Merge branch 'for-3.8' of git://linux-nfs.org/~bfields/linux

Pull nfsd update from Bruce Fields:
 "Included this time:

   - more nfsd containerization work from Stanislav Kinsbursky: we're
     not quite there yet, but should be by 3.9.

   - NFSv4.1 progress: implementation of basic backchannel security
     negotiation and the mandatory BACKCHANNEL_CTL operation.  See

       http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues

     for remaining TODO's

   - Fixes for some bugs that could be triggered by unusual compounds.
     Our xdr code wasn't designed with v4 compounds in mind, and it
     shows.  A more thorough rewrite is still a todo.

   - If you've ever seen "RPC: multiple fragments per record not
     supported" logged while using some sort of odd userland NFS client,
     that should now be fixed.

   - Further work from Jeff Layton on our mechanism for storing
     information about NFSv4 clients across reboots.

   - Further work from Bryan Schumaker on his fault-injection mechanism
     (which allows us to discard selective NFSv4 state, to excercise
     rarely-taken recovery code paths in the client.)

   - The usual mix of miscellaneous bugs and cleanup.

  Thanks to everyone who tested or contributed this cycle."

* 'for-3.8' of git://linux-nfs.org/~bfields/linux: (111 commits)
  nfsd4: don't leave freed stateid hashed
  nfsd4: free_stateid can use the current stateid
  nfsd4: cleanup: replace rq_resused count by rq_next_page pointer
  nfsd: warn on odd reply state in nfsd_vfs_read
  nfsd4: fix oops on unusual readlike compound
  nfsd4: disable zero-copy on non-final read ops
  svcrpc: fix some printks
  NFSD: Correct the size calculation in fault_inject_write
  NFSD: Pass correct buffer size to rpc_ntop
  nfsd: pass proper net to nfsd_destroy() from NFSd kthreads
  nfsd: simplify service shutdown
  nfsd: replace boolean nfsd_up flag by users counter
  nfsd: simplify NFSv4 state init and shutdown
  nfsd: introduce helpers for generic resources init and shutdown
  nfsd: make NFSd service structure allocated per net
  nfsd: make NFSd service boot time per-net
  nfsd: per-net NFSd up flag introduced
  nfsd: move per-net startup code to separated function
  nfsd: pass net to __write_ports() and down
  nfsd: pass net to nfsd_set_nrthreads()
  ...

Documentation/filesystems/nfs/nfs41-server.txt

@@ -39,21 +39,10 @@ interoperability problems with future clients.  Known issues:
 	  from a linux client are possible, but we aren't really
 	  conformant with the spec (for example, we don't use kerberos
 	  on the backchannel correctly).
-	- Incomplete backchannel support: incomplete backchannel gss
-	  support and no support for BACKCHANNEL_CTL mean that
-	  callbacks (hence delegations and layouts) may not be
-	  available and clients confused by the incomplete
-	  implementation may fail.
 	- We do not support SSV, which provides security for shared
 	  client-server state (thus preventing unauthorized tampering
 	  with locks and opens, for example).  It is mandatory for
 	  servers to support this, though no clients use it yet.
-	- Mandatory operations which we do not support, such as
-	  DESTROY_CLIENTID, are not currently used by clients, but will be
-	  (and the spec recommends their uses in common cases), and
-	  clients should not be expected to know how to recover from the
-	  case where they are not supported.  This will eventually cause
-	  interoperability failures.
 
 In addition, some limitations are inherited from the current NFSv4
 implementation:
@@ -89,7 +78,7 @@ Operations
    |                      | MNI        | or OPT)      |                |
    +----------------------+------------+--------------+----------------+
    | ACCESS               | REQ        |              | Section 18.1   |
-NS | BACKCHANNEL_CTL      | REQ        |              | Section 18.33  |
+I  | BACKCHANNEL_CTL      | REQ        |              | Section 18.33  |
 I  | BIND_CONN_TO_SESSION | REQ        |              | Section 18.34  |
    | CLOSE                | REQ        |              | Section 18.2   |
    | COMMIT               | REQ        |              | Section 18.3   |
@@ -99,7 +88,7 @@ NS*| DELEGPURGE           | OPT        | FDELG (REQ)  | Section 18.5   |
    | DELEGRETURN          | OPT        | FDELG,       | Section 18.6   |
    |                      |            | DDELG, pNFS  |                |
    |                      |            | (REQ)        |                |
-NS | DESTROY_CLIENTID     | REQ        |              | Section 18.50  |
+I  | DESTROY_CLIENTID     | REQ        |              | Section 18.50  |
 I  | DESTROY_SESSION      | REQ        |              | Section 18.37  |
 I  | EXCHANGE_ID          | REQ        |              | Section 18.35  |
 I  | FREE_STATEID         | REQ        |              | Section 18.38  |
@@ -192,7 +181,6 @@ EXCHANGE_ID:
 
 CREATE_SESSION:
 * backchannel attributes are ignored
-* backchannel security parameters are ignored
 
 SEQUENCE:
 * no support for dynamic slot table renegotiation (optional)
@@ -202,7 +190,7 @@ Nonstandard compound limitations:
   ca_maxrequestsize request and a ca_maxresponsesize reply, so we may
   fail to live up to the promise we made in CREATE_SESSION fore channel
   negotiation.
-* No more than one IO operation (read, write, readdir) allowed per
-  compound.
+* No more than one read-like operation allowed per compound; encoding
+  replies that cross page boundaries (except for read data) not handled.
 
 See also http://wiki.linux-nfs.org/wiki/index.php/Server_4.0_and_4.1_issues.

fs/exportfs/expfs.c

@@ -322,10 +322,10 @@ static int export_encode_fh(struct inode *inode, struct fid *fid,
 
 	if (parent && (len < 4)) {
 		*max_len = 4;
-		return 255;
+		return FILEID_INVALID;
 	} else if (len < 2) {
 		*max_len = 2;
-		return 255;
+		return FILEID_INVALID;
 	}
 
 	len = 2;

fs/fhandle.c

@@ -52,7 +52,7 @@ static long do_sys_name_to_handle(struct path *path,
 	handle_bytes = handle_dwords * sizeof(u32);
 	handle->handle_bytes = handle_bytes;
 	if ((handle->handle_bytes > f_handle.handle_bytes) ||
-	    (retval == 255) || (retval == -ENOSPC)) {
+	    (retval == FILEID_INVALID) || (retval == -ENOSPC)) {
 		/* As per old exportfs_encode_fh documentation
 		 * we could return ENOSPC to indicate overflow
 		 * But file system returned 255 always. So handle

fs/nfsd/fault_inject.c

@@ -8,61 +8,144 @@
 #include <linux/fs.h>
 #include <linux/debugfs.h>
 #include <linux/module.h>
+#include <linux/nsproxy.h>
+#include <linux/sunrpc/clnt.h>
+#include <asm/uaccess.h>
 
 #include "state.h"
-#include "fault_inject.h"
+#include "netns.h"
 
 struct nfsd_fault_inject_op {
 	char *file;
-	void (*func)(u64);
+	u64 (*forget)(struct nfs4_client *, u64);
+	u64 (*print)(struct nfs4_client *, u64);
 };
 
 static struct nfsd_fault_inject_op inject_ops[] = {
 	{
 		.file   = "forget_clients",
-		.func   = nfsd_forget_clients,
+		.forget = nfsd_forget_client,
+		.print  = nfsd_print_client,
 	},
 	{
 		.file   = "forget_locks",
-		.func   = nfsd_forget_locks,
+		.forget = nfsd_forget_client_locks,
+		.print  = nfsd_print_client_locks,
 	},
 	{
 		.file   = "forget_openowners",
-		.func   = nfsd_forget_openowners,
+		.forget = nfsd_forget_client_openowners,
+		.print  = nfsd_print_client_openowners,
 	},
 	{
 		.file   = "forget_delegations",
-		.func   = nfsd_forget_delegations,
+		.forget = nfsd_forget_client_delegations,
+		.print  = nfsd_print_client_delegations,
 	},
 	{
 		.file   = "recall_delegations",
-		.func   = nfsd_recall_delegations,
+		.forget = nfsd_recall_client_delegations,
+		.print  = nfsd_print_client_delegations,
 	},
 };
 
 static long int NUM_INJECT_OPS = sizeof(inject_ops) / sizeof(struct nfsd_fault_inject_op);
 static struct dentry *debug_dir;
 
-static int nfsd_inject_set(void *op_ptr, u64 val)
+static void nfsd_inject_set(struct nfsd_fault_inject_op *op, u64 val)
 {
-	struct nfsd_fault_inject_op *op = op_ptr;
+	u64 count = 0;
 
 	if (val == 0)
 		printk(KERN_INFO "NFSD Fault Injection: %s (all)", op->file);
 	else
 		printk(KERN_INFO "NFSD Fault Injection: %s (n = %llu)", op->file, val);
 
-	op->func(val);
-	return 0;
+	nfs4_lock_state();
+	count = nfsd_for_n_state(val, op->forget);
+	nfs4_unlock_state();
+	printk(KERN_INFO "NFSD: %s: found %llu", op->file, count);
 }
 
-static int nfsd_inject_get(void *data, u64 *val)
+static void nfsd_inject_set_client(struct nfsd_fault_inject_op *op,
+				   struct sockaddr_storage *addr,
+				   size_t addr_size)
 {
-	*val = 0;
-	return 0;
+	char buf[INET6_ADDRSTRLEN];
+	struct nfs4_client *clp;
+	u64 count;
+
+	nfs4_lock_state();
+	clp = nfsd_find_client(addr, addr_size);
+	if (clp) {
+		count = op->forget(clp, 0);
+		rpc_ntop((struct sockaddr *)&clp->cl_addr, buf, sizeof(buf));
+		printk(KERN_INFO "NFSD [%s]: Client %s had %llu state object(s)\n", op->file, buf, count);
+	}
+	nfs4_unlock_state();
+}
+
+static void nfsd_inject_get(struct nfsd_fault_inject_op *op, u64 *val)
+{
+	nfs4_lock_state();
+	*val = nfsd_for_n_state(0, op->print);
+	nfs4_unlock_state();
 }
 
-DEFINE_SIMPLE_ATTRIBUTE(fops_nfsd, nfsd_inject_get, nfsd_inject_set, "%llu\n");
+static ssize_t fault_inject_read(struct file *file, char __user *buf,
+				 size_t len, loff_t *ppos)
+{
+	static u64 val;
+	char read_buf[25];
+	size_t size, ret;
+	loff_t pos = *ppos;
+
+	if (!pos)
+		nfsd_inject_get(file->f_dentry->d_inode->i_private, &val);
+	size = scnprintf(read_buf, sizeof(read_buf), "%llu\n", val);
+
+	if (pos < 0)
+		return -EINVAL;
+	if (pos >= size || !len)
+		return 0;
+	if (len > size - pos)
+		len = size - pos;
+	ret = copy_to_user(buf, read_buf + pos, len);
+	if (ret == len)
+		return -EFAULT;
+	len -= ret;
+	*ppos = pos + len;
+	return len;
+}
+
+static ssize_t fault_inject_write(struct file *file, const char __user *buf,
+				  size_t len, loff_t *ppos)
+{
+	char write_buf[INET6_ADDRSTRLEN];
+	size_t size = min(sizeof(write_buf) - 1, len);
+	struct net *net = current->nsproxy->net_ns;
+	struct sockaddr_storage sa;
+	u64 val;
+
+	if (copy_from_user(write_buf, buf, size))
+		return -EFAULT;
+	write_buf[size] = '\0';
+
+	size = rpc_pton(net, write_buf, size, (struct sockaddr *)&sa, sizeof(sa));
+	if (size > 0)
+		nfsd_inject_set_client(file->f_dentry->d_inode->i_private, &sa, size);
+	else {
+		val = simple_strtoll(write_buf, NULL, 0);
+		nfsd_inject_set(file->f_dentry->d_inode->i_private, val);
+	}
+	return len; /* on success, claim we got the whole input */
+}
+
+static const struct file_operations fops_nfsd = {
+	.owner   = THIS_MODULE,
+	.read    = fault_inject_read,
+	.write   = fault_inject_write,
+};
 
 void nfsd_fault_inject_cleanup(void)
 {

fs/nfsd/netns.h

@@ -24,7 +24,18 @@
 #include <net/net_namespace.h>
 #include <net/netns/generic.h>
 
+/* Hash tables for nfs4_clientid state */
+#define CLIENT_HASH_BITS                 4
+#define CLIENT_HASH_SIZE                (1 << CLIENT_HASH_BITS)
+#define CLIENT_HASH_MASK                (CLIENT_HASH_SIZE - 1)
+
+#define LOCKOWNER_INO_HASH_BITS		8
+#define LOCKOWNER_INO_HASH_SIZE		(1 << LOCKOWNER_INO_HASH_BITS)
+
+#define SESSION_HASH_SIZE	512
+
 struct cld_net;
+struct nfsd4_client_tracking_ops;
 
 struct nfsd_net {
 	struct cld_net *cld_net;
@@ -38,7 +49,62 @@ struct nfsd_net {
 	struct lock_manager nfsd4_manager;
 	bool grace_ended;
 	time_t boot_time;
+
+	/*
+	 * reclaim_str_hashtbl[] holds known client info from previous reset/reboot
+	 * used in reboot/reset lease grace period processing
+	 *
+	 * conf_id_hashtbl[], and conf_name_tree hold confirmed
+	 * setclientid_confirmed info.
+	 *
+	 * unconf_str_hastbl[] and unconf_name_tree hold unconfirmed
+	 * setclientid info.
+	 */
+	struct list_head *reclaim_str_hashtbl;
+	int reclaim_str_hashtbl_size;
+	struct list_head *conf_id_hashtbl;
+	struct rb_root conf_name_tree;
+	struct list_head *unconf_id_hashtbl;
+	struct rb_root unconf_name_tree;
+	struct list_head *ownerstr_hashtbl;
+	struct list_head *lockowner_ino_hashtbl;
+	struct list_head *sessionid_hashtbl;
+	/*
+	 * client_lru holds client queue ordered by nfs4_client.cl_time
+	 * for lease renewal.
+	 *
+	 * close_lru holds (open) stateowner queue ordered by nfs4_stateowner.so_time
+	 * for last close replay.
+	 *
+	 * All of the above fields are protected by the client_mutex.
+	 */
+	struct list_head client_lru;
+	struct list_head close_lru;
+
+	struct delayed_work laundromat_work;
+
+	/* client_lock protects the client lru list and session hash table */
+	spinlock_t client_lock;
+
+	struct file *rec_file;
+	bool in_grace;
+	struct nfsd4_client_tracking_ops *client_tracking_ops;
+
+	time_t nfsd4_lease;
+	time_t nfsd4_grace;
+
+	bool nfsd_net_up;
+
+	/*
+	 * Time of server startup
+	 */
+	struct timeval nfssvc_boot;
+
+	struct svc_serv *nfsd_serv;
 };
 
+/* Simple check to find out if a given net was properly initialized */
+#define nfsd_netns_ready(nn) ((nn)->sessionid_hashtbl)
+
 extern int nfsd_net_id;
 #endif /* __NFSD_NETNS_H__ */

fs/nfsd/nfs2acl.c

@@ -253,7 +253,7 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 		(resp->mask & NFS_ACL)   ? resp->acl_access  : NULL,
 		(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
 	while (w > 0) {
-		if (!rqstp->rq_respages[rqstp->rq_resused++])
+		if (!*(rqstp->rq_next_page++))
 			return 0;
 		w -= PAGE_SIZE;
 	}

fs/nfsd/nfs3acl.c

@@ -184,7 +184,7 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 			(resp->mask & NFS_ACL)   ? resp->acl_access  : NULL,
 			(resp->mask & NFS_DFACL) ? resp->acl_default : NULL);
 		while (w > 0) {
-			if (!rqstp->rq_respages[rqstp->rq_resused++])
+			if (!*(rqstp->rq_next_page++))
 				return 0;
 			w -= PAGE_SIZE;
 		}

fs/nfsd/nfs3proc.c

@@ -460,7 +460,7 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
 	__be32	nfserr;
 	int	count = 0;
 	loff_t	offset;
-	int	i;
+	struct page **p;
 	caddr_t	page_addr = NULL;
 
 	dprintk("nfsd: READDIR+(3) %s %d bytes at %d\n",
@@ -484,8 +484,8 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
 				     &resp->common,
 				     nfs3svc_encode_entry_plus);
 	memcpy(resp->verf, argp->verf, 8);
-	for (i=1; i<rqstp->rq_resused ; i++) {
-		page_addr = page_address(rqstp->rq_respages[i]);
+	for (p = rqstp->rq_respages + 1; p < rqstp->rq_next_page; p++) {
+		page_addr = page_address(*p);
 
 		if (((caddr_t)resp->buffer >= page_addr) &&
 		    ((caddr_t)resp->buffer < page_addr + PAGE_SIZE)) {