1 files changed, 114 insertions, 96 deletions

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index b60fddf606f..75366dc8968 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -39,6 +39,8 @@
 #include <linux/delay.h>
 #include <linux/errno.h>
 #include <linux/string.h>
+#include <linux/ratelimit.h>
+#include <linux/printk.h>
 #include <linux/slab.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/gss_api.h>
@@ -50,9 +52,11 @@
 #include <linux/namei.h>
 #include <linux/mount.h>
 #include <linux/module.h>
+#include <linux/nfs_idmap.h>
 #include <linux/sunrpc/bc_xprt.h>
 #include <linux/xattr.h>
 #include <linux/utsname.h>
+#include <linux/freezer.h>
 
 #include "nfs4_fs.h"
 #include "delegation.h"
@@ -241,7 +245,7 @@ static int nfs4_delay(struct rpc_clnt *clnt, long *timeout)
 		*timeout = NFS4_POLL_RETRY_MIN;
 	if (*timeout > NFS4_POLL_RETRY_MAX)
 		*timeout = NFS4_POLL_RETRY_MAX;
-	schedule_timeout_killable(*timeout);
+	freezable_schedule_timeout_killable(*timeout);
 	if (fatal_signal_pending(current))
 		res = -ERESTARTSYS;
 	*timeout <<= 1;
@@ -361,9 +365,8 @@ static void renew_lease(const struct nfs_server *server, unsigned long timestamp
  * Must be called while holding tbl->slot_tbl_lock
  */
 static void
-nfs4_free_slot(struct nfs4_slot_table *tbl, struct nfs4_slot *free_slot)
+nfs4_free_slot(struct nfs4_slot_table *tbl, u8 free_slotid)
 {
-	int free_slotid = free_slot - tbl->slots;
 	int slotid = free_slotid;
 
 	BUG_ON(slotid < 0 || slotid >= NFS4_MAX_SLOT_TABLE);
@@ -428,7 +431,7 @@ static void nfs41_sequence_free_slot(struct nfs4_sequence_res *res)
 	}
 
 	spin_lock(&tbl->slot_tbl_lock);
-	nfs4_free_slot(tbl, res->sr_slot);
+	nfs4_free_slot(tbl, res->sr_slot - tbl->slots);
 	nfs4_check_drain_fc_complete(res->sr_session);
 	spin_unlock(&tbl->slot_tbl_lock);
 	res->sr_slot = NULL;
@@ -551,13 +554,10 @@ int nfs41_setup_sequence(struct nfs4_session *session,
 	spin_lock(&tbl->slot_tbl_lock);
 	if (test_bit(NFS4_SESSION_DRAINING, &session->session_state) &&
 	    !rpc_task_has_priority(task, RPC_PRIORITY_PRIVILEGED)) {
-		/*
-		 * The state manager will wait until the slot table is empty.
-		 * Schedule the reset thread
-		 */
+		/* The state manager will wait until the slot table is empty */
 		rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
 		spin_unlock(&tbl->slot_tbl_lock);
-		dprintk("%s Schedule Session Reset\n", __func__);
+		dprintk("%s session is draining\n", __func__);
 		return -EAGAIN;
 	}
 
@@ -762,6 +762,8 @@ struct nfs4_opendata {
 	struct nfs_openres o_res;
 	struct nfs_open_confirmargs c_arg;
 	struct nfs_open_confirmres c_res;
+	struct nfs4_string owner_name;
+	struct nfs4_string group_name;
 	struct nfs_fattr f_attr;
 	struct nfs_fattr dir_attr;
 	struct dentry *dir;
@@ -785,6 +787,7 @@ static void nfs4_init_opendata_res(struct nfs4_opendata *p)
 	p->o_res.server = p->o_arg.server;
 	nfs_fattr_init(&p->f_attr);
 	nfs_fattr_init(&p->dir_attr);
+	nfs_fattr_init_names(&p->f_attr, &p->owner_name, &p->group_name);
 }
 
 static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
@@ -816,6 +819,7 @@ static struct nfs4_opendata *nfs4_opendata_alloc(struct dentry *dentry,
 	p->o_arg.name = &dentry->d_name;
 	p->o_arg.server = server;
 	p->o_arg.bitmask = server->attr_bitmask;
+	p->o_arg.dir_bitmask = server->cache_consistency_bitmask;
 	p->o_arg.claim = NFS4_OPEN_CLAIM_NULL;
 	if (flags & O_CREAT) {
 		u32 *s;
@@ -852,6 +856,7 @@ static void nfs4_opendata_free(struct kref *kref)
 	dput(p->dir);
 	dput(p->dentry);
 	nfs_sb_deactive(sb);
+	nfs_fattr_free_names(&p->f_attr);
 	kfree(p);
 }
 
@@ -894,6 +899,8 @@ out:
 
 static int can_open_delegated(struct nfs_delegation *delegation, fmode_t fmode)
 {
+	if (delegation == NULL)
+		return 0;
 	if ((delegation->type & fmode) != fmode)
 		return 0;
 	if (test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags))
@@ -1036,8 +1043,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
 		}
 		rcu_read_lock();
 		delegation = rcu_dereference(nfsi->delegation);
-		if (delegation == NULL ||
-		    !can_open_delegated(delegation, fmode)) {
+		if (!can_open_delegated(delegation, fmode)) {
 			rcu_read_unlock();
 			break;
 		}
@@ -1091,7 +1097,12 @@ static struct nfs4_state *nfs4_opendata_to_nfs4_state(struct nfs4_opendata *data
 		if (delegation)
 			delegation_flags = delegation->flags;
 		rcu_read_unlock();
-		if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
+		if (data->o_arg.claim == NFS4_OPEN_CLAIM_DELEGATE_CUR) {
+			pr_err_ratelimited("NFS: Broken NFSv4 server %s is "
+					"returning a delegation for "
+					"OPEN(CLAIM_DELEGATE_CUR)\n",
+					NFS_CLIENT(inode)->cl_server);
+		} else if ((delegation_flags & 1UL<<NFS_DELEGATION_NEED_RECLAIM) == 0)
 			nfs_inode_set_delegation(state->inode,
 					data->owner->so_cred,
 					&data->o_res);
@@ -1423,11 +1434,9 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 			goto out_no_action;
 		rcu_read_lock();
 		delegation = rcu_dereference(NFS_I(data->state->inode)->delegation);
-		if (delegation != NULL &&
-		    test_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags) == 0) {
-			rcu_read_unlock();
-			goto out_no_action;
-		}
+		if (data->o_arg.claim != NFS4_OPEN_CLAIM_DELEGATE_CUR &&
+		    can_open_delegated(delegation, data->o_arg.fmode))
+			goto unlock_no_action;
 		rcu_read_unlock();
 	}
 	/* Update sequence id. */
@@ -1444,6 +1453,8 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 		return;
 	rpc_call_start(task);
 	return;
+unlock_no_action:
+	rcu_read_unlock();
 out_no_action:
 	task->tk_action = NULL;
 
@@ -1570,6 +1581,8 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data)
 	if (status != 0 || !data->rpc_done)
 		return status;
 
+	nfs_fattr_map_and_free_names(NFS_SERVER(dir), &data->f_attr);
+
 	nfs_refresh_inode(dir, o_res->dir_attr);
 
 	if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
@@ -1602,6 +1615,8 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 		return status;
 	}
 
+	nfs_fattr_map_and_free_names(server, &data->f_attr);
+
 	if (o_arg->open_flags & O_CREAT) {
 		update_changeattr(dir, &o_res->cinfo);
 		nfs_post_op_update_inode(dir, o_res->dir_attr);
@@ -2464,8 +2479,7 @@ static int nfs4_proc_lookup(struct rpc_clnt *clnt, struct inode *dir, struct qst
 		case -NFS4ERR_BADNAME:
 			return -ENOENT;
 		case -NFS4ERR_MOVED:
-			err = nfs4_get_referral(dir, name, fattr, fhandle);
-			break;
+			return nfs4_get_referral(dir, name, fattr, fhandle);
 		case -NFS4ERR_WRONGSEC:
 			nfs_fixup_secinfo_attributes(fattr, fhandle);
 		}
@@ -3423,19 +3437,6 @@ static inline int nfs4_server_supports_acls(struct nfs_server *server)
  */
 #define NFS4ACL_MAXPAGES (XATTR_SIZE_MAX >> PAGE_CACHE_SHIFT)
 
-static void buf_to_pages(const void *buf, size_t buflen,
-		struct page **pages, unsigned int *pgbase)
-{
-	const void *p = buf;
-
-	*pgbase = offset_in_page(buf);
-	p -= *pgbase;
-	while (p < buf + buflen) {
-		*(pages++) = virt_to_page(p);
-		p += PAGE_CACHE_SIZE;
-	}
-}
-
 static int buf_to_pages_noslab(const void *buf, size_t buflen,
 		struct page **pages, unsigned int *pgbase)
 {
@@ -3532,9 +3533,19 @@ out:
 	nfs4_set_cached_acl(inode, acl);
 }
 
+/*
+ * The getxattr API returns the required buffer length when called with a
+ * NULL buf. The NFSv4 acl tool then calls getxattr again after allocating
+ * the required buf.  On a NULL buf, we send a page of data to the server
+ * guessing that the ACL request can be serviced by a page. If so, we cache
+ * up to the page of ACL data, and the 2nd call to getxattr is serviced by
+ * the cache. If not so, we throw away the page, and cache the required
+ * length. The next getxattr call will then produce another round trip to
+ * the server, this time with the input buf of the required size.
+ */
 static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
 {
-	struct page *pages[NFS4ACL_MAXPAGES];
+	struct page *pages[NFS4ACL_MAXPAGES] = {NULL, };
 	struct nfs_getaclargs args = {
 		.fh = NFS_FH(inode),
 		.acl_pages = pages,
@@ -3549,41 +3560,60 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	struct page *localpage = NULL;
-	int ret;
+	int ret = -ENOMEM, npages, i, acl_len = 0;
 
-	if (buflen < PAGE_SIZE) {
-		/* As long as we're doing a round trip to the server anyway,
-		 * let's be prepared for a page of acl data. */
-		localpage = alloc_page(GFP_KERNEL);
-		resp_buf = page_address(localpage);
-		if (localpage == NULL)
-			return -ENOMEM;
-		args.acl_pages[0] = localpage;
-		args.acl_pgbase = 0;
-		args.acl_len = PAGE_SIZE;
-	} else {
-		resp_buf = buf;
-		buf_to_pages(buf, buflen, args.acl_pages, &args.acl_pgbase);
+	npages = (buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
+	/* As long as we're doing a round trip to the server anyway,
+	 * let's be prepared for a page of acl data. */
+	if (npages == 0)
+		npages = 1;
+
+	for (i = 0; i < npages; i++) {
+		pages[i] = alloc_page(GFP_KERNEL);
+		if (!pages[i])
+			goto out_free;
+	}
+	if (npages > 1) {
+		/* for decoding across pages */
+		args.acl_scratch = alloc_page(GFP_KERNEL);
+		if (!args.acl_scratch)
+			goto out_free;
 	}
-	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode), &msg, &args.seq_args, &res.seq_res, 0);
+	args.acl_len = npages * PAGE_SIZE;
+	args.acl_pgbase = 0;
+	/* Let decode_getfacl know not to fail if the ACL data is larger than
+	 * the page we send as a guess */
+	if (buf == NULL)
+		res.acl_flags |= NFS4_ACL_LEN_REQUEST;
+	resp_buf = page_address(pages[0]);
+
+	dprintk("%s  buf %p buflen %ld npages %d args.acl_len %ld\n",
+		__func__, buf, buflen, npages, args.acl_len);
+	ret = nfs4_call_sync(NFS_SERVER(inode)->client, NFS_SERVER(inode),
+			     &msg, &args.seq_args, &res.seq_res, 0);
 	if (ret)
 		goto out_free;
-	if (res.acl_len > args.acl_len)
-		nfs4_write_cached_acl(inode, NULL, res.acl_len);
+
+	acl_len = res.acl_len - res.acl_data_offset;
+	if (acl_len > args.acl_len)
+		nfs4_write_cached_acl(inode, NULL, acl_len);
 	else
-		nfs4_write_cached_acl(inode, resp_buf, res.acl_len);
+		nfs4_write_cached_acl(inode, resp_buf + res.acl_data_offset,
+				      acl_len);
 	if (buf) {
 		ret = -ERANGE;
-		if (res.acl_len > buflen)
+		if (acl_len > buflen)
 			goto out_free;
-		if (localpage)
-			memcpy(buf, resp_buf, res.acl_len);
+		_copy_from_pages(buf, pages, res.acl_data_offset,
+				res.acl_len);
 	}
-	ret = res.acl_len;
+	ret = acl_len;
 out_free:
-	if (localpage)
-		__free_page(localpage);
+	for (i = 0; i < npages; i++)
+		if (pages[i])
+			__free_page(pages[i]);
+	if (args.acl_scratch)
+		__free_page(args.acl_scratch);
 	return ret;
 }
 
@@ -3614,6 +3644,8 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
 		nfs_zap_acl_cache(inode);
 	ret = nfs4_read_cached_acl(inode, buf, buflen);
 	if (ret != -ENOENT)
+		/* -ENOENT is returned if there is no ACL or if there is an ACL
+		 * but no cached acl data, just the acl length */
 		return ret;
 	return nfs4_get_acl_uncached(inode, buf, buflen);
 }
@@ -3951,7 +3983,7 @@ int nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, const nfs4
 static unsigned long
 nfs4_set_lock_task_retry(unsigned long timeout)
 {
-	schedule_timeout_killable(timeout);
+	freezable_schedule_timeout_killable(timeout);
 	timeout <<= 1;
 	if (timeout > NFS4_LOCK_MAXTIMEOUT)
 		return NFS4_LOCK_MAXTIMEOUT;
@@ -5014,23 +5046,6 @@ out:
 	return ret;
 }
 
-/*
- * Reset the forechannel and backchannel slot tables
- */
-static int nfs4_reset_slot_tables(struct nfs4_session *session)
-{
-	int status;
-
-	status = nfs4_reset_slot_table(&session->fc_slot_table,
-			session->fc_attrs.max_reqs, 1);
-	if (status)
-		return status;
-
-	status = nfs4_reset_slot_table(&session->bc_slot_table,
-			session->bc_attrs.max_reqs, 0);
-	return status;
-}
-
 /* Destroy the slot table */
 static void nfs4_destroy_slot_tables(struct nfs4_session *session)
 {
@@ -5076,29 +5091,35 @@ out:
 }
 
 /*
- * Initialize the forechannel and backchannel tables
+ * Initialize or reset the forechannel and backchannel tables
  */
-static int nfs4_init_slot_tables(struct nfs4_session *session)
+static int nfs4_setup_session_slot_tables(struct nfs4_session *ses)
 {
 	struct nfs4_slot_table *tbl;
-	int status = 0;
+	int status;
 
-	tbl = &session->fc_slot_table;
+	dprintk("--> %s\n", __func__);
+	/* Fore channel */
+	tbl = &ses->fc_slot_table;
 	if (tbl->slots == NULL) {
-		status = nfs4_init_slot_table(tbl,
-				session->fc_attrs.max_reqs, 1);
+		status = nfs4_init_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
+		if (status) /* -ENOMEM */
+			return status;
+	} else {
+		status = nfs4_reset_slot_table(tbl, ses->fc_attrs.max_reqs, 1);
 		if (status)
 			return status;
 	}
-
-	tbl = &session->bc_slot_table;
+	/* Back channel */
+	tbl = &ses->bc_slot_table;
 	if (tbl->slots == NULL) {
-		status = nfs4_init_slot_table(tbl,
-				session->bc_attrs.max_reqs, 0);
+		status = nfs4_init_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
 		if (status)
-			nfs4_destroy_slot_tables(session);
-	}
-
+			/* Fore and back channel share a connection so get
+			 * both slot tables or neither */
+			nfs4_destroy_slot_tables(ses);
+	} else
+		status = nfs4_reset_slot_table(tbl, ses->bc_attrs.max_reqs, 0);
 	return status;
 }
 
@@ -5286,13 +5307,9 @@ int nfs4_proc_create_session(struct nfs_client *clp)
 	if (status)
 		goto out;
 
-	/* Init and reset the fore channel */
-	status = nfs4_init_slot_tables(session);
-	dprintk("slot table initialization returned %d\n", status);
-	if (status)
-		goto out;
-	status = nfs4_reset_slot_tables(session);
-	dprintk("slot table reset returned %d\n", status);
+	/* Init or reset the session slot tables */
+	status = nfs4_setup_session_slot_tables(session);
+	dprintk("slot table setup returned %d\n", status);
 	if (status)
 		goto out;
 
@@ -6253,6 +6270,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.dentry_ops	= &nfs4_dentry_operations,
 	.dir_inode_ops	= &nfs4_dir_inode_operations,
 	.file_inode_ops	= &nfs4_file_inode_operations,
+	.file_ops	= &nfs4_file_operations,
 	.getroot	= nfs4_proc_get_root,
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,