9 files changed, 149 insertions, 103 deletions

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 1c5ff6d58385..6a4f3666e273 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1412,24 +1412,18 @@ int nfs_fs_proc_net_init(struct net *net)
         p = proc_create("volumes", S_IFREG|S_IRUGO,
                         nn->proc_nfsfs, &nfs_volume_list_fops);
         if (!p)
-                goto error_2;
+                goto error_1;
         return 0;
 
-error_2:
-        remove_proc_entry("servers", nn->proc_nfsfs);
 error_1:
-        remove_proc_entry("fs/nfsfs", NULL);
+        remove_proc_subtree("nfsfs", net->proc_net);
 error_0:
         return -ENOMEM;
 }
 
 void nfs_fs_proc_net_exit(struct net *net)
 {
-        struct nfs_net *nn = net_generic(net, nfs_net_id);
-
-        remove_proc_entry("volumes", nn->proc_nfsfs);
-        remove_proc_entry("servers", nn->proc_nfsfs);
-        remove_proc_entry("fs/nfsfs", NULL);
+        remove_proc_subtree("nfsfs", net->proc_net);
 }
 
 /*
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index 1359c4a27393..90978075f730 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -1269,11 +1269,12 @@ filelayout_search_commit_reqs(struct nfs_commit_info *cinfo, struct page *page)
 static void filelayout_retry_commit(struct nfs_commit_info *cinfo, int idx)
 {
         struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
-        struct pnfs_commit_bucket *bucket = fl_cinfo->buckets;
+        struct pnfs_commit_bucket *bucket;
         struct pnfs_layout_segment *freeme;
         int i;
 
-        for (i = idx; i < fl_cinfo->nbuckets; i++, bucket++) {
+        for (i = idx; i < fl_cinfo->nbuckets; i++) {
+                bucket = &fl_cinfo->buckets[i];
                 if (list_empty(&bucket->committing))
                         continue;
                 nfs_retry_commit(&bucket->committing, bucket->clseg, cinfo);
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index d0fec260132a..24c6898159cc 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -129,7 +129,10 @@ static int __nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
                 .rpc_argp       = &args,
                 .rpc_resp       = &fattr,
         };
-        int status;
+        int status = 0;
+
+        if (acl == NULL && (!S_ISDIR(inode->i_mode) || dfacl == NULL))
+                goto out;
 
         status = -EOPNOTSUPP;
         if (!nfs_server_capable(inode, NFS_CAP_ACLS))
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 92193eddb41d..a8b855ab4e22 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -130,16 +130,15 @@ enum {
  */
 
 struct nfs4_lock_state {
-        struct list_head                ls_locks;   /* Other lock stateids */
-        struct nfs4_state *             ls_state;   /* Pointer to open state */
+        struct list_head        ls_locks;       /* Other lock stateids */
+        struct nfs4_state *     ls_state;       /* Pointer to open state */
 #define NFS_LOCK_INITIALIZED 0
 #define NFS_LOCK_LOST        1
-        unsigned long                   ls_flags;
+        unsigned long           ls_flags;
         struct nfs_seqid_counter        ls_seqid;
-        nfs4_stateid                    ls_stateid;
-        atomic_t                        ls_count;
-        fl_owner_t                      ls_owner;
-        struct work_struct              ls_release;
+        nfs4_stateid            ls_stateid;
+        atomic_t                ls_count;
+        fl_owner_t              ls_owner;
 };
 
 /* bits for nfs4_state->flags */
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 53e435a95260..ffdb28d86cf8 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -482,6 +482,16 @@ int nfs40_walk_client_list(struct nfs_client *new,
 
         spin_lock(&nn->nfs_client_lock);
         list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
+
+                if (pos->rpc_ops != new->rpc_ops)
+                        continue;
+
+                if (pos->cl_proto != new->cl_proto)
+                        continue;
+
+                if (pos->cl_minorversion != new->cl_minorversion)
+                        continue;
+
                 /* If "pos" isn't marked ready, we can't trust the
                  * remaining fields in "pos" */
                 if (pos->cl_cons_state > NFS_CS_READY) {
@@ -501,15 +511,6 @@ int nfs40_walk_client_list(struct nfs_client *new,
                 if (pos->cl_cons_state != NFS_CS_READY)
                         continue;
 
-                if (pos->rpc_ops != new->rpc_ops)
-                        continue;
-
-                if (pos->cl_proto != new->cl_proto)
-                        continue;
-
-                if (pos->cl_minorversion != new->cl_minorversion)
-                        continue;
-
                 if (pos->cl_clientid != new->cl_clientid)
                         continue;
 
@@ -622,6 +623,16 @@ int nfs41_walk_client_list(struct nfs_client *new,
 
         spin_lock(&nn->nfs_client_lock);
         list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
+
+                if (pos->rpc_ops != new->rpc_ops)
+                        continue;
+
+                if (pos->cl_proto != new->cl_proto)
+                        continue;
+
+                if (pos->cl_minorversion != new->cl_minorversion)
+                        continue;
+
                 /* If "pos" isn't marked ready, we can't trust the
                  * remaining fields in "pos", especially the client
                  * ID and serverowner fields.  Wait for CREATE_SESSION
@@ -647,15 +658,6 @@ int nfs41_walk_client_list(struct nfs_client *new,
                 if (pos->cl_cons_state != NFS_CS_READY)
                         continue;
 
-                if (pos->rpc_ops != new->rpc_ops)
-                        continue;
-
-                if (pos->cl_proto != new->cl_proto)
-                        continue;
-
-                if (pos->cl_minorversion != new->cl_minorversion)
-                        continue;
-
                 if (!nfs4_match_clientids(pos, new))
                         continue;
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 75ae8d22f067..6ca0c8e7a945 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2226,9 +2226,13 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
         ret = _nfs4_proc_open(opendata);
         if (ret != 0) {
                 if (ret == -ENOENT) {
-                        d_drop(opendata->dentry);
-                        d_add(opendata->dentry, NULL);
-                        nfs_set_verifier(opendata->dentry,
+                        dentry = opendata->dentry;
+                        if (dentry->d_inode)
+                                d_delete(dentry);
+                        else if (d_unhashed(dentry))
+                                d_add(dentry, NULL);
+
+                        nfs_set_verifier(dentry,
                                          nfs_save_change_attribute(opendata->dir->d_inode));
                 }
                 goto out;
@@ -2560,6 +2564,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
         struct nfs4_closedata *calldata = data;
         struct nfs4_state *state = calldata->state;
         struct nfs_server *server = NFS_SERVER(calldata->inode);
+        nfs4_stateid *res_stateid = NULL;
 
         dprintk("%s: begin!\n", __func__);
         if (!nfs4_sequence_done(task, &calldata->res.seq_res))
@@ -2570,12 +2575,12 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
          */
         switch (task->tk_status) {
                 case 0:
-                        if (calldata->roc)
+                        res_stateid = &calldata->res.stateid;
+                        if (calldata->arg.fmode == 0 && calldata->roc)
                                 pnfs_roc_set_barrier(state->inode,
                                                      calldata->roc_barrier);
-                        nfs_clear_open_stateid(state, &calldata->res.stateid, 0);
                         renew_lease(server, calldata->timestamp);
-                        goto out_release;
+                        break;
                 case -NFS4ERR_ADMIN_REVOKED:
                 case -NFS4ERR_STALE_STATEID:
                 case -NFS4ERR_OLD_STATEID:
@@ -2589,7 +2594,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
                                 goto out_release;
                         }
         }
-        nfs_clear_open_stateid(state, NULL, calldata->arg.fmode);
+        nfs_clear_open_stateid(state, res_stateid, calldata->arg.fmode);
 out_release:
         nfs_release_seqid(calldata->arg.seqid);
         nfs_refresh_inode(calldata->inode, calldata->res.fattr);
@@ -2601,6 +2606,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
         struct nfs4_closedata *calldata = data;
         struct nfs4_state *state = calldata->state;
         struct inode *inode = calldata->inode;
+        bool is_rdonly, is_wronly, is_rdwr;
         int call_close = 0;
 
         dprintk("%s: begin!\n", __func__);
@@ -2608,21 +2614,27 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
                 goto out_wait;
 
         task->tk_msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_OPEN_DOWNGRADE];
-        calldata->arg.fmode = FMODE_READ|FMODE_WRITE;
         spin_lock(&state->owner->so_lock);
+        is_rdwr = test_bit(NFS_O_RDWR_STATE, &state->flags);
+        is_rdonly = test_bit(NFS_O_RDONLY_STATE, &state->flags);
+        is_wronly = test_bit(NFS_O_WRONLY_STATE, &state->flags);
         /* Calculate the change in open mode */
+        calldata->arg.fmode = 0;
         if (state->n_rdwr == 0) {
-                if (state->n_rdonly == 0) {
-                        call_close |= test_bit(NFS_O_RDONLY_STATE, &state->flags);
-                        call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
-                        calldata->arg.fmode &= ~FMODE_READ;
-                }
-                if (state->n_wronly == 0) {
-                        call_close |= test_bit(NFS_O_WRONLY_STATE, &state->flags);
-                        call_close |= test_bit(NFS_O_RDWR_STATE, &state->flags);
-                        calldata->arg.fmode &= ~FMODE_WRITE;
-                }
-        }
+                if (state->n_rdonly == 0)
+                        call_close |= is_rdonly;
+                else if (is_rdonly)
+                        calldata->arg.fmode |= FMODE_READ;
+                if (state->n_wronly == 0)
+                        call_close |= is_wronly;
+                else if (is_wronly)
+                        calldata->arg.fmode |= FMODE_WRITE;
+        } else if (is_rdwr)
+                calldata->arg.fmode |= FMODE_READ|FMODE_WRITE;
+
+        if (calldata->arg.fmode == 0)
+                call_close |= is_rdwr;
+
         if (!nfs4_valid_open_stateid(state))
                 call_close = 0;
         spin_unlock(&state->owner->so_lock);
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index a043f618cd5a..22fe35104c0c 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -799,18 +799,6 @@ __nfs4_find_lock_state(struct nfs4_state *state, fl_owner_t fl_owner)
         return NULL;
 }
 
-static void
-free_lock_state_work(struct work_struct *work)
-{
-        struct nfs4_lock_state *lsp = container_of(work,
-                                        struct nfs4_lock_state, ls_release);
-        struct nfs4_state *state = lsp->ls_state;
-        struct nfs_server *server = state->owner->so_server;
-        struct nfs_client *clp = server->nfs_client;
-
-        clp->cl_mvops->free_lock_state(server, lsp);
-}
-
 /*
  * Return a compatible lock_state. If no initialized lock_state structure
  * exists, return an uninitialized one.
@@ -832,7 +820,6 @@ static struct nfs4_lock_state *nfs4_alloc_lock_state(struct nfs4_state *state, f
         if (lsp->ls_seqid.owner_id < 0)
                 goto out_free;
         INIT_LIST_HEAD(&lsp->ls_locks);
-        INIT_WORK(&lsp->ls_release, free_lock_state_work);
         return lsp;
 out_free:
         kfree(lsp);
@@ -896,12 +883,13 @@ void nfs4_put_lock_state(struct nfs4_lock_state *lsp)
         if (list_empty(&state->lock_states))
                 clear_bit(LK_STATE_IN_USE, &state->flags);
         spin_unlock(&state->state_lock);
-        if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags))
-                queue_work(nfsiod_workqueue, &lsp->ls_release);
-        else {
-                server = state->owner->so_server;
+        server = state->owner->so_server;
+        if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags)) {
+                struct nfs_client *clp = server->nfs_client;
+
+                clp->cl_mvops->free_lock_state(server, lsp);
+        } else
                 nfs4_free_lock_state(server, lsp);
-        }
 }
 
 static void nfs4_fl_copy_lock(struct file_lock *dst, struct file_lock *src)
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index ba491926df5f..be7cbce6e4c7 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -116,7 +116,7 @@ __nfs_iocounter_wait(struct nfs_io_counter *c)
                 if (atomic_read(&c->io_count) == 0)
                         break;
                 ret = nfs_wait_bit_killable(&q.key);
-        } while (atomic_read(&c->io_count) != 0);
+        } while (atomic_read(&c->io_count) != 0 && !ret);
         finish_wait(wq, &q.wait);
         return ret;
 }
@@ -139,26 +139,49 @@ nfs_iocounter_wait(struct nfs_io_counter *c)
 /*
  * nfs_page_group_lock - lock the head of the page group
  * @req - request in group that is to be locked
+ * @nonblock - if true don't block waiting for lock
  *
  * this lock must be held if modifying the page group list
  *
- * returns result from wait_on_bit_lock: 0 on success, < 0 on error
+ * return 0 on success, < 0 on error: -EDELAY if nonblocking or the
+ * result from wait_on_bit_lock
+ *
+ * NOTE: calling with nonblock=false should always have set the
+ *       lock bit (see fs/buffer.c and other uses of wait_on_bit_lock
+ *       with TASK_UNINTERRUPTIBLE), so there is no need to check the result.
  */
 int
-nfs_page_group_lock(struct nfs_page *req, bool wait)
+nfs_page_group_lock(struct nfs_page *req, bool nonblock)
 {
         struct nfs_page *head = req->wb_head;
-        int ret;
 
         WARN_ON_ONCE(head != head->wb_head);
 
-        do {
-                ret = wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
-                        TASK_UNINTERRUPTIBLE);
-        } while (wait && ret != 0);
+        if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags))
+                return 0;
 
-        WARN_ON_ONCE(ret > 0);
-        return ret;
+        if (!nonblock)
+                return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
+                                TASK_UNINTERRUPTIBLE);
+
+        return -EAGAIN;
+}
+
+/*
+ * nfs_page_group_lock_wait - wait for the lock to clear, but don't grab it
+ * @req - a request in the group
+ *
+ * This is a blocking call to wait for the group lock to be cleared.
+ */
+void
+nfs_page_group_lock_wait(struct nfs_page *req)
+{
+        struct nfs_page *head = req->wb_head;
+
+        WARN_ON_ONCE(head != head->wb_head);
+
+        wait_on_bit(&head->wb_flags, PG_HEADLOCK,
+                TASK_UNINTERRUPTIBLE);
 }
 
 /*
@@ -219,7 +242,7 @@ bool nfs_page_group_sync_on_bit(struct nfs_page *req, unsigned int bit)
 {
         bool ret;
 
-        nfs_page_group_lock(req, true);
+        nfs_page_group_lock(req, false);
         ret = nfs_page_group_sync_on_bit_locked(req, bit);
         nfs_page_group_unlock(req);
 
@@ -701,10 +724,11 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
                      struct nfs_pgio_header *hdr)
 {
         struct nfs_page         *req;
-        struct page             **pages;
+        struct page             **pages,
+                                *last_page;
         struct list_head *head = &desc->pg_list;
         struct nfs_commit_info cinfo;
-        unsigned int pagecount;
+        unsigned int pagecount, pageused;
 
         pagecount = nfs_page_array_len(desc->pg_base, desc->pg_count);
         if (!nfs_pgarray_set(&hdr->page_array, pagecount))
@@ -712,12 +736,23 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 
         nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
         pages = hdr->page_array.pagevec;
+        last_page = NULL;
+        pageused = 0;
         while (!list_empty(head)) {
                 req = nfs_list_entry(head->next);
                 nfs_list_remove_request(req);
                 nfs_list_add_request(req, &hdr->pages);
-                *pages++ = req->wb_page;
+
+                if (WARN_ON_ONCE(pageused >= pagecount))
+                        return nfs_pgio_error(desc, hdr);
+
+                if (!last_page || last_page != req->wb_page) {
+                        *pages++ = last_page = req->wb_page;
+                        pageused++;
+                }
         }
+        if (WARN_ON_ONCE(pageused != pagecount))
+                return nfs_pgio_error(desc, hdr);
 
         if ((desc->pg_ioflags & FLUSH_COND_STABLE) &&
             (desc->pg_moreio || nfs_reqs_to_commit(&cinfo)))
@@ -788,6 +823,14 @@ static bool nfs_can_coalesce_requests(struct nfs_page *prev,
                         return false;
                 if (req_offset(req) != req_offset(prev) + prev->wb_bytes)
                         return false;
+                if (req->wb_page == prev->wb_page) {
+                        if (req->wb_pgbase != prev->wb_pgbase + prev->wb_bytes)
+                                return false;
+                } else {
+                        if (req->wb_pgbase != 0 ||
+                            prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
+                                return false;
+                }
         }
         size = pgio->pg_ops->pg_test(pgio, prev, req);
         WARN_ON_ONCE(size > req->wb_bytes);
@@ -858,13 +901,8 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
         struct nfs_page *subreq;
         unsigned int bytes_left = 0;
         unsigned int offset, pgbase;
-        int ret;
 
-        ret = nfs_page_group_lock(req, false);
-        if (ret < 0) {
-                desc->pg_error = ret;
-                return 0;
-        }
+        nfs_page_group_lock(req, false);
 
         subreq = req;
         bytes_left = subreq->wb_bytes;
@@ -886,11 +924,7 @@ static int __nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
                         if (desc->pg_recoalesce)
                                 return 0;
                         /* retry add_request for this subreq */
-                        ret = nfs_page_group_lock(req, false);
-                        if (ret < 0) {
-                                desc->pg_error = ret;
-                                return 0;
-                        }
+                        nfs_page_group_lock(req, false);
                         continue;
                 }
 
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index e3b5cf28bdc5..175d5d073ccf 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -241,7 +241,7 @@ static bool nfs_page_group_covers_page(struct nfs_page *req)
         unsigned int pos = 0;
         unsigned int len = nfs_page_length(req->wb_page);
 
-        nfs_page_group_lock(req, true);
+        nfs_page_group_lock(req, false);
 
         do {
                 tmp = nfs_page_group_search_locked(req->wb_head, pos);
@@ -478,10 +478,23 @@ try_again:
                 return NULL;
         }
 
-        /* lock each request in the page group */
-        ret = nfs_page_group_lock(head, false);
-        if (ret < 0)
+        /* holding inode lock, so always make a non-blocking call to try the
+         * page group lock */
+        ret = nfs_page_group_lock(head, true);
+        if (ret < 0) {
+                spin_unlock(&inode->i_lock);
+
+                if (!nonblock && ret == -EAGAIN) {
+                        nfs_page_group_lock_wait(head);
+                        nfs_release_request(head);
+                        goto try_again;
+                }
+
+                nfs_release_request(head);
                 return ERR_PTR(ret);
+        }
+
+        /* lock each request in the page group */
         subreq = head;
         do {
                 /*