diff options
Diffstat (limited to 'fs/nfs')
35 files changed, 4437 insertions, 1492 deletions
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index f7e13db613cb..ba306658a6db 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -76,13 +76,17 @@ config NFS_V4 config NFS_V4_1 bool "NFS client support for NFSv4.1 (EXPERIMENTAL)" - depends on NFS_V4 && EXPERIMENTAL + depends on NFS_FS && NFS_V4 && EXPERIMENTAL + select PNFS_FILE_LAYOUT help This option enables support for minor version 1 of the NFSv4 protocol - (draft-ietf-nfsv4-minorversion1) in the kernel's NFS client. + (RFC 5661) in the kernel's NFS client. If unsure, say N. +config PNFS_FILE_LAYOUT + tristate + config ROOT_NFS bool "Root file system on NFS" depends on NFS_FS=y && IP_PNP @@ -117,3 +121,14 @@ config NFS_USE_KERNEL_DNS select DNS_RESOLVER select KEYS default y + +config NFS_USE_NEW_IDMAPPER + bool "Use the new idmapper upcall routine" + depends on NFS_V4 && KEYS + help + Say Y here if you want NFS to use the new idmapper upcall functions. + You will need /sbin/request-key (usually provided by the keyutils + package). For details, read + <file:Documentation/filesystems/nfs/idmapper.txt>. + + If you are unsure, say N. diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index da7fda639eac..4776ff9e3814 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -15,5 +15,9 @@ nfs-$(CONFIG_NFS_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \ delegation.o idmap.o \ callback.o callback_xdr.o callback_proc.o \ nfs4namespace.o +nfs-$(CONFIG_NFS_V4_1) += pnfs.o nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o + +obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o +nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index e17b49e2eabd..aeec017fe814 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -109,7 +109,7 @@ nfs4_callback_up(struct svc_serv *serv) { int ret; - ret = svc_create_xprt(serv, "tcp", PF_INET, + ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET, nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); if (ret <= 0) goto out_err; @@ -117,7 +117,7 @@ nfs4_callback_up(struct svc_serv *serv) dprintk("NFS: Callback listener port = %u (af %u)\n", nfs_callback_tcpport, PF_INET); - ret = svc_create_xprt(serv, "tcp", PF_INET6, + ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET6, nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS); if (ret > 0) { nfs_callback_tcpport6 = ret; diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c index 930d10fecdaf..2950fca0c61b 100644 --- a/fs/nfs/callback_proc.c +++ b/fs/nfs/callback_proc.c @@ -118,11 +118,11 @@ int nfs41_validate_delegation_stateid(struct nfs_delegation *delegation, const n if (delegation == NULL) return 0; - /* seqid is 4-bytes long */ - if (((u32 *) &stateid->data)[0] != 0) + if (stateid->stateid.seqid != 0) return 0; - if (memcmp(&delegation->stateid.data[4], &stateid->data[4], - sizeof(stateid->data)-4)) + if (memcmp(&delegation->stateid.stateid.other, + &stateid->stateid.other, + NFS4_STATEID_OTHER_SIZE)) return 0; return 1; diff --git a/fs/nfs/client.c b/fs/nfs/client.c index e7340729af89..0870d0d4efc0 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -48,6 +48,7 @@ #include "iostat.h" #include "internal.h" #include "fscache.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_CLIENT @@ -155,7 +156,9 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_ cred = rpc_lookup_machine_cred(); if (!IS_ERR(cred)) clp->cl_machine_cred = cred; - +#if defined(CONFIG_NFS_V4_1) + INIT_LIST_HEAD(&clp->cl_layouts); +#endif nfs_fscache_get_client_cookie(clp); return clp; @@ -252,6 +255,7 @@ void nfs_put_client(struct nfs_client *clp) nfs_free_client(clp); } } +EXPORT_SYMBOL_GPL(nfs_put_client); #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) /* @@ -601,6 +605,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp, { struct rpc_clnt *clnt = NULL; struct rpc_create_args args = { + .net = &init_net, .protocol = clp->cl_proto, .address = (struct sockaddr *)&clp->cl_addr, .addrsize = clp->cl_addrlen, @@ -635,7 +640,8 @@ static int nfs_create_rpc_client(struct nfs_client *clp, */ static void nfs_destroy_server(struct nfs_server *server) { - if (!(server->flags & NFS_MOUNT_NONLM)) + if (!(server->flags & NFS_MOUNT_LOCAL_FLOCK) || + !(server->flags & NFS_MOUNT_LOCAL_FCNTL)) nlmclnt_done(server->nlm_host); } @@ -657,7 +663,8 @@ static int nfs_start_lockd(struct nfs_server *server) if (nlm_init.nfs_version > 3) return 0; - if (server->flags & NFS_MOUNT_NONLM) + if ((server->flags & NFS_MOUNT_LOCAL_FLOCK) && + (server->flags & NFS_MOUNT_LOCAL_FCNTL)) return 0; switch (clp->cl_proto) { @@ -898,11 +905,13 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo * 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; + set_pnfs_layoutdriver(server, fsinfo->layouttype); + 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 > PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES) + server->dtsize = PAGE_CACHE_SIZE * NFS_MAX_READDIR_PAGES; if (server->dtsize > server->rsize) server->dtsize = server->rsize; @@ -913,6 +922,8 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, struct nfs_fsinfo * server->maxfilesize = fsinfo->maxfilesize; + server->time_delta = fsinfo->time_delta; + /* We're airborne Set socket buffersize */ rpc_setbufsize(server->client, server->wsize + 100, server->rsize + 100); } @@ -935,6 +946,7 @@ static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, str } fsinfo.fattr = fattr; + fsinfo.layouttype = 0; error = clp->rpc_ops->fsinfo(server, mntfh, &fsinfo); if (error < 0) goto out_error; @@ -1017,6 +1029,7 @@ void nfs_free_server(struct nfs_server *server) { dprintk("--> nfs_free_server()\n"); + unset_pnfs_layoutdriver(server); spin_lock(&nfs_client_lock); list_del(&server->client_link); list_del(&server->master_link); @@ -1356,8 +1369,9 @@ static int nfs4_init_server(struct nfs_server *server, /* Initialise the client representation from the mount data */ server->flags = data->flags; - server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR| - NFS_CAP_POSIX_LOCK; + server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR|NFS_CAP_POSIX_LOCK; + if (!(data->flags & NFS_MOUNT_NORDIRPLUS)) + server->caps |= NFS_CAP_READDIRPLUS; server->options = data->options; /* Get a client record */ diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index b9c3c43cea1d..232a7eead33a 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -71,20 +71,20 @@ static int nfs_delegation_claim_locks(struct nfs_open_context *ctx, struct nfs4_ if (inode->i_flock == NULL) goto out; - /* Protect inode->i_flock using the BKL */ - lock_kernel(); + /* Protect inode->i_flock using the file locks lock */ + lock_flocks(); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) continue; if (nfs_file_open_context(fl->fl_file) != ctx) continue; - unlock_kernel(); + unlock_flocks(); status = nfs4_lock_delegation_recall(state, fl); if (status < 0) goto out; - lock_kernel(); + lock_flocks(); } - unlock_kernel(); + unlock_flocks(); out: return status; } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index e257172d438c..07ac3847e562 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -33,11 +33,12 @@ #include <linux/namei.h> #include <linux/mount.h> #include <linux/sched.h> +#include <linux/vmalloc.h> -#include "nfs4_fs.h" #include "delegation.h" #include "iostat.h" #include "internal.h" +#include "fscache.h" /* #define NFS_DEBUG_VERBOSE 1 */ @@ -55,6 +56,7 @@ static int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); static int nfs_fsync_dir(struct file *, int); static loff_t nfs_llseek_dir(struct file *, loff_t, int); +static int nfs_readdir_clear_array(struct page*, gfp_t); const struct file_operations nfs_dir_operations = { .llseek = nfs_llseek_dir, @@ -80,6 +82,10 @@ const struct inode_operations nfs_dir_inode_operations = { .setattr = nfs_setattr, }; +const struct address_space_operations nfs_dir_addr_space_ops = { + .releasepage = nfs_readdir_clear_array, +}; + #ifdef CONFIG_NFS_V3 const struct inode_operations nfs3_dir_inode_operations = { .create = nfs_create, @@ -104,8 +110,9 @@ const struct inode_operations nfs3_dir_inode_operations = { #ifdef CONFIG_NFS_V4 static struct dentry *nfs_atomic_lookup(struct inode *, struct dentry *, struct nameidata *); +static int nfs_open_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd); const struct inode_operations nfs4_dir_inode_operations = { - .create = nfs_create, + .create = nfs_open_create, .lookup = nfs_atomic_lookup, .link = nfs_link, .unlink = nfs_unlink, @@ -150,51 +157,197 @@ nfs_opendir(struct inode *inode, struct file *filp) return res; } -typedef __be32 * (*decode_dirent_t)(__be32 *, struct nfs_entry *, int); +struct nfs_cache_array_entry { + u64 cookie; + u64 ino; + struct qstr string; +}; + +struct nfs_cache_array { + unsigned int size; + int eof_index; + u64 last_cookie; + struct nfs_cache_array_entry array[0]; +}; + +#define MAX_READDIR_ARRAY ((PAGE_SIZE - sizeof(struct nfs_cache_array)) / sizeof(struct nfs_cache_array_entry)) + +typedef __be32 * (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int); typedef struct { struct file *file; struct page *page; unsigned long page_index; - __be32 *ptr; u64 *dir_cookie; loff_t current_index; - struct nfs_entry *entry; decode_dirent_t decode; - int plus; + unsigned long timestamp; unsigned long gencount; - int timestamp_valid; + unsigned int cache_entry_index; + unsigned int plus:1; + unsigned int eof:1; } nfs_readdir_descriptor_t; -/* Now we cache directories properly, by stuffing the dirent - * data directly in the page cache. - * - * Inode invalidation due to refresh etc. takes care of - * _everything_, no sloppy entry flushing logic, no extraneous - * copying, network direct to page cache, the way it was meant - * to be. - * - * NOTE: Dirent information verification is done always by the - * page-in of the RPC reply, nowhere else, this simplies - * things substantially. +/* + * The caller is responsible for calling nfs_readdir_release_array(page) */ static -int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page) +struct nfs_cache_array *nfs_readdir_get_array(struct page *page) +{ + if (page == NULL) + return ERR_PTR(-EIO); + return (struct nfs_cache_array *)kmap(page); +} + +static +void nfs_readdir_release_array(struct page *page) +{ + kunmap(page); +} + +/* + * we are freeing strings created by nfs_add_to_readdir_array() + */ +static +int nfs_readdir_clear_array(struct page *page, gfp_t mask) +{ + struct nfs_cache_array *array = nfs_readdir_get_array(page); + int i; + for (i = 0; i < array->size; i++) + kfree(array->array[i].string.name); + nfs_readdir_release_array(page); + return 0; +} + +/* + * the caller is responsible for freeing qstr.name + * when called by nfs_readdir_add_to_array, the strings will be freed in + * nfs_clear_readdir_array() + */ +static +int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int len) +{ + string->len = len; + string->name = kmemdup(name, len, GFP_KERNEL); + if (string->name == NULL) + return -ENOMEM; + string->hash = full_name_hash(name, len); + return 0; +} + +static +int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page) +{ + struct nfs_cache_array *array = nfs_readdir_get_array(page); + struct nfs_cache_array_entry *cache_entry; + int ret; + + if (IS_ERR(array)) + return PTR_ERR(array); + ret = -EIO; + if (array->size >= MAX_READDIR_ARRAY) + goto out; + + cache_entry = &array->array[array->size]; + cache_entry->cookie = entry->prev_cookie; + cache_entry->ino = entry->ino; + ret = nfs_readdir_make_qstr(&cache_entry->string, entry->name, entry->len); + if (ret) + goto out; + array->last_cookie = entry->cookie; + if (entry->eof == 1) + array->eof_index = array->size; + array->size++; +out: + nfs_readdir_release_array(page); + return ret; +} + +static +int nfs_readdir_search_for_pos(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc) +{ + loff_t diff = desc->file->f_pos - desc->current_index; + unsigned int index; + + if (diff < 0) + goto out_eof; + if (diff >= array->size) { + if (array->eof_index > 0) + goto out_eof; + desc->current_index += array->size; + return -EAGAIN; + } + + index = (unsigned int)diff; + *desc->dir_cookie = array->array[index].cookie; + desc->cache_entry_index = index; + if (index == array->eof_index) + desc->eof = 1; + return 0; +out_eof: + desc->eof = 1; + return -EBADCOOKIE; +} + +static +int nfs_readdir_search_for_cookie(struct nfs_cache_array *array, nfs_readdir_descriptor_t *desc) +{ + int i; + int status = -EAGAIN; + + for (i = 0; i < array->size; i++) { + if (i == array->eof_index) { + desc->eof = 1; + status = -EBADCOOKIE; + } + if (array->array[i].cookie == *desc->dir_cookie) { + desc->cache_entry_index = i; + status = 0; + break; + } + } + + return status; +} + +static +int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc) +{ + struct nfs_cache_array *array; + int status = -EBADCOOKIE; + + if (desc->dir_cookie == NULL) + goto out; + + array = nfs_readdir_get_array(desc->page); + if (IS_ERR(array)) { + status = PTR_ERR(array); + goto out; + } + + if (*desc->dir_cookie == 0) + status = nfs_readdir_search_for_pos(array, desc); + else + status = nfs_readdir_search_for_cookie(array, desc); + + nfs_readdir_release_array(desc->page); +out: + return status; +} + +/* Fill a page with xdr information before transferring to the cache page */ +static +int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc, + struct nfs_entry *entry, struct file *file, struct inode *inode) { - struct file *file = desc->file; - struct inode *inode = file->f_path.dentry->d_inode; struct rpc_cred *cred = nfs_file_cred(file); unsigned long timestamp, gencount; int error; - dfprintk(DIRCACHE, "NFS: %s: reading cookie %Lu into page %lu\n", - __func__, (long long)desc->entry->cookie, - page->index); - again: timestamp = jiffies; gencount = nfs_inc_attr_generation_counter(); - error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, desc->entry->cookie, page, + error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, entry->cookie, pages, NFS_SERVER(inode)->dtsize, desc->plus); if (error < 0) { /* We requested READDIRPLUS, but the server doesn't grok it */ @@ -208,190 +361,292 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page) } desc->timestamp = timestamp; desc->gencount = gencount; - desc->timestamp_valid = 1; - SetPageUptodate(page); - /* Ensure consistent page alignment of the data. - * Note: assumes we have exclusive access to this mapping either - * through inode->i_mutex or some other mechanism. - */ - if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) { - /* Should never happen */ - nfs_zap_mapping(inode, inode->i_mapping); - } - unlock_page(page); - return 0; - error: - unlock_page(page); - return -EIO; +error: + return error; } -static inline -int dir_decode(nfs_readdir_descriptor_t *desc) +/* Fill in an entry based on the xdr code stored in desc->page */ +static +int xdr_decode(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, struct xdr_stream *stream) { - __be32 *p = desc->ptr; - p = desc->decode(p, desc->entry, desc->plus); + __be32 *p = desc->decode(stream, entry, NFS_SERVER(desc->file->f_path.dentry->d_inode), desc->plus); if (IS_ERR(p)) return PTR_ERR(p); - desc->ptr = p; - if (desc->timestamp_valid) { - desc->entry->fattr->time_start = desc->timestamp; - desc->entry->fattr->gencount = desc->gencount; - } else - desc->entry->fattr->valid &= ~NFS_ATTR_FATTR; + + entry->fattr->time_start = desc->timestamp; + entry->fattr->gencount = desc->gencount; return 0; } -static inline -void dir_page_release(nfs_readdir_descriptor_t *desc) +static +int nfs_same_file(struct dentry *dentry, struct nfs_entry *entry) { - kunmap(desc->page); - page_cache_release(desc->page); - desc->page = NULL; - desc->ptr = NULL; + struct nfs_inode *node; + if (dentry->d_inode == NULL) + goto different; + node = NFS_I(dentry->d_inode); + if (node->fh.size != entry->fh->size) + goto different; + if (strncmp(node->fh.data, entry->fh->data, node->fh.size) != 0) + goto different; + return 1; +different: + return 0; } -/* - * Given a pointer to a buffer that has already been filled by a call - * to readdir, find the next entry with cookie '*desc->dir_cookie'. - * - * If the end of the buffer has been reached, return -EAGAIN, if not, - * return the offset within the buffer of the next entry to be - * read. - */ -static inline -int find_dirent(nfs_readdir_descriptor_t *desc) +static +void nfs_prime_dcache(struct dentry *parent, struct nfs_entry *entry) { - struct nfs_entry *entry = desc->entry; - int loop_count = 0, - status; + struct qstr filename = { + .len = entry->len, + .name = entry->name, + }; + struct dentry *dentry; + struct dentry *alias; + struct inode *dir = parent->d_inode; + struct inode *inode; - while((status = dir_decode(desc)) == 0) { - dfprintk(DIRCACHE, "NFS: %s: examining cookie %Lu\n", - __func__, (unsigned long long)entry->cookie); - if (entry->prev_cookie == *desc->dir_cookie) - break; - if (loop_count++ > 200) { - loop_count = 0; - schedule(); + if (filename.name[0] == '.') { + if (filename.len == 1) + return; + if (filename.len == 2 && filename.name[1] == '.') + return; + } + filename.hash = full_name_hash(filename.name, filename.len); + + dentry = d_lookup(parent, &filename); + if (dentry != NULL) { + if (nfs_same_file(dentry, entry)) { + nfs_refresh_inode(dentry->d_inode, entry->fattr); + goto out; + } else { + d_drop(dentry); + dput(dentry); } } - return status; + + dentry = d_alloc(parent, &filename); + if (dentry == NULL) + return; + + dentry->d_op = NFS_PROTO(dir)->dentry_ops; + inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr); + if (IS_ERR(inode)) + goto out; + + alias = d_materialise_unique(dentry, inode); + if (IS_ERR(alias)) + goto out; + else if (alias) { + nfs_set_verifier(alias, nfs_save_change_attribute(dir)); + dput(alias); + } else + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + +out: + dput(dentry); +} + +/* Perform conversion from xdr to cache array */ +static +void nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *entry, + void *xdr_page, struct page *page, unsigned int buflen) +{ + struct xdr_stream stream; + struct xdr_buf buf; + __be32 *ptr = xdr_page; + int status; + struct nfs_cache_array *array; + + buf.head->iov_base = xdr_page; + buf.head->iov_len = buflen; + buf.tail->iov_len = 0; + buf.page_base = 0; + buf.page_len = 0; + buf.buflen = buf.head->iov_len; + buf.len = buf.head->iov_len; + + xdr_init_decode(&stream, &buf, ptr); + + + do { + status = xdr_decode(desc, entry, &stream); + if (status != 0) + break; + + if (nfs_readdir_add_to_array(entry, page) == -1) + break; + if (desc->plus == 1) + nfs_prime_dcache(desc->file->f_path.dentry, entry); + } while (!entry->eof); + + if (status == -EBADCOOKIE && entry->eof) { + array = nfs_readdir_get_array(page); + array->eof_index = array->size - 1; + status = 0; + nfs_readdir_release_array(page); + } +} + +static +void nfs_readdir_free_pagearray(struct page **pages, unsigned int npages) +{ + unsigned int i; + for (i = 0; i < npages; i++) + put_page(pages[i]); +} + +static +void nfs_readdir_free_large_page(void *ptr, struct page **pages, + unsigned int npages) +{ + vm_unmap_ram(ptr, npages); + nfs_readdir_free_pagearray(pages, npages); } /* - * Given a pointer to a buffer that has already been filled by a call - * to readdir, find the entry at offset 'desc->file->f_pos'. - * - * If the end of the buffer has been reached, return -EAGAIN, if not, - * return the offset within the buffer of the next entry to be - * read. + * nfs_readdir_large_page will allocate pages that must be freed with a call + * to nfs_readdir_free_large_page */ -static inline -int find_dirent_index(nfs_readdir_descriptor_t *desc) +static +void *nfs_readdir_large_page(struct page **pages, unsigned int npages) { - struct nfs_entry *entry = desc->entry; - int loop_count = 0, - status; + void *ptr; + unsigned int i; + + for (i = 0; i < npages; i++) { + struct page *page = alloc_page(GFP_KERNEL); + if (page == NULL) + goto out_freepages; + pages[i] = page; + } - for(;;) { - status = dir_decode(desc); - if (status) - break; + ptr = vm_map_ram(pages, npages, 0, PAGE_KERNEL); + if (!IS_ERR_OR_NULL(ptr)) + return ptr; +out_freepages: + nfs_readdir_free_pagearray(pages, i); + return NULL; +} + +static +int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page, struct inode *inode) +{ + struct page *pages[NFS_MAX_READDIR_PAGES]; + void *pages_ptr = NULL; + struct nfs_entry entry; + struct file *file = desc->file; + struct nfs_cache_array *array; + int status = 0; + unsigned int array_size = ARRAY_SIZE(pages); + + entry.prev_cookie = 0; + entry.cookie = *desc->dir_cookie; + entry.eof = 0; + entry.fh = nfs_alloc_fhandle(); + entry.fattr = nfs_alloc_fattr(); + if (entry.fh == NULL || entry.fattr == NULL) + goto out; - dfprintk(DIRCACHE, "NFS: found cookie %Lu at index %Ld\n", - (unsigned long long)entry->cookie, desc->current_index); + array = nfs_readdir_get_array(page); + memset(array, 0, sizeof(struct nfs_cache_array)); + array->eof_index = -1; - if (desc->file->f_pos == desc->current_index) { - *desc->dir_cookie = entry->cookie; + pages_ptr = nfs_readdir_large_page(pages, array_size); + if (!pages_ptr) + goto out_release_array; + do { + status = nfs_readdir_xdr_filler(pages, desc, &entry, file, inode); + + if (status < 0) break; - } - desc->current_index++; - if (loop_count++ > 200) { - loop_count = 0; - schedule(); - } - } + nfs_readdir_page_filler(desc, &entry, pages_ptr, page, array_size * PAGE_SIZE); + } while (array->eof_index < 0 && array->size < MAX_READDIR_ARRAY); + + nfs_readdir_free_large_page(pages_ptr, pages, array_size); +out_release_array: + nfs_readdir_release_array(page); +out: + nfs_free_fattr(entry.fattr); + nfs_free_fhandle(entry.fh); return status; } /* - * Find the given page, and call find_dirent() or find_dirent_index in - * order to try to return the next entry. + * Now we cache directories properly, by converting xdr information + * to an array that can be used for lookups later. This results in + * fewer cache pages, since we can store more information on each page. + * We only need to convert from xdr once so future lookups are much simpler */ -static inline -int find_dirent_page(nfs_readdir_descriptor_t *desc) +static +int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page) { struct inode *inode = desc->file->f_path.dentry->d_inode; - struct page *page; - int status; - dfprintk(DIRCACHE, "NFS: %s: searching page %ld for target %Lu\n", - __func__, desc->page_index, - (long long) *desc->dir_cookie); + if (nfs_readdir_xdr_to_array(desc, page, inode) < 0) + goto error; + SetPageUptodate(page); - /* If we find the page in the page_cache, we cannot be sure - * how fresh the data is, so we will ignore readdir_plus attributes. - */ - desc->timestamp_valid = 0; - page = read_cache_page(inode->i_mapping, desc->page_index, - (filler_t *)nfs_readdir_filler, desc); - if (IS_ERR(page)) { - status = PTR_ERR(page); - goto out; + if (invalidate_inode_pages2_range(inode->i_mapping, page->index + 1, -1) < 0) { + /* Should never happen */ + nfs_zap_mapping(inode, inode->i_mapping); } + unlock_page(page); + return 0; + error: + unlock_page(page); + return -EIO; +} - /* NOTE: Someone else may have changed the READDIRPLUS flag */ - desc->page = page; - desc->ptr = kmap(page); /* matching kunmap in nfs_do_filldir */ - if (*desc->dir_cookie != 0) - status = find_dirent(desc); - else - status = find_dirent_index(desc); - if (status < 0) - dir_page_release(desc); - out: - dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status); - return status; +static +void cache_page_release(nfs_readdir_descriptor_t *desc) +{ + page_cache_release(desc->page); + desc->page = NULL; +} + +static +struct page *get_cache_page(nfs_readdir_descriptor_t *desc) +{ + struct page *page; + page = read_cache_page(desc->file->f_path.dentry->d_inode->i_mapping, + desc->page_index, (filler_t *)nfs_readdir_filler, desc); + if (IS_ERR(page)) + desc->eof = 1; + return page; } /* - * Recurse through the page cache pages, and return a - * filled nfs_entry structure of the next directory entry if possible. - * - * The target for the search is '*desc->dir_cookie' if non-0, - * 'desc->file->f_pos' otherwise + * Returns 0 if desc->dir_cookie was found on page desc->page_index */ +static +int find_cache_page(nfs_readdir_descriptor_t *desc) +{ + int res; + + desc->page = get_cache_page(desc); + if (IS_ERR(desc->page)) + return PTR_ERR(desc->page); + + res = nfs_readdir_search_array(desc); + if (res == 0) + return 0; + cache_page_release(desc); + return res; +} + +/* Search for desc->dir_cookie from the beginning of the page cache */ static inline int readdir_search_pagecache(nfs_readdir_descriptor_t *desc) { - int loop_count = 0; - int res; - - /* Always search-by-index from the beginning of the cache */ - if (*desc->dir_cookie == 0) { - dfprintk(DIRCACHE, "NFS: readdir_search_pagecache() searching for offset %Ld\n", - (long long)desc->file->f_pos); - desc->page_index = 0; - desc->entry->cookie = desc->entry->prev_cookie = 0; - desc->entry->eof = 0; - desc->current_index = 0; - } else - dfprintk(DIRCACHE, "NFS: readdir_search_pagecache() searching for cookie %Lu\n", - (unsigned long long)*desc->dir_cookie); + int res = -EAGAIN; - for (;;) { - res = find_dirent_page(desc); + while (1) { + res = find_cache_page(desc); if (res != -EAGAIN) break; - /* Align to beginning of next page */ - desc->page_index ++; - if (loop_count++ > 200) { - loop_count = 0; - schedule(); - } + desc->page_index++; } - - dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, res); return res; } @@ -400,8 +655,6 @@ static inline unsigned int dt_type(struct inode *inode) return (inode->i_mode >> 12) & 15; } -static struct dentry *nfs_readdir_lookup(nfs_readdir_descriptor_t *desc); - /* * Once we've found the start of the dirent within a page: fill 'er up... */ @@ -410,49 +663,36 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc, void *dirent, filldir_t filldir) { struct file *file = desc->file; - struct nfs_entry *entry = desc->entry; - struct dentry *dentry = NULL; - u64 fileid; - int loop_count = 0, - res; - - dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling starting @ cookie %Lu\n", - (unsigned long long)entry->cookie); - - for(;;) { - unsigned d_type = DT_UNKNOWN; - /* Note: entry->prev_cookie contains the cookie for - * retrieving the current dirent on the server */ - fileid = entry->ino; - - /* Get a dentry if we have one */ - if (dentry != NULL) - dput(dentry); - dentry = nfs_readdir_lookup(desc); + int i = 0; + int res = 0; + struct nfs_cache_array *array = NULL; + unsigned int d_type = DT_UNKNOWN; + struct dentry *dentry = NULL; - /* Use readdirplus info */ - if (dentry != NULL && dentry->d_inode != NULL) { - d_type = dt_type(dentry->d_inode); - fileid = NFS_FILEID(dentry->d_inode); - } + array = nfs_readdir_get_array(desc->page); - res = filldir(dirent, entry->name, entry->len, - file->f_pos, nfs_compat_user_ino64(fileid), - d_type); + for (i = desc->cache_entry_index; i < array->size; i++) { + d_type = DT_UNKNOWN; + + res = filldir(dirent, array->array[i].string.name, + array->array[i].string.len, file->f_pos, + nfs_compat_user_ino64(array->array[i].ino), d_type); if (res < 0) break; file->f_pos++; - *desc->dir_cookie = entry->cookie; - if (dir_decode(desc) != 0) { - desc->page_index ++; + desc->cache_entry_index = i; + if (i < (array->size-1)) + *desc->dir_cookie = array->array[i+1].cookie; + else + *desc->dir_cookie = array->last_cookie; + if (i == array->eof_index) { + desc->eof = 1; break; } - if (loop_count++ > 200) { - loop_count = 0; - schedule(); - } } - dir_page_release(desc); + + nfs_readdir_release_array(desc->page); + cache_page_release(desc); if (dentry != NULL) dput(dentry); dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n", @@ -476,12 +716,9 @@ static inline int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent, filldir_t filldir) { - struct file *file = desc->file; - struct inode *inode = file->f_path.dentry->d_inode; - struct rpc_cred *cred = nfs_file_cred(file); struct page *page = NULL; int status; - unsigned long timestamp, gencount; + struct inode *inode = desc->file->f_path.dentry->d_inode; dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n", (unsigned long long)*desc->dir_cookie); @@ -491,38 +728,22 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent, status = -ENOMEM; goto out; } - timestamp = jiffies; - gencount = nfs_inc_attr_generation_counter(); - status = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, - *desc->dir_cookie, page, - NFS_SERVER(inode)->dtsize, - desc->plus); - desc->page = page; - desc->ptr = kmap(page); /* matching kunmap in nfs_do_filldir */ - if (status >= 0) { - desc->timestamp = timestamp; - desc->gencount = gencount; - desc->timestamp_valid = 1; - if ((status = dir_decode(desc)) == 0) - desc->entry->prev_cookie = *desc->dir_cookie; - } else + + if (nfs_readdir_xdr_to_array(desc, page, inode) == -1) { status = -EIO; - if (status < 0) goto out_release; + } + desc->page_index = 0; + desc->page = page; status = nfs_do_filldir(desc, dirent, filldir); - /* Reset read descriptor so it searches the page cache from - * the start upon the next call to readdir_search_pagecache() */ - desc->page_index = 0; - desc->entry->cookie = desc->entry->prev_cookie = 0; - desc->entry->eof = 0; out: dfprintk(DIRCACHE, "NFS: %s: returns %d\n", __func__, status); return status; out_release: - dir_page_release(desc); + cache_page_release(desc); goto out; } @@ -536,7 +757,6 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) struct inode *inode = dentry->d_inode; nfs_readdir_descriptor_t my_desc, *desc = &my_desc; - struct nfs_entry my_entry; int res = -ENOMEM; dfprintk(FILE, "NFS: readdir(%s/%s) starting at cookie %llu\n", @@ -557,26 +777,17 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) desc->decode = NFS_PROTO(inode)->decode_dirent; desc->plus = NFS_USE_READDIRPLUS(inode); - my_entry.cookie = my_entry.prev_cookie = 0; - my_entry.eof = 0; - my_entry.fh = nfs_alloc_fhandle(); - my_entry.fattr = nfs_alloc_fattr(); - if (my_entry.fh == NULL || my_entry.fattr == NULL) - goto out_alloc_failed; - - desc->entry = &my_entry; - nfs_block_sillyrename(dentry); res = nfs_revalidate_mapping(inode, filp->f_mapping); if (res < 0) goto out; - while(!desc->entry->eof) { + while (desc->eof != 1) { res = readdir_search_pagecache(desc); if (res == -EBADCOOKIE) { /* This means either end of directory */ - if (*desc->dir_cookie && desc->entry->cookie != *desc->dir_cookie) { + if (*desc->dir_cookie && desc->eof == 0) { /* Or that the server has 'lost' a cookie */ res = uncached_readdir(desc, dirent, filldir); if (res >= 0) @@ -588,8 +799,9 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) if (res == -ETOOSMALL && desc->plus) { clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); nfs_zap_caches(inode); + desc->page_index = 0; desc->plus = 0; - desc->entry->eof = 0; + desc->eof = 0; continue; } if (res < 0) @@ -605,9 +817,6 @@ out: nfs_unblock_sillyrename(dentry); if (res > 0) res = 0; -out_alloc_failed: - nfs_free_fattr(my_entry.fattr); - nfs_free_fhandle(my_entry.fh); dfprintk(FILE, "NFS: readdir(%s/%s) returns %d\n", dentry->d_parent->d_name.name, dentry->d_name.name, res); @@ -1029,10 +1238,63 @@ static int is_atomic_open(struct nameidata *nd) return 1; } +static struct nfs_open_context *nameidata_to_nfs_open_context(struct dentry *dentry, struct nameidata *nd) +{ + struct path path = { + .mnt = nd->path.mnt, + .dentry = dentry, + }; + struct nfs_open_context *ctx; + struct rpc_cred *cred; + fmode_t fmode = nd->intent.open.flags & (FMODE_READ | FMODE_WRITE | FMODE_EXEC); + + cred = rpc_lookup_cred(); + if (IS_ERR(cred)) + return ERR_CAST(cred); + ctx = alloc_nfs_open_context(&path, cred, fmode); + put_rpccred(cred); + if (ctx == NULL) + return ERR_PTR(-ENOMEM); + return ctx; +} + +static int do_open(struct inode *inode, struct file *filp) +{ + nfs_fscache_set_inode_cookie(inode, filp); + return 0; +} + +static int nfs_intent_set_file(struct nameidata *nd, struct nfs_open_context *ctx) +{ + struct file *filp; + int ret = 0; + + /* If the open_intent is for execute, we have an extra check to make */ + if (ctx->mode & FMODE_EXEC) { + ret = nfs_may_open(ctx->path.dentry->d_inode, + ctx->cred, + nd->intent.open.flags); + if (ret < 0) + goto out; + } + filp = lookup_instantiate_filp(nd, ctx->path.dentry, do_open); + if (IS_ERR(filp)) + ret = PTR_ERR(filp); + else + nfs_file_set_open_context(filp, ctx); +out: + put_nfs_open_context(ctx); + return ret; +} + static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry, struct nameidata *nd) { + struct nfs_open_context *ctx; + struct iattr attr; struct dentry *res = NULL; - int error; + struct inode *inode; + int open_flags; + int err; dfprintk(VFS, "NFS: atomic_lookup(%s/%ld), %s\n", dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); @@ -1054,13 +1316,32 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry goto out; } + ctx = nameidata_to_nfs_open_context(dentry, nd); + res = ERR_CAST(ctx); + if (IS_ERR(ctx)) + goto out; + + open_flags = nd->intent.open.flags; + if (nd->flags & LOOKUP_CREATE) { + attr.ia_mode = nd->intent.open.create_mode; + attr.ia_valid = ATTR_MODE; + if (!IS_POSIXACL(dir)) + attr.ia_mode &= ~current_umask(); + } else { + open_flags &= ~(O_EXCL | O_CREAT); + attr.ia_valid = 0; + } + /* Open the file on the server */ - res = nfs4_atomic_open(dir, dentry, nd); - if (IS_ERR(res)) { - error = PTR_ERR(res); - switch (error) { + nfs_block_sillyrename(dentry->d_parent); + inode = NFS_PROTO(dir)->open_context(dir, ctx, open_flags, &attr); + if (IS_ERR(inode)) { + nfs_unblock_sillyrename(dentry->d_parent); + put_nfs_open_context(ctx); + switch (PTR_ERR(inode)) { /* Make a negative dentry */ case -ENOENT: + d_add(dentry, NULL); res = NULL; goto out; /* This turned out not to be a regular file */ @@ -1072,11 +1353,25 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry goto no_open; /* case -EINVAL: */ default: + res = ERR_CAST(inode); goto out; } - } else if (res != NULL) + } + res = d_add_unique(dentry, inode); + nfs_unblock_sillyrename(dentry->d_parent); + if (res != NULL) { + dput(ctx->path.dentry); + ctx->path.dentry = dget(res); dentry = res; + } + err = nfs_intent_set_file(nd, ctx); + if (err < 0) { + if (res != NULL) + dput(res); + return ERR_PTR(err); + } out: + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); return res; no_open: return nfs_lookup(dir, dentry, nd); @@ -1087,12 +1382,15 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd) struct dentry *parent = NULL; struct inode *inode = dentry->d_inode; struct inode *dir; + struct nfs_open_context *ctx; int openflags, ret = 0; if (!is_atomic_open(nd) || d_mountpoint(dentry)) goto no_open; + parent = dget_parent(dentry); dir = parent->d_inode; + /* We can't create new files in nfs_open_revalidate(), so we * optimize away revalidation of negative dentries. */ @@ -1112,99 +1410,96 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd) /* We can't create new files, or truncate existing ones here */ openflags &= ~(O_CREAT|O_EXCL|O_TRUNC); + ctx = nameidata_to_nfs_open_context(dentry, nd); + ret = PTR_ERR(ctx); + if (IS_ERR(ctx)) + goto out; /* * Note: we're not holding inode->i_mutex and so may be racing with * operations that change the directory. We therefore save the * change attribute *before* we do the RPC call. */ - ret = nfs4_open_revalidate(dir, dentry, openflags, nd); + inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, NULL); + if (IS_ERR(inode)) { + ret = PTR_ERR(inode); + switch (ret) { + case -EPERM: + case -EACCES: + case -EDQUOT: + case -ENOSPC: + case -EROFS: + goto out_put_ctx; + default: + goto out_drop; + } + } + iput(inode); + if (inode != dentry->d_inode) + goto out_drop; + + nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); + ret = nfs_intent_set_file(nd, ctx); + if (ret >= 0) + ret = 1; out: dput(parent); - if (!ret) - d_drop(dentry); return ret; +out_drop: + d_drop(dentry); + ret = 0; +out_put_ctx: + put_nfs_open_context(ctx); + goto out; + no_open_dput: dput(parent); no_open: return nfs_lookup_revalidate(dentry, nd); } -#endif /* CONFIG_NFSV4 */ -static struct dentry *nfs_readdir_lookup(nfs_readdir_descriptor_t *desc) +static int nfs_open_create(struct inode *dir, struct dentry *dentry, int mode, + struct nameidata *nd) { - struct dentry *parent = desc->file->f_path.dentry; - struct inode *dir = parent->d_inode; - struct nfs_entry *entry = desc->entry; - struct dentry *dentry, *alias; - struct qstr name = { - .name = entry->name, - .len = entry->len, - }; - struct inode *inode; - unsigned long verf = nfs_save_change_attribute(dir); + struct nfs_open_context *ctx = NULL; + struct iattr attr; + int error; + int open_flags = 0; - switch (name.len) { - case 2: - if (name.name[0] == '.' && name.name[1] == '.') - return dget_parent(parent); - break; - case 1: - if (name.name[0] == '.') - return dget(parent); - } + dfprintk(VFS, "NFS: create(%s/%ld), %s\n", + dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); - spin_lock(&dir->i_lock); - if (NFS_I(dir)->cache_validity & NFS_INO_INVALID_DATA) { - spin_unlock(&dir->i_lock); - return NULL; - } - spin_unlock(&dir->i_lock); + attr.ia_mode = mode; + attr.ia_valid = ATTR_MODE; - name.hash = full_name_hash(name.name, name.len); - dentry = d_lookup(parent, &name); - if (dentry != NULL) { - /* Is this a positive dentry that matches the readdir info? */ - if (dentry->d_inode != NULL && - (NFS_FILEID(dentry->d_inode) == entry->ino || - d_mountpoint(dentry))) { - if (!desc->plus || entry->fh->size == 0) - return dentry; - if (nfs_compare_fh(NFS_FH(dentry->d_inode), - entry->fh) == 0) - goto out_renew; - } - /* No, so d_drop to allow one to be created */ - d_drop(dentry); - dput(dentry); - } - if (!desc->plus || !(entry->fattr->valid & NFS_ATTR_FATTR)) - return NULL; - if (name.len > NFS_SERVER(dir)->namelen) - return NULL; - /* Note: caller is already holding the dir->i_mutex! */ - dentry = d_alloc(parent, &name); - if (dentry == NULL) - return NULL; - dentry->d_op = NFS_PROTO(dir)->dentry_ops; - inode = nfs_fhget(dentry->d_sb, entry->fh, entry->fattr); - if (IS_ERR(inode)) { - dput(dentry); - return NULL; - } + if ((nd->flags & LOOKUP_CREATE) != 0) { + open_flags = nd->intent.open.flags; - alias = d_materialise_unique(dentry, inode); - if (alias != NULL) { - dput(dentry); - if (IS_ERR(alias)) - return NULL; - dentry = alias; + ctx = nameidata_to_nfs_open_context(dentry, nd); + error = PTR_ERR(ctx); + if (IS_ERR(ctx)) + goto out_err_drop; } -out_renew: - nfs_set_verifier(dentry, verf); - return dentry; + error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, ctx); + if (error != 0) + goto out_put_ctx; + if (ctx != NULL) { + error = nfs_intent_set_file(nd, ctx); + if (error < 0) + goto out_err; + } + return 0; +out_put_ctx: + if (ctx != NULL) + put_nfs_open_context(ctx); +out_err_drop: + d_drop(dentry); +out_err: + return error; } +#endif /* CONFIG_NFSV4 */ + /* * Code common to create, mkdir, and mknod. */ @@ -1258,7 +1553,6 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode, { struct iattr attr; int error; - int open_flags = 0; dfprintk(VFS, "NFS: create(%s/%ld), %s\n", dir->i_sb->s_id, dir->i_ino, dentry->d_name.name); @@ -1266,10 +1560,7 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode, attr.ia_mode = mode; attr.ia_valid = ATTR_MODE; - if ((nd->flags & LOOKUP_CREATE) != 0) - open_flags = nd->intent.open.flags; - - error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, nd); + error = NFS_PROTO(dir)->create(dir, dentry, &attr, 0, NULL); if (error != 0) goto out_err; return 0; @@ -1351,76 +1642,6 @@ static int nfs_rmdir(struct inode *dir, struct dentry *dentry) return error; } -static int nfs_sillyrename(struct inode *dir, struct dentry *dentry) -{ - static unsigned int sillycounter; - const int fileidsize = sizeof(NFS_FILEID(dentry->d_inode))*2; - const int countersize = sizeof(sillycounter)*2; - const int slen = sizeof(".nfs")+fileidsize+countersize-1; - char silly[slen+1]; - struct qstr qsilly; - struct dentry *sdentry; - int error = -EIO; - - dfprintk(VFS, "NFS: silly-rename(%s/%s, ct=%d)\n", - dentry->d_parent->d_name.name, dentry->d_name.name, - atomic_read(&dentry->d_count)); - nfs_inc_stats(dir, NFSIOS_SILLYRENAME); - - /* - * We don't allow a dentry to be silly-renamed twice. - */ - error = -EBUSY; - if (dentry->d_flags & DCACHE_NFSFS_RENAMED) - goto out; - - sprintf(silly, ".nfs%*.*Lx", - fileidsize, fileidsize, - (unsigned long long)NFS_FILEID(dentry->d_inode)); - - /* Return delegation in anticipation of the rename */ - nfs_inode_return_delegation(dentry->d_inode); - - sdentry = NULL; - do { - char *suffix = silly + slen - countersize; - - dput(sdentry); - sillycounter++; - sprintf(suffix, "%*.*x", countersize, countersize, sillycounter); - - dfprintk(VFS, "NFS: trying to rename %s to %s\n", - dentry->d_name.name, silly); - - sdentry = lookup_one_len(silly, dentry->d_parent, slen); - /* - * N.B. Better to return EBUSY here ... it could be - * dangerous to delete the file while it's in use. - */ - if (IS_ERR(sdentry)) - goto out; - } while(sdentry->d_inode != NULL); /* need negative lookup */ - - qsilly.name = silly; - qsilly.len = strlen(silly); - if (dentry->d_inode) { - error = NFS_PROTO(dir)->rename(dir, &dentry->d_name, - dir, &qsilly); - nfs_mark_for_revalidate(dentry->d_inode); - } else - error = NFS_PROTO(dir)->rename(dir, &dentry->d_name, - dir, &qsilly); - if (!error) { - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - d_move(dentry, sdentry); - error = nfs_async_unlink(dir, dentry); - /* If we return 0 we don't unlink */ - } - dput(sdentry); -out: - return error; -} - /* * Remove a file after making sure there are no pending writes, * and after checking that the file has only one user. @@ -1580,7 +1801,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) d_drop(dentry); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); if (error == 0) { - atomic_inc(&inode->i_count); + ihold(inode); d_add(dentry, inode); } return error; @@ -1711,14 +1932,14 @@ static void nfs_access_free_list(struct list_head *head) int nfs_access_cache_shrinker(struct shrinker *shrink, int nr_to_scan, gfp_t gfp_mask) { LIST_HEAD(head); - struct nfs_inode *nfsi; + struct nfs_inode *nfsi, *next; struct nfs_access_entry *cache; if ((gfp_mask & GFP_KERNEL) != GFP_KERNEL) return (nr_to_scan == 0) ? 0 : -1; spin_lock(&nfs_access_lru_lock); - list_for_each_entry(nfsi, &nfs_access_lru_list, access_cache_inode_lru) { + list_for_each_entry_safe(nfsi, next, &nfs_access_lru_list, access_cache_inode_lru) { struct inode *inode; if (nr_to_scan-- == 0) diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 064a80961677..84d3c8b90206 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -873,7 +873,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, dreq->inode = inode; dreq->ctx = get_nfs_open_context(nfs_file_open_context(iocb->ki_filp)); dreq->l_ctx = nfs_get_lock_context(dreq->ctx); - if (dreq->l_ctx != NULL) + if (dreq->l_ctx == NULL) goto out_release; if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index dba50a5625db..a6e711ad130f 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -167,7 +167,7 @@ static int nfs_dns_show(struct seq_file *m, struct cache_detail *cd, return 0; } item = container_of(h, struct nfs_dns_ent, h); - ttl = (long)item->h.expiry_time - (long)get_seconds(); + ttl = item->h.expiry_time - seconds_since_boot(); if (ttl < 0) ttl = 0; @@ -239,7 +239,7 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen) ttl = get_expiry(&buf); if (ttl == 0) goto out; - key.h.expiry_time = ttl + get_seconds(); + key.h.expiry_time = ttl + seconds_since_boot(); ret = -ENOMEM; item = nfs_dns_lookup(cd, &key); @@ -301,7 +301,7 @@ static int do_cache_lookup_nowait(struct cache_detail *cd, goto out_err; ret = -ETIMEDOUT; if (!test_bit(CACHE_VALID, &(*item)->h.flags) - || (*item)->h.expiry_time < get_seconds() + || (*item)->h.expiry_time < seconds_since_boot() || cd->flush_time > (*item)->h.last_refresh) goto out_put; ret = -ENOENT; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index 05bf3c0dc751..e756075637b0 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -36,6 +36,7 @@ #include "internal.h" #include "iostat.h" #include "fscache.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_FILE @@ -386,6 +387,10 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping, file->f_path.dentry->d_name.name, mapping->host->i_ino, len, (long long) pos); + pnfs_update_layout(mapping->host, + nfs_file_open_context(file), + IOMODE_RW); + start: /* * Prevent starvation issues if someone is doing a consistency @@ -551,7 +556,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) struct file *filp = vma->vm_file; struct dentry *dentry = filp->f_path.dentry; unsigned pagelen; - int ret = -EINVAL; + int ret = VM_FAULT_NOPAGE; struct address_space *mapping; dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%s/%s(%ld), offset %lld)\n", @@ -567,21 +572,20 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) if (mapping != dentry->d_inode->i_mapping) goto out_unlock; - ret = 0; pagelen = nfs_page_length(page); if (pagelen == 0) goto out_unlock; - ret = nfs_flush_incompatible(filp, page); - if (ret != 0) - goto out_unlock; + ret = VM_FAULT_LOCKED; + if (nfs_flush_incompatible(filp, page) == 0 && + nfs_updatepage(filp, page, 0, pagelen) == 0) + goto out; - ret = nfs_updatepage(filp, page, 0, pagelen); + ret = VM_FAULT_SIGBUS; out_unlock: - if (!ret) - return VM_FAULT_LOCKED; unlock_page(page); - return VM_FAULT_SIGBUS; +out: + return ret; } static const struct vm_operations_struct nfs_file_vm_ops = { @@ -684,7 +688,8 @@ static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe, return ret; } -static int do_getlk(struct file *filp, int cmd, struct file_lock *fl) +static int +do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) { struct inode *inode = filp->f_mapping->host; int status = 0; @@ -699,7 +704,7 @@ static int do_getlk(struct file *filp, int cmd, struct file_lock *fl) if (nfs_have_delegation(inode, FMODE_READ)) goto out_noconflict; - if (NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM) + if (is_local) goto out_noconflict; status = NFS_PROTO(inode)->lock(filp, cmd, fl); @@ -726,7 +731,8 @@ static int do_vfs_lock(struct file *file, struct file_lock *fl) return res; } -static int do_unlk(struct file *filp, int cmd, struct file_lock *fl) +static int +do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) { struct inode *inode = filp->f_mapping->host; int status; @@ -741,15 +747,24 @@ static int do_unlk(struct file *filp, int cmd, struct file_lock *fl) * If we're signalled while cleaning up locks on process exit, we * still need to complete the unlock. */ - /* Use local locking if mounted with "-onolock" */ - if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM)) + /* + * Use local locking if mounted with "-onolock" or with appropriate + * "-olocal_lock=" + */ + if (!is_local) status = NFS_PROTO(inode)->lock(filp, cmd, fl); else status = do_vfs_lock(filp, fl); return status; } -static int do_setlk(struct file *filp, int cmd, struct file_lock *fl) +static int +is_time_granular(struct timespec *ts) { + return ((ts->tv_sec == 0) && (ts->tv_nsec <= 1000)); +} + +static int +do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) { struct inode *inode = filp->f_mapping->host; int status; @@ -762,20 +777,31 @@ static int do_setlk(struct file *filp, int cmd, struct file_lock *fl) if (status != 0) goto out; - /* Use local locking if mounted with "-onolock" */ - if (!(NFS_SERVER(inode)->flags & NFS_MOUNT_NONLM)) + /* + * Use local locking if mounted with "-onolock" or with appropriate + * "-olocal_lock=" + */ + if (!is_local) status = NFS_PROTO(inode)->lock(filp, cmd, fl); else status = do_vfs_lock(filp, fl); if (status < 0) goto out; + /* - * Make sure we clear the cache whenever we try to get the lock. + * Revalidate the cache if the server has time stamps granular + * enough to detect subsecond changes. Otherwise, clear the + * cache to prevent missing any changes. + * * This makes locking act as a cache coherency point. */ nfs_sync_mapping(filp->f_mapping); - if (!nfs_have_delegation(inode, FMODE_READ)) - nfs_zap_caches(inode); + if (!nfs_have_delegation(inode, FMODE_READ)) { + if (is_time_granular(&NFS_SERVER(inode)->time_delta)) + __nfs_revalidate_inode(NFS_SERVER(inode), inode); + else + nfs_zap_caches(inode); + } out: return status; } @@ -787,6 +813,7 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl) { struct inode *inode = filp->f_mapping->host; int ret = -ENOLCK; + int is_local = 0; dprintk("NFS: lock(%s/%s, t=%x, fl=%x, r=%lld:%lld)\n", filp->f_path.dentry->d_parent->d_name.name, @@ -800,6 +827,9 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl) if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK) goto out_err; + if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FCNTL) + is_local = 1; + if (NFS_PROTO(inode)->lock_check_bounds != NULL) { ret = NFS_PROTO(inode)->lock_check_bounds(fl); if (ret < 0) @@ -807,11 +837,11 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl) } if (IS_GETLK(cmd)) - ret = do_getlk(filp, cmd, fl); + ret = do_getlk(filp, cmd, fl, is_local); else if (fl->fl_type == F_UNLCK) - ret = do_unlk(filp, cmd, fl); + ret = do_unlk(filp, cmd, fl, is_local); else - ret = do_setlk(filp, cmd, fl); + ret = do_setlk(filp, cmd, fl, is_local); out_err: return ret; } @@ -821,6 +851,9 @@ out_err: */ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl) { + struct inode *inode = filp->f_mapping->host; + int is_local = 0; + dprintk("NFS: flock(%s/%s, t=%x, fl=%x)\n", filp->f_path.dentry->d_parent->d_name.name, filp->f_path.dentry->d_name.name, @@ -829,14 +862,17 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; + if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK) + is_local = 1; + /* We're simulating flock() locks using posix locks on the server */ fl->fl_owner = (fl_owner_t)filp; fl->fl_start = 0; fl->fl_end = OFFSET_MAX; if (fl->fl_type == F_UNLCK) - return do_unlk(filp, cmd, fl); - return do_setlk(filp, cmd, fl); + return do_unlk(filp, cmd, fl, is_local); + return do_setlk(filp, cmd, fl, is_local); } /* diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index a70e446e1605..ac7b814ce162 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -54,8 +54,7 @@ static int nfs_superblock_set_dummy_root(struct super_block *sb, struct inode *i iput(inode); return -ENOMEM; } - /* Circumvent igrab(): we know the inode is not being freed */ - atomic_inc(&inode->i_count); + ihold(inode); /* * Ensure that this dentry is invisible to d_find_alias(). * Otherwise, it may be spliced into the tree by diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 21a84d45916f..4e2d9b6b1380 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -34,6 +34,212 @@ * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE. */ +#ifdef CONFIG_NFS_USE_NEW_IDMAPPER + +#include <linux/slab.h> +#include <linux/cred.h> +#include <linux/nfs_idmap.h> +#include <linux/keyctl.h> +#include <linux/key-type.h> +#include <linux/rcupdate.h> +#include <linux/kernel.h> +#include <linux/err.h> + +#include <keys/user-type.h> + +#define NFS_UINT_MAXLEN 11 + +const struct cred *id_resolver_cache; + +struct key_type key_type_id_resolver = { + .name = "id_resolver", + .instantiate = user_instantiate, + .match = user_match, + .revoke = user_revoke, + .destroy = user_destroy, + .describe = user_describe, + .read = user_read, +}; + +int nfs_idmap_init(void) +{ + struct cred *cred; + struct key *keyring; + int ret = 0; + + printk(KERN_NOTICE "Registering the %s key type\n", key_type_id_resolver.name); + + cred = prepare_kernel_cred(NULL); + if (!cred) + return -ENOMEM; + + keyring = key_alloc(&key_type_keyring, ".id_resolver", 0, 0, cred, + (KEY_POS_ALL & ~KEY_POS_SETATTR) | + KEY_USR_VIEW | KEY_USR_READ, + KEY_ALLOC_NOT_IN_QUOTA); + if (IS_ERR(keyring)) { + ret = PTR_ERR(keyring); + goto failed_put_cred; + } + + ret = key_instantiate_and_link(keyring, NULL, 0, NULL, NULL); + if (ret < 0) + goto failed_put_key; + + ret = register_key_type(&key_type_id_resolver); + if (ret < 0) + goto failed_put_key; + + cred->thread_keyring = keyring; + cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; + id_resolver_cache = cred; + return 0; + +failed_put_key: + key_put(keyring); +failed_put_cred: + put_cred(cred); + return ret; +} + +void nfs_idmap_quit(void) +{ + key_revoke(id_resolver_cache->thread_keyring); + unregister_key_type(&key_type_id_resolver); + put_cred(id_resolver_cache); +} + +/* + * Assemble the description to pass to request_key() + * This function will allocate a new string and update dest to point + * at it. The caller is responsible for freeing dest. + * + * On error 0 is returned. Otherwise, the length of dest is returned. + */ +static ssize_t nfs_idmap_get_desc(const char *name, size_t namelen, + const char *type, size_t typelen, char **desc) +{ + char *cp; + size_t desclen = typelen + namelen + 2; + + *desc = kmalloc(desclen, GFP_KERNEL); + if (!*desc) + return -ENOMEM; + + cp = *desc; + memcpy(cp, type, typelen); + cp += typelen; + *cp++ = ':'; + + memcpy(cp, name, namelen); + cp += namelen; + *cp = '\0'; + return desclen; +} + +static ssize_t nfs_idmap_request_key(const char *name, size_t namelen, + const char *type, void *data, size_t data_size) +{ + const struct cred *saved_cred; + struct key *rkey; + char *desc; + struct user_key_payload *payload; + ssize_t ret; + + ret = nfs_idmap_get_desc(name, namelen, type, strlen(type), &desc); + if (ret <= 0) + goto out; + + saved_cred = override_creds(id_resolver_cache); + rkey = request_key(&key_type_id_resolver, desc, ""); + revert_creds(saved_cred); + kfree(desc); + if (IS_ERR(rkey)) { + ret = PTR_ERR(rkey); + goto out; + } + + rcu_read_lock(); + rkey->perm |= KEY_USR_VIEW; + + ret = key_validate(rkey); + if (ret < 0) + goto out_up; + + payload = rcu_dereference(rkey->payload.data); + if (IS_ERR_OR_NULL(payload)) { + ret = PTR_ERR(payload); + goto out_up; + } + + ret = payload->datalen; + if (ret > 0 && ret <= data_size) + memcpy(data, payload->data, ret); + else + ret = -EINVAL; + +out_up: + rcu_read_unlock(); + key_put(rkey); +out: + return ret; +} + + +/* ID -> Name */ +static ssize_t nfs_idmap_lookup_name(__u32 id, const char *type, char *buf, size_t buflen) +{ + char id_str[NFS_UINT_MAXLEN]; + int id_len; + ssize_t ret; + + id_len = snprintf(id_str, sizeof(id_str), "%u", id); + ret = nfs_idmap_request_key(id_str, id_len, type, buf, buflen); + if (ret < 0) + return -EINVAL; + return ret; +} + +/* Name -> ID */ +static int nfs_idmap_lookup_id(const char *name, size_t namelen, + const char *type, __u32 *id) +{ + char id_str[NFS_UINT_MAXLEN]; + long id_long; + ssize_t data_size; + int ret = 0; + + data_size = nfs_idmap_request_key(name, namelen, type, id_str, NFS_UINT_MAXLEN); + if (data_size <= 0) { + ret = -EINVAL; + } else { + ret = strict_strtol(id_str, 10, &id_long); + *id = (__u32)id_long; + } + return ret; +} + +int nfs_map_name_to_uid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *uid) +{ + return nfs_idmap_lookup_id(name, namelen, "uid", uid); +} + +int nfs_map_group_to_gid(struct nfs_client *clp, const char *name, size_t namelen, __u32 *gid) +{ + return nfs_idmap_lookup_id(name, namelen, "gid", gid); +} + +int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen) +{ + return nfs_idmap_lookup_name(uid, "user", buf, buflen); +} +int nfs_map_gid_to_group(struct nfs_client *clp, __u32 gid, char *buf, size_t buflen) +{ + return nfs_idmap_lookup_name(gid, "group", buf, buflen); +} + +#else /* CONFIG_NFS_USE_IDMAPPER not defined */ + #include <linux/module.h> #include <linux/mutex.h> #include <linux/init.h> @@ -503,16 +709,17 @@ int nfs_map_group_to_gid(struct nfs_client *clp, const char *name, size_t namele return nfs_idmap_id(idmap, &idmap->idmap_group_hash, name, namelen, uid); } -int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf) +int nfs_map_uid_to_name(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen) { struct idmap *idmap = clp->cl_idmap; return nfs_idmap_name(idmap, &idmap->idmap_user_hash, uid, buf); } -int nfs_map_gid_to_group(struct nfs_client *clp, __u32 uid, char *buf) +int nfs_map_gid_to_group(struct nfs_client *clp, __u32 uid, char *buf, size_t buflen) { struct idmap *idmap = clp->cl_idmap; return nfs_idmap_name(idmap, &idmap->idmap_group_hash, uid, buf); } +#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */ diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 7d2d6c72aa78..314f57164602 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -48,6 +48,7 @@ #include "internal.h" #include "fscache.h" #include "dns_resolve.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -234,9 +235,6 @@ nfs_init_locked(struct inode *inode, void *opaque) return 0; } -/* Don't use READDIRPLUS on directories that we believe are too large */ -#define NFS_LIMIT_READDIRPLUS (8*PAGE_SIZE) - /* * This is our front-end to iget that looks up inodes by file handle * instead of inode number. @@ -291,8 +289,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr) } else if (S_ISDIR(inode->i_mode)) { inode->i_op = NFS_SB(sb)->nfs_client->rpc_ops->dir_inode_ops; inode->i_fop = &nfs_dir_operations; - if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS) - && fattr->size <= NFS_LIMIT_READDIRPLUS) + if (nfs_server_capable(inode, NFS_CAP_READDIRPLUS)) set_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags); /* Deal with crossing mountpoints */ if ((fattr->valid & NFS_ATTR_FATTR_FSID) @@ -623,7 +620,7 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync) nfs_revalidate_inode(server, inode); } -static struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct rpc_cred *cred) +struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct rpc_cred *cred, fmode_t f_mode) { struct nfs_open_context *ctx; @@ -633,11 +630,13 @@ static struct nfs_open_context *alloc_nfs_open_context(struct path *path, struct path_get(&ctx->path); ctx->cred = get_rpccred(cred); ctx->state = NULL; + ctx->mode = f_mode; ctx->flags = 0; ctx->error = 0; ctx->dir_cookie = 0; nfs_init_lock_context(&ctx->lock_context); ctx->lock_context.open_context = ctx; + INIT_LIST_HEAD(&ctx->list); } return ctx; } @@ -653,11 +652,15 @@ static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) { struct inode *inode = ctx->path.dentry->d_inode; - if (!atomic_dec_and_lock(&ctx->lock_context.count, &inode->i_lock)) + if (!list_empty(&ctx->list)) { + if (!atomic_dec_and_lock(&ctx->lock_context.count, &inode->i_lock)) + return; + list_del(&ctx->list); + spin_unlock(&inode->i_lock); + } else if (!atomic_dec_and_test(&ctx->lock_context.count)) return; - list_del(&ctx->list); - spin_unlock(&inode->i_lock); - NFS_PROTO(inode)->close_context(ctx, is_sync); + if (inode != NULL) + NFS_PROTO(inode)->close_context(ctx, is_sync); if (ctx->cred != NULL) put_rpccred(ctx->cred); path_put(&ctx->path); @@ -673,7 +676,7 @@ void put_nfs_open_context(struct nfs_open_context *ctx) * Ensure that mmap has a recent RPC credential for use when writing out * shared pages */ -static void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx) +void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx) { struct inode *inode = filp->f_path.dentry->d_inode; struct nfs_inode *nfsi = NFS_I(inode); @@ -730,11 +733,10 @@ int nfs_open(struct inode *inode, struct file *filp) cred = rpc_lookup_cred(); if (IS_ERR(cred)) return PTR_ERR(cred); - ctx = alloc_nfs_open_context(&filp->f_path, cred); + ctx = alloc_nfs_open_context(&filp->f_path, cred, filp->f_mode); put_rpccred(cred); if (ctx == NULL) return -ENOMEM; - ctx->mode = filp->f_mode; nfs_file_set_open_context(filp, ctx); put_nfs_open_context(ctx); nfs_fscache_set_inode_cookie(inode, filp); @@ -1409,6 +1411,7 @@ void nfs4_evict_inode(struct inode *inode) { truncate_inode_pages(&inode->i_data, 0); end_writeback(inode); + pnfs_destroy_layout(NFS_I(inode)); /* If we are holding a delegation, return it! */ nfs_inode_return_delegation_noreclaim(inode); /* First call standard NFS clear_inode() code */ @@ -1446,6 +1449,7 @@ static inline void nfs4_init_once(struct nfs_inode *nfsi) nfsi->delegation = NULL; nfsi->delegation_state = 0; init_rwsem(&nfsi->rwsem); + nfsi->layout = NULL; #endif } @@ -1493,7 +1497,7 @@ static int nfsiod_start(void) { struct workqueue_struct *wq; dprintk("RPC: creating workqueue nfsiod\n"); - wq = create_singlethread_workqueue("nfsiod"); + wq = alloc_workqueue("nfsiod", WQ_RESCUER, 0); if (wq == NULL) return -ENOMEM; nfsiod_workqueue = wq; @@ -1521,6 +1525,10 @@ static int __init init_nfs_fs(void) { int err; + err = nfs_idmap_init(); + if (err < 0) + goto out9; + err = nfs_dns_resolver_init(); if (err < 0) goto out8; @@ -1585,6 +1593,8 @@ out6: out7: nfs_dns_resolver_destroy(); out8: + nfs_idmap_quit(); +out9: return err; } @@ -1597,6 +1607,7 @@ static void __exit exit_nfs_fs(void) nfs_destroy_nfspagecache(); nfs_fscache_unregister(); nfs_dns_resolver_destroy(); + nfs_idmap_quit(); #ifdef CONFIG_PROC_FS rpc_proc_unregister("nfs"); #endif diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index c961bc92c107..db08ff3ff454 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -63,6 +63,12 @@ struct nfs_clone_mount { #define NFS_UNSPEC_PORT (-1) /* + * Maximum number of pages that readdir can use for creating + * a vmapped array of pages. + */ +#define NFS_MAX_READDIR_PAGES 8 + +/* * In-kernel mount arguments */ struct nfs_parsed_mount_data { @@ -181,15 +187,15 @@ extern void nfs_destroy_directcache(void); /* nfs2xdr.c */ extern int nfs_stat_to_errno(int); extern struct rpc_procinfo nfs_procedures[]; -extern __be32 * nfs_decode_dirent(__be32 *, struct nfs_entry *, int); +extern __be32 *nfs_decode_dirent(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int); /* nfs3xdr.c */ extern struct rpc_procinfo nfs3_procedures[]; -extern __be32 *nfs3_decode_dirent(__be32 *, struct nfs_entry *, int); +extern __be32 *nfs3_decode_dirent(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int); /* nfs4xdr.c */ #ifdef CONFIG_NFS_V4 -extern __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus); +extern __be32 *nfs4_decode_dirent(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int); #endif #ifdef CONFIG_NFS_V4_1 extern const u32 nfs41_maxread_overhead; diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c index 59047f8d7d72..eceafe74f473 100644 --- a/fs/nfs/mount_clnt.c +++ b/fs/nfs/mount_clnt.c @@ -153,6 +153,7 @@ int nfs_mount(struct nfs_mount_request *info) .rpc_resp = &result, }; struct rpc_create_args args = { + .net = &init_net, .protocol = info->protocol, .address = info->sap, .addrsize = info->salen, @@ -224,6 +225,7 @@ void nfs_umount(const struct nfs_mount_request *info) .to_retries = 2, }; struct rpc_create_args args = { + .net = &init_net, .protocol = IPPROTO_UDP, .address = info->sap, .addrsize = info->salen, @@ -436,7 +438,7 @@ static int decode_auth_flavors(struct xdr_stream *xdr, struct mountres *res) for (i = 0; i < entries; i++) { flavors[i] = ntohl(*p++); - dprintk("NFS:\tflavor %u: %d\n", i, flavors[i]); + dprintk("NFS: auth flavor[%u]: %d\n", i, flavors[i]); } *count = i; diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index db8846a0e82e..e6bf45710cc7 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -337,10 +337,10 @@ nfs_xdr_createargs(struct rpc_rqst *req, __be32 *p, struct nfs_createargs *args) static int nfs_xdr_renameargs(struct rpc_rqst *req, __be32 *p, struct nfs_renameargs *args) { - p = xdr_encode_fhandle(p, args->fromfh); - p = xdr_encode_array(p, args->fromname, args->fromlen); - p = xdr_encode_fhandle(p, args->tofh); - p = xdr_encode_array(p, args->toname, args->tolen); + p = xdr_encode_fhandle(p, args->old_dir); + p = xdr_encode_array(p, args->old_name->name, args->old_name->len); + p = xdr_encode_fhandle(p, args->new_dir); + p = xdr_encode_array(p, args->new_name->name, args->new_name->len); req->rq_slen = xdr_adjust_iovec(req->rq_svec, p); return 0; } @@ -423,9 +423,7 @@ nfs_xdr_readdirres(struct rpc_rqst *req, __be32 *p, void *dummy) struct page **page; size_t hdrlen; unsigned int pglen, recvd; - u32 len; int status, nr = 0; - __be32 *end, *entry, *kaddr; if ((status = ntohl(*p++))) return nfs_stat_to_errno(status); @@ -445,80 +443,59 @@ nfs_xdr_readdirres(struct rpc_rqst *req, __be32 *p, void *dummy) if (pglen > recvd) pglen = recvd; page = rcvbuf->pages; - kaddr = p = kmap_atomic(*page, KM_USER0); - end = (__be32 *)((char *)p + pglen); - entry = p; - - /* Make sure the packet actually has a value_follows and EOF entry */ - if ((entry + 1) > end) - goto short_pkt; - - for (; *p++; nr++) { - if (p + 2 > end) - goto short_pkt; - p++; /* fileid */ - len = ntohl(*p++); - p += XDR_QUADLEN(len) + 1; /* name plus cookie */ - if (len > NFS2_MAXNAMLEN) { - dprintk("NFS: giant filename in readdir (len 0x%x)!\n", - len); - goto err_unmap; - } - if (p + 2 > end) - goto short_pkt; - entry = p; - } - - /* - * Apparently some server sends responses that are a valid size, but - * contain no entries, and have value_follows==0 and EOF==0. For - * those, just set the EOF marker. - */ - if (!nr && entry[1] == 0) { - dprintk("NFS: readdir reply truncated!\n"); - entry[1] = 1; - } - out: - kunmap_atomic(kaddr, KM_USER0); return nr; - short_pkt: - /* - * When we get a short packet there are 2 possibilities. We can - * return an error, or fix up the response to look like a valid - * response and return what we have so far. If there are no - * entries and the packet was short, then return -EIO. If there - * are valid entries in the response, return them and pretend that - * the call was successful, but incomplete. The caller can retry the - * readdir starting at the last cookie. - */ - entry[0] = entry[1] = 0; - if (!nr) - nr = -errno_NFSERR_IO; - goto out; -err_unmap: - nr = -errno_NFSERR_IO; - goto out; +} + +static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) +{ + dprintk("nfs: %s: prematurely hit end of receive buffer. " + "Remaining buffer length is %tu words.\n", + func, xdr->end - xdr->p); } __be32 * -nfs_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus) +nfs_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, struct nfs_server *server, int plus) { - if (!*p++) { - if (!*p) + __be32 *p; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + if (!ntohl(*p++)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + if (!ntohl(*p++)) return ERR_PTR(-EAGAIN); entry->eof = 1; return ERR_PTR(-EBADCOOKIE); } + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + entry->ino = ntohl(*p++); entry->len = ntohl(*p++); + + p = xdr_inline_decode(xdr, entry->len + 4); + if (unlikely(!p)) + goto out_overflow; entry->name = (const char *) p; p += XDR_QUADLEN(entry->len); entry->prev_cookie = entry->cookie; entry->cookie = ntohl(*p++); - entry->eof = !p[0] && p[1]; + + p = xdr_inline_peek(xdr, 8); + if (p != NULL) + entry->eof = !p[0] && p[1]; + else + entry->eof = 0; return p; + +out_overflow: + print_overflow_msg(__func__, xdr); + return ERR_PTR(-EIO); } /* @@ -596,7 +573,6 @@ nfs_xdr_readlinkres(struct rpc_rqst *req, __be32 *p, void *dummy) struct kvec *iov = rcvbuf->head; size_t hdrlen; u32 len, recvd; - char *kaddr; int status; if ((status = ntohl(*p++))) @@ -623,10 +599,7 @@ nfs_xdr_readlinkres(struct rpc_rqst *req, __be32 *p, void *dummy) return -EIO; } - /* NULL terminate the string we got */ - kaddr = (char *)kmap_atomic(rcvbuf->pages[0], KM_USER0); - kaddr[len+rcvbuf->page_base] = '\0'; - kunmap_atomic(kaddr, KM_USER0); + xdr_terminate_string(rcvbuf, len); return 0; } diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index fabb4f2849a1..ce939c062a52 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -313,7 +313,7 @@ static void nfs3_free_createdata(struct nfs3_createdata *data) */ static int nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags, struct nameidata *nd) + int flags, struct nfs_open_context *ctx) { struct nfs3_createdata *data; mode_t mode = sattr->ia_mode; @@ -438,19 +438,38 @@ nfs3_proc_unlink_done(struct rpc_task *task, struct inode *dir) return 1; } +static void +nfs3_proc_rename_setup(struct rpc_message *msg, struct inode *dir) +{ + msg->rpc_proc = &nfs3_procedures[NFS3PROC_RENAME]; +} + +static int +nfs3_proc_rename_done(struct rpc_task *task, struct inode *old_dir, + struct inode *new_dir) +{ + struct nfs_renameres *res; + + if (nfs3_async_handle_jukebox(task, old_dir)) + return 0; + res = task->tk_msg.rpc_resp; + + nfs_post_op_update_inode(old_dir, res->old_fattr); + nfs_post_op_update_inode(new_dir, res->new_fattr); + return 1; +} + static int nfs3_proc_rename(struct inode *old_dir, struct qstr *old_name, struct inode *new_dir, struct qstr *new_name) { - struct nfs3_renameargs arg = { - .fromfh = NFS_FH(old_dir), - .fromname = old_name->name, - .fromlen = old_name->len, - .tofh = NFS_FH(new_dir), - .toname = new_name->name, - .tolen = new_name->len + struct nfs_renameargs arg = { + .old_dir = NFS_FH(old_dir), + .old_name = old_name, + .new_dir = NFS_FH(new_dir), + .new_name = new_name, }; - struct nfs3_renameres res; + struct nfs_renameres res; struct rpc_message msg = { .rpc_proc = &nfs3_procedures[NFS3PROC_RENAME], .rpc_argp = &arg, @@ -460,17 +479,17 @@ nfs3_proc_rename(struct inode *old_dir, struct qstr *old_name, dprintk("NFS call rename %s -> %s\n", old_name->name, new_name->name); - res.fromattr = nfs_alloc_fattr(); - res.toattr = nfs_alloc_fattr(); - if (res.fromattr == NULL || res.toattr == NULL) + res.old_fattr = nfs_alloc_fattr(); + res.new_fattr = nfs_alloc_fattr(); + if (res.old_fattr == NULL || res.new_fattr == NULL) goto out; status = rpc_call_sync(NFS_CLIENT(old_dir), &msg, 0); - nfs_post_op_update_inode(old_dir, res.fromattr); - nfs_post_op_update_inode(new_dir, res.toattr); + nfs_post_op_update_inode(old_dir, res.old_fattr); + nfs_post_op_update_inode(new_dir, res.new_fattr); out: - nfs_free_fattr(res.toattr); - nfs_free_fattr(res.fromattr); + nfs_free_fattr(res.old_fattr); + nfs_free_fattr(res.new_fattr); dprintk("NFS reply rename: %d\n", status); return status; } @@ -611,7 +630,7 @@ out: */ static int nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page *page, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, int plus) { struct inode *dir = dentry->d_inode; __be32 *verf = NFS_COOKIEVERF(dir); @@ -621,7 +640,7 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, .verf = {verf[0], verf[1]}, .plus = plus, .count = count, - .pages = &page + .pages = pages }; struct nfs3_readdirres res = { .verf = verf, @@ -652,7 +671,8 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, nfs_free_fattr(res.dir_attr); out: - dprintk("NFS reply readdir: %d\n", status); + dprintk("NFS reply readdir%s: %d\n", + plus? "plus" : "", status); return status; } @@ -722,7 +742,7 @@ nfs3_proc_statfs(struct nfs_server *server, struct nfs_fh *fhandle, dprintk("NFS call fsstat\n"); nfs_fattr_init(stat->fattr); status = rpc_call_sync(server->client, &msg, 0); - dprintk("NFS reply statfs: %d\n", status); + dprintk("NFS reply fsstat: %d\n", status); return status; } @@ -844,6 +864,8 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .unlink_setup = nfs3_proc_unlink_setup, .unlink_done = nfs3_proc_unlink_done, .rename = nfs3_proc_rename, + .rename_setup = nfs3_proc_rename_setup, + .rename_done = nfs3_proc_rename_done, .link = nfs3_proc_link, .symlink = nfs3_proc_symlink, .mkdir = nfs3_proc_mkdir, diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 9769704f8ce6..d9a5e832c257 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -100,6 +100,13 @@ static const umode_t nfs_type2fmt[] = { [NF3FIFO] = S_IFIFO, }; +static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) +{ + dprintk("nfs: %s: prematurely hit end of receive buffer. " + "Remaining buffer length is %tu words.\n", + func, xdr->end - xdr->p); +} + /* * Common NFS XDR functions as inlines */ @@ -119,6 +126,29 @@ xdr_decode_fhandle(__be32 *p, struct nfs_fh *fh) return NULL; } +static inline __be32 * +xdr_decode_fhandle_stream(struct xdr_stream *xdr, struct nfs_fh *fh) +{ + __be32 *p; + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + fh->size = ntohl(*p++); + + if (fh->size <= NFS3_FHSIZE) { + p = xdr_inline_decode(xdr, fh->size); + if (unlikely(!p)) + goto out_overflow; + memcpy(fh->data, p, fh->size); + return p + XDR_QUADLEN(fh->size); + } + return NULL; + +out_overflow: + print_overflow_msg(__func__, xdr); + return ERR_PTR(-EIO); +} + /* * Encode/decode time. */ @@ -241,6 +271,26 @@ xdr_decode_post_op_attr(__be32 *p, struct nfs_fattr *fattr) } static inline __be32 * +xdr_decode_post_op_attr_stream(struct xdr_stream *xdr, struct nfs_fattr *fattr) +{ + __be32 *p; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + if (ntohl(*p++)) { + p = xdr_inline_decode(xdr, 84); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_fattr(p, fattr); + } + return p; +out_overflow: + print_overflow_msg(__func__, xdr); + return ERR_PTR(-EIO); +} + +static inline __be32 * xdr_decode_pre_op_attr(__be32 *p, struct nfs_fattr *fattr) { if (*p++) @@ -442,12 +492,12 @@ nfs3_xdr_mknodargs(struct rpc_rqst *req, __be32 *p, struct nfs3_mknodargs *args) * Encode RENAME arguments */ static int -nfs3_xdr_renameargs(struct rpc_rqst *req, __be32 *p, struct nfs3_renameargs *args) +nfs3_xdr_renameargs(struct rpc_rqst *req, __be32 *p, struct nfs_renameargs *args) { - p = xdr_encode_fhandle(p, args->fromfh); - p = xdr_encode_array(p, args->fromname, args->fromlen); - p = xdr_encode_fhandle(p, args->tofh); - p = xdr_encode_array(p, args->toname, args->tolen); + p = xdr_encode_fhandle(p, args->old_dir); + p = xdr_encode_array(p, args->old_name->name, args->old_name->len); + p = xdr_encode_fhandle(p, args->new_dir); + p = xdr_encode_array(p, args->new_name->name, args->new_name->len); req->rq_slen = xdr_adjust_iovec(req->rq_svec, p); return 0; } @@ -504,9 +554,8 @@ nfs3_xdr_readdirres(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirres *res struct kvec *iov = rcvbuf->head; struct page **page; size_t hdrlen; - u32 len, recvd, pglen; + u32 recvd, pglen; int status, nr = 0; - __be32 *entry, *end, *kaddr; status = ntohl(*p++); /* Decode post_op_attrs */ @@ -536,99 +585,38 @@ nfs3_xdr_readdirres(struct rpc_rqst *req, __be32 *p, struct nfs3_readdirres *res if (pglen > recvd) pglen = recvd; page = rcvbuf->pages; - kaddr = p = kmap_atomic(*page, KM_USER0); - end = (__be32 *)((char *)p + pglen); - entry = p; - - /* Make sure the packet actually has a value_follows and EOF entry */ - if ((entry + 1) > end) - goto short_pkt; - - for (; *p++; nr++) { - if (p + 3 > end) - goto short_pkt; - p += 2; /* inode # */ - len = ntohl(*p++); /* string length */ - p += XDR_QUADLEN(len) + 2; /* name + cookie */ - if (len > NFS3_MAXNAMLEN) { - dprintk("NFS: giant filename in readdir (len 0x%x)!\n", - len); - goto err_unmap; - } - if (res->plus) { - /* post_op_attr */ - if (p + 2 > end) - goto short_pkt; - if (*p++) { - p += 21; - if (p + 1 > end) - goto short_pkt; - } - /* post_op_fh3 */ - if (*p++) { - if (p + 1 > end) - goto short_pkt; - len = ntohl(*p++); - if (len > NFS3_FHSIZE) { - dprintk("NFS: giant filehandle in " - "readdir (len 0x%x)!\n", len); - goto err_unmap; - } - p += XDR_QUADLEN(len); - } - } - - if (p + 2 > end) - goto short_pkt; - entry = p; - } - - /* - * Apparently some server sends responses that are a valid size, but - * contain no entries, and have value_follows==0 and EOF==0. For - * those, just set the EOF marker. - */ - if (!nr && entry[1] == 0) { - dprintk("NFS: readdir reply truncated!\n"); - entry[1] = 1; - } - out: - kunmap_atomic(kaddr, KM_USER0); return nr; - short_pkt: - /* - * When we get a short packet there are 2 possibilities. We can - * return an error, or fix up the response to look like a valid - * response and return what we have so far. If there are no - * entries and the packet was short, then return -EIO. If there - * are valid entries in the response, return them and pretend that - * the call was successful, but incomplete. The caller can retry the - * readdir starting at the last cookie. - */ - entry[0] = entry[1] = 0; - if (!nr) - nr = -errno_NFSERR_IO; - goto out; -err_unmap: - nr = -errno_NFSERR_IO; - goto out; } __be32 * -nfs3_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus) +nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, struct nfs_server *server, int plus) { + __be32 *p; struct nfs_entry old = *entry; - if (!*p++) { - if (!*p) + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + if (!ntohl(*p++)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + if (!ntohl(*p++)) return ERR_PTR(-EAGAIN); entry->eof = 1; return ERR_PTR(-EBADCOOKIE); } + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; p = xdr_decode_hyper(p, &entry->ino); entry->len = ntohl(*p++); + + p = xdr_inline_decode(xdr, entry->len + 8); + if (unlikely(!p)) + goto out_overflow; entry->name = (const char *) p; p += XDR_QUADLEN(entry->len); entry->prev_cookie = entry->cookie; @@ -636,10 +624,17 @@ nfs3_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus) if (plus) { entry->fattr->valid = 0; - p = xdr_decode_post_op_attr(p, entry->fattr); + p = xdr_decode_post_op_attr_stream(xdr, entry->fattr); + if (IS_ERR(p)) + goto out_overflow_exit; /* In fact, a post_op_fh3: */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; if (*p++) { - p = xdr_decode_fhandle(p, entry->fh); + p = xdr_decode_fhandle_stream(xdr, entry->fh); + if (IS_ERR(p)) + goto out_overflow_exit; /* Ugh -- server reply was truncated */ if (p == NULL) { dprintk("NFS: FH truncated\n"); @@ -650,8 +645,18 @@ nfs3_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus) memset((u8*)(entry->fh), 0, sizeof(*entry->fh)); } - entry->eof = !p[0] && p[1]; + p = xdr_inline_peek(xdr, 8); + if (p != NULL) + entry->eof = !p[0] && p[1]; + else + entry->eof = 0; + return p; + +out_overflow: + print_overflow_msg(__func__, xdr); +out_overflow_exit: + return ERR_PTR(-EIO); } /* @@ -824,7 +829,6 @@ nfs3_xdr_readlinkres(struct rpc_rqst *req, __be32 *p, struct nfs_fattr *fattr) struct kvec *iov = rcvbuf->head; size_t hdrlen; u32 len, recvd; - char *kaddr; int status; status = ntohl(*p++); @@ -857,10 +861,7 @@ nfs3_xdr_readlinkres(struct rpc_rqst *req, __be32 *p, struct nfs_fattr *fattr) return -EIO; } - /* NULL terminate the string we got */ - kaddr = (char*)kmap_atomic(rcvbuf->pages[0], KM_USER0); - kaddr[len+rcvbuf->page_base] = '\0'; - kunmap_atomic(kaddr, KM_USER0); + xdr_terminate_string(rcvbuf, len); return 0; } @@ -970,14 +971,14 @@ nfs3_xdr_createres(struct rpc_rqst *req, __be32 *p, struct nfs3_diropres *res) * Decode RENAME reply */ static int -nfs3_xdr_renameres(struct rpc_rqst *req, __be32 *p, struct nfs3_renameres *res) +nfs3_xdr_renameres(struct rpc_rqst *req, __be32 *p, struct nfs_renameres *res) { int status; if ((status = ntohl(*p++)) != 0) status = nfs_stat_to_errno(status); - p = xdr_decode_wcc_data(p, res->fromattr); - p = xdr_decode_wcc_data(p, res->toattr); + p = xdr_decode_wcc_data(p, res->old_fattr); + p = xdr_decode_wcc_data(p, res->new_fattr); return status; } @@ -1043,8 +1044,9 @@ nfs3_xdr_fsinfores(struct rpc_rqst *req, __be32 *p, struct nfs_fsinfo *res) res->wtmult = ntohl(*p++); res->dtpref = ntohl(*p++); p = xdr_decode_hyper(p, &res->maxfilesize); + p = xdr_decode_time3(p, &res->time_delta); - /* ignore time_delta and properties */ + /* ignore properties */ res->lease_time = 0; return 0; } diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index 311e15cc8af0..9fa496387fdf 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -242,8 +242,6 @@ extern int nfs4_proc_renew(struct nfs_client *, struct rpc_cred *); extern int nfs4_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs41_init_clientid(struct nfs_client *, struct rpc_cred *); extern int nfs4_do_close(struct path *path, struct nfs4_state *state, gfp_t gfp_mask, int wait); -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, const struct qstr *name, struct nfs4_fs_locations *fs_locations, struct page *page); @@ -333,7 +331,7 @@ extern void nfs_free_seqid(struct nfs_seqid *seqid); extern const nfs4_stateid zero_stateid; /* nfs4xdr.c */ -extern __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus); +extern __be32 *nfs4_decode_dirent(struct xdr_stream *, struct nfs_entry *, struct nfs_server *, int); extern struct rpc_procinfo nfs4_procedures[]; struct nfs4_mount_data; diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c new file mode 100644 index 000000000000..2e92f0d8d654 --- /dev/null +++ b/fs/nfs/nfs4filelayout.c @@ -0,0 +1,280 @@ +/* + * Module for the pnfs nfs4 file layout driver. + * Defines all I/O and Policy interface operations, plus code + * to register itself with the pNFS client. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#include <linux/nfs_fs.h> + +#include "internal.h" +#include "nfs4filelayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Dean Hildebrand <dhildebz@umich.edu>"); +MODULE_DESCRIPTION("The NFSv4 file layout driver"); + +static int +filelayout_set_layoutdriver(struct nfs_server *nfss) +{ + int status = pnfs_alloc_init_deviceid_cache(nfss->nfs_client, + nfs4_fl_free_deviceid_callback); + if (status) { + printk(KERN_WARNING "%s: deviceid cache could not be " + "initialized\n", __func__); + return status; + } + dprintk("%s: deviceid cache has been initialized successfully\n", + __func__); + return 0; +} + +/* Clear out the layout by destroying its device list */ +static int +filelayout_clear_layoutdriver(struct nfs_server *nfss) +{ + dprintk("--> %s\n", __func__); + + if (nfss->nfs_client->cl_devid_cache) + pnfs_put_deviceid_cache(nfss->nfs_client); + return 0; +} + +/* + * filelayout_check_layout() + * + * Make sure layout segment parameters are sane WRT the device. + * At this point no generic layer initialization of the lseg has occurred, + * and nothing has been added to the layout_hdr cache. + * + */ +static int +filelayout_check_layout(struct pnfs_layout_hdr *lo, + struct nfs4_filelayout_segment *fl, + struct nfs4_layoutget_res *lgr, + struct nfs4_deviceid *id) +{ + struct nfs4_file_layout_dsaddr *dsaddr; + int status = -EINVAL; + struct nfs_server *nfss = NFS_SERVER(lo->inode); + + dprintk("--> %s\n", __func__); + + if (fl->pattern_offset > lgr->range.offset) { + dprintk("%s pattern_offset %lld to large\n", + __func__, fl->pattern_offset); + goto out; + } + + if (fl->stripe_unit % PAGE_SIZE) { + dprintk("%s Stripe unit (%u) not page aligned\n", + __func__, fl->stripe_unit); + goto out; + } + + /* find and reference the deviceid */ + dsaddr = nfs4_fl_find_get_deviceid(nfss->nfs_client, id); + if (dsaddr == NULL) { + dsaddr = get_device_info(lo->inode, id); + if (dsaddr == NULL) + goto out; + } + fl->dsaddr = dsaddr; + + if (fl->first_stripe_index < 0 || + fl->first_stripe_index >= dsaddr->stripe_count) { + dprintk("%s Bad first_stripe_index %d\n", + __func__, fl->first_stripe_index); + goto out_put; + } + + if ((fl->stripe_type == STRIPE_SPARSE && + fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) || + (fl->stripe_type == STRIPE_DENSE && + fl->num_fh != dsaddr->stripe_count)) { + dprintk("%s num_fh %u not valid for given packing\n", + __func__, fl->num_fh); + goto out_put; + } + + if (fl->stripe_unit % nfss->rsize || fl->stripe_unit % nfss->wsize) { + dprintk("%s Stripe unit (%u) not aligned with rsize %u " + "wsize %u\n", __func__, fl->stripe_unit, nfss->rsize, + nfss->wsize); + } + + status = 0; +out: + dprintk("--> %s returns %d\n", __func__, status); + return status; +out_put: + pnfs_put_deviceid(nfss->nfs_client->cl_devid_cache, &dsaddr->deviceid); + goto out; +} + +static void filelayout_free_fh_array(struct nfs4_filelayout_segment *fl) +{ + int i; + + for (i = 0; i < fl->num_fh; i++) { + if (!fl->fh_array[i]) + break; + kfree(fl->fh_array[i]); + } + kfree(fl->fh_array); + fl->fh_array = NULL; +} + +static void +_filelayout_free_lseg(struct nfs4_filelayout_segment *fl) +{ + filelayout_free_fh_array(fl); + kfree(fl); +} + +static int +filelayout_decode_layout(struct pnfs_layout_hdr *flo, + struct nfs4_filelayout_segment *fl, + struct nfs4_layoutget_res *lgr, + struct nfs4_deviceid *id) +{ + uint32_t *p = (uint32_t *)lgr->layout.buf; + uint32_t nfl_util; + int i; + + dprintk("%s: set_layout_map Begin\n", __func__); + + memcpy(id, p, sizeof(*id)); + p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE); + print_deviceid(id); + + nfl_util = be32_to_cpup(p++); + if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS) + fl->commit_through_mds = 1; + if (nfl_util & NFL4_UFLG_DENSE) + fl->stripe_type = STRIPE_DENSE; + else + fl->stripe_type = STRIPE_SPARSE; + fl->stripe_unit = nfl_util & ~NFL4_UFLG_MASK; + + fl->first_stripe_index = be32_to_cpup(p++); + p = xdr_decode_hyper(p, &fl->pattern_offset); + fl->num_fh = be32_to_cpup(p++); + + dprintk("%s: nfl_util 0x%X num_fh %u fsi %u po %llu\n", + __func__, nfl_util, fl->num_fh, fl->first_stripe_index, + fl->pattern_offset); + + fl->fh_array = kzalloc(fl->num_fh * sizeof(struct nfs_fh *), + GFP_KERNEL); + if (!fl->fh_array) + return -ENOMEM; + + for (i = 0; i < fl->num_fh; i++) { + /* Do we want to use a mempool here? */ + fl->fh_array[i] = kmalloc(sizeof(struct nfs_fh), GFP_KERNEL); + if (!fl->fh_array[i]) { + filelayout_free_fh_array(fl); + return -ENOMEM; + } + fl->fh_array[i]->size = be32_to_cpup(p++); + if (sizeof(struct nfs_fh) < fl->fh_array[i]->size) { + printk(KERN_ERR "Too big fh %d received %d\n", + i, fl->fh_array[i]->size); + filelayout_free_fh_array(fl); + return -EIO; + } + memcpy(fl->fh_array[i]->data, p, fl->fh_array[i]->size); + p += XDR_QUADLEN(fl->fh_array[i]->size); + dprintk("DEBUG: %s: fh len %d\n", __func__, + fl->fh_array[i]->size); + } + + return 0; +} + +static struct pnfs_layout_segment * +filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid, + struct nfs4_layoutget_res *lgr) +{ + struct nfs4_filelayout_segment *fl; + int rc; + struct nfs4_deviceid id; + + dprintk("--> %s\n", __func__); + fl = kzalloc(sizeof(*fl), GFP_KERNEL); + if (!fl) + return NULL; + + rc = filelayout_decode_layout(layoutid, fl, lgr, &id); + if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id)) { + _filelayout_free_lseg(fl); + return NULL; + } + return &fl->generic_hdr; +} + +static void +filelayout_free_lseg(struct pnfs_layout_segment *lseg) +{ + struct nfs_server *nfss = NFS_SERVER(lseg->layout->inode); + struct nfs4_filelayout_segment *fl = FILELAYOUT_LSEG(lseg); + + dprintk("--> %s\n", __func__); + pnfs_put_deviceid(nfss->nfs_client->cl_devid_cache, + &fl->dsaddr->deviceid); + _filelayout_free_lseg(fl); +} + +static struct pnfs_layoutdriver_type filelayout_type = { + .id = LAYOUT_NFSV4_1_FILES, + .name = "LAYOUT_NFSV4_1_FILES", + .owner = THIS_MODULE, + .set_layoutdriver = filelayout_set_layoutdriver, + .clear_layoutdriver = filelayout_clear_layoutdriver, + .alloc_lseg = filelayout_alloc_lseg, + .free_lseg = filelayout_free_lseg, +}; + +static int __init nfs4filelayout_init(void) +{ + printk(KERN_INFO "%s: NFSv4 File Layout Driver Registering...\n", + __func__); + return pnfs_register_layoutdriver(&filelayout_type); +} + +static void __exit nfs4filelayout_exit(void) +{ + printk(KERN_INFO "%s: NFSv4 File Layout Driver Unregistering...\n", + __func__); + pnfs_unregister_layoutdriver(&filelayout_type); +} + +module_init(nfs4filelayout_init); +module_exit(nfs4filelayout_exit); diff --git a/fs/nfs/nfs4filelayout.h b/fs/nfs/nfs4filelayout.h new file mode 100644 index 000000000000..bbf60dd2ab9d --- /dev/null +++ b/fs/nfs/nfs4filelayout.h @@ -0,0 +1,94 @@ +/* + * NFSv4 file layout driver data structures. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#ifndef FS_NFS_NFS4FILELAYOUT_H +#define FS_NFS_NFS4FILELAYOUT_H + +#include "pnfs.h" + +/* + * Field testing shows we need to support upto 4096 stripe indices. + * We store each index as a u8 (u32 on the wire) to keep the memory footprint + * reasonable. This in turn means we support a maximum of 256 + * RFC 5661 multipath_list4 structures. + */ +#define NFS4_PNFS_MAX_STRIPE_CNT 4096 +#define NFS4_PNFS_MAX_MULTI_CNT 256 /* 256 fit into a u8 stripe_index */ + +enum stripetype4 { + STRIPE_SPARSE = 1, + STRIPE_DENSE = 2 +}; + +/* Individual ip address */ +struct nfs4_pnfs_ds { + struct list_head ds_node; /* nfs4_pnfs_dev_hlist dev_dslist */ + u32 ds_ip_addr; + u32 ds_port; + struct nfs_client *ds_clp; + atomic_t ds_count; +}; + +struct nfs4_file_layout_dsaddr { + struct pnfs_deviceid_node deviceid; + u32 stripe_count; + u8 *stripe_indices; + u32 ds_num; + struct nfs4_pnfs_ds *ds_list[1]; +}; + +struct nfs4_filelayout_segment { + struct pnfs_layout_segment generic_hdr; + u32 stripe_type; + u32 commit_through_mds; + u32 stripe_unit; + u32 first_stripe_index; + u64 pattern_offset; + struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */ + unsigned int num_fh; + struct nfs_fh **fh_array; +}; + +static inline struct nfs4_filelayout_segment * +FILELAYOUT_LSEG(struct pnfs_layout_segment *lseg) +{ + return container_of(lseg, + struct nfs4_filelayout_segment, + generic_hdr); +} + +extern void nfs4_fl_free_deviceid_callback(struct pnfs_deviceid_node *); +extern void print_ds(struct nfs4_pnfs_ds *ds); +extern void print_deviceid(struct nfs4_deviceid *dev_id); +extern struct nfs4_file_layout_dsaddr * +nfs4_fl_find_get_deviceid(struct nfs_client *, struct nfs4_deviceid *dev_id); +struct nfs4_file_layout_dsaddr * +get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id); + +#endif /* FS_NFS_NFS4FILELAYOUT_H */ diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c new file mode 100644 index 000000000000..51fe64ace55a --- /dev/null +++ b/fs/nfs/nfs4filelayoutdev.c @@ -0,0 +1,448 @@ +/* + * Device operations for the pnfs nfs4 file layout driver. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * Garth Goodson <Garth.Goodson@netapp.com> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#include <linux/nfs_fs.h> +#include <linux/vmalloc.h> + +#include "internal.h" +#include "nfs4filelayout.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS_LD + +/* + * Data server cache + * + * Data servers can be mapped to different device ids. + * nfs4_pnfs_ds reference counting + * - set to 1 on allocation + * - incremented when a device id maps a data server already in the cache. + * - decremented when deviceid is removed from the cache. + */ +DEFINE_SPINLOCK(nfs4_ds_cache_lock); +static LIST_HEAD(nfs4_data_server_cache); + +/* Debug routines */ +void +print_ds(struct nfs4_pnfs_ds *ds) +{ + if (ds == NULL) { + printk("%s NULL device\n", __func__); + return; + } + printk(" ip_addr %x port %hu\n" + " ref count %d\n" + " client %p\n" + " cl_exchange_flags %x\n", + ntohl(ds->ds_ip_addr), ntohs(ds->ds_port), + atomic_read(&ds->ds_count), ds->ds_clp, + ds->ds_clp ? ds->ds_clp->cl_exchange_flags : 0); +} + +void +print_ds_list(struct nfs4_file_layout_dsaddr *dsaddr) +{ + int i; + + ifdebug(FACILITY) { + printk("%s dsaddr->ds_num %d\n", __func__, + dsaddr->ds_num); + for (i = 0; i < dsaddr->ds_num; i++) + print_ds(dsaddr->ds_list[i]); + } +} + +void print_deviceid(struct nfs4_deviceid *id) +{ + u32 *p = (u32 *)id; + + dprintk("%s: device id= [%x%x%x%x]\n", __func__, + p[0], p[1], p[2], p[3]); +} + +/* nfs4_ds_cache_lock is held */ +static struct nfs4_pnfs_ds * +_data_server_lookup_locked(u32 ip_addr, u32 port) +{ + struct nfs4_pnfs_ds *ds; + + dprintk("_data_server_lookup: ip_addr=%x port=%hu\n", + ntohl(ip_addr), ntohs(port)); + + list_for_each_entry(ds, &nfs4_data_server_cache, ds_node) { + if (ds->ds_ip_addr == ip_addr && + ds->ds_port == port) { + return ds; + } + } + return NULL; +} + +static void +destroy_ds(struct nfs4_pnfs_ds *ds) +{ + dprintk("--> %s\n", __func__); + ifdebug(FACILITY) + print_ds(ds); + + if (ds->ds_clp) + nfs_put_client(ds->ds_clp); + kfree(ds); +} + +static void +nfs4_fl_free_deviceid(struct nfs4_file_layout_dsaddr *dsaddr) +{ + struct nfs4_pnfs_ds *ds; + int i; + + print_deviceid(&dsaddr->deviceid.de_id); + + for (i = 0; i < dsaddr->ds_num; i++) { + ds = dsaddr->ds_list[i]; + if (ds != NULL) { + if (atomic_dec_and_lock(&ds->ds_count, + &nfs4_ds_cache_lock)) { + list_del_init(&ds->ds_node); + spin_unlock(&nfs4_ds_cache_lock); + destroy_ds(ds); + } + } + } + kfree(dsaddr->stripe_indices); + kfree(dsaddr); +} + +void +nfs4_fl_free_deviceid_callback(struct pnfs_deviceid_node *device) +{ + struct nfs4_file_layout_dsaddr *dsaddr = + container_of(device, struct nfs4_file_layout_dsaddr, deviceid); + + nfs4_fl_free_deviceid(dsaddr); +} + +static struct nfs4_pnfs_ds * +nfs4_pnfs_ds_add(struct inode *inode, u32 ip_addr, u32 port) +{ + struct nfs4_pnfs_ds *tmp_ds, *ds; + + ds = kzalloc(sizeof(*tmp_ds), GFP_KERNEL); + if (!ds) + goto out; + + spin_lock(&nfs4_ds_cache_lock); + tmp_ds = _data_server_lookup_locked(ip_addr, port); + if (tmp_ds == NULL) { + ds->ds_ip_addr = ip_addr; + ds->ds_port = port; + atomic_set(&ds->ds_count, 1); + INIT_LIST_HEAD(&ds->ds_node); + ds->ds_clp = NULL; + list_add(&ds->ds_node, &nfs4_data_server_cache); + dprintk("%s add new data server ip 0x%x\n", __func__, + ds->ds_ip_addr); + } else { + kfree(ds); + atomic_inc(&tmp_ds->ds_count); + dprintk("%s data server found ip 0x%x, inc'ed ds_count to %d\n", + __func__, tmp_ds->ds_ip_addr, + atomic_read(&tmp_ds->ds_count)); + ds = tmp_ds; + } + spin_unlock(&nfs4_ds_cache_lock); +out: + return ds; +} + +/* + * Currently only support ipv4, and one multi-path address. + */ +static struct nfs4_pnfs_ds * +decode_and_add_ds(__be32 **pp, struct inode *inode) +{ + struct nfs4_pnfs_ds *ds = NULL; + char *buf; + const char *ipend, *pstr; + u32 ip_addr, port; + int nlen, rlen, i; + int tmp[2]; + __be32 *r_netid, *r_addr, *p = *pp; + + /* r_netid */ + nlen = be32_to_cpup(p++); + r_netid = p; + p += XDR_QUADLEN(nlen); + + /* r_addr */ + rlen = be32_to_cpup(p++); + r_addr = p; + p += XDR_QUADLEN(rlen); + *pp = p; + + /* Check that netid is "tcp" */ + if (nlen != 3 || memcmp((char *)r_netid, "tcp", 3)) { + dprintk("%s: ERROR: non ipv4 TCP r_netid\n", __func__); + goto out_err; + } + + /* ipv6 length plus port is legal */ + if (rlen > INET6_ADDRSTRLEN + 8) { + dprintk("%s Invalid address, length %d\n", __func__, + rlen); + goto out_err; + } + buf = kmalloc(rlen + 1, GFP_KERNEL); + buf[rlen] = '\0'; + memcpy(buf, r_addr, rlen); + + /* replace the port dots with dashes for the in4_pton() delimiter*/ + for (i = 0; i < 2; i++) { + char *res = strrchr(buf, '.'); + *res = '-'; + } + + /* Currently only support ipv4 address */ + if (in4_pton(buf, rlen, (u8 *)&ip_addr, '-', &ipend) == 0) { + dprintk("%s: Only ipv4 addresses supported\n", __func__); + goto out_free; + } + + /* port */ + pstr = ipend; + sscanf(pstr, "-%d-%d", &tmp[0], &tmp[1]); + port = htons((tmp[0] << 8) | (tmp[1])); + + ds = nfs4_pnfs_ds_add(inode, ip_addr, port); + dprintk("%s Decoded address and port %s\n", __func__, buf); +out_free: + kfree(buf); +out_err: + return ds; +} + +/* Decode opaque device data and return the result */ +static struct nfs4_file_layout_dsaddr* +decode_device(struct inode *ino, struct pnfs_device *pdev) +{ + int i, dummy; + u32 cnt, num; + u8 *indexp; + __be32 *p = (__be32 *)pdev->area, *indicesp; + struct nfs4_file_layout_dsaddr *dsaddr; + + /* Get the stripe count (number of stripe index) */ + cnt = be32_to_cpup(p++); + dprintk("%s stripe count %d\n", __func__, cnt); + if (cnt > NFS4_PNFS_MAX_STRIPE_CNT) { + printk(KERN_WARNING "%s: stripe count %d greater than " + "supported maximum %d\n", __func__, + cnt, NFS4_PNFS_MAX_STRIPE_CNT); + goto out_err; + } + + /* Check the multipath list count */ + indicesp = p; + p += XDR_QUADLEN(cnt << 2); + num = be32_to_cpup(p++); + dprintk("%s ds_num %u\n", __func__, num); + if (num > NFS4_PNFS_MAX_MULTI_CNT) { + printk(KERN_WARNING "%s: multipath count %d greater than " + "supported maximum %d\n", __func__, + num, NFS4_PNFS_MAX_MULTI_CNT); + goto out_err; + } + dsaddr = kzalloc(sizeof(*dsaddr) + + (sizeof(struct nfs4_pnfs_ds *) * (num - 1)), + GFP_KERNEL); + if (!dsaddr) + goto out_err; + + dsaddr->stripe_indices = kzalloc(sizeof(u8) * cnt, GFP_KERNEL); + if (!dsaddr->stripe_indices) + goto out_err_free; + + dsaddr->stripe_count = cnt; + dsaddr->ds_num = num; + + memcpy(&dsaddr->deviceid.de_id, &pdev->dev_id, sizeof(pdev->dev_id)); + + /* Go back an read stripe indices */ + p = indicesp; + indexp = &dsaddr->stripe_indices[0]; + for (i = 0; i < dsaddr->stripe_count; i++) { + *indexp = be32_to_cpup(p++); + if (*indexp >= num) + goto out_err_free; + indexp++; + } + /* Skip already read multipath list count */ + p++; + + for (i = 0; i < dsaddr->ds_num; i++) { + int j; + + dummy = be32_to_cpup(p++); /* multipath count */ + if (dummy > 1) { + printk(KERN_WARNING + "%s: Multipath count %d not supported, " + "skipping all greater than 1\n", __func__, + dummy); + } + for (j = 0; j < dummy; j++) { + if (j == 0) { + dsaddr->ds_list[i] = decode_and_add_ds(&p, ino); + if (dsaddr->ds_list[i] == NULL) + goto out_err_free; + } else { + u32 len; + /* skip extra multipath */ + len = be32_to_cpup(p++); + p += XDR_QUADLEN(len); + len = be32_to_cpup(p++); + p += XDR_QUADLEN(len); + continue; + } + } + } + return dsaddr; + +out_err_free: + nfs4_fl_free_deviceid(dsaddr); +out_err: + dprintk("%s ERROR: returning NULL\n", __func__); + return NULL; +} + +/* + * Decode the opaque device specified in 'dev' + * and add it to the list of available devices. + * If the deviceid is already cached, nfs4_add_deviceid will return + * a pointer to the cached struct and throw away the new. + */ +static struct nfs4_file_layout_dsaddr* +decode_and_add_device(struct inode *inode, struct pnfs_device *dev) +{ + struct nfs4_file_layout_dsaddr *dsaddr; + struct pnfs_deviceid_node *d; + + dsaddr = decode_device(inode, dev); + if (!dsaddr) { + printk(KERN_WARNING "%s: Could not decode or add device\n", + __func__); + return NULL; + } + + d = pnfs_add_deviceid(NFS_SERVER(inode)->nfs_client->cl_devid_cache, + &dsaddr->deviceid); + + return container_of(d, struct nfs4_file_layout_dsaddr, deviceid); +} + +/* + * Retrieve the information for dev_id, add it to the list + * of available devices, and return it. + */ +struct nfs4_file_layout_dsaddr * +get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id) +{ + struct pnfs_device *pdev = NULL; + u32 max_resp_sz; + int max_pages; + struct page **pages = NULL; + struct nfs4_file_layout_dsaddr *dsaddr = NULL; + int rc, i; + struct nfs_server *server = NFS_SERVER(inode); + + /* + * Use the session max response size as the basis for setting + * GETDEVICEINFO's maxcount + */ + max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + max_pages = max_resp_sz >> PAGE_SHIFT; + dprintk("%s inode %p max_resp_sz %u max_pages %d\n", + __func__, inode, max_resp_sz, max_pages); + + pdev = kzalloc(sizeof(struct pnfs_device), GFP_KERNEL); + if (pdev == NULL) + return NULL; + + pages = kzalloc(max_pages * sizeof(struct page *), GFP_KERNEL); + if (pages == NULL) { + kfree(pdev); + return NULL; + } + for (i = 0; i < max_pages; i++) { + pages[i] = alloc_page(GFP_KERNEL); + if (!pages[i]) + goto out_free; + } + + /* set pdev->area */ + pdev->area = vmap(pages, max_pages, VM_MAP, PAGE_KERNEL); + if (!pdev->area) + goto out_free; + + memcpy(&pdev->dev_id, dev_id, sizeof(*dev_id)); + pdev->layout_type = LAYOUT_NFSV4_1_FILES; + pdev->pages = pages; + pdev->pgbase = 0; + pdev->pglen = PAGE_SIZE * max_pages; + pdev->mincount = 0; + + rc = nfs4_proc_getdeviceinfo(server, pdev); + dprintk("%s getdevice info returns %d\n", __func__, rc); + if (rc) + goto out_free; + + /* + * Found new device, need to decode it and then add it to the + * list of known devices for this mountpoint. + */ + dsaddr = decode_and_add_device(inode, pdev); +out_free: + if (pdev->area != NULL) + vunmap(pdev->area); + for (i = 0; i < max_pages; i++) + __free_page(pages[i]); + kfree(pages); + kfree(pdev); + dprintk("<-- %s dsaddr %p\n", __func__, dsaddr); + return dsaddr; +} + +struct nfs4_file_layout_dsaddr * +nfs4_fl_find_get_deviceid(struct nfs_client *clp, struct nfs4_deviceid *id) +{ + struct pnfs_deviceid_node *d; + + d = pnfs_find_get_deviceid(clp->cl_devid_cache, id); + return (d == NULL) ? NULL : + container_of(d, struct nfs4_file_layout_dsaddr, deviceid); +} diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index 089da5b5d20a..0f24cdf2cb13 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -55,6 +55,7 @@ #include "internal.h" #include "iostat.h" #include "callback.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_PROC @@ -129,7 +130,8 @@ const u32 nfs4_fsinfo_bitmap[2] = { FATTR4_WORD0_MAXFILESIZE | FATTR4_WORD0_MAXREAD | FATTR4_WORD0_MAXWRITE | FATTR4_WORD0_LEASE_TIME, - 0 + FATTR4_WORD1_TIME_DELTA + | FATTR4_WORD1_FS_LAYOUT_TYPES }; const u32 nfs4_fs_locations_bitmap[2] = { @@ -255,9 +257,6 @@ static int nfs4_handle_exception(const struct nfs_server *server, int errorcode, nfs4_state_mark_reclaim_nograce(clp, state); goto do_state_recovery; case -NFS4ERR_STALE_STATEID: - if (state == NULL) - break; - nfs4_state_mark_reclaim_reboot(clp, state); case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_EXPIRED: goto do_state_recovery; @@ -334,10 +333,12 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp * Must be called while holding tbl->slot_tbl_lock */ static void -nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid) +nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *free_slot) { + int free_slotid = free_slot - tbl->slots; int slotid = free_slotid; + BUG_ON(slotid < 0 || slotid >= NFS4_MAX_SLOT_TABLE); /* clear used bit in bitmap */ __clear_bit(slotid, tbl->used_slots); @@ -379,7 +380,7 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res) struct nfs4_slot_table *tbl; tbl = &res->sr_session->fc_slot_table; - if (res->sr_slotid == NFS4_MAX_SLOT_TABLE) { + if (!res->sr_slot) { /* just wake up the next guy waiting since * we may have not consumed a slot after all */ dprintk("%s: No slot\n", __func__); @@ -387,17 +388,15 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res) } spin_lock(&tbl->slot_tbl_lock); - nfs4_free_slot(tbl, res->sr_slotid); + nfs4_free_slot(tbl, res->sr_slot); nfs41_check_drain_session_complete(res->sr_session); spin_unlock(&tbl->slot_tbl_lock); - res->sr_slotid = NFS4_MAX_SLOT_TABLE; + res->sr_slot = NULL; } static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res) { unsigned long timestamp; - struct nfs4_slot_table *tbl; - struct nfs4_slot *slot; struct nfs_client *clp; /* @@ -410,17 +409,14 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res * res->sr_status = NFS_OK; /* -ERESTARTSYS can result in skipping nfs41_sequence_setup */ - if (res->sr_slotid == NFS4_MAX_SLOT_TABLE) + if (!res->sr_slot) goto out; - tbl = &res->sr_session->fc_slot_table; - slot = tbl->slots + res->sr_slotid; - /* Check the SEQUENCE operation status */ switch (res->sr_status) { case 0: /* Update the slot's sequence and clientid lease timer */ - ++slot->seq_nr; + ++res->sr_slot->seq_nr; timestamp = res->sr_renewal_time; clp = res->sr_session->clp; do_renew_lease(clp, timestamp); @@ -433,12 +429,14 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res * * returned NFS4ERR_DELAY as per Section 2.10.6.2 * of RFC5661. */ - dprintk("%s: slot=%d seq=%d: Operation in progress\n", - __func__, res->sr_slotid, slot->seq_nr); + dprintk("%s: slot=%td seq=%d: Operation in progress\n", + __func__, + res->sr_slot - res->sr_session->fc_slot_table.slots, + res->sr_slot->seq_nr); goto out_retry; default: /* Just update the slot sequence no. */ - ++slot->seq_nr; + ++res->sr_slot->seq_nr; } out: /* The session may be reset by one of the error handlers. */ @@ -505,10 +503,9 @@ static int nfs41_setup_sequence(struct nfs4_session *session, dprintk("--> %s\n", __func__); /* slot already allocated? */ - if (res->sr_slotid != NFS4_MAX_SLOT_TABLE) + if (res->sr_slot != NULL) return 0; - res->sr_slotid = NFS4_MAX_SLOT_TABLE; tbl = &session->fc_slot_table; spin_lock(&tbl->slot_tbl_lock); @@ -550,7 +547,7 @@ static int nfs41_setup_sequence(struct nfs4_session *session, dprintk("<-- %s slotid=%d seqid=%d\n", __func__, slotid, slot->seq_nr); res->sr_session = session; - res->sr_slotid = slotid; + res->sr_slot = slot; res->sr_renewal_time = jiffies; res->sr_status_flags = 0; /* @@ -576,8 +573,9 @@ int nfs4_setup_sequence(const struct nfs_server *server, goto out; } - dprintk("--> %s clp %p session %p sr_slotid %d\n", - __func__, session->clp, session, res->sr_slotid); + dprintk("--> %s clp %p session %p sr_slot %td\n", + __func__, session->clp, session, res->sr_slot ? + res->sr_slot - session->fc_slot_table.slots : -1); ret = nfs41_setup_sequence(session, args, res, cache_reply, task); @@ -650,7 +648,7 @@ static int nfs4_call_sync_sequence(struct nfs_server *server, .callback_data = &data }; - res->sr_slotid = NFS4_MAX_SLOT_TABLE; + res->sr_slot = NULL; if (privileged) task_setup.callback_ops = &nfs41_call_priv_sync_ops; task = rpc_run_task(&task_setup); @@ -735,7 +733,6 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p) p->o_res.server = p->o_arg.server; nfs_fattr_init(&p->f_attr); nfs_fattr_init(&p->dir_attr); - p->o_res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE; } static struct nfs4_opendata *nfs4_opendata_alloc(struct path *path, @@ -1120,6 +1117,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state * clear_bit(NFS_DELEGATED_STATE, &state->flags); smp_rmb(); if (state->n_rdwr != 0) { + clear_bit(NFS_O_RDWR_STATE, &state->flags); ret = nfs4_open_recover_helper(opendata, FMODE_READ|FMODE_WRITE, &newstate); if (ret != 0) return ret; @@ -1127,6 +1125,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state * return -ESTALE; } if (state->n_wronly != 0) { + clear_bit(NFS_O_WRONLY_STATE, &state->flags); ret = nfs4_open_recover_helper(opendata, FMODE_WRITE, &newstate); if (ret != 0) return ret; @@ -1134,6 +1133,7 @@ static int nfs4_open_recover(struct nfs4_opendata *opendata, struct nfs4_state * return -ESTALE; } if (state->n_rdonly != 0) { + clear_bit(NFS_O_RDONLY_STATE, &state->flags); ret = nfs4_open_recover_helper(opendata, FMODE_READ, &newstate); if (ret != 0) return ret; @@ -1188,7 +1188,7 @@ static int nfs4_do_open_reclaim(struct nfs_open_context *ctx, struct nfs4_state int err; do { err = _nfs4_do_open_reclaim(ctx, state); - if (err != -NFS4ERR_DELAY && err != -EKEYEXPIRED) + if (err != -NFS4ERR_DELAY) break; nfs4_handle_exception(server, err, &exception); } while (exception.retry); @@ -1258,6 +1258,13 @@ int nfs4_open_delegation_recall(struct nfs_open_context *ctx, struct nfs4_state case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_BAD_STATEID: nfs4_state_mark_reclaim_nograce(server->nfs_client, state); + case -EKEYEXPIRED: + /* + * User RPCSEC_GSS context has expired. + * We cannot recover this stateid now, so + * skip it and allow recovery thread to + * proceed. + */ case -ENOMEM: err = 0; goto out; @@ -1605,7 +1612,6 @@ static int nfs4_do_open_expired(struct nfs_open_context *ctx, struct nfs4_state goto out; case -NFS4ERR_GRACE: case -NFS4ERR_DELAY: - case -EKEYEXPIRED: nfs4_handle_exception(server, err, &exception); err = 0; } @@ -1975,7 +1981,6 @@ int nfs4_do_close(struct path *path, struct nfs4_state *state, gfp_t gfp_mask, i calldata->res.fattr = &calldata->fattr; calldata->res.seqid = calldata->arg.seqid; calldata->res.server = server; - calldata->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE; path_get(path); calldata->path = *path; @@ -1998,120 +2003,17 @@ out: return status; } -static int nfs4_intent_set_file(struct nameidata *nd, struct path *path, struct nfs4_state *state, fmode_t fmode) +static struct inode * +nfs4_atomic_open(struct inode *dir, struct nfs_open_context *ctx, int open_flags, struct iattr *attr) { - struct file *filp; - int ret; - - /* If the open_intent is for execute, we have an extra check to make */ - if (fmode & FMODE_EXEC) { - ret = nfs_may_open(state->inode, - state->owner->so_cred, - nd->intent.open.flags); - if (ret < 0) - goto out_close; - } - filp = lookup_instantiate_filp(nd, path->dentry, NULL); - if (!IS_ERR(filp)) { - struct nfs_open_context *ctx; - ctx = nfs_file_open_context(filp); - ctx->state = state; - return 0; - } - ret = PTR_ERR(filp); -out_close: - nfs4_close_sync(path, state, fmode & (FMODE_READ|FMODE_WRITE)); - return ret; -} - -struct dentry * -nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd) -{ - struct path path = { - .mnt = nd->path.mnt, - .dentry = dentry, - }; - struct dentry *parent; - struct iattr attr; - struct rpc_cred *cred; struct nfs4_state *state; - struct dentry *res; - int open_flags = nd->intent.open.flags; - fmode_t fmode = open_flags & (FMODE_READ | FMODE_WRITE | FMODE_EXEC); - - if (nd->flags & LOOKUP_CREATE) { - attr.ia_mode = nd->intent.open.create_mode; - attr.ia_valid = ATTR_MODE; - if (!IS_POSIXACL(dir)) - attr.ia_mode &= ~current_umask(); - } else { - open_flags &= ~O_EXCL; - attr.ia_valid = 0; - BUG_ON(open_flags & O_CREAT); - } - cred = rpc_lookup_cred(); - if (IS_ERR(cred)) - return (struct dentry *)cred; - parent = dentry->d_parent; /* Protect against concurrent sillydeletes */ - nfs_block_sillyrename(parent); - state = nfs4_do_open(dir, &path, fmode, open_flags, &attr, cred); - put_rpccred(cred); - if (IS_ERR(state)) { - if (PTR_ERR(state) == -ENOENT) { - d_add(dentry, NULL); - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - } - nfs_unblock_sillyrename(parent); - return (struct dentry *)state; - } - res = d_add_unique(dentry, igrab(state->inode)); - if (res != NULL) - path.dentry = res; - nfs_set_verifier(path.dentry, nfs_save_change_attribute(dir)); - nfs_unblock_sillyrename(parent); - nfs4_intent_set_file(nd, &path, state, fmode); - return res; -} - -int -nfs4_open_revalidate(struct inode *dir, struct dentry *dentry, int openflags, struct nameidata *nd) -{ - struct path path = { - .mnt = nd->path.mnt, - .dentry = dentry, - }; - struct rpc_cred *cred; - struct nfs4_state *state; - fmode_t fmode = openflags & (FMODE_READ | FMODE_WRITE); - - cred = rpc_lookup_cred(); - if (IS_ERR(cred)) - return PTR_ERR(cred); - state = nfs4_do_open(dir, &path, fmode, openflags, NULL, cred); - put_rpccred(cred); - if (IS_ERR(state)) { - switch (PTR_ERR(state)) { - case -EPERM: - case -EACCES: - case -EDQUOT: - case -ENOSPC: - case -EROFS: - return PTR_ERR(state); - default: - goto out_drop; - } - } - if (state->inode == dentry->d_inode) { - nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - nfs4_intent_set_file(nd, &path, state, fmode); - return 1; - } - nfs4_close_sync(&path, state, fmode); -out_drop: - d_drop(dentry); - return 0; + state = nfs4_do_open(dir, &ctx->path, ctx->mode, open_flags, attr, ctx->cred); + if (IS_ERR(state)) + return ERR_CAST(state); + ctx->state = state; + return igrab(state->inode); } static void nfs4_close_context(struct nfs_open_context *ctx, int is_sync) @@ -2568,36 +2470,34 @@ static int nfs4_proc_readlink(struct inode *inode, struct page *page, static int nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags, struct nameidata *nd) + int flags, struct nfs_open_context *ctx) { - struct path path = { - .mnt = nd->path.mnt, + struct path my_path = { .dentry = dentry, }; + struct path *path = &my_path; struct nfs4_state *state; - struct rpc_cred *cred; - fmode_t fmode = flags & (FMODE_READ | FMODE_WRITE); + struct rpc_cred *cred = NULL; + fmode_t fmode = 0; int status = 0; - cred = rpc_lookup_cred(); - if (IS_ERR(cred)) { - status = PTR_ERR(cred); - goto out; + if (ctx != NULL) { + cred = ctx->cred; + path = &ctx->path; + fmode = ctx->mode; } - state = nfs4_do_open(dir, &path, fmode, flags, sattr, cred); + state = nfs4_do_open(dir, path, fmode, flags, sattr, cred); d_drop(dentry); if (IS_ERR(state)) { status = PTR_ERR(state); - goto out_putcred; + goto out; } d_add(dentry, igrab(state->inode)); nfs_set_verifier(dentry, nfs_save_change_attribute(dir)); - if (status == 0 && (nd->flags & LOOKUP_OPEN) != 0) - status = nfs4_intent_set_file(nd, &path, state, fmode); + if (ctx != NULL) + ctx->state = state; else - nfs4_close_sync(&path, state, fmode); -out_putcred: - put_rpccred(cred); + nfs4_close_sync(path, state, fmode); out: return status; } @@ -2655,6 +2555,7 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir) args->bitmask = server->cache_consistency_bitmask; res->server = server; + res->seq_res.sr_slot = NULL; msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_REMOVE]; } @@ -2671,18 +2572,46 @@ static int nfs4_proc_unlink_done(struct rpc_task *task, struct inode *dir) return 1; } +static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir) +{ + struct nfs_server *server = NFS_SERVER(dir); + struct nfs_renameargs *arg = msg->rpc_argp; + struct nfs_renameres *res = msg->rpc_resp; + + msg->rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_RENAME]; + arg->bitmask = server->attr_bitmask; + res->server = server; +} + +static int nfs4_proc_rename_done(struct rpc_task *task, struct inode *old_dir, + struct inode *new_dir) +{ + struct nfs_renameres *res = task->tk_msg.rpc_resp; + + if (!nfs4_sequence_done(task, &res->seq_res)) + return 0; + if (nfs4_async_handle_error(task, res->server, NULL) == -EAGAIN) + return 0; + + update_changeattr(old_dir, &res->old_cinfo); + nfs_post_op_update_inode(old_dir, res->old_fattr); + update_changeattr(new_dir, &res->new_cinfo); + nfs_post_op_update_inode(new_dir, res->new_fattr); + return 1; +} + static int _nfs4_proc_rename(struct inode *old_dir, struct qstr *old_name, struct inode *new_dir, struct qstr *new_name) { struct nfs_server *server = NFS_SERVER(old_dir); - struct nfs4_rename_arg arg = { + struct nfs_renameargs arg = { .old_dir = NFS_FH(old_dir), .new_dir = NFS_FH(new_dir), .old_name = old_name, .new_name = new_name, .bitmask = server->attr_bitmask, }; - struct nfs4_rename_res res = { + struct nfs_renameres res = { .server = server, }; struct rpc_message msg = { @@ -2896,15 +2825,16 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry, } static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page *page, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, int plus) { struct inode *dir = dentry->d_inode; struct nfs4_readdir_arg args = { .fh = NFS_FH(dir), - .pages = &page, + .pages = pages, .pgbase = 0, .count = count, .bitmask = NFS_SERVER(dentry->d_inode)->attr_bitmask, + .plus = plus, }; struct nfs4_readdir_res res; struct rpc_message msg = { @@ -2932,14 +2862,14 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, } static int nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page *page, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, int plus) { struct nfs4_exception exception = { }; int err; do { err = nfs4_handle_exception(NFS_SERVER(dentry->d_inode), _nfs4_proc_readdir(dentry, cred, cookie, - page, count, plus), + pages, count, plus), &exception); } while (exception.retry); return err; @@ -3490,9 +3420,6 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server, nfs4_state_mark_reclaim_nograce(clp, state); goto do_state_recovery; case -NFS4ERR_STALE_STATEID: - if (state == NULL) - break; - nfs4_state_mark_reclaim_reboot(clp, state); case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_EXPIRED: goto do_state_recovery; @@ -3626,7 +3553,6 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp, case -NFS4ERR_RESOURCE: /* The IBM lawyers misread another document! */ case -NFS4ERR_DELAY: - case -EKEYEXPIRED: err = nfs4_delay(clp->cl_rpcclient, &timeout); } } while (err == 0); @@ -3721,7 +3647,6 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co memcpy(&data->stateid, stateid, sizeof(data->stateid)); data->res.fattr = &data->fattr; data->res.server = server; - data->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE; nfs_fattr_init(data->res.fattr); data->timestamp = jiffies; data->rpc_status = 0; @@ -3874,7 +3799,6 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl, p->arg.fl = &p->fl; p->arg.seqid = seqid; p->res.seqid = seqid; - p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE; p->arg.stateid = &lsp->ls_stateid; p->lsp = lsp; atomic_inc(&lsp->ls_count); @@ -4054,7 +3978,6 @@ static struct nfs4_lockdata *nfs4_alloc_lockdata(struct file_lock *fl, p->arg.lock_owner.clientid = server->nfs_client->cl_clientid; p->arg.lock_owner.id = lsp->ls_id.id; p->res.lock_seqid = p->arg.lock_seqid; - p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE; p->lsp = lsp; p->server = server; atomic_inc(&lsp->ls_count); @@ -4241,7 +4164,7 @@ static int nfs4_lock_reclaim(struct nfs4_state *state, struct file_lock *request if (test_bit(NFS_DELEGATED_STATE, &state->flags) != 0) return 0; err = _nfs4_do_setlk(state, F_SETLK, request, NFS_LOCK_RECLAIM); - if (err != -NFS4ERR_DELAY && err != -EKEYEXPIRED) + if (err != -NFS4ERR_DELAY) break; nfs4_handle_exception(server, err, &exception); } while (exception.retry); @@ -4266,7 +4189,6 @@ static int nfs4_lock_expired(struct nfs4_state *state, struct file_lock *request goto out; case -NFS4ERR_GRACE: case -NFS4ERR_DELAY: - case -EKEYEXPIRED: nfs4_handle_exception(server, err, &exception); err = 0; } @@ -4412,13 +4334,21 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl) nfs4_state_mark_reclaim_nograce(server->nfs_client, state); err = 0; goto out; + case -EKEYEXPIRED: + /* + * User RPCSEC_GSS context has expired. + * We cannot recover this stateid now, so + * skip it and allow recovery thread to + * proceed. + */ + err = 0; + goto out; case -ENOMEM: case -NFS4ERR_DENIED: /* kill_proc(fl->fl_pid, SIGLOST, 1); */ err = 0; goto out; case -NFS4ERR_DELAY: - case -EKEYEXPIRED: break; } err = nfs4_handle_exception(server, err, &exception); @@ -4647,7 +4577,6 @@ static void nfs4_get_lease_time_done(struct rpc_task *task, void *calldata) switch (task->tk_status) { case -NFS4ERR_DELAY: case -NFS4ERR_GRACE: - case -EKEYEXPIRED: dprintk("%s Retry: tk_status %d\n", __func__, task->tk_status); rpc_delay(task, NFS4_POLL_RETRY_MIN); task->tk_status = 0; @@ -4687,7 +4616,6 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo) }; int status; - res.lr_seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE; dprintk("--> %s\n", __func__); task = rpc_run_task(&task_setup); @@ -4914,49 +4842,56 @@ static void nfs4_init_channel_attrs(struct nfs41_create_session_args *args) args->bc_attrs.max_reqs); } -static int _verify_channel_attr(char *chan, char *attr_name, u32 sent, u32 rcvd) +static int nfs4_verify_fore_channel_attrs(struct nfs41_create_session_args *args, struct nfs4_session *session) { - if (rcvd <= sent) - return 0; - printk(KERN_WARNING "%s: Session INVALID: %s channel %s increased. " - "sent=%u rcvd=%u\n", __func__, chan, attr_name, sent, rcvd); - return -EINVAL; + struct nfs4_channel_attrs *sent = &args->fc_attrs; + struct nfs4_channel_attrs *rcvd = &session->fc_attrs; + + if (rcvd->headerpadsz > sent->headerpadsz) + return -EINVAL; + if (rcvd->max_resp_sz > sent->max_resp_sz) + return -EINVAL; + /* + * Our requested max_ops is the minimum we need; we're not + * prepared to break up compounds into smaller pieces than that. + * So, no point even trying to continue if the server won't + * cooperate: + */ + if (rcvd->max_ops < sent->max_ops) + return -EINVAL; + if (rcvd->max_reqs == 0) + return -EINVAL; + return 0; } -#define _verify_fore_channel_attr(_name_) \ - _verify_channel_attr("fore", #_name_, \ - args->fc_attrs._name_, \ - session->fc_attrs._name_) +static int nfs4_verify_back_channel_attrs(struct nfs41_create_session_args *args, struct nfs4_session *session) +{ + struct nfs4_channel_attrs *sent = &args->bc_attrs; + struct nfs4_channel_attrs *rcvd = &session->bc_attrs; -#define _verify_back_channel_attr(_name_) \ - _verify_channel_attr("back", #_name_, \ - args->bc_attrs._name_, \ - session->bc_attrs._name_) + if (rcvd->max_rqst_sz > sent->max_rqst_sz) + return -EINVAL; + if (rcvd->max_resp_sz < sent->max_resp_sz) + return -EINVAL; + if (rcvd->max_resp_sz_cached > sent->max_resp_sz_cached) + return -EINVAL; + /* These would render the backchannel useless: */ + if (rcvd->max_ops == 0) + return -EINVAL; + if (rcvd->max_reqs == 0) + return -EINVAL; + return 0; +} -/* - * The server is not allowed to increase the fore channel header pad size, - * maximum response size, or maximum number of operations. - * - * The back channel attributes are only negotiatied down: We send what the - * (back channel) server insists upon. - */ static int nfs4_verify_channel_attrs(struct nfs41_create_session_args *args, struct nfs4_session *session) { - int ret = 0; - - ret |= _verify_fore_channel_attr(headerpadsz); - ret |= _verify_fore_channel_attr(max_resp_sz); - ret |= _verify_fore_channel_attr(max_ops); - - ret |= _verify_back_channel_attr(headerpadsz); - ret |= _verify_back_channel_attr(max_rqst_sz); - ret |= _verify_back_channel_attr(max_resp_sz); - ret |= _verify_back_channel_attr(max_resp_sz_cached); - ret |= _verify_back_channel_attr(max_ops); - ret |= _verify_back_channel_attr(max_reqs); + int ret; - return ret; + ret = nfs4_verify_fore_channel_attrs(args, session); + if (ret) + return ret; + return nfs4_verify_back_channel_attrs(args, session); } static int _nfs4_proc_create_session(struct nfs_client *clp) @@ -5111,7 +5046,6 @@ static int nfs41_sequence_handle_errors(struct rpc_task *task, struct nfs_client { switch(task->tk_status) { case -NFS4ERR_DELAY: - case -EKEYEXPIRED: rpc_delay(task, NFS4_POLL_RETRY_MAX); return -EAGAIN; default: @@ -5180,12 +5114,11 @@ static struct rpc_task *_nfs41_proc_sequence(struct nfs_client *clp, struct rpc_ if (!atomic_inc_not_zero(&clp->cl_count)) return ERR_PTR(-EIO); - calldata = kmalloc(sizeof(*calldata), GFP_NOFS); + calldata = kzalloc(sizeof(*calldata), GFP_NOFS); if (calldata == NULL) { nfs_put_client(clp); return ERR_PTR(-ENOMEM); } - calldata->res.sr_slotid = NFS4_MAX_SLOT_TABLE; msg.rpc_argp = &calldata->args; msg.rpc_resp = &calldata->res; calldata->clp = clp; @@ -5254,7 +5187,6 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf case -NFS4ERR_WRONG_CRED: /* What to do here? */ break; case -NFS4ERR_DELAY: - case -EKEYEXPIRED: rpc_delay(task, NFS4_POLL_RETRY_MAX); return -EAGAIN; default: @@ -5317,7 +5249,6 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp) goto out; calldata->clp = clp; calldata->arg.one_fs = 0; - calldata->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE; msg.rpc_argp = &calldata->arg; msg.rpc_resp = &calldata->res; @@ -5333,6 +5264,147 @@ out: dprintk("<-- %s status=%d\n", __func__, status); return status; } + +static void +nfs4_layoutget_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutget *lgp = calldata; + struct inode *ino = lgp->args.inode; + struct nfs_server *server = NFS_SERVER(ino); + + dprintk("--> %s\n", __func__); + if (nfs4_setup_sequence(server, &lgp->args.seq_args, + &lgp->res.seq_res, 0, task)) + return; + rpc_call_start(task); +} + +static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) +{ + struct nfs4_layoutget *lgp = calldata; + struct nfs_server *server = NFS_SERVER(lgp->args.inode); + + dprintk("--> %s\n", __func__); + + if (!nfs4_sequence_done(task, &lgp->res.seq_res)) + return; + + switch (task->tk_status) { + case 0: + break; + case -NFS4ERR_LAYOUTTRYLATER: + case -NFS4ERR_RECALLCONFLICT: + task->tk_status = -NFS4ERR_DELAY; + /* Fall through */ + default: + if (nfs4_async_handle_error(task, server, NULL) == -EAGAIN) { + rpc_restart_call_prepare(task); + return; + } + } + lgp->status = task->tk_status; + dprintk("<-- %s\n", __func__); +} + +static void nfs4_layoutget_release(void *calldata) +{ + struct nfs4_layoutget *lgp = calldata; + + dprintk("--> %s\n", __func__); + put_layout_hdr(lgp->args.inode); + if (lgp->res.layout.buf != NULL) + free_page((unsigned long) lgp->res.layout.buf); + put_nfs_open_context(lgp->args.ctx); + kfree(calldata); + dprintk("<-- %s\n", __func__); +} + +static const struct rpc_call_ops nfs4_layoutget_call_ops = { + .rpc_call_prepare = nfs4_layoutget_prepare, + .rpc_call_done = nfs4_layoutget_done, + .rpc_release = nfs4_layoutget_release, +}; + +int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) +{ + struct nfs_server *server = NFS_SERVER(lgp->args.inode); + struct rpc_task *task; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTGET], + .rpc_argp = &lgp->args, + .rpc_resp = &lgp->res, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = server->client, + .rpc_message = &msg, + .callback_ops = &nfs4_layoutget_call_ops, + .callback_data = lgp, + .flags = RPC_TASK_ASYNC, + }; + int status = 0; + + dprintk("--> %s\n", __func__); + + lgp->res.layout.buf = (void *)__get_free_page(GFP_NOFS); + if (lgp->res.layout.buf == NULL) { + nfs4_layoutget_release(lgp); + return -ENOMEM; + } + + lgp->res.seq_res.sr_slot = NULL; + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + status = nfs4_wait_for_completion_rpc_task(task); + if (status != 0) + goto out; + status = lgp->status; + if (status != 0) + goto out; + status = pnfs_layout_process(lgp); +out: + rpc_put_task(task); + dprintk("<-- %s status=%d\n", __func__, status); + return status; +} + +static int +_nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev) +{ + struct nfs4_getdeviceinfo_args args = { + .pdev = pdev, + }; + struct nfs4_getdeviceinfo_res res = { + .pdev = pdev, + }; + struct rpc_message msg = { + .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETDEVICEINFO], + .rpc_argp = &args, + .rpc_resp = &res, + }; + int status; + + dprintk("--> %s\n", __func__); + status = nfs4_call_sync(server, &msg, &args, &res, 0); + dprintk("<-- %s status=%d\n", __func__, status); + + return status; +} + +int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *pdev) +{ + struct nfs4_exception exception = { }; + int err; + + do { + err = nfs4_handle_exception(server, + _nfs4_proc_getdeviceinfo(server, pdev), + &exception); + } while (exception.retry); + return err; +} +EXPORT_SYMBOL_GPL(nfs4_proc_getdeviceinfo); + #endif /* CONFIG_NFS_V4_1 */ struct nfs4_state_recovery_ops nfs40_reboot_recovery_ops = { @@ -5443,6 +5515,8 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .unlink_setup = nfs4_proc_unlink_setup, .unlink_done = nfs4_proc_unlink_done, .rename = nfs4_proc_rename, + .rename_setup = nfs4_proc_rename_setup, + .rename_done = nfs4_proc_rename_done, .link = nfs4_proc_link, .symlink = nfs4_proc_symlink, .mkdir = nfs4_proc_mkdir, @@ -5463,6 +5537,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .lock = nfs4_proc_lock, .clear_acl_cache = nfs4_zap_acl_attr, .close_context = nfs4_close_context, + .open_context = nfs4_atomic_open, }; /* diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index 3e2f19b04c06..f575a3126737 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -40,12 +40,13 @@ #include <linux/kernel.h> #include <linux/slab.h> -#include <linux/smp_lock.h> +#include <linux/fs.h> #include <linux/nfs_fs.h> #include <linux/nfs_idmap.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/random.h> +#include <linux/ratelimit.h> #include <linux/workqueue.h> #include <linux/bitops.h> @@ -53,6 +54,7 @@ #include "callback.h" #include "delegation.h" #include "internal.h" +#include "pnfs.h" #define OPENOWNER_POOL_SIZE 8 @@ -970,13 +972,13 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ /* Guard against delegation returns and new lock/unlock calls */ down_write(&nfsi->rwsem); /* Protect inode->i_flock using the BKL */ - lock_kernel(); + lock_flocks(); for (fl = inode->i_flock; fl != NULL; fl = fl->fl_next) { if (!(fl->fl_flags & (FL_POSIX|FL_FLOCK))) continue; if (nfs_file_open_context(fl->fl_file)->state != state) continue; - unlock_kernel(); + unlock_flocks(); status = ops->recover_lock(state, fl); switch (status) { case 0: @@ -1003,9 +1005,9 @@ static int nfs4_reclaim_locks(struct nfs4_state *state, const struct nfs4_state_ /* kill_proc(fl->fl_pid, SIGLOST, 1); */ status = 0; } - lock_kernel(); + lock_flocks(); } - unlock_kernel(); + unlock_flocks(); out: up_write(&nfsi->rwsem); return status; @@ -1063,6 +1065,14 @@ restart: /* Mark the file as being 'closed' */ state->state = 0; break; + case -EKEYEXPIRED: + /* + * User RPCSEC_GSS context has expired. + * We cannot recover this stateid now, so + * skip it and allow recovery thread to + * proceed. + */ + break; case -NFS4ERR_ADMIN_REVOKED: case -NFS4ERR_STALE_STATEID: case -NFS4ERR_BAD_STATEID: @@ -1138,16 +1148,14 @@ static void nfs4_reclaim_complete(struct nfs_client *clp, (void)ops->reclaim_complete(clp); } -static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp) +static int nfs4_state_clear_reclaim_reboot(struct nfs_client *clp) { struct nfs4_state_owner *sp; struct rb_node *pos; struct nfs4_state *state; if (!test_and_clear_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) - return; - - nfs4_reclaim_complete(clp, clp->cl_mvops->reboot_recovery_ops); + return 0; for (pos = rb_first(&clp->cl_state_owners); pos != NULL; pos = rb_next(pos)) { sp = rb_entry(pos, struct nfs4_state_owner, so_client_node); @@ -1161,6 +1169,14 @@ static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp) } nfs_delegation_reap_unclaimed(clp); + return 1; +} + +static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp) +{ + if (!nfs4_state_clear_reclaim_reboot(clp)) + return; + nfs4_reclaim_complete(clp, clp->cl_mvops->reboot_recovery_ops); } static void nfs_delegation_clear_all(struct nfs_client *clp) @@ -1175,6 +1191,14 @@ static void nfs4_state_start_reclaim_nograce(struct nfs_client *clp) nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_nograce); } +static void nfs4_warn_keyexpired(const char *s) +{ + printk_ratelimited(KERN_WARNING "Error: state manager" + " encountered RPCSEC_GSS session" + " expired against NFSv4 server %s.\n", + s); +} + static int nfs4_recovery_handle_error(struct nfs_client *clp, int error) { switch (error) { @@ -1187,7 +1211,7 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error) case -NFS4ERR_STALE_CLIENTID: case -NFS4ERR_LEASE_MOVED: set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); - nfs4_state_end_reclaim_reboot(clp); + nfs4_state_clear_reclaim_reboot(clp); nfs4_state_start_reclaim_reboot(clp); break; case -NFS4ERR_EXPIRED: @@ -1204,6 +1228,10 @@ static int nfs4_recovery_handle_error(struct nfs_client *clp, int error) set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state); /* Zero session reset errors */ return 0; + case -EKEYEXPIRED: + /* Nothing we can do */ + nfs4_warn_keyexpired(clp->cl_hostname); + return 0; } return error; } @@ -1414,9 +1442,10 @@ static void nfs4_set_lease_expired(struct nfs_client *clp, int status) case -NFS4ERR_DELAY: case -NFS4ERR_CLID_INUSE: case -EAGAIN: - case -EKEYEXPIRED: break; + case -EKEYEXPIRED: + nfs4_warn_keyexpired(clp->cl_hostname); case -NFS4ERR_NOT_SAME: /* FixMe: implement recovery * in nfs4_exchange_id */ default: @@ -1447,6 +1476,7 @@ static void nfs4_state_manager(struct nfs_client *clp) } clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); + pnfs_destroy_all_layouts(clp); } if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) { diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 08ef91291132..f313c4cce7e4 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -52,6 +52,7 @@ #include <linux/nfs_idmap.h> #include "nfs4_fs.h" #include "internal.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_XDR @@ -310,6 +311,19 @@ static int nfs4_stat_to_errno(int); XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) #define encode_reclaim_complete_maxsz (op_encode_hdr_maxsz + 4) #define decode_reclaim_complete_maxsz (op_decode_hdr_maxsz + 4) +#define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + 4 + \ + XDR_QUADLEN(NFS4_DEVICEID4_SIZE)) +#define decode_getdeviceinfo_maxsz (op_decode_hdr_maxsz + \ + 1 /* layout type */ + \ + 1 /* opaque devaddr4 length */ + \ + /* devaddr4 payload is read into page */ \ + 1 /* notification bitmap length */ + \ + 1 /* notification bitmap */) +#define encode_layoutget_maxsz (op_encode_hdr_maxsz + 10 + \ + encode_stateid_maxsz) +#define decode_layoutget_maxsz (op_decode_hdr_maxsz + 8 + \ + decode_stateid_maxsz + \ + XDR_QUADLEN(PNFS_LAYOUT_MAXSIZE)) #else /* CONFIG_NFS_V4_1 */ #define encode_sequence_maxsz 0 #define decode_sequence_maxsz 0 @@ -699,6 +713,20 @@ static int nfs4_stat_to_errno(int); #define NFS4_dec_reclaim_complete_sz (compound_decode_hdr_maxsz + \ decode_sequence_maxsz + \ decode_reclaim_complete_maxsz) +#define NFS4_enc_getdeviceinfo_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz +\ + encode_getdeviceinfo_maxsz) +#define NFS4_dec_getdeviceinfo_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_getdeviceinfo_maxsz) +#define NFS4_enc_layoutget_sz (compound_encode_hdr_maxsz + \ + encode_sequence_maxsz + \ + encode_putfh_maxsz + \ + encode_layoutget_maxsz) +#define NFS4_dec_layoutget_sz (compound_decode_hdr_maxsz + \ + decode_sequence_maxsz + \ + decode_putfh_maxsz + \ + decode_layoutget_maxsz) const u32 nfs41_maxwrite_overhead = ((RPC_MAX_HEADER_WITH_AUTH + compound_encode_hdr_maxsz + @@ -816,7 +844,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const if (iap->ia_valid & ATTR_MODE) len += 4; if (iap->ia_valid & ATTR_UID) { - owner_namelen = nfs_map_uid_to_name(server->nfs_client, iap->ia_uid, owner_name); + owner_namelen = nfs_map_uid_to_name(server->nfs_client, iap->ia_uid, owner_name, IDMAP_NAMESZ); if (owner_namelen < 0) { dprintk("nfs: couldn't resolve uid %d to string\n", iap->ia_uid); @@ -828,7 +856,7 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap, const len += 4 + (XDR_QUADLEN(owner_namelen) << 2); } if (iap->ia_valid & ATTR_GID) { - owner_grouplen = nfs_map_gid_to_group(server->nfs_client, iap->ia_gid, owner_group); + owner_grouplen = nfs_map_gid_to_group(server->nfs_client, iap->ia_gid, owner_group, IDMAP_NAMESZ); if (owner_grouplen < 0) { dprintk("nfs: couldn't resolve gid %d to string\n", iap->ia_gid); @@ -1385,24 +1413,35 @@ static void encode_read(struct xdr_stream *xdr, const struct nfs_readargs *args, static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg *readdir, struct rpc_rqst *req, struct compound_hdr *hdr) { - uint32_t attrs[2] = { - FATTR4_WORD0_RDATTR_ERROR|FATTR4_WORD0_FILEID, - FATTR4_WORD1_MOUNTED_ON_FILEID, - }; + uint32_t attrs[2] = {0, 0}; + uint32_t dircount = readdir->count >> 1; __be32 *p; + if (readdir->plus) { + attrs[0] |= FATTR4_WORD0_TYPE|FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE| + FATTR4_WORD0_FSID|FATTR4_WORD0_FILEHANDLE; + attrs[1] |= 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; + dircount >>= 1; + } + attrs[0] |= FATTR4_WORD0_RDATTR_ERROR|FATTR4_WORD0_FILEID; + attrs[1] |= FATTR4_WORD1_MOUNTED_ON_FILEID; + /* Switch to mounted_on_fileid if the server supports it */ + if (readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID) + attrs[0] &= ~FATTR4_WORD0_FILEID; + else + attrs[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; + p = reserve_space(xdr, 12+NFS4_VERIFIER_SIZE+20); *p++ = cpu_to_be32(OP_READDIR); p = xdr_encode_hyper(p, readdir->cookie); p = xdr_encode_opaque_fixed(p, readdir->verifier.data, NFS4_VERIFIER_SIZE); - *p++ = cpu_to_be32(readdir->count >> 1); /* We're not doing readdirplus */ + *p++ = cpu_to_be32(dircount); *p++ = cpu_to_be32(readdir->count); *p++ = cpu_to_be32(2); - /* Switch to mounted_on_fileid if the server supports it */ - if (readdir->bitmask[1] & FATTR4_WORD1_MOUNTED_ON_FILEID) - attrs[0] &= ~FATTR4_WORD0_FILEID; - else - attrs[1] &= ~FATTR4_WORD1_MOUNTED_ON_FILEID; + *p++ = cpu_to_be32(attrs[0] & readdir->bitmask[0]); *p = cpu_to_be32(attrs[1] & readdir->bitmask[1]); hdr->nops++; @@ -1726,6 +1765,58 @@ static void encode_sequence(struct xdr_stream *xdr, #endif /* CONFIG_NFS_V4_1 */ } +#ifdef CONFIG_NFS_V4_1 +static void +encode_getdeviceinfo(struct xdr_stream *xdr, + const struct nfs4_getdeviceinfo_args *args, + struct compound_hdr *hdr) +{ + __be32 *p; + + p = reserve_space(xdr, 16 + NFS4_DEVICEID4_SIZE); + *p++ = cpu_to_be32(OP_GETDEVICEINFO); + p = xdr_encode_opaque_fixed(p, args->pdev->dev_id.data, + NFS4_DEVICEID4_SIZE); + *p++ = cpu_to_be32(args->pdev->layout_type); + *p++ = cpu_to_be32(args->pdev->pglen); /* gdia_maxcount */ + *p++ = cpu_to_be32(0); /* bitmap length 0 */ + hdr->nops++; + hdr->replen += decode_getdeviceinfo_maxsz; +} + +static void +encode_layoutget(struct xdr_stream *xdr, + const struct nfs4_layoutget_args *args, + struct compound_hdr *hdr) +{ + nfs4_stateid stateid; + __be32 *p; + + p = reserve_space(xdr, 44 + NFS4_STATEID_SIZE); + *p++ = cpu_to_be32(OP_LAYOUTGET); + *p++ = cpu_to_be32(0); /* Signal layout available */ + *p++ = cpu_to_be32(args->type); + *p++ = cpu_to_be32(args->range.iomode); + p = xdr_encode_hyper(p, args->range.offset); + p = xdr_encode_hyper(p, args->range.length); + p = xdr_encode_hyper(p, args->minlength); + pnfs_get_layout_stateid(&stateid, NFS_I(args->inode)->layout, + args->ctx->state); + p = xdr_encode_opaque_fixed(p, &stateid.data, NFS4_STATEID_SIZE); + *p = cpu_to_be32(args->maxcount); + + dprintk("%s: 1st type:0x%x iomode:%d off:%lu len:%lu mc:%d\n", + __func__, + args->type, + args->range.iomode, + (unsigned long)args->range.offset, + (unsigned long)args->range.length, + args->maxcount); + hdr->nops++; + hdr->replen += decode_layoutget_maxsz; +} +#endif /* CONFIG_NFS_V4_1 */ + /* * END OF "GENERIC" ENCODE ROUTINES. */ @@ -1823,7 +1914,7 @@ static int nfs4_xdr_enc_remove(struct rpc_rqst *req, __be32 *p, const struct nfs /* * Encode RENAME request */ -static int nfs4_xdr_enc_rename(struct rpc_rqst *req, __be32 *p, const struct nfs4_rename_arg *args) +static int nfs4_xdr_enc_rename(struct rpc_rqst *req, __be32 *p, const struct nfs_renameargs *args) { struct xdr_stream xdr; struct compound_hdr hdr = { @@ -2543,6 +2634,51 @@ static int nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req, uint32_t *p, return 0; } +/* + * Encode GETDEVICEINFO request + */ +static int nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req, uint32_t *p, + struct nfs4_getdeviceinfo_args *args) +{ + struct xdr_stream xdr; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + xdr_init_encode(&xdr, &req->rq_snd_buf, p); + encode_compound_hdr(&xdr, req, &hdr); + encode_sequence(&xdr, &args->seq_args, &hdr); + encode_getdeviceinfo(&xdr, args, &hdr); + + /* set up reply kvec. Subtract notification bitmap max size (2) + * so that notification bitmap is put in xdr_buf tail */ + xdr_inline_pages(&req->rq_rcv_buf, (hdr.replen - 2) << 2, + args->pdev->pages, args->pdev->pgbase, + args->pdev->pglen); + + encode_nops(&hdr); + return 0; +} + +/* + * Encode LAYOUTGET request + */ +static int nfs4_xdr_enc_layoutget(struct rpc_rqst *req, uint32_t *p, + struct nfs4_layoutget_args *args) +{ + struct xdr_stream xdr; + struct compound_hdr hdr = { + .minorversion = nfs4_xdr_minorversion(&args->seq_args), + }; + + xdr_init_encode(&xdr, &req->rq_snd_buf, p); + encode_compound_hdr(&xdr, req, &hdr); + encode_sequence(&xdr, &args->seq_args, &hdr); + encode_putfh(&xdr, NFS_FH(args->inode), &hdr); + encode_layoutget(&xdr, args, &hdr); + encode_nops(&hdr); + return 0; +} #endif /* CONFIG_NFS_V4_1 */ static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) @@ -2676,7 +2812,10 @@ out_overflow: static int decode_attr_supported(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *bitmask) { if (likely(bitmap[0] & FATTR4_WORD0_SUPPORTED_ATTRS)) { - decode_attr_bitmap(xdr, bitmask); + int ret; + ret = decode_attr_bitmap(xdr, bitmask); + if (unlikely(ret < 0)) + return ret; bitmap[0] &= ~FATTR4_WORD0_SUPPORTED_ATTRS; } else bitmask[0] = bitmask[1] = 0; @@ -2848,6 +2987,56 @@ out_overflow: return -EIO; } +static int decode_attr_error(struct xdr_stream *xdr, uint32_t *bitmap) +{ + __be32 *p; + + if (unlikely(bitmap[0] & (FATTR4_WORD0_RDATTR_ERROR - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_RDATTR_ERROR)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR; + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_attr_filehandle(struct xdr_stream *xdr, uint32_t *bitmap, struct nfs_fh *fh) +{ + __be32 *p; + int len; + + if (fh != NULL) + memset(fh, 0, sizeof(*fh)); + + if (unlikely(bitmap[0] & (FATTR4_WORD0_FILEHANDLE - 1U))) + return -EIO; + if (likely(bitmap[0] & FATTR4_WORD0_FILEHANDLE)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + if (len > NFS4_FHSIZE) + return -EIO; + p = xdr_inline_decode(xdr, len); + if (unlikely(!p)) + goto out_overflow; + if (fh != NULL) { + memcpy(fh->data, p, len); + fh->size = len; + } + bitmap[0] &= ~FATTR4_WORD0_FILEHANDLE; + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + static int decode_attr_aclsupport(struct xdr_stream *xdr, uint32_t *bitmap, uint32_t *res) { __be32 *p; @@ -3521,6 +3710,24 @@ static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, s return status; } +static int decode_attr_time_delta(struct xdr_stream *xdr, uint32_t *bitmap, + struct timespec *time) +{ + int status = 0; + + time->tv_sec = 0; + time->tv_nsec = 0; + if (unlikely(bitmap[1] & (FATTR4_WORD1_TIME_DELTA - 1U))) + return -EIO; + if (likely(bitmap[1] & FATTR4_WORD1_TIME_DELTA)) { + status = decode_attr_time(xdr, time); + bitmap[1] &= ~FATTR4_WORD1_TIME_DELTA; + } + dprintk("%s: time_delta=%ld %ld\n", __func__, (long)time->tv_sec, + (long)time->tv_nsec); + return status; +} + static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec *time) { int status = 0; @@ -3744,29 +3951,14 @@ xdr_error: return status; } -static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, +static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap, + struct nfs_fattr *fattr, struct nfs_fh *fh, const struct nfs_server *server, int may_sleep) { - __be32 *savep; - uint32_t attrlen, - bitmap[2] = {0}, - type; int status; umode_t fmode = 0; uint64_t fileid; - - status = decode_op_hdr(xdr, OP_GETATTR); - if (status < 0) - goto xdr_error; - - status = decode_attr_bitmap(xdr, bitmap); - if (status < 0) - goto xdr_error; - - status = decode_attr_length(xdr, &attrlen, &savep); - if (status < 0) - goto xdr_error; - + uint32_t type; status = decode_attr_type(xdr, bitmap, &type); if (status < 0) @@ -3792,6 +3984,14 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, goto xdr_error; fattr->valid |= status; + status = decode_attr_error(xdr, bitmap); + if (status < 0) + goto xdr_error; + + status = decode_attr_filehandle(xdr, bitmap, fh); + if (status < 0) + goto xdr_error; + status = decode_attr_fileid(xdr, bitmap, &fattr->fileid); if (status < 0) goto xdr_error; @@ -3862,12 +4062,101 @@ static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, fattr->valid |= status; } +xdr_error: + dprintk("%s: xdr returned %d\n", __func__, -status); + return status; +} + +static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fattr, + struct nfs_fh *fh, const struct nfs_server *server, int may_sleep) +{ + __be32 *savep; + uint32_t attrlen, + bitmap[2] = {0}; + int status; + + status = decode_op_hdr(xdr, OP_GETATTR); + if (status < 0) + goto xdr_error; + + status = decode_attr_bitmap(xdr, bitmap); + if (status < 0) + goto xdr_error; + + status = decode_attr_length(xdr, &attrlen, &savep); + if (status < 0) + goto xdr_error; + + status = decode_getfattr_attrs(xdr, bitmap, fattr, fh, server, may_sleep); + if (status < 0) + goto xdr_error; + status = verify_attr_len(xdr, savep, attrlen); xdr_error: dprintk("%s: xdr returned %d\n", __func__, -status); return status; } +static int decode_getfattr(struct xdr_stream *xdr, struct nfs_fattr *fattr, + const struct nfs_server *server, int may_sleep) +{ + return decode_getfattr_generic(xdr, fattr, NULL, server, may_sleep); +} + +/* + * Decode potentially multiple layout types. Currently we only support + * one layout driver per file system. + */ +static int decode_first_pnfs_layout_type(struct xdr_stream *xdr, + uint32_t *layouttype) +{ + uint32_t *p; + int num; + + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + num = be32_to_cpup(p); + + /* pNFS is not supported by the underlying file system */ + if (num == 0) { + *layouttype = 0; + return 0; + } + if (num > 1) + printk(KERN_INFO "%s: Warning: Multiple pNFS layout drivers " + "per filesystem not supported\n", __func__); + + /* Decode and set first layout type, move xdr->p past unused types */ + p = xdr_inline_decode(xdr, num * 4); + if (unlikely(!p)) + goto out_overflow; + *layouttype = be32_to_cpup(p); + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +/* + * The type of file system exported. + * Note we must ensure that layouttype is set in any non-error case. + */ +static int decode_attr_pnfstype(struct xdr_stream *xdr, uint32_t *bitmap, + uint32_t *layouttype) +{ + int status = 0; + + dprintk("%s: bitmap is %x\n", __func__, bitmap[1]); + if (unlikely(bitmap[1] & (FATTR4_WORD1_FS_LAYOUT_TYPES - 1U))) + return -EIO; + if (bitmap[1] & FATTR4_WORD1_FS_LAYOUT_TYPES) { + status = decode_first_pnfs_layout_type(xdr, layouttype); + bitmap[1] &= ~FATTR4_WORD1_FS_LAYOUT_TYPES; + } else + *layouttype = 0; + return status; +} static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) { @@ -3894,6 +4183,12 @@ static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) if ((status = decode_attr_maxwrite(xdr, bitmap, &fsinfo->wtmax)) != 0) goto xdr_error; fsinfo->wtpref = fsinfo->wtmax; + status = decode_attr_time_delta(xdr, bitmap, &fsinfo->time_delta); + if (status != 0) + goto xdr_error; + status = decode_attr_pnfstype(xdr, bitmap, &fsinfo->layouttype); + if (status != 0) + goto xdr_error; status = verify_attr_len(xdr, savep, attrlen); xdr_error: @@ -3950,13 +4245,13 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) __be32 *p; uint32_t namelen, type; - p = xdr_inline_decode(xdr, 32); + p = xdr_inline_decode(xdr, 32); /* read 32 bytes */ if (unlikely(!p)) goto out_overflow; - p = xdr_decode_hyper(p, &offset); + p = xdr_decode_hyper(p, &offset); /* read 2 8-byte long words */ p = xdr_decode_hyper(p, &length); - type = be32_to_cpup(p++); - if (fl != NULL) { + type = be32_to_cpup(p++); /* 4 byte read */ + if (fl != NULL) { /* manipulate file lock */ fl->fl_start = (loff_t)offset; fl->fl_end = fl->fl_start + (loff_t)length - 1; if (length == ~(uint64_t)0) @@ -3966,9 +4261,9 @@ static int decode_lock_denied (struct xdr_stream *xdr, struct file_lock *fl) fl->fl_type = F_RDLCK; fl->fl_pid = 0; } - p = xdr_decode_hyper(p, &clientid); - namelen = be32_to_cpup(p); - p = xdr_inline_decode(xdr, namelen); + p = xdr_decode_hyper(p, &clientid); /* read 8 bytes */ + namelen = be32_to_cpup(p); /* read 4 bytes */ /* have read all 32 bytes now */ + p = xdr_inline_decode(xdr, namelen); /* variable size field */ if (likely(p)) return -NFS4ERR_DENIED; out_overflow: @@ -4200,12 +4495,9 @@ out_overflow: static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs4_readdir_res *readdir) { struct xdr_buf *rcvbuf = &req->rq_rcv_buf; - struct page *page = *rcvbuf->pages; struct kvec *iov = rcvbuf->head; size_t hdrlen; u32 recvd, pglen = rcvbuf->page_len; - __be32 *end, *entry, *p, *kaddr; - unsigned int nr = 0; int status; status = decode_op_hdr(xdr, OP_READDIR); @@ -4225,71 +4517,8 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n pglen = recvd; xdr_read_pages(xdr, pglen); - BUG_ON(pglen + readdir->pgbase > PAGE_CACHE_SIZE); - kaddr = p = kmap_atomic(page, KM_USER0); - end = p + ((pglen + readdir->pgbase) >> 2); - entry = p; - - /* Make sure the packet actually has a value_follows and EOF entry */ - if ((entry + 1) > end) - goto short_pkt; - - for (; *p++; nr++) { - u32 len, attrlen, xlen; - if (end - p < 3) - goto short_pkt; - dprintk("cookie = %Lu, ", *((unsigned long long *)p)); - p += 2; /* cookie */ - len = ntohl(*p++); /* filename length */ - if (len > NFS4_MAXNAMLEN) { - dprintk("NFS: giant filename in readdir (len 0x%x)\n", - len); - goto err_unmap; - } - xlen = XDR_QUADLEN(len); - if (end - p < xlen + 1) - goto short_pkt; - dprintk("filename = %*s\n", len, (char *)p); - p += xlen; - len = ntohl(*p++); /* bitmap length */ - if (end - p < len + 1) - goto short_pkt; - p += len; - attrlen = XDR_QUADLEN(ntohl(*p++)); - if (end - p < attrlen + 2) - goto short_pkt; - p += attrlen; /* attributes */ - entry = p; - } - /* - * Apparently some server sends responses that are a valid size, but - * contain no entries, and have value_follows==0 and EOF==0. For - * those, just set the EOF marker. - */ - if (!nr && entry[1] == 0) { - dprintk("NFS: readdir reply truncated!\n"); - entry[1] = 1; - } -out: - kunmap_atomic(kaddr, KM_USER0); + return 0; -short_pkt: - /* - * When we get a short packet there are 2 possibilities. We can - * return an error, or fix up the response to look like a valid - * response and return what we have so far. If there are no - * entries and the packet was short, then return -EIO. If there - * are valid entries in the response, return them and pretend that - * the call was successful, but incomplete. The caller can retry the - * readdir starting at the last cookie. - */ - dprintk("%s: short packet at entry %d\n", __func__, nr); - entry[0] = entry[1] = 0; - if (nr) - goto out; -err_unmap: - kunmap_atomic(kaddr, KM_USER0); - return -errno_NFSERR_IO; } static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) @@ -4299,7 +4528,6 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) size_t hdrlen; u32 len, recvd; __be32 *p; - char *kaddr; int status; status = decode_op_hdr(xdr, OP_READLINK); @@ -4330,9 +4558,7 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) * and and null-terminate the text (the VFS expects * null-termination). */ - kaddr = (char *)kmap_atomic(rcvbuf->pages[0], KM_USER0); - kaddr[len+rcvbuf->page_base] = '\0'; - kunmap_atomic(kaddr, KM_USER0); + xdr_terminate_string(rcvbuf, len); return 0; out_overflow: print_overflow_msg(__func__, xdr); @@ -4668,7 +4894,6 @@ static int decode_sequence(struct xdr_stream *xdr, struct rpc_rqst *rqstp) { #if defined(CONFIG_NFS_V4_1) - struct nfs4_slot *slot; struct nfs4_sessionid id; u32 dummy; int status; @@ -4700,15 +4925,14 @@ static int decode_sequence(struct xdr_stream *xdr, goto out_overflow; /* seqid */ - slot = &res->sr_session->fc_slot_table.slots[res->sr_slotid]; dummy = be32_to_cpup(p++); - if (dummy != slot->seq_nr) { + if (dummy != res->sr_slot->seq_nr) { dprintk("%s Invalid sequence number\n", __func__); goto out_err; } /* slot id */ dummy = be32_to_cpup(p++); - if (dummy != res->sr_slotid) { + if (dummy != res->sr_slot - res->sr_session->fc_slot_table.slots) { dprintk("%s Invalid slot id\n", __func__); goto out_err; } @@ -4731,6 +4955,134 @@ out_overflow: #endif /* CONFIG_NFS_V4_1 */ } +#if defined(CONFIG_NFS_V4_1) + +static int decode_getdeviceinfo(struct xdr_stream *xdr, + struct pnfs_device *pdev) +{ + __be32 *p; + uint32_t len, type; + int status; + + status = decode_op_hdr(xdr, OP_GETDEVICEINFO); + if (status) { + if (status == -ETOOSMALL) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + pdev->mincount = be32_to_cpup(p); + dprintk("%s: Min count too small. mincnt = %u\n", + __func__, pdev->mincount); + } + return status; + } + + p = xdr_inline_decode(xdr, 8); + if (unlikely(!p)) + goto out_overflow; + type = be32_to_cpup(p++); + if (type != pdev->layout_type) { + dprintk("%s: layout mismatch req: %u pdev: %u\n", + __func__, pdev->layout_type, type); + return -EINVAL; + } + /* + * Get the length of the opaque device_addr4. xdr_read_pages places + * the opaque device_addr4 in the xdr_buf->pages (pnfs_device->pages) + * and places the remaining xdr data in xdr_buf->tail + */ + pdev->mincount = be32_to_cpup(p); + xdr_read_pages(xdr, pdev->mincount); /* include space for the length */ + + /* Parse notification bitmap, verifying that it is zero. */ + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + len = be32_to_cpup(p); + if (len) { + int i; + + p = xdr_inline_decode(xdr, 4 * len); + if (unlikely(!p)) + goto out_overflow; + for (i = 0; i < len; i++, p++) { + if (be32_to_cpup(p)) { + dprintk("%s: notifications not supported\n", + __func__); + return -EIO; + } + } + } + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} + +static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, + struct nfs4_layoutget_res *res) +{ + __be32 *p; + int status; + u32 layout_count; + + status = decode_op_hdr(xdr, OP_LAYOUTGET); + if (status) + return status; + p = xdr_inline_decode(xdr, 8 + NFS4_STATEID_SIZE); + if (unlikely(!p)) + goto out_overflow; + res->return_on_close = be32_to_cpup(p++); + p = xdr_decode_opaque_fixed(p, res->stateid.data, NFS4_STATEID_SIZE); + layout_count = be32_to_cpup(p); + if (!layout_count) { + dprintk("%s: server responded with empty layout array\n", + __func__); + return -EINVAL; + } + + p = xdr_inline_decode(xdr, 24); + if (unlikely(!p)) + goto out_overflow; + p = xdr_decode_hyper(p, &res->range.offset); + p = xdr_decode_hyper(p, &res->range.length); + res->range.iomode = be32_to_cpup(p++); + res->type = be32_to_cpup(p++); + + status = decode_opaque_inline(xdr, &res->layout.len, (char **)&p); + if (unlikely(status)) + return status; + + dprintk("%s roff:%lu rlen:%lu riomode:%d, lo_type:0x%x, lo.len:%d\n", + __func__, + (unsigned long)res->range.offset, + (unsigned long)res->range.length, + res->range.iomode, + res->type, + res->layout.len); + + /* nfs4_proc_layoutget allocated a single page */ + if (res->layout.len > PAGE_SIZE) + return -ENOMEM; + memcpy(res->layout.buf, p, res->layout.len); + + if (layout_count > 1) { + /* We only handle a length one array at the moment. Any + * further entries are just ignored. Note that this means + * the client may see a response that is less than the + * minimum it requested. + */ + dprintk("%s: server responded with %d layouts, dropping tail\n", + __func__, layout_count); + } + + return 0; +out_overflow: + print_overflow_msg(__func__, xdr); + return -EIO; +} +#endif /* CONFIG_NFS_V4_1 */ + /* * END OF "GENERIC" DECODE ROUTINES. */ @@ -4873,7 +5225,7 @@ out: /* * Decode RENAME response */ -static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, __be32 *p, struct nfs4_rename_res *res) +static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, __be32 *p, struct nfs_renameres *res) { struct xdr_stream xdr; struct compound_hdr hdr; @@ -5758,25 +6110,84 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp, uint32_t *p, status = decode_reclaim_complete(&xdr, (void *)NULL); return status; } + +/* + * Decode GETDEVINFO response + */ +static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp, uint32_t *p, + struct nfs4_getdeviceinfo_res *res) +{ + struct xdr_stream xdr; + struct compound_hdr hdr; + int status; + + xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p); + status = decode_compound_hdr(&xdr, &hdr); + if (status != 0) + goto out; + status = decode_sequence(&xdr, &res->seq_res, rqstp); + if (status != 0) + goto out; + status = decode_getdeviceinfo(&xdr, res->pdev); +out: + return status; +} + +/* + * Decode LAYOUTGET response + */ +static int nfs4_xdr_dec_layoutget(struct rpc_rqst *rqstp, uint32_t *p, + struct nfs4_layoutget_res *res) +{ + struct xdr_stream xdr; + struct compound_hdr hdr; + int status; + + xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p); + status = decode_compound_hdr(&xdr, &hdr); + if (status) + goto out; + status = decode_sequence(&xdr, &res->seq_res, rqstp); + if (status) + goto out; + status = decode_putfh(&xdr); + if (status) + goto out; + status = decode_layoutget(&xdr, rqstp, res); +out: + return status; +} #endif /* CONFIG_NFS_V4_1 */ -__be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus) +__be32 *nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, + struct nfs_server *server, int plus) { uint32_t bitmap[2] = {0}; uint32_t len; - - if (!*p++) { - if (!*p) + __be32 *p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + if (!ntohl(*p++)) { + p = xdr_inline_decode(xdr, 4); + if (unlikely(!p)) + goto out_overflow; + if (!ntohl(*p++)) return ERR_PTR(-EAGAIN); entry->eof = 1; return ERR_PTR(-EBADCOOKIE); } + p = xdr_inline_decode(xdr, 12); + if (unlikely(!p)) + goto out_overflow; entry->prev_cookie = entry->cookie; p = xdr_decode_hyper(p, &entry->cookie); entry->len = ntohl(*p++); + + p = xdr_inline_decode(xdr, entry->len); + if (unlikely(!p)) + goto out_overflow; entry->name = (const char *) p; - p += XDR_QUADLEN(entry->len); /* * In case the server doesn't return an inode number, @@ -5784,32 +6195,33 @@ __be32 *nfs4_decode_dirent(__be32 *p, struct nfs_entry *entry, int plus) * since glibc seems to choke on it...) */ entry->ino = 1; + entry->fattr->valid = 0; - len = ntohl(*p++); /* bitmap length */ - if (len-- > 0) { - bitmap[0] = ntohl(*p++); - if (len-- > 0) { - bitmap[1] = ntohl(*p++); - p += len; - } - } - len = XDR_QUADLEN(ntohl(*p++)); /* attribute buffer length */ - if (len > 0) { - if (bitmap[0] & FATTR4_WORD0_RDATTR_ERROR) { - bitmap[0] &= ~FATTR4_WORD0_RDATTR_ERROR; - /* Ignore the return value of rdattr_error for now */ - p++; - len--; - } - if (bitmap[0] == 0 && bitmap[1] == FATTR4_WORD1_MOUNTED_ON_FILEID) - xdr_decode_hyper(p, &entry->ino); - else if (bitmap[0] == FATTR4_WORD0_FILEID) - xdr_decode_hyper(p, &entry->ino); - p += len; - } + if (decode_attr_bitmap(xdr, bitmap) < 0) + goto out_overflow; + + if (decode_attr_length(xdr, &len, &p) < 0) + goto out_overflow; + + if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh, server, 1) < 0) + goto out_overflow; + if (entry->fattr->valid & NFS_ATTR_FATTR_FILEID) + entry->ino = entry->fattr->fileid; + + if (verify_attr_len(xdr, p, len) < 0) + goto out_overflow; + + p = xdr_inline_peek(xdr, 8); + if (p != NULL) + entry->eof = !p[0] && p[1]; + else + entry->eof = 0; - entry->eof = !p[0] && p[1]; return p; + +out_overflow: + print_overflow_msg(__func__, xdr); + return ERR_PTR(-EIO); } /* @@ -5936,6 +6348,8 @@ struct rpc_procinfo nfs4_procedures[] = { PROC(SEQUENCE, enc_sequence, dec_sequence), PROC(GET_LEASE_TIME, enc_get_lease_time, dec_get_lease_time), PROC(RECLAIM_COMPLETE, enc_reclaim_complete, dec_reclaim_complete), + PROC(GETDEVICEINFO, enc_getdeviceinfo, dec_getdeviceinfo), + PROC(LAYOUTGET, enc_layoutget, dec_layoutget), #endif /* CONFIG_NFS_V4_1 */ }; diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c index df101d9f546a..903908a20023 100644 --- a/fs/nfs/nfsroot.c +++ b/fs/nfs/nfsroot.c @@ -3,9 +3,10 @@ * * Allow an NFS filesystem to be mounted as root. The way this works is: * (1) Use the IP autoconfig mechanism to set local IP addresses and routes. - * (2) Handle RPC negotiation with the system which replied to RARP or - * was reported as a boot server by BOOTP or manually. - * (3) The actual mounting is done later, when init() is running. + * (2) Construct the device string and the options string using DHCP + * option 17 and/or kernel command line options. + * (3) When mount_root() sets up the root file system, pass these strings + * to the NFS client's regular mount interface via sys_mount(). * * * Changes: @@ -65,470 +66,245 @@ * Hua Qin : Support for mounting root file system via * NFS over TCP. * Fabian Frederick: Option parser rebuilt (using parser lib) -*/ + * Chuck Lever : Use super.c's text-based mount option parsing + * Chuck Lever : Add "nfsrootdebug". + */ #include <linux/types.h> #include <linux/string.h> -#include <linux/kernel.h> -#include <linux/time.h> -#include <linux/fs.h> #include <linux/init.h> -#include <linux/sunrpc/clnt.h> -#include <linux/sunrpc/xprtsock.h> #include <linux/nfs.h> #include <linux/nfs_fs.h> -#include <linux/nfs_mount.h> -#include <linux/in.h> -#include <linux/major.h> #include <linux/utsname.h> -#include <linux/inet.h> #include <linux/root_dev.h> #include <net/ipconfig.h> -#include <linux/parser.h> #include "internal.h" -/* Define this to allow debugging output */ -#undef NFSROOT_DEBUG #define NFSDBG_FACILITY NFSDBG_ROOT -/* Default port to use if server is not running a portmapper */ -#define NFS_MNT_PORT 627 - /* Default path we try to mount. "%s" gets replaced by our IP address */ #define NFS_ROOT "/tftpboot/%s" /* Parameters passed from the kernel command line */ -static char nfs_root_name[256] __initdata = ""; +static char nfs_root_parms[256] __initdata = ""; + +/* Text-based mount options passed to super.c */ +static char nfs_root_options[256] __initdata = ""; /* Address of NFS server */ -static __be32 servaddr __initdata = 0; +static __be32 servaddr __initdata = htonl(INADDR_NONE); /* Name of directory to mount */ -static char nfs_export_path[NFS_MAXPATHLEN + 1] __initdata = { 0, }; - -/* NFS-related data */ -static struct nfs_mount_data nfs_data __initdata = { 0, };/* NFS mount info */ -static int nfs_port __initdata = 0; /* Port to connect to for NFS */ -static int mount_port __initdata = 0; /* Mount daemon port number */ - - -/*************************************************************************** - - Parsing of options - - ***************************************************************************/ - -enum { - /* Options that take integer arguments */ - Opt_port, Opt_rsize, Opt_wsize, Opt_timeo, Opt_retrans, Opt_acregmin, - Opt_acregmax, Opt_acdirmin, Opt_acdirmax, - /* Options that take no arguments */ - Opt_soft, Opt_hard, Opt_intr, - Opt_nointr, Opt_posix, Opt_noposix, Opt_cto, Opt_nocto, Opt_ac, - Opt_noac, Opt_lock, Opt_nolock, Opt_v2, Opt_v3, Opt_udp, Opt_tcp, - Opt_acl, Opt_noacl, - /* Error token */ - Opt_err -}; - -static const match_table_t tokens __initconst = { - {Opt_port, "port=%u"}, - {Opt_rsize, "rsize=%u"}, - {Opt_wsize, "wsize=%u"}, - {Opt_timeo, "timeo=%u"}, - {Opt_retrans, "retrans=%u"}, - {Opt_acregmin, "acregmin=%u"}, - {Opt_acregmax, "acregmax=%u"}, - {Opt_acdirmin, "acdirmin=%u"}, - {Opt_acdirmax, "acdirmax=%u"}, - {Opt_soft, "soft"}, - {Opt_hard, "hard"}, - {Opt_intr, "intr"}, - {Opt_nointr, "nointr"}, - {Opt_posix, "posix"}, - {Opt_noposix, "noposix"}, - {Opt_cto, "cto"}, - {Opt_nocto, "nocto"}, - {Opt_ac, "ac"}, - {Opt_noac, "noac"}, - {Opt_lock, "lock"}, - {Opt_nolock, "nolock"}, - {Opt_v2, "nfsvers=2"}, - {Opt_v2, "v2"}, - {Opt_v3, "nfsvers=3"}, - {Opt_v3, "v3"}, - {Opt_udp, "proto=udp"}, - {Opt_udp, "udp"}, - {Opt_tcp, "proto=tcp"}, - {Opt_tcp, "tcp"}, - {Opt_acl, "acl"}, - {Opt_noacl, "noacl"}, - {Opt_err, NULL} - -}; +static char nfs_export_path[NFS_MAXPATHLEN + 1] __initdata = ""; +/* server:export path string passed to super.c */ +static char nfs_root_device[NFS_MAXPATHLEN + 1] __initdata = ""; + +#ifdef RPC_DEBUG /* - * Parse option string. + * When the "nfsrootdebug" kernel command line option is specified, + * enable debugging messages for NFSROOT. */ - -static int __init root_nfs_parse(char *name, char *buf) +static int __init nfs_root_debug(char *__unused) { - - char *p; - substring_t args[MAX_OPT_ARGS]; - int option; - - if (!name) - return 1; - - /* Set the NFS remote path */ - p = strsep(&name, ","); - if (p[0] != '\0' && strcmp(p, "default") != 0) - strlcpy(buf, p, NFS_MAXPATHLEN); - - while ((p = strsep (&name, ",")) != NULL) { - int token; - if (!*p) - continue; - token = match_token(p, tokens, args); - - /* %u tokens only. Beware if you add new tokens! */ - if (token < Opt_soft && match_int(&args[0], &option)) - return 0; - switch (token) { - case Opt_port: - nfs_port = option; - break; - case Opt_rsize: - nfs_data.rsize = option; - break; - case Opt_wsize: - nfs_data.wsize = option; - break; - case Opt_timeo: - nfs_data.timeo = option; - break; - case Opt_retrans: - nfs_data.retrans = option; - break; - case Opt_acregmin: - nfs_data.acregmin = option; - break; - case Opt_acregmax: - nfs_data.acregmax = option; - break; - case Opt_acdirmin: - nfs_data.acdirmin = option; - break; - case Opt_acdirmax: - nfs_data.acdirmax = option; - break; - case Opt_soft: - nfs_data.flags |= NFS_MOUNT_SOFT; - break; - case Opt_hard: - nfs_data.flags &= ~NFS_MOUNT_SOFT; - break; - case Opt_intr: - case Opt_nointr: - break; - case Opt_posix: - nfs_data.flags |= NFS_MOUNT_POSIX; - break; - case Opt_noposix: - nfs_data.flags &= ~NFS_MOUNT_POSIX; - break; - case Opt_cto: - nfs_data.flags &= ~NFS_MOUNT_NOCTO; - break; - case Opt_nocto: - nfs_data.flags |= NFS_MOUNT_NOCTO; - break; - case Opt_ac: - nfs_data.flags &= ~NFS_MOUNT_NOAC; - break; - case Opt_noac: - nfs_data.flags |= NFS_MOUNT_NOAC; - break; - case Opt_lock: - nfs_data.flags &= ~NFS_MOUNT_NONLM; - break; - case Opt_nolock: - nfs_data.flags |= NFS_MOUNT_NONLM; - break; - case Opt_v2: - nfs_data.flags &= ~NFS_MOUNT_VER3; - break; - case Opt_v3: - nfs_data.flags |= NFS_MOUNT_VER3; - break; - case Opt_udp: - nfs_data.flags &= ~NFS_MOUNT_TCP; - break; - case Opt_tcp: - nfs_data.flags |= NFS_MOUNT_TCP; - break; - case Opt_acl: - nfs_data.flags &= ~NFS_MOUNT_NOACL; - break; - case Opt_noacl: - nfs_data.flags |= NFS_MOUNT_NOACL; - break; - default: - printk(KERN_WARNING "Root-NFS: unknown " - "option: %s\n", p); - return 0; - } - } - + nfs_debug |= NFSDBG_ROOT | NFSDBG_MOUNT; return 1; } +__setup("nfsrootdebug", nfs_root_debug); +#endif + /* - * Prepare the NFS data structure and parse all options. + * Parse NFS server and directory information passed on the kernel + * command line. + * + * nfsroot=[<server-ip>:]<root-dir>[,<nfs-options>] + * + * If there is a "%s" token in the <root-dir> string, it is replaced + * by the ASCII-representation of the client's IP address. */ -static int __init root_nfs_name(char *name) +static int __init nfs_root_setup(char *line) { - static char buf[NFS_MAXPATHLEN] __initdata; - char *cp; - - /* Set some default values */ - memset(&nfs_data, 0, sizeof(nfs_data)); - nfs_port = -1; - nfs_data.version = NFS_MOUNT_VERSION; - nfs_data.flags = NFS_MOUNT_NONLM; /* No lockd in nfs root yet */ - nfs_data.rsize = NFS_DEF_FILE_IO_SIZE; - nfs_data.wsize = NFS_DEF_FILE_IO_SIZE; - nfs_data.acregmin = NFS_DEF_ACREGMIN; - nfs_data.acregmax = NFS_DEF_ACREGMAX; - nfs_data.acdirmin = NFS_DEF_ACDIRMIN; - nfs_data.acdirmax = NFS_DEF_ACDIRMAX; - strcpy(buf, NFS_ROOT); - - /* Process options received from the remote server */ - root_nfs_parse(root_server_path, buf); - - /* Override them by options set on kernel command-line */ - root_nfs_parse(name, buf); - - cp = utsname()->nodename; - if (strlen(buf) + strlen(cp) > NFS_MAXPATHLEN) { - printk(KERN_ERR "Root-NFS: Pathname for remote directory too long.\n"); - return -1; + ROOT_DEV = Root_NFS; + + if (line[0] == '/' || line[0] == ',' || (line[0] >= '0' && line[0] <= '9')) { + strlcpy(nfs_root_parms, line, sizeof(nfs_root_parms)); + } else { + size_t n = strlen(line) + sizeof(NFS_ROOT) - 1; + if (n >= sizeof(nfs_root_parms)) + line[sizeof(nfs_root_parms) - sizeof(NFS_ROOT) - 2] = '\0'; + sprintf(nfs_root_parms, NFS_ROOT, line); } - sprintf(nfs_export_path, buf, cp); + + /* + * Extract the IP address of the NFS server containing our + * root file system, if one was specified. + * + * Note: root_nfs_parse_addr() removes the server-ip from + * nfs_root_parms, if it exists. + */ + root_server_addr = root_nfs_parse_addr(nfs_root_parms); return 1; } +__setup("nfsroot=", nfs_root_setup); -/* - * Get NFS server address. - */ -static int __init root_nfs_addr(void) +static int __init root_nfs_copy(char *dest, const char *src, + const size_t destlen) { - if ((servaddr = root_server_addr) == htonl(INADDR_NONE)) { - printk(KERN_ERR "Root-NFS: No NFS server available, giving up.\n"); + if (strlcpy(dest, src, destlen) > destlen) return -1; - } + return 0; +} - snprintf(nfs_data.hostname, sizeof(nfs_data.hostname), - "%pI4", &servaddr); +static int __init root_nfs_cat(char *dest, const char *src, + const size_t destlen) +{ + if (strlcat(dest, src, destlen) > destlen) + return -1; return 0; } /* - * Tell the user what's going on. + * Parse out root export path and mount options from + * passed-in string @incoming. + * + * Copy the export path into @exppath. */ -#ifdef NFSROOT_DEBUG -static void __init root_nfs_print(void) +static int __init root_nfs_parse_options(char *incoming, char *exppath, + const size_t exppathlen) { - printk(KERN_NOTICE "Root-NFS: Mounting %s on server %s as root\n", - nfs_export_path, nfs_data.hostname); - printk(KERN_NOTICE "Root-NFS: rsize = %d, wsize = %d, timeo = %d, retrans = %d\n", - nfs_data.rsize, nfs_data.wsize, nfs_data.timeo, nfs_data.retrans); - printk(KERN_NOTICE "Root-NFS: acreg (min,max) = (%d,%d), acdir (min,max) = (%d,%d)\n", - nfs_data.acregmin, nfs_data.acregmax, - nfs_data.acdirmin, nfs_data.acdirmax); - printk(KERN_NOTICE "Root-NFS: nfsd port = %d, mountd port = %d, flags = %08x\n", - nfs_port, mount_port, nfs_data.flags); -} -#endif - + char *p; -static int __init root_nfs_init(void) -{ -#ifdef NFSROOT_DEBUG - nfs_debug |= NFSDBG_ROOT; -#endif + /* + * Set the NFS remote path + */ + p = strsep(&incoming, ","); + if (*p != '\0' && strcmp(p, "default") != 0) + if (root_nfs_copy(exppath, p, exppathlen)) + return -1; /* - * Decode the root directory path name and NFS options from - * the kernel command line. This has to go here in order to - * be able to use the client IP address for the remote root - * directory (necessary for pure RARP booting). + * @incoming now points to the rest of the string; if it + * contains something, append it to our root options buffer */ - if (root_nfs_name(nfs_root_name) < 0 || - root_nfs_addr() < 0) - return -1; + if (incoming != NULL && *incoming != '\0') + if (root_nfs_cat(nfs_root_options, incoming, + sizeof(nfs_root_options))) + return -1; -#ifdef NFSROOT_DEBUG - root_nfs_print(); -#endif + /* + * Possibly prepare for more options to be appended + */ + if (nfs_root_options[0] != '\0' && + nfs_root_options[strlen(nfs_root_options)] != ',') + if (root_nfs_cat(nfs_root_options, ",", + sizeof(nfs_root_options))) + return -1; return 0; } - /* - * Parse NFS server and directory information passed on the kernel - * command line. + * Decode the export directory path name and NFS options from + * the kernel command line. This has to be done late in order to + * use a dynamically acquired client IP address for the remote + * root directory path. + * + * Returns zero if successful; otherwise -1 is returned. */ -static int __init nfs_root_setup(char *line) +static int __init root_nfs_data(char *cmdline) { - ROOT_DEV = Root_NFS; - if (line[0] == '/' || line[0] == ',' || (line[0] >= '0' && line[0] <= '9')) { - strlcpy(nfs_root_name, line, sizeof(nfs_root_name)); - } else { - int n = strlen(line) + sizeof(NFS_ROOT) - 1; - if (n >= sizeof(nfs_root_name)) - line[sizeof(nfs_root_name) - sizeof(NFS_ROOT) - 2] = '\0'; - sprintf(nfs_root_name, NFS_ROOT, line); + char addr_option[sizeof("nolock,addr=") + INET_ADDRSTRLEN + 1]; + int len, retval = -1; + char *tmp = NULL; + const size_t tmplen = sizeof(nfs_export_path); + + tmp = kzalloc(tmplen, GFP_KERNEL); + if (tmp == NULL) + goto out_nomem; + strcpy(tmp, NFS_ROOT); + + if (root_server_path[0] != '\0') { + dprintk("Root-NFS: DHCPv4 option 17: %s\n", + root_server_path); + if (root_nfs_parse_options(root_server_path, tmp, tmplen)) + goto out_optionstoolong; } - root_server_addr = root_nfs_parse_addr(nfs_root_name); - return 1; -} - -__setup("nfsroot=", nfs_root_setup); - -/*************************************************************************** - Routines to actually mount the root directory + if (cmdline[0] != '\0') { + dprintk("Root-NFS: nfsroot=%s\n", cmdline); + if (root_nfs_parse_options(cmdline, tmp, tmplen)) + goto out_optionstoolong; + } - ***************************************************************************/ + /* + * Append mandatory options for nfsroot so they override + * what has come before + */ + snprintf(addr_option, sizeof(addr_option), "nolock,addr=%pI4", + &servaddr); + if (root_nfs_cat(nfs_root_options, addr_option, + sizeof(nfs_root_options))) + goto out_optionstoolong; -/* - * Construct sockaddr_in from address and port number. - */ -static inline void -set_sockaddr(struct sockaddr_in *sin, __be32 addr, __be16 port) -{ - sin->sin_family = AF_INET; - sin->sin_addr.s_addr = addr; - sin->sin_port = port; -} + /* + * Set up nfs_root_device. For NFS mounts, this looks like + * + * server:/path + * + * At this point, utsname()->nodename contains our local + * IP address or hostname, set by ipconfig. If "%s" exists + * in tmp, substitute the nodename, then shovel the whole + * mess into nfs_root_device. + */ + len = snprintf(nfs_export_path, sizeof(nfs_export_path), + tmp, utsname()->nodename); + if (len > (int)sizeof(nfs_export_path)) + goto out_devnametoolong; + len = snprintf(nfs_root_device, sizeof(nfs_root_device), + "%pI4:%s", &servaddr, nfs_export_path); + if (len > (int)sizeof(nfs_root_device)) + goto out_devnametoolong; -/* - * Query server portmapper for the port of a daemon program. - */ -static int __init root_nfs_getport(int program, int version, int proto) -{ - struct sockaddr_in sin; + retval = 0; - printk(KERN_NOTICE "Looking up port of RPC %d/%d on %pI4\n", - program, version, &servaddr); - set_sockaddr(&sin, servaddr, 0); - return rpcb_getport_sync(&sin, program, version, proto); +out: + kfree(tmp); + return retval; +out_nomem: + printk(KERN_ERR "Root-NFS: could not allocate memory\n"); + goto out; +out_optionstoolong: + printk(KERN_ERR "Root-NFS: mount options string too long\n"); + goto out; +out_devnametoolong: + printk(KERN_ERR "Root-NFS: root device name too long.\n"); + goto out; } - -/* - * Use portmapper to find mountd and nfsd port numbers if not overriden - * by the user. Use defaults if portmapper is not available. - * XXX: Is there any nfs server with no portmapper? +/** + * nfs_root_data - Return prepared 'data' for NFSROOT mount + * @root_device: OUT: address of string containing NFSROOT device + * @root_data: OUT: address of string containing NFSROOT mount options + * + * Returns zero and sets @root_device and @root_data if successful, + * otherwise -1 is returned. */ -static int __init root_nfs_ports(void) +int __init nfs_root_data(char **root_device, char **root_data) { - int port; - int nfsd_ver, mountd_ver; - int nfsd_port, mountd_port; - int proto; - - if (nfs_data.flags & NFS_MOUNT_VER3) { - nfsd_ver = NFS3_VERSION; - mountd_ver = NFS_MNT3_VERSION; - nfsd_port = NFS_PORT; - mountd_port = NFS_MNT_PORT; - } else { - nfsd_ver = NFS2_VERSION; - mountd_ver = NFS_MNT_VERSION; - nfsd_port = NFS_PORT; - mountd_port = NFS_MNT_PORT; - } - - proto = (nfs_data.flags & NFS_MOUNT_TCP) ? IPPROTO_TCP : IPPROTO_UDP; - - if (nfs_port < 0) { - if ((port = root_nfs_getport(NFS_PROGRAM, nfsd_ver, proto)) < 0) { - printk(KERN_ERR "Root-NFS: Unable to get nfsd port " - "number from server, using default\n"); - port = nfsd_port; - } - nfs_port = port; - dprintk("Root-NFS: Portmapper on server returned %d " - "as nfsd port\n", port); + servaddr = root_server_addr; + if (servaddr == htonl(INADDR_NONE)) { + printk(KERN_ERR "Root-NFS: no NFS server address\n"); + return -1; } - if ((port = root_nfs_getport(NFS_MNT_PROGRAM, mountd_ver, proto)) < 0) { - printk(KERN_ERR "Root-NFS: Unable to get mountd port " - "number from server, using default\n"); - port = mountd_port; - } - mount_port = port; - dprintk("Root-NFS: mountd port is %d\n", port); + if (root_nfs_data(nfs_root_parms) < 0) + return -1; + *root_device = nfs_root_device; + *root_data = nfs_root_options; return 0; } - - -/* - * Get a file handle from the server for the directory which is to be - * mounted. - */ -static int __init root_nfs_get_handle(void) -{ - struct sockaddr_in sin; - unsigned int auth_flav_len = 0; - struct nfs_mount_request request = { - .sap = (struct sockaddr *)&sin, - .salen = sizeof(sin), - .dirpath = nfs_export_path, - .version = (nfs_data.flags & NFS_MOUNT_VER3) ? - NFS_MNT3_VERSION : NFS_MNT_VERSION, - .protocol = (nfs_data.flags & NFS_MOUNT_TCP) ? - XPRT_TRANSPORT_TCP : XPRT_TRANSPORT_UDP, - .auth_flav_len = &auth_flav_len, - }; - int status = -ENOMEM; - - request.fh = nfs_alloc_fhandle(); - if (!request.fh) - goto out; - set_sockaddr(&sin, servaddr, htons(mount_port)); - status = nfs_mount(&request); - if (status < 0) - printk(KERN_ERR "Root-NFS: Server returned error %d " - "while mounting %s\n", status, nfs_export_path); - else { - nfs_data.root.size = request.fh->size; - memcpy(&nfs_data.root.data, request.fh->data, request.fh->size); - } - nfs_free_fhandle(request.fh); -out: - return status; -} - -/* - * Get the NFS port numbers and file handle, and return the prepared 'data' - * argument for mount() if everything went OK. Return NULL otherwise. - */ -void * __init nfs_root_data(void) -{ - if (root_nfs_init() < 0 - || root_nfs_ports() < 0 - || root_nfs_get_handle() < 0) - return NULL; - set_sockaddr((struct sockaddr_in *) &nfs_data.addr, servaddr, htons(nfs_port)); - return (void*)&nfs_data; -} diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index 919490232e17..137b549e63db 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -65,6 +65,13 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, if (req == NULL) return ERR_PTR(-ENOMEM); + /* get lock context early so we can deal with alloc failures */ + req->wb_lock_context = nfs_get_lock_context(ctx); + if (req->wb_lock_context == NULL) { + nfs_page_free(req); + return ERR_PTR(-ENOMEM); + } + /* Initialize the request struct. Initially, we assume a * long write-back delay. This will be adjusted in * update_nfs_request below if the region is not locked. */ @@ -79,7 +86,6 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, req->wb_pgbase = offset; req->wb_bytes = count; req->wb_context = get_nfs_open_context(ctx); - req->wb_lock_context = nfs_get_lock_context(ctx); kref_init(&req->wb_kref); return req; } diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c new file mode 100644 index 000000000000..db773428f95f --- /dev/null +++ b/fs/nfs/pnfs.c @@ -0,0 +1,783 @@ +/* + * pNFS functions to call and manage layout drivers. + * + * Copyright (c) 2002 [year of first publication] + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#include <linux/nfs_fs.h> +#include "internal.h" +#include "pnfs.h" + +#define NFSDBG_FACILITY NFSDBG_PNFS + +/* Locking: + * + * pnfs_spinlock: + * protects pnfs_modules_tbl. + */ +static DEFINE_SPINLOCK(pnfs_spinlock); + +/* + * pnfs_modules_tbl holds all pnfs modules + */ +static LIST_HEAD(pnfs_modules_tbl); + +/* Return the registered pnfs layout driver module matching given id */ +static struct pnfs_layoutdriver_type * +find_pnfs_driver_locked(u32 id) +{ + struct pnfs_layoutdriver_type *local; + + list_for_each_entry(local, &pnfs_modules_tbl, pnfs_tblid) + if (local->id == id) + goto out; + local = NULL; +out: + dprintk("%s: Searching for id %u, found %p\n", __func__, id, local); + return local; +} + +static struct pnfs_layoutdriver_type * +find_pnfs_driver(u32 id) +{ + struct pnfs_layoutdriver_type *local; + + spin_lock(&pnfs_spinlock); + local = find_pnfs_driver_locked(id); + spin_unlock(&pnfs_spinlock); + return local; +} + +void +unset_pnfs_layoutdriver(struct nfs_server *nfss) +{ + if (nfss->pnfs_curr_ld) { + nfss->pnfs_curr_ld->clear_layoutdriver(nfss); + module_put(nfss->pnfs_curr_ld->owner); + } + nfss->pnfs_curr_ld = NULL; +} + +/* + * Try to set the server's pnfs module to the pnfs layout type specified by id. + * Currently only one pNFS layout driver per filesystem is supported. + * + * @id layout type. Zero (illegal layout type) indicates pNFS not in use. + */ +void +set_pnfs_layoutdriver(struct nfs_server *server, u32 id) +{ + struct pnfs_layoutdriver_type *ld_type = NULL; + + if (id == 0) + goto out_no_driver; + if (!(server->nfs_client->cl_exchange_flags & + (EXCHGID4_FLAG_USE_NON_PNFS | EXCHGID4_FLAG_USE_PNFS_MDS))) { + printk(KERN_ERR "%s: id %u cl_exchange_flags 0x%x\n", __func__, + id, server->nfs_client->cl_exchange_flags); + goto out_no_driver; + } + ld_type = find_pnfs_driver(id); + if (!ld_type) { + request_module("%s-%u", LAYOUT_NFSV4_1_MODULE_PREFIX, id); + ld_type = find_pnfs_driver(id); + if (!ld_type) { + dprintk("%s: No pNFS module found for %u.\n", + __func__, id); + goto out_no_driver; + } + } + if (!try_module_get(ld_type->owner)) { + dprintk("%s: Could not grab reference on module\n", __func__); + goto out_no_driver; + } + server->pnfs_curr_ld = ld_type; + if (ld_type->set_layoutdriver(server)) { + printk(KERN_ERR + "%s: Error initializing mount point for layout driver %u.\n", + __func__, id); + module_put(ld_type->owner); + goto out_no_driver; + } + dprintk("%s: pNFS module for %u set\n", __func__, id); + return; + +out_no_driver: + dprintk("%s: Using NFSv4 I/O\n", __func__); + server->pnfs_curr_ld = NULL; +} + +int +pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *ld_type) +{ + int status = -EINVAL; + struct pnfs_layoutdriver_type *tmp; + + if (ld_type->id == 0) { + printk(KERN_ERR "%s id 0 is reserved\n", __func__); + return status; + } + if (!ld_type->alloc_lseg || !ld_type->free_lseg) { + printk(KERN_ERR "%s Layout driver must provide " + "alloc_lseg and free_lseg.\n", __func__); + return status; + } + + spin_lock(&pnfs_spinlock); + tmp = find_pnfs_driver_locked(ld_type->id); + if (!tmp) { + list_add(&ld_type->pnfs_tblid, &pnfs_modules_tbl); + status = 0; + dprintk("%s Registering id:%u name:%s\n", __func__, ld_type->id, + ld_type->name); + } else { + printk(KERN_ERR "%s Module with id %d already loaded!\n", + __func__, ld_type->id); + } + spin_unlock(&pnfs_spinlock); + + return status; +} +EXPORT_SYMBOL_GPL(pnfs_register_layoutdriver); + +void +pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *ld_type) +{ + dprintk("%s Deregistering id:%u\n", __func__, ld_type->id); + spin_lock(&pnfs_spinlock); + list_del(&ld_type->pnfs_tblid); + spin_unlock(&pnfs_spinlock); +} +EXPORT_SYMBOL_GPL(pnfs_unregister_layoutdriver); + +/* + * pNFS client layout cache + */ + +static void +get_layout_hdr_locked(struct pnfs_layout_hdr *lo) +{ + assert_spin_locked(&lo->inode->i_lock); + lo->refcount++; +} + +static void +put_layout_hdr_locked(struct pnfs_layout_hdr *lo) +{ + assert_spin_locked(&lo->inode->i_lock); + BUG_ON(lo->refcount == 0); + + lo->refcount--; + if (!lo->refcount) { + dprintk("%s: freeing layout cache %p\n", __func__, lo); + BUG_ON(!list_empty(&lo->layouts)); + NFS_I(lo->inode)->layout = NULL; + kfree(lo); + } +} + +void +put_layout_hdr(struct inode *inode) +{ + spin_lock(&inode->i_lock); + put_layout_hdr_locked(NFS_I(inode)->layout); + spin_unlock(&inode->i_lock); +} + +static void +init_lseg(struct pnfs_layout_hdr *lo, struct pnfs_layout_segment *lseg) +{ + INIT_LIST_HEAD(&lseg->fi_list); + kref_init(&lseg->kref); + lseg->layout = lo; +} + +/* Called without i_lock held, as the free_lseg call may sleep */ +static void +destroy_lseg(struct kref *kref) +{ + struct pnfs_layout_segment *lseg = + container_of(kref, struct pnfs_layout_segment, kref); + struct inode *ino = lseg->layout->inode; + + dprintk("--> %s\n", __func__); + NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg); + /* Matched by get_layout_hdr_locked in pnfs_insert_layout */ + put_layout_hdr(ino); +} + +static void +put_lseg(struct pnfs_layout_segment *lseg) +{ + if (!lseg) + return; + + dprintk("%s: lseg %p ref %d\n", __func__, lseg, + atomic_read(&lseg->kref.refcount)); + kref_put(&lseg->kref, destroy_lseg); +} + +static void +pnfs_clear_lseg_list(struct pnfs_layout_hdr *lo, struct list_head *tmp_list) +{ + struct pnfs_layout_segment *lseg, *next; + struct nfs_client *clp; + + dprintk("%s:Begin lo %p\n", __func__, lo); + + assert_spin_locked(&lo->inode->i_lock); + list_for_each_entry_safe(lseg, next, &lo->segs, fi_list) { + dprintk("%s: freeing lseg %p\n", __func__, lseg); + list_move(&lseg->fi_list, tmp_list); + } + clp = NFS_SERVER(lo->inode)->nfs_client; + spin_lock(&clp->cl_lock); + /* List does not take a reference, so no need for put here */ + list_del_init(&lo->layouts); + spin_unlock(&clp->cl_lock); + write_seqlock(&lo->seqlock); + clear_bit(NFS_LAYOUT_STATEID_SET, &lo->state); + write_sequnlock(&lo->seqlock); + + dprintk("%s:Return\n", __func__); +} + +static void +pnfs_free_lseg_list(struct list_head *tmp_list) +{ + struct pnfs_layout_segment *lseg; + + while (!list_empty(tmp_list)) { + lseg = list_entry(tmp_list->next, struct pnfs_layout_segment, + fi_list); + dprintk("%s calling put_lseg on %p\n", __func__, lseg); + list_del(&lseg->fi_list); + put_lseg(lseg); + } +} + +void +pnfs_destroy_layout(struct nfs_inode *nfsi) +{ + struct pnfs_layout_hdr *lo; + LIST_HEAD(tmp_list); + + spin_lock(&nfsi->vfs_inode.i_lock); + lo = nfsi->layout; + if (lo) { + pnfs_clear_lseg_list(lo, &tmp_list); + /* Matched by refcount set to 1 in alloc_init_layout_hdr */ + put_layout_hdr_locked(lo); + } + spin_unlock(&nfsi->vfs_inode.i_lock); + pnfs_free_lseg_list(&tmp_list); +} + +/* + * Called by the state manger to remove all layouts established under an + * expired lease. + */ +void +pnfs_destroy_all_layouts(struct nfs_client *clp) +{ + struct pnfs_layout_hdr *lo; + LIST_HEAD(tmp_list); + + spin_lock(&clp->cl_lock); + list_splice_init(&clp->cl_layouts, &tmp_list); + spin_unlock(&clp->cl_lock); + + while (!list_empty(&tmp_list)) { + lo = list_entry(tmp_list.next, struct pnfs_layout_hdr, + layouts); + dprintk("%s freeing layout for inode %lu\n", __func__, + lo->inode->i_ino); + pnfs_destroy_layout(NFS_I(lo->inode)); + } +} + +/* update lo->stateid with new if is more recent + * + * lo->stateid could be the open stateid, in which case we just use what given. + */ +static void +pnfs_set_layout_stateid(struct pnfs_layout_hdr *lo, + const nfs4_stateid *new) +{ + nfs4_stateid *old = &lo->stateid; + bool overwrite = false; + + write_seqlock(&lo->seqlock); + if (!test_bit(NFS_LAYOUT_STATEID_SET, &lo->state) || + memcmp(old->stateid.other, new->stateid.other, sizeof(new->stateid.other))) + overwrite = true; + else { + u32 oldseq, newseq; + + oldseq = be32_to_cpu(old->stateid.seqid); + newseq = be32_to_cpu(new->stateid.seqid); + if ((int)(newseq - oldseq) > 0) + overwrite = true; + } + if (overwrite) + memcpy(&old->stateid, &new->stateid, sizeof(new->stateid)); + write_sequnlock(&lo->seqlock); +} + +static void +pnfs_layout_from_open_stateid(struct pnfs_layout_hdr *lo, + struct nfs4_state *state) +{ + int seq; + + dprintk("--> %s\n", __func__); + write_seqlock(&lo->seqlock); + do { + seq = read_seqbegin(&state->seqlock); + memcpy(lo->stateid.data, state->stateid.data, + sizeof(state->stateid.data)); + } while (read_seqretry(&state->seqlock, seq)); + set_bit(NFS_LAYOUT_STATEID_SET, &lo->state); + write_sequnlock(&lo->seqlock); + dprintk("<-- %s\n", __func__); +} + +void +pnfs_get_layout_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, + struct nfs4_state *open_state) +{ + int seq; + + dprintk("--> %s\n", __func__); + do { + seq = read_seqbegin(&lo->seqlock); + if (!test_bit(NFS_LAYOUT_STATEID_SET, &lo->state)) { + /* This will trigger retry of the read */ + pnfs_layout_from_open_stateid(lo, open_state); + } else + memcpy(dst->data, lo->stateid.data, + sizeof(lo->stateid.data)); + } while (read_seqretry(&lo->seqlock, seq)); + dprintk("<-- %s\n", __func__); +} + +/* +* Get layout from server. +* for now, assume that whole file layouts are requested. +* arg->offset: 0 +* arg->length: all ones +*/ +static struct pnfs_layout_segment * +send_layoutget(struct pnfs_layout_hdr *lo, + struct nfs_open_context *ctx, + u32 iomode) +{ + struct inode *ino = lo->inode; + struct nfs_server *server = NFS_SERVER(ino); + struct nfs4_layoutget *lgp; + struct pnfs_layout_segment *lseg = NULL; + + dprintk("--> %s\n", __func__); + + BUG_ON(ctx == NULL); + lgp = kzalloc(sizeof(*lgp), GFP_KERNEL); + if (lgp == NULL) { + put_layout_hdr(lo->inode); + return NULL; + } + lgp->args.minlength = NFS4_MAX_UINT64; + lgp->args.maxcount = PNFS_LAYOUT_MAXSIZE; + lgp->args.range.iomode = iomode; + lgp->args.range.offset = 0; + lgp->args.range.length = NFS4_MAX_UINT64; + lgp->args.type = server->pnfs_curr_ld->id; + lgp->args.inode = ino; + lgp->args.ctx = get_nfs_open_context(ctx); + lgp->lsegpp = &lseg; + + /* Synchronously retrieve layout information from server and + * store in lseg. + */ + nfs4_proc_layoutget(lgp); + if (!lseg) { + /* remember that LAYOUTGET failed and suspend trying */ + set_bit(lo_fail_bit(iomode), &lo->state); + } + return lseg; +} + +/* + * Compare two layout segments for sorting into layout cache. + * We want to preferentially return RW over RO layouts, so ensure those + * are seen first. + */ +static s64 +cmp_layout(u32 iomode1, u32 iomode2) +{ + /* read > read/write */ + return (int)(iomode2 == IOMODE_READ) - (int)(iomode1 == IOMODE_READ); +} + +static void +pnfs_insert_layout(struct pnfs_layout_hdr *lo, + struct pnfs_layout_segment *lseg) +{ + struct pnfs_layout_segment *lp; + int found = 0; + + dprintk("%s:Begin\n", __func__); + + assert_spin_locked(&lo->inode->i_lock); + if (list_empty(&lo->segs)) { + struct nfs_client *clp = NFS_SERVER(lo->inode)->nfs_client; + + spin_lock(&clp->cl_lock); + BUG_ON(!list_empty(&lo->layouts)); + list_add_tail(&lo->layouts, &clp->cl_layouts); + spin_unlock(&clp->cl_lock); + } + list_for_each_entry(lp, &lo->segs, fi_list) { + if (cmp_layout(lp->range.iomode, lseg->range.iomode) > 0) + continue; + list_add_tail(&lseg->fi_list, &lp->fi_list); + dprintk("%s: inserted lseg %p " + "iomode %d offset %llu length %llu before " + "lp %p iomode %d offset %llu length %llu\n", + __func__, lseg, lseg->range.iomode, + lseg->range.offset, lseg->range.length, + lp, lp->range.iomode, lp->range.offset, + lp->range.length); + found = 1; + break; + } + if (!found) { + list_add_tail(&lseg->fi_list, &lo->segs); + dprintk("%s: inserted lseg %p " + "iomode %d offset %llu length %llu at tail\n", + __func__, lseg, lseg->range.iomode, + lseg->range.offset, lseg->range.length); + } + get_layout_hdr_locked(lo); + + dprintk("%s:Return\n", __func__); +} + +static struct pnfs_layout_hdr * +alloc_init_layout_hdr(struct inode *ino) +{ + struct pnfs_layout_hdr *lo; + + lo = kzalloc(sizeof(struct pnfs_layout_hdr), GFP_KERNEL); + if (!lo) + return NULL; + lo->refcount = 1; + INIT_LIST_HEAD(&lo->layouts); + INIT_LIST_HEAD(&lo->segs); + seqlock_init(&lo->seqlock); + lo->inode = ino; + return lo; +} + +static struct pnfs_layout_hdr * +pnfs_find_alloc_layout(struct inode *ino) +{ + struct nfs_inode *nfsi = NFS_I(ino); + struct pnfs_layout_hdr *new = NULL; + + dprintk("%s Begin ino=%p layout=%p\n", __func__, ino, nfsi->layout); + + assert_spin_locked(&ino->i_lock); + if (nfsi->layout) + return nfsi->layout; + + spin_unlock(&ino->i_lock); + new = alloc_init_layout_hdr(ino); + spin_lock(&ino->i_lock); + + if (likely(nfsi->layout == NULL)) /* Won the race? */ + nfsi->layout = new; + else + kfree(new); + return nfsi->layout; +} + +/* + * iomode matching rules: + * iomode lseg match + * ----- ----- ----- + * ANY READ true + * ANY RW true + * RW READ false + * RW RW true + * READ READ true + * READ RW true + */ +static int +is_matching_lseg(struct pnfs_layout_segment *lseg, u32 iomode) +{ + return (iomode != IOMODE_RW || lseg->range.iomode == IOMODE_RW); +} + +/* + * lookup range in layout + */ +static struct pnfs_layout_segment * +pnfs_has_layout(struct pnfs_layout_hdr *lo, u32 iomode) +{ + struct pnfs_layout_segment *lseg, *ret = NULL; + + dprintk("%s:Begin\n", __func__); + + assert_spin_locked(&lo->inode->i_lock); + list_for_each_entry(lseg, &lo->segs, fi_list) { + if (is_matching_lseg(lseg, iomode)) { + ret = lseg; + break; + } + if (cmp_layout(iomode, lseg->range.iomode) > 0) + break; + } + + dprintk("%s:Return lseg %p ref %d\n", + __func__, ret, ret ? atomic_read(&ret->kref.refcount) : 0); + return ret; +} + +/* + * Layout segment is retreived from the server if not cached. + * The appropriate layout segment is referenced and returned to the caller. + */ +struct pnfs_layout_segment * +pnfs_update_layout(struct inode *ino, + struct nfs_open_context *ctx, + enum pnfs_iomode iomode) +{ + struct nfs_inode *nfsi = NFS_I(ino); + struct pnfs_layout_hdr *lo; + struct pnfs_layout_segment *lseg = NULL; + + if (!pnfs_enabled_sb(NFS_SERVER(ino))) + return NULL; + spin_lock(&ino->i_lock); + lo = pnfs_find_alloc_layout(ino); + if (lo == NULL) { + dprintk("%s ERROR: can't get pnfs_layout_hdr\n", __func__); + goto out_unlock; + } + + /* Check to see if the layout for the given range already exists */ + lseg = pnfs_has_layout(lo, iomode); + if (lseg) { + dprintk("%s: Using cached lseg %p for iomode %d)\n", + __func__, lseg, iomode); + goto out_unlock; + } + + /* if LAYOUTGET already failed once we don't try again */ + if (test_bit(lo_fail_bit(iomode), &nfsi->layout->state)) + goto out_unlock; + + get_layout_hdr_locked(lo); /* Matched in nfs4_layoutget_release */ + spin_unlock(&ino->i_lock); + + lseg = send_layoutget(lo, ctx, iomode); +out: + dprintk("%s end, state 0x%lx lseg %p\n", __func__, + nfsi->layout->state, lseg); + return lseg; +out_unlock: + spin_unlock(&ino->i_lock); + goto out; +} + +int +pnfs_layout_process(struct nfs4_layoutget *lgp) +{ + struct pnfs_layout_hdr *lo = NFS_I(lgp->args.inode)->layout; + struct nfs4_layoutget_res *res = &lgp->res; + struct pnfs_layout_segment *lseg; + struct inode *ino = lo->inode; + int status = 0; + + /* Inject layout blob into I/O device driver */ + lseg = NFS_SERVER(ino)->pnfs_curr_ld->alloc_lseg(lo, res); + if (!lseg || IS_ERR(lseg)) { + if (!lseg) + status = -ENOMEM; + else + status = PTR_ERR(lseg); + dprintk("%s: Could not allocate layout: error %d\n", + __func__, status); + goto out; + } + + spin_lock(&ino->i_lock); + init_lseg(lo, lseg); + lseg->range = res->range; + *lgp->lsegpp = lseg; + pnfs_insert_layout(lo, lseg); + + /* Done processing layoutget. Set the layout stateid */ + pnfs_set_layout_stateid(lo, &res->stateid); + spin_unlock(&ino->i_lock); +out: + return status; +} + +/* + * Device ID cache. Currently supports one layout type per struct nfs_client. + * Add layout type to the lookup key to expand to support multiple types. + */ +int +pnfs_alloc_init_deviceid_cache(struct nfs_client *clp, + void (*free_callback)(struct pnfs_deviceid_node *)) +{ + struct pnfs_deviceid_cache *c; + + c = kzalloc(sizeof(struct pnfs_deviceid_cache), GFP_KERNEL); + if (!c) + return -ENOMEM; + spin_lock(&clp->cl_lock); + if (clp->cl_devid_cache != NULL) { + atomic_inc(&clp->cl_devid_cache->dc_ref); + dprintk("%s [kref [%d]]\n", __func__, + atomic_read(&clp->cl_devid_cache->dc_ref)); + kfree(c); + } else { + /* kzalloc initializes hlists */ + spin_lock_init(&c->dc_lock); + atomic_set(&c->dc_ref, 1); + c->dc_free_callback = free_callback; + clp->cl_devid_cache = c; + dprintk("%s [new]\n", __func__); + } + spin_unlock(&clp->cl_lock); + return 0; +} +EXPORT_SYMBOL_GPL(pnfs_alloc_init_deviceid_cache); + +/* + * Called from pnfs_layoutdriver_type->free_lseg + * last layout segment reference frees deviceid + */ +void +pnfs_put_deviceid(struct pnfs_deviceid_cache *c, + struct pnfs_deviceid_node *devid) +{ + struct nfs4_deviceid *id = &devid->de_id; + struct pnfs_deviceid_node *d; + struct hlist_node *n; + long h = nfs4_deviceid_hash(id); + + dprintk("%s [%d]\n", __func__, atomic_read(&devid->de_ref)); + if (!atomic_dec_and_lock(&devid->de_ref, &c->dc_lock)) + return; + + hlist_for_each_entry_rcu(d, n, &c->dc_deviceids[h], de_node) + if (!memcmp(&d->de_id, id, sizeof(*id))) { + hlist_del_rcu(&d->de_node); + spin_unlock(&c->dc_lock); + synchronize_rcu(); + c->dc_free_callback(devid); + return; + } + spin_unlock(&c->dc_lock); + /* Why wasn't it found in the list? */ + BUG(); +} +EXPORT_SYMBOL_GPL(pnfs_put_deviceid); + +/* Find and reference a deviceid */ +struct pnfs_deviceid_node * +pnfs_find_get_deviceid(struct pnfs_deviceid_cache *c, struct nfs4_deviceid *id) +{ + struct pnfs_deviceid_node *d; + struct hlist_node *n; + long hash = nfs4_deviceid_hash(id); + + dprintk("--> %s hash %ld\n", __func__, hash); + rcu_read_lock(); + hlist_for_each_entry_rcu(d, n, &c->dc_deviceids[hash], de_node) { + if (!memcmp(&d->de_id, id, sizeof(*id))) { + if (!atomic_inc_not_zero(&d->de_ref)) { + goto fail; + } else { + rcu_read_unlock(); + return d; + } + } + } +fail: + rcu_read_unlock(); + return NULL; +} +EXPORT_SYMBOL_GPL(pnfs_find_get_deviceid); + +/* + * Add a deviceid to the cache. + * GETDEVICEINFOs for same deviceid can race. If deviceid is found, discard new + */ +struct pnfs_deviceid_node * +pnfs_add_deviceid(struct pnfs_deviceid_cache *c, struct pnfs_deviceid_node *new) +{ + struct pnfs_deviceid_node *d; + long hash = nfs4_deviceid_hash(&new->de_id); + + dprintk("--> %s hash %ld\n", __func__, hash); + spin_lock(&c->dc_lock); + d = pnfs_find_get_deviceid(c, &new->de_id); + if (d) { + spin_unlock(&c->dc_lock); + dprintk("%s [discard]\n", __func__); + c->dc_free_callback(new); + return d; + } + INIT_HLIST_NODE(&new->de_node); + atomic_set(&new->de_ref, 1); + hlist_add_head_rcu(&new->de_node, &c->dc_deviceids[hash]); + spin_unlock(&c->dc_lock); + dprintk("%s [new]\n", __func__); + return new; +} +EXPORT_SYMBOL_GPL(pnfs_add_deviceid); + +void +pnfs_put_deviceid_cache(struct nfs_client *clp) +{ + struct pnfs_deviceid_cache *local = clp->cl_devid_cache; + + dprintk("--> %s cl_devid_cache %p\n", __func__, clp->cl_devid_cache); + if (atomic_dec_and_lock(&local->dc_ref, &clp->cl_lock)) { + int i; + /* Verify cache is empty */ + for (i = 0; i < NFS4_DEVICE_ID_HASH_SIZE; i++) + BUG_ON(!hlist_empty(&local->dc_deviceids[i])); + clp->cl_devid_cache = NULL; + spin_unlock(&clp->cl_lock); + kfree(local); + } +} +EXPORT_SYMBOL_GPL(pnfs_put_deviceid_cache); diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h new file mode 100644 index 000000000000..e12367d50489 --- /dev/null +++ b/fs/nfs/pnfs.h @@ -0,0 +1,189 @@ +/* + * pNFS client data structures. + * + * Copyright (c) 2002 + * The Regents of the University of Michigan + * All Rights Reserved + * + * Dean Hildebrand <dhildebz@umich.edu> + * + * Permission is granted to use, copy, create derivative works, and + * redistribute this software and such derivative works for any purpose, + * so long as the name of the University of Michigan is not used in + * any advertising or publicity pertaining to the use or distribution + * of this software without specific, written prior authorization. If + * the above copyright notice or any other identification of the + * University of Michigan is included in any copy of any portion of + * this software, then the disclaimer below must also be included. + * + * This software is provided as is, without representation or warranty + * of any kind either express or implied, including without limitation + * the implied warranties of merchantability, fitness for a particular + * purpose, or noninfringement. The Regents of the University of + * Michigan shall not be liable for any damages, including special, + * indirect, incidental, or consequential damages, with respect to any + * claim arising out of or in connection with the use of the software, + * even if it has been or is hereafter advised of the possibility of + * such damages. + */ + +#ifndef FS_NFS_PNFS_H +#define FS_NFS_PNFS_H + +struct pnfs_layout_segment { + struct list_head fi_list; + struct pnfs_layout_range range; + struct kref kref; + struct pnfs_layout_hdr *layout; +}; + +#ifdef CONFIG_NFS_V4_1 + +#define LAYOUT_NFSV4_1_MODULE_PREFIX "nfs-layouttype4" + +enum { + NFS_LAYOUT_RO_FAILED = 0, /* get ro layout failed stop trying */ + NFS_LAYOUT_RW_FAILED, /* get rw layout failed stop trying */ + NFS_LAYOUT_STATEID_SET, /* have a valid layout stateid */ +}; + +/* Per-layout driver specific registration structure */ +struct pnfs_layoutdriver_type { + struct list_head pnfs_tblid; + const u32 id; + const char *name; + struct module *owner; + int (*set_layoutdriver) (struct nfs_server *); + int (*clear_layoutdriver) (struct nfs_server *); + struct pnfs_layout_segment * (*alloc_lseg) (struct pnfs_layout_hdr *layoutid, struct nfs4_layoutget_res *lgr); + void (*free_lseg) (struct pnfs_layout_segment *lseg); +}; + +struct pnfs_layout_hdr { + unsigned long refcount; + struct list_head layouts; /* other client layouts */ + struct list_head segs; /* layout segments list */ + seqlock_t seqlock; /* Protects the stateid */ + nfs4_stateid stateid; + unsigned long state; + struct inode *inode; +}; + +struct pnfs_device { + struct nfs4_deviceid dev_id; + unsigned int layout_type; + unsigned int mincount; + struct page **pages; + void *area; + unsigned int pgbase; + unsigned int pglen; +}; + +/* + * Device ID RCU cache. A device ID is unique per client ID and layout type. + */ +#define NFS4_DEVICE_ID_HASH_BITS 5 +#define NFS4_DEVICE_ID_HASH_SIZE (1 << NFS4_DEVICE_ID_HASH_BITS) +#define NFS4_DEVICE_ID_HASH_MASK (NFS4_DEVICE_ID_HASH_SIZE - 1) + +static inline u32 +nfs4_deviceid_hash(struct nfs4_deviceid *id) +{ + unsigned char *cptr = (unsigned char *)id->data; + unsigned int nbytes = NFS4_DEVICEID4_SIZE; + u32 x = 0; + + while (nbytes--) { + x *= 37; + x += *cptr++; + } + return x & NFS4_DEVICE_ID_HASH_MASK; +} + +struct pnfs_deviceid_node { + struct hlist_node de_node; + struct nfs4_deviceid de_id; + atomic_t de_ref; +}; + +struct pnfs_deviceid_cache { + spinlock_t dc_lock; + atomic_t dc_ref; + void (*dc_free_callback)(struct pnfs_deviceid_node *); + struct hlist_head dc_deviceids[NFS4_DEVICE_ID_HASH_SIZE]; +}; + +extern int pnfs_alloc_init_deviceid_cache(struct nfs_client *, + void (*free_callback)(struct pnfs_deviceid_node *)); +extern void pnfs_put_deviceid_cache(struct nfs_client *); +extern struct pnfs_deviceid_node *pnfs_find_get_deviceid( + struct pnfs_deviceid_cache *, + struct nfs4_deviceid *); +extern struct pnfs_deviceid_node *pnfs_add_deviceid( + struct pnfs_deviceid_cache *, + struct pnfs_deviceid_node *); +extern void pnfs_put_deviceid(struct pnfs_deviceid_cache *c, + struct pnfs_deviceid_node *devid); + +extern int pnfs_register_layoutdriver(struct pnfs_layoutdriver_type *); +extern void pnfs_unregister_layoutdriver(struct pnfs_layoutdriver_type *); + +/* nfs4proc.c */ +extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, + struct pnfs_device *dev); +extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp); + +/* pnfs.c */ +struct pnfs_layout_segment * +pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx, + enum pnfs_iomode access_type); +void set_pnfs_layoutdriver(struct nfs_server *, u32 id); +void unset_pnfs_layoutdriver(struct nfs_server *); +int pnfs_layout_process(struct nfs4_layoutget *lgp); +void pnfs_destroy_layout(struct nfs_inode *); +void pnfs_destroy_all_layouts(struct nfs_client *); +void put_layout_hdr(struct inode *inode); +void pnfs_get_layout_stateid(nfs4_stateid *dst, struct pnfs_layout_hdr *lo, + struct nfs4_state *open_state); + + +static inline int lo_fail_bit(u32 iomode) +{ + return iomode == IOMODE_RW ? + NFS_LAYOUT_RW_FAILED : NFS_LAYOUT_RO_FAILED; +} + +/* Return true if a layout driver is being used for this mountpoint */ +static inline int pnfs_enabled_sb(struct nfs_server *nfss) +{ + return nfss->pnfs_curr_ld != NULL; +} + +#else /* CONFIG_NFS_V4_1 */ + +static inline void pnfs_destroy_all_layouts(struct nfs_client *clp) +{ +} + +static inline void pnfs_destroy_layout(struct nfs_inode *nfsi) +{ +} + +static inline struct pnfs_layout_segment * +pnfs_update_layout(struct inode *ino, struct nfs_open_context *ctx, + enum pnfs_iomode access_type) +{ + return NULL; +} + +static inline void set_pnfs_layoutdriver(struct nfs_server *s, u32 id) +{ +} + +static inline void unset_pnfs_layoutdriver(struct nfs_server *s) +{ +} + +#endif /* CONFIG_NFS_V4_1 */ + +#endif /* FS_NFS_PNFS_H */ diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 611bec22f552..58e7f84fc1fd 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -258,7 +258,7 @@ static void nfs_free_createdata(const struct nfs_createdata *data) static int nfs_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, - int flags, struct nameidata *nd) + int flags, struct nfs_open_context *ctx) { struct nfs_createdata *data; struct rpc_message msg = { @@ -365,17 +365,32 @@ static int nfs_proc_unlink_done(struct rpc_task *task, struct inode *dir) return 1; } +static void +nfs_proc_rename_setup(struct rpc_message *msg, struct inode *dir) +{ + msg->rpc_proc = &nfs_procedures[NFSPROC_RENAME]; +} + +static int +nfs_proc_rename_done(struct rpc_task *task, struct inode *old_dir, + struct inode *new_dir) +{ + if (nfs_async_handle_expired_key(task)) + return 0; + nfs_mark_for_revalidate(old_dir); + nfs_mark_for_revalidate(new_dir); + return 1; +} + static int nfs_proc_rename(struct inode *old_dir, struct qstr *old_name, struct inode *new_dir, struct qstr *new_name) { struct nfs_renameargs arg = { - .fromfh = NFS_FH(old_dir), - .fromname = old_name->name, - .fromlen = old_name->len, - .tofh = NFS_FH(new_dir), - .toname = new_name->name, - .tolen = new_name->len + .old_dir = NFS_FH(old_dir), + .old_name = old_name, + .new_dir = NFS_FH(new_dir), + .new_name = new_name, }; struct rpc_message msg = { .rpc_proc = &nfs_procedures[NFSPROC_RENAME], @@ -519,14 +534,14 @@ nfs_proc_rmdir(struct inode *dir, struct qstr *name) */ static int nfs_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, - u64 cookie, struct page *page, unsigned int count, int plus) + u64 cookie, struct page **pages, unsigned int count, int plus) { struct inode *dir = dentry->d_inode; struct nfs_readdirargs arg = { .fh = NFS_FH(dir), .cookie = cookie, .count = count, - .pages = &page, + .pages = pages, }; struct rpc_message msg = { .rpc_proc = &nfs_procedures[NFSPROC_READDIR], @@ -705,6 +720,8 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .unlink_setup = nfs_proc_unlink_setup, .unlink_done = nfs_proc_unlink_done, .rename = nfs_proc_rename, + .rename_setup = nfs_proc_rename_setup, + .rename_done = nfs_proc_rename_done, .link = nfs_proc_link, .symlink = nfs_proc_symlink, .mkdir = nfs_proc_mkdir, diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 87adc2744246..e4b62c6f5a6e 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -25,6 +25,7 @@ #include "internal.h" #include "iostat.h" #include "fscache.h" +#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_PAGECACHE @@ -46,7 +47,6 @@ struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount) memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&p->pages); p->npages = pagecount; - p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE; if (pagecount <= ARRAY_SIZE(p->page_array)) p->pagevec = p->page_array; else { @@ -121,6 +121,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, len = nfs_page_length(page); if (len == 0) return nfs_return_empty_page(page); + pnfs_update_layout(inode, ctx, IOMODE_READ); new = nfs_create_request(ctx, inode, page, 0, len); if (IS_ERR(new)) { unlock_page(page); @@ -625,6 +626,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) goto read_complete; /* all pages were read */ + pnfs_update_layout(inode, desc.ctx, IOMODE_READ); if (rsize < PAGE_CACHE_SIZE) nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0); else diff --git a/fs/nfs/super.c b/fs/nfs/super.c index f4cbf0c306c6..0a42e8f4adcb 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -100,6 +100,7 @@ enum { Opt_addr, Opt_mountaddr, Opt_clientaddr, Opt_lookupcache, Opt_fscache_uniq, + Opt_local_lock, /* Special mount options */ Opt_userspace, Opt_deprecated, Opt_sloppy, @@ -171,6 +172,7 @@ static const match_table_t nfs_mount_option_tokens = { { Opt_lookupcache, "lookupcache=%s" }, { Opt_fscache_uniq, "fsc=%s" }, + { Opt_local_lock, "local_lock=%s" }, { Opt_err, NULL } }; @@ -236,14 +238,30 @@ static match_table_t nfs_lookupcache_tokens = { { Opt_lookupcache_err, NULL } }; +enum { + Opt_local_lock_all, Opt_local_lock_flock, Opt_local_lock_posix, + Opt_local_lock_none, + + Opt_local_lock_err +}; + +static match_table_t nfs_local_lock_tokens = { + { Opt_local_lock_all, "all" }, + { Opt_local_lock_flock, "flock" }, + { Opt_local_lock_posix, "posix" }, + { Opt_local_lock_none, "none" }, + + { Opt_local_lock_err, NULL } +}; + static void nfs_umount_begin(struct super_block *); static int nfs_statfs(struct dentry *, struct kstatfs *); static int nfs_show_options(struct seq_file *, struct vfsmount *); static int nfs_show_stats(struct seq_file *, struct vfsmount *); static int nfs_get_sb(struct file_system_type *, int, const char *, void *, struct vfsmount *); -static int nfs_xdev_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); +static struct dentry *nfs_xdev_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); static void nfs_put_super(struct super_block *); static void nfs_kill_super(struct super_block *); static int nfs_remount(struct super_block *sb, int *flags, char *raw_data); @@ -259,7 +277,7 @@ static struct file_system_type nfs_fs_type = { struct file_system_type nfs_xdev_fs_type = { .owner = THIS_MODULE, .name = "nfs", - .get_sb = nfs_xdev_get_sb, + .mount = nfs_xdev_mount, .kill_sb = nfs_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; @@ -284,14 +302,14 @@ static int nfs4_try_mount(int flags, const char *dev_name, struct nfs_parsed_mount_data *data, struct vfsmount *mnt); static int nfs4_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); -static int nfs4_remote_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); -static int nfs4_xdev_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); +static struct dentry *nfs4_remote_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); +static struct dentry *nfs4_xdev_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); static int nfs4_referral_get_sb(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); -static int nfs4_remote_referral_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt); +static struct dentry *nfs4_remote_referral_mount(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 = { @@ -305,7 +323,7 @@ static struct file_system_type nfs4_fs_type = { static struct file_system_type nfs4_remote_fs_type = { .owner = THIS_MODULE, .name = "nfs4", - .get_sb = nfs4_remote_get_sb, + .mount = nfs4_remote_mount, .kill_sb = nfs4_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; @@ -313,7 +331,7 @@ static struct file_system_type nfs4_remote_fs_type = { struct file_system_type nfs4_xdev_fs_type = { .owner = THIS_MODULE, .name = "nfs4", - .get_sb = nfs4_xdev_get_sb, + .mount = nfs4_xdev_mount, .kill_sb = nfs4_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; @@ -321,7 +339,7 @@ struct file_system_type nfs4_xdev_fs_type = { static struct file_system_type nfs4_remote_referral_fs_type = { .owner = THIS_MODULE, .name = "nfs4", - .get_sb = nfs4_remote_referral_get_sb, + .mount = nfs4_remote_referral_mount, .kill_sb = nfs4_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; @@ -622,6 +640,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, const struct proc_nfs_info *nfs_infop; struct nfs_client *clp = nfss->nfs_client; u32 version = clp->rpc_ops->version; + int local_flock, local_fcntl; seq_printf(m, ",vers=%u", version); seq_printf(m, ",rsize=%u", nfss->rsize); @@ -670,6 +689,18 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, else seq_printf(m, ",lookupcache=pos"); } + + local_flock = nfss->flags & NFS_MOUNT_LOCAL_FLOCK; + local_fcntl = nfss->flags & NFS_MOUNT_LOCAL_FCNTL; + + if (!local_flock && !local_fcntl) + seq_printf(m, ",local_lock=none"); + else if (local_flock && local_fcntl) + seq_printf(m, ",local_lock=all"); + else if (local_flock) + seq_printf(m, ",local_lock=flock"); + else + seq_printf(m, ",local_lock=posix"); } /* @@ -1017,9 +1048,13 @@ static int nfs_parse_mount_options(char *raw, break; case Opt_lock: mnt->flags &= ~NFS_MOUNT_NONLM; + mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | + NFS_MOUNT_LOCAL_FCNTL); break; case Opt_nolock: mnt->flags |= NFS_MOUNT_NONLM; + mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK | + NFS_MOUNT_LOCAL_FCNTL); break; case Opt_v2: mnt->flags &= ~NFS_MOUNT_VER3; @@ -1420,6 +1455,34 @@ static int nfs_parse_mount_options(char *raw, mnt->fscache_uniq = string; mnt->options |= NFS_OPTION_FSCACHE; break; + case Opt_local_lock: + string = match_strdup(args); + if (string == NULL) + goto out_nomem; + token = match_token(string, nfs_local_lock_tokens, + args); + kfree(string); + switch (token) { + case Opt_local_lock_all: + mnt->flags |= (NFS_MOUNT_LOCAL_FLOCK | + NFS_MOUNT_LOCAL_FCNTL); + break; + case Opt_local_lock_flock: + mnt->flags |= NFS_MOUNT_LOCAL_FLOCK; + break; + case Opt_local_lock_posix: + mnt->flags |= NFS_MOUNT_LOCAL_FCNTL; + break; + case Opt_local_lock_none: + mnt->flags &= ~(NFS_MOUNT_LOCAL_FLOCK | + NFS_MOUNT_LOCAL_FCNTL); + break; + default: + dfprintk(MOUNT, "NFS: invalid " + "local_lock argument\n"); + return 0; + }; + break; /* * Special options @@ -1825,6 +1888,12 @@ static int nfs_validate_mount_data(void *options, if (!args->nfs_server.hostname) goto out_nomem; + if (!(data->flags & NFS_MOUNT_NONLM)) + args->flags &= ~(NFS_MOUNT_LOCAL_FLOCK| + NFS_MOUNT_LOCAL_FCNTL); + else + args->flags |= (NFS_MOUNT_LOCAL_FLOCK| + NFS_MOUNT_LOCAL_FCNTL); /* * The legacy version 6 binary mount data from userspace has a * field used only to transport selinux information into the @@ -2328,9 +2397,9 @@ static void nfs_kill_super(struct super_block *s) /* * Clone an NFS2/3 server record on xdev traversal (FSID-change) */ -static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data, - struct vfsmount *mnt) +static struct dentry * +nfs_xdev_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) { struct nfs_clone_mount *data = raw_data; struct super_block *s; @@ -2342,7 +2411,7 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags, }; int error; - dprintk("--> nfs_xdev_get_sb()\n"); + dprintk("--> nfs_xdev_mount()\n"); /* create a new volume representation */ server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr); @@ -2389,28 +2458,26 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type, int flags, } s->s_flags |= MS_ACTIVE; - mnt->mnt_sb = s; - mnt->mnt_root = mntroot; /* clone any lsm security options from the parent to the new sb */ security_sb_clone_mnt_opts(data->sb, s); - dprintk("<-- nfs_xdev_get_sb() = 0\n"); - return 0; + dprintk("<-- nfs_xdev_mount() = 0\n"); + return mntroot; out_err_nosb: nfs_free_server(server); out_err_noserver: - dprintk("<-- nfs_xdev_get_sb() = %d [error]\n", error); - return error; + dprintk("<-- nfs_xdev_mount() = %d [error]\n", error); + return ERR_PTR(error); error_splat_super: if (server && !s->s_root) bdi_unregister(&server->backing_dev_info); error_splat_bdi: deactivate_locked_super(s); - dprintk("<-- nfs_xdev_get_sb() = %d [splat]\n", error); - return error; + dprintk("<-- nfs_xdev_mount() = %d [splat]\n", error); + return ERR_PTR(error); } #ifdef CONFIG_NFS_V4 @@ -2441,7 +2508,8 @@ static void nfs4_fill_super(struct super_block *sb) static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args) { - args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3); + args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3| + NFS_MOUNT_LOCAL_FLOCK|NFS_MOUNT_LOCAL_FCNTL); } static int nfs4_validate_text_mount_data(void *options, @@ -2579,8 +2647,9 @@ out_no_address: /* * Get the superblock for the NFS4 root partition */ -static int nfs4_remote_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt) +static struct dentry * +nfs4_remote_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) { struct nfs_parsed_mount_data *data = raw_data; struct super_block *s; @@ -2644,15 +2713,16 @@ static int nfs4_remote_get_sb(struct file_system_type *fs_type, goto error_splat_root; s->s_flags |= MS_ACTIVE; - mnt->mnt_sb = s; - mnt->mnt_root = mntroot; - error = 0; + + security_free_mnt_opts(&data->lsm_opts); + nfs_free_fhandle(mntfh); + return mntroot; out: security_free_mnt_opts(&data->lsm_opts); out_free_fh: nfs_free_fhandle(mntfh); - return error; + return ERR_PTR(error); out_free: nfs_free_server(server); @@ -2898,9 +2968,9 @@ static void nfs4_kill_super(struct super_block *sb) /* * Clone an NFS4 server record on xdev traversal (FSID-change) */ -static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data, - struct vfsmount *mnt) +static struct dentry * +nfs4_xdev_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) { struct nfs_clone_mount *data = raw_data; struct super_block *s; @@ -2912,7 +2982,7 @@ static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags, }; int error; - dprintk("--> nfs4_xdev_get_sb()\n"); + dprintk("--> nfs4_xdev_mount()\n"); /* create a new volume representation */ server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr); @@ -2959,32 +3029,30 @@ static int nfs4_xdev_get_sb(struct file_system_type *fs_type, int flags, } s->s_flags |= MS_ACTIVE; - mnt->mnt_sb = s; - mnt->mnt_root = mntroot; security_sb_clone_mnt_opts(data->sb, s); - dprintk("<-- nfs4_xdev_get_sb() = 0\n"); - return 0; + dprintk("<-- nfs4_xdev_mount() = 0\n"); + return mntroot; out_err_nosb: nfs_free_server(server); out_err_noserver: - dprintk("<-- nfs4_xdev_get_sb() = %d [error]\n", error); - return error; + dprintk("<-- nfs4_xdev_mount() = %d [error]\n", error); + return ERR_PTR(error); error_splat_super: if (server && !s->s_root) bdi_unregister(&server->backing_dev_info); error_splat_bdi: deactivate_locked_super(s); - dprintk("<-- nfs4_xdev_get_sb() = %d [splat]\n", error); - return error; + dprintk("<-- nfs4_xdev_mount() = %d [splat]\n", error); + return ERR_PTR(error); } -static int nfs4_remote_referral_get_sb(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data, - struct vfsmount *mnt) +static struct dentry * +nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) { struct nfs_clone_mount *data = raw_data; struct super_block *s; @@ -3048,14 +3116,12 @@ static int nfs4_remote_referral_get_sb(struct file_system_type *fs_type, } s->s_flags |= MS_ACTIVE; - mnt->mnt_sb = s; - mnt->mnt_root = mntroot; security_sb_clone_mnt_opts(data->sb, s); nfs_free_fhandle(mntfh); dprintk("<-- nfs4_referral_get_sb() = 0\n"); - return 0; + return mntroot; out_err_nosb: nfs_free_server(server); @@ -3063,7 +3129,7 @@ out_err_noserver: nfs_free_fhandle(mntfh); out_err_nofh: dprintk("<-- nfs4_referral_get_sb() = %d [error]\n", error); - return error; + return ERR_PTR(error); error_splat_super: if (server && !s->s_root) @@ -3072,7 +3138,7 @@ error_splat_bdi: deactivate_locked_super(s); nfs_free_fhandle(mntfh); dprintk("<-- nfs4_referral_get_sb() = %d [splat]\n", error); - return error; + return ERR_PTR(error); } /* diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c index ad4d2e787b20..978aaeb8a093 100644 --- a/fs/nfs/sysctl.c +++ b/fs/nfs/sysctl.c @@ -32,6 +32,7 @@ static ctl_table nfs_cb_sysctls[] = { .extra1 = (int *)&nfs_set_port_min, .extra2 = (int *)&nfs_set_port_max, }, +#ifndef CONFIG_NFS_USE_NEW_IDMAPPER { .procname = "idmap_cache_timeout", .data = &nfs_idmap_cache_timeout, @@ -39,6 +40,7 @@ static ctl_table nfs_cb_sysctls[] = { .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, +#endif /* CONFIG_NFS_USE_NEW_IDMAPPER */ #endif { .procname = "nfs_mountpoint_timeout", diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 2f84adaad427..7bdec8531400 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -13,9 +13,12 @@ #include <linux/nfs_fs.h> #include <linux/sched.h> #include <linux/wait.h> +#include <linux/namei.h> #include "internal.h" #include "nfs4_fs.h" +#include "iostat.h" +#include "delegation.h" struct nfs_unlinkdata { struct hlist_node list; @@ -244,7 +247,7 @@ void nfs_unblock_sillyrename(struct dentry *dentry) * @dir: parent directory of dentry * @dentry: dentry to unlink */ -int +static int nfs_async_unlink(struct inode *dir, struct dentry *dentry) { struct nfs_unlinkdata *data; @@ -259,7 +262,6 @@ nfs_async_unlink(struct inode *dir, struct dentry *dentry) status = PTR_ERR(data->cred); goto out_free; } - data->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE; data->res.dir_attr = &data->dir_attr; status = -EBUSY; @@ -303,3 +305,256 @@ nfs_complete_unlink(struct dentry *dentry, struct inode *inode) if (data != NULL && (NFS_STALE(inode) || !nfs_call_unlink(dentry, data))) nfs_free_unlinkdata(data); } + +/* Cancel a queued async unlink. Called when a sillyrename run fails. */ +static void +nfs_cancel_async_unlink(struct dentry *dentry) +{ + spin_lock(&dentry->d_lock); + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) { + struct nfs_unlinkdata *data = dentry->d_fsdata; + + dentry->d_flags &= ~DCACHE_NFSFS_RENAMED; + spin_unlock(&dentry->d_lock); + nfs_free_unlinkdata(data); + return; + } + spin_unlock(&dentry->d_lock); +} + +struct nfs_renamedata { + struct nfs_renameargs args; + struct nfs_renameres res; + struct rpc_cred *cred; + struct inode *old_dir; + struct dentry *old_dentry; + struct nfs_fattr old_fattr; + struct inode *new_dir; + struct dentry *new_dentry; + struct nfs_fattr new_fattr; +}; + +/** + * nfs_async_rename_done - Sillyrename post-processing + * @task: rpc_task of the sillyrename + * @calldata: nfs_renamedata for the sillyrename + * + * Do the directory attribute updates and the d_move + */ +static void nfs_async_rename_done(struct rpc_task *task, void *calldata) +{ + struct nfs_renamedata *data = calldata; + struct inode *old_dir = data->old_dir; + struct inode *new_dir = data->new_dir; + + if (!NFS_PROTO(old_dir)->rename_done(task, old_dir, new_dir)) { + nfs_restart_rpc(task, NFS_SERVER(old_dir)->nfs_client); + return; + } + + if (task->tk_status != 0) { + nfs_cancel_async_unlink(data->old_dentry); + return; + } + + nfs_set_verifier(data->old_dentry, nfs_save_change_attribute(old_dir)); + d_move(data->old_dentry, data->new_dentry); +} + +/** + * nfs_async_rename_release - Release the sillyrename data. + * @calldata: the struct nfs_renamedata to be released + */ +static void nfs_async_rename_release(void *calldata) +{ + struct nfs_renamedata *data = calldata; + struct super_block *sb = data->old_dir->i_sb; + + if (data->old_dentry->d_inode) + nfs_mark_for_revalidate(data->old_dentry->d_inode); + + dput(data->old_dentry); + dput(data->new_dentry); + iput(data->old_dir); + iput(data->new_dir); + nfs_sb_deactive(sb); + put_rpccred(data->cred); + kfree(data); +} + +#if defined(CONFIG_NFS_V4_1) +static void nfs_rename_prepare(struct rpc_task *task, void *calldata) +{ + struct nfs_renamedata *data = calldata; + struct nfs_server *server = NFS_SERVER(data->old_dir); + + if (nfs4_setup_sequence(server, &data->args.seq_args, + &data->res.seq_res, 1, task)) + return; + rpc_call_start(task); +} +#endif /* CONFIG_NFS_V4_1 */ + +static const struct rpc_call_ops nfs_rename_ops = { + .rpc_call_done = nfs_async_rename_done, + .rpc_release = nfs_async_rename_release, +#if defined(CONFIG_NFS_V4_1) + .rpc_call_prepare = nfs_rename_prepare, +#endif /* CONFIG_NFS_V4_1 */ +}; + +/** + * nfs_async_rename - perform an asynchronous rename operation + * @old_dir: directory that currently holds the dentry to be renamed + * @new_dir: target directory for the rename + * @old_dentry: original dentry to be renamed + * @new_dentry: dentry to which the old_dentry should be renamed + * + * It's expected that valid references to the dentries and inodes are held + */ +static struct rpc_task * +nfs_async_rename(struct inode *old_dir, struct inode *new_dir, + struct dentry *old_dentry, struct dentry *new_dentry) +{ + struct nfs_renamedata *data; + struct rpc_message msg = { }; + struct rpc_task_setup task_setup_data = { + .rpc_message = &msg, + .callback_ops = &nfs_rename_ops, + .workqueue = nfsiod_workqueue, + .rpc_client = NFS_CLIENT(old_dir), + .flags = RPC_TASK_ASYNC, + }; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (data == NULL) + return ERR_PTR(-ENOMEM); + task_setup_data.callback_data = data, + + data->cred = rpc_lookup_cred(); + if (IS_ERR(data->cred)) { + struct rpc_task *task = ERR_CAST(data->cred); + kfree(data); + return task; + } + + msg.rpc_argp = &data->args; + msg.rpc_resp = &data->res; + msg.rpc_cred = data->cred; + + /* set up nfs_renamedata */ + data->old_dir = old_dir; + ihold(old_dir); + data->new_dir = new_dir; + ihold(new_dir); + data->old_dentry = dget(old_dentry); + data->new_dentry = dget(new_dentry); + nfs_fattr_init(&data->old_fattr); + nfs_fattr_init(&data->new_fattr); + + /* set up nfs_renameargs */ + data->args.old_dir = NFS_FH(old_dir); + data->args.old_name = &old_dentry->d_name; + data->args.new_dir = NFS_FH(new_dir); + data->args.new_name = &new_dentry->d_name; + + /* set up nfs_renameres */ + data->res.old_fattr = &data->old_fattr; + data->res.new_fattr = &data->new_fattr; + + nfs_sb_active(old_dir->i_sb); + + NFS_PROTO(data->old_dir)->rename_setup(&msg, old_dir); + + return rpc_run_task(&task_setup_data); +} + +/** + * nfs_sillyrename - Perform a silly-rename of a dentry + * @dir: inode of directory that contains dentry + * @dentry: dentry to be sillyrenamed + * + * NFSv2/3 is stateless and the server doesn't know when the client is + * holding a file open. To prevent application problems when a file is + * unlinked while it's still open, the client performs a "silly-rename". + * That is, it renames the file to a hidden file in the same directory, + * and only performs the unlink once the last reference to it is put. + * + * The final cleanup is done during dentry_iput. + */ +int +nfs_sillyrename(struct inode *dir, struct dentry *dentry) +{ + static unsigned int sillycounter; + const int fileidsize = sizeof(NFS_FILEID(dentry->d_inode))*2; + const int countersize = sizeof(sillycounter)*2; + const int slen = sizeof(".nfs")+fileidsize+countersize-1; + char silly[slen+1]; + struct dentry *sdentry; + struct rpc_task *task; + int error = -EIO; + + dfprintk(VFS, "NFS: silly-rename(%s/%s, ct=%d)\n", + dentry->d_parent->d_name.name, dentry->d_name.name, + atomic_read(&dentry->d_count)); + nfs_inc_stats(dir, NFSIOS_SILLYRENAME); + + /* + * We don't allow a dentry to be silly-renamed twice. + */ + error = -EBUSY; + if (dentry->d_flags & DCACHE_NFSFS_RENAMED) + goto out; + + sprintf(silly, ".nfs%*.*Lx", + fileidsize, fileidsize, + (unsigned long long)NFS_FILEID(dentry->d_inode)); + + /* Return delegation in anticipation of the rename */ + nfs_inode_return_delegation(dentry->d_inode); + + sdentry = NULL; + do { + char *suffix = silly + slen - countersize; + + dput(sdentry); + sillycounter++; + sprintf(suffix, "%*.*x", countersize, countersize, sillycounter); + + dfprintk(VFS, "NFS: trying to rename %s to %s\n", + dentry->d_name.name, silly); + + sdentry = lookup_one_len(silly, dentry->d_parent, slen); + /* + * N.B. Better to return EBUSY here ... it could be + * dangerous to delete the file while it's in use. + */ + if (IS_ERR(sdentry)) + goto out; + } while (sdentry->d_inode != NULL); /* need negative lookup */ + + /* queue unlink first. Can't do this from rpc_release as it + * has to allocate memory + */ + error = nfs_async_unlink(dir, dentry); + if (error) + goto out_dput; + + /* run the rename task, undo unlink if it fails */ + task = nfs_async_rename(dir, dir, dentry, sdentry); + if (IS_ERR(task)) { + error = -EBUSY; + nfs_cancel_async_unlink(dentry); + goto out_dput; + } + + /* wait for the RPC task to complete, unless a SIGKILL intervenes */ + error = rpc_wait_for_completion_task(task); + if (error == 0) + error = task->tk_status; + rpc_put_task(task); +out_dput: + dput(sdentry); +out: + return error; +} diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 874972d9427c..4c14c17a5276 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -55,7 +55,6 @@ struct nfs_write_data *nfs_commitdata_alloc(void) if (p) { memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&p->pages); - p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE; } return p; } @@ -75,7 +74,6 @@ struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount) memset(p, 0, sizeof(*p)); INIT_LIST_HEAD(&p->pages); p->npages = pagecount; - p->res.seq_res.sr_slotid = NFS4_MAX_SLOT_TABLE; if (pagecount <= ARRAY_SIZE(p->page_array)) p->pagevec = p->page_array; else { @@ -292,9 +290,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, st nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); nfs_pageio_cond_complete(pgio, page->index); - ret = nfs_page_async_flush(pgio, page, - wbc->sync_mode == WB_SYNC_NONE || - wbc->nonblocking != 0); + ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); if (ret == -EAGAIN) { redirty_page_for_writepage(wbc, page); ret = 0; @@ -1433,15 +1429,17 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr int flags = FLUSH_SYNC; int ret = 0; - /* Don't commit yet if this is a non-blocking flush and there are - * lots of outstanding writes for this mapping. - */ - if (wbc->sync_mode == WB_SYNC_NONE && - nfsi->ncommit <= (nfsi->npages >> 1)) - goto out_mark_dirty; + if (wbc->sync_mode == WB_SYNC_NONE) { + /* Don't commit yet if this is a non-blocking flush and there + * are a lot of outstanding writes for this mapping. + */ + if (nfsi->ncommit <= (nfsi->npages >> 1)) + goto out_mark_dirty; - if (wbc->nonblocking || wbc->for_background) + /* don't wait for the COMMIT response */ flags = 0; + } + ret = nfs_commit_inode(inode, flags); if (ret >= 0) { if (wbc->sync_mode == WB_SYNC_NONE) { |