Merge tag 'v3.3-rc7' into sched/core

Merge reason: merge back final fixes, prepare for the merge window.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

10 files changed, 138 insertions, 77 deletions

diff --git a/fs/aio.c b/fs/aio.c
index 969beb0e2231..b9d64d89a043 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -228,12 +228,6 @@ static void __put_ioctx(struct kioctx *ctx)
 	call_rcu(&ctx->rcu_head, ctx_rcu_free);
 }
 
-static inline void get_ioctx(struct kioctx *kioctx)
-{
-	BUG_ON(atomic_read(&kioctx->users) <= 0);
-	atomic_inc(&kioctx->users);
-}
-
 static inline int try_get_ioctx(struct kioctx *kioctx)
 {
 	return atomic_inc_not_zero(&kioctx->users);
@@ -273,7 +267,7 @@ static struct kioctx *ioctx_alloc(unsigned nr_events)
 	mm = ctx->mm = current->mm;
 	atomic_inc(&mm->mm_count);
 
-	atomic_set(&ctx->users, 1);
+	atomic_set(&ctx->users, 2);
 	spin_lock_init(&ctx->ctx_lock);
 	spin_lock_init(&ctx->ring_info.ring_lock);
 	init_waitqueue_head(&ctx->wait);
@@ -490,6 +484,8 @@ static void kiocb_batch_free(struct kioctx *ctx, struct kiocb_batch *batch)
 		kmem_cache_free(kiocb_cachep, req);
 		ctx->reqs_active--;
 	}
+	if (unlikely(!ctx->reqs_active && ctx->dead))
+		wake_up_all(&ctx->wait);
 	spin_unlock_irq(&ctx->ctx_lock);
 }
 
@@ -607,11 +603,16 @@ static void aio_fput_routine(struct work_struct *data)
 			fput(req->ki_filp);
 
 		/* Link the iocb into the context's free list */
+		rcu_read_lock();
 		spin_lock_irq(&ctx->ctx_lock);
 		really_put_req(ctx, req);
+		/*
+		 * at that point ctx might've been killed, but actual
+		 * freeing is RCU'd
+		 */
 		spin_unlock_irq(&ctx->ctx_lock);
+		rcu_read_unlock();
 
-		put_ioctx(ctx);
 		spin_lock_irq(&fput_lock);
 	}
 	spin_unlock_irq(&fput_lock);
@@ -642,7 +643,6 @@ static int __aio_put_req(struct kioctx *ctx, struct kiocb *req)
 	 * this function will be executed w/out any aio kthread wakeup.
 	 */
 	if (unlikely(!fput_atomic(req->ki_filp))) {
-		get_ioctx(ctx);
 		spin_lock(&fput_lock);
 		list_add(&req->ki_list, &fput_head);
 		spin_unlock(&fput_lock);
@@ -1336,10 +1336,10 @@ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp)
 	ret = PTR_ERR(ioctx);
 	if (!IS_ERR(ioctx)) {
 		ret = put_user(ioctx->user_id, ctxp);
-		if (!ret)
+		if (!ret) {
+			put_ioctx(ioctx);
 			return 0;
-
-		get_ioctx(ioctx); /* io_destroy() expects us to hold a ref */
+		}
 		io_destroy(ioctx);
 	}
 
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index a6395bdb26ae..1ff94054d35a 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -259,6 +259,13 @@ static int load_aout_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 	current->mm->free_area_cache = current->mm->mmap_base;
 	current->mm->cached_hole_size = 0;
 
+	retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
+	if (retval < 0) {
+		/* Someone check-me: is this error path enough? */
+		send_sig(SIGKILL, current, 0);
+		return retval;
+	}
+
 	install_exec_creds(bprm);
  	current->flags &= ~PF_FORKNOEXEC;
 
@@ -352,13 +359,6 @@ beyond_if:
 		return retval;
 	}
 
-	retval = setup_arg_pages(bprm, STACK_TOP, EXSTACK_DEFAULT);
-	if (retval < 0) { 
-		/* Someone check-me: is this error path enough? */ 
-		send_sig(SIGKILL, current, 0); 
-		return retval;
-	}
-
 	current->mm->start_stack =
 		(unsigned long) create_aout_tables((char __user *) bprm->p, bprm);
 #ifdef __alpha__
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index bcb884e2d613..07d096c49920 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1421,7 +1421,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 	for (i = 1; i < view->n; ++i) {
 		const struct user_regset *regset = &view->regsets[i];
 		do_thread_regset_writeback(t->task, regset);
-		if (regset->core_note_type &&
+		if (regset->core_note_type && regset->get &&
 		    (!regset->active || regset->active(t->task, regset))) {
 			int ret;
 			size_t size = regset->n * regset->size;
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 98f6bf10bbd4..0436c12da8c2 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -583,7 +583,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
 	struct btrfs_path *path;
 	struct btrfs_key info_key = { 0 };
 	struct btrfs_delayed_ref_root *delayed_refs = NULL;
-	struct btrfs_delayed_ref_head *head = NULL;
+	struct btrfs_delayed_ref_head *head;
 	int info_level = 0;
 	int ret;
 	struct list_head prefs_delayed;
@@ -607,6 +607,8 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
 	 * at a specified point in time
 	 */
 again:
+	head = NULL;
+
 	ret = btrfs_search_slot(trans, fs_info->extent_root, &key, path, 0, 0);
 	if (ret < 0)
 		goto out;
@@ -635,8 +637,10 @@ again:
 			goto again;
 		}
 		ret = __add_delayed_refs(head, seq, &info_key, &prefs_delayed);
-		if (ret)
+		if (ret) {
+			spin_unlock(&delayed_refs->lock);
 			goto out;
+		}
 	}
 	spin_unlock(&delayed_refs->lock);
 
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index 2373b39a132b..22db04550f6a 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -305,7 +305,7 @@ again:
 
 	spin_lock(&fs_info->reada_lock);
 	ret = radix_tree_insert(&dev->reada_zones,
-				(unsigned long)zone->end >> PAGE_CACHE_SHIFT,
+				(unsigned long)(zone->end >> PAGE_CACHE_SHIFT),
 				zone);
 	spin_unlock(&fs_info->reada_lock);
 
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 63a196b97d50..bc7e24420ac0 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -584,10 +584,26 @@ cifs_lookup(struct inode *parent_dir_inode, struct dentry *direntry,
 			 * If either that or op not supported returned, follow
 			 * the normal lookup.
 			 */
-			if ((rc == 0) || (rc == -ENOENT))
+			switch (rc) {
+			case 0:
+				/*
+				 * The server may allow us to open things like
+				 * FIFOs, but the client isn't set up to deal
+				 * with that. If it's not a regular file, just
+				 * close it and proceed as if it were a normal
+				 * lookup.
+				 */
+				if (newInode && !S_ISREG(newInode->i_mode)) {
+					CIFSSMBClose(xid, pTcon, fileHandle);
+					break;
+				}
+			case -ENOENT:
 				posix_open = true;
-			else if ((rc == -EINVAL) || (rc != -EOPNOTSUPP))
+			case -EOPNOTSUPP:
+				break;
+			default:
 				pTcon->broken_posix_open = true;
+			}
 		}
 		if (!posix_open)
 			rc = cifs_get_inode_info_unix(&newInode, full_path,
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a5f54b7d9822..745da3d0653e 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -534,6 +534,11 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
 	if (fattr->cf_cifsattrs & ATTR_DIRECTORY) {
 		fattr->cf_mode = S_IFDIR | cifs_sb->mnt_dir_mode;
 		fattr->cf_dtype = DT_DIR;
+		/*
+		 * Server can return wrong NumberOfLinks value for directories
+		 * when Unix extensions are disabled - fake it.
+		 */
+		fattr->cf_nlink = 2;
 	} else {
 		fattr->cf_mode = S_IFREG | cifs_sb->mnt_file_mode;
 		fattr->cf_dtype = DT_REG;
@@ -541,9 +546,9 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
 		/* clear write bits if ATTR_READONLY is set */
 		if (fattr->cf_cifsattrs & ATTR_READONLY)
 			fattr->cf_mode &= ~(S_IWUGO);
-	}
 
-	fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
+		fattr->cf_nlink = le32_to_cpu(info->NumberOfLinks);
+	}
 
 	fattr->cf_uid = cifs_sb->mnt_uid;
 	fattr->cf_gid = cifs_sb->mnt_gid;
@@ -1322,7 +1327,6 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, umode_t mode)
 			}
 /*BB check (cifs_sb->mnt_cifs_flags & CIFS_MOUNT_SET_UID ) to see if need
 	to set uid/gid */
-			inc_nlink(inode);
 
 			cifs_unix_basic_to_fattr(&fattr, pInfo, cifs_sb);
 			cifs_fill_uniqueid(inode->i_sb, &fattr);
@@ -1355,7 +1359,6 @@ mkdir_retry_old:
 		d_drop(direntry);
 	} else {
 mkdir_get_info:
-		inc_nlink(inode);
 		if (pTcon->unix_ext)
 			rc = cifs_get_inode_info_unix(&newinode, full_path,
 						      inode->i_sb, xid);
@@ -1436,6 +1439,11 @@ mkdir_get_info:
 		}
 	}
 mkdir_out:
+	/*
+	 * Force revalidate to get parent dir info when needed since cached
+	 * attributes are invalid now.
+	 */
+	CIFS_I(inode)->time = 0;
 	kfree(full_path);
 	FreeXid(xid);
 	cifs_put_tlink(tlink);
@@ -1475,7 +1483,6 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
 	cifs_put_tlink(tlink);
 
 	if (!rc) {
-		drop_nlink(inode);
 		spin_lock(&direntry->d_inode->i_lock);
 		i_size_write(direntry->d_inode, 0);
 		clear_nlink(direntry->d_inode);
@@ -1483,12 +1490,15 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
 	}
 
 	cifsInode = CIFS_I(direntry->d_inode);
-	cifsInode->time = 0;	/* force revalidate to go get info when
-				   needed */
+	/* force revalidate to go get info when needed */
+	cifsInode->time = 0;
 
 	cifsInode = CIFS_I(inode);
-	cifsInode->time = 0;	/* force revalidate to get parent dir info
-				   since cached search results now invalid */
+	/*
+	 * Force revalidate to get parent dir info when needed since cached
+	 * attributes are invalid now.
+	 */
+	cifsInode->time = 0;
 
 	direntry->d_inode->i_ctime = inode->i_ctime = inode->i_mtime =
 		current_fs_time(inode->i_sb);
diff --git a/fs/dcache.c b/fs/dcache.c
index fe19ac13f75f..bcbdb33fcc20 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -104,7 +104,7 @@ static unsigned int d_hash_shift __read_mostly;
 
 static struct hlist_bl_head *dentry_hashtable __read_mostly;
 
-static inline struct hlist_bl_head *d_hash(struct dentry *parent,
+static inline struct hlist_bl_head *d_hash(const struct dentry *parent,
 					unsigned long hash)
 {
 	hash += ((unsigned long) parent ^ GOLDEN_RATIO_PRIME) / L1_CACHE_BYTES;
@@ -137,6 +137,26 @@ int proc_nr_dentry(ctl_table *table, int write, void __user *buffer,
 }
 #endif
 
+/*
+ * Compare 2 name strings, return 0 if they match, otherwise non-zero.
+ * The strings are both count bytes long, and count is non-zero.
+ */
+static inline int dentry_cmp(const unsigned char *cs, size_t scount,
+				const unsigned char *ct, size_t tcount)
+{
+	if (scount != tcount)
+		return 1;
+
+	do {
+		if (*cs != *ct)
+			return 1;
+		cs++;
+		ct++;
+		tcount--;
+	} while (tcount);
+	return 0;
+}
+
 static void __d_free(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
@@ -1717,8 +1737,9 @@ EXPORT_SYMBOL(d_add_ci);
  * child is looked up. Thus, an interlocking stepping of sequence lock checks
  * is formed, giving integrity down the path walk.
  */
-struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name,
-				unsigned *seq, struct inode **inode)
+struct dentry *__d_lookup_rcu(const struct dentry *parent,
+				const struct qstr *name,
+				unsigned *seqp, struct inode **inode)
 {
 	unsigned int len = name->len;
 	unsigned int hash = name->hash;
@@ -1748,6 +1769,7 @@ struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name,
 	 * See Documentation/filesystems/path-lookup.txt for more details.
 	 */
 	hlist_bl_for_each_entry_rcu(dentry, node, b, d_hash) {
+		unsigned seq;
 		struct inode *i;
 		const char *tname;
 		int tlen;
@@ -1756,7 +1778,7 @@ struct dentry *__d_lookup_rcu(struct dentry *parent, struct qstr *name,
 			continue;
 
 seqretry:
-		*seq = read_seqcount_begin(&dentry->d_seq);
+		seq = read_seqcount_begin(&dentry->d_seq);
 		if (dentry->d_parent != parent)
 			continue;
 		if (d_unhashed(dentry))
@@ -1771,7 +1793,7 @@ seqretry:
 		 * edge of memory when walking. If we could load this
 		 * atomically some other way, we could drop this check.
 		 */
-		if (read_seqcount_retry(&dentry->d_seq, *seq))
+		if (read_seqcount_retry(&dentry->d_seq, seq))
 			goto seqretry;
 		if (unlikely(parent->d_flags & DCACHE_OP_COMPARE)) {
 			if (parent->d_op->d_compare(parent, *inode,
@@ -1788,6 +1810,7 @@ seqretry:
 		 * order to do anything useful with the returned dentry
 		 * anyway.
 		 */
+		*seqp = seq;
 		*inode = i;
 		return dentry;
 	}
diff --git a/fs/exec.c b/fs/exec.c
index 92ce83a11e90..153dee14fe55 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1915,7 +1915,6 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
 {
 	struct task_struct *tsk = current;
 	struct mm_struct *mm = tsk->mm;
-	struct completion *vfork_done;
 	int core_waiters = -EBUSY;
 
 	init_completion(&core_state->startup);
@@ -1927,22 +1926,9 @@ static int coredump_wait(int exit_code, struct core_state *core_state)
 		core_waiters = zap_threads(tsk, mm, core_state, exit_code);
 	up_write(&mm->mmap_sem);
 
-	if (unlikely(core_waiters < 0))
-		goto fail;
-
-	/*
-	 * Make sure nobody is waiting for us to release the VM,
-	 * otherwise we can deadlock when we wait on each other
-	 */
-	vfork_done = tsk->vfork_done;
-	if (vfork_done) {
-		tsk->vfork_done = NULL;
-		complete(vfork_done);
-	}
-
-	if (core_waiters)
+	if (core_waiters > 0)
 		wait_for_completion(&core_state->startup);
-fail:
+
 	return core_waiters;
 }
 
diff --git a/fs/namei.c b/fs/namei.c
index a780ea515c47..e2ba62820a0f 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1374,6 +1374,34 @@ static inline int can_lookup(struct inode *inode)
 	return 1;
 }
 
+unsigned int full_name_hash(const unsigned char *name, unsigned int len)
+{
+	unsigned long hash = init_name_hash();
+	while (len--)
+		hash = partial_name_hash(*name++, hash);
+	return end_name_hash(hash);
+}
+EXPORT_SYMBOL(full_name_hash);
+
+/*
+ * We know there's a real path component here of at least
+ * one character.
+ */
+static inline unsigned long hash_name(const char *name, unsigned int *hashp)
+{
+	unsigned long hash = init_name_hash();
+	unsigned long len = 0, c;
+
+	c = (unsigned char)*name;
+	do {
+		len++;
+		hash = partial_name_hash(c, hash);
+		c = (unsigned char)name[len];
+	} while (c && c != '/');
+	*hashp = end_name_hash(hash);
+	return len;
+}
+
 /*
  * Name resolution.
  * This is the basic name resolution function, turning a pathname into
@@ -1394,31 +1422,22 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 
 	/* At this point we know we have a real path component. */
 	for(;;) {
-		unsigned long hash;
 		struct qstr this;
-		unsigned int c;
+		long len;
 		int type;
 
 		err = may_lookup(nd);
  		if (err)
 			break;
 
+		len = hash_name(name, &this.hash);
 		this.name = name;
-		c = *(const unsigned char *)name;
-
-		hash = init_name_hash();
-		do {
-			name++;
-			hash = partial_name_hash(c, hash);
-			c = *(const unsigned char *)name;
-		} while (c && (c != '/'));
-		this.len = name - (const char *) this.name;
-		this.hash = end_name_hash(hash);
+		this.len = len;
 
 		type = LAST_NORM;
-		if (this.name[0] == '.') switch (this.len) {
+		if (name[0] == '.') switch (len) {
 			case 2:
-				if (this.name[1] == '.') {
+				if (name[1] == '.') {
 					type = LAST_DOTDOT;
 					nd->flags |= LOOKUP_JUMPED;
 				}
@@ -1437,12 +1456,18 @@ static int link_path_walk(const char *name, struct nameidata *nd)
 			}
 		}
 
-		/* remove trailing slashes? */
-		if (!c)
+		if (!name[len])
 			goto last_component;
-		while (*++name == '/');
-		if (!*name)
+		/*
+		 * If it wasn't NUL, we know it was '/'. Skip that
+		 * slash, and continue until no more slashes.
+		 */
+		do {
+			len++;
+		} while (unlikely(name[len] == '/'));
+		if (!name[len])
 			goto last_component;
+		name += len;
 
 		err = walk_component(nd, &next, &this, type, LOOKUP_FOLLOW);
 		if (err < 0)
@@ -1775,24 +1800,21 @@ static struct dentry *lookup_hash(struct nameidata *nd)
 struct dentry *lookup_one_len(const char *name, struct dentry *base, int len)
 {
 	struct qstr this;
-	unsigned long hash;
 	unsigned int c;
 
 	WARN_ON_ONCE(!mutex_is_locked(&base->d_inode->i_mutex));
 
 	this.name = name;
 	this.len = len;
+	this.hash = full_name_hash(name, len);
 	if (!len)
 		return ERR_PTR(-EACCES);
 
-	hash = init_name_hash();
 	while (len--) {
 		c = *(const unsigned char *)name++;
 		if (c == '/' || c == '\0')
 			return ERR_PTR(-EACCES);
-		hash = partial_name_hash(c, hash);
 	}
-	this.hash = end_name_hash(hash);
 	/*
 	 * See if the low-level filesystem might want
 	 * to use its own hash..