Merge branch 'nfs-for-2.6.32'

14 files changed, 1780 insertions, 800 deletions

diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile
index db73fd2a3f0e..9d2fca5ad14a 100644
--- a/net/sunrpc/Makefile
+++ b/net/sunrpc/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/
 sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \
 	    auth.o auth_null.o auth_unix.o auth_generic.o \
 	    svc.o svcsock.o svcauth.o svcauth_unix.o \
-	    rpcb_clnt.o timer.o xdr.o \
+	    addr.o rpcb_clnt.o timer.o xdr.o \
 	    sunrpc_syms.o cache.o rpc_pipe.o \
 	    svc_xprt.o
 sunrpc-$(CONFIG_NFS_V4_1) += backchannel_rqst.o bc_svc.o
diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c
new file mode 100644
index 000000000000..22e8fd89477f
--- /dev/null
+++ b/net/sunrpc/addr.c
@@ -0,0 +1,364 @@
+/*
+ * Copyright 2009, Oracle.  All rights reserved.
+ *
+ * Convert socket addresses to presentation addresses and universal
+ * addresses, and vice versa.
+ *
+ * Universal addresses are introduced by RFC 1833 and further refined by
+ * recent RFCs describing NFSv4.  The universal address format is part
+ * of the external (network) interface provided by rpcbind version 3
+ * and 4, and by NFSv4.  Such an address is a string containing a
+ * presentation format IP address followed by a port number in
+ * "hibyte.lobyte" format.
+ *
+ * IPv6 addresses can also include a scope ID, typically denoted by
+ * a '%' followed by a device name or a non-negative integer.  Refer to
+ * RFC 4291, Section 2.2 for details on IPv6 presentation formats.
+ */
+
+#include <net/ipv6.h>
+#include <linux/sunrpc/clnt.h>
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+
+static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap,
+				  char *buf, const int buflen)
+{
+	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	const struct in6_addr *addr = &sin6->sin6_addr;
+
+	/*
+	 * RFC 4291, Section 2.2.2
+	 *
+	 * Shorthanded ANY address
+	 */
+	if (ipv6_addr_any(addr))
+		return snprintf(buf, buflen, "::");
+
+	/*
+	 * RFC 4291, Section 2.2.2
+	 *
+	 * Shorthanded loopback address
+	 */
+	if (ipv6_addr_loopback(addr))
+		return snprintf(buf, buflen, "::1");
+
+	/*
+	 * RFC 4291, Section 2.2.3
+	 *
+	 * Special presentation address format for mapped v4
+	 * addresses.
+	 */
+	if (ipv6_addr_v4mapped(addr))
+		return snprintf(buf, buflen, "::ffff:%pI4",
+					&addr->s6_addr32[3]);
+
+	/*
+	 * RFC 4291, Section 2.2.1
+	 *
+	 * To keep the result as short as possible, especially
+	 * since we don't shorthand, we don't want leading zeros
+	 * in each halfword, so avoid %pI6.
+	 */
+	return snprintf(buf, buflen, "%x:%x:%x:%x:%x:%x:%x:%x",
+		ntohs(addr->s6_addr16[0]), ntohs(addr->s6_addr16[1]),
+		ntohs(addr->s6_addr16[2]), ntohs(addr->s6_addr16[3]),
+		ntohs(addr->s6_addr16[4]), ntohs(addr->s6_addr16[5]),
+		ntohs(addr->s6_addr16[6]), ntohs(addr->s6_addr16[7]));
+}
+
+static size_t rpc_ntop6(const struct sockaddr *sap,
+			char *buf, const size_t buflen)
+{
+	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	char scopebuf[IPV6_SCOPE_ID_LEN];
+	size_t len;
+	int rc;
+
+	len = rpc_ntop6_noscopeid(sap, buf, buflen);
+	if (unlikely(len == 0))
+		return len;
+
+	if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+	    !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL))
+		return len;
+
+	rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u",
+			IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id);
+	if (unlikely((size_t)rc > sizeof(scopebuf)))
+		return 0;
+
+	len += rc;
+	if (unlikely(len > buflen))
+		return 0;
+
+	strcat(buf, scopebuf);
+	return len;
+}
+
+#else	/* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */
+
+static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap,
+				  char *buf, const int buflen)
+{
+	return 0;
+}
+
+static size_t rpc_ntop6(const struct sockaddr *sap,
+			char *buf, const size_t buflen)
+{
+	return 0;
+}
+
+#endif	/* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */
+
+static int rpc_ntop4(const struct sockaddr *sap,
+		     char *buf, const size_t buflen)
+{
+	const struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+
+	return snprintf(buf, buflen, "%pI4", &sin->sin_addr);
+}
+
+/**
+ * rpc_ntop - construct a presentation address in @buf
+ * @sap: socket address
+ * @buf: construction area
+ * @buflen: size of @buf, in bytes
+ *
+ * Plants a %NUL-terminated string in @buf and returns the length
+ * of the string, excluding the %NUL.  Otherwise zero is returned.
+ */
+size_t rpc_ntop(const struct sockaddr *sap, char *buf, const size_t buflen)
+{
+	switch (sap->sa_family) {
+	case AF_INET:
+		return rpc_ntop4(sap, buf, buflen);
+	case AF_INET6:
+		return rpc_ntop6(sap, buf, buflen);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rpc_ntop);
+
+static size_t rpc_pton4(const char *buf, const size_t buflen,
+			struct sockaddr *sap, const size_t salen)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+	u8 *addr = (u8 *)&sin->sin_addr.s_addr;
+
+	if (buflen > INET_ADDRSTRLEN || salen < sizeof(struct sockaddr_in))
+		return 0;
+
+	memset(sap, 0, sizeof(struct sockaddr_in));
+
+	if (in4_pton(buf, buflen, addr, '\0', NULL) == 0)
+		return 0;
+
+	sin->sin_family = AF_INET;
+	return sizeof(struct sockaddr_in);;
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static int rpc_parse_scope_id(const char *buf, const size_t buflen,
+			      const char *delim, struct sockaddr_in6 *sin6)
+{
+	char *p;
+	size_t len;
+
+	if ((buf + buflen) == delim)
+		return 1;
+
+	if (*delim != IPV6_SCOPE_DELIMITER)
+		return 0;
+
+	if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+	    !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL))
+		return 0;
+
+	len = (buf + buflen) - delim - 1;
+	p = kstrndup(delim + 1, len, GFP_KERNEL);
+	if (p) {
+		unsigned long scope_id = 0;
+		struct net_device *dev;
+
+		dev = dev_get_by_name(&init_net, p);
+		if (dev != NULL) {
+			scope_id = dev->ifindex;
+			dev_put(dev);
+		} else {
+			if (strict_strtoul(p, 10, &scope_id) == 0) {
+				kfree(p);
+				return 0;
+			}
+		}
+
+		kfree(p);
+
+		sin6->sin6_scope_id = scope_id;
+		return 1;
+	}
+
+	return 0;
+}
+
+static size_t rpc_pton6(const char *buf, const size_t buflen,
+			struct sockaddr *sap, const size_t salen)
+{
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	u8 *addr = (u8 *)&sin6->sin6_addr.in6_u;
+	const char *delim;
+
+	if (buflen > (INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN) ||
+	    salen < sizeof(struct sockaddr_in6))
+		return 0;
+
+	memset(sap, 0, sizeof(struct sockaddr_in6));
+
+	if (in6_pton(buf, buflen, addr, IPV6_SCOPE_DELIMITER, &delim) == 0)
+		return 0;
+
+	if (!rpc_parse_scope_id(buf, buflen, delim, sin6))
+		return 0;
+
+	sin6->sin6_family = AF_INET6;
+	return sizeof(struct sockaddr_in6);
+}
+#else
+static size_t rpc_pton6(const char *buf, const size_t buflen,
+			struct sockaddr *sap, const size_t salen)
+{
+	return 0;
+}
+#endif
+
+/**
+ * rpc_pton - Construct a sockaddr in @sap
+ * @buf: C string containing presentation format IP address
+ * @buflen: length of presentation address in bytes
+ * @sap: buffer into which to plant socket address
+ * @salen: size of buffer in bytes
+ *
+ * Returns the size of the socket address if successful; otherwise
+ * zero is returned.
+ *
+ * Plants a socket address in @sap and returns the size of the
+ * socket address, if successful.  Returns zero if an error
+ * occurred.
+ */
+size_t rpc_pton(const char *buf, const size_t buflen,
+		struct sockaddr *sap, const size_t salen)
+{
+	unsigned int i;
+
+	for (i = 0; i < buflen; i++)
+		if (buf[i] == ':')
+			return rpc_pton6(buf, buflen, sap, salen);
+	return rpc_pton4(buf, buflen, sap, salen);
+}
+EXPORT_SYMBOL_GPL(rpc_pton);
+
+/**
+ * rpc_sockaddr2uaddr - Construct a universal address string from @sap.
+ * @sap: socket address
+ *
+ * Returns a %NUL-terminated string in dynamically allocated memory;
+ * otherwise NULL is returned if an error occurred.  Caller must
+ * free the returned string.
+ */
+char *rpc_sockaddr2uaddr(const struct sockaddr *sap)
+{
+	char portbuf[RPCBIND_MAXUADDRPLEN];
+	char addrbuf[RPCBIND_MAXUADDRLEN];
+	unsigned short port;
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		if (rpc_ntop4(sap, addrbuf, sizeof(addrbuf)) == 0)
+			return NULL;
+		port = ntohs(((struct sockaddr_in *)sap)->sin_port);
+		break;
+	case AF_INET6:
+		if (rpc_ntop6_noscopeid(sap, addrbuf, sizeof(addrbuf)) == 0)
+			return NULL;
+		port = ntohs(((struct sockaddr_in6 *)sap)->sin6_port);
+		break;
+	default:
+		return NULL;
+	}
+
+	if (snprintf(portbuf, sizeof(portbuf),
+		     ".%u.%u", port >> 8, port & 0xff) > (int)sizeof(portbuf))
+		return NULL;
+
+	if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf))
+		return NULL;
+
+	return kstrdup(addrbuf, GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(rpc_sockaddr2uaddr);
+
+/**
+ * rpc_uaddr2sockaddr - convert a universal address to a socket address.
+ * @uaddr: C string containing universal address to convert
+ * @uaddr_len: length of universal address string
+ * @sap: buffer into which to plant socket address
+ * @salen: size of buffer
+ *
+ * Returns the size of the socket address if successful; otherwise
+ * zero is returned.
+ */
+size_t rpc_uaddr2sockaddr(const char *uaddr, const size_t uaddr_len,
+			  struct sockaddr *sap, const size_t salen)
+{
+	char *c, buf[RPCBIND_MAXUADDRLEN];
+	unsigned long portlo, porthi;
+	unsigned short port;
+
+	if (uaddr_len > sizeof(buf))
+		return 0;
+
+	memcpy(buf, uaddr, uaddr_len);
+
+	buf[uaddr_len] = '\n';
+	buf[uaddr_len + 1] = '\0';
+
+	c = strrchr(buf, '.');
+	if (unlikely(c == NULL))
+		return 0;
+	if (unlikely(strict_strtoul(c + 1, 10, &portlo) != 0))
+		return 0;
+	if (unlikely(portlo > 255))
+		return 0;
+
+	c[0] = '\n';
+	c[1] = '\0';
+
+	c = strrchr(buf, '.');
+	if (unlikely(c == NULL))
+		return 0;
+	if (unlikely(strict_strtoul(c + 1, 10, &porthi) != 0))
+		return 0;
+	if (unlikely(porthi > 255))
+		return 0;
+
+	port = (unsigned short)((porthi << 8) | portlo);
+
+	c[0] = '\0';
+
+	if (rpc_pton(buf, strlen(buf), sap, salen) == 0)
+		return 0;
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		((struct sockaddr_in *)sap)->sin_port = htons(port);
+		return sizeof(struct sockaddr_in);
+	case AF_INET6:
+		((struct sockaddr_in6 *)sap)->sin6_port = htons(port);
+		return sizeof(struct sockaddr_in6);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rpc_uaddr2sockaddr);
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 66d458fc6920..fc6a43ccd950 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -89,8 +89,8 @@ static struct rpc_wait_queue pipe_version_rpc_waitqueue;
 static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue);
 
 static void gss_free_ctx(struct gss_cl_ctx *);
-static struct rpc_pipe_ops gss_upcall_ops_v0;
-static struct rpc_pipe_ops gss_upcall_ops_v1;
+static const struct rpc_pipe_ops gss_upcall_ops_v0;
+static const struct rpc_pipe_ops gss_upcall_ops_v1;
 
 static inline struct gss_cl_ctx *
 gss_get_ctx(struct gss_cl_ctx *ctx)
@@ -777,7 +777,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
 	 * that we supported only the old pipe.  So we instead create
 	 * the new pipe first.
 	 */
-	gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_dentry,
+	gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_path.dentry,
 					 "gssd",
 					 clnt, &gss_upcall_ops_v1,
 					 RPC_PIPE_WAIT_FOR_OPEN);
@@ -786,7 +786,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
 		goto err_put_mech;
 	}
 
-	gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_dentry,
+	gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_path.dentry,
 					 gss_auth->mech->gm_name,
 					 clnt, &gss_upcall_ops_v0,
 					 RPC_PIPE_WAIT_FOR_OPEN);
@@ -1507,7 +1507,7 @@ static const struct rpc_credops gss_nullops = {
 	.crunwrap_resp	= gss_unwrap_resp,
 };
 
-static struct rpc_pipe_ops gss_upcall_ops_v0 = {
+static const struct rpc_pipe_ops gss_upcall_ops_v0 = {
 	.upcall		= gss_pipe_upcall,
 	.downcall	= gss_pipe_downcall,
 	.destroy_msg	= gss_pipe_destroy_msg,
@@ -1515,7 +1515,7 @@ static struct rpc_pipe_ops gss_upcall_ops_v0 = {
 	.release_pipe	= gss_pipe_release,
 };
 
-static struct rpc_pipe_ops gss_upcall_ops_v1 = {
+static const struct rpc_pipe_ops gss_upcall_ops_v1 = {
 	.upcall		= gss_pipe_upcall,
 	.downcall	= gss_pipe_downcall,
 	.destroy_msg	= gss_pipe_destroy_msg,
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 2278a50c6444..2e6a148d277c 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -181,6 +181,11 @@ static void rsi_request(struct cache_detail *cd,
 	(*bpp)[-1] = '\n';
 }
 
+static int rsi_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall(cd, h, rsi_request);
+}
+
 
 static int rsi_parse(struct cache_detail *cd,
 		    char *mesg, int mlen)
@@ -270,7 +275,7 @@ static struct cache_detail rsi_cache = {
 	.hash_table     = rsi_table,
 	.name           = "auth.rpcsec.init",
 	.cache_put      = rsi_put,
-	.cache_request  = rsi_request,
+	.cache_upcall   = rsi_upcall,
 	.cache_parse    = rsi_parse,
 	.match		= rsi_match,
 	.init		= rsi_init,
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index ff0c23053d2f..45cdaff9b361 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -27,10 +27,12 @@
 #include <linux/net.h>
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
+#include <linux/pagemap.h>
 #include <asm/ioctls.h>
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/stats.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
 
 #define	 RPCDBG_FACILITY RPCDBG_CACHE
 
@@ -175,7 +177,13 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 }
 EXPORT_SYMBOL_GPL(sunrpc_cache_update);
 
-static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h);
+static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	if (!cd->cache_upcall)
+		return -EINVAL;
+	return cd->cache_upcall(cd, h);
+}
+
 /*
  * This is the generic cache management routine for all
  * the authentication caches.
@@ -284,76 +292,11 @@ static DEFINE_SPINLOCK(cache_list_lock);
 static struct cache_detail *current_detail;
 static int current_index;
 
-static const struct file_operations cache_file_operations;
-static const struct file_operations content_file_operations;
-static const struct file_operations cache_flush_operations;
-
 static void do_cache_clean(struct work_struct *work);
 static DECLARE_DELAYED_WORK(cache_cleaner, do_cache_clean);
 
-static void remove_cache_proc_entries(struct cache_detail *cd)
-{
-	if (cd->proc_ent == NULL)
-		return;
-	if (cd->flush_ent)
-		remove_proc_entry("flush", cd->proc_ent);
-	if (cd->channel_ent)
-		remove_proc_entry("channel", cd->proc_ent);
-	if (cd->content_ent)
-		remove_proc_entry("content", cd->proc_ent);
-	cd->proc_ent = NULL;
-	remove_proc_entry(cd->name, proc_net_rpc);
-}
-
-#ifdef CONFIG_PROC_FS
-static int create_cache_proc_entries(struct cache_detail *cd)
-{
-	struct proc_dir_entry *p;
-
-	cd->proc_ent = proc_mkdir(cd->name, proc_net_rpc);
-	if (cd->proc_ent == NULL)
-		goto out_nomem;
-	cd->channel_ent = cd->content_ent = NULL;
-
-	p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR,
-			     cd->proc_ent, &cache_flush_operations, cd);
-	cd->flush_ent = p;
-	if (p == NULL)
-		goto out_nomem;
-
-	if (cd->cache_request || cd->cache_parse) {
-		p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR,
-				     cd->proc_ent, &cache_file_operations, cd);
-		cd->channel_ent = p;
-		if (p == NULL)
-			goto out_nomem;
-	}
-	if (cd->cache_show) {
-		p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR,
-				cd->proc_ent, &content_file_operations, cd);
-		cd->content_ent = p;
-		if (p == NULL)
-			goto out_nomem;
-	}
-	return 0;
-out_nomem:
-	remove_cache_proc_entries(cd);
-	return -ENOMEM;
-}
-#else /* CONFIG_PROC_FS */
-static int create_cache_proc_entries(struct cache_detail *cd)
-{
-	return 0;
-}
-#endif
-
-int cache_register(struct cache_detail *cd)
+static void sunrpc_init_cache_detail(struct cache_detail *cd)
 {
-	int ret;
-
-	ret = create_cache_proc_entries(cd);
-	if (ret)
-		return ret;
 	rwlock_init(&cd->hash_lock);
 	INIT_LIST_HEAD(&cd->queue);
 	spin_lock(&cache_list_lock);
@@ -367,11 +310,9 @@ int cache_register(struct cache_detail *cd)
 
 	/* start the cleaning process */
 	schedule_delayed_work(&cache_cleaner, 0);
-	return 0;
 }
-EXPORT_SYMBOL_GPL(cache_register);
 
-void cache_unregister(struct cache_detail *cd)
+static void sunrpc_destroy_cache_detail(struct cache_detail *cd)
 {
 	cache_purge(cd);
 	spin_lock(&cache_list_lock);
@@ -386,7 +327,6 @@ void cache_unregister(struct cache_detail *cd)
 	list_del_init(&cd->others);
 	write_unlock(&cd->hash_lock);
 	spin_unlock(&cache_list_lock);
-	remove_cache_proc_entries(cd);
 	if (list_empty(&cache_list)) {
 		/* module must be being unloaded so its safe to kill the worker */
 		cancel_delayed_work_sync(&cache_cleaner);
@@ -395,7 +335,6 @@ void cache_unregister(struct cache_detail *cd)
 out:
 	printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name);
 }
-EXPORT_SYMBOL_GPL(cache_unregister);
 
 /* clean cache tries to find something to clean
  * and cleans it.
@@ -687,18 +626,18 @@ struct cache_reader {
 	int			offset;	/* if non-0, we have a refcnt on next request */
 };
 
-static ssize_t
-cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
+static ssize_t cache_read(struct file *filp, char __user *buf, size_t count,
+			  loff_t *ppos, struct cache_detail *cd)
 {
 	struct cache_reader *rp = filp->private_data;
 	struct cache_request *rq;
-	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
+	struct inode *inode = filp->f_path.dentry->d_inode;
 	int err;
 
 	if (count == 0)
 		return 0;
 
-	mutex_lock(&queue_io_mutex); /* protect against multiple concurrent
+	mutex_lock(&inode->i_mutex); /* protect against multiple concurrent
 			      * readers on this file */
  again:
 	spin_lock(&queue_lock);
@@ -711,7 +650,7 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
 	}
 	if (rp->q.list.next == &cd->queue) {
 		spin_unlock(&queue_lock);
-		mutex_unlock(&queue_io_mutex);
+		mutex_unlock(&inode->i_mutex);
 		BUG_ON(rp->offset);
 		return 0;
 	}
@@ -758,49 +697,90 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
 	}
 	if (err == -EAGAIN)
 		goto again;
-	mutex_unlock(&queue_io_mutex);
+	mutex_unlock(&inode->i_mutex);
 	return err ? err :  count;
 }
 
-static char write_buf[8192]; /* protected by queue_io_mutex */
+static ssize_t cache_do_downcall(char *kaddr, const char __user *buf,
+				 size_t count, struct cache_detail *cd)
+{
+	ssize_t ret;
 
-static ssize_t
-cache_write(struct file *filp, const char __user *buf, size_t count,
-	    loff_t *ppos)
+	if (copy_from_user(kaddr, buf, count))
+		return -EFAULT;
+	kaddr[count] = '\0';
+	ret = cd->cache_parse(cd, kaddr, count);
+	if (!ret)
+		ret = count;
+	return ret;
+}
+
+static ssize_t cache_slow_downcall(const char __user *buf,
+				   size_t count, struct cache_detail *cd)
 {
-	int err;
-	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
+	static char write_buf[8192]; /* protected by queue_io_mutex */
+	ssize_t ret = -EINVAL;
 
-	if (count == 0)
-		return 0;
 	if (count >= sizeof(write_buf))
-		return -EINVAL;
-
+		goto out;
 	mutex_lock(&queue_io_mutex);
+	ret = cache_do_downcall(write_buf, buf, count, cd);
+	mutex_unlock(&queue_io_mutex);
+out:
+	return ret;
+}
 
-	if (copy_from_user(write_buf, buf, count)) {
-		mutex_unlock(&queue_io_mutex);
-		return -EFAULT;
-	}
-	write_buf[count] = '\0';
-	if (cd->cache_parse)
-		err = cd->cache_parse(cd, write_buf, count);
-	else
-		err = -EINVAL;
+static ssize_t cache_downcall(struct address_space *mapping,
+			      const char __user *buf,
+			      size_t count, struct cache_detail *cd)
+{
+	struct page *page;
+	char *kaddr;
+	ssize_t ret = -ENOMEM;
+
+	if (count >= PAGE_CACHE_SIZE)
+		goto out_slow;
+
+	page = find_or_create_page(mapping, 0, GFP_KERNEL);
+	if (!page)
+		goto out_slow;
+
+	kaddr = kmap(page);
+	ret = cache_do_downcall(kaddr, buf, count, cd);
+	kunmap(page);
+	unlock_page(page);
+	page_cache_release(page);
+	return ret;
+out_slow:
+	return cache_slow_downcall(buf, count, cd);
+}
 
-	mutex_unlock(&queue_io_mutex);
-	return err ? err : count;
+static ssize_t cache_write(struct file *filp, const char __user *buf,
+			   size_t count, loff_t *ppos,
+			   struct cache_detail *cd)
+{
+	struct address_space *mapping = filp->f_mapping;
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	ssize_t ret = -EINVAL;
+
+	if (!cd->cache_parse)
+		goto out;
+
+	mutex_lock(&inode->i_mutex);
+	ret = cache_downcall(mapping, buf, count, cd);
+	mutex_unlock(&inode->i_mutex);
+out:
+	return ret;
 }
 
 static DECLARE_WAIT_QUEUE_HEAD(queue_wait);
 
-static unsigned int
-cache_poll(struct file *filp, poll_table *wait)
+static unsigned int cache_poll(struct file *filp, poll_table *wait,
+			       struct cache_detail *cd)
 {
 	unsigned int mask;
 	struct cache_reader *rp = filp->private_data;
 	struct cache_queue *cq;
-	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
 
 	poll_wait(filp, &queue_wait, wait);
 
@@ -822,14 +802,13 @@ cache_poll(struct file *filp, poll_table *wait)
 	return mask;
 }
 
-static int
-cache_ioctl(struct inode *ino, struct file *filp,
-	    unsigned int cmd, unsigned long arg)
+static int cache_ioctl(struct inode *ino, struct file *filp,
+		       unsigned int cmd, unsigned long arg,
+		       struct cache_detail *cd)
 {
 	int len = 0;
 	struct cache_reader *rp = filp->private_data;
 	struct cache_queue *cq;
-	struct cache_detail *cd = PDE(ino)->data;
 
 	if (cmd != FIONREAD || !rp)
 		return -EINVAL;
@@ -852,15 +831,15 @@ cache_ioctl(struct inode *ino, struct file *filp,
 	return put_user(len, (int __user *)arg);
 }
 
-static int
-cache_open(struct inode *inode, struct file *filp)
+static int cache_open(struct inode *inode, struct file *filp,
+		      struct cache_detail *cd)
 {
 	struct cache_reader *rp = NULL;
 
+	if (!cd || !try_module_get(cd->owner))
+		return -EACCES;
 	nonseekable_open(inode, filp);
 	if (filp->f_mode & FMODE_READ) {
-		struct cache_detail *cd = PDE(inode)->data;
-
 		rp = kmalloc(sizeof(*rp), GFP_KERNEL);
 		if (!rp)
 			return -ENOMEM;
@@ -875,11 +854,10 @@ cache_open(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static int
-cache_release(struct inode *inode, struct file *filp)
+static int cache_release(struct inode *inode, struct file *filp,
+			 struct cache_detail *cd)
 {
 	struct cache_reader *rp = filp->private_data;
-	struct cache_detail *cd = PDE(inode)->data;
 
 	if (rp) {
 		spin_lock(&queue_lock);
@@ -903,23 +881,12 @@ cache_release(struct inode *inode, struct file *filp)
 		cd->last_close = get_seconds();
 		atomic_dec(&cd->readers);
 	}
+	module_put(cd->owner);
 	return 0;
 }
 
 
 
-static const struct file_operations cache_file_operations = {
-	.owner		= THIS_MODULE,
-	.llseek		= no_llseek,
-	.read		= cache_read,
-	.write		= cache_write,
-	.poll		= cache_poll,
-	.ioctl		= cache_ioctl, /* for FIONREAD */
-	.open		= cache_open,
-	.release	= cache_release,
-};
-
-
 static void queue_loose(struct cache_detail *detail, struct cache_head *ch)
 {
 	struct cache_queue *cq;
@@ -1020,15 +987,21 @@ static void warn_no_listener(struct cache_detail *detail)
 	if (detail->last_warn != detail->last_close) {
 		detail->last_warn = detail->last_close;
 		if (detail->warn_no_listener)
-			detail->warn_no_listener(detail);
+			detail->warn_no_listener(detail, detail->last_close != 0);
 	}
 }
 
 /*
- * register an upcall request to user-space.
+ * register an upcall request to user-space and queue it up for read() by the
+ * upcall daemon.
+ *
  * Each request is at most one page long.
  */
-static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h)
+int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h,
+		void (*cache_request)(struct cache_detail *,
+				      struct cache_head *,
+				      char **,
+				      int *))
 {
 
 	char *buf;
@@ -1036,9 +1009,6 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h)
 	char *bp;
 	int len;
 
-	if (detail->cache_request == NULL)
-		return -EINVAL;
-
 	if (atomic_read(&detail->readers) == 0 &&
 	    detail->last_close < get_seconds() - 30) {
 			warn_no_listener(detail);
@@ -1057,7 +1027,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h)
 
 	bp = buf; len = PAGE_SIZE;
 
-	detail->cache_request(detail, h, &bp, &len);
+	cache_request(detail, h, &bp, &len);
 
 	if (len < 0) {
 		kfree(buf);
@@ -1075,6 +1045,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h)
 	wake_up(&queue_wait);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(sunrpc_cache_pipe_upcall);
 
 /*
  * parse a message from user-space and pass it
@@ -1242,11 +1213,13 @@ static const struct seq_operations cache_content_op = {
 	.show	= c_show,
 };
 
-static int content_open(struct inode *inode, struct file *file)
+static int content_open(struct inode *inode, struct file *file,
+			struct cache_detail *cd)
 {
 	struct handle *han;
-	struct cache_detail *cd = PDE(inode)->data;
 
+	if (!cd || !try_module_get(cd->owner))
+		return -EACCES;
 	han = __seq_open_private(file, &cache_content_op, sizeof(*han));
 	if (han == NULL)
 		return -ENOMEM;
@@ -1255,17 +1228,33 @@ static int content_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static const struct file_operations content_file_operations = {
-	.open		= content_open,
-	.read		= seq_read,
-	.llseek		= seq_lseek,
-	.release	= seq_release_private,
-};
+static int content_release(struct inode *inode, struct file *file,
+		struct cache_detail *cd)
+{
+	int ret = seq_release_private(inode, file);
+	module_put(cd->owner);
+	return ret;
+}
+
+static int open_flush(struct inode *inode, struct file *file,
+			struct cache_detail *cd)
+{
+	if (!cd || !try_module_get(cd->owner))
+		return -EACCES;
+	return nonseekable_open(inode, file);
+}
+
+static int release_flush(struct inode *inode, struct file *file,
+			struct cache_detail *cd)
+{
+	module_put(cd->owner);
+	return 0;
+}
 
 static ssize_t read_flush(struct file *file, char __user *buf,
-			    size_t count, loff_t *ppos)
+			  size_t count, loff_t *ppos,
+			  struct cache_detail *cd)
 {
-	struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data;
 	char tbuf[20];
 	unsigned long p = *ppos;
 	size_t len;
@@ -1283,10 +1272,10 @@ static ssize_t read_flush(struct file *file, char __user *buf,
 	return len;
 }
 
-static ssize_t write_flush(struct file * file, const char __user * buf,
-			     size_t count, loff_t *ppos)
+static ssize_t write_flush(struct file *file, const char __user *buf,
+			   size_t count, loff_t *ppos,
+			   struct cache_detail *cd)
 {
-	struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data;
 	char tbuf[20];
 	char *ep;
 	long flushtime;
@@ -1307,8 +1296,343 @@ static ssize_t write_flush(struct file * file, const char __user * buf,
 	return count;
 }
 
-static const struct file_operations cache_flush_operations = {
-	.open		= nonseekable_open,
-	.read		= read_flush,
-	.write		= write_flush,
+static ssize_t cache_read_procfs(struct file *filp, char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
+
+	return cache_read(filp, buf, count, ppos, cd);
+}
+
+static ssize_t cache_write_procfs(struct file *filp, const char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
+
+	return cache_write(filp, buf, count, ppos, cd);
+}
+
+static unsigned int cache_poll_procfs(struct file *filp, poll_table *wait)
+{
+	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
+
+	return cache_poll(filp, wait, cd);
+}
+
+static int cache_ioctl_procfs(struct inode *inode, struct file *filp,
+			      unsigned int cmd, unsigned long arg)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return cache_ioctl(inode, filp, cmd, arg, cd);
+}
+
+static int cache_open_procfs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return cache_open(inode, filp, cd);
+}
+
+static int cache_release_procfs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return cache_release(inode, filp, cd);
+}
+
+static const struct file_operations cache_file_operations_procfs = {
+	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
+	.read		= cache_read_procfs,
+	.write		= cache_write_procfs,
+	.poll		= cache_poll_procfs,
+	.ioctl		= cache_ioctl_procfs, /* for FIONREAD */
+	.open		= cache_open_procfs,
+	.release	= cache_release_procfs,
 };
+
+static int content_open_procfs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return content_open(inode, filp, cd);
+}
+
+static int content_release_procfs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return content_release(inode, filp, cd);
+}
+
+static const struct file_operations content_file_operations_procfs = {
+	.open		= content_open_procfs,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= content_release_procfs,
+};
+
+static int open_flush_procfs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return open_flush