From 102a0743326a03cd1a1202ceda21e175b7d3575c Mon Sep 17 00:00:00 2001 From: hc <hc@nodka.com> Date: Tue, 20 Feb 2024 01:20:52 +0000 Subject: [PATCH] add new system file --- kernel/fs/nfs/delegation.c | 801 ++++++++++++++++++++++++++++++++++++-------------------- 1 files changed, 512 insertions(+), 289 deletions(-) diff --git a/kernel/fs/nfs/delegation.c b/kernel/fs/nfs/delegation.c index b0c0c2f..1eb6c7a 100644 --- a/kernel/fs/nfs/delegation.c +++ b/kernel/fs/nfs/delegation.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/nfs/delegation.c * @@ -24,13 +25,44 @@ #include "internal.h" #include "nfs4trace.h" +#define NFS_DEFAULT_DELEGATION_WATERMARK (5000U) + +static atomic_long_t nfs_active_delegations; +static unsigned nfs_delegation_watermark = NFS_DEFAULT_DELEGATION_WATERMARK; + +static void __nfs_free_delegation(struct nfs_delegation *delegation) +{ + put_cred(delegation->cred); + delegation->cred = NULL; + kfree_rcu(delegation, rcu); +} + +static void nfs_mark_delegation_revoked(struct nfs_delegation *delegation) +{ + if (!test_and_set_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { + delegation->stateid.type = NFS4_INVALID_STATEID_TYPE; + atomic_long_dec(&nfs_active_delegations); + if (!test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) + nfs_clear_verifier_delegated(delegation->inode); + } +} + +static struct nfs_delegation *nfs_get_delegation(struct nfs_delegation *delegation) +{ + refcount_inc(&delegation->refcount); + return delegation; +} + +static void nfs_put_delegation(struct nfs_delegation *delegation) +{ + if (refcount_dec_and_test(&delegation->refcount)) + __nfs_free_delegation(delegation); +} + static void nfs_free_delegation(struct nfs_delegation *delegation) { - if (delegation->cred) { - put_rpccred(delegation->cred); - delegation->cred = NULL; - } - kfree_rcu(delegation, rcu); + nfs_mark_delegation_revoked(delegation); + nfs_put_delegation(delegation); } /** @@ -41,6 +73,13 @@ void nfs_mark_delegation_referenced(struct nfs_delegation *delegation) { set_bit(NFS_DELEGATION_REFERENCED, &delegation->flags); +} + +static void nfs_mark_return_delegation(struct nfs_server *server, + struct nfs_delegation *delegation) +{ + set_bit(NFS_DELEGATION_RETURN, &delegation->flags); + set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state); } static bool @@ -146,8 +185,8 @@ int err; again: - spin_lock(&inode->i_lock); - list_for_each_entry(ctx, &nfsi->open_files, list) { + rcu_read_lock(); + list_for_each_entry_rcu(ctx, &nfsi->open_files, list) { state = ctx->state; if (state == NULL) continue; @@ -157,8 +196,9 @@ continue; if (!nfs4_stateid_match(&state->stateid, stateid)) continue; - get_nfs_open_context(ctx); - spin_unlock(&inode->i_lock); + if (!get_nfs_open_context(ctx)) + continue; + rcu_read_unlock(); sp = state->owner; /* Block nfs4_proc_unlck */ mutex_lock(&sp->so_delegreturn_mutex); @@ -174,7 +214,7 @@ return err; goto again; } - spin_unlock(&inode->i_lock); + rcu_read_unlock(); return 0; } @@ -187,49 +227,51 @@ * @pagemod_limit: write delegation "space_limit" * */ -void nfs_inode_reclaim_delegation(struct inode *inode, struct rpc_cred *cred, - fmode_t type, - const nfs4_stateid *stateid, +void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred, + fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit) { struct nfs_delegation *delegation; - struct rpc_cred *oldcred = NULL; + const struct cred *oldcred = NULL; rcu_read_lock(); delegation = rcu_dereference(NFS_I(inode)->delegation); if (delegation != NULL) { spin_lock(&delegation->lock); - if (delegation->inode != NULL) { - nfs4_stateid_copy(&delegation->stateid, stateid); - delegation->type = type; - delegation->pagemod_limit = pagemod_limit; - oldcred = delegation->cred; - delegation->cred = get_rpccred(cred); - clear_bit(NFS_DELEGATION_NEED_RECLAIM, - &delegation->flags); - spin_unlock(&delegation->lock); - rcu_read_unlock(); - put_rpccred(oldcred); - trace_nfs4_reclaim_delegation(inode, type); - return; - } - /* We appear to have raced with a delegation return. */ + nfs4_stateid_copy(&delegation->stateid, stateid); + delegation->type = type; + delegation->pagemod_limit = pagemod_limit; + oldcred = delegation->cred; + delegation->cred = get_cred(cred); + clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags); + if (test_and_clear_bit(NFS_DELEGATION_REVOKED, + &delegation->flags)) + atomic_long_inc(&nfs_active_delegations); spin_unlock(&delegation->lock); + rcu_read_unlock(); + put_cred(oldcred); + trace_nfs4_reclaim_delegation(inode, type); + } else { + rcu_read_unlock(); + nfs_inode_set_delegation(inode, cred, type, stateid, + pagemod_limit); } - rcu_read_unlock(); - nfs_inode_set_delegation(inode, cred, type, stateid, pagemod_limit); } static int nfs_do_return_delegation(struct inode *inode, struct nfs_delegation *delegation, int issync) { + const struct cred *cred; int res = 0; - if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) - res = nfs4_proc_delegreturn(inode, - delegation->cred, + if (!test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { + spin_lock(&delegation->lock); + cred = get_cred(delegation->cred); + spin_unlock(&delegation->lock); + res = nfs4_proc_delegreturn(inode, cred, &delegation->stateid, issync); - nfs_free_delegation(delegation); + put_cred(cred); + } return res; } @@ -255,9 +297,14 @@ if (delegation == NULL) goto out; spin_lock(&delegation->lock); - if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) - ret = delegation; + if (!test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { + clear_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags); + /* Refcount matched in nfs_end_delegation_return() */ + ret = nfs_get_delegation(delegation); + } spin_unlock(&delegation->lock); + if (ret) + nfs_clear_verifier_delegated(&nfsi->vfs_inode); out: return ret; } @@ -273,16 +320,17 @@ return delegation; } -static void -nfs_abort_delegation_return(struct nfs_delegation *delegation, - struct nfs_client *clp) +static void nfs_abort_delegation_return(struct nfs_delegation *delegation, + struct nfs_client *clp, int err) { spin_lock(&delegation->lock); clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags); - set_bit(NFS_DELEGATION_RETURN, &delegation->flags); + if (err == -EAGAIN) { + set_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags); + set_bit(NFS4CLNT_DELEGRETURN_DELAYED, &clp->cl_state); + } spin_unlock(&delegation->lock); - set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state); } static struct nfs_delegation * @@ -298,7 +346,10 @@ return NULL; spin_lock(&delegation->lock); - set_bit(NFS_DELEGATION_RETURNING, &delegation->flags); + if (!delegation->inode) { + spin_unlock(&delegation->lock); + return NULL; + } list_del_rcu(&delegation->super_list); delegation->inode = NULL; rcu_assign_pointer(nfsi->delegation, NULL); @@ -325,10 +376,24 @@ struct nfs_server *server = NFS_SERVER(inode); struct nfs_delegation *delegation; - delegation = nfs_start_delegation_return(nfsi); - if (delegation == NULL) - return NULL; - return nfs_detach_delegation(nfsi, delegation, server); + rcu_read_lock(); + delegation = rcu_dereference(nfsi->delegation); + if (delegation != NULL) + delegation = nfs_detach_delegation(nfsi, delegation, server); + rcu_read_unlock(); + return delegation; +} + +static void +nfs_update_delegation_cred(struct nfs_delegation *delegation, + const struct cred *cred) +{ + const struct cred *old; + + if (cred_fscmp(delegation->cred, cred) != 0) { + old = xchg(&delegation->cred, get_cred(cred)); + put_cred(old); + } } static void @@ -339,6 +404,14 @@ delegation->stateid.seqid = update->stateid.seqid; smp_wmb(); delegation->type = update->type; + delegation->pagemod_limit = update->pagemod_limit; + if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { + delegation->change_attr = update->change_attr; + nfs_update_delegation_cred(delegation, update->cred); + /* smp_mb__before_atomic() is implicit due to xchg() */ + clear_bit(NFS_DELEGATION_REVOKED, &delegation->flags); + atomic_long_inc(&nfs_active_delegations); + } } } @@ -352,7 +425,7 @@ * * Returns zero on success, or a negative errno value. */ -int nfs_inode_set_delegation(struct inode *inode, struct rpc_cred *cred, +int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred, fmode_t type, const nfs4_stateid *stateid, unsigned long pagemod_limit) @@ -368,10 +441,11 @@ if (delegation == NULL) return -ENOMEM; nfs4_stateid_copy(&delegation->stateid, stateid); + refcount_set(&delegation->refcount, 1); delegation->type = type; delegation->pagemod_limit = pagemod_limit; delegation->change_attr = inode_peek_iversion_raw(inode); - delegation->cred = get_rpccred(cred); + delegation->cred = get_cred(cred); delegation->inode = inode; delegation->flags = 1<<NFS_DELEGATION_REFERENCED; spin_lock_init(&delegation->lock); @@ -379,14 +453,18 @@ spin_lock(&clp->cl_lock); old_delegation = rcu_dereference_protected(nfsi->delegation, lockdep_is_held(&clp->cl_lock)); - if (old_delegation != NULL) { - /* Is this an update of the existing delegation? */ - if (nfs4_stateid_match_other(&old_delegation->stateid, - &delegation->stateid)) { - nfs_update_inplace_delegation(old_delegation, - delegation); - goto out; - } + if (old_delegation == NULL) + goto add_new; + /* Is this an update of the existing delegation? */ + if (nfs4_stateid_match_other(&old_delegation->stateid, + &delegation->stateid)) { + spin_lock(&old_delegation->lock); + nfs_update_inplace_delegation(old_delegation, + delegation); + spin_unlock(&old_delegation->lock); + goto out; + } + if (!test_bit(NFS_DELEGATION_REVOKED, &old_delegation->flags)) { /* * Deal with broken servers that hand out two * delegations for the same file. @@ -405,14 +483,16 @@ if (test_and_set_bit(NFS_DELEGATION_RETURNING, &old_delegation->flags)) goto out; - freeme = nfs_detach_delegation_locked(nfsi, - old_delegation, clp); - if (freeme == NULL) - goto out; } + freeme = nfs_detach_delegation_locked(nfsi, old_delegation, clp); + if (freeme == NULL) + goto out; +add_new: list_add_tail_rcu(&delegation->super_list, &server->delegations); rcu_assign_pointer(nfsi->delegation, delegation); delegation = NULL; + + atomic_long_inc(&nfs_active_delegations); trace_nfs4_set_delegation(inode, type); @@ -423,9 +503,11 @@ out: spin_unlock(&clp->cl_lock); if (delegation != NULL) - nfs_free_delegation(delegation); - if (freeme != NULL) + __nfs_free_delegation(delegation); + if (freeme != NULL) { nfs_do_return_delegation(inode, freeme, 0); + nfs_free_delegation(freeme); + } return status; } @@ -435,7 +517,6 @@ static int nfs_end_delegation_return(struct inode *inode, struct nfs_delegation *delegation, int issync) { struct nfs_client *clp = NFS_SERVER(inode)->nfs_client; - struct nfs_inode *nfsi = NFS_I(inode); int err = 0; if (delegation == NULL) @@ -454,14 +535,14 @@ } while (err == 0); if (err) { - nfs_abort_delegation_return(delegation, clp); + nfs_abort_delegation_return(delegation, clp, err); goto out; } - if (!nfs_detach_delegation(nfsi, delegation, NFS_SERVER(inode))) - goto out; err = nfs_do_return_delegation(inode, delegation, issync); out: + /* Refcount matched in nfs_start_delegation_return_locked() */ + nfs_put_delegation(delegation); return err; } @@ -469,11 +550,9 @@ { bool ret = false; - if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) - goto out; if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags)) ret = true; - if (test_and_clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) && !ret) { + else if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags)) { struct inode *inode; spin_lock(&delegation->lock); @@ -482,6 +561,117 @@ ret = true; spin_unlock(&delegation->lock); } + if (ret) + clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); + if (test_bit(NFS_DELEGATION_RETURNING, &delegation->flags) || + test_bit(NFS_DELEGATION_RETURN_DELAYED, &delegation->flags) || + test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) + ret = false; + + return ret; +} + +static int nfs_server_return_marked_delegations(struct nfs_server *server, + void __always_unused *data) +{ + struct nfs_delegation *delegation; + struct nfs_delegation *prev; + struct inode *inode; + struct inode *place_holder = NULL; + struct nfs_delegation *place_holder_deleg = NULL; + int err = 0; + +restart: + /* + * To avoid quadratic looping we hold a reference + * to an inode place_holder. Each time we restart, we + * list delegation in the server from the delegations + * of that inode. + * prev is an RCU-protected pointer to a delegation which + * wasn't marked for return and might be a good choice for + * the next place_holder. + */ + prev = NULL; + delegation = NULL; + rcu_read_lock(); + if (place_holder) + delegation = rcu_dereference(NFS_I(place_holder)->delegation); + if (!delegation || delegation != place_holder_deleg) + delegation = list_entry_rcu(server->delegations.next, + struct nfs_delegation, super_list); + list_for_each_entry_from_rcu(delegation, &server->delegations, super_list) { + struct inode *to_put = NULL; + + if (test_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags)) + continue; + if (!nfs_delegation_need_return(delegation)) { + if (nfs4_is_valid_delegation(delegation, 0)) + prev = delegation; + continue; + } + + if (prev) { + struct inode *tmp = nfs_delegation_grab_inode(prev); + if (tmp) { + to_put = place_holder; + place_holder = tmp; + place_holder_deleg = prev; + } + } + + inode = nfs_delegation_grab_inode(delegation); + if (inode == NULL) { + rcu_read_unlock(); + iput(to_put); + goto restart; + } + delegation = nfs_start_delegation_return_locked(NFS_I(inode)); + rcu_read_unlock(); + + iput(to_put); + + err = nfs_end_delegation_return(inode, delegation, 0); + iput(inode); + cond_resched(); + if (!err) + goto restart; + set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state); + goto out; + } + rcu_read_unlock(); +out: + iput(place_holder); + return err; +} + +static bool nfs_server_clear_delayed_delegations(struct nfs_server *server) +{ + struct nfs_delegation *d; + bool ret = false; + + list_for_each_entry_rcu (d, &server->delegations, super_list) { + if (!test_bit(NFS_DELEGATION_RETURN_DELAYED, &d->flags)) + continue; + nfs_mark_return_delegation(server, d); + clear_bit(NFS_DELEGATION_RETURN_DELAYED, &d->flags); + ret = true; + } + return ret; +} + +static bool nfs_client_clear_delayed_delegations(struct nfs_client *clp) +{ + struct nfs_server *server; + bool ret = false; + + if (!test_and_clear_bit(NFS4CLNT_DELEGRETURN_DELAYED, &clp->cl_state)) + goto out; + rcu_read_lock(); + list_for_each_entry_rcu (server, &clp->cl_superblocks, client_link) { + if (nfs_server_clear_delayed_delegations(server)) + ret = true; + } + rcu_read_unlock(); out: return ret; } @@ -498,106 +688,35 @@ */ int nfs_client_return_marked_delegations(struct nfs_client *clp) { - struct nfs_delegation *delegation; - struct nfs_delegation *prev; - struct nfs_server *server; - struct inode *inode; - struct inode *place_holder = NULL; - struct nfs_delegation *place_holder_deleg = NULL; - int err = 0; - -restart: - /* - * To avoid quadratic looping we hold a reference - * to an inode place_holder. Each time we restart, we - * list nfs_servers from the server of that inode, and - * delegation in the server from the delegations of that - * inode. - * prev is an RCU-protected pointer to a delegation which - * wasn't marked for return and might be a good choice for - * the next place_holder. - */ - rcu_read_lock(); - prev = NULL; - if (place_holder) - server = NFS_SERVER(place_holder); - else - server = list_entry_rcu(clp->cl_superblocks.next, - struct nfs_server, client_link); - list_for_each_entry_from_rcu(server, &clp->cl_superblocks, client_link) { - delegation = NULL; - if (place_holder && server == NFS_SERVER(place_holder)) - delegation = rcu_dereference(NFS_I(place_holder)->delegation); - if (!delegation || delegation != place_holder_deleg) - delegation = list_entry_rcu(server->delegations.next, - struct nfs_delegation, super_list); - list_for_each_entry_from_rcu(delegation, &server->delegations, super_list) { - struct inode *to_put = NULL; - - if (!nfs_delegation_need_return(delegation)) { - prev = delegation; - continue; - } - if (!nfs_sb_active(server->super)) - break; /* continue in outer loop */ - - if (prev) { - struct inode *tmp; - - tmp = nfs_delegation_grab_inode(prev); - if (tmp) { - to_put = place_holder; - place_holder = tmp; - place_holder_deleg = prev; - } - } - - inode = nfs_delegation_grab_inode(delegation); - if (inode == NULL) { - rcu_read_unlock(); - if (to_put) - iput(to_put); - nfs_sb_deactive(server->super); - goto restart; - } - delegation = nfs_start_delegation_return_locked(NFS_I(inode)); - rcu_read_unlock(); - - if (to_put) - iput(to_put); - - err = nfs_end_delegation_return(inode, delegation, 0); - iput(inode); - nfs_sb_deactive(server->super); - cond_resched(); - if (!err) - goto restart; - set_bit(NFS4CLNT_DELEGRETURN, &clp->cl_state); - if (place_holder) - iput(place_holder); - return err; - } - } - rcu_read_unlock(); - if (place_holder) - iput(place_holder); + int err = nfs_client_for_each_server( + clp, nfs_server_return_marked_delegations, NULL); + if (err) + return err; + /* If a return was delayed, sleep to prevent hard looping */ + if (nfs_client_clear_delayed_delegations(clp)) + ssleep(1); return 0; } /** - * nfs_inode_return_delegation_noreclaim - return delegation, don't reclaim opens + * nfs_inode_evict_delegation - return delegation, don't reclaim opens * @inode: inode to process * * Does not protect against delegation reclaims, therefore really only safe - * to be called from nfs4_clear_inode(). + * to be called from nfs4_clear_inode(). Guaranteed to always free + * the delegation structure. */ -void nfs_inode_return_delegation_noreclaim(struct inode *inode) +void nfs_inode_evict_delegation(struct inode *inode) { struct nfs_delegation *delegation; delegation = nfs_inode_detach_delegation(inode); - if (delegation != NULL) + if (delegation != NULL) { + set_bit(NFS_DELEGATION_RETURNING, &delegation->flags); + set_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags); nfs_do_return_delegation(inode, delegation, 1); + nfs_free_delegation(delegation); + } } /** @@ -624,6 +743,43 @@ } /** + * nfs_inode_return_delegation_on_close - asynchronously return a delegation + * @inode: inode to process + * + * This routine is called on file close in order to determine if the + * inode delegation needs to be returned immediately. + */ +void nfs4_inode_return_delegation_on_close(struct inode *inode) +{ + struct nfs_delegation *delegation; + struct nfs_delegation *ret = NULL; + + if (!inode) + return; + rcu_read_lock(); + delegation = nfs4_get_valid_delegation(inode); + if (!delegation) + goto out; + if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) || + atomic_long_read(&nfs_active_delegations) >= nfs_delegation_watermark) { + spin_lock(&delegation->lock); + if (delegation->inode && + list_empty(&NFS_I(inode)->open_files) && + !test_and_set_bit(NFS_DELEGATION_RETURNING, &delegation->flags)) { + clear_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); + /* Refcount matched in nfs_end_delegation_return() */ + ret = nfs_get_delegation(delegation); + } + spin_unlock(&delegation->lock); + if (ret) + nfs_clear_verifier_delegated(inode); + } +out: + rcu_read_unlock(); + nfs_end_delegation_return(inode, ret, 0); +} + +/** * nfs4_inode_make_writeable * @inode: pointer to inode * @@ -633,23 +789,24 @@ */ int nfs4_inode_make_writeable(struct inode *inode) { - if (!nfs4_has_session(NFS_SERVER(inode)->nfs_client) || - !nfs4_check_delegation(inode, FMODE_WRITE)) - return nfs4_inode_return_delegation(inode); - return 0; + struct nfs_delegation *delegation; + + rcu_read_lock(); + delegation = nfs4_get_valid_delegation(inode); + if (delegation == NULL || + (nfs4_has_session(NFS_SERVER(inode)->nfs_client) && + (delegation->type & FMODE_WRITE))) { + rcu_read_unlock(); + return 0; + } + rcu_read_unlock(); + return nfs4_inode_return_delegation(inode); } static void nfs_mark_return_if_closed_delegation(struct nfs_server *server, struct nfs_delegation *delegation) { set_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags); - set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state); -} - -static void nfs_mark_return_delegation(struct nfs_server *server, - struct nfs_delegation *delegation) -{ - set_bit(NFS_DELEGATION_RETURN, &delegation->flags); set_bit(NFS4CLNT_DELEGRETURN, &server->nfs_client->cl_state); } @@ -694,7 +851,7 @@ /** * nfs_super_return_all_delegations - return delegations for one superblock - * @sb: sb to process + * @server: pointer to nfs_server to process * */ void nfs_server_return_all_delegations(struct nfs_server *server) @@ -739,15 +896,7 @@ rcu_read_unlock(); } -static void nfs_mark_delegation_revoked(struct nfs_server *server, - struct nfs_delegation *delegation) -{ - set_bit(NFS_DELEGATION_REVOKED, &delegation->flags); - delegation->stateid.type = NFS4_INVALID_STATEID_TYPE; - nfs_mark_return_delegation(server, delegation); -} - -static bool nfs_revoke_delegation(struct inode *inode, +static void nfs_revoke_delegation(struct inode *inode, const nfs4_stateid *stateid) { struct nfs_delegation *delegation; @@ -761,29 +910,69 @@ if (stateid == NULL) { nfs4_stateid_copy(&tmp, &delegation->stateid); stateid = &tmp; - } else if (!nfs4_stateid_match(stateid, &delegation->stateid)) - goto out; - nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation); + } else { + if (!nfs4_stateid_match_other(stateid, &delegation->stateid)) + goto out; + spin_lock(&delegation->lock); + if (stateid->seqid) { + if (nfs4_stateid_is_newer(&delegation->stateid, stateid)) { + spin_unlock(&delegation->lock); + goto out; + } + delegation->stateid.seqid = stateid->seqid; + } + spin_unlock(&delegation->lock); + } + nfs_mark_delegation_revoked(delegation); ret = true; out: rcu_read_unlock(); if (ret) nfs_inode_find_state_and_recover(inode, stateid); - return ret; } void nfs_remove_bad_delegation(struct inode *inode, const nfs4_stateid *stateid) { - struct nfs_delegation *delegation; - - if (!nfs_revoke_delegation(inode, stateid)) - return; - delegation = nfs_inode_detach_delegation(inode); - if (delegation) - nfs_free_delegation(delegation); + nfs_revoke_delegation(inode, stateid); } EXPORT_SYMBOL_GPL(nfs_remove_bad_delegation); + +void nfs_delegation_mark_returned(struct inode *inode, + const nfs4_stateid *stateid) +{ + struct nfs_delegation *delegation; + + if (!inode) + return; + + rcu_read_lock(); + delegation = rcu_dereference(NFS_I(inode)->delegation); + if (!delegation) + goto out_rcu_unlock; + + spin_lock(&delegation->lock); + if (!nfs4_stateid_match_other(stateid, &delegation->stateid)) + goto out_spin_unlock; + if (stateid->seqid) { + /* If delegation->stateid is newer, dont mark as returned */ + if (nfs4_stateid_is_newer(&delegation->stateid, stateid)) + goto out_clear_returning; + if (delegation->stateid.seqid != stateid->seqid) + delegation->stateid.seqid = stateid->seqid; + } + + nfs_mark_delegation_revoked(delegation); + +out_clear_returning: + clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags); +out_spin_unlock: + spin_unlock(&delegation->lock); +out_rcu_unlock: + rcu_read_unlock(); + + nfs_inode_find_state_and_recover(inode, stateid); +} /** * nfs_expire_unused_delegation_types @@ -840,7 +1029,7 @@ struct nfs_delegation *delegation; rcu_read_lock(); - delegation = rcu_dereference(NFS_I(inode)->delegation); + delegation = nfs4_get_valid_delegation(inode); if (delegation == NULL) goto out_enoent; if (stateid != NULL && @@ -861,21 +1050,24 @@ const struct nfs_fh *fhandle) { struct nfs_delegation *delegation; - struct inode *freeme, *res = NULL; + struct super_block *freeme = NULL; + struct inode *res = NULL; list_for_each_entry_rcu(delegation, &server->delegations, super_list) { spin_lock(&delegation->lock); if (delegation->inode != NULL && + !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) && nfs_compare_fh(fhandle, &NFS_I(delegation->inode)->fh) == 0) { - freeme = igrab(delegation->inode); - if (freeme && nfs_sb_active(freeme->i_sb)) - res = freeme; + if (nfs_sb_active(server->super)) { + freeme = server->super; + res = igrab(delegation->inode); + } spin_unlock(&delegation->lock); if (res != NULL) return res; if (freeme) { rcu_read_unlock(); - iput(freeme); + nfs_sb_deactive(freeme); rcu_read_lock(); } return ERR_PTR(-EAGAIN); @@ -941,6 +1133,42 @@ rcu_read_unlock(); } +static int nfs_server_reap_unclaimed_delegations(struct nfs_server *server, + void __always_unused *data) +{ + struct nfs_delegation *delegation; + struct inode *inode; +restart: + rcu_read_lock(); +restart_locked: + list_for_each_entry_rcu(delegation, &server->delegations, super_list) { + if (test_bit(NFS_DELEGATION_INODE_FREEING, + &delegation->flags) || + test_bit(NFS_DELEGATION_RETURNING, + &delegation->flags) || + test_bit(NFS_DELEGATION_NEED_RECLAIM, + &delegation->flags) == 0) + continue; + inode = nfs_delegation_grab_inode(delegation); + if (inode == NULL) + goto restart_locked; + delegation = nfs_start_delegation_return_locked(NFS_I(inode)); + rcu_read_unlock(); + if (delegation != NULL) { + if (nfs_detach_delegation(NFS_I(inode), delegation, + server) != NULL) + nfs_free_delegation(delegation); + /* Match nfs_start_delegation_return_locked */ + nfs_put_delegation(delegation); + } + iput(inode); + cond_resched(); + goto restart; + } + rcu_read_unlock(); + return 0; +} + /** * nfs_delegation_reap_unclaimed - reap unclaimed delegations after reboot recovery is done * @clp: nfs_client to process @@ -948,45 +1176,8 @@ */ void nfs_delegation_reap_unclaimed(struct nfs_client *clp) { - struct nfs_delegation *delegation; - struct nfs_server *server; - struct inode *inode; - -restart: - rcu_read_lock(); - list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { - list_for_each_entry_rcu(delegation, &server->delegations, - super_list) { - if (test_bit(NFS_DELEGATION_INODE_FREEING, - &delegation->flags) || - test_bit(NFS_DELEGATION_RETURNING, - &delegation->flags) || - test_bit(NFS_DELEGATION_NEED_RECLAIM, - &delegation->flags) == 0) - continue; - if (!nfs_sb_active(server->super)) - break; /* continue in outer loop */ - inode = nfs_delegation_grab_inode(delegation); - if (inode == NULL) { - rcu_read_unlock(); - nfs_sb_deactive(server->super); - goto restart; - } - delegation = nfs_start_delegation_return_locked(NFS_I(inode)); - rcu_read_unlock(); - if (delegation != NULL) { - delegation = nfs_detach_delegation(NFS_I(inode), - delegation, server); - if (delegation != NULL) - nfs_free_delegation(delegation); - } - iput(inode); - nfs_sb_deactive(server->super); - cond_resched(); - goto restart; - } - } - rcu_read_unlock(); + nfs_client_for_each_server(clp, nfs_server_reap_unclaimed_delegations, + NULL); } static inline bool nfs4_server_rebooted(const struct nfs_client *clp) @@ -1045,6 +1236,76 @@ } /** + * nfs_test_expired_all_delegations - test all delegations for a client + * @clp: nfs_client to process + * + * Helper for handling "recallable state revoked" status from server. + */ +void nfs_test_expired_all_delegations(struct nfs_client *clp) +{ + nfs_mark_test_expired_all_delegations(clp); + nfs4_schedule_state_manager(clp); +} + +static void +nfs_delegation_test_free_expired(struct inode *inode, + nfs4_stateid *stateid, + const struct cred *cred) +{ + struct nfs_server *server = NFS_SERVER(inode); + const struct nfs4_minor_version_ops *ops = server->nfs_client->cl_mvops; + int status; + + if (!cred) + return; + status = ops->test_and_free_expired(server, stateid, cred); + if (status == -NFS4ERR_EXPIRED || status == -NFS4ERR_BAD_STATEID) + nfs_remove_bad_delegation(inode, stateid); +} + +static int nfs_server_reap_expired_delegations(struct nfs_server *server, + void __always_unused *data) +{ + struct nfs_delegation *delegation; + struct inode *inode; + const struct cred *cred; + nfs4_stateid stateid; +restart: + rcu_read_lock(); +restart_locked: + list_for_each_entry_rcu(delegation, &server->delegations, super_list) { + if (test_bit(NFS_DELEGATION_INODE_FREEING, + &delegation->flags) || + test_bit(NFS_DELEGATION_RETURNING, + &delegation->flags) || + test_bit(NFS_DELEGATION_TEST_EXPIRED, + &delegation->flags) == 0) + continue; + inode = nfs_delegation_grab_inode(delegation); + if (inode == NULL) + goto restart_locked; + spin_lock(&delegation->lock); + cred = get_cred_rcu(delegation->cred); + nfs4_stateid_copy(&stateid, &delegation->stateid); + spin_unlock(&delegation->lock); + clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags); + rcu_read_unlock(); + nfs_delegation_test_free_expired(inode, &stateid, cred); + put_cred(cred); + if (!nfs4_server_rebooted(server->nfs_client)) { + iput(inode); + cond_resched(); + goto restart; + } + nfs_inode_mark_test_expired_delegation(server,inode); + iput(inode); + return -EAGAIN; + } + rcu_read_unlock(); + return 0; +} + +/** * nfs_reap_expired_delegations - reap expired delegations * @clp: nfs_client to process * @@ -1055,56 +1316,8 @@ */ void nfs_reap_expired_delegations(struct nfs_client *clp) { - const struct nfs4_minor_version_ops *ops = clp->cl_mvops; - struct nfs_delegation *delegation; - struct nfs_server *server; - struct inode *inode; - struct rpc_cred *cred; - nfs4_stateid stateid; - -restart: - rcu_read_lock(); - list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) { - list_for_each_entry_rcu(delegation, &server->delegations, - super_list) { - if (test_bit(NFS_DELEGATION_INODE_FREEING, - &delegation->flags) || - test_bit(NFS_DELEGATION_RETURNING, - &delegation->flags) || - test_bit(NFS_DELEGATION_TEST_EXPIRED, - &delegation->flags) == 0) - continue; - if (!nfs_sb_active(server->super)) - break; /* continue in outer loop */ - inode = nfs_delegation_grab_inode(delegation); - if (inode == NULL) { - rcu_read_unlock(); - nfs_sb_deactive(server->super); - goto restart; - } - cred = get_rpccred_rcu(delegation->cred); - nfs4_stateid_copy(&stateid, &delegation->stateid); - clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags); - rcu_read_unlock(); - if (cred != NULL && - ops->test_and_free_expired(server, &stateid, cred) < 0) { - nfs_revoke_delegation(inode, &stateid); - nfs_inode_find_state_and_recover(inode, &stateid); - } - put_rpccred(cred); - if (nfs4_server_rebooted(clp)) { - nfs_inode_mark_test_expired_delegation(server,inode); - iput(inode); - nfs_sb_deactive(server->super); - return; - } - iput(inode); - nfs_sb_deactive(server->super); - cond_resched(); - goto restart; - } - } - rcu_read_unlock(); + nfs_client_for_each_server(clp, nfs_server_reap_expired_delegations, + NULL); } void nfs_inode_find_delegation_state_and_recover(struct inode *inode, @@ -1117,7 +1330,8 @@ rcu_read_lock(); delegation = rcu_dereference(NFS_I(inode)->delegation); if (delegation && - nfs4_stateid_match_other(&delegation->stateid, stateid)) { + nfs4_stateid_match_or_older(&delegation->stateid, stateid) && + !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { nfs_mark_test_expired_delegation(NFS_SERVER(inode), delegation); found = true; } @@ -1166,7 +1380,9 @@ rcu_read_lock(); delegation = rcu_dereference(NFS_I(inode)->delegation); if (delegation != NULL && - nfs4_stateid_match_other(dst, &delegation->stateid)) { + nfs4_stateid_match_other(dst, &delegation->stateid) && + nfs4_stateid_is_newer(&delegation->stateid, dst) && + !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) { dst->seqid = delegation->stateid.seqid; ret = true; } @@ -1186,22 +1402,27 @@ * otherwise "false" is returned. */ bool nfs4_copy_delegation_stateid(struct inode *inode, fmode_t flags, - nfs4_stateid *dst, struct rpc_cred **cred) + nfs4_stateid *dst, const struct cred **cred) { struct nfs_inode *nfsi = NFS_I(inode); struct nfs_delegation *delegation; - bool ret; + bool ret = false; flags &= FMODE_READ|FMODE_WRITE; rcu_read_lock(); delegation = rcu_dereference(nfsi->delegation); + if (!delegation) + goto out; + spin_lock(&delegation->lock); ret = nfs4_is_valid_delegation(delegation, flags); if (ret) { nfs4_stateid_copy(dst, &delegation->stateid); nfs_mark_delegation_referenced(delegation); if (cred) - *cred = get_rpccred(delegation->cred); + *cred = get_cred(delegation->cred); } + spin_unlock(&delegation->lock); +out: rcu_read_unlock(); return ret; } @@ -1230,3 +1451,5 @@ rcu_read_unlock(); return ret; } + +module_param_named(delegation_watermark, nfs_delegation_watermark, uint, 0644); -- Gitblit v1.6.2