diff options
Diffstat (limited to 'fs/nfsd/nfs4state.c')
| -rw-r--r-- | fs/nfsd/nfs4state.c | 5638 |
1 files changed, 3837 insertions, 1801 deletions
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c index fb3c9844c82a..808c24fb5c9a 100644 --- a/fs/nfsd/nfs4state.c +++ b/fs/nfsd/nfs4state.c @@ -42,6 +42,11 @@ #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/addr.h> #include <linux/jhash.h> +#include <linux/string_helpers.h> +#include <linux/fsnotify.h> +#include <linux/rhashtable.h> +#include <linux/nfs_ssc.h> + #include "xdr4.h" #include "xdr4cb.h" #include "vfs.h" @@ -49,10 +54,12 @@ #include "netns.h" #include "pnfs.h" +#include "filecache.h" +#include "trace.h" #define NFSDDBG_FACILITY NFSDDBG_PROC -#define all_ones {{~0,~0},~0} +#define all_ones {{ ~0, ~0}, ~0} static const stateid_t one_stateid = { .si_generation = ~0, .si_opaque = all_ones, @@ -77,6 +84,10 @@ static u64 current_sessionid = 1; /* forward declarations */ static bool check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner); static void nfs4_free_ol_stateid(struct nfs4_stid *stid); +void nfsd4_end_grace(struct nfsd_net *nn); +static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps); +static void nfsd4_file_hash_remove(struct nfs4_file *fi); +static void deleg_reaper(struct nfsd_net *nn); /* Locking: */ @@ -98,6 +109,13 @@ enum nfsd4_st_mutex_lock_subclass { */ static DECLARE_WAIT_QUEUE_HEAD(close_wq); +/* + * A waitqueue where a writer to clients/#/ctl destroying a client can + * wait for cl_rpc_users to drop to 0 and then for the client to be + * unhashed. + */ +static DECLARE_WAIT_QUEUE_HEAD(expiry_wq); + static struct kmem_cache *client_slab; static struct kmem_cache *openowner_slab; static struct kmem_cache *lockowner_slab; @@ -110,17 +128,35 @@ static void free_session(struct nfsd4_session *); static const struct nfsd4_callback_ops nfsd4_cb_recall_ops; static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops; +static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops; + +static struct workqueue_struct *laundry_wq; + +int nfsd4_create_laundry_wq(void) +{ + int rc = 0; + + laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4"); + if (laundry_wq == NULL) + rc = -ENOMEM; + return rc; +} + +void nfsd4_destroy_laundry_wq(void) +{ + destroy_workqueue(laundry_wq); +} static bool is_session_dead(struct nfsd4_session *ses) { - return ses->se_flags & NFS4_SESSION_DEAD; + return ses->se_dead; } static __be32 mark_session_dead_locked(struct nfsd4_session *ses, int ref_held_by_me) { if (atomic_read(&ses->se_ref) > ref_held_by_me) return nfserr_jukebox; - ses->se_flags |= NFS4_SESSION_DEAD; + ses->se_dead = true; return nfs_ok; } @@ -129,6 +165,13 @@ static bool is_client_expired(struct nfs4_client *clp) return clp->cl_time == 0; } +static void nfsd4_dec_courtesy_client_count(struct nfsd_net *nn, + struct nfs4_client *clp) +{ + if (clp->cl_state != NFSD4_ACTIVE) + atomic_add_unless(&nn->nfsd_courtesy_clients, -1, 0); +} + static __be32 get_client_locked(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); @@ -137,7 +180,9 @@ static __be32 get_client_locked(struct nfs4_client *clp) if (is_client_expired(clp)) return nfserr_expired; - atomic_inc(&clp->cl_refcount); + atomic_inc(&clp->cl_rpc_users); + nfsd4_dec_courtesy_client_count(nn, clp); + clp->cl_state = NFSD4_ACTIVE; return nfs_ok; } @@ -156,11 +201,10 @@ renew_client_locked(struct nfs4_client *clp) return; } - dprintk("renewing client (clientid %08x/%08x)\n", - clp->cl_clientid.cl_boot, - clp->cl_clientid.cl_id); list_move_tail(&clp->cl_lru, &nn->client_lru); - clp->cl_time = get_seconds(); + clp->cl_time = ktime_get_boottime_seconds(); + nfsd4_dec_courtesy_client_count(nn, clp); + clp->cl_state = NFSD4_ACTIVE; } static void put_client_renew_locked(struct nfs4_client *clp) @@ -169,20 +213,24 @@ static void put_client_renew_locked(struct nfs4_client *clp) lockdep_assert_held(&nn->client_lock); - if (!atomic_dec_and_test(&clp->cl_refcount)) + if (!atomic_dec_and_test(&clp->cl_rpc_users)) return; if (!is_client_expired(clp)) renew_client_locked(clp); + else + wake_up_all(&expiry_wq); } static void put_client_renew(struct nfs4_client *clp) { struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); - if (!atomic_dec_and_lock(&clp->cl_refcount, &nn->client_lock)) + if (!atomic_dec_and_lock(&clp->cl_rpc_users, &nn->client_lock)) return; if (!is_client_expired(clp)) renew_client_locked(clp); + else + wake_up_all(&expiry_wq); spin_unlock(&nn->client_lock); } @@ -231,6 +279,7 @@ find_blocked_lock(struct nfs4_lockowner *lo, struct knfsd_fh *fh, list_for_each_entry(cur, &lo->lo_blocked, nbl_list) { if (fh_match(fh, &cur->nbl_fh)) { list_del_init(&cur->nbl_list); + WARN_ON(list_empty(&cur->nbl_lru)); list_del_init(&cur->nbl_lru); found = cur; break; @@ -250,10 +299,13 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, nbl = find_blocked_lock(lo, fh, nn); if (!nbl) { - nbl= kmalloc(sizeof(*nbl), GFP_KERNEL); + nbl = kmalloc(sizeof(*nbl), GFP_KERNEL); if (nbl) { + INIT_LIST_HEAD(&nbl->nbl_list); + INIT_LIST_HEAD(&nbl->nbl_lru); fh_copy_shallow(&nbl->nbl_fh, fh); locks_init_lock(&nbl->nbl_lock); + kref_init(&nbl->nbl_kref); nfsd4_init_cb(&nbl->nbl_cb, lo->lo_owner.so_client, &nfsd4_cb_notify_lock_ops, NFSPROC4_CLNT_CB_NOTIFY_LOCK); @@ -263,13 +315,23 @@ find_or_allocate_block(struct nfs4_lockowner *lo, struct knfsd_fh *fh, } static void -free_blocked_lock(struct nfsd4_blocked_lock *nbl) +free_nbl(struct kref *kref) { + struct nfsd4_blocked_lock *nbl; + + nbl = container_of(kref, struct nfsd4_blocked_lock, nbl_kref); locks_release_private(&nbl->nbl_lock); kfree(nbl); } static void +free_blocked_lock(struct nfsd4_blocked_lock *nbl) +{ + locks_delete_block(&nbl->nbl_lock); + kref_put(&nbl->nbl_kref, free_nbl); +} + +static void remove_blocked_locks(struct nfs4_lockowner *lo) { struct nfs4_client *clp = lo->lo_owner.so_client; @@ -284,6 +346,7 @@ remove_blocked_locks(struct nfs4_lockowner *lo) struct nfsd4_blocked_lock, nbl_list); list_del_init(&nbl->nbl_list); + WARN_ON(list_empty(&nbl->nbl_lru)); list_move(&nbl->nbl_lru, &reaplist); } spin_unlock(&nn->blocked_locks_lock); @@ -293,14 +356,23 @@ remove_blocked_locks(struct nfs4_lockowner *lo) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } } +static void +nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb) +{ + struct nfsd4_blocked_lock *nbl = container_of(cb, + struct nfsd4_blocked_lock, nbl_cb); + locks_delete_block(&nbl->nbl_lock); +} + static int nfsd4_cb_notify_lock_done(struct nfsd4_callback *cb, struct rpc_task *task) { + trace_nfsd_cb_notify_lock_done(&zero_stateid, task); + /* * Since this is just an optimization, we don't try very hard if it * turns out not to succeed. We'll requeue it on NFS4ERR_DELAY, and @@ -325,10 +397,136 @@ nfsd4_cb_notify_lock_release(struct nfsd4_callback *cb) } static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops = { + .prepare = nfsd4_cb_notify_lock_prepare, .done = nfsd4_cb_notify_lock_done, .release = nfsd4_cb_notify_lock_release, + .opcode = OP_CB_NOTIFY_LOCK, }; +/* + * We store the NONE, READ, WRITE, and BOTH bits separately in the + * st_{access,deny}_bmap field of the stateid, in order to track not + * only what share bits are currently in force, but also what + * combinations of share bits previous opens have used. This allows us + * to enforce the recommendation in + * https://datatracker.ietf.org/doc/html/rfc7530#section-16.19.4 that + * the server return an error if the client attempt to downgrade to a + * combination of share bits not explicable by closing some of its + * previous opens. + * + * This enforcement is arguably incomplete, since we don't keep + * track of access/deny bit combinations; so, e.g., we allow: + * + * OPEN allow read, deny write + * OPEN allow both, deny none + * DOWNGRADE allow read, deny none + * + * which we should reject. + * + * But you could also argue that our current code is already overkill, + * since it only exists to return NFS4ERR_INVAL on incorrect client + * behavior. + */ +static unsigned int +bmap_to_share_mode(unsigned long bmap) +{ + int i; + unsigned int access = 0; + + for (i = 1; i < 4; i++) { + if (test_bit(i, &bmap)) + access |= i; + } + return access; +} + +/* set share access for a given stateid */ +static inline void +set_access(u32 access, struct nfs4_ol_stateid *stp) +{ + unsigned char mask = 1 << access; + + WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH); + stp->st_access_bmap |= mask; +} + +/* clear share access for a given stateid */ +static inline void +clear_access(u32 access, struct nfs4_ol_stateid *stp) +{ + unsigned char mask = 1 << access; + + WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH); + stp->st_access_bmap &= ~mask; +} + +/* test whether a given stateid has access */ +static inline bool +test_access(u32 access, struct nfs4_ol_stateid *stp) +{ + unsigned char mask = 1 << access; + + return (bool)(stp->st_access_bmap & mask); +} + +/* set share deny for a given stateid */ +static inline void +set_deny(u32 deny, struct nfs4_ol_stateid *stp) +{ + unsigned char mask = 1 << deny; + + WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH); + stp->st_deny_bmap |= mask; +} + +/* clear share deny for a given stateid */ +static inline void +clear_deny(u32 deny, struct nfs4_ol_stateid *stp) +{ + unsigned char mask = 1 << deny; + + WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH); + stp->st_deny_bmap &= ~mask; +} + +/* test whether a given stateid is denying specific access */ +static inline bool +test_deny(u32 deny, struct nfs4_ol_stateid *stp) +{ + unsigned char mask = 1 << deny; + + return (bool)(stp->st_deny_bmap & mask); +} + +static int nfs4_access_to_omode(u32 access) +{ + switch (access & NFS4_SHARE_ACCESS_BOTH) { + case NFS4_SHARE_ACCESS_READ: + return O_RDONLY; + case NFS4_SHARE_ACCESS_WRITE: + return O_WRONLY; + case NFS4_SHARE_ACCESS_BOTH: + return O_RDWR; + } + WARN_ON_ONCE(1); + return O_RDONLY; +} + +static inline int +access_permit_read(struct nfs4_ol_stateid *stp) +{ + return test_access(NFS4_SHARE_ACCESS_READ, stp) || + test_access(NFS4_SHARE_ACCESS_BOTH, stp) || + test_access(NFS4_SHARE_ACCESS_WRITE, stp); +} + +static inline int +access_permit_write(struct nfs4_ol_stateid *stp) +{ + return test_access(NFS4_SHARE_ACCESS_WRITE, stp) || + test_access(NFS4_SHARE_ACCESS_BOTH, stp); +} + static inline struct nfs4_stateowner * nfs4_get_stateowner(struct nfs4_stateowner *sop) { @@ -344,7 +542,7 @@ same_owner_str(struct nfs4_stateowner *sop, struct xdr_netobj *owner) } static struct nfs4_openowner * -find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open, +find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, struct nfs4_client *clp) { struct nfs4_stateowner *so; @@ -361,18 +559,6 @@ find_openstateowner_str_locked(unsigned int hashval, struct nfsd4_open *open, return NULL; } -static struct nfs4_openowner * -find_openstateowner_str(unsigned int hashval, struct nfsd4_open *open, - struct nfs4_client *clp) -{ - struct nfs4_openowner *oo; - - spin_lock(&clp->cl_lock); - oo = find_openstateowner_str_locked(hashval, open, clp); - spin_unlock(&clp->cl_lock); - return oo; -} - static inline u32 opaque_hashval(const void *ptr, int nbytes) { @@ -386,52 +572,34 @@ opaque_hashval(const void *ptr, int nbytes) return x; } -static void nfsd4_free_file_rcu(struct rcu_head *rcu) -{ - struct nfs4_file *fp = container_of(rcu, struct nfs4_file, fi_rcu); - - kmem_cache_free(file_slab, fp); -} - void put_nfs4_file(struct nfs4_file *fi) { - might_lock(&state_lock); - - if (refcount_dec_and_lock(&fi->fi_ref, &state_lock)) { - hlist_del_rcu(&fi->fi_hash); - spin_unlock(&state_lock); + if (refcount_dec_and_test(&fi->fi_ref)) { + nfsd4_file_hash_remove(fi); WARN_ON_ONCE(!list_empty(&fi->fi_clnt_odstate)); WARN_ON_ONCE(!list_empty(&fi->fi_delegations)); - call_rcu(&fi->fi_rcu, nfsd4_free_file_rcu); + kfree_rcu(fi, fi_rcu); } } -static struct file * -__nfs4_get_fd(struct nfs4_file *f, int oflag) -{ - if (f->fi_fds[oflag]) - return get_file(f->fi_fds[oflag]); - return NULL; -} - -static struct file * +static struct nfsd_file * find_writeable_file_locked(struct nfs4_file *f) { - struct file *ret; + 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; } -static struct file * +static struct nfsd_file * find_writeable_file(struct nfs4_file *f) { - struct file *ret; + struct nfsd_file *ret; spin_lock(&f->fi_lock); ret = find_writeable_file_locked(f); @@ -440,22 +608,23 @@ find_writeable_file(struct nfs4_file *f) return ret; } -static struct file *find_readable_file_locked(struct nfs4_file *f) +static struct nfsd_file * +find_readable_file_locked(struct nfs4_file *f) { - struct file *ret; + struct nfsd_file *ret; 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; } -static struct file * +static struct nfsd_file * find_readable_file(struct nfs4_file *f) { - struct file *ret; + struct nfsd_file *ret; spin_lock(&f->fi_lock); ret = find_readable_file_locked(f); @@ -464,22 +633,37 @@ find_readable_file(struct nfs4_file *f) return ret; } -struct file * +struct nfsd_file * find_any_file(struct nfs4_file *f) { - struct file *ret; + struct nfsd_file *ret; + 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; } +static struct nfsd_file *find_any_file_locked(struct nfs4_file *f) +{ + lockdep_assert_held(&f->fi_lock); + + if (f->fi_fds[O_RDWR]) + return f->fi_fds[O_RDWR]; + if (f->fi_fds[O_WRONLY]) + return f->fi_fds[O_WRONLY]; + if (f->fi_fds[O_RDONLY]) + return f->fi_fds[O_RDONLY]; + return NULL; +} + static atomic_long_t num_delegations; unsigned long max_delegations; @@ -500,21 +684,71 @@ static unsigned int ownerstr_hashval(struct xdr_netobj *ownername) return ret & OWNER_HASH_MASK; } -/* hash table for nfs4_file */ -#define FILE_HASH_BITS 8 -#define FILE_HASH_SIZE (1 << FILE_HASH_BITS) +static struct rhltable nfs4_file_rhltable ____cacheline_aligned_in_smp; -static unsigned int nfsd_fh_hashval(struct knfsd_fh *fh) -{ - return jhash2(fh->fh_base.fh_pad, XDR_QUADLEN(fh->fh_size), 0); -} +static const struct rhashtable_params nfs4_file_rhash_params = { + .key_len = sizeof_field(struct nfs4_file, fi_inode), + .key_offset = offsetof(struct nfs4_file, fi_inode), + .head_offset = offsetof(struct nfs4_file, fi_rlist), -static unsigned int file_hashval(struct knfsd_fh *fh) + /* + * Start with a single page hash table to reduce resizing churn + * on light workloads. + */ + .min_size = 256, + .automatic_shrinking = true, +}; + +/* + * Check if courtesy clients have conflicting access and resolve it if possible + * + * access: is op_share_access if share_access is true. + * Check if access mode, op_share_access, would conflict with + * the current deny mode of the file 'fp'. + * access: is op_share_deny if share_access is false. + * Check if the deny mode, op_share_deny, would conflict with + * current access of the file 'fp'. + * stp: skip checking this entry. + * new_stp: normal open, not open upgrade. + * + * Function returns: + * false - access/deny mode conflict with normal client. + * true - no conflict or conflict with courtesy client(s) is resolved. + */ +static bool +nfs4_resolve_deny_conflicts_locked(struct nfs4_file *fp, bool new_stp, + struct nfs4_ol_stateid *stp, u32 access, bool share_access) { - return nfsd_fh_hashval(fh) & (FILE_HASH_SIZE - 1); -} + struct nfs4_ol_stateid *st; + bool resolvable = true; + unsigned char bmap; + struct nfsd_net *nn; + struct nfs4_client *clp; -static struct hlist_head file_hashtbl[FILE_HASH_SIZE]; + lockdep_assert_held(&fp->fi_lock); + list_for_each_entry(st, &fp->fi_stateids, st_perfile) { + /* ignore lock stateid */ + if (st->st_openstp) + continue; + if (st == stp && new_stp) + continue; + /* check file access against deny mode or vice versa */ + bmap = share_access ? st->st_deny_bmap : st->st_access_bmap; + if (!(access & bmap_to_share_mode(bmap))) + continue; + clp = st->st_stid.sc_client; + if (try_to_expire_client(clp)) + continue; + resolvable = false; + break; + } + if (resolvable) { + clp = stp->st_stid.sc_client; + nn = net_generic(clp->net, nfsd_net_id); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + } + return resolvable; +} static void __nfs4_file_get_access(struct nfs4_file *fp, u32 access) @@ -568,17 +802,17 @@ static void __nfs4_file_put_access(struct nfs4_file *fp, int oflag) might_lock(&fp->fi_lock); if (atomic_dec_and_lock(&fp->fi_access[oflag], &fp->fi_lock)) { - struct file *f1 = NULL; - struct file *f2 = NULL; + struct nfsd_file *f1 = NULL; + struct nfsd_file *f2 = NULL; swap(f1, fp->fi_fds[oflag]); if (atomic_read(&fp->fi_access[1 - oflag]) == 0) swap(f2, fp->fi_fds[O_RDWR]); spin_unlock(&fp->fi_lock); if (f1) - fput(f1); + nfsd_file_put(f1); if (f2) - fput(f2); + nfsd_file_put(f2); } } @@ -684,7 +918,8 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *sla idr_preload(GFP_KERNEL); spin_lock(&cl->cl_lock); - new_id = idr_alloc_cyclic(&cl->cl_stateids, stid, 0, 0, GFP_NOWAIT); + /* Reserving 0 for start of file in nfsdfs "states" file: */ + new_id = idr_alloc_cyclic(&cl->cl_stateids, stid, 1, 0, GFP_NOWAIT); spin_unlock(&cl->cl_lock); idr_preload_end(); if (new_id < 0) @@ -697,16 +932,8 @@ struct nfs4_stid *nfs4_alloc_stid(struct nfs4_client *cl, struct kmem_cache *sla /* Will be incremented before return to client: */ refcount_set(&stid->sc_count, 1); spin_lock_init(&stid->sc_lock); + INIT_LIST_HEAD(&stid->sc_cp_list); - /* - * It shouldn't be a problem to reuse an opaque stateid value. - * I don't think it is for 4.1. But with 4.0 I worry that, for - * example, a stray write retransmission could be accepted by - * the server when it should have been rejected. Therefore, - * adopt a trick from the sctp code to attempt to maximize the - * amount of time until an id is reused, by ensuring they always - * "increase" (mod INT_MAX): - */ return stid; out_free: kmem_cache_free(slab, stid); @@ -716,30 +943,78 @@ out_free: /* * Create a unique stateid_t to represent each COPY. */ -int nfs4_init_cp_state(struct nfsd_net *nn, struct nfsd4_copy *copy) +static int nfs4_init_cp_state(struct nfsd_net *nn, copy_stateid_t *stid, + unsigned char cs_type) { int new_id; + 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; + idr_preload(GFP_KERNEL); spin_lock(&nn->s2s_cp_lock); - new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, copy, 0, 0, GFP_NOWAIT); + new_id = idr_alloc_cyclic(&nn->s2s_cp_stateids, stid, 0, 0, GFP_NOWAIT); + stid->cs_stid.si_opaque.so_id = new_id; + stid->cs_stid.si_generation = 1; spin_unlock(&nn->s2s_cp_lock); idr_preload_end(); if (new_id < 0) return 0; - copy->cp_stateid.si_opaque.so_id = new_id; - copy->cp_stateid.si_opaque.so_clid.cl_boot = nn->boot_time; - copy->cp_stateid.si_opaque.so_clid.cl_id = nn->s2s_cp_cl_id; + stid->cs_type = cs_type; return 1; } -void nfs4_free_cp_state(struct nfsd4_copy *copy) +int nfs4_init_copy_state(struct nfsd_net *nn, struct nfsd4_copy *copy) +{ + return nfs4_init_cp_state(nn, ©->cp_stateid, NFS4_COPY_STID); +} + +struct nfs4_cpntf_state *nfs4_alloc_init_cpntf_state(struct nfsd_net *nn, + struct nfs4_stid *p_stid) +{ + struct nfs4_cpntf_state *cps; + + cps = kzalloc(sizeof(struct nfs4_cpntf_state), GFP_KERNEL); + if (!cps) + return NULL; + cps->cpntf_time = ktime_get_boottime_seconds(); + refcount_set(&cps->cp_stateid.cs_count, 1); + if (!nfs4_init_cp_state(nn, &cps->cp_stateid, NFS4_COPYNOTIFY_STID)) + goto out_free; + spin_lock(&nn->s2s_cp_lock); + list_add(&cps->cp_list, &p_stid->sc_cp_list); + spin_unlock(&nn->s2s_cp_lock); + return cps; +out_free: + kfree(cps); + return NULL; +} + +void nfs4_free_copy_state(struct nfsd4_copy *copy) { struct nfsd_net *nn; + 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, copy->cp_stateid.si_opaque.so_id); + idr_remove(&nn->s2s_cp_stateids, + copy->cp_stateid.cs_stid.si_opaque.so_id); + spin_unlock(&nn->s2s_cp_lock); +} + +static void nfs4_free_cpntf_statelist(struct net *net, struct nfs4_stid *stid) +{ + struct nfs4_cpntf_state *cps; + struct nfsd_net *nn; + + nn = net_generic(net, nfsd_net_id); + spin_lock(&nn->s2s_cp_lock); + while (!list_empty(&stid->sc_cp_list)) { + cps = list_first_entry(&stid->sc_cp_list, + struct nfs4_cpntf_state, cp_list); + _free_cpntf_state_locked(nn, cps); + } spin_unlock(&nn->s2s_cp_lock); } @@ -754,8 +1029,20 @@ static struct nfs4_ol_stateid * nfs4_alloc_open_stateid(struct nfs4_client *clp) return openlockstateid(stid); } +/* + * As the sc_free callback of deleg, this may be called by nfs4_put_stid + * in nfsd_break_one_deleg. + * Considering nfsd_break_one_deleg is called with the flc->flc_lock held, + * this function mustn't ever sleep. + */ static void nfs4_free_deleg(struct nfs4_stid *stid) { + struct nfs4_delegation *dp = delegstateid(stid); + + WARN_ON_ONCE(!list_empty(&stid->sc_cp_list)); + WARN_ON_ONCE(!list_empty(&dp->dl_perfile)); + WARN_ON_ONCE(!list_empty(&dp->dl_perclnt)); + WARN_ON_ONCE(!list_empty(&dp->dl_recall_lru)); kmem_cache_free(deleg_slab, stid); atomic_long_dec(&num_delegations); } @@ -769,7 +1056,8 @@ static void nfs4_free_deleg(struct nfs4_stid *stid) * When a delegation is recalled, the filehandle is stored in the "new" * filter. * Every 30 seconds we swap the filters and clear the "new" one, - * unless both are empty of course. + * unless both are empty of course. This results in delegations for a + * given filehandle being blocked for between 30 and 60 seconds. * * Each filter is 256 bits. We hash the filehandle to 32bit and use the * low 3 bytes as hash-table indices. @@ -781,7 +1069,7 @@ static void nfs4_free_deleg(struct nfs4_stid *stid) static DEFINE_SPINLOCK(blocked_delegations_lock); static struct bloom_pair { int entries, old_entries; - time_t swap_time; + time64_t swap_time; int new; /* index into 'set' */ DECLARE_BITMAP(set[2], 256); } blocked_delegations; @@ -793,19 +1081,19 @@ static int delegation_blocked(struct knfsd_fh *fh) if (bd->entries == 0) return 0; - if (seconds_since_boot() - bd->swap_time > 30) { + if (ktime_get_seconds() - bd->swap_time > 30) { spin_lock(&blocked_delegations_lock); - if (seconds_since_boot() - bd->swap_time > 30) { + if (ktime_get_seconds() - bd->swap_time > 30) { bd->entries -= bd->old_entries; bd->old_entries = bd->entries; + bd->new = 1-bd->new; memset(bd->set[bd->new], 0, sizeof(bd->set[0])); - bd->new = 1-bd->new; - bd->swap_time = seconds_since_boot(); + bd->swap_time = ktime_get_seconds(); } spin_unlock(&blocked_delegations_lock); } - hash = jhash(&fh->fh_base, fh->fh_size, 0); + hash = jhash(&fh->fh_raw, fh->fh_size, 0); if (test_bit(hash&255, bd->set[0]) && test_bit((hash>>8)&255, bd->set[0]) && test_bit((hash>>16)&255, bd->set[0])) @@ -824,35 +1112,36 @@ static void block_delegations(struct knfsd_fh *fh) u32 hash; struct bloom_pair *bd = &blocked_delegations; - hash = jhash(&fh->fh_base, fh->fh_size, 0); + hash = jhash(&fh->fh_raw, fh->fh_size, 0); spin_lock(&blocked_delegations_lock); __set_bit(hash&255, bd->set[bd->new]); __set_bit((hash>>8)&255, bd->set[bd->new]); __set_bit((hash>>16)&255, bd->set[bd->new]); if (bd->entries == 0) - bd->swap_time = seconds_since_boot(); + bd->swap_time = ktime_get_seconds(); bd->entries += 1; spin_unlock(&blocked_delegations_lock); } static struct nfs4_delegation * alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, - struct svc_fh *current_fh, - struct nfs4_clnt_odstate *odstate) + struct nfs4_clnt_odstate *odstate, u32 dl_type) { struct nfs4_delegation *dp; + struct nfs4_stid *stid; long n; dprintk("NFSD alloc_init_deleg\n"); n = atomic_long_inc_return(&num_delegations); if (n < 0 || n > max_delegations) goto out_dec; - if (delegation_blocked(¤t_fh->fh_handle)) + if (delegation_blocked(&fp->fi_fhandle)) goto out_dec; - dp = delegstateid(nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg)); - if (dp == NULL) + stid = nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg); + if (stid == NULL) goto out_dec; + dp = delegstateid(stid); /* * delegation seqid's are never incremented. The 4.1 special @@ -865,10 +1154,14 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp, INIT_LIST_HEAD(&dp->dl_recall_lru); dp->dl_clnt_odstate = odstate; get_clnt_odstate(odstate); - dp->dl_type = NFS4_OPEN_DELEGATE_READ; + dp->dl_type = dl_type; dp->dl_retries = 1; + dp->dl_recalled = false; nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client, &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL); + nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client, + &nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR); + dp->dl_cb_fattr.ncf_file_modified = false; get_nfs4_file(fp); dp->dl_stid.sc_file = fp; return dp; @@ -890,6 +1183,9 @@ nfs4_put_stid(struct nfs4_stid *s) return; } idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id); + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) + atomic_dec(&s->sc_client->cl_admin_revoked); + nfs4_free_cpntf_statelist(clp->net, s); spin_unlock(&clp->cl_lock); s->sc_free(s); if (fp) @@ -910,25 +1206,67 @@ nfs4_inc_and_copy_stateid(stateid_t *dst, struct nfs4_stid *stid) static void put_deleg_file(struct nfs4_file *fp) { - struct file *filp = NULL; + struct nfsd_file *rnf = NULL; + struct nfsd_file *nf = NULL; spin_lock(&fp->fi_lock); - if (--fp->fi_delegees == 0) - swap(filp, fp->fi_deleg_file); + if (--fp->fi_delegees == 0) { + swap(nf, fp->fi_deleg_file); + swap(rnf, fp->fi_rdeleg_file); + } spin_unlock(&fp->fi_lock); - if (filp) - fput(filp); + if (nf) + nfsd_file_put(nf); + if (rnf) + nfs4_file_put_access(fp, NFS4_SHARE_ACCESS_READ); +} + +static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct file *f) +{ + struct iattr ia = { .ia_valid = ATTR_ATIME | ATTR_CTIME | ATTR_MTIME }; + struct inode *inode = file_inode(f); + int ret; + + /* don't do anything if FMODE_NOCMTIME isn't set */ + if ((READ_ONCE(f->f_mode) & FMODE_NOCMTIME) == 0) + return; + + spin_lock(&f->f_lock); + f->f_mode &= ~FMODE_NOCMTIME; + spin_unlock(&f->f_lock); + + /* was it never written? */ + if (!dp->dl_written) + return; + + /* did it get a setattr for the timestamps at some point? */ + if (dp->dl_setattr) + return; + + /* Stamp everything to "now" */ + inode_lock(inode); + ret = notify_change(&nop_mnt_idmap, f->f_path.dentry, &ia, NULL); + inode_unlock(inode); + if (ret) { + struct inode *inode = file_inode(f); + + pr_notice_ratelimited("Unable to update timestamps on inode %02x:%02x:%lu: %d\n", + MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), + inode->i_ino, ret); + } } static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp) { struct nfs4_file *fp = dp->dl_stid.sc_file; - struct file *filp = fp->fi_deleg_file; + struct nfsd_file *nf = fp->fi_deleg_file; WARN_ON_ONCE(!fp->fi_delegees); - vfs_setlease(filp, F_UNLCK, NULL, (void **)&dp); + nfsd4_finalize_deleg_timestamps(dp, nf->nf_file); + kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp); put_deleg_file(fp); } @@ -939,11 +1277,6 @@ static void destroy_unhashed_deleg(struct nfs4_delegation *dp) nfs4_put_stid(&dp->dl_stid); } -void nfs4_unhash_stid(struct nfs4_stid *s) -{ - s->sc_type = 0; -} - /** * nfs4_delegation_exists - Discover if this delegation already exists * @clp: a pointer to the nfs4_client we're granting a delegation to @@ -991,27 +1324,39 @@ hash_delegation_locked(struct nfs4_delegation *dp, struct nfs4_file *fp) lockdep_assert_held(&state_lock); lockdep_assert_held(&fp->fi_lock); + lockdep_assert_held(&clp->cl_lock); if (nfs4_delegation_exists(clp, fp)) return -EAGAIN; refcount_inc(&dp->dl_stid.sc_count); - dp->dl_stid.sc_type = NFS4_DELEG_STID; + dp->dl_stid.sc_type = SC_TYPE_DELEG; list_add(&dp->dl_perfile, &fp->fi_delegations); list_add(&dp->dl_perclnt, &clp->cl_delegations); return 0; } +static bool delegation_hashed(struct nfs4_delegation *dp) +{ + return !(list_empty(&dp->dl_perfile)); +} + static bool -unhash_delegation_locked(struct nfs4_delegation *dp) +unhash_delegation_locked(struct nfs4_delegation *dp, unsigned short statusmask) { struct nfs4_file *fp = dp->dl_stid.sc_file; lockdep_assert_held(&state_lock); - if (list_empty(&dp->dl_perfile)) + if (!delegation_hashed(dp)) return false; - dp->dl_stid.sc_type = NFS4_CLOSED_DELEG_STID; + if (statusmask == SC_STATUS_REVOKED && + dp->dl_stid.sc_client->cl_minorversion == 0) + statusmask = SC_STATUS_CLOSED; + dp->dl_stid.sc_status |= statusmask; + if (statusmask & SC_STATUS_ADMIN_REVOKED) + atomic_inc(&dp->dl_stid.sc_client->cl_admin_revoked); + /* Ensure that deleg break won't try to requeue it */ ++dp->dl_time; spin_lock(&fp->fi_lock); @@ -1027,30 +1372,59 @@ static void destroy_delegation(struct nfs4_delegation *dp) bool unhashed; spin_lock(&state_lock); - unhashed = unhash_delegation_locked(dp); + unhashed = unhash_delegation_locked(dp, SC_STATUS_CLOSED); spin_unlock(&state_lock); if (unhashed) destroy_unhashed_deleg(dp); } +/** + * revoke_delegation - perform nfs4 delegation structure cleanup + * @dp: pointer to the delegation + * + * This function assumes that it's called either from the administrative + * interface (nfsd4_revoke_states()) that's revoking a specific delegation + * stateid or it's called from a laundromat thread (nfsd4_landromat()) that + * determined that this specific state has expired and needs to be revoked + * (both mark state with the appropriate stid sc_status mode). It is also + * assumed that a reference was taken on the @dp state. + * + * If this function finds that the @dp state is SC_STATUS_FREED it means + * that a FREE_STATEID operation for this stateid has been processed and + * we can proceed to removing it from recalled list. However, if @dp state + * isn't marked SC_STATUS_FREED, it means we need place it on the cl_revoked + * list and wait for the FREE_STATEID to arrive from the client. At the same + * time, we need to mark it as SC_STATUS_FREEABLE to indicate to the + * nfsd4_free_stateid() function that this stateid has already been added + * to the cl_revoked list and that nfsd4_free_stateid() is now responsible + * for removing it from the list. Inspection of where the delegation state + * in the revocation process is protected by the clp->cl_lock. + */ static void revoke_delegation(struct nfs4_delegation *dp) { struct nfs4_client *clp = dp->dl_stid.sc_client; WARN_ON(!list_empty(&dp->dl_recall_lru)); + WARN_ON_ONCE(dp->dl_stid.sc_client->cl_minorversion > 0 && + !(dp->dl_stid.sc_status & + (SC_STATUS_REVOKED | SC_STATUS_ADMIN_REVOKED))); - if (clp->cl_minorversion) { - dp->dl_stid.sc_type = NFS4_REVOKED_DELEG_STID; - refcount_inc(&dp->dl_stid.sc_count); - spin_lock(&clp->cl_lock); - list_add(&dp->dl_recall_lru, &clp->cl_revoked); - spin_unlock(&clp->cl_lock); + trace_nfsd_stid_revoke(&dp->dl_stid); + + spin_lock(&clp->cl_lock); + if (dp->dl_stid.sc_status & SC_STATUS_FREED) { + list_del_init(&dp->dl_recall_lru); + goto out; } + list_add(&dp->dl_recall_lru, &clp->cl_revoked); + dp->dl_stid.sc_status |= SC_STATUS_FREEABLE; +out: + spin_unlock(&clp->cl_lock); destroy_unhashed_deleg(dp); } -/* - * SETCLIENTID state +/* + * SETCLIENTID state */ static unsigned int clientid_hashval(u32 id) @@ -1058,111 +1432,9 @@ static unsigned int clientid_hashval(u32 id) return id & CLIENT_HASH_MASK; } -static unsigned int clientstr_hashval(const char *name) +static unsigned int clientstr_hashval(struct xdr_netobj name) { - return opaque_hashval(name, 8) & CLIENT_HASH_MASK; -} - -/* - * We store the NONE, READ, WRITE, and BOTH bits separately in the - * st_{access,deny}_bmap field of the stateid, in order to track not - * only what share bits are currently in force, but also what - * combinations of share bits previous opens have used. This allows us - * to enforce the recommendation of rfc 3530 14.2.19 that the server - * return an error if the client attempt to downgrade to a combination - * of share bits not explicable by closing some of its previous opens. - * - * XXX: This enforcement is actually incomplete, since we don't keep - * track of access/deny bit combinations; so, e.g., we allow: - * - * OPEN allow read, deny write - * OPEN allow both, deny none - * DOWNGRADE allow read, deny none - * - * which we should reject. - */ -static unsigned int -bmap_to_share_mode(unsigned long bmap) { - int i; - unsigned int access = 0; - - for (i = 1; i < 4; i++) { - if (test_bit(i, &bmap)) - access |= i; - } - return access; -} - -/* set share access for a given stateid */ -static inline void -set_access(u32 access, struct nfs4_ol_stateid *stp) -{ - unsigned char mask = 1 << access; - - WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH); - stp->st_access_bmap |= mask; -} - -/* clear share access for a given stateid */ -static inline void -clear_access(u32 access, struct nfs4_ol_stateid *stp) -{ - unsigned char mask = 1 << access; - - WARN_ON_ONCE(access > NFS4_SHARE_ACCESS_BOTH); - stp->st_access_bmap &= ~mask; -} - -/* test whether a given stateid has access */ -static inline bool -test_access(u32 access, struct nfs4_ol_stateid *stp) -{ - unsigned char mask = 1 << access; - - return (bool)(stp->st_access_bmap & mask); -} - -/* set share deny for a given stateid */ -static inline void -set_deny(u32 deny, struct nfs4_ol_stateid *stp) -{ - unsigned char mask = 1 << deny; - - WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH); - stp->st_deny_bmap |= mask; -} - -/* clear share deny for a given stateid */ -static inline void -clear_deny(u32 deny, struct nfs4_ol_stateid *stp) -{ - unsigned char mask = 1 << deny; - - WARN_ON_ONCE(deny > NFS4_SHARE_DENY_BOTH); - stp->st_deny_bmap &= ~mask; -} - -/* test whether a given stateid is denying specific access */ -static inline bool -test_deny(u32 deny, struct nfs4_ol_stateid *stp) -{ - unsigned char mask = 1 << deny; - - return (bool)(stp->st_deny_bmap & mask); -} - -static int nfs4_access_to_omode(u32 access) -{ - switch (access & NFS4_SHARE_ACCESS_BOTH) { - case NFS4_SHARE_ACCESS_READ: - return O_RDONLY; - case NFS4_SHARE_ACCESS_WRITE: - return O_WRONLY; - case NFS4_SHARE_ACCESS_BOTH: - return O_RDWR; - } - WARN_ON_ONCE(1); - return O_RDONLY; + return opaque_hashval(name.data, 8) & CLIENT_HASH_MASK; } /* @@ -1173,11 +1445,16 @@ static void recalculate_deny_mode(struct nfs4_file *fp) { struct nfs4_ol_stateid *stp; + u32 old_deny; spin_lock(&fp->fi_lock); + old_deny = fp->fi_share_deny; fp->fi_share_deny = 0; - list_for_each_entry(stp, &fp->fi_stateids, st_perfile) + list_for_each_entry(stp, &fp->fi_stateids, st_perfile) { fp->fi_share_deny |= bmap_to_share_mode(stp->st_deny_bmap); + if (fp->fi_share_deny == old_deny) + break; + } spin_unlock(&fp->fi_lock); } @@ -1235,6 +1512,12 @@ static void nfs4_put_stateowner(struct nfs4_stateowner *sop) nfs4_free_stateowner(sop); } +static bool +nfs4_ol_stateid_unhashed(const struct nfs4_ol_stateid *stp) +{ + return list_empty(&stp->st_perfile); +} + static bool unhash_ol_stateid(struct nfs4_ol_stateid *stp) { struct nfs4_file *fp = stp->st_stid.sc_file; @@ -1259,6 +1542,8 @@ static void nfs4_free_ol_stateid(struct nfs4_stid *stid) release_all_access(stp); if (stp->st_stateowner) nfs4_put_stateowner(stp->st_stateowner); + if (!list_empty(&stid->sc_cp_list)) + nfs4_free_cpntf_statelist(stid->sc_client->net, stid); kmem_cache_free(stateid_slab, stid); } @@ -1266,11 +1551,14 @@ static void nfs4_free_lock_stateid(struct nfs4_stid *stid) { struct nfs4_ol_stateid *stp = openlockstateid(stid); struct nfs4_lockowner *lo = lockowner(stp->st_stateowner); - struct file *file; + struct nfsd_file *nf; - file = find_any_file(stp->st_stid.sc_file); - if (file) - filp_close(file, (fl_owner_t)lo); + nf = find_any_file(stp->st_stid.sc_file); + if (nf) { + get_file(nf->nf_file); + filp_close(nf->nf_file, (fl_owner_t)lo); + nfsd_file_put(nf); + } nfs4_free_ol_stateid(stid); } @@ -1295,6 +1583,8 @@ static void put_ol_stateid_locked(struct nfs4_ol_stateid *stp, } idr_remove(&clp->cl_stateids, s->sc_stateid.si_opaque.so_id); + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) + atomic_dec(&s->sc_client->cl_admin_revoked); list_add(&stp->st_locks, reaplist); } @@ -1302,9 +1592,11 @@ static bool unhash_lock_stateid(struct nfs4_ol_stateid *stp) { lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); + if (!unhash_ol_stateid(stp)) + return false; list_del_init(&stp->st_locks); - nfs4_unhash_stid(&stp->st_stid); - return unhash_ol_stateid(stp); + stp->st_stid.sc_status |= SC_STATUS_CLOSED; + return true; } static void release_lock_stateid(struct nfs4_ol_stateid *stp) @@ -1361,7 +1653,7 @@ static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp, while (!list_empty(&open_stp->st_locks)) { stp = list_entry(open_stp->st_locks.next, struct nfs4_ol_stateid, st_locks); - WARN_ON(!unhash_lock_stateid(stp)); + unhash_lock_stateid(stp); put_ol_stateid_locked(stp, reaplist); } } @@ -1369,13 +1661,12 @@ static void release_open_stateid_locks(struct nfs4_ol_stateid *open_stp, static bool unhash_open_stateid(struct nfs4_ol_stateid *stp, struct list_head *reaplist) { - bool unhashed; - lockdep_assert_held(&stp->st_stid.sc_client->cl_lock); - unhashed = unhash_ol_stateid(stp); + if (!unhash_ol_stateid(stp)) + return false; release_open_stateid_locks(stp, reaplist); - return unhashed; + return true; } static void release_open_stateid(struct nfs4_ol_stateid *stp) @@ -1383,12 +1674,21 @@ static void release_open_stateid(struct nfs4_ol_stateid *stp) LIST_HEAD(reaplist); spin_lock(&stp->st_stid.sc_client->cl_lock); + stp->st_stid.sc_status |= SC_STATUS_CLOSED; if (unhash_open_stateid(stp, &reaplist)) put_ol_stateid_locked(stp, &reaplist); spin_unlock(&stp->st_stid.sc_client->cl_lock); free_ol_stateid_reaplist(&reaplist); } +static bool nfs4_openowner_unhashed(struct nfs4_openowner *oo) +{ + lockdep_assert_held(&oo->oo_owner.so_client->cl_lock); + + return list_empty(&oo->oo_owner.so_strhash) && + list_empty(&oo->oo_perclient); +} + static void unhash_openowner_locked(struct nfs4_openowner *oo) { struct nfs4_client *clp = oo->oo_owner.so_client; @@ -1420,9 +1720,7 @@ static void release_openowner(struct nfs4_openowner *oo) { struct nfs4_ol_stateid *stp; struct nfs4_client *clp = oo->oo_owner.so_client; - struct list_head reaplist; - - INIT_LIST_HEAD(&reaplist); + LIST_HEAD(reaplist); spin_lock(&clp->cl_lock); unhash_openowner_locked(oo); @@ -1438,6 +1736,137 @@ static void release_openowner(struct nfs4_openowner *oo) nfs4_put_stateowner(&oo->oo_owner); } +static struct nfs4_stid *find_one_sb_stid(struct nfs4_client *clp, + struct super_block *sb, + unsigned int sc_types) +{ + unsigned long id, tmp; + struct nfs4_stid *stid; + + spin_lock(&clp->cl_lock); + idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) + if ((stid->sc_type & sc_types) && + stid->sc_status == 0 && + stid->sc_file->fi_inode->i_sb == sb) { + refcount_inc(&stid->sc_count); + break; + } + spin_unlock(&clp->cl_lock); + return stid; +} + +/** + * nfsd4_revoke_states - revoke all nfsv4 states associated with given filesystem + * @net: used to identify instance of nfsd (there is one per net namespace) + * @sb: super_block used to identify target filesystem + * + * All nfs4 states (open, lock, delegation, layout) held by the server instance + * and associated with a file on the given filesystem will be revoked resulting + * in any files being closed and so all references from nfsd to the filesystem + * being released. Thus nfsd will no longer prevent the filesystem from being + * unmounted. + * + * The clients which own the states will subsequently being notified that the + * states have been "admin-revoked". + */ +void nfsd4_revoke_states(struct net *net, struct super_block *sb) +{ + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + unsigned int idhashval; + unsigned int sc_types; + + sc_types = SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG | SC_TYPE_LAYOUT; + + spin_lock(&nn->client_lock); + for (idhashval = 0; idhashval < CLIENT_HASH_MASK; idhashval++) { + struct list_head *head = &nn->conf_id_hashtbl[idhashval]; + struct nfs4_client *clp; + retry: + list_for_each_entry(clp, head, cl_idhash) { + struct nfs4_stid *stid = find_one_sb_stid(clp, sb, + sc_types); + if (stid) { + struct nfs4_ol_stateid *stp; + struct nfs4_delegation *dp; + struct nfs4_layout_stateid *ls; + + spin_unlock(&nn->client_lock); + switch (stid->sc_type) { + case SC_TYPE_OPEN: + stp = openlockstateid(stid); + mutex_lock_nested(&stp->st_mutex, + OPEN_STATEID_MUTEX); + + spin_lock(&clp->cl_lock); + if (stid->sc_status == 0) { + stid->sc_status |= + SC_STATUS_ADMIN_REVOKED; + atomic_inc(&clp->cl_admin_revoked); + spin_unlock(&clp->cl_lock); + release_all_access(stp); + } else + spin_unlock(&clp->cl_lock); + mutex_unlock(&stp->st_mutex); + break; + case SC_TYPE_LOCK: + stp = openlockstateid(stid); + mutex_lock_nested(&stp->st_mutex, + LOCK_STATEID_MUTEX); + spin_lock(&clp->cl_lock); + if (stid->sc_status == 0) { + struct nfs4_lockowner *lo = + lockowner(stp->st_stateowner); + struct nfsd_file *nf; + + stid->sc_status |= + SC_STATUS_ADMIN_REVOKED; + atomic_inc(&clp->cl_admin_revoked); + spin_unlock(&clp->cl_lock); + nf = find_any_file(stp->st_stid.sc_file); + if (nf) { + get_file(nf->nf_file); + filp_close(nf->nf_file, + (fl_owner_t)lo); + nfsd_file_put(nf); + } + release_all_access(stp); + } else + spin_unlock(&clp->cl_lock); + mutex_unlock(&stp->st_mutex); + break; + case SC_TYPE_DELEG: + refcount_inc(&stid->sc_count); + dp = delegstateid(stid); + spin_lock(&state_lock); + if (!unhash_delegation_locked( + dp, SC_STATUS_ADMIN_REVOKED)) + dp = NULL; + spin_unlock(&state_lock); + if (dp) + revoke_delegation(dp); + break; + case SC_TYPE_LAYOUT: + ls = layoutstateid(stid); + nfsd4_close_layout(ls); + break; + } + nfs4_put_stid(stid); + spin_lock(&nn->client_lock); + if (clp->cl_minorversion == 0) + /* Allow cleanup after a lease period. + * store_release ensures cleanup will + * see any newly revoked states if it + * sees the time updated. + */ + nn->nfs40_last_revoke = + ktime_get_boottime_seconds(); + goto retry; + } + } + } + spin_unlock(&nn->client_lock); +} + static inline int hash_sessionid(struct nfs4_sessionid *sessionid) { @@ -1509,96 +1938,145 @@ gen_sessionid(struct nfsd4_session *ses) */ #define NFSD_MIN_HDR_SEQ_SZ (24 + 12 + 44) +static struct shrinker *nfsd_slot_shrinker; +static DEFINE_SPINLOCK(nfsd_session_list_lock); +static LIST_HEAD(nfsd_session_list); +/* The sum of "target_slots-1" on every session. The shrinker can push this + * down, though it can take a little while for the memory to actually + * be freed. The "-1" is because we can never free slot 0 while the + * session is active. + */ +static atomic_t nfsd_total_target_slots = ATOMIC_INIT(0); + static void -free_session_slots(struct nfsd4_session *ses) +free_session_slots(struct nfsd4_session *ses, int from) { int i; - for (i = 0; i < ses->se_fchannel.maxreqs; i++) { - free_svc_cred(&ses->se_slots[i]->sl_cred); - kfree(ses->se_slots[i]); + if (from >= ses->se_fchannel.maxreqs) + return; + + for (i = from; i < ses->se_fchannel.maxreqs; i++) { + struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); + + /* + * Save the seqid in case we reactivate this slot. + * This will never require a memory allocation so GFP + * flag is irrelevant + */ + xa_store(&ses->se_slots, i, xa_mk_value(slot->sl_seqid), 0); + free_svc_cred(&slot->sl_cred); + kfree(slot); + } + ses->se_fchannel.maxreqs = from; + if (ses->se_target_maxslots > from) { + int new_target = from ?: 1; + atomic_sub(ses->se_target_maxslots - new_target, &nfsd_total_target_slots); + ses->se_target_maxslots = new_target; } } -/* - * We don't actually need to cache the rpc and session headers, so we - * can allocate a little less for each slot: +/** + * reduce_session_slots - reduce the target max-slots of a session if possible + * @ses: The session to affect + * @dec: how much to decrease the target by + * + * This interface can be used by a shrinker to reduce the target max-slots + * for a session so that some slots can eventually be freed. + * It uses spin_trylock() as it may be called in a context where another + * spinlock is held that has a dependency on client_lock. As shrinkers are + * best-effort, skiping a session is client_lock is already held has no + * great coast + * + * Return value: + * The number of slots that the target was reduced by. */ -static inline u32 slot_bytes(struct nfsd4_channel_attrs *ca) +static int +reduce_session_slots(struct nfsd4_session *ses, int dec) { - u32 size; + struct nfsd_net *nn = net_generic(ses->se_client->net, + nfsd_net_id); + int ret = 0; - if (ca->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ) - size = 0; - else - size = ca->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; - return size + sizeof(struct nfsd4_slot); + if (ses->se_target_maxslots <= 1) + return ret; + if (!spin_trylock(&nn->client_lock)) + return ret; + ret = min(dec, ses->se_target_maxslots-1); + ses->se_target_maxslots -= ret; + atomic_sub(ret, &nfsd_total_target_slots); + ses->se_slot_gen += 1; + if (ses->se_slot_gen == 0) { + int i; + ses->se_slot_gen = 1; + for (i = 0; i < ses->se_fchannel.maxreqs; i++) { + struct nfsd4_slot *slot = xa_load(&ses->se_slots, i); + slot->sl_generation = 0; + } + } + spin_unlock(&nn->client_lock); + return ret; } -/* - * XXX: If we run out of reserved DRC memory we could (up to a point) - * re-negotiate active sessions and reduce their slot usage to make - * room for new connections. For now we just fail the create session. - */ -static u32 nfsd4_get_drc_mem(struct nfsd4_channel_attrs *ca) +static struct nfsd4_slot *nfsd4_alloc_slot(struct nfsd4_channel_attrs *fattrs, + int index, gfp_t gfp) { - u32 slotsize = slot_bytes(ca); - u32 num = ca->maxreqs; - int avail; + struct nfsd4_slot *slot; + size_t size; - spin_lock(&nfsd_drc_lock); - avail = min((unsigned long)NFSD_MAX_MEM_PER_SESSION, - nfsd_drc_max_mem - nfsd_drc_mem_used); /* - * Never use more than a third of the remaining memory, - * unless it's the only way to give this client a slot: + * The RPC and NFS session headers are never saved in + * the slot reply cache buffer. */ - avail = clamp_t(int, avail, slotsize, avail/3); - num = min_t(int, num, avail / slotsize); - nfsd_drc_mem_used += num * slotsize; - spin_unlock(&nfsd_drc_lock); - - return num; -} + size = fattrs->maxresp_cached < NFSD_MIN_HDR_SEQ_SZ ? + 0 : fattrs->maxresp_cached - NFSD_MIN_HDR_SEQ_SZ; -static void nfsd4_put_drc_mem(struct nfsd4_channel_attrs *ca) -{ - int slotsize = slot_bytes(ca); - - spin_lock(&nfsd_drc_lock); - nfsd_drc_mem_used -= slotsize * ca->maxreqs; - spin_unlock(&nfsd_drc_lock); + slot = kzalloc(struct_size(slot, sl_data, size), gfp); + if (!slot) + return NULL; + slot->sl_index = index; + return slot; } static struct nfsd4_session *alloc_session(struct nfsd4_channel_attrs *fattrs, struct nfsd4_channel_attrs *battrs) { int numslots = fattrs->maxreqs; - int slotsize = slot_bytes(fattrs); struct nfsd4_session *new; - int mem, i; - - BUILD_BUG_ON(NFSD_MAX_SLOTS_PER_SESSION * sizeof(struct nfsd4_slot *) - + sizeof(struct nfsd4_session) > PAGE_SIZE); - mem = numslots * sizeof(struct nfsd4_slot *); + struct nfsd4_slot *slot; + int i; - new = kzalloc(sizeof(*new) + mem, GFP_KERNEL); + new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) return NULL; - /* allocate each struct nfsd4_slot and data cache in one piece */ - for (i = 0; i < numslots; i++) { - new->se_slots[i] = kzalloc(slotsize, GFP_KERNEL); - if (!new->se_slots[i]) - goto out_free; - } + xa_init(&new->se_slots); - memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs)); - memcpy(&new->se_bchannel, battrs, sizeof(struct nfsd4_channel_attrs)); + slot = nfsd4_alloc_slot(fattrs, 0, GFP_KERNEL); + if (!slot || xa_is_err(xa_store(&new->se_slots, 0, slot, GFP_KERNEL))) + goto out_free; + for (i = 1; i < numslots; i++) { + const gfp_t gfp = GFP_KERNEL | __GFP_NORETRY | __GFP_NOWARN; + slot = nfsd4_alloc_slot(fattrs, i, gfp); + if (!slot) + break; + if (xa_is_err(xa_store(&new->se_slots, i, slot, gfp))) { + kfree(slot); + break; + } + } + fattrs->maxreqs = i; + memcpy(&new->se_fchannel, fattrs, sizeof(struct nfsd4_channel_attrs)); + new->se_target_maxslots = i; + atomic_add(i - 1, &nfsd_total_target_slots); + new->se_cb_slot_avail = ~0U; + new->se_cb_highest_slot = min(battrs->maxreqs - 1, + NFSD_BC_SLOT_TABLE_SIZE - 1); + spin_lock_init(&new->se_lock); return new; out_free: - while (i--) - kfree(new->se_slots[i]); + kfree(slot); + xa_destroy(&new->se_slots); kfree(new); return NULL; } @@ -1614,6 +2092,8 @@ static void nfsd4_conn_lost(struct svc_xpt_user *u) struct nfsd4_conn *c = container_of(u, struct nfsd4_conn, cn_xpt_user); struct nfs4_client *clp = c->cn_session->se_client; + trace_nfsd_cb_lost(clp); + spin_lock(&clp->cl_lock); if (!list_empty(&c->cn_persession)) { list_del(&c->cn_persession); @@ -1702,17 +2182,47 @@ static void nfsd4_del_conns(struct nfsd4_session *s) static void __free_session(struct nfsd4_session *ses) { - free_session_slots(ses); + free_session_slots(ses, 0); + xa_destroy(&ses->se_slots); kfree(ses); } static void free_session(struct nfsd4_session *ses) { nfsd4_del_conns(ses); - nfsd4_put_drc_mem(&ses->se_fchannel); __free_session(ses); } +static unsigned long +nfsd_slot_count(struct shrinker *s, struct shrink_control *sc) +{ + unsigned long cnt = atomic_read(&nfsd_total_target_slots); + + return cnt ? cnt : SHRINK_EMPTY; +} + +static unsigned long +nfsd_slot_scan(struct shrinker *s, struct shrink_control *sc) +{ + struct nfsd4_session *ses; + unsigned long scanned = 0; + unsigned long freed = 0; + + spin_lock(&nfsd_session_list_lock); + list_for_each_entry(ses, &nfsd_session_list, se_all_sessions) { + freed += reduce_session_slots(ses, 1); + scanned += 1; + if (scanned >= sc->nr_to_scan) { + /* Move starting point for next scan */ + list_move(&nfsd_session_list, &ses->se_all_sessions); + break; + } + } + spin_unlock(&nfsd_session_list_lock); + sc->nr_scanned = scanned; + return freed; +} + static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, struct nfs4_client *clp, struct nfsd4_create_session *cses) { int idx; @@ -1723,17 +2233,24 @@ static void init_session(struct svc_rqst *rqstp, struct nfsd4_session *new, stru INIT_LIST_HEAD(&new->se_conns); - new->se_cb_seq_nr = 1; - new->se_flags = cses->flags; + atomic_set(&new->se_ref, 0); + new->se_dead = false; new->se_cb_prog = cses->callback_prog; new->se_cb_sec = cses->cb_sec; - atomic_set(&new->se_ref, 0); + + for (idx = 0; idx < NFSD_BC_SLOT_TABLE_SIZE; ++idx) + new->se_cb_seq_nr[idx] = 1; + idx = hash_sessionid(&new->se_sessionid); list_add(&new->se_hash, &nn->sessionid_hashtbl[idx]); spin_lock(&clp->cl_lock); list_add(&new->se_perclnt, &clp->cl_sessions); spin_unlock(&clp->cl_lock); + spin_lock(&nfsd_session_list_lock); + list_add_tail(&new->se_all_sessions, &nfsd_session_list); + spin_unlock(&nfsd_session_list_lock); + { struct sockaddr *sa = svc_addr(rqstp); /* @@ -1803,6 +2320,9 @@ unhash_session(struct nfsd4_session *ses) spin_lock(&ses->se_client->cl_lock); list_del(&ses->se_perclnt); spin_unlock(&ses->se_client->cl_lock); + spin_lock(&nfsd_session_list_lock); + list_del(&ses->se_all_sessions); + spin_unlock(&nfsd_session_list_lock); } /* SETCLIENTID and SETCLIENTID_CONFIRM Helper functions */ @@ -1816,25 +2336,24 @@ STALE_CLIENTID(clientid_t *clid, struct nfsd_net *nn) */ if (clid->cl_boot == (u32)nn->boot_time) return 0; - dprintk("NFSD stale clientid (%08x/%08x) boot_time %08lx\n", - clid->cl_boot, clid->cl_id, nn->boot_time); + trace_nfsd_clid_stale(clid); return 1; } -/* - * XXX Should we use a slab cache ? - * This type of memory management is somewhat inefficient, but we use it - * anyway since SETCLIENTID is not a common operation. - */ -static struct nfs4_client *alloc_client(struct xdr_netobj name) +static struct nfs4_client *alloc_client(struct xdr_netobj name, + struct nfsd_net *nn) { struct nfs4_client *clp; int i; + if (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients && + atomic_read(&nn->nfsd_courtesy_clients) > 0) + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + clp = kmem_cache_zalloc(client_slab, GFP_KERNEL); if (clp == NULL) return NULL; - clp->cl_name.data = kmemdup(name.data, name.len, GFP_KERNEL); + xdr_netobj_dup(&clp->cl_name, &name, GFP_KERNEL); if (clp->cl_name.data == NULL) goto err_no_name; clp->cl_ownerstr_hashtbl = kmalloc_array(OWNER_HASH_SIZE, @@ -1842,13 +2361,19 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) GFP_KERNEL); if (!clp->cl_ownerstr_hashtbl) goto err_no_hashtbl; + clp->cl_callback_wq = alloc_ordered_workqueue("nfsd4_callbacks", 0); + if (!clp->cl_callback_wq) + goto err_no_callback_wq; + for (i = 0; i < OWNER_HASH_SIZE; i++) INIT_LIST_HEAD(&clp->cl_ownerstr_hashtbl[i]); - clp->cl_name.len = name.len; INIT_LIST_HEAD(&clp->cl_sessions); idr_init(&clp->cl_stateids); - atomic_set(&clp->cl_refcount, 0); + atomic_set(&clp->cl_rpc_users, 0); clp->cl_cb_state = NFSD4_CB_UNKNOWN; + clp->cl_state = NFSD4_ACTIVE; + atomic_inc(&nn->nfs4_client_count); + atomic_set(&clp->cl_delegs_in_recall, 0); INIT_LIST_HEAD(&clp->cl_idhash); INIT_LIST_HEAD(&clp->cl_openowners); INIT_LIST_HEAD(&clp->cl_delegations); @@ -1862,6 +2387,8 @@ static struct nfs4_client *alloc_client(struct xdr_netobj name) spin_lock_init(&clp->cl_lock); rpc_init_wait_queue(&clp->cl_cb_waitq, "Backchannel slot table"); return clp; +err_no_callback_wq: + kfree(clp->cl_ownerstr_hashtbl); err_no_hashtbl: kfree(clp->cl_name.data); err_no_name: @@ -1869,6 +2396,27 @@ err_no_name: return NULL; } +static void __free_client(struct kref *k) +{ + struct nfsdfs_client *c = container_of(k, struct nfsdfs_client, cl_ref); + struct nfs4_client *clp = container_of(c, struct nfs4_client, cl_nfsdfs); + + free_svc_cred(&clp->cl_cred); + destroy_workqueue(clp->cl_callback_wq); + kfree(clp->cl_ownerstr_hashtbl); + kfree(clp->cl_name.data); + kfree(clp->cl_nii_domain.data); + kfree(clp->cl_nii_name.data); + idr_destroy(&clp->cl_stateids); + kfree(clp->cl_ra); + kmem_cache_free(client_slab, clp); +} + +static void drop_client(struct nfs4_client *clp) +{ + kref_put(&clp->cl_nfsdfs.cl_ref, __free_client); +} + static void free_client(struct nfs4_client *clp) { @@ -1881,11 +2429,12 @@ free_client(struct nfs4_client *clp) free_session(ses); } rpc_destroy_wait_queue(&clp->cl_cb_waitq); - free_svc_cred(&clp->cl_cred); - kfree(clp->cl_ownerstr_hashtbl); - kfree(clp->cl_name.data); - idr_destroy(&clp->cl_stateids); - kmem_cache_free(client_slab, clp); + if (clp->cl_nfsd_dentry) { + nfsd_client_rmdir(clp->cl_nfsd_dentry); + clp->cl_nfsd_dentry = NULL; + wake_up_all(&expiry_wq); + } + drop_client(clp); } /* must be called under the client_lock */ @@ -1909,8 +2458,12 @@ unhash_client_locked(struct nfs4_client *clp) } list_del_init(&clp->cl_lru); spin_lock(&clp->cl_lock); - list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + spin_lock(&nfsd_session_list_lock); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) { list_del_init(&ses->se_hash); + list_del_init(&ses->se_all_sessions); + } + spin_unlock(&nfsd_session_list_lock); spin_unlock(&clp->cl_lock); } @@ -1926,7 +2479,11 @@ unhash_client(struct nfs4_client *clp) static __be32 mark_client_expired_locked(struct nfs4_client *clp) { - if (atomic_read(&clp->cl_refcount)) + int users = atomic_read(&clp->cl_rpc_users); + + trace_nfsd_mark_client_expired(clp, users); + + if (users) return nfserr_jukebox; unhash_client_locked(clp); return nfs_ok; @@ -1935,16 +2492,16 @@ static __be32 mark_client_expired_locked(struct nfs4_client *clp) static void __destroy_client(struct nfs4_client *clp) { + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); int i; struct nfs4_openowner *oo; struct nfs4_delegation *dp; - struct list_head reaplist; + LIST_HEAD(reaplist); - INIT_LIST_HEAD(&reaplist); spin_lock(&state_lock); while (!list_empty(&clp->cl_delegations)) { dp = list_entry(clp->cl_delegations.next, struct nfs4_delegation, dl_perclnt); - WARN_ON(!unhash_delegation_locked(dp)); + unhash_delegation_locked(dp, SC_STATUS_CLOSED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); @@ -1978,7 +2535,10 @@ __destroy_client(struct nfs4_client *clp) nfsd4_shutdown_callback(clp); if (clp->cl_cb_conn.cb_xprt) svc_xprt_put(clp->cl_cb_conn.cb_xprt); + atomic_add_unless(&nn->nfs4_client_count, -1, 0); + nfsd4_dec_courtesy_client_count(nn, clp); free_client(clp); + wake_up_all(&expiry_wq); } static void @@ -1988,6 +2548,22 @@ destroy_client(struct nfs4_client *clp) __destroy_client(clp); } +static void inc_reclaim_complete(struct nfs4_client *clp) +{ + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + + if (!nn->track_reclaim_completes) + return; + if (!nfsd4_find_reclaim_client(clp->cl_name, nn)) + return; + if (atomic_inc_return(&nn->nr_reclaim_complete) == + nn->reclaim_str_hashtbl_size) { + printk(KERN_INFO "NFSD: all clients done reclaiming, ending NFSv4 grace period (net %x)\n", + clp->net->ns.inum); + nfsd4_end_grace(nn); + } +} + static void expire_client(struct nfs4_client *clp) { unhash_client(clp); @@ -2039,11 +2615,6 @@ compare_blob(const struct xdr_netobj *o1, const struct xdr_netobj *o2) return memcmp(o1->data, o2->data, o1->len); } -static int same_name(const char *n1, const char *n2) -{ - return 0 == memcmp(n1, n2, HEXDIR_LEN); -} - static int same_verf(nfs4_verifier *v1, nfs4_verifier *v2) { @@ -2138,14 +2709,14 @@ static void gen_confirm(struct nfs4_client *clp, struct nfsd_net *nn) * This is opaque to client, so no need to byte-swap. Use * __force to keep sparse happy */ - verf[0] = (__force __be32)get_seconds(); + verf[0] = (__force __be32)(u32)ktime_get_real_seconds(); verf[1] = (__force __be32)nn->clverifier_counter++; memcpy(clp->cl_confirm.data, verf, sizeof(clp->cl_confirm.data)); } static void gen_clid(struct nfs4_client *clp, struct nfsd_net *nn) { - clp->cl_clientid.cl_boot = nn->boot_time; + clp->cl_clientid.cl_boot = (u32)nn->boot_time; clp->cl_clientid.cl_id = nn->clientid_counter++; gen_confirm(clp, nn); } @@ -2162,14 +2733,16 @@ find_stateid_locked(struct nfs4_client *cl, stateid_t *t) } static struct nfs4_stid * -find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask) +find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, + unsigned short typemask, unsigned short ok_states) { struct nfs4_stid *s; spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, t); if (s != NULL) { - if (typemask & s->sc_type) + if ((s->sc_status & ~ok_states) == 0 && + (typemask & s->sc_type)) refcount_inc(&s->sc_count); else s = NULL; @@ -2178,6 +2751,519 @@ find_stateid_by_type(struct nfs4_client *cl, stateid_t *t, char typemask) return s; } +static struct nfs4_client *get_nfsdfs_clp(struct inode *inode) +{ + struct nfsdfs_client *nc; + nc = get_nfsdfs_client(inode); + if (!nc) + return NULL; + return container_of(nc, struct nfs4_client, cl_nfsdfs); +} + +static void seq_quote_mem(struct seq_file *m, char *data, int len) +{ + seq_puts(m, "\""); + seq_escape_mem(m, data, len, ESCAPE_HEX | ESCAPE_NAP | ESCAPE_APPEND, "\"\\"); + seq_puts(m, "\""); +} + +static const char *cb_state2str(int state) +{ + switch (state) { + case NFSD4_CB_UP: + return "UP"; + case NFSD4_CB_UNKNOWN: + return "UNKNOWN"; + case NFSD4_CB_DOWN: + return "DOWN"; + case NFSD4_CB_FAULT: + return "FAULT"; + } + return "UNDEFINED"; +} + +static int client_info_show(struct seq_file *m, void *v) +{ + struct inode *inode = file_inode(m->file); + struct nfsd4_session *ses; + struct nfs4_client *clp; + u64 clid; + + clp = get_nfsdfs_clp(inode); + if (!clp) + return -ENXIO; + memcpy(&clid, &clp->cl_clientid, sizeof(clid)); + seq_printf(m, "clientid: 0x%llx\n", clid); + seq_printf(m, "address: \"%pISpc\"\n", (struct sockaddr *)&clp->cl_addr); + + if (clp->cl_state == NFSD4_COURTESY) + seq_puts(m, "status: courtesy\n"); + else if (clp->cl_state == NFSD4_EXPIRABLE) + seq_puts(m, "status: expirable\n"); + else if (test_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags)) + seq_puts(m, "status: confirmed\n"); + else + seq_puts(m, "status: unconfirmed\n"); + seq_printf(m, "seconds from last renew: %lld\n", + ktime_get_boottime_seconds() - clp->cl_time); + seq_puts(m, "name: "); + seq_quote_mem(m, clp->cl_name.data, clp->cl_name.len); + seq_printf(m, "\nminor version: %d\n", clp->cl_minorversion); + if (clp->cl_nii_domain.data) { + seq_puts(m, "Implementation domain: "); + seq_quote_mem(m, clp->cl_nii_domain.data, + clp->cl_nii_domain.len); + seq_puts(m, "\nImplementation name: "); + seq_quote_mem(m, clp->cl_nii_name.data, clp->cl_nii_name.len); + seq_printf(m, "\nImplementation time: [%lld, %ld]\n", + clp->cl_nii_time.tv_sec, clp->cl_nii_time.tv_nsec); + } + seq_printf(m, "callback state: %s\n", cb_state2str(clp->cl_cb_state)); + seq_printf(m, "callback address: \"%pISpc\"\n", &clp->cl_cb_conn.cb_addr); + seq_printf(m, "admin-revoked states: %d\n", + atomic_read(&clp->cl_admin_revoked)); + spin_lock(&clp->cl_lock); + seq_printf(m, "session slots:"); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + seq_printf(m, " %u", ses->se_fchannel.maxreqs); + seq_printf(m, "\nsession target slots:"); + list_for_each_entry(ses, &clp->cl_sessions, se_perclnt) + seq_printf(m, " %u", ses->se_target_maxslots); + spin_unlock(&clp->cl_lock); + seq_puts(m, "\n"); + + drop_client(clp); + + return 0; +} + +DEFINE_SHOW_ATTRIBUTE(client_info); + +static void *states_start(struct seq_file *s, loff_t *pos) + __acquires(&clp->cl_lock) +{ + struct nfs4_client *clp = s->private; + unsigned long id = *pos; + void *ret; + + spin_lock(&clp->cl_lock); + ret = idr_get_next_ul(&clp->cl_stateids, &id); + *pos = id; + return ret; +} + +static void *states_next(struct seq_file *s, void *v, loff_t *pos) +{ + struct nfs4_client *clp = s->private; + unsigned long id = *pos; + void *ret; + + id = *pos; + id++; + ret = idr_get_next_ul(&clp->cl_stateids, &id); + *pos = id; + return ret; +} + +static void states_stop(struct seq_file *s, void *v) + __releases(&clp->cl_lock) +{ + struct nfs4_client *clp = s->private; + + spin_unlock(&clp->cl_lock); +} + +static void nfs4_show_fname(struct seq_file *s, struct nfsd_file *f) +{ + seq_printf(s, "filename: \"%pD2\"", f->nf_file); +} + +static void nfs4_show_superblock(struct seq_file *s, struct nfsd_file *f) +{ + struct inode *inode = file_inode(f->nf_file); + + seq_printf(s, "superblock: \"%02x:%02x:%ld\"", + MAJOR(inode->i_sb->s_dev), + MINOR(inode->i_sb->s_dev), + inode->i_ino); +} + +static void nfs4_show_owner(struct seq_file *s, struct nfs4_stateowner *oo) +{ + seq_puts(s, "owner: "); + seq_quote_mem(s, oo->so_owner.data, oo->so_owner.len); +} + +static void nfs4_show_stateid(struct seq_file *s, stateid_t *stid) +{ + seq_printf(s, "0x%.8x", stid->si_generation); + seq_printf(s, "%12phN", &stid->si_opaque); +} + +static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st) +{ + struct nfs4_ol_stateid *ols; + struct nfs4_file *nf; + struct nfsd_file *file; + struct nfs4_stateowner *oo; + unsigned int access, deny; + + ols = openlockstateid(st); + oo = ols->st_stateowner; + nf = st->sc_file; + + seq_puts(s, "- "); + nfs4_show_stateid(s, &st->sc_stateid); + seq_puts(s, ": { type: open, "); + + access = bmap_to_share_mode(ols->st_access_bmap); + deny = bmap_to_share_mode(ols->st_deny_bmap); + + seq_printf(s, "access: %s%s, ", + access & NFS4_SHARE_ACCESS_READ ? "r" : "-", + access & NFS4_SHARE_ACCESS_WRITE ? "w" : "-"); + seq_printf(s, "deny: %s%s, ", + deny & NFS4_SHARE_ACCESS_READ ? "r" : "-", + deny & NFS4_SHARE_ACCESS_WRITE ? "w" : "-"); + + if (nf) { + spin_lock(&nf->fi_lock); + file = find_any_file_locked(nf); + if (file) { + nfs4_show_superblock(s, file); + seq_puts(s, ", "); + nfs4_show_fname(s, file); + seq_puts(s, ", "); + } + spin_unlock(&nf->fi_lock); + } else + seq_puts(s, "closed, "); + nfs4_show_owner(s, oo); + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); + return 0; +} + +static int nfs4_show_lock(struct seq_file *s, struct nfs4_stid *st) +{ + struct nfs4_ol_stateid *ols; + struct nfs4_file *nf; + struct nfsd_file *file; + struct nfs4_stateowner *oo; + + ols = openlockstateid(st); + oo = ols->st_stateowner; + nf = st->sc_file; + + seq_puts(s, "- "); + nfs4_show_stateid(s, &st->sc_stateid); + seq_puts(s, ": { type: lock, "); + + spin_lock(&nf->fi_lock); + file = find_any_file_locked(nf); + if (file) { + /* + * Note: a lock stateid isn't really the same thing as a lock, + * it's the locking state held by one owner on a file, and there + * may be multiple (or no) lock ranges associated with it. + * (Same for the matter is true of open stateids.) + */ + + nfs4_show_superblock(s, file); + /* XXX: open stateid? */ + seq_puts(s, ", "); + nfs4_show_fname(s, file); + seq_puts(s, ", "); + } + nfs4_show_owner(s, oo); + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); + spin_unlock(&nf->fi_lock); + return 0; +} + +static char *nfs4_show_deleg_type(u32 dl_type) +{ + switch (dl_type) { + case OPEN_DELEGATE_READ: + return "r"; + case OPEN_DELEGATE_WRITE: + return "w"; + case OPEN_DELEGATE_READ_ATTRS_DELEG: + return "ra"; + case OPEN_DELEGATE_WRITE_ATTRS_DELEG: + return "wa"; + } + return "?"; +} + +static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st) +{ + struct nfs4_delegation *ds; + struct nfs4_file *nf; + struct nfsd_file *file; + + ds = delegstateid(st); + nf = st->sc_file; + + seq_puts(s, "- "); + nfs4_show_stateid(s, &st->sc_stateid); + seq_puts(s, ": { type: deleg, "); + + seq_printf(s, "access: %s", nfs4_show_deleg_type(ds->dl_type)); + + /* XXX: lease time, whether it's being recalled. */ + + spin_lock(&nf->fi_lock); + file = nf->fi_deleg_file; + if (file) { + seq_puts(s, ", "); + nfs4_show_superblock(s, file); + seq_puts(s, ", "); + nfs4_show_fname(s, file); + } + spin_unlock(&nf->fi_lock); + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); + return 0; +} + +static int nfs4_show_layout(struct seq_file *s, struct nfs4_stid *st) +{ + struct nfs4_layout_stateid *ls; + struct nfsd_file *file; + + ls = container_of(st, struct nfs4_layout_stateid, ls_stid); + + seq_puts(s, "- "); + nfs4_show_stateid(s, &st->sc_stateid); + seq_puts(s, ": { type: layout"); + + /* XXX: What else would be useful? */ + + spin_lock(&ls->ls_stid.sc_file->fi_lock); + file = ls->ls_file; + if (file) { + seq_puts(s, ", "); + nfs4_show_superblock(s, file); + seq_puts(s, ", "); + nfs4_show_fname(s, file); + } + spin_unlock(&ls->ls_stid.sc_file->fi_lock); + if (st->sc_status & SC_STATUS_ADMIN_REVOKED) + seq_puts(s, ", admin-revoked"); + seq_puts(s, " }\n"); + + return 0; +} + +static int states_show(struct seq_file *s, void *v) +{ + struct nfs4_stid *st = v; + + switch (st->sc_type) { + case SC_TYPE_OPEN: + return nfs4_show_open(s, st); + case SC_TYPE_LOCK: + return nfs4_show_lock(s, st); + case SC_TYPE_DELEG: + return nfs4_show_deleg(s, st); + case SC_TYPE_LAYOUT: + return nfs4_show_layout(s, st); + default: + return 0; /* XXX: or SEQ_SKIP? */ + } + /* XXX: copy stateids? */ +} + +static struct seq_operations states_seq_ops = { + .start = states_start, + .next = states_next, + .stop = states_stop, + .show = states_show +}; + +static int client_states_open(struct inode *inode, struct file *file) +{ + struct seq_file *s; + struct nfs4_client *clp; + int ret; + + clp = get_nfsdfs_clp(inode); + if (!clp) + return -ENXIO; + + ret = seq_open(file, &states_seq_ops); + if (ret) + return ret; + s = file->private_data; + s->private = clp; + return 0; +} + +static int client_opens_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + struct nfs4_client *clp = m->private; + + /* XXX: alternatively, we could get/drop in seq start/stop */ + drop_client(clp); + return seq_release(inode, file); +} + +static const struct file_operations client_states_fops = { + .open = client_states_open, + .read = seq_read, + .llseek = seq_lseek, + .release = client_opens_release, +}; + +/* + * Normally we refuse to destroy clients that are in use, but here the + * administrator is telling us to just do it. We also want to wait + * so the caller has a guarantee that the client's locks are gone by + * the time the write returns: + */ +static void force_expire_client(struct nfs4_client *clp) +{ + struct nfsd_net *nn = net_generic(clp->net, nfsd_net_id); + bool already_expired; + + trace_nfsd_clid_admin_expired(&clp->cl_clientid); + + spin_lock(&nn->client_lock); + clp->cl_time = 0; + spin_unlock(&nn->client_lock); + + wait_event(expiry_wq, atomic_read(&clp->cl_rpc_users) == 0); + spin_lock(&nn->client_lock); + already_expired = list_empty(&clp->cl_lru); + if (!already_expired) + unhash_client_locked(clp); + spin_unlock(&nn->client_lock); + + if (!already_expired) + expire_client(clp); + else + wait_event(expiry_wq, clp->cl_nfsd_dentry == NULL); +} + +static ssize_t client_ctl_write(struct file *file, const char __user *buf, + size_t size, loff_t *pos) +{ + char *data; + struct nfs4_client *clp; + + data = simple_transaction_get(file, buf, size); + if (IS_ERR(data)) + return PTR_ERR(data); + if (size != 7 || 0 != memcmp(data, "expire\n", 7)) + return -EINVAL; + clp = get_nfsdfs_clp(file_inode(file)); + if (!clp) + return -ENXIO; + force_expire_client(clp); + drop_client(clp); + return 7; +} + +static const struct file_operations client_ctl_fops = { + .write = client_ctl_write, + .release = simple_transaction_release, +}; + +static const struct tree_descr client_files[] = { + [0] = {"info", &client_info_fops, S_IRUSR}, + [1] = {"states", &client_states_fops, S_IRUSR}, + [2] = {"ctl", &client_ctl_fops, S_IWUSR}, + [3] = {""}, +}; + +static int +nfsd4_cb_recall_any_done(struct nfsd4_callback *cb, + struct rpc_task *task) +{ + trace_nfsd_cb_recall_any_done(cb, task); + switch (task->tk_status) { + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; + default: + return 1; + } +} + +static void +nfsd4_cb_recall_any_release(struct nfsd4_callback *cb) +{ + struct nfs4_client *clp = cb->cb_clp; + + drop_client(clp); +} + +static int +nfsd4_cb_getattr_done(struct nfsd4_callback *cb, struct rpc_task *task) +{ + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + struct nfs4_delegation *dp = + container_of(ncf, struct nfs4_delegation, dl_cb_fattr); + + trace_nfsd_cb_getattr_done(&dp->dl_stid.sc_stateid, task); + ncf->ncf_cb_status = task->tk_status; + switch (task->tk_status) { + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; + default: + return 1; + } +} + +static void +nfsd4_cb_getattr_release(struct nfsd4_callback *cb) +{ + struct nfs4_cb_fattr *ncf = + container_of(cb, struct nfs4_cb_fattr, ncf_getattr); + struct nfs4_delegation *dp = + container_of(ncf, struct nfs4_delegation, dl_cb_fattr); + + nfs4_put_stid(&dp->dl_stid); +} + +static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = { + .done = nfsd4_cb_recall_any_done, + .release = nfsd4_cb_recall_any_release, + .opcode = OP_CB_RECALL_ANY, +}; + +static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = { + .done = nfsd4_cb_getattr_done, + .release = nfsd4_cb_getattr_release, + .opcode = OP_CB_GETATTR, +}; + +static void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf) +{ + struct nfs4_delegation *dp = + container_of(ncf, struct nfs4_delegation, dl_cb_fattr); + + if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &ncf->ncf_getattr.cb_flags)) + return; + + /* set to proper status when nfsd4_cb_getattr_done runs */ + ncf->ncf_cb_status = NFS4ERR_IO; + + /* ensure that wake_bit is done when RUNNING is cleared */ + set_bit(NFSD4_CALLBACK_WAKE, &ncf->ncf_getattr.cb_flags); + + refcount_inc(&dp->dl_stid.sc_count); + nfsd4_run_cb(&ncf->ncf_getattr); +} + static struct nfs4_client *create_client(struct xdr_netobj name, struct svc_rqst *rqstp, nfs4_verifier *verf) { @@ -2185,8 +3271,10 @@ static struct nfs4_client *create_client(struct xdr_netobj name, struct sockaddr *sa = svc_addr(rqstp); int ret; struct net *net = SVC_NET(rqstp); + struct nfsd_net *nn = net_generic(net, nfsd_net_id); + struct dentry *dentries[ARRAY_SIZE(client_files)]; - clp = alloc_client(name); + clp = alloc_client(name, nn); if (clp == NULL) return NULL; @@ -2195,13 +3283,31 @@ static struct nfs4_client *create_client(struct xdr_netobj name, free_client(clp); return NULL; } + gen_clid(clp, nn); + kref_init(&clp->cl_nfsdfs.cl_ref); nfsd4_init_cb(&clp->cl_cb_null, clp, NULL, NFSPROC4_CLNT_CB_NULL); - clp->cl_time = get_seconds(); - clear_bit(0, &clp->cl_cb_slot_busy); + clp->cl_time = ktime_get_boottime_seconds(); copy_verf(clp, verf); - rpc_copy_addr((struct sockaddr *) &clp->cl_addr, sa); + memcpy(&clp->cl_addr, sa, sizeof(struct sockaddr_storage)); clp->cl_cb_session = NULL; clp->net = net; + clp->cl_nfsd_dentry = nfsd_client_mkdir( + nn, &clp->cl_nfsdfs, + clp->cl_clientid.cl_id - nn->clientid_base, + client_files, dentries); + clp->cl_nfsd_info_dentry = dentries[0]; + if (!clp->cl_nfsd_dentry) { + free_client(clp); + return NULL; + } + clp->cl_ra = kzalloc(sizeof(*clp->cl_ra), GFP_KERNEL); + if (!clp->cl_ra) { + free_client(clp); + return NULL; + } + clp->cl_ra_time = 0; + nfsd4_init_cb(&clp->cl_ra->ra_cb, clp, &nfsd4_cb_recall_any_ops, + NFSPROC4_CLNT_CB_RECALL_ANY); return clp; } @@ -2268,11 +3374,11 @@ move_to_confirmed(struct nfs4_client *clp) lockdep_assert_held(&nn->client_lock); - dprintk("NFSD: move_to_confirm nfs4_client %p\n", clp); list_move(&clp->cl_idhash, &nn->conf_id_hashtbl[idhashval]); rb_erase(&clp->cl_namenode, &nn->unconf_name_tree); add_clp_to_name_tree(clp, &nn->conf_name_tree); set_bit(NFSD4_CLIENT_CONFIRMED, &clp->cl_flags); + trace_nfsd_clid_confirmed(&clp->cl_clientid); renew_client_locked(clp); } @@ -2362,14 +3468,12 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_r conn->cb_prog = se->se_callback_prog; conn->cb_ident = se->se_callback_ident; memcpy(&conn->cb_saddr, &rqstp->rq_daddr, rqstp->rq_daddrlen); + trace_nfsd_cb_args(clp, conn); return; out_err: conn->cb_addr.ss_family = AF_UNSPEC; conn->cb_addrlen = 0; - dprintk("NFSD: this client (clientid %08x/%08x) " - "will not receive delegations\n", - clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id); - + trace_nfsd_cb_nodelegs(clp); return; } @@ -2379,11 +3483,24 @@ out_err: static void nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) { - struct xdr_buf *buf = resp->xdr.buf; + struct xdr_buf *buf = resp->xdr->buf; struct nfsd4_slot *slot = resp->cstate.slot; unsigned int base; - dprintk("--> %s slot %p\n", __func__, slot); + /* + * RFC 5661 Section 2.10.6.1.2: + * + * Any time SEQUENCE ... returns an error ... [t]he replier MUST NOT + * modify the reply cache entry for the slot whenever an error is + * returned from SEQUENCE ... + * + * Because nfsd4_store_cache_entry is called only by + * nfsd4_sequence_done(), nfsd4_store_cache_entry() is called only + * when a SEQUENCE operation was part of the COMPOUND. + * nfs41_check_op_ordering() ensures SEQUENCE is the first op. + */ + if (resp->opcnt == 1 && resp->cstate.status != nfs_ok) + return; slot->sl_flags |= NFSD4_SLOT_INITIALIZED; slot->sl_opcnt = resp->opcnt; @@ -2391,7 +3508,7 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) free_svc_cred(&slot->sl_cred); copy_cred(&slot->sl_cred, &resp->rqstp->rq_cred); - if (!nfsd4_cache_this(resp)) { + if (!(resp->cstate.slot->sl_flags & NFSD4_SLOT_CACHETHIS)) { slot->sl_flags &= ~NFSD4_SLOT_CACHED; return; } @@ -2406,41 +3523,6 @@ nfsd4_store_cache_entry(struct nfsd4_compoundres *resp) } /* - * Encode the replay sequence operation from the slot values. - * If cachethis is FALSE encode the uncached rep error on the next - * operation which sets resp->p and increments resp->opcnt for - * nfs4svc_encode_compoundres. - * - */ -static __be32 -nfsd4_enc_sequence_replay(struct nfsd4_compoundargs *args, - struct nfsd4_compoundres *resp) -{ - struct nfsd4_op *op; - struct nfsd4_slot *slot = resp->cstate.slot; - - /* Encode the replayed sequence operation */ - op = &args->ops[resp->opcnt - 1]; - nfsd4_encode_operation(resp, op); - - if (slot->sl_flags & NFSD4_SLOT_CACHED) - return op->status; - if (args->opcnt == 1) { - /* - * The original operation wasn't a solo sequence--we - * always cache those--so this retry must not match the - * original: - */ - op->status = nfserr_seq_false_retry; - } else { - op = &args->ops[resp->opcnt++]; - op->status = nfserr_retry_uncached_rep; - nfsd4_encode_operation(resp, op); - } - return op->status; -} - -/* * The sequence operation is not cached because we can use the slot and * session values. */ @@ -2448,17 +3530,30 @@ static __be32 nfsd4_replay_cache_entry(struct nfsd4_compoundres *resp, struct nfsd4_sequence *seq) { + struct nfsd4_compoundargs *args = resp->rqstp->rq_argp; struct nfsd4_slot *slot = resp->cstate.slot; - struct xdr_stream *xdr = &resp->xdr; + struct xdr_stream *xdr = resp->xdr; __be32 *p; - __be32 status; dprintk("--> %s slot %p\n", __func__, slot); - status = nfsd4_enc_sequence_replay(resp->rqstp->rq_argp, resp); - if (status) - return status; + /* Always encode the SEQUENCE response. */ + nfsd4_encode_operation(resp, &args->ops[0]); + if (args->opcnt == 1) + /* A solo SEQUENCE - nothing was cached */ + return args->ops[0].status; + + if (!(slot->sl_flags & NFSD4_SLOT_CACHED)) { + /* We weren't asked to cache this. */ + struct nfsd4_op *op; + + op = &args->ops[resp->opcnt++]; + op->status = nfserr_retry_uncached_rep; + nfsd4_encode_operation(resp, op); + return op->status; + } + /* return reply from cache */ p = xdr_reserve_space(xdr, slot->sl_datalen); if (!p) { WARN_ON_ONCE(1); @@ -2509,7 +3604,22 @@ static bool client_has_state(struct nfs4_client *clp) #endif || !list_empty(&clp->cl_delegations) || !list_empty(&clp->cl_sessions) - || !list_empty(&clp->async_copies); + || nfsd4_has_active_async_copies(clp); +} + +static __be32 copy_impl_id(struct nfs4_client *clp, + struct nfsd4_exchange_id *exid) +{ + if (!exid->nii_domain.data) + return 0; + xdr_netobj_dup(&clp->cl_nii_domain, &exid->nii_domain, GFP_KERNEL); + if (!clp->cl_nii_domain.data) + return nfserr_jukebox; + xdr_netobj_dup(&clp->cl_nii_name, &exid->nii_name, GFP_KERNEL); + if (!clp->cl_nii_name.data) + return nfserr_jukebox; + clp->cl_nii_time = exid->nii_time; + return 0; } __be32 @@ -2528,16 +3638,25 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, rpc_ntop(sa, addr_str, sizeof(addr_str)); dprintk("%s rqstp=%p exid=%p clname.len=%u clname.data=%p " - "ip_addr=%s flags %x, spa_how %d\n", + "ip_addr=%s flags %x, spa_how %u\n", __func__, rqstp, exid, exid->clname.len, exid->clname.data, addr_str, exid->flags, exid->spa_how); + exid->server_impl_name = kasprintf(GFP_KERNEL, "%s %s %s %s", + utsname()->sysname, utsname()->release, + utsname()->version, utsname()->machine); + if (!exid->server_impl_name) + return nfserr_jukebox; + if (exid->flags & ~EXCHGID4_FLAG_MASK_A) return nfserr_inval; new = create_client(exid->clname, rqstp, &verf); if (new == NULL) return nfserr_jukebox; + status = copy_impl_id(new, exid); + if (status) + goto out_nolock; switch (exid->spa_how) { case SP4_MACH_CRED: @@ -2572,10 +3691,12 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out_nolock; } new->cl_mach_cred = true; + break; case SP4_NONE: break; default: /* checked by xdr code */ WARN_ON_ONCE(1); + fallthrough; case SP4_SSV: status = nfserr_encr_alg_unsupp; goto out_nolock; @@ -2607,20 +3728,24 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } /* case 6 */ exid->flags |= EXCHGID4_FLAG_CONFIRMED_R; + trace_nfsd_clid_confirmed_r(conf); goto out_copy; } if (!creds_match) { /* case 3 */ if (client_has_state(conf)) { status = nfserr_clid_inuse; + trace_nfsd_clid_cred_mismatch(conf, rqstp); goto out; } goto out_new; } if (verfs_match) { /* case 2 */ conf->cl_exchange_flags |= EXCHGID4_FLAG_CONFIRMED_R; + trace_nfsd_clid_confirmed_r(conf); goto out_copy; } /* case 5, client reboot */ + trace_nfsd_clid_verf_mismatch(conf, rqstp, &verf); conf = NULL; goto out_new; } @@ -2630,22 +3755,27 @@ nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } - unconf = find_unconfirmed_client_by_name(&exid->clname, nn); + unconf = find_unconfirmed_client_by_name(&exid->clname, nn); if (unconf) /* case 4, possible retry or client restart */ unhash_client_locked(unconf); - /* case 1 (normal case) */ + /* case 1, new owner ID */ + trace_nfsd_clid_fresh(new); + out_new: if (conf) { status = mark_client_expired_locked(conf); if (status) goto out; + trace_nfsd_clid_replaced(&conf->cl_clientid); } new->cl_minorversion = cstate->minorversion; new->cl_spo_must_allow.u.words[0] = exid->spo_must_allow[0]; new->cl_spo_must_allow.u.words[1] = exid->spo_must_allow[1]; - gen_clid(new, nn); + /* Contrived initial CREATE_SESSION response */ + new->cl_cs_slot.sl_status = nfserr_seq_misordered; + add_to_unconfirmed(new); swap(new, conf); out_copy: @@ -2655,6 +3785,23 @@ out_copy: exid->seqid = conf->cl_cs_slot.sl_seqid + 1; nfsd4_set_ex_flags(conf, exid); + exid->nii_domain.len = sizeof("kernel.org") - 1; + exid->nii_domain.data = "kernel.org"; + + /* + * Note that RFC 8881 places no length limit on + * nii_name, but this implementation permits no + * more than NFS4_OPAQUE_LIMIT bytes. + */ + exid->nii_name.len = strlen(exid->server_impl_name); + if (exid->nii_name.len > NFS4_OPAQUE_LIMIT) + exid->nii_name.len = NFS4_OPAQUE_LIMIT; + exid->nii_name.data = exid->server_impl_name; + + /* just send zeros - the date is in nii_name */ + exid->nii_time.tv_sec = 0; + exid->nii_time.tv_nsec = 0; + dprintk("nfsd4_exchange_id seqid %d flags %x\n", conf->cl_cs_slot.sl_seqid, conf->cl_exchange_flags); status = nfs_ok; @@ -2664,19 +3811,25 @@ out: out_nolock: if (new) expire_client(new); - if (unconf) + if (unconf) { + trace_nfsd_clid_expire_unconf(&unconf->cl_clientid); expire_client(unconf); + } return status; } -static __be32 -check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse) +void +nfsd4_exchange_id_release(union nfsd4_op_u *u) { - dprintk("%s enter. seqid %d slot_seqid %d\n", __func__, seqid, - slot_seqid); + struct nfsd4_exchange_id *exid = &u->exchange_id; + + kfree(exid->server_impl_name); +} +static __be32 check_slot_seqid(u32 seqid, u32 slot_seqid, u8 flags) +{ /* The slot is in use, and no response has been sent. */ - if (slot_inuse) { + if (flags & NFSD4_SLOT_INUSE) { if (seqid == slot_seqid) return nfserr_jukebox; else @@ -2685,6 +3838,8 @@ check_slot_seqid(u32 seqid, u32 slot_seqid, int slot_inuse) /* Note unsigned 32-bit arithmetic handles wraparound: */ if (likely(seqid == slot_seqid + 1)) return nfs_ok; + if ((flags & NFSD4_SLOT_REUSED) && seqid == 1) + return nfs_ok; if (seqid == slot_seqid) return nfserr_replay_cache; return nfserr_seq_misordered; @@ -2743,17 +3898,6 @@ static __be32 check_forechannel_attrs(struct nfsd4_channel_attrs *ca, struct nfs ca->maxresp_cached = min_t(u32, ca->maxresp_cached, NFSD_SLOT_CACHE_SIZE + NFSD_MIN_HDR_SEQ_SZ); ca->maxreqs = min_t(u32, ca->maxreqs, NFSD_MAX_SLOTS_PER_SESSION); - /* - * Note decreasing slot size below client's request may make it - * difficult for client to function correctly, whereas - * decreasing the number of slots will (just?) affect - * performance. When short on memory we therefore prefer to - * decrease number of slots instead of their size. Clients that - * request larger slots than they need will get poor results: - */ - ca->maxreqs = nfsd4_get_drc_mem(ca); - if (!ca->maxreqs) - return nfserr_jukebox; return nfs_ok; } @@ -2814,10 +3958,10 @@ nfsd4_create_session(struct svc_rqst *rqstp, struct nfsd4_create_session *cr_ses = &u->create_session; struct sockaddr *sa = svc_addr(rqstp); struct nfs4_client *conf, *unconf; + struct nfsd4_clid_slot *cs_slot; struct nfs4_client *old = NULL; struct nfsd4_session *new; struct nfsd4_conn *conn; - struct nfsd4_clid_slot *cs_slot = NULL; __be32 status = 0; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); @@ -2831,93 +3975,120 @@ nfsd4_create_session(struct svc_rqst *rqstp, return status; status = check_backchannel_attrs(&cr_ses->back_channel); if (status) - goto out_release_drc_mem; + goto out_err; status = nfserr_jukebox; new = alloc_session(&cr_ses->fore_channel, &cr_ses->back_channel); if (!new) - goto out_release_drc_mem; + goto out_err; conn = alloc_conn_from_crses(rqstp, cr_ses); if (!conn) goto out_free_session; spin_lock(&nn->client_lock); + + /* RFC 8881 Section 18.36.4 Phase 1: Client record look-up. */ unconf = find_unconfirmed_client(&cr_ses->clientid, true, nn); conf = find_confirmed_client(&cr_ses->clientid, true, nn); - WARN_ON_ONCE(conf && unconf); + if (!conf && !unconf) { + status = nfserr_stale_clientid; + goto out_free_conn; + } + + /* RFC 8881 Section 18.36.4 Phase 2: Sequence ID processing. */ + if (conf) { + cs_slot = &conf->cl_cs_slot; + trace_nfsd_slot_seqid_conf(conf, cr_ses); + } else { + cs_slot = &unconf->cl_cs_slot; + trace_nfsd_slot_seqid_unconf(unconf, cr_ses); + } + status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); + switch (status) { + case nfs_ok: + cs_slot->sl_seqid++; + cr_ses->seqid = cs_slot->sl_seqid; + break; + case nfserr_replay_cache: + status = nfsd4_replay_create_session(cr_ses, cs_slot); + fallthrough; + case nfserr_jukebox: + /* The server MUST NOT cache NFS4ERR_DELAY */ + goto out_free_conn; + default: + goto out_cache_error; + } + /* RFC 8881 Section 18.36.4 Phase 3: Client ID confirmation. */ if (conf) { status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(conf, rqstp)) - goto out_free_conn; - cs_slot = &conf->cl_cs_slot; - status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); - if (status) { - if (status == nfserr_replay_cache) - status = nfsd4_replay_create_session(cr_ses, cs_slot); - goto out_free_conn; - } - } else if (unconf) { + goto out_cache_error; + } else { + status = nfserr_clid_inuse; if (!same_creds(&unconf->cl_cred, &rqstp->rq_cred) || !rpc_cmp_addr(sa, (struct sockaddr *) &unconf->cl_addr)) { - status = nfserr_clid_inuse; - goto out_free_conn; + trace_nfsd_clid_cred_mismatch(unconf, rqstp); + goto out_cache_error; } status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(unconf, rqstp)) - goto out_free_conn; - cs_slot = &unconf->cl_cs_slot; - status = check_slot_seqid(cr_ses->seqid, cs_slot->sl_seqid, 0); - if (status) { - /* an unconfirmed replay returns misordered */ - status = nfserr_seq_misordered; - goto out_free_conn; - } + goto out_cache_error; old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { status = mark_client_expired_locked(old); - if (status) { - old = NULL; - goto out_free_conn; - } + if (status) + goto out_expired_error; + trace_nfsd_clid_replaced(&old->cl_clientid); } move_to_confirmed(unconf); conf = unconf; - } else { - status = nfserr_stale_clientid; - goto out_free_conn; } + + /* RFC 8881 Section 18.36.4 Phase 4: Session creation. */ status = nfs_ok; /* Persistent sessions are not supported */ cr_ses->flags &= ~SESSION4_PERSIST; /* Upshifting from TCP to RDMA is not supported */ cr_ses->flags &= ~SESSION4_RDMA; + /* Report the correct number of backchannel slots */ + cr_ses->back_channel.maxreqs = new->se_cb_highest_slot + 1; init_session(rqstp, new, conf, cr_ses); nfsd4_get_session_locked(new); memcpy(cr_ses->sessionid.data, new->se_sessionid.data, NFS4_MAX_SESSIONID_LEN); - cs_slot->sl_seqid++; - cr_ses->seqid = cs_slot->sl_seqid; /* cache solo and embedded create sessions under the client_lock */ nfsd4_cache_create_session(cr_ses, cs_slot, status); spin_unlock(&nn->client_lock); + if (conf == unconf) + fsnotify_dentry(conf->cl_nfsd_info_dentry, FS_MODIFY); /* init connection and backchannel */ nfsd4_init_conn(rqstp, conn, new); nfsd4_put_session(new); if (old) expire_client(old); return status; + +out_expired_error: + /* + * Revert the slot seq_nr change so the server will process + * the client's resend instead of returning a cached response. + */ + if (status == nfserr_jukebox) { + cs_slot->sl_seqid--; + cr_ses->seqid = cs_slot->sl_seqid; + goto out_free_conn; + } +out_cache_error: + nfsd4_cache_create_session(cr_ses, cs_slot, status); out_free_conn: spin_unlock(&nn->client_lock); free_conn(conn); - if (old) - expire_client(old); out_free_session: __free_session(new); -out_release_drc_mem: - nfsd4_put_drc_mem(&cr_ses->fore_channel); +out_err: return status; } @@ -2931,7 +4102,7 @@ static __be32 nfsd4_map_bcts_dir(u32 *dir) case NFS4_CDFC4_BACK_OR_BOTH: *dir = NFS4_CDFC4_BOTH; return nfs_ok; - }; + } return nfserr_inval; } @@ -2957,6 +4128,47 @@ __be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, return nfs_ok; } +static struct nfsd4_conn *__nfsd4_find_conn(struct svc_xprt *xpt, struct nfsd4_session *s) +{ + struct nfsd4_conn *c; + + list_for_each_entry(c, &s->se_conns, cn_persession) { + if (c->cn_xprt == xpt) { + return c; + } + } + return NULL; +} + +static __be32 nfsd4_match_existing_connection(struct svc_rqst *rqst, + struct nfsd4_session *session, u32 req, struct nfsd4_conn **conn) +{ + struct nfs4_client *clp = session->se_client; + struct svc_xprt *xpt = rqst->rq_xprt; + struct nfsd4_conn *c; + __be32 status; + + /* Following the last paragraph of RFC 5661 Section 18.34.3: */ + spin_lock(&clp->cl_lock); + c = __nfsd4_find_conn(xpt, session); + if (!c) + status = nfserr_noent; + else if (req == c->cn_flags) + status = nfs_ok; + else if (req == NFS4_CDFC4_FORE_OR_BOTH && + c->cn_flags != NFS4_CDFC4_BACK) + status = nfs_ok; + else if (req == NFS4_CDFC4_BACK_OR_BOTH && + c->cn_flags != NFS4_CDFC4_FORE) + status = nfs_ok; + else + status = nfserr_inval; + spin_unlock(&clp->cl_lock); + if (status == nfs_ok && conn) + *conn = c; + return status; +} + __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) @@ -2978,6 +4190,17 @@ __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp, status = nfserr_wrong_cred; if (!nfsd4_mach_creds_match(session->se_client, rqstp)) goto out; + status = nfsd4_match_existing_connection(rqstp, session, + bcts->dir, &conn); + if (status == nfs_ok) { + if (bcts->dir == NFS4_CDFC4_FORE_OR_BOTH || + bcts->dir == NFS4_CDFC4_BACK) + conn->cn_flags |= NFS4_CDFC4_BACK; + nfsd4_probe_callback(session->se_client); + goto out; + } + if (status == nfserr_inval) + goto out; status = nfsd4_map_bcts_dir(&bcts->dir); if (status) goto out; @@ -3043,18 +4266,6 @@ out: return status; } -static struct nfsd4_conn *__nfsd4_find_conn(struct svc_xprt *xpt, struct nfsd4_session *s) -{ - struct nfsd4_conn *c; - - list_for_each_entry(c, &s->se_conns, cn_persession) { - if (c->cn_xprt == xpt) { - return c; - } - } - return NULL; -} - static __be32 nfsd4_sequence_check_conn(struct nfsd4_conn *new, struct nfsd4_session *ses) { struct nfs4_client *clp = ses->se_client; @@ -3106,12 +4317,17 @@ static bool replay_matches_cache(struct svc_rqst *rqstp, (bool)seq->cachethis) return false; /* - * If there's an error than the reply can have fewer ops than - * the call. But if we cached a reply with *more* ops than the - * call you're sending us now, then this new call is clearly not - * really a replay of the old one: + * If there's an error then the reply can have fewer ops than + * the call. */ - if (slot->sl_opcnt < argp->opcnt) + if (slot->sl_opcnt < argp->opcnt && !slot->sl_status) + return false; + /* + * But if we cached a reply with *more* ops than the call you're + * sending us now, then this new call is clearly not really a + * replay of the old one: + */ + if (slot->sl_opcnt > argp->opcnt) return false; /* This is the only check explicitly called by spec: */ if (!same_creds(&rqstp->rq_cred, &slot->sl_cred)) @@ -3125,13 +4341,43 @@ static bool replay_matches_cache(struct svc_rqst *rqstp, return true; } +/* + * Note that the response is constructed here both for the case + * of a new SEQUENCE request and for a replayed SEQUENCE request. + * We do not cache SEQUENCE responses as SEQUENCE is idempotent. + */ +static void nfsd4_construct_sequence_response(struct nfsd4_session *session, + struct nfsd4_sequence *seq) +{ + struct nfs4_client *clp = session->se_client; + + seq->maxslots_response = max(session->se_target_maxslots, + seq->maxslots); + seq->target_maxslots = session->se_target_maxslots; + + switch (clp->cl_cb_state) { + case NFSD4_CB_DOWN: + seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; + break; + case NFSD4_CB_FAULT: + seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; + break; + default: + seq->status_flags = 0; + } + if (!list_empty(&clp->cl_revoked)) + seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; + if (atomic_read(&clp->cl_admin_revoked)) + seq->status_flags |= SEQ4_STATUS_ADMIN_STATE_REVOKED; +} + __be32 nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_sequence *seq = &u->sequence; struct nfsd4_compoundres *resp = rqstp->rq_resp; - struct xdr_stream *xdr = &resp->xdr; + struct xdr_stream *xdr = resp->xdr; struct nfsd4_session *session; struct nfs4_client *clp; struct nfsd4_slot *slot; @@ -3170,16 +4416,14 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (seq->slotid >= session->se_fchannel.maxreqs) goto out_put_session; - slot = session->se_slots[seq->slotid]; + slot = xa_load(&session->se_slots, seq->slotid); dprintk("%s: slotid %d\n", __func__, seq->slotid); - /* We do not negotiate the number of slots yet, so set the - * maxslots to the session maxreqs which is used to encode - * sr_highest_slotid and the sr_target_slot id to maxslots */ - seq->maxslots = session->se_fchannel.maxreqs; + trace_nfsd_slot_seqid_sequence(clp, seq, slot); + + nfsd4_construct_sequence_response(session, seq); - status = check_slot_seqid(seq->seqid, slot->sl_seqid, - slot->sl_flags & NFSD4_SLOT_INUSE); + status = check_slot_seqid(seq->seqid, slot->sl_seqid, slot->sl_flags); if (status == nfserr_replay_cache) { status = nfserr_seq_misordered; if (!(slot->sl_flags & NFSD4_SLOT_INITIALIZED)) @@ -3204,6 +4448,12 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out_put_session; + if (session->se_target_maxslots < session->se_fchannel.maxreqs && + slot->sl_generation == session->se_slot_gen && + seq->maxslots <= session->se_target_maxslots) + /* Client acknowledged our reduce maxreqs */ + free_session_slots(session, session->se_target_maxslots); + buflen = (seq->cachethis) ? session->se_fchannel.maxresp_cached : session->se_fchannel.maxresp_sz; @@ -3211,12 +4461,14 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nfserr_rep_too_big; if (xdr_restrict_buflen(xdr, buflen - rqstp->rq_auth_slack)) goto out_put_session; - svc_reserve(rqstp, buflen); + svc_reserve_auth(rqstp, buflen); status = nfs_ok; - /* Success! bump slot seqid */ + /* Success! accept new slot seqid */ slot->sl_seqid = seq->seqid; + slot->sl_flags &= ~NFSD4_SLOT_REUSED; slot->sl_flags |= NFSD4_SLOT_INUSE; + slot->sl_generation = session->se_slot_gen; if (seq->cachethis) slot->sl_flags |= NFSD4_SLOT_CACHETHIS; else @@ -3226,19 +4478,49 @@ nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, cstate->session = session; cstate->clp = clp; -out: - switch (clp->cl_cb_state) { - case NFSD4_CB_DOWN: - seq->status_flags = SEQ4_STATUS_CB_PATH_DOWN; - break; - case NFSD4_CB_FAULT: - seq->status_flags = SEQ4_STATUS_BACKCHANNEL_FAULT; - break; - default: - seq->status_flags = 0; + /* + * If the client ever uses the highest available slot, + * gently try to allocate another 20%. This allows + * fairly quick growth without grossly over-shooting what + * the client might use. + */ + if (seq->slotid == session->se_fchannel.maxreqs - 1 && + session->se_target_maxslots >= session->se_fchannel.maxreqs && + session->se_fchannel.maxreqs < NFSD_MAX_SLOTS_PER_SESSION) { + int s = session->se_fchannel.maxreqs; + int cnt = DIV_ROUND_UP(s, 5); + void *prev_slot; + + do { + /* + * GFP_NOWAIT both allows allocation under a + * spinlock, and only succeeds if there is + * plenty of memory. + */ + slot = nfsd4_alloc_slot(&session->se_fchannel, s, + GFP_NOWAIT); + prev_slot = xa_load(&session->se_slots, s); + if (xa_is_value(prev_slot) && slot) { + slot->sl_seqid = xa_to_value(prev_slot); + slot->sl_flags |= NFSD4_SLOT_REUSED; + } + if (slot && + !xa_is_err(xa_store(&session->se_slots, s, slot, + GFP_NOWAIT))) { + s += 1; + session->se_fchannel.maxreqs = s; + atomic_add(s - session->se_target_maxslots, + &nfsd_total_target_slots); + session->se_target_maxslots = s; + } else { + kfree(slot); + slot = NULL; + } + } while (slot && --cnt > 0); } - if (!list_empty(&clp->cl_revoked)) - seq->status_flags |= SEQ4_STATUS_RECALLABLE_STATE_REVOKED; + +out: + trace_nfsd_seq4_status(rqstp, seq); out_no_session: if (conn) free_conn(conn); @@ -3301,6 +4583,7 @@ nfsd4_destroy_clientid(struct svc_rqst *rqstp, status = nfserr_wrong_cred; goto out; } + trace_nfsd_clid_destroyed(&clp->cl_clientid); unhash_client_locked(clp); out: spin_unlock(&nn->client_lock); @@ -3314,6 +4597,7 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_reclaim_complete *rc = &u->reclaim_complete; + struct nfs4_client *clp = cstate->clp; __be32 status = 0; if (rc->rca_one_fs) { @@ -3327,12 +4611,11 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, } status = nfserr_complete_already; - if (test_and_set_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, - &cstate->session->se_client->cl_flags)) + if (test_and_set_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &clp->cl_flags)) goto out; status = nfserr_stale_clientid; - if (is_client_expired(cstate->session->se_client)) + if (is_client_expired(clp)) /* * The following error isn't really legal. * But we only get here if the client just explicitly @@ -3343,7 +4626,9 @@ nfsd4_reclaim_complete(struct svc_rqst *rqstp, goto out; status = nfs_ok; - nfsd4_client_record_create(cstate->session->se_client); + trace_nfsd_clid_reclaim_complete(&clp->cl_clientid); + nfsd4_client_record_create(clp); + inc_reclaim_complete(clp); out: return status; } @@ -3363,32 +4648,29 @@ nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, new = create_client(clname, rqstp, &clverifier); if (new == NULL) return nfserr_jukebox; - /* Cases below refer to rfc 3530 section 14.2.33: */ spin_lock(&nn->client_lock); conf = find_confirmed_client_by_name(&clname, nn); if (conf && client_has_state(conf)) { - /* case 0: */ status = nfserr_clid_inuse; if (clp_used_exchangeid(conf)) goto out; if (!same_creds(&conf->cl_cred, &rqstp->rq_cred)) { - char addr_str[INET6_ADDRSTRLEN]; - rpc_ntop((struct sockaddr *) &conf->cl_addr, addr_str, - sizeof(addr_str)); - dprintk("NFSD: setclientid: string in use by client " - "at %s\n", addr_str); + trace_nfsd_clid_cred_mismatch(conf, rqstp); goto out; } } unconf = find_unconfirmed_client_by_name(&clname, nn); if (unconf) unhash_client_locked(unconf); - if (conf && same_verf(&conf->cl_verifier, &clverifier)) { - /* case 1: probable callback update */ - copy_clid(new, conf); - gen_confirm(new, nn); - } else /* case 4 (new client) or cases 2, 3 (client reboot): */ - gen_clid(new, nn); + if (conf) { + if (same_verf(&conf->cl_verifier, &clverifier)) { + copy_clid(new, conf); + gen_confirm(new, nn); + } else + trace_nfsd_clid_verf_mismatch(conf, rqstp, + &clverifier); + } else + trace_nfsd_clid_fresh(new); new->cl_minorversion = 0; gen_callback(new, setclid, rqstp); add_to_unconfirmed(new); @@ -3401,12 +4683,13 @@ out: spin_unlock(&nn->client_lock); if (new) free_client(new); - if (unconf) + if (unconf) { + trace_nfsd_clid_expire_unconf(&unconf->cl_clientid); expire_client(unconf); + } return status; } - __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, @@ -3435,43 +4718,60 @@ nfsd4_setclientid_confirm(struct svc_rqst *rqstp, * Nevertheless, RFC 7530 recommends INUSE for this case: */ status = nfserr_clid_inuse; - if (unconf && !same_creds(&unconf->cl_cred, &rqstp->rq_cred)) + if (unconf && !same_creds(&unconf->cl_cred, &rqstp->rq_cred)) { + trace_nfsd_clid_cred_mismatch(unconf, rqstp); goto out; - if (conf && !same_creds(&conf->cl_cred, &rqstp->rq_cred)) + } + if (conf && !same_creds(&conf->cl_cred, &rqstp->rq_cred)) { + trace_nfsd_clid_cred_mismatch(conf, rqstp); goto out; - /* cases below refer to rfc 3530 section 14.2.34: */ + } if (!unconf || !same_verf(&confirm, &unconf->cl_confirm)) { if (conf && same_verf(&confirm, &conf->cl_confirm)) { - /* case 2: probable retransmit */ status = nfs_ok; - } else /* case 4: client hasn't noticed we rebooted yet? */ + } else status = nfserr_stale_clientid; goto out; } status = nfs_ok; - if (conf) { /* case 1: callback update */ - old = unconf; - unhash_client_locked(old); - nfsd4_change_callback(conf, &unconf->cl_cb_conn); - } else { /* case 3: normal case; new or rebooted client */ + if (conf) { + if (get_client_locked(conf) == nfs_ok) { + old = unconf; + unhash_client_locked(old); + nfsd4_change_callback(conf, &unconf->cl_cb_conn); + } else { + conf = NULL; + } + } + + if (!conf) { old = find_confirmed_client_by_name(&unconf->cl_name, nn); if (old) { status = nfserr_clid_inuse; if (client_has_state(old) && !same_creds(&unconf->cl_cred, - &old->cl_cred)) + &old->cl_cred)) { + old = NULL; goto out; + } status = mark_client_expired_locked(old); if (status) { old = NULL; goto out; } + trace_nfsd_clid_replaced(&old->cl_clientid); + } + status = get_client_locked(unconf); + if (status != nfs_ok) { + old = NULL; + goto out; } move_to_confirmed(unconf); conf = unconf; } - get_client_locked(conf); spin_unlock(&nn->client_lock); + if (conf == unconf) + fsnotify_dentry(conf->cl_nfsd_info_dentry, FS_MODIFY); nfsd4_probe_callback(conf); spin_lock(&nn->client_lock); put_client_renew_locked(conf); @@ -3488,27 +4788,27 @@ static struct nfs4_file *nfsd4_alloc_file(void) } /* OPEN Share state helper functions */ -static void nfsd4_init_file(struct knfsd_fh *fh, unsigned int hashval, - struct nfs4_file *fp) -{ - lockdep_assert_held(&state_lock); +static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp) +{ refcount_set(&fp->fi_ref, 1); spin_lock_init(&fp->fi_lock); INIT_LIST_HEAD(&fp->fi_stateids); INIT_LIST_HEAD(&fp->fi_delegations); INIT_LIST_HEAD(&fp->fi_clnt_odstate); - fh_copy_shallow(&fp->fi_fhandle, fh); + fh_copy_shallow(&fp->fi_fhandle, &fh->fh_handle); fp->fi_deleg_file = NULL; + fp->fi_rdeleg_file = NULL; fp->fi_had_conflict = false; fp->fi_share_deny = 0; memset(fp->fi_fds, 0, sizeof(fp->fi_fds)); memset(fp->fi_access, 0, sizeof(fp->fi_access)); + fp->fi_aliased = false; + fp->fi_inode = d_inode(fh->fh_dentry); #ifdef CONFIG_NFSD_PNFS INIT_LIST_HEAD(&fp->fi_lo_states); atomic_set(&fp->fi_lo_recalls, 0); #endif - hlist_add_head_rcu(&fp->fi_hash, &file_hashtbl[hashval]); } void @@ -3526,32 +4826,25 @@ nfsd4_free_slabs(void) int nfsd4_init_slabs(void) { - client_slab = kmem_cache_create("nfsd4_clients", - sizeof(struct nfs4_client), 0, 0, NULL); + client_slab = KMEM_CACHE(nfs4_client, 0); if (client_slab == NULL) goto out; - openowner_slab = kmem_cache_create("nfsd4_openowners", - sizeof(struct nfs4_openowner), 0, 0, NULL); + openowner_slab = KMEM_CACHE(nfs4_openowner, 0); if (openowner_slab == NULL) goto out_free_client_slab; - lockowner_slab = kmem_cache_create("nfsd4_lockowners", - sizeof(struct nfs4_lockowner), 0, 0, NULL); + lockowner_slab = KMEM_CACHE(nfs4_lockowner, 0); if (lockowner_slab == NULL) goto out_free_openowner_slab; - file_slab = kmem_cache_create("nfsd4_files", - sizeof(struct nfs4_file), 0, 0, NULL); + file_slab = KMEM_CACHE(nfs4_file, 0); if (file_slab == NULL) goto out_free_lockowner_slab; - stateid_slab = kmem_cache_create("nfsd4_stateids", - sizeof(struct nfs4_ol_stateid), 0, 0, NULL); + stateid_slab = KMEM_CACHE(nfs4_ol_stateid, 0); if (stateid_slab == NULL) goto out_free_file_slab; - deleg_slab = kmem_cache_create("nfsd4_delegations", - sizeof(struct nfs4_delegation), 0, 0, NULL); + deleg_slab = KMEM_CACHE(nfs4_delegation, 0); if (deleg_slab == NULL) goto out_free_stateid_slab; - odstate_slab = kmem_cache_create("nfsd4_odstate", - sizeof(struct nfs4_clnt_odstate), 0, 0, NULL); + odstate_slab = KMEM_CACHE(nfs4_clnt_odstate, 0); if (odstate_slab == NULL) goto out_free_deleg_slab; return 0; @@ -3569,25 +4862,79 @@ out_free_openowner_slab: out_free_client_slab: kmem_cache_destroy(client_slab); out: - dprintk("nfsd4: out of memory while initializing nfsv4\n"); return -ENOMEM; } +static unsigned long +nfsd4_state_shrinker_count(struct shrinker *shrink, struct shrink_control *sc) +{ + struct nfsd_net *nn = shrink->private_data; + long count; + + count = atomic_read(&nn->nfsd_courtesy_clients); + if (!count) + count = atomic_long_read(&num_delegations); + if (count) + queue_work(laundry_wq, &nn->nfsd_shrinker_work); + return (unsigned long)count; +} + +static unsigned long +nfsd4_state_shrinker_scan(struct shrinker *shrink, struct shrink_control *sc) +{ + return SHRINK_STOP; +} + +void +nfsd4_init_leases_net(struct nfsd_net *nn) +{ + struct sysinfo si; + u64 max_clients; + + nn->nfsd4_lease = 90; /* default lease time */ + nn->nfsd4_grace = 90; + nn->somebody_reclaimed = false; + nn->track_reclaim_completes = false; + nn->clverifier_counter = get_random_u32(); + nn->clientid_base = get_random_u32(); + nn->clientid_counter = nn->clientid_base + 1; + nn->s2s_cp_cl_id = nn->clientid_counter++; + + atomic_set(&nn->nfs4_client_count, 0); + si_meminfo(&si); + max_clients = (u64)si.totalram * si.mem_unit / (1024 * 1024 * 1024); + max_clients *= NFS4_CLIENTS_PER_GB; + nn->nfs4_max_clients = max_t(int, max_clients, NFS4_CLIENTS_PER_GB); + + atomic_set(&nn->nfsd_courtesy_clients, 0); +} + +enum rp_lock { + RP_UNLOCKED, + RP_LOCKED, + RP_UNHASHED, +}; + static void init_nfs4_replay(struct nfs4_replay *rp) { rp->rp_status = nfserr_serverfault; rp->rp_buflen = 0; rp->rp_buf = rp->rp_ibuf; - mutex_init(&rp->rp_mutex); + rp->rp_locked = RP_UNLOCKED; } -static void nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, - struct nfs4_stateowner *so) +static int nfsd4_cstate_assign_replay(struct nfsd4_compound_state *cstate, + struct nfs4_stateowner *so) { if (!nfsd4_has_session(cstate)) { - mutex_lock(&so->so_replay.rp_mutex); + wait_var_event(&so->so_replay.rp_locked, + cmpxchg(&so->so_replay.rp_locked, + RP_UNLOCKED, RP_LOCKED) != RP_LOCKED); + if (so->so_replay.rp_locked == RP_UNHASHED) + return -EAGAIN; cstate->replay_owner = nfs4_get_stateowner(so); } + return 0; } void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate) @@ -3596,7 +4943,7 @@ void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate) if (so != NULL) { cstate->replay_owner = NULL; - mutex_unlock(&so->so_replay.rp_mutex); + store_release_wake_up(&so->so_replay.rp_locked, RP_UNLOCKED); nfs4_put_stateowner(so); } } @@ -3609,12 +4956,11 @@ static inline void *alloc_stateowner(struct kmem_cache *slab, struct xdr_netobj if (!sop) return NULL; - sop->so_owner.data = kmemdup(owner->data, owner->len, GFP_KERNEL); + xdr_netobj_dup(&sop->so_owner, owner, GFP_KERNEL); if (!sop->so_owner.data) { kmem_cache_free(slab, sop); return NULL; } - sop->so_owner.len = owner->len; INIT_LIST_HEAD(&sop->so_stateids); sop->so_client = clp; @@ -3663,7 +5009,8 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) continue; if (local->st_stateowner != &oo->oo_owner) continue; - if (local->st_stid.sc_type == NFS4_OPEN_STID) { + if (local->st_stid.sc_type == SC_TYPE_OPEN && + !local->st_stid.sc_status) { ret = local; refcount_inc(&ret->st_stid.sc_count); break; @@ -3672,22 +5019,75 @@ nfsd4_find_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) return ret; } -static __be32 -nfsd4_verify_open_stid(struct nfs4_stid *s) +static void nfsd4_drop_revoked_stid(struct nfs4_stid *s) + __releases(&s->sc_client->cl_lock) { - __be32 ret = nfs_ok; + struct nfs4_client *cl = s->sc_client; + LIST_HEAD(reaplist); + struct nfs4_ol_stateid *stp; + struct nfs4_delegation *dp; + bool unhashed; switch (s->sc_type) { - default: + case SC_TYPE_OPEN: + stp = openlockstateid(s); + if (unhash_open_stateid(stp, &reaplist)) + put_ol_stateid_locked(stp, &reaplist); + spin_unlock(&cl->cl_lock); + free_ol_stateid_reaplist(&reaplist); break; - case 0: - case NFS4_CLOSED_STID: - case NFS4_CLOSED_DELEG_STID: - ret = nfserr_bad_stateid; + case SC_TYPE_LOCK: + stp = openlockstateid(s); + unhashed = unhash_lock_stateid(stp); + spin_unlock(&cl->cl_lock); + if (unhashed) + nfs4_put_stid(s); break; - case NFS4_REVOKED_DELEG_STID: - ret = nfserr_deleg_revoked; + case SC_TYPE_DELEG: + dp = delegstateid(s); + list_del_init(&dp->dl_recall_lru); + spin_unlock(&cl->cl_lock); + nfs4_put_stid(s); + break; + default: + spin_unlock(&cl->cl_lock); } +} + +static void nfsd40_drop_revoked_stid(struct nfs4_client *cl, + stateid_t *stid) +{ + /* NFSv4.0 has no way for the client to tell the server + * that it can forget an admin-revoked stateid. + * So we keep it around until the first time that the + * client uses it, and drop it the first time + * nfserr_admin_revoked is returned. + * For v4.1 and later we wait until explicitly told + * to free the stateid. + */ + if (cl->cl_minorversion == 0) { + struct nfs4_stid *st; + + spin_lock(&cl->cl_lock); + st = find_stateid_locked(cl, stid); + if (st) + nfsd4_drop_revoked_stid(st); + else + spin_unlock(&cl->cl_lock); + } +} + +static __be32 +nfsd4_verify_open_stid(struct nfs4_stid *s) +{ + __be32 ret = nfs_ok; + + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) + ret = nfserr_admin_revoked; + else if (s->sc_status & SC_STATUS_REVOKED) + ret = nfserr_deleg_revoked; + else if (s->sc_status & SC_STATUS_CLOSED) + ret = nfserr_bad_stateid; return ret; } @@ -3699,6 +5099,10 @@ nfsd4_lock_ol_stateid(struct nfs4_ol_stateid *stp) mutex_lock_nested(&stp->st_mutex, LOCK_STATEID_MUTEX); ret = nfsd4_verify_open_stid(&stp->st_stid); + if (ret == nfserr_admin_revoked) + nfsd40_drop_revoked_stid(stp->st_stid.sc_client, + &stp->st_stid.sc_stateid); + if (ret != nfs_ok) mutex_unlock(&stp->st_mutex); return ret; @@ -3720,34 +5124,46 @@ nfsd4_find_and_lock_existing_open(struct nfs4_file *fp, struct nfsd4_open *open) } static struct nfs4_openowner * -alloc_init_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, - struct nfsd4_compound_state *cstate) +find_or_alloc_open_stateowner(unsigned int strhashval, struct nfsd4_open *open, + struct nfsd4_compound_state *cstate) { struct nfs4_client *clp = cstate->clp; - struct nfs4_openowner *oo, *ret; + struct nfs4_openowner *oo, *new = NULL; - oo = alloc_stateowner(openowner_slab, &open->op_owner, clp); - if (!oo) - return NULL; - oo->oo_owner.so_ops = &openowner_ops; - oo->oo_owner.so_is_open_owner = 1; - oo->oo_owner.so_seqid = open->op_seqid; - oo->oo_flags = 0; - if (nfsd4_has_session(cstate)) - oo->oo_flags |= NFS4_OO_CONFIRMED; - oo->oo_time = 0; - oo->oo_last_closed_stid = NULL; - INIT_LIST_HEAD(&oo->oo_close_lru); +retry: spin_lock(&clp->cl_lock); - ret = find_openstateowner_str_locked(strhashval, open, clp); - if (ret == NULL) { - hash_openowner(oo, clp, strhashval); - ret = oo; - } else - nfs4_free_stateowner(&oo->oo_owner); - + oo = find_openstateowner_str(strhashval, open, clp); + if (!oo && new) { + hash_openowner(new, clp, strhashval); + spin_unlock(&clp->cl_lock); + return new; + } spin_unlock(&clp->cl_lock); - return ret; + + if (oo && !(oo->oo_flags & NFS4_OO_CONFIRMED)) { + /* Replace unconfirmed owners without checking for replay. */ + release_openowner(oo); + oo = NULL; + } + if (oo) { + if (new) + nfs4_free_stateowner(&new->oo_owner); + return oo; + } + + new = alloc_stateowner(openowner_slab, &open->op_owner, clp); + if (!new) + return NULL; + new->oo_owner.so_ops = &openowner_ops; + new->oo_owner.so_is_open_owner = 1; + new->oo_owner.so_seqid = open->op_seqid; + new->oo_flags = 0; + if (nfsd4_has_session(cstate)) + new->oo_flags |= NFS4_OO_CONFIRMED; + new->oo_time = 0; + new->oo_last_closed_stid = NULL; + INIT_LIST_HEAD(&new->oo_close_lru); + goto retry; } static struct nfs4_ol_stateid * @@ -3767,13 +5183,19 @@ retry: spin_lock(&oo->oo_owner.so_client->cl_lock); spin_lock(&fp->fi_lock); + if (nfs4_openowner_unhashed(oo)) { + mutex_unlock(&stp->st_mutex); + stp = NULL; + goto out_unlock; + } + retstp = nfsd4_find_existing_open(fp, open); if (retstp) goto out_unlock; open->op_stp = NULL; refcount_inc(&stp->st_stid.sc_count); - stp->st_stid.sc_type = NFS4_OPEN_STID; + stp->st_stid.sc_type = SC_TYPE_OPEN; INIT_LIST_HEAD(&stp->st_locks); stp->st_stateowner = nfs4_get_stateowner(&oo->oo_owner); get_nfs4_file(fp); @@ -3823,7 +5245,10 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) * Wait for the refcount to drop to 2. Since it has been unhashed, * there should be no danger of the refcount going back up again at * this point. + * Some threads with a reference might be waiting for rp_locked, + * so tell them to stop waiting. */ + store_release_wake_up(&oo->oo_owner.so_replay.rp_locked, RP_UNHASHED); wait_event(close_wq, refcount_read(&s->st_stid.sc_count) == 2); release_all_access(s); @@ -3836,60 +5261,86 @@ move_to_close_lru(struct nfs4_ol_stateid *s, struct net *net) last = oo->oo_last_closed_stid; oo->oo_last_closed_stid = s; list_move_tail(&oo->oo_close_lru, &nn->close_lru); - oo->oo_time = get_seconds(); + oo->oo_time = ktime_get_boottime_seconds(); spin_unlock(&nn->client_lock); if (last) nfs4_put_stid(&last->st_stid); } -/* search file_hashtbl[] for file */ -static struct nfs4_file * -find_file_locked(struct knfsd_fh *fh, unsigned int hashval) +static noinline_for_stack struct nfs4_file * +nfsd4_file_hash_lookup(const struct svc_fh *fhp) { - struct nfs4_file *fp; + struct inode *inode = d_inode(fhp->fh_dentry); + struct rhlist_head *tmp, *list; + struct nfs4_file *fi; - hlist_for_each_entry_rcu(fp, &file_hashtbl[hashval], fi_hash) { - if (fh_match(&fp->fi_fhandle, fh)) { - if (refcount_inc_not_zero(&fp->fi_ref)) - return fp; + rcu_read_lock(); + list = rhltable_lookup(&nfs4_file_rhltable, &inode, + nfs4_file_rhash_params); + rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { + if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { + if (refcount_inc_not_zero(&fi->fi_ref)) { + rcu_read_unlock(); + return fi; + } } } + rcu_read_unlock(); return NULL; } -struct nfs4_file * -find_file(struct knfsd_fh *fh) -{ - struct nfs4_file *fp; - unsigned int hashval = file_hashval(fh); +/* + * On hash insertion, identify entries with the same inode but + * distinct filehandles. They will all be on the list returned + * by rhltable_lookup(). + * + * inode->i_lock prevents racing insertions from adding an entry + * for the same inode/fhp pair twice. + */ +static noinline_for_stack struct nfs4_file * +nfsd4_file_hash_insert(struct nfs4_file *new, const struct svc_fh *fhp) +{ + struct inode *inode = d_inode(fhp->fh_dentry); + struct rhlist_head *tmp, *list; + struct nfs4_file *ret = NULL; + bool alias_found = false; + struct nfs4_file *fi; + int err; rcu_read_lock(); - fp = find_file_locked(fh, hashval); - rcu_read_unlock(); - return fp; -} + spin_lock(&inode->i_lock); -static struct nfs4_file * -find_or_add_file(struct nfs4_file *new, struct knfsd_fh *fh) -{ - struct nfs4_file *fp; - unsigned int hashval = file_hashval(fh); + list = rhltable_lookup(&nfs4_file_rhltable, &inode, + nfs4_file_rhash_params); + rhl_for_each_entry_rcu(fi, tmp, list, fi_rlist) { + if (fh_match(&fi->fi_fhandle, &fhp->fh_handle)) { + if (refcount_inc_not_zero(&fi->fi_ref)) + ret = fi; + } else + fi->fi_aliased = alias_found = true; + } + if (ret) + goto out_unlock; - rcu_read_lock(); - fp = find_file_locked(fh, hashval); - rcu_read_unlock(); - if (fp) - return fp; + nfsd4_file_init(fhp, new); + err = rhltable_insert(&nfs4_file_rhltable, &new->fi_rlist, + nfs4_file_rhash_params); + if (err) + goto out_unlock; - spin_lock(&state_lock); - fp = find_file_locked(fh, hashval); - if (likely(fp == NULL)) { - nfsd4_init_file(fh, hashval, new); - fp = new; - } - spin_unlock(&state_lock); + new->fi_aliased = alias_found; + ret = new; - return fp; +out_unlock: + spin_unlock(&inode->i_lock); + rcu_read_unlock(); + return ret; +} + +static noinline_for_stack void nfsd4_file_hash_remove(struct nfs4_file *fi) +{ + rhltable_remove(&nfs4_file_rhltable, &fi->fi_rlist, + nfs4_file_rhash_params); } /* @@ -3902,9 +5353,10 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) struct nfs4_file *fp; __be32 ret = nfs_ok; - fp = find_file(¤t_fh->fh_handle); + fp = nfsd4_file_hash_lookup(current_fh); if (!fp) return ret; + /* Check for conflicting share reservations */ spin_lock(&fp->fi_lock); if (fp->fi_share_deny & deny_type) @@ -3914,6 +5366,35 @@ nfs4_share_conflict(struct svc_fh *current_fh, unsigned int deny_type) return ret; } +static bool nfsd4_deleg_present(const struct inode *inode) +{ + struct file_lock_context *ctx = locks_inode_context(inode); + + return ctx && !list_empty_careful(&ctx->flc_lease); +} + +/** + * nfsd_wait_for_delegreturn - wait for delegations to be returned + * @rqstp: the RPC transaction being executed + * @inode: in-core inode of the file being waited for + * + * The timeout prevents deadlock if all nfsd threads happen to be + * tied up waiting for returning delegations. + * + * Return values: + * %true: delegation was returned + * %false: timed out waiting for delegreturn + */ +bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode) +{ + long __maybe_unused timeo; + + timeo = wait_var_event_timeout(inode, !nfsd4_deleg_present(inode), + NFSD_DELEGRETURN_TIMEOUT); + trace_nfsd_delegret_wakeup(rqstp, inode, timeo); + return timeo > 0; +} + static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb) { struct nfs4_delegation *dp = cb_to_delegation(cb); @@ -3930,8 +5411,8 @@ static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb) * queued for a lease break. Don't queue it again. */ spin_lock(&state_lock); - if (dp->dl_time == 0) { - dp->dl_time = get_seconds(); + if (delegation_hashed(dp) && dp->dl_time == 0) { + dp->dl_time = ktime_get_boottime_seconds(); list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru); } spin_unlock(&state_lock); @@ -3942,12 +5423,18 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, { struct nfs4_delegation *dp = cb_to_delegation(cb); - if (dp->dl_stid.sc_type == NFS4_CLOSED_DELEG_STID) - return 1; + trace_nfsd_cb_recall_done(&dp->dl_stid.sc_stateid, task); + + if (dp->dl_stid.sc_status) + /* CLOSED or REVOKED */ + return 1; switch (task->tk_status) { case 0: return 1; + case -NFS4ERR_DELAY: + rpc_delay(task, 2 * HZ); + return 0; case -EBADHANDLE: case -NFS4ERR_BAD_STATEID: /* @@ -3958,9 +5445,9 @@ static int nfsd4_cb_recall_done(struct nfsd4_callback *cb, rpc_delay(task, 2 * HZ); return 0; } - /*FALLTHRU*/ + fallthrough; default: - return -1; + return 1; } } @@ -3975,28 +5462,47 @@ static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = { .prepare = nfsd4_cb_recall_prepare, .done = nfsd4_cb_recall_done, .release = nfsd4_cb_recall_release, + .opcode = OP_CB_RECALL, }; static void nfsd_break_one_deleg(struct nfs4_delegation *dp) { + bool queued; + + if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &dp->dl_recall.cb_flags)) + return; + /* * We're assuming the state code never drops its reference * without first removing the lease. Since we're in this lease * callback (and since the lease code is serialized by the - * i_lock) we know the server hasn't removed the lease yet, and + * flc_lock) we know the server hasn't removed the lease yet, and * we know it's safe to take a reference. */ refcount_inc(&dp->dl_stid.sc_count); - nfsd4_run_cb(&dp->dl_recall); + queued = nfsd4_run_cb(&dp->dl_recall); + WARN_ON_ONCE(!queued); + if (!queued) + refcount_dec(&dp->dl_stid.sc_count); } -/* Called from break_lease() with i_lock held. */ +/* Called from break_lease() with flc_lock held. */ static bool -nfsd_break_deleg_cb(struct file_lock *fl) +nfsd_break_deleg_cb(struct file_lease *fl) { - bool ret = false; - struct nfs4_delegation *dp = (struct nfs4_delegation *)fl->fl_owner; + struct nfs4_delegation *dp = (struct nfs4_delegation *) fl->c.flc_owner; struct nfs4_file *fp = dp->dl_stid.sc_file; + struct nfs4_client *clp = dp->dl_stid.sc_client; + struct nfsd_net *nn; + + trace_nfsd_cb_recall(&dp->dl_stid); + + dp->dl_recalled = true; + atomic_inc(&clp->cl_delegs_in_recall); + if (try_to_expire_client(clp)) { + nn = net_generic(clp->net, nfsd_net_id); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + } /* * We don't want the locks code to timeout the lease for us; @@ -4005,24 +5511,49 @@ nfsd_break_deleg_cb(struct file_lock *fl) */ fl->fl_break_time = 0; - spin_lock(&fp->fi_lock); fp->fi_had_conflict = true; nfsd_break_one_deleg(dp); - spin_unlock(&fp->fi_lock); - return ret; + return false; +} + +/** + * nfsd_breaker_owns_lease - Check if lease conflict was resolved + * @fl: Lock state to check + * + * Return values: + * %true: Lease conflict was resolved + * %false: Lease conflict was not resolved. + */ +static bool nfsd_breaker_owns_lease(struct file_lease *fl) +{ + struct nfs4_delegation *dl = fl->c.flc_owner; + struct svc_rqst *rqst; + struct nfs4_client *clp; + + rqst = nfsd_current_rqst(); + if (!nfsd_v4client(rqst)) + return false; + clp = *(rqst->rq_lease_breaker); + return dl->dl_stid.sc_client == clp; } static int -nfsd_change_deleg_cb(struct file_lock *onlist, int arg, +nfsd_change_deleg_cb(struct file_lease *onlist, int arg, struct list_head *dispose) { - if (arg & F_UNLCK) + struct nfs4_delegation *dp = (struct nfs4_delegation *) onlist->c.flc_owner; + struct nfs4_client *clp = dp->dl_stid.sc_client; + + if (arg & F_UNLCK) { + if (dp->dl_recalled) + atomic_dec(&clp->cl_delegs_in_recall); return lease_modify(onlist, arg, dispose); - else + } else return -EAGAIN; } -static const struct lock_manager_operations nfsd_lease_mng_ops = { +static const struct lease_manager_operations nfsd_lease_mng_ops = { + .lm_breaker_owns_lease = nfsd_breaker_owns_lease, .lm_break = nfsd_break_deleg_cb, .lm_change = nfsd_change_deleg_cb, }; @@ -4038,39 +5569,37 @@ static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4 return nfserr_bad_seqid; } -static __be32 lookup_clientid(clientid_t *clid, - struct nfsd4_compound_state *cstate, - struct nfsd_net *nn) +static struct nfs4_client *lookup_clientid(clientid_t *clid, bool sessions, + struct nfsd_net *nn) { struct nfs4_client *found; + spin_lock(&nn->client_lock); + found = find_confirmed_client(clid, sessions, nn); + if (found) + atomic_inc(&found->cl_rpc_users); + spin_unlock(&nn->client_lock); + return found; +} + +static __be32 set_client(clientid_t *clid, + struct nfsd4_compound_state *cstate, + struct nfsd_net *nn) +{ if (cstate->clp) { - found = cstate->clp; - if (!same_clid(&found->cl_clientid, clid)) + if (!same_clid(&cstate->clp->cl_clientid, clid)) return nfserr_stale_clientid; return nfs_ok; } - if (STALE_CLIENTID(clid, nn)) return nfserr_stale_clientid; - /* - * For v4.1+ we get the client in the SEQUENCE op. If we don't have one - * cached already then we know this is for is for v4.0 and "sessions" - * will be false. + * We're in the 4.0 case (otherwise the SEQUENCE op would have + * set cstate->clp), so session = false: */ - WARN_ON_ONCE(cstate->session); - spin_lock(&nn->client_lock); - found = find_confirmed_client(clid, false, nn); - if (!found) { - spin_unlock(&nn->client_lock); + cstate->clp = lookup_clientid(clid, false, nn); + if (!cstate->clp) return nfserr_expired; - } - atomic_inc(&found->cl_refcount); - spin_unlock(&nn->client_lock); - - /* Cache the nfs4_client in cstate! */ - cstate->clp = found; return nfs_ok; } @@ -4084,8 +5613,6 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate, struct nfs4_openowner *oo = NULL; __be32 status; - if (STALE_CLIENTID(&open->op_clientid, nn)) - return nfserr_stale_clientid; /* * In case we need it later, after we've already created the * file and don't want to risk a further failure: @@ -4094,33 +5621,25 @@ nfsd4_process_open1(struct nfsd4_compound_state *cstate, if (open->op_file == NULL) return nfserr_jukebox; - status = lookup_clientid(clientid, cstate, nn); + status = set_client(clientid, cstate, nn); if (status) return status; clp = cstate->clp; strhashval = ownerstr_hashval(&open->op_owner); - oo = find_openstateowner_str(strhashval, open, clp); +retry: + oo = find_or_alloc_open_stateowner(strhashval, open, cstate); open->op_openowner = oo; - if (!oo) { - goto new_owner; - } - if (!(oo->oo_flags & NFS4_OO_CONFIRMED)) { - /* Replace unconfirmed owners without checking for replay. */ - release_openowner(oo); - open->op_openowner = NULL; - goto new_owner; + if (!oo) + return nfserr_jukebox; + if (nfsd4_cstate_assign_replay(cstate, &oo->oo_owner) == -EAGAIN) { + nfs4_put_stateowner(&oo->oo_owner); + goto retry; } status = nfsd4_check_seqid(cstate, &oo->oo_owner, open->op_seqid); if (status) return status; - goto alloc_stateid; -new_owner: - oo = alloc_init_open_stateowner(strhashval, open, cstate); - if (oo == NULL) - return nfserr_jukebox; - open->op_openowner = oo; -alloc_stateid: + open->op_stp = nfs4_alloc_open_stateid(clp); if (!open->op_stp) return nfserr_jukebox; @@ -4138,7 +5657,7 @@ alloc_stateid: static inline __be32 nfs4_check_delegmode(struct nfs4_delegation *dp, int flags) { - if ((flags & WR_STATE) && (dp->dl_type == NFS4_OPEN_DELEGATE_READ)) + if (!(flags & RD_STATE) && deleg_is_read(dp->dl_type)) return nfserr_openmode; else return nfs_ok; @@ -4149,12 +5668,12 @@ static int share_access_to_flags(u32 share_access) return share_access == NFS4_SHARE_ACCESS_READ ? RD_STATE : WR_STATE; } -static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, stateid_t *s) +static struct nfs4_delegation *find_deleg_stateid(struct nfs4_client *cl, + stateid_t *s) { struct nfs4_stid *ret; - ret = find_stateid_by_type(cl, s, - NFS4_DELEG_STID|NFS4_REVOKED_DELEG_STID); + ret = find_stateid_by_type(cl, s, SC_TYPE_DELEG, SC_STATUS_REVOKED); if (!ret) return NULL; return delegstateid(ret); @@ -4177,10 +5696,15 @@ nfs4_check_deleg(struct nfs4_client *cl, struct nfsd4_open *open, deleg = find_deleg_stateid(cl, &open->op_delegate_stateid); if (deleg == NULL) goto out; - if (deleg->dl_stid.sc_type == NFS4_REVOKED_DELEG_STID) { + if (deleg->dl_stid.sc_status & SC_STATUS_ADMIN_REVOKED) { nfs4_put_stid(&deleg->dl_stid); - if (cl->cl_minorversion) - status = nfserr_deleg_revoked; + status = nfserr_admin_revoked; + goto out; + } + if (deleg->dl_stid.sc_status & SC_STATUS_REVOKED) { + nfs4_put_stid(&deleg->dl_stid); + nfsd40_drop_revoked_stid(cl, &open->op_delegate_stateid); + status = nfserr_deleg_revoked; goto out; } flags = share_access_to_flags(open->op_share_access); @@ -4218,18 +5742,21 @@ nfsd4_truncate(struct svc_rqst *rqstp, struct svc_fh *fh, .ia_valid = ATTR_SIZE, .ia_size = 0, }; + struct nfsd_attrs attrs = { + .na_iattr = &iattr, + }; if (!open->op_truncate) return 0; if (!(open->op_share_access & NFS4_SHARE_ACCESS_WRITE)) return nfserr_inval; - return nfsd_setattr(rqstp, fh, &iattr, 0, (time_t)0); + return nfsd_setattr(rqstp, fh, &attrs, NULL); } static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, - struct nfsd4_open *open) + struct nfsd4_open *open, bool new_stp) { - struct file *filp = NULL; + struct nfsd_file *nf = NULL; __be32 status; int oflag = nfs4_access_to_omode(open->op_share_access); int access = nfs4_access_to_access(open->op_share_access); @@ -4243,6 +5770,13 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, */ status = nfs4_file_check_deny(fp, open->op_share_deny); if (status != nfs_ok) { + if (status != nfserr_share_denied) { + spin_unlock(&fp->fi_lock); + goto out; + } + if (nfs4_resolve_deny_conflicts_locked(fp, new_stp, + stp, open->op_share_deny, false)) + status = nfserr_jukebox; spin_unlock(&fp->fi_lock); goto out; } @@ -4250,6 +5784,13 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, /* set access to the file */ status = nfs4_file_get_access(fp, open->op_share_access); if (status != nfs_ok) { + if (status != nfserr_share_denied) { + spin_unlock(&fp->fi_lock); + goto out; + } + if (nfs4_resolve_deny_conflicts_locked(fp, new_stp, + stp, open->op_share_access, true)) + status = nfserr_jukebox; spin_unlock(&fp->fi_lock); goto out; } @@ -4265,18 +5806,26 @@ static __be32 nfs4_get_vfs_file(struct svc_rqst *rqstp, struct nfs4_file *fp, if (!fp->fi_fds[oflag]) { spin_unlock(&fp->fi_lock); - status = nfsd_open(rqstp, cur_fh, S_IFREG, access, &filp); - if (status) + + 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]) { - fp->fi_fds[oflag] = filp; - filp = NULL; + fp->fi_fds[oflag] = nf; + nf = NULL; } } spin_unlock(&fp->fi_lock); - if (filp) - fput(filp); + if (nf) + nfsd_file_put(nf); + + status = nfserrno(nfsd_open_break_lease(cur_fh->fh_dentry->d_inode, + access)); + if (status) + goto out_put_access; status = nfsd4_truncate(rqstp, cur_fh, open); if (status) @@ -4291,21 +5840,30 @@ out_put_access: } static __be32 -nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, struct nfsd4_open *open) +nfs4_upgrade_open(struct svc_rqst *rqstp, struct nfs4_file *fp, + struct svc_fh *cur_fh, struct nfs4_ol_stateid *stp, + struct nfsd4_open *open) { __be32 status; unsigned char old_deny_bmap = stp->st_deny_bmap; if (!test_access(open->op_share_access, stp)) - return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open); + return nfs4_get_vfs_file(rqstp, fp, cur_fh, stp, open, false); /* test and set deny mode */ spin_lock(&fp->fi_lock); status = nfs4_file_check_deny(fp, open->op_share_deny); - if (status == nfs_ok) { + switch (status) { + case nfs_ok: set_deny(open->op_share_deny, stp); fp->fi_share_deny |= - (open->op_share_deny & NFS4_SHARE_DENY_BOTH); + (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); @@ -4331,32 +5889,151 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp) return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN; } -static struct file_lock *nfs4_alloc_init_lease(struct nfs4_delegation *dp, - int flag) +static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp) { - struct file_lock *fl; + struct file_lease *fl; - fl = locks_alloc_lock(); + fl = locks_alloc_lease(); if (!fl) return NULL; fl->fl_lmops = &nfsd_lease_mng_ops; - fl->fl_flags = FL_DELEG; - fl->fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK; - fl->fl_end = OFFSET_MAX; - fl->fl_owner = (fl_owner_t)dp; - fl->fl_pid = current->tgid; - fl->fl_file = dp->dl_stid.sc_file->fi_deleg_file; + fl->c.flc_flags = FL_DELEG; + fl->c.flc_type = deleg_is_read(dp->dl_type) ? F_RDLCK : F_WRLCK; + fl->c.flc_owner = (fl_owner_t)dp; + fl->c.flc_pid = current->tgid; + fl->c.flc_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file; return fl; } +static int nfsd4_check_conflicting_opens(struct nfs4_client *clp, + struct nfs4_file *fp) +{ + struct nfs4_ol_stateid *st; + struct file *f = fp->fi_deleg_file->nf_file; + struct inode *ino = file_inode(f); + int writes; + + writes = atomic_read(&ino->i_writecount); + if (!writes) + return 0; + /* + * There could be multiple filehandles (hence multiple + * nfs4_files) referencing this file, but that's not too + * common; let's just give up in that case rather than + * trying to go look up all the clients using that other + * nfs4_file as well: + */ + if (fp->fi_aliased) + return -EAGAIN; + /* + * If there's a close in progress, make sure that we see it + * clear any fi_fds[] entries before we see it decrement + * i_writecount: + */ + smp_mb__after_atomic(); + + if (fp->fi_fds[O_WRONLY]) + writes--; + if (fp->fi_fds[O_RDWR]) + writes--; + if (writes > 0) + return -EAGAIN; /* There may be non-NFSv4 writers */ + /* + * It's possible there are non-NFSv4 write opens in progress, + * but if they haven't incremented i_writecount yet then they + * also haven't called break lease yet; so, they'll break this + * lease soon enough. So, all that's left to check for is NFSv4 + * opens: + */ + spin_lock(&fp->fi_lock); + list_for_each_entry(st, &fp->fi_stateids, st_perfile) { + if (st->st_openstp == NULL /* it's an open */ && + access_permit_write(st) && + st->st_stid.sc_client != clp) { + spin_unlock(&fp->fi_lock); + return -EAGAIN; + } + } + spin_unlock(&fp->fi_lock); + /* + * There's a small chance that we could be racing with another + * NFSv4 open. However, any open that hasn't added itself to + * the fi_stateids list also hasn't called break_lease yet; so, + * they'll break this lease soon enough. + */ + return 0; +} + +/* + * It's possible that between opening the dentry and setting the delegation, + * that it has been renamed or unlinked. Redo the lookup to verify that this + * hasn't happened. + */ +static int +nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp, + struct svc_fh *parent) +{ + struct svc_export *exp; + struct dentry *child; + __be32 err; + + err = nfsd_lookup_dentry(open->op_rqstp, parent, + open->op_fname, open->op_fnamelen, + &exp, &child); + + if (err) + return -EAGAIN; + + exp_put(exp); + dput(child); + if (child != file_dentry(fp->fi_deleg_file->nf_file)) + return -EAGAIN; + + 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; +} + +#ifdef CONFIG_NFSD_V4_DELEG_TIMESTAMPS +static bool nfsd4_want_deleg_timestamps(const struct nfsd4_open *open) +{ + return open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_DELEG_TIMESTAMPS; +} +#else /* CONFIG_NFSD_V4_DELEG_TIMESTAMPS */ +static bool nfsd4_want_deleg_timestamps(const struct nfsd4_open *open) +{ + return false; +} +#endif /* CONFIG NFSD_V4_DELEG_TIMESTAMPS */ + static struct nfs4_delegation * -nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, - struct nfs4_file *fp, struct nfs4_clnt_odstate *odstate) +nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp, + struct svc_fh *parent) { - int status = 0; + bool deleg_ts = nfsd4_want_deleg_timestamps(open); + struct nfs4_client *clp = stp->st_stid.sc_client; + struct nfs4_file *fp = stp->st_stid.sc_file; + struct nfs4_clnt_odstate *odstate = stp->st_clnt_odstate; struct nfs4_delegation *dp; - struct file *filp; - struct file_lock *fl; + struct nfsd_file *nf = NULL; + struct file_lease *fl; + int status = 0; + u32 dl_type; /* * The fi_had_conflict and nfs_get_existing_delegation checks @@ -4366,53 +6043,114 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, if (fp->fi_had_conflict) return ERR_PTR(-EAGAIN); - filp = find_readable_file(fp); - if (!filp) { - /* We should always have a readable file here */ - WARN_ON_ONCE(1); - return ERR_PTR(-EBADF); + /* + * Try for a write delegation first. RFC8881 section 10.4 says: + * + * "An OPEN_DELEGATE_WRITE delegation allows the client to handle, + * on its own, all opens." + * + * Furthermore, section 9.1.2 says: + * + * "In the case of READ, the server may perform the corresponding + * check on the access mode, or it may choose to allow READ for + * OPEN4_SHARE_ACCESS_WRITE, to accommodate clients whose WRITE + * implementation may unavoidably do reads (e.g., due to buffer + * cache constraints)." + * + * We choose to offer a write delegation for OPEN with the + * OPEN4_SHARE_ACCESS_WRITE access mode to accommodate such clients. + */ + if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { + nf = find_writeable_file(fp); + dl_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : OPEN_DELEGATE_WRITE; + } + + /* + * If the file is being opened O_RDONLY or we couldn't get a O_RDWR + * file for some reason, then try for a read delegation instead. + */ + if (!nf && (open->op_share_access & NFS4_SHARE_ACCESS_READ)) { + nf = find_readable_file(fp); + dl_type = deleg_ts ? OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ; + } + + if (!nf) + return ERR_PTR(-EAGAIN); + + /* + * File delegations and associated locks cannot be recovered if the + * export is from an NFS proxy server. + */ + if (exportfs_cannot_lock(nf->nf_file->f_path.mnt->mnt_sb->s_export_op)) { + nfsd_file_put(nf); + return ERR_PTR(-EOPNOTSUPP); } + spin_lock(&state_lock); 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 = filp; + fp->fi_deleg_file = nf; /* increment early to prevent fi_deleg_file from being * cleared */ fp->fi_delegees = 1; - filp = NULL; + nf = NULL; } else fp->fi_delegees++; spin_unlock(&fp->fi_lock); spin_unlock(&state_lock); - if (filp) - fput(filp); + if (nf) + nfsd_file_put(nf); if (status) return ERR_PTR(status); status = -ENOMEM; - dp = alloc_init_deleg(clp, fp, fh, odstate); + dp = alloc_init_deleg(clp, fp, odstate, dl_type); if (!dp) goto out_delegees; - fl = nfs4_alloc_init_lease(dp, NFS4_OPEN_DELEGATE_READ); + fl = nfs4_alloc_init_lease(dp); if (!fl) goto out_clnt_odstate; - status = vfs_setlease(fp->fi_deleg_file, fl->fl_type, &fl, NULL); + status = kernel_setlease(fp->fi_deleg_file->nf_file, + fl->c.flc_type, &fl, NULL); if (fl) - locks_free_lock(fl); + locks_free_lease(fl); if (status) goto out_clnt_odstate; + if (parent) { + status = nfsd4_verify_deleg_dentry(open, fp, parent); + if (status) + goto out_unlock; + } + + status = nfsd4_check_conflicting_opens(clp, fp); + 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 looking. + */ + status = nfsd4_verify_setuid_write(open, fp->fi_deleg_file); + if (status) + goto out_unlock; + + status = -EAGAIN; + if (fp->fi_had_conflict) + goto out_unlock; + spin_lock(&state_lock); + spin_lock(&clp->cl_lock); spin_lock(&fp->fi_lock); - if (fp->fi_had_conflict) - status = -EAGAIN; - else - status = hash_delegation_locked(dp, fp); + status = hash_delegation_locked(dp, fp); spin_unlock(&fp->fi_lock); + spin_unlock(&clp->cl_lock); spin_unlock(&state_lock); if (status) @@ -4420,7 +6158,7 @@ nfs4_set_delegation(struct nfs4_client *clp, struct svc_fh *fh, return dp; out_unlock: - vfs_setlease(fp->fi_deleg_file, F_UNLCK, NULL, (void **)&dp); + kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp); out_clnt_odstate: put_clnt_odstate(dp->dl_clnt_odstate); nfs4_put_stid(&dp->dl_stid); @@ -4431,51 +6169,124 @@ out_delegees: static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; if (status == -EAGAIN) open->op_why_no_deleg = WND4_CONTENTION; else { open->op_why_no_deleg = WND4_RESOURCE; switch (open->op_deleg_want) { - case NFS4_SHARE_WANT_READ_DELEG: - case NFS4_SHARE_WANT_WRITE_DELEG: - case NFS4_SHARE_WANT_ANY_DELEG: + case OPEN4_SHARE_ACCESS_WANT_READ_DELEG: + case OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG: + case OPEN4_SHARE_ACCESS_WANT_ANY_DELEG: break; - case NFS4_SHARE_WANT_CANCEL: + case OPEN4_SHARE_ACCESS_WANT_CANCEL: open->op_why_no_deleg = WND4_CANCELLED; break; - case NFS4_SHARE_WANT_NO_DELEG: + case OPEN4_SHARE_ACCESS_WANT_NO_DELEG: WARN_ON_ONCE(1); } } } +static bool +nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh, + struct kstat *stat) +{ + struct nfsd_file *nf = find_writeable_file(dp->dl_stid.sc_file); + struct path path; + int rc; + + if (!nf) + return false; + + path.mnt = currentfh->fh_export->ex_path.mnt; + path.dentry = file_dentry(nf->nf_file); + + rc = vfs_getattr(&path, stat, + STATX_MODE | STATX_SIZE | STATX_ATIME | + STATX_MTIME | STATX_CTIME | STATX_CHANGE_COOKIE, + AT_STATX_SYNC_AS_STAT); + + nfsd_file_put(nf); + return rc == 0; +} + +/* + * Add NFS4_SHARE_ACCESS_READ to the write delegation granted on OPEN + * with NFS4_SHARE_ACCESS_WRITE by allocating separate nfsd_file and + * struct file to be used for read with delegation stateid. + * + */ +static bool +nfsd4_add_rdaccess_to_wrdeleg(struct svc_rqst *rqstp, struct nfsd4_open *open, + struct svc_fh *fh, struct nfs4_ol_stateid *stp) +{ + struct nfs4_file *fp; + struct nfsd_file *nf = NULL; + + if ((open->op_share_access & NFS4_SHARE_ACCESS_BOTH) == + NFS4_SHARE_ACCESS_WRITE) { + if (nfsd_file_acquire_opened(rqstp, fh, NFSD_MAY_READ, NULL, &nf)) + return (false); + fp = stp->st_stid.sc_file; + spin_lock(&fp->fi_lock); + __nfs4_file_get_access(fp, NFS4_SHARE_ACCESS_READ); + fp = stp->st_stid.sc_file; + fp->fi_fds[O_RDONLY] = nf; + fp->fi_rdeleg_file = nf; + spin_unlock(&fp->fi_lock); + } + return true; +} + /* - * Attempt to hand out a delegation. + * The Linux NFS server does not offer write delegations to NFSv4.0 + * clients in order to avoid conflicts between write delegations and + * GETATTRs requesting CHANGE or SIZE attributes. + * + * With NFSv4.1 and later minorversions, the SEQUENCE operation that + * begins each COMPOUND contains a client ID. Delegation recall can + * be avoided when the server recognizes the client sending a + * GETATTR also holds write delegation it conflicts with. * - * Note we don't support write delegations, and won't until the vfs has - * proper support for them. + * However, the NFSv4.0 protocol does not enable a server to + * determine that a GETATTR originated from the client holding the + * conflicting delegation versus coming from some other client. Per + * RFC 7530 Section 16.7.5, the server must recall or send a + * CB_GETATTR even when the GETATTR originates from the client that + * holds the conflicting delegation. + * + * An NFSv4.0 client can trigger a pathological situation if it + * always sends a DELEGRETURN preceded by a conflicting GETATTR in + * the same COMPOUND. COMPOUND execution will always stop at the + * GETATTR and the DELEGRETURN will never get executed. The server + * eventually revokes the delegation, which can result in loss of + * open or lock state. */ static void -nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, - struct nfs4_ol_stateid *stp) +nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open, + struct nfs4_ol_stateid *stp, struct svc_fh *currentfh, + struct svc_fh *fh) { - struct nfs4_delegation *dp; struct nfs4_openowner *oo = openowner(stp->st_stateowner); + bool deleg_ts = nfsd4_want_deleg_timestamps(open); struct nfs4_client *clp = stp->st_stid.sc_client; - int cb_up; + struct svc_fh *parent = NULL; + struct nfs4_delegation *dp; + struct kstat stat; int status = 0; + int cb_up; cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client); - open->op_recall = 0; + open->op_recall = false; switch (open->op_claim_type) { case NFS4_OPEN_CLAIM_PREVIOUS: if (!cb_up) - open->op_recall = 1; - if (open->op_delegate_type != NFS4_OPEN_DELEGATE_READ) - goto out_no_deleg; + open->op_recall = true; break; case NFS4_OPEN_CLAIM_NULL: + parent = currentfh; + fallthrough; case NFS4_OPEN_CLAIM_FH: /* * Let's not give out any delegations till everyone's @@ -4486,39 +6297,49 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, goto out_no_deleg; if (!cb_up || !(oo->oo_flags & NFS4_OO_CONFIRMED)) goto out_no_deleg; - /* - * Also, if the file was opened for write or - * create, there's a good chance the client's - * about to write to it, resulting in an - * immediate recall (since we don't support - * write delegations): - */ - if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) - goto out_no_deleg; - if (open->op_create == NFS4_OPEN_CREATE) + if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE && + !clp->cl_minorversion) goto out_no_deleg; break; default: goto out_no_deleg; } - dp = nfs4_set_delegation(clp, fh, stp->st_stid.sc_file, stp->st_clnt_odstate); + dp = nfs4_set_delegation(open, stp, parent); if (IS_ERR(dp)) goto out_no_deleg; memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid)); - dprintk("NFSD: delegation stateid=" STATEID_FMT "\n", - STATEID_VAL(&dp->dl_stid.sc_stateid)); - open->op_delegate_type = NFS4_OPEN_DELEGATE_READ; + if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) { + struct file *f = dp->dl_stid.sc_file->fi_deleg_file->nf_file; + + if (!nfsd4_add_rdaccess_to_wrdeleg(rqstp, open, fh, stp) || + !nfs4_delegation_stat(dp, currentfh, &stat)) { + nfs4_put_stid(&dp->dl_stid); + destroy_delegation(dp); + goto out_no_deleg; + } + open->op_delegate_type = deleg_ts ? OPEN_DELEGATE_WRITE_ATTRS_DELEG : + OPEN_DELEGATE_WRITE; + dp->dl_cb_fattr.ncf_cur_fsize = stat.size; + dp->dl_cb_fattr.ncf_initial_cinfo = nfsd4_change_attribute(&stat); + dp->dl_atime = stat.atime; + dp->dl_ctime = stat.ctime; + dp->dl_mtime = stat.mtime; + spin_lock(&f->f_lock); + f->f_mode |= FMODE_NOCMTIME; + spin_unlock(&f->f_lock); + trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid); + } else { + open->op_delegate_type = deleg_ts && nfs4_delegation_stat(dp, currentfh, &stat) ? + OPEN_DELEGATE_READ_ATTRS_DELEG : OPEN_DELEGATE_READ; + dp->dl_atime = stat.atime; + trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid); + } nfs4_put_stid(&dp->dl_stid); return; out_no_deleg: - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE; - if (open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS && - open->op_delegate_type != NFS4_OPEN_DELEGATE_NONE) { - dprintk("NFSD: WARNING: refusing delegation reclaim\n"); - open->op_recall = 1; - } + open->op_delegate_type = OPEN_DELEGATE_NONE; /* 4.1 client asking for a delegation? */ if (open->op_deleg_want) @@ -4529,21 +6350,44 @@ out_no_deleg: static void nfsd4_deleg_xgrade_none_ext(struct nfsd4_open *open, struct nfs4_delegation *dp) { - if (open->op_deleg_want == NFS4_SHARE_WANT_READ_DELEG && - dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; - open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE; - } else if (open->op_deleg_want == NFS4_SHARE_WANT_WRITE_DELEG && - dp->dl_type == NFS4_OPEN_DELEGATE_WRITE) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; - open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE; + if (deleg_is_write(dp->dl_type)) { + if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_READ_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; + open->op_why_no_deleg = WND4_NOT_SUPP_DOWNGRADE; + } else if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_WRITE_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; + open->op_why_no_deleg = WND4_NOT_SUPP_UPGRADE; + } } /* Otherwise the client must be confused wanting a delegation * it already has, therefore we don't return - * NFS4_OPEN_DELEGATE_NONE_EXT and reason. + * OPEN_DELEGATE_NONE_EXT and reason. */ } +/* Are we returning only a delegation stateid? */ +static bool open_xor_delegation(struct nfsd4_open *open) +{ + if (!(open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_OPEN_XOR_DELEGATION)) + return false; + /* Did we actually get a delegation? */ + if (!deleg_is_read(open->op_delegate_type) && !deleg_is_write(open->op_delegate_type)) + return false; + return true; +} + +/** + * nfsd4_process_open2 - finish open processing + * @rqstp: the RPC transaction being executed + * @current_fh: NFSv4 COMPOUND's current filehandle + * @open: OPEN arguments + * + * If successful, (1) truncate the file if open->op_truncate was + * set, (2) set open->op_stateid, (3) set open->op_delegation. + * + * Returns %nfs_ok on success; otherwise an nfs4stat value in + * network byte order is returned. + */ __be32 nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open) { @@ -4560,11 +6404,27 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf * and check for delegations in the process of being recalled. * If not found, create the nfs4_file struct */ - fp = find_or_add_file(open->op_file, ¤t_fh->fh_handle); + fp = nfsd4_file_hash_insert(open->op_file, current_fh); + if (unlikely(!fp)) + return nfserr_jukebox; if (fp != open->op_file) { status = nfs4_check_deleg(cl, open, &dp); if (status) goto out; + if (dp && nfsd4_is_deleg_cur(open) && + (dp->dl_stid.sc_file != fp)) { + /* + * RFC8881 section 8.2.4 mandates the server to return + * NFS4ERR_BAD_STATEID if the selected table entry does + * not match the current filehandle. However returning + * NFS4ERR_BAD_STATEID in the OPEN can cause the client + * to repeatedly retry the operation with the same + * stateid, since the stateid itself is valid. To avoid + * this situation NFSD returns NFS4ERR_INVAL instead. + */ + status = nfserr_inval; + goto out; + } stp = nfsd4_find_and_lock_existing_open(fp, open); } else { open->op_file = NULL; @@ -4575,6 +6435,11 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf if (!stp) { stp = init_open_stateid(fp, open); + if (!stp) { + status = nfserr_jukebox; + goto out; + } + if (!open->op_stp) new_stp = true; } @@ -4593,9 +6458,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf goto out; } } else { - status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open); + status = nfs4_get_vfs_file(rqstp, fp, current_fh, stp, open, true); if (status) { - stp->st_stid.sc_type = NFS4_CLOSED_STID; release_open_stateid(stp); mutex_unlock(&stp->st_mutex); goto out; @@ -4611,8 +6475,8 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf mutex_unlock(&stp->st_mutex); if (nfsd4_has_session(&resp->cstate)) { - if (open->op_deleg_want & NFS4_SHARE_WANT_NO_DELEG) { - open->op_delegate_type = NFS4_OPEN_DELEGATE_NONE_EXT; + if (open->op_deleg_want & OPEN4_SHARE_ACCESS_WANT_NO_DELEG) { + open->op_delegate_type = OPEN_DELEGATE_NONE_EXT; open->op_why_no_deleg = WND4_NOT_WANTED; goto nodeleg; } @@ -4622,15 +6486,25 @@ nfsd4_process_open2(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nf * Attempt to hand out a delegation. No error return, because the * OPEN succeeds even if we fail. */ - nfs4_open_delegation(current_fh, open, stp); + nfs4_open_delegation(rqstp, open, stp, + &resp->cstate.current_fh, current_fh); + + /* + * If there is an existing open stateid, it must be updated and + * returned. Only respect WANT_OPEN_XOR_DELEGATION when a new + * open stateid would have to be created. + */ + if (new_stp && open_xor_delegation(open)) { + memcpy(&open->op_stateid, &zero_stateid, sizeof(open->op_stateid)); + open->op_rflags |= OPEN4_RESULT_NO_OPEN_STATEID; + release_open_stateid(stp); + } nodeleg: status = nfs_ok; - - dprintk("%s: stateid=" STATEID_FMT "\n", __func__, - STATEID_VAL(&stp->st_stid.sc_stateid)); + trace_nfsd_open(&stp->st_stid.sc_stateid); out: /* 4.1 client trying to upgrade/downgrade delegation? */ - if (open->op_delegate_type == NFS4_OPEN_DELEGATE_NONE && dp && + if (open->op_delegate_type == OPEN_DELEGATE_NONE && dp && open->op_deleg_want) nfsd4_deleg_xgrade_none_ext(open, dp); @@ -4641,7 +6515,7 @@ out: /* * To finish the open response, we just need to set the rflags. */ - open->op_rflags = NFS4_OPEN_RESULT_LOCKTYPE_POSIX; + open->op_rflags |= NFS4_OPEN_RESULT_LOCKTYPE_POSIX; if (nfsd4_has_session(&resp->cstate)) open->op_rflags |= NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK; else if (!(open->op_openowner->oo_flags & NFS4_OO_CONFIRMED)) @@ -4658,12 +6532,8 @@ out: void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate, struct nfsd4_open *open) { - if (open->op_openowner) { - struct nfs4_stateowner *so = &open->op_openowner->oo_owner; - - nfsd4_cstate_assign_replay(cstate, so); - nfs4_put_stateowner(so); - } + if (open->op_openowner) + nfs4_put_stateowner(&open->op_openowner->oo_owner); if (open->op_file) kmem_cache_free(file_slab, open->op_file); if (open->op_stp) @@ -4681,19 +6551,15 @@ nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - dprintk("process_renew(%08x/%08x): starting\n", - clid->cl_boot, clid->cl_id); - status = lookup_clientid(clid, cstate, nn); + trace_nfsd_clid_renew(clid); + status = set_client(clid, cstate, nn); if (status) - goto out; + return status; clp = cstate->clp; - status = nfserr_cb_path_down; if (!list_empty(&clp->cl_delegations) && clp->cl_cb_state != NFSD4_CB_UP) - goto out; - status = nfs_ok; -out: - return status; + return nfserr_cb_path_down; + return nfs_ok; } void @@ -4703,7 +6569,7 @@ nfsd4_end_grace(struct nfsd_net *nn) if (nn->grace_ended) return; - dprintk("NFSD: end of grace period\n"); + trace_nfsd_grace_complete(nn); nn->grace_ended = true; /* * If the server goes down again right now, an NFSv4 @@ -4735,10 +6601,13 @@ nfsd4_end_grace(struct nfsd_net *nn) */ static bool clients_still_reclaiming(struct nfsd_net *nn) { - unsigned long now = get_seconds(); - unsigned long double_grace_period_end = nn->boot_time + - 2 * nn->nfsd4_lease; + time64_t double_grace_period_end = nn->boot_time + + 2 * nn->nfsd4_lease; + if (nn->track_reclaim_completes && + atomic_read(&nn->nr_reclaim_complete) == + nn->reclaim_str_hashtbl_size) + return false; if (!nn->somebody_reclaimed) return false; nn->somebody_reclaimed = false; @@ -4746,63 +6615,291 @@ static bool clients_still_reclaiming(struct nfsd_net *nn) * If we've given them *two* lease times to reclaim, and they're * still not done, give up: */ - if (time_after(now, double_grace_period_end)) + if (ktime_get_boottime_seconds() > double_grace_period_end) return false; return true; } -static time_t -nfs4_laundromat(struct nfsd_net *nn) +struct laundry_time { + time64_t cutoff; + time64_t new_timeo; +}; + +static bool state_expired(struct laundry_time *lt, time64_t last_refresh) { - struct nfs4_client *clp; - struct nfs4_openowner *oo; - struct nfs4_delegation *dp; + time64_t time_remaining; + + if (last_refresh < lt->cutoff) + return true; + time_remaining = last_refresh - lt->cutoff; + lt->new_timeo = min(lt->new_timeo, time_remaining); + return false; +} + +#ifdef CONFIG_NFSD_V4_2_INTER_SSC +void nfsd4_ssc_init_umount_work(struct nfsd_net *nn) +{ + spin_lock_init(&nn->nfsd_ssc_lock); + INIT_LIST_HEAD(&nn->nfsd_ssc_mount_list); + init_waitqueue_head(&nn->nfsd_ssc_waitq); +} + +/* + * This is called when nfsd is being shutdown, after all inter_ssc + * cleanup were done, to destroy the ssc delayed unmount list. + */ +static void nfsd4_ssc_shutdown_umount(struct nfsd_net *nn) +{ + struct nfsd4_ssc_umount_item *ni = NULL; + struct nfsd4_ssc_umount_item *tmp; + + spin_lock(&nn->nfsd_ssc_lock); + list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { + list_del(&ni->nsui_list); + spin_unlock(&nn->nfsd_ssc_lock); + mntput(ni->nsui_vfsmount); + kfree(ni); + spin_lock(&nn->nfsd_ssc_lock); + } + spin_unlock(&nn->nfsd_ssc_lock); +} + +static void nfsd4_ssc_expire_umount(struct nfsd_net *nn) +{ + bool do_wakeup = false; + struct nfsd4_ssc_umount_item *ni = NULL; + struct nfsd4_ssc_umount_item *tmp; + + spin_lock(&nn->nfsd_ssc_lock); + list_for_each_entry_safe(ni, tmp, &nn->nfsd_ssc_mount_list, nsui_list) { + if (time_after(jiffies, ni->nsui_expire)) { + if (refcount_read(&ni->nsui_refcnt) > 1) + continue; + + /* mark being unmount */ + ni->nsui_busy = true; + spin_unlock(&nn->nfsd_ssc_lock); + mntput(ni->nsui_vfsmount); + spin_lock(&nn->nfsd_ssc_lock); + + /* waiters need to start from begin of list */ + list_del(&ni->nsui_list); + kfree(ni); + + /* wakeup ssc_connect waiters */ + do_wakeup = true; + continue; + } + break; + } + if (do_wakeup) + wake_up_all(&nn->nfsd_ssc_waitq); + spin_unlock(&nn->nfsd_ssc_lock); +} +#endif + +/* Check if any lock belonging to this lockowner has any blockers */ +static bool +nfs4_lockowner_has_blockers(struct nfs4_lockowner *lo) +{ + struct file_lock_context *ctx; struct nfs4_ol_stateid *stp; - struct nfsd4_blocked_lock *nbl; - struct list_head *pos, *next, reaplist; - time_t cutoff = get_seconds() - nn->nfsd4_lease; - time_t t, new_timeo = nn->nfsd4_lease; + struct nfs4_file *nf; - dprintk("NFSD: laundromat service - starting\n"); + list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { + nf = stp->st_stid.sc_file; + ctx = locks_inode_context(nf->fi_inode); + if (!ctx) + continue; + if (locks_owner_has_blockers(ctx, lo)) + return true; + } + return false; +} - if (clients_still_reclaiming(nn)) { - new_timeo = 0; - goto out; +static bool +nfs4_anylock_blockers(struct nfs4_client *clp) +{ + int i; + struct nfs4_stateowner *so; + struct nfs4_lockowner *lo; + + if (atomic_read(&clp->cl_delegs_in_recall)) + return true; + spin_lock(&clp->cl_lock); + for (i = 0; i < OWNER_HASH_SIZE; i++) { + list_for_each_entry(so, &clp->cl_ownerstr_hashtbl[i], + so_strhash) { + if (so->so_is_open_owner) + continue; + lo = lockowner(so); + if (nfs4_lockowner_has_blockers(lo)) { + spin_unlock(&clp->cl_lock); + return true; + } + } } - nfsd4_end_grace(nn); - INIT_LIST_HEAD(&reaplist); + spin_unlock(&clp->cl_lock); + return false; +} + +static void +nfs4_get_client_reaplist(struct nfsd_net *nn, struct list_head *reaplist, + struct laundry_time *lt) +{ + unsigned int maxreap, reapcnt = 0; + struct list_head *pos, *next; + struct nfs4_client *clp; + + maxreap = (atomic_read(&nn->nfs4_client_count) >= nn->nfs4_max_clients) ? + NFSD_CLIENT_MAX_TRIM_PER_RUN : 0; + INIT_LIST_HEAD(reaplist); spin_lock(&nn->client_lock); list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); - if (time_after((unsigned long)clp->cl_time, (unsigned long)cutoff)) { - t = clp->cl_time - cutoff; - new_timeo = min(new_timeo, t); + if (clp->cl_state == NFSD4_EXPIRABLE) + goto exp_client; + if (!state_expired(lt, clp->cl_time)) break; + if (!atomic_read(&clp->cl_rpc_users)) { + if (clp->cl_state == NFSD4_ACTIVE) + atomic_inc(&nn->nfsd_courtesy_clients); + clp->cl_state = NFSD4_COURTESY; } - if (mark_client_expired_locked(clp)) { - dprintk("NFSD: client in use (clientid %08x)\n", - clp->cl_clientid.cl_id); - continue; + if (!client_has_state(clp)) + goto exp_client; + if (!nfs4_anylock_blockers(clp)) + if (reapcnt >= maxreap) + continue; +exp_client: + if (!mark_client_expired_locked(clp)) { + list_add(&clp->cl_lru, reaplist); + reapcnt++; } - list_add(&clp->cl_lru, &reaplist); } spin_unlock(&nn->client_lock); - list_for_each_safe(pos, next, &reaplist) { +} + +static void +nfs4_get_courtesy_client_reaplist(struct nfsd_net *nn, + struct list_head *reaplist) +{ + unsigned int maxreap = 0, reapcnt = 0; + struct list_head *pos, *next; + struct nfs4_client *clp; + + maxreap = NFSD_CLIENT_MAX_TRIM_PER_RUN; + INIT_LIST_HEAD(reaplist); + + spin_lock(&nn->client_lock); + list_for_each_safe(pos, next, &nn->client_lru) { clp = list_entry(pos, struct nfs4_client, cl_lru); - dprintk("NFSD: purging unused client (clientid %08x)\n", - clp->cl_clientid.cl_id); + if (clp->cl_state == NFSD4_ACTIVE) + break; + if (reapcnt >= maxreap) + break; + if (!mark_client_expired_locked(clp)) { + list_add(&clp->cl_lru, reaplist); + reapcnt++; + } + } + spin_unlock(&nn->client_lock); +} + +static void +nfs4_process_client_reaplist(struct list_head *reaplist) +{ + struct list_head *pos, *next; + struct nfs4_client *clp; + + list_for_each_safe(pos, next, reaplist) { + clp = list_entry(pos, struct nfs4_client, cl_lru); + trace_nfsd_clid_purged(&clp->cl_clientid); list_del_init(&clp->cl_lru); expire_client(clp); } +} + +static void nfs40_clean_admin_revoked(struct nfsd_net *nn, + struct laundry_time *lt) +{ + struct nfs4_client *clp; + + spin_lock(&nn->client_lock); + if (nn->nfs40_last_revoke == 0 || + nn->nfs40_last_revoke > lt->cutoff) { + spin_unlock(&nn->client_lock); + return; + } + nn->nfs40_last_revoke = 0; + +retry: + list_for_each_entry(clp, &nn->client_lru, cl_lru) { + unsigned long id, tmp; + struct nfs4_stid *stid; + + if (atomic_read(&clp->cl_admin_revoked) == 0) + continue; + + spin_lock(&clp->cl_lock); + idr_for_each_entry_ul(&clp->cl_stateids, stid, tmp, id) + if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { + refcount_inc(&stid->sc_count); + spin_unlock(&nn->client_lock); + /* this function drops ->cl_lock */ + nfsd4_drop_revoked_stid(stid); + nfs4_put_stid(stid); + spin_lock(&nn->client_lock); + goto retry; + } + spin_unlock(&clp->cl_lock); + } + spin_unlock(&nn->client_lock); +} + +static time64_t +nfs4_laundromat(struct nfsd_net *nn) +{ + struct nfs4_openowner *oo; + struct nfs4_delegation *dp; + struct nfs4_ol_stateid *stp; + struct nfsd4_blocked_lock *nbl; + struct list_head *pos, *next, reaplist; + struct laundry_time lt = { + .cutoff = ktime_get_boottime_seconds() - nn->nfsd4_lease, + .new_timeo = nn->nfsd4_lease + }; + struct nfs4_cpntf_state *cps; + copy_stateid_t *cps_t; + int i; + + if (clients_still_reclaiming(nn)) { + lt.new_timeo = 0; + goto out; + } + nfsd4_end_grace(nn); + + spin_lock(&nn->s2s_cp_lock); + idr_for_each_entry(&nn->s2s_cp_stateids, cps_t, i) { + cps = container_of(cps_t, struct nfs4_cpntf_state, cp_stateid); + if (cps->cp_stateid.cs_type == NFS4_COPYNOTIFY_STID && + state_expired(<, cps->cpntf_time)) + _free_cpntf_state_locked(nn, cps); + } + spin_unlock(&nn->s2s_cp_lock); + nfsd4_async_copy_reaper(nn); + nfs4_get_client_reaplist(nn, &reaplist, <); + nfs4_process_client_reaplist(&reaplist); + + nfs40_clean_admin_revoked(nn, <); + spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); - if (time_after((unsigned long)dp->dl_time, (unsigned long)cutoff)) { - t = dp->dl_time - cutoff; - new_timeo = min(new_timeo, t); + if (!state_expired(<, dp->dl_time)) break; - } - WARN_ON(!unhash_delegation_locked(dp)); + refcount_inc(&dp->dl_stid.sc_count); + unhash_delegation_locked(dp, SC_STATUS_REVOKED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); @@ -4817,12 +6914,8 @@ nfs4_laundromat(struct nfsd_net *nn) while (!list_empty(&nn->close_lru)) { oo = list_first_entry(&nn->close_lru, struct nfs4_openowner, oo_close_lru); - if (time_after((unsigned long)oo->oo_time, - (unsigned long)cutoff)) { - t = oo->oo_time - cutoff; - new_timeo = min(new_timeo, t); + if (!state_expired(<, oo->oo_time)) break; - } list_del_init(&oo->oo_close_lru); stp = oo->oo_last_closed_stid; oo->oo_last_closed_stid = NULL; @@ -4848,12 +6941,8 @@ nfs4_laundromat(struct nfsd_net *nn) while (!list_empty(&nn->blocked_locks_lru)) { nbl = list_first_entry(&nn->blocked_locks_lru, struct nfsd4_blocked_lock, nbl_lru); - if (time_after((unsigned long)nbl->nbl_time, - (unsigned long)cutoff)) { - t = nbl->nbl_time - cutoff; - new_timeo = min(new_timeo, t); + if (!state_expired(<, nbl->nbl_time)) break; - } list_move(&nbl->nbl_lru, &reaplist); list_del_init(&nbl->nbl_list); } @@ -4863,50 +6952,91 @@ nfs4_laundromat(struct nfsd_net *nn) nbl = list_first_entry(&reaplist, struct nfsd4_blocked_lock, nbl_lru); list_del_init(&nbl->nbl_lru); - locks_delete_block(&nbl->nbl_lock); free_blocked_lock(nbl); } +#ifdef CONFIG_NFSD_V4_2_INTER_SSC + /* service the server-to-server copy delayed unmount list */ + nfsd4_ssc_expire_umount(nn); +#endif + if (atomic_long_read(&num_delegations) >= max_delegations) + deleg_reaper(nn); out: - new_timeo = max_t(time_t, new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); - return new_timeo; + return max_t(time64_t, lt.new_timeo, NFSD_LAUNDROMAT_MINTIMEOUT); } -static struct workqueue_struct *laundry_wq; static void laundromat_main(struct work_struct *); static void laundromat_main(struct work_struct *laundry) { - time_t t; + time64_t t; struct delayed_work *dwork = to_delayed_work(laundry); struct nfsd_net *nn = container_of(dwork, struct nfsd_net, laundromat_work); t = nfs4_laundromat(nn); - dprintk("NFSD: laundromat_main - sleeping for %ld seconds\n", t); queue_delayed_work(laundry_wq, &nn->laundromat_work, t*HZ); } -static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) +static void +courtesy_client_reaper(struct nfsd_net *nn) { - if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) - return nfserr_bad_stateid; - return nfs_ok; + struct list_head reaplist; + + nfs4_get_courtesy_client_reaplist(nn, &reaplist); + nfs4_process_client_reaplist(&reaplist); } -static inline int -access_permit_read(struct nfs4_ol_stateid *stp) +static void +deleg_reaper(struct nfsd_net *nn) { - return test_access(NFS4_SHARE_ACCESS_READ, stp) || - test_access(NFS4_SHARE_ACCESS_BOTH, stp) || - test_access(NFS4_SHARE_ACCESS_WRITE, stp); + struct list_head *pos, *next; + struct nfs4_client *clp; + + spin_lock(&nn->client_lock); + list_for_each_safe(pos, next, &nn->client_lru) { + clp = list_entry(pos, struct nfs4_client, cl_lru); + + if (clp->cl_state != NFSD4_ACTIVE) + continue; + if (list_empty(&clp->cl_delegations)) + continue; + if (atomic_read(&clp->cl_delegs_in_recall)) + continue; + if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &clp->cl_ra->ra_cb.cb_flags)) + continue; + if (ktime_get_boottime_seconds() - clp->cl_ra_time < 5) + continue; + if (clp->cl_cb_state != NFSD4_CB_UP) + continue; + + /* release in nfsd4_cb_recall_any_release */ + kref_get(&clp->cl_nfsdfs.cl_ref); + clp->cl_ra_time = ktime_get_boottime_seconds(); + clp->cl_ra->ra_keep = 0; + clp->cl_ra->ra_bmval[0] = BIT(RCA4_TYPE_MASK_RDATA_DLG) | + BIT(RCA4_TYPE_MASK_WDATA_DLG); + trace_nfsd_cb_recall_any(clp->cl_ra); + nfsd4_run_cb(&clp->cl_ra->ra_cb); + } + spin_unlock(&nn->client_lock); } -static inline int -access_permit_write(struct nfs4_ol_stateid *stp) +static void +nfsd4_state_shrinker_worker(struct work_struct *work) { - return test_access(NFS4_SHARE_ACCESS_WRITE, stp) || - test_access(NFS4_SHARE_ACCESS_BOTH, stp); + struct nfsd_net *nn = container_of(work, struct nfsd_net, + nfsd_shrinker_work); + + courtesy_client_reaper(nn); + deleg_reaper(nn); +} + +static inline __be32 nfs4_check_fh(struct svc_fh *fhp, struct nfs4_stid *stp) +{ + if (!fh_match(&fhp->fh_handle, &stp->sc_file->fi_fhandle)) + return nfserr_bad_stateid; + return nfs_ok; } static @@ -4943,16 +7073,6 @@ check_special_stateids(struct net *net, svc_fh *current_fh, stateid_t *stateid, NFS4_SHARE_DENY_READ); } -/* - * Allow READ/WRITE during grace period on recovered state only for files - * that are not able to provide mandatory locking. - */ -static inline int -grace_disallows_io(struct net *net, struct inode *inode) -{ - return opens_in_grace(net) && mandatory_lock(inode); -} - static __be32 check_stateid_generation(stateid_t *in, stateid_t *ref, bool has_session) { /* @@ -4990,6 +7110,9 @@ static __be32 nfsd4_stid_check_stateid_generation(stateid_t *in, struct nfs4_sti if (ret == nfs_ok) ret = check_stateid_generation(in, &s->sc_stateid, has_session); spin_unlock(&s->sc_lock); + if (ret == nfserr_admin_revoked) + nfsd40_drop_revoked_stid(s->sc_client, + &s->sc_stateid); return ret; } @@ -5009,15 +7132,6 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) return status; - /* Client debugging aid. */ - if (!same_clid(&stateid->si_opaque.so_clid, &cl->cl_clientid)) { - char addr_str[INET6_ADDRSTRLEN]; - rpc_ntop((struct sockaddr *)&cl->cl_addr, addr_str, - sizeof(addr_str)); - pr_warn_ratelimited("NFSD: client %s testing state ID " - "with incorrect client ID\n", addr_str); - return status; - } spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, stateid); if (!s) @@ -5025,50 +7139,57 @@ static __be32 nfsd4_validate_stateid(struct nfs4_client *cl, stateid_t *stateid) status = nfsd4_stid_check_stateid_generation(stateid, s, 1); if (status) goto out_unlock; + status = nfsd4_verify_open_stid(s); + if (status) + goto out_unlock; + switch (s->sc_type) { - case NFS4_DELEG_STID: + case SC_TYPE_DELEG: status = nfs_ok; break; - case NFS4_REVOKED_DELEG_STID: - status = nfserr_deleg_revoked; - break; - case NFS4_OPEN_STID: - case NFS4_LOCK_STID: + case SC_TYPE_OPEN: + case SC_TYPE_LOCK: status = nfsd4_check_openowner_confirmed(openlockstateid(s)); break; default: printk("unknown stateid type %x\n", s->sc_type); - /* Fallthrough */ - case NFS4_CLOSED_STID: - case NFS4_CLOSED_DELEG_STID: status = nfserr_bad_stateid; } out_unlock: spin_unlock(&cl->cl_lock); + if (status == nfserr_admin_revoked) + nfsd40_drop_revoked_stid(cl, stateid); return status; } __be32 nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, - stateid_t *stateid, unsigned char typemask, + stateid_t *stateid, + unsigned short typemask, unsigned short statusmask, struct nfs4_stid **s, struct nfsd_net *nn) { __be32 status; + struct nfs4_stid *stid; bool return_revoked = false; /* * only return revoked delegations if explicitly asked. * otherwise we report revoked or bad_stateid status. */ - if (typemask & NFS4_REVOKED_DELEG_STID) + if (statusmask & SC_STATUS_REVOKED) return_revoked = true; - else if (typemask & NFS4_DELEG_STID) - typemask |= NFS4_REVOKED_DELEG_STID; + if (typemask & SC_TYPE_DELEG) + /* Always allow REVOKED for DELEG so we can + * return the appropriate error. + */ + statusmask |= SC_STATUS_REVOKED; + + statusmask |= SC_STATUS_ADMIN_REVOKED | SC_STATUS_FREEABLE; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid) || CLOSE_STATEID(stateid)) return nfserr_bad_stateid; - status = lookup_clientid(&stateid->si_opaque.so_clid, cstate, nn); + status = set_client(&stateid->si_opaque.so_clid, cstate, nn); if (status == nfserr_stale_clientid) { if (cstate->session) return nfserr_bad_stateid; @@ -5076,39 +7197,41 @@ nfsd4_lookup_stateid(struct nfsd4_compound_state *cstate, } if (status) return status; - *s = find_stateid_by_type(cstate->clp, stateid, typemask); - if (!*s) - return nfserr_bad_stateid; - if (((*s)->sc_type == NFS4_REVOKED_DELEG_STID) && !return_revoked) { - nfs4_put_stid(*s); - if (cstate->minorversion) - return nfserr_deleg_revoked; + stid = find_stateid_by_type(cstate->clp, stateid, typemask, statusmask); + if (!stid) return nfserr_bad_stateid; + if ((stid->sc_status & SC_STATUS_REVOKED) && !return_revoked) { + nfs4_put_stid(stid); + return nfserr_deleg_revoked; + } + if (stid->sc_status & SC_STATUS_ADMIN_REVOKED) { + nfsd40_drop_revoked_stid(cstate->clp, stateid); + nfs4_put_stid(stid); + return nfserr_admin_revoked; } + *s = stid; return nfs_ok; } -static struct file * +static struct nfsd_file * nfs4_find_file(struct nfs4_stid *s, int flags) { - if (!s) + struct nfsd_file *ret = NULL; + + if (!s || s->sc_status) return NULL; switch (s->sc_type) { - case NFS4_DELEG_STID: - if (WARN_ON_ONCE(!s->sc_file->fi_deleg_file)) - return NULL; - return get_file(s->sc_file->fi_deleg_file); - case NFS4_OPEN_STID: - case NFS4_LOCK_STID: + case SC_TYPE_DELEG: + case SC_TYPE_OPEN: + case SC_TYPE_LOCK: 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); - break; + ret = find_writeable_file(s->sc_file); } - return NULL; + return ret; } static __be32 @@ -5124,55 +7247,144 @@ nfs4_check_olstateid(struct nfs4_ol_stateid *ols, int flags) static __be32 nfs4_check_file(struct svc_rqst *rqstp, struct svc_fh *fhp, struct nfs4_stid *s, - struct file **filpp, bool *tmp_file, int flags) + struct nfsd_file **nfp, int flags) { int acc = (flags & RD_STATE) ? NFSD_MAY_READ : NFSD_MAY_WRITE; - struct file *file; + struct nfsd_file *nf; __be32 status; - file = nfs4_find_file(s, flags); - if (file) { - status = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry, + nf = nfs4_find_file(s, flags); + if (nf) { + status = nfsd_permission(&rqstp->rq_cred, + fhp->fh_export, fhp->fh_dentry, acc | NFSD_MAY_OWNER_OVERRIDE); if (status) { - fput(file); - return status; + nfsd_file_put(nf); + goto out; } - - *filpp = file; } else { - status = nfsd_open(rqstp, fhp, S_IFREG, acc, filpp); + status = nfsd_file_acquire(rqstp, fhp, acc, &nf); if (status) return status; - - if (tmp_file) - *tmp_file = true; } + *nfp = nf; +out: + return status; +} +static void +_free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) +{ + WARN_ON_ONCE(cps->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID); + if (!refcount_dec_and_test(&cps->cp_stateid.cs_count)) + return; + list_del(&cps->cp_list); + idr_remove(&nn->s2s_cp_stateids, + cps->cp_stateid.cs_stid.si_opaque.so_id); + kfree(cps); +} +/* + * A READ from an inter server to server COPY will have a + * copy stateid. Look up the copy notify stateid from the + * idr structure and take a reference on it. + */ +__be32 manage_cpntf_state(struct nfsd_net *nn, stateid_t *st, + struct nfs4_client *clp, + struct nfs4_cpntf_state **cps) +{ + copy_stateid_t *cps_t; + struct nfs4_cpntf_state *state = NULL; + if (st->si_opaque.so_clid.cl_id != nn->s2s_cp_cl_id) + return nfserr_bad_stateid; + spin_lock(&nn->s2s_cp_lock); + cps_t = idr_find(&nn->s2s_cp_stateids, st->si_opaque.so_id); + if (cps_t) { + state = container_of(cps_t, struct nfs4_cpntf_state, + cp_stateid); + if (state->cp_stateid.cs_type != NFS4_COPYNOTIFY_STID) { + state = NULL; + goto unlock; + } + if (!clp) + refcount_inc(&state->cp_stateid.cs_count); + else + _free_cpntf_state_locked(nn, state); + } +unlock: + spin_unlock(&nn->s2s_cp_lock); + if (!state) + return nfserr_bad_stateid; + if (!clp) + *cps = state; return 0; } -/* - * Checks for stateid operations +static __be32 find_cpntf_state(struct nfsd_net *nn, stateid_t *st, + struct nfs4_stid **stid) +{ + __be32 status; + struct nfs4_cpntf_state *cps = NULL; + struct nfs4_client *found; + + status = manage_cpntf_state(nn, st, NULL, &cps); + if (status) + return status; + + cps->cpntf_time = ktime_get_boottime_seconds(); + + status = nfserr_expired; + found = lookup_clientid(&cps->cp_p_clid, true, nn); + if (!found) + goto out; + + *stid = find_stateid_by_type(found, &cps->cp_p_stateid, + SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK, + 0); + if (*stid) + status = nfs_ok; + else + status = nfserr_bad_stateid; + + put_client_renew(found); +out: + nfs4_put_cpntf_state(nn, cps); + return status; +} + +void nfs4_put_cpntf_state(struct nfsd_net *nn, struct nfs4_cpntf_state *cps) +{ + spin_lock(&nn->s2s_cp_lock); + _free_cpntf_state_locked(nn, cps); + spin_unlock(&nn->s2s_cp_lock); +} + +/** + * 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, struct nfsd4_compound_state *cstate, struct svc_fh *fhp, - stateid_t *stateid, int flags, struct file **filpp, bool *tmp_file) + stateid_t *stateid, int flags, struct nfsd_file **nfp, + struct nfs4_stid **cstid) { - struct inode *ino = d_inode(fhp->fh_dentry); struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct nfs4_stid *s = NULL; __be32 status; - if (filpp) - *filpp = NULL; - if (tmp_file) - *tmp_file = false; - - if (grace_disallows_io(net, ino)) - return nfserr_grace; + if (nfp) + *nfp = NULL; if (ZERO_STATEID(stateid) || ONE_STATEID(stateid)) { status = check_special_stateids(net, fhp, stateid, flags); @@ -5180,8 +7392,10 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, } status = nfsd4_lookup_stateid(cstate, stateid, - NFS4_DELEG_STID|NFS4_OPEN_STID|NFS4_LOCK_STID, - &s, nn); + SC_TYPE_DELEG|SC_TYPE_OPEN|SC_TYPE_LOCK, + 0, &s, nn); + if (status == nfserr_bad_stateid) + status = find_cpntf_state(nn, stateid, &s); if (status) return status; status = nfsd4_stid_check_stateid_generation(stateid, s, @@ -5190,27 +7404,28 @@ nfs4_preprocess_stateid_op(struct svc_rqst *rqstp, goto out; switch (s->sc_type) { - case NFS4_DELEG_STID: + case SC_TYPE_DELEG: status = nfs4_check_delegmode(delegstateid(s), flags); break; - case NFS4_OPEN_STID: - case NFS4_LOCK_STID: + case SC_TYPE_OPEN: + case SC_TYPE_LOCK: status = nfs4_check_olstateid(openlockstateid(s), flags); break; - default: - status = nfserr_bad_stateid; - break; } if (status) goto out; status = nfs4_check_fh(fhp, s); done: - if (!status && filpp) - status = nfs4_check_file(rqstp, fhp, s, filpp, tmp_file, flags); + if (status == nfs_ok && nfp) + status = nfs4_check_file(rqstp, fhp, s, nfp, flags); out: - if (s) - nfs4_put_stid(s); + if (s) { + if (!status && cstid) + *cstid = s; + else + nfs4_put_stid(s); + } return status; } @@ -5223,7 +7438,7 @@ nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, { struct nfsd4_test_stateid *test_stateid = &u->test_stateid; struct nfsd4_test_stateid_id *stateid; - struct nfs4_client *cl = cstate->session->se_client; + struct nfs4_client *cl = cstate->clp; list_for_each_entry(stateid, &test_stateid->ts_stateid_list, ts_id_list) stateid->ts_id_status = @@ -5269,39 +7484,47 @@ nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stateid_t *stateid = &free_stateid->fr_stateid; struct nfs4_stid *s; struct nfs4_delegation *dp; - struct nfs4_client *cl = cstate->session->se_client; + struct nfs4_client *cl = cstate->clp; __be32 ret = nfserr_bad_stateid; spin_lock(&cl->cl_lock); s = find_stateid_locked(cl, stateid); - if (!s) + if (!s || s->sc_status & SC_STATUS_CLOSED) goto out_unlock; + if (s->sc_status & SC_STATUS_ADMIN_REVOKED) { + nfsd4_drop_revoked_stid(s); + ret = nfs_ok; + goto out; + } spin_lock(&s->sc_lock); switch (s->sc_type) { - case NFS4_DELEG_STID: + case SC_TYPE_DELEG: + if (s->sc_status & SC_STATUS_REVOKED) { + s->sc_status |= SC_STATUS_CLOSED; + spin_unlock(&s->sc_lock); + dp = delegstateid(s); + if (s->sc_status & SC_STATUS_FREEABLE) + list_del_init(&dp->dl_recall_lru); + s->sc_status |= SC_STATUS_FREED; + spin_unlock(&cl->cl_lock); + nfs4_put_stid(s); + ret = nfs_ok; + goto out; + } ret = nfserr_locks_held; break; - case NFS4_OPEN_STID: + case SC_TYPE_OPEN: ret = check_stateid_generation(stateid, &s->sc_stateid, 1); if (ret) break; ret = nfserr_locks_held; break; - case NFS4_LOCK_STID: + case SC_TYPE_LOCK: spin_unlock(&s->sc_lock); refcount_inc(&s->sc_count); spin_unlock(&cl->cl_lock); ret = nfsd4_free_lock_stateid(stateid, s); goto out; - case NFS4_REVOKED_DELEG_STID: - spin_unlock(&s->sc_lock); - dp = delegstateid(s); - list_del_init(&dp->dl_recall_lru); - spin_unlock(&cl->cl_lock); - nfs4_put_stid(s); - ret = nfs_ok; - goto out; - /* Default falls through and returns nfserr_bad_stateid */ } spin_unlock(&s->sc_lock); out_unlock: @@ -5337,12 +7560,24 @@ 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 + * @statusmask: mask of allowed states: 0 or STID_CLOSED + * @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, - stateid_t *stateid, char typemask, + stateid_t *stateid, + unsigned short typemask, unsigned short statusmask, struct nfs4_ol_stateid **stpp, struct nfsd_net *nn) { @@ -5350,15 +7585,19 @@ nfs4_preprocess_seqid_op(struct nfsd4_compound_state *cstate, u32 seqid, struct nfs4_stid *s; struct nfs4_ol_stateid *stp = NULL; - dprintk("NFSD: %s: seqid=%d stateid = " STATEID_FMT "\n", __func__, - seqid, STATEID_VAL(stateid)); + trace_nfsd_preprocess(seqid, stateid); *stpp = NULL; - status = nfsd4_lookup_stateid(cstate, stateid, typemask, &s, nn); +retry: + status = nfsd4_lookup_stateid(cstate, stateid, + typemask, statusmask, &s, nn); if (status) return status; stp = openlockstateid(s); - nfsd4_cstate_assign_replay(cstate, stp->st_stateowner); + if (nfsd4_cstate_assign_replay(cstate, stp->st_stateowner) == -EAGAIN) { + nfs4_put_stateowner(stp->st_stateowner); + goto retry; + } status = nfs4_seqid_op_checks(cstate, stateid, seqid, stp); if (!status) @@ -5376,7 +7615,7 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs struct nfs4_ol_stateid *stp; status = nfs4_preprocess_seqid_op(cstate, seqid, stateid, - NFS4_OPEN_STID, &stp, nn); + SC_TYPE_OPEN, 0, &stp, nn); if (status) return status; oo = openowner(stp->st_stateowner); @@ -5407,8 +7646,8 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return status; status = nfs4_preprocess_seqid_op(cstate, - oc->oc_seqid, &oc->oc_req_stateid, - NFS4_OPEN_STID, &stp, nn); + oc->oc_seqid, &oc->oc_req_stateid, + SC_TYPE_OPEN, 0, &stp, nn); if (status) goto out; oo = openowner(stp->st_stateowner); @@ -5420,9 +7659,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, oo->oo_flags |= NFS4_OO_CONFIRMED; nfs4_inc_and_copy_stateid(&oc->oc_resp_stateid, &stp->st_stid); mutex_unlock(&stp->st_mutex); - dprintk("NFSD: %s: success, seqid=%d stateid=" STATEID_FMT "\n", - __func__, oc->oc_seqid, STATEID_VAL(&stp->st_stid.sc_stateid)); - + trace_nfsd_open_confirm(oc->oc_seqid, &stp->st_stid.sc_stateid); nfsd4_client_record_create(oo->oo_owner.so_client); status = nfs_ok; put_stateid: @@ -5502,11 +7739,12 @@ out: return status; } -static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) +static bool nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) { struct nfs4_client *clp = s->st_stid.sc_client; bool unhashed; LIST_HEAD(reaplist); + struct nfs4_ol_stateid *stp; spin_lock(&clp->cl_lock); unhashed = unhash_open_stateid(s, &reaplist); @@ -5515,12 +7753,14 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s) if (unhashed) put_ol_stateid_locked(s, &reaplist); spin_unlock(&clp->cl_lock); + list_for_each_entry(stp, &reaplist, st_locks) + nfs4_free_cpntf_statelist(clp->net, &stp->st_stid); free_ol_stateid_reaplist(&reaplist); + return false; } else { spin_unlock(&clp->cl_lock); free_ol_stateid_reaplist(&reaplist); - if (unhashed) - move_to_close_lru(s, clp->net); + return unhashed; } } @@ -5536,19 +7776,22 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *stp; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); + bool need_move_to_close_list; - dprintk("NFSD: nfsd4_close on file %pd\n", + dprintk("NFSD: nfsd4_close on file %pd\n", cstate->current_fh.fh_dentry); status = nfs4_preprocess_seqid_op(cstate, close->cl_seqid, - &close->cl_stateid, - NFS4_OPEN_STID|NFS4_CLOSED_STID, - &stp, nn); + &close->cl_stateid, + SC_TYPE_OPEN, SC_STATUS_CLOSED, + &stp, nn); nfsd4_bump_seqid(cstate, status); if (status) - goto out; + goto out; - stp->st_stid.sc_type = NFS4_CLOSED_STID; + spin_lock(&stp->st_stid.sc_client->cl_lock); + stp->st_stid.sc_status |= SC_STATUS_CLOSED; + spin_unlock(&stp->st_stid.sc_client->cl_lock); /* * Technically we don't _really_ have to increment or copy it, since @@ -5558,8 +7801,10 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, */ nfs4_inc_and_copy_stateid(&close->cl_stateid, &stp->st_stid); - nfsd4_close_open_stateid(stp); + need_move_to_close_list = nfsd4_close_open_stateid(stp); mutex_unlock(&stp->st_mutex); + if (need_move_to_close_list) + move_to_close_lru(stp, net); /* v4.1+ suggests that we send a special stateid in here, since the * clients should just ignore this anyway. Since this is not useful @@ -5587,10 +7832,11 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, __be32 status; struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); - if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0))) + status = fh_verify(rqstp, &cstate->current_fh, 0, 0); + if (status) return status; - status = nfsd4_lookup_stateid(cstate, stateid, NFS4_DELEG_STID, &s, nn); + status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, SC_STATUS_REVOKED, &s, nn); if (status) goto out; dp = delegstateid(s); @@ -5598,22 +7844,16 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto put_stateid; + trace_nfsd_deleg_return(stateid); destroy_delegation(dp); + smp_mb__after_atomic(); + wake_up_var(d_inode(cstate->current_fh.fh_dentry)); put_stateid: nfs4_put_stid(&dp->dl_stid); out: return status; } -static inline u64 -end_offset(u64 start, u64 len) -{ - u64 end; - - end = start + len; - return end >= start ? end: NFS4_MAX_UINT64; -} - /* last octet in a range */ static inline u64 last_byte_offset(u64 start, u64 len) @@ -5643,7 +7883,7 @@ nfs4_transform_lock_offset(struct file_lock *lock) } static fl_owner_t -nfsd4_fl_get_owner(fl_owner_t owner) +nfsd4_lm_get_owner(fl_owner_t owner) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; @@ -5652,7 +7892,7 @@ nfsd4_fl_get_owner(fl_owner_t owner) } static void -nfsd4_fl_put_owner(fl_owner_t owner) +nfsd4_lm_put_owner(fl_owner_t owner) { struct nfs4_lockowner *lo = (struct nfs4_lockowner *)owner; @@ -5660,10 +7900,33 @@ nfsd4_fl_put_owner(fl_owner_t owner) nfs4_put_stateowner(&lo->lo_owner); } +/* return pointer to struct nfs4_client if client is expirable */ +static bool +nfsd4_lm_lock_expirable(struct file_lock *cfl) +{ + struct nfs4_lockowner *lo = (struct nfs4_lockowner *) cfl->c.flc_owner; + struct nfs4_client *clp = lo->lo_owner.so_client; + struct nfsd_net *nn; + + if (try_to_expire_client(clp)) { + nn = net_generic(clp->net, nfsd_net_id); + mod_delayed_work(laundry_wq, &nn->laundromat_work, 0); + return true; + } + return false; +} + +/* schedule laundromat to run immediately and wait for it to complete */ +static void +nfsd4_lm_expire_lock(void) +{ + flush_workqueue(laundry_wq); +} + static void nfsd4_lm_notify(struct file_lock *fl) { - struct nfs4_lockowner *lo = (struct nfs4_lockowner *)fl->fl_owner; + struct nfs4_lockowner *lo = (struct nfs4_lockowner *) fl->c.flc_owner; struct net *net = lo->lo_owner.so_client->net; struct nfsd_net *nn = net_generic(net, nfsd_net_id); struct nfsd4_blocked_lock *nbl = container_of(fl, @@ -5679,14 +7942,19 @@ nfsd4_lm_notify(struct file_lock *fl) } spin_unlock(&nn->blocked_locks_lock); - if (queue) - nfsd4_run_cb(&nbl->nbl_cb); + if (queue) { + trace_nfsd_cb_notify_lock(lo, nbl); + nfsd4_try_run_cb(&nbl->nbl_cb); + } } static const struct lock_manager_operations nfsd_posix_mng_ops = { + .lm_mod_owner = THIS_MODULE, .lm_notify = nfsd4_lm_notify, - .lm_get_owner = nfsd4_fl_get_owner, - .lm_put_owner = nfsd4_fl_put_owner, + .lm_get_owner = nfsd4_lm_get_owner, + .lm_put_owner = nfsd4_lm_put_owner, + .lm_lock_expirable = nfsd4_lm_lock_expirable, + .lm_expire_lock = nfsd4_lm_expire_lock, }; static inline void @@ -5695,13 +7963,12 @@ nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny) struct nfs4_lockowner *lo; if (fl->fl_lmops == &nfsd_posix_mng_ops) { - lo = (struct nfs4_lockowner *) fl->fl_owner; - deny->ld_owner.data = kmemdup(lo->lo_owner.so_owner.data, - lo->lo_owner.so_owner.len, GFP_KERNEL); + lo = (struct nfs4_lockowner *) fl->c.flc_owner; + xdr_netobj_dup(&deny->ld_owner, &lo->lo_owner.so_owner, + GFP_KERNEL); if (!deny->ld_owner.data) /* We just don't care that much */ goto nevermind; - deny->ld_owner.len = lo->lo_owner.so_owner.len; deny->ld_clientid = lo->lo_owner.so_client->cl_clientid; } else { nevermind: @@ -5715,7 +7982,7 @@ nevermind: if (fl->fl_end != NFS4_MAX_UINT64) deny->ld_length = fl->fl_end - fl->fl_start + 1; deny->ld_type = NFS4_READ_LT; - if (fl->fl_type != F_RDLCK) + if (fl->c.flc_type != F_RDLCK) deny->ld_type = NFS4_WRITE_LT; } @@ -5801,21 +8068,21 @@ alloc_init_lock_stateowner(unsigned int strhashval, struct nfs4_client *clp, } static struct nfs4_ol_stateid * -find_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fp) +find_lock_stateid(const struct nfs4_lockowner *lo, + const struct nfs4_ol_stateid *ost) { struct nfs4_ol_stateid *lst; - struct nfs4_client *clp = lo->lo_owner.so_client; - lockdep_assert_held(&clp->cl_lock); + lockdep_assert_held(&ost->st_stid.sc_client->cl_lock); - list_for_each_entry(lst, &lo->lo_owner.so_stateids, st_perstateowner) { - if (lst->st_stid.sc_type != NFS4_LOCK_STID) - continue; - if (lst->st_stid.sc_file == fp) { - refcount_inc(&lst->st_stid.sc_count); - return lst; + /* If ost is not hashed, ost->st_locks will not be valid */ + if (!nfs4_ol_stateid_unhashed(ost)) + list_for_each_entry(lst, &ost->st_locks, st_locks) { + if (lst->st_stateowner == &lo->lo_owner) { + refcount_inc(&lst->st_stid.sc_count); + return lst; + } } - } return NULL; } @@ -5831,35 +8098,39 @@ init_lock_stateid(struct nfs4_ol_stateid *stp, struct nfs4_lockowner *lo, mutex_lock_nested(&stp->st_mutex, OPEN_STATEID_MUTEX); retry: spin_lock(&clp->cl_lock); - spin_lock(&fp->fi_lock); - retstp = find_lock_stateid(lo, fp); + if (nfs4_ol_stateid_unhashed(open_stp)) + goto out_close; + retstp = find_lock_stateid(lo, open_stp); if (retstp) - goto out_unlock; - + goto out_found; refcount_inc(&stp->st_stid.sc_count); - stp->st_stid.sc_type = NFS4_LOCK_STID; + stp->st_stid.sc_type = SC_TYPE_LOCK; stp->st_stateowner = nfs4_get_stateowner(&lo->lo_owner); get_nfs4_file(fp); stp->st_stid.sc_file = fp; stp->st_access_bmap = 0; stp->st_deny_bmap = open_stp->st_deny_bmap; stp->st_openstp = open_stp; + spin_lock(&fp->fi_lock); list_add(&stp->st_locks, &open_stp->st_locks); list_add(&stp->st_perstateowner, &lo->lo_owner.so_stateids); list_add(&stp->st_perfile, &fp->fi_stateids); -out_unlock: spin_unlock(&fp->fi_lock); spin_unlock(&clp->cl_lock); - if (retstp) { - if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { - nfs4_put_stid(&retstp->st_stid); - goto retry; - } - /* To keep mutex tracking happy */ - mutex_unlock(&stp->st_mutex); - stp = retstp; - } return stp; +out_found: + spin_unlock(&clp->cl_lock); + if (nfsd4_lock_ol_stateid(retstp) != nfs_ok) { + nfs4_put_stid(&retstp->st_stid); + goto retry; + } + /* To keep mutex tracking happy */ + mutex_unlock(&stp->st_mutex); + return retstp; +out_close: + spin_unlock(&clp->cl_lock); + mutex_unlock(&stp->st_mutex); + return NULL; } static struct nfs4_ol_stateid * @@ -5874,7 +8145,7 @@ find_or_create_lock_stateid(struct nfs4_lockowner *lo, struct nfs4_file *fi, *new = false; spin_lock(&clp->cl_lock); - lst = find_lock_stateid(lo, fi); + lst = find_lock_stateid(lo, ost); spin_unlock(&clp->cl_lock); if (lst != NULL) { if (nfsd4_lock_ol_stateid(lst) == nfs_ok) @@ -5968,7 +8239,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfs4_ol_stateid *lock_stp = NULL; struct nfs4_ol_stateid *open_stp = NULL; struct nfs4_file *fp; - struct file *filp = NULL; + struct nfsd_file *nf = NULL; struct nfsd4_blocked_lock *nbl = NULL; struct file_lock *file_lock = NULL; struct file_lock *conflock = NULL; @@ -5976,8 +8247,8 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, int lkflg; int err; bool new = false; - unsigned char fl_type; - unsigned int fl_flags = FL_POSIX; + unsigned char type; + unsigned int flags = FL_POSIX; struct net *net = SVC_NET(rqstp); struct nfsd_net *nn = net_generic(net, nfsd_net_id); @@ -5988,23 +8259,21 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (check_lock_length(lock->lk_offset, lock->lk_length)) return nfserr_inval; - if ((status = fh_verify(rqstp, &cstate->current_fh, - S_IFREG, NFSD_MAY_LOCK))) { - dprintk("NFSD: nfsd4_lock: permission denied!\n"); + status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0); + if (status != nfs_ok) return status; + if (exportfs_cannot_lock(cstate->current_fh.fh_dentry->d_sb->s_export_op)) { + status = nfserr_notsupp; + goto out; } if (lock->lk_is_new) { if (nfsd4_has_session(cstate)) /* See rfc 5661 18.10.3: given clientid is ignored: */ memcpy(&lock->lk_new_clientid, - &cstate->session->se_client->cl_clientid, + &cstate->clp->cl_clientid, sizeof(clientid_t)); - status = nfserr_stale_clientid; - if (STALE_CLIENTID(&lock->lk_new_clientid, nn)) - goto out; - /* validate and update open stateid and open seqid */ status = nfs4_preprocess_confirmed_seqid_op(cstate, lock->lk_new_open_seqid, @@ -6022,9 +8291,10 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, &lock_stp, &new); } else { status = nfs4_preprocess_seqid_op(cstate, - lock->lk_old_lock_seqid, - &lock->lk_old_lock_stateid, - NFS4_LOCK_STID, &lock_stp, nn); + lock->lk_old_lock_seqid, + &lock->lk_old_lock_stateid, + SC_TYPE_LOCK, 0, &lock_stp, + nn); } if (status) goto out; @@ -6042,42 +8312,46 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (!locks_in_grace(net) && lock->lk_reclaim) goto out; + if (lock->lk_reclaim) + flags |= FL_RECLAIM; + fp = lock_stp->st_stid.sc_file; switch (lock->lk_type) { case NFS4_READW_LT: - if (nfsd4_has_session(cstate)) - fl_flags |= FL_SLEEP; - /* Fallthrough */ + fallthrough; case NFS4_READ_LT: spin_lock(&fp->fi_lock); - filp = find_readable_file_locked(fp); - if (filp) + nf = find_readable_file_locked(fp); + if (nf) get_lock_access(lock_stp, NFS4_SHARE_ACCESS_READ); spin_unlock(&fp->fi_lock); - fl_type = F_RDLCK; + type = F_RDLCK; break; case NFS4_WRITEW_LT: - if (nfsd4_has_session(cstate)) - fl_flags |= FL_SLEEP; - /* Fallthrough */ + fallthrough; case NFS4_WRITE_LT: spin_lock(&fp->fi_lock); - filp = find_writeable_file_locked(fp); - if (filp) + nf = find_writeable_file_locked(fp); + if (nf) get_lock_access(lock_stp, NFS4_SHARE_ACCESS_WRITE); spin_unlock(&fp->fi_lock); - fl_type = F_WRLCK; + type = F_WRLCK; break; default: status = nfserr_inval; goto out; } - if (!filp) { + if (!nf) { status = nfserr_openmode; goto out; } + if (lock->lk_type & (NFS4_READW_LT | NFS4_WRITEW_LT) && + nfsd4_has_session(cstate) && + locks_can_async_lock(nf->nf_file->f_op)) + flags |= FL_SLEEP; + nbl = find_or_allocate_block(lock_sop, &fp->fi_fhandle, nn); if (!nbl) { dprintk("NFSD: %s: unable to allocate block!\n", __func__); @@ -6086,11 +8360,11 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, } file_lock = &nbl->nbl_lock; - file_lock->fl_type = fl_type; - file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner)); - file_lock->fl_pid = current->tgid; - file_lock->fl_file = filp; - file_lock->fl_flags = fl_flags; + file_lock->c.flc_type = type; + file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(&lock_sop->lo_owner)); + file_lock->c.flc_pid = current->tgid; + file_lock->c.flc_file = nf->nf_file; + file_lock->c.flc_flags = flags; file_lock->fl_lmops = &nfsd_posix_mng_ops; file_lock->fl_start = lock->lk_offset; file_lock->fl_end = last_byte_offset(lock->lk_offset, lock->lk_length); @@ -6103,15 +8377,16 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, goto out; } - if (fl_flags & FL_SLEEP) { - nbl->nbl_time = jiffies; + if (flags & FL_SLEEP) { + nbl->nbl_time = ktime_get_boottime_seconds(); spin_lock(&nn->blocked_locks_lock); list_add_tail(&nbl->nbl_list, &lock_sop->lo_blocked); list_add_tail(&nbl->nbl_lru, &nn->blocked_locks_lru); + kref_get(&nbl->nbl_kref); spin_unlock(&nn->blocked_locks_lock); } - err = vfs_lock_file(filp, F_SETLK, file_lock, conflock); + err = vfs_lock_file(nf->nf_file, F_SETLK, file_lock, conflock); switch (err) { case 0: /* success! */ nfs4_inc_and_copy_stateid(&lock->lk_resp_stateid, &lock_stp->st_stid); @@ -6120,8 +8395,9 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, nn->somebody_reclaimed = true; break; case FILE_LOCK_DEFERRED: + kref_put(&nbl->nbl_kref, free_nbl); nbl = NULL; - /* Fallthrough */ + fallthrough; case -EAGAIN: /* conflock holds conflicting lock */ status = nfserr_denied; dprintk("NFSD: nfsd4_lock: conflicting lock found!\n"); @@ -6138,16 +8414,21 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, out: if (nbl) { /* dequeue it if we queued it before */ - if (fl_flags & FL_SLEEP) { + if (flags & FL_SLEEP) { spin_lock(&nn->blocked_locks_lock); - list_del_init(&nbl->nbl_list); - list_del_init(&nbl->nbl_lru); + if (!list_empty(&nbl->nbl_list) && + !list_empty(&nbl->nbl_lru)) { + list_del_init(&nbl->nbl_list); + list_del_init(&nbl->nbl_lru); + kref_put(&nbl->nbl_kref, free_nbl); + } + /* nbl can use one of lists to be linked to reaplist */ spin_unlock(&nn->blocked_locks_lock); } free_blocked_lock(nbl); } - if (filp) - fput(filp); + if (nf) + nfsd_file_put(nf); if (lock_stp) { /* Bump seqid manually if the 4.0 replay owner is openowner */ if (cstate->replay_owner && @@ -6174,20 +8455,39 @@ out: return status; } +void nfsd4_lock_release(union nfsd4_op_u *u) +{ + struct nfsd4_lock *lock = &u->lock; + struct nfsd4_lock_denied *deny = &lock->lk_denied; + + kfree(deny->ld_owner.data); +} + /* * The NFSv4 spec allows a client to do a LOCKT without holding an OPEN, * so we do a temporary open here just to get an open file to pass to - * vfs_test_lock. (Arguably perhaps test_lock should be done with an - * inode operation.) + * vfs_test_lock. */ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock) { - struct file *file; - __be32 err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file); - if (!err) { - err = nfserrno(vfs_test_lock(file, lock)); - fput(file); - } + struct nfsd_file *nf; + struct inode *inode; + __be32 err; + + err = nfsd_file_acquire(rqstp, fhp, NFSD_MAY_READ, &nf); + if (err) + return err; + inode = fhp->fh_dentry->d_inode; + inode_lock(inode); /* to block new leases till after test_lock: */ + err = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); + if (err) + goto out; + lock->c.flc_file = nf->nf_file; + err = nfserrno(vfs_test_lock(nf->nf_file, lock)); + lock->c.flc_file = NULL; +out: + inode_unlock(inode); + nfsd_file_put(nf); return err; } @@ -6211,7 +8511,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_inval; if (!nfsd4_has_session(cstate)) { - status = lookup_clientid(&lockt->lt_clientid, cstate, nn); + status = set_client(&lockt->lt_clientid, cstate, nn); if (status) goto out; } @@ -6229,11 +8529,11 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, switch (lockt->lt_type) { case NFS4_READ_LT: case NFS4_READW_LT: - file_lock->fl_type = F_RDLCK; + file_lock->c.flc_type = F_RDLCK; break; case NFS4_WRITE_LT: case NFS4_WRITEW_LT: - file_lock->fl_type = F_WRLCK; + file_lock->c.flc_type = F_WRLCK; break; default: dprintk("NFSD: nfs4_lockt: bad lock type!\n"); @@ -6243,9 +8543,9 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, lo = find_lockowner_str(cstate->clp, &lockt->lt_owner); if (lo) - file_lock->fl_owner = (fl_owner_t)lo; - file_lock->fl_pid = current->tgid; - file_lock->fl_flags = FL_POSIX; + file_lock->c.flc_owner = (fl_owner_t)lo; + file_lock->c.flc_pid = current->tgid; + file_lock->c.flc_flags = FL_POSIX; file_lock->fl_start = lockt->lt_offset; file_lock->fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length); @@ -6256,7 +8556,7 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, if (status) goto out; - if (file_lock->fl_type != F_UNLCK) { + if (file_lock->c.flc_type != F_UNLCK) { status = nfserr_denied; nfs4_set_lock_denied(file_lock, &lockt->lt_denied); } @@ -6268,13 +8568,21 @@ out: return status; } +void nfsd4_lockt_release(union nfsd4_op_u *u) +{ + struct nfsd4_lockt *lockt = &u->lockt; + struct nfsd4_lock_denied *deny = &lockt->lt_denied; + + kfree(deny->ld_owner.data); +} + __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_locku *locku = &u->locku; struct nfs4_ol_stateid *stp; - struct file *filp = NULL; + struct nfsd_file *nf = NULL; struct file_lock *file_lock = NULL; __be32 status; int err; @@ -6288,27 +8596,32 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, return nfserr_inval; status = nfs4_preprocess_seqid_op(cstate, locku->lu_seqid, - &locku->lu_stateid, NFS4_LOCK_STID, - &stp, nn); + &locku->lu_stateid, SC_TYPE_LOCK, 0, + &stp, nn); if (status) goto out; - filp = find_any_file(stp->st_stid.sc_file); - if (!filp) { + nf = find_any_file(stp->st_stid.sc_file); + if (!nf) { status = nfserr_lock_range; goto put_stateid; } + if (exportfs_cannot_lock(nf->nf_file->f_path.mnt->mnt_sb->s_export_op)) { + status = nfserr_notsupp; + goto put_file; + } + file_lock = locks_alloc_lock(); if (!file_lock) { dprintk("NFSD: %s: unable to allocate lock!\n", __func__); status = nfserr_jukebox; - goto fput; + goto put_file; } - file_lock->fl_type = F_UNLCK; - file_lock->fl_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner)); - file_lock->fl_pid = current->tgid; - file_lock->fl_file = filp; - file_lock->fl_flags = FL_POSIX; + file_lock->c.flc_type = F_UNLCK; + file_lock->c.flc_owner = (fl_owner_t)lockowner(nfs4_get_stateowner(stp->st_stateowner)); + file_lock->c.flc_pid = current->tgid; + file_lock->c.flc_file = nf->nf_file; + file_lock->c.flc_flags = FL_POSIX; file_lock->fl_lmops = &nfsd_posix_mng_ops; file_lock->fl_start = locku->lu_offset; @@ -6316,14 +8629,14 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, locku->lu_length); nfs4_transform_lock_offset(file_lock); - err = vfs_lock_file(filp, F_SETLK, file_lock, NULL); + err = vfs_lock_file(nf->nf_file, F_SETLK, file_lock, NULL); if (err) { dprintk("NFSD: nfs4_locku: vfs_lock_file failed!\n"); goto out_nfserr; } nfs4_inc_and_copy_stateid(&locku->lu_stateid, &stp->st_stid); -fput: - fput(filp); +put_file: + nfsd_file_put(nf); put_stateid: mutex_unlock(&stp->st_mutex); nfs4_put_stid(&stp->st_stid); @@ -6335,7 +8648,7 @@ out: out_nfserr: status = nfserrno(err); - goto fput; + goto put_file; } /* @@ -6348,98 +8661,101 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner) { struct file_lock *fl; int status = false; - struct file *filp = find_any_file(fp); + struct nfsd_file *nf; struct inode *inode; struct file_lock_context *flctx; - if (!filp) { + spin_lock(&fp->fi_lock); + nf = find_any_file_locked(fp); + if (!nf) { /* Any valid lock stateid should have some sort of access */ WARN_ON_ONCE(1); - return status; + goto out; } - inode = locks_inode(filp); - flctx = inode->i_flctx; + inode = file_inode(nf->nf_file); + flctx = locks_inode_context(inode); if (flctx && !list_empty_careful(&flctx->flc_posix)) { spin_lock(&flctx->flc_lock); - list_for_each_entry(fl, &flctx->flc_posix, fl_list) { - if (fl->fl_owner == (fl_owner_t)lowner) { + for_each_file_lock(fl, &flctx->flc_posix) { + if (fl->c.flc_owner == (fl_owner_t)lowner) { status = true; break; } } spin_unlock(&flctx->flc_lock); } - fput(filp); +out: + spin_unlock(&fp->fi_lock); return status; } +/** + * nfsd4_release_lockowner - process NFSv4.0 RELEASE_LOCKOWNER operations + * @rqstp: RPC transaction + * @cstate: NFSv4 COMPOUND state + * @u: RELEASE_LOCKOWNER arguments + * + * Check if there are any locks still held and if not, free the lockowner + * and any lock state that is owned. + * + * Return values: + * %nfs_ok: lockowner released or not found + * %nfserr_locks_held: lockowner still in use + * %nfserr_stale_clientid: clientid no longer active + * %nfserr_expired: clientid not recognized + */ __be32 nfsd4_release_lockowner(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, union nfsd4_op_u *u) { struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); clientid_t *clid = &rlockowner->rl_clientid; - struct nfs4_stateowner *sop; - struct nfs4_lockowner *lo = NULL; struct nfs4_ol_stateid *stp; - struct xdr_netobj *owner = &rlockowner->rl_owner; - unsigned int hashval = ownerstr_hashval(owner); - __be32 status; - struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct nfs4_lockowner *lo; struct nfs4_client *clp; - LIST_HEAD (reaplist); + LIST_HEAD(reaplist); + __be32 status; dprintk("nfsd4_release_lockowner clientid: (%08x/%08x):\n", clid->cl_boot, clid->cl_id); - status = lookup_clientid(clid, cstate, nn); + status = set_client(clid, cstate, nn); if (status) return status; - clp = cstate->clp; - /* Find the matching lock stateowner */ - spin_lock(&clp->cl_lock); - list_for_each_entry(sop, &clp->cl_ownerstr_hashtbl[hashval], - so_strhash) { - - if (sop->so_is_open_owner || !same_owner_str(sop, owner)) - continue; - - /* see if there are still any locks associated with it */ - lo = lockowner(sop); - list_for_each_entry(stp, &sop->so_stateids, st_perstateowner) { - if (check_for_locks(stp->st_stid.sc_file, lo)) { - status = nfserr_locks_held; - spin_unlock(&clp->cl_lock); - return status; - } - } - nfs4_get_stateowner(sop); - break; - } + spin_lock(&clp->cl_lock); + lo = find_lockowner_str_locked(clp, &rlockowner->rl_owner); if (!lo) { spin_unlock(&clp->cl_lock); - return status; + return nfs_ok; } + list_for_each_entry(stp, &lo->lo_owner.so_stateids, st_perstateowner) { + if (check_for_locks(stp->st_stid.sc_file, lo)) { + spin_unlock(&clp->cl_lock); + nfs4_put_stateowner(&lo->lo_owner); + return nfserr_locks_held; + } + } unhash_lockowner_locked(lo); while (!list_empty(&lo->lo_owner.so_stateids)) { stp = list_first_entry(&lo->lo_owner.so_stateids, struct nfs4_ol_stateid, st_perstateowner); - WARN_ON(!unhash_lock_stateid(stp)); + unhash_lock_stateid(stp); put_ol_stateid_locked(stp, &reaplist); } spin_unlock(&clp->cl_lock); + free_ol_stateid_reaplist(&reaplist); remove_blocked_locks(lo); nfs4_put_stateowner(&lo->lo_owner); - - return status; + return nfs_ok; } static inline struct nfs4_client_reclaim * @@ -6449,7 +8765,7 @@ alloc_reclaim(void) } bool -nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn) +nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn) { struct nfs4_client_reclaim *crp; @@ -6461,20 +8777,42 @@ nfs4_has_reclaimed_state(const char *name, struct nfsd_net *nn) * failure => all reset bets are off, nfserr_no_grace... */ struct nfs4_client_reclaim * -nfs4_client_to_reclaim(const char *name, struct nfsd_net *nn) +nfs4_client_to_reclaim(struct xdr_netobj name, struct xdr_netobj princhash, + struct nfsd_net *nn) { unsigned int strhashval; struct nfs4_client_reclaim *crp; - dprintk("NFSD nfs4_client_to_reclaim NAME: %.*s\n", HEXDIR_LEN, name); + name.data = kmemdup(name.data, name.len, GFP_KERNEL); + if (!name.data) { + dprintk("%s: failed to allocate memory for name.data!\n", + __func__); + return NULL; + } + if (princhash.len) { + princhash.data = kmemdup(princhash.data, princhash.len, GFP_KERNEL); + if (!princhash.data) { + dprintk("%s: failed to allocate memory for princhash.data!\n", + __func__); + kfree(name.data); + return NULL; + } + } else + princhash.data = NULL; crp = alloc_reclaim(); if (crp) { strhashval = clientstr_hashval(name); INIT_LIST_HEAD(&crp->cr_strhash); list_add(&crp->cr_strhash, &nn->reclaim_str_hashtbl[strhashval]); - memcpy(crp->cr_recdir, name, HEXDIR_LEN); + crp->cr_name.data = name.data; + crp->cr_name.len = name.len; + crp->cr_princhash.data = princhash.data; + crp->cr_princhash.len = princhash.len; crp->cr_clp = NULL; nn->reclaim_str_hashtbl_size++; + } else { + kfree(name.data); + kfree(princhash.data); } return crp; } @@ -6483,6 +8821,8 @@ void nfs4_remove_reclaim_record(struct nfs4_client_reclaim *crp, struct nfsd_net *nn) { list_del(&crp->cr_strhash); + kfree(crp->cr_name.data); + kfree(crp->cr_princhash.data); kfree(crp); nn->reclaim_str_hashtbl_size--; } @@ -6506,636 +8846,32 @@ nfs4_release_reclaim(struct nfsd_net *nn) /* * called from OPEN, CLAIM_PREVIOUS with a new clientid. */ struct nfs4_client_reclaim * -nfsd4_find_reclaim_client(const char *recdir, struct nfsd_net *nn) +nfsd4_find_reclaim_client(struct xdr_netobj name, struct nfsd_net *nn) { unsigned int strhashval; struct nfs4_client_reclaim *crp = NULL; - dprintk("NFSD: nfs4_find_reclaim_client for recdir %s\n", recdir); - - strhashval = clientstr_hashval(recdir); + strhashval = clientstr_hashval(name); list_for_each_entry(crp, &nn->reclaim_str_hashtbl[strhashval], cr_strhash) { - if (same_name(crp->cr_recdir, recdir)) { + if (compare_blob(&crp->cr_name, &name) == 0) { return crp; } } return NULL; } -/* -* Called from OPEN. Look for clientid in reclaim list. -*/ __be32 -nfs4_check_open_reclaim(clientid_t *clid, - struct nfsd4_compound_state *cstate, - struct nfsd_net *nn) +nfs4_check_open_reclaim(struct nfs4_client *clp) { - __be32 status; - - /* find clientid in conf_id_hashtbl */ - status = lookup_clientid(clid, cstate, nn); - if (status) - return nfserr_reclaim_bad; - - if (test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &cstate->clp->cl_flags)) + if (test_bit(NFSD4_CLIENT_RECLAIM_COMPLETE, &clp->cl_flags)) return nfserr_no_grace; - if (nfsd4_client_record_check(cstate->clp)) + if (nfsd4_client_record_check(clp)) return nfserr_reclaim_bad; return nfs_ok; } -#ifdef CONFIG_NFSD_FAULT_INJECTION -static inline void -put_client(struct nfs4_client *clp) -{ - atomic_dec(&clp->cl_refcount); -} - -static struct nfs4_client * -nfsd_find_client(struct sockaddr_storage *addr, size_t addr_size) -{ - struct nfs4_client *clp; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - - if (!nfsd_netns_ready(nn)) - return NULL; - - list_for_each_entry(clp, &nn->client_lru, cl_lru) { - if (memcmp(&clp->cl_addr, addr, addr_size) == 0) - return clp; - } - return NULL; -} - -u64 -nfsd_inject_print_clients(void) -{ - struct nfs4_client *clp; - u64 count = 0; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - char buf[INET6_ADDRSTRLEN]; - - if (!nfsd_netns_ready(nn)) - return 0; - - spin_lock(&nn->client_lock); - list_for_each_entry(clp, &nn->client_lru, cl_lru) { - rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf)); - pr_info("NFS Client: %s\n", buf); - ++count; - } - spin_unlock(&nn->client_lock); - - return count; -} - -u64 -nfsd_inject_forget_client(struct sockaddr_storage *addr, size_t addr_size) -{ - u64 count = 0; - struct nfs4_client *clp; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - - if (!nfsd_netns_ready(nn)) - return count; - - spin_lock(&nn->client_lock); - clp = nfsd_find_client(addr, addr_size); - if (clp) { - if (mark_client_expired_locked(clp) == nfs_ok) - ++count; - else - clp = NULL; - } - spin_unlock(&nn->client_lock); - - if (clp) - expire_client(clp); - - return count; -} - -u64 -nfsd_inject_forget_clients(u64 max) -{ - u64 count = 0; - struct nfs4_client *clp, *next; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - LIST_HEAD(reaplist); - - if (!nfsd_netns_ready(nn)) - return count; - - spin_lock(&nn->client_lock); - list_for_each_entry_safe(clp, next, &nn->client_lru, cl_lru) { - if (mark_client_expired_locked(clp) == nfs_ok) { - list_add(&clp->cl_lru, &reaplist); - if (max != 0 && ++count >= max) - break; - } - } - spin_unlock(&nn->client_lock); - - list_for_each_entry_safe(clp, next, &reaplist, cl_lru) - expire_client(clp); - - return count; -} - -static void nfsd_print_count(struct nfs4_client *clp, unsigned int count, - const char *type) -{ - char buf[INET6_ADDRSTRLEN]; - rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf)); - printk(KERN_INFO "NFS Client: %s has %u %s\n", buf, count, type); -} - -static void -nfsd_inject_add_lock_to_list(struct nfs4_ol_stateid *lst, - struct list_head *collect) -{ - struct nfs4_client *clp = lst->st_stid.sc_client; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - - if (!collect) - return; - - lockdep_assert_held(&nn->client_lock); - atomic_inc(&clp->cl_refcount); - list_add(&lst->st_locks, collect); -} - -static u64 nfsd_foreach_client_lock(struct nfs4_client *clp, u64 max, - struct list_head *collect, - bool (*func)(struct nfs4_ol_stateid *)) -{ - struct nfs4_openowner *oop; - struct nfs4_ol_stateid *stp, *st_next; - struct nfs4_ol_stateid *lst, *lst_next; - u64 count = 0; - - spin_lock(&clp->cl_lock); - list_for_each_entry(oop, &clp->cl_openowners, oo_perclient) { - list_for_each_entry_safe(stp, st_next, - &oop->oo_owner.so_stateids, st_perstateowner) { - list_for_each_entry_safe(lst, lst_next, - &stp->st_locks, st_locks) { - if (func) { - if (func(lst)) - nfsd_inject_add_lock_to_list(lst, - collect); - } - ++count; - /* - * Despite the fact that these functions deal - * with 64-bit integers for "count", we must - * ensure that it doesn't blow up the - * clp->cl_refcount. Throw a warning if we - * start to approach INT_MAX here. - */ - WARN_ON_ONCE(count == (INT_MAX / 2)); - if (count == max) - goto out; - } - } - } -out: - spin_unlock(&clp->cl_lock); - - return count; -} - -static u64 -nfsd_collect_client_locks(struct nfs4_client *clp, struct list_head *collect, - u64 max) -{ - return nfsd_foreach_client_lock(clp, max, collect, unhash_lock_stateid); -} - -static u64 -nfsd_print_client_locks(struct nfs4_client *clp) -{ - u64 count = nfsd_foreach_client_lock(clp, 0, NULL, NULL); - nfsd_print_count(clp, count, "locked files"); - return count; -} - -u64 -nfsd_inject_print_locks(void) -{ - struct nfs4_client *clp; - u64 count = 0; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - - if (!nfsd_netns_ready(nn)) - return 0; - - spin_lock(&nn->client_lock); - list_for_each_entry(clp, &nn->client_lru, cl_lru) - count += nfsd_print_client_locks(clp); - spin_unlock(&nn->client_lock); - - return count; -} - -static void -nfsd_reap_locks(struct list_head *reaplist) -{ - struct nfs4_client *clp; - struct nfs4_ol_stateid *stp, *next; - - list_for_each_entry_safe(stp, next, reaplist, st_locks) { - list_del_init(&stp->st_locks); - clp = stp->st_stid.sc_client; - nfs4_put_stid(&stp->st_stid); - put_client(clp); - } -} - -u64 -nfsd_inject_forget_client_locks(struct sockaddr_storage *addr, size_t addr_size) -{ - unsigned int count = 0; - struct nfs4_client *clp; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - LIST_HEAD(reaplist); - - if (!nfsd_netns_ready(nn)) - return count; - - spin_lock(&nn->client_lock); - clp = nfsd_find_client(addr, addr_size); - if (clp) - count = nfsd_collect_client_locks(clp, &reaplist, 0); - spin_unlock(&nn->client_lock); - nfsd_reap_locks(&reaplist); - return count; -} - -u64 -nfsd_inject_forget_locks(u64 max) -{ - u64 count = 0; - struct nfs4_client *clp; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - LIST_HEAD(reaplist); - - if (!nfsd_netns_ready(nn)) - return count; - - spin_lock(&nn->client_lock); - list_for_each_entry(clp, &nn->client_lru, cl_lru) { - count += nfsd_collect_client_locks(clp, &reaplist, max - count); - if (max != 0 && count >= max) - break; - } - spin_unlock(&nn->client_lock); - nfsd_reap_locks(&reaplist); - return count; -} - -static u64 -nfsd_foreach_client_openowner(struct nfs4_client *clp, u64 max, - struct list_head *collect, - void (*func)(struct nfs4_openowner *)) -{ - struct nfs4_openowner *oop, *next; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - u64 count = 0; - - lockdep_assert_held(&nn->client_lock); - - spin_lock(&clp->cl_lock); - list_for_each_entry_safe(oop, next, &clp->cl_openowners, oo_perclient) { - if (func) { - func(oop); - if (collect) { - atomic_inc(&clp->cl_refcount); - list_add(&oop->oo_perclient, collect); - } - } - ++count; - /* - * Despite the fact that these functions deal with - * 64-bit integers for "count", we must ensure that - * it doesn't blow up the clp->cl_refcount. Throw a - * warning if we start to approach INT_MAX here. - */ - WARN_ON_ONCE(count == (INT_MAX / 2)); - if (count == max) - break; - } - spin_unlock(&clp->cl_lock); - - return count; -} - -static u64 -nfsd_print_client_openowners(struct nfs4_client *clp) -{ - u64 count = nfsd_foreach_client_openowner(clp, 0, NULL, NULL); - - nfsd_print_count(clp, count, "openowners"); - return count; -} - -static u64 -nfsd_collect_client_openowners(struct nfs4_client *clp, - struct list_head *collect, u64 max) -{ - return nfsd_foreach_client_openowner(clp, max, collect, - unhash_openowner_locked); -} - -u64 -nfsd_inject_print_openowners(void) -{ - struct nfs4_client *clp; - u64 count = 0; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - - if (!nfsd_netns_ready(nn)) - return 0; - - spin_lock(&nn->client_lock); - list_for_each_entry(clp, &nn->client_lru, cl_lru) - count += nfsd_print_client_openowners(clp); - spin_unlock(&nn->client_lock); - - return count; -} - -static void -nfsd_reap_openowners(struct list_head *reaplist) -{ - struct nfs4_client *clp; - struct nfs4_openowner *oop, *next; - - list_for_each_entry_safe(oop, next, reaplist, oo_perclient) { - list_del_init(&oop->oo_perclient); - clp = oop->oo_owner.so_client; - release_openowner(oop); - put_client(clp); - } -} - -u64 -nfsd_inject_forget_client_openowners(struct sockaddr_storage *addr, - size_t addr_size) -{ - unsigned int count = 0; - struct nfs4_client *clp; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - LIST_HEAD(reaplist); - - if (!nfsd_netns_ready(nn)) - return count; - - spin_lock(&nn->client_lock); - clp = nfsd_find_client(addr, addr_size); - if (clp) - count = nfsd_collect_client_openowners(clp, &reaplist, 0); - spin_unlock(&nn->client_lock); - nfsd_reap_openowners(&reaplist); - return count; -} - -u64 -nfsd_inject_forget_openowners(u64 max) -{ - u64 count = 0; - struct nfs4_client *clp; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - LIST_HEAD(reaplist); - - if (!nfsd_netns_ready(nn)) - return count; - - spin_lock(&nn->client_lock); - list_for_each_entry(clp, &nn->client_lru, cl_lru) { - count += nfsd_collect_client_openowners(clp, &reaplist, - max - count); - if (max != 0 && count >= max) - break; - } - spin_unlock(&nn->client_lock); - nfsd_reap_openowners(&reaplist); - return count; -} - -static u64 nfsd_find_all_delegations(struct nfs4_client *clp, u64 max, - struct list_head *victims) -{ - struct nfs4_delegation *dp, *next; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - u64 count = 0; - - lockdep_assert_held(&nn->client_lock); - - spin_lock(&state_lock); - list_for_each_entry_safe(dp, next, &clp->cl_delegations, dl_perclnt) { - if (victims) { - /* - * It's not safe to mess with delegations that have a - * non-zero dl_time. They might have already been broken - * and could be processed by the laundromat outside of - * the state_lock. Just leave them be. - */ - if (dp->dl_time != 0) - continue; - - atomic_inc(&clp->cl_refcount); - WARN_ON(!unhash_delegation_locked(dp)); - list_add(&dp->dl_recall_lru, victims); - } - ++count; - /* - * Despite the fact that these functions deal with - * 64-bit integers for "count", we must ensure that - * it doesn't blow up the clp->cl_refcount. Throw a - * warning if we start to approach INT_MAX here. - */ - WARN_ON_ONCE(count == (INT_MAX / 2)); - if (count == max) - break; - } - spin_unlock(&state_lock); - return count; -} - -static u64 -nfsd_print_client_delegations(struct nfs4_client *clp) -{ - u64 count = nfsd_find_all_delegations(clp, 0, NULL); - - nfsd_print_count(clp, count, "delegations"); - return count; -} - -u64 -nfsd_inject_print_delegations(void) -{ - struct nfs4_client *clp; - u64 count = 0; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - - if (!nfsd_netns_ready(nn)) - return 0; - - spin_lock(&nn->client_lock); - list_for_each_entry(clp, &nn->client_lru, cl_lru) - count += nfsd_print_client_delegations(clp); - spin_unlock(&nn->client_lock); - - return count; -} - -static void -nfsd_forget_delegations(struct list_head *reaplist) -{ - struct nfs4_client *clp; - struct nfs4_delegation *dp, *next; - - list_for_each_entry_safe(dp, next, reaplist, dl_recall_lru) { - list_del_init(&dp->dl_recall_lru); - clp = dp->dl_stid.sc_client; - revoke_delegation(dp); - put_client(clp); - } -} - -u64 -nfsd_inject_forget_client_delegations(struct sockaddr_storage *addr, - size_t addr_size) -{ - u64 count = 0; - struct nfs4_client *clp; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - LIST_HEAD(reaplist); - - if (!nfsd_netns_ready(nn)) - return count; - - spin_lock(&nn->client_lock); - clp = nfsd_find_client(addr, addr_size); - if (clp) - count = nfsd_find_all_delegations(clp, 0, &reaplist); - spin_unlock(&nn->client_lock); - - nfsd_forget_delegations(&reaplist); - return count; -} - -u64 -nfsd_inject_forget_delegations(u64 max) -{ - u64 count = 0; - struct nfs4_client *clp; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - LIST_HEAD(reaplist); - - if (!nfsd_netns_ready(nn)) - return count; - - spin_lock(&nn->client_lock); - list_for_each_entry(clp, &nn->client_lru, cl_lru) { - count += nfsd_find_all_delegations(clp, max - count, &reaplist); - if (max != 0 && count >= max) - break; - } - spin_unlock(&nn->client_lock); - nfsd_forget_delegations(&reaplist); - return count; -} - -static void -nfsd_recall_delegations(struct list_head *reaplist) -{ - struct nfs4_client *clp; - struct nfs4_delegation *dp, *next; - - list_for_each_entry_safe(dp, next, reaplist, dl_recall_lru) { - list_del_init(&dp->dl_recall_lru); - clp = dp->dl_stid.sc_client; - /* - * We skipped all entries that had a zero dl_time before, - * so we can now reset the dl_time back to 0. If a delegation - * break comes in now, then it won't make any difference since - * we're recalling it either way. - */ - spin_lock(&state_lock); - dp->dl_time = 0; - spin_unlock(&state_lock); - nfsd_break_one_deleg(dp); - put_client(clp); - } -} - -u64 -nfsd_inject_recall_client_delegations(struct sockaddr_storage *addr, - size_t addr_size) -{ - u64 count = 0; - struct nfs4_client *clp; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - LIST_HEAD(reaplist); - - if (!nfsd_netns_ready(nn)) - return count; - - spin_lock(&nn->client_lock); - clp = nfsd_find_client(addr, addr_size); - if (clp) - count = nfsd_find_all_delegations(clp, 0, &reaplist); - spin_unlock(&nn->client_lock); - - nfsd_recall_delegations(&reaplist); - return count; -} - -u64 -nfsd_inject_recall_delegations(u64 max) -{ - u64 count = 0; - struct nfs4_client *clp, *next; - struct nfsd_net *nn = net_generic(current->nsproxy->net_ns, - nfsd_net_id); - LIST_HEAD(reaplist); - - if (!nfsd_netns_ready(nn)) - return count; - - spin_lock(&nn->client_lock); - list_for_each_entry_safe(clp, next, &nn->client_lru, cl_lru) { - count += nfsd_find_all_delegations(clp, max - count, &reaplist); - if (max != 0 && ++count >= max) - break; - } - spin_unlock(&nn->client_lock); - nfsd_recall_delegations(&reaplist); - return count; -} -#endif /* CONFIG_NFSD_FAULT_INJECTION */ - /* * Since the lifetime of a delegation isn't limited to that of an open, a * client may quite reasonably hang on to a delegation as long as it has @@ -7186,7 +8922,7 @@ static int nfs4_state_create_net(struct net *net) INIT_LIST_HEAD(&nn->sessionid_hashtbl[i]); nn->conf_name_tree = RB_ROOT; nn->unconf_name_tree = RB_ROOT; - nn->boot_time = get_seconds(); + nn->boot_time = ktime_get_real_seconds(); nn->grace_ended = false; nn->nfsd4_manager.block_opens = true; INIT_LIST_HEAD(&nn->nfsd4_manager.list); @@ -7196,15 +8932,30 @@ static int nfs4_state_create_net(struct net *net) spin_lock_init(&nn->client_lock); spin_lock_init(&nn->s2s_cp_lock); idr_init(&nn->s2s_cp_stateids); + atomic_set(&nn->pending_async_copies, 0); spin_lock_init(&nn->blocked_locks_lock); INIT_LIST_HEAD(&nn->blocked_locks_lru); INIT_DELAYED_WORK(&nn->laundromat_work, laundromat_main); + INIT_WORK(&nn->nfsd_shrinker_work, nfsd4_state_shrinker_worker); get_net(net); + nn->nfsd_client_shrinker = shrinker_alloc(0, "nfsd-client"); + if (!nn->nfsd_client_shrinker) + goto err_shrinker; + + nn->nfsd_client_shrinker->scan_objects = nfsd4_state_shrinker_scan; + nn->nfsd_client_shrinker->count_objects = nfsd4_state_shrinker_count; + nn->nfsd_client_shrinker->private_data = nn; + + shrinker_register(nn->nfsd_client_shrinker); + return 0; +err_shrinker: + put_net(net); + kfree(nn->sessionid_hashtbl); err_sessionid: kfree(nn->unconf_id_hashtbl); err_unconf_id: @@ -7253,35 +9004,43 @@ nfs4_state_start_net(struct net *net) return ret; locks_start_grace(net, &nn->nfsd4_manager); nfsd4_client_tracking_init(net); - printk(KERN_INFO "NFSD: starting %ld-second grace period (net %x)\n", + if (nn->track_reclaim_completes && nn->reclaim_str_hashtbl_size == 0) + goto skip_grace; + printk(KERN_INFO "NFSD: starting %lld-second grace period (net %x)\n", nn->nfsd4_grace, net->ns.inum); + trace_nfsd_grace_start(nn); queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_grace * HZ); return 0; + +skip_grace: + printk(KERN_INFO "NFSD: no clients to reclaim, skipping NFSv4 grace period (net %x)\n", + net->ns.inum); + queue_delayed_work(laundry_wq, &nn->laundromat_work, nn->nfsd4_lease * HZ); + nfsd4_end_grace(nn); + return 0; } /* initialization to perform when the nfsd service is started: */ - int nfs4_state_start(void) { int ret; - laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4"); - if (laundry_wq == NULL) { - ret = -ENOMEM; - goto out; - } - ret = nfsd4_create_callback_queue(); + ret = rhltable_init(&nfs4_file_rhltable, &nfs4_file_rhash_params); if (ret) - goto out_free_laundry; + return ret; + + nfsd_slot_shrinker = shrinker_alloc(0, "nfsd-DRC-slot"); + if (!nfsd_slot_shrinker) { + rhltable_destroy(&nfs4_file_rhltable); + return -ENOMEM; + } + nfsd_slot_shrinker->count_objects = nfsd_slot_count; + nfsd_slot_shrinker->scan_objects = nfsd_slot_scan; + shrinker_register(nfsd_slot_shrinker); set_max_delegations(); return 0; - -out_free_laundry: - destroy_workqueue(laundry_wq); -out: - return ret; } void @@ -7291,6 +9050,8 @@ nfs4_state_shutdown_net(struct net *net) struct list_head *pos, *next, reaplist; struct nfsd_net *nn = net_generic(net, nfsd_net_id); + shrinker_free(nn->nfsd_client_shrinker); + cancel_work_sync(&nn->nfsd_shrinker_work); cancel_delayed_work_sync(&nn->laundromat_work); locks_end_grace(&nn->nfsd4_manager); @@ -7298,7 +9059,7 @@ nfs4_state_shutdown_net(struct net *net) spin_lock(&state_lock); list_for_each_safe(pos, next, &nn->del_recall_lru) { dp = list_entry (pos, struct nfs4_delegation, dl_recall_lru); - WARN_ON(!unhash_delegation_locked(dp)); + unhash_delegation_locked(dp, SC_STATUS_CLOSED); list_add(&dp->dl_recall_lru, &reaplist); } spin_unlock(&state_lock); @@ -7310,19 +9071,23 @@ nfs4_state_shutdown_net(struct net *net) nfsd4_client_tracking_exit(net); nfs4_state_destroy_net(net); +#ifdef CONFIG_NFSD_V4_2_INTER_SSC + nfsd4_ssc_shutdown_umount(nn); +#endif } void nfs4_state_shutdown(void) { - destroy_workqueue(laundry_wq); - nfsd4_destroy_callback_queue(); + rhltable_destroy(&nfs4_file_rhltable); + shrinker_free(nfsd_slot_shrinker); } static void get_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid) { - if (HAS_STATE_ID(cstate, CURRENT_STATE_ID_FLAG) && CURRENT_STATEID(stateid)) + if (HAS_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG) && + CURRENT_STATEID(stateid)) memcpy(stateid, &cstate->current_stateid, sizeof(stateid_t)); } @@ -7331,14 +9096,14 @@ put_stateid(struct nfsd4_compound_state *cstate, stateid_t *stateid) { if (cstate->minorversion) { memcpy(&cstate->current_stateid, stateid, sizeof(stateid_t)); - SET_STATE_ID(cstate, CURRENT_STATE_ID_FLAG); + SET_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG); } } void clear_current_stateid(struct nfsd4_compound_state *cstate) { - CLEAR_STATE_ID(cstate, CURRENT_STATE_ID_FLAG); + CLEAR_CSTATE_FLAG(cstate, CURRENT_STATE_ID_FLAG); } /* @@ -7431,3 +9196,274 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, { get_stateid(cstate, &u->write.wr_stateid); } + +/** + * nfsd4_vet_deleg_time - vet and set the timespec for a delegated timestamp update + * @req: timestamp from the client + * @orig: original timestamp in the inode + * @now: current time + * + * Given a timestamp from the client response, check it against the + * current timestamp in the inode and the current time. Returns true + * if the inode's timestamp needs to be updated, and false otherwise. + * @req may also be changed if the timestamp needs to be clamped. + */ +bool nfsd4_vet_deleg_time(struct timespec64 *req, const struct timespec64 *orig, + const struct timespec64 *now) +{ + + /* + * "When the time presented is before the original time, then the + * update is ignored." Also no need to update if there is no change. + */ + if (timespec64_compare(req, orig) <= 0) + return false; + + /* + * "When the time presented is in the future, the server can either + * clamp the new time to the current time, or it may + * return NFS4ERR_DELAY to the client, allowing it to retry." + */ + if (timespec64_compare(req, now) > 0) + *req = *now; + + return true; +} + +static int cb_getattr_update_times(struct dentry *dentry, struct nfs4_delegation *dp) +{ + struct inode *inode = d_inode(dentry); + struct nfs4_cb_fattr *ncf = &dp->dl_cb_fattr; + struct iattr attrs = { }; + int ret; + + if (deleg_attrs_deleg(dp->dl_type)) { + struct timespec64 now = current_time(inode); + + attrs.ia_atime = ncf->ncf_cb_atime; + attrs.ia_mtime = ncf->ncf_cb_mtime; + + if (nfsd4_vet_deleg_time(&attrs.ia_atime, &dp->dl_atime, &now)) + attrs.ia_valid |= ATTR_ATIME | ATTR_ATIME_SET; + + if (nfsd4_vet_deleg_time(&attrs.ia_mtime, &dp->dl_mtime, &now)) { + attrs.ia_valid |= ATTR_MTIME | ATTR_MTIME_SET; + attrs.ia_ctime = attrs.ia_mtime; + if (nfsd4_vet_deleg_time(&attrs.ia_ctime, &dp->dl_ctime, &now)) + attrs.ia_valid |= ATTR_CTIME | ATTR_CTIME_SET; + } + } else { + attrs.ia_valid |= ATTR_MTIME | ATTR_CTIME; + } + + if (!attrs.ia_valid) + return 0; + + attrs.ia_valid |= ATTR_DELEG; + inode_lock(inode); + ret = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL); + inode_unlock(inode); + return ret; +} + +/** + * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict + * @rqstp: RPC transaction context + * @dentry: dentry of inode to be checked for a conflict + * @pdp: returned WRITE delegation, if one was found + * + * This function is called when there is a conflict between a write + * delegation and a change/size GETATTR from another client. The server + * must either use the CB_GETATTR to get the current values of the + * attributes from the client that holds the delegation or recall the + * delegation before replying to the GETATTR. See RFC 8881 section + * 18.7.4. + * + * Returns 0 if there is no conflict; otherwise an nfs_stat + * code is returned. If @pdp is set to a non-NULL value, then the + * caller must put the reference. + */ +__be32 +nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry, + struct nfs4_delegation **pdp) +{ + __be32 status; + struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id); + struct file_lock_context *ctx; + struct nfs4_delegation *dp = NULL; + struct file_lease *fl; + struct nfs4_cb_fattr *ncf; + struct inode *inode = d_inode(dentry); + + ctx = locks_inode_context(inode); + if (!ctx) + return nfs_ok; + +#define NON_NFSD_LEASE ((void *)1) + + spin_lock(&ctx->flc_lock); + for_each_file_lock(fl, &ctx->flc_lease) { + if (fl->c.flc_flags == FL_LAYOUT) + continue; + if (fl->c.flc_type == F_WRLCK) { + if (fl->fl_lmops == &nfsd_lease_mng_ops) + dp = fl->c.flc_owner; + else + dp = NON_NFSD_LEASE; + } + break; + } + if (dp == NULL || dp == NON_NFSD_LEASE || + dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) { + spin_unlock(&ctx->flc_lock); + if (dp == NON_NFSD_LEASE) { + status = nfserrno(nfsd_open_break_lease(inode, + NFSD_MAY_READ)); + if (status != nfserr_jukebox || + !nfsd_wait_for_delegreturn(rqstp, inode)) + return status; + } + return 0; + } + + nfsd_stats_wdeleg_getattr_inc(nn); + refcount_inc(&dp->dl_stid.sc_count); + ncf = &dp->dl_cb_fattr; + nfs4_cb_getattr(&dp->dl_cb_fattr); + spin_unlock(&ctx->flc_lock); + + wait_on_bit_timeout(&ncf->ncf_getattr.cb_flags, NFSD4_CALLBACK_RUNNING, + TASK_UNINTERRUPTIBLE, NFSD_CB_GETATTR_TIMEOUT); + if (ncf->ncf_cb_status) { + /* Recall delegation only if client didn't respond */ + status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ)); + if (status != nfserr_jukebox || + !nfsd_wait_for_delegreturn(rqstp, inode)) + goto out_status; + } + if (!ncf->ncf_file_modified && + (ncf->ncf_initial_cinfo != ncf->ncf_cb_change || + ncf->ncf_cur_fsize != ncf->ncf_cb_fsize)) + ncf->ncf_file_modified = true; + if (ncf->ncf_file_modified) { + int err; + + /* + * Per section 10.4.3 of RFC 8881, the server would + * not update the file's metadata with the client's + * modified size + */ + err = cb_getattr_update_times(dentry, dp); + if (err) { + status = nfserrno(err); + goto out_status; + } + ncf->ncf_cur_fsize = ncf->ncf_cb_fsize; + *pdp = dp; + return nfs_ok; + } + status = nfs_ok; +out_status: + nfs4_put_stid(&dp->dl_stid); + return status; +} + +/** + * nfsd_get_dir_deleg - attempt to get a directory delegation + * @cstate: compound state + * @gdd: GET_DIR_DELEGATION arg/resp structure + * @nf: nfsd_file opened on the directory + * + * Given a GET_DIR_DELEGATION request @gdd, attempt to acquire a delegation + * on the directory to which @nf refers. Note that this does not set up any + * sort of async notifications for the delegation. + */ +struct nfs4_delegation * +nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate, + struct nfsd4_get_dir_delegation *gdd, + struct nfsd_file *nf) +{ + struct nfs4_client *clp = cstate->clp; + struct nfs4_delegation *dp; + struct file_lease *fl; + struct nfs4_file *fp, *rfp; + int status = 0; + + fp = nfsd4_alloc_file(); + if (!fp) + return ERR_PTR(-ENOMEM); + + nfsd4_file_init(&cstate->current_fh, fp); + + rfp = nfsd4_file_hash_insert(fp, &cstate->current_fh); + if (unlikely(!rfp)) { + put_nfs4_file(fp); + return ERR_PTR(-ENOMEM); + } + + if (rfp != fp) { + put_nfs4_file(fp); + fp = rfp; + } + + /* if this client already has one, return that it's unavailable */ + spin_lock(&state_lock); + spin_lock(&fp->fi_lock); + /* existing delegation? */ + if (nfs4_delegation_exists(clp, fp)) { + status = -EAGAIN; + } else if (!fp->fi_deleg_file) { + fp->fi_deleg_file = nfsd_file_get(nf); + fp->fi_delegees = 1; + } else { + ++fp->fi_delegees; + } + spin_unlock(&fp->fi_lock); + spin_unlock(&state_lock); + + if (status) { + put_nfs4_file(fp); + return ERR_PTR(status); + } + + /* Try to set up the lease */ + status = -ENOMEM; + dp = alloc_init_deleg(clp, fp, NULL, NFS4_OPEN_DELEGATE_READ); + if (!dp) + goto out_delegees; + + fl = nfs4_alloc_init_lease(dp); + if (!fl) + goto out_put_stid; + + status = kernel_setlease(nf->nf_file, + fl->c.flc_type, &fl, NULL); + if (fl) + locks_free_lease(fl); + if (status) + goto out_put_stid; + + /* + * Now, try to hash it. This can fail if we race another nfsd task + * trying to set a delegation on the same file. If that happens, + * then just say UNAVAIL. + */ + spin_lock(&state_lock); + spin_lock(&clp->cl_lock); + spin_lock(&fp->fi_lock); + status = hash_delegation_locked(dp, fp); + spin_unlock(&fp->fi_lock); + spin_unlock(&clp->cl_lock); + spin_unlock(&state_lock); + + if (!status) + return dp; + + /* Something failed. Drop the lease and clean up the stid */ + kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp); +out_put_stid: + nfs4_put_stid(&dp->dl_stid); +out_delegees: + put_deleg_file(fp); + return ERR_PTR(status); +} |