diff options
Diffstat (limited to 'fs/nfs')
47 files changed, 3003 insertions, 2199 deletions
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig index f90f4f5..db7ad719 100644 --- a/fs/nfs/Kconfig +++ b/fs/nfs/Kconfig @@ -30,7 +30,7 @@ config NFS_FS If unsure, say N. config NFS_V2 - bool "NFS client support for NFS version 2" + tristate "NFS client support for NFS version 2" depends on NFS_FS default y help @@ -40,7 +40,7 @@ config NFS_V2 If unsure, say Y. config NFS_V3 - bool "NFS client support for NFS version 3" + tristate "NFS client support for NFS version 3" depends on NFS_FS default y help @@ -72,7 +72,7 @@ config NFS_V3_ACL If unsure, say N. config NFS_V4 - bool "NFS client support for NFS version 4" + tristate "NFS client support for NFS version 4" depends on NFS_FS select SUNRPC_GSS select KEYS @@ -86,11 +86,18 @@ config NFS_V4 If unsure, say Y. +config NFS_SWAP + bool "Provide swap over NFS support" + default n + depends on NFS_FS + select SUNRPC_SWAP + help + This option enables swapon to work on files located on NFS mounts. + config NFS_V4_1 bool "NFS client support for NFSv4.1 (EXPERIMENTAL)" - depends on NFS_FS && NFS_V4 && EXPERIMENTAL + depends on NFS_V4 && EXPERIMENTAL select SUNRPC_BACKCHANNEL - select PNFS_FILE_LAYOUT help This option enables support for minor version 1 of the NFSv4 protocol (RFC 5661) in the kernel's NFS client. @@ -99,15 +106,17 @@ config NFS_V4_1 config PNFS_FILE_LAYOUT tristate + depends on NFS_V4_1 + default m config PNFS_BLOCK tristate - depends on NFS_FS && NFS_V4_1 && BLK_DEV_DM + depends on NFS_V4_1 && BLK_DEV_DM default m config PNFS_OBJLAYOUT tristate - depends on NFS_FS && NFS_V4_1 && SCSI_OSD_ULD + depends on NFS_V4_1 && SCSI_OSD_ULD default m config NFS_V4_1_IMPLEMENTATION_ID_DOMAIN diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile index 7ddd45d..b7db608 100644 --- a/fs/nfs/Makefile +++ b/fs/nfs/Makefile @@ -9,17 +9,23 @@ nfs-y := client.o dir.o file.o getroot.o inode.o super.o \ write.o namespace.o mount_clnt.o \ dns_resolve.o cache_lib.o nfs-$(CONFIG_ROOT_NFS) += nfsroot.o -nfs-$(CONFIG_NFS_V2) += proc.o nfs2xdr.o -nfs-$(CONFIG_NFS_V3) += nfs3proc.o nfs3xdr.o -nfs-$(CONFIG_NFS_V3_ACL) += nfs3acl.o -nfs-$(CONFIG_NFS_V4) += nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \ - delegation.o idmap.o \ - callback.o callback_xdr.o callback_proc.o \ - nfs4namespace.o -nfs-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o -nfs-$(CONFIG_SYSCTL) += sysctl.o +nfs-$(CONFIG_SYSCTL) += sysctl.o nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o +obj-$(CONFIG_NFS_V2) += nfsv2.o +nfsv2-y := nfs2super.o proc.o nfs2xdr.o + +obj-$(CONFIG_NFS_V3) += nfsv3.o +nfsv3-y := nfs3super.o nfs3client.o nfs3proc.o nfs3xdr.o +nfsv3-$(CONFIG_NFS_V3_ACL) += nfs3acl.o + +obj-$(CONFIG_NFS_V4) += nfsv4.o +nfsv4-y := nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o nfs4super.o nfs4file.o \ + delegation.o idmap.o callback.o callback_xdr.o callback_proc.o \ + nfs4namespace.o nfs4getroot.o nfs4client.o +nfsv4-$(CONFIG_SYSCTL) += nfs4sysctl.o +nfsv4-$(CONFIG_NFS_V4_1) += pnfs.o pnfs_dev.o + obj-$(CONFIG_PNFS_FILE_LAYOUT) += nfs_layout_nfsv41_files.o nfs_layout_nfsv41_files-y := nfs4filelayout.o nfs4filelayoutdev.o diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c index 7ae8a60..dd392ed 100644 --- a/fs/nfs/blocklayout/blocklayout.c +++ b/fs/nfs/blocklayout/blocklayout.c @@ -228,6 +228,14 @@ bl_end_par_io_read(void *data, int unused) schedule_work(&rdata->task.u.tk_work); } +static bool +bl_check_alignment(u64 offset, u32 len, unsigned long blkmask) +{ + if ((offset & blkmask) || (len & blkmask)) + return false; + return true; +} + static enum pnfs_try_status bl_read_pagelist(struct nfs_read_data *rdata) { @@ -244,6 +252,9 @@ bl_read_pagelist(struct nfs_read_data *rdata) dprintk("%s enter nr_pages %u offset %lld count %u\n", __func__, rdata->pages.npages, f_offset, (unsigned int)rdata->args.count); + if (!bl_check_alignment(f_offset, rdata->args.count, PAGE_CACHE_MASK)) + goto use_mds; + par = alloc_parallel(rdata); if (!par) goto use_mds; @@ -552,7 +563,7 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync) struct bio *bio = NULL; struct pnfs_block_extent *be = NULL, *cow_read = NULL; sector_t isect, last_isect = 0, extent_length = 0; - struct parallel_io *par; + struct parallel_io *par = NULL; loff_t offset = wdata->args.offset; size_t count = wdata->args.count; struct page **pages = wdata->args.pages; @@ -563,6 +574,10 @@ bl_write_pagelist(struct nfs_write_data *wdata, int sync) NFS_SERVER(header->inode)->pnfs_blksize >> PAGE_CACHE_SHIFT; dprintk("%s enter, %Zu@%lld\n", __func__, count, offset); + /* Check for alignment first */ + if (!bl_check_alignment(offset, count, PAGE_CACHE_MASK)) + goto out_mds; + /* At this point, wdata->pages is a (sequential) list of nfs_pages. * We want to write each, and if there is an error set pnfs_error * to have it redone using nfs. @@ -996,14 +1011,32 @@ bl_clear_layoutdriver(struct nfs_server *server) return 0; } +static void +bl_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK)) + nfs_pageio_reset_read_mds(pgio); + else + pnfs_generic_pg_init_read(pgio, req); +} + +static void +bl_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + if (!bl_check_alignment(req->wb_offset, req->wb_bytes, PAGE_CACHE_MASK)) + nfs_pageio_reset_write_mds(pgio); + else + pnfs_generic_pg_init_write(pgio, req); +} + static const struct nfs_pageio_ops bl_pg_read_ops = { - .pg_init = pnfs_generic_pg_init_read, + .pg_init = bl_pg_init_read, .pg_test = pnfs_generic_pg_test, .pg_doio = pnfs_generic_pg_readpages, }; static const struct nfs_pageio_ops bl_pg_write_ops = { - .pg_init = pnfs_generic_pg_init_write, + .pg_init = bl_pg_init_write, .pg_test = pnfs_generic_pg_test, .pg_doio = pnfs_generic_pg_writepages, }; diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c index 23ff18f..4c8459e 100644 --- a/fs/nfs/callback.c +++ b/fs/nfs/callback.c @@ -37,31 +37,7 @@ static struct nfs_callback_data nfs_callback_info[NFS4_MAX_MINOR_VERSION + 1]; static DEFINE_MUTEX(nfs_callback_mutex); static struct svc_program nfs4_callback_program; -unsigned int nfs_callback_set_tcpport; -unsigned short nfs_callback_tcpport; unsigned short nfs_callback_tcpport6; -#define NFS_CALLBACK_MAXPORTNR (65535U) - -static int param_set_portnr(const char *val, const struct kernel_param *kp) -{ - unsigned long num; - int ret; - - if (!val) - return -EINVAL; - ret = strict_strtoul(val, 0, &num); - if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR) - return -EINVAL; - *((unsigned int *)kp->arg) = num; - return 0; -} -static struct kernel_param_ops param_ops_portnr = { - .set = param_set_portnr, - .get = param_get_uint, -}; -#define param_check_portnr(name, p) __param_check(name, p, unsigned int); - -module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644); /* * This is the NFSv4 callback kernel thread. @@ -265,6 +241,10 @@ int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt) ret = -ENOMEM; goto out_err; } + /* As there is only one thread we need to over-ride the + * default maximum of 80 connections + */ + serv->sv_maxconn = 1024; ret = svc_bind(serv, net); if (ret < 0) { diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h index a5527c9..b44d7b1 100644 --- a/fs/nfs/callback.h +++ b/fs/nfs/callback.h @@ -192,7 +192,7 @@ extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args, struct cb_process_state *cps); extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy, struct cb_process_state *cps); -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt); extern void nfs_callback_down(int minorversion); extern int nfs4_validate_delegation_stateid(struct nfs_delegation *delegation, diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c index e64b01d..742ff4f 100644 --- a/fs/nfs/callback_xdr.c +++ b/fs/nfs/callback_xdr.c @@ -863,7 +863,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r .drc_status = 0, .clp = NULL, .slotid = NFS4_NO_SLOT, - .net = rqstp->rq_xprt->xpt_net, + .net = SVC_NET(rqstp), }; unsigned int nops = 0; @@ -879,7 +879,7 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r return rpc_garbage_args; if (hdr_arg.minorversion == 0) { - cps.clp = nfs4_find_client_ident(rqstp->rq_xprt->xpt_net, hdr_arg.cb_ident); + cps.clp = nfs4_find_client_ident(SVC_NET(rqstp), hdr_arg.cb_ident); if (!cps.clp || !check_gss_callback_principal(cps.clp, rqstp)) return rpc_drop_reply; } diff --git a/fs/nfs/client.c b/fs/nfs/client.c index f005b5b..9969444 100644 --- a/fs/nfs/client.c +++ b/fs/nfs/client.c @@ -51,54 +51,23 @@ #include "internal.h" #include "fscache.h" #include "pnfs.h" +#include "nfs.h" #include "netns.h" #define NFSDBG_FACILITY NFSDBG_CLIENT static DECLARE_WAIT_QUEUE_HEAD(nfs_client_active_wq); -#ifdef CONFIG_NFS_V4 - -/* - * Get a unique NFSv4.0 callback identifier which will be used - * by the V4.0 callback service to lookup the nfs_client struct - */ -static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) -{ - int ret = 0; - struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); - - if (clp->rpc_ops->version != 4 || minorversion != 0) - return ret; -retry: - if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL)) - return -ENOMEM; - spin_lock(&nn->nfs_client_lock); - ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident); - spin_unlock(&nn->nfs_client_lock); - if (ret == -EAGAIN) - goto retry; - return ret; -} -#endif /* CONFIG_NFS_V4 */ - -/* - * Turn off NFSv4 uid/gid mapping when using AUTH_SYS - */ -static bool nfs4_disable_idmapping = true; +static DEFINE_SPINLOCK(nfs_version_lock); +static DEFINE_MUTEX(nfs_version_mutex); +static LIST_HEAD(nfs_versions); /* * RPC cruft for NFS */ static const struct rpc_version *nfs_version[5] = { -#ifdef CONFIG_NFS_V2 - [2] = &nfs_version2, -#endif -#ifdef CONFIG_NFS_V3 - [3] = &nfs_version3, -#endif -#ifdef CONFIG_NFS_V4 - [4] = &nfs_version4, -#endif + [2] = NULL, + [3] = NULL, + [4] = NULL, }; const struct rpc_program nfs_program = { @@ -114,32 +83,64 @@ struct rpc_stat nfs_rpcstat = { .program = &nfs_program }; +static struct nfs_subversion *find_nfs_version(unsigned int version) +{ + struct nfs_subversion *nfs; + spin_lock(&nfs_version_lock); -#ifdef CONFIG_NFS_V3_ACL -static struct rpc_stat nfsacl_rpcstat = { &nfsacl_program }; -static const struct rpc_version *nfsacl_version[] = { - [3] = &nfsacl_version3, -}; + list_for_each_entry(nfs, &nfs_versions, list) { + if (nfs->rpc_ops->version == version) { + spin_unlock(&nfs_version_lock); + return nfs; + } + }; -const struct rpc_program nfsacl_program = { - .name = "nfsacl", - .number = NFS_ACL_PROGRAM, - .nrvers = ARRAY_SIZE(nfsacl_version), - .version = nfsacl_version, - .stats = &nfsacl_rpcstat, -}; -#endif /* CONFIG_NFS_V3_ACL */ - -struct nfs_client_initdata { - unsigned long init_flags; - const char *hostname; - const struct sockaddr *addr; - size_t addrlen; - const struct nfs_rpc_ops *rpc_ops; - int proto; - u32 minorversion; - struct net *net; -}; + spin_unlock(&nfs_version_lock); + return ERR_PTR(-EPROTONOSUPPORT);; +} + +struct nfs_subversion *get_nfs_version(unsigned int version) +{ + struct nfs_subversion *nfs = find_nfs_version(version); + + if (IS_ERR(nfs)) { + mutex_lock(&nfs_version_mutex); + request_module("nfsv%d", version); + nfs = find_nfs_version(version); + mutex_unlock(&nfs_version_mutex); + } + + if (!IS_ERR(nfs)) + try_module_get(nfs->owner); + return nfs; +} + +void put_nfs_version(struct nfs_subversion *nfs) +{ + module_put(nfs->owner); +} + +void register_nfs_version(struct nfs_subversion *nfs) +{ + spin_lock(&nfs_version_lock); + + list_add(&nfs->list, &nfs_versions); + nfs_version[nfs->rpc_ops->version] = nfs->rpc_vers; + + spin_unlock(&nfs_version_lock); +} +EXPORT_SYMBOL_GPL(register_nfs_version); + +void unregister_nfs_version(struct nfs_subversion *nfs) +{ + spin_lock(&nfs_version_lock); + + nfs_version[nfs->rpc_ops->version] = NULL; + list_del(&nfs->list); + + spin_unlock(&nfs_version_lock); +} +EXPORT_SYMBOL_GPL(unregister_nfs_version); /* * Allocate a shared client record @@ -147,7 +148,7 @@ struct nfs_client_initdata { * Since these are allocated/deallocated very rarely, we don't * bother putting them in a slab cache... */ -static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) +struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_init) { struct nfs_client *clp; struct rpc_cred *cred; @@ -156,7 +157,10 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_ if ((clp = kzalloc(sizeof(*clp), GFP_KERNEL)) == NULL) goto error_0; - clp->rpc_ops = cl_init->rpc_ops; + clp->cl_nfs_mod = cl_init->nfs_mod; + try_module_get(clp->cl_nfs_mod->owner); + + clp->rpc_ops = clp->cl_nfs_mod->rpc_ops; atomic_set(&clp->cl_count, 1); clp->cl_cons_state = NFS_CS_INITING; @@ -177,18 +181,6 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_ clp->cl_proto = cl_init->proto; clp->cl_net = get_net(cl_init->net); -#ifdef CONFIG_NFS_V4 - err = nfs_get_cb_ident_idr(clp, cl_init->minorversion); - if (err) - goto error_cleanup; - - spin_lock_init(&clp->cl_lock); - INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state); - rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client"); - clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; - clp->cl_minorversion = cl_init->minorversion; - clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion]; -#endif cred = rpc_lookup_machine_cred("*"); if (!IS_ERR(cred)) clp->cl_machine_cred = cred; @@ -197,51 +189,14 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_ return clp; error_cleanup: + put_nfs_version(clp->cl_nfs_mod); kfree(clp); error_0: return ERR_PTR(err); } +EXPORT_SYMBOL_GPL(nfs_alloc_client); -#ifdef CONFIG_NFS_V4 -#ifdef CONFIG_NFS_V4_1 -static void nfs4_shutdown_session(struct nfs_client *clp) -{ - if (nfs4_has_session(clp)) { - nfs4_destroy_session(clp->cl_session); - nfs4_destroy_clientid(clp); - } - -} -#else /* CONFIG_NFS_V4_1 */ -static void nfs4_shutdown_session(struct nfs_client *clp) -{ -} -#endif /* CONFIG_NFS_V4_1 */ - -/* - * Destroy the NFS4 callback service - */ -static void nfs4_destroy_callback(struct nfs_client *clp) -{ - if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state)) - nfs_callback_down(clp->cl_mvops->minor_version); -} - -static void nfs4_shutdown_client(struct nfs_client *clp) -{ - if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state)) - nfs4_kill_renewd(clp); - nfs4_shutdown_session(clp); - nfs4_destroy_callback(clp); - if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state)) - nfs_idmap_delete(clp); - - rpc_destroy_wait_queue(&clp->cl_rpcwaitq); - kfree(clp->cl_serverowner); - kfree(clp->cl_serverscope); - kfree(clp->cl_implid); -} - +#if IS_ENABLED(CONFIG_NFS_V4) /* idr_remove_all is not needed as all id's are removed by nfs_put_client */ void nfs_cleanup_cb_ident_idr(struct net *net) { @@ -264,16 +219,7 @@ static void pnfs_init_server(struct nfs_server *server) rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC"); } -static void nfs4_destroy_server(struct nfs_server *server) -{ - nfs4_purge_state_owners(server); -} - #else -static void nfs4_shutdown_client(struct nfs_client *clp) -{ -} - void nfs_cleanup_cb_ident_idr(struct net *net) { } @@ -291,12 +237,10 @@ static void pnfs_init_server(struct nfs_server *server) /* * Destroy a shared client record */ -static void nfs_free_client(struct nfs_client *clp) +void nfs_free_client(struct nfs_client *clp) { dprintk("--> nfs_free_client(%u)\n", clp->rpc_ops->version); - nfs4_shutdown_client(clp); - nfs_fscache_release_client_cookie(clp); /* -EIO all pending I/O */ @@ -307,11 +251,13 @@ static void nfs_free_client(struct nfs_client *clp) put_rpccred(clp->cl_machine_cred); put_net(clp->cl_net); + put_nfs_version(clp->cl_nfs_mod); kfree(clp->cl_hostname); kfree(clp); dprintk("<-- nfs_free_client()\n"); } +EXPORT_SYMBOL_GPL(nfs_free_client); /* * Release a reference to a shared client record @@ -333,7 +279,7 @@ void nfs_put_client(struct nfs_client *clp) BUG_ON(!list_empty(&clp->cl_superblocks)); - nfs_free_client(clp); + clp->rpc_ops->free_client(clp); } } EXPORT_SYMBOL_GPL(nfs_put_client); @@ -412,8 +358,8 @@ static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1, * Test if two socket addresses represent the same actual socket, * by comparing (only) relevant fields, excluding the port number. */ -static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1, - const struct sockaddr *sa2) +int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1, + const struct sockaddr *sa2) { if (sa1->sa_family != sa2->sa_family) return 0; @@ -426,6 +372,7 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1, } return 0; } +EXPORT_SYMBOL_GPL(nfs_sockaddr_match_ipaddr); #endif /* CONFIG_NFS_V4_1 */ /* @@ -447,33 +394,6 @@ static int nfs_sockaddr_cmp(const struct sockaddr *sa1, return 0; } -#if defined(CONFIG_NFS_V4_1) -/* Common match routine for v4.0 and v4.1 callback services */ -static bool nfs4_cb_match_client(const struct sockaddr *addr, - struct nfs_client *clp, u32 minorversion) -{ - struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr; - - /* Don't match clients that failed to initialise */ - if (!(clp->cl_cons_state == NFS_CS_READY || - clp->cl_cons_state == NFS_CS_SESSION_INITING)) - return false; - - smp_rmb(); - - /* Match the version and minorversion */ - if (clp->rpc_ops->version != 4 || - clp->cl_minorversion != minorversion) - return false; - - /* Match only the IP address, not the port number */ - if (!nfs_sockaddr_match_ipaddr(addr, clap)) - return false; - - return true; -} -#endif /* CONFIG_NFS_V4_1 */ - /* * Find an nfs_client on the list that matches the initialisation data * that is supplied. @@ -491,7 +411,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat continue; /* Different NFS versions cannot share the same nfs_client */ - if (clp->rpc_ops != data->rpc_ops) + if (clp->rpc_ops != data->nfs_mod->rpc_ops) continue; if (clp->cl_proto != data->proto) @@ -519,6 +439,7 @@ int nfs_wait_client_init_complete(const struct nfs_client *clp) return wait_event_killable(nfs_client_active_wq, nfs_client_init_is_complete(clp)); } +EXPORT_SYMBOL_GPL(nfs_wait_client_init_complete); /* * Found an existing client. Make sure it's ready before returning. @@ -552,7 +473,7 @@ nfs_found_client(const struct nfs_client_initdata *cl_init, * Look up a client by IP address and protocol version * - creates a new record if one doesn't yet exist */ -static struct nfs_client * +struct nfs_client * nfs_get_client(const struct nfs_client_initdata *cl_init, const struct rpc_timeout *timeparms, const char *ip_addr, @@ -560,9 +481,10 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, { struct nfs_client *clp, *new = NULL; struct nfs_net *nn = net_generic(cl_init->net, nfs_net_id); + const struct nfs_rpc_ops *rpc_ops = cl_init->nfs_mod->rpc_ops; dprintk("--> nfs_get_client(%s,v%u)\n", - cl_init->hostname ?: "", cl_init->rpc_ops->version); + cl_init->hostname ?: "", rpc_ops->version); /* see if the client already exists */ do { @@ -572,27 +494,27 @@ nfs_get_client(const struct nfs_client_initdata *cl_init, if (clp) { spin_unlock(&nn->nfs_client_lock); if (new) - nfs_free_client(new); + new->rpc_ops->free_client(new); return nfs_found_client(cl_init, clp); } if (new) { list_add(&new->cl_share_link, &nn->nfs_client_list); spin_unlock(&nn->nfs_client_lock); new->cl_flags = cl_init->init_flags; - return cl_init->rpc_ops->init_client(new, - timeparms, ip_addr, - authflavour); + return rpc_ops->init_client(new, timeparms, ip_addr, + authflavour); } spin_unlock(&nn->nfs_client_lock); - new = nfs_alloc_client(cl_init); + new = rpc_ops->alloc_client(cl_init); } while (!IS_ERR(new)); dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n", cl_init->hostname ?: "", PTR_ERR(new)); return new; } +EXPORT_SYMBOL_GPL(nfs_get_client); /* * Mark a server as ready or failed @@ -603,11 +525,12 @@ void nfs_mark_client_ready(struct nfs_client *clp, int state) clp->cl_cons_state = state; wake_up_all(&nfs_client_active_wq); } +EXPORT_SYMBOL_GPL(nfs_mark_client_ready); /* * Initialise the timeout values for a connection */ -static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, +void nfs_init_timeout_values(struct rpc_timeout *to, int proto, unsigned int timeo, unsigned int retrans) { to->to_initval = timeo * HZ / 10; @@ -644,13 +567,14 @@ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto, BUG(); } } +EXPORT_SYMBOL_GPL(nfs_init_timeout_values); /* * Create an RPC client handle */ -static int nfs_create_rpc_client(struct nfs_client *clp, - const struct rpc_timeout *timeparms, - rpc_authflavor_t flavor) +int nfs_create_rpc_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, + rpc_authflavor_t flavor) { struct rpc_clnt *clnt = NULL; struct rpc_create_args args = { @@ -683,6 +607,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp, clp->cl_rpcclient = clnt; return 0; } +EXPORT_SYMBOL_GPL(nfs_create_rpc_client); /* * Version 2 or 3 client destruction @@ -735,39 +660,9 @@ static int nfs_start_lockd(struct nfs_server *server) } /* - * Initialise an NFSv3 ACL client connection - */ -#ifdef CONFIG_NFS_V3_ACL -static void nfs_init_server_aclclient(struct nfs_server *server) -{ - if (server->nfs_client->rpc_ops->version != 3) - goto out_noacl; - if (server->flags & NFS_MOUNT_NOACL) - goto out_noacl; - - server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3); - if (IS_ERR(server->client_acl)) - goto out_noacl; - - /* No errors! Assume that Sun nfsacls are supported */ - server->caps |= NFS_CAP_ACLS; - return; - -out_noacl: - server->caps &= ~NFS_CAP_ACLS; -} -#else -static inline void nfs_init_server_aclclient(struct nfs_server *server) -{ - server->flags &= ~NFS_MOUNT_NOACL; - server->caps &= ~NFS_CAP_ACLS; -} -#endif - -/* * Create a general RPC client */ -static int nfs_init_server_rpcclient(struct nfs_server *server, +int nfs_init_server_rpcclient(struct nfs_server *server, const struct rpc_timeout *timeo, rpc_authflavor_t pseudoflavour) { @@ -799,6 +694,7 @@ static int nfs_init_server_rpcclient(struct nfs_server *server, return 0; } +EXPORT_SYMBOL_GPL(nfs_init_server_rpcclient); /** * nfs_init_client - Initialise an NFS2 or NFS3 client @@ -838,18 +734,20 @@ error: dprintk("<-- nfs_init_client() = xerror %d\n", error); return ERR_PTR(error); } +EXPORT_SYMBOL_GPL(nfs_init_client); /* * Create a version 2 or 3 client */ static int nfs_init_server(struct nfs_server *server, - const struct nfs_parsed_mount_data *data) + const struct nfs_parsed_mount_data *data, + struct nfs_subversion *nfs_mod) { struct nfs_client_initdata cl_init = { .hostname = data->nfs_server.hostname, .addr = (const struct sockaddr *)&data->nfs_server.address, .addrlen = data->nfs_server.addrlen, - .rpc_ops = NULL, + .nfs_mod = nfs_mod, .proto = data->nfs_server.protocol, .net = data->net, }; @@ -859,21 +757,6 @@ static int nfs_init_server(struct nfs_server *server, dprintk("--> nfs_init_server()\n"); - switch (data->version) { -#ifdef CONFIG_NFS_V2 - case 2: - cl_init.rpc_ops = &nfs_v2_clientops; - break; -#endif -#ifdef CONFIG_NFS_V3 - case 3: - cl_init.rpc_ops = &nfs_v3_clientops; - break; -#endif - default: - return -EPROTONOSUPPORT; - } - nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, data->timeo, data->retrans); if (data->flags & NFS_MOUNT_NORESVPORT) @@ -927,8 +810,6 @@ static int nfs_init_server(struct nfs_server *server, server->mountd_protocol = data->mount_server.protocol; server->namelen = data->namlen; - /* Create a client RPC handle for the NFSv3 ACL management interface */ - nfs_init_server_aclclient(server); dprintk("<-- nfs_init_server() = 0 [new %p]\n", clp); return 0; @@ -975,7 +856,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, server->wsize = NFS_MAX_FILE_IO_SIZE; server->wpages = (server->wsize + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; server->pnfs_blksize = fsinfo->blksize; - set_pnfs_layoutdriver(server, mntfh, fsinfo->layouttype); server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL); @@ -1001,7 +881,7 @@ static void nfs_server_set_fsinfo(struct nfs_server *server, /* * Probe filesystem information, including the FSID on v2/v3 */ -static int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr) +int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs_fattr *fattr) { struct nfs_fsinfo fsinfo; struct nfs_client *clp = server->nfs_client; @@ -1041,11 +921,12 @@ out_error: dprintk("nfs_probe_fsinfo: error = %d\n", -error); return error; } +EXPORT_SYMBOL_GPL(nfs_probe_fsinfo); /* * Copy useful information when duplicating a server record */ -static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source) +void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *source) { target->flags = source->flags; target->rsize = source->rsize; @@ -1057,8 +938,9 @@ static void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_serve target->caps = source->caps; target->options = source->options; } +EXPORT_SYMBOL_GPL(nfs_server_copy_userdata); -static void nfs_server_insert_lists(struct nfs_server *server) +void nfs_server_insert_lists(struct nfs_server *server) { struct nfs_client *clp = server->nfs_client; struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); @@ -1070,6 +952,7 @@ static void nfs_server_insert_lists(struct nfs_server *server) spin_unlock(&nn->nfs_client_lock); } +EXPORT_SYMBOL_GPL(nfs_server_insert_lists); static void nfs_server_remove_lists(struct nfs_server *server) { @@ -1092,7 +975,7 @@ static void nfs_server_remove_lists(struct nfs_server *server) /* * Allocate and initialise a server record */ -static struct nfs_server *nfs_alloc_server(void) +struct nfs_server *nfs_alloc_server(void) { struct nfs_server *server; @@ -1129,6 +1012,7 @@ static struct nfs_server *nfs_alloc_server(void) return server; } +EXPORT_SYMBOL_GPL(nfs_alloc_server); /* * Free up a server record @@ -1138,7 +1022,6 @@ void nfs_free_server(struct nfs_server *server) dprintk("--> nfs_free_server()\n"); nfs_server_remove_lists(server); - unset_pnfs_layoutdriver(server); if (server->destroy != NULL) server->destroy(server); @@ -1158,13 +1041,14 @@ void nfs_free_server(struct nfs_server *server) nfs_release_automount_timer(); dprintk("<-- nfs_free_server()\n"); } +EXPORT_SYMBOL_GPL(nfs_free_server); /* * Create a version 2 or 3 volume record * - keyed on server and FSID */ -struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data, - struct nfs_fh *mntfh) +struct nfs_server *nfs_create_server(struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) { struct nfs_server *server; struct nfs_fattr *fattr; @@ -1180,7 +1064,7 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data, goto error; /* Get a client representation */ - error = nfs_init_server(server, data); + error = nfs_init_server(server, mount_info->parsed, nfs_mod); if (error < 0) goto error; @@ -1189,13 +1073,13 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data, BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops); /* Probe the root fh to retrieve its FSID */ - error = nfs_probe_fsinfo(server, mntfh, fattr); + error = nfs_probe_fsinfo(server, mount_info->mntfh, fattr); if (error < 0) goto error; if (server->nfs_client->rpc_ops->version == 3) { if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN) server->namelen = NFS3_MAXNAMLEN; - if (!(data->flags & NFS_MOUNT_NORDIRPLUS)) + if (!(mount_info->parsed->flags & NFS_MOUNT_NORDIRPLUS)) server->caps |= NFS_CAP_READDIRPLUS; } else { if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN) @@ -1203,7 +1087,7 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data, } if (!(fattr->valid & NFS_ATTR_FATTR)) { - error = server->nfs_client->rpc_ops->getattr(server, mntfh, fattr); + error = nfs_mod->rpc_ops->getattr(server, mount_info->mntfh, fattr); if (error < 0) { dprintk("nfs_create_server: getattr error = %d\n", -error); goto error; @@ -1225,522 +1109,7 @@ error: nfs_free_server(server); return ERR_PTR(error); } - -#ifdef CONFIG_NFS_V4 -/* - * NFSv4.0 callback thread helper - * - * Find a client by callback identifier - */ -struct nfs_client * -nfs4_find_client_ident(struct net *net, int cb_ident) -{ - struct nfs_client *clp; - struct nfs_net *nn = net_generic(net, nfs_net_id); - - spin_lock(&nn->nfs_client_lock); - clp = idr_find(&nn->cb_ident_idr, cb_ident); - if (clp) - atomic_inc(&clp->cl_count); - spin_unlock(&nn->nfs_client_lock); - return clp; -} - -#if defined(CONFIG_NFS_V4_1) -/* - * NFSv4.1 callback thread helper - * For CB_COMPOUND calls, find a client by IP address, protocol version, - * minorversion, and sessionID - * - * Returns NULL if no such client - */ -struct nfs_client * -nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr, - struct nfs4_sessionid *sid) -{ - struct nfs_client *clp; - struct nfs_net *nn = net_generic(net, nfs_net_id); - - spin_lock(&nn->nfs_client_lock); - list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { - if (nfs4_cb_match_client(addr, clp, 1) == false) - continue; - - if (!nfs4_has_session(clp)) - continue; - - /* Match sessionid*/ - if (memcmp(clp->cl_session->sess_id.data, - sid->data, NFS4_MAX_SESSIONID_LEN) != 0) - continue; - - atomic_inc(&clp->cl_count); - spin_unlock(&nn->nfs_client_lock); - return clp; - } - spin_unlock(&nn->nfs_client_lock); - return NULL; -} - -#else /* CONFIG_NFS_V4_1 */ - -struct nfs_client * -nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr, - struct nfs4_sessionid *sid) -{ - return NULL; -} -#endif /* CONFIG_NFS_V4_1 */ - -/* - * Initialize the NFS4 callback service - */ -static int nfs4_init_callback(struct nfs_client *clp) -{ - int error; - - if (clp->rpc_ops->version == 4) { - struct rpc_xprt *xprt; - - xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt); - - if (nfs4_has_session(clp)) { - error = xprt_setup_backchannel(xprt, - NFS41_BC_MIN_CALLBACKS); - if (error < 0) - return error; - } - - error = nfs_callback_up(clp->cl_mvops->minor_version, xprt); - if (error < 0) { - dprintk("%s: failed to start callback. Error = %d\n", - __func__, error); - return error; - } - __set_bit(NFS_CS_CALLBACK, &clp->cl_res_state); - } - return 0; -} - -/* - * Initialize the minor version specific parts of an NFS4 client record - */ -static int nfs4_init_client_minor_version(struct nfs_client *clp) -{ -#if defined(CONFIG_NFS_V4_1) - if (clp->cl_mvops->minor_version) { - struct nfs4_session *session = NULL; - /* - * Create the session and mark it expired. - * When a SEQUENCE operation encounters the expired session - * it will do session recovery to initialize it. - */ - session = nfs4_alloc_session(clp); - if (!session) - return -ENOMEM; - - clp->cl_session = session; - /* - * The create session reply races with the server back - * channel probe. Mark the client NFS_CS_SESSION_INITING - * so that the client back channel can find the - * nfs_client struct - */ - nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING); - } -#endif /* CONFIG_NFS_V4_1 */ - - return nfs4_init_callback(clp); -} - -/** - * nfs4_init_client - Initialise an NFS4 client record - * - * @clp: nfs_client to initialise - * @timeparms: timeout parameters for underlying RPC transport - * @ip_addr: callback IP address in presentation format - * @authflavor: authentication flavor for underlying RPC transport - * - * Returns pointer to an NFS client, or an ERR_PTR value. - */ -struct nfs_client *nfs4_init_client(struct nfs_client *clp, - const struct rpc_timeout *timeparms, - const char *ip_addr, - rpc_authflavor_t authflavour) -{ - char buf[INET6_ADDRSTRLEN + 1]; - int error; - - if (clp->cl_cons_state == NFS_CS_READY) { - /* the client is initialised already */ - dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp); - return clp; - } - - /* Check NFS protocol revision and initialize RPC op vector */ - clp->rpc_ops = &nfs_v4_clientops; - - __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); - error = nfs_create_rpc_client(clp, timeparms, authflavour); - if (error < 0) - goto error; - - /* If no clientaddr= option was specified, find a usable cb address */ - if (ip_addr == NULL) { - struct sockaddr_storage cb_addr; - struct sockaddr *sap = (struct sockaddr *)&cb_addr; - - error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr)); - if (error < 0) - goto error; - error = rpc_ntop(sap, buf, sizeof(buf)); - if (error < 0) - goto error; - ip_addr = (const char *)buf; - } - strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr)); - - error = nfs_idmap_new(clp); - if (error < 0) { - dprintk("%s: failed to create idmapper. Error = %d\n", - __func__, error); - goto error; - } - __set_bit(NFS_CS_IDMAP, &clp->cl_res_state); - - error = nfs4_init_client_minor_version(clp); - if (error < 0) - goto error; - - if (!nfs4_has_session(clp)) - nfs_mark_client_ready(clp, NFS_CS_READY); - return clp; - -error: - nfs_mark_client_ready(clp, error); - nfs_put_client(clp); - dprintk("<-- nfs4_init_client() = xerror %d\n", error); - return ERR_PTR(error); -} - -/* - * Set up an NFS4 client - */ -static int nfs4_set_client(struct nfs_server *server, - const char *hostname, - const struct sockaddr *addr, - const size_t addrlen, - const char *ip_addr, - rpc_authflavor_t authflavour, - int proto, const struct rpc_timeout *timeparms, - u32 minorversion, struct net *net) -{ - struct nfs_client_initdata cl_init = { - .hostname = hostname, - .addr = addr, - .addrlen = addrlen, - .rpc_ops = &nfs_v4_clientops, - .proto = proto, - .minorversion = minorversion, - .net = net, - }; - struct nfs_client *clp; - int error; - - dprintk("--> nfs4_set_client()\n"); - - if (server->flags & NFS_MOUNT_NORESVPORT) - set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); - - /* Allocate or find a client reference we can use */ - clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour); - if (IS_ERR(clp)) { - error = PTR_ERR(clp); - goto error; - } - - /* - * Query for the lease time on clientid setup or renewal - * - * Note that this will be set on nfs_clients that were created - * only for the DS role and did not set this bit, but now will - * serve a dual role. - */ - set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state); - - server->nfs_client = clp; - dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp); - return 0; -error: - dprintk("<-- nfs4_set_client() = xerror %d\n", error); - return error; -} - -/* - * Set up a pNFS Data Server client. - * - * Return any existing nfs_client that matches server address,port,version - * and minorversion. - * - * For a new nfs_client, use a soft mount (default), a low retrans and a - * low timeout interval so that if a connection is lost, we retry through - * the MDS. - */ -struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, - const struct sockaddr *ds_addr, int ds_addrlen, - int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans) -{ - struct nfs_client_initdata cl_init = { - .addr = ds_addr, - .addrlen = ds_addrlen, - .rpc_ops = &nfs_v4_clientops, - .proto = ds_proto, - .minorversion = mds_clp->cl_minorversion, - .net = mds_clp->cl_net, - }; - struct rpc_timeout ds_timeout; - struct nfs_client *clp; - - /* - * Set an authflavor equual to the MDS value. Use the MDS nfs_client - * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS - * (section 13.1 RFC 5661). - */ - nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); - clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr, - mds_clp->cl_rpcclient->cl_auth->au_flavor); - - dprintk("<-- %s %p\n", __func__, clp); - return clp; -} -EXPORT_SYMBOL_GPL(nfs4_set_ds_client); - -/* - * Session has been established, and the client marked ready. - * Set the mount rsize and wsize with negotiated fore channel - * attributes which will be bound checked in nfs_server_set_fsinfo. - */ -static void nfs4_session_set_rwsize(struct nfs_server *server) -{ -#ifdef CONFIG_NFS_V4_1 - struct nfs4_session *sess; - u32 server_resp_sz; - u32 server_rqst_sz; - - if (!nfs4_has_session(server->nfs_client)) - return; - sess = server->nfs_client->cl_session; - server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead; - server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead; - - if (server->rsize > server_resp_sz) - server->rsize = server_resp_sz; - if (server->wsize > server_rqst_sz) - server->wsize = server_rqst_sz; -#endif /* CONFIG_NFS_V4_1 */ -} - -static int nfs4_server_common_setup(struct nfs_server *server, - struct nfs_fh *mntfh) -{ - struct nfs_fattr *fattr; - int error; - - BUG_ON(!server->nfs_client); - BUG_ON(!server->nfs_client->rpc_ops); - BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops); - - /* data servers support only a subset of NFSv4.1 */ - if (is_ds_only_client(server->nfs_client)) - return -EPROTONOSUPPORT; - - fattr = nfs_alloc_fattr(); - if (fattr == NULL) - return -ENOMEM; - - /* We must ensure the session is initialised first */ - error = nfs4_init_session(server); - if (error < 0) - goto out; - - /* Probe the root fh to retrieve its FSID and filehandle */ - error = nfs4_get_rootfh(server, mntfh); - if (error < 0) - goto out; - - dprintk("Server FSID: %llx:%llx\n", - (unsigned long long) server->fsid.major, - (unsigned long long) server->fsid.minor); - dprintk("Mount FH: %d\n", mntfh->size); - - nfs4_session_set_rwsize(server); - - error = nfs_probe_fsinfo(server, mntfh, fattr); - if (error < 0) - goto out; - - if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN) - server->namelen = NFS4_MAXNAMLEN; - - nfs_server_insert_lists(server); - server->mount_time = jiffies; - server->destroy = nfs4_destroy_server; -out: - nfs_free_fattr(fattr); - return error; -} - -/* - * Create a version 4 volume record - */ -static int nfs4_init_server(struct nfs_server *server, - const struct nfs_parsed_mount_data *data) -{ - struct rpc_timeout timeparms; - int error; - - dprintk("--> nfs4_init_server()\n"); - - nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, - data->timeo, data->retrans); - - /* 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; - if (!(data->flags & NFS_MOUNT_NORDIRPLUS)) - server->caps |= NFS_CAP_READDIRPLUS; - server->options = data->options; - - /* Get a client record */ - error = nfs4_set_client(server, - data->nfs_server.hostname, - (const struct sockaddr *)&data->nfs_server.address, - data->nfs_server.addrlen, - data->client_address, - data->auth_flavors[0], - data->nfs_server.protocol, - &timeparms, - data->minorversion, - data->net); - if (error < 0) - goto error; - - /* - * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower - * authentication. - */ - if (nfs4_disable_idmapping && data->auth_flavors[0] == RPC_AUTH_UNIX) - server->caps |= NFS_CAP_UIDGID_NOMAP; - - if (data->rsize) - server->rsize = nfs_block_size(data->rsize, NULL); - if (data->wsize) - server->wsize = nfs_block_size(data->wsize, NULL); - - server->acregmin = data->acregmin * HZ; - server->acregmax = data->acregmax * HZ; - server->acdirmin = data->acdirmin * HZ; - server->acdirmax = data->acdirmax * HZ; - - server->port = data->nfs_server.port; - - error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]); - -error: - /* Done */ - dprintk("<-- nfs4_init_server() = %d\n", error); - return error; -} - -/* - * Create a version 4 volume record - * - keyed on server and FSID - */ -struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data, - struct nfs_fh *mntfh) -{ - struct nfs_server *server; - int error; - - dprintk("--> nfs4_create_server()\n"); - - server = nfs_alloc_server(); - if (!server) - return ERR_PTR(-ENOMEM); - - /* set up the general RPC client */ - error = nfs4_init_server(server, data); - if (error < 0) - goto error; - - error = nfs4_server_common_setup(server, mntfh); - if (error < 0) - goto error; - - dprintk("<-- nfs4_create_server() = %p\n", server); - return server; - -error: - nfs_free_server(server); - dprintk("<-- nfs4_create_server() = error %d\n", error); - return ERR_PTR(error); -} - -/* - * Create an NFS4 referral server record - */ -struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, - struct nfs_fh *mntfh) -{ - struct nfs_client *parent_client; - struct nfs_server *server, *parent_server; - int error; - - dprintk("--> nfs4_create_referral_server()\n"); - - server = nfs_alloc_server(); - if (!server) - return ERR_PTR(-ENOMEM); - - parent_server = NFS_SB(data->sb); - parent_client = parent_server->nfs_client; - - /* Initialise the client representation from the parent server */ - nfs_server_copy_userdata(server, parent_server); - server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR; - - /* Get a client representation. - * Note: NFSv4 always uses TCP, */ - error = nfs4_set_client(server, data->hostname, - data->addr, - data->addrlen, - parent_client->cl_ipaddr, - data->authflavor, - rpc_protocol(parent_server->client), - parent_server->client->cl_timeout, - parent_client->cl_mvops->minor_version, - parent_client->cl_net); - if (error < 0) - goto error; - - error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor); - if (error < 0) - goto error; - - error = nfs4_server_common_setup(server, mntfh); - if (error < 0) - goto error; - - dprintk("<-- nfs_create_referral_server() = %p\n", server); - return server; - -error: - nfs_free_server(server); - dprintk("<-- nfs4_create_referral_server() = error %d\n", error); - return ERR_PTR(error); -} - -#endif /* CONFIG_NFS_V4 */ +EXPORT_SYMBOL_GPL(nfs_create_server); /* * Clone an NFS2, NFS3 or NFS4 server record @@ -1780,8 +1149,6 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source, flavor); if (error < 0) goto out_free_server; - if (!IS_ERR(source->client_acl)) - nfs_init_server_aclclient(server); /* probe the filesystem info for this server filesystem */ error = nfs_probe_fsinfo(server, fh, fattr_fsinfo); @@ -1812,6 +1179,7 @@ out_free_server: dprintk("<-- nfs_clone_server() = error %d\n", error); return ERR_PTR(error); } +EXPORT_SYMBOL_GPL(nfs_clone_server); void nfs_clients_init(struct net *net) { @@ -1819,7 +1187,7 @@ void nfs_clients_init(struct net *net) INIT_LIST_HEAD(&nn->nfs_client_list); INIT_LIST_HEAD(&nn->nfs_volume_list); -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) idr_init(&nn->cb_ident_idr); #endif spin_lock_init(&nn->nfs_client_lock); @@ -2091,7 +1459,3 @@ void nfs_fs_proc_exit(void) } #endif /* CONFIG_PROC_FS */ - -module_param(nfs4_disable_idmapping, bool, 0644); -MODULE_PARM_DESC(nfs4_disable_idmapping, - "Turn off NFSv4 idmapping when using 'sec=sys'"); diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c index bd3a960..81c5eec 100644 --- a/fs/nfs/delegation.c +++ b/fs/nfs/delegation.c @@ -47,7 +47,7 @@ void nfs_mark_delegation_referenced(struct nfs_delegation *delegation) * * Returns one if inode has the indicated delegation, otherwise zero. */ -int nfs_have_delegation(struct inode *inode, fmode_t flags) +int nfs4_have_delegation(struct inode *inode, fmode_t flags) { struct nfs_delegation *delegation; int ret = 0; @@ -388,7 +388,7 @@ void nfs_inode_return_delegation_noreclaim(struct inode *inode) * * Returns zero on success, or a negative errno value. */ -int nfs_inode_return_delegation(struct inode *inode) +int nfs4_inode_return_delegation(struct inode *inode) { struct nfs_server *server = NFS_SERVER(inode); struct nfs_inode *nfsi = NFS_I(inode); @@ -417,9 +417,8 @@ static void nfs_mark_return_delegation(struct nfs_server *server, * @sb: sb to process * */ -void nfs_super_return_all_delegations(struct super_block *sb) +void nfs_server_return_all_delegations(struct nfs_server *server) { - struct nfs_server *server = NFS_SB(sb); struct nfs_client *clp = server->nfs_client; struct nfs_delegation *delegation; diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h index 72709c4..bbc6a4d 100644 --- a/fs/nfs/delegation.h +++ b/fs/nfs/delegation.h @@ -8,7 +8,7 @@ #ifndef FS_NFS_DELEGATION_H #define FS_NFS_DELEGATION_H -#if defined(CONFIG_NFS_V4) +#if IS_ENABLED(CONFIG_NFS_V4) /* * NFSv4 delegation */ @@ -33,12 +33,12 @@ enum { int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, struct nfs_openres *res); -int nfs_inode_return_delegation(struct inode *inode); +int nfs4_inode_return_delegation(struct inode *inode); int nfs_async_inode_return_delegation(struct inode *inode, const nfs4_stateid *stateid); void nfs_inode_return_delegation_noreclaim(struct inode *inode); struct inode *nfs_delegation_find_inode(struct nfs_client *clp, const struct nfs_fh *fhandle); -void nfs_super_return_all_delegations(struct super_block *sb); +void nfs_server_return_all_delegations(struct nfs_server *); void nfs_expire_all_delegations(struct nfs_client *clp); void nfs_expire_all_delegation_types(struct nfs_client *clp, fmode_t flags); void nfs_expire_unreferenced_delegations(struct nfs_client *clp); @@ -56,24 +56,13 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl); bool nfs4_copy_delegation_stateid(nfs4_stateid *dst, struct inode *inode, fmode_t flags); void nfs_mark_delegation_referenced(struct nfs_delegation *delegation); -int nfs_have_delegation(struct inode *inode, fmode_t flags); +int nfs4_have_delegation(struct inode *inode, fmode_t flags); -#else -static inline int nfs_have_delegation(struct inode *inode, fmode_t flags) -{ - return 0; -} - -static inline int nfs_inode_return_delegation(struct inode *inode) -{ - nfs_wb_all(inode); - return 0; -} #endif static inline int nfs_have_delegated_attributes(struct inode *inode) { - return nfs_have_delegation(inode, FMODE_READ) && + return NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) && !(NFS_I(inode)->cache_validity & NFS_INO_REVAL_FORCED); } diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index a6b1c7f..627f108 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -17,6 +17,7 @@ * 6 Jun 1999 Cache readdir lookups in the page cache. -DaveM */ +#include <linux/module.h> #include <linux/time.h> #include <linux/errno.h> #include <linux/stat.h> @@ -46,16 +47,6 @@ static int nfs_opendir(struct inode *, struct file *); static int nfs_closedir(struct inode *, struct file *); static int nfs_readdir(struct file *, void *, filldir_t); -static struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); -static int nfs_create(struct inode *, struct dentry *, umode_t, bool); -static int nfs_mkdir(struct inode *, struct dentry *, umode_t); -static int nfs_rmdir(struct inode *, struct dentry *); -static int nfs_unlink(struct inode *, struct dentry *); -static int nfs_symlink(struct inode *, struct dentry *, const char *); -static int nfs_link(struct dentry *, struct inode *, struct dentry *); -static int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); -static int nfs_rename(struct inode *, struct dentry *, - struct inode *, struct dentry *); static int nfs_fsync_dir(struct file *, loff_t, loff_t, int); static loff_t nfs_llseek_dir(struct file *, loff_t, int); static void nfs_readdir_clear_array(struct page*); @@ -69,73 +60,10 @@ const struct file_operations nfs_dir_operations = { .fsync = nfs_fsync_dir, }; -const struct inode_operations nfs_dir_inode_operations = { - .create = nfs_create, - .lookup = nfs_lookup, - .link = nfs_link, - .unlink = nfs_unlink, - .symlink = nfs_symlink, - .mkdir = nfs_mkdir, - .rmdir = nfs_rmdir, - .mknod = nfs_mknod, - .rename = nfs_rename, - .permission = nfs_permission, - .getattr = nfs_getattr, - .setattr = nfs_setattr, -}; - const struct address_space_operations nfs_dir_aops = { .freepage = nfs_readdir_clear_array, }; -#ifdef CONFIG_NFS_V3 -const struct inode_operations nfs3_dir_inode_operations = { - .create = nfs_create, - .lookup = nfs_lookup, - .link = nfs_link, - .unlink = nfs_unlink, - .symlink = nfs_symlink, - .mkdir = nfs_mkdir, - .rmdir = nfs_rmdir, - .mknod = nfs_mknod, - .rename = nfs_rename, - .permission = nfs_permission, - .getattr = nfs_getattr, - .setattr = nfs_setattr, - .listxattr = nfs3_listxattr, - .getxattr = nfs3_getxattr, - .setxattr = nfs3_setxattr, - .removexattr = nfs3_removexattr, -}; -#endif /* CONFIG_NFS_V3 */ - -#ifdef CONFIG_NFS_V4 - -static int nfs_atomic_open(struct inode *, struct dentry *, - struct file *, unsigned, umode_t, - int *); -const struct inode_operations nfs4_dir_inode_operations = { - .create = nfs_create, - .lookup = nfs_lookup, - .atomic_open = nfs_atomic_open, - .link = nfs_link, - .unlink = nfs_unlink, - .symlink = nfs_symlink, - .mkdir = nfs_mkdir, - .rmdir = nfs_rmdir, - .mknod = nfs_mknod, - .rename = nfs_rename, - .permission = nfs_permission, - .getattr = nfs_getattr, - .setattr = nfs_setattr, - .getxattr = generic_getxattr, - .setxattr = generic_setxattr, - .listxattr = generic_listxattr, - .removexattr = generic_removexattr, -}; - -#endif /* CONFIG_NFS_V4 */ - static struct nfs_open_dir_context *alloc_nfs_open_dir_context(struct inode *dir, struct rpc_cred *cred) { struct nfs_open_dir_context *ctx; @@ -1008,6 +936,7 @@ void nfs_force_lookup_revalidate(struct inode *dir) { NFS_I(dir)->cache_change_attribute++; } +EXPORT_SYMBOL_GPL(nfs_force_lookup_revalidate); /* * A check for whether or not the parent directory has changed. @@ -1128,7 +1057,7 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags) goto out_bad; } - if (nfs_have_delegation(inode, FMODE_READ)) + if (NFS_PROTO(dir)->have_delegation(inode, FMODE_READ)) goto out_set_verifier; /* Force a full look up iff the parent directory has changed */ @@ -1269,8 +1198,9 @@ const struct dentry_operations nfs_dentry_operations = { .d_automount = nfs_d_automount, .d_release = nfs_d_release, }; +EXPORT_SYMBOL_GPL(nfs_dentry_operations); -static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) +struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, unsigned int flags) { struct dentry *res; struct dentry *parent; @@ -1336,8 +1266,9 @@ out: nfs_free_fhandle(fhandle); return res; } +EXPORT_SYMBOL_GPL(nfs_lookup); -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) static int nfs4_lookup_revalidate(struct dentry *, unsigned int); const struct dentry_operations nfs4_dentry_operations = { @@ -1347,6 +1278,7 @@ const struct dentry_operations nfs4_dentry_operations = { .d_automount = nfs_d_automount, .d_release = nfs_d_release, }; +EXPORT_SYMBOL_GPL(nfs4_dentry_operations); static fmode_t flags_to_mode(int flags) { @@ -1398,9 +1330,9 @@ out: return err; } -static int nfs_atomic_open(struct inode *dir, struct dentry *dentry, - struct file *file, unsigned open_flags, - umode_t mode, int *opened) +int nfs_atomic_open(struct inode *dir, struct dentry *dentry, + struct file *file, unsigned open_flags, + umode_t mode, int *opened) { struct nfs_open_context *ctx; struct dentry *res; @@ -1489,6 +1421,7 @@ no_open: return finish_no_open(file, res); } +EXPORT_SYMBOL_GPL(nfs_atomic_open); static int nfs4_lookup_revalidate(struct dentry *dentry, unsigned int flags) { @@ -1581,6 +1514,7 @@ out_error: dput(parent); return error; } +EXPORT_SYMBOL_GPL(nfs_instantiate); /* * Following a failed create operation, we drop the dentry rather @@ -1588,7 +1522,7 @@ out_error: * that the operation succeeded on the server, but an error in the * reply path made it appear to have failed. */ -static int nfs_create(struct inode *dir, struct dentry *dentry, +int nfs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { struct iattr attr; @@ -1609,11 +1543,12 @@ out_err: d_drop(dentry); return error; } +EXPORT_SYMBOL_GPL(nfs_create); /* * See comments for nfs_proc_create regarding failed operations. */ -static int +int nfs_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t rdev) { struct iattr attr; @@ -1636,11 +1571,12 @@ out_err: d_drop(dentry); return status; } +EXPORT_SYMBOL_GPL(nfs_mknod); /* * See comments for nfs_proc_create regarding failed operations. */ -static int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) +int nfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { struct iattr attr; int error; @@ -1659,6 +1595,7 @@ out_err: d_drop(dentry); return error; } +EXPORT_SYMBOL_GPL(nfs_mkdir); static void nfs_dentry_handle_enoent(struct dentry *dentry) { @@ -1666,7 +1603,7 @@ static void nfs_dentry_handle_enoent(struct dentry *dentry) d_delete(dentry); } -static int nfs_rmdir(struct inode *dir, struct dentry *dentry) +int nfs_rmdir(struct inode *dir, struct dentry *dentry) { int error; @@ -1682,6 +1619,7 @@ static int nfs_rmdir(struct inode *dir, struct dentry *dentry) return error; } +EXPORT_SYMBOL_GPL(nfs_rmdir); /* * Remove a file after making sure there are no pending writes, @@ -1706,7 +1644,7 @@ static int nfs_safe_remove(struct dentry *dentry) } if (inode != NULL) { - nfs_inode_return_delegation(inode); + NFS_PROTO(inode)->return_delegation(inode); error = NFS_PROTO(dir)->remove(dir, &dentry->d_name); /* The VFS may want to delete this inode */ if (error == 0) @@ -1725,7 +1663,7 @@ out: * * If sillyrename() returns 0, we do nothing, otherwise we unlink. */ -static int nfs_unlink(struct inode *dir, struct dentry *dentry) +int nfs_unlink(struct inode *dir, struct dentry *dentry) { int error; int need_rehash = 0; @@ -1753,6 +1691,7 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry) d_rehash(dentry); return error; } +EXPORT_SYMBOL_GPL(nfs_unlink); /* * To create a symbolic link, most file systems instantiate a new inode, @@ -1769,7 +1708,7 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry) * now have a new file handle and can instantiate an in-core NFS inode * and move the raw page into its mapping. */ -static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) +int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *symname) { struct pagevec lru_pvec; struct page *page; @@ -1823,8 +1762,9 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym return 0; } +EXPORT_SYMBOL_GPL(nfs_symlink); -static int +int nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { struct inode *inode = old_dentry->d_inode; @@ -1834,7 +1774,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) old_dentry->d_parent->d_name.name, old_dentry->d_name.name, dentry->d_parent->d_name.name, dentry->d_name.name); - nfs_inode_return_delegation(inode); + NFS_PROTO(inode)->return_delegation(inode); d_drop(dentry); error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name); @@ -1844,6 +1784,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) } return error; } +EXPORT_SYMBOL_GPL(nfs_link); /* * RENAME @@ -1869,7 +1810,7 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) * If these conditions are met, we can drop the dentries before doing * the rename. */ -static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, +int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry) { struct inode *old_inode = old_dentry->d_inode; @@ -1918,9 +1859,9 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry, } } - nfs_inode_return_delegation(old_inode); + NFS_PROTO(old_inode)->return_delegation(old_inode); if (new_inode != NULL) - nfs_inode_return_delegation(new_inode); + NFS_PROTO(new_inode)->return_delegation(new_inode); error = NFS_PROTO(old_dir)->rename(old_dir, &old_dentry->d_name, new_dir, &new_dentry->d_name); @@ -1942,6 +1883,7 @@ out: dput(dentry); return error; } +EXPORT_SYMBOL_GPL(nfs_rename); static DEFINE_SPINLOCK(nfs_access_lru_lock); static LIST_HEAD(nfs_access_lru_list); @@ -2042,6 +1984,7 @@ void nfs_access_zap_cache(struct inode *inode) spin_unlock(&nfs_access_lru_lock); nfs_access_free_list(&head); } +EXPORT_SYMBOL_GPL(nfs_access_zap_cache); static struct nfs_access_entry *nfs_access_search_rbtree(struct inode *inode, struct rpc_cred *cred) { @@ -2202,6 +2145,7 @@ int nfs_may_open(struct inode *inode, struct rpc_cred *cred, int openflags) { return nfs_do_access(inode, cred, nfs_open_permission_mask(openflags)); } +EXPORT_SYMBOL_GPL(nfs_may_open); int nfs_permission(struct inode *inode, int mask) { @@ -2261,6 +2205,7 @@ out_notsup: res = generic_permission(inode, mask); goto out; } +EXPORT_SYMBOL_GPL(nfs_permission); /* * Local variables: diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c index 4825337..1ba385b 100644 --- a/fs/nfs/direct.c +++ b/fs/nfs/direct.c @@ -115,17 +115,28 @@ static inline int put_dreq(struct nfs_direct_req *dreq) * @nr_segs: size of iovec array * * The presence of this routine in the address space ops vector means - * the NFS client supports direct I/O. However, we shunt off direct - * read and write requests before the VFS gets them, so this method - * should never be called. + * the NFS client supports direct I/O. However, for most direct IO, we + * shunt off direct read and write requests before the VFS gets them, + * so this method is only ever called for swap. */ ssize_t nfs_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs) { +#ifndef CONFIG_NFS_SWAP dprintk("NFS: nfs_direct_IO (%s) off/no(%Ld/%lu) EINVAL\n", iocb->ki_filp->f_path.dentry->d_name.name, (long long) pos, nr_segs); return -EINVAL; +#else + VM_BUG_ON(iocb->ki_left != PAGE_SIZE); + VM_BUG_ON(iocb->ki_nbytes != PAGE_SIZE); + + if (rw == READ || rw == KERNEL_READ) + return nfs_file_direct_read(iocb, iov, nr_segs, pos, + rw == READ ? true : false); + return nfs_file_direct_write(iocb, iov, nr_segs, pos, + rw == WRITE ? true : false); +#endif /* CONFIG_NFS_SWAP */ } static void nfs_direct_release_pages(struct page **pages, unsigned int npages) @@ -303,7 +314,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_read_completion_ops = { */ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *desc, const struct iovec *iov, - loff_t pos) + loff_t pos, bool uio) { struct nfs_direct_req *dreq = desc->pg_dreq; struct nfs_open_context *ctx = dreq->ctx; @@ -331,12 +342,20 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de GFP_KERNEL); if (!pagevec) break; - down_read(¤t->mm->mmap_sem); - result = get_user_pages(current, current->mm, user_addr, + if (uio) { + down_read(¤t->mm->mmap_sem); + result = get_user_pages(current, current->mm, user_addr, npages, 1, 0, pagevec, NULL); - up_read(¤t->mm->mmap_sem); - if (result < 0) - break; + up_read(¤t->mm->mmap_sem); + if (result < 0) + break; + } else { + WARN_ON(npages != 1); + result = get_kernel_page(user_addr, 1, pagevec); + if (WARN_ON(result != 1)) + break; + } + if ((unsigned)result < npages) { bytes = result * PAGE_SIZE; if (bytes <= pgbase) { @@ -386,21 +405,21 @@ static ssize_t nfs_direct_read_schedule_segment(struct nfs_pageio_descriptor *de static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, const struct iovec *iov, unsigned long nr_segs, - loff_t pos) + loff_t pos, bool uio) { struct nfs_pageio_descriptor desc; ssize_t result = -EINVAL; size_t requested_bytes = 0; unsigned long seg; - nfs_pageio_init_read(&desc, dreq->inode, + NFS_PROTO(dreq->inode)->read_pageio_init(&desc, dreq->inode, &nfs_direct_read_completion_ops); get_dreq(dreq); desc.pg_dreq = dreq; for (seg = 0; seg < nr_segs; seg++) { const struct iovec *vec = &iov[seg]; - result = nfs_direct_read_schedule_segment(&desc, vec, pos); + result = nfs_direct_read_schedule_segment(&desc, vec, pos, uio); if (result < 0) break; requested_bytes += result; @@ -426,7 +445,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq, } static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) + unsigned long nr_segs, loff_t pos, bool uio) { ssize_t result = -ENOMEM; struct inode *inode = iocb->ki_filp->f_mapping->host; @@ -444,7 +463,7 @@ static ssize_t nfs_direct_read(struct kiocb *iocb, const struct iovec *iov, if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; - result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos); + result = nfs_direct_read_schedule_iovec(dreq, iov, nr_segs, pos, uio); if (!result) result = nfs_direct_wait(dreq); NFS_I(inode)->read_io += result; @@ -460,7 +479,7 @@ static void nfs_inode_dio_write_done(struct inode *inode) inode_dio_done(inode); } -#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) +#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) { struct nfs_pageio_descriptor desc; @@ -478,7 +497,7 @@ static void nfs_direct_write_reschedule(struct nfs_direct_req *dreq) dreq->count = 0; get_dreq(dreq); - nfs_pageio_init_write(&desc, dreq->inode, FLUSH_STABLE, + NFS_PROTO(dreq->inode)->write_pageio_init(&desc, dreq->inode, FLUSH_STABLE, &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; @@ -610,7 +629,7 @@ static void nfs_direct_write_complete(struct nfs_direct_req *dreq, struct inode */ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *desc, const struct iovec *iov, - loff_t pos) + loff_t pos, bool uio) { struct nfs_direct_req *dreq = desc->pg_dreq; struct nfs_open_context *ctx = dreq->ctx; @@ -638,12 +657,19 @@ static ssize_t nfs_direct_write_schedule_segment(struct nfs_pageio_descriptor *d if (!pagevec) break; - down_read(¤t->mm->mmap_sem); - result = get_user_pages(current, current->mm, user_addr, - npages, 0, 0, pagevec, NULL); - up_read(¤t->mm->mmap_sem); - if (result < 0) - break; + if (uio) { + down_read(¤t->mm->mmap_sem); + result = get_user_pages(current, current->mm, user_addr, + npages, 0, 0, pagevec, NULL); + up_read(¤t->mm->mmap_sem); + if (result < 0) + break; + } else { + WARN_ON(npages != 1); + result = get_kernel_page(user_addr, 0, pagevec); + if (WARN_ON(result != 1)) + break; + } if ((unsigned)result < npages) { bytes = result * PAGE_SIZE; @@ -774,7 +800,7 @@ static const struct nfs_pgio_completion_ops nfs_direct_write_completion_ops = { static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, const struct iovec *iov, unsigned long nr_segs, - loff_t pos) + loff_t pos, bool uio) { struct nfs_pageio_descriptor desc; struct inode *inode = dreq->inode; @@ -782,7 +808,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, size_t requested_bytes = 0; unsigned long seg; - nfs_pageio_init_write(&desc, inode, FLUSH_COND_STABLE, + NFS_PROTO(inode)->write_pageio_init(&desc, inode, FLUSH_COND_STABLE, &nfs_direct_write_completion_ops); desc.pg_dreq = dreq; get_dreq(dreq); @@ -790,7 +816,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, for (seg = 0; seg < nr_segs; seg++) { const struct iovec *vec = &iov[seg]; - result = nfs_direct_write_schedule_segment(&desc, vec, pos); + result = nfs_direct_write_schedule_segment(&desc, vec, pos, uio); if (result < 0) break; requested_bytes += result; @@ -818,7 +844,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq, static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos, - size_t count) + size_t count, bool uio) { ssize_t result = -ENOMEM; struct inode *inode = iocb->ki_filp->f_mapping->host; @@ -836,7 +862,7 @@ static ssize_t nfs_direct_write(struct kiocb *iocb, const struct iovec *iov, if (!is_sync_kiocb(iocb)) dreq->iocb = iocb; - result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos); + result = nfs_direct_write_schedule_iovec(dreq, iov, nr_segs, pos, uio); if (!result) result = nfs_direct_wait(dreq); out_release: @@ -867,7 +893,7 @@ out: * cache. */ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) + unsigned long nr_segs, loff_t pos, bool uio) { ssize_t retval = -EINVAL; struct file *file = iocb->ki_filp; @@ -892,7 +918,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov, task_io_account_read(count); - retval = nfs_direct_read(iocb, iov, nr_segs, pos); + retval = nfs_direct_read(iocb, iov, nr_segs, pos, uio); if (retval > 0) iocb->ki_pos = pos + retval; @@ -923,7 +949,7 @@ out: * is no atomic O_APPEND write facility in the NFS protocol. */ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) + unsigned long nr_segs, loff_t pos, bool uio) { ssize_t retval = -EINVAL; struct file *file = iocb->ki_filp; @@ -955,7 +981,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov, task_io_account_write(count); - retval = nfs_direct_write(iocb, iov, nr_segs, pos, count); + retval = nfs_direct_write(iocb, iov, nr_segs, pos, count, uio); if (retval > 0) { struct inode *inode = mapping->host; diff --git a/fs/nfs/dns_resolve.c b/fs/nfs/dns_resolve.c index b3924b8..31c26c4 100644 --- a/fs/nfs/dns_resolve.c +++ b/fs/nfs/dns_resolve.c @@ -8,6 +8,7 @@ #ifdef CONFIG_NFS_USE_KERNEL_DNS +#include <linux/module.h> #include <linux/sunrpc/clnt.h> #include <linux/dns_resolver.h> #include "dns_resolve.h" @@ -27,9 +28,11 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, size_t namelen, kfree(ip_addr); return ret; } +EXPORT_SYMBOL_GPL(nfs_dns_resolve_name); #else +#include <linux/module.h> #include <linux/hash.h> #include <linux/string.h> #include <linux/kmod.h> @@ -345,6 +348,7 @@ ssize_t nfs_dns_resolve_name(struct net *net, char *name, ret = -ESRCH; return ret; } +EXPORT_SYMBOL_GPL(nfs_dns_resolve_name); int nfs_dns_resolver_cache_init(struct net *net) { diff --git a/fs/nfs/file.c b/fs/nfs/file.c index a6708e6b..6a7fcab 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -16,6 +16,7 @@ * nfs regular file handling functions */ +#include <linux/module.h> #include <linux/time.h> #include <linux/kernel.h> #include <linux/errno.h> @@ -35,42 +36,24 @@ #include "internal.h" #include "iostat.h" #include "fscache.h" -#include "pnfs.h" #define NFSDBG_FACILITY NFSDBG_FILE static const struct vm_operations_struct nfs_file_vm_ops; -const struct inode_operations nfs_file_inode_operations = { - .permission = nfs_permission, - .getattr = nfs_getattr, - .setattr = nfs_setattr, -}; - -#ifdef CONFIG_NFS_V3 -const struct inode_operations nfs3_file_inode_operations = { - .permission = nfs_permission, - .getattr = nfs_getattr, - .setattr = nfs_setattr, - .listxattr = nfs3_listxattr, - .getxattr = nfs3_getxattr, - .setxattr = nfs3_setxattr, - .removexattr = nfs3_removexattr, -}; -#endif /* CONFIG_NFS_v3 */ - /* Hack for future NFS swap support */ #ifndef IS_SWAPFILE # define IS_SWAPFILE(inode) (0) #endif -static int nfs_check_flags(int flags) +int nfs_check_flags(int flags) { if ((flags & (O_APPEND | O_DIRECT)) == (O_APPEND | O_DIRECT)) return -EINVAL; return 0; } +EXPORT_SYMBOL_GPL(nfs_check_flags); /* * Open file @@ -93,7 +76,7 @@ nfs_file_open(struct inode *inode, struct file *filp) return res; } -static int +int nfs_file_release(struct inode *inode, struct file *filp) { dprintk("NFS: release(%s/%s)\n", @@ -103,6 +86,7 @@ nfs_file_release(struct inode *inode, struct file *filp) nfs_inc_stats(inode, NFSIOS_VFSRELEASE); return nfs_release(inode, filp); } +EXPORT_SYMBOL_GPL(nfs_file_release); /** * nfs_revalidate_size - Revalidate the file size @@ -135,7 +119,7 @@ force_reval: return __nfs_revalidate_inode(server, inode); } -static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin) +loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin) { dprintk("NFS: llseek file(%s/%s, %lld, %d)\n", filp->f_path.dentry->d_parent->d_name.name, @@ -156,11 +140,12 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin) return generic_file_llseek(filp, offset, origin); } +EXPORT_SYMBOL_GPL(nfs_file_llseek); /* * Flush all dirty pages, and check for write errors. */ -static int +int nfs_file_flush(struct file *file, fl_owner_t id) { struct dentry *dentry = file->f_path.dentry; @@ -178,14 +163,15 @@ nfs_file_flush(struct file *file, fl_owner_t id) * If we're holding a write delegation, then just start the i/o * but don't wait for completion (or send a commit). */ - if (nfs_have_delegation(inode, FMODE_WRITE)) + if (NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) return filemap_fdatawrite(file->f_mapping); /* Flush writes to the server and return any errors */ return vfs_fsync(file, 0); } +EXPORT_SYMBOL_GPL(nfs_file_flush); -static ssize_t +ssize_t nfs_file_read(struct kiocb *iocb, const struct iovec *iov, unsigned long nr_segs, loff_t pos) { @@ -194,7 +180,7 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov, ssize_t result; if (iocb->ki_filp->f_flags & O_DIRECT) - return nfs_file_direct_read(iocb, iov, nr_segs, pos); + return nfs_file_direct_read(iocb, iov, nr_segs, pos, true); dprintk("NFS: read(%s/%s, %lu@%lu)\n", dentry->d_parent->d_name.name, dentry->d_name.name, @@ -208,8 +194,9 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov, } return result; } +EXPORT_SYMBOL_GPL(nfs_file_read); -static ssize_t +ssize_t nfs_file_splice_read(struct file *filp, loff_t *ppos, struct pipe_inode_info *pipe, size_t count, unsigned int flags) @@ -230,8 +217,9 @@ nfs_file_splice_read(struct file *filp, loff_t *ppos, } return res; } +EXPORT_SYMBOL_GPL(nfs_file_splice_read); -static int +int nfs_file_mmap(struct file * file, struct vm_area_struct * vma) { struct dentry *dentry = file->f_path.dentry; @@ -251,6 +239,7 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma) } return status; } +EXPORT_SYMBOL_GPL(nfs_file_mmap); /* * Flush any dirty pages for this process, and check for write errors. @@ -264,8 +253,8 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma) * nfs_file_write() that a write error occurred, and hence cause it to * fall back to doing a synchronous write. */ -static int -nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) +int +nfs_file_fsync_commit(struct file *file, loff_t start, loff_t end, int datasync) { struct dentry *dentry = file->f_path.dentry; struct nfs_open_context *ctx = nfs_file_open_context(file); @@ -277,9 +266,6 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) dentry->d_parent->d_name.name, dentry->d_name.name, datasync); - ret = filemap_write_and_wait_range(inode->i_mapping, start, end); - mutex_lock(&inode->i_mutex); - nfs_inc_stats(inode, NFSIOS_VFSFSYNC); have_error = test_and_clear_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); status = nfs_commit_inode(inode, FLUSH_SYNC); @@ -290,10 +276,23 @@ nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) ret = xchg(&ctx->error, 0); if (!ret && status < 0) ret = status; - if (!ret && !datasync) - /* application has asked for meta-data sync */ - ret = pnfs_layoutcommit_inode(inode, true); + return ret; +} +EXPORT_SYMBOL_GPL(nfs_file_fsync_commit); + +static int +nfs_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) +{ + int ret; + struct inode *inode = file->f_path.dentry->d_inode; + + ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (ret != 0) + goto out; + mutex_lock(&inode->i_mutex); + ret = nfs_file_fsync_commit(file, start, end, datasync); mutex_unlock(&inode->i_mutex); +out: return ret; } @@ -442,7 +441,7 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset) if (offset != 0) return; /* Cancel any unstarted writes on this page */ - nfs_wb_page_cancel(page->mapping->host, page); + nfs_wb_page_cancel(page_file_mapping(page)->host, page); nfs_fscache_invalidate_page(page, page->mapping->host); } @@ -459,8 +458,11 @@ static int nfs_release_page(struct page *page, gfp_t gfp) dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page); - /* Only do I/O if gfp is a superset of GFP_KERNEL */ - if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL) { + /* Only do I/O if gfp is a superset of GFP_KERNEL, and we're not + * doing this memory reclaim for a fs-related allocation. + */ + if (mapping && (gfp & GFP_KERNEL) == GFP_KERNEL && + !(current->flags & PF_FSTRANS)) { int how = FLUSH_SYNC; /* Don't let kswapd deadlock waiting for OOM RPC calls */ @@ -484,7 +486,7 @@ static int nfs_release_page(struct page *page, gfp_t gfp) */ static int nfs_launder_page(struct page *page) { - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; struct nfs_inode *nfsi = NFS_I(inode); dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n", @@ -494,6 +496,20 @@ static int nfs_launder_page(struct page *page) return nfs_wb_page(inode, page); } +#ifdef CONFIG_NFS_SWAP +static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file, + sector_t *span) +{ + *span = sis->pages; + return xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 1); +} + +static void nfs_swap_deactivate(struct file *file) +{ + xs_swapper(NFS_CLIENT(file->f_mapping->host)->cl_xprt, 0); +} +#endif + const struct address_space_operations nfs_file_aops = { .readpage = nfs_readpage, .readpages = nfs_readpages, @@ -508,6 +524,10 @@ const struct address_space_operations nfs_file_aops = { .migratepage = nfs_migrate_page, .launder_page = nfs_launder_page, .error_remove_page = generic_error_remove_page, +#ifdef CONFIG_NFS_SWAP + .swap_activate = nfs_swap_activate, + .swap_deactivate = nfs_swap_deactivate, +#endif }; /* @@ -533,7 +553,7 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf) nfs_fscache_wait_on_page_write(NFS_I(dentry->d_inode), page); lock_page(page); - mapping = page->mapping; + mapping = page_file_mapping(page); if (mapping != dentry->d_inode->i_mapping) goto out_unlock; @@ -572,8 +592,8 @@ static int nfs_need_sync_write(struct file *filp, struct inode *inode) return 0; } -static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, - unsigned long nr_segs, loff_t pos) +ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) { struct dentry * dentry = iocb->ki_filp->f_path.dentry; struct inode * inode = dentry->d_inode; @@ -582,7 +602,7 @@ static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov, size_t count = iov_length(iov, nr_segs); if (iocb->ki_filp->f_flags & O_DIRECT) - return nfs_file_direct_write(iocb, iov, nr_segs, pos); + return nfs_file_direct_write(iocb, iov, nr_segs, pos, true); dprintk("NFS: write(%s/%s, %lu@%Ld)\n", dentry->d_parent->d_name.name, dentry->d_name.name, @@ -623,10 +643,11 @@ out_swapfile: printk(KERN_INFO "NFS: attempt to write to active swap file!\n"); goto out; } +EXPORT_SYMBOL_GPL(nfs_file_write); -static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe, - struct file *filp, loff_t *ppos, - size_t count, unsigned int flags) +ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe, + struct file *filp, loff_t *ppos, + size_t count, unsigned int flags) { struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; @@ -654,6 +675,7 @@ static ssize_t nfs_file_splice_write(struct pipe_inode_info *pipe, nfs_add_stats(inode, NFSIOS_NORMALWRITTENBYTES, written); return ret; } +EXPORT_SYMBOL_GPL(nfs_file_splice_write); static int do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) @@ -670,7 +692,7 @@ do_getlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) } fl->fl_type = saved_type; - if (nfs_have_delegation(inode, FMODE_READ)) + if (NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) goto out_noconflict; if (is_local) @@ -765,7 +787,7 @@ do_setlk(struct file *filp, int cmd, struct file_lock *fl, int is_local) * This makes locking act as a cache coherency point. */ nfs_sync_mapping(filp->f_mapping); - if (!nfs_have_delegation(inode, FMODE_READ)) { + if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ)) { if (is_time_granular(&NFS_SERVER(inode)->time_delta)) __nfs_revalidate_inode(NFS_SERVER(inode), inode); else @@ -778,7 +800,7 @@ out: /* * Lock a (portion of) a file */ -static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl) +int nfs_lock(struct file *filp, int cmd, struct file_lock *fl) { struct inode *inode = filp->f_mapping->host; int ret = -ENOLCK; @@ -814,11 +836,12 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl) out_err: return ret; } +EXPORT_SYMBOL_GPL(nfs_lock); /* * Lock a (portion of) a file */ -static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl) +int nfs_flock(struct file *filp, int cmd, struct file_lock *fl) { struct inode *inode = filp->f_mapping->host; int is_local = 0; @@ -831,6 +854,15 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl) if (!(fl->fl_flags & FL_FLOCK)) return -ENOLCK; + /* + * The NFSv4 protocol doesn't support LOCK_MAND, which is not part of + * any standard. In principle we might be able to support LOCK_MAND + * on NFSv2/3 since NLMv3/4 support DOS share modes, but for now the + * NFS code is not set up for it. + */ + if (fl->fl_type & LOCK_MAND) + return -EINVAL; + if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK) is_local = 1; @@ -843,18 +875,20 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl) return do_unlk(filp, cmd, fl, is_local); return do_setlk(filp, cmd, fl, is_local); } +EXPORT_SYMBOL_GPL(nfs_flock); /* * There is no protocol support for leases, so we have no way to implement * them correctly in the face of opens by other clients. */ -static int nfs_setlease(struct file *file, long arg, struct file_lock **fl) +int nfs_setlease(struct file *file, long arg, struct file_lock **fl) { dprintk("NFS: setlease(%s/%s, arg=%ld)\n", file->f_path.dentry->d_parent->d_name.name, file->f_path.dentry->d_name.name, arg); return -EINVAL; } +EXPORT_SYMBOL_GPL(nfs_setlease); const struct file_operations nfs_file_operations = { .llseek = nfs_file_llseek, @@ -874,104 +908,4 @@ const struct file_operations nfs_file_operations = { .check_flags = nfs_check_flags, .setlease = nfs_setlease, }; - -#ifdef CONFIG_NFS_V4 -static int -nfs4_file_open(struct inode *inode, struct file *filp) -{ - struct nfs_open_context *ctx; - struct dentry *dentry = filp->f_path.dentry; - struct dentry *parent = NULL; - struct inode *dir; - unsigned openflags = filp->f_flags; - struct iattr attr; - int err; - - BUG_ON(inode != dentry->d_inode); - /* - * If no cached dentry exists or if it's negative, NFSv4 handled the - * opens in ->lookup() or ->create(). - * - * We only get this far for a cached positive dentry. We skipped - * revalidation, so handle it here by dropping the dentry and returning - * -EOPENSTALE. The VFS will retry the lookup/create/open. - */ - - dprintk("NFS: open file(%s/%s)\n", - dentry->d_parent->d_name.name, - dentry->d_name.name); - - if ((openflags & O_ACCMODE) == 3) - openflags--; - - /* We can't create new files here */ - openflags &= ~(O_CREAT|O_EXCL); - - parent = dget_parent(dentry); - dir = parent->d_inode; - - ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode); - err = PTR_ERR(ctx); - if (IS_ERR(ctx)) - goto out; - - attr.ia_valid = ATTR_OPEN; - if (openflags & O_TRUNC) { - attr.ia_valid |= ATTR_SIZE; - attr.ia_size = 0; - nfs_wb_all(inode); - } - - inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr); - if (IS_ERR(inode)) { - err = PTR_ERR(inode); - switch (err) { - 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)); - nfs_file_set_open_context(filp, ctx); - err = 0; - -out_put_ctx: - put_nfs_open_context(ctx); -out: - dput(parent); - return err; - -out_drop: - d_drop(dentry); - err = -EOPENSTALE; - goto out_put_ctx; -} - -const struct file_operations nfs4_file_operations = { - .llseek = nfs_file_llseek, - .read = do_sync_read, - .write = do_sync_write, - .aio_read = nfs_file_read, - .aio_write = nfs_file_write, - .mmap = nfs_file_mmap, - .open = nfs4_file_open, - .flush = nfs_file_flush, - .release = nfs_file_release, - .fsync = nfs_file_fsync, - .lock = nfs_lock, - .flock = nfs_flock, - .splice_read = nfs_file_splice_read, - .splice_write = nfs_file_splice_write, - .check_flags = nfs_check_flags, - .setlease = nfs_setlease, -}; -#endif /* CONFIG_NFS_V4 */ +EXPORT_SYMBOL_GPL(nfs_file_operations); diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c index a67990f..4654ced 100644 --- a/fs/nfs/getroot.c +++ b/fs/nfs/getroot.c @@ -23,21 +23,15 @@ #include <linux/sunrpc/stats.h> #include <linux/nfs_fs.h> #include <linux/nfs_mount.h> -#include <linux/nfs4_mount.h> #include <linux/lockd/bind.h> #include <linux/seq_file.h> #include <linux/mount.h> -#include <linux/nfs_idmap.h> #include <linux/vfs.h> #include <linux/namei.h> #include <linux/security.h> #include <asm/uaccess.h> -#include "nfs4_fs.h" -#include "delegation.h" -#include "internal.h" - #define NFSDBG_FACILITY NFSDBG_CLIENT /* @@ -135,47 +129,3 @@ out: nfs_free_fattr(fsinfo.fattr); return ret; } - -#ifdef CONFIG_NFS_V4 - -int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh) -{ - struct nfs_fsinfo fsinfo; - int ret = -ENOMEM; - - dprintk("--> nfs4_get_rootfh()\n"); - - fsinfo.fattr = nfs_alloc_fattr(); - if (fsinfo.fattr == NULL) - goto out; - - /* Start by getting the root filehandle from the server */ - ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo); - if (ret < 0) { - dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret); - goto out; - } - - if (!(fsinfo.fattr->valid & NFS_ATTR_FATTR_TYPE) - || !S_ISDIR(fsinfo.fattr->mode)) { - printk(KERN_ERR "nfs4_get_rootfh:" - " getroot encountered non-directory\n"); - ret = -ENOTDIR; - goto out; - } - - if (fsinfo.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { - printk(KERN_ERR "nfs4_get_rootfh:" - " getroot obtained referral\n"); - ret = -EREMOTE; - goto out; - } - - memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid)); -out: - nfs_free_fattr(fsinfo.fattr); - dprintk("<-- nfs4_get_rootfh() = %d\n", ret); - return ret; -} - -#endif /* CONFIG_NFS_V4 */ diff --git a/fs/nfs/idmap.c b/fs/nfs/idmap.c index 864c51e..a850079 100644 --- a/fs/nfs/idmap.c +++ b/fs/nfs/idmap.c @@ -52,8 +52,6 @@ #define NFS_UINT_MAXLEN 11 -/* Default cache timeout is 10 minutes */ -unsigned int nfs_idmap_cache_timeout = 600; static const struct cred *id_resolver_cache; static struct key_type key_type_id_resolver_legacy; @@ -63,6 +61,12 @@ struct idmap { struct mutex idmap_mutex; }; +struct idmap_legacy_upcalldata { + struct rpc_pipe_msg pipe_msg; + struct idmap_msg idmap_msg; + struct idmap *idmap; +}; + /** * nfs_fattr_init_names - initialise the nfs_fattr owner_name/group_name fields * @fattr: fully initialised struct nfs_fattr @@ -205,12 +209,18 @@ static int nfs_idmap_init_keyring(void) if (ret < 0) goto failed_put_key; + ret = register_key_type(&key_type_id_resolver_legacy); + if (ret < 0) + goto failed_reg_legacy; + set_bit(KEY_FLAG_ROOT_CAN_CLEAR, &keyring->flags); cred->thread_keyring = keyring; cred->jit_keyring = KEY_REQKEY_DEFL_THREAD_KEYRING; id_resolver_cache = cred; return 0; +failed_reg_legacy: + unregister_key_type(&key_type_id_resolver); failed_put_key: key_put(keyring); failed_put_cred: @@ -222,6 +232,7 @@ static void nfs_idmap_quit_keyring(void) { key_revoke(id_resolver_cache->thread_keyring); unregister_key_type(&key_type_id_resolver); + unregister_key_type(&key_type_id_resolver_legacy); put_cred(id_resolver_cache); } @@ -319,6 +330,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen, ret = nfs_idmap_request_key(&key_type_id_resolver_legacy, name, namelen, type, data, data_size, idmap); + idmap->idmap_key_cons = NULL; mutex_unlock(&idmap->idmap_mutex); } return ret; @@ -359,7 +371,6 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *typ } /* idmap classic begins here */ -module_param(nfs_idmap_cache_timeout, int, 0644); enum { Opt_find_uid, Opt_find_gid, Opt_find_user, Opt_find_group, Opt_find_err @@ -376,16 +387,18 @@ static const match_table_t nfs_idmap_tokens = { static int nfs_idmap_legacy_upcall(struct key_construction *, const char *, void *); static ssize_t idmap_pipe_downcall(struct file *, const char __user *, size_t); +static void idmap_release_pipe(struct inode *); static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *); static const struct rpc_pipe_ops idmap_upcall_ops = { .upcall = rpc_pipe_generic_upcall, .downcall = idmap_pipe_downcall, + .release_pipe = idmap_release_pipe, .destroy_msg = idmap_pipe_destroy_msg, }; static struct key_type key_type_id_resolver_legacy = { - .name = "id_resolver", + .name = "id_legacy", .instantiate = user_instantiate, .match = user_match, .revoke = user_revoke, @@ -612,7 +625,8 @@ void nfs_idmap_quit(void) nfs_idmap_quit_keyring(); } -static int nfs_idmap_prepare_message(char *desc, struct idmap_msg *im, +static int nfs_idmap_prepare_message(char *desc, struct idmap *idmap, + struct idmap_msg *im, struct rpc_pipe_msg *msg) { substring_t substr; @@ -655,6 +669,7 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, const char *op, void *aux) { + struct idmap_legacy_upcalldata *data; struct rpc_pipe_msg *msg; struct idmap_msg *im; struct idmap *idmap = (struct idmap *)aux; @@ -662,33 +677,33 @@ static int nfs_idmap_legacy_upcall(struct key_construction *cons, int ret = -ENOMEM; /* msg and im are freed in idmap_pipe_destroy_msg */ - msg = kmalloc(sizeof(*msg), GFP_KERNEL); - if (!msg) - goto out0; - - im = kmalloc(sizeof(*im), GFP_KERNEL); - if (!im) + data = kmalloc(sizeof(*data), GFP_KERNEL); + if (!data) goto out1; - ret = nfs_idmap_prepare_message(key->description, im, msg); + msg = &data->pipe_msg; + im = &data->idmap_msg; + data->idmap = idmap; + + ret = nfs_idmap_prepare_message(key->description, idmap, im, msg); if (ret < 0) goto out2; + BUG_ON(idmap->idmap_key_cons != NULL); idmap->idmap_key_cons = cons; ret = rpc_queue_upcall(idmap->idmap_pipe, msg); if (ret < 0) - goto out2; + goto out3; return ret; +out3: + idmap->idmap_key_cons = NULL; out2: - kfree(im); + kfree(data); out1: - kfree(msg); -out0: - key_revoke(cons->key); - key_revoke(cons->authkey); + complete_request_key(cons, ret); return ret; } @@ -722,11 +737,18 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) { struct rpc_inode *rpci = RPC_I(filp->f_path.dentry->d_inode); struct idmap *idmap = (struct idmap *)rpci->private; - struct key_construction *cons = idmap->idmap_key_cons; + struct key_construction *cons; struct idmap_msg im; size_t namelen_in; int ret; + /* If instantiation is successful, anyone waiting for key construction + * will have been woken up and someone else may now have used + * idmap_key_cons - so after this point we may no longer touch it. + */ + cons = ACCESS_ONCE(idmap->idmap_key_cons); + idmap->idmap_key_cons = NULL; + if (mlen != sizeof(im)) { ret = -ENOSPC; goto out; @@ -738,9 +760,8 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) } if (!(im.im_status & IDMAP_STATUS_SUCCESS)) { - ret = mlen; - complete_request_key(idmap->idmap_key_cons, -ENOKEY); - goto out_incomplete; + ret = -ENOKEY; + goto out; } namelen_in = strnlen(im.im_name, IDMAP_NAMESZ); @@ -756,17 +777,33 @@ idmap_pipe_downcall(struct file *filp, const char __user *src, size_t mlen) } out: - complete_request_key(idmap->idmap_key_cons, ret); -out_incomplete: + complete_request_key(cons, ret); return ret; } static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *msg) { + struct idmap_legacy_upcalldata *data = container_of(msg, + struct idmap_legacy_upcalldata, + pipe_msg); + struct idmap *idmap = data->idmap; + struct key_construction *cons; + if (msg->errno) { + cons = ACCESS_ONCE(idmap->idmap_key_cons); + idmap->idmap_key_cons = NULL; + complete_request_key(cons, msg->errno); + } /* Free memory allocated in nfs_idmap_legacy_upcall() */ - kfree(msg->data); - kfree(msg); + kfree(data); +} + +static void +idmap_release_pipe(struct inode *inode) +{ + struct rpc_inode *rpci = RPC_I(inode); + struct idmap *idmap = (struct idmap *)rpci->private; + idmap->idmap_key_cons = NULL; } int nfs_map_name_to_uid(const struct nfs_server *server, const char *name, size_t namelen, __u32 *uid) diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index f729698..9b47610 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -32,7 +32,6 @@ #include <linux/lockd/bind.h> #include <linux/seq_file.h> #include <linux/mount.h> -#include <linux/nfs_idmap.h> #include <linux/vfs.h> #include <linux/inet.h> #include <linux/nfs_xdr.h> @@ -51,6 +50,7 @@ #include "fscache.h" #include "dns_resolve.h" #include "pnfs.h" +#include "nfs.h" #include "netns.h" #define NFSDBG_FACILITY NFSDBG_VFS @@ -82,6 +82,7 @@ int nfs_wait_bit_killable(void *word) freezable_schedule(); return 0; } +EXPORT_SYMBOL_GPL(nfs_wait_bit_killable); /** * nfs_compat_user_ino64 - returns the user-visible inode number @@ -106,7 +107,7 @@ u64 nfs_compat_user_ino64(u64 fileid) return ino; } -static void nfs_clear_inode(struct inode *inode) +void nfs_clear_inode(struct inode *inode) { /* * The following should never happen... @@ -117,6 +118,7 @@ static void nfs_clear_inode(struct inode *inode) nfs_access_zap_cache(inode); nfs_fscache_release_inode_cookie(inode); } +EXPORT_SYMBOL_GPL(nfs_clear_inode); void nfs_evict_inode(struct inode *inode) { @@ -152,7 +154,7 @@ static void nfs_zap_caches_locked(struct inode *inode) nfsi->attrtimeo = NFS_MINATTRTIMEO(inode); nfsi->attrtimeo_timestamp = jiffies; - memset(NFS_COOKIEVERF(inode), 0, sizeof(NFS_COOKIEVERF(inode))); + memset(NFS_I(inode)->cookieverf, 0, sizeof(NFS_I(inode)->cookieverf)); if (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) nfsi->cache_validity |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL|NFS_INO_REVAL_PAGECACHE; else @@ -186,6 +188,7 @@ void nfs_zap_acl_cache(struct inode *inode) NFS_I(inode)->cache_validity &= ~NFS_INO_INVALID_ACL; spin_unlock(&inode->i_lock); } +EXPORT_SYMBOL_GPL(nfs_zap_acl_cache); void nfs_invalidate_atime(struct inode *inode) { @@ -193,6 +196,7 @@ void nfs_invalidate_atime(struct inode *inode) NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATIME; spin_unlock(&inode->i_lock); } +EXPORT_SYMBOL_GPL(nfs_invalidate_atime); /* * Invalidate, but do not unhash, the inode. @@ -391,6 +395,7 @@ out_no_inode: dprintk("nfs_fhget: iget failed with error %ld\n", PTR_ERR(inode)); goto out; } +EXPORT_SYMBOL_GPL(nfs_fhget); #define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE|ATTR_OPEN) @@ -430,7 +435,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr) * Return any delegations if we're going to change ACLs */ if ((attr->ia_valid & (ATTR_MODE|ATTR_UID|ATTR_GID)) != 0) - nfs_inode_return_delegation(inode); + NFS_PROTO(inode)->return_delegation(inode); error = NFS_PROTO(inode)->setattr(dentry, fattr, attr); if (error == 0) nfs_refresh_inode(inode, fattr); @@ -438,6 +443,7 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr) out: return error; } +EXPORT_SYMBOL_GPL(nfs_setattr); /** * nfs_vmtruncate - unmap mappings "freed" by truncate() syscall @@ -496,6 +502,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr) nfs_vmtruncate(inode, attr->ia_size); } } +EXPORT_SYMBOL_GPL(nfs_setattr_update_inode); int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) { @@ -535,6 +542,7 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat) out: return err; } +EXPORT_SYMBOL_GPL(nfs_getattr); static void nfs_init_lock_context(struct nfs_lock_context *l_ctx) { @@ -623,6 +631,7 @@ void nfs_close_context(struct nfs_open_context *ctx, int is_sync) return; nfs_revalidate_inode(server, inode); } +EXPORT_SYMBOL_GPL(nfs_close_context); struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f_mode) { @@ -649,6 +658,7 @@ struct nfs_open_context *alloc_nfs_open_context(struct dentry *dentry, fmode_t f ctx->mdsthreshold = NULL; return ctx; } +EXPORT_SYMBOL_GPL(alloc_nfs_open_context); struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx) { @@ -656,6 +666,7 @@ struct nfs_open_context *get_nfs_open_context(struct nfs_open_context *ctx) atomic_inc(&ctx->lock_context.count); return ctx; } +EXPORT_SYMBOL_GPL(get_nfs_open_context); static void __put_nfs_open_context(struct nfs_open_context *ctx, int is_sync) { @@ -683,6 +694,7 @@ void put_nfs_open_context(struct nfs_open_context *ctx) { __put_nfs_open_context(ctx, 0); } +EXPORT_SYMBOL_GPL(put_nfs_open_context); /* * Ensure that mmap has a recent RPC credential for use when writing out @@ -698,6 +710,7 @@ void nfs_file_set_open_context(struct file *filp, struct nfs_open_context *ctx) list_add(&ctx->list, &nfsi->open_files); spin_unlock(&inode->i_lock); } +EXPORT_SYMBOL_GPL(nfs_file_set_open_context); /* * Given an inode, search for an open context with the desired characteristics @@ -842,6 +855,7 @@ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) return NFS_STALE(inode) ? -ESTALE : 0; return __nfs_revalidate_inode(server, inode); } +EXPORT_SYMBOL_GPL(nfs_revalidate_inode); static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping) { @@ -883,6 +897,10 @@ int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) struct nfs_inode *nfsi = NFS_I(inode); int ret = 0; + /* swapfiles are not supposed to be shared. */ + if (IS_SWAPFILE(inode)) + goto out; + if (nfs_mapping_need_revalidate_inode(inode)) { ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); if (ret < 0) @@ -1028,6 +1046,7 @@ void nfs_fattr_init(struct nfs_fattr *fattr) fattr->owner_name = NULL; fattr->group_name = NULL; } +EXPORT_SYMBOL_GPL(nfs_fattr_init); struct nfs_fattr *nfs_alloc_fattr(void) { @@ -1038,6 +1057,7 @@ struct nfs_fattr *nfs_alloc_fattr(void) nfs_fattr_init(fattr); return fattr; } +EXPORT_SYMBOL_GPL(nfs_alloc_fattr); struct nfs_fh *nfs_alloc_fhandle(void) { @@ -1048,6 +1068,7 @@ struct nfs_fh *nfs_alloc_fhandle(void) fh->size = 0; return fh; } +EXPORT_SYMBOL_GPL(nfs_alloc_fhandle); #ifdef NFS_DEBUG /* @@ -1168,6 +1189,7 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr) return status; } +EXPORT_SYMBOL_GPL(nfs_refresh_inode); static int nfs_post_op_update_inode_locked(struct inode *inode, struct nfs_fattr *fattr) { @@ -1204,6 +1226,7 @@ int nfs_post_op_update_inode(struct inode *inode, struct nfs_fattr *fattr) spin_unlock(&inode->i_lock); return status; } +EXPORT_SYMBOL_GPL(nfs_post_op_update_inode); /** * nfs_post_op_update_inode_force_wcc - try to update the inode attribute cache @@ -1255,6 +1278,7 @@ out_noforce: spin_unlock(&inode->i_lock); return status; } +EXPORT_SYMBOL_GPL(nfs_post_op_update_inode_force_wcc); /* * Many nfs protocol calls return the new file attributes after @@ -1457,7 +1481,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))) invalid &= ~NFS_INO_INVALID_DATA; - if (!nfs_have_delegation(inode, FMODE_READ) || + if (!NFS_PROTO(inode)->have_delegation(inode, FMODE_READ) || (save_cache_validity & NFS_INO_REVAL_FORCED)) nfsi->cache_validity |= invalid; @@ -1472,27 +1496,6 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr) return -ESTALE; } - -#ifdef CONFIG_NFS_V4 - -/* - * Clean out any remaining NFSv4 state that might be left over due - * to open() calls that passed nfs_atomic_lookup, but failed to call - * nfs_open(). - */ -void nfs4_evict_inode(struct inode *inode) -{ - truncate_inode_pages(&inode->i_data, 0); - clear_inode(inode); - pnfs_return_layout(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 */ - nfs_clear_inode(inode); -} -#endif - struct inode *nfs_alloc_inode(struct super_block *sb) { struct nfs_inode *nfsi; @@ -1505,11 +1508,12 @@ struct inode *nfs_alloc_inode(struct super_block *sb) nfsi->acl_access = ERR_PTR(-EAGAIN); nfsi->acl_default = ERR_PTR(-EAGAIN); #endif -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) nfsi->nfs4_acl = NULL; #endif /* CONFIG_NFS_V4 */ return &nfsi->vfs_inode; } +EXPORT_SYMBOL_GPL(nfs_alloc_inode); static void nfs_i_callback(struct rcu_head *head) { @@ -1521,10 +1525,11 @@ void nfs_destroy_inode(struct inode *inode) { call_rcu(&inode->i_rcu, nfs_i_callback); } +EXPORT_SYMBOL_GPL(nfs_destroy_inode); static inline void nfs4_init_once(struct nfs_inode *nfsi) { -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) INIT_LIST_HEAD(&nfsi->open_states); nfsi->delegation = NULL; nfsi->delegation_state = 0; @@ -1570,6 +1575,7 @@ static void nfs_destroy_inodecache(void) } struct workqueue_struct *nfsiod_workqueue; +EXPORT_SYMBOL_GPL(nfsiod_workqueue); /* * start up the nfsiod workqueue @@ -1628,81 +1634,76 @@ static int __init init_nfs_fs(void) { int err; - err = nfs_idmap_init(); - if (err < 0) - goto out10; - err = nfs_dns_resolver_init(); if (err < 0) - goto out9; + goto out10;; err = register_pernet_subsys(&nfs_net_ops); if (err < 0) - goto out8; + goto out9; err = nfs_fscache_register(); if (err < 0) - goto out7; + goto out8; err = nfsiod_start(); if (err) - goto out6; + goto out7; err = nfs_fs_proc_init(); if (err) - goto out5; + goto out6; err = nfs_init_nfspagecache(); if (err) - goto out4; + goto out5; err = nfs_init_inodecache(); if (err) - goto out3; + goto out4; err = nfs_init_readpagecache(); if (err) - goto out2; + goto out3; err = nfs_init_writepagecache(); if (err) - goto out1; + goto out2; err = nfs_init_directcache(); if (err) - goto out0; + goto out1; #ifdef CONFIG_PROC_FS rpc_proc_register(&init_net, &nfs_rpcstat); #endif if ((err = register_nfs_fs()) != 0) - goto out; + goto out0; + return 0; -out: +out0: #ifdef CONFIG_PROC_FS rpc_proc_unregister(&init_net, "nfs"); #endif nfs_destroy_directcache(); -out0: - nfs_destroy_writepagecache(); out1: - nfs_destroy_readpagecache(); + nfs_destroy_writepagecache(); out2: - nfs_destroy_inodecache(); + nfs_destroy_readpagecache(); out3: - nfs_destroy_nfspagecache(); + nfs_destroy_inodecache(); out4: - nfs_fs_proc_exit(); + nfs_destroy_nfspagecache(); out5: - nfsiod_stop(); + nfs_fs_proc_exit(); out6: - nfs_fscache_unregister(); + nfsiod_stop(); out7: - unregister_pernet_subsys(&nfs_net_ops); + nfs_fscache_unregister(); out8: - nfs_dns_resolver_destroy(); + unregister_pernet_subsys(&nfs_net_ops); out9: - nfs_idmap_quit(); + nfs_dns_resolver_destroy(); out10: return err; } @@ -1717,7 +1718,6 @@ static void __exit exit_nfs_fs(void) nfs_fscache_unregister(); unregister_pernet_subsys(&nfs_net_ops); nfs_dns_resolver_destroy(); - nfs_idmap_quit(); #ifdef CONFIG_PROC_FS rpc_proc_unregister(&init_net, "nfs"); #endif diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h index 18f99ef..31fdb03 100644 --- a/fs/nfs/internal.h +++ b/fs/nfs/internal.h @@ -85,6 +85,17 @@ struct nfs_clone_mount { */ #define NFS_MAX_READDIR_PAGES 8 +struct nfs_client_initdata { + unsigned long init_flags; + const char *hostname; + const struct sockaddr *addr; + size_t addrlen; + struct nfs_subversion *nfs_mod; + int proto; + u32 minorversion; + struct net *net; +}; + /* * In-kernel mount arguments */ @@ -142,25 +153,45 @@ struct nfs_mount_request { struct net *net; }; +struct nfs_mount_info { + void (*fill_super)(struct super_block *, struct nfs_mount_info *); + int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *); + struct nfs_parsed_mount_data *parsed; + struct nfs_clone_mount *cloned; + struct nfs_fh *mntfh; +}; + extern int nfs_mount(struct nfs_mount_request *info); extern void nfs_umount(const struct nfs_mount_request *info); /* client.c */ extern const struct rpc_program nfs_program; extern void nfs_clients_init(struct net *net); +extern struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *); +int nfs_create_rpc_client(struct nfs_client *, const struct rpc_timeout *, rpc_authflavor_t); +struct nfs_client *nfs_get_client(const struct nfs_client_initdata *, + const struct rpc_timeout *, const char *, + rpc_authflavor_t); +int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *, struct nfs_fattr *); +void nfs_server_insert_lists(struct nfs_server *); +void nfs_init_timeout_values(struct rpc_timeout *, int, unsigned int, unsigned int); +int nfs_init_server_rpcclient(struct nfs_server *, const struct rpc_timeout *t, + rpc_authflavor_t); +struct nfs_server *nfs_alloc_server(void); +void nfs_server_copy_userdata(struct nfs_server *, struct nfs_server *); extern void nfs_cleanup_cb_ident_idr(struct net *); extern void nfs_put_client(struct nfs_client *); +extern void nfs_free_client(struct nfs_client *); extern struct nfs_client *nfs4_find_client_ident(struct net *, int); extern struct nfs_client * nfs4_find_client_sessionid(struct net *, const struct sockaddr *, struct nfs4_sessionid *); -extern struct nfs_server *nfs_create_server( - const struct nfs_parsed_mount_data *, - struct nfs_fh *); +extern struct nfs_server *nfs_create_server(struct nfs_mount_info *, + struct nfs_subversion *); extern struct nfs_server *nfs4_create_server( - const struct nfs_parsed_mount_data *, - struct nfs_fh *); + struct nfs_mount_info *, + struct nfs_subversion *); extern struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *, struct nfs_fh *); extern void nfs_free_server(struct nfs_server *server); @@ -188,6 +219,17 @@ static inline void nfs_fs_proc_exit(void) } #endif +#ifdef CONFIG_NFS_V4_1 +int nfs_sockaddr_match_ipaddr(const struct sockaddr *, const struct sockaddr *); +#endif + +/* nfs3client.c */ +#if IS_ENABLED(CONFIG_NFS_V3) +struct nfs_server *nfs3_create_server(struct nfs_mount_info *, struct nfs_subversion *); +struct nfs_server *nfs3_clone_server(struct nfs_server *, struct nfs_fh *, + struct nfs_fattr *, rpc_authflavor_t); +#endif + /* callback_xdr.c */ extern struct svc_version nfs4_callback_version1; extern struct svc_version nfs4_callback_version4; @@ -220,7 +262,7 @@ extern int nfs3_decode_dirent(struct xdr_stream *, struct nfs_entry *, int); /* nfs4xdr.c */ -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) extern int nfs4_decode_dirent(struct xdr_stream *, struct nfs_entry *, int); #endif @@ -230,7 +272,7 @@ extern const u32 nfs41_maxwrite_overhead; #endif /* nfs4proc.c */ -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) extern struct rpc_procinfo nfs4_procedures[]; #endif @@ -245,25 +287,63 @@ extern struct nfs_client *nfs_init_client(struct nfs_client *clp, /* dir.c */ extern int nfs_access_cache_shrinker(struct shrinker *shrink, struct shrink_control *sc); +struct dentry *nfs_lookup(struct inode *, struct dentry *, unsigned int); +int nfs_create(struct inode *, struct dentry *, umode_t, bool); +int nfs_mkdir(struct inode *, struct dentry *, umode_t); +int nfs_rmdir(struct inode *, struct dentry *); +int nfs_unlink(struct inode *, struct dentry *); +int nfs_symlink(struct inode *, struct dentry *, const char *); +int nfs_link(struct dentry *, struct inode *, struct dentry *); +int nfs_mknod(struct inode *, struct dentry *, umode_t, dev_t); +int nfs_rename(struct inode *, struct dentry *, struct inode *, struct dentry *); + +/* file.c */ +int nfs_file_fsync_commit(struct file *, loff_t, loff_t, int); +loff_t nfs_file_llseek(struct file *, loff_t, int); +int nfs_file_flush(struct file *, fl_owner_t); +ssize_t nfs_file_read(struct kiocb *, const struct iovec *, unsigned long, loff_t); +ssize_t nfs_file_splice_read(struct file *, loff_t *, struct pipe_inode_info *, + size_t, unsigned int); +int nfs_file_mmap(struct file *, struct vm_area_struct *); +ssize_t nfs_file_write(struct kiocb *, const struct iovec *, unsigned long, loff_t); +int nfs_file_release(struct inode *, struct file *); +int nfs_lock(struct file *, int, struct file_lock *); +int nfs_flock(struct file *, int, struct file_lock *); +ssize_t nfs_file_splice_write(struct pipe_inode_info *, struct file *, loff_t *, + size_t, unsigned int); +int nfs_check_flags(int); +int nfs_setlease(struct file *, long, struct file_lock **); /* inode.c */ extern struct workqueue_struct *nfsiod_workqueue; extern struct inode *nfs_alloc_inode(struct super_block *sb); extern void nfs_destroy_inode(struct inode *); extern int nfs_write_inode(struct inode *, struct writeback_control *); +extern void nfs_clear_inode(struct inode *); extern void nfs_evict_inode(struct inode *); -#ifdef CONFIG_NFS_V4 -extern void nfs4_evict_inode(struct inode *); -#endif void nfs_zap_acl_cache(struct inode *inode); extern int nfs_wait_bit_killable(void *word); /* super.c */ +extern const struct super_operations nfs_sops; +extern struct file_system_type nfs_fs_type; extern struct file_system_type nfs_xdev_fs_type; -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) extern struct file_system_type nfs4_xdev_fs_type; extern struct file_system_type nfs4_referral_fs_type; #endif +struct dentry *nfs_try_mount(int, const char *, struct nfs_mount_info *, + struct nfs_subversion *); +void nfs_initialise_sb(struct super_block *); +int nfs_set_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *); +int nfs_clone_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *); +struct dentry *nfs_fs_mount_common(struct nfs_server *, int, const char *, + struct nfs_mount_info *, struct nfs_subversion *); +struct dentry *nfs_fs_mount(struct file_system_type *, int, const char *, void *); +struct dentry * nfs_xdev_mount_common(struct file_system_type *, int, + const char *, struct nfs_mount_info *); +void nfs_kill_super(struct super_block *); +void nfs_fill_super(struct super_block *, struct nfs_mount_info *); extern struct rpc_stat nfs_rpcstat; @@ -284,7 +364,7 @@ struct vfsmount *nfs_do_submount(struct dentry *, struct nfs_fh *, /* getroot.c */ extern struct dentry *nfs_get_root(struct super_block *, struct nfs_fh *, const char *); -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) extern struct dentry *nfs4_get_root(struct super_block *, struct nfs_fh *, const char *); @@ -304,12 +384,23 @@ extern int nfs_initiate_read(struct rpc_clnt *clnt, extern void nfs_read_prepare(struct rpc_task *task, void *calldata); extern int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr); -extern void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, +extern void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio); extern void nfs_readdata_release(struct nfs_read_data *rdata); +/* super.c */ +void nfs_clone_super(struct super_block *, struct nfs_mount_info *); +void nfs_umount_begin(struct super_block *); +int nfs_statfs(struct dentry *, struct kstatfs *); +int nfs_show_options(struct seq_file *, struct dentry *); +int nfs_show_devname(struct seq_file *, struct dentry *); +int nfs_show_path(struct seq_file *, struct dentry *); +int nfs_show_stats(struct seq_file *, struct dentry *); +void nfs_put_super(struct super_block *); +int nfs_remount(struct super_block *sb, int *flags, char *raw_data); + /* write.c */ extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, @@ -318,7 +409,7 @@ extern struct nfs_write_header *nfs_writehdr_alloc(void); extern void nfs_writehdr_free(struct nfs_pgio_header *hdr); extern int nfs_generic_flush(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr); -extern void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, +extern void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, const struct nfs_pgio_completion_ops *compl_ops); extern void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio); @@ -463,13 +554,14 @@ void nfs_super_set_maxbytes(struct super_block *sb, __u64 maxfilesize) static inline unsigned int nfs_page_length(struct page *page) { - loff_t i_size = i_size_read(page->mapping->host); + loff_t i_size = i_size_read(page_file_mapping(page)->host); if (i_size > 0) { + pgoff_t page_index = page_file_index(page); pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT; - if (page->index < end_index) + if (page_index < end_index) return PAGE_CACHE_SIZE; - if (page->index == end_index) + if (page_index == end_index) return ((i_size - 1) & ~PAGE_CACHE_MASK) + 1; } return 0; diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c index 08b9c93..6559253 100644 --- a/fs/nfs/namespace.c +++ b/fs/nfs/namespace.c @@ -7,6 +7,7 @@ * NFS namespace */ +#include <linux/module.h> #include <linux/dcache.h> #include <linux/gfp.h> #include <linux/mount.h> @@ -112,6 +113,7 @@ Elong_unlock: Elong: return ERR_PTR(-ENAMETOOLONG); } +EXPORT_SYMBOL_GPL(nfs_path); /* * nfs_d_automount - Handle crossing a mountpoint on the server @@ -195,20 +197,7 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server, const char *devname, struct nfs_clone_mount *mountdata) { -#ifdef CONFIG_NFS_V4 - struct vfsmount *mnt = ERR_PTR(-EINVAL); - switch (server->nfs_client->rpc_ops->version) { - case 2: - case 3: - mnt = vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata); - break; - case 4: - mnt = vfs_kern_mount(&nfs4_xdev_fs_type, 0, devname, mountdata); - } - return mnt; -#else return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata); -#endif } /** @@ -253,6 +242,7 @@ out: dprintk("<-- nfs_do_submount() = %p\n", mnt); return mnt; } +EXPORT_SYMBOL_GPL(nfs_do_submount); struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry, struct nfs_fh *fh, struct nfs_fattr *fattr) @@ -268,3 +258,4 @@ struct vfsmount *nfs_submount(struct nfs_server *server, struct dentry *dentry, return nfs_do_submount(dentry, fh, fattr, server->client->cl_auth->au_flavor); } +EXPORT_SYMBOL_GPL(nfs_submount); diff --git a/fs/nfs/netns.h b/fs/nfs/netns.h index 8a6394e..0539de1 100644 --- a/fs/nfs/netns.h +++ b/fs/nfs/netns.h @@ -20,7 +20,7 @@ struct nfs_net { wait_queue_head_t bl_wq; struct list_head nfs_client_list; struct list_head nfs_volume_list; -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) struct idr cb_ident_idr; /* Protected by nfs_client_lock */ #endif spinlock_t nfs_client_lock; diff --git a/fs/nfs/nfs.h b/fs/nfs/nfs.h new file mode 100644 index 0000000..43679df --- /dev/null +++ b/fs/nfs/nfs.h @@ -0,0 +1,29 @@ +/* + * Copyright (c) 2012 Netapp, Inc. All rights reserved. + * + * Function and structures exported by the NFS module + * for use by NFS version-specific modules. + */ +#ifndef __LINUX_INTERNAL_NFS_H +#define __LINUX_INTERNAL_NFS_H + +#include <linux/fs.h> +#include <linux/sunrpc/sched.h> +#include <linux/nfs_xdr.h> + +struct nfs_subversion { + struct module *owner; /* THIS_MODULE pointer */ + struct file_system_type *nfs_fs; /* NFS filesystem type */ + const struct rpc_version *rpc_vers; /* NFS version information */ + const struct nfs_rpc_ops *rpc_ops; /* NFS operations */ + const struct super_operations *sops; /* NFS Super operations */ + const struct xattr_handler **xattr; /* NFS xattr handlers */ + struct list_head list; /* List of NFS versions */ +}; + +struct nfs_subversion *get_nfs_version(unsigned int); +void put_nfs_version(struct nfs_subversion *); +void register_nfs_version(struct nfs_subversion *); +void unregister_nfs_version(struct nfs_subversion *); + +#endif /* __LINUX_INTERNAL_NFS_H */ diff --git a/fs/nfs/nfs2super.c b/fs/nfs/nfs2super.c new file mode 100644 index 0000000..0a9782c --- /dev/null +++ b/fs/nfs/nfs2super.c @@ -0,0 +1,31 @@ +/* + * Copyright (c) 2012 Netapp, Inc. All rights reserved. + */ +#include <linux/module.h> +#include <linux/nfs_fs.h> +#include "internal.h" +#include "nfs.h" + +static struct nfs_subversion nfs_v2 = { + .owner = THIS_MODULE, + .nfs_fs = &nfs_fs_type, + .rpc_vers = &nfs_version2, + .rpc_ops = &nfs_v2_clientops, + .sops = &nfs_sops, +}; + +static int __init init_nfs_v2(void) +{ + register_nfs_version(&nfs_v2); + return 0; +} + +static void __exit exit_nfs_v2(void) +{ + unregister_nfs_version(&nfs_v2); +} + +MODULE_LICENSE("GPL"); + +module_init(init_nfs_v2); +module_exit(exit_nfs_v2); diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c index baf759b..d04f0df 100644 --- a/fs/nfs/nfs2xdr.c +++ b/fs/nfs/nfs2xdr.c @@ -106,19 +106,16 @@ static void print_overflow_msg(const char *func, const struct xdr_stream *xdr) static int decode_nfsdata(struct xdr_stream *xdr, struct nfs_readres *result) { u32 recvd, count; - size_t hdrlen; __be32 *p; p = xdr_inline_decode(xdr, 4); if (unlikely(p == NULL)) goto out_overflow; count = be32_to_cpup(p); - hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base; - recvd = xdr->buf->len - hdrlen; + recvd = xdr_read_pages(xdr, count); if (unlikely(count > recvd)) goto out_cheating; out: - xdr_read_pages(xdr, count); result->eof = 0; /* NFSv2 does not pass EOF flag on the wire. */ result->count = count; return count; @@ -440,7 +437,6 @@ static void encode_path(struct xdr_stream *xdr, struct page **pages, u32 length) static int decode_path(struct xdr_stream *xdr) { u32 length, recvd; - size_t hdrlen; __be32 *p; p = xdr_inline_decode(xdr, 4); @@ -449,12 +445,9 @@ static int decode_path(struct xdr_stream *xdr) length = be32_to_cpup(p); if (unlikely(length >= xdr->buf->page_len || length > NFS_MAXPATHLEN)) goto out_size; - hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base; - recvd = xdr->buf->len - hdrlen; + recvd = xdr_read_pages(xdr, length); if (unlikely(length > recvd)) goto out_cheating; - - xdr_read_pages(xdr, length); xdr_terminate_string(xdr->buf, length); return 0; out_size: @@ -972,22 +965,7 @@ out_overflow: */ static int decode_readdirok(struct xdr_stream *xdr) { - u32 recvd, pglen; - size_t hdrlen; - - pglen = xdr->buf->page_len; - hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base; - recvd = xdr->buf->len - hdrlen; - if (unlikely(pglen > recvd)) - goto out_cheating; -out: - xdr_read_pages(xdr, pglen); - return pglen; -out_cheating: - dprintk("NFS: server cheating in readdir result: " - "pglen %u > recvd %u\n", pglen, recvd); - pglen = recvd; - goto out; + return xdr_read_pages(xdr, xdr->buf->page_len); } static int nfs2_xdr_dec_readdirres(struct rpc_rqst *req, diff --git a/fs/nfs/nfs3client.c b/fs/nfs/nfs3client.c new file mode 100644 index 0000000..b3fc65e --- /dev/null +++ b/fs/nfs/nfs3client.c @@ -0,0 +1,65 @@ +#include <linux/nfs_fs.h> +#include <linux/nfs_mount.h> +#include "internal.h" + +#ifdef CONFIG_NFS_V3_ACL +static struct rpc_stat nfsacl_rpcstat = { &nfsacl_program }; +static const struct rpc_version *nfsacl_version[] = { + [3] = &nfsacl_version3, +}; + +const struct rpc_program nfsacl_program = { + .name = "nfsacl", + .number = NFS_ACL_PROGRAM, + .nrvers = ARRAY_SIZE(nfsacl_version), + .version = nfsacl_version, + .stats = &nfsacl_rpcstat, +}; + +/* + * Initialise an NFSv3 ACL client connection + */ +static void nfs_init_server_aclclient(struct nfs_server *server) +{ + if (server->flags & NFS_MOUNT_NOACL) + goto out_noacl; + + server->client_acl = rpc_bind_new_program(server->client, &nfsacl_program, 3); + if (IS_ERR(server->client_acl)) + goto out_noacl; + + /* No errors! Assume that Sun nfsacls are supported */ + server->caps |= NFS_CAP_ACLS; + return; + +out_noacl: + server->caps &= ~NFS_CAP_ACLS; +} +#else +static inline void nfs_init_server_aclclient(struct nfs_server *server) +{ + server->flags &= ~NFS_MOUNT_NOACL; + server->caps &= ~NFS_CAP_ACLS; +} +#endif + +struct nfs_server *nfs3_create_server(struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) +{ + struct nfs_server *server = nfs_create_server(mount_info, nfs_mod); + /* Create a client RPC handle for the NFS v3 ACL management interface */ + if (!IS_ERR(server)) + nfs_init_server_aclclient(server); + return server; +} + +struct nfs_server *nfs3_clone_server(struct nfs_server *source, + struct nfs_fh *fh, + struct nfs_fattr *fattr, + rpc_authflavor_t flavor) +{ + struct nfs_server *server = nfs_clone_server(source, fh, fattr, flavor); + if (!IS_ERR(server) && !IS_ERR(source->client_acl)) + nfs_init_server_aclclient(server); + return server; +} diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c index 3187e24..6932209 100644 --- a/fs/nfs/nfs3proc.c +++ b/fs/nfs/nfs3proc.c @@ -69,7 +69,7 @@ do_proc_get_root(struct rpc_clnt *client, struct nfs_fh *fhandle, nfs_fattr_init(info->fattr); status = rpc_call_sync(client, &msg, 0); dprintk("%s: reply fsinfo: %d\n", __func__, status); - if (!(info->fattr->valid & NFS_ATTR_FATTR)) { + if (status == 0 && !(info->fattr->valid & NFS_ATTR_FATTR)) { msg.rpc_proc = &nfs3_procedures[NFS3PROC_GETATTR]; msg.rpc_resp = info->fattr; status = rpc_call_sync(client, &msg, 0); @@ -643,7 +643,7 @@ nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, u64 cookie, struct page **pages, unsigned int count, int plus) { struct inode *dir = dentry->d_inode; - __be32 *verf = NFS_COOKIEVERF(dir); + __be32 *verf = NFS_I(dir)->cookieverf; struct nfs3_readdirargs arg = { .fh = NFS_FH(dir), .cookie = cookie, @@ -877,6 +877,46 @@ nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl) return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl); } +static int nfs3_have_delegation(struct inode *inode, fmode_t flags) +{ + return 0; +} + +static int nfs3_return_delegation(struct inode *inode) +{ + nfs_wb_all(inode); + return 0; +} + +static const struct inode_operations nfs3_dir_inode_operations = { + .create = nfs_create, + .lookup = nfs_lookup, + .link = nfs_link, + .unlink = nfs_unlink, + .symlink = nfs_symlink, + .mkdir = nfs_mkdir, + .rmdir = nfs_rmdir, + .mknod = nfs_mknod, + .rename = nfs_rename, + .permission = nfs_permission, + .getattr = nfs_getattr, + .setattr = nfs_setattr, + .listxattr = nfs3_listxattr, + .getxattr = nfs3_getxattr, + .setxattr = nfs3_setxattr, + .removexattr = nfs3_removexattr, +}; + +static const struct inode_operations nfs3_file_inode_operations = { + .permission = nfs_permission, + .getattr = nfs_getattr, + .setattr = nfs_setattr, + .listxattr = nfs3_listxattr, + .getxattr = nfs3_getxattr, + .setxattr = nfs3_setxattr, + .removexattr = nfs3_removexattr, +}; + const struct nfs_rpc_ops nfs_v3_clientops = { .version = 3, /* protocol version */ .dentry_ops = &nfs_dentry_operations, @@ -885,6 +925,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .file_ops = &nfs_file_operations, .getroot = nfs3_proc_get_root, .submount = nfs_submount, + .try_mount = nfs_try_mount, .getattr = nfs3_proc_getattr, .setattr = nfs3_proc_setattr, .lookup = nfs3_proc_lookup, @@ -910,9 +951,11 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .pathconf = nfs3_proc_pathconf, .decode_dirent = nfs3_decode_dirent, .read_setup = nfs3_proc_read_setup, + .read_pageio_init = nfs_pageio_init_read, .read_rpc_prepare = nfs3_proc_read_rpc_prepare, .read_done = nfs3_read_done, .write_setup = nfs3_proc_write_setup, + .write_pageio_init = nfs_pageio_init_write, .write_rpc_prepare = nfs3_proc_write_rpc_prepare, .write_done = nfs3_write_done, .commit_setup = nfs3_proc_commit_setup, @@ -921,5 +964,11 @@ const struct nfs_rpc_ops nfs_v3_clientops = { .lock = nfs3_proc_lock, .clear_acl_cache = nfs3_forget_cached_acls, .close_context = nfs_close_context, + .have_delegation = nfs3_have_delegation, + .return_delegation = nfs3_return_delegation, + .alloc_client = nfs_alloc_client, .init_client = nfs_init_client, + .free_client = nfs_free_client, + .create_server = nfs3_create_server, + .clone_server = nfs3_clone_server, }; diff --git a/fs/nfs/nfs3super.c b/fs/nfs/nfs3super.c new file mode 100644 index 0000000..cc471c7 --- /dev/null +++ b/fs/nfs/nfs3super.c @@ -0,0 +1,31 @@ +/* + * Copyright (c) 2012 Netapp, Inc. All rights reserved. + */ +#include <linux/module.h> +#include <linux/nfs_fs.h> +#include "internal.h" +#include "nfs.h" + +static struct nfs_subversion nfs_v3 = { + .owner = THIS_MODULE, + .nfs_fs = &nfs_fs_type, + .rpc_vers = &nfs_version3, + .rpc_ops = &nfs_v3_clientops, + .sops = &nfs_sops, +}; + +static int __init init_nfs_v3(void) +{ + register_nfs_version(&nfs_v3); + return 0; +} + +static void __exit exit_nfs_v3(void) +{ + unregister_nfs_version(&nfs_v3); +} + +MODULE_LICENSE("GPL"); + +module_init(init_nfs_v3); +module_exit(exit_nfs_v3); diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c index 902de48..6cbe894 100644 --- a/fs/nfs/nfs3xdr.c +++ b/fs/nfs/nfs3xdr.c @@ -246,7 +246,6 @@ static void encode_nfspath3(struct xdr_stream *xdr, struct page **pages, static int decode_nfspath3(struct xdr_stream *xdr) { u32 recvd, count; - size_t hdrlen; __be32 *p; p = xdr_inline_decode(xdr, 4); @@ -255,12 +254,9 @@ static int decode_nfspath3(struct xdr_stream *xdr) count = be32_to_cpup(p); if (unlikely(count >= xdr->buf->page_len || count > NFS3_MAXPATHLEN)) goto out_nametoolong; - hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base; - recvd = xdr->buf->len - hdrlen; + recvd = xdr_read_pages(xdr, count); if (unlikely(count > recvd)) goto out_cheating; - - xdr_read_pages(xdr, count); xdr_terminate_string(xdr->buf, count); return 0; @@ -329,14 +325,14 @@ static void encode_createverf3(struct xdr_stream *xdr, const __be32 *verifier) memcpy(p, verifier, NFS3_CREATEVERFSIZE); } -static int decode_writeverf3(struct xdr_stream *xdr, __be32 *verifier) +static int decode_writeverf3(struct xdr_stream *xdr, struct nfs_write_verifier *verifier) { __be32 *p; p = xdr_inline_decode(xdr, NFS3_WRITEVERFSIZE); if (unlikely(p == NULL)) goto out_overflow; - memcpy(verifier, p, NFS3_WRITEVERFSIZE); + memcpy(verifier->data, p, NFS3_WRITEVERFSIZE); return 0; out_overflow: print_overflow_msg(__func__, xdr); @@ -1587,7 +1583,6 @@ static int decode_read3resok(struct xdr_stream *xdr, struct nfs_readres *result) { u32 eof, count, ocount, recvd; - size_t hdrlen; __be32 *p; p = xdr_inline_decode(xdr, 4 + 4 + 4); @@ -1598,13 +1593,10 @@ static int decode_read3resok(struct xdr_stream *xdr, ocount = be32_to_cpup(p++); if (unlikely(ocount != count)) goto out_mismatch; - hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base; - recvd = xdr->buf->len - hdrlen; + recvd = xdr_read_pages(xdr, count); if (unlikely(count > recvd)) goto out_cheating; - out: - xdr_read_pages(xdr, count); result->eof = eof; result->count = count; return count; @@ -1676,20 +1668,22 @@ static int decode_write3resok(struct xdr_stream *xdr, { __be32 *p; - p = xdr_inline_decode(xdr, 4 + 4 + NFS3_WRITEVERFSIZE); + p = xdr_inline_decode(xdr, 4 + 4); if (unlikely(p == NULL)) goto out_overflow; result->count = be32_to_cpup(p++); result->verf->committed = be32_to_cpup(p++); if (unlikely(result->verf->committed > NFS_FILE_SYNC)) goto out_badvalue; - memcpy(result->verf->verifier, p, NFS3_WRITEVERFSIZE); + if (decode_writeverf3(xdr, &result->verf->verifier)) + goto out_eio; return result->count; out_badvalue: dprintk("NFS: bad stable_how value: %u\n", result->verf->committed); return -EIO; out_overflow: print_overflow_msg(__func__, xdr); +out_eio: return -EIO; } @@ -2039,22 +2033,7 @@ out_truncated: */ static int decode_dirlist3(struct xdr_stream *xdr) { - u32 recvd, pglen; - size_t hdrlen; - - pglen = xdr->buf->page_len; - hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base; - recvd = xdr->buf->len - hdrlen; - if (unlikely(pglen > recvd)) - goto out_cheating; -out: - xdr_read_pages(xdr, pglen); - return pglen; -out_cheating: - dprintk("NFS: server cheating in readdir result: " - "pglen %u > recvd %u\n", pglen, recvd); - pglen = recvd; - goto out; + return xdr_read_pages(xdr, xdr->buf->page_len); } static int decode_readdir3resok(struct xdr_stream *xdr, @@ -2337,7 +2316,7 @@ static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req, goto out; if (status != NFS3_OK) goto out_status; - error = decode_writeverf3(xdr, result->verf->verifier); + error = decode_writeverf3(xdr, &result->verf->verifier); out: return error; out_status: @@ -2364,7 +2343,7 @@ static inline int decode_getacl3resok(struct xdr_stream *xdr, if (result->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT)) goto out; - hdrlen = (u8 *)xdr->p - (u8 *)xdr->iov->iov_base; + hdrlen = xdr_stream_pos(xdr); acl = NULL; if (result->mask & NFS_ACL) diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h index cc5900a..da0618a 100644 --- a/fs/nfs/nfs4_fs.h +++ b/fs/nfs/nfs4_fs.h @@ -9,7 +9,7 @@ #ifndef __LINUX_FS_NFS_NFS4_FS_H #define __LINUX_FS_NFS_NFS4_FS_H -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) struct idmap; @@ -200,7 +200,13 @@ struct nfs4_state_maintenance_ops { }; extern const struct dentry_operations nfs4_dentry_operations; -extern const struct inode_operations nfs4_dir_inode_operations; + +/* dir.c */ +int nfs_atomic_open(struct inode *, struct dentry *, struct file *, + unsigned, umode_t, int *); + +/* super.c */ +extern struct file_system_type nfs4_fs_type; /* nfs4namespace.c */ rpc_authflavor_t nfs_find_best_sec(struct nfs4_secinfo_flavors *); @@ -301,6 +307,10 @@ extern const u32 nfs4_pathconf_bitmap[2]; extern const u32 nfs4_fsinfo_bitmap[3]; extern const u32 nfs4_fs_locations_bitmap[2]; +void nfs4_free_client(struct nfs_client *); + +struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *); + /* nfs4renewd.c */ extern void nfs4_schedule_state_renewal(struct nfs_client *); extern void nfs4_renewd_prepare_shutdown(struct nfs_server *); @@ -354,6 +364,29 @@ extern void nfs4_free_lock_state(struct nfs_server *server, struct nfs4_lock_sta extern const nfs4_stateid zero_stateid; +/* nfs4super.c */ +struct nfs_mount_info; +extern struct nfs_subversion nfs_v4; +struct dentry *nfs4_try_mount(int, const char *, struct nfs_mount_info *, struct nfs_subversion *); +extern bool nfs4_disable_idmapping; +extern unsigned short max_session_slots; +extern unsigned short send_implementation_id; + +/* nfs4sysctl.c */ +#ifdef CONFIG_SYSCTL +int nfs4_register_sysctl(void); +void nfs4_unregister_sysctl(void); +#else +static inline int nfs4_register_sysctl(void) +{ + return 0; +} + +static inline void nfs4_unregister_sysctl(void) +{ +} +#endif + /* nfs4xdr.c */ extern struct rpc_procinfo nfs4_procedures[]; diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c new file mode 100644 index 0000000..24eb663 --- /dev/null +++ b/fs/nfs/nfs4client.c @@ -0,0 +1,656 @@ +/* + * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. + * Written by David Howells (dhowells@redhat.com) + */ +#include <linux/module.h> +#include <linux/nfs_fs.h> +#include <linux/nfs_idmap.h> +#include <linux/nfs_mount.h> +#include <linux/sunrpc/auth.h> +#include <linux/sunrpc/xprt.h> +#include <linux/sunrpc/bc_xprt.h> +#include "internal.h" +#include "callback.h" +#include "delegation.h" +#include "pnfs.h" +#include "netns.h" + +#define NFSDBG_FACILITY NFSDBG_CLIENT + +/* + * Get a unique NFSv4.0 callback identifier which will be used + * by the V4.0 callback service to lookup the nfs_client struct + */ +static int nfs_get_cb_ident_idr(struct nfs_client *clp, int minorversion) +{ + int ret = 0; + struct nfs_net *nn = net_generic(clp->cl_net, nfs_net_id); + + if (clp->rpc_ops->version != 4 || minorversion != 0) + return ret; +retry: + if (!idr_pre_get(&nn->cb_ident_idr, GFP_KERNEL)) + return -ENOMEM; + spin_lock(&nn->nfs_client_lock); + ret = idr_get_new(&nn->cb_ident_idr, clp, &clp->cl_cb_ident); + spin_unlock(&nn->nfs_client_lock); + if (ret == -EAGAIN) + goto retry; + return ret; +} + +#ifdef CONFIG_NFS_V4_1 +static void nfs4_shutdown_session(struct nfs_client *clp) +{ + if (nfs4_has_session(clp)) { + nfs4_destroy_session(clp->cl_session); + nfs4_destroy_clientid(clp); + } + +} +#else /* CONFIG_NFS_V4_1 */ +static void nfs4_shutdown_session(struct nfs_client *clp) +{ +} +#endif /* CONFIG_NFS_V4_1 */ + +struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init) +{ + int err; + struct nfs_client *clp = nfs_alloc_client(cl_init); + if (IS_ERR(clp)) + return clp; + + err = nfs_get_cb_ident_idr(clp, cl_init->minorversion); + if (err) + goto error; + + spin_lock_init(&clp->cl_lock); + INIT_DELAYED_WORK(&clp->cl_renewd, nfs4_renew_state); + rpc_init_wait_queue(&clp->cl_rpcwaitq, "NFS client"); + clp->cl_state = 1 << NFS4CLNT_LEASE_EXPIRED; + clp->cl_minorversion = cl_init->minorversion; + clp->cl_mvops = nfs_v4_minor_ops[cl_init->minorversion]; + return clp; + +error: + nfs_free_client(clp); + return ERR_PTR(err); +} + +/* + * Destroy the NFS4 callback service + */ +static void nfs4_destroy_callback(struct nfs_client *clp) +{ + if (__test_and_clear_bit(NFS_CS_CALLBACK, &clp->cl_res_state)) + nfs_callback_down(clp->cl_mvops->minor_version); +} + +static void nfs4_shutdown_client(struct nfs_client *clp) +{ + if (__test_and_clear_bit(NFS_CS_RENEWD, &clp->cl_res_state)) + nfs4_kill_renewd(clp); + nfs4_shutdown_session(clp); + nfs4_destroy_callback(clp); + if (__test_and_clear_bit(NFS_CS_IDMAP, &clp->cl_res_state)) + nfs_idmap_delete(clp); + + rpc_destroy_wait_queue(&clp->cl_rpcwaitq); + kfree(clp->cl_serverowner); + kfree(clp->cl_serverscope); + kfree(clp->cl_implid); +} + +void nfs4_free_client(struct nfs_client *clp) +{ + nfs4_shutdown_client(clp); + nfs_free_client(clp); +} + +/* + * Initialize the NFS4 callback service + */ +static int nfs4_init_callback(struct nfs_client *clp) +{ + int error; + + if (clp->rpc_ops->version == 4) { + struct rpc_xprt *xprt; + + xprt = rcu_dereference_raw(clp->cl_rpcclient->cl_xprt); + + if (nfs4_has_session(clp)) { + error = xprt_setup_backchannel(xprt, + NFS41_BC_MIN_CALLBACKS); + if (error < 0) + return error; + } + + error = nfs_callback_up(clp->cl_mvops->minor_version, xprt); + if (error < 0) { + dprintk("%s: failed to start callback. Error = %d\n", + __func__, error); + return error; + } + __set_bit(NFS_CS_CALLBACK, &clp->cl_res_state); + } + return 0; +} + +/* + * Initialize the minor version specific parts of an NFS4 client record + */ +static int nfs4_init_client_minor_version(struct nfs_client *clp) +{ +#if defined(CONFIG_NFS_V4_1) + if (clp->cl_mvops->minor_version) { + struct nfs4_session *session = NULL; + /* + * Create the session and mark it expired. + * When a SEQUENCE operation encounters the expired session + * it will do session recovery to initialize it. + */ + session = nfs4_alloc_session(clp); + if (!session) + return -ENOMEM; + + clp->cl_session = session; + /* + * The create session reply races with the server back + * channel probe. Mark the client NFS_CS_SESSION_INITING + * so that the client back channel can find the + * nfs_client struct + */ + nfs_mark_client_ready(clp, NFS_CS_SESSION_INITING); + } +#endif /* CONFIG_NFS_V4_1 */ + + return nfs4_init_callback(clp); +} + +/** + * nfs4_init_client - Initialise an NFS4 client record + * + * @clp: nfs_client to initialise + * @timeparms: timeout parameters for underlying RPC transport + * @ip_addr: callback IP address in presentation format + * @authflavor: authentication flavor for underlying RPC transport + * + * Returns pointer to an NFS client, or an ERR_PTR value. + */ +struct nfs_client *nfs4_init_client(struct nfs_client *clp, + const struct rpc_timeout *timeparms, + const char *ip_addr, + rpc_authflavor_t authflavour) +{ + char buf[INET6_ADDRSTRLEN + 1]; + int error; + + if (clp->cl_cons_state == NFS_CS_READY) { + /* the client is initialised already */ + dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp); + return clp; + } + + /* Check NFS protocol revision and initialize RPC op vector */ + clp->rpc_ops = &nfs_v4_clientops; + + __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags); + error = nfs_create_rpc_client(clp, timeparms, authflavour); + if (error < 0) + goto error; + + /* If no clientaddr= option was specified, find a usable cb address */ + if (ip_addr == NULL) { + struct sockaddr_storage cb_addr; + struct sockaddr *sap = (struct sockaddr *)&cb_addr; + + error = rpc_localaddr(clp->cl_rpcclient, sap, sizeof(cb_addr)); + if (error < 0) + goto error; + error = rpc_ntop(sap, buf, sizeof(buf)); + if (error < 0) + goto error; + ip_addr = (const char *)buf; + } + strlcpy(clp->cl_ipaddr, ip_addr, sizeof(clp->cl_ipaddr)); + + error = nfs_idmap_new(clp); + if (error < 0) { + dprintk("%s: failed to create idmapper. Error = %d\n", + __func__, error); + goto error; + } + __set_bit(NFS_CS_IDMAP, &clp->cl_res_state); + + error = nfs4_init_client_minor_version(clp); + if (error < 0) + goto error; + + if (!nfs4_has_session(clp)) + nfs_mark_client_ready(clp, NFS_CS_READY); + return clp; + +error: + nfs_mark_client_ready(clp, error); + nfs_put_client(clp); + dprintk("<-- nfs4_init_client() = xerror %d\n", error); + return ERR_PTR(error); +} + +static void nfs4_destroy_server(struct nfs_server *server) +{ + nfs_server_return_all_delegations(server); + unset_pnfs_layoutdriver(server); + nfs4_purge_state_owners(server); +} + +/* + * NFSv4.0 callback thread helper + * + * Find a client by callback identifier + */ +struct nfs_client * +nfs4_find_client_ident(struct net *net, int cb_ident) +{ + struct nfs_client *clp; + struct nfs_net *nn = net_generic(net, nfs_net_id); + + spin_lock(&nn->nfs_client_lock); + clp = idr_find(&nn->cb_ident_idr, cb_ident); + if (clp) + atomic_inc(&clp->cl_count); + spin_unlock(&nn->nfs_client_lock); + return clp; +} + +#if defined(CONFIG_NFS_V4_1) +/* Common match routine for v4.0 and v4.1 callback services */ +static bool nfs4_cb_match_client(const struct sockaddr *addr, + struct nfs_client *clp, u32 minorversion) +{ + struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr; + + /* Don't match clients that failed to initialise */ + if (!(clp->cl_cons_state == NFS_CS_READY || + clp->cl_cons_state == NFS_CS_SESSION_INITING)) + return false; + + smp_rmb(); + + /* Match the version and minorversion */ + if (clp->rpc_ops->version != 4 || + clp->cl_minorversion != minorversion) + return false; + + /* Match only the IP address, not the port number */ + if (!nfs_sockaddr_match_ipaddr(addr, clap)) + return false; + + return true; +} + +/* + * NFSv4.1 callback thread helper + * For CB_COMPOUND calls, find a client by IP address, protocol version, + * minorversion, and sessionID + * + * Returns NULL if no such client + */ +struct nfs_client * +nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr, + struct nfs4_sessionid *sid) +{ + struct nfs_client *clp; + struct nfs_net *nn = net_generic(net, nfs_net_id); + + spin_lock(&nn->nfs_client_lock); + list_for_each_entry(clp, &nn->nfs_client_list, cl_share_link) { + if (nfs4_cb_match_client(addr, clp, 1) == false) + continue; + + if (!nfs4_has_session(clp)) + continue; + + /* Match sessionid*/ + if (memcmp(clp->cl_session->sess_id.data, + sid->data, NFS4_MAX_SESSIONID_LEN) != 0) + continue; + + atomic_inc(&clp->cl_count); + spin_unlock(&nn->nfs_client_lock); + return clp; + } + spin_unlock(&nn->nfs_client_lock); + return NULL; +} + +#else /* CONFIG_NFS_V4_1 */ + +struct nfs_client * +nfs4_find_client_sessionid(struct net *net, const struct sockaddr *addr, + struct nfs4_sessionid *sid) +{ + return NULL; +} +#endif /* CONFIG_NFS_V4_1 */ + +/* + * Set up an NFS4 client + */ +static int nfs4_set_client(struct nfs_server *server, + const char *hostname, + const struct sockaddr *addr, + const size_t addrlen, + const char *ip_addr, + rpc_authflavor_t authflavour, + int proto, const struct rpc_timeout *timeparms, + u32 minorversion, struct net *net) +{ + struct nfs_client_initdata cl_init = { + .hostname = hostname, + .addr = addr, + .addrlen = addrlen, + .nfs_mod = &nfs_v4, + .proto = proto, + .minorversion = minorversion, + .net = net, + }; + struct nfs_client *clp; + int error; + + dprintk("--> nfs4_set_client()\n"); + + if (server->flags & NFS_MOUNT_NORESVPORT) + set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags); + + /* Allocate or find a client reference we can use */ + clp = nfs_get_client(&cl_init, timeparms, ip_addr, authflavour); + if (IS_ERR(clp)) { + error = PTR_ERR(clp); + goto error; + } + + /* + * Query for the lease time on clientid setup or renewal + * + * Note that this will be set on nfs_clients that were created + * only for the DS role and did not set this bit, but now will + * serve a dual role. + */ + set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state); + + server->nfs_client = clp; + dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp); + return 0; +error: + dprintk("<-- nfs4_set_client() = xerror %d\n", error); + return error; +} + +/* + * Set up a pNFS Data Server client. + * + * Return any existing nfs_client that matches server address,port,version + * and minorversion. + * + * For a new nfs_client, use a soft mount (default), a low retrans and a + * low timeout interval so that if a connection is lost, we retry through + * the MDS. + */ +struct nfs_client *nfs4_set_ds_client(struct nfs_client* mds_clp, + const struct sockaddr *ds_addr, int ds_addrlen, + int ds_proto, unsigned int ds_timeo, unsigned int ds_retrans) +{ + struct nfs_client_initdata cl_init = { + .addr = ds_addr, + .addrlen = ds_addrlen, + .nfs_mod = &nfs_v4, + .proto = ds_proto, + .minorversion = mds_clp->cl_minorversion, + .net = mds_clp->cl_net, + }; + struct rpc_timeout ds_timeout; + struct nfs_client *clp; + + /* + * Set an authflavor equual to the MDS value. Use the MDS nfs_client + * cl_ipaddr so as to use the same EXCHANGE_ID co_ownerid as the MDS + * (section 13.1 RFC 5661). + */ + nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans); + clp = nfs_get_client(&cl_init, &ds_timeout, mds_clp->cl_ipaddr, + mds_clp->cl_rpcclient->cl_auth->au_flavor); + + dprintk("<-- %s %p\n", __func__, clp); + return clp; +} +EXPORT_SYMBOL_GPL(nfs4_set_ds_client); + +/* + * Session has been established, and the client marked ready. + * Set the mount rsize and wsize with negotiated fore channel + * attributes which will be bound checked in nfs_server_set_fsinfo. + */ +static void nfs4_session_set_rwsize(struct nfs_server *server) +{ +#ifdef CONFIG_NFS_V4_1 + struct nfs4_session *sess; + u32 server_resp_sz; + u32 server_rqst_sz; + + if (!nfs4_has_session(server->nfs_client)) + return; + sess = server->nfs_client->cl_session; + server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead; + server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead; + + if (server->rsize > server_resp_sz) + server->rsize = server_resp_sz; + if (server->wsize > server_rqst_sz) + server->wsize = server_rqst_sz; +#endif /* CONFIG_NFS_V4_1 */ +} + +static int nfs4_server_common_setup(struct nfs_server *server, + struct nfs_fh *mntfh) +{ + struct nfs_fattr *fattr; + int error; + + BUG_ON(!server->nfs_client); + BUG_ON(!server->nfs_client->rpc_ops); + BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops); + + /* data servers support only a subset of NFSv4.1 */ + if (is_ds_only_client(server->nfs_client)) + return -EPROTONOSUPPORT; + + fattr = nfs_alloc_fattr(); + if (fattr == NULL) + return -ENOMEM; + + /* We must ensure the session is initialised first */ + error = nfs4_init_session(server); + if (error < 0) + goto out; + + /* Probe the root fh to retrieve its FSID and filehandle */ + error = nfs4_get_rootfh(server, mntfh); + if (error < 0) + goto out; + + dprintk("Server FSID: %llx:%llx\n", + (unsigned long long) server->fsid.major, + (unsigned long long) server->fsid.minor); + dprintk("Mount FH: %d\n", mntfh->size); + + nfs4_session_set_rwsize(server); + + error = nfs_probe_fsinfo(server, mntfh, fattr); + if (error < 0) + goto out; + + if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN) + server->namelen = NFS4_MAXNAMLEN; + + nfs_server_insert_lists(server); + server->mount_time = jiffies; + server->destroy = nfs4_destroy_server; +out: + nfs_free_fattr(fattr); + return error; +} + +/* + * Create a version 4 volume record + */ +static int nfs4_init_server(struct nfs_server *server, + const struct nfs_parsed_mount_data *data) +{ + struct rpc_timeout timeparms; + int error; + + dprintk("--> nfs4_init_server()\n"); + + nfs_init_timeout_values(&timeparms, data->nfs_server.protocol, + data->timeo, data->retrans); + + /* 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; + if (!(data->flags & NFS_MOUNT_NORDIRPLUS)) + server->caps |= NFS_CAP_READDIRPLUS; + server->options = data->options; + + /* Get a client record */ + error = nfs4_set_client(server, + data->nfs_server.hostname, + (const struct sockaddr *)&data->nfs_server.address, + data->nfs_server.addrlen, + data->client_address, + data->auth_flavors[0], + data->nfs_server.protocol, + &timeparms, + data->minorversion, + data->net); + if (error < 0) + goto error; + + /* + * Don't use NFS uid/gid mapping if we're using AUTH_SYS or lower + * authentication. + */ + if (nfs4_disable_idmapping && data->auth_flavors[0] == RPC_AUTH_UNIX) + server->caps |= NFS_CAP_UIDGID_NOMAP; + + if (data->rsize) + server->rsize = nfs_block_size(data->rsize, NULL); + if (data->wsize) + server->wsize = nfs_block_size(data->wsize, NULL); + + server->acregmin = data->acregmin * HZ; + server->acregmax = data->acregmax * HZ; + server->acdirmin = data->acdirmin * HZ; + server->acdirmax = data->acdirmax * HZ; + + server->port = data->nfs_server.port; + + error = nfs_init_server_rpcclient(server, &timeparms, data->auth_flavors[0]); + +error: + /* Done */ + dprintk("<-- nfs4_init_server() = %d\n", error); + return error; +} + +/* + * Create a version 4 volume record + * - keyed on server and FSID + */ +/*struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data, + struct nfs_fh *mntfh)*/ +struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) +{ + struct nfs_server *server; + int error; + + dprintk("--> nfs4_create_server()\n"); + + server = nfs_alloc_server(); + if (!server) + return ERR_PTR(-ENOMEM); + + /* set up the general RPC client */ + error = nfs4_init_server(server, mount_info->parsed); + if (error < 0) + goto error; + + error = nfs4_server_common_setup(server, mount_info->mntfh); + if (error < 0) + goto error; + + dprintk("<-- nfs4_create_server() = %p\n", server); + return server; + +error: + nfs_free_server(server); + dprintk("<-- nfs4_create_server() = error %d\n", error); + return ERR_PTR(error); +} + +/* + * Create an NFS4 referral server record + */ +struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data, + struct nfs_fh *mntfh) +{ + struct nfs_client *parent_client; + struct nfs_server *server, *parent_server; + int error; + + dprintk("--> nfs4_create_referral_server()\n"); + + server = nfs_alloc_server(); + if (!server) + return ERR_PTR(-ENOMEM); + + parent_server = NFS_SB(data->sb); + parent_client = parent_server->nfs_client; + + /* Initialise the client representation from the parent server */ + nfs_server_copy_userdata(server, parent_server); + server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR; + + /* Get a client representation. + * Note: NFSv4 always uses TCP, */ + error = nfs4_set_client(server, data->hostname, + data->addr, + data->addrlen, + parent_client->cl_ipaddr, + data->authflavor, + rpc_protocol(parent_server->client), + parent_server->client->cl_timeout, + parent_client->cl_mvops->minor_version, + parent_client->cl_net); + if (error < 0) + goto error; + + error = nfs_init_server_rpcclient(server, parent_server->client->cl_timeout, data->authflavor); + if (error < 0) + goto error; + + error = nfs4_server_common_setup(server, mntfh); + if (error < 0) + goto error; + + dprintk("<-- nfs_create_referral_server() = %p\n", server); + return server; + +error: + nfs_free_server(server); + dprintk("<-- nfs4_create_referral_server() = error %d\n", error); + return ERR_PTR(error); +} diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c new file mode 100644 index 0000000..eb5eb8e --- /dev/null +++ b/fs/nfs/nfs4file.c @@ -0,0 +1,128 @@ +/* + * linux/fs/nfs/file.c + * + * Copyright (C) 1992 Rick Sladkey + */ +#include <linux/nfs_fs.h> +#include "internal.h" +#include "pnfs.h" + +#define NFSDBG_FACILITY NFSDBG_FILE + +static int +nfs4_file_open(struct inode *inode, struct file *filp) +{ + struct nfs_open_context *ctx; + struct dentry *dentry = filp->f_path.dentry; + struct dentry *parent = NULL; + struct inode *dir; + unsigned openflags = filp->f_flags; + struct iattr attr; + int err; + + BUG_ON(inode != dentry->d_inode); + /* + * If no cached dentry exists or if it's negative, NFSv4 handled the + * opens in ->lookup() or ->create(). + * + * We only get this far for a cached positive dentry. We skipped + * revalidation, so handle it here by dropping the dentry and returning + * -EOPENSTALE. The VFS will retry the lookup/create/open. + */ + + dprintk("NFS: open file(%s/%s)\n", + dentry->d_parent->d_name.name, + dentry->d_name.name); + + if ((openflags & O_ACCMODE) == 3) + openflags--; + + /* We can't create new files here */ + openflags &= ~(O_CREAT|O_EXCL); + + parent = dget_parent(dentry); + dir = parent->d_inode; + + ctx = alloc_nfs_open_context(filp->f_path.dentry, filp->f_mode); + err = PTR_ERR(ctx); + if (IS_ERR(ctx)) + goto out; + + attr.ia_valid = ATTR_OPEN; + if (openflags & O_TRUNC) { + attr.ia_valid |= ATTR_SIZE; + attr.ia_size = 0; + nfs_wb_all(inode); + } + + inode = NFS_PROTO(dir)->open_context(dir, ctx, openflags, &attr); + if (IS_ERR(inode)) { + err = PTR_ERR(inode); + switch (err) { + 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)); + nfs_file_set_open_context(filp, ctx); + err = 0; + +out_put_ctx: + put_nfs_open_context(ctx); +out: + dput(parent); + return err; + +out_drop: + d_drop(dentry); + err = -EOPENSTALE; + goto out_put_ctx; +} + +static int +nfs4_file_fsync(struct file *file, loff_t start, loff_t end, int datasync) +{ + int ret; + struct inode *inode = file->f_path.dentry->d_inode; + + ret = filemap_write_and_wait_range(inode->i_mapping, start, end); + if (ret != 0) + goto out; + mutex_lock(&inode->i_mutex); + ret = nfs_file_fsync_commit(file, start, end, datasync); + if (!ret && !datasync) + /* application has asked for meta-data sync */ + ret = pnfs_layoutcommit_inode(inode, true); + mutex_unlock(&inode->i_mutex); +out: + return ret; +} + +const struct file_operations nfs4_file_operations = { + .llseek = nfs_file_llseek, + .read = do_sync_read, + .write = do_sync_write, + .aio_read = nfs_file_read, + .aio_write = nfs_file_write, + .mmap = nfs_file_mmap, + .open = nfs4_file_open, + .flush = nfs_file_flush, + .release = nfs_file_release, + .fsync = nfs4_file_fsync, + .lock = nfs_lock, + .flock = nfs_flock, + .splice_read = nfs_file_splice_read, + .splice_write = nfs_file_splice_write, + .check_flags = nfs_check_flags, + .setlease = nfs_setlease, +}; diff --git a/fs/nfs/nfs4filelayout.c b/fs/nfs/nfs4filelayout.c index e134029..53f94d9 100644 --- a/fs/nfs/nfs4filelayout.c +++ b/fs/nfs/nfs4filelayout.c @@ -205,9 +205,9 @@ static int filelayout_async_handle_error(struct rpc_task *task, case -EPIPE: dprintk("%s DS connection error %d\n", __func__, task->tk_status); - if (!filelayout_test_devid_invalid(devid)) - _pnfs_return_layout(inode); filelayout_mark_devid_invalid(devid); + clear_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags); + _pnfs_return_layout(inode); rpc_wake_up(&tbl->slot_tbl_waitq); nfs4_ds_disconnect(clp); /* fall through */ @@ -351,9 +351,9 @@ static void prepare_to_resend_writes(struct nfs_commit_data *data) struct nfs_page *first = nfs_list_entry(data->pages.next); data->task.tk_status = 0; - memcpy(data->verf.verifier, first->wb_verf.verifier, - sizeof(first->wb_verf.verifier)); - data->verf.verifier[0]++; /* ensure verifier mismatch */ + memcpy(&data->verf.verifier, &first->wb_verf, + sizeof(data->verf.verifier)); + data->verf.verifier.data[0]++; /* ensure verifier mismatch */ } static int filelayout_commit_done_cb(struct rpc_task *task, diff --git a/fs/nfs/nfs4filelayoutdev.c b/fs/nfs/nfs4filelayoutdev.c index a1fab8d..f81231f 100644 --- a/fs/nfs/nfs4filelayoutdev.c +++ b/fs/nfs/nfs4filelayoutdev.c @@ -728,7 +728,7 @@ get_device_info(struct inode *inode, struct nfs4_deviceid *dev_id, gfp_t gfp_fla pdev->layout_type = LAYOUT_NFSV4_1_FILES; pdev->pages = pages; pdev->pgbase = 0; - pdev->pglen = PAGE_SIZE * max_pages; + pdev->pglen = max_resp_sz; pdev->mincount = 0; rc = nfs4_proc_getdeviceinfo(server, pdev); diff --git a/fs/nfs/nfs4getroot.c b/fs/nfs/nfs4getroot.c new file mode 100644 index 0000000..6a83780 --- /dev/null +++ b/fs/nfs/nfs4getroot.c @@ -0,0 +1,49 @@ +/* +* Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. +* Written by David Howells (dhowells@redhat.com) +*/ + +#include <linux/nfs_fs.h> +#include "nfs4_fs.h" + +#define NFSDBG_FACILITY NFSDBG_CLIENT + +int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh) +{ + struct nfs_fsinfo fsinfo; + int ret = -ENOMEM; + + dprintk("--> nfs4_get_rootfh()\n"); + + fsinfo.fattr = nfs_alloc_fattr(); + if (fsinfo.fattr == NULL) + goto out; + + /* Start by getting the root filehandle from the server */ + ret = nfs4_proc_get_rootfh(server, mntfh, &fsinfo); + if (ret < 0) { + dprintk("nfs4_get_rootfh: getroot error = %d\n", -ret); + goto out; + } + + if (!(fsinfo.fattr->valid & NFS_ATTR_FATTR_TYPE) + || !S_ISDIR(fsinfo.fattr->mode)) { + printk(KERN_ERR "nfs4_get_rootfh:" + " getroot encountered non-directory\n"); + ret = -ENOTDIR; + goto out; + } + + if (fsinfo.fattr->valid & NFS_ATTR_FATTR_V4_REFERRAL) { + printk(KERN_ERR "nfs4_get_rootfh:" + " getroot obtained referral\n"); + ret = -EREMOTE; + goto out; + } + + memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid)); +out: + nfs_free_fattr(fsinfo.fattr); + dprintk("<-- nfs4_get_rootfh() = %d\n", ret); + return ret; +} diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c index c157b20..1e50326 100644 --- a/fs/nfs/nfs4proc.c +++ b/fs/nfs/nfs4proc.c @@ -43,7 +43,6 @@ #include <linux/printk.h> #include <linux/slab.h> #include <linux/sunrpc/clnt.h> -#include <linux/sunrpc/gss_api.h> #include <linux/nfs.h> #include <linux/nfs4.h> #include <linux/nfs_fs.h> @@ -73,8 +72,6 @@ #define NFS4_MAX_LOOP_ON_RECOVER (10) -static unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE; - struct nfs4_opendata; static int _nfs4_proc_open(struct nfs4_opendata *data); static int _nfs4_recover_proc_open(struct nfs4_opendata *data); @@ -259,7 +256,12 @@ static int nfs4_wait_clnt_recover(struct nfs_client *clp) res = wait_on_bit(&clp->cl_state, NFS4CLNT_MANAGER_RUNNING, nfs_wait_bit_killable, TASK_KILLABLE); - return res; + if (res) + return res; + + if (clp->cl_cons_state < 0) + return clp->cl_cons_state; + return 0; } static int nfs4_delay(struct rpc_clnt *clnt, long *timeout) @@ -294,8 +296,8 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc case 0: return 0; case -NFS4ERR_OPENMODE: - if (inode && nfs_have_delegation(inode, FMODE_READ)) { - nfs_inode_return_delegation(inode); + if (inode && nfs4_have_delegation(inode, FMODE_READ)) { + nfs4_inode_return_delegation(inode); exception->retry = 1; return 0; } @@ -1065,7 +1067,7 @@ static void nfs4_return_incompatible_delegation(struct inode *inode, fmode_t fmo return; } rcu_read_unlock(); - nfs_inode_return_delegation(inode); + nfs4_inode_return_delegation(inode); } static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata) @@ -1756,33 +1758,70 @@ static int nfs4_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *sta } #if defined(CONFIG_NFS_V4_1) -static int nfs41_check_expired_stateid(struct nfs4_state *state, nfs4_stateid *stateid, unsigned int flags) +static void nfs41_clear_delegation_stateid(struct nfs4_state *state) { - int status = NFS_OK; struct nfs_server *server = NFS_SERVER(state->inode); + nfs4_stateid *stateid = &state->stateid; + int status; + + /* If a state reset has been done, test_stateid is unneeded */ + if (test_bit(NFS_DELEGATED_STATE, &state->flags) == 0) + return; - if (state->flags & flags) { - status = nfs41_test_stateid(server, stateid); - if (status != NFS_OK) { + status = nfs41_test_stateid(server, stateid); + if (status != NFS_OK) { + /* Free the stateid unless the server explicitly + * informs us the stateid is unrecognized. */ + if (status != -NFS4ERR_BAD_STATEID) nfs41_free_stateid(server, stateid); - state->flags &= ~flags; - } + + clear_bit(NFS_DELEGATED_STATE, &state->flags); + } +} + +/** + * nfs41_check_open_stateid - possibly free an open stateid + * + * @state: NFSv4 state for an inode + * + * Returns NFS_OK if recovery for this stateid is now finished. + * Otherwise a negative NFS4ERR value is returned. + */ +static int nfs41_check_open_stateid(struct nfs4_state *state) +{ + struct nfs_server *server = NFS_SERVER(state->inode); + nfs4_stateid *stateid = &state->stateid; + int status; + + /* If a state reset has been done, test_stateid is unneeded */ + if ((test_bit(NFS_O_RDONLY_STATE, &state->flags) == 0) && + (test_bit(NFS_O_WRONLY_STATE, &state->flags) == 0) && + (test_bit(NFS_O_RDWR_STATE, &state->flags) == 0)) + return -NFS4ERR_BAD_STATEID; + + status = nfs41_test_stateid(server, stateid); + if (status != NFS_OK) { + /* Free the stateid unless the server explicitly + * informs us the stateid is unrecognized. */ + if (status != -NFS4ERR_BAD_STATEID) + nfs41_free_stateid(server, stateid); + + clear_bit(NFS_O_RDONLY_STATE, &state->flags); + clear_bit(NFS_O_WRONLY_STATE, &state->flags); + clear_bit(NFS_O_RDWR_STATE, &state->flags); } return status; } static int nfs41_open_expired(struct nfs4_state_owner *sp, struct nfs4_state *state) { - int deleg_status, open_status; - int deleg_flags = 1 << NFS_DELEGATED_STATE; - int open_flags = (1 << NFS_O_RDONLY_STATE) | (1 << NFS_O_WRONLY_STATE) | (1 << NFS_O_RDWR_STATE); - - deleg_status = nfs41_check_expired_stateid(state, &state->stateid, deleg_flags); - open_status = nfs41_check_expired_stateid(state, &state->open_stateid, open_flags); + int status; - if ((deleg_status == NFS_OK) && (open_status == NFS_OK)) - return NFS_OK; - return nfs4_open_expired(sp, state); + nfs41_clear_delegation_stateid(state); + status = nfs41_check_open_stateid(state); + if (status != NFS_OK) + status = nfs4_open_expired(sp, state); + return status; } #endif @@ -2375,11 +2414,15 @@ static int nfs4_find_root_sec(struct nfs_server *server, struct nfs_fh *fhandle, int i, len, status = 0; rpc_authflavor_t flav_array[NFS_MAX_SECFLAVORS]; - len = gss_mech_list_pseudoflavors(&flav_array[0]); - flav_array[len] = RPC_AUTH_NULL; - len += 1; + len = rpcauth_list_flavors(flav_array, ARRAY_SIZE(flav_array)); + BUG_ON(len < 0); for (i = 0; i < len; i++) { + /* AUTH_UNIX is the default flavor if none was specified, + * thus has already been tried. */ + if (flav_array[i] == RPC_AUTH_UNIX) + continue; + status = nfs4_lookup_root_sec(server, fhandle, info, flav_array[i]); if (status == -NFS4ERR_WRONGSEC || status == -EACCES) continue; @@ -2766,9 +2809,7 @@ static int nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry) * * In the case of WRITE, we also want to put the GETATTR after * the operation -- in this case because we want to make sure - * we get the post-operation mtime and size. This means that - * we can't use xdr_encode_pages() as written: we need a variant - * of it which would leave room in the 'tail' iovec. + * we get the post-operation mtime and size. * * Both of these changes to the XDR layer would in fact be quite * minor, but I decided to leave them for a subsequent patch. @@ -2821,7 +2862,9 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr, return PTR_ERR(ctx); sattr->ia_mode &= ~current_umask(); - state = nfs4_do_open(dir, dentry, ctx->mode, flags, sattr, ctx->cred, NULL); + state = nfs4_do_open(dir, dentry, ctx->mode, + flags, sattr, ctx->cred, + &ctx->mdsthreshold); d_drop(dentry); if (IS_ERR(state)) { status = PTR_ERR(state); @@ -3172,11 +3215,11 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred, dentry->d_parent->d_name.name, dentry->d_name.name, (unsigned long long)cookie); - nfs4_setup_readdir(cookie, NFS_COOKIEVERF(dir), dentry, &args); + nfs4_setup_readdir(cookie, NFS_I(dir)->cookieverf, dentry, &args); res.pgbase = args.pgbase; status = nfs4_call_sync(NFS_SERVER(dir)->client, NFS_SERVER(dir), &msg, &args.seq_args, &res.seq_res, 0); if (status >= 0) { - memcpy(NFS_COOKIEVERF(dir), res.verifier.data, NFS4_VERIFIER_SIZE); + memcpy(NFS_I(dir)->cookieverf, res.verifier.data, NFS4_VERIFIER_SIZE); status += args.pgbase; } @@ -3315,8 +3358,14 @@ static int nfs4_do_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, str static int nfs4_proc_fsinfo(struct nfs_server *server, struct nfs_fh *fhandle, struct nfs_fsinfo *fsinfo) { + int error; + nfs_fattr_init(fsinfo->fattr); - return nfs4_do_fsinfo(server, fhandle, fsinfo); + error = nfs4_do_fsinfo(server, fhandle, fsinfo); + if (error == 0) + set_pnfs_layoutdriver(server, fhandle, fsinfo->layouttype); + + return error; } static int _nfs4_proc_pathconf(struct nfs_server *server, struct nfs_fh *fhandle, @@ -3443,7 +3492,7 @@ bool nfs4_write_need_cache_consistency_data(const struct nfs_write_data *data) /* Otherwise, request attributes if and only if we don't hold * a delegation */ - return nfs_have_delegation(hdr->inode, FMODE_READ) == 0; + return nfs4_have_delegation(hdr->inode, FMODE_READ) == 0; } static void nfs4_proc_write_setup(struct nfs_write_data *data, struct rpc_message *msg) @@ -3604,11 +3653,11 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server) && (server->acl_bitmask & ACL4_SUPPORT_DENY_ACL); } -/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_CACHE_SIZE, and that - * it's OK to put sizeof(void) * (XATTR_SIZE_MAX/PAGE_CACHE_SIZE) bytes on +/* Assuming that XATTR_SIZE_MAX is a multiple of PAGE_SIZE, and that + * it's OK to put sizeof(void) * (XATTR_SIZE_MAX/PAGE_SIZE) bytes on * the stack. */ -#define NFS4ACL_MAXPAGES (XATTR_SIZE_MAX >> PAGE_CACHE_SHIFT) +#define NFS4ACL_MAXPAGES DIV_ROUND_UP(XATTR_SIZE_MAX, PAGE_SIZE) static int buf_to_pages_noslab(const void *buf, size_t buflen, struct page **pages, unsigned int *pgbase) @@ -3619,7 +3668,7 @@ static int buf_to_pages_noslab(const void *buf, size_t buflen, spages = pages; do { - len = min_t(size_t, PAGE_CACHE_SIZE, buflen); + len = min_t(size_t, PAGE_SIZE, buflen); newpage = alloc_page(GFP_KERNEL); if (newpage == NULL) @@ -3688,9 +3737,10 @@ out: static void nfs4_write_cached_acl(struct inode *inode, struct page **pages, size_t pgbase, size_t acl_len) { struct nfs4_cached_acl *acl; + size_t buflen = sizeof(*acl) + acl_len; - if (pages && acl_len <= PAGE_SIZE) { - acl = kmalloc(sizeof(*acl) + acl_len, GFP_KERNEL); + if (buflen <= PAGE_SIZE) { + acl = kmalloc(buflen, GFP_KERNEL); if (acl == NULL) goto out; acl->cached = 1; @@ -3732,16 +3782,15 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu .rpc_argp = &args, .rpc_resp = &res, }; - int ret = -ENOMEM, npages, i, acl_len = 0; + unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE); + int ret = -ENOMEM, i; - npages = (buflen + PAGE_SIZE - 1) >> PAGE_SHIFT; /* As long as we're doing a round trip to the server anyway, * let's be prepared for a page of acl data. */ if (npages == 0) npages = 1; - - /* Add an extra page to handle the bitmap returned */ - npages++; + if (npages > ARRAY_SIZE(pages)) + return -ERANGE; for (i = 0; i < npages; i++) { pages[i] = alloc_page(GFP_KERNEL); @@ -3757,11 +3806,6 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu args.acl_len = npages * PAGE_SIZE; args.acl_pgbase = 0; - /* Let decode_getfacl know not to fail if the ACL data is larger than - * the page we send as a guess */ - if (buf == NULL) - res.acl_flags |= NFS4_ACL_LEN_REQUEST; - dprintk("%s buf %p buflen %zu npages %d args.acl_len %zu\n", __func__, buf, buflen, npages, args.acl_len); ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), @@ -3769,20 +3813,19 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu if (ret) goto out_free; - acl_len = res.acl_len - res.acl_data_offset; - if (acl_len > args.acl_len) - nfs4_write_cached_acl(inode, NULL, 0, acl_len); - else - nfs4_write_cached_acl(inode, pages, res.acl_data_offset, - acl_len); - if (buf) { + /* Handle the case where the passed-in buffer is too short */ + if (res.acl_flags & NFS4_ACL_TRUNC) { + /* Did the user only issue a request for the acl length? */ + if (buf == NULL) + goto out_ok; ret = -ERANGE; - if (acl_len > buflen) - goto out_free; - _copy_from_pages(buf, pages, res.acl_data_offset, - acl_len); + goto out_free; } - ret = acl_len; + nfs4_write_cached_acl(inode, pages, res.acl_data_offset, res.acl_len); + if (buf) + _copy_from_pages(buf, pages, res.acl_data_offset, res.acl_len); +out_ok: + ret = res.acl_len; out_free: for (i = 0; i < npages; i++) if (pages[i]) @@ -3840,14 +3883,17 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl .rpc_argp = &arg, .rpc_resp = &res, }; + unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE); int ret, i; if (!nfs4_server_supports_acls(server)) return -EOPNOTSUPP; + if (npages > ARRAY_SIZE(pages)) + return -ERANGE; i = buf_to_pages_noslab(buf, buflen, arg.acl_pages, &arg.acl_pgbase); if (i < 0) return i; - nfs_inode_return_delegation(inode); + nfs4_inode_return_delegation(inode); ret = nfs4_call_sync(server->client, server, &msg, &arg.seq_args, &res.seq_res, 1); /* @@ -3961,6 +4007,16 @@ static void nfs4_init_boot_verifier(const struct nfs_client *clp, memcpy(bootverf->data, verf, sizeof(bootverf->data)); } +/** + * nfs4_proc_setclientid - Negotiate client ID + * @clp: state data structure + * @program: RPC program for NFSv4 callback service + * @port: IP port number for NFS4 callback service + * @cred: RPC credential to use for this call + * @res: where to place the result + * + * Returns zero, a negative errno, or a negative NFS4ERR status code. + */ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, unsigned short port, struct rpc_cred *cred, struct nfs4_setclientid_res *res) @@ -3977,44 +4033,44 @@ int nfs4_proc_setclientid(struct nfs_client *clp, u32 program, .rpc_resp = res, .rpc_cred = cred, }; - int loop = 0; int status; + /* nfs_client_id4 */ nfs4_init_boot_verifier(clp, &sc_verifier); - - for(;;) { - rcu_read_lock(); - setclientid.sc_name_len = scnprintf(setclientid.sc_name, - sizeof(setclientid.sc_name), "%s/%s %s %s %u", - clp->cl_ipaddr, - rpc_peeraddr2str(clp->cl_rpcclient, - RPC_DISPLAY_ADDR), - rpc_peeraddr2str(clp->cl_rpcclient, - RPC_DISPLAY_PROTO), - clp->cl_rpcclient->cl_auth->au_ops->au_name, - clp->cl_id_uniquifier); - setclientid.sc_netid_len = scnprintf(setclientid.sc_netid, + rcu_read_lock(); + setclientid.sc_name_len = scnprintf(setclientid.sc_name, + sizeof(setclientid.sc_name), "%s/%s %s", + clp->cl_ipaddr, + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_ADDR), + rpc_peeraddr2str(clp->cl_rpcclient, + RPC_DISPLAY_PROTO)); + /* cb_client4 */ + setclientid.sc_netid_len = scnprintf(setclientid.sc_netid, sizeof(setclientid.sc_netid), rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_NETID)); - setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr, + rcu_read_unlock(); + setclientid.sc_uaddr_len = scnprintf(setclientid.sc_uaddr, sizeof(setclientid.sc_uaddr), "%s.%u.%u", clp->cl_ipaddr, port >> 8, port & 255); - rcu_read_unlock(); - status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); - if (status != -NFS4ERR_CLID_INUSE) - break; - if (loop != 0) { - ++clp->cl_id_uniquifier; - break; - } - ++loop; - ssleep(clp->cl_lease_time / HZ + 1); - } + dprintk("NFS call setclientid auth=%s, '%.*s'\n", + clp->cl_rpcclient->cl_auth->au_ops->au_name, + setclientid.sc_name_len, setclientid.sc_name); + status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); + dprintk("NFS reply setclientid: %d\n", status); return status; } +/** + * nfs4_proc_setclientid_confirm - Confirm client ID + * @clp: state data structure + * @res: result of a previous SETCLIENTID + * @cred: RPC credential to use for this call + * + * Returns zero, a negative errno, or a negative NFS4ERR status code. + */ int nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct nfs4_setclientid_res *arg, struct rpc_cred *cred) @@ -4029,6 +4085,9 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp, unsigned long now; int status; + dprintk("NFS call setclientid_confirm auth=%s, (client ID %llx)\n", + clp->cl_rpcclient->cl_auth->au_ops->au_name, + clp->cl_clientid); now = jiffies; status = rpc_call_sync(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT); if (status == 0) { @@ -4037,6 +4096,7 @@ int nfs4_proc_setclientid_confirm(struct nfs_client *clp, clp->cl_last_renewal = now; spin_unlock(&clp->cl_lock); } + dprintk("NFS reply setclientid_confirm: %d\n", status); return status; } @@ -4681,9 +4741,17 @@ out: } #if defined(CONFIG_NFS_V4_1) +/** + * nfs41_check_expired_locks - possibly free a lock stateid + * + * @state: NFSv4 state for an inode + * + * Returns NFS_OK if recovery for this stateid is now finished. + * Otherwise a negative NFS4ERR value is returned. + */ static int nfs41_check_expired_locks(struct nfs4_state *state) { - int status, ret = NFS_OK; + int status, ret = -NFS4ERR_BAD_STATEID; struct nfs4_lock_state *lsp; struct nfs_server *server = NFS_SERVER(state->inode); @@ -4691,7 +4759,11 @@ static int nfs41_check_expired_locks(struct nfs4_state *state) if (lsp->ls_flags & NFS_LOCK_INITIALIZED) { status = nfs41_test_stateid(server, &lsp->ls_stateid); if (status != NFS_OK) { - nfs41_free_stateid(server, &lsp->ls_stateid); + /* Free the stateid unless the server + * informs us the stateid is unrecognized. */ + if (status != -NFS4ERR_BAD_STATEID) + nfs41_free_stateid(server, + &lsp->ls_stateid); lsp->ls_flags &= ~NFS_LOCK_INITIALIZED; ret = status; } @@ -4707,9 +4779,9 @@ static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *reques if (test_bit(LK_STATE_IN_USE, &state->flags)) status = nfs41_check_expired_locks(state); - if (status == NFS_OK) - return status; - return nfs4_lock_expired(state, request); + if (status != NFS_OK) + status = nfs4_lock_expired(state, request); + return status; } #endif @@ -4807,7 +4879,7 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request) * Don't rely on the VFS having checked the file open mode, * since it won't do this for flock() locks. */ - switch (request->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) { + switch (request->fl_type) { case F_RDLCK: if (!(filp->f_mode & FMODE_READ)) return -EBADF; @@ -5168,6 +5240,8 @@ out: /* * nfs4_proc_exchange_id() * + * Returns zero, a negative errno, or a negative NFS4ERR status code. + * * Since the clientid has expired, all compounds using sessions * associated with the stale clientid will be returning * NFS4ERR_BADSESSION in the sequence operation, and will therefore @@ -5192,16 +5266,14 @@ int nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred) .rpc_cred = cred, }; - dprintk("--> %s\n", __func__); - BUG_ON(clp == NULL); - nfs4_init_boot_verifier(clp, &verifier); - args.id_len = scnprintf(args.id, sizeof(args.id), - "%s/%s/%u", + "%s/%s", clp->cl_ipaddr, - clp->cl_rpcclient->cl_nodename, - clp->cl_rpcclient->cl_auth->au_flavor); + clp->cl_rpcclient->cl_nodename); + dprintk("NFS call exchange_id auth=%s, '%.*s'\n", + clp->cl_rpcclient->cl_auth->au_ops->au_name, + args.id_len, args.id); res.server_owner = kzalloc(sizeof(struct nfs41_server_owner), GFP_NOFS); @@ -5264,12 +5336,12 @@ out_server_scope: kfree(res.server_scope); out: if (clp->cl_implid != NULL) - dprintk("%s: Server Implementation ID: " + dprintk("NFS reply exchange_id: Server Implementation ID: " "domain: %s, name: %s, date: %llu,%u\n", - __func__, clp->cl_implid->domain, clp->cl_implid->name, + clp->cl_implid->domain, clp->cl_implid->name, clp->cl_implid->date.seconds, clp->cl_implid->date.nseconds); - dprintk("<-- %s status= %d\n", __func__, status); + dprintk("NFS reply exchange_id: %d\n", status); return status; } @@ -6147,11 +6219,58 @@ static void nfs4_layoutget_done(struct rpc_task *task, void *calldata) dprintk("<-- %s\n", __func__); } +static size_t max_response_pages(struct nfs_server *server) +{ + u32 max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; + return nfs_page_array_len(0, max_resp_sz); +} + +static void nfs4_free_pages(struct page **pages, size_t size) +{ + int i; + + if (!pages) + return; + + for (i = 0; i < size; i++) { + if (!pages[i]) + break; + __free_page(pages[i]); + } + kfree(pages); +} + +static struct page **nfs4_alloc_pages(size_t size, gfp_t gfp_flags) +{ + struct page **pages; + int i; + + pages = kcalloc(size, sizeof(struct page *), gfp_flags); + if (!pages) { + dprintk("%s: can't alloc array of %zu pages\n", __func__, size); + return NULL; + } + + for (i = 0; i < size; i++) { + pages[i] = alloc_page(gfp_flags); + if (!pages[i]) { + dprintk("%s: failed to allocate page\n", __func__); + nfs4_free_pages(pages, size); + return NULL; + } + } + + return pages; +} + static void nfs4_layoutget_release(void *calldata) { struct nfs4_layoutget *lgp = calldata; + struct nfs_server *server = NFS_SERVER(lgp->args.inode); + size_t max_pages = max_response_pages(server); dprintk("--> %s\n", __func__); + nfs4_free_pages(lgp->args.layout.pages, max_pages); put_nfs_open_context(lgp->args.ctx); kfree(calldata); dprintk("<-- %s\n", __func__); @@ -6163,9 +6282,10 @@ static const struct rpc_call_ops nfs4_layoutget_call_ops = { .rpc_release = nfs4_layoutget_release, }; -int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) +void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags) { struct nfs_server *server = NFS_SERVER(lgp->args.inode); + size_t max_pages = max_response_pages(server); struct rpc_task *task; struct rpc_message msg = { .rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LAYOUTGET], @@ -6183,12 +6303,19 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) dprintk("--> %s\n", __func__); + lgp->args.layout.pages = nfs4_alloc_pages(max_pages, gfp_flags); + if (!lgp->args.layout.pages) { + nfs4_layoutget_release(lgp); + return; + } + lgp->args.layout.pglen = max_pages * PAGE_SIZE; + lgp->res.layoutp = &lgp->args.layout; lgp->res.seq_res.sr_slot = NULL; nfs41_init_sequence(&lgp->args.seq_args, &lgp->res.seq_res, 0); task = rpc_run_task(&task_setup_data); if (IS_ERR(task)) - return PTR_ERR(task); + return; status = nfs4_wait_for_completion_rpc_task(task); if (status == 0) status = task->tk_status; @@ -6196,7 +6323,7 @@ int nfs4_proc_layoutget(struct nfs4_layoutget *lgp) status = pnfs_layout_process(lgp); rpc_put_task(task); dprintk("<-- %s status=%d\n", __func__, status); - return status; + return; } static void @@ -6228,12 +6355,8 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata) return; } spin_lock(&lo->plh_inode->i_lock); - if (task->tk_status == 0) { - if (lrp->res.lrs_present) { - pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); - } else - BUG_ON(!list_empty(&lo->plh_segs)); - } + if (task->tk_status == 0 && lrp->res.lrs_present) + pnfs_set_layout_stateid(lo, &lrp->res.stateid, true); lo->plh_block_lgets--; spin_unlock(&lo->plh_inode->i_lock); dprintk("<-- %s\n", __func__); @@ -6570,22 +6693,36 @@ static int _nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid) .rpc_resp = &res, }; + dprintk("NFS call test_stateid %p\n", stateid); nfs41_init_sequence(&args.seq_args, &res.seq_res, 0); status = nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1); - - if (status == NFS_OK) - return res.status; - return status; + if (status != NFS_OK) { + dprintk("NFS reply test_stateid: failed, %d\n", status); + return status; + } + dprintk("NFS reply test_stateid: succeeded, %d\n", -res.status); + return -res.status; } +/** + * nfs41_test_stateid - perform a TEST_STATEID operation + * + * @server: server / transport on which to perform the operation + * @stateid: state ID to test + * + * Returns NFS_OK if the server recognizes that "stateid" is valid. + * Otherwise a negative NFS4ERR value is returned if the operation + * failed or the state ID is not currently valid. + */ static int nfs41_test_stateid(struct nfs_server *server, nfs4_stateid *stateid) { struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(server, - _nfs41_test_stateid(server, stateid), - &exception); + err = _nfs41_test_stateid(server, stateid); + if (err != -NFS4ERR_DELAY) + break; + nfs4_handle_exception(server, err, &exception); } while (exception.retry); return err; } @@ -6601,19 +6738,34 @@ static int _nfs4_free_stateid(struct nfs_server *server, nfs4_stateid *stateid) .rpc_argp = &args, .rpc_resp = &res, }; + int status; + dprintk("NFS call free_stateid %p\n", stateid); nfs41_init_sequence(&args.seq_args, &res.seq_res, 0); - return nfs4_call_sync_sequence(server->client, server, &msg, &args.seq_args, &res.seq_res, 1); + status = nfs4_call_sync_sequence(server->client, server, &msg, + &args.seq_args, &res.seq_res, 1); + dprintk("NFS reply free_stateid: %d\n", status); + return status; } +/** + * nfs41_free_stateid - perform a FREE_STATEID operation + * + * @server: server / transport on which to perform the operation + * @stateid: state ID to release + * + * Returns NFS_OK if the server freed "stateid". Otherwise a + * negative NFS4ERR value is returned. + */ static int nfs41_free_stateid(struct nfs_server *server, nfs4_stateid *stateid) { struct nfs4_exception exception = { }; int err; do { - err = nfs4_handle_exception(server, - _nfs4_free_stateid(server, stateid), - &exception); + err = _nfs4_free_stateid(server, stateid); + if (err != -NFS4ERR_DELAY) + break; + nfs4_handle_exception(server, err, &exception); } while (exception.retry); return err; } @@ -6725,6 +6877,26 @@ const struct nfs4_minor_version_ops *nfs_v4_minor_ops[] = { #endif }; +const struct inode_operations nfs4_dir_inode_operations = { + .create = nfs_create, + .lookup = nfs_lookup, + .atomic_open = nfs_atomic_open, + .link = nfs_link, + .unlink = nfs_unlink, + .symlink = nfs_symlink, + .mkdir = nfs_mkdir, + .rmdir = nfs_rmdir, + .mknod = nfs_mknod, + .rename = nfs_rename, + .permission = nfs_permission, + .getattr = nfs_getattr, + .setattr = nfs_setattr, + .getxattr = generic_getxattr, + .setxattr = generic_setxattr, + .listxattr = generic_listxattr, + .removexattr = generic_removexattr, +}; + static const struct inode_operations nfs4_file_inode_operations = { .permission = nfs_permission, .getattr = nfs_getattr, @@ -6743,6 +6915,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .file_ops = &nfs4_file_operations, .getroot = nfs4_proc_get_root, .submount = nfs4_submount, + .try_mount = nfs4_try_mount, .getattr = nfs4_proc_getattr, .setattr = nfs4_proc_setattr, .lookup = nfs4_proc_lookup, @@ -6769,9 +6942,11 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .set_capabilities = nfs4_server_capabilities, .decode_dirent = nfs4_decode_dirent, .read_setup = nfs4_proc_read_setup, + .read_pageio_init = pnfs_pageio_init_read, .read_rpc_prepare = nfs4_proc_read_rpc_prepare, .read_done = nfs4_read_done, .write_setup = nfs4_proc_write_setup, + .write_pageio_init = pnfs_pageio_init_write, .write_rpc_prepare = nfs4_proc_write_rpc_prepare, .write_done = nfs4_write_done, .commit_setup = nfs4_proc_commit_setup, @@ -6781,7 +6956,13 @@ const struct nfs_rpc_ops nfs_v4_clientops = { .clear_acl_cache = nfs4_zap_acl_attr, .close_context = nfs4_close_context, .open_context = nfs4_atomic_open, + .have_delegation = nfs4_have_delegation, + .return_delegation = nfs4_inode_return_delegation, + .alloc_client = nfs4_alloc_client, .init_client = nfs4_init_client, + .free_client = nfs4_free_client, + .create_server = nfs4_create_server, + .clone_server = nfs_clone_server, }; static const struct xattr_handler nfs4_xattr_nfs4_acl_handler = { @@ -6796,10 +6977,6 @@ const struct xattr_handler *nfs4_xattr_handlers[] = { NULL }; -module_param(max_session_slots, ushort, 0644); -MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 " - "requests the client will negotiate"); - /* * Local variables: * c-basic-offset: 8 diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c index f38300e..55148de 100644 --- a/fs/nfs/nfs4state.c +++ b/fs/nfs/nfs4state.c @@ -1606,10 +1606,15 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) return -ESERVERFAULT; /* Lease confirmation error: retry after purging the lease */ ssleep(1); - case -NFS4ERR_CLID_INUSE: case -NFS4ERR_STALE_CLIENTID: clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); break; + case -NFS4ERR_CLID_INUSE: + pr_err("NFS: Server %s reports our clientid is in use\n", + clp->cl_hostname); + nfs_mark_client_ready(clp, -EPERM); + clear_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state); + return -EPERM; case -EACCES: if (clp->cl_machine_cred == NULL) return -EACCES; @@ -1642,7 +1647,7 @@ static int nfs4_handle_reclaim_lease_error(struct nfs_client *clp, int status) return 0; } -static int nfs4_reclaim_lease(struct nfs_client *clp) +static int nfs4_establish_lease(struct nfs_client *clp) { struct rpc_cred *cred; const struct nfs4_state_recovery_ops *ops = @@ -1655,7 +1660,41 @@ static int nfs4_reclaim_lease(struct nfs_client *clp) status = ops->establish_clid(clp, cred); put_rpccred(cred); if (status != 0) + return status; + pnfs_destroy_all_layouts(clp); + return 0; +} + +/* + * Returns zero or a negative errno. NFS4ERR values are converted + * to local errno values. + */ +static int nfs4_reclaim_lease(struct nfs_client *clp) +{ + int status; + + status = nfs4_establish_lease(clp); + if (status < 0) + return nfs4_handle_reclaim_lease_error(clp, status); + if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, &clp->cl_state)) + nfs4_state_start_reclaim_nograce(clp); + if (!test_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) + set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state); + clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); + clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + return 0; +} + +static int nfs4_purge_lease(struct nfs_client *clp) +{ + int status; + + status = nfs4_establish_lease(clp); + if (status < 0) return nfs4_handle_reclaim_lease_error(clp, status); + clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state); + set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + nfs4_state_start_reclaim_nograce(clp); return 0; } @@ -1764,6 +1803,8 @@ static int nfs4_reset_session(struct nfs_client *clp) struct rpc_cred *cred; int status; + if (!nfs4_has_session(clp)) + return 0; nfs4_begin_drain_session(clp); cred = nfs4_get_exchange_id_cred(clp); status = nfs4_proc_destroy_session(clp->cl_session, cred); @@ -1792,12 +1833,14 @@ out: static int nfs4_recall_slot(struct nfs_client *clp) { - struct nfs4_slot_table *fc_tbl = &clp->cl_session->fc_slot_table; - struct nfs4_channel_attrs *fc_attrs = &clp->cl_session->fc_attrs; + struct nfs4_slot_table *fc_tbl; struct nfs4_slot *new, *old; int i; + if (!nfs4_has_session(clp)) + return 0; nfs4_begin_drain_session(clp); + fc_tbl = &clp->cl_session->fc_slot_table; new = kmalloc(fc_tbl->target_max_slots * sizeof(struct nfs4_slot), GFP_NOFS); if (!new) @@ -1810,11 +1853,10 @@ static int nfs4_recall_slot(struct nfs_client *clp) fc_tbl->slots = new; fc_tbl->max_slots = fc_tbl->target_max_slots; fc_tbl->target_max_slots = 0; - fc_attrs->max_reqs = fc_tbl->max_slots; + clp->cl_session->fc_attrs.max_reqs = fc_tbl->max_slots; spin_unlock(&fc_tbl->slot_tbl_lock); kfree(old); - nfs4_end_drain_session(clp); return 0; } @@ -1823,6 +1865,8 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp) struct rpc_cred *cred; int ret; + if (!nfs4_has_session(clp)) + return 0; nfs4_begin_drain_session(clp); cred = nfs4_get_exchange_id_cred(clp); ret = nfs4_proc_bind_conn_to_session(clp, cred); @@ -1857,37 +1901,29 @@ static int nfs4_bind_conn_to_session(struct nfs_client *clp) static void nfs4_state_manager(struct nfs_client *clp) { int status = 0; + const char *section = "", *section_sep = ""; /* Ensure exclusive access to NFSv4 state */ do { if (test_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state)) { - status = nfs4_reclaim_lease(clp); + section = "purge state"; + status = nfs4_purge_lease(clp); if (status < 0) goto out_error; - clear_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state); - set_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state); + continue; } - if (test_and_clear_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) { + if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) { + section = "lease expired"; /* We're going to have to re-establish a clientid */ status = nfs4_reclaim_lease(clp); if (status < 0) goto out_error; - if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) - continue; - clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state); - - if (test_and_clear_bit(NFS4CLNT_SERVER_SCOPE_MISMATCH, - &clp->cl_state)) - nfs4_state_start_reclaim_nograce(clp); - else - set_bit(NFS4CLNT_RECLAIM_REBOOT, - &clp->cl_state); - - pnfs_destroy_all_layouts(clp); + continue; } if (test_and_clear_bit(NFS4CLNT_CHECK_LEASE, &clp->cl_state)) { + section = "check lease"; status = nfs4_check_lease(clp); if (status < 0) goto out_error; @@ -1896,8 +1932,8 @@ static void nfs4_state_manager(struct nfs_client *clp) } /* Initialize or reset the session */ - if (test_and_clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state) - && nfs4_has_session(clp)) { + if (test_and_clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state)) { + section = "reset session"; status = nfs4_reset_session(clp); if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state)) continue; @@ -1907,15 +1943,26 @@ static void nfs4_state_manager(struct nfs_client *clp) /* Send BIND_CONN_TO_SESSION */ if (test_and_clear_bit(NFS4CLNT_BIND_CONN_TO_SESSION, - &clp->cl_state) && nfs4_has_session(clp)) { + &clp->cl_state)) { + section = "bind conn to session"; status = nfs4_bind_conn_to_session(clp); if (status < 0) goto out_error; continue; } + /* Recall session slots */ + if (test_and_clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state)) { + section = "recall slot"; + status = nfs4_recall_slot(clp); + if (status < 0) + goto out_error; + continue; + } + /* First recover reboot state... */ if (test_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state)) { + section = "reclaim reboot"; status = nfs4_do_reclaim(clp, clp->cl_mvops->reboot_recovery_ops); if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) || @@ -1930,6 +1977,7 @@ static void nfs4_state_manager(struct nfs_client *clp) /* Now recover expired state... */ if (test_and_clear_bit(NFS4CLNT_RECLAIM_NOGRACE, &clp->cl_state)) { + section = "reclaim nograce"; status = nfs4_do_reclaim(clp, clp->cl_mvops->nograce_recovery_ops); if (test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) || @@ -1945,15 +1993,6 @@ static void nfs4_state_manager(struct nfs_client *clp) nfs_client_return_marked_delegations(clp); continue; } - /* Recall session slots */ - if (test_and_clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state) - && nfs4_has_session(clp)) { - status = nfs4_recall_slot(clp); - if (status < 0) - goto out_error; - continue; - } - nfs4_clear_state_manager_bit(clp); /* Did we race with an attempt to give us more work? */ @@ -1964,8 +2003,11 @@ static void nfs4_state_manager(struct nfs_client *clp) } while (atomic_read(&clp->cl_count) > 1); return; out_error: - pr_warn_ratelimited("NFS: state manager failed on NFSv4 server %s" - " with error %d\n", clp->cl_hostname, -status); + if (strlen(section)) + section_sep = ": "; + pr_warn_ratelimited("NFS: state manager%s%s failed on NFSv4 server %s" + " with error %d\n", section_sep, section, + clp->cl_hostname, -status); nfs4_end_drain_session(clp); nfs4_clear_state_manager_bit(clp); } diff --git a/fs/nfs/nfs4super.c b/fs/nfs/nfs4super.c new file mode 100644 index 0000000..bd61221 --- /dev/null +++ b/fs/nfs/nfs4super.c @@ -0,0 +1,357 @@ +/* + * Copyright (c) 2012 Bryan Schumaker <bjschuma@netapp.com> + */ +#include <linux/init.h> +#include <linux/module.h> +#include <linux/nfs_idmap.h> +#include <linux/nfs4_mount.h> +#include <linux/nfs_fs.h> +#include "delegation.h" +#include "internal.h" +#include "nfs4_fs.h" +#include "pnfs.h" +#include "nfs.h" + +#define NFSDBG_FACILITY NFSDBG_VFS + +static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc); +static void nfs4_evict_inode(struct inode *inode); +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_referral_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); +static struct dentry *nfs4_remote_referral_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data); + +static struct file_system_type nfs4_remote_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .mount = nfs4_remote_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, +}; + +static struct file_system_type nfs4_remote_referral_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .mount = nfs4_remote_referral_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, +}; + +struct file_system_type nfs4_referral_fs_type = { + .owner = THIS_MODULE, + .name = "nfs4", + .mount = nfs4_referral_mount, + .kill_sb = nfs_kill_super, + .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, +}; + +static const struct super_operations nfs4_sops = { + .alloc_inode = nfs_alloc_inode, + .destroy_inode = nfs_destroy_inode, + .write_inode = nfs4_write_inode, + .put_super = nfs_put_super, + .statfs = nfs_statfs, + .evict_inode = nfs4_evict_inode, + .umount_begin = nfs_umount_begin, + .show_options = nfs_show_options, + .show_devname = nfs_show_devname, + .show_path = nfs_show_path, + .show_stats = nfs_show_stats, + .remount_fs = nfs_remount, +}; + +struct nfs_subversion nfs_v4 = { + .owner = THIS_MODULE, + .nfs_fs = &nfs4_fs_type, + .rpc_vers = &nfs_version4, + .rpc_ops = &nfs_v4_clientops, + .sops = &nfs4_sops, + .xattr = nfs4_xattr_handlers, +}; + +static int nfs4_write_inode(struct inode *inode, struct writeback_control *wbc) +{ + int ret = nfs_write_inode(inode, wbc); + + if (ret >= 0 && test_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags)) { + int status; + bool sync = true; + + if (wbc->sync_mode == WB_SYNC_NONE) + sync = false; + + status = pnfs_layoutcommit_inode(inode, sync); + if (status < 0) + return status; + } + return ret; +} + +/* + * Clean out any remaining NFSv4 state that might be left over due + * to open() calls that passed nfs_atomic_lookup, but failed to call + * nfs_open(). + */ +static void nfs4_evict_inode(struct inode *inode) +{ + truncate_inode_pages(&inode->i_data, 0); + clear_inode(inode); + pnfs_return_layout(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 */ + nfs_clear_inode(inode); +} + +/* + * Get the superblock for the NFS4 root partition + */ +static struct dentry * +nfs4_remote_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *info) +{ + struct nfs_mount_info *mount_info = info; + struct nfs_server *server; + struct dentry *mntroot = ERR_PTR(-ENOMEM); + + mount_info->set_security = nfs_set_sb_security; + + /* Get a volume representation */ + server = nfs4_create_server(mount_info, &nfs_v4); + if (IS_ERR(server)) { + mntroot = ERR_CAST(server); + goto out; + } + + mntroot = nfs_fs_mount_common(server, flags, dev_name, mount_info, &nfs_v4); + +out: + return mntroot; +} + +static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type, + int flags, void *data, const char *hostname) +{ + struct vfsmount *root_mnt; + char *root_devname; + size_t len; + + len = strlen(hostname) + 5; + root_devname = kmalloc(len, GFP_KERNEL); + if (root_devname == NULL) + return ERR_PTR(-ENOMEM); + /* Does hostname needs to be enclosed in brackets? */ + if (strchr(hostname, ':')) + snprintf(root_devname, len, "[%s]:/", hostname); + else + snprintf(root_devname, len, "%s:/", hostname); + root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data); + kfree(root_devname); + return root_mnt; +} + +struct nfs_referral_count { + struct list_head list; + const struct task_struct *task; + unsigned int referral_count; +}; + +static LIST_HEAD(nfs_referral_count_list); +static DEFINE_SPINLOCK(nfs_referral_count_list_lock); + +static struct nfs_referral_count *nfs_find_referral_count(void) +{ + struct nfs_referral_count *p; + + list_for_each_entry(p, &nfs_referral_count_list, list) { + if (p->task == current) + return p; + } + return NULL; +} + +#define NFS_MAX_NESTED_REFERRALS 2 + +static int nfs_referral_loop_protect(void) +{ + struct nfs_referral_count *p, *new; + int ret = -ENOMEM; + + new = kmalloc(sizeof(*new), GFP_KERNEL); + if (!new) + goto out; + new->task = current; + new->referral_count = 1; + + ret = 0; + spin_lock(&nfs_referral_count_list_lock); + p = nfs_find_referral_count(); + if (p != NULL) { + if (p->referral_count >= NFS_MAX_NESTED_REFERRALS) + ret = -ELOOP; + else + p->referral_count++; + } else { + list_add(&new->list, &nfs_referral_count_list); + new = NULL; + } + spin_unlock(&nfs_referral_count_list_lock); + kfree(new); +out: + return ret; +} + +static void nfs_referral_loop_unprotect(void) +{ + struct nfs_referral_count *p; + + spin_lock(&nfs_referral_count_list_lock); + p = nfs_find_referral_count(); + p->referral_count--; + if (p->referral_count == 0) + list_del(&p->list); + else + p = NULL; + spin_unlock(&nfs_referral_count_list_lock); + kfree(p); +} + +static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt, + const char *export_path) +{ + struct dentry *dentry; + int err; + + if (IS_ERR(root_mnt)) + return ERR_CAST(root_mnt); + + err = nfs_referral_loop_protect(); + if (err) { + mntput(root_mnt); + return ERR_PTR(err); + } + + dentry = mount_subtree(root_mnt, export_path); + nfs_referral_loop_unprotect(); + + return dentry; +} + +struct dentry *nfs4_try_mount(int flags, const char *dev_name, + struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) +{ + char *export_path; + struct vfsmount *root_mnt; + struct dentry *res; + struct nfs_parsed_mount_data *data = mount_info->parsed; + + dfprintk(MOUNT, "--> nfs4_try_mount()\n"); + + export_path = data->nfs_server.export_path; + data->nfs_server.export_path = "/"; + root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info, + data->nfs_server.hostname); + data->nfs_server.export_path = export_path; + + res = nfs_follow_remote_path(root_mnt, export_path); + + dfprintk(MOUNT, "<-- nfs4_try_mount() = %ld%s\n", + IS_ERR(res) ? PTR_ERR(res) : 0, + IS_ERR(res) ? " [error]" : ""); + return res; +} + +static struct dentry * +nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags, + const char *dev_name, void *raw_data) +{ + struct nfs_mount_info mount_info = { + .fill_super = nfs_fill_super, + .set_security = nfs_clone_sb_security, + .cloned = raw_data, + }; + struct nfs_server *server; + struct dentry *mntroot = ERR_PTR(-ENOMEM); + + dprintk("--> nfs4_referral_get_sb()\n"); + + mount_info.mntfh = nfs_alloc_fhandle(); + if (mount_info.cloned == NULL || mount_info.mntfh == NULL) + goto out; + + /* create a new volume representation */ + server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh); + if (IS_ERR(server)) { + mntroot = ERR_CAST(server); + goto out; + } + + mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, &nfs_v4); +out: + nfs_free_fhandle(mount_info.mntfh); + return mntroot; +} + +/* + * Create an NFS4 server record on referral traversal + */ +static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, + int flags, const char *dev_name, void *raw_data) +{ + struct nfs_clone_mount *data = raw_data; + char *export_path; + struct vfsmount *root_mnt; + struct dentry *res; + + dprintk("--> nfs4_referral_mount()\n"); + + export_path = data->mnt_path; + data->mnt_path = "/"; + + root_mnt = nfs_do_root_mount(&nfs4_remote_referral_fs_type, + flags, data, data->hostname); + data->mnt_path = export_path; + + res = nfs_follow_remote_path(root_mnt, export_path); + dprintk("<-- nfs4_referral_mount() = %ld%s\n", + IS_ERR(res) ? PTR_ERR(res) : 0, + IS_ERR(res) ? " [error]" : ""); + return res; +} + + +static int __init init_nfs_v4(void) +{ + int err; + + err = nfs_idmap_init(); + if (err) + goto out; + + err = nfs4_register_sysctl(); + if (err) + goto out1; + + register_nfs_version(&nfs_v4); + return 0; +out1: + nfs_idmap_quit(); +out: + return err; +} + +static void __exit exit_nfs_v4(void) +{ + unregister_nfs_version(&nfs_v4); + nfs4_unregister_sysctl(); + nfs_idmap_quit(); +} + +MODULE_LICENSE("GPL"); + +module_init(init_nfs_v4); +module_exit(exit_nfs_v4); diff --git a/fs/nfs/nfs4sysctl.c b/fs/nfs/nfs4sysctl.c new file mode 100644 index 0000000..5729bc8 --- /dev/null +++ b/fs/nfs/nfs4sysctl.c @@ -0,0 +1,68 @@ +/* + * linux/fs/nfs/nfs4sysctl.c + * + * Sysctl interface to NFS v4 parameters + * + * Copyright (c) 2006 Trond Myklebust <Trond.Myklebust@netapp.com> + */ +#include <linux/sysctl.h> +#include <linux/nfs_idmap.h> +#include <linux/nfs_fs.h> + +#include "callback.h" + +static const int nfs_set_port_min = 0; +static const int nfs_set_port_max = 65535; +static struct ctl_table_header *nfs4_callback_sysctl_table; + +static ctl_table nfs4_cb_sysctls[] = { + { + .procname = "nfs_callback_tcpport", + .data = &nfs_callback_set_tcpport, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = (int *)&nfs_set_port_min, + .extra2 = (int *)&nfs_set_port_max, + }, + { + .procname = "idmap_cache_timeout", + .data = &nfs_idmap_cache_timeout, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { } +}; + +static ctl_table nfs4_cb_sysctl_dir[] = { + { + .procname = "nfs", + .mode = 0555, + .child = nfs4_cb_sysctls, + }, + { } +}; + +static ctl_table nfs4_cb_sysctl_root[] = { + { + .procname = "fs", + .mode = 0555, + .child = nfs4_cb_sysctl_dir, + }, + { } +}; + +int nfs4_register_sysctl(void) +{ + nfs4_callback_sysctl_table = register_sysctl_table(nfs4_cb_sysctl_root); + if (nfs4_callback_sysctl_table == NULL) + return -ENOMEM; + return 0; +} + +void nfs4_unregister_sysctl(void) +{ + unregister_sysctl_table(nfs4_callback_sysctl_table); + nfs4_callback_sysctl_table = NULL; +} diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c index 18fae29..8dba6bd 100644 --- a/fs/nfs/nfs4xdr.c +++ b/fs/nfs/nfs4xdr.c @@ -852,12 +852,6 @@ const u32 nfs41_maxread_overhead = ((RPC_MAX_HEADER_WITH_AUTH + XDR_UNIT); #endif /* CONFIG_NFS_V4_1 */ -static unsigned short send_implementation_id = 1; - -module_param(send_implementation_id, ushort, 0644); -MODULE_PARM_DESC(send_implementation_id, - "Send implementation ID with NFSv4.1 exchange_id"); - static const umode_t nfs_type2fmt[] = { [NF4BAD] = 0, [NF4REG] = S_IFREG, @@ -1236,7 +1230,7 @@ static void encode_link(struct xdr_stream *xdr, const struct qstr *name, struct static inline int nfs4_lock_type(struct file_lock *fl, int block) { - if ((fl->fl_type & (F_RDLCK|F_WRLCK|F_UNLCK)) == F_RDLCK) + if (fl->fl_type == F_RDLCK) return block ? NFS4_READW_LT : NFS4_READ_LT; return block ? NFS4_WRITEW_LT : NFS4_WRITE_LT; } @@ -3078,7 +3072,7 @@ out_overflow: return -EIO; } -static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, __be32 **savep) +static int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, unsigned int *savep) { __be32 *p; @@ -3086,7 +3080,7 @@ static inline int decode_attr_length(struct xdr_stream *xdr, uint32_t *attrlen, if (unlikely(!p)) goto out_overflow; *attrlen = be32_to_cpup(p); - *savep = xdr->p; + *savep = xdr_stream_pos(xdr); return 0; out_overflow: print_overflow_msg(__func__, xdr); @@ -4068,10 +4062,10 @@ static int decode_attr_time_modify(struct xdr_stream *xdr, uint32_t *bitmap, str return status; } -static int verify_attr_len(struct xdr_stream *xdr, __be32 *savep, uint32_t attrlen) +static int verify_attr_len(struct xdr_stream *xdr, unsigned int savep, uint32_t attrlen) { unsigned int attrwords = XDR_QUADLEN(attrlen); - unsigned int nwords = xdr->p - savep; + unsigned int nwords = (xdr_stream_pos(xdr) - savep) >> 2; if (unlikely(attrwords != nwords)) { dprintk("%s: server returned incorrect attribute length: " @@ -4158,13 +4152,18 @@ static int decode_verifier(struct xdr_stream *xdr, void *verifier) return decode_opaque_fixed(xdr, verifier, NFS4_VERIFIER_SIZE); } +static int decode_write_verifier(struct xdr_stream *xdr, struct nfs_write_verifier *verifier) +{ + return decode_opaque_fixed(xdr, verifier->data, NFS4_VERIFIER_SIZE); +} + static int decode_commit(struct xdr_stream *xdr, struct nfs_commitres *res) { int status; status = decode_op_hdr(xdr, OP_COMMIT); if (!status) - status = decode_verifier(xdr, res->verf->verifier); + status = decode_write_verifier(xdr, &res->verf->verifier); return status; } @@ -4193,7 +4192,7 @@ out_overflow: static int decode_server_caps(struct xdr_stream *xdr, struct nfs4_server_caps_res *res) { - __be32 *savep; + unsigned int savep; uint32_t attrlen, bitmap[3] = {0}; int status; @@ -4222,7 +4221,7 @@ xdr_error: static int decode_statfs(struct xdr_stream *xdr, struct nfs_fsstat *fsstat) { - __be32 *savep; + unsigned int savep; uint32_t attrlen, bitmap[3] = {0}; int status; @@ -4254,7 +4253,7 @@ xdr_error: static int decode_pathconf(struct xdr_stream *xdr, struct nfs_pathconf *pathconf) { - __be32 *savep; + unsigned int savep; uint32_t attrlen, bitmap[3] = {0}; int status; @@ -4299,7 +4298,8 @@ out_overflow: static int decode_first_threshold_item4(struct xdr_stream *xdr, struct nfs4_threshold *res) { - __be32 *p, *savep; + __be32 *p; + unsigned int savep; uint32_t bitmap[3] = {0,}, attrlen; int status; @@ -4503,7 +4503,7 @@ static int decode_getfattr_generic(struct xdr_stream *xdr, struct nfs_fattr *fat struct nfs_fh *fh, struct nfs4_fs_locations *fs_loc, const struct nfs_server *server) { - __be32 *savep; + unsigned int savep; uint32_t attrlen, bitmap[3] = {0}; int status; @@ -4615,7 +4615,7 @@ static int decode_attr_layout_blksize(struct xdr_stream *xdr, uint32_t *bitmap, static int decode_fsinfo(struct xdr_stream *xdr, struct nfs_fsinfo *fsinfo) { - __be32 *savep; + unsigned int savep; uint32_t attrlen, bitmap[3]; int status; @@ -4920,9 +4920,8 @@ static int decode_putrootfh(struct xdr_stream *xdr) static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_readres *res) { - struct kvec *iov = req->rq_rcv_buf.head; __be32 *p; - uint32_t count, eof, recvd, hdrlen; + uint32_t count, eof, recvd; int status; status = decode_op_hdr(xdr, OP_READ); @@ -4933,15 +4932,13 @@ static int decode_read(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_ goto out_overflow; eof = be32_to_cpup(p++); count = be32_to_cpup(p); - hdrlen = (u8 *) xdr->p - (u8 *) iov->iov_base; - recvd = req->rq_rcv_buf.len - hdrlen; + recvd = xdr_read_pages(xdr, count); if (count > recvd) { dprintk("NFS: server cheating in read reply: " "count %u > recvd %u\n", count, recvd); count = recvd; eof = 0; } - xdr_read_pages(xdr, count); res->eof = eof; res->count = count; return 0; @@ -4952,10 +4949,6 @@ 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 kvec *iov = rcvbuf->head; - size_t hdrlen; - u32 recvd, pglen = rcvbuf->page_len; int status; __be32 verf[2]; @@ -4967,22 +4960,12 @@ static int decode_readdir(struct xdr_stream *xdr, struct rpc_rqst *req, struct n memcpy(verf, readdir->verifier.data, sizeof(verf)); dprintk("%s: verifier = %08x:%08x\n", __func__, verf[0], verf[1]); - - hdrlen = (char *) xdr->p - (char *) iov->iov_base; - recvd = rcvbuf->len - hdrlen; - if (pglen > recvd) - pglen = recvd; - xdr_read_pages(xdr, pglen); - - - return pglen; + return xdr_read_pages(xdr, xdr->buf->page_len); } static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) { struct xdr_buf *rcvbuf = &req->rq_rcv_buf; - struct kvec *iov = rcvbuf->head; - size_t hdrlen; u32 len, recvd; __be32 *p; int status; @@ -5000,14 +4983,12 @@ static int decode_readlink(struct xdr_stream *xdr, struct rpc_rqst *req) dprintk("nfs: server returned giant symlink!\n"); return -ENAMETOOLONG; } - hdrlen = (char *) xdr->p - (char *) iov->iov_base; - recvd = req->rq_rcv_buf.len - hdrlen; + recvd = xdr_read_pages(xdr, len); if (recvd < len) { dprintk("NFS: server cheating in readlink reply: " "count %u > recvd %u\n", len, recvd); return -EIO; } - xdr_read_pages(xdr, len); /* * The XDR encode routine has set things up so that * the link text will be copied directly into the @@ -5063,23 +5044,20 @@ decode_restorefh(struct xdr_stream *xdr) static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, struct nfs_getaclres *res) { - __be32 *savep, *bm_p; + unsigned int savep; uint32_t attrlen, bitmap[3] = {0}; - struct kvec *iov = req->rq_rcv_buf.head; int status; - size_t page_len = xdr->buf->page_len; + unsigned int pg_offset; res->acl_len = 0; if ((status = decode_op_hdr(xdr, OP_GETATTR)) != 0) goto out; - bm_p = xdr->p; - res->acl_data_offset = be32_to_cpup(bm_p) + 2; - res->acl_data_offset <<= 2; - /* Check if the acl data starts beyond the allocated buffer */ - if (res->acl_data_offset > page_len) - return -ERANGE; + xdr_enter_page(xdr, xdr->buf->page_len); + + /* Calculate the offset of the page data */ + pg_offset = xdr->buf->head[0].iov_len; if ((status = decode_attr_bitmap(xdr, bitmap)) != 0) goto out; @@ -5089,29 +5067,20 @@ static int decode_getacl(struct xdr_stream *xdr, struct rpc_rqst *req, if (unlikely(bitmap[0] & (FATTR4_WORD0_ACL - 1U))) return -EIO; if (likely(bitmap[0] & FATTR4_WORD0_ACL)) { - size_t hdrlen; /* The bitmap (xdr len + bitmaps) and the attr xdr len words * are stored with the acl data to handle the problem of * variable length bitmaps.*/ - xdr->p = bm_p; - - /* We ignore &savep and don't do consistency checks on - * the attr length. Let userspace figure it out.... */ - hdrlen = (u8 *)xdr->p - (u8 *)iov->iov_base; - attrlen += res->acl_data_offset; - if (attrlen > page_len) { - if (res->acl_flags & NFS4_ACL_LEN_REQUEST) { - /* getxattr interface called with a NULL buf */ - res->acl_len = attrlen; - goto out; - } - dprintk("NFS: acl reply: attrlen %u > page_len %zu\n", - attrlen, page_len); - return -EINVAL; - } - xdr_read_pages(xdr, attrlen); + res->acl_data_offset = xdr_stream_pos(xdr) - pg_offset; res->acl_len = attrlen; + + /* Check for receive buffer overflow */ + if (res->acl_len > (xdr->nwords << 2) || + res->acl_len + res->acl_data_offset > xdr->buf->page_len) { + res->acl_flags |= NFS4_ACL_TRUNC; + dprintk("NFS: acl reply: attrlen %u > page_len %u\n", + attrlen, xdr->nwords << 2); + } } else status = -EOPNOTSUPP; @@ -5212,13 +5181,12 @@ static int decode_write(struct xdr_stream *xdr, struct nfs_writeres *res) if (status) return status; - p = xdr_inline_decode(xdr, 16); + p = xdr_inline_decode(xdr, 8); if (unlikely(!p)) goto out_overflow; res->count = be32_to_cpup(p++); res->verf->committed = be32_to_cpup(p++); - memcpy(res->verf->verifier, p, NFS4_VERIFIER_SIZE); - return 0; + return decode_write_verifier(xdr, &res->verf->verifier); out_overflow: print_overflow_msg(__func__, xdr); return -EIO; @@ -5599,7 +5567,7 @@ static int decode_getdevicelist(struct xdr_stream *xdr, { __be32 *p; int status, i; - struct nfs_writeverf verftemp; + nfs4_verifier verftemp; status = decode_op_hdr(xdr, OP_GETDEVICELIST); if (status) @@ -5613,7 +5581,7 @@ static int decode_getdevicelist(struct xdr_stream *xdr, p += 2; /* Read verifier */ - p = xdr_decode_opaque_fixed(p, verftemp.verifier, NFS4_VERIFIER_SIZE); + p = xdr_decode_opaque_fixed(p, verftemp.data, NFS4_VERIFIER_SIZE); res->num_devs = be32_to_cpup(p); @@ -5707,9 +5675,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, __be32 *p; int status; u32 layout_count; - struct xdr_buf *rcvbuf = &req->rq_rcv_buf; - struct kvec *iov = rcvbuf->head; - u32 hdrlen, recvd; + u32 recvd; status = decode_op_hdr(xdr, OP_LAYOUTGET); if (status) @@ -5746,8 +5712,7 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, res->type, res->layoutp->len); - hdrlen = (u8 *) xdr->p - (u8 *) iov->iov_base; - recvd = req->rq_rcv_buf.len - hdrlen; + recvd = xdr_read_pages(xdr, res->layoutp->len); if (res->layoutp->len > recvd) { dprintk("NFS: server cheating in layoutget reply: " "layout len %u > recvd %u\n", @@ -5755,8 +5720,6 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req, return -EINVAL; } - xdr_read_pages(xdr, res->layoutp->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 @@ -6262,7 +6225,8 @@ static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr, status = decode_open(xdr, res); if (status) goto out; - if (decode_getfh(xdr, &res->fh) != 0) + status = decode_getfh(xdr, &res->fh); + if (status) goto out; decode_getfattr(xdr, res->f_attr, res->server); out: @@ -7103,6 +7067,7 @@ out: int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, int plus) { + unsigned int savep; uint32_t bitmap[3] = {0}; uint32_t len; __be32 *p = xdr_inline_decode(xdr, 4); @@ -7141,7 +7106,7 @@ int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry, if (decode_attr_bitmap(xdr, bitmap) < 0) goto out_overflow; - if (decode_attr_length(xdr, &len, &p) < 0) + if (decode_attr_length(xdr, &len, &savep) < 0) goto out_overflow; if (decode_getfattr_attrs(xdr, bitmap, entry->fattr, entry->fh, diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c index f50d3e8..ea6d111 100644 --- a/fs/nfs/objlayout/objio_osd.c +++ b/fs/nfs/objlayout/objio_osd.c @@ -570,17 +570,66 @@ static bool objio_pg_test(struct nfs_pageio_descriptor *pgio, return false; return pgio->pg_count + req->wb_bytes <= - OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; + (unsigned long)pgio->pg_layout_private; +} + +void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + pnfs_generic_pg_init_read(pgio, req); + if (unlikely(pgio->pg_lseg == NULL)) + return; /* Not pNFS */ + + pgio->pg_layout_private = (void *) + OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; +} + +static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout, + unsigned long *stripe_end) +{ + u32 stripe_off; + unsigned stripe_size; + + if (layout->raid_algorithm == PNFS_OSD_RAID_0) + return true; + + stripe_size = layout->stripe_unit * + (layout->group_width - layout->parity); + + div_u64_rem(offset, stripe_size, &stripe_off); + if (!stripe_off) + return true; + + *stripe_end = stripe_size - stripe_off; + return false; +} + +void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req) +{ + unsigned long stripe_end = 0; + + pnfs_generic_pg_init_write(pgio, req); + if (unlikely(pgio->pg_lseg == NULL)) + return; /* Not pNFS */ + + if (req->wb_offset || + !aligned_on_raid_stripe(req->wb_index * PAGE_SIZE, + &OBJIO_LSEG(pgio->pg_lseg)->layout, + &stripe_end)) { + pgio->pg_layout_private = (void *)stripe_end; + } else { + pgio->pg_layout_private = (void *) + OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length; + } } static const struct nfs_pageio_ops objio_pg_read_ops = { - .pg_init = pnfs_generic_pg_init_read, + .pg_init = objio_init_read, .pg_test = objio_pg_test, .pg_doio = pnfs_generic_pg_readpages, }; static const struct nfs_pageio_ops objio_pg_write_ops = { - .pg_init = pnfs_generic_pg_init_write, + .pg_init = objio_init_write, .pg_test = objio_pg_test, .pg_doio = pnfs_generic_pg_writepages, }; diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c index aed913c..311a796 100644 --- a/fs/nfs/pagelist.c +++ b/fs/nfs/pagelist.c @@ -49,11 +49,13 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc, hdr->io_start = req_offset(hdr->req); hdr->good_bytes = desc->pg_count; hdr->dreq = desc->pg_dreq; + hdr->layout_private = desc->pg_layout_private; hdr->release = release; hdr->completion_ops = desc->pg_completion_ops; if (hdr->completion_ops->init_hdr) hdr->completion_ops->init_hdr(hdr); } +EXPORT_SYMBOL_GPL(nfs_pgheader_init); void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) { @@ -70,7 +72,7 @@ void nfs_set_pgio_error(struct nfs_pgio_header *hdr, int error, loff_t pos) static inline struct nfs_page * nfs_page_alloc(void) { - struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_KERNEL); + struct nfs_page *p = kmem_cache_zalloc(nfs_page_cachep, GFP_NOIO); if (p) INIT_LIST_HEAD(&p->wb_list); return p; @@ -117,7 +119,7 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode, * long write-back delay. This will be adjusted in * update_nfs_request below if the region is not locked. */ req->wb_page = page; - req->wb_index = page->index; + req->wb_index = page_file_index(page); page_cache_get(page); req->wb_offset = offset; req->wb_pgbase = offset; @@ -267,7 +269,9 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc, desc->pg_error = 0; desc->pg_lseg = NULL; desc->pg_dreq = NULL; + desc->pg_layout_private = NULL; } +EXPORT_SYMBOL_GPL(nfs_pageio_init); /** * nfs_can_coalesce_requests - test two requests for compatibility @@ -409,6 +413,7 @@ int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc, } while (ret); return ret; } +EXPORT_SYMBOL_GPL(nfs_pageio_add_request); /** * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor @@ -424,6 +429,7 @@ void nfs_pageio_complete(struct nfs_pageio_descriptor *desc) break; } } +EXPORT_SYMBOL_GPL(nfs_pageio_complete); /** * nfs_pageio_cond_complete - Conditional I/O completion diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c index bbc49ca..2e00fea 100644 --- a/fs/nfs/pnfs.c +++ b/fs/nfs/pnfs.c @@ -583,9 +583,6 @@ send_layoutget(struct pnfs_layout_hdr *lo, struct nfs_server *server = NFS_SERVER(ino); struct nfs4_layoutget *lgp; struct pnfs_layout_segment *lseg = NULL; - struct page **pages = NULL; - int i; - u32 max_resp_sz, max_pages; dprintk("--> %s\n", __func__); @@ -594,20 +591,6 @@ send_layoutget(struct pnfs_layout_hdr *lo, if (lgp == NULL) return NULL; - /* allocate pages for xdr post processing */ - max_resp_sz = server->nfs_client->cl_session->fc_attrs.max_resp_sz; - max_pages = nfs_page_array_len(0, max_resp_sz); - - pages = kcalloc(max_pages, sizeof(struct page *), gfp_flags); - if (!pages) - goto out_err_free; - - for (i = 0; i < max_pages; i++) { - pages[i] = alloc_page(gfp_flags); - if (!pages[i]) - goto out_err_free; - } - lgp->args.minlength = PAGE_CACHE_SIZE; if (lgp->args.minlength > range->length) lgp->args.minlength = range->length; @@ -616,42 +599,29 @@ send_layoutget(struct pnfs_layout_hdr *lo, lgp->args.type = server->pnfs_curr_ld->id; lgp->args.inode = ino; lgp->args.ctx = get_nfs_open_context(ctx); - lgp->args.layout.pages = pages; - lgp->args.layout.pglen = max_pages * PAGE_SIZE; lgp->lsegpp = &lseg; lgp->gfp_flags = gfp_flags; /* Synchronously retrieve layout information from server and * store in lseg. */ - nfs4_proc_layoutget(lgp); + nfs4_proc_layoutget(lgp, gfp_flags); if (!lseg) { /* remember that LAYOUTGET failed and suspend trying */ set_bit(lo_fail_bit(range->iomode), &lo->plh_flags); } - /* free xdr pages */ - for (i = 0; i < max_pages; i++) - __free_page(pages[i]); - kfree(pages); - return lseg; - -out_err_free: - /* free any allocated xdr pages, lgp as it's not used */ - if (pages) { - for (i = 0; i < max_pages; i++) { - if (!pages[i]) - break; - __free_page(pages[i]); - } - kfree(pages); - } - kfree(lgp); - return NULL; } -/* Initiates a LAYOUTRETURN(FILE) */ +/* + * Initiates a LAYOUTRETURN(FILE), and removes the pnfs_layout_hdr + * when the layout segment list is empty. + * + * Note that a pnfs_layout_hdr can exist with an empty layout segment + * list when LAYOUTGET has failed, or when LAYOUTGET succeeded, but the + * deviceid is marked invalid. + */ int _pnfs_return_layout(struct inode *ino) { @@ -660,22 +630,31 @@ _pnfs_return_layout(struct inode *ino) LIST_HEAD(tmp_list); struct nfs4_layoutreturn *lrp; nfs4_stateid stateid; - int status = 0; + int status = 0, empty; - dprintk("--> %s\n", __func__); + dprintk("NFS: %s for inode %lu\n", __func__, ino->i_ino); spin_lock(&ino->i_lock); lo = nfsi->layout; - if (!lo) { + if (!lo || pnfs_test_layout_returned(lo)) { spin_unlock(&ino->i_lock); - dprintk("%s: no layout to return\n", __func__); - return status; + dprintk("NFS: %s no layout to return\n", __func__); + goto out; } stateid = nfsi->layout->plh_stateid; /* Reference matched in nfs4_layoutreturn_release */ get_layout_hdr(lo); + empty = list_empty(&lo->plh_segs); mark_matching_lsegs_invalid(lo, &tmp_list, NULL); + /* Don't send a LAYOUTRETURN if list was initially empty */ + if (empty) { + spin_unlock(&ino->i_lock); + put_layout_hdr(lo); + dprintk("NFS: %s no layout segments to return\n", __func__); + goto out; + } lo->plh_block_lgets++; + pnfs_mark_layout_returned(lo); spin_unlock(&ino->i_lock); pnfs_free_lseg_list(&tmp_list); @@ -686,6 +665,7 @@ _pnfs_return_layout(struct inode *ino) status = -ENOMEM; set_bit(NFS_LAYOUT_RW_FAILED, &lo->plh_flags); set_bit(NFS_LAYOUT_RO_FAILED, &lo->plh_flags); + pnfs_clear_layout_returned(lo); put_layout_hdr(lo); goto out; } @@ -1075,6 +1055,10 @@ pnfs_update_layout(struct inode *ino, get_layout_hdr(lo); if (list_empty(&lo->plh_segs)) first = true; + + /* Enable LAYOUTRETURNs */ + pnfs_clear_layout_returned(lo); + spin_unlock(&ino->i_lock); if (first) { /* The lo must be on the clp list if there is any @@ -1209,7 +1193,7 @@ pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page * } EXPORT_SYMBOL_GPL(pnfs_generic_pg_init_write); -bool +void pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, const struct nfs_pgio_completion_ops *compl_ops) { @@ -1217,13 +1201,12 @@ pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld; if (ld == NULL) - return false; - nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops, - server->rsize, 0); - return true; + nfs_pageio_init_read(pgio, inode, compl_ops); + else + nfs_pageio_init(pgio, inode, ld->pg_read_ops, compl_ops, server->rsize, 0); } -bool +void pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, const struct nfs_pgio_completion_ops *compl_ops) @@ -1232,10 +1215,9 @@ pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, struct pnfs_layoutdriver_type *ld = server->pnfs_curr_ld; if (ld == NULL) - return false; - nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops, - server->wsize, ioflags); - return true; + nfs_pageio_init_write(pgio, inode, ioflags, compl_ops); + else + nfs_pageio_init(pgio, inode, ld->pg_write_ops, compl_ops, server->wsize, ioflags); } bool @@ -1272,7 +1254,7 @@ int pnfs_write_done_resend_to_mds(struct inode *inode, LIST_HEAD(failed); /* Resend all requests through the MDS */ - nfs_pageio_init_write_mds(&pgio, inode, FLUSH_STABLE, compl_ops); + nfs_pageio_init_write(&pgio, inode, FLUSH_STABLE, compl_ops); while (!list_empty(head)) { struct nfs_page *req = nfs_list_entry(head->next); @@ -1388,6 +1370,7 @@ static void pnfs_writehdr_free(struct nfs_pgio_header *hdr) put_lseg(hdr->lseg); nfs_writehdr_free(hdr); } +EXPORT_SYMBOL_GPL(pnfs_writehdr_free); int pnfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) @@ -1427,7 +1410,7 @@ int pnfs_read_done_resend_to_mds(struct inode *inode, LIST_HEAD(failed); /* Resend all requests through the MDS */ - nfs_pageio_init_read_mds(&pgio, inode, compl_ops); + nfs_pageio_init_read(&pgio, inode, compl_ops); while (!list_empty(head)) { struct nfs_page *req = nfs_list_entry(head->next); @@ -1542,6 +1525,7 @@ static void pnfs_readhdr_free(struct nfs_pgio_header *hdr) put_lseg(hdr->lseg); nfs_readhdr_free(hdr); } +EXPORT_SYMBOL_GPL(pnfs_readhdr_free); int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h index 64f90d8..745aa1b 100644 --- a/fs/nfs/pnfs.h +++ b/fs/nfs/pnfs.h @@ -64,6 +64,7 @@ enum { NFS_LAYOUT_ROC, /* some lseg had roc bit set */ NFS_LAYOUT_DESTROYED, /* no new use of layout allowed */ NFS_LAYOUT_INVALID, /* layout is being destroyed */ + NFS_LAYOUT_RETURNED, /* layout has already been returned */ }; enum layoutdriver_policy_flags { @@ -171,16 +172,16 @@ extern int nfs4_proc_getdevicelist(struct nfs_server *server, struct pnfs_devicelist *devlist); extern int nfs4_proc_getdeviceinfo(struct nfs_server *server, struct pnfs_device *dev); -extern int nfs4_proc_layoutget(struct nfs4_layoutget *lgp); +extern void nfs4_proc_layoutget(struct nfs4_layoutget *lgp, gfp_t gfp_flags); extern int nfs4_proc_layoutreturn(struct nfs4_layoutreturn *lrp); /* pnfs.c */ void get_layout_hdr(struct pnfs_layout_hdr *lo); void put_lseg(struct pnfs_layout_segment *lseg); -bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *, +void pnfs_pageio_init_read(struct nfs_pageio_descriptor *, struct inode *, const struct nfs_pgio_completion_ops *); -bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, +void pnfs_pageio_init_write(struct nfs_pageio_descriptor *, struct inode *, int, const struct nfs_pgio_completion_ops *); void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, u32); @@ -255,6 +256,24 @@ struct nfs4_deviceid_node *nfs4_insert_deviceid_node(struct nfs4_deviceid_node * bool nfs4_put_deviceid_node(struct nfs4_deviceid_node *); void nfs4_deviceid_purge_client(const struct nfs_client *); +static inline void +pnfs_mark_layout_returned(struct pnfs_layout_hdr *lo) +{ + set_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags); +} + +static inline void +pnfs_clear_layout_returned(struct pnfs_layout_hdr *lo) +{ + clear_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags); +} + +static inline bool +pnfs_test_layout_returned(struct pnfs_layout_hdr *lo) +{ + return test_bit(NFS_LAYOUT_RETURNED, &lo->plh_flags); +} + static inline int lo_fail_bit(u32 iomode) { return iomode == IOMODE_RW ? @@ -438,16 +457,16 @@ static inline void unset_pnfs_layoutdriver(struct nfs_server *s) { } -static inline bool pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, +static inline void pnfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, const struct nfs_pgio_completion_ops *compl_ops) { - return false; + nfs_pageio_init_read(pgio, inode, compl_ops); } -static inline bool pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, +static inline void pnfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, const struct nfs_pgio_completion_ops *compl_ops) { - return false; + nfs_pageio_init_write(pgio, inode, ioflags, compl_ops); } static inline int diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c index 4433806..50a88c3 100644 --- a/fs/nfs/proc.c +++ b/fs/nfs/proc.c @@ -734,6 +734,38 @@ out_einval: return -EINVAL; } +static int nfs_have_delegation(struct inode *inode, fmode_t flags) +{ + return 0; +} + +static int nfs_return_delegation(struct inode *inode) +{ + nfs_wb_all(inode); + return 0; +} + +static const struct inode_operations nfs_dir_inode_operations = { + .create = nfs_create, + .lookup = nfs_lookup, + .link = nfs_link, + .unlink = nfs_unlink, + .symlink = nfs_symlink, + .mkdir = nfs_mkdir, + .rmdir = nfs_rmdir, + .mknod = nfs_mknod, + .rename = nfs_rename, + .permission = nfs_permission, + .getattr = nfs_getattr, + .setattr = nfs_setattr, +}; + +static const struct inode_operations nfs_file_inode_operations = { + .permission = nfs_permission, + .getattr = nfs_getattr, + .setattr = nfs_setattr, +}; + const struct nfs_rpc_ops nfs_v2_clientops = { .version = 2, /* protocol version */ .dentry_ops = &nfs_dentry_operations, @@ -742,6 +774,7 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .file_ops = &nfs_file_operations, .getroot = nfs_proc_get_root, .submount = nfs_submount, + .try_mount = nfs_try_mount, .getattr = nfs_proc_getattr, .setattr = nfs_proc_setattr, .lookup = nfs_proc_lookup, @@ -767,9 +800,11 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .pathconf = nfs_proc_pathconf, .decode_dirent = nfs2_decode_dirent, .read_setup = nfs_proc_read_setup, + .read_pageio_init = nfs_pageio_init_read, .read_rpc_prepare = nfs_proc_read_rpc_prepare, .read_done = nfs_read_done, .write_setup = nfs_proc_write_setup, + .write_pageio_init = nfs_pageio_init_write, .write_rpc_prepare = nfs_proc_write_rpc_prepare, .write_done = nfs_write_done, .commit_setup = nfs_proc_commit_setup, @@ -777,5 +812,11 @@ const struct nfs_rpc_ops nfs_v2_clientops = { .lock = nfs_proc_lock, .lock_check_bounds = nfs_lock_check_bounds, .close_context = nfs_close_context, + .have_delegation = nfs_have_delegation, + .return_delegation = nfs_return_delegation, + .alloc_client = nfs_alloc_client, .init_client = nfs_init_client, + .free_client = nfs_free_client, + .create_server = nfs_create_server, + .clone_server = nfs_clone_server, }; diff --git a/fs/nfs/read.c b/fs/nfs/read.c index 86ced78..b6bdb18 100644 --- a/fs/nfs/read.c +++ b/fs/nfs/read.c @@ -20,8 +20,6 @@ #include <linux/nfs_page.h> #include <linux/module.h> -#include "pnfs.h" - #include "nfs4_fs.h" #include "internal.h" #include "iostat.h" @@ -50,6 +48,7 @@ struct nfs_read_header *nfs_readhdr_alloc(void) } return rhdr; } +EXPORT_SYMBOL_GPL(nfs_readhdr_alloc); static struct nfs_read_data *nfs_readdata_alloc(struct nfs_pgio_header *hdr, unsigned int pagecount) @@ -82,6 +81,7 @@ void nfs_readhdr_free(struct nfs_pgio_header *hdr) kmem_cache_free(nfs_rdata_cachep, rhdr); } +EXPORT_SYMBOL_GPL(nfs_readhdr_free); void nfs_readdata_release(struct nfs_read_data *rdata) { @@ -98,6 +98,7 @@ void nfs_readdata_release(struct nfs_read_data *rdata) if (atomic_dec_and_test(&hdr->refcnt)) hdr->completion_ops->completion(hdr); } +EXPORT_SYMBOL_GPL(nfs_readdata_release); static int nfs_return_empty_page(struct page *page) @@ -108,13 +109,14 @@ int nfs_return_empty_page(struct page *page) return 0; } -void nfs_pageio_init_read_mds(struct nfs_pageio_descriptor *pgio, +void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, struct inode *inode, const struct nfs_pgio_completion_ops *compl_ops) { nfs_pageio_init(pgio, inode, &nfs_pageio_read_ops, compl_ops, NFS_SERVER(inode)->rsize, 0); } +EXPORT_SYMBOL_GPL(nfs_pageio_init_read); void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) { @@ -123,14 +125,6 @@ void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio) } EXPORT_SYMBOL_GPL(nfs_pageio_reset_read_mds); -void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio, - struct inode *inode, - const struct nfs_pgio_completion_ops *compl_ops) -{ - if (!pnfs_pageio_init_read(pgio, inode, compl_ops)) - nfs_pageio_init_read_mds(pgio, inode, compl_ops); -} - int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, struct page *page) { @@ -149,7 +143,7 @@ int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode, if (len < PAGE_CACHE_SIZE) zero_user_segment(page, len, PAGE_CACHE_SIZE); - nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops); + NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops); nfs_pageio_add_request(&pgio, new); nfs_pageio_complete(&pgio); NFS_I(inode)->read_io += pgio.pg_bytes_written; @@ -407,6 +401,7 @@ int nfs_generic_pagein(struct nfs_pageio_descriptor *desc, return nfs_pagein_multi(desc, hdr); return nfs_pagein_one(desc, hdr); } +EXPORT_SYMBOL_GPL(nfs_generic_pagein); static int nfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc) { @@ -532,11 +527,11 @@ static const struct rpc_call_ops nfs_read_common_ops = { int nfs_readpage(struct file *file, struct page *page) { struct nfs_open_context *ctx; - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; int error; dprintk("NFS: nfs_readpage (%p %ld@%lu)\n", - page, PAGE_CACHE_SIZE, page->index); + page, PAGE_CACHE_SIZE, page_file_index(page)); nfs_inc_stats(inode, NFSIOS_VFSREADPAGE); nfs_add_stats(inode, NFSIOS_READPAGES, 1); @@ -590,7 +585,7 @@ static int readpage_async_filler(void *data, struct page *page) { struct nfs_readdesc *desc = (struct nfs_readdesc *)data; - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; struct nfs_page *new; unsigned int len; int error; @@ -652,7 +647,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping, if (ret == 0) goto read_complete; /* all pages were read */ - nfs_pageio_init_read(&pgio, inode, &nfs_async_read_completion_ops); + NFS_PROTO(inode)->read_pageio_init(&pgio, inode, &nfs_async_read_completion_ops); ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc); diff --git a/fs/nfs/super.c b/fs/nfs/super.c index 120d8e9..d2c7f5d 100644 --- a/fs/nfs/super.c +++ b/fs/nfs/super.c @@ -64,11 +64,12 @@ #include "internal.h" #include "fscache.h" #include "pnfs.h" +#include "nfs.h" #define NFSDBG_FACILITY NFSDBG_VFS #define NFS_TEXT_DATA 1 -#ifdef CONFIG_NFS_V3 +#if IS_ENABLED(CONFIG_NFS_V3) #define NFS_DEFAULT_VERSION 3 #else #define NFS_DEFAULT_VERSION 2 @@ -278,37 +279,17 @@ static match_table_t nfs_vers_tokens = { { Opt_vers_err, NULL } }; -struct nfs_mount_info { - void (*fill_super)(struct super_block *, struct nfs_mount_info *); - int (*set_security)(struct super_block *, struct dentry *, struct nfs_mount_info *); - struct nfs_parsed_mount_data *parsed; - struct nfs_clone_mount *cloned; - struct nfs_fh *mntfh; -}; - -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 dentry *); -static int nfs_show_devname(struct seq_file *, struct dentry *); -static int nfs_show_path(struct seq_file *, struct dentry *); -static int nfs_show_stats(struct seq_file *, struct dentry *); -static struct dentry *nfs_fs_mount_common(struct file_system_type *, - struct nfs_server *, int, const char *, struct nfs_mount_info *); -static struct dentry *nfs_fs_mount(struct file_system_type *, - int, const char *, void *); 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); -static struct file_system_type nfs_fs_type = { +struct file_system_type nfs_fs_type = { .owner = THIS_MODULE, .name = "nfs", .mount = nfs_fs_mount, .kill_sb = nfs_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; +EXPORT_SYMBOL_GPL(nfs_fs_type); struct file_system_type nfs_xdev_fs_type = { .owner = THIS_MODULE, @@ -318,7 +299,7 @@ struct file_system_type nfs_xdev_fs_type = { .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; -static const struct super_operations nfs_sops = { +const struct super_operations nfs_sops = { .alloc_inode = nfs_alloc_inode, .destroy_inode = nfs_destroy_inode, .write_inode = nfs_write_inode, @@ -332,77 +313,40 @@ static const struct super_operations nfs_sops = { .show_stats = nfs_show_stats, .remount_fs = nfs_remount, }; +EXPORT_SYMBOL_GPL(nfs_sops); -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *); static int nfs4_validate_mount_data(void *options, struct nfs_parsed_mount_data *args, const char *dev_name); -static struct dentry *nfs4_try_mount(int flags, const char *dev_name, - struct nfs_mount_info *mount_info); -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 struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data); -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 = { - .owner = THIS_MODULE, - .name = "nfs4", - .mount = nfs_fs_mount, - .kill_sb = nfs4_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, -}; -static struct file_system_type nfs4_remote_fs_type = { +struct file_system_type nfs4_fs_type = { .owner = THIS_MODULE, .name = "nfs4", - .mount = nfs4_remote_mount, - .kill_sb = nfs4_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, -}; - -struct file_system_type nfs4_xdev_fs_type = { - .owner = THIS_MODULE, - .name = "nfs4", - .mount = nfs4_xdev_mount, - .kill_sb = nfs4_kill_super, + .mount = nfs_fs_mount, + .kill_sb = nfs_kill_super, .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, }; +EXPORT_SYMBOL_GPL(nfs4_fs_type); -static struct file_system_type nfs4_remote_referral_fs_type = { - .owner = THIS_MODULE, - .name = "nfs4", - .mount = nfs4_remote_referral_mount, - .kill_sb = nfs4_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, -}; +static int __init register_nfs4_fs(void) +{ + return register_filesystem(&nfs4_fs_type); +} -struct file_system_type nfs4_referral_fs_type = { - .owner = THIS_MODULE, - .name = "nfs4", - .mount = nfs4_referral_mount, - .kill_sb = nfs4_kill_super, - .fs_flags = FS_RENAME_DOES_D_MOVE|FS_REVAL_DOT|FS_BINARY_MOUNTDATA, -}; +static void unregister_nfs4_fs(void) +{ + unregister_filesystem(&nfs4_fs_type); +} +#else +static int __init register_nfs4_fs(void) +{ + return 0; +} -static const struct super_operations nfs4_sops = { - .alloc_inode = nfs_alloc_inode, - .destroy_inode = nfs_destroy_inode, - .write_inode = nfs_write_inode, - .put_super = nfs_put_super, - .statfs = nfs_statfs, - .evict_inode = nfs4_evict_inode, - .umount_begin = nfs_umount_begin, - .show_options = nfs_show_options, - .show_devname = nfs_show_devname, - .show_path = nfs_show_path, - .show_stats = nfs_show_stats, - .remount_fs = nfs_remount, -}; +static void unregister_nfs4_fs(void) +{ +} #endif static struct shrinker acl_shrinker = { @@ -421,21 +365,18 @@ int __init register_nfs_fs(void) if (ret < 0) goto error_0; - ret = nfs_register_sysctl(); + ret = register_nfs4_fs(); if (ret < 0) goto error_1; -#ifdef CONFIG_NFS_V4 - ret = register_filesystem(&nfs4_fs_type); + + ret = nfs_register_sysctl(); if (ret < 0) goto error_2; -#endif register_shrinker(&acl_shrinker); return 0; -#ifdef CONFIG_NFS_V4 error_2: - nfs_unregister_sysctl(); -#endif + unregister_nfs4_fs(); error_1: unregister_filesystem(&nfs_fs_type); error_0: @@ -448,10 +389,8 @@ error_0: void __exit unregister_nfs_fs(void) { unregister_shrinker(&acl_shrinker); -#ifdef CONFIG_NFS_V4 - unregister_filesystem(&nfs4_fs_type); -#endif nfs_unregister_sysctl(); + unregister_nfs4_fs(); unregister_filesystem(&nfs_fs_type); } @@ -462,6 +401,7 @@ void nfs_sb_active(struct super_block *sb) if (atomic_inc_return(&server->active) == 1) atomic_inc(&sb->s_active); } +EXPORT_SYMBOL_GPL(nfs_sb_active); void nfs_sb_deactive(struct super_block *sb) { @@ -470,11 +410,12 @@ void nfs_sb_deactive(struct super_block *sb) if (atomic_dec_and_test(&server->active)) deactivate_super(sb); } +EXPORT_SYMBOL_GPL(nfs_sb_deactive); /* * Deliver file system statistics to userspace */ -static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf) +int nfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct nfs_server *server = NFS_SB(dentry->d_sb); unsigned char blockbits; @@ -535,6 +476,7 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf) dprintk("%s: statfs error = %d\n", __func__, -error); return error; } +EXPORT_SYMBOL_GPL(nfs_statfs); /* * Map the security flavour number to a name @@ -640,7 +582,7 @@ static void nfs_show_mountd_options(struct seq_file *m, struct nfs_server *nfss, nfs_show_mountd_netid(m, nfss, showdefaults); } -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) static void nfs_show_nfsv4_options(struct seq_file *m, struct nfs_server *nfss, int showdefaults) { @@ -757,7 +699,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss, /* * Describe the mount options on this VFS mountpoint */ -static int nfs_show_options(struct seq_file *m, struct dentry *root) +int nfs_show_options(struct seq_file *m, struct dentry *root) { struct nfs_server *nfss = NFS_SB(root->d_sb); @@ -771,8 +713,9 @@ static int nfs_show_options(struct seq_file *m, struct dentry *root) return 0; } +EXPORT_SYMBOL_GPL(nfs_show_options); -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) #ifdef CONFIG_NFS_V4_1 static void show_sessions(struct seq_file *m, struct nfs_server *server) { @@ -805,7 +748,7 @@ static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss) } } #else -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) static void show_pnfs(struct seq_file *m, struct nfs_server *server) { } @@ -815,7 +758,7 @@ static void show_implementation_id(struct seq_file *m, struct nfs_server *nfss) } #endif -static int nfs_show_devname(struct seq_file *m, struct dentry *root) +int nfs_show_devname(struct seq_file *m, struct dentry *root) { char *page = (char *) __get_free_page(GFP_KERNEL); char *devname, *dummy; @@ -830,17 +773,19 @@ static int nfs_show_devname(struct seq_file *m, struct dentry *root) free_page((unsigned long)page); return err; } +EXPORT_SYMBOL_GPL(nfs_show_devname); -static int nfs_show_path(struct seq_file *m, struct dentry *dentry) +int nfs_show_path(struct seq_file *m, struct dentry *dentry) { seq_puts(m, "/"); return 0; } +EXPORT_SYMBOL_GPL(nfs_show_path); /* * Present statistical information for this VFS mountpoint */ -static int nfs_show_stats(struct seq_file *m, struct dentry *root) +int nfs_show_stats(struct seq_file *m, struct dentry *root) { int i, cpu; struct nfs_server *nfss = NFS_SB(root->d_sb); @@ -870,7 +815,7 @@ static int nfs_show_stats(struct seq_file *m, struct dentry *root) seq_printf(m, ",bsize=%u", nfss->bsize); seq_printf(m, ",namlen=%u", nfss->namelen); -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) if (nfss->nfs_client->rpc_ops->version == 4) { seq_printf(m, "\n\tnfsv4:\t"); seq_printf(m, "bm0=0x%x", nfss->attr_bitmask[0]); @@ -928,12 +873,13 @@ static int nfs_show_stats(struct seq_file *m, struct dentry *root) return 0; } +EXPORT_SYMBOL_GPL(nfs_show_stats); /* * Begin unmount by attempting to remove all automounted mountpoints we added * in response to xdev traversals and referrals */ -static void nfs_umount_begin(struct super_block *sb) +void nfs_umount_begin(struct super_block *sb) { struct nfs_server *server; struct rpc_clnt *rpc; @@ -947,6 +893,7 @@ static void nfs_umount_begin(struct super_block *sb) if (!IS_ERR(rpc)) rpc_killall_tasks(rpc); } +EXPORT_SYMBOL_GPL(nfs_umount_begin); static struct nfs_parsed_mount_data *nfs_alloc_parsed_mount_data(void) { @@ -1748,8 +1695,9 @@ static int nfs_request_mount(struct nfs_parsed_mount_data *args, return nfs_walk_authlist(args, &request); } -static struct dentry *nfs_try_mount(int flags, const char *dev_name, - struct nfs_mount_info *mount_info) +struct dentry *nfs_try_mount(int flags, const char *dev_name, + struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) { int status; struct nfs_server *server; @@ -1761,12 +1709,13 @@ static struct dentry *nfs_try_mount(int flags, const char *dev_name, } /* Get a volume representation */ - server = nfs_create_server(mount_info->parsed, mount_info->mntfh); + server = nfs_mod->rpc_ops->create_server(mount_info, nfs_mod); if (IS_ERR(server)) return ERR_CAST(server); - return nfs_fs_mount_common(&nfs_fs_type, server, flags, dev_name, mount_info); + return nfs_fs_mount_common(server, flags, dev_name, mount_info, nfs_mod); } +EXPORT_SYMBOL_GPL(nfs_try_mount); /* * Split "dev_name" into "hostname:export_path". @@ -1918,6 +1867,7 @@ static int nfs23_validate_mount_data(void *options, memcpy(sap, &data->addr, sizeof(data->addr)); args->nfs_server.addrlen = sizeof(data->addr); + args->nfs_server.port = ntohs(data->addr.sin_port); if (!nfs_verify_server_address(sap)) goto out_no_address; @@ -1970,7 +1920,7 @@ static int nfs23_validate_mount_data(void *options, return NFS_TEXT_DATA; } -#ifndef CONFIG_NFS_V3 +#if !IS_ENABLED(CONFIG_NFS_V3) if (args->version == 3) goto out_v3_not_compiled; #endif /* !CONFIG_NFS_V3 */ @@ -1990,7 +1940,7 @@ out_no_sec: dfprintk(MOUNT, "NFS: nfs_mount_data version supports only AUTH_SYS\n"); return -EINVAL; -#ifndef CONFIG_NFS_V3 +#if !IS_ENABLED(CONFIG_NFS_V3) out_v3_not_compiled: dfprintk(MOUNT, "NFS: NFSv3 is not compiled into kernel\n"); return -EPROTONOSUPPORT; @@ -2009,7 +1959,7 @@ out_invalid_fh: return -EINVAL; } -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) static int nfs_validate_mount_data(struct file_system_type *fs_type, void *options, struct nfs_parsed_mount_data *args, @@ -2047,7 +1997,7 @@ static int nfs_validate_text_mount_data(void *options, goto out_no_address; if (args->version == 4) { -#ifdef CONFIG_NFS_V4 +#if IS_ENABLED(CONFIG_NFS_V4) port = NFS_PORT; max_namelen = NFS4_MAXNAMLEN; max_pathlen = NFS4_MAXPATHLEN; @@ -2070,7 +2020,7 @@ static int nfs_validate_text_mount_data(void *options, &args->nfs_server.export_path, max_pathlen); -#ifndef CONFIG_NFS_V4 +#if !IS_ENABLED(CONFIG_NFS_V4) out_v4_not_compiled: dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n"); return -EPROTONOSUPPORT; @@ -2108,7 +2058,7 @@ nfs_compare_remount_data(struct nfs_server *nfss, return 0; } -static int +int nfs_remount(struct super_block *sb, int *flags, char *raw_data) { int error; @@ -2169,11 +2119,12 @@ out: kfree(data); return error; } +EXPORT_SYMBOL_GPL(nfs_remount); /* * Initialise the common bits of the superblock */ -static inline void nfs_initialise_sb(struct super_block *sb) +inline void nfs_initialise_sb(struct super_block *sb) { struct nfs_server *server = NFS_SB(sb); @@ -2195,18 +2146,19 @@ static inline void nfs_initialise_sb(struct super_block *sb) /* * Finish setting up an NFS2/3 superblock */ -static void nfs_fill_super(struct super_block *sb, - struct nfs_mount_info *mount_info) +void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info) { struct nfs_parsed_mount_data *data = mount_info->parsed; struct nfs_server *server = NFS_SB(sb); sb->s_blocksize_bits = 0; sb->s_blocksize = 0; - if (data->bsize) + sb->s_xattr = server->nfs_client->cl_nfs_mod->xattr; + sb->s_op = server->nfs_client->cl_nfs_mod->sops; + if (data && data->bsize) sb->s_blocksize = nfs_block_size(data->bsize, &sb->s_blocksize_bits); - if (server->nfs_client->rpc_ops->version == 3) { + if (server->nfs_client->rpc_ops->version != 2) { /* The VFS shouldn't apply the umask to mode bits. We will do * so ourselves when necessary. */ @@ -2214,15 +2166,14 @@ static void nfs_fill_super(struct super_block *sb, sb->s_time_gran = 1; } - sb->s_op = &nfs_sops; nfs_initialise_sb(sb); } +EXPORT_SYMBOL_GPL(nfs_fill_super); /* - * Finish setting up a cloned NFS2/3 superblock + * Finish setting up a cloned NFS2/3/4 superblock */ -static void nfs_clone_super(struct super_block *sb, - struct nfs_mount_info *mount_info) +void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info) { const struct super_block *old_sb = mount_info->cloned->sb; struct nfs_server *server = NFS_SB(sb); @@ -2230,16 +2181,17 @@ static void nfs_clone_super(struct super_block *sb, sb->s_blocksize_bits = old_sb->s_blocksize_bits; sb->s_blocksize = old_sb->s_blocksize; sb->s_maxbytes = old_sb->s_maxbytes; + sb->s_xattr = old_sb->s_xattr; + sb->s_op = old_sb->s_op; + sb->s_time_gran = 1; - if (server->nfs_client->rpc_ops->version == 3) { + if (server->nfs_client->rpc_ops->version != 2) { /* The VFS shouldn't apply the umask to mode bits. We will do * so ourselves when necessary. */ sb->s_flags |= MS_POSIXACL; - sb->s_time_gran = 1; } - sb->s_op = old_sb->s_op; nfs_initialise_sb(sb); } @@ -2381,14 +2333,15 @@ static int nfs_bdi_register(struct nfs_server *server) return bdi_register_dev(&server->backing_dev_info, server->s_dev); } -static int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot, - struct nfs_mount_info *mount_info) +int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot, + struct nfs_mount_info *mount_info) { return security_sb_set_mnt_opts(s, &mount_info->parsed->lsm_opts); } +EXPORT_SYMBOL_GPL(nfs_set_sb_security); -static int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot, - struct nfs_mount_info *mount_info) +int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot, + struct nfs_mount_info *mount_info) { /* clone any lsm security options from the parent to the new sb */ security_sb_clone_mnt_opts(mount_info->cloned->sb, s); @@ -2396,11 +2349,12 @@ static int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot, return -ESTALE; return 0; } +EXPORT_SYMBOL_GPL(nfs_clone_sb_security); -static struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type, - struct nfs_server *server, - int flags, const char *dev_name, - struct nfs_mount_info *mount_info) +struct dentry *nfs_fs_mount_common(struct nfs_server *server, + int flags, const char *dev_name, + struct nfs_mount_info *mount_info, + struct nfs_subversion *nfs_mod) { struct super_block *s; struct dentry *mntroot = ERR_PTR(-ENOMEM); @@ -2419,7 +2373,7 @@ static struct dentry *nfs_fs_mount_common(struct file_system_type *fs_type, sb_mntdata.mntflags |= MS_SYNCHRONOUS; /* Get a superblock - note that we may end up sharing one that already exists */ - s = sget(fs_type, compare_super, nfs_set_super, flags, &sb_mntdata); + s = sget(nfs_mod->nfs_fs, compare_super, nfs_set_super, flags, &sb_mntdata); if (IS_ERR(s)) { mntroot = ERR_CAST(s); goto out_err_nosb; @@ -2469,8 +2423,9 @@ error_splat_bdi: deactivate_locked_super(s); goto out; } +EXPORT_SYMBOL_GPL(nfs_fs_mount_common); -static struct dentry *nfs_fs_mount(struct file_system_type *fs_type, +struct dentry *nfs_fs_mount(struct file_system_type *fs_type, int flags, const char *dev_name, void *raw_data) { struct nfs_mount_info mount_info = { @@ -2478,6 +2433,7 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type, .set_security = nfs_set_sb_security, }; struct dentry *mntroot = ERR_PTR(-ENOMEM); + struct nfs_subversion *nfs_mod; int error; mount_info.parsed = nfs_alloc_parsed_mount_data(); @@ -2494,34 +2450,38 @@ static struct dentry *nfs_fs_mount(struct file_system_type *fs_type, goto out; } -#ifdef CONFIG_NFS_V4 - if (mount_info.parsed->version == 4) - mntroot = nfs4_try_mount(flags, dev_name, &mount_info); - else -#endif /* CONFIG_NFS_V4 */ - mntroot = nfs_try_mount(flags, dev_name, &mount_info); + nfs_mod = get_nfs_version(mount_info.parsed->version); + if (IS_ERR(nfs_mod)) { + mntroot = ERR_CAST(nfs_mod); + goto out; + } + + mntroot = nfs_mod->rpc_ops->try_mount(flags, dev_name, &mount_info, nfs_mod); + put_nfs_version(nfs_mod); out: nfs_free_parsed_mount_data(mount_info.parsed); nfs_free_fhandle(mount_info.mntfh); return mntroot; } +EXPORT_SYMBOL_GPL(nfs_fs_mount); /* * Ensure that we unregister the bdi before kill_anon_super * releases the device name */ -static void nfs_put_super(struct super_block *s) +void nfs_put_super(struct super_block *s) { struct nfs_server *server = NFS_SB(s); bdi_unregister(&server->backing_dev_info); } +EXPORT_SYMBOL_GPL(nfs_put_super); /* * Destroy an NFS2/3 superblock */ -static void nfs_kill_super(struct super_block *s) +void nfs_kill_super(struct super_block *s) { struct nfs_server *server = NFS_SB(s); @@ -2529,31 +2489,38 @@ static void nfs_kill_super(struct super_block *s) nfs_fscache_release_super_cookie(s); nfs_free_server(server); } +EXPORT_SYMBOL_GPL(nfs_kill_super); /* * Clone an NFS2/3/4 server record on xdev traversal (FSID-change) */ -static struct dentry * -nfs_xdev_mount_common(struct file_system_type *fs_type, int flags, - const char *dev_name, struct nfs_mount_info *mount_info) +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 = mount_info->cloned; + struct nfs_clone_mount *data = raw_data; + struct nfs_mount_info mount_info = { + .fill_super = nfs_clone_super, + .set_security = nfs_clone_sb_security, + .cloned = data, + }; struct nfs_server *server; struct dentry *mntroot = ERR_PTR(-ENOMEM); + struct nfs_subversion *nfs_mod = NFS_SB(data->sb)->nfs_client->cl_nfs_mod; int error; dprintk("--> nfs_xdev_mount_common()\n"); - mount_info->mntfh = data->fh; + mount_info.mntfh = mount_info.cloned->fh; /* create a new volume representation */ - server = nfs_clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor); + server = nfs_mod->rpc_ops->clone_server(NFS_SB(data->sb), data->fh, data->fattr, data->authflavor); if (IS_ERR(server)) { error = PTR_ERR(server); goto out_err; } - mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info); + mntroot = nfs_fs_mount_common(server, flags, dev_name, &mount_info, nfs_mod); dprintk("<-- nfs_xdev_mount_common() = 0\n"); out: return mntroot; @@ -2563,60 +2530,7 @@ out_err: goto out; } -/* - * Clone an NFS2/3 server record on xdev traversal (FSID-change) - */ -static struct dentry * -nfs_xdev_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data) -{ - struct nfs_mount_info mount_info = { - .fill_super = nfs_clone_super, - .set_security = nfs_clone_sb_security, - .cloned = raw_data, - }; - return nfs_xdev_mount_common(&nfs_fs_type, flags, dev_name, &mount_info); -} - -#ifdef CONFIG_NFS_V4 - -/* - * Finish setting up a cloned NFS4 superblock - */ -static void nfs4_clone_super(struct super_block *sb, - struct nfs_mount_info *mount_info) -{ - const struct super_block *old_sb = mount_info->cloned->sb; - sb->s_blocksize_bits = old_sb->s_blocksize_bits; - sb->s_blocksize = old_sb->s_blocksize; - sb->s_maxbytes = old_sb->s_maxbytes; - sb->s_time_gran = 1; - sb->s_op = old_sb->s_op; - /* - * The VFS shouldn't apply the umask to mode bits. We will do - * so ourselves when necessary. - */ - sb->s_flags |= MS_POSIXACL; - sb->s_xattr = old_sb->s_xattr; - nfs_initialise_sb(sb); -} - -/* - * Set up an NFS4 superblock - */ -static void nfs4_fill_super(struct super_block *sb, - struct nfs_mount_info *mount_info) -{ - sb->s_time_gran = 1; - sb->s_op = &nfs4_sops; - /* - * The VFS shouldn't apply the umask to mode bits. We will do - * so ourselves when necessary. - */ - sb->s_flags |= MS_POSIXACL; - sb->s_xattr = nfs4_xattr_handlers; - nfs_initialise_sb(sb); -} +#if IS_ENABLED(CONFIG_NFS_V4) static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args) { @@ -2651,6 +2565,7 @@ static int nfs4_validate_mount_data(void *options, return -EFAULT; if (!nfs_verify_server_address(sap)) goto out_no_address; + args->nfs_server.port = ntohs(((struct sockaddr_in *)sap)->sin_port); if (data->auth_flavourlen) { if (data->auth_flavourlen > 1) @@ -2716,249 +2631,57 @@ out_no_address: } /* - * Get the superblock for the NFS4 root partition + * NFS v4 module parameters need to stay in the + * NFS client for backwards compatibility */ -static struct dentry * -nfs4_remote_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *info) -{ - struct nfs_mount_info *mount_info = info; - struct nfs_server *server; - struct dentry *mntroot = ERR_PTR(-ENOMEM); - - mount_info->fill_super = nfs4_fill_super; - mount_info->set_security = nfs_set_sb_security; - - /* Get a volume representation */ - server = nfs4_create_server(mount_info->parsed, mount_info->mntfh); - if (IS_ERR(server)) { - mntroot = ERR_CAST(server); - goto out; - } - - mntroot = nfs_fs_mount_common(fs_type, server, flags, dev_name, mount_info); - -out: - return mntroot; -} - -static struct vfsmount *nfs_do_root_mount(struct file_system_type *fs_type, - int flags, void *data, const char *hostname) -{ - struct vfsmount *root_mnt; - char *root_devname; - size_t len; +unsigned int nfs_callback_set_tcpport; +unsigned short nfs_callback_tcpport; +/* Default cache timeout is 10 minutes */ +unsigned int nfs_idmap_cache_timeout = 600; +/* Turn off NFSv4 uid/gid mapping when using AUTH_SYS */ +bool nfs4_disable_idmapping = true; +unsigned short max_session_slots = NFS4_DEF_SLOT_TABLE_SIZE; +unsigned short send_implementation_id = 1; + +EXPORT_SYMBOL_GPL(nfs_callback_set_tcpport); +EXPORT_SYMBOL_GPL(nfs_callback_tcpport); +EXPORT_SYMBOL_GPL(nfs_idmap_cache_timeout); +EXPORT_SYMBOL_GPL(nfs4_disable_idmapping); +EXPORT_SYMBOL_GPL(max_session_slots); +EXPORT_SYMBOL_GPL(send_implementation_id); + +#define NFS_CALLBACK_MAXPORTNR (65535U) + +static int param_set_portnr(const char *val, const struct kernel_param *kp) +{ + unsigned long num; + int ret; - len = strlen(hostname) + 5; - root_devname = kmalloc(len, GFP_KERNEL); - if (root_devname == NULL) - return ERR_PTR(-ENOMEM); - /* Does hostname needs to be enclosed in brackets? */ - if (strchr(hostname, ':')) - snprintf(root_devname, len, "[%s]:/", hostname); - else - snprintf(root_devname, len, "%s:/", hostname); - root_mnt = vfs_kern_mount(fs_type, flags, root_devname, data); - kfree(root_devname); - return root_mnt; + if (!val) + return -EINVAL; + ret = strict_strtoul(val, 0, &num); + if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR) + return -EINVAL; + *((unsigned int *)kp->arg) = num; + return 0; } - -struct nfs_referral_count { - struct list_head list; - const struct task_struct *task; - unsigned int referral_count; +static struct kernel_param_ops param_ops_portnr = { + .set = param_set_portnr, + .get = param_get_uint, }; - -static LIST_HEAD(nfs_referral_count_list); -static DEFINE_SPINLOCK(nfs_referral_count_list_lock); - -static struct nfs_referral_count *nfs_find_referral_count(void) -{ - struct nfs_referral_count *p; - - list_for_each_entry(p, &nfs_referral_count_list, list) { - if (p->task == current) - return p; - } - return NULL; -} - -#define NFS_MAX_NESTED_REFERRALS 2 - -static int nfs_referral_loop_protect(void) -{ - struct nfs_referral_count *p, *new; - int ret = -ENOMEM; - - new = kmalloc(sizeof(*new), GFP_KERNEL); - if (!new) - goto out; - new->task = current; - new->referral_count = 1; - - ret = 0; - spin_lock(&nfs_referral_count_list_lock); - p = nfs_find_referral_count(); - if (p != NULL) { - if (p->referral_count >= NFS_MAX_NESTED_REFERRALS) - ret = -ELOOP; - else - p->referral_count++; - } else { - list_add(&new->list, &nfs_referral_count_list); - new = NULL; - } - spin_unlock(&nfs_referral_count_list_lock); - kfree(new); -out: - return ret; -} - -static void nfs_referral_loop_unprotect(void) -{ - struct nfs_referral_count *p; - - spin_lock(&nfs_referral_count_list_lock); - p = nfs_find_referral_count(); - p->referral_count--; - if (p->referral_count == 0) - list_del(&p->list); - else - p = NULL; - spin_unlock(&nfs_referral_count_list_lock); - kfree(p); -} - -static struct dentry *nfs_follow_remote_path(struct vfsmount *root_mnt, - const char *export_path) -{ - struct dentry *dentry; - int err; - - if (IS_ERR(root_mnt)) - return ERR_CAST(root_mnt); - - err = nfs_referral_loop_protect(); - if (err) { - mntput(root_mnt); - return ERR_PTR(err); - } - - dentry = mount_subtree(root_mnt, export_path); - nfs_referral_loop_unprotect(); - - return dentry; -} - -static struct dentry *nfs4_try_mount(int flags, const char *dev_name, - struct nfs_mount_info *mount_info) -{ - char *export_path; - struct vfsmount *root_mnt; - struct dentry *res; - struct nfs_parsed_mount_data *data = mount_info->parsed; - - dfprintk(MOUNT, "--> nfs4_try_mount()\n"); - - mount_info->fill_super = nfs4_fill_super; - - export_path = data->nfs_server.export_path; - data->nfs_server.export_path = "/"; - root_mnt = nfs_do_root_mount(&nfs4_remote_fs_type, flags, mount_info, - data->nfs_server.hostname); - data->nfs_server.export_path = export_path; - - res = nfs_follow_remote_path(root_mnt, export_path); - - dfprintk(MOUNT, "<-- nfs4_try_mount() = %ld%s\n", - IS_ERR(res) ? PTR_ERR(res) : 0, - IS_ERR(res) ? " [error]" : ""); - return res; -} - -static void nfs4_kill_super(struct super_block *sb) -{ - struct nfs_server *server = NFS_SB(sb); - - dprintk("--> %s\n", __func__); - nfs_super_return_all_delegations(sb); - kill_anon_super(sb); - nfs_fscache_release_super_cookie(sb); - nfs_free_server(server); - dprintk("<-- %s\n", __func__); -} - -/* - * Clone an NFS4 server record on xdev traversal (FSID-change) - */ -static struct dentry * -nfs4_xdev_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data) -{ - struct nfs_mount_info mount_info = { - .fill_super = nfs4_clone_super, - .set_security = nfs_clone_sb_security, - .cloned = raw_data, - }; - return nfs_xdev_mount_common(&nfs4_fs_type, flags, dev_name, &mount_info); -} - -static struct dentry * -nfs4_remote_referral_mount(struct file_system_type *fs_type, int flags, - const char *dev_name, void *raw_data) -{ - struct nfs_mount_info mount_info = { - .fill_super = nfs4_fill_super, - .set_security = nfs_clone_sb_security, - .cloned = raw_data, - }; - struct nfs_server *server; - struct dentry *mntroot = ERR_PTR(-ENOMEM); - - dprintk("--> nfs4_referral_get_sb()\n"); - - mount_info.mntfh = nfs_alloc_fhandle(); - if (mount_info.cloned == NULL || mount_info.mntfh == NULL) - goto out; - - /* create a new volume representation */ - server = nfs4_create_referral_server(mount_info.cloned, mount_info.mntfh); - if (IS_ERR(server)) { - mntroot = ERR_CAST(server); - goto out; - } - - mntroot = nfs_fs_mount_common(&nfs4_fs_type, server, flags, dev_name, &mount_info); -out: - nfs_free_fhandle(mount_info.mntfh); - return mntroot; -} - -/* - * Create an NFS4 server record on referral traversal - */ -static struct dentry *nfs4_referral_mount(struct file_system_type *fs_type, - int flags, const char *dev_name, void *raw_data) -{ - struct nfs_clone_mount *data = raw_data; - char *export_path; - struct vfsmount *root_mnt; - struct dentry *res; - - dprintk("--> nfs4_referral_mount()\n"); - - export_path = data->mnt_path; - data->mnt_path = "/"; - - root_mnt = nfs_do_root_mount(&nfs4_remote_referral_fs_type, - flags, data, data->hostname); - data->mnt_path = export_path; - - res = nfs_follow_remote_path(root_mnt, export_path); - dprintk("<-- nfs4_referral_mount() = %ld%s\n", - IS_ERR(res) ? PTR_ERR(res) : 0, - IS_ERR(res) ? " [error]" : ""); - return res; -} +#define param_check_portnr(name, p) __param_check(name, p, unsigned int); + +module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644); +module_param(nfs_idmap_cache_timeout, int, 0644); +module_param(nfs4_disable_idmapping, bool, 0644); +MODULE_PARM_DESC(nfs4_disable_idmapping, + "Turn off NFSv4 idmapping when using 'sec=sys'"); +module_param(max_session_slots, ushort, 0644); +MODULE_PARM_DESC(max_session_slots, "Maximum number of outstanding NFSv4.1 " + "requests the client will negotiate"); +module_param(send_implementation_id, ushort, 0644); +MODULE_PARM_DESC(send_implementation_id, + "Send implementation ID with NFSv4.1 exchange_id"); +MODULE_ALIAS("nfs4"); #endif /* CONFIG_NFS_V4 */ diff --git a/fs/nfs/sysctl.c b/fs/nfs/sysctl.c index ad4d2e7..6b3f253 100644 --- a/fs/nfs/sysctl.c +++ b/fs/nfs/sysctl.c @@ -9,37 +9,11 @@ #include <linux/fs.h> #include <linux/sysctl.h> #include <linux/module.h> -#include <linux/nfs4.h> -#include <linux/nfs_idmap.h> #include <linux/nfs_fs.h> -#include "callback.h" - -#ifdef CONFIG_NFS_V4 -static const int nfs_set_port_min = 0; -static const int nfs_set_port_max = 65535; -#endif static struct ctl_table_header *nfs_callback_sysctl_table; static ctl_table nfs_cb_sysctls[] = { -#ifdef CONFIG_NFS_V4 - { - .procname = "nfs_callback_tcpport", - .data = &nfs_callback_set_tcpport, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = (int *)&nfs_set_port_min, - .extra2 = (int *)&nfs_set_port_max, - }, - { - .procname = "idmap_cache_timeout", - .data = &nfs_idmap_cache_timeout, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, -#endif { .procname = "nfs_mountpoint_timeout", .data = &nfs_mountpoint_expiry_timeout, diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c index 3210a03..13cea63 100644 --- a/fs/nfs/unlink.c +++ b/fs/nfs/unlink.c @@ -501,7 +501,7 @@ nfs_sillyrename(struct inode *dir, struct dentry *dentry) (unsigned long long)NFS_FILEID(dentry->d_inode)); /* Return delegation in anticipation of the rename */ - nfs_inode_return_delegation(dentry->d_inode); + NFS_PROTO(dentry->d_inode)->return_delegation(dentry->d_inode); sdentry = NULL; do { diff --git a/fs/nfs/write.c b/fs/nfs/write.c index 4d6861c..e3b5537 100644 --- a/fs/nfs/write.c +++ b/fs/nfs/write.c @@ -52,7 +52,7 @@ static mempool_t *nfs_commit_mempool; struct nfs_commit_data *nfs_commitdata_alloc(void) { - struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOFS); + struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOIO); if (p) { memset(p, 0, sizeof(*p)); @@ -70,7 +70,7 @@ EXPORT_SYMBOL_GPL(nfs_commit_free); struct nfs_write_header *nfs_writehdr_alloc(void) { - struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS); + struct nfs_write_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO); if (p) { struct nfs_pgio_header *hdr = &p->header; @@ -84,6 +84,7 @@ struct nfs_write_header *nfs_writehdr_alloc(void) } return p; } +EXPORT_SYMBOL_GPL(nfs_writehdr_alloc); static struct nfs_write_data *nfs_writedata_alloc(struct nfs_pgio_header *hdr, unsigned int pagecount) @@ -115,6 +116,7 @@ void nfs_writehdr_free(struct nfs_pgio_header *hdr) struct nfs_write_header *whdr = container_of(hdr, struct nfs_write_header, header); mempool_free(whdr, nfs_wdata_mempool); } +EXPORT_SYMBOL_GPL(nfs_writehdr_free); void nfs_writedata_release(struct nfs_write_data *wdata) { @@ -131,6 +133,7 @@ void nfs_writedata_release(struct nfs_write_data *wdata) if (atomic_dec_and_test(&hdr->refcnt)) hdr->completion_ops->completion(hdr); } +EXPORT_SYMBOL_GPL(nfs_writedata_release); static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) { @@ -139,25 +142,38 @@ static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error) set_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags); } -static struct nfs_page *nfs_page_find_request_locked(struct page *page) +static struct nfs_page * +nfs_page_find_request_locked(struct nfs_inode *nfsi, struct page *page) { struct nfs_page *req = NULL; - if (PagePrivate(page)) { + if (PagePrivate(page)) req = (struct nfs_page *)page_private(page); - if (req != NULL) - kref_get(&req->wb_kref); + else if (unlikely(PageSwapCache(page))) { + struct nfs_page *freq, *t; + + /* Linearly search the commit list for the correct req */ + list_for_each_entry_safe(freq, t, &nfsi->commit_info.list, wb_list) { + if (freq->wb_page == page) { + req = freq; + break; + } + } } + + if (req) + kref_get(&req->wb_kref); + return req; } static struct nfs_page *nfs_page_find_request(struct page *page) { - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; struct nfs_page *req = NULL; spin_lock(&inode->i_lock); - req = nfs_page_find_request_locked(page); + req = nfs_page_find_request_locked(NFS_I(inode), page); spin_unlock(&inode->i_lock); return req; } @@ -165,16 +181,16 @@ static struct nfs_page *nfs_page_find_request(struct page *page) /* Adjust the file length if we're writing beyond the end */ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int count) { - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; loff_t end, i_size; pgoff_t end_index; spin_lock(&inode->i_lock); i_size = i_size_read(inode); end_index = (i_size - 1) >> PAGE_CACHE_SHIFT; - if (i_size > 0 && page->index < end_index) + if (i_size > 0 && page_file_index(page) < end_index) goto out; - end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + ((loff_t)offset+count); + end = page_file_offset(page) + ((loff_t)offset+count); if (i_size >= end) goto out; i_size_write(inode, end); @@ -187,7 +203,7 @@ out: static void nfs_set_pageerror(struct page *page) { SetPageError(page); - nfs_zap_mapping(page->mapping->host, page->mapping); + nfs_zap_mapping(page_file_mapping(page)->host, page_file_mapping(page)); } /* We can set the PG_uptodate flag if we see that a write request @@ -228,7 +244,7 @@ static int nfs_set_page_writeback(struct page *page) int ret = test_set_page_writeback(page); if (!ret) { - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; struct nfs_server *nfss = NFS_SERVER(inode); if (atomic_long_inc_return(&nfss->writeback) > @@ -242,7 +258,7 @@ static int nfs_set_page_writeback(struct page *page) static void nfs_end_page_writeback(struct page *page) { - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; struct nfs_server *nfss = NFS_SERVER(inode); end_page_writeback(page); @@ -252,13 +268,13 @@ static void nfs_end_page_writeback(struct page *page) static struct nfs_page *nfs_find_and_lock_request(struct page *page, bool nonblock) { - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; struct nfs_page *req; int ret; spin_lock(&inode->i_lock); for (;;) { - req = nfs_page_find_request_locked(page); + req = nfs_page_find_request_locked(NFS_I(inode), page); if (req == NULL) break; if (nfs_lock_request(req)) @@ -313,13 +329,13 @@ out: static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio) { - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; int ret; nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE); nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1); - nfs_pageio_cond_complete(pgio, page->index); + nfs_pageio_cond_complete(pgio, page_file_index(page)); ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE); if (ret == -EAGAIN) { redirty_page_for_writepage(wbc, page); @@ -336,8 +352,10 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc struct nfs_pageio_descriptor pgio; int err; - nfs_pageio_init_write(&pgio, page->mapping->host, wb_priority(wbc), - &nfs_async_write_completion_ops); + NFS_PROTO(page_file_mapping(page)->host)->write_pageio_init(&pgio, + page->mapping->host, + wb_priority(wbc), + &nfs_async_write_completion_ops); err = nfs_do_writepage(page, wbc, &pgio); nfs_pageio_complete(&pgio); if (err < 0) @@ -380,8 +398,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc) nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES); - nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), - &nfs_async_write_completion_ops); + NFS_PROTO(inode)->write_pageio_init(&pgio, inode, wb_priority(wbc), &nfs_async_write_completion_ops); err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio); nfs_pageio_complete(&pgio); @@ -410,11 +427,17 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req) nfs_lock_request(req); spin_lock(&inode->i_lock); - if (!nfsi->npages && nfs_have_delegation(inode, FMODE_WRITE)) + if (!nfsi->npages && NFS_PROTO(inode)->have_delegation(inode, FMODE_WRITE)) inode->i_version++; - set_bit(PG_MAPPED, &req->wb_flags); - SetPagePrivate(req->wb_page); - set_page_private(req->wb_page, (unsigned long)req); + /* + * Swap-space should not get truncated. Hence no need to plug the race + * with invalidate/truncate. + */ + if (likely(!PageSwapCache(req->wb_page))) { + set_bit(PG_MAPPED, &req->wb_flags); + SetPagePrivate(req->wb_page); + set_page_private(req->wb_page, (unsigned long)req); + } nfsi->npages++; kref_get(&req->wb_kref); spin_unlock(&inode->i_lock); @@ -431,9 +454,11 @@ static void nfs_inode_remove_request(struct nfs_page *req) BUG_ON (!NFS_WBACK_BUSY(req)); spin_lock(&inode->i_lock); - set_page_private(req->wb_page, 0); - ClearPagePrivate(req->wb_page); - clear_bit(PG_MAPPED, &req->wb_flags); + if (likely(!PageSwapCache(req->wb_page))) { + set_page_private(req->wb_page, 0); + ClearPagePrivate(req->wb_page); + clear_bit(PG_MAPPED, &req->wb_flags); + } nfsi->npages--; spin_unlock(&inode->i_lock); nfs_release_request(req); @@ -445,7 +470,7 @@ nfs_mark_request_dirty(struct nfs_page *req) __set_page_dirty_nobuffers(req->wb_page); } -#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) +#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) /** * nfs_request_add_commit_list - add request to a commit list * @req: pointer to a struct nfs_page @@ -470,7 +495,7 @@ nfs_request_add_commit_list(struct nfs_page *req, struct list_head *dst, spin_unlock(cinfo->lock); if (!cinfo->dreq) { inc_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - inc_bdi_stat(req->wb_page->mapping->backing_dev_info, + inc_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info, BDI_RECLAIMABLE); __mark_inode_dirty(req->wb_context->dentry->d_inode, I_DIRTY_DATASYNC); @@ -537,7 +562,7 @@ static void nfs_clear_page_commit(struct page *page) { dec_zone_page_state(page, NR_UNSTABLE_NFS); - dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE); + dec_bdi_stat(page_file_mapping(page)->backing_dev_info, BDI_RECLAIMABLE); } static void @@ -620,7 +645,7 @@ static void nfs_write_completion(struct nfs_pgio_header *hdr) goto next; } if (test_bit(NFS_IOHDR_NEED_COMMIT, &hdr->flags)) { - memcpy(&req->wb_verf, hdr->verf, sizeof(req->wb_verf)); + memcpy(&req->wb_verf, &hdr->verf->verifier, sizeof(req->wb_verf)); nfs_mark_request_commit(req, hdr->lseg, &cinfo); goto next; } @@ -635,7 +660,7 @@ out: hdr->release(hdr); } -#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) +#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) static unsigned long nfs_reqs_to_commit(struct nfs_commit_info *cinfo) { @@ -729,7 +754,7 @@ static struct nfs_page *nfs_try_to_update_request(struct inode *inode, spin_lock(&inode->i_lock); for (;;) { - req = nfs_page_find_request_locked(page); + req = nfs_page_find_request_locked(NFS_I(inode), page); if (req == NULL) goto out_unlock; @@ -788,7 +813,7 @@ out_err: static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx, struct page *page, unsigned int offset, unsigned int bytes) { - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; struct nfs_page *req; req = nfs_try_to_update_request(inode, page, offset, bytes); @@ -841,7 +866,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page) nfs_release_request(req); if (!do_flush) return 0; - status = nfs_wb_page(page->mapping->host, page); + status = nfs_wb_page(page_file_mapping(page)->host, page); } while (status == 0); return status; } @@ -871,7 +896,7 @@ int nfs_updatepage(struct file *file, struct page *page, unsigned int offset, unsigned int count) { struct nfs_open_context *ctx = nfs_file_open_context(file); - struct inode *inode = page->mapping->host; + struct inode *inode = page_file_mapping(page)->host; int status = 0; nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE); @@ -879,7 +904,7 @@ int nfs_updatepage(struct file *file, struct page *page, dprintk("NFS: nfs_updatepage(%s/%s %d@%lld)\n", file->f_path.dentry->d_parent->d_name.name, file->f_path.dentry->d_name.name, count, - (long long)(page_offset(page) + offset)); + (long long)(page_file_offset(page) + offset)); /* If we're not using byte range locks, and we know the page * is up to date, it may be more efficient to extend the write @@ -1172,6 +1197,7 @@ int nfs_generic_flush(struct nfs_pageio_descriptor *desc, return nfs_flush_multi(desc, hdr); return nfs_flush_one(desc, hdr); } +EXPORT_SYMBOL_GPL(nfs_generic_flush); static int nfs_generic_pg_writepages(struct nfs_pageio_descriptor *desc) { @@ -1202,13 +1228,14 @@ static const struct nfs_pageio_ops nfs_pageio_write_ops = { .pg_doio = nfs_generic_pg_writepages, }; -void nfs_pageio_init_write_mds(struct nfs_pageio_descriptor *pgio, +void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, struct inode *inode, int ioflags, const struct nfs_pgio_completion_ops *compl_ops) { nfs_pageio_init(pgio, inode, &nfs_pageio_write_ops, compl_ops, NFS_SERVER(inode)->wsize, ioflags); } +EXPORT_SYMBOL_GPL(nfs_pageio_init_write); void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) { @@ -1217,13 +1244,6 @@ void nfs_pageio_reset_write_mds(struct nfs_pageio_descriptor *pgio) } EXPORT_SYMBOL_GPL(nfs_pageio_reset_write_mds); -void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio, - struct inode *inode, int ioflags, - const struct nfs_pgio_completion_ops *compl_ops) -{ - if (!pnfs_pageio_init_write(pgio, inode, ioflags, compl_ops)) - nfs_pageio_init_write_mds(pgio, inode, ioflags, compl_ops); -} void nfs_write_prepare(struct rpc_task *task, void *calldata) { @@ -1303,7 +1323,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) return; nfs_add_stats(inode, NFSIOS_SERVERWRITTENBYTES, resp->count); -#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) +#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) if (resp->verf->committed < argp->stable && task->tk_status >= 0) { /* We tried a write call, but the server did not * commit data to stable storage even though we @@ -1363,7 +1383,7 @@ void nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data) } -#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4) +#if IS_ENABLED(CONFIG_NFS_V3) || IS_ENABLED(CONFIG_NFS_V4) static int nfs_commit_set_lock(struct nfs_inode *nfsi, int may_wait) { int ret; @@ -1475,7 +1495,7 @@ void nfs_retry_commit(struct list_head *page_list, nfs_mark_request_commit(req, lseg, cinfo); if (!cinfo->dreq) { dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS); - dec_bdi_stat(req->wb_page->mapping->backing_dev_info, + dec_bdi_stat(page_file_mapping(req->wb_page)->backing_dev_info, BDI_RECLAIMABLE); } nfs_unlock_and_release_request(req); @@ -1547,7 +1567,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data) /* Okay, COMMIT succeeded, apparently. Check the verifier * returned by the server against all stored verfs. */ - if (!memcmp(req->wb_verf.verifier, data->verf.verifier, sizeof(data->verf.verifier))) { + if (!memcmp(&req->wb_verf, &data->verf.verifier, sizeof(req->wb_verf))) { /* We have a match */ nfs_inode_remove_request(req); dprintk(" OK\n"); @@ -1677,22 +1697,9 @@ static int nfs_commit_unstable_pages(struct inode *inode, struct writeback_contr int nfs_write_inode(struct inode *inode, struct writeback_control *wbc) { - int ret; - - ret = nfs_commit_unstable_pages(inode, wbc); - if (ret >= 0 && test_bit(NFS_INO_LAYOUTCOMMIT, &NFS_I(inode)->flags)) { - int status; - bool sync = true; - - if (wbc->sync_mode == WB_SYNC_NONE) - sync = false; - - status = pnfs_layoutcommit_inode(inode, sync); - if (status < 0) - return status; - } - return ret; + return nfs_commit_unstable_pages(inode, wbc); } +EXPORT_SYMBOL_GPL(nfs_write_inode); /* * flush the inode to disk. @@ -1708,6 +1715,7 @@ int nfs_wb_all(struct inode *inode) return sync_inode(inode, &wbc); } +EXPORT_SYMBOL_GPL(nfs_wb_all); int nfs_wb_page_cancel(struct inode *inode, struct page *page) { @@ -1744,7 +1752,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page) */ int nfs_wb_page(struct inode *inode, struct page *page) { - loff_t range_start = page_offset(page); + loff_t range_start = page_file_offset(page); loff_t range_end = range_start + (loff_t)(PAGE_CACHE_SIZE - 1); struct writeback_control wbc = { .sync_mode = WB_SYNC_ALL, @@ -1806,19 +1814,19 @@ int __init nfs_init_writepagecache(void) nfs_wdata_mempool = mempool_create_slab_pool(MIN_POOL_WRITE, nfs_wdata_cachep); if (nfs_wdata_mempool == NULL) - return -ENOMEM; + goto out_destroy_write_cache; nfs_cdata_cachep = kmem_cache_create("nfs_commit_data", sizeof(struct nfs_commit_data), 0, SLAB_HWCACHE_ALIGN, NULL); if (nfs_cdata_cachep == NULL) - return -ENOMEM; + goto out_destroy_write_mempool; nfs_commit_mempool = mempool_create_slab_pool(MIN_POOL_COMMIT, nfs_wdata_cachep); if (nfs_commit_mempool == NULL) - return -ENOMEM; + goto out_destroy_commit_cache; /* * NFS congestion size, scale with available memory. @@ -1841,11 +1849,20 @@ int __init nfs_init_writepagecache(void) nfs_congestion_kb = 256*1024; return 0; + +out_destroy_commit_cache: + kmem_cache_destroy(nfs_cdata_cachep); +out_destroy_write_mempool: + mempool_destroy(nfs_wdata_mempool); +out_destroy_write_cache: + kmem_cache_destroy(nfs_wdata_cachep); + return -ENOMEM; } void nfs_destroy_writepagecache(void) { mempool_destroy(nfs_commit_mempool); + kmem_cache_destroy(nfs_cdata_cachep); mempool_destroy(nfs_wdata_mempool); kmem_cache_destroy(nfs_wdata_cachep); } |