdirmin=%d", nfss->acdirmin/HZ); - if (nfss->acdirmax != 60*HZ || showdefaults) - seq_printf(m, ",acdirmax=%d", nfss->acdirmax/HZ); - for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) { - if (nfss->flags & nfs_infop->flag) - seq_puts(m, nfs_infop->str); - else - seq_puts(m, nfs_infop->nostr); - } - switch (nfss->client->cl_xprt->prot) { - case IPPROTO_TCP: - proto = "tcp"; - break; - case IPPROTO_UDP: - proto = "udp"; - break; - default: - snprintf(buf, sizeof(buf), "%u", nfss->client->cl_xprt->prot); - proto = buf; - } - seq_printf(m, ",proto=%s", proto); - seq_printf(m, ",timeo=%lu", 10U * nfss->retrans_timeo / HZ); - seq_printf(m, ",retrans=%u", nfss->retrans_count); -} - -static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt) -{ - struct nfs_server *nfss = NFS_SB(mnt->mnt_sb); - - nfs_show_mount_options(m, nfss, 0); - - seq_puts(m, ",addr="); - seq_escape(m, nfss->hostname, " \t\n\\"); - - return 0; -} - -static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt) -{ - int i, cpu; - struct nfs_server *nfss = NFS_SB(mnt->mnt_sb); - struct rpc_auth *auth = nfss->client->cl_auth; - struct nfs_iostats totals = { }; - - seq_printf(m, "statvers=%s", NFS_IOSTAT_VERS); - - /* - * Display all mount option settings - */ - seq_printf(m, "\n\topts:\t"); - seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? "ro" : "rw"); - seq_puts(m, mnt->mnt_sb->s_flags & MS_SYNCHRONOUS ? ",sync" : ""); - seq_puts(m, mnt->mnt_sb->s_flags & MS_NOATIME ? ",noatime" : ""); - seq_puts(m, mnt->mnt_sb->s_flags & MS_NODIRATIME ? ",nodiratime" : ""); - nfs_show_mount_options(m, nfss, 1); - - seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ); - - seq_printf(m, "\n\tcaps:\t"); - seq_printf(m, "caps=0x%x", nfss->caps); - seq_printf(m, ",wtmult=%d", nfss->wtmult); - seq_printf(m, ",dtsize=%d", nfss->dtsize); - seq_printf(m, ",bsize=%d", nfss->bsize); - seq_printf(m, ",namelen=%d", nfss->namelen); - -#ifdef CONFIG_NFS_V4 - if (nfss->rpc_ops->version == 4) { - seq_printf(m, "\n\tnfsv4:\t"); - seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]); - seq_printf(m, ",bm1=0x%x", nfss->attr_bitmask[1]); - seq_printf(m, ",acl=0x%x", nfss->acl_bitmask); - } -#endif - - /* - * Display security flavor in effect for this mount - */ - seq_printf(m, "\n\tsec:\tflavor=%d", auth->au_ops->au_flavor); - if (auth->au_flavor) - seq_printf(m, ",pseudoflavor=%d", auth->au_flavor); - - /* - * Display superblock I/O counters - */ - for_each_possible_cpu(cpu) { - struct nfs_iostats *stats; - - preempt_disable(); - stats = per_cpu_ptr(nfss->io_stats, cpu); - - for (i = 0; i < __NFSIOS_COUNTSMAX; i++) - totals.events[i] += stats->events[i]; - for (i = 0; i < __NFSIOS_BYTESMAX; i++) - totals.bytes[i] += stats->bytes[i]; - - preempt_enable(); - } - - seq_printf(m, "\n\tevents:\t"); - for (i = 0; i < __NFSIOS_COUNTSMAX; i++) - seq_printf(m, "%lu ", totals.events[i]); - seq_printf(m, "\n\tbytes:\t"); - for (i = 0; i < __NFSIOS_BYTESMAX; i++) - seq_printf(m, "%Lu ", totals.bytes[i]); - seq_printf(m, "\n"); - - rpc_print_iostats(m, nfss->client); - - return 0; -} - /** * nfs_sync_mapping - helper to flush all mmapped dirty data to disk */ @@ -889,6 +254,14 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS) && fattr->size <= NFS_LIMIT_READDIRPLUS) set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_FLAGS(inode)); + /* Deal with crossing mountpoints */ + if (!nfs_fsid_equal(&NFS_SB(sb)->fsid, &fattr->fsid)) { + if (fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) + inode->i_op = &nfs_referral_inode_operations; + else + inode->i_op = &nfs_mountpoint_inode_operations; + inode->i_fop = NULL; + } } else if (S_ISLNK(inode->i_mode)) inode->i_op = &nfs_symlink_inode_operations; else @@ -1207,6 +580,7 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) dfprintk(PAGECACHE, "NFS: revalidating (%s/%Ld)\n", inode->i_sb->s_id, (long long)NFS_FILEID(inode)); + nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE); lock_kernel(); if (!inode || is_bad_inode(inode)) goto out_nowait; @@ -1220,7 +594,7 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) status = -ESTALE; /* Do we trust the cached ESTALE? */ if (NFS_ATTRTIMEO(inode) != 0) { - if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ATIME)) { + if (nfsi->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ATIME)) { /* no */ } else goto out; @@ -1251,8 +625,6 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) } spin_unlock(&inode->i_lock); - nfs_revalidate_mapping(inode, inode->i_mapping); - if (nfsi->cache_validity & NFS_INO_INVALID_ACL) nfs_zap_acl_cache(inode); @@ -1286,8 +658,7 @@ int nfs_attribute_timeout(struct inode *inode) */ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) { - nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE); - if (!(NFS_I(inode)->cache_validity & (NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA)) + if (!(NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATTR) && !nfs_attribute_timeout(inode)) return NFS_STALE(inode) ? -ESTALE : 0; return __nfs_revalidate_inode(server, inode); @@ -1298,9 +669,16 @@ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) * @inode - pointer to host inode * @mapping - pointer to mapping */ -void nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) +int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) { struct nfs_inode *nfsi = NFS_I(inode); + int ret = 0; + + if (NFS_STALE(inode)) + ret = -ESTALE; + if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) + || nfs_attribute_timeout(inode)) + ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); if (nfsi->cache_validity & NFS_INO_INVALID_DATA) { nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); @@ -1321,6 +699,7 @@ void nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) inode->i_sb->s_id, (long long)NFS_FILEID(inode)); } + return ret; } /** @@ -1360,12 +739,6 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr) { struct nfs_inode *nfsi = NFS_I(inode); - if ((fattr->valid & NFS_ATTR_PRE_CHANGE) != 0 - && nfsi->change_attr == fattr->pre_change_attr) { - nfsi->change_attr = fattr->change_attr; - nfsi->cache_change_attribute = jiffies; - } - /* If we have atomic WCC data, we may update some attributes */ if ((fattr->valid & NFS_ATTR_WCC) != 0) { if (timespec_equal(&inode->i_ctime, &fattr->pre_ctime)) { @@ -1399,9 +772,6 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat int data_unstable; - if ((fattr->valid & NFS_ATTR_FATTR) == 0) - return 0; - /* Has the inode gone and changed behind our back? */ if (nfsi->fileid != fattr->fileid || (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) { @@ -1414,20 +784,13 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); - if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0) { - if (nfsi->change_attr == fattr->change_attr) - goto out; - nfsi->cache_validity |= NFS_INO_INVALID_ATTR; - if (!data_unstable) - nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE; - } + if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 && + nfsi->change_attr != fattr->change_attr) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; /* Verify a few of the more important attributes */ - if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) { - nfsi->cache_validity |= NFS_INO_INVALID_ATTR; - if (!data_unstable) - nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE; - } + if (!timespec_equal(&inode->i_mtime, &fattr->mtime)) + nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; cur_size = i_size_read(inode); new_isize = nfs_size_to_loff_t(fattr->size); @@ -1444,7 +807,6 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat if (inode->i_nlink != fattr->nlink) nfsi->cache_validity |= NFS_INO_INVALID_ATTR; -out: if (!timespec_equal(&inode->i_atime, &fattr->atime)) nfsi->cache_validity |= NFS_INO_INVALID_ATIME; @@ -1470,7 +832,6 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr) if ((fattr->valid & NFS_ATTR_FATTR) == 0) return 0; spin_lock(&inode->i_lock); - nfsi->cache_validity &= ~NFS_INO_REVAL_PAGECACHE; if (time_after(fattr->time_start, nfsi->last_updated)) status = nfs_update_inode(inode, fattr); else @@ -1495,7 +856,7 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr) spin_lock(&inode->i_lock); if (unlikely((fattr->valid & NFS_ATTR_FATTR) == 0)) { - nfsi->cache_validity |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS; + nfsi->cache_validity |= NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE; goto out; } status = nfs_update_inode(inode, fattr); @@ -1518,6 +879,7 @@ out: */ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) { + struct nfs_server *server; struct nfs_inode *nfsi = NFS_I(inode); loff_t cur_isize, new_isize; unsigned int invalid = 0; @@ -1527,9 +889,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) __FUNCTION__, inode->i_sb->s_id, inode->i_ino, atomic_read(&inode->i_count), fattr->valid); - if ((fattr->valid & NFS_ATTR_FATTR) == 0) - return 0; - if (nfsi->fileid != fattr->fileid) goto out_fileid; @@ -1539,6 +898,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if ((inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT)) goto out_changed; + server = NFS_SERVER(inode); + /* Update the fsid if and only if this is the root directory */ + if (inode == inode->i_sb->s_root->d_inode + && !nfs_fsid_equal(&server->fsid, &fattr->fsid)) + server->fsid = fattr->fsid; + /* * Update the read time so we don't revalidate too often. */ @@ -1548,7 +913,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) /* Are we racing with known updates of the metadata on the server? */ data_stable = nfs_verify_change_attribute(inode, fattr->time_start); if (data_stable) - nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ATIME); + nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_ATIME); /* Do atomic weak cache consistency updates */ nfs_wcc_update_inode(inode, fattr); @@ -1612,15 +977,13 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) inode->i_blksize = fattr->du.nfs2.blocksize; } - if ((fattr->valid & NFS_ATTR_FATTR_V4)) { - if (nfsi->change_attr != fattr->change_attr) { - dprintk("NFS: change_attr change on server for file %s/%ld\n", - inode->i_sb->s_id, inode->i_ino); - nfsi->change_attr = fattr->change_attr; - invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; - nfsi->cache_change_attribute = jiffies; - } else - invalid &= ~(NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA); + if ((fattr->valid & NFS_ATTR_FATTR_V4) != 0 && + nfsi->change_attr != fattr->change_attr) { + dprintk("NFS: change_attr change on server for file %s/%ld\n", + inode->i_sb->s_id, inode->i_ino); + nfsi->change_attr = fattr->change_attr; + invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL; + nfsi->cache_change_attribute = jiffies; } /* Update attrtimeo value if we're out of the unstable period */ @@ -1668,190 +1031,15 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) goto out_err; } -/* - * File system information - */ - -static int nfs_set_super(struct super_block *s, void *data) -{ - s->s_fs_info = data; - return set_anon_super(s, data); -} - -static int nfs_compare_super(struct super_block *sb, void *data) -{ - struct nfs_server *server = data; - struct nfs_server *old = NFS_SB(sb); - - if (old->addr.sin_addr.s_addr != server->addr.sin_addr.s_addr) - return 0; - if (old->addr.sin_port != server->addr.sin_port) - return 0; - return !nfs_compare_fh(&old->fh, &server->fh); -} - -static struct super_block *nfs_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data) -{ - int error; - struct nfs_server *server = NULL; - struct super_block *s; - struct nfs_fh *root; - struct nfs_mount_data *data = raw_data; - - s = ERR_PTR(-EINVAL); - if (data == NULL) { - dprintk("%s: missing data argument\n", __FUNCTION__); - goto out_err; - } - if (data->version <= 0 || data->version > NFS_MOUNT_VERSION) { - dprintk("%s: bad mount version\n", __FUNCTION__); - goto out_err; - } - switch (data->version) { - case 1: - data->namlen = 0; - case 2: - data->bsize = 0; - case 3: - if (data->flags & NFS_MOUNT_VER3) { - dprintk("%s: mount structure version %d does not support NFSv3\n", - __FUNCTION__, - data->version); - goto out_err; - } - data->root.size = NFS2_FHSIZE; - memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE); - case 4: - if (data->flags & NFS_MOUNT_SECFLAVOUR) { - dprintk("%s: mount structure version %d does not support strong security\n", - __FUNCTION__, - data->version); - goto out_err; - } - case 5: - memset(data->context, 0, sizeof(data->context)); - } -#ifndef CONFIG_NFS_V3 - /* If NFSv3 is not compiled in, return -EPROTONOSUPPORT */ - s = ERR_PTR(-EPROTONOSUPPORT); - if (data->flags & NFS_MOUNT_VER3) { - dprintk("%s: NFSv3 not compiled into kernel\n", __FUNCTION__); - goto out_err; - } -#endif /* CONFIG_NFS_V3 */ - - s = ERR_PTR(-ENOMEM); - server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL); - if (!server) - goto out_err; - /* Zero out the NFS state stuff */ - init_nfsv4_state(server); - server->client = server->client_sys = server->client_acl = ERR_PTR(-EINVAL); - - root = &server->fh; - if (data->flags & NFS_MOUNT_VER3) - root->size = data->root.size; - else - root->size = NFS2_FHSIZE; - s = ERR_PTR(-EINVAL); - if (root->size > sizeof(root->data)) { - dprintk("%s: invalid root filehandle\n", __FUNCTION__); - goto out_err; - } - memcpy(root->data, data->root.data, root->size); - - /* We now require that the mount process passes the remote address */ - memcpy(&server->addr, &data->addr, sizeof(server->addr)); - if (server->addr.sin_addr.s_addr == INADDR_ANY) { - dprintk("%s: mount program didn't pass remote address!\n", - __FUNCTION__); - goto out_err; - } - - /* Fire up rpciod if not yet running */ - s = ERR_PTR(rpciod_up()); - if (IS_ERR(s)) { - dprintk("%s: couldn't start rpciod! Error = %ld\n", - __FUNCTION__, PTR_ERR(s)); - goto out_err; - } - - s = sget(fs_type, nfs_compare_super, nfs_set_super, server); - if (IS_ERR(s) || s->s_root) - goto out_rpciod_down; - - s->s_flags = flags; - - error = nfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0); - if (error) { - up_write(&s->s_umount); - deactivate_super(s); - return ERR_PTR(error); - } - s->s_flags |= MS_ACTIVE; - return s; -out_rpciod_down: - rpciod_down(); -out_err: - kfree(server); - return s; -} - -static void nfs_kill_super(struct super_block *s) -{ - struct nfs_server *server = NFS_SB(s); - - kill_anon_super(s); - - if (!IS_ERR(server->client)) - rpc_shutdown_client(server->client); - if (!IS_ERR(server->client_sys)) - rpc_shutdown_client(server->client_sys); - if (!IS_ERR(server->client_acl)) - rpc_shutdown_client(server->client_acl); - - if (!(server->flags & NFS_MOUNT_NONLM)) - lockd_down(); /* release rpc.lockd */ - - rpciod_down(); /* release rpciod */ - - nfs_free_iostats(server->io_stats); - kfree(server->hostname); - kfree(server); -} - -static struct file_system_type nfs_fs_type = { - .owner = THIS_MODULE, - .name = "nfs", - .get_sb = nfs_get_sb, - .kill_sb = nfs_kill_super, - .fs_flags = FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, -}; #ifdef CONFIG_NFS_V4 -static void nfs4_clear_inode(struct inode *); - - -static struct super_operations nfs4_sops = { - .alloc_inode = nfs_alloc_inode, - .destroy_inode = nfs_destroy_inode, - .write_inode = nfs_write_inode, - .delete_inode = nfs_delete_inode, - .statfs = nfs_statfs, - .clear_inode = nfs4_clear_inode, - .umount_begin = nfs_umount_begin, - .show_options = nfs_show_options, - .show_stats = nfs_show_stats, -}; - /* * Clean out any remaining NFSv4 state that might be left over due * to open() calls that passed nfs_atomic_lookup, but failed to call * nfs_open(). */ -static void nfs4_clear_inode(struct inode *inode) +void nfs4_clear_inode(struct inode *inode) { struct nfs_inode *nfsi = NFS_I(inode); @@ -1875,357 +1063,9 @@ static void nfs4_clear_inode(struct inode *inode) nfs4_close_state(state, state->state); } } - - -static int nfs4_fill_super(struct super_block *sb, struct nfs4_mount_data *data, int silent) -{ - struct nfs_server *server; - struct nfs4_client *clp = NULL; - struct rpc_xprt *xprt = NULL; - struct rpc_clnt *clnt = NULL; - struct rpc_timeout timeparms; - rpc_authflavor_t authflavour; - int err = -EIO; - - sb->s_blocksize_bits = 0; - sb->s_blocksize = 0; - server = NFS_SB(sb); - if (data->rsize != 0) - server->rsize = nfs_block_size(data->rsize, NULL); - if (data->wsize != 0) - server->wsize = nfs_block_size(data->wsize, NULL); - server->flags = data->flags & NFS_MOUNT_FLAGMASK; - server->caps = NFS_CAP_ATOMIC_OPEN; - - server->acregmin = data->acregmin*HZ; - server->acregmax = data->acregmax*HZ; - server->acdirmin = data->acdirmin*HZ; - server->acdirmax = data->acdirmax*HZ; - - server->rpc_ops = &nfs_v4_clientops; - - nfs_init_timeout_values(&timeparms, data->proto, data->timeo, data->retrans); - - server->retrans_timeo = timeparms.to_initval; - server->retrans_count = timeparms.to_retries; - - clp = nfs4_get_client(&server->addr.sin_addr); - if (!clp) { - dprintk("%s: failed to create NFS4 client.\n", __FUNCTION__); - return -EIO; - } - - /* Now create transport and client */ - authflavour = RPC_AUTH_UNIX; - if (data->auth_flavourlen != 0) { - if (data->auth_flavourlen != 1) { - dprintk("%s: Invalid number of RPC auth flavours %d.\n", - __FUNCTION__, data->auth_flavourlen); - err = -EINVAL; - goto out_fail; - } - if (copy_from_user(&authflavour, data->auth_flavours, sizeof(authflavour))) { - err = -EFAULT; - goto out_fail; - } - } - - down_write(&clp->cl_sem); - if (IS_ERR(clp->cl_rpcclient)) { - xprt = xprt_create_proto(data->proto, &server->addr, &timeparms); - if (IS_ERR(xprt)) { - up_write(&clp->cl_sem); - err = PTR_ERR(xprt); - dprintk("%s: cannot create RPC transport. Error = %d\n", - __FUNCTION__, err); - goto out_fail; - } - clnt = rpc_create_client(xprt, server->hostname, &nfs_program, - server->rpc_ops->version, authflavour); - if (IS_ERR(clnt)) { - up_write(&clp->cl_sem); - err = PTR_ERR(clnt); - dprintk("%s: cannot create RPC client. Error = %d\n", - __FUNCTION__, err); - goto out_fail; - } - clnt->cl_intr = 1; - clnt->cl_softrtry = 1; - clp->cl_rpcclient = clnt; - memcpy(clp->cl_ipaddr, server->ip_addr, sizeof(clp->cl_ipaddr)); - nfs_idmap_new(clp); - } - list_add_tail(&server->nfs4_siblings, &clp->cl_superblocks); - clnt = rpc_clone_client(clp->cl_rpcclient); - if (!IS_ERR(clnt)) - server->nfs4_state = clp; - up_write(&clp->cl_sem); - clp = NULL; - - if (IS_ERR(clnt)) { - err = PTR_ERR(clnt); - dprintk("%s: cannot create RPC client. Error = %d\n", - __FUNCTION__, err); - return err; - } - - server->client = clnt; - - if (server->nfs4_state->cl_idmap == NULL) { - dprintk("%s: failed to create idmapper.\n", __FUNCTION__); - return -ENOMEM; - } - - if (clnt->cl_auth->au_flavor != authflavour) { - struct rpc_auth *auth; - - auth = rpcauth_create(authflavour, clnt); - if (IS_ERR(auth)) { - dprintk("%s: couldn't create credcache!\n", __FUNCTION__); - return PTR_ERR(auth); - } - } - - sb->s_time_gran = 1; - - sb->s_op = &nfs4_sops; - err = nfs_sb_init(sb, authflavour); - if (err == 0) - return 0; -out_fail: - if (clp) - nfs4_put_client(clp); - return err; -} - -static int nfs4_compare_super(struct super_block *sb, void *data) -{ - struct nfs_server *server = data; - struct nfs_server *old = NFS_SB(sb); - - if (strcmp(server->hostname, old->hostname) != 0) - return 0; - if (strcmp(server->mnt_path, old->mnt_path) != 0) - return 0; - return 1; -} - -static void * -nfs_copy_user_string(char *dst, struct nfs_string *src, int maxlen) -{ - void *p = NULL; - - if (!src->len) - return ERR_PTR(-EINVAL); - if (src->len < maxlen) - maxlen = src->len; - if (dst == NULL) { - p = dst = kmalloc(maxlen + 1, GFP_KERNEL); - if (p == NULL) - return ERR_PTR(-ENOMEM); - } - if (copy_from_user(dst, src->data, maxlen)) { - kfree(p); - return ERR_PTR(-EFAULT); - } - dst[maxlen] = '\0'; - return dst; -} - -static struct super_block *nfs4_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data) -{ - int error; - struct nfs_server *server; - struct super_block *s; - struct nfs4_mount_data *data = raw_data; - void *p; - - if (data == NULL) { - dprintk("%s: missing data argument\n", __FUNCTION__); - return ERR_PTR(-EINVAL); - } - if (data->version <= 0 || data->version > NFS4_MOUNT_VERSION) { - dprintk("%s: bad mount version\n", __FUNCTION__); - return ERR_PTR(-EINVAL); - } - - server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL); - if (!server) - return ERR_PTR(-ENOMEM); - /* Zero out the NFS state stuff */ - init_nfsv4_state(server); - server->client = server->client_sys = server->client_acl = ERR_PTR(-EINVAL); - - p = nfs_copy_user_string(NULL, &data->hostname, 256); - if (IS_ERR(p)) - goto out_err; - server->hostname = p; - - p = nfs_copy_user_string(NULL, &data->mnt_path, 1024); - if (IS_ERR(p)) - goto out_err; - server->mnt_path = p; - - p = nfs_copy_user_string(server->ip_addr, &data->client_addr, - sizeof(server->ip_addr) - 1); - if (IS_ERR(p)) - goto out_err; - - /* We now require that the mount process passes the remote address */ - if (data->host_addrlen != sizeof(server->addr)) { - s = ERR_PTR(-EINVAL); - goto out_free; - } - if (copy_from_user(&server->addr, data->host_addr, sizeof(server->addr))) { - s = ERR_PTR(-EFAULT); - goto out_free; - } - if (server->addr.sin_family != AF_INET || - server->addr.sin_addr.s_addr == INADDR_ANY) { - dprintk("%s: mount program didn't pass remote IP address!\n", - __FUNCTION__); - s = ERR_PTR(-EINVAL); - goto out_free; - } - - /* Fire up rpciod if not yet running */ - s = ERR_PTR(rpciod_up()); - if (IS_ERR(s)) { - dprintk("%s: couldn't start rpciod! Error = %ld\n", - __FUNCTION__, PTR_ERR(s)); - goto out_free; - } - - s = sget(fs_type, nfs4_compare_super, nfs_set_super, server); - - if (IS_ERR(s) || s->s_root) - goto out_free; - - s->s_flags = flags; - - error = nfs4_fill_super(s, data, flags & MS_SILENT ? 1 : 0); - if (error) { - up_write(&s->s_umount); - deactivate_super(s); - return ERR_PTR(error); - } - s->s_flags |= MS_ACTIVE; - return s; -out_err: - s = (struct super_block *)p; -out_free: - kfree(server->mnt_path); - kfree(server->hostname); - kfree(server); - return s; -} - -static void nfs4_kill_super(struct super_block *sb) -{ - struct nfs_server *server = NFS_SB(sb); - - nfs_return_all_delegations(sb); - kill_anon_super(sb); - - nfs4_renewd_prepare_shutdown(server); - - if (server->client != NULL && !IS_ERR(server->client)) - rpc_shutdown_client(server->client); - - destroy_nfsv4_state(server); - - rpciod_down(); - - nfs_free_iostats(server->io_stats); - kfree(server->hostname); - kfree(server); -} - -static struct file_system_type nfs4_fs_type = { - .owner = THIS_MODULE, - .name = "nfs4", - .get_sb = nfs4_get_sb, - .kill_sb = nfs4_kill_super, - .fs_flags = FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, -}; - -static const int nfs_set_port_min = 0; -static const int nfs_set_port_max = 65535; -static int param_set_port(const char *val, struct kernel_param *kp) -{ - char *endp; - int num = simple_strtol(val, &endp, 0); - if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max) - return -EINVAL; - *((int *)kp->arg) = num; - return 0; -} - -module_param_call(callback_tcpport, param_set_port, param_get_int, - &nfs_callback_set_tcpport, 0644); - -static int param_set_idmap_timeout(const char *val, struct kernel_param *kp) -{ - char *endp; - int num = simple_strtol(val, &endp, 0); - int jif = num * HZ; - if (endp == val || *endp || num < 0 || jif < num) - return -EINVAL; - *((int *)kp->arg) = jif; - return 0; -} - -module_param_call(idmap_cache_timeout, param_set_idmap_timeout, param_get_int, - &nfs_idmap_cache_timeout, 0644); - -#define nfs4_init_once(nfsi) \ - do { \ - INIT_LIST_HEAD(&(nfsi)->open_states); \ - nfsi->delegation = NULL; \ - nfsi->delegation_state = 0; \ - init_rwsem(&nfsi->rwsem); \ - } while(0) - -static inline int register_nfs4fs(void) -{ - int ret; - - ret = nfs_register_sysctl(); - if (ret != 0) - return ret; - ret = register_filesystem(&nfs4_fs_type); - if (ret != 0) - nfs_unregister_sysctl(); - return ret; -} - -static inline void unregister_nfs4fs(void) -{ - unregister_filesystem(&nfs4_fs_type); - nfs_unregister_sysctl(); -} -#else -#define nfs4_init_once(nfsi) \ - do { } while (0) -#define register_nfs4fs() (0) -#define unregister_nfs4fs() #endif -extern int nfs_init_nfspagecache(void); -extern void nfs_destroy_nfspagecache(void); -extern int nfs_init_readpagecache(void); -extern void nfs_destroy_readpagecache(void); -extern int nfs_init_writepagecache(void); -extern void nfs_destroy_writepagecache(void); -#ifdef CONFIG_NFS_DIRECTIO -extern int nfs_init_directcache(void); -extern void nfs_destroy_directcache(void); -#endif - -static kmem_cache_t * nfs_inode_cachep; - -static struct inode *nfs_alloc_inode(struct super_block *sb) +struct inode *nfs_alloc_inode(struct super_block *sb) { struct nfs_inode *nfsi; nfsi = (struct nfs_inode *)kmem_cache_alloc(nfs_inode_cachep, SLAB_KERNEL); @@ -2244,11 +1084,19 @@ static struct inode *nfs_alloc_inode(struct super_block *sb) return &nfsi->vfs_inode; } -static void nfs_destroy_inode(struct inode *inode) +void nfs_destroy_inode(struct inode *inode) { kmem_cache_free(nfs_inode_cachep, NFS_I(inode)); } +#define nfs4_init_once(nfsi) \ + do { \ + INIT_LIST_HEAD(&(nfsi)->open_states); \ + nfsi->delegation = NULL; \ + nfsi->delegation_state = 0; \ + init_rwsem(&nfsi->rwsem); \ + } while(0) + static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags) { struct nfs_inode *nfsi = (struct nfs_inode *) foo; @@ -2269,7 +1117,7 @@ static void init_once(void * foo, kmem_cache_t * cachep, unsigned long flags) } } -static int nfs_init_inodecache(void) +static int __init nfs_init_inodecache(void) { nfs_inode_cachep = kmem_cache_create("nfs_inode_cache", sizeof(struct nfs_inode), @@ -2282,7 +1130,7 @@ static int nfs_init_inodecache(void) return 0; } -static void nfs_destroy_inodecache(void) +static void __exit nfs_destroy_inodecache(void) { if (kmem_cache_destroy(nfs_inode_cachep)) printk(KERN_INFO "nfs_inode_cache: not all structures were freed\n"); @@ -2311,29 +1159,22 @@ static int __init init_nfs_fs(void) if (err) goto out1; -#ifdef CONFIG_NFS_DIRECTIO err = nfs_init_directcache(); if (err) goto out0; -#endif #ifdef CONFIG_PROC_FS rpc_proc_register(&nfs_rpcstat); #endif - err = register_filesystem(&nfs_fs_type); - if (err) - goto out; - if ((err = register_nfs4fs()) != 0) + if ((err = register_nfs_fs()) != 0) goto out; return 0; out: #ifdef CONFIG_PROC_FS rpc_proc_unregister("nfs"); #endif -#ifdef CONFIG_NFS_DIRECTIO nfs_destroy_directcache(); out0: -#endif nfs_destroy_writepagecache(); out1: nfs_destroy_readpagecache(); @@ -2347,9 +1188,7 @@ out4: static void __exit exit_nfs_fs(void) { -#ifdef CONFIG_NFS_DIRECTIO nfs_destroy_directcache(); -#endif nfs_destroy_writepagecache(); nfs_destroy_readpagecache(); nfs_destroy_inodecache(); @@ -2357,8 +1196,7 @@ static void __exit exit_nfs_fs(void) #ifdef CONFIG_PROC_FS rpc_proc_unregister("nfs"); #endif - unregister_filesystem(&nfs_fs_type); - unregister_nfs4fs(); + unregister_nfs_fs(); } /* Not quite true; I just maintain it */ diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h new file mode 100644 index 0000000..5e51c45 --- /dev/null +++ b/fs/nfs/internal.h @@ -0,0 +1,179 @@ +/* + * NFS internal definitions + */ + +#include <linux/mount.h> + +struct nfs_clone_mount { + const struct super_block *sb; + const struct dentry *dentry; + struct nfs_fh *fh; + struct nfs_fattr *fattr; + char *hostname; + char *mnt_path; + struct sockaddr_in *addr; + rpc_authflavor_t authflavor; +}; + +/* namespace-nfs4.c */ +#ifdef CONFIG_NFS_V4 +extern struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentry *dentry); +#else +static inline +struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentry *dentry) +{ + return ERR_PTR(-ENOENT); +} +#endif + +/* callback_xdr.c */ +extern struct svc_version nfs4_callback_version1; + +/* pagelist.c */ +extern int __init nfs_init_nfspagecache(void); +extern void __exit nfs_destroy_nfspagecache(void); +extern int __init nfs_init_readpagecache(void); +extern void __exit nfs_destroy_readpagecache(void); +extern int __init nfs_init_writepagecache(void); +extern void __exit nfs_destroy_writepagecache(void); + +#ifdef CONFIG_NFS_DIRECTIO +extern int __init nfs_init_directcache(void); +extern void __exit nfs_destroy_directcache(void); +#else +#define nfs_init_directcache() (0) +#define nfs_destroy_directcache() do {} while(0) +#endif + +/* nfs2xdr.c */ +extern struct rpc_procinfo nfs_procedures[]; +extern u32 * nfs_decode_dirent(u32 *, struct nfs_entry *, int); + +/* nfs3xdr.c */ +extern struct rpc_procinfo nfs3_procedures[]; +extern u32 *nfs3_decode_dirent(u32 *, struct nfs_entry *, int); + +/* nfs4xdr.c */ +extern int nfs_stat_to_errno(int); +extern u32 *nfs4_decode_dirent(u32 *p, struct nfs_entry *entry, int plus); + +/* nfs4proc.c */ +extern struct rpc_procinfo nfs4_procedures[]; + +extern int nfs4_proc_fs_locations(struct inode *dir, struct dentry *dentry, + struct nfs4_fs_locations *fs_locations, + struct page *page); + +/* inode.c */ +extern struct inode *nfs_alloc_inode(struct super_block *sb); +extern void nfs_destroy_inode(struct inode *); +extern int nfs_write_inode(struct inode *,int); +extern void nfs_clear_inode(struct inode *); +#ifdef CONFIG_NFS_V4 +extern void nfs4_clear_inode(struct inode *); +#endif + +/* super.c */ +extern struct file_system_type nfs_referral_nfs4_fs_type; +extern struct file_system_type clone_nfs_fs_type; +#ifdef CONFIG_NFS_V4 +extern struct file_system_type clone_nfs4_fs_type; +#endif +#ifdef CONFIG_PROC_FS +extern struct rpc_stat nfs_rpcstat; +#endif +extern int __init register_nfs_fs(void); +extern void __exit unregister_nfs_fs(void); + +/* namespace.c */ +extern char *nfs_path(const char *base, const struct dentry *dentry, + char *buffer, ssize_t buflen); + +/* + * Determine the mount path as a string + */ +static inline char *nfs4_path(const struct dentry *dentry, char *buffer, ssize_t buflen) +{ + return nfs_path(NFS_SB(dentry->d_sb)->mnt_path, dentry, buffer, buflen); +} + +/* + * Determine the device name as a string + */ +static inline char *nfs_devname(const struct vfsmount *mnt_parent, + const struct dentry *dentry, + char *buffer, ssize_t buflen) +{ + return nfs_path(mnt_parent->mnt_devname, dentry, buffer, buflen); +} + +/* + * Determine the actual block size (and log2 thereof) + */ +static inline +unsigned long nfs_block_bits(unsigned long bsize, unsigned char *nrbitsp) +{ + /* make sure blocksize is a power of two */ + if ((bsize & (bsize - 1)) || nrbitsp) { + unsigned char nrbits; + + for (nrbits = 31; nrbits && !(bsize & (1 << nrbits)); nrbits--) + ; + bsize = 1 << nrbits; + if (nrbitsp) + *nrbitsp = nrbits; + } + + return bsize; +} + +/* + * Calculate the number of 512byte blocks used. + */ +static inline unsigned long nfs_calc_block_size(u64 tsize) +{ + loff_t used = (tsize + 511) >> 9; + return (used > ULONG_MAX) ? ULONG_MAX : used; +} + +/* + * Compute and set NFS server blocksize + */ +static inline +unsigned long nfs_block_size(unsigned long bsize, unsigned char *nrbitsp) +{ + if (bsize < NFS_MIN_FILE_IO_SIZE) + bsize = NFS_DEF_FILE_IO_SIZE; + else if (bsize >= NFS_MAX_FILE_IO_SIZE) + bsize = NFS_MAX_FILE_IO_SIZE; + + return nfs_block_bits(bsize, nrbitsp); +} + +/* + * Determine the maximum file size for a superblock + */ +static inline +void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) +{ + sb->s_maxbytes = (loff_t)maxfilesize; + if (sb->s_maxbytes > MAX_LFS_FILESIZE || sb->s_maxbytes <= 0) + sb->s_maxbytes = MAX_LFS_FILESIZE; +} + +/* + * Check if the string represents a "valid" IPv4 address + */ +static inline int valid_ipaddr4(const char *buf) +{ + int rc, count, in[4]; + + rc = sscanf(buf, "%d.%d.%d.%d", &in[0], &in[1], &in[2], &in[3]); + if (rc != 4) + return -EINVAL; + for (count = 0; count < 4; count++) { + if (in[count] > 255) + return -EINVAL; + } + return 0; +} diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c new file mode 100644 index 0000000..19b98ca --- /dev/null +++ b/fs/nfs/namespace.c @@ -0,0 +1,229 @@ +/* + * linux/fs/nfs/namespace.c + * + * Copyright (C) 2005 Trond Myklebust <Trond.Myklebust@netapp.com> + * + * NFS namespace + */ + +#include <linux/config.h> + +#include <linux/dcache.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/nfs_fs.h> +#include <linux/string.h> +#include <linux/sunrpc/clnt.h> +#include <linux/vfs.h> +#include "internal.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +static void nfs_expire_automounts(void *list); + +LIST_HEAD(nfs_automount_list); +static DECLARE_WORK(nfs_automount_task, nfs_expire_automounts, &nfs_automount_list); +int nfs_mountpoint_expiry_timeout = 500 * HZ; + +/* + * nfs_path - reconstruct the path given an arbitrary dentry + * @base - arbitrary string to prepend to the path + * @dentry - pointer to dentry + * @buffer - result buffer + * @buflen - length of buffer + * + * Helper function for constructing the path from the + * root dentry to an arbitrary hashed dentry. + * + * This is mainly for use in figuring out the path on the + * server side when automounting on top of an existing partition. + */ +char *nfs_path(const char *base, const struct dentry *dentry, + char *buffer, ssize_t buflen) +{ + char *end = buffer+buflen; + int namelen; + + *--end = '\0'; + buflen--; + spin_lock(&dcache_lock); + while (!IS_ROOT(dentry)) { + namelen = dentry->d_name.len; + buflen -= namelen + 1; + if (buflen < 0) + goto Elong; + end -= namelen; + memcpy(end, dentry->d_name.name, namelen); + *--end = '/'; + dentry = dentry->d_parent; + } + spin_unlock(&dcache_lock); + namelen = strlen(base); + /* Strip off excess slashes in base string */ + while (namelen > 0 && base[namelen - 1] == '/') + namelen--; + buflen -= namelen; + if (buflen < 0) + goto Elong; + end -= namelen; + memcpy(end, base, namelen); + return end; +Elong: + return ERR_PTR(-ENAMETOOLONG); +} + +/* + * nfs_follow_mountpoint - handle crossing a mountpoint on the server + * @dentry - dentry of mountpoint + * @nd - nameidata info + * + * When we encounter a mountpoint on the server, we want to set up + * a mountpoint on the client too, to prevent inode numbers from + * colliding, and to allow "df" to work properly. + * On NFSv4, we also want to allow for the fact that different + * filesystems may be migrated to different servers in a failover + * situation, and that different filesystems may want to use + * different security flavours. + */ +static void * nfs_follow_mountpoint(struct dentry *dentry, struct nameidata *nd) +{ + struct vfsmount *mnt; + struct nfs_server *server = NFS_SERVER(dentry->d_inode); + struct dentry *parent; + struct nfs_fh fh; + struct nfs_fattr fattr; + int err; + + BUG_ON(IS_ROOT(dentry)); + dprintk("%s: enter\n", __FUNCTION__); + dput(nd->dentry); + nd->dentry = dget(dentry); + if (d_mountpoint(nd->dentry)) + goto out_follow; + /* Look it up again */ + parent = dget_parent(nd->dentry); + err = server->rpc_ops->lookup(parent->d_inode, &nd->dentry->d_name, &fh, &fattr); + dput(parent); + if (err != 0) + goto out_err; + + if (fattr.valid & NFS_ATTR_FATTR_V4_REFERRAL) + mnt = nfs_do_refmount(nd->mnt, nd->dentry); + else + mnt = nfs_do_submount(nd->mnt, nd->dentry, &fh, &fattr); + err = PTR_ERR(mnt); + if (IS_ERR(mnt)) + goto out_err; + + mntget(mnt); + err = do_add_mount(mnt, nd, nd->mnt->mnt_flags|MNT_SHRINKABLE, &nfs_automount_list); + if (err < 0) { + mntput(mnt); + if (err == -EBUSY) + goto out_follow; + goto out_err; + } + mntput(nd->mnt); + dput(nd->dentry); + nd->mnt = mnt; + nd->dentry = dget(mnt->mnt_root); + schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout); +out: + dprintk("%s: done, returned %d\n", __FUNCTION__, err); + return ERR_PTR(err); +out_err: + path_release(nd); + goto out; +out_follow: + while(d_mountpoint(nd->dentry) && follow_down(&nd->mnt, &nd->dentry)) + ; + err = 0; + goto out; +} + +struct inode_operations nfs_mountpoint_inode_operations = { + .follow_link = nfs_follow_mountpoint, + .getattr = nfs_getattr, +}; + +struct inode_operations nfs_referral_inode_operations = { + .follow_link = nfs_follow_mountpoint, +}; + +static void nfs_expire_automounts(void *data) +{ + struct list_head *list = (struct list_head *)data; + + mark_mounts_for_expiry(list); + if (!list_empty(list)) + schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout); +} + +void nfs_release_automount_timer(void) +{ + if (list_empty(&nfs_automount_list)) { + cancel_delayed_work(&nfs_automount_task); + flush_scheduled_work(); + } +} + +/* + * Clone a mountpoint of the appropriate type + */ +static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, char *devname, + struct nfs_clone_mount *mountdata) +{ +#ifdef CONFIG_NFS_V4 + struct vfsmount *mnt = NULL; + switch (server->rpc_ops->version) { + case 2: + case 3: + mnt = vfs_kern_mount(&clone_nfs_fs_type, 0, devname, mountdata); + break; + case 4: + mnt = vfs_kern_mount(&clone_nfs4_fs_type, 0, devname, mountdata); + } + return mnt; +#else + return vfs_kern_mount(&clone_nfs_fs_type, 0, devname, mountdata); +#endif +} + +/** + * nfs_do_submount - set up mountpoint when crossing a filesystem boundary + * @mnt_parent - mountpoint of parent directory + * @dentry - parent directory + * @fh - filehandle for new root dentry + * @fattr - attributes for new root inode + * + */ +struct vfsmount *nfs_do_submount(const struct vfsmount *mnt_parent, + const struct dentry *dentry, struct nfs_fh *fh, + struct nfs_fattr *fattr) +{ + struct nfs_clone_mount mountdata = { + .sb = mnt_parent->mnt_sb, + .dentry = dentry, + .fh = fh, + .fattr = fattr, + }; + struct vfsmount *mnt = ERR_PTR(-ENOMEM); + char *page = (char *) __get_free_page(GFP_USER); + char *devname; + + dprintk("%s: submounting on %s/%s\n", __FUNCTION__, + dentry->d_parent->d_name.name, + dentry->d_name.name); + if (page == NULL) + goto out; + devname = nfs_devname(mnt_parent, dentry, page, PAGE_SIZE); + mnt = (struct vfsmount *)devname; + if (IS_ERR(devname)) + goto free_page; + mnt = nfs_do_clone_mount(NFS_SB(mnt_parent->mnt_sb), devname, &mountdata); +free_page: + free_page((unsigned long)page); +out: + dprintk("%s: done\n", __FUNCTION__); + return mnt; +} diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index f0015fa..4a006f8 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -27,8 +27,6 @@ #define NFSDBG_FACILITY NFSDBG_XDR /* #define NFS_PARANOIA 1 */ -extern int nfs_stat_to_errno(int stat); - /* Mapping from NFS error code to "errno" error code. */ #define errno_NFSERR_IO EIO @@ -131,7 +129,8 @@ xdr_decode_fattr(u32 *p, struct nfs_fattr *fattr) fattr->du.nfs2.blocksize = ntohl(*p++); rdev = ntohl(*p++); fattr->du.nfs2.blocks = ntohl(*p++); - fattr->fsid_u.nfs3 = ntohl(*p++); + fattr->fsid.major = ntohl(*p++); + fattr->fsid.minor = 0; fattr->fileid = ntohl(*p++); p = xdr_decode_time(p, &fattr->atime); p = xdr_decode_time(p, &fattr->mtime); diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c index 3328787..7322da4 100644 --- a/fs/nfs/nfs3acl.c +++ b/fs/nfs/nfs3acl.c @@ -172,8 +172,10 @@ static void nfs3_cache_acls(struct inode *inode, struct posix_acl *acl, inode->i_ino, acl, dfacl); spin_lock(&inode->i_lock); __nfs3_forget_cached_acls(NFS_I(inode)); - nfsi->acl_access = posix_acl_dup(acl); - nfsi->acl_default = posix_acl_dup(dfacl); + if (!IS_ERR(acl)) + nfsi->acl_access = posix_acl_dup(acl); + if (!IS_ERR(dfacl)) + nfsi->acl_default = posix_acl_dup(dfacl); spin_unlock(&inode->i_lock); } @@ -254,7 +256,9 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type) res.acl_access = NULL; } } - nfs3_cache_acls(inode, res.acl_access, res.acl_default); + nfs3_cache_acls(inode, + (res.mask & NFS_ACL) ? res.acl_access : ERR_PTR(-EINVAL), + (res.mask & NFS_DFACL) ? res.acl_default : ERR_PTR(-EINVAL)); switch(type) { case ACL_TYPE_ACCESS: @@ -329,6 +333,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl, switch (status) { case 0: status = nfs_refresh_inode(inode, &fattr); + nfs3_cache_acls(inode, acl, dfacl); break; case -EPFNOSUPPORT: case -EPROTONOSUPPORT: diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index cf186f0..7143b1f 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -20,11 +20,10 @@ #include <linux/nfs_mount.h> #include "iostat.h" +#include "internal.h" #define NFSDBG_FACILITY NFSDBG_PROC -extern struct rpc_procinfo nfs3_procedures[]; - /* A wrapper to handle the EJUKEBOX error message */ static int nfs3_rpc_wrapper(struct rpc_clnt *clnt, struct rpc_message *msg, int flags) @@ -809,8 +808,6 @@ nfs3_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, return status; } -extern u32 *nfs3_decode_dirent(u32 *, struct nfs_entry *, int); - static int nfs3_read_done(struct rpc_task *task, struct nfs_read_data *data) { if (nfs3_async_handle_jukebox(task, data->inode)) diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index ec23361..0250269 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -22,14 +22,13 @@ #include <linux/nfs3.h> #include <linux/nfs_fs.h> #include <linux/nfsacl.h> +#include "internal.h" #define NFSDBG_FACILITY NFSDBG_XDR /* Mapping from NFS error code to "errno" error code. */ #define errno_NFSERR_IO EIO -extern int nfs_stat_to_errno(int); - /* * Declare the space requirements for NFS arguments and replies as * number of 32bit-words @@ -166,7 +165,8 @@ xdr_decode_fattr(u32 *p, struct nfs_fattr *fattr) if (MAJOR(fattr->rdev) != major || MINOR(fattr->rdev) != minor) fattr->rdev = 0; - p = xdr_decode_hyper(p, &fattr->fsid_u.nfs3); + p = xdr_decode_hyper(p, &fattr->fsid.major); + fattr->fsid.minor = 0; p = xdr_decode_hyper(p, &fattr->fileid); p = xdr_decode_time3(p, &fattr->atime); p = xdr_decode_time3(p, &fattr->mtime); diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 0f5e4e7..9a10286 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -217,6 +217,9 @@ extern int nfs4_proc_renew(struct nfs4_client *, struct rpc_cred *); extern int nfs4_do_close(struct inode *inode, struct nfs4_state *state); extern struct dentry *nfs4_atomic_open(struct inode *, struct dentry *, struct nameidata *); extern int nfs4_open_revalidate(struct inode *, struct dentry *, int, struct nameidata *); +extern int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle); +extern int nfs4_proc_fs_locations(struct inode *dir, struct dentry *dentry, + struct nfs4_fs_locations *fs_locations, struct page *page); extern struct nfs4_state_recovery_ops nfs4_reboot_recovery_ops; extern struct nfs4_state_recovery_ops nfs4_network_partition_recovery_ops; @@ -225,6 +228,7 @@ extern const u32 nfs4_fattr_bitmap[2]; extern const u32 nfs4_statfs_bitmap[2]; extern const u32 nfs4_pathconf_bitmap[2]; extern const u32 nfs4_fsinfo_bitmap[2]; +extern const u32 nfs4_fs_locations_bitmap[2]; /* nfs4renewd.c */ extern void nfs4_schedule_state_renewal(struct nfs4_client *); diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c new file mode 100644 index 0000000..ea38d27 --- /dev/null +++ b/fs/nfs/nfs4namespace.c @@ -0,0 +1,201 @@ +/* + * linux/fs/nfs/nfs4namespace.c + * + * Copyright (C) 2005 Trond Myklebust <Trond.Myklebust@netapp.com> + * + * NFSv4 namespace + */ + +#include <linux/config.h> + +#include <linux/dcache.h> +#include <linux/mount.h> +#include <linux/namei.h> +#include <linux/nfs_fs.h> +#include <linux/string.h> +#include <linux/sunrpc/clnt.h> +#include <linux/vfs.h> +#include <linux/inet.h> +#include "internal.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +/* + * Check if fs_root is valid + */ +static inline char *nfs4_pathname_string(struct nfs4_pathname *pathname, + char *buffer, ssize_t buflen) +{ + char *end = buffer + buflen; + int n; + + *--end = '\0'; + buflen--; + + n = pathname->ncomponents; + while (--n >= 0) { + struct nfs4_string *component = &pathname->components[n]; + buflen -= component->len + 1; + if (buflen < 0) + goto Elong; + end -= component->len; + memcpy(end, component->data, component->len); + *--end = '/'; + } + return end; +Elong: + return ERR_PTR(-ENAMETOOLONG); +} + + +/** + * nfs_follow_referral - set up mountpoint when hitting a referral on moved error + * @mnt_parent - mountpoint of parent directory + * @dentry - parent directory + * @fspath - fs path returned in fs_locations + * @mntpath - mount path to new server + * @hostname - hostname of new server + * @addr - host addr of new server + * + */ +static struct vfsmount *nfs_follow_referral(const struct vfsmount *mnt_parent, + const struct dentry *dentry, + struct nfs4_fs_locations *locations) +{ + struct vfsmount *mnt = ERR_PTR(-ENOENT); + struct nfs_clone_mount mountdata = { + .sb = mnt_parent->mnt_sb, + .dentry = dentry, + .authflavor = NFS_SB(mnt_parent->mnt_sb)->client->cl_auth->au_flavor, + }; + char *page, *page2; + char *path, *fs_path; + char *devname; + int loc, s; + + if (locations == NULL || locations->nlocations <= 0) + goto out; + + dprintk("%s: referral at %s/%s\n", __FUNCTION__, + dentry->d_parent->d_name.name, dentry->d_name.name); + + /* Ensure fs path is a prefix of current dentry path */ + page = (char *) __get_free_page(GFP_USER); + if (page == NULL) + goto out; + page2 = (char *) __get_free_page(GFP_USER); + if (page2 == NULL) + goto out; + + path = nfs4_path(dentry, page, PAGE_SIZE); + if (IS_ERR(path)) + goto out_free; + + fs_path = nfs4_pathname_string(&locations->fs_path, page2, PAGE_SIZE); + if (IS_ERR(fs_path)) + goto out_free; + + if (strncmp(path, fs_path, strlen(fs_path)) != 0) { + dprintk("%s: path %s does not begin with fsroot %s\n", __FUNCTION__, path, fs_path); + goto out_free; + } + + devname = nfs_devname(mnt_parent, dentry, page, PAGE_SIZE); + if (IS_ERR(devname)) { + mnt = (struct vfsmount *)devname; + goto out_free; + } + + loc = 0; + while (loc < locations->nlocations && IS_ERR(mnt)) { + struct nfs4_fs_location *location = &locations->locations[loc]; + char *mnt_path; + + if (location == NULL || location->nservers <= 0 || + location->rootpath.ncomponents == 0) { + loc++; + continue; + } + + mnt_path = nfs4_pathname_string(&location->rootpath, page2, PAGE_SIZE); + if (IS_ERR(mnt_path)) { + loc++; + continue; + } + mountdata.mnt_path = mnt_path; + + s = 0; + while (s < location->nservers) { + struct sockaddr_in addr = {}; + + if (location->servers[s].len <= 0 || + valid_ipaddr4(location->servers[s].data) < 0) { + s++; + continue; + } + + mountdata.hostname = location->servers[s].data; + addr.sin_addr.s_addr = in_aton(mountdata.hostname); + addr.sin_family = AF_INET; + addr.sin_port = htons(NFS_PORT); + mountdata.addr = &addr; + + mnt = vfs_kern_mount(&nfs_referral_nfs4_fs_type, 0, devname, &mountdata); + if (!IS_ERR(mnt)) { + break; + } + s++; + } + loc++; + } + +out_free: + free_page((unsigned long)page); + free_page((unsigned long)page2); +out: + dprintk("%s: done\n", __FUNCTION__); + return mnt; +} + +/* + * nfs_do_refmount - handle crossing a referral on server + * @dentry - dentry of referral + * @nd - nameidata info + * + */ +struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, struct dentry *dentry) +{ + struct vfsmount *mnt = ERR_PTR(-ENOENT); + struct dentry *parent; + struct nfs4_fs_locations *fs_locations = NULL; + struct page *page; + int err; + + /* BUG_ON(IS_ROOT(dentry)); */ + dprintk("%s: enter\n", __FUNCTION__); + + page = alloc_page(GFP_KERNEL); + if (page == NULL) + goto out; + + fs_locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); + if (fs_locations == NULL) + goto out_free; + + /* Get locations */ + parent = dget_parent(dentry); + dprintk("%s: getting locations for %s/%s\n", __FUNCTION__, parent->d_name.name, dentry->d_name.name); + err = nfs4_proc_fs_locations(parent->d_inode, dentry, fs_locations, page); + dput(parent); + if (err != 0 || fs_locations->nlocations <= 0 || + fs_locations->fs_path.ncomponents <= 0) + goto out_free; + + mnt = nfs_follow_referral(mnt_parent, dentry, fs_locations); +out_free: + __free_page(page); + kfree(fs_locations); +out: + dprintk("%s: done\n", __FUNCTION__); + return mnt; +} diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index d86c0db..b4916b0 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -65,8 +65,6 @@ static int nfs4_async_handle_error(struct rpc_task *, const struct nfs_server *) static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry); static int nfs4_handle_exception(const struct nfs_server *server, int errorcode, struct nfs4_exception *exception); static int nfs4_wait_clnt_recover(struct rpc_clnt *clnt, struct nfs4_client *clp); -extern u32 *nfs4_decode_dirent(u32 *p, struct nfs_entry *entry, int plus); -extern struct rpc_procinfo nfs4_procedures[]; /* Prevent leaks of NFSv4 errors into userland */ int nfs4_map_errors(int err) @@ -121,6 +119,25 @@ const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE 0 }; +const u32 nfs4_fs_locations_bitmap[2] = { + FATTR4_WORD0_TYPE + | FATTR4_WORD0_CHANGE + | FATTR4_WORD0_SIZE + | FATTR4_WORD0_FSID + | FATTR4_WORD0_FILEID + | FATTR4_WORD0_FS_LOCATIONS, + FATTR4_WORD1_MODE + | FATTR4_WORD1_NUMLINKS + | FATTR4_WORD1_OWNER + | FATTR4_WORD1_OWNER_GROUP + | FATTR4_WORD1_RAWDEV + | FATTR4_WORD1_SPACE_USED + | FATTR4_WORD1_TIME_ACCESS + | FATTR4_WORD1_TIME_METADATA + | FATTR4_WORD1_TIME_MODIFY + | FATTR4_WORD1_MOUNTED_ON_FILEID +}; + static void nfs4_setup_readdir(u64 cookie, u32 *verifier, struct dentry *dentry, struct nfs4_readdir_arg *readdir) { @@ -185,15 +202,15 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp spin_unlock(&clp->cl_lock); } -static void update_changeattr(struct inode *inode, struct nfs4_change_info *cinfo) +static void update_changeattr(struct inode *dir, struct nfs4_change_info *cinfo) { - struct nfs_inode *nfsi = NFS_I(inode); + struct nfs_inode *nfsi = NFS_I(dir); - spin_lock(&inode->i_lock); - nfsi->cache_validity |= NFS_INO_INVALID_ATTR; + spin_lock(&dir->i_lock); + nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA; if (cinfo->before == nfsi->change_attr && cinfo->atomic) nfsi->change_attr = cinfo->after; - spin_unlock(&inode->i_lock); + spin_unlock(&dir->i_lock); } struct nfs4_opendata { @@ -1331,7 +1348,7 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f return status; } -static int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) +int nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *fhandle) { struct nfs4_exception exception = { }; int err; @@ -1443,6 +1460,50 @@ out: return nfs4_map_errors(status); } +/* + * Get locations and (maybe) other attributes of a referral. + * Note that we'll actually follow the referral later when + * we detect fsid mismatch in inode revalidation + */ +static int nfs4_get_referral(struct inode *dir, struct qstr *name, struct nfs_fattr *fattr, struct nfs_fh *fhandle) +{ + int status = -ENOMEM; + struct page *page = NULL; + struct nfs4_fs_locations *locations = NULL; + struct dentry dentry = {}; + + page = alloc_page(GFP_KERNEL); + if (page == NULL) + goto out; + locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL); + if (locations == NULL) + goto out; + + dentry.d_name.name = name->name; + dentry.d_name.len = name->len; + status = nfs4_proc_fs_locations(dir, &dentry, locations, page); + if (status != 0) + goto out; + /* Make sure server returned a different fsid for the referral */ + if (nfs_fsid_equal(&NFS_SERVER(dir)->fsid, &locations->fattr.fsid)) { + dprintk("%s: server did not return a different fsid for a referral at %s\n", __FUNCTION__, name->name); + status = -EIO; + goto out; + } + + memcpy(fattr, &locations->fattr, sizeof(struct nfs_fattr)); + fattr->valid |= NFS_ATTR_FATTR_V4_REFERRAL; + if (!fattr->mode) + fattr->mode = S_IFDIR; + memset(fhandle, 0, sizeof(struct nfs_fh)); +out: + if (page) + __free_page(page); + if (locations) + kfree(locations); + return status; +} + static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fattr *fattr) { struct nfs4_getattr_arg args = { @@ -1547,6 +1608,8 @@ static int _nfs4_proc_lookup(struct inode *dir, struct qstr *name, dprintk("NFS call lookup %s\n", name->name); status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0); + if (status == -NFS4ERR_MOVED) + status = nfs4_get_referral(dir, name, fattr, fhandle); dprintk("NFS reply lookup: %d\n", status); return status; } @@ -2008,7 +2071,7 @@ static int _nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr * if (!status) { update_changeattr(dir, &res.cinfo); nfs_post_op_update_inode(dir, res.dir_attr); - nfs_refresh_inode(inode, res.fattr); + nfs_post_op_update_inode(inode, res.fattr); } return status; @@ -3570,6 +3633,36 @@ ssize_t nfs4_listxattr(struct dentry *dentry, char *buf, size_t buflen) return len; } +int nfs4_proc_fs_locations(struct inode *dir, struct dentry *dentry, + struct nfs4_fs_locations *fs_locations, struct page *page) +{ + struct nfs_server *server = NFS_SERVER(dir); + u32 bitmask[2] = { + [0] = FATTR4_WORD0_FSID | FATTR4_WORD0_FS_LOCATIONS, + [1] = FATTR4_WORD1_MOUNTED_ON_FILEID, + }; + struct nfs4_fs_locations_arg args = { + .dir_fh = NFS_FH(dir), + .name = &dentry->d_name, + .page = page, + .bitmask = bitmask, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_FS_LOCATIONS], + .rpc_argp = &args, + .rpc_resp = fs_locations, + }; + int status; + + dprintk("%s: start\n", __FUNCTION__); + fs_locations->fattr.valid = 0; + fs_locations->server = server; + fs_locations->nlocations = 0; + status = rpc_call_sync(server->client, &msg, 0); + dprintk("%s: returned status = %d\n", __FUNCTION__, status); + return status; +} + struct nfs4_state_recovery_ops nfs4_reboot_recovery_ops = { .recover_open = nfs4_open_reclaim, .recover_lock = nfs4_lock_reclaim, diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 7c5d70e..1750d99 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -411,6 +411,15 @@ static int nfs_stat_to_errno(int); #define NFS4_dec_setacl_sz (compound_decode_hdr_maxsz + \ decode_putfh_maxsz + \ op_decode_hdr_maxsz + nfs4_fattr_bitmap_maxsz) +#define NFS4_enc_fs_locations_sz \ + (compound_encode_hdr_maxsz + \ + encode_putfh_maxsz + \ + encode_getattr_maxsz) +#define NFS4_dec_fs_locations_sz \ + (compound_decode_hdr_maxsz + \ + decode_putfh_maxsz + \ + op_decode_hdr_maxsz + \ + nfs4_fattr_bitmap_maxsz) static struct { unsigned int mode; @@ -722,6 +731,13 @@ static int encode_fsinfo(struct xdr_stream *xdr, const u32* bitmask) bitmask[1] & nfs4_fsinfo_bitmap[1]); } +static int encode_fs_locations(struct xdr_stream *xdr, const u32* bitmask) +{ + return encode_getattr_two(xdr, + bitmask[0] & nfs4_fs_locations_bitmap[0], + bitmask[1] & nfs4_fs_locations_bitmap[1]); +} + static int encode_getfh(struct xdr_stream *xdr) { uint32_t *p; @@ -2003,6 +2019,38 @@ out: } /* + * Encode FS_LOCATIONS request + */ +static int nfs4_xdr_enc_fs_locations(struct rpc_rqst *req, uint32_t *p, struct nfs4_fs_locations_arg *args) +{ + struct xdr_stream xdr; + struct compound_hdr hdr = { + .nops = 3, + }; + struct rpc_auth *auth = req->rq_task->tk_auth; + int replen; + int status; + + xdr_init_encode(&xdr, &req->rq_snd_buf, p); + encode_compound_hdr(&xdr, &hdr); + if ((status = encode_putfh(&xdr, args->dir_fh)) != 0) + goto out; + if ((status = encode_lookup(&xdr, args->name)) != 0) + goto out; + if ((status = encode_fs_locations(&xdr, args->bitmask)) != 0) + goto out; + /* set up reply + * toplevel_status + OP_PUTFH + status + * + OP_LOOKUP + status + OP_GETATTR + status = 7 + */ + replen = (RPC_REPHDRSIZE + auth->au_rslack + 7) << 2; + xdr_inline_pages(&req->rq_rcv_buf, replen, &args->page, + 0, PAGE_SIZE); +out: + return status; +} + +/* * START OF "GENERIC" DECODE ROUTINES. * These may look a little ugly since they are imported from a "generic" * set of XDR encode/decode routines which are intended to be shared by @@ -2036,7 +2084,7 @@ out: } \ } while (0) -static int decode_opaque_inline(struct xdr_stream *xdr, uint32_t *len, char **string) +static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char **string) { uint32_t *p; @@ -2087,7 +2135,7 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected) static int decode_ace(struct xdr_stream *xdr, void *ace, struct nfs4_client *clp) { uint32_t *p; - uint32_t strlen; + unsigned int strlen; char *str; READ_BUF(12); @@ -2217,7 +2265,7 @@ static int decode_attr_symlink_support(struct xdr_stream *xdr, uint32_t *bitmap, return 0; } -static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs4_fsid *fsid) +static int decode_attr_fsid(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fsid *fsid) { uint32_t *p; @@ -2285,6 +2333,22 @@ static int decode_attr_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t return 0; } +static int decode_attr_mounted_on_fileid(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *fileid) +{ + uint32_t *p; + + *fileid = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_MOUNTED_ON_FILEID - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_MOUNTED_ON_FILEID)) { + READ_BUF(8); + READ64(*fileid); + bitmap[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; + } + dprintk("%s: fileid=%Lu\n", __FUNCTION__, (unsigned long long)*fileid); + return 0; +} + static int decode_attr_files_avail(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) { uint32_t *p; @@ -2336,6 +2400,116 @@ static int decode_attr_files_total(struct xdr_stream *xdr, uint32_t *bitmap, uin return status; } +static int decode_pathname(struct xdr_stream *xdr, struct nfs4_pathname *path) +{ + int n; + uint32_t *p; + int status = 0; + + READ_BUF(4); + READ32(n); + if (n < 0) + goto out_eio; + if (n == 0) + goto root_path; + dprintk("path "); + path->ncomponents = 0; + while (path->ncomponents < n) { + struct nfs4_string *component = &path->components[path->ncomponents]; + status = decode_opaque_inline(xdr, &component->len, &component->data); + if (unlikely(status != 0)) + goto out_eio; + if (path->ncomponents != n) + dprintk("/"); + dprintk("%s", component->data); + if (path->ncomponents < NFS4_PATHNAME_MAXCOMPONENTS) + path->ncomponents++; + else { + dprintk("cannot parse %d components in path\n", n); + goto out_eio; + } + } +out: + dprintk("\n"); + return status; +root_path: +/* a root pathname is sent as a zero component4 */ + path->ncomponents = 1; + path->components[0].len=0; + path->components[0].data=NULL; + dprintk("path /\n"); + goto out; +out_eio: + dprintk(" status %d", status); + status = -EIO; + goto out; +} + +static int decode_attr_fs_locations(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs4_fs_locations *res) +{ + int n; + uint32_t *p; + int status = -EIO; + + if (unlikely(bitmap[0] & (FATTR4_WORD0_FS_LOCATIONS -1U))) + goto out; + status = 0; + if (unlikely(!(bitmap[0] & FATTR4_WORD0_FS_LOCATIONS))) + goto out; + dprintk("%s: fsroot ", __FUNCTION__); + status = decode_pathname(xdr, &res->fs_path); + if (unlikely(status != 0)) + goto out; + READ_BUF(4); + READ32(n); + if (n <= 0) + goto out_eio; + res->nlocations = 0; + while (res->nlocations < n) { + int m; + struct nfs4_fs_location *loc = &res->locations[res->nlocations]; + + READ_BUF(4); + READ32(m); + if (m <= 0) + goto out_eio; + + loc->nservers = 0; + dprintk("%s: servers ", __FUNCTION__); + while (loc->nservers < m) { + struct nfs4_string *server = &loc->servers[loc->nservers]; + status = decode_opaque_inline(xdr, &server->len, &server->data); + if (unlikely(status != 0)) + goto out_eio; + dprintk("%s ", server->data); + if (loc->nservers < NFS4_FS_LOCATION_MAXSERVERS) + loc->nservers++; + else { + int i; + dprintk("%s: using first %d of %d servers returned for location %d\n", __FUNCTION__, NFS4_FS_LOCATION_MAXSERVERS, m, res->nlocations); + for (i = loc->nservers; i < m; i++) { + int len; + char *data; + status = decode_opaque_inline(xdr, &len, &data); + if (unlikely(status != 0)) + goto out_eio; + } + } + } + status = decode_pathname(xdr, &loc->rootpath); + if (unlikely(status != 0)) + goto out_eio; + if (res->nlocations < NFS4_FS_LOCATIONS_MAXENTRIES) + res->nlocations++; + } +out: + dprintk("%s: fs_locations done, error = %d\n", __FUNCTION__, status); + return status; +out_eio: + status = -EIO; + goto out; +} + static int decode_attr_maxfilesize(struct xdr_stream *xdr, uint32_t *bitmap, uint64_t *res) { uint32_t *p; @@ -2841,6 +3015,7 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons bitmap[2] = {0}, type; int status, fmode = 0; + uint64_t fileid; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) goto xdr_error; @@ -2863,10 +3038,14 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons goto xdr_error; if ((status = decode_attr_size(xdr, bitmap, &fattr->size)) != 0) goto xdr_error; - if ((status = decode_attr_fsid(xdr, bitmap, &fattr->fsid_u.nfs4)) != 0) + if ((status = decode_attr_fsid(xdr, bitmap, &fattr->fsid)) != 0) goto xdr_error; if ((status = decode_attr_fileid(xdr, bitmap, &fattr->fileid)) != 0) goto xdr_error; + if ((status = decode_attr_fs_locations(xdr, bitmap, container_of(fattr, + struct nfs4_fs_locations, + fattr))) != 0) + goto xdr_error; if ((status = decode_attr_mode(xdr, bitmap, &fattr->mode)) != 0) goto xdr_error; fattr->mode |= fmode; @@ -2886,6 +3065,10 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, cons goto xdr_error; if ((status = decode_attr_time_modify(xdr, bitmap, &fattr->mtime)) != 0) goto xdr_error; + if ((status = decode_attr_mounted_on_fileid(xdr, bitmap, &fileid)) != 0) + goto xdr_error; + if (fattr->fileid == 0 && fileid != 0) + fattr->fileid = fileid; if ((status = verify_attr_len(xdr, savep, attrlen)) == 0) fattr->valid = NFS_ATTR_FATTR | NFS_ATTR_FATTR_V3 | NFS_ATTR_FATTR_V4; xdr_error: @@ -3350,8 +3533,7 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, attrlen, recvd); return -EINVAL; } - if (attrlen <= *acl_len) - xdr_read_pages(xdr, attrlen); + xdr_read_pages(xdr, attrlen); *acl_len = attrlen; } else status = -EOPNOTSUPP; @@ -4211,6 +4393,29 @@ out: return status; } +/* + * FS_LOCATIONS request + */ +static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req, uint32_t *p, struct nfs4_fs_locations *res) +{ + struct xdr_stream xdr; + struct compound_hdr hdr; + int status; + + xdr_init_decode(&xdr, &req->rq_rcv_buf, p); + status = decode_compound_hdr(&xdr, &hdr); + if (status != 0) + goto out; + if ((status = decode_putfh(&xdr)) != 0) + goto out; + if ((status = decode_lookup(&xdr)) != 0) + goto out; + xdr_enter_page(&xdr, PAGE_SIZE); + status = decode_getfattr(&xdr, &res->fattr, res->server); +out: + return status; +} + uint32_t *nfs4_decode_dirent(uint32_t *p, struct nfs_entry *entry, int plus) { uint32_t bitmap[2] = {0}; @@ -4382,6 +4587,7 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(DELEGRETURN, enc_delegreturn, dec_delegreturn), PROC(GETACL, enc_getacl, dec_getacl), PROC(SETACL, enc_setacl, dec_setacl), + PROC(FS_LOCATIONS, enc_fs_locations, dec_fs_locations), }; struct rpc_version nfs_version4 = { diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 106aca3..ef94296 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -325,6 +325,7 @@ out: /** * nfs_scan_list - Scan a list for matching requests + * @nfsi: NFS inode * @head: One of the NFS inode request lists * @dst: Destination list * @idx_start: lower bound of page->index to scan @@ -336,14 +337,15 @@ out: * The requests are *not* checked to ensure that they form a contiguous set. * You must be holding the inode's req_lock when calling this function */ -int -nfs_scan_list(struct list_head *head, struct list_head *dst, - unsigned long idx_start, unsigned int npages) +int nfs_scan_list(struct nfs_inode *nfsi, struct list_head *head, + struct list_head *dst, unsigned long idx_start, + unsigned int npages) { - struct list_head *pos, *tmp; - struct nfs_page *req; - unsigned long idx_end; - int res; + struct nfs_page *pgvec[NFS_SCAN_MAXENTRIES]; + struct nfs_page *req; + unsigned long idx_end; + int found, i; + int res; res = 0; if (npages == 0) @@ -351,25 +353,32 @@ nfs_scan_list(struct list_head *head, struct list_head *dst, else idx_end = idx_start + npages - 1; - list_for_each_safe(pos, tmp, head) { - - req = nfs_list_entry(pos); - - if (req->wb_index < idx_start) - continue; - if (req->wb_index > idx_end) + for (;;) { + found = radix_tree_gang_lookup(&nfsi->nfs_page_tree, + (void **)&pgvec[0], idx_start, + NFS_SCAN_MAXENTRIES); + if (found <= 0) break; + for (i = 0; i < found; i++) { + req = pgvec[i]; + if (req->wb_index > idx_end) + goto out; + idx_start = req->wb_index + 1; + if (req->wb_list_head != head) + continue; + if (nfs_set_page_writeback_locked(req)) { + nfs_list_remove_request(req); + nfs_list_add_request(req, dst); + res++; + } + } - if (!nfs_set_page_writeback_locked(req)) - continue; - nfs_list_remove_request(req); - nfs_list_add_request(req, dst); - res++; } +out: return res; } -int nfs_init_nfspagecache(void) +int __init nfs_init_nfspagecache(void) { nfs_page_cachep = kmem_cache_create("nfs_page", sizeof(struct nfs_page), @@ -381,7 +390,7 @@ int nfs_init_nfspagecache(void) return 0; } -void nfs_destroy_nfspagecache(void) +void __exit nfs_destroy_nfspagecache(void) { if (kmem_cache_destroy(nfs_page_cachep)) printk(KERN_INFO "nfs_page: not all structures were freed\n"); diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 9dd85ca..b3899ea 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -44,11 +44,10 @@ #include <linux/nfs_page.h> #include <linux/lockd/bind.h> #include <linux/smp_lock.h> +#include "internal.h" #define NFSDBG_FACILITY NFSDBG_PROC -extern struct rpc_procinfo nfs_procedures[]; - /* * Bare-bones access to getattr: this is for nfs_read_super. */ @@ -611,8 +610,6 @@ nfs_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, return 0; } -extern u32 * nfs_decode_dirent(u32 *, struct nfs_entry *, int); - static int nfs_read_done(struct rpc_task *task, struct nfs_read_data *data) { if (task->tk_status >= 0) { diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 624ca71..41c2ffe 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -51,14 +51,11 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) if (p) { memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&p->pages); - if (pagecount < NFS_PAGEVEC_SIZE) - p->pagevec = &p->page_array[0]; + if (pagecount <= ARRAY_SIZE(p->page_array)) + p->pagevec = p->page_array; else { - size_t size = ++pagecount * sizeof(struct page *); - p->pagevec = kmalloc(size, GFP_NOFS); - if (p->pagevec) { - memset(p->pagevec, 0, size); - } else { + p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS); + if (!p->pagevec) { mempool_free(p, nfs_rdata_mempool); p = NULL; } @@ -104,6 +101,28 @@ int nfs_return_empty_page(struct page *page) return 0; } +static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data) +{ + unsigned int remainder = data->args.count - data->res.count; + unsigned int base = data->args.pgbase + data->res.count; + unsigned int pglen; + struct page **pages; + + if (data->res.eof == 0 || remainder == 0) + return; + /* + * Note: "remainder" can never be negative, since we check for + * this in the XDR code. + */ + pages = &data->args.pages[base >> PAGE_CACHE_SHIFT]; + base &= ~PAGE_CACHE_MASK; + pglen = PAGE_CACHE_SIZE - base; + if (pglen < remainder) + memclear_highpage_flush(*pages, base, pglen); + else + memclear_highpage_flush(*pages, base, remainder); +} + /* * Read a page synchronously. */ @@ -177,11 +196,9 @@ static int nfs_readpage_sync(struct nfs_open_context *ctx, struct inode *inode, NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATIME; spin_unlock(&inode->i_lock); - if (count) - memclear_highpage_flush(page, rdata->args.pgbase, count); - SetPageUptodate(page); - if (PageError(page)) - ClearPageError(page); + nfs_readpage_truncate_uninitialised_page(rdata); + if (rdata->res.eof || rdata->res.count == rdata->args.count) + SetPageUptodate(page); result = 0; io_error: @@ -436,20 +453,12 @@ static void nfs_readpage_result_partial(struct rpc_task *task, void *calldata) struct nfs_page *req = data->req; struct page *page = req->wb_page; + if (likely(task->tk_status >= 0)) + nfs_readpage_truncate_uninitialised_page(data); + else + SetPageError(page); if (nfs_readpage_result(task, data) != 0) return; - if (task->tk_status >= 0) { - unsigned int request = data->args.count; - unsigned int result = data->res.count; - - if (result < request) { - memclear_highpage_flush(page, - data->args.pgbase + result, - request - result); - } - } else - SetPageError(page); - if (atomic_dec_and_test(&req->wb_complete)) { if (!PageError(page)) SetPageUptodate(page); @@ -462,6 +471,40 @@ static const struct rpc_call_ops nfs_read_partial_ops = { .rpc_release = nfs_readdata_release, }; +static void nfs_readpage_set_pages_uptodate(struct nfs_read_data *data) +{ + unsigned int count = data->res.count; + unsigned int base = data->args.pgbase; + struct page **pages; + + if (unlikely(count == 0)) + return; + pages = &data->args.pages[base >> PAGE_CACHE_SHIFT]; + base &= ~PAGE_CACHE_MASK; + count += base; + for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++) + SetPageUptodate(*pages); + /* + * Was this an eof or a short read? If the latter, don't mark the page + * as uptodate yet. + */ + if (count > 0 && (data->res.eof || data->args.count == data->res.count)) + SetPageUptodate(*pages); +} + +static void nfs_readpage_set_pages_error(struct nfs_read_data *data) +{ + unsigned int count = data->args.count; + unsigned int base = data->args.pgbase; + struct page **pages; + + pages = &data->args.pages[base >> PAGE_CACHE_SHIFT]; + base &= ~PAGE_CACHE_MASK; + count += base; + for (;count >= PAGE_CACHE_SIZE; count -= PAGE_CACHE_SIZE, pages++) + SetPageError(*pages); +} + /* * This is the callback from RPC telling us whether a reply was * received or some error occurred (timeout or socket shutdown). @@ -469,27 +512,24 @@ static const struct rpc_call_ops nfs_read_partial_ops = { static void nfs_readpage_result_full(struct rpc_task *task, void *calldata) { struct nfs_read_data *data = calldata; - unsigned int count = data->res.count; + /* + * Note: nfs_readpage_result may change the values of + * data->args. In the multi-page case, we therefore need + * to ensure that we call the next nfs_readpage_set_page_uptodate() + * first in the multi-page case. + */ + if (likely(task->tk_status >= 0)) { + nfs_readpage_truncate_uninitialised_page(data); + nfs_readpage_set_pages_uptodate(data); + } else + nfs_readpage_set_pages_error(data); if (nfs_readpage_result(task, data) != 0) return; while (!list_empty(&data->pages)) { struct nfs_page *req = nfs_list_entry(data->pages.next); - struct page *page = req->wb_page; - nfs_list_remove_request(req); - if (task->tk_status >= 0) { - if (count < PAGE_CACHE_SIZE) { - if (count < req->wb_bytes) - memclear_highpage_flush(page, - req->wb_pgbase + count, - req->wb_bytes - count); - count = 0; - } else - count -= PAGE_CACHE_SIZE; - SetPageUptodate(page); - } else - SetPageError(page); + nfs_list_remove_request(req); nfs_readpage_release(req); } } @@ -654,7 +694,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, return ret; } -int nfs_init_readpagecache(void) +int __init nfs_init_readpagecache(void) { nfs_rdata_cachep = kmem_cache_create("nfs_read_data", sizeof(struct nfs_read_data), @@ -671,7 +711,7 @@ int nfs_init_readpagecache(void) return 0; } -void nfs_destroy_readpagecache(void) +void __exit nfs_destroy_readpagecache(void) { mempool_destroy(nfs_rdata_mempool); if (kmem_cache_destroy(nfs_rdata_cachep)) diff --git a/fs/nfs/super.c b/fs/nfs/super.c new file mode 100644 index 0000000..30f939b --- /dev/null +++ b/fs/nfs/super.c @@ -0,0 +1,1497 @@ +/* + * linux/fs/nfs/super.c + * + * Copyright (C) 1992 Rick Sladkey + * + * nfs superblock handling functions + * + * Modularised by Alan Cox <Alan.Cox@linux.org>, while hacking some + * experimental NFS changes. Modularisation taken straight from SYS5 fs. + * + * Change to nfs_read_super() to permit NFS mounts to multi-homed hosts. + * J.S.Peatfield@damtp.cam.ac.uk + * + * Split from inode.c by David Howells <dhowells@redhat.com> + * + */ + +#include <linux/config.h> +#include <linux/module.h> +#include <linux/init.h> + +#include <linux/time.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/stat.h> +#include <linux/errno.h> +#include <linux/unistd.h> +#include <linux/sunrpc/clnt.h> +#include <linux/sunrpc/stats.h> +#include <linux/sunrpc/metrics.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include <linux/nfs4_mount.h> +#include <linux/lockd/bind.h> +#include <linux/smp_lock.h> +#include <linux/seq_file.h> +#include <linux/mount.h> +#include <linux/nfs_idmap.h> +#include <linux/vfs.h> +#include <linux/inet.h> +#include <linux/nfs_xdr.h> + +#include <asm/system.h> +#include <asm/uaccess.h> + +#include "nfs4_fs.h" +#include "callback.h" +#include "delegation.h" +#include "iostat.h" +#include "internal.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +/* Maximum number of readahead requests + * FIXME: this should really be a sysctl so that users may tune it to suit + * their needs. People that do NFS over a slow network, might for + * instance want to reduce it to something closer to 1 for improved + * interactive response. + */ +#define NFS_MAX_READAHEAD (RPC_DEF_SLOT_TABLE - 1) + +/* + * RPC cruft for NFS + */ +static struct rpc_version * nfs_version[] = { + NULL, + NULL, + &nfs_version2, +#if defined(CONFIG_NFS_V3) + &nfs_version3, +#elif defined(CONFIG_NFS_V4) + NULL, +#endif +#if defined(CONFIG_NFS_V4) + &nfs_version4, +#endif +}; + +static struct rpc_program nfs_program = { + .name = "nfs", + .number = NFS_PROGRAM, + .nrvers = ARRAY_SIZE(nfs_version), + .version = nfs_version, + .stats = &nfs_rpcstat, + .pipe_dir_name = "/nfs", +}; + +struct rpc_stat nfs_rpcstat = { + .program = &nfs_program +}; + + +#ifdef CONFIG_NFS_V3_ACL +static struct rpc_stat nfsacl_rpcstat = { &nfsacl_program }; +static struct rpc_version * nfsacl_version[] = { + [3] = &nfsacl_version3, +}; + +struct rpc_program nfsacl_program = { + .name = "nfsacl", + .number = NFS_ACL_PROGRAM, + .nrvers = ARRAY_SIZE(nfsacl_version), + .version = nfsacl_version, + .stats = &nfsacl_rpcstat, +}; +#endif /* CONFIG_NFS_V3_ACL */ + +static void nfs_umount_begin(struct vfsmount *, int); +static int nfs_statfs(struct super_block *, struct kstatfs *); +static int nfs_show_options(struct seq_file *, struct vfsmount *); +static int nfs_show_stats(struct seq_file *, struct vfsmount *); +static struct super_block *nfs_get_sb(struct file_system_type *, int, const char *, void *); +static struct super_block *nfs_clone_nfs_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); +static void nfs_kill_super(struct super_block *); + +static struct file_system_type nfs_fs_type = { + .owner = THIS_MODULE, + .name = "nfs", + .get_sb = nfs_get_sb, + .kill_sb = nfs_kill_super, + .fs_flags = FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, +}; + +struct file_system_type clone_nfs_fs_type = { + .owner = THIS_MODULE, + .name = "nfs", + .get_sb = nfs_clone_nfs_sb, + .kill_sb = nfs_kill_super, + .fs_flags = FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, +}; + +static struct super_operations nfs_sops = { + .alloc_inode = nfs_alloc_inode, + .destroy_inode = nfs_destroy_inode, + .write_inode = nfs_write_inode, + .statfs = nfs_statfs, + .clear_inode = nfs_clear_inode, + .umount_begin = nfs_umount_begin, + .show_options = nfs_show_options, + .show_stats = nfs_show_stats, +}; + +#ifdef CONFIG_NFS_V4 +static struct super_block *nfs4_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); +static struct super_block *nfs_clone_nfs4_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); +static struct super_block *nfs_referral_nfs4_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); +static void nfs4_kill_super(struct super_block *sb); + +static struct file_system_type nfs4_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .get_sb = nfs4_get_sb, + .kill_sb = nfs4_kill_super, + .fs_flags = FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, +}; + +struct file_system_type clone_nfs4_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .get_sb = nfs_clone_nfs4_sb, + .kill_sb = nfs4_kill_super, + .fs_flags = FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, +}; + +struct file_system_type nfs_referral_nfs4_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .get_sb = nfs_referral_nfs4_sb, + .kill_sb = nfs4_kill_super, + .fs_flags = FS_ODD_RENAME|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, +}; + +static struct super_operations nfs4_sops = { + .alloc_inode = nfs_alloc_inode, + .destroy_inode = nfs_destroy_inode, + .write_inode = nfs_write_inode, + .statfs = nfs_statfs, + .clear_inode = nfs4_clear_inode, + .umount_begin = nfs_umount_begin, + .show_options = nfs_show_options, + .show_stats = nfs_show_stats, +}; +#endif + +static const int nfs_set_port_min = 0; +static const int nfs_set_port_max = 65535; + +static int param_set_port(const char *val, struct kernel_param *kp) +{ + char *endp; + int num = simple_strtol(val, &endp, 0); + if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max) + return -EINVAL; + *((int *)kp->arg) = num; + return 0; +} + +module_param_call(callback_tcpport, param_set_port, param_get_int, + &nfs_callback_set_tcpport, 0644); + +static int param_set_idmap_timeout(const char *val, struct kernel_param *kp) +{ + char *endp; + int num = simple_strtol(val, &endp, 0); + int jif = num * HZ; + if (endp == val || *endp || num < 0 || jif < num) + return -EINVAL; + *((int *)kp->arg) = jif; + return 0; +} + +module_param_call(idmap_cache_timeout, param_set_idmap_timeout, param_get_int, + &nfs_idmap_cache_timeout, 0644); + +/* + * Register the NFS filesystems + */ +int __init register_nfs_fs(void) +{ + int ret; + + ret = register_filesystem(&nfs_fs_type); + if (ret < 0) + goto error_0; + +#ifdef CONFIG_NFS_V4 + ret = nfs_register_sysctl(); + if (ret < 0) + goto error_1; + ret = register_filesystem(&nfs4_fs_type); + if (ret < 0) + goto error_2; +#endif + return 0; + +#ifdef CONFIG_NFS_V4 +error_2: + nfs_unregister_sysctl(); +error_1: + unregister_filesystem(&nfs_fs_type); +#endif +error_0: + return ret; +} + +/* + * Unregister the NFS filesystems + */ +void __exit unregister_nfs_fs(void) +{ +#ifdef CONFIG_NFS_V4 + unregister_filesystem(&nfs4_fs_type); + nfs_unregister_sysctl(); +#endif + unregister_filesystem(&nfs_fs_type); +} + +/* + * Deliver file system statistics to userspace + */ +static int nfs_statfs(struct super_block *sb, struct kstatfs *buf) +{ + struct nfs_server *server = NFS_SB(sb); + unsigned char blockbits; + unsigned long blockres; + struct nfs_fh *rootfh = NFS_FH(sb->s_root->d_inode); + struct nfs_fattr fattr; + struct nfs_fsstat res = { + .fattr = &fattr, + }; + int error; + + lock_kernel(); + + error = server->rpc_ops->statfs(server, rootfh, &res); + buf->f_type = NFS_SUPER_MAGIC; + if (error < 0) + goto out_err; + + /* + * Current versions of glibc do not correctly handle the + * case where f_frsize != f_bsize. Eventually we want to + * report the value of wtmult in this field. + */ + buf->f_frsize = sb->s_blocksize; + + /* + * On most *nix systems, f_blocks, f_bfree, and f_bavail + * are reported in units of f_frsize. Linux hasn't had + * an f_frsize field in its statfs struct until recently, + * thus historically Linux's sys_statfs reports these + * fields in units of f_bsize. + */ + buf->f_bsize = sb->s_blocksize; + blockbits = sb->s_blocksize_bits; + blockres = (1 << blockbits) - 1; + buf->f_blocks = (res.tbytes + blockres) >> blockbits; + buf->f_bfree = (res.fbytes + blockres) >> blockbits; + buf->f_bavail = (res.abytes + blockres) >> blockbits; + + buf->f_files = res.tfiles; + buf->f_ffree = res.afiles; + + buf->f_namelen = server->namelen; + out: + unlock_kernel(); + return 0; + + out_err: + dprintk("%s: statfs error = %d\n", __FUNCTION__, -error); + buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1; + goto out; + +} + +static const char *nfs_pseudoflavour_to_name(rpc_authflavor_t flavour) +{ + static struct { + rpc_authflavor_t flavour; + const char *str; + } sec_flavours[] = { + { RPC_AUTH_NULL, "null" }, + { RPC_AUTH_UNIX, "sys" }, + { RPC_AUTH_GSS_KRB5, "krb5" }, + { RPC_AUTH_GSS_KRB5I, "krb5i" }, + { RPC_AUTH_GSS_KRB5P, "krb5p" }, + { RPC_AUTH_GSS_LKEY, "lkey" }, + { RPC_AUTH_GSS_LKEYI, "lkeyi" }, + { RPC_AUTH_GSS_LKEYP, "lkeyp" }, + { RPC_AUTH_GSS_SPKM, "spkm" }, + { RPC_AUTH_GSS_SPKMI, "spkmi" }, + { RPC_AUTH_GSS_SPKMP, "spkmp" }, + { -1, "unknown" } + }; + int i; + + for (i=0; sec_flavours[i].flavour != -1; i++) { + if (sec_flavours[i].flavour == flavour) + break; + } + return sec_flavours[i].str; +} + +/* + * Describe the mount options in force on this server representation + */ +static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, int showdefaults) +{ + static struct proc_nfs_info { + int flag; + char *str; + char *nostr; + } nfs_info[] = { + { NFS_MOUNT_SOFT, ",soft", ",hard" }, + { NFS_MOUNT_INTR, ",intr", "" }, + { NFS_MOUNT_NOCTO, ",nocto", "" }, + { NFS_MOUNT_NOAC, ",noac", "" }, + { NFS_MOUNT_NONLM, ",nolock", "" }, + { NFS_MOUNT_NOACL, ",noacl", "" }, + { 0, NULL, NULL } + }; + struct proc_nfs_info *nfs_infop; + char buf[12]; + char *proto; + + seq_printf(m, ",vers=%d", nfss->rpc_ops->version); + seq_printf(m, ",rsize=%d", nfss->rsize); + seq_printf(m, ",wsize=%d", nfss->wsize); + if (nfss->acregmin != 3*HZ || showdefaults) + seq_printf(m, ",acregmin=%d", nfss->acregmin/HZ); + if (nfss->acregmax != 60*HZ || showdefaults) + seq_printf(m, ",acregmax=%d", nfss->acregmax/HZ); + if (nfss->acdirmin != 30*HZ || showdefaults) + seq_printf(m, ",acdirmin=%d", nfss->acdirmin/HZ); + if (nfss->acdirmax != 60*HZ || showdefaults) + seq_printf(m, ",acdirmax=%d", nfss->acdirmax/HZ); + for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) { + if (nfss->flags & nfs_infop->flag) + seq_puts(m, nfs_infop->str); + else + seq_puts(m, nfs_infop->nostr); + } + switch (nfss->client->cl_xprt->prot) { + case IPPROTO_TCP: + proto = "tcp"; + break; + case IPPROTO_UDP: + proto = "udp"; + break; + default: + snprintf(buf, sizeof(buf), "%u", nfss->client->cl_xprt->prot); + proto = buf; + } + seq_printf(m, ",proto=%s", proto); + seq_printf(m, ",timeo=%lu", 10U * nfss->retrans_timeo / HZ); + seq_printf(m, ",retrans=%u", nfss->retrans_count); + seq_printf(m, ",sec=%s", nfs_pseudoflavour_to_name(nfss->client->cl_auth->au_flavor)); +} + +/* + * Describe the mount options on this VFS mountpoint + */ +static int nfs_show_options(struct seq_file *m, struct vfsmount *mnt) +{ + struct nfs_server *nfss = NFS_SB(mnt->mnt_sb); + + nfs_show_mount_options(m, nfss, 0); + + seq_puts(m, ",addr="); + seq_escape(m, nfss->hostname, " \t\n\\"); + + return 0; +} + +/* + * Present statistical information for this VFS mountpoint + */ +static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt) +{ + int i, cpu; + struct nfs_server *nfss = NFS_SB(mnt->mnt_sb); + struct rpc_auth *auth = nfss->client->cl_auth; + struct nfs_iostats totals = { }; + + seq_printf(m, "statvers=%s", NFS_IOSTAT_VERS); + + /* + * Display all mount option settings + */ + seq_printf(m, "\n\topts:\t"); + seq_puts(m, mnt->mnt_sb->s_flags & MS_RDONLY ? "ro" : "rw"); + seq_puts(m, mnt->mnt_sb->s_flags & MS_SYNCHRONOUS ? ",sync" : ""); + seq_puts(m, mnt->mnt_sb->s_flags & MS_NOATIME ? ",noatime" : ""); + seq_puts(m, mnt->mnt_sb->s_flags & MS_NODIRATIME ? ",nodiratime" : ""); + nfs_show_mount_options(m, nfss, 1); + + seq_printf(m, "\n\tage:\t%lu", (jiffies - nfss->mount_time) / HZ); + + seq_printf(m, "\n\tcaps:\t"); + seq_printf(m, "caps=0x%x", nfss->caps); + seq_printf(m, ",wtmult=%d", nfss->wtmult); + seq_printf(m, ",dtsize=%d", nfss->dtsize); + seq_printf(m, ",bsize=%d", nfss->bsize); + seq_printf(m, ",namelen=%d", nfss->namelen); + +#ifdef CONFIG_NFS_V4 + if (nfss->rpc_ops->version == 4) { + seq_printf(m, "\n\tnfsv4:\t"); + seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]); + seq_printf(m, ",bm1=0x%x", nfss->attr_bitmask[1]); + seq_printf(m, ",acl=0x%x", nfss->acl_bitmask); + } +#endif + + /* + * Display security flavor in effect for this mount + */ + seq_printf(m, "\n\tsec:\tflavor=%d", auth->au_ops->au_flavor); + if (auth->au_flavor) + seq_printf(m, ",pseudoflavor=%d", auth->au_flavor); + + /* + * Display superblock I/O counters + */ + for_each_possible_cpu(cpu) { + struct nfs_iostats *stats; + + preempt_disable(); + stats = per_cpu_ptr(nfss->io_stats, cpu); + + for (i = 0; i < __NFSIOS_COUNTSMAX; i++) + totals.events[i] += stats->events[i]; + for (i = 0; i < __NFSIOS_BYTESMAX; i++) + totals.bytes[i] += stats->bytes[i]; + + preempt_enable(); + } + + seq_printf(m, "\n\tevents:\t"); + for (i = 0; i < __NFSIOS_COUNTSMAX; i++) + seq_printf(m, "%lu ", totals.events[i]); + seq_printf(m, "\n\tbytes:\t"); + for (i = 0; i < __NFSIOS_BYTESMAX; i++) + seq_printf(m, "%Lu ", totals.bytes[i]); + seq_printf(m, "\n"); + + rpc_print_iostats(m, nfss->client); + + return 0; +} + +/* + * Begin unmount by attempting to remove all automounted mountpoints we added + * in response to traversals + */ +static void nfs_umount_begin(struct vfsmount *vfsmnt, int flags) +{ + struct nfs_server *server; + struct rpc_clnt *rpc; + + shrink_submounts(vfsmnt, &nfs_automount_list); + if (!(flags & MNT_FORCE)) + return; + /* -EIO all pending I/O */ + server = NFS_SB(vfsmnt->mnt_sb); + rpc = server->client; + if (!IS_ERR(rpc)) + rpc_killall_tasks(rpc); + rpc = server->client_acl; + if (!IS_ERR(rpc)) + rpc_killall_tasks(rpc); +} + +/* + * Obtain the root inode of the file system. + */ +static struct inode * +nfs_get_root(struct super_block *sb, struct nfs_fh *rootfh, struct nfs_fsinfo *fsinfo) +{ + struct nfs_server *server = NFS_SB(sb); + int error; + + error = server->rpc_ops->getroot(server, rootfh, fsinfo); + if (error < 0) { + dprintk("nfs_get_root: getattr error = %d\n", -error); + return ERR_PTR(error); + } + + server->fsid = fsinfo->fattr->fsid; + return nfs_fhget(sb, rootfh, fsinfo->fattr); +} + +/* + * Do NFS version-independent mount processing, and sanity checking + */ +static int +nfs_sb_init(struct super_block *sb, rpc_authflavor_t authflavor) +{ + struct nfs_server *server; + struct inode *root_inode; + struct nfs_fattr fattr; + struct nfs_fsinfo fsinfo = { + .fattr = &fattr, + }; + struct nfs_pathconf pathinfo = { + .fattr = &fattr, + }; + int no_root_error = 0; + unsigned long max_rpc_payload; + + /* We probably want something more informative here */ + snprintf(sb->s_id, sizeof(sb->s_id), "%x:%x", MAJOR(sb->s_dev), MINOR(sb->s_dev)); + + server = NFS_SB(sb); + + sb->s_magic = NFS_SUPER_MAGIC; + + server->io_stats = nfs_alloc_iostats(); + if (server->io_stats == NULL) + return -ENOMEM; + + root_inode = nfs_get_root(sb, &server->fh, &fsinfo); + /* Did getting the root inode fail? */ + if (IS_ERR(root_inode)) { + no_root_error = PTR_ERR(root_inode); + goto out_no_root; + } + sb->s_root = d_alloc_root(root_inode); + if (!sb->s_root) { + no_root_error = -ENOMEM; + goto out_no_root; + } + sb->s_root->d_op = server->rpc_ops->dentry_ops; + + /* mount time stamp, in seconds */ + server->mount_time = jiffies; + + /* Get some general file system info */ + if (server->namelen == 0 && + server->rpc_ops->pathconf(server, &server->fh, &pathinfo) >= 0) + server->namelen = pathinfo.max_namelen; + /* Work out a lot of parameters */ + if (server->rsize == 0) + server->rsize = nfs_block_size(fsinfo.rtpref, NULL); + if (server->wsize == 0) + server->wsize = nfs_block_size(fsinfo.wtpref, NULL); + + if (fsinfo.rtmax >= 512 && server->rsize > fsinfo.rtmax) + server->rsize = nfs_block_size(fsinfo.rtmax, NULL); + if (fsinfo.wtmax >= 512 && server->wsize > fsinfo.wtmax) + server->wsize = nfs_block_size(fsinfo.wtmax, NULL); + + max_rpc_payload = nfs_block_size(rpc_max_payload(server->client), NULL); + if (server->rsize > max_rpc_payload) + server->rsize = max_rpc_payload; + if (server->rsize > NFS_MAX_FILE_IO_SIZE) + server->rsize = NFS_MAX_FILE_IO_SIZE; + server->rpages = (server->rsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + + if (server->wsize > max_rpc_payload) + server->wsize = max_rpc_payload; + if (server->wsize > NFS_MAX_FILE_IO_SIZE) + server->wsize = NFS_MAX_FILE_IO_SIZE; + server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + + if (sb->s_blocksize == 0) + sb->s_blocksize = nfs_block_bits(server->wsize, + &sb->s_blocksize_bits); + server->wtmult = nfs_block_bits(fsinfo.wtmult, NULL); + + server->dtsize = nfs_block_size(fsinfo.dtpref, NULL); + if (server->dtsize > PAGE_CACHE_SIZE) + server->dtsize = PAGE_CACHE_SIZE; + if (server->dtsize > server->rsize) + server->dtsize = server->rsize; + + if (server->flags & NFS_MOUNT_NOAC) { + server->acregmin = server->acregmax = 0; + server->acdirmin = server->acdirmax = 0; + sb->s_flags |= MS_SYNCHRONOUS; + } + server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD; + + nfs_super_set_maxbytes(sb, fsinfo.maxfilesize); + + server->client->cl_intr = (server->flags & NFS_MOUNT_INTR) ? 1 : 0; + server->client->cl_softrtry = (server->flags & NFS_MOUNT_SOFT) ? 1 : 0; + + /* We're airborne Set socket buffersize */ + rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100); + return 0; + /* Yargs. It didn't work out. */ +out_no_root: + dprintk("nfs_sb_init: get root inode failed: errno %d\n", -no_root_error); + if (!IS_ERR(root_inode)) + iput(root_inode); + return no_root_error; +} + +/* + * Initialise the timeout values for a connection + */ +static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, unsigned int timeo, unsigned int retrans) +{ + to->to_initval = timeo * HZ / 10; + to->to_retries = retrans; + if (!to->to_retries) + to->to_retries = 2; + + switch (proto) { + case IPPROTO_TCP: + if (!to->to_initval) + to->to_initval = 60 * HZ; + if (to->to_initval > NFS_MAX_TCP_TIMEOUT) + to->to_initval = NFS_MAX_TCP_TIMEOUT; + to->to_increment = to->to_initval; + to->to_maxval = to->to_initval + (to->to_increment * to->to_retries); + to->to_exponential = 0; + break; + case IPPROTO_UDP: + default: + if (!to->to_initval) + to->to_initval = 11 * HZ / 10; + if (to->to_initval > NFS_MAX_UDP_TIMEOUT) + to->to_initval = NFS_MAX_UDP_TIMEOUT; + to->to_maxval = NFS_MAX_UDP_TIMEOUT; + to->to_exponential = 1; + break; + } +} + +/* + * Create an RPC client handle. + */ +static struct rpc_clnt * +nfs_create_client(struct nfs_server *server, const struct nfs_mount_data *data) +{ + struct rpc_timeout timeparms; + struct rpc_xprt *xprt = NULL; + struct rpc_clnt *clnt = NULL; + int proto = (data->flags & NFS_MOUNT_TCP) ? IPPROTO_TCP : IPPROTO_UDP; + + nfs_init_timeout_values(&timeparms, proto, data->timeo, data->retrans); + + server->retrans_timeo = timeparms.to_initval; + server->retrans_count = timeparms.to_retries; + + /* create transport and client */ + xprt = xprt_create_proto(proto, &server->addr, &timeparms); + if (IS_ERR(xprt)) { + dprintk("%s: cannot create RPC transport. Error = %ld\n", + __FUNCTION__, PTR_ERR(xprt)); + return (struct rpc_clnt *)xprt; + } + clnt = rpc_create_client(xprt, server->hostname, &nfs_program, + server->rpc_ops->version, data->pseudoflavor); + if (IS_ERR(clnt)) { + dprintk("%s: cannot create RPC client. Error = %ld\n", + __FUNCTION__, PTR_ERR(xprt)); + goto out_fail; + } + + clnt->cl_intr = 1; + clnt->cl_softrtry = 1; + + return clnt; + +out_fail: + return clnt; +} + +/* + * Clone a server record + */ +static struct nfs_server *nfs_clone_server(struct super_block *sb, struct nfs_clone_mount *data) +{ + struct nfs_server *server = NFS_SB(sb); + struct nfs_server *parent = NFS_SB(data->sb); + struct inode *root_inode; + struct nfs_fsinfo fsinfo; + void *err = ERR_PTR(-ENOMEM); + + sb->s_op = data->sb->s_op; + sb->s_blocksize = data->sb->s_blocksize; + sb->s_blocksize_bits = data->sb->s_blocksize_bits; + sb->s_maxbytes = data->sb->s_maxbytes; + + server->client_sys = server->client_acl = ERR_PTR(-EINVAL); + server->io_stats = nfs_alloc_iostats(); + if (server->io_stats == NULL) + goto out; + + server->client = rpc_clone_client(parent->client); + if (IS_ERR((err = server->client))) + goto out; + + if (!IS_ERR(parent->client_sys)) { + server->client_sys = rpc_clone_client(parent->client_sys); + if (IS_ERR((err = server->client_sys))) + goto out; + } + if (!IS_ERR(parent->client_acl)) { + server->client_acl = rpc_clone_client(parent->client_acl); + if (IS_ERR((err = server->client_acl))) + goto out; + } + root_inode = nfs_fhget(sb, data->fh, data->fattr); + if (!root_inode) + goto out; + sb->s_root = d_alloc_root(root_inode); + if (!sb->s_root) + goto out_put_root; + fsinfo.fattr = data->fattr; + if (NFS_PROTO(root_inode)->fsinfo(server, data->fh, &fsinfo) == 0) + nfs_super_set_maxbytes(sb, fsinfo.maxfilesize); + sb->s_root->d_op = server->rpc_ops->dentry_ops; + sb->s_flags |= MS_ACTIVE; + return server; +out_put_root: + iput(root_inode); +out: + return err; +} + +/* + * Copy an existing superblock and attach revised data + */ +static struct super_block *nfs_clone_generic_sb(struct nfs_clone_mount *data, + struct super_block *(*fill_sb)(struct nfs_server *, struct nfs_clone_mount *), + struct nfs_server *(*fill_server)(struct super_block *, struct nfs_clone_mount *)) +{ + struct nfs_server *server; + struct nfs_server *parent = NFS_SB(data->sb); + struct super_block *sb = ERR_PTR(-EINVAL); + void *err = ERR_PTR(-ENOMEM); + char *hostname; + int len; + + server = kmalloc(sizeof(struct nfs_server), GFP_KERNEL); + if (server == NULL) + goto out_err; + memcpy(server, parent, sizeof(*server)); + hostname = (data->hostname != NULL) ? data->hostname : parent->hostname; + len = strlen(hostname) + 1; + server->hostname = kmalloc(len, GFP_KERNEL); + if (server->hostname == NULL) + goto free_server; + memcpy(server->hostname, hostname, len); + if (rpciod_up() != 0) + goto free_hostname; + + sb = fill_sb(server, data); + if (IS_ERR((err = sb)) || sb->s_root) + goto kill_rpciod; + + server = fill_server(sb, data); + if (IS_ERR((err = server))) + goto out_deactivate; + return sb; +out_deactivate: + up_write(&sb->s_umount); + deactivate_super(sb); + return (struct super_block *)err; +kill_rpciod: + rpciod_down(); +free_hostname: + kfree(server->hostname); +free_server: + kfree(server); +out_err: + return (struct super_block *)err; +} + +/* + * Set up an NFS2/3 superblock + * + * The way this works is that the mount process passes a structure + * in the data argument which contains the server's IP address + * and the root file handle obtained from the server's mount + * daemon. We stash these away in the private superblock fields. + */ +static int +nfs_fill_super(struct super_block *sb, struct nfs_mount_data *data, int silent) +{ + struct nfs_server *server; + rpc_authflavor_t authflavor; + + server = NFS_SB(sb); + sb->s_blocksize_bits = 0; + sb->s_blocksize = 0; + if (data->bsize) + sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits); + if (data->rsize) + server->rsize = nfs_block_size(data->rsize, NULL); + if (data->wsize) + server->wsize = nfs_block_size(data->wsize, NULL); + server->flags = data->flags & NFS_MOUNT_FLAGMASK; + + server->acregmin = data->acregmin*HZ; + server->acregmax = data->acregmax*HZ; + server->acdirmin = data->acdirmin*HZ; + server->acdirmax = data->acdirmax*HZ; + + /* Start lockd here, before we might error out */ + if (!(server->flags & NFS_MOUNT_NONLM)) + lockd_up(); + + server->namelen = data->namlen; + server->hostname = kmalloc(strlen(data->hostname) + 1, GFP_KERNEL); + if (!server->hostname) + return -ENOMEM; + strcpy(server->hostname, data->hostname); + + /* Check NFS protocol revision and initialize RPC op vector + * and file handle pool. */ +#ifdef CONFIG_NFS_V3 + if (server->flags & NFS_MOUNT_VER3) { + server->rpc_ops = &nfs_v3_clientops; + server->caps |= NFS_CAP_READDIRPLUS; + } else { + server->rpc_ops = &nfs_v2_clientops; + } +#else + server->rpc_ops = &nfs_v2_clientops; +#endif + + /* Fill in pseudoflavor for mount version < 5 */ + if (!(data->flags & NFS_MOUNT_SECFLAVOUR)) + data->pseudoflavor = RPC_AUTH_UNIX; + authflavor = data->pseudoflavor; /* save for sb_init() */ + /* XXX maybe we want to add a server->pseudoflavor field */ + + /* Create RPC client handles */ + server->client = nfs_create_client(server, data); + if (IS_ERR(server->client)) + return PTR_ERR(server->client); + /* RFC 2623, sec 2.3.2 */ + if (authflavor != RPC_AUTH_UNIX) { + struct rpc_auth *auth; + + server->client_sys = rpc_clone_client(server->client); + if (IS_ERR(server->client_sys)) + return PTR_ERR(server->client_sys); + auth = rpcauth_create(RPC_AUTH_UNIX, server->client_sys); + if (IS_ERR(auth)) + return PTR_ERR(auth); + } else { + atomic_inc(&server->client->cl_count); + server->client_sys = server->client; + } + if (server->flags & NFS_MOUNT_VER3) { +#ifdef CONFIG_NFS_V3_ACL + if (!(server->flags & NFS_MOUNT_NOACL)) { + server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3); + /* No errors! Assume that Sun nfsacls are supported */ + if (!IS_ERR(server->client_acl)) + server->caps |= NFS_CAP_ACLS; + } +#else + server->flags &= ~NFS_MOUNT_NOACL; +#endif /* CONFIG_NFS_V3_ACL */ + /* + * The VFS shouldn't apply the umask to mode bits. We will + * do so ourselves when necessary. + */ + sb->s_flags |= MS_POSIXACL; + if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN) + server->namelen = NFS3_MAXNAMLEN; + sb->s_time_gran = 1; + } else { + if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN) + server->namelen = NFS2_MAXNAMLEN; + } + + sb->s_op = &nfs_sops; + return nfs_sb_init(sb, authflavor); +} + +static int nfs_set_super(struct super_block *s, void *data) +{ + s->s_fs_info = data; + return set_anon_super(s, data); +} + +static int nfs_compare_super(struct super_block *sb, void *data) +{ + struct nfs_server *server = data; + struct nfs_server *old = NFS_SB(sb); + + if (old->addr.sin_addr.s_addr != server->addr.sin_addr.s_addr) + return 0; + if (old->addr.sin_port != server->addr.sin_port) + return 0; + return !nfs_compare_fh(&old->fh, &server->fh); +} + +static struct super_block *nfs_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) +{ + int error; + struct nfs_server *server = NULL; + struct super_block *s; + struct nfs_fh *root; + struct nfs_mount_data *data = raw_data; + + s = ERR_PTR(-EINVAL); + if (data == NULL) { + dprintk("%s: missing data argument\n", __FUNCTION__); + goto out_err; + } + if (data->version <= 0 || data->version > NFS_MOUNT_VERSION) { + dprintk("%s: bad mount version\n", __FUNCTION__); + goto out_err; + } + switch (data->version) { + case 1: + data->namlen = 0; + case 2: + data->bsize = 0; + case 3: + if (data->flags & NFS_MOUNT_VER3) { + dprintk("%s: mount structure version %d does not support NFSv3\n", + __FUNCTION__, + data->version); + goto out_err; + } + data->root.size = NFS2_FHSIZE; + memcpy(data->root.data, data->old_root.data, NFS2_FHSIZE); + case 4: + if (data->flags & NFS_MOUNT_SECFLAVOUR) { + dprintk("%s: mount structure version %d does not support strong security\n", + __FUNCTION__, + data->version); + goto out_err; + } + case 5: + memset(data->context, 0, sizeof(data->context)); + } +#ifndef CONFIG_NFS_V3 + /* If NFSv3 is not compiled in, return -EPROTONOSUPPORT */ + s = ERR_PTR(-EPROTONOSUPPORT); + if (data->flags & NFS_MOUNT_VER3) { + dprintk("%s: NFSv3 not compiled into kernel\n", __FUNCTION__); + goto out_err; + } +#endif /* CONFIG_NFS_V3 */ + + s = ERR_PTR(-ENOMEM); + server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL); + if (!server) + goto out_err; + /* Zero out the NFS state stuff */ + init_nfsv4_state(server); + server->client = server->client_sys = server->client_acl = ERR_PTR(-EINVAL); + + root = &server->fh; + if (data->flags & NFS_MOUNT_VER3) + root->size = data->root.size; + else + root->size = NFS2_FHSIZE; + s = ERR_PTR(-EINVAL); + if (root->size > sizeof(root->data)) { + dprintk("%s: invalid root filehandle\n", __FUNCTION__); + goto out_err; + } + memcpy(root->data, data->root.data, root->size); + + /* We now require that the mount process passes the remote address */ + memcpy(&server->addr, &data->addr, sizeof(server->addr)); + if (server->addr.sin_addr.s_addr == INADDR_ANY) { + dprintk("%s: mount program didn't pass remote address!\n", + __FUNCTION__); + goto out_err; + } + + /* Fire up rpciod if not yet running */ + s = ERR_PTR(rpciod_up()); + if (IS_ERR(s)) { + dprintk("%s: couldn't start rpciod! Error = %ld\n", + __FUNCTION__, PTR_ERR(s)); + goto out_err; + } + + s = sget(fs_type, nfs_compare_super, nfs_set_super, server); + if (IS_ERR(s) || s->s_root) + goto out_rpciod_down; + + s->s_flags = flags; + + error = nfs_fill_super(s, data, flags & MS_SILENT ? 1 : 0); + if (error) { + up_write(&s->s_umount); + deactivate_super(s); + return ERR_PTR(error); + } + s->s_flags |= MS_ACTIVE; + return s; +out_rpciod_down: + rpciod_down(); +out_err: + kfree(server); + return s; +} + +static void nfs_kill_super(struct super_block *s) +{ + struct nfs_server *server = NFS_SB(s); + + kill_anon_super(s); + + if (!IS_ERR(server->client)) + rpc_shutdown_client(server->client); + if (!IS_ERR(server->client_sys)) + rpc_shutdown_client(server->client_sys); + if (!IS_ERR(server->client_acl)) + rpc_shutdown_client(server->client_acl); + + if (!(server->flags & NFS_MOUNT_NONLM)) + lockd_down(); /* release rpc.lockd */ + + rpciod_down(); /* release rpciod */ + + nfs_free_iostats(server->io_stats); + kfree(server->hostname); + kfree(server); + nfs_release_automount_timer(); +} + +static struct super_block *nfs_clone_sb(struct nfs_server *server, struct nfs_clone_mount *data) +{ + struct super_block *sb; + + server->fsid = data->fattr->fsid; + nfs_copy_fh(&server->fh, data->fh); + sb = sget(&nfs_fs_type, nfs_compare_super, nfs_set_super, server); + if (!IS_ERR(sb) && sb->s_root == NULL && !(server->flags & NFS_MOUNT_NONLM)) + lockd_up(); + return sb; +} + +static struct super_block *nfs_clone_nfs_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) +{ + struct nfs_clone_mount *data = raw_data; + return nfs_clone_generic_sb(data, nfs_clone_sb, nfs_clone_server); +} + +#ifdef CONFIG_NFS_V4 +static struct rpc_clnt *nfs4_create_client(struct nfs_server *server, + struct rpc_timeout *timeparms, int proto, rpc_authflavor_t flavor) +{ + struct nfs4_client *clp; + struct rpc_xprt *xprt = NULL; + struct rpc_clnt *clnt = NULL; + int err = -EIO; + + clp = nfs4_get_client(&server->addr.sin_addr); + if (!clp) { + dprintk("%s: failed to create NFS4 client.\n", __FUNCTION__); + return ERR_PTR(err); + } + + /* Now create transport and client */ + down_write(&clp->cl_sem); + if (IS_ERR(clp->cl_rpcclient)) { + xprt = xprt_create_proto(proto, &server->addr, timeparms); + if (IS_ERR(xprt)) { + up_write(&clp->cl_sem); + err = PTR_ERR(xprt); + dprintk("%s: cannot create RPC transport. Error = %d\n", + __FUNCTION__, err); + goto out_fail; + } + /* Bind to a reserved port! */ + xprt->resvport = 1; + clnt = rpc_create_client(xprt, server->hostname, &nfs_program, + server->rpc_ops->version, flavor); + if (IS_ERR(clnt)) { + up_write(&clp->cl_sem); + err = PTR_ERR(clnt); + dprintk("%s: cannot create RPC client. Error = %d\n", + __FUNCTION__, err); + goto out_fail; + } + clnt->cl_intr = 1; + clnt->cl_softrtry = 1; + clp->cl_rpcclient = clnt; + memcpy(clp->cl_ipaddr, server->ip_addr, sizeof(clp->cl_ipaddr)); + nfs_idmap_new(clp); + } + list_add_tail(&server->nfs4_siblings, &clp->cl_superblocks); + clnt = rpc_clone_client(clp->cl_rpcclient); + if (!IS_ERR(clnt)) + server->nfs4_state = clp; + up_write(&clp->cl_sem); + clp = NULL; + + if (IS_ERR(clnt)) { + dprintk("%s: cannot create RPC client. Error = %d\n", + __FUNCTION__, err); + return clnt; + } + + if (server->nfs4_state->cl_idmap == NULL) { + dprintk("%s: failed to create idmapper.\n", __FUNCTION__); + return ERR_PTR(-ENOMEM); + } + + if (clnt->cl_auth->au_flavor != flavor) { + struct rpc_auth *auth; + + auth = rpcauth_create(flavor, clnt); + if (IS_ERR(auth)) { + dprintk("%s: couldn't create credcache!\n", __FUNCTION__); + return (struct rpc_clnt *)auth; + } + } + return clnt; + + out_fail: + if (clp) + nfs4_put_client(clp); + return ERR_PTR(err); +} + +/* + * Set up an NFS4 superblock + */ +static int nfs4_fill_super(struct super_block *sb, struct nfs4_mount_data *data, int silent) +{ + struct nfs_server *server; + struct rpc_timeout timeparms; + rpc_authflavor_t authflavour; + int err = -EIO; + + sb->s_blocksize_bits = 0; + sb->s_blocksize = 0; + server = NFS_SB(sb); + if (data->rsize != 0) + server->rsize = nfs_block_size(data->rsize, NULL); + if (data->wsize != 0) + server->wsize = nfs_block_size(data->wsize, NULL); + server->flags = data->flags & NFS_MOUNT_FLAGMASK; + server->caps = NFS_CAP_ATOMIC_OPEN; + + server->acregmin = data->acregmin*HZ; + server->acregmax = data->acregmax*HZ; + server->acdirmin = data->acdirmin*HZ; + server->acdirmax = data->acdirmax*HZ; + + server->rpc_ops = &nfs_v4_clientops; + + nfs_init_timeout_values(&timeparms, data->proto, data->timeo, data->retrans); + + server->retrans_timeo = timeparms.to_initval; + server->retrans_count = timeparms.to_retries; + + /* Now create transport and client */ + authflavour = RPC_AUTH_UNIX; + if (data->auth_flavourlen != 0) { + if (data->auth_flavourlen != 1) { + dprintk("%s: Invalid number of RPC auth flavours %d.\n", + __FUNCTION__, data->auth_flavourlen); + err = -EINVAL; + goto out_fail; + } + if (copy_from_user(&authflavour, data->auth_flavours, sizeof(authflavour))) { + err = -EFAULT; + goto out_fail; + } + } + + server->client = nfs4_create_client(server, &timeparms, data->proto, authflavour); + if (IS_ERR(server->client)) { + err = PTR_ERR(server->client); + dprintk("%s: cannot create RPC client. Error = %d\n", + __FUNCTION__, err); + goto out_fail; + } + + sb->s_time_gran = 1; + + sb->s_op = &nfs4_sops; + err = nfs_sb_init(sb, authflavour); + + out_fail: + return err; +} + +static int nfs4_compare_super(struct super_block *sb, void *data) +{ + struct nfs_server *server = data; + struct nfs_server *old = NFS_SB(sb); + + if (strcmp(server->hostname, old->hostname) != 0) + return 0; + if (strcmp(server->mnt_path, old->mnt_path) != 0) + return 0; + return 1; +} + +static void * +nfs_copy_user_string(char *dst, struct nfs_string *src, int maxlen) +{ + void *p = NULL; + + if (!src->len) + return ERR_PTR(-EINVAL); + if (src->len < maxlen) + maxlen = src->len; + if (dst == NULL) { + p = dst = kmalloc(maxlen + 1, GFP_KERNEL); + if (p == NULL) + return ERR_PTR(-ENOMEM); + } + if (copy_from_user(dst, src->data, maxlen)) { + kfree(p); + return ERR_PTR(-EFAULT); + } + dst[maxlen] = '\0'; + return dst; +} + +static struct super_block *nfs4_get_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) +{ + int error; + struct nfs_server *server; + struct super_block *s; + struct nfs4_mount_data *data = raw_data; + void *p; + + if (data == NULL) { + dprintk("%s: missing data argument\n", __FUNCTION__); + return ERR_PTR(-EINVAL); + } + if (data->version <= 0 || data->version > NFS4_MOUNT_VERSION) { + dprintk("%s: bad mount version\n", __FUNCTION__); + return ERR_PTR(-EINVAL); + } + + server = kzalloc(sizeof(struct nfs_server), GFP_KERNEL); + if (!server) + return ERR_PTR(-ENOMEM); + /* Zero out the NFS state stuff */ + init_nfsv4_state(server); + server->client = server->client_sys = server->client_acl = ERR_PTR(-EINVAL); + + p = nfs_copy_user_string(NULL, &data->hostname, 256); + if (IS_ERR(p)) + goto out_err; + server->hostname = p; + + p = nfs_copy_user_string(NULL, &data->mnt_path, 1024); + if (IS_ERR(p)) + goto out_err; + server->mnt_path = p; + + p = nfs_copy_user_string(server->ip_addr, &data->client_addr, + sizeof(server->ip_addr) - 1); + if (IS_ERR(p)) + goto out_err; + + /* We now require that the mount process passes the remote address */ + if (data->host_addrlen != sizeof(server->addr)) { + s = ERR_PTR(-EINVAL); + goto out_free; + } + if (copy_from_user(&server->addr, data->host_addr, sizeof(server->addr))) { + s = ERR_PTR(-EFAULT); + goto out_free; + } + if (server->addr.sin_family != AF_INET || + server->addr.sin_addr.s_addr == INADDR_ANY) { + dprintk("%s: mount program didn't pass remote IP address!\n", + __FUNCTION__); + s = ERR_PTR(-EINVAL); + goto out_free; + } + + /* Fire up rpciod if not yet running */ + s = ERR_PTR(rpciod_up()); + if (IS_ERR(s)) { + dprintk("%s: couldn't start rpciod! Error = %ld\n", + __FUNCTION__, PTR_ERR(s)); + goto out_free; + } + + s = sget(fs_type, nfs4_compare_super, nfs_set_super, server); + + if (IS_ERR(s) || s->s_root) + goto out_free; + + s->s_flags = flags; + + error = nfs4_fill_super(s, data, flags & MS_SILENT ? 1 : 0); + if (error) { + up_write(&s->s_umount); + deactivate_super(s); + return ERR_PTR(error); + } + s->s_flags |= MS_ACTIVE; + return s; +out_err: + s = (struct super_block *)p; +out_free: + kfree(server->mnt_path); + kfree(server->hostname); + kfree(server); + return s; +} + +static void nfs4_kill_super(struct super_block *sb) +{ + struct nfs_server *server = NFS_SB(sb); + + nfs_return_all_delegations(sb); + kill_anon_super(sb); + + nfs4_renewd_prepare_shutdown(server); + + if (server->client != NULL && !IS_ERR(server->client)) + rpc_shutdown_client(server->client); + + destroy_nfsv4_state(server); + + rpciod_down(); + + nfs_free_iostats(server->io_stats); + kfree(server->hostname); + kfree(server); + nfs_release_automount_timer(); +} + +/* + * Constructs the SERVER-side path + */ +static inline char *nfs4_dup_path(const struct dentry *dentry) +{ + char *page = (char *) __get_free_page(GFP_USER); + char *path; + + path = nfs4_path(dentry, page, PAGE_SIZE); + if (!IS_ERR(path)) { + int len = PAGE_SIZE + page - path; + char *tmp = path; + + path = kmalloc(len, GFP_KERNEL); + if (path) + memcpy(path, tmp, len); + else + path = ERR_PTR(-ENOMEM); + } + free_page((unsigned long)page); + return path; +} + +static struct super_block *nfs4_clone_sb(struct nfs_server *server, struct nfs_clone_mount *data) +{ + const struct dentry *dentry = data->dentry; + struct nfs4_client *clp = server->nfs4_state; + struct super_block *sb; + + server->fsid = data->fattr->fsid; + nfs_copy_fh(&server->fh, data->fh); + server->mnt_path = nfs4_dup_path(dentry); + if (IS_ERR(server->mnt_path)) { + sb = (struct super_block *)server->mnt_path; + goto err; + } + sb = sget(&nfs4_fs_type, nfs4_compare_super, nfs_set_super, server); + if (IS_ERR(sb) || sb->s_root) + goto free_path; + nfs4_server_capabilities(server, &server->fh); + + down_write(&clp->cl_sem); + atomic_inc(&clp->cl_count); + list_add_tail(&server->nfs4_siblings, &clp->cl_superblocks); + up_write(&clp->cl_sem); + return sb; +free_path: + kfree(server->mnt_path); +err: + server->mnt_path = NULL; + return sb; +} + +static struct super_block *nfs_clone_nfs4_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) +{ + struct nfs_clone_mount *data = raw_data; + return nfs_clone_generic_sb(data, nfs4_clone_sb, nfs_clone_server); +} + +static struct super_block *nfs4_referral_sb(struct nfs_server *server, struct nfs_clone_mount *data) +{ + struct super_block *sb = ERR_PTR(-ENOMEM); + int len; + + len = strlen(data->mnt_path) + 1; + server->mnt_path = kmalloc(len, GFP_KERNEL); + if (server->mnt_path == NULL) + goto err; + memcpy(server->mnt_path, data->mnt_path, len); + memcpy(&server->addr, data->addr, sizeof(struct sockaddr_in)); + + sb = sget(&nfs4_fs_type, nfs4_compare_super, nfs_set_super, server); + if (IS_ERR(sb) || sb->s_root) + goto free_path; + return sb; +free_path: + kfree(server->mnt_path); +err: + server->mnt_path = NULL; + return sb; +} + +static struct nfs_server *nfs4_referral_server(struct super_block *sb, struct nfs_clone_mount *data) +{ + struct nfs_server *server = NFS_SB(sb); + struct rpc_timeout timeparms; + int proto, timeo, retrans; + void *err; + + proto = IPPROTO_TCP; + /* Since we are following a referral and there may be alternatives, + set the timeouts and retries to low values */ + timeo = 2; + retrans = 1; + nfs_init_timeout_values(&timeparms, proto, timeo, retrans); + + server->client = nfs4_create_client(server, &timeparms, proto, data->authflavor); + if (IS_ERR((err = server->client))) + goto out_err; + + sb->s_time_gran = 1; + sb->s_op = &nfs4_sops; + err = ERR_PTR(nfs_sb_init(sb, data->authflavor)); + if (!IS_ERR(err)) + return server; +out_err: + return (struct nfs_server *)err; +} + +static struct super_block *nfs_referral_nfs4_sb(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) +{ + struct nfs_clone_mount *data = raw_data; + return nfs_clone_generic_sb(data, nfs4_referral_sb, nfs4_referral_server); +} + +#endif diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c index 18dc95b..636c479 100644 --- a/fs/nfs/symlink.c +++ b/fs/nfs/symlink.c @@ -52,7 +52,7 @@ static void *nfs_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; struct page *page; - void *err = ERR_PTR(nfs_revalidate_inode(NFS_SERVER(inode), inode)); + void *err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping)); if (err) goto read_failed; page = read_cache_page(&inode->i_data, 0, diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c index 4c486eb..db61e51 100644 --- a/fs/nfs/sysctl.c +++ b/fs/nfs/sysctl.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/nfs4.h> #include <linux/nfs_idmap.h> +#include <linux/nfs_fs.h> #include "callback.h" @@ -46,6 +47,15 @@ static ctl_table nfs_cb_sysctls[] = { .strategy = &sysctl_jiffies, }, #endif + { + .ctl_name = CTL_UNNUMBERED, + .procname = "nfs_mountpoint_timeout", + .data = &nfs_mountpoint_expiry_timeout, + .maxlen = sizeof(nfs_mountpoint_expiry_timeout), + .mode = 0644, + .proc_handler = &proc_dointvec_jiffies, + .strategy = &sysctl_jiffies, + }, { .ctl_name = 0 } }; diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 4cfada2..b383fdd 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -98,11 +98,10 @@ struct nfs_write_data *nfs_commit_alloc(unsigned int pagecount) if (p) { memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&p->pages); - if (pagecount < NFS_PAGEVEC_SIZE) - p->pagevec = &p->page_array[0]; + if (pagecount <= ARRAY_SIZE(p->page_array)) + p->pagevec = p->page_array; else { - size_t size = ++pagecount * sizeof(struct page *); - p->pagevec = kzalloc(size, GFP_NOFS); + p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS); if (!p->pagevec) { mempool_free(p, nfs_commit_mempool); p = NULL; @@ -126,14 +125,11 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) if (p) { memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&p->pages); - if (pagecount < NFS_PAGEVEC_SIZE) - p->pagevec = &p->page_array[0]; + if (pagecount <= ARRAY_SIZE(p->page_array)) + p->pagevec = p->page_array; else { - size_t size = ++pagecount * sizeof(struct page *); - p->pagevec = kmalloc(size, GFP_NOFS); - if (p->pagevec) { - memset(p->pagevec, 0, size); - } else { + p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_NOFS); + if (!p->pagevec) { mempool_free(p, nfs_wdata_mempool); p = NULL; } @@ -583,6 +579,17 @@ static int nfs_wait_on_requests(struct inode *inode, unsigned long idx_start, un return ret; } +static void nfs_cancel_requests(struct list_head *head) +{ + struct nfs_page *req; + while(!list_empty(head)) { + req = nfs_list_entry(head->next); + nfs_list_remove_request(req); + nfs_inode_remove_request(req); + nfs_clear_page_writeback(req); + } +} + /* * nfs_scan_dirty - Scan an inode for dirty requests * @inode: NFS inode to scan @@ -627,7 +634,7 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst, unsigned long idx_st int res = 0; if (nfsi->ncommit != 0) { - res = nfs_scan_list(&nfsi->commit, dst, idx_start, npages); + res = nfs_scan_list(nfsi, &nfsi->commit, dst, idx_start, npages); nfsi->ncommit -= res; if ((nfsi->ncommit == 0) != list_empty(&nfsi->commit)) printk(KERN_ERR "NFS: desynchronized value of nfs_i.ncommit.\n"); @@ -1495,15 +1502,25 @@ int nfs_sync_inode_wait(struct inode *inode, unsigned long idx_start, pages = nfs_scan_dirty(inode, &head, idx_start, npages); if (pages != 0) { spin_unlock(&nfsi->req_lock); - ret = nfs_flush_list(inode, &head, pages, how); + if (how & FLUSH_INVALIDATE) + nfs_cancel_requests(&head); + else + ret = nfs_flush_list(inode, &head, pages, how); spin_lock(&nfsi->req_lock); continue; } if (nocommit) break; - pages = nfs_scan_commit(inode, &head, 0, 0); + pages = nfs_scan_commit(inode, &head, idx_start, npages); if (pages == 0) break; + if (how & FLUSH_INVALIDATE) { + spin_unlock(&nfsi->req_lock); + nfs_cancel_requests(&head); + spin_lock(&nfsi->req_lock); + continue; + } + pages += nfs_scan_commit(inode, &head, 0, 0); spin_unlock(&nfsi->req_lock); ret = nfs_commit_list(inode, &head, how); spin_lock(&nfsi->req_lock); @@ -1512,7 +1529,7 @@ int nfs_sync_inode_wait(struct inode *inode, unsigned long idx_start, return ret; } -int nfs_init_writepagecache(void) +int __init nfs_init_writepagecache(void) { nfs_wdata_cachep = kmem_cache_create("nfs_write_data", sizeof(struct nfs_write_data), @@ -1534,7 +1551,7 @@ int nfs_init_writepagecache(void) return 0; } -void nfs_destroy_writepagecache(void) +void __exit nfs_destroy_writepagecache(void) { mempool_destroy(nfs_commit_mempool); mempool_destroy(nfs_wdata_mempool); @@ -800,17 +800,13 @@ struct super_block *get_sb_single(struct file_system_type *fs_type, EXPORT_SYMBOL(get_sb_single); struct vfsmount * -do_kern_mount(const char *fstype, int flags, const char *name, void *data) +vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data) { - struct file_system_type *type = get_fs_type(fstype); struct super_block *sb = ERR_PTR(-ENOMEM); struct vfsmount *mnt; int error; char *secdata = NULL; - if (!type) - return ERR_PTR(-ENODEV); - mnt = alloc_vfsmnt(name); if (!mnt) goto out; @@ -841,7 +837,6 @@ do_kern_mount(const char *fstype, int flags, const char *name, void *data) mnt->mnt_parent = mnt; up_write(&sb->s_umount); free_secdata(secdata); - put_filesystem(type); return mnt; out_sb: up_write(&sb->s_umount); @@ -852,15 +847,26 @@ out_free_secdata: out_mnt: free_vfsmnt(mnt); out: - put_filesystem(type); return (struct vfsmount *)sb; } -EXPORT_SYMBOL_GPL(do_kern_mount); +EXPORT_SYMBOL_GPL(vfs_kern_mount); + +struct vfsmount * +do_kern_mount(const char *fstype, int flags, const char *name, void *data) +{ + struct file_system_type *type = get_fs_type(fstype); + struct vfsmount *mnt; + if (!type) + return ERR_PTR(-ENODEV); + mnt = vfs_kern_mount(type, flags, name, data); + put_filesystem(type); + return mnt; +} struct vfsmount *kern_mount(struct file_system_type *type) { - return do_kern_mount(type->name, 0, type->name, NULL); + return vfs_kern_mount(type, 0, type->name, NULL); } EXPORT_SYMBOL(kern_mount); diff --git a/include/linux/fs.h b/include/linux/fs.h index ecc8c2c..2d5a112 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -1100,7 +1100,7 @@ struct super_operations { int (*statfs) (struct super_block *, struct kstatfs *); int (*remount_fs) (struct super_block *, int *, char *); void (*clear_inode) (struct inode *); - void (*umount_begin) (struct super_block *); + void (*umount_begin) (struct vfsmount *, int); int (*show_options)(struct seq_file *, struct vfsmount *); int (*show_stats)(struct seq_file *, struct vfsmount *); @@ -1762,7 +1762,7 @@ extern struct inode_operations simple_dir_inode_operations; struct tree_descr { char *name; const struct file_operations *ops; int mode; }; struct dentry *d_alloc_name(struct dentry *, const char *); extern int simple_fill_super(struct super_block *, int, struct tree_descr *); -extern int simple_pin_fs(char *name, struct vfsmount **mount, int *count); +extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count); extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *, size_t, loff_t *, const void *, size_t); diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h index a8876bc..aa4fe90 100644 --- a/include/linux/lockd/lockd.h +++ b/include/linux/lockd/lockd.h @@ -49,11 +49,12 @@ struct nlm_host { h_killed : 1, h_monitored : 1; wait_queue_head_t h_gracewait; /* wait while reclaiming */ + struct rw_semaphore h_rwsem; /* Reboot recovery lock */ u32 h_state; /* pseudo-state counter */ u32 h_nsmstate; /* true remote NSM state */ u32 h_pidcount; /* Pseudopids */ atomic_t h_count; /* reference count */ - struct semaphore h_sema; /* mutex for pmap binding */ + struct mutex h_mutex; /* mutex for pmap binding */ unsigned long h_nextrebind; /* next portmap call */ unsigned long h_expires; /* eligible for GC */ struct list_head h_lockowners; /* Lockowners for the client */ @@ -219,6 +220,7 @@ static __inline__ int nlm_compare_locks(const struct file_lock *fl1, const struct file_lock *fl2) { return fl1->fl_pid == fl2->fl_pid + && fl1->fl_owner == fl2->fl_owner && fl1->fl_start == fl2->fl_start && fl1->fl_end == fl2->fl_end &&(fl1->fl_type == fl2->fl_type || fl2->fl_type == F_UNLCK); diff --git a/include/linux/mount.h b/include/linux/mount.h index b7472ae..9b4e007 100644 --- a/include/linux/mount.h +++ b/include/linux/mount.h @@ -23,6 +23,8 @@ #define MNT_NOATIME 0x08 #define MNT_NODIRATIME 0x10 +#define MNT_SHRINKABLE 0x100 + #define MNT_SHARED 0x1000 /* if the vfsmount is a shared mount */ #define MNT_UNBINDABLE 0x2000 /* if the vfsmount is a unbindable mount */ #define MNT_PNODE_MASK 0x3000 /* propogation flag mask */ @@ -73,12 +75,18 @@ extern struct vfsmount *alloc_vfsmnt(const char *name); extern struct vfsmount *do_kern_mount(const char *fstype, int flags, const char *name, void *data); +struct file_system_type; +extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, + int flags, const char *name, + void *data); + struct nameidata; extern int do_add_mount(struct vfsmount *newmnt, struct nameidata *nd, int mnt_flags, struct list_head *fslist); extern void mark_mounts_for_expiry(struct list_head *mounts); +extern void shrink_submounts(struct vfsmount *mountpoint, struct list_head *mounts); extern spinlock_t vfsmount_lock; extern dev_t name_to_dev_t(char *name); diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h index 1059e6d..5f681d5 100644 --- a/include/linux/nfs4.h +++ b/include/linux/nfs4.h @@ -384,6 +384,7 @@ enum { NFSPROC4_CLNT_DELEGRETURN, NFSPROC4_CLNT_GETACL, NFSPROC4_CLNT_SETACL, + NFSPROC4_CLNT_FS_LOCATIONS, }; #endif diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h index 7e079f8..1527989 100644 --- a/include/linux/nfs_fs.h +++ b/include/linux/nfs_fs.h @@ -9,6 +9,27 @@ #ifndef _LINUX_NFS_FS_H #define _LINUX_NFS_FS_H +#include <linux/config.h> +#include <linux/in.h> +#include <linux/mm.h> +#include <linux/pagemap.h> +#include <linux/rwsem.h> +#include <linux/wait.h> + +#include <linux/sunrpc/debug.h> +#include <linux/sunrpc/auth.h> +#include <linux/sunrpc/clnt.h> + +#include <linux/nfs.h> +#include <linux/nfs2.h> +#include <linux/nfs3.h> +#include <linux/nfs4.h> +#include <linux/nfs_xdr.h> + +#include <linux/nfs_fs_sb.h> + +#include <linux/rwsem.h> +#include <linux/mempool.h> /* * Enable debugging support for nfs client. @@ -41,27 +62,9 @@ #define FLUSH_LOWPRI 8 /* low priority background flush */ #define FLUSH_HIGHPRI 16 /* high priority memory reclaim flush */ #define FLUSH_NOCOMMIT 32 /* Don't send the NFSv3/v4 COMMIT */ +#define FLUSH_INVALIDATE 64 /* Invalidate the page cache */ #ifdef __KERNEL__ -#include <linux/in.h> -#include <linux/mm.h> -#include <linux/pagemap.h> -#include <linux/rwsem.h> -#include <linux/wait.h> - -#include <linux/nfs_fs_sb.h> - -#include <linux/sunrpc/debug.h> -#include <linux/sunrpc/auth.h> -#include <linux/sunrpc/clnt.h> - -#include <linux/nfs.h> -#include <linux/nfs2.h> -#include <linux/nfs3.h> -#include <linux/nfs4.h> -#include <linux/nfs_xdr.h> -#include <linux/rwsem.h> -#include <linux/mempool.h> /* * NFSv3/v4 Access mode cache entry @@ -233,8 +236,12 @@ static inline int nfs_caches_unstable(struct inode *inode) static inline void nfs_mark_for_revalidate(struct inode *inode) { + struct nfs_inode *nfsi = NFS_I(inode); + spin_lock(&inode->i_lock); - NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATTR | NFS_INO_INVALID_ACCESS; + nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS; + if (S_ISDIR(inode->i_mode)) + nfsi->cache_validity |= NFS_INO_REVAL_PAGECACHE|NFS_INO_INVALID_DATA; spin_unlock(&inode->i_lock); } @@ -296,7 +303,7 @@ extern int nfs_release(struct inode *, struct file *); extern int nfs_attribute_timeout(struct inode *inode); extern int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode); extern int __nfs_revalidate_inode(struct nfs_server *, struct inode *); -extern void nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); +extern int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping); extern int nfs_setattr(struct dentry *, struct iattr *); extern void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr); extern void nfs_begin_attr_update(struct inode *); @@ -306,6 +313,12 @@ extern void nfs_end_data_update(struct inode *); extern struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx); extern void put_nfs_open_context(struct nfs_open_context *ctx); extern struct nfs_open_context *nfs_find_open_context(struct inode *inode, struct rpc_cred *cred, int mode); +extern struct vfsmount *nfs_do_submount(const struct vfsmount *mnt_parent, + const struct dentry *dentry, + struct nfs_fh *fh, + struct nfs_fattr *fattr); +extern struct vfsmount *nfs_do_refmount(const struct vfsmount *mnt_parent, + struct dentry *dentry); /* linux/net/ipv4/ipconfig.c: trims ip addr off front of name, too. */ extern u32 root_nfs_parse_addr(char *name); /*__init*/ @@ -392,6 +405,15 @@ extern void nfs_unregister_sysctl(void); #endif /* + * linux/fs/nfs/namespace.c + */ +extern struct list_head nfs_automount_list; +extern struct inode_operations nfs_mountpoint_inode_operations; +extern struct inode_operations nfs_referral_inode_operations; +extern int nfs_mountpoint_expiry_timeout; +extern void nfs_release_automount_timer(void); + +/* * linux/fs/nfs/unlink.c */ extern int nfs_async_unlink(struct dentry *); diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h index 65dec21..6b4a13c 100644 --- a/include/linux/nfs_fs_sb.h +++ b/include/linux/nfs_fs_sb.h @@ -35,6 +35,7 @@ struct nfs_server { char * hostname; /* remote hostname */ struct nfs_fh fh; struct sockaddr_in addr; + struct nfs_fsid fsid; unsigned long mount_time; /* when this fs was mounted */ #ifdef CONFIG_NFS_V4 /* Our own IP address, as a null-terminated string. diff --git a/include/linux/nfs_page.h b/include/linux/nfs_page.h index 66e2ed6..1f7bd28 100644 --- a/include/linux/nfs_page.h +++ b/include/linux/nfs_page.h @@ -13,7 +13,6 @@ #include <linux/list.h> #include <linux/pagemap.h> #include <linux/wait.h> -#include <linux/nfs_fs_sb.h> #include <linux/sunrpc/auth.h> #include <linux/nfs_xdr.h> @@ -63,8 +62,8 @@ extern void nfs_release_request(struct nfs_page *req); extern int nfs_scan_lock_dirty(struct nfs_inode *nfsi, struct list_head *dst, unsigned long idx_start, unsigned int npages); -extern int nfs_scan_list(struct list_head *, struct list_head *, - unsigned long, unsigned int); +extern int nfs_scan_list(struct nfs_inode *nfsi, struct list_head *head, struct list_head *dst, + unsigned long idx_start, unsigned int npages); extern int nfs_coalesce_requests(struct list_head *, struct list_head *, unsigned int); extern int nfs_wait_on_request(struct nfs_page *); diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h index 7fafc4c..7c7320f 100644 --- a/include/linux/nfs_xdr.h +++ b/include/linux/nfs_xdr.h @@ -14,11 +14,19 @@ #define NFS_DEF_FILE_IO_SIZE (4096U) #define NFS_MIN_FILE_IO_SIZE (1024U) -struct nfs4_fsid { - __u64 major; - __u64 minor; +struct nfs_fsid { + uint64_t major; + uint64_t minor; }; +/* + * Helper for checking equality between 2 fsids. + */ +static inline int nfs_fsid_equal(const struct nfs_fsid *a, const struct nfs_fsid *b) +{ + return a->major == b->major && a->minor == b->minor; +} + struct nfs_fattr { unsigned short valid; /* which fields are valid */ __u64 pre_size; /* pre_op_attr.size */ @@ -40,10 +48,7 @@ struct nfs_fattr { } nfs3; } du; dev_t rdev; - union { - __u64 nfs3; /* also nfs2 */ - struct nfs4_fsid nfs4; - } fsid_u; + struct nfs_fsid fsid; __u64 fileid; struct timespec atime; struct timespec mtime; @@ -57,8 +62,8 @@ struct nfs_fattr { #define NFS_ATTR_WCC 0x0001 /* pre-op WCC data */ #define NFS_ATTR_FATTR 0x0002 /* post-op attributes */ #define NFS_ATTR_FATTR_V3 0x0004 /* NFSv3 attributes */ -#define NFS_ATTR_FATTR_V4 0x0008 -#define NFS_ATTR_PRE_CHANGE 0x0010 +#define NFS_ATTR_FATTR_V4 0x0008 /* NFSv4 change attribute */ +#define NFS_ATTR_FATTR_V4_REFERRAL 0x0010 /* NFSv4 referral */ /* * Info on the file system @@ -675,6 +680,40 @@ struct nfs4_server_caps_res { u32 has_symlinks; }; +struct nfs4_string { + unsigned int len; + char *data; +}; + +#define NFS4_PATHNAME_MAXCOMPONENTS 512 +struct nfs4_pathname { + unsigned int ncomponents; + struct nfs4_string components[NFS4_PATHNAME_MAXCOMPONENTS]; +}; + +#define NFS4_FS_LOCATION_MAXSERVERS 10 +struct nfs4_fs_location { + unsigned int nservers; + struct nfs4_string servers[NFS4_FS_LOCATION_MAXSERVERS]; + struct nfs4_pathname rootpath; +}; + +#define NFS4_FS_LOCATIONS_MAXENTRIES 10 +struct nfs4_fs_locations { + struct nfs_fattr fattr; + const struct nfs_server *server; + struct nfs4_pathname fs_path; + int nlocations; + struct nfs4_fs_location locations[NFS4_FS_LOCATIONS_MAXENTRIES]; +}; + +struct nfs4_fs_locations_arg { + const struct nfs_fh *dir_fh; + const struct qstr *name; + struct page *page; + const u32 *bitmask; +}; + #endif /* CONFIG_NFS_V4 */ struct nfs_page; @@ -695,7 +734,7 @@ struct nfs_read_data { #ifdef CONFIG_NFS_V4 unsigned long timestamp; /* For lease renewal */ #endif - struct page *page_array[NFS_PAGEVEC_SIZE + 1]; + struct page *page_array[NFS_PAGEVEC_SIZE]; }; struct nfs_write_data { @@ -713,7 +752,7 @@ struct nfs_write_data { #ifdef CONFIG_NFS_V4 unsigned long timestamp; /* For lease renewal */ #endif - struct page *page_array[NFS_PAGEVEC_SIZE + 1]; + struct page *page_array[NFS_PAGEVEC_SIZE]; }; struct nfs_access_entry; diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h index 84c35d4..e6d3d34 100644 --- a/include/linux/sunrpc/xdr.h +++ b/include/linux/sunrpc/xdr.h @@ -194,6 +194,7 @@ extern void xdr_write_pages(struct xdr_stream *xdr, struct page **pages, extern void xdr_init_decode(struct xdr_stream *xdr, struct xdr_buf *buf, uint32_t *p); extern uint32_t *xdr_inline_decode(struct xdr_stream *xdr, size_t nbytes); extern void xdr_read_pages(struct xdr_stream *xdr, unsigned int len); +extern void xdr_enter_page(struct xdr_stream *xdr, unsigned int len); #endif /* __KERNEL__ */ @@ -2263,7 +2263,7 @@ static int __init init_tmpfs(void) #ifdef CONFIG_TMPFS devfs_mk_dir("shm"); #endif - shm_mnt = do_kern_mount(tmpfs_fs_type.name, MS_NOUSER, + shm_mnt = vfs_kern_mount(&tmpfs_fs_type, MS_NOUSER, tmpfs_fs_type.name, NULL); if (IS_ERR(shm_mnt)) { error = PTR_ERR(shm_mnt); diff --git a/net/sunrpc/auth_null.c b/net/sunrpc/auth_null.c index f56767a..2eccffa 100644 --- a/net/sunrpc/auth_null.c +++ b/net/sunrpc/auth_null.c @@ -118,6 +118,8 @@ struct rpc_auth null_auth = { .au_cslack = 4, .au_rslack = 2, .au_ops = &authnull_ops, + .au_flavor = RPC_AUTH_NULL, + .au_count = ATOMIC_INIT(0), }; static diff --git a/net/sunrpc/auth_unix.c b/net/sunrpc/auth_unix.c index df14b6b..74c7406 100644 --- a/net/sunrpc/auth_unix.c +++ b/net/sunrpc/auth_unix.c @@ -225,6 +225,7 @@ struct rpc_auth unix_auth = { .au_cslack = UNX_WRITESLACK, .au_rslack = 2, /* assume AUTH_NULL verf */ .au_ops = &authunix_ops, + .au_flavor = RPC_AUTH_UNIX, .au_count = ATOMIC_INIT(0), .au_credcache = &unix_cred_cache, }; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index cc673dd..a5226df 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -439,7 +439,7 @@ struct vfsmount *rpc_get_mount(void) { int err; - err = simple_pin_fs("rpc_pipefs", &rpc_mount, &rpc_mount_count); + err = simple_pin_fs(&rpc_pipe_fs_type, &rpc_mount, &rpc_mount_count); if (err != 0) return ERR_PTR(err); return rpc_mount; diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index ca4bfa5..49174f0 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -568,8 +568,7 @@ EXPORT_SYMBOL(xdr_inline_decode); * * Moves data beyond the current pointer position from the XDR head[] buffer * into the page list. Any data that lies beyond current position + "len" - * bytes is moved into the XDR tail[]. The current pointer is then - * repositioned at the beginning of the XDR tail. + * bytes is moved into the XDR tail[]. */ void xdr_read_pages(struct xdr_stream *xdr, unsigned int len) { @@ -606,6 +605,31 @@ void xdr_read_pages(struct xdr_stream *xdr, unsigned int len) } EXPORT_SYMBOL(xdr_read_pages); +/** + * xdr_enter_page - decode data from the XDR page + * @xdr: pointer to xdr_stream struct + * @len: number of bytes of page data + * + * Moves data beyond the current pointer position from the XDR head[] buffer + * into the page list. Any data that lies beyond current position + "len" + * bytes is moved into the XDR tail[]. The current pointer is then + * repositioned at the beginning of the first XDR page. + */ +void xdr_enter_page(struct xdr_stream *xdr, unsigned int len) +{ + char * kaddr = page_address(xdr->buf->pages[0]); + xdr_read_pages(xdr, len); + /* + * Position current pointer at beginning of tail, and + * set remaining message length. + */ + if (len > PAGE_CACHE_SIZE - xdr->buf->page_base) + len = PAGE_CACHE_SIZE - xdr->buf->page_base; + xdr->p = (uint32_t *)(kaddr + xdr->buf->page_base); + xdr->end = (uint32_t *)((char *)xdr->p + len); +} +EXPORT_SYMBOL(xdr_enter_page); + static struct kvec empty_iov = {.iov_base = NULL, .iov_len = 0}; void diff --git a/net/sunrpc/xprt.c b/net/sunrpc/xprt.c index 4dd5b3c..02060d0 100644 --- a/net/sunrpc/xprt.c +++ b/net/sunrpc/xprt.c @@ -41,7 +41,7 @@ #include <linux/types.h> #include <linux/interrupt.h> #include <linux/workqueue.h> -#include <linux/random.h> +#include <linux/net.h> #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/metrics.h> @@ -830,7 +830,7 @@ static inline u32 xprt_alloc_xid(struct rpc_xprt *xprt) static inline void xprt_init_xid(struct rpc_xprt *xprt) { - get_random_bytes(&xprt->xid, sizeof(xprt->xid)); + xprt->xid = net_random(); } static void xprt_request_init(struct rpc_task *task, struct rpc_xprt *xprt) diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 4b4e7df..21006b1 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -930,6 +930,13 @@ static void xs_udp_timer(struct rpc_task *task) xprt_adjust_cwnd(task, -ETIMEDOUT); } +static unsigned short xs_get_random_port(void) +{ + unsigned short range = xprt_max_resvport - xprt_min_resvport; + unsigned short rand = (unsigned short) net_random() % range; + return rand + xprt_min_resvport; +} + /** * xs_set_port - reset the port number in the remote endpoint address * @xprt: generic transport @@ -1275,7 +1282,7 @@ int xs_setup_udp(struct rpc_xprt *xprt, struct rpc_timeout *to) memset(xprt->slot, 0, slot_table_size); xprt->prot = IPPROTO_UDP; - xprt->port = xprt_max_resvport; + xprt->port = xs_get_random_port(); xprt->tsh_size = 0; xprt->resvport = capable(CAP_NET_BIND_SERVICE) ? 1 : 0; /* XXX: header size can vary due to auth type, IPv6, etc. */ @@ -1317,7 +1324,7 @@ int xs_setup_tcp(struct rpc_xprt *xprt, struct rpc_timeout *to) memset(xprt->slot, 0, slot_table_size); xprt->prot = IPPROTO_TCP; - xprt->port = xprt_max_resvport; + xprt->port = xs_get_random_port(); xprt->tsh_size = sizeof(rpc_fraghdr) / sizeof(u32); xprt->resvport = capable(CAP_NET_BIND_SERVICE) ? 1 : 0; xprt->max_payload = RPC_MAX_FRAGMENT_SIZE; diff --git a/security/inode.c b/security/inode.c index 0f77b02..8bf4062 100644 --- a/security/inode.c +++ b/security/inode.c @@ -224,7 +224,7 @@ struct dentry *securityfs_create_file(const char *name, mode_t mode, pr_debug("securityfs: creating file '%s'\n",name); - error = simple_pin_fs("securityfs", &mount, &mount_count); + error = simple_pin_fs(&fs_type, &mount, &mount_count); if (error) { dentry = ERR_PTR(error); goto exit; |