10 files changed, 162 insertions, 48 deletions

diff --git a/Documentation/filesystems/nfs-rdma.txt b/Documentation/filesystems/nfs-rdma.txt
index 1ae34879574b..d0ec45ae4e7d 100644
--- a/Documentation/filesystems/nfs-rdma.txt
+++ b/Documentation/filesystems/nfs-rdma.txt
@@ -5,7 +5,7 @@
 ################################################################################
 
  Author: NetApp and Open Grid Computing
- Date: February 25, 2008
+ Date: April 15, 2008
 
 Table of Contents
 ~~~~~~~~~~~~~~~~~
@@ -197,12 +197,16 @@ NFS/RDMA Setup
   - On the server system, configure the /etc/exports file and
     start the NFS/RDMA server.
 
-    Exports entries with the following format have been tested:
+    Exports entries with the following formats have been tested:
 
-    /vol0   10.97.103.47(rw,async) 192.168.0.47(rw,async,insecure,no_root_squash)
+    /vol0   192.168.0.47(fsid=0,rw,async,insecure,no_root_squash)
+    /vol0   192.168.0.0/255.255.255.0(fsid=0,rw,async,insecure,no_root_squash)
 
-    Here the first IP address is the client's Ethernet address and the second
-    IP address is the clients IPoIB address.
+    The IP address(es) is(are) the client's IPoIB address for an InfiniBand HCA or the
+    cleint's iWARP address(es) for an RNIC.
+
+    NOTE: The "insecure" option must be used because the NFS/RDMA client does not
+    use a reserved port.
 
  Each time a machine boots:
 
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 1f122c1940af..4d81553d2948 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -632,7 +632,7 @@ nlmsvc_update_deferred_block(struct nlm_block *block, struct file_lock *conf,
                 block->b_flags |= B_TIMED_OUT;
         if (conf) {
                 if (block->b_fl)
-                        locks_copy_lock(block->b_fl, conf);
+                        __locks_copy_lock(block->b_fl, conf);
         }
 }
 
diff --git a/fs/lockd/svcsubs.c b/fs/lockd/svcsubs.c
index dbbefbcd6712..d1c48b539df8 100644
--- a/fs/lockd/svcsubs.c
+++ b/fs/lockd/svcsubs.c
@@ -18,6 +18,8 @@
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
 #include <linux/lockd/sm_inter.h>
+#include <linux/module.h>
+#include <linux/mount.h>
 
 #define NLMDBG_FACILITY         NLMDBG_SVCSUBS
 
@@ -194,6 +196,12 @@ again:
         return 0;
 }
 
+static int
+nlmsvc_always_match(void *dummy1, struct nlm_host *dummy2)
+{
+        return 1;
+}
+
 /*
  * Inspect a single file
  */
@@ -230,7 +238,8 @@ nlm_file_inuse(struct nlm_file *file)
  * Loop over all files in the file table.
  */
 static int
-nlm_traverse_files(struct nlm_host *host, nlm_host_match_fn_t match)
+nlm_traverse_files(void *data, nlm_host_match_fn_t match,
+                int (*is_failover_file)(void *data, struct nlm_file *file))
 {
         struct hlist_node *pos, *next;
         struct nlm_file *file;
@@ -239,12 +248,14 @@ nlm_traverse_files(struct nlm_host *host, nlm_host_match_fn_t match)
         mutex_lock(&nlm_file_mutex);
         for (i = 0; i < FILE_NRHASH; i++) {
                 hlist_for_each_entry_safe(file, pos, next, &nlm_files[i], f_list) {
+                        if (is_failover_file && !is_failover_file(data, file))
+                                continue;
                         file->f_count++;
                         mutex_unlock(&nlm_file_mutex);
 
                         /* Traverse locks, blocks and shares of this file
                          * and update file->f_locks count */
-                        if (nlm_inspect_file(host, file, match))
+                        if (nlm_inspect_file(data, file, match))
                                 ret = 1;
 
                         mutex_lock(&nlm_file_mutex);
@@ -303,21 +314,27 @@ nlm_release_file(struct nlm_file *file)
  *      Used by nlmsvc_invalidate_all
  */
 static int
-nlmsvc_mark_host(struct nlm_host *host, struct nlm_host *dummy)
+nlmsvc_mark_host(void *data, struct nlm_host *dummy)
 {
+        struct nlm_host *host = data;
+
         host->h_inuse = 1;
         return 0;
 }
 
 static int
-nlmsvc_same_host(struct nlm_host *host, struct nlm_host *other)
+nlmsvc_same_host(void *data, struct nlm_host *other)
 {
+        struct nlm_host *host = data;
+
         return host == other;
 }
 
 static int
-nlmsvc_is_client(struct nlm_host *host, struct nlm_host *dummy)
+nlmsvc_is_client(void *data, struct nlm_host *dummy)
 {
+        struct nlm_host *host = data;
+
         if (host->h_server) {
                 /* we are destroying locks even though the client
                  * hasn't asked us too, so don't unmonitor the
@@ -337,7 +354,7 @@ void
 nlmsvc_mark_resources(void)
 {
         dprintk("lockd: nlmsvc_mark_resources\n");
-        nlm_traverse_files(NULL, nlmsvc_mark_host);
+        nlm_traverse_files(NULL, nlmsvc_mark_host, NULL);
 }
 
 /*
@@ -348,7 +365,7 @@ nlmsvc_free_host_resources(struct nlm_host *host)
 {
         dprintk("lockd: nlmsvc_free_host_resources\n");
 
-        if (nlm_traverse_files(host, nlmsvc_same_host)) {
+        if (nlm_traverse_files(host, nlmsvc_same_host, NULL)) {
                 printk(KERN_WARNING
                         "lockd: couldn't remove all locks held by %s\n",
                         host->h_name);
@@ -368,5 +385,41 @@ nlmsvc_invalidate_all(void)
          * turn, which is about as inefficient as it gets.
          * Now we just do it once in nlm_traverse_files.
          */
-        nlm_traverse_files(NULL, nlmsvc_is_client);
+        nlm_traverse_files(NULL, nlmsvc_is_client, NULL);
+}
+
+static int
+nlmsvc_match_sb(void *datap, struct nlm_file *file)
+{
+        struct super_block *sb = datap;
+
+        return sb == file->f_file->f_path.mnt->mnt_sb;
+}
+
+int
+nlmsvc_unlock_all_by_sb(struct super_block *sb)
+{
+        int ret;
+
+        ret = nlm_traverse_files(sb, nlmsvc_always_match, nlmsvc_match_sb);
+        return ret ? -EIO : 0;
+}
+EXPORT_SYMBOL_GPL(nlmsvc_unlock_all_by_sb);
+
+static int
+nlmsvc_match_ip(void *datap, struct nlm_host *host)
+{
+        __be32 *server_addr = datap;
+
+        return host->h_saddr.sin_addr.s_addr == *server_addr;
+}
+
+int
+nlmsvc_unlock_all_by_ip(__be32 server_addr)
+{
+        int ret;
+        ret = nlm_traverse_files(&server_addr, nlmsvc_match_ip, NULL);
+        return ret ? -EIO : 0;
+
 }
+EXPORT_SYMBOL_GPL(nlmsvc_unlock_all_by_ip);
diff --git a/fs/locks.c b/fs/locks.c
index 592faadbcec1..e1ea2fe03681 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -224,7 +224,7 @@ static void locks_copy_private(struct file_lock *new, struct file_lock *fl)
 /*
  * Initialize a new lock from an existing file_lock structure.
  */
-static void __locks_copy_lock(struct file_lock *new, const struct file_lock *fl)
+void __locks_copy_lock(struct file_lock *new, const struct file_lock *fl)
 {
         new->fl_owner = fl->fl_owner;
         new->fl_pid = fl->fl_pid;
@@ -833,7 +833,7 @@ static int __posix_lock_file(struct inode *inode, struct file_lock *request, str
                         if (!posix_locks_conflict(request, fl))
                                 continue;
                         if (conflock)
-                                locks_copy_lock(conflock, fl);
+                                __locks_copy_lock(conflock, fl);
                         error = -EAGAIN;
                         if (!(request->fl_flags & FL_SLEEP))
                                 goto out;
@@ -1367,18 +1367,20 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
 
         lease = *flp;
 
-        error = -EAGAIN;
-        if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
-                goto out;
-        if ((arg == F_WRLCK)
-            && ((atomic_read(&dentry->d_count) > 1)
-                || (atomic_read(&inode->i_count) > 1)))
-                goto out;
+        if (arg != F_UNLCK) {
+                error = -ENOMEM;
+                new_fl = locks_alloc_lock();
+                if (new_fl == NULL)
+                        goto out;
 
-        error = -ENOMEM;
-        new_fl = locks_alloc_lock();
-        if (new_fl == NULL)
-                goto out;
+                error = -EAGAIN;
+                if ((arg == F_RDLCK) && (atomic_read(&inode->i_writecount) > 0))
+                        goto out;
+                if ((arg == F_WRLCK)
+                    && ((atomic_read(&dentry->d_count) > 1)
+                        || (atomic_read(&inode->i_count) > 1)))
+                        goto out;
+        }
 
         /*
          * At this point, we know that if there is an exclusive
@@ -1404,6 +1406,7 @@ int generic_setlease(struct file *filp, long arg, struct file_lock **flp)
                         rdlease_count++;
         }
 
+        error = -EAGAIN;
         if ((arg == F_RDLCK && (wrlease_count > 0)) ||
             (arg == F_WRLCK && ((rdlease_count + wrlease_count) > 0)))
                 goto out;
@@ -1490,8 +1493,7 @@ EXPORT_SYMBOL_GPL(vfs_setlease);
 int fcntl_setlease(unsigned int fd, struct file *filp, long arg)
 {
         struct file_lock fl, *flp = &fl;
-        struct dentry *dentry = filp->f_path.dentry;
-        struct inode *inode = dentry->d_inode;
+        struct inode *inode = filp->f_path.dentry->d_inode;
         int error;
 
         locks_init_lock(&fl);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 55dfdd71f1b0..8799b8708188 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -2712,9 +2712,6 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
         * Note: locks.c uses the BKL to protect the inode's lock list.
         */
 
-        /* XXX?: Just to divert the locks_release_private at the start of
-         * locks_copy_lock: */
-        locks_init_lock(&conflock);
         err = vfs_lock_file(filp, cmd, &file_lock, &conflock);
         switch (-err) {
         case 0: /* success! */
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 1ba7ad981935..c513bbdf2d36 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -376,20 +376,6 @@ nfsd4_decode_fattr(struct nfsd4_compoundargs *argp, u32 *bmval, struct iattr *ia
                         goto xdr_error;
                 }
         }
-        if (bmval[1] & FATTR4_WORD1_TIME_METADATA) {
-                /* We require the high 32 bits of 'seconds' to be 0, and we ignore
-                   all 32 bits of 'nseconds'. */
-                READ_BUF(12);
-                len += 12;
-                READ32(dummy32);
-                if (dummy32)
-                        return nfserr_inval;
-                READ32(iattr->ia_ctime.tv_sec);
-                READ32(iattr->ia_ctime.tv_nsec);
-                if (iattr->ia_ctime.tv_nsec >= (u32)1000000000)
-                        return nfserr_inval;
-                iattr->ia_valid |= ATTR_CTIME;
-        }
         if (bmval[1] & FATTR4_WORD1_TIME_MODIFY_SET) {
                 READ_BUF(4);
                 len += 4;
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index 613bcb8171a5..42f3820ee8f5 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -22,6 +22,7 @@
 #include <linux/seq_file.h>
 #include <linux/pagemap.h>
 #include <linux/init.h>
+#include <linux/inet.h>
 #include <linux/string.h>
 #include <linux/smp_lock.h>
 #include <linux/ctype.h>
@@ -35,6 +36,7 @@
 #include <linux/nfsd/cache.h>
 #include <linux/nfsd/xdr.h>
 #include <linux/nfsd/syscall.h>
+#include <linux/lockd/lockd.h>
 
 #include <asm/uaccess.h>
 #include <net/ipv6.h>
@@ -53,6 +55,8 @@ enum {
         NFSD_Getfs,
         NFSD_List,
         NFSD_Fh,
+        NFSD_FO_UnlockIP,
+        NFSD_FO_UnlockFS,
         NFSD_Threads,
         NFSD_Pool_Threads,
         NFSD_Versions,
@@ -89,6 +93,9 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size);
 static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
 #endif
 
+static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size);
+static ssize_t failover_unlock_fs(struct file *file, char *buf, size_t size);
+
 static ssize_t (*write_op[])(struct file *, char *, size_t) = {
         [NFSD_Svc] = write_svc,
         [NFSD_Add] = write_add,
@@ -98,6 +105,8 @@ static ssize_t (*write_op[])(struct file *, char *, size_t) = {
         [NFSD_Getfd] = write_getfd,
         [NFSD_Getfs] = write_getfs,
         [NFSD_Fh] = write_filehandle,
+        [NFSD_FO_UnlockIP] = failover_unlock_ip,
+        [NFSD_FO_UnlockFS] = failover_unlock_fs,
         [NFSD_Threads] = write_threads,
         [NFSD_Pool_Threads] = write_pool_threads,
         [NFSD_Versions] = write_versions,
@@ -298,6 +307,58 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size)
         return err;
 }
 
+static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size)
+{
+        __be32 server_ip;
+        char *fo_path, c;
+        int b1, b2, b3, b4;
+
+        /* sanity check */
+        if (size == 0)
+                return -EINVAL;
+
+        if (buf[size-1] != '\n')
+                return -EINVAL;
+
+        fo_path = buf;
+        if (qword_get(&buf, fo_path, size) < 0)
+                return -EINVAL;
+
+        /* get ipv4 address */
+        if (sscanf(fo_path, "%u.%u.%u.%u%c", &b1, &b2, &b3, &b4, &c) != 4)
+                return -EINVAL;
+        server_ip = htonl((((((b1<<8)|b2)<<8)|b3)<<8)|b4);
+
+        return nlmsvc_unlock_all_by_ip(server_ip);
+}
+
+static ssize_t failover_unlock_fs(struct file *file, char *buf, size_t size)
+{
+        struct nameidata nd;
+        char *fo_path;
+        int error;
+
+        /* sanity check */
+        if (size == 0)
+                return -EINVAL;
+
+        if (buf[size-1] != '\n')
+                return -EINVAL;
+
+        fo_path = buf;
+        if (qword_get(&buf, fo_path, size) < 0)
+                return -EINVAL;
+
+        error = path_lookup(fo_path, 0, &nd);
+        if (error)
+                return error;
+
+        error = nlmsvc_unlock_all_by_sb(nd.path.mnt->mnt_sb);
+
+        path_put(&nd.path);
+        return error;
+}
+
 static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
 {
         /* request is:
@@ -700,6 +761,10 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
                 [NFSD_Getfd] = {".getfd", &transaction_ops, S_IWUSR|S_IRUSR},
                 [NFSD_Getfs] = {".getfs", &transaction_ops, S_IWUSR|S_IRUSR},
                 [NFSD_List] = {"exports", &exports_operations, S_IRUGO},
+                [NFSD_FO_UnlockIP] = {"unlock_ip",
+                                        &transaction_ops, S_IWUSR|S_IRUSR},
+                [NFSD_FO_UnlockFS] = {"unlock_filesystem",
+                                        &transaction_ops, S_IWUSR|S_IRUSR},
                 [NFSD_Fh] = {"filehandle", &transaction_ops, S_IWUSR|S_IRUSR},
                 [NFSD_Threads] = {"threads", &transaction_ops, S_IWUSR|S_IRUSR},
                 [NFSD_Pool_Threads] = {"pool_threads", &transaction_ops, S_IWUSR|S_IRUSR},
diff --git a/include/linux/fs.h b/include/linux/fs.h
index cc2be2cf7d41..6556f2f967e5 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -973,6 +973,7 @@ extern int do_sync_mapping_range(struct address_space *mapping, loff_t offset,
 /* fs/locks.c */
 extern void locks_init_lock(struct file_lock *);
 extern void locks_copy_lock(struct file_lock *, struct file_lock *);
+extern void __locks_copy_lock(struct file_lock *, const struct file_lock *);
 extern void locks_remove_posix(struct file *, fl_owner_t);
 extern void locks_remove_flock(struct file *);
 extern void posix_test_lock(struct file *, struct file_lock *);
diff --git a/include/linux/lockd/lockd.h b/include/linux/lockd/lockd.h
index 94649a8da014..102d928f7206 100644
--- a/include/linux/lockd/lockd.h
+++ b/include/linux/lockd/lockd.h
@@ -194,7 +194,7 @@ void		  nsm_release(struct nsm_handle *);
  * This is used in garbage collection and resource reclaim
  * A return value != 0 means destroy the lock/block/share
  */
-typedef int       (*nlm_host_match_fn_t)(struct nlm_host *cur, struct nlm_host *ref);
+typedef int       (*nlm_host_match_fn_t)(void *cur, struct nlm_host *ref);
 
 /*
  * Server-side lock handling
@@ -220,6 +220,12 @@ void		  nlmsvc_mark_resources(void);
 void              nlmsvc_free_host_resources(struct nlm_host *);
 void              nlmsvc_invalidate_all(void);
 
+/*
+ * Cluster failover support
+ */
+int           nlmsvc_unlock_all_by_sb(struct super_block *sb);
+int           nlmsvc_unlock_all_by_ip(__be32 server_addr);
+
 static inline struct inode *nlmsvc_file_inode(struct nlm_file *file)
 {
         return file->f_file->f_path.dentry->d_inode;
diff --git a/include/linux/nfsd/nfsd.h b/include/linux/nfsd/nfsd.h
index 21ee440dd3e7..41d30c9c9de6 100644
--- a/include/linux/nfsd/nfsd.h
+++ b/include/linux/nfsd/nfsd.h
@@ -329,7 +329,7 @@ extern struct timeval	nfssvc_boot;
 (FATTR4_WORD0_SIZE              | FATTR4_WORD0_ACL                                         )
 #define NFSD_WRITEABLE_ATTRS_WORD1                                                          \
 (FATTR4_WORD1_MODE              | FATTR4_WORD1_OWNER         | FATTR4_WORD1_OWNER_GROUP     \
- | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY_SET)
+ | FATTR4_WORD1_TIME_ACCESS_SET | FATTR4_WORD1_TIME_MODIFY_SET)
 
 #endif /* CONFIG_NFSD_V4 */