6 files changed, 207 insertions, 36 deletions

diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
new file mode 100644
index 000000000000..36fe20d6eba2
--- /dev/null
+++ b/fs/nfs/Kconfig
@@ -0,0 +1,86 @@
+config NFS_FS
+        tristate "NFS client support"
+        depends on INET
+        select LOCKD
+        select SUNRPC
+        select NFS_ACL_SUPPORT if NFS_V3_ACL
+        help
+          Choose Y here if you want to access files residing on other
+          computers using Sun's Network File System protocol.  To compile
+          this file system support as a module, choose M here: the module
+          will be called nfs.
+
+          To mount file systems exported by NFS servers, you also need to
+          install the user space mount.nfs command which can be found in
+          the Linux nfs-utils package, available from http://linux-nfs.org/.
+          Information about using the mount command is available in the
+          mount(8) man page.  More detail about the Linux NFS client
+          implementation is available via the nfs(5) man page.
+
+          Below you can choose which versions of the NFS protocol are
+          available in the kernel to mount NFS servers.  Support for NFS
+          version 2 (RFC 1094) is always available when NFS_FS is selected.
+
+          To configure a system which mounts its root file system via NFS
+          at boot time, say Y here, select "Kernel level IP
+          autoconfiguration" in the NETWORK menu, and select "Root file
+          system on NFS" below.  You cannot compile this file system as a
+          module in this case.
+
+          If unsure, say N.
+
+config NFS_V3
+        bool "NFS client support for NFS version 3"
+        depends on NFS_FS
+        help
+          This option enables support for version 3 of the NFS protocol
+          (RFC 1813) in the kernel's NFS client.
+
+          If unsure, say Y.
+
+config NFS_V3_ACL
+        bool "NFS client support for the NFSv3 ACL protocol extension"
+        depends on NFS_V3
+        help
+          Some NFS servers support an auxiliary NFSv3 ACL protocol that
+          Sun added to Solaris but never became an official part of the
+          NFS version 3 protocol.  This protocol extension allows
+          applications on NFS clients to manipulate POSIX Access Control
+          Lists on files residing on NFS servers.  NFS servers enforce
+          ACLs on local files whether this protocol is available or not.
+
+          Choose Y here if your NFS server supports the Solaris NFSv3 ACL
+          protocol extension and you want your NFS client to allow
+          applications to access and modify ACLs on files on the server.
+
+          Most NFS servers don't support the Solaris NFSv3 ACL protocol
+          extension.  You can choose N here or specify the "noacl" mount
+          option to prevent your NFS client from trying to use the NFSv3
+          ACL protocol.
+
+          If unsure, say N.
+
+config NFS_V4
+        bool "NFS client support for NFS version 4 (EXPERIMENTAL)"
+        depends on NFS_FS && EXPERIMENTAL
+        select RPCSEC_GSS_KRB5
+        help
+          This option enables support for version 4 of the NFS protocol
+          (RFC 3530) in the kernel's NFS client.
+
+          To mount NFS servers using NFSv4, you also need to install user
+          space programs which can be found in the Linux nfs-utils package,
+          available from http://linux-nfs.org/.
+
+          If unsure, say N.
+
+config ROOT_NFS
+        bool "Root file system on NFS"
+        depends on NFS_FS=y && IP_PNP
+        help
+          If you want your system to mount its root file system via NFS,
+          choose Y here.  This is common practice for managing systems
+          without local permanent storage.  For details, read
+          <file:Documentation/filesystems/nfsroot.txt>.
+
+          Most people say N here.
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 9b728f3565a1..574158ae2398 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -255,6 +255,32 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
         }
         return 0;
 }
+
+/*
+ * Test if two ip6 socket addresses refer to the same socket by
+ * comparing relevant fields. The padding bytes specifically, are not
+ * compared. sin6_flowinfo is not compared because it only affects QoS
+ * and sin6_scope_id is only compared if the address is "link local"
+ * because "link local" addresses need only be unique to a specific
+ * link. Conversely, ordinary unicast addresses might have different
+ * sin6_scope_id.
+ *
+ * The caller should ensure both socket addresses are AF_INET6.
+ */
+static int nfs_sockaddr_cmp_ip6(const struct sockaddr *sa1,
+                                const struct sockaddr *sa2)
+{
+        const struct sockaddr_in6 *saddr1 = (const struct sockaddr_in6 *)sa1;
+        const struct sockaddr_in6 *saddr2 = (const struct sockaddr_in6 *)sa2;
+
+        if (!ipv6_addr_equal(&saddr1->sin6_addr,
+                             &saddr1->sin6_addr))
+                return 0;
+        if (ipv6_addr_scope(&saddr1->sin6_addr) == IPV6_ADDR_SCOPE_LINKLOCAL &&
+            saddr1->sin6_scope_id != saddr2->sin6_scope_id)
+                return 0;
+        return saddr1->sin6_port == saddr2->sin6_port;
+}
 #else
 static int nfs_sockaddr_match_ipaddr4(const struct sockaddr_in *sa1,
                                  const struct sockaddr_in *sa2)
@@ -270,9 +296,52 @@ static int nfs_sockaddr_match_ipaddr(const struct sockaddr *sa1,
         return nfs_sockaddr_match_ipaddr4((const struct sockaddr_in *)sa1,
                         (const struct sockaddr_in *)sa2);
 }
+
+static int nfs_sockaddr_cmp_ip6(const struct sockaddr * sa1,
+                                const struct sockaddr * sa2)
+{
+        return 0;
+}
 #endif
 
 /*
+ * Test if two ip4 socket addresses refer to the same socket, by
+ * comparing relevant fields. The padding bytes specifically, are
+ * not compared.
+ *
+ * The caller should ensure both socket addresses are AF_INET.
+ */
+static int nfs_sockaddr_cmp_ip4(const struct sockaddr *sa1,
+                                const struct sockaddr *sa2)
+{
+        const struct sockaddr_in *saddr1 = (const struct sockaddr_in *)sa1;
+        const struct sockaddr_in *saddr2 = (const struct sockaddr_in *)sa2;
+
+        if (saddr1->sin_addr.s_addr != saddr2->sin_addr.s_addr)
+                return 0;
+        return saddr1->sin_port == saddr2->sin_port;
+}
+
+/*
+ * Test if two socket addresses represent the same actual socket,
+ * by comparing (only) relevant fields.
+ */
+static int nfs_sockaddr_cmp(const struct sockaddr *sa1,
+                            const struct sockaddr *sa2)
+{
+        if (sa1->sa_family != sa2->sa_family)
+                return 0;
+
+        switch (sa1->sa_family) {
+        case AF_INET:
+                return nfs_sockaddr_cmp_ip4(sa1, sa2);
+        case AF_INET6:
+                return nfs_sockaddr_cmp_ip6(sa1, sa2);
+        }
+        return 0;
+}
+
+/*
  * Find a client by IP address and protocol version
  * - returns NULL if no such client
  */
@@ -344,8 +413,10 @@ struct nfs_client *nfs_find_client_next(struct nfs_client *clp)
 static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *data)
 {
         struct nfs_client *clp;
+        const struct sockaddr *sap = data->addr;
 
         list_for_each_entry(clp, &nfs_client_list, cl_share_link) {
+                const struct sockaddr *clap = (struct sockaddr *)&clp->cl_addr;
                 /* Don't match clients that failed to initialise properly */
                 if (clp->cl_cons_state < 0)
                         continue;
@@ -358,7 +429,7 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
                         continue;
 
                 /* Match the full socket address */
-                if (memcmp(&clp->cl_addr, data->addr, sizeof(clp->cl_addr)) != 0)
+                if (!nfs_sockaddr_cmp(sap, clap))
                         continue;
 
                 atomic_inc(&clp->cl_count);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index e35c8199f82f..672368f865ca 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1892,8 +1892,14 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
         cache.cred = cred;
         cache.jiffies = jiffies;
         status = NFS_PROTO(inode)->access(inode, &cache);
-        if (status != 0)
+        if (status != 0) {
+                if (status == -ESTALE) {
+                        nfs_zap_caches(inode);
+                        if (!S_ISDIR(inode->i_mode))
+                                set_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
+                }
                 return status;
+        }
         nfs_access_add_cache(inode, &cache);
 out:
         if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) == 0)
diff --git a/fs/nfs/nfs3acl.c b/fs/nfs/nfs3acl.c
index cef62557c87d..6bbf0e6daad2 100644
--- a/fs/nfs/nfs3acl.c
+++ b/fs/nfs/nfs3acl.c
@@ -292,7 +292,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 {
         struct nfs_server *server = NFS_SERVER(inode);
         struct nfs_fattr fattr;
-        struct page *pages[NFSACL_MAXPAGES] = { };
+        struct page *pages[NFSACL_MAXPAGES];
         struct nfs3_setaclargs args = {
                 .inode = inode,
                 .mask = NFS_ACL,
@@ -303,7 +303,7 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
                 .rpc_argp       = &args,
                 .rpc_resp       = &fattr,
         };
-        int status, count;
+        int status;
 
         status = -EOPNOTSUPP;
         if (!nfs_server_capable(inode, NFS_CAP_ACLS))
@@ -319,6 +319,20 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
         if (S_ISDIR(inode->i_mode)) {
                 args.mask |= NFS_DFACL;
                 args.acl_default = dfacl;
+                args.len = nfsacl_size(acl, dfacl);
+        } else
+                args.len = nfsacl_size(acl, NULL);
+
+        if (args.len > NFS_ACL_INLINE_BUFSIZE) {
+                unsigned int npages = 1 + ((args.len - 1) >> PAGE_SHIFT);
+
+                status = -ENOMEM;
+                do {
+                        args.pages[args.npages] = alloc_page(GFP_KERNEL);
+                        if (args.pages[args.npages] == NULL)
+                                goto out_freepages;
+                        args.npages++;
+                } while (args.npages < npages);
         }
 
         dprintk("NFS call setacl\n");
@@ -329,10 +343,6 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
         nfs_zap_acl_cache(inode);
         dprintk("NFS reply setacl: %d\n", status);
 
-        /* pages may have been allocated at the xdr layer. */
-        for (count = 0; count < NFSACL_MAXPAGES && args.pages[count]; count++)
-                __free_page(args.pages[count]);
-
         switch (status) {
                 case 0:
                         status = nfs_refresh_inode(inode, &fattr);
@@ -346,6 +356,11 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
                 case -ENOTSUPP:
                         status = -EOPNOTSUPP;
         }
+out_freepages:
+        while (args.npages != 0) {
+                args.npages--;
+                __free_page(args.pages[args.npages]);
+        }
 out:
         return status;
 }
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 11cdddec1432..6cdeacffde46 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -82,8 +82,10 @@
 #define NFS3_commitres_sz       (1+NFS3_wcc_data_sz+2)
 
 #define ACL3_getaclargs_sz      (NFS3_fh_sz+1)
-#define ACL3_setaclargs_sz      (NFS3_fh_sz+1+2*(2+5*3))
-#define ACL3_getaclres_sz       (1+NFS3_post_op_attr_sz+1+2*(2+5*3))
+#define ACL3_setaclargs_sz      (NFS3_fh_sz+1+ \
+                                XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE))
+#define ACL3_getaclres_sz       (1+NFS3_post_op_attr_sz+1+ \
+                                XDR_QUADLEN(NFS_ACL_INLINE_BUFSIZE))
 #define ACL3_setaclres_sz       (1+NFS3_post_op_attr_sz)
 
 /*
@@ -703,28 +705,18 @@ nfs3_xdr_setaclargs(struct rpc_rqst *req, __be32 *p,
                    struct nfs3_setaclargs *args)
 {
         struct xdr_buf *buf = &req->rq_snd_buf;
-        unsigned int base, len_in_head, len = nfsacl_size(
-                (args->mask & NFS_ACL)   ? args->acl_access  : NULL,
-                (args->mask & NFS_DFACL) ? args->acl_default : NULL);
-        int count, err;
+        unsigned int base;
+        int err;
 
         p = xdr_encode_fhandle(p, NFS_FH(args->inode));
         *p++ = htonl(args->mask);
-        base = (char *)p - (char *)buf->head->iov_base;
-        /* put as much of the acls into head as possible. */
-        len_in_head = min_t(unsigned int, buf->head->iov_len - base, len);
-        len -= len_in_head;
-        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p + (len_in_head >> 2));
-
-        for (count = 0; (count << PAGE_SHIFT) < len; count++) {
-                args->pages[count] = alloc_page(GFP_KERNEL);
-                if (!args->pages[count]) {
-                        while (count)
-                                __free_page(args->pages[--count]);
-                        return -ENOMEM;
-                }
-        }
-        xdr_encode_pages(buf, args->pages, 0, len);
+        req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+        base = req->rq_slen;
+
+        if (args->npages != 0)
+                xdr_encode_pages(buf, args->pages, 0, args->len);
+        else
+                req->rq_slen += args->len;
 
         err = nfsacl_encode(buf, base, args->inode,
                             (args->mask & NFS_ACL) ?
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 30befc39b3c6..2a2a0a7143ad 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -21,7 +21,9 @@
 #define NFSDBG_FACILITY         NFSDBG_VFS
 
 /*
- * Check if fs_root is valid
+ * Convert the NFSv4 pathname components into a standard posix path.
+ *
+ * Note that the resulting string will be placed at the end of the buffer
  */
 static inline char *nfs4_pathname_string(const struct nfs4_pathname *pathname,
                                          char *buffer, ssize_t buflen)
@@ -99,21 +101,20 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 {
         struct vfsmount *mnt = ERR_PTR(-ENOENT);
         char *mnt_path;
-        int page2len;
+        unsigned int maxbuflen;
         unsigned int s;
 
         mnt_path = nfs4_pathname_string(&location->rootpath, page2, PAGE_SIZE);
         if (IS_ERR(mnt_path))
                 return mnt;
         mountdata->mnt_path = mnt_path;
-        page2 += strlen(mnt_path) + 1;
-        page2len = PAGE_SIZE - strlen(mnt_path) - 1;
+        maxbuflen = mnt_path - 1 - page2;
 
         for (s = 0; s < location->nservers; s++) {
                 const struct nfs4_string *buf = &location->servers[s];
                 struct sockaddr_storage addr;
 
-                if (buf->len <= 0 || buf->len >= PAGE_SIZE)
+                if (buf->len <= 0 || buf->len >= maxbuflen)
                         continue;
 
                 mountdata->addr = (struct sockaddr *)&addr;
@@ -126,8 +127,8 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
                         continue;
                 nfs_set_port(mountdata->addr, NFS_PORT);
 
-                strncpy(page2, buf->data, page2len);
-                page2[page2len] = '\0';
+                memcpy(page2, buf->data, buf->len);
+                page2[buf->len] = '\0';
                 mountdata->hostname = page2;
 
                 snprintf(page, PAGE_SIZE, "%s:%s",