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()
  ...

22 files changed, 1814 insertions, 985 deletions

diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index 606bb074c501..5df4bb4aab14 100644
--- a/fs/exportfs/expfs.c
+++ b/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;
diff --git a/fs/fhandle.c b/fs/fhandle.c
index cccdc874bb55..999ff5c3cab0 100644
--- a/fs/fhandle.c
+++ b/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
diff --git a/fs/nfsd/fault_inject.c b/fs/nfsd/fault_inject.c
index e6c38159622f..e761ee95617f 100644
--- a/fs/nfsd/fault_inject.c
+++ b/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)
 {
diff --git a/fs/nfsd/fault_inject.h b/fs/nfsd/fault_inject.h
deleted file mode 100644
index 90bd0570956c..000000000000
--- a/fs/nfsd/fault_inject.h
+++ /dev/null
@@ -1,28 +0,0 @@
-/*
- * Copyright (c) 2011 Bryan Schumaker <bjschuma@netapp.com>
- *
- * Function definitions for fault injection
- */
-
-#ifndef LINUX_NFSD_FAULT_INJECT_H
-#define LINUX_NFSD_FAULT_INJECT_H
-
-#ifdef CONFIG_NFSD_FAULT_INJECTION
-int nfsd_fault_inject_init(void);
-void nfsd_fault_inject_cleanup(void);
-void nfsd_forget_clients(u64);
-void nfsd_forget_locks(u64);
-void nfsd_forget_openowners(u64);
-void nfsd_forget_delegations(u64);
-void nfsd_recall_delegations(u64);
-#else /* CONFIG_NFSD_FAULT_INJECTION */
-static inline int nfsd_fault_inject_init(void) { return 0; }
-static inline void nfsd_fault_inject_cleanup(void) {}
-static inline void nfsd_forget_clients(u64 num) {}
-static inline void nfsd_forget_locks(u64 num) {}
-static inline void nfsd_forget_openowners(u64 num) {}
-static inline void nfsd_forget_delegations(u64 num) {}
-static inline void nfsd_recall_delegations(u64 num) {}
-#endif /* CONFIG_NFSD_FAULT_INJECTION */
-
-#endif /* LINUX_NFSD_FAULT_INJECT_H */
diff --git a/fs/nfsd/netns.h b/fs/nfsd/netns.h
index 65c2431ea32f..1051bebff1b0 100644
--- a/fs/nfsd/netns.h
+++ b/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__ */
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index b314888825d5..9170861c804a 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/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;
 	}
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index a596e9d987e4..9cbc1a841f87 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/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;
 		}
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index 97d90d1c8608..1fc02dfdc5c4 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/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)) {
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index 43f46cd9edea..324c0baf7cda 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -7,8 +7,10 @@
  */
 
 #include <linux/namei.h>
+#include <linux/sunrpc/svc_xprt.h>
 #include "xdr3.h"
 #include "auth.h"
+#include "netns.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_XDR
 
@@ -323,7 +325,7 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd3_readargs *args)
 {
 	unsigned int len;
-	int v,pn;
+	int v;
 	u32 max_blocksize = svc_max_payload(rqstp);
 
 	if (!(p = decode_fh(p, &args->fh)))
@@ -338,8 +340,9 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 	/* set up the kvec */
 	v=0;
 	while (len > 0) {
-		pn = rqstp->rq_resused++;
-		rqstp->rq_vec[v].iov_base = page_address(rqstp->rq_respages[pn]);
+		struct page *p = *(rqstp->rq_next_page++);
+
+		rqstp->rq_vec[v].iov_base = page_address(p);
 		rqstp->rq_vec[v].iov_len = len < PAGE_SIZE? len : PAGE_SIZE;
 		len -= rqstp->rq_vec[v].iov_len;
 		v++;
@@ -461,8 +464,7 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 	len = ntohl(*p++);
 	if (len == 0 || len > NFS3_MAXPATHLEN || len >= PAGE_SIZE)
 		return 0;
-	args->tname = new =
-		page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+	args->tname = new = page_address(*(rqstp->rq_next_page++));
 	args->tlen = len;
 	/* first copy and check from the first page */
 	old = (char*)p;
@@ -533,8 +535,7 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
 {
 	if (!(p = decode_fh(p, &args->fh)))
 		return 0;
-	args->buffer =
-		page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+	args->buffer = page_address(*(rqstp->rq_next_page++));
 
 	return xdr_argsize_check(rqstp, p);
 }
@@ -565,8 +566,7 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
 	if (args->count > PAGE_SIZE)
 		args->count = PAGE_SIZE;
 
-	args->buffer =
-		page_address(rqstp->rq_respages[rqstp->rq_resused++]);
+	args->buffer = page_address(*(rqstp->rq_next_page++));
 
 	return xdr_argsize_check(rqstp, p);
 }
@@ -575,7 +575,7 @@ int
 nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd3_readdirargs *args)
 {
-	int len, pn;
+	int len;
 	u32 max_blocksize = svc_max_payload(rqstp);
 
 	if (!(p = decode_fh(p, &args->fh)))
@@ -590,9 +590,9 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
 	args->count = len;
 
 	while (len > 0) {
-		pn = rqstp->rq_resused++;
+		struct page *p = *(rqstp->rq_next_page++);
 		if (!args->buffer)
-			args->buffer = page_address(rqstp->rq_respages[pn]);
+			args->buffer = page_address(p);
 		len -= PAGE_SIZE;
 	}
 
@@ -720,12 +720,14 @@ int
 nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd3_writeres *resp)
 {
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
 	p = encode_wcc_data(rqstp, p, &resp->fh);
 	if (resp->status == 0) {
 		*p++ = htonl(resp->count);
 		*p++ = htonl(resp->committed);
-		*p++ = htonl(nfssvc_boot.tv_sec);
-		*p++ = htonl(nfssvc_boot.tv_usec);
+		*p++ = htonl(nn->nfssvc_boot.tv_sec);
+		*p++ = htonl(nn->nfssvc_boot.tv_usec);
 	}
 	return xdr_ressize_check(rqstp, p);
 }
@@ -876,7 +878,7 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
 		       					common);
 	__be32		*p = cd->buffer;
 	caddr_t		curr_page_addr = NULL;
-	int		pn;		/* current page number */
+	struct page **	page;
 	int		slen;		/* string (name) length */
 	int		elen;		/* estimated entry length in words */
 	int		num_entry_words = 0;	/* actual number of words */
@@ -913,8 +915,9 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
 	}
 
 	/* determine which page in rq_respages[] we are currently filling */
-	for (pn=1; pn < cd->rqstp->rq_resused; pn++) {
-		curr_page_addr = page_address(cd->rqstp->rq_respages[pn]);
+	for (page = cd->rqstp->rq_respages + 1;
+				page < cd->rqstp->rq_next_page; page++) {
+		curr_page_addr = page_address(*page);
 
 		if (((caddr_t)cd->buffer >= curr_page_addr) &&
 		    ((caddr_t)cd->buffer <  curr_page_addr + PAGE_SIZE))
@@ -929,14 +932,14 @@ encode_entry(struct readdir_cd *ccd, const char *name, int namlen,
 		if (plus)
 			p = encode_entryplus_baggage(cd, p, name, namlen);
 		num_entry_words = p - cd->buffer;
-	} else if (cd->rqstp->rq_respages[pn+1] != NULL) {
+	} else if (*(page+1) != NULL) {
 		/* temporarily encode entry into next page, then move back to
 		 * current and next page in rq_respages[] */
 		__be32 *p1, *tmp;
 		int len1, len2;
 
 		/* grab next page for temporary storage of entry */
-		p1 = tmp = page_address(cd->rqstp->rq_respages[pn+1]);
+		p1 = tmp = page_address(*(page+1));
 
 		p1 = encode_entry_baggage(cd, p1, name, namlen, ino);
 
@@ -1082,11 +1085,13 @@ int
 nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p,
 					struct nfsd3_commitres *resp)
 {
+	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+
 	p = encode_wcc_data(rqstp, p, &resp->fh);
 	/* Write verifier */
 	if (resp->status == 0) {
-		*p++ = htonl(nfssvc_boot.tv_sec);
-		*p++ = htonl(nfssvc_boot.tv_usec);
+		*p++ = htonl(nn->nfssvc_boot.tv_sec);
+		*p++ = htonl(nn->nfssvc_boot.tv_usec);
 	}
 	return xdr_ressize_check(rqstp, p);
 }
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index bdf29c96e4cd..99bc85ff0217 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -36,6 +36,7 @@
 #include <linux/slab.h>
 #include "nfsd.h"
 #include "state.h"
+#include "netns.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
 
@@ -625,20 +626,46 @@ static const struct rpc_program cb_program = {
 	.pipe_dir_name		= "nfsd4_cb",
 };
 
-static int max_cb_time(void)
+static int max_cb_time(struct net *net)
 {
-	return max(nfsd4_lease/10, (time_t)1) * HZ;
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	return max(nn->nfsd4_lease/10, (time_t)1) * HZ;
 }
 
+static struct rpc_cred *callback_cred;
+
+int set_callback_cred(void)
+{
+	if (callback_cred)
+		return 0;
+	callback_cred = rpc_lookup_machine_cred("nfs");
+	if (!callback_cred)
+		return -ENOMEM;
+	return 0;
+}
+
+static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses)
+{
+	if (clp->cl_minorversion == 0) {
+		return get_rpccred(callback_cred);
+	} else {
+		struct rpc_auth *auth = client->cl_auth;
+		struct auth_cred acred = {};
+
+		acred.uid = ses->se_cb_sec.uid;
+		acred.gid = ses->se_cb_sec.gid;
+		return auth->au_ops->lookup_cred(client->cl_auth, &acred, 0);
+	}
+}
 
 static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *conn, struct nfsd4_session *ses)
 {
 	struct rpc_timeout	timeparms = {
-		.to_initval	= max_cb_time(),
+		.to_initval	= max_cb_time(clp->net),
 		.to_retries	= 0,
 	};
 	struct rpc_create_args args = {
-		.net		= &init_net,
+		.net		= clp->net,
 		.address	= (struct sockaddr *) &conn->cb_addr,
 		.addrsize	= conn->cb_addrlen,
 		.saddress	= (struct sockaddr *) &conn->cb_saddr,
@@ -648,6 +675,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		.flags		= (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET),
 	};
 	struct rpc_clnt *client;
+	struct rpc_cred *cred;
 
 	if (clp->cl_minorversion == 0) {
 		if (!clp->cl_cred.cr_principal &&
@@ -666,7 +694,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		args.bc_xprt = conn->cb_xprt;
 		args.prognumber = clp->cl_cb_session->se_cb_prog;
 		args.protocol = XPRT_TRANSPORT_BC_TCP;
-		args.authflavor = RPC_AUTH_UNIX;
+		args.authflavor = ses->se_cb_sec.flavor;
 	}
 	/* Create RPC client */
 	client = rpc_create(&args);
@@ -675,9 +703,14 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 			PTR_ERR(client));
 		return PTR_ERR(client);
 	}
+	cred = get_backchannel_cred(clp, client, ses);
+	if (IS_ERR(cred)) {
+		rpc_shutdown_client(client);
+		return PTR_ERR(cred);
+	}
 	clp->cl_cb_client = client;
+	clp->cl_cb_cred = cred;
 	return 0;
-
 }
 
 static void warn_no_callback_path(struct nfs4_client *clp, int reason)
@@ -714,18 +747,6 @@ static const struct rpc_call_ops nfsd4_cb_probe_ops = {
 	.rpc_call_done = nfsd4_cb_probe_done,
 };
 
-static struct rpc_cred *callback_cred;
-
-int set_callback_cred(void)
-{
-	if (callback_cred)
-		return 0;
-	callback_cred = rpc_lookup_machine_cred("nfs");
-	if (!callback_cred)
-		return -ENOMEM;
-	return 0;
-}
-
 static struct workqueue_struct *callback_wq;
 
 static void run_nfsd4_cb(struct nfsd4_callback *cb)
@@ -743,7 +764,6 @@ static void do_probe_callback(struct nfs4_client *clp)
 	cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL];
 	cb->cb_msg.rpc_argp = NULL;
 	cb->cb_msg.rpc_resp = NULL;
-	cb->cb_msg.rpc_cred = callback_cred;
 
 	cb->cb_ops = &nfsd4_cb_probe_ops;
 
@@ -962,6 +982,8 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 	if (clp->cl_cb_client) {
 		rpc_shutdown_client(clp->cl_cb_client);
 		clp->cl_cb_client = NULL;
+		put_rpccred(clp->cl_cb_cred);
+		clp->cl_cb_cred = NULL;
 	}
 	if (clp->cl_cb_conn.cb_xprt) {
 		svc_xprt_put(clp->cl_cb_conn.cb_xprt);
@@ -995,7 +1017,7 @@ static void nfsd4_process_cb_update(struct nfsd4_callback *cb)
 		run_nfsd4_cb(cb);
 }
 
-void nfsd4_do_callback_rpc(struct work_struct *w)
+static void nfsd4_do_callback_rpc(struct work_struct *w)
 {
 	struct nfsd4_callback *cb = container_of(w, struct nfsd4_callback, cb_work);
 	struct nfs4_client *clp = cb->cb_clp;
@@ -1010,10 +1032,16 @@ void nfsd4_do_callback_rpc(struct work_struct *w)
 		nfsd4_release_cb(cb);
 		return;
 	}
+	cb->cb_msg.rpc_cred = clp->cl_cb_cred;
 	rpc_call_async(clnt, &cb->cb_msg, RPC_TASK_SOFT | RPC_TASK_SOFTCONN,
 			cb->cb_ops, cb);
 }
 
+void nfsd4_init_callback(struct nfsd4_callback *cb)
+{
+	INIT_WORK(&cb->cb_work, nfsd4_do_callback_rpc);
+}
+
 void nfsd4_cb_recall(struct nfs4_delegation *dp)
 {
 	struct nfsd4_callback *cb = &dp->dl_recall;
@@ -1025,7 +1053,6 @@ void nfsd4_cb_recall(struct nfs4_delegation *dp)
 	cb->cb_msg.rpc_proc = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_RECALL];
 	cb->cb_msg.rpc_argp = cb;
 	cb->cb_msg.rpc_resp = cb;
-	cb->cb_msg.rpc_cred = callback_cred;
 
 	cb->cb_ops = &nfsd4_cb_recall_ops;
 
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 6c9a4b291dba..9d1c5dba2bbb 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -40,6 +40,7 @@
 #include "xdr4.h"
 #include "vfs.h"
 #include "current_stateid.h"
+#include "netns.h"
 
 #define NFSDDBG_FACILITY		NFSDDBG_PROC
 
@@ -194,6 +195,7 @@ static __be32
 do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_open *open)
 {
 	struct svc_fh *resfh;
+	int accmode;
 	__be32 status;
 
 	resfh = kmalloc(sizeof(struct svc_fh), GFP_KERNEL);
@@ -253,9 +255,10 @@ do_open_lookup(struct svc_rqst *rqstp, struct svc_fh *current_fh, struct nfsd4_o
 	/* set reply cache */
 	fh_copy_shallow(&open->op_openowner->oo_owner.so_replay.rp_openfh,
 			&resfh->fh_handle);
-	if (!open->op_created)
-		status = do_open_permission(rqstp, resfh, open,
-					    NFSD_MAY_NOP);
+	accmode = NFSD_MAY_NOP;
+	if (open->op_created)
+		accmode |= NFSD_MAY_OWNER_OVERRIDE;
+	status = do_open_permission(rqstp, resfh, open, accmode);
 	set_change_info(&open->op_cinfo, current_fh);
 	fh_dup2(current_fh, resfh);
 out:
@@ -304,6 +307,8 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	__be32 status;
 	struct nfsd4_compoundres *resp;
+	struct net *net = SVC_NET(rqstp);
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
 	dprintk("NFSD: nfsd4_open filename %.*s op_openowner %p\n",
 		(int)open->op_fname.len, open->op_fname.data,
@@ -331,7 +336,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	/* check seqid for replay. set nfs4_owner */
 	resp = rqstp->rq_resp;
-	status = nfsd4_process_open1(&resp->cstate, open);
+	status = nfsd4_process_open1(&resp->cstate, open, nn);
 	if (status == nfserr_replay_me) {
 		struct nfs4_replay *rp = &open->op_openowner->oo_owner.so_replay;
 		fh_put(&cstate->current_fh);
@@ -354,10 +359,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	/* Openowner is now set, so sequence id will get bumped.  Now we need
 	 * these checks before we do any creates: */
 	status = nfserr_grace;
-	if (locks_in_grace(SVC_NET(rqstp)) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
+	if (locks_in_grace(net) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
 		goto out;
 	status = nfserr_no_grace;
-	if (!locks_in_grace(SVC_NET(rqstp)) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
+	if (!locks_in_grace(net) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
 		goto out;
 
 	switch (open->op_claim_type) {
@@ -370,7 +375,9 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			break;
 		case NFS4_OPEN_CLAIM_PREVIOUS:
 			open->op_openowner->oo_flags |= NFS4_OO_CONFIRMED;
-			status = nfs4_check_open_reclaim(&open->op_clientid, cstate->minorversion);
+			status = nfs4_check_open_reclaim(&open->op_clientid,
+							 cstate->minorversion,
+							 nn);
 			if (status)
 				goto out;
 		case NFS4_OPEN_CLAIM_FH:
@@ -490,12 +497,13 @@ nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 			   &access->ac_supported);
 }
 
-static void gen_boot_verifier(nfs4_verifier *verifier)
+static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net)
 {
 	__be32 verf[2];
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
-	verf[0] = (__be32)nfssvc_boot.tv_sec;
-	verf[1] = (__be32)nfssvc_boot.tv_usec;
+	verf[0] = (__be32)nn->nfssvc_boot.tv_sec;
+	verf[1] = (__be32)nn->nfssvc_boot.tv_usec;
 	memcpy(verifier->data, verf, sizeof(verifier->data));
 }
 
@@ -503,7 +511,7 @@ static __be32
 nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	     struct nfsd4_commit *commit)
 {
-	gen_boot_verifier(&commit->co_verf);
+	gen_boot_verifier(&commit->co_verf, SVC_NET(rqstp));
 	return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
 			     commit->co_count);
 }
@@ -684,6 +692,17 @@ nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if (read->rd_offset >= OFFSET_MAX)
 		return nfserr_inval;
 
+	/*
+	 * If we do a zero copy read, then a client will see read data
+	 * that reflects the state of the file *after* performing the
+	 * following compound.
+	 *
+	 * To ensure proper ordering, we therefore turn off zero copy if
+	 * the client wants us to do more in this compound:
+	 */
+	if (!nfsd4_last_compound_op(rqstp))
+		rqstp->rq_splice_ok = false;
+
 	nfs4_lock_state();
 	/* check stateid */
 	if ((status = nfs4_preprocess_stateid_op(SVC_NET(rqstp),
@@ -876,6 +895,24 @@ out:
 	return status;
 }
 
+static int fill_in_write_vector(struct kvec *vec, struct nfsd4_write *write)
+{
+        int i = 1;
+        int buflen = write->wr_buflen;
+
+        vec[0].iov_base = write->wr_head.iov_base;
+        vec[0].iov_len = min_t(int, buflen, write->wr_head.iov_len);
+        buflen -= vec[0].iov_len;
+
+        while (buflen) {
+                vec[i].iov_base = page_address(write->wr_pagelist[i - 1]);
+                vec[i].iov_len = min_t(int, PAGE_SIZE, buflen);
+                buflen -= vec[i].iov_len;
+                i++;
+        }
+        return i;
+}
+
 static __be32
 nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	    struct nfsd4_write *write)
@@ -884,6 +921,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	struct file *filp = NULL;
 	__be32 status = nfs_ok;
 	unsigned long cnt;
+	int nvecs;
 
 	/* no need to check permission - this will be done in nfsd_write() */
 
@@ -904,10 +942,13 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	cnt = write->wr_buflen;
 	write->wr_how_written = write->wr_stable_how;
-	gen_boot_verifier(&write->wr_verifier);
+	gen_boot_verifier(&write->wr_verifier, SVC_NET(rqstp));
+
+	nvecs = fill_in_write_vector(rqstp->rq_vec, write);
+	WARN_ON_ONCE(nvecs > ARRAY_SIZE(rqstp->rq_vec));
 
 	status =  nfsd_write(rqstp, &cstate->current_fh, filp,
-			     write->wr_offset, rqstp->rq_vec, write->wr_vlen,
+			     write->wr_offset, rqstp->rq_vec, nvecs,
 			     &cnt, &write->wr_how_written);
 	if (filp)
 		fput(filp);
@@ -1666,6 +1707,12 @@ static struct nfsd4_operation nfsd4_ops[] = {
 		.op_name = "OP_EXCHANGE_ID",
 		.op_rsize_bop = (nfsd4op_rsize)nfsd4_exchange_id_rsize,
 	},
+	[OP_BACKCHANNEL_CTL] = {