Merge branch 'linux-2.6'

14 files changed, 66 insertions, 148 deletions

diff --git a/fs/aio.c b/fs/aio.c
index f12db415c0f6..9dec7d2d546e 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -1161,7 +1161,12 @@ retry:
                         ret = 0;
                         if (to.timed_out)       /* Only check after read evt */
                                 break;
-                        io_schedule();
+                        /* Try to only show up in io wait if there are ops
+                         *  in flight */
+                        if (ctx->reqs_active)
+                                io_schedule();
+                        else
+                                schedule();
                         if (signal_pending(tsk)) {
                                 ret = -EINTR;
                                 break;
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index 294c41baef6e..a64a71d444f5 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -178,7 +178,8 @@ static void bfs_delete_inode(struct inode *inode)
         brelse(bh);
 
         if (bi->i_dsk_ino) {
-                info->si_freeb += BFS_FILEBLOCKS(bi);
+                if (bi->i_sblock)
+                        info->si_freeb += bi->i_eblock + 1 - bi->i_sblock;
                 info->si_freei++;
                 clear_bit(ino, info->si_imap);
                 dump_imap("delete_inode", s);
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index f02fdef463a7..c312adcba4fc 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -134,9 +134,10 @@ int compare_sids(const struct cifs_sid *ctsid, const struct cifs_sid *cwsid)
    pmode is the existing mode (we only want to overwrite part of this
    bits to set can be: S_IRWXU, S_IRWXG or S_IRWXO ie 00700 or 00070 or 00007
 */
-static void access_flags_to_mode(__u32 ace_flags, int type, umode_t *pmode,
+static void access_flags_to_mode(__le32 ace_flags, int type, umode_t *pmode,
                                  umode_t *pbits_to_set)
 {
+        __u32 flags = le32_to_cpu(ace_flags);
         /* the order of ACEs is important.  The canonical order is to begin with
            DENY entries followed by ALLOW, otherwise an allow entry could be
            encountered first, making the subsequent deny entry like "dead code"
@@ -146,17 +147,17 @@ static void access_flags_to_mode(__u32 ace_flags, int type, umode_t *pmode,
         /* For deny ACEs we change the mask so that subsequent allow access
            control entries do not turn on the bits we are denying */
         if (type == ACCESS_DENIED) {
-                if (ace_flags & GENERIC_ALL) {
+                if (flags & GENERIC_ALL) {
                         *pbits_to_set &= ~S_IRWXUGO;
                 }
-                if ((ace_flags & GENERIC_WRITE) ||
-                        ((ace_flags & FILE_WRITE_RIGHTS) == FILE_WRITE_RIGHTS))
+                if ((flags & GENERIC_WRITE) ||
+                        ((flags & FILE_WRITE_RIGHTS) == FILE_WRITE_RIGHTS))
                         *pbits_to_set &= ~S_IWUGO;
-                if ((ace_flags & GENERIC_READ) ||
-                        ((ace_flags & FILE_READ_RIGHTS) == FILE_READ_RIGHTS))
+                if ((flags & GENERIC_READ) ||
+                        ((flags & FILE_READ_RIGHTS) == FILE_READ_RIGHTS))
                         *pbits_to_set &= ~S_IRUGO;
-                if ((ace_flags & GENERIC_EXECUTE) ||
-                        ((ace_flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS))
+                if ((flags & GENERIC_EXECUTE) ||
+                        ((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS))
                         *pbits_to_set &= ~S_IXUGO;
                 return;
         } else if (type != ACCESS_ALLOWED) {
@@ -165,25 +166,25 @@ static void access_flags_to_mode(__u32 ace_flags, int type, umode_t *pmode,
         }
         /* else ACCESS_ALLOWED type */
 
-        if (ace_flags & GENERIC_ALL) {
+        if (flags & GENERIC_ALL) {
                 *pmode |= (S_IRWXUGO & (*pbits_to_set));
 #ifdef CONFIG_CIFS_DEBUG2
                 cFYI(1, ("all perms"));
 #endif
                 return;
         }
-        if ((ace_flags & GENERIC_WRITE) ||
-                        ((ace_flags & FILE_WRITE_RIGHTS) == FILE_WRITE_RIGHTS))
+        if ((flags & GENERIC_WRITE) ||
+                        ((flags & FILE_WRITE_RIGHTS) == FILE_WRITE_RIGHTS))
                 *pmode |= (S_IWUGO & (*pbits_to_set));
-        if ((ace_flags & GENERIC_READ) ||
-                        ((ace_flags & FILE_READ_RIGHTS) == FILE_READ_RIGHTS))
+        if ((flags & GENERIC_READ) ||
+                        ((flags & FILE_READ_RIGHTS) == FILE_READ_RIGHTS))
                 *pmode |= (S_IRUGO & (*pbits_to_set));
-        if ((ace_flags & GENERIC_EXECUTE) ||
-                        ((ace_flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS))
+        if ((flags & GENERIC_EXECUTE) ||
+                        ((flags & FILE_EXEC_RIGHTS) == FILE_EXEC_RIGHTS))
                 *pmode |= (S_IXUGO & (*pbits_to_set));
 
 #ifdef CONFIG_CIFS_DEBUG2
-        cFYI(1, ("access flags 0x%x mode now 0x%x", ace_flags, *pmode));
+        cFYI(1, ("access flags 0x%x mode now 0x%x", flags, *pmode));
 #endif
         return;
 }
diff --git a/fs/jbd/checkpoint.c b/fs/jbd/checkpoint.c
index 47552d4a6324..0f69c416eebc 100644
--- a/fs/jbd/checkpoint.c
+++ b/fs/jbd/checkpoint.c
@@ -602,15 +602,15 @@ int __journal_remove_checkpoint(struct journal_head *jh)
 
         /*
          * There is one special case to worry about: if we have just pulled the
-         * buffer off a committing transaction's forget list, then even if the
-         * checkpoint list is empty, the transaction obviously cannot be
-         * dropped!
+         * buffer off a running or committing transaction's checkpoing list,
+         * then even if the checkpoint list is empty, the transaction obviously
+         * cannot be dropped!
          *
-         * The locking here around j_committing_transaction is a bit sleazy.
+         * The locking here around t_state is a bit sleazy.
          * See the comment at the end of journal_commit_transaction().
          */
-        if (transaction == journal->j_committing_transaction) {
-                JBUFFER_TRACE(jh, "belongs to committing transaction");
+        if (transaction->t_state != T_FINISHED) {
+                JBUFFER_TRACE(jh, "belongs to running/committing transaction");
                 goto out;
         }
 
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 8f1f2aa5fb39..610264b99a8e 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -858,10 +858,10 @@ restart_loop:
         }
         spin_unlock(&journal->j_list_lock);
         /*
-         * This is a bit sleazy.  We borrow j_list_lock to protect
-         * journal->j_committing_transaction in __journal_remove_checkpoint.
-         * Really, __journal_remove_checkpoint should be using j_state_lock but
-         * it's a bit hassle to hold that across __journal_remove_checkpoint
+         * This is a bit sleazy.  We use j_list_lock to protect transition
+         * of a transaction into T_FINISHED state and calling
+         * __journal_drop_transaction(). Otherwise we could race with
+         * other checkpointing code processing the transaction...
          */
         spin_lock(&journal->j_state_lock);
         spin_lock(&journal->j_list_lock);
diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c
index d568ae846741..8adebd3e43c6 100644
--- a/fs/jffs2/background.c
+++ b/fs/jffs2/background.c
@@ -105,7 +105,7 @@ static int jffs2_garbage_collect_thread(void *_c)
 
                 /* Put_super will send a SIGKILL and then wait on the sem.
                  */
-                while (signal_pending(current)) {
+                while (signal_pending(current) || freezing(current)) {
                         siginfo_t info;
                         unsigned long signr;
 
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index d84bd155997b..ee50c9610e7f 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -72,14 +72,6 @@
 
 #include "tcp_internal.h"
 
-/* 
- * The linux network stack isn't sparse endian clean.. It has macros like
- * ntohs() which perform the endian checks and structs like sockaddr_in
- * which aren't annotated.  So __force is found here to get the build
- * clean.  When they emerge from the dark ages and annotate the code
- * we can remove these.
- */
-
 #define SC_NODEF_FMT "node %s (num %u) at %u.%u.%u.%u:%u"
 #define SC_NODEF_ARGS(sc) sc->sc_node->nd_name, sc->sc_node->nd_num,    \
                           NIPQUAD(sc->sc_node->nd_ipv4_address),        \
@@ -1500,7 +1492,7 @@ static void o2net_start_connect(struct work_struct *work)
 
         myaddr.sin_family = AF_INET;
         myaddr.sin_addr.s_addr = mynode->nd_ipv4_address;
-        myaddr.sin_port = (__force u16)htons(0); /* any port */
+        myaddr.sin_port = htons(0); /* any port */
 
         ret = sock->ops->bind(sock, (struct sockaddr *)&myaddr,
                               sizeof(myaddr));
@@ -1701,11 +1693,11 @@ static int o2net_accept_one(struct socket *sock)
         if (ret < 0)
                 goto out;
 
-        node = o2nm_get_node_by_ip((__force __be32)sin.sin_addr.s_addr);
+        node = o2nm_get_node_by_ip(sin.sin_addr.s_addr);
         if (node == NULL) {
                 mlog(ML_NOTICE, "attempt to connect from unknown node at "
                      "%u.%u.%u.%u:%d\n", NIPQUAD(sin.sin_addr.s_addr),
-                     ntohs((__force __be16)sin.sin_port));
+                     ntohs(sin.sin_port));
                 ret = -EINVAL;
                 goto out;
         }
@@ -1714,7 +1706,7 @@ static int o2net_accept_one(struct socket *sock)
                 mlog(ML_NOTICE, "unexpected connect attempted from a lower "
                      "numbered node '%s' at " "%u.%u.%u.%u:%d with num %u\n",
                      node->nd_name, NIPQUAD(sin.sin_addr.s_addr),
-                     ntohs((__force __be16)sin.sin_port), node->nd_num);
+                     ntohs(sin.sin_port), node->nd_num);
                 ret = -EINVAL;
                 goto out;
         }
@@ -1725,7 +1717,7 @@ static int o2net_accept_one(struct socket *sock)
                 mlog(ML_CONN, "attempt to connect from node '%s' at "
                      "%u.%u.%u.%u:%d but it isn't heartbeating\n",
                      node->nd_name, NIPQUAD(sin.sin_addr.s_addr),
-                     ntohs((__force __be16)sin.sin_port));
+                     ntohs(sin.sin_port));
                 ret = -EINVAL;
                 goto out;
         }
@@ -1742,7 +1734,7 @@ static int o2net_accept_one(struct socket *sock)
                 mlog(ML_NOTICE, "attempt to connect from node '%s' at "
                      "%u.%u.%u.%u:%d but it already has an open connection\n",
                      node->nd_name, NIPQUAD(sin.sin_addr.s_addr),
-                     ntohs((__force __be16)sin.sin_port));
+                     ntohs(sin.sin_port));
                 goto out;
         }
 
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index 39f3d6519035..8d49838e5554 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -374,9 +374,16 @@ static int proc_delete_dentry(struct dentry * dentry)
         return 1;
 }
 
+static int proc_revalidate_dentry(struct dentry *dentry, struct nameidata *nd)
+{
+        d_drop(dentry);
+        return 0;
+}
+
 static struct dentry_operations proc_dentry_operations =
 {
         .d_delete       = proc_delete_dentry,
+        .d_revalidate   = proc_revalidate_dentry,
 };
 
 /*
@@ -397,8 +404,11 @@ struct dentry *proc_lookup(struct inode * dir, struct dentry *dentry, struct nam
                         if (de->namelen != dentry->d_name.len)
                                 continue;
                         if (!memcmp(dentry->d_name.name, de->name, de->namelen)) {
-                                unsigned int ino = de->low_ino;
+                                unsigned int ino;
 
+                                if (de->shadow_proc)
+                                        de = de->shadow_proc(current, de);
+                                ino = de->low_ino;
                                 de_get(de);
                                 spin_unlock(&proc_subdir_lock);
                                 error = -EINVAL;
@@ -585,6 +595,7 @@ static struct proc_dir_entry *proc_create(struct proc_dir_entry **parent,
         ent->namelen = len;
         ent->mode = mode;
         ent->nlink = nlink;
+        atomic_set(&ent->count, 1);
         ent->pde_users = 0;
         spin_lock_init(&ent->pde_unload_lock);
         ent->pde_unload_completion = NULL;
@@ -682,7 +693,6 @@ void free_proc_entry(struct proc_dir_entry *de)
 
 /*
  * Remove a /proc entry and free it if it's not currently in use.
- * If it is in use, we set the 'deleted' flag.
  */
 void remove_proc_entry(const char *name, struct proc_dir_entry *parent)
 {
@@ -731,13 +741,8 @@ continue_removing:
                         parent->nlink--;
                 de->nlink = 0;
                 WARN_ON(de->subdir);
-                if (!atomic_read(&de->count))
+                if (atomic_dec_and_test(&de->count))
                         free_proc_entry(de);
-                else {
-                        de->deleted = 1;
-                        printk("remove_proc_entry: %s/%s busy, count=%d\n",
-                                parent->name, de->name, atomic_read(&de->count));
-                }
                 break;
         }
         spin_unlock(&proc_subdir_lock);
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index abe6a3f04368..1a551d92e1d8 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -43,13 +43,8 @@ void de_put(struct proc_dir_entry *de)
                         return;
                 }
 
-                if (atomic_dec_and_test(&de->count)) {
-                        if (de->deleted) {
-                                printk("de_put: deferred delete of %s\n",
-                                        de->name);
-                                free_proc_entry(de);
-                        }
-                }               
+                if (atomic_dec_and_test(&de->count))
+                        free_proc_entry(de);
                 unlock_kernel();
         }
 }
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index 131f9c68be5f..0afe21ee0607 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -50,89 +50,14 @@ struct net *get_proc_net(const struct inode *inode)
 }
 EXPORT_SYMBOL_GPL(get_proc_net);
 
-static struct proc_dir_entry *proc_net_shadow;
+static struct proc_dir_entry *shadow_pde;
 
-static struct dentry *proc_net_shadow_dentry(struct dentry *parent,
+static struct proc_dir_entry *proc_net_shadow(struct task_struct *task,
                                                 struct proc_dir_entry *de)
 {
-        struct dentry *shadow = NULL;
-        struct inode *inode;
-        if (!de)
-                goto out;
-        de_get(de);
-        inode = proc_get_inode(parent->d_inode->i_sb, de->low_ino, de);
-        if (!inode)
-                goto out_de_put;
-        shadow = d_alloc_name(parent, de->name);
-        if (!shadow)
-                goto out_iput;
-        shadow->d_op = parent->d_op; /* proc_dentry_operations */
-        d_instantiate(shadow, inode);
-out:
-        return shadow;
-out_iput:
-        iput(inode);
-out_de_put:
-        de_put(de);
-        goto out;
-}
-
-static void *proc_net_follow_link(struct dentry *parent, struct nameidata *nd)
-{
-        struct net *net = current->nsproxy->net_ns;
-        struct dentry *shadow;
-        shadow = proc_net_shadow_dentry(parent, net->proc_net);
-        if (!shadow)
-                return ERR_PTR(-ENOENT);
-
-        dput(nd->dentry);
-        /* My dentry count is 1 and that should be enough as the
-         * shadow dentry is thrown away immediately.
-         */
-        nd->dentry = shadow;
-        return NULL;
+        return task->nsproxy->net_ns->proc_net;
 }
 
-static struct dentry *proc_net_lookup(struct inode *dir, struct dentry *dentry,
-                                      struct nameidata *nd)
-{
-        struct net *net = current->nsproxy->net_ns;
-        struct dentry *shadow;
-
-        shadow = proc_net_shadow_dentry(nd->dentry, net->proc_net);
-        if (!shadow)
-                return ERR_PTR(-ENOENT);
-
-        dput(nd->dentry);
-        nd->dentry = shadow;
-
-        return shadow->d_inode->i_op->lookup(shadow->d_inode, dentry, nd);
-}
-
-static int proc_net_setattr(struct dentry *dentry, struct iattr *iattr)
-{
-        struct net *net = current->nsproxy->net_ns;
-        struct dentry *shadow;
-        int ret;
-
-        shadow = proc_net_shadow_dentry(dentry->d_parent, net->proc_net);
-        if (!shadow)
-                return -ENOENT;
-        ret = shadow->d_inode->i_op->setattr(shadow, iattr);
-        dput(shadow);
-        return ret;
-}
-
-static const struct file_operations proc_net_dir_operations = {
-        .read                   = generic_read_dir,
-};
-
-static struct inode_operations proc_net_dir_inode_operations = {
-        .follow_link    = proc_net_follow_link,
-        .lookup         = proc_net_lookup,
-        .setattr        = proc_net_setattr,
-};
-
 static __net_init int proc_net_ns_init(struct net *net)
 {
         struct proc_dir_entry *root, *netd, *net_statd;
@@ -185,9 +110,8 @@ static struct pernet_operations __net_initdata proc_net_ns_ops = {
 
 int __init proc_net_init(void)
 {
-        proc_net_shadow = proc_mkdir("net", NULL);
-        proc_net_shadow->proc_iops = &proc_net_dir_inode_operations;
-        proc_net_shadow->proc_fops = &proc_net_dir_operations;
+        shadow_pde = proc_mkdir("net", NULL);
+        shadow_pde->shadow_proc = proc_net_shadow;
 
         return register_pernet_subsys(&proc_net_ns_ops);
 }
diff --git a/fs/proc/root.c b/fs/proc/root.c
index ec9cb3b6c93b..81f99e691f99 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -207,6 +207,7 @@ struct proc_dir_entry proc_root = {
         .name           = "/proc",
         .mode           = S_IFDIR | S_IRUGO | S_IXUGO, 
         .nlink          = 2, 
+        .count          = ATOMIC_INIT(1),
         .proc_iops      = &proc_root_inode_operations, 
         .proc_fops      = &proc_root_operations,
         .parent         = &proc_root,
diff --git a/fs/reiserfs/procfs.c b/fs/reiserfs/procfs.c
index 9aa7a06e093f..001144621672 100644
--- a/fs/reiserfs/procfs.c
+++ b/fs/reiserfs/procfs.c
@@ -420,12 +420,6 @@ static void *r_start(struct seq_file *m, loff_t * pos)
                 return NULL;
 
         up_write(&s->s_umount);
-
-        if (de->deleted) {
-                deactivate_super(s);
-                return NULL;
-        }
-
         return s;
 }
 
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index 30f8c2bb0c3e..aaf2878305ce 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -179,7 +179,7 @@ bad_entry:
         goto fail;
 Eend:
         p = (struct ufs_dir_entry *)(kaddr + offs);
-        ufs_error (sb, "ext2_check_page",
+        ufs_error(sb, __FUNCTION__,
                    "entry in directory #%lu spans the page boundary"
                    "offset=%lu",
                    dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs);
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index c78c04fd993f..0072cb33ebec 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -755,13 +755,13 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
                 break;
         
         case UFS_MOUNT_UFSTYPE_NEXTSTEP:
-                /*TODO: check may be we need set special dir block size?*/
                 UFSD("ufstype=nextstep\n");
                 uspi->s_fsize = block_size = 1024;
                 uspi->s_fmask = ~(1024 - 1);
                 uspi->s_fshift = 10;
                 uspi->s_sbsize = super_block_size = 2048;
                 uspi->s_sbbase = 0;
+                uspi->s_dirblksize = 1024;
                 flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD;
                 if (!(sb->s_flags & MS_RDONLY)) {
                         if (!silent)
@@ -771,13 +771,13 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
                 break;
         
         case UFS_MOUNT_UFSTYPE_NEXTSTEP_CD:
-                /*TODO: check may be we need set special dir block size?*/
                 UFSD("ufstype=nextstep-cd\n");
                 uspi->s_fsize = block_size = 2048;
                 uspi->s_fmask = ~(2048 - 1);
                 uspi->s_fshift = 11;
                 uspi->s_sbsize = super_block_size = 2048;
                 uspi->s_sbbase = 0;
+                uspi->s_dirblksize = 1024;
                 flags |= UFS_DE_OLD | UFS_UID_OLD | UFS_ST_OLD | UFS_CG_OLD;
                 if (!(sb->s_flags & MS_RDONLY)) {
                         if (!silent)