diff options
Diffstat (limited to 'fs/nfsd')
-rw-r--r-- | fs/nfsd/fault_inject.c | 142 | ||||
-rw-r--r-- | fs/nfsd/filecache.c | 150 | ||||
-rw-r--r-- | fs/nfsd/filecache.h | 5 | ||||
-rw-r--r-- | fs/nfsd/netns.h | 3 | ||||
-rw-r--r-- | fs/nfsd/nfs2acl.c | 9 | ||||
-rw-r--r-- | fs/nfsd/nfs3acl.c | 9 | ||||
-rw-r--r-- | fs/nfsd/nfs3proc.c | 7 | ||||
-rw-r--r-- | fs/nfsd/nfs4layouts.c | 4 | ||||
-rw-r--r-- | fs/nfsd/nfs4proc.c | 210 | ||||
-rw-r--r-- | fs/nfsd/nfs4recover.c | 6 | ||||
-rw-r--r-- | fs/nfsd/nfs4state.c | 182 | ||||
-rw-r--r-- | fs/nfsd/nfs4xdr.c | 17 | ||||
-rw-r--r-- | fs/nfsd/nfscache.c | 4 | ||||
-rw-r--r-- | fs/nfsd/nfsctl.c | 84 | ||||
-rw-r--r-- | fs/nfsd/nfsd.h | 8 | ||||
-rw-r--r-- | fs/nfsd/nfsfh.c | 44 | ||||
-rw-r--r-- | fs/nfsd/nfsfh.h | 29 | ||||
-rw-r--r-- | fs/nfsd/nfsproc.c | 12 | ||||
-rw-r--r-- | fs/nfsd/nfssvc.c | 25 | ||||
-rw-r--r-- | fs/nfsd/state.h | 2 | ||||
-rw-r--r-- | fs/nfsd/trace.h | 83 | ||||
-rw-r--r-- | fs/nfsd/vfs.c | 49 | ||||
-rw-r--r-- | fs/nfsd/vfs.h | 7 | ||||
-rw-r--r-- | fs/nfsd/xdr4.h | 2 |
24 files changed, 489 insertions, 604 deletions
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c deleted file mode 100644 index 76bee0a0d308..000000000000 --- a/fs/nfsd/fault_inject.c +++ /dev/null @@ -1,142 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0 -/* - * Copyright (c) 2011 Bryan Schumaker <bjschuma@netapp.com> - * - * Uses debugfs to create fault injection points for client testing - */ - -#include <linux/types.h> -#include <linux/fs.h> -#include <linux/debugfs.h> -#include <linux/module.h> -#include <linux/nsproxy.h> -#include <linux/sunrpc/addr.h> -#include <linux/uaccess.h> -#include <linux/kernel.h> - -#include "state.h" -#include "netns.h" - -struct nfsd_fault_inject_op { - char *file; - u64 (*get)(void); - u64 (*set_val)(u64); - u64 (*set_clnt)(struct sockaddr_storage *, size_t); -}; - -static struct dentry *debug_dir; - -static ssize_t fault_inject_read(struct file *file, char __user *buf, - size_t len, loff_t *ppos) -{ - static u64 val; - char read_buf[25]; - size_t size; - loff_t pos = *ppos; - struct nfsd_fault_inject_op *op = file_inode(file)->i_private; - - if (!pos) - val = op->get(); - size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val); - - return simple_read_from_buffer(buf, len, ppos, read_buf, size); -} - -static ssize_t fault_inject_write(struct file *file, const char __user *buf, - size_t len, loff_t *ppos) -{ - char write_buf[INET6_ADDRSTRLEN]; - size_t size = min(sizeof(write_buf) - 1, len); - struct net *net = current->nsproxy->net_ns; - struct sockaddr_storage sa; - struct nfsd_fault_inject_op *op = file_inode(file)->i_private; - u64 val; - char *nl; - - if (copy_from_user(write_buf, buf, size)) - return -EFAULT; - write_buf[size] = '\0'; - - /* Deal with any embedded newlines in the string */ - nl = strchr(write_buf, '\n'); - if (nl) { - size = nl - write_buf; - *nl = '\0'; - } - - size = rpc_pton(net, write_buf, size, (struct sockaddr *)&sa, sizeof(sa)); - if (size > 0) { - val = op->set_clnt(&sa, size); - if (val) - pr_info("NFSD [%s]: Client %s had %llu state object(s)\n", - op->file, write_buf, val); - } else { - val = simple_strtoll(write_buf, NULL, 0); - if (val == 0) - pr_info("NFSD Fault Injection: %s (all)", op->file); - else - pr_info("NFSD Fault Injection: %s (n = %llu)", - op->file, val); - val = op->set_val(val); - pr_info("NFSD: %s: found %llu", op->file, val); - } - return len; /* on success, claim we got the whole input */ -} - -static const struct file_operations fops_nfsd = { - .owner = THIS_MODULE, - .read = fault_inject_read, - .write = fault_inject_write, -}; - -void nfsd_fault_inject_cleanup(void) -{ - debugfs_remove_recursive(debug_dir); -} - -static struct nfsd_fault_inject_op inject_ops[] = { - { - .file = "forget_clients", - .get = nfsd_inject_print_clients, - .set_val = nfsd_inject_forget_clients, - .set_clnt = nfsd_inject_forget_client, - }, - { - .file = "forget_locks", - .get = nfsd_inject_print_locks, - .set_val = nfsd_inject_forget_locks, - .set_clnt = nfsd_inject_forget_client_locks, - }, - { - .file = "forget_openowners", - .get = nfsd_inject_print_openowners, - .set_val = nfsd_inject_forget_openowners, - .set_clnt = nfsd_inject_forget_client_openowners, - }, - { - .file = "forget_delegations", - .get = nfsd_inject_print_delegations, - .set_val = nfsd_inject_forget_delegations, - .set_clnt = nfsd_inject_forget_client_delegations, - }, - { - .file = "recall_delegations", - .get = nfsd_inject_print_delegations, - .set_val = nfsd_inject_recall_delegations, - .set_clnt = nfsd_inject_recall_client_delegations, - }, -}; - -void nfsd_fault_inject_init(void) -{ - unsigned int i; - struct nfsd_fault_inject_op *op; - umode_t mode = S_IFREG | S_IRUSR | S_IWUSR; - - debug_dir = debugfs_create_dir("nfsd", NULL); - - for (i = 0; i < ARRAY_SIZE(inject_ops); i++) { - op = &inject_ops[i]; - debugfs_create_file(op->file, mode, debug_dir, op, &fops_nfsd); - } -} diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c index 45b2c9e3f636..6e8712bd7c99 100644 --- a/fs/nfsd/filecache.c +++ b/fs/nfsd/filecache.c @@ -331,37 +331,27 @@ nfsd_file_alloc(struct nfsd_file_lookup_key *key, unsigned int may) return nf; } +/** + * nfsd_file_check_write_error - check for writeback errors on a file + * @nf: nfsd_file to check for writeback errors + * + * Check whether a nfsd_file has an unseen error. Reset the write + * verifier if so. + */ static void -nfsd_file_fsync(struct nfsd_file *nf) -{ - struct file *file = nf->nf_file; - int ret; - - if (!file || !(file->f_mode & FMODE_WRITE)) - return; - ret = vfs_fsync(file, 1); - trace_nfsd_file_fsync(nf, ret); - if (ret) - nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); -} - -static int nfsd_file_check_write_error(struct nfsd_file *nf) { struct file *file = nf->nf_file; - if (!file || !(file->f_mode & FMODE_WRITE)) - return 0; - return filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err)); + if ((file->f_mode & FMODE_WRITE) && + filemap_check_wb_err(file->f_mapping, READ_ONCE(file->f_wb_err))) + nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); } static void nfsd_file_hash_remove(struct nfsd_file *nf) { trace_nfsd_file_unhash(nf); - - if (nfsd_file_check_write_error(nf)) - nfsd_reset_write_verifier(net_generic(nf->nf_net, nfsd_net_id)); rhashtable_remove_fast(&nfsd_file_rhash_tbl, &nf->nf_rhash, nfsd_file_rhash_params); } @@ -387,23 +377,12 @@ nfsd_file_free(struct nfsd_file *nf) this_cpu_add(nfsd_file_total_age, age); nfsd_file_unhash(nf); - - /* - * We call fsync here in order to catch writeback errors. It's not - * strictly required by the protocol, but an nfsd_file could get - * evicted from the cache before a COMMIT comes in. If another - * task were to open that file in the interim and scrape the error, - * then the client may never see it. By calling fsync here, we ensure - * that writeback happens before the entry is freed, and that any - * errors reported result in the write verifier changing. - */ - nfsd_file_fsync(nf); - if (nf->nf_mark) nfsd_file_mark_put(nf->nf_mark); if (nf->nf_file) { get_file(nf->nf_file); filp_close(nf->nf_file, NULL); + nfsd_file_check_write_error(nf); fput(nf->nf_file); } @@ -452,7 +431,7 @@ static bool nfsd_file_lru_remove(struct nfsd_file *nf) struct nfsd_file * nfsd_file_get(struct nfsd_file *nf) { - if (likely(refcount_inc_not_zero(&nf->nf_ref))) + if (nf && refcount_inc_not_zero(&nf->nf_ref)) return nf; return NULL; } @@ -662,6 +641,39 @@ static struct shrinker nfsd_file_shrinker = { }; /** + * nfsd_file_cond_queue - conditionally unhash and queue a nfsd_file + * @nf: nfsd_file to attempt to queue + * @dispose: private list to queue successfully-put objects + * + * Unhash an nfsd_file, try to get a reference to it, and then put that + * reference. If it's the last reference, queue it to the dispose list. + */ +static void +nfsd_file_cond_queue(struct nfsd_file *nf, struct list_head *dispose) + __must_hold(RCU) +{ + int decrement = 1; + + /* If we raced with someone else unhashing, ignore it */ + if (!nfsd_file_unhash(nf)) + return; + + /* If we can't get a reference, ignore it */ + if (!nfsd_file_get(nf)) + return; + + /* Extra decrement if we remove from the LRU */ + if (nfsd_file_lru_remove(nf)) + ++decrement; + + /* If refcount goes to 0, then put on the dispose list */ + if (refcount_sub_and_test(decrement, &nf->nf_ref)) { + list_add(&nf->nf_lru, dispose); + trace_nfsd_file_closing(nf); + } +} + +/** * nfsd_file_queue_for_close: try to close out any open nfsd_files for an inode * @inode: inode on which to close out nfsd_files * @dispose: list on which to gather nfsd_files to close out @@ -688,30 +700,11 @@ nfsd_file_queue_for_close(struct inode *inode, struct list_head *dispose) rcu_read_lock(); do { - int decrement = 1; - nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, nfsd_file_rhash_params); if (!nf) break; - - /* If we raced with someone else unhashing, ignore it */ - if (!nfsd_file_unhash(nf)) - continue; - - /* If we can't get a reference, ignore it */ - if (!nfsd_file_get(nf)) - continue; - - /* Extra decrement if we remove from the LRU */ - if (nfsd_file_lru_remove(nf)) - ++decrement; - - /* If refcount goes to 0, then put on the dispose list */ - if (refcount_sub_and_test(decrement, &nf->nf_ref)) { - list_add(&nf->nf_lru, dispose); - trace_nfsd_file_closing(nf); - } + nfsd_file_cond_queue(nf, dispose); } while (1); rcu_read_unlock(); } @@ -928,11 +921,8 @@ __nfsd_file_cache_purge(struct net *net) nf = rhashtable_walk_next(&iter); while (!IS_ERR_OR_NULL(nf)) { - if (!net || nf->nf_net == net) { - nfsd_file_unhash(nf); - nfsd_file_lru_remove(nf); - list_add(&nf->nf_lru, &dispose); - } + if (!net || nf->nf_net == net) + nfsd_file_cond_queue(nf, &dispose); nf = rhashtable_walk_next(&iter); } @@ -1071,8 +1061,8 @@ nfsd_file_is_cached(struct inode *inode) static __be32 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, - unsigned int may_flags, struct nfsd_file **pnf, - bool open, bool want_gc) + unsigned int may_flags, struct file *file, + struct nfsd_file **pnf, bool want_gc) { struct nfsd_file_lookup_key key = { .type = NFSD_FILE_KEY_FULL, @@ -1096,8 +1086,7 @@ retry: rcu_read_lock(); nf = rhashtable_lookup(&nfsd_file_rhash_tbl, &key, nfsd_file_rhash_params); - if (nf) - nf = nfsd_file_get(nf); + nf = nfsd_file_get(nf); rcu_read_unlock(); if (nf) { @@ -1147,8 +1136,8 @@ wait_for_construction: status = nfserrno(nfsd_open_break_lease(file_inode(nf->nf_file), may_flags)); out: if (status == nfs_ok) { - if (open) - this_cpu_inc(nfsd_file_acquisitions); + this_cpu_inc(nfsd_file_acquisitions); + nfsd_file_check_write_error(nf); *pnf = nf; } else { if (refcount_dec_and_test(&nf->nf_ref)) @@ -1158,20 +1147,23 @@ out: out_status: put_cred(key.cred); - if (open) - trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); + trace_nfsd_file_acquire(rqstp, key.inode, may_flags, nf, status); return status; open_file: trace_nfsd_file_alloc(nf); nf->nf_mark = nfsd_file_mark_find_or_create(nf, key.inode); if (nf->nf_mark) { - if (open) { + if (file) { + get_file(file); + nf->nf_file = file; + status = nfs_ok; + trace_nfsd_file_opened(nf, status); + } else { status = nfsd_open_verified(rqstp, fhp, may_flags, &nf->nf_file); trace_nfsd_file_open(nf, status); - } else - status = nfs_ok; + } } else status = nfserr_jukebox; /* @@ -1207,7 +1199,7 @@ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, true); + return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true); } /** @@ -1228,28 +1220,30 @@ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, true, false); + return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false); } /** - * nfsd_file_create - Get a struct nfsd_file, do not open + * nfsd_file_acquire_opened - Get a struct nfsd_file using existing open file * @rqstp: the RPC transaction being executed * @fhp: the NFS filehandle of the file just created * @may_flags: NFSD_MAY_ settings for the file + * @file: cached, already-open file (may be NULL) * @pnf: OUT: new or found "struct nfsd_file" object * - * The nfsd_file_object returned by this API is reference-counted - * but not garbage-collected. The object is released immediately - * one RCU grace period after the final nfsd_file_put(). + * Acquire a nfsd_file object that is not GC'ed. If one doesn't already exist, + * and @file is non-NULL, use it to instantiate a new nfsd_file instead of + * opening a new one. * * Returns nfs_ok and sets @pnf on success; otherwise an nfsstat in * network byte order is returned. */ __be32 -nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp, - unsigned int may_flags, struct nfsd_file **pnf) +nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct file *file, + struct nfsd_file **pnf) { - return nfsd_file_do_acquire(rqstp, fhp, may_flags, pnf, false, false); + return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false); } /* diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h index b7efb2c3ddb1..41516a4263ea 100644 --- a/fs/nfsd/filecache.h +++ b/fs/nfsd/filecache.h @@ -60,7 +60,8 @@ __be32 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **nfp); __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp, unsigned int may_flags, struct nfsd_file **nfp); -__be32 nfsd_file_create(struct svc_rqst *rqstp, struct svc_fh *fhp, - unsigned int may_flags, struct nfsd_file **nfp); +__be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp, + unsigned int may_flags, struct file *file, + struct nfsd_file **nfp); int nfsd_file_cache_stats_show(struct seq_file *m, void *v); #endif /* _FS_NFSD_FILECACHE_H */ diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h index 8c854ba3285b..ec49b200b797 100644 --- a/fs/nfsd/netns.h +++ b/fs/nfsd/netns.h @@ -10,6 +10,7 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> +#include <linux/filelock.h> #include <linux/percpu_counter.h> #include <linux/siphash.h> @@ -195,7 +196,7 @@ struct nfsd_net { atomic_t nfsd_courtesy_clients; struct shrinker nfsd_client_shrinker; - struct delayed_work nfsd_shrinker_work; + struct work_struct nfsd_shrinker_work; }; /* Simple check to find out if a given net was properly initialized */ diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c index 1457f59f447a..12b2b9bc07bf 100644 --- a/fs/nfsd/nfs2acl.c +++ b/fs/nfsd/nfs2acl.c @@ -113,11 +113,11 @@ static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp) inode_lock(inode); - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_ACCESS, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS, argp->acl_access); if (error) goto out_drop_lock; - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_DEFAULT, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT, argp->acl_default); if (error) goto out_drop_lock; @@ -377,10 +377,11 @@ static const struct svc_procedure nfsd_acl_procedures2[5] = { }, }; -static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)]); const struct svc_version nfsd_acl_version2 = { .vs_vers = 2, - .vs_nproc = 5, + .vs_nproc = ARRAY_SIZE(nfsd_acl_procedures2), .vs_proc = nfsd_acl_procedures2, .vs_count = nfsd_acl_count2, .vs_dispatch = nfsd_dispatch, diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c index 647108138e8a..73adca47d373 100644 --- a/fs/nfsd/nfs3acl.c +++ b/fs/nfsd/nfs3acl.c @@ -103,11 +103,11 @@ static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp) inode_lock(inode); - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_ACCESS, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_ACCESS, argp->acl_access); if (error) goto out_drop_lock; - error = set_posix_acl(&init_user_ns, fh->fh_dentry, ACL_TYPE_DEFAULT, + error = set_posix_acl(&nop_mnt_idmap, fh->fh_dentry, ACL_TYPE_DEFAULT, argp->acl_default); out_drop_lock: @@ -266,10 +266,11 @@ static const struct svc_procedure nfsd_acl_procedures3[3] = { }, }; -static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)]); const struct svc_version nfsd_acl_version3 = { .vs_vers = 3, - .vs_nproc = 3, + .vs_nproc = ARRAY_SIZE(nfsd_acl_procedures3), .vs_proc = nfsd_acl_procedures3, .vs_count = nfsd_acl_count3, .vs_dispatch = nfsd_dispatch, diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c index d01b29aba662..e6bb8eeb5bc2 100644 --- a/fs/nfsd/nfs3proc.c +++ b/fs/nfsd/nfs3proc.c @@ -320,7 +320,7 @@ nfsd3_create_file(struct svc_rqst *rqstp, struct svc_fh *fhp, iap->ia_mode &= ~current_umask(); fh_fill_pre_attrs(fhp); - host_err = vfs_create(&init_user_ns, inode, child, iap->ia_mode, true); + host_err = vfs_create(&nop_mnt_idmap, inode, child, iap->ia_mode, true); if (host_err < 0) { status = nfserrno(host_err); goto out; @@ -1064,10 +1064,11 @@ static const struct svc_procedure nfsd_procedures3[22] = { }, }; -static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_count3[ARRAY_SIZE(nfsd_procedures3)]); const struct svc_version nfsd_version3 = { .vs_vers = 3, - .vs_nproc = 22, + .vs_nproc = ARRAY_SIZE(nfsd_procedures3), .vs_proc = nfsd_procedures3, .vs_dispatch = nfsd_dispatch, .vs_count = nfsd_count3, diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c index 3564d1c6f610..e8a80052cb1b 100644 --- a/fs/nfsd/nfs4layouts.c +++ b/fs/nfsd/nfs4layouts.c @@ -323,11 +323,11 @@ nfsd4_recall_file_layout(struct nfs4_layout_stateid *ls) if (ls->ls_recalled) goto out_unlock; - ls->ls_recalled = true; - atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls); if (list_empty(&ls->ls_layouts)) goto out_unlock; + ls->ls_recalled = true; + atomic_inc(&ls->ls_stid.sc_file->fi_lo_recalls); trace_nfsd_layout_recall(&ls->ls_stid.sc_stateid); refcount_inc(&ls->ls_stid.sc_count); diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c index bd880d55f565..5ae670807449 100644 --- a/fs/nfsd/nfs4proc.c +++ b/fs/nfsd/nfs4proc.c @@ -937,7 +937,7 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, * the client wants us to do more in this compound: */ if (!nfsd4_last_compound_op(rqstp)) - __clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); + clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); /* check stateid */ status = nfs4_preprocess_stateid_op(rqstp, cstate, &cstate->current_fh, @@ -1214,8 +1214,10 @@ out: return status; out_put_dst: nfsd_file_put(*dst); + *dst = NULL; out_put_src: nfsd_file_put(*src); + *src = NULL; goto out; } @@ -1293,15 +1295,15 @@ extern void nfs_sb_deactive(struct super_block *sb); * setup a work entry in the ssc delayed unmount list. */ static __be32 nfsd4_ssc_setup_dul(struct nfsd_net *nn, char *ipaddr, - struct nfsd4_ssc_umount_item **retwork, struct vfsmount **ss_mnt) + struct nfsd4_ssc_umount_item **nsui) { struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd4_ssc_umount_item *work = NULL; struct nfsd4_ssc_umount_item *tmp; DEFINE_WAIT(wait); + __be32 status = 0; - *ss_mnt = NULL; - *retwork = NULL; + *nsui = NULL; work = kzalloc(sizeof(*work), GFP_KERNEL); try_again: spin_lock(&nn->nfsd_ssc_lock); @@ -1318,18 +1320,19 @@ try_again: /* allow 20secs for mount/unmount for now - revisit */ if (signal_pending(current) || (schedule_timeout(20*HZ) == 0)) { + finish_wait(&nn->nfsd_ssc_waitq, &wait); kfree(work); return nfserr_eagain; } finish_wait(&nn->nfsd_ssc_waitq, &wait); goto try_again; } - *ss_mnt = ni->nsui_vfsmount; + *nsui = ni; refcount_inc(&ni->nsui_refcnt); spin_unlock(&nn->nfsd_ssc_lock); kfree(work); - /* return vfsmount in ss_mnt */ + /* return vfsmount in (*nsui)->nsui_vfsmount */ return 0; } if (work) { @@ -1337,31 +1340,32 @@ try_again: refcount_set(&work->nsui_refcnt, 2); work->nsui_busy = true; list_add_tail(&work->nsui_list, &nn->nfsd_ssc_mount_list); - *retwork = work; - } + *nsui = work; + } else + status = nfserr_resource; spin_unlock(&nn->nfsd_ssc_lock); - return 0; + return status; } -static void nfsd4_ssc_update_dul_work(struct nfsd_net *nn, - struct nfsd4_ssc_umount_item *work, struct vfsmount *ss_mnt) +static void nfsd4_ssc_update_dul(struct nfsd_net *nn, + struct nfsd4_ssc_umount_item *nsui, + struct vfsmount *ss_mnt) { - /* set nsui_vfsmount, clear busy flag and wakeup waiters */ spin_lock(&nn->nfsd_ssc_lock); - work->nsui_vfsmount = ss_mnt; - work->nsui_busy = false; + nsui->nsui_vfsmount = ss_mnt; + nsui->nsui_busy = false; wake_up_all(&nn->nfsd_ssc_waitq); spin_unlock(&nn->nfsd_ssc_lock); } -static void nfsd4_ssc_cancel_dul_work(struct nfsd_net *nn, - struct nfsd4_ssc_umount_item *work) +static void nfsd4_ssc_cancel_dul(struct nfsd_net *nn, + struct nfsd4_ssc_umount_item *nsui) { spin_lock(&nn->nfsd_ssc_lock); - list_del(&work->nsui_list); + list_del(&nsui->nsui_list); wake_up_all(&nn->nfsd_ssc_waitq); spin_unlock(&nn->nfsd_ssc_lock); - kfree(work); + kfree(nsui); } /* @@ -1369,7 +1373,7 @@ static void nfsd4_ssc_cancel_dul_work(struct nfsd_net *nn, */ static __be32 nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, - struct vfsmount **mount) + struct nfsd4_ssc_umount_item **nsui) { struct file_system_type *type; struct vfsmount *ss_mnt; @@ -1380,7 +1384,6 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, char *ipaddr, *dev_name, *raw_data; int len, raw_len; __be32 status = nfserr_inval; - struct nfsd4_ssc_umount_item *work = NULL; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); naddr = &nss->u.nl4_addr; @@ -1388,6 +1391,7 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, naddr->addr_len, (struct sockaddr *)&tmp_addr, sizeof(tmp_addr)); + *nsui = NULL; if (tmp_addrlen == 0) goto out_err; @@ -1430,10 +1434,10 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, goto out_free_rawdata; snprintf(dev_name, len + 5, "%s%s%s:/", startsep, ipaddr, endsep); - status = nfsd4_ssc_setup_dul(nn, ipaddr, &work, &ss_mnt); + status = nfsd4_ssc_setup_dul(nn, ipaddr, nsui); if (status) goto out_free_devname; - if (ss_mnt) + if ((*nsui)->nsui_vfsmount) goto out_done; /* Use an 'internal' mount: SB_KERNMOUNT -> MNT_INTERNAL */ @@ -1441,15 +1445,12 @@ nfsd4_interssc_connect(struct nl4_server *nss, struct svc_rqst *rqstp, module_put(type->owner); if (IS_ERR(ss_mnt)) { status = nfserr_nodev; - if (work) - nfsd4_ssc_cancel_dul_work(nn, work); + nfsd4_ssc_cancel_dul(nn, *nsui); goto out_free_devname; } - if (work) - nfsd4_ssc_update_dul_work(nn, work, ss_mnt); + nfsd4_ssc_update_dul(nn, *nsui, ss_mnt); out_done: status = 0; - *mount = ss_mnt; out_free_devname: kfree(dev_name); @@ -1473,7 +1474,7 @@ out_err: static __be32 nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_copy *copy, struct vfsmount **mount) + struct nfsd4_copy *copy) { struct svc_fh *s_fh = NULL; stateid_t *s_stid = ©->cp_src_stateid; @@ -1486,7 +1487,7 @@ nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, if (status) goto out; - status = nfsd4_interssc_connect(copy->cp_src, rqstp, mount); + status = nfsd4_interssc_connect(copy->cp_src, rqstp, ©->ss_nsui); if (status) goto out; @@ -1504,45 +1505,26 @@ out: } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, +nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp, struct nfsd_file *dst) { - bool found = false; - long timeout; - struct nfsd4_ssc_umount_item *tmp; - struct nfsd4_ssc_umount_item *ni = NULL; struct nfsd_net *nn = net_generic(dst->nf_net, nfsd_net_id); + long timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout); nfs42_ssc_close(filp); - nfsd_file_put(dst); fput(filp); - if (!nn) { - mntput(ss_mnt); - return; - } spin_lock(&nn->nfsd_ssc_lock); - timeout = msecs_to_jiffies(nfsd4_ssc_umount_timeout); - list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { - if (ni->nsui_vfsmount->mnt_sb == ss_mnt->mnt_sb) { - list_del(&ni->nsui_list); - /* - * vfsmount can be shared by multiple exports, - * decrement refcnt. If the count drops to 1 it - * will be unmounted when nsui_expire expires. - */ - refcount_dec(&ni->nsui_refcnt); - ni->nsui_expire = jiffies + timeout; - list_add_tail(&ni->nsui_list, &nn->nfsd_ssc_mount_list); - found = true; - break; - } - } + list_del(&nsui->nsui_list); + /* + * vfsmount can be shared by multiple exports, + * decrement refcnt. If the count drops to 1 it + * will be unmounted when nsui_expire expires. + */ + refcount_dec(&nsui->nsui_refcnt); + nsui->nsui_expire = jiffies + timeout; + list_add_tail(&nsui->nsui_list, &nn->nfsd_ssc_mount_list); spin_unlock(&nn->nfsd_ssc_lock); - if (!found) { - mntput(ss_mnt); - return; - } } #else /* CONFIG_NFSD_V4_2_INTER_SSC */ @@ -1550,15 +1532,13 @@ nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, static __be32 nfsd4_setup_inter_ssc(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, - struct nfsd4_copy *copy, - struct vfsmount **mount) + struct nfsd4_copy *copy) { - *mount = NULL; return nfserr_inval; } static void -nfsd4_cleanup_inter_ssc(struct vfsmount *ss_mnt, struct file *filp, +nfsd4_cleanup_inter_ssc(struct nfsd4_ssc_umount_item *nsui, struct file *filp, struct nfsd_file *dst) { } @@ -1581,13 +1561,6 @@ nfsd4_setup_intra_ssc(struct svc_rqst *rqstp, ©->nf_dst); } -static void -nfsd4_cleanup_intra_ssc(struct nfsd_file *src, struct nfsd_file *dst) -{ - nfsd_file_put(src); - nfsd_file_put(dst); -} - static void nfsd4_cb_offload_release(struct nfsd4_callback *cb) { struct nfsd4_cb_offload *cbo = @@ -1699,18 +1672,27 @@ static void dup_copy_fields(struct nfsd4_copy *src, struct nfsd4_copy *dst) memcpy(dst->cp_src, src->cp_src, sizeof(struct nl4_server)); memcpy(&dst->stateid, &src->stateid, sizeof(src->stateid)); memcpy(&dst->c_fh, &src->c_fh, sizeof(src->c_fh)); - dst->ss_mnt = src->ss_mnt; + dst->ss_nsui = src->ss_nsui; +} + +static void release_copy_files(struct nfsd4_copy *copy) +{ + if (copy->nf_src) + nfsd_file_put(copy->nf_src); + if (copy->nf_dst) + nfsd_file_put(copy->nf_dst); } static void cleanup_async_copy(struct nfsd4_copy *copy) { nfs4_free_copy_state(copy); - nfsd_file_put(copy->nf_dst); - if (!nfsd4_ssc_is_inter(copy)) - nfsd_file_put(copy->nf_src); - spin_lock(©->cp_clp->async_lock); - list_del(©->copies); - spin_unlock(©->cp_clp->async_lock); + release_copy_files(copy); + if (copy->cp_clp) { + spin_lock(©->cp_clp->async_lock); + if (!list_empty(©->copies)) + list_del_init(©->copies); + spin_unlock(©->cp_clp->async_lock); + } nfs4_put_copy(copy); } @@ -1748,8 +1730,8 @@ static int nfsd4_do_async_copy(void *data) if (nfsd4_ssc_is_inter(copy)) { struct file *filp; - filp = nfs42_ssc_open(copy->ss_mnt, ©->c_fh, - ©->stateid); + filp = nfs42_ssc_open(copy->ss_nsui->nsui_vfsmount, + ©->c_fh, ©->stateid); if (IS_ERR(filp)) { switch (PTR_ERR(filp)) { case -EBADF: @@ -1763,11 +1745,10 @@ static int nfsd4_do_async_copy(void *data) } nfserr = nfsd4_do_copy(copy, filp, copy->nf_dst->nf_file, false); - nfsd4_cleanup_inter_ssc(copy->ss_mnt, filp, copy->nf_dst); + nfsd4_cleanup_inter_ssc(copy->ss_nsui, filp, copy->nf_dst); } else { nfserr = nfsd4_do_copy(copy, copy->nf_src->nf_file, copy->nf_dst->nf_file, false); - nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst); } do_callback: @@ -1789,8 +1770,7 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, status = nfserr_notsupp; goto out; } - status = nfsd4_setup_inter_ssc(rqstp, cstate, copy, - ©->ss_mnt); + status = nfsd4_setup_inter_ssc(rqstp, cstate, copy); if (status) return nfserr_offload_denied; } else { @@ -1809,12 +1789,13 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, async_copy = kzalloc(sizeof(struct nfsd4_copy), GFP_KERNEL); if (!async_copy) goto out_err; + INIT_LIST_HEAD(&async_copy->copies); + refcount_set(&async_copy->refcount, 1); async_copy->cp_src = kmalloc(sizeof(*async_copy->cp_src), GFP_KERNEL); if (!async_copy->cp_src) goto out_err; if (!nfs4_init_copy_state(nn, copy)) goto out_err; - refcount_set(&async_copy->refcount, 1); memcpy(©->cp_res.cb_stateid, ©->cp_stateid.cs_stid, sizeof(copy->cp_res.cb_stateid)); dup_copy_fields(copy, async_copy); @@ -1831,38 +1812,53 @@ nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } else { status = nfsd4_do_copy(copy, copy->nf_src->nf_file, copy->nf_dst->nf_file, true); - nfsd4_cleanup_intra_ssc(copy->nf_src, copy->nf_dst); } out: + release_copy_files(copy); return status; out_err: + if (nfsd4_ssc_is_inter(copy)) { + /* + * Source's vfsmount of inter-copy will be unmounted + * by the laundromat. Use copy instead of async_copy + * since async_copy->ss_nsui might not be set yet. + */ + refcount_dec(©->ss_nsui->nsui_refcnt); + } if (async_copy) cleanup_async_copy(async_copy); status = nfserrno(-ENOMEM); - /* - * source's vfsmount of inter-copy will be unmounted - * by the laundromat - */ goto out; } -struct nfsd4_copy * -find_async_copy(struct nfs4_client *clp, stateid_t *stateid) +static struct nfsd4_copy * +find_async_copy_locked(struct nfs4_client *clp, stateid_t *stateid) { struct nfsd4_copy *copy; - spin_lock(&clp->async_lock); + lockdep_assert_held(&clp->async_lock); + list_for_each_entry(copy, &clp->async_copies, copies) { if (memcmp(©->cp_stateid.cs_stid, stateid, NFS4_STATEID_SIZE)) continue; - refcount_inc(©->refcount); - spin_unlock(&clp->async_lock); return copy; } - spin_unlock(&clp->async_lock); return NULL; } +static struct nfsd4_copy * +find_async_copy(struct nfs4_client *clp, stateid_t *stateid) +{ + struct nfsd4_copy *copy; + + spin_lock(&clp->async_lock); + copy = find_async_copy_locked(clp, stateid); + if (copy) + refcount_inc(©->refcount); + spin_unlock(&clp->async_lock); + return copy; +} + static __be32 nfsd4_offload_cancel(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, @@ -1947,22 +1943,24 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfsd_file_put(nf); return status; } + static __be32 nfsd4_offload_status(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_offload_status *os = &u->offload_status; - __be32 status = 0; + __be32 status = nfs_ok; struct nfsd4_copy *copy; struct nfs4_client *clp = cstate->clp; - copy = find_async_copy(clp, &os->stateid); - if (copy) { + spin_lock(&clp->async_lock); + copy = find_async_copy_locked(clp, &os->stateid); + if (copy) os->count = copy->cp_res.wr_bytes_written; - nfs4_put_copy(copy); - } else + else status = nfserr_bad_stateid; + spin_unlock(&clp->async_lock); return status; } @@ -2607,12 +2605,11 @@ nfsd4_proc_compound(struct svc_rqst *rqstp) cstate->minorversion = args->minorversion; fh_init(current_fh, NFS4_FHSIZE); fh_init(save_fh, NFS4_FHSIZE); - /* * Don't use the deferral mechanism for NFSv4; compounds make it * too hard to avoid non-idempotency problems. */ - __clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); + clear_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); /* * According to RFC3010, this takes precedence over all other errors. @@ -2734,7 +2731,7 @@ encode_op: out: cstate->status = status; /* Reset deferral mechanism for RPC deferrals */ - __set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); + set_bit(RQ_USEDEFERRAL, &rqstp->rq_flags); return rpc_success; } @@ -3619,12 +3616,13 @@ static const struct svc_procedure nfsd_procedures4[2] = { }, }; -static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_count4[ARRAY_SIZE(nfsd_procedures4)]); const struct svc_version nfsd_version4 = { .vs_vers = 4, - .vs_nproc = 2, + .vs_nproc = ARRAY_SIZE(nfsd_procedures4), .vs_proc = nfsd_procedures4, - .vs_count = nfsd_count3, + .vs_count = nfsd_count4, .vs_dispatch = nfsd_dispatch, .vs_xdrsize = NFS4_SVC_XDRSIZE, .vs_rpcb_optnl = true, diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c index 78b8cd9651d5..3509e73abe1f 100644 --- a/fs/nfsd/nfs4recover.c +++ b/fs/nfsd/nfs4recover.c @@ -233,7 +233,7 @@ nfsd4_create_clid_dir(struct nfs4_client *clp) * as well be forgiving and just succeed silently. */ goto out_put; - status = vfs_mkdir(&init_user_ns, d_inode(dir), dentry, S_IRWXU); + status = vfs_mkdir(&nop_mnt_idmap, d_inode(dir), dentry, S_IRWXU); out_put: dput(dentry); out_unlock: @@ -353,7 +353,7 @@ nfsd4_unlink_clid_dir(char *name, int namlen, struct nfsd_net *nn) status = -ENOENT; if (d_really_is_negative(dentry)) goto out; - status = vfs_rmdir(&init_user_ns, d_inode(dir), dentry); + status = vfs_rmdir(&nop_mnt_idmap, d_inode(dir), dentry); out: dput(dentry); out_unlock: @@ -443,7 +443,7 @@ purge_old(struct dentry *parent, struct dentry *child, struct nfsd_net *nn) if (nfs4_has_reclaimed_state(name, nn)) goto out_free; - status = vfs_rmdir(&init_user_ns, d_inode(parent), child); + status = vfs_rmdir(&nop_mnt_idmap, d_inode(parent), child); if (status) printk("failed to remove client recovery directory %pd\n", child); diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index 7b2ee535ade8..6e61fa3acaf1 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -600,23 +600,15 @@ put_nfs4_file(struct nfs4_file *fi) } static struct nfsd_file * -__nfs4_get_fd(struct nfs4_file *f, int oflag) -{ - if (f->fi_fds[oflag]) - return nfsd_file_get(f->fi_fds[oflag]); - return NULL; -} - -static struct nfsd_file * find_writeable_file_locked(struct nfs4_file *f) { struct nfsd_file *ret; lockdep_assert_held(&f->fi_lock); - ret = __nfs4_get_fd(f, O_WRONLY); + ret = nfsd_file_get(f->fi_fds[O_WRONLY]); if (!ret) - ret = __nfs4_get_fd(f, O_RDWR); + ret = nfsd_file_get(f->fi_fds[O_RDWR]); return ret; } @@ -639,9 +631,9 @@ find_readable_file_locked(struct nfs4_file *f) lockdep_assert_held(&f->fi_lock); - ret = __nfs4_get_fd(f, O_RDONLY); + ret = nfsd_file_get(f->fi_fds[O_RDONLY]); if (!ret) - ret = __nfs4_get_fd(f, O_RDWR); + ret = nfsd_file_get(f->fi_fds[O_RDWR]); return ret; } @@ -665,11 +657,11 @@ find_any_file(struct nfs4_file *f) if (!f) return NULL; spin_lock(&f->fi_lock); - ret = __nfs4_get_fd(f, O_RDWR); + ret = nfsd_file_get(f->fi_fds[O_RDWR]); if (!ret) { - ret = __nfs4_get_fd(f, O_WRONLY); + ret = nfsd_file_get(f->fi_fds[O_WRONLY]); if (!ret) - ret = __nfs4_get_fd(f, O_RDONLY); + ret = nfsd_file_get(f->fi_fds[O_RDONLY]); } spin_unlock(&f->fi_lock); return ret; @@ -688,15 +680,6 @@ static struct nfsd_file *find_any_file_locked(struct nfs4_file *f) return NULL; } -static struct nfsd_file *find_deleg_file_locked(struct nfs4_file *f) -{ - lockdep_assert_held(&f->fi_lock); - - if (f->fi_deleg_file) - return f->fi_deleg_file; - return NULL; -} - static atomic_long_t num_delegations; unsigned long max_delegations; @@ -992,7 +975,6 @@ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, stid->cs_stid.si_opaque.so_clid.cl_boot = (u32)nn->boot_time; stid->cs_stid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id; - stid->cs_type = cs_type; idr_preload(GFP_KERNEL); spin_lock(&nn->s2s_cp_lock); @@ -1003,6 +985,7 @@ static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, idr_preload_end(); if (new_id < 0) return 0; + stid->cs_type = cs_type; return 1; } @@ -1036,7 +1019,8 @@ void nfs4_free_copy_state(struct nfsd4_copy *copy) { struct nfsd_net *nn; - WARN_ON_ONCE(copy->cp_stateid.cs_type != NFS4_COPY_STID); + if (copy->cp_stateid.cs_type != NFS4_COPY_STID) + return; nn = net_generic(copy->cp_clp->net, nfsd_net_id); spin_lock(&nn->s2s_cp_lock); idr_remove(&nn->s2s_cp_stateids, @@ -2705,7 +2689,7 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) ds = delegstateid(st); nf = st->sc_file; spin_lock(&nf->fi_lock); - file = find_deleg_file_locked(nf); + file = nf->fi_deleg_file; if (!file) goto out; @@ -4411,7 +4395,7 @@ nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) if (!count) count = atomic_long_read(&num_delegations); if (count) - mod_delayed_work(laundry_wq, &nn->nfsd_shrinker_work, 0); + queue_work(laundry_wq, &nn->nfsd_shrinker_work); return (unsigned long)count; } @@ -4421,7 +4405,7 @@ nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc) return SHRINK_STOP; } -int +void nfsd4_init_leases_net(struct nfsd_net *nn) { struct sysinfo si; @@ -4443,16 +4427,6 @@ nfsd4_init_leases_net(struct nfsd_net *nn) nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB); atomic_set(&nn->nfsd_courtesy_clients, 0); - nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; - nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; - nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; - return register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client"); -} - -void -nfsd4_leases_net_shutdown(struct nfsd_net *nn) -{ - unregister_shrinker(&nn->nfsd_client_shrinker); } static void init_nfs4_replay(struct nfs4_replay *rp) @@ -5262,18 +5236,10 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, if (!fp->fi_fds[oflag]) { spin_unlock(&fp->fi_lock); - if (!open->op_filp) { - status = nfsd_file_acquire(rqstp, cur_fh, access, &nf); - if (status != nfs_ok) - goto out_put_access; - } else { - status = nfsd_file_create(rqstp, cur_fh, access, &nf); - if (status != nfs_ok) - goto out_put_access; - nf->nf_file = open->op_filp; - open->op_filp = NULL; - trace_nfsd_file_create(rqstp, access, nf); - } + status = nfsd_file_acquire_opened(rqstp, cur_fh, access, + open->op_filp, &nf); + if (status != nfs_ok) + goto out_put_access; spin_lock(&fp->fi_lock); if (!fp->fi_fds[oflag]) { @@ -5316,16 +5282,17 @@ nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, /* test and set deny mode */ spin_lock(&fp->fi_lock); status = nfs4_file_check_deny(fp, open->op_share_deny); - if (status == nfs_ok) { - if (status != nfserr_share_denied) { - set_deny(open->op_share_deny, stp); - fp->fi_share_deny |= - (open->op_share_deny & NFS4_SHARE_DENY_BOTH); - } else { - if (nfs4_resolve_deny_conflicts_locked(fp, false, - stp, open->op_share_deny, false)) - status = nfserr_jukebox; - } + switch (status) { + case nfs_ok: + set_deny(open->op_share_deny, stp); + fp->fi_share_deny |= + (open->op_share_deny & NFS4_SHARE_DENY_BOTH); + break; + case nfserr_share_denied: + if (nfs4_resolve_deny_conflicts_locked(fp, false, + stp, open->op_share_deny, false)) + status = nfserr_jukebox; + break; } spin_unlock(&fp->fi_lock); @@ -5374,7 +5341,7 @@ static int nfsd4_check_conflicting_opens(struct nfs4_client *clp, { struct nfs4_ol_stateid *st; struct file *f = fp->fi_deleg_file->nf_file; - struct inode *ino = locks_inode(f); + struct inode *ino = file_inode(f); int writes; writes = atomic_read(&ino->i_writecount); @@ -5456,6 +5423,23 @@ nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp, return 0; } +/* + * We avoid breaking delegations held by a client due to its own activity, but + * clearing setuid/setgid bits on a write is an implicit activity and the client + * may not notice and continue using the old mode. Avoid giving out a delegation + * on setuid/setgid files when the client is requesting an open for write. + */ +static int +nfsd4_verify_setuid_write(struct nfsd4_open *open, struct nfsd_file *nf) +{ + struct inode *inode = file_inode(nf->nf_file); + + if ((open->op_share_access & NFS4_SHARE_ACCESS_WRITE) && + (inode->i_mode & (S_ISUID|S_ISGID))) + return -EAGAIN; + return 0; +} + static struct nfs4_delegation * nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, struct svc_fh *parent) @@ -5489,6 +5473,8 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, spin_lock(&fp->fi_lock); if (nfs4_delegation_exists(clp, fp)) status = -EAGAIN; + else if (nfsd4_verify_setuid_write(open, nf)) + status = -EAGAIN; else if (!fp->fi_deleg_file) { fp->fi_deleg_file = nf; /* increment early to prevent fi_deleg_file from being @@ -5529,6 +5515,14 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, if (status) goto out_unlock; + /* + * Now that the deleg is set, check again to ensure that nothing + * raced in and changed the mode while we weren't lookng. + */ + status = nfsd4_verify_setuid_write(open, fp->fi_deleg_file); + if (status) + goto out_unlock; + spin_lock(&state_lock); spin_lock(&fp->fi_lock); if (fp->fi_had_conflict) @@ -6243,8 +6237,7 @@ deleg_reaper(struct nfsd_net *nn) static void nfsd4_state_shrinker_worker(struct work_struct *work) { - struct delayed_work *dwork = to_delayed_work(work); - struct nfsd_net *nn = container_of(dwork, struct nfsd_net, + struct nfsd_net *nn = container_of(work, struct nfsd_net, nfsd_shrinker_work); courtesy_client_reaper(nn); @@ -6425,23 +6418,26 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, static struct nfsd_file * nfs4_find_file(struct nfs4_stid *s, int flags) { + struct nfsd_file *ret = NULL; + if (!s) return NULL; switch (s->sc_type) { case NFS4_DELEG_STID: - if (WARN_ON_ONCE(!s->sc_file->fi_deleg_file)) - return NULL; - return nfsd_file_get(s->sc_file->fi_deleg_file); + spin_lock(&s->sc_file->fi_lock); + ret = nfsd_file_get(s->sc_file->fi_deleg_file); + spin_unlock(&s->sc_file->fi_lock); + break; case NFS4_OPEN_STID: case NFS4_LOCK_STID: if (flags & RD_STATE) - return find_readable_file(s->sc_file); + ret = find_readable_file(s->sc_file); else - return find_writeable_file(s->sc_file); + ret = find_writeable_file(s->sc_file); } - return NULL; + return ret; } static __be32 @@ -6566,8 +6562,19 @@ void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) spin_unlock(&nn->s2s_cp_lock); } -/* - * Checks for stateid operations +/** + * nfs4_preprocess_stateid_op - find and prep stateid for an operation + * @rqstp: incoming request from client + * @cstate: current compound state + * @fhp: filehandle associated with requested stateid + * @stateid: stateid (provided by client) + * @flags: flags describing type of operation to be done + * @nfp: optional nfsd_file return pointer (may be NULL) + * @cstid: optional returned nfs4_stid pointer (may be NULL) + * + * Given info from the client, look up a nfs4_stid for the operation. On + * success, it returns a reference to the nfs4_stid and/or the nfsd_file + * associated with it. */ __be32 nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, @@ -6756,8 +6763,18 @@ static __be32 nfs4_seqid_op_checks(struct nfsd4_compound_state *cstate, stateid_ return status; } -/* - * Checks for sequence id mutating operations. +/** + * nfs4_preprocess_seqid_op - find and prep an ol_stateid for a seqid-morphing op + * @cstate: compund state + * @seqid: seqid (provided by client) + * @stateid: stateid (provided by client) + * @typemask: mask of allowable types for this operation + * @stpp: return pointer for the stateid found + * @nn: net namespace for request + * + * Given a stateid+seqid from a client, look up an nfs4_ol_stateid and + * return it in @stpp. On a nfs_ok return, the returned stateid will + * have its st_mutex locked. */ static __be32 nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, @@ -7828,7 +7845,7 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) return status; } - inode = locks_inode(nf->nf_file); + inode = file_inode(nf->nf_file); flctx = locks_inode_context(inode); if (flctx && !list_empty_careful(&flctx->flc_posix)) { @@ -8074,11 +8091,20 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->blocked_locks_lru); INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); - INIT_DELAYED_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); + INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net); + nn->nfsd_client_shrinker.scan_objects = nfsd4_state_shrinker_scan; + nn->nfsd_client_shrinker.count_objects = nfsd4_state_shrinker_count; + nn->nfsd_client_shrinker.seeks = DEFAULT_SEEKS; + + if (register_shrinker(&nn->nfsd_client_shrinker, "nfsd-client")) + goto err_shrinker; return 0; +err_shrinker: + put_net(net); + kfree(nn->sessionid_hashtbl); err_sessionid: kfree(nn->unconf_id_hashtbl); err_unconf_id: @@ -8171,6 +8197,8 @@ nfs4_state_shutdown_net(struct net *net) struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + unregister_shrinker(&nn->nfsd_client_shrinker); + cancel_work(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); @@ -8190,7 +8218,6 @@ nfs4_state_shutdown_net(struct net *net) nfsd4_client_tracking_exit(net); nfs4_state_destroy_net(net); - rhltable_destroy(&nfs4_file_rhltable); #ifdef CONFIG_NFSD_V4_2_INTER_SSC nfsd4_ssc_shutdown_umount(nn); #endif @@ -8200,6 +8227,7 @@ void nfs4_state_shutdown(void) { nfsd4_destroy_callback_queue(); + rhltable_destroy(&nfs4_file_rhltable); } static void diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index 2b4ae858c89b..e12e5a4ad502 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -2523,7 +2523,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp) argp->rqstp->rq_cachetype = cachethis ? RC_REPLBUFF : RC_NOCACHE; if (readcount > 1 || max_reply > PAGE_SIZE - auth_slack) - __clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); + clear_bit(RQ_SPLICE_OK, &argp->rqstp->rq_flags); return true; } @@ -2965,7 +2965,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp, goto out; } - err = vfs_getattr(&path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT); + err = vfs_getattr(&path, &stat, + STATX_BASIC_STATS | STATX_BTIME | STATX_CHANGE_COOKIE, + AT_STATX_SYNC_AS_STAT); if (err) goto out_nfserr; if (!(stat.result_mask & STATX_BTIME)) @@ -3629,6 +3631,17 @@ nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, case nfserr_noent: xdr_truncate_encode(xdr, start_offset); goto skip_entry; + case nfserr_jukebox: + /* + * The pseudoroot should only display dentries that lead to + * exports. If we get EJUKEBOX here, then we can't tell whether + * this entry should be included. Just fail the whole READDIR + * with NFS4ERR_DELAY in that case, and hope that the situation + * will resolve itself by the client's next attempt. + */ + if (cd->rd_fhp->fh_export->ex_flags & NFSEXP_V4ROOT) + goto fail; + fallthrough; default: /* * If the client requested the RDATTR_ERROR attribute, diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c index 3e64a3d50a1c..041faa13b852 100644 --- a/fs/nfsd/nfscache.c +++ b/fs/nfsd/nfscache.c @@ -488,7 +488,7 @@ found_entry: case RC_NOCACHE: break; case RC_REPLSTAT: - svc_putu32(&rqstp->rq_res.head[0], rp->c_replstat); + xdr_stream_encode_be32(&rqstp->rq_res_stream, rp->c_replstat); rtn = RC_REPLY; break; case RC_REPLBUFF: @@ -509,7 +509,7 @@ out_trace: * nfsd_cache_update - Update an entry in the duplicate reply cache. * @rqstp: svc_rqst with a finished Reply * @cachetype: which cache to update - * @statp: Reply's status code + * @statp: pointer to Reply's NFS status code, or NULL * * This is called from nfsd_dispatch when the procedure has been * executed and the complete reply is in rqstp->rq_res. diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c index d1e581a60480..7b8f17ee5224 100644 --- a/fs/nfsd/nfsctl.c +++ b/fs/nfsd/nfsctl.c @@ -14,7 +14,6 @@ #include <linux/lockd/lockd.h> #include <linux/sunrpc/addr.h> #include <linux/sunrpc/gss_api.h> -#include <linux/sunrpc/gss_krb5_enctypes.h> #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/module.h> #include <linux/fsnotify.h> @@ -47,7 +46,6 @@ enum { NFSD_MaxBlkSize, NFSD_MaxConnections, NFSD_Filecache, - NFSD_SupportedEnctypes, /* * The below MUST come last. Otherwise we leave a hole in nfsd_files[] * with !CONFIG_NFSD_V4 and simple_fill_super() goes oops @@ -187,16 +185,6 @@ static int export_features_show(struct seq_file *m, void *v) DEFINE_SHOW_ATTRIBUTE(export_features); -#if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE) -static int supported_enctypes_show(struct seq_file *m, void *v) -{ - seq_printf(m, KRB5_SUPPORTED_ENCTYPES); - return 0; -} - -DEFINE_SHOW_ATTRIBUTE(supported_enctypes); -#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ - static const struct file_operations pool_stats_operations = { .open = nfsd_pool_stats_open, .read = seq_read, @@ -1150,6 +1138,9 @@ static struct inode *nfsd_get_inode(struct super_block *sb, umode_t mode) inode->i_op = &simple_dir_inode_operations; inc_nlink(inode); break; + case S_IFLNK: + inode->i_op = &simple_symlink_inode_operations; + break; default: break; } @@ -1195,6 +1186,54 @@ out_err: goto out; } +#if IS_ENABLED(CONFIG_SUNRPC_GSS) +static int __nfsd_symlink(struct inode *dir, struct dentry *dentry, + umode_t mode, const char *content) +{ + struct inode *inode; + + inode = nfsd_get_inode(dir->i_sb, mode); + if (!inode) + return -ENOMEM; + + inode->i_link = (char *)content; + inode->i_size = strlen(content); + + d_add(dentry, inode); + inc_nlink(dir); + fsnotify_create(dir, dentry); + return 0; +} + +/* + * @content is assumed to be a NUL-terminated string that lives + * longer than the symlink itself. + */ +static void nfsd_symlink(struct dentry *parent, const char *name, + const char *content) +{ + struct inode *dir = parent->d_inode; + struct dentry *dentry; + int ret; + + inode_lock(dir); + dentry = d_alloc_name(parent, name); + if (!dentry) + goto out; + ret = __nfsd_symlink(d_inode(parent), dentry, S_IFLNK | 0777, content); + if (ret) + dput(dentry); +out: + inode_unlock(dir); +} +#else +static inline void nfsd_symlink(struct dentry *parent, const char *name, + const char *content) +{ +} + +#endif + static void clear_ncl(struct inode *inode) { struct nfsdfs_client *ncl = inode->i_private; @@ -1355,10 +1394,6 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) [NFSD_MaxBlkSize] = {"max_block_size", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_MaxConnections] = {"max_connections", &transaction_ops, S_IWUSR|S_IRUGO}, [NFSD_Filecache] = {"filecache", &nfsd_file_cache_stats_fops, S_IRUGO}, -#if defined(CONFIG_SUNRPC_GSS) || defined(CONFIG_SUNRPC_GSS_MODULE) - [NFSD_SupportedEnctypes] = {"supported_krb5_enctypes", - &supported_enctypes_fops, S_IRUGO}, -#endif /* CONFIG_SUNRPC_GSS or CONFIG_SUNRPC_GSS_MODULE */ #ifdef CONFIG_NFSD_V4 [NFSD_Leasetime] = {"nfsv4leasetime", &transaction_ops, S_IWUSR|S_IRUSR}, [NFSD_Gracetime] = {"nfsv4gracetime", &transaction_ops, S_IWUSR|S_IRUSR}, @@ -1371,6 +1406,8 @@ static int nfsd_fill_super(struct super_block *sb, struct fs_context *fc) ret = simple_fill_super(sb, 0x6e667364, nfsd_files); if (ret) return ret; + nfsd_symlink(sb->s_root, "supported_krb5_enctypes", + "/proc/net/rpc/gss_krb5_enctypes"); dentry = nfsd_mkdir(sb->s_root, NULL, "clients"); if (IS_ERR(dentry)) return PTR_ERR(dentry); @@ -1457,21 +1494,12 @@ static __net_init int nfsd_init_net(struct net *net) goto out_idmap_error; nn->nfsd_versions = NULL; nn->nfsd4_minorversions = NULL; - retval = nfsd4_init_leases_net(nn); - if (retval) - goto out_drc_error; - retval = nfsd_reply_cache_init(nn); - if (retval) - goto out_cache_error; + nfsd4_init_leases_net(nn); get_random_bytes(&nn->siphash_key, sizeof(nn->siphash_key)); seqlock_init(&nn->writeverf_lock); return 0; -out_cache_error: - nfsd4_leases_net_shutdown(nn); -out_drc_error: - nfsd_idmap_shutdown(net); out_idmap_error: nfsd_export_shutdown(net); out_export_error: @@ -1480,13 +1508,9 @@ out_export_error: static __net_exit void nfsd_exit_net(struct net *net) { - struct nfsd_net *nn = net_generic(net, nfsd_net_id); - - nfsd_reply_cache_shutdown(nn); nfsd_idmap_shutdown(net); nfsd_export_shutdown(net); nfsd_netns_free_versions(net_generic(net, nfsd_net_id)); - nfsd4_leases_net_shutdown(nn); } static struct pernet_operations nfsd_net_ops = { diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h index 93b42ef9ed91..d88498f8b275 100644 --- a/fs/nfsd/nfsd.h +++ b/fs/nfsd/nfsd.h @@ -86,7 +86,7 @@ bool nfssvc_encode_voidres(struct svc_rqst *rqstp, * Function prototypes. */ int nfsd_svc(int nrservs, struct net *net, const struct cred *cred); -int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp); +int nfsd_dispatch(struct svc_rqst *rqstp); int nfsd_nrthreads(struct net *); int nfsd_nrpools(struct net *); @@ -504,8 +504,7 @@ extern void unregister_cld_notifier(void); extern void nfsd4_ssc_init_umount_work(struct nfsd_net *nn); #endif -extern int nfsd4_init_leases_net(struct nfsd_net *nn); -extern void nfsd4_leases_net_shutdown(struct nfsd_net *nn); +extern void nfsd4_init_leases_net(struct nfsd_net *nn); #else /* CONFIG_NFSD_V4 */ static inline int nfsd4_is_junction(struct dentry *dentry) @@ -513,8 +512,7 @@ static inline int nfsd4_is_junction(struct dentry *dentry) return 0; } -static inline int nfsd4_init_leases_net(struct nfsd_net *nn) { return 0; }; -static inline void nfsd4_leases_net_shutdown(struct nfsd_net *nn) {}; +static inline void nfsd4_init_leases_net(struct nfsd_net *nn) { }; #define register_cld_notifier() 0 #define unregister_cld_notifier() do { } while(0) diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index 8c52b6c9d31a..ccd8485fee04 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -40,7 +40,7 @@ static int nfsd_acceptable(void *expv, struct dentry *dentry) /* make sure parents give x permission to user */ int err; parent = dget_parent(tdentry); - err = inode_permission(&init_user_ns, + err = inode_permission(&nop_mnt_idmap, d_inode(parent), MAY_EXEC); if (err < 0) { dput(parent); @@ -628,6 +628,10 @@ void fh_fill_pre_attrs(struct svc_fh *fhp) stat.mtime = inode->i_mtime; stat.ctime = inode->i_ctime; stat.size = inode->i_size; + if (v4 && IS_I_VERSION(inode)) { + stat.change_cookie = inode_query_iversion(inode); + stat.result_mask |= STATX_CHANGE_COOKIE; + } } if (v4) fhp->fh_pre_change = nfsd4_change_attribute(&stat, inode); @@ -659,6 +663,10 @@ void fh_fill_post_attrs(struct svc_fh *fhp) if (err) { fhp->fh_post_saved = false; fhp->fh_post_attr.ctime = inode->i_ctime; + if (v4 && IS_I_VERSION(inode)) { + fhp->fh_post_attr.change_cookie = inode_query_iversion(inode); + fhp->fh_post_attr.result_mask |= STATX_CHANGE_COOKIE; + } } else fhp->fh_post_saved = true; if (v4) @@ -748,3 +756,37 @@ enum fsid_source fsid_source(const struct svc_fh *fhp) return FSIDSOURCE_UUID; return FSIDSOURCE_DEV; } + +/* + * We could use i_version alone as the change attribute. However, i_version + * can go backwards on a regular file after an unclean shutdown. On its own + * that doesn't necessarily cause a problem, but if i_version goes backwards + * and then is incremented again it could reuse a value that was previously + * used before boot, and a client who queried the two values might incorrectly + * assume nothing changed. + * + * By using both ctime and the i_version counter we guarantee that as long as + * time doesn't go backwards we never reuse an old value. If the filesystem + * advertises STATX_ATTR_CHANGE_MONOTONIC, then this mitigation is not + * needed. + * + * We only need to do this for regular files as well. For directories, we + * assume that the new change attr is always logged to stable storage in some + * fashion before the results can be seen. + */ +u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode) +{ + u64 chattr; + + if (stat->result_mask & STATX_CHANGE_COOKIE) { + chattr = stat->change_cookie; + if (S_ISREG(inode->i_mode) && + !(stat->attributes & STATX_ATTR_CHANGE_MONOTONIC)) { + chattr += (u64)stat->ctime.tv_sec << 30; + chattr += stat->ctime.tv_nsec; + } + } else { + chattr = time_to_chattr(&stat->ctime); + } + return chattr; +} diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h index 513e028b0bbe..4e0ecf0ae2cf 100644 --- a/fs/nfsd/nfsfh.h +++ b/fs/nfsd/nfsfh.h @@ -293,34 +293,7 @@ static inline void fh_clear_pre_post_attrs(struct svc_fh *fhp) fhp->fh_pre_saved = false; } -/* - * We could use i_version alone as the change attribute. However, - * i_version can go backwards after a reboot. On its own that doesn't - * necessarily cause a problem, but if i_version goes backwards and then - * is incremented again it could reuse a value that was previously used - * before boot, and a client who queried the two values might - * incorrectly assume nothing changed. - * - * By using both ctime and the i_version counter we guarantee that as - * long as time doesn't go backwards we never reuse an old value. - */ -static inline u64 nfsd4_change_attribute(struct kstat *stat, - struct inode *inode) -{ - if (inode->i_sb->s_export_op->fetch_iversion) - return inode->i_sb->s_export_op->fetch_iversion(inode); - else if (IS_I_VERSION(inode)) { - u64 chattr; - - chattr = stat->ctime.tv_sec; - chattr <<= 30; - chattr += stat->ctime.tv_nsec; - chattr += inode_query_iversion(inode); - return chattr; - } else - return time_to_chattr(&stat->ctime); -} - +u64 nfsd4_change_attribute(struct kstat *stat, struct inode *inode); extern void fh_fill_pre_attrs(struct svc_fh *fhp); extern void fh_fill_post_attrs(struct svc_fh *fhp); extern void fh_fill_both_attrs(struct svc_fh *fhp); diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c index a5570cf75f3f..c37195572fd0 100644 --- a/fs/nfsd/nfsproc.c +++ b/fs/nfsd/nfsproc.c @@ -93,7 +93,7 @@ nfsd_proc_setattr(struct svc_rqst *rqstp) if (delta < 0) delta = -delta; if (delta < MAX_TOUCH_TIME_ERROR && - setattr_prepare(&init_user_ns, fhp->fh_dentry, iap) != 0) { + setattr_prepare(&nop_mnt_idmap, fhp->fh_dentry, iap) != 0) { /* * Turn off ATTR_[AM]TIME_SET but leave ATTR_[AM]TIME. * This will cause notify_change to set these times @@ -211,7 +211,7 @@ nfsd_proc_read(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - __set_bit(RQ_DROPME, &rqstp->rq_flags); + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } @@ -246,7 +246,7 @@ nfsd_proc_write(struct svc_rqst *rqstp) if (resp->status == nfs_ok) resp->status = fh_getattr(&resp->fh, &resp->stat); else if (resp->status == nfserr_jukebox) - __set_bit(RQ_DROPME, &rqstp->rq_flags); + set_bit(RQ_DROPME, &rqstp->rq_flags); return rpc_success; } @@ -838,11 +838,11 @@ static const struct svc_procedure nfsd_procedures2[18] = { }, }; - -static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]; +static DEFINE_PER_CPU_ALIGNED(unsigned long, + nfsd_count2[ARRAY_SIZE(nfsd_procedures2)]); const struct svc_version nfsd_version2 = { .vs_vers = 2, - .vs_nproc = 18, + .vs_nproc = ARRAY_SIZE(nfsd_procedures2), .vs_proc = nfsd_procedures2, .vs_count = nfsd_count2, .vs_dispatch = nfsd_dispatch, diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 56fba1cba3af..9c7b1ef5be40 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -363,7 +363,7 @@ void nfsd_copy_write_verifier(__be32 verf[2], struct nfsd_net *nn) do { read_seqbegin_or_lock(&nn->writeverf_lock, &seq); - memcpy(verf, nn->writeverf, sizeof(*verf)); + memcpy(verf, nn->writeverf, sizeof(nn->writeverf)); } while (need_seqretry(&nn->writeverf_lock, seq)); done_seqretry(&nn->writeverf_lock, seq); } @@ -427,16 +427,23 @@ static int nfsd_startup_net(struct net *net, const struct cred *cred) ret = nfsd_file_cache_start_net(net); if (ret) goto out_lockd; - ret = nfs4_state_start_net(net); + + ret = nfsd_reply_cache_init(nn); if (ret) goto out_filecache; + ret = nfs4_state_start_net(net); + if (ret) + goto out_reply_cache; + #ifdef CONFIG_NFSD_V4_2_INTER_SSC nfsd4_ssc_init_umount_work(nn); #endif nn->nfsd_net_up = true; return 0; +out_reply_cache: + nfsd_reply_cache_shutdown(nn); out_filecache: nfsd_file_cache_shutdown_net(net); out_lockd: @@ -453,8 +460,9 @@ static void nfsd_shutdown_net(struct net *net) { struct nfsd_net *nn = net_generic(net, nfsd_net_id); - nfsd_file_cache_shutdown_net(net); nfs4_state_shutdown_net(net); + nfsd_reply_cache_shutdown(nn); + nfsd_file_cache_shutdown_net(net); if (nn->lockd_up) { lockd_down(net); nn->lockd_up = false; @@ -1022,7 +1030,6 @@ out: /** * nfsd_dispatch - Process an NFS or NFSACL Request * @rqstp: incoming request - * @statp: pointer to location of accept_stat field in RPC Reply buffer * * This RPC dispatcher integrates the NFS server's duplicate reply cache. * @@ -1030,9 +1037,10 @@ out: * %0: Processing complete; do not send a Reply * %1: Processing complete; send Reply in rqstp->rq_res */ -int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) +int nfsd_dispatch(struct svc_rqst *rqstp) { const struct svc_procedure *proc = rqstp->rq_procinfo; + __be32 *statp = rqstp->rq_accept_statp; /* * Give the xdr decoder a chance to change this if it wants @@ -1040,7 +1048,6 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) */ rqstp->rq_cachetype = proc->pc_cachetype; - svcxdr_init_decode(rqstp); if (!proc->pc_decode(rqstp, &rqstp->rq_arg_stream)) goto out_decode_err; @@ -1053,12 +1060,6 @@ int nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp) goto out_dropit; } - /* - * Need to grab the location to store the status, as - * NFSv4 does some encoding while processing - */ - svcxdr_init_encode(rqstp); - *statp = proc->pc_func(rqstp); if (test_bit(RQ_DROPME, &rqstp->rq_flags)) goto out_update_drop; diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h index e94634d30591..d49d3060ed4f 100644 --- a/fs/nfsd/state.h +++ b/fs/nfsd/state.h @@ -705,8 +705,6 @@ extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn); void put_nfs4_file(struct nfs4_file *fi); -extern struct nfsd4_copy * -find_async_copy(struct nfs4_client *clp, stateid_t *staetid); extern void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); extern __be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st, diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h index c852ae8eaf37..4183819ea082 100644 --- a/fs/nfsd/trace.h +++ b/fs/nfsd/trace.h @@ -981,43 +981,6 @@ TRACE_EVENT(nfsd_file_acquire, ) ); -TRACE_EVENT(nfsd_file_create, - TP_PROTO( - const struct svc_rqst *rqstp, - unsigned int may_flags, - const struct nfsd_file *nf - ), - - TP_ARGS(rqstp, may_flags, nf), - - TP_STRUCT__entry( - __field(const void *, nf_inode) - __field(const void *, nf_file) - __field(unsigned long, may_flags) - __field(unsigned long, nf_flags) - __field(unsigned long, nf_may) - __field(unsigned int, nf_ref) - __field(u32, xid) - ), - - TP_fast_assign( - __entry->nf_inode = nf->nf_inode; - __entry->nf_file = nf->nf_file; - __entry->may_flags = may_flags; - __entry->nf_flags = nf->nf_flags; - __entry->nf_may = nf->nf_may; - __entry->nf_ref = refcount_read(&nf->nf_ref); - __entry->xid = be32_to_cpu(rqstp->rq_xid); - ), - - TP_printk("xid=0x%x inode=%p may_flags=%s ref=%u nf_flags=%s nf_may=%s nf_file=%p", - __entry->xid, __entry->nf_inode, - show_nfsd_may_flags(__entry->may_flags), - __entry->nf_ref, show_nf_flags(__entry->nf_flags), - show_nfsd_may_flags(__entry->nf_may), __entry->nf_file - ) -); - TRACE_EVENT(nfsd_file_insert_err, TP_PROTO( const struct svc_rqst *rqstp, @@ -1079,8 +1042,8 @@ TRACE_EVENT(nfsd_file_cons_err, ) ); -TRACE_EVENT(nfsd_file_open, - TP_PROTO(struct nfsd_file *nf, __be32 status), +DECLARE_EVENT_CLASS(nfsd_file_open_class, + TP_PROTO(const struct nfsd_file *nf, __be32 status), TP_ARGS(nf, status), TP_STRUCT__entry( __field(void *, nf_inode) /* cannot be dereferenced */ @@ -1104,6 +1067,17 @@ TRACE_EVENT(nfsd_file_open, __entry->nf_file) ) +#define DEFINE_NFSD_FILE_OPEN_EVENT(name) \ +DEFINE_EVENT(nfsd_file_open_class, name, \ + TP_PROTO( \ + const struct nfsd_file *nf, \ + __be32 status \ + ), \ + TP_ARGS(nf, status)) + +DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_open); +DEFINE_NFSD_FILE_OPEN_EVENT(nfsd_file_opened); + TRACE_EVENT(nfsd_file_is_cached, TP_PROTO( const struct inode *inode, @@ -1228,37 +1202,6 @@ TRACE_EVENT(nfsd_file_close, ) ); -TRACE_EVENT(nfsd_file_fsync, - TP_PROTO( - const struct nfsd_file *nf, - int ret - ), - TP_ARGS(nf, ret), - TP_STRUCT__entry( - __field(void *, nf_inode) - __field(int, nf_ref) - __field(int, ret) - __field(unsigned long, nf_flags) - __field(unsigned char, nf_may) - __field(struct file *, nf_file) - ), - TP_fast_assign( - __entry->nf_inode = nf->nf_inode; - __entry->nf_ref = refcount_read(&nf->nf_ref); - __entry->ret = ret; - __entry->nf_flags = nf->nf_flags; - __entry->nf_may = nf->nf_may; - __entry->nf_file = nf->nf_file; - ), - TP_printk("inode=%p ref=%d flags=%s may=%s nf_file=%p ret=%d", - __entry->nf_inode, - __entry->nf_ref, - show_nf_flags(__entry->nf_flags), - show_nfsd_may_flags(__entry->nf_may), - __entry->nf_file, __entry->ret - ) -); - #include "cache.h" TRACE_DEFINE_ENUM(RC_DROPIT); diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 4c3a0d84043c..e7462b5e5f1e 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -126,9 +126,13 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp, struct dentry *dentry = *dpp; struct path path = {.mnt = mntget(exp->ex_path.mnt), .dentry = dget(dentry)}; + unsigned int follow_flags = 0; int err = 0; - err = follow_down(&path); + if (exp->ex_flags & NFSEXP_CROSSMOUNT) + follow_flags = LOOKUP_AUTOMOUNT; + + err = follow_down(&path, follow_flags); if (err < 0) goto out; if (path.mnt == exp->ex_path.mnt && path.dentry == dentry && @@ -223,7 +227,7 @@ int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp) return 1; if (nfsd4_is_junction(dentry)) return 1; - if (d_mountpoint(dentry)) + if (d_managed(dentry)) /* * Might only be a mountpoint in a different namespace, * but we need to check. @@ -426,7 +430,7 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) if (iap->ia_size < 0) return -EFBIG; - host_err = notify_change(&init_user_ns, dentry, &size_attr, NULL); + host_err = notify_change(&nop_mnt_idmap, dentry, &size_attr, NULL); if (host_err) return host_err; iap->ia_valid &= ~ATTR_SIZE; @@ -444,7 +448,7 @@ static int __nfsd_setattr(struct dentry *dentry, struct iattr *iap) return 0; iap->ia_valid |= ATTR_CTIME; - return notify_change(&init_user_ns, dentry, iap, NULL); + return notify_change(&nop_mnt_idmap, dentry, iap, NULL); } /** @@ -542,12 +546,12 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, attr->na_labelerr = security_inode_setsecctx(dentry, attr->na_seclabel->data, attr->na_seclabel->len); if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && attr->na_pacl) - attr->na_aclerr = set_posix_acl(&init_user_ns, + attr->na_aclerr = set_posix_acl(&nop_mnt_idmap, dentry, ACL_TYPE_ACCESS, attr->na_pacl); if (IS_ENABLED(CONFIG_FS_POSIX_ACL) && !attr->na_aclerr && attr->na_dpacl && S_ISDIR(inode->i_mode)) - attr->na_aclerr = set_posix_acl(&init_user_ns, + attr->na_aclerr = set_posix_acl(&nop_mnt_idmap, dentry, ACL_TYPE_DEFAULT, attr->na_dpacl); inode_unlock(inode); @@ -583,7 +587,7 @@ int nfsd4_is_junction(struct dentry *dentry) return 0; if (!(inode->i_mode & S_ISVTX)) return 0; - if (vfs_getxattr(&init_user_ns, dentry, NFSD_JUNCTION_XATTR_NAME, + if (vfs_getxattr(&nop_mnt_idmap, dentry, NFSD_JUNCTION_XATTR_NAME, NULL, 0) <= 0) return 0; return 1; @@ -1363,12 +1367,13 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, err = 0; switch (type) { case S_IFREG: - host_err = vfs_create(&init_user_ns, dirp, dchild, iap->ia_mode, true); + host_err = vfs_create(&nop_mnt_idmap, dirp, dchild, + iap->ia_mode, true); if (!host_err) nfsd_check_ignore_resizing(iap); break; case S_IFDIR: - host_err = vfs_mkdir(&init_user_ns, dirp, dchild, iap->ia_mode); + host_err = vfs_mkdir(&nop_mnt_idmap, dirp, dchild, iap->ia_mode); if (!host_err && unlikely(d_unhashed(dchild))) { struct dentry *d; d = lookup_one_len(dchild->d_name.name, @@ -1396,7 +1401,7 @@ nfsd_create_locked(struct svc_rqst *rqstp, struct svc_fh *fhp, case S_IFBLK: case S_IFIFO: case S_IFSOCK: - host_err = vfs_mknod(&init_user_ns, dirp, dchild, + host_err = vfs_mknod(&nop_mnt_idmap, dirp, dchild, iap->ia_mode, rdev); break; default: @@ -1557,7 +1562,7 @@ nfsd_symlink(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out_drop_write; } fh_fill_pre_attrs(fhp); - host_err = vfs_symlink(&init_user_ns, d_inode(dentry), dnew, path); + host_err = vfs_symlink(&nop_mnt_idmap, d_inode(dentry), dnew, path); err = nfserrno(host_err); cerr = fh_compose(resfhp, fhp->fh_export, dnew, fhp); if (!err) @@ -1625,7 +1630,7 @@ nfsd_link(struct svc_rqst *rqstp, struct svc_fh *ffhp, if (d_really_is_negative(dold)) goto out_dput; fh_fill_pre_attrs(ffhp); - host_err = vfs_link(dold, &init_user_ns, dirp, dnew, NULL); + host_err = vfs_link(dold, &nop_mnt_idmap, dirp, dnew, NULL); fh_fill_post_attrs(ffhp); inode_unlock(dirp); if (!host_err) { @@ -1745,10 +1750,10 @@ retry: goto out_dput_old; } else { struct renamedata rd = { - .old_mnt_userns = &init_user_ns, + .old_mnt_idmap = &nop_mnt_idmap, .old_dir = fdir, .old_dentry = odentry, - .new_mnt_userns = &init_user_ns, + .new_mnt_idmap = &nop_mnt_idmap, .new_dir = tdir, .new_dentry = ndentry, }; @@ -1850,14 +1855,14 @@ nfsd_unlink(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, nfsd_close_cached_files(rdentry); for (retries = 1;;) { - host_err = vfs_unlink(&init_user_ns, dirp, rdentry, NULL); + host_err = vfs_unlink(&nop_mnt_idmap, dirp, rdentry, NULL); if (host_err != -EAGAIN || !retries--) break; if (!nfsd_wait_for_delegreturn(rqstp, rinode)) break; } } else { - host_err = vfs_rmdir(&init_user_ns, dirp, rdentry); + host_err = vfs_rmdir(&nop_mnt_idmap, dirp, rdentry); } fh_fill_post_attrs(fhp); @@ -2129,7 +2134,7 @@ nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, inode_lock_shared(inode); - len = vfs_getxattr(&init_user_ns, dentry, name, NULL, 0); + len = vfs_getxattr(&nop_mnt_idmap, dentry, name, NULL, 0); /* * Zero-length attribute, just return. @@ -2156,7 +2161,7 @@ nfsd_getxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, goto out; } - len = vfs_getxattr(&init_user_ns, dentry, name, buf, len); + len = vfs_getxattr(&nop_mnt_idmap, dentry, name, buf, len); if (len <= 0) { kvfree(buf); buf = NULL; @@ -2267,7 +2272,7 @@ nfsd_removexattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name) inode_lock(fhp->fh_dentry->d_inode); fh_fill_pre_attrs(fhp); - ret = __vfs_removexattr_locked(&init_user_ns, fhp->fh_dentry, + ret = __vfs_removexattr_locked(&nop_mnt_idmap, fhp->fh_dentry, name, NULL); fh_fill_post_attrs(fhp); @@ -2294,7 +2299,7 @@ nfsd_setxattr(struct svc_rqst *rqstp, struct svc_fh *fhp, char *name, inode_lock(fhp->fh_dentry->d_inode); fh_fill_pre_attrs(fhp); - ret = __vfs_setxattr_locked(&init_user_ns, fhp->fh_dentry, name, buf, + ret = __vfs_setxattr_locked(&nop_mnt_idmap, fhp->fh_dentry, name, buf, len, flags, NULL); fh_fill_post_attrs(fhp); inode_unlock(fhp->fh_dentry->d_inode); @@ -2378,14 +2383,14 @@ nfsd_permission(struct svc_rqst *rqstp, struct svc_export *exp, return 0; /* This assumes NFSD_MAY_{READ,WRITE,EXEC} == MAY_{READ,WRITE,EXEC} */ - err = inode_permission(&init_user_ns, inode, + err = inode_permission(&nop_mnt_idmap, inode, acc & (MAY_READ | MAY_WRITE | MAY_EXEC)); /* Allow read access to binaries even when mode 111 */ if (err == -EACCES && S_ISREG(inode->i_mode) && (acc == (NFSD_MAY_READ | NFSD_MAY_OWNER_OVERRIDE) || acc == (NFSD_MAY_READ | NFSD_MAY_READ_IF_EXEC))) - err = inode_permission(&init_user_ns, inode, MAY_EXEC); + err = inode_permission(&nop_mnt_idmap, inode, MAY_EXEC); return err? nfserrno(err) : 0; } diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h index dbdfef7ae85b..43fb57a301d3 100644 --- a/fs/nfsd/vfs.h +++ b/fs/nfsd/vfs.h @@ -170,9 +170,14 @@ static inline void fh_drop_write(struct svc_fh *fh) static inline __be32 fh_getattr(const struct svc_fh *fh, struct kstat *stat) { + u32 request_mask = STATX_BASIC_STATS; struct path p = {.mnt = fh->fh_export->ex_path.mnt, .dentry = fh->fh_dentry}; - return nfserrno(vfs_getattr(&p, stat, STATX_BASIC_STATS, + + if (fh->fh_maxsize == NFS4_FHSIZE) + request_mask |= (STATX_BTIME | STATX_CHANGE_COOKIE); + + return nfserrno(vfs_getattr(&p, stat, request_mask, AT_STATX_SYNC_AS_STAT)); } diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h index 4fd2cf6d1d2d..510978e602da 100644 --- a/fs/nfsd/xdr4.h +++ b/fs/nfsd/xdr4.h @@ -571,7 +571,7 @@ struct nfsd4_copy { struct task_struct *copy_task; refcount_t refcount; - struct vfsmount *ss_mnt; + struct nfsd4_ssc_umount_item *ss_nsui; struct nfs_fh c_fh; nfs4_stateid stateid; }; |