Merge branch 'bugfixes' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6

* 'bugfixes' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6:
  NFS: Fix an Oops in the NFSv4 atomic open code
  NFS: Fix the selection of security flavours in Kconfig
  NFS: fix the return value of nfs_file_fsync()
  rpcrdma: Fix SQ size calculation when memreg is FRMR
  xprtrdma: Do not truncate iova_start values in frmr registrations.
  nfs: Remove redundant NULL check upon kfree()
  nfs: Add "lookupcache" to displayed mount options
  NFS: allow close-to-open cache semantics to apply to root of NFS filesystem
  SUNRPC: fix NFS client over TCP hangs due to packet loss (Bug 16494)

10 files changed, 68 insertions, 24 deletions

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 26a510a..6c2aad4 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -63,7 +63,6 @@ config NFS_V3_ACL
 config NFS_V4
 	bool "NFS client support for NFS version 4"
 	depends on NFS_FS
-	select RPCSEC_GSS_KRB5
 	help
 	  This option enables support for version 4 of the NFS protocol
 	  (RFC 3530) in the kernel's NFS client.
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index 29539ce..e257172 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -140,6 +140,13 @@ nfs_opendir(struct inode *inode, struct file *filp)
 
 	/* Call generic open code in order to cache credentials */
 	res = nfs_open(inode, filp);
+	if (filp->f_path.dentry == filp->f_path.mnt->mnt_root) {
+		/* This is a mountpoint, so d_revalidate will never
+		 * have been called, so we need to refresh the
+		 * inode (for close-open consistency) ourselves.
+		 */
+		__nfs_revalidate_inode(NFS_SERVER(inode), inode);
+	}
 	return res;
 }
 
@@ -1103,7 +1110,7 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
 	if ((openflags & (O_CREAT|O_EXCL)) == (O_CREAT|O_EXCL))
 		goto no_open_dput;
 	/* We can't create new files, or truncate existing ones here */
-	openflags &= ~(O_CREAT|O_TRUNC);
+	openflags &= ~(O_CREAT|O_EXCL|O_TRUNC);
 
 	/*
 	 * Note: we're not holding inode->i_mutex and so may be racing with
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 2d141a7..eb51bd6 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -323,7 +323,7 @@ nfs_file_fsync(struct file *file, int datasync)
 	have_error |= test_bit(NFS_CONTEXT_ERROR_WRITE, &ctx->flags);
 	if (have_error)
 		ret = xchg(&ctx->error, 0);
-	if (!ret)
+	if (!ret && status < 0)
 		ret = status;
 	return ret;
 }
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 7ffbb98..089da5b 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2036,7 +2036,8 @@ nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 	struct rpc_cred *cred;
 	struct nfs4_state *state;
 	struct dentry *res;
-	fmode_t fmode = nd->intent.open.flags & (FMODE_READ | FMODE_WRITE | FMODE_EXEC);
+	int open_flags = nd->intent.open.flags;
+	fmode_t fmode = open_flags & (FMODE_READ | FMODE_WRITE | FMODE_EXEC);
 
 	if (nd->flags & LOOKUP_CREATE) {
 		attr.ia_mode = nd->intent.open.create_mode;
@@ -2044,8 +2045,9 @@ nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 		if (!IS_POSIXACL(dir))
 			attr.ia_mode &= ~current_umask();
 	} else {
+		open_flags &= ~O_EXCL;
 		attr.ia_valid = 0;
-		BUG_ON(nd->intent.open.flags & O_CREAT);
+		BUG_ON(open_flags & O_CREAT);
 	}
 
 	cred = rpc_lookup_cred();
@@ -2054,7 +2056,7 @@ nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 	parent = dentry->d_parent;
 	/* Protect against concurrent sillydeletes */
 	nfs_block_sillyrename(parent);
-	state = nfs4_do_open(dir, &path, fmode, nd->intent.open.flags, &attr, cred);
+	state = nfs4_do_open(dir, &path, fmode, open_flags, &attr, cred);
 	put_rpccred(cred);
 	if (IS_ERR(state)) {
 		if (PTR_ERR(state) == -ENOENT) {
@@ -2273,8 +2275,7 @@ static int nfs4_get_referral(struct inode *dir, const struct qstr *name, struct
 out:
 	if (page)
 		__free_page(page);
-	if (locations)
-		kfree(locations);
+	kfree(locations);
 	return status;
 }
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index ee26316..ec3966e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -655,6 +655,13 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 
 	if (nfss->options & NFS_OPTION_FSCACHE)
 		seq_printf(m, ",fsc");
+
+	if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONEG) {
+		if (nfss->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
+			seq_printf(m, ",lookupcache=none");
+		else
+			seq_printf(m, ",lookupcache=pos");
+	}
 }
 
 /*
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 503b9da..95932f5 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -69,7 +69,6 @@ config NFSD_V4
 	depends on NFSD && PROC_FS && EXPERIMENTAL
 	select NFSD_V3
 	select FS_POSIX_ACL
-	select RPCSEC_GSS_KRB5
 	help
 	  This option enables support in your system's NFS server for
 	  version 4 of the NFS protocol (RFC 3530).
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index 443c161..3376d76 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -18,10 +18,11 @@ config SUNRPC_XPRT_RDMA
 	  If unsure, say N.
 
 config RPCSEC_GSS_KRB5
-	tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)"
-	depends on SUNRPC && EXPERIMENTAL
+	tristate
+	depends on SUNRPC && CRYPTO
+	prompt "Secure RPC: Kerberos V mechanism" if !(NFS_V4 || NFSD_V4)
+	default y
 	select SUNRPC_GSS
-	select CRYPTO
 	select CRYPTO_MD5
 	select CRYPTO_DES
 	select CRYPTO_CBC
@@ -34,7 +35,7 @@ config RPCSEC_GSS_KRB5
 	  available from http://linux-nfs.org/.  In addition, user-space
 	  Kerberos support should be installed.
 
-	  If unsure, say N.
+	  If unsure, say Y.
 
 config RPCSEC_GSS_SPKM3
 	tristate "Secure RPC: SPKM3 mechanism (EXPERIMENTAL)"
diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c
index e5e28d1..2ac3f6e 100644
--- a/net/sunrpc/xprtrdma/rpc_rdma.c
+++ b/net/sunrpc/xprtrdma/rpc_rdma.c
@@ -249,6 +249,8 @@ rpcrdma_create_chunks(struct rpc_rqst *rqst, struct xdr_buf *target,
 	req->rl_nchunks = nchunks;
 
 	BUG_ON(nchunks == 0);
+	BUG_ON((r_xprt->rx_ia.ri_memreg_strategy == RPCRDMA_FRMR)
+	       && (nchunks > 3));
 
 	/*
 	 * finish off header. If write, marshal discrim and nchunks.
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index 27015c6..5f4c7b3 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -650,10 +650,22 @@ rpcrdma_ep_create(struct rpcrdma_ep *ep, struct rpcrdma_ia *ia,
 	ep->rep_attr.cap.max_send_wr = cdata->max_requests;
 	switch (ia->ri_memreg_strategy) {
 	case RPCRDMA_FRMR:
-		/* Add room for frmr register and invalidate WRs */
-		ep->rep_attr.cap.max_send_wr *= 3;
-		if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr)
-			return -EINVAL;
+		/* Add room for frmr register and invalidate WRs.
+		 * 1. FRMR reg WR for head
+		 * 2. FRMR invalidate WR for head
+		 * 3. FRMR reg WR for pagelist
+		 * 4. FRMR invalidate WR for pagelist
+		 * 5. FRMR reg WR for tail
+		 * 6. FRMR invalidate WR for tail
+		 * 7. The RDMA_SEND WR
+		 */
+		ep->rep_attr.cap.max_send_wr *= 7;
+		if (ep->rep_attr.cap.max_send_wr > devattr.max_qp_wr) {
+			cdata->max_requests = devattr.max_qp_wr / 7;
+			if (!cdata->max_requests)
+				return -EINVAL;
+			ep->rep_attr.cap.max_send_wr = cdata->max_requests * 7;
+		}
 		break;
 	case RPCRDMA_MEMWINDOWS_ASYNC:
 	case RPCRDMA_MEMWINDOWS:
@@ -1490,7 +1502,7 @@ rpcrdma_register_frmr_external(struct rpcrdma_mr_seg *seg,
 	memset(&frmr_wr, 0, sizeof frmr_wr);
 	frmr_wr.opcode = IB_WR_FAST_REG_MR;
 	frmr_wr.send_flags = 0;			/* unsignaled */
-	frmr_wr.wr.fast_reg.iova_start = (unsigned long)seg1->mr_dma;
+	frmr_wr.wr.fast_reg.iova_start = seg1->mr_dma;
 	frmr_wr.wr.fast_reg.page_list = seg1->mr_chunk.rl_mw->r.frmr.fr_pgl;
 	frmr_wr.wr.fast_reg.page_list_len = i;
 	frmr_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c
index 49a62f0..b6309db 100644
--- a/net/sunrpc/xprtsock.c
+++ b/net/sunrpc/xprtsock.c
@@ -1305,10 +1305,11 @@ static void xs_tcp_state_change(struct sock *sk)
 	if (!(xprt = xprt_from_sock(sk)))
 		goto out;
 	dprintk("RPC:       xs_tcp_state_change client %p...\n", xprt);
-	dprintk("RPC:       state %x conn %d dead %d zapped %d\n",
+	dprintk("RPC:       state %x conn %d dead %d zapped %d sk_shutdown %d\n",
 			sk->sk_state, xprt_connected(xprt),
 			sock_flag(sk, SOCK_DEAD),
-			sock_flag(sk, SOCK_ZAPPED));
+			sock_flag(sk, SOCK_ZAPPED),
+			sk->sk_shutdown);
 
 	switch (sk->sk_state) {
 	case TCP_ESTABLISHED:
@@ -1779,10 +1780,25 @@ static void xs_tcp_reuse_connection(struct rpc_xprt *xprt, struct sock_xprt *tra
 {
 	unsigned int state = transport->inet->sk_state;
 
-	if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED)
-		return;
-	if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT))
-		return;
+	if (state == TCP_CLOSE && transport->sock->state == SS_UNCONNECTED) {
+		/* we don't need to abort the connection if the socket
+		 * hasn't undergone a shutdown
+		 */
+		if (transport->inet->sk_shutdown == 0)
+			return;
+		dprintk("RPC:       %s: TCP_CLOSEd and sk_shutdown set to %d\n",
+				__func__, transport->inet->sk_shutdown);
+	}
+	if ((1 << state) & (TCPF_ESTABLISHED|TCPF_SYN_SENT)) {
+		/* we don't need to abort the connection if the socket
+		 * hasn't undergone a shutdown
+		 */
+		if (transport->inet->sk_shutdown == 0)
+			return;
+		dprintk("RPC:       %s: ESTABLISHED/SYN_SENT "
+				"sk_shutdown set to %d\n",
+				__func__, transport->inet->sk_shutdown);
+	}
 	xs_abort_connection(xprt, transport);
 }