Merge branch 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs

Pull more vfs updates from Al Viro:
 "Assorted VFS fixes and related cleanups (IMO the most interesting in
  that part are f_path-related things and Eric's descriptor-related
  stuff).  UFS regression fixes (it got broken last cycle).  9P fixes.
  fs-cache series, DAX patches, Jan's file_remove_suid() work"

[ I'd say this is much more than "fixes and related cleanups".  The
  file_table locking rule change by Eric Dumazet is a rather big and
  fundamental update even if the patch isn't huge.   - Linus ]

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs: (49 commits)
  9p: cope with bogus responses from server in p9_client_{read,write}
  p9_client_write(): avoid double p9_free_req()
  9p: forgetting to cancel request on interrupted zero-copy RPC
  dax: bdev_direct_access() may sleep
  block: Add support for DAX reads/writes to block devices
  dax: Use copy_from_iter_nocache
  dax: Add block size note to documentation
  fs/file.c: __fget() and dup2() atomicity rules
  fs/file.c: don't acquire files->file_lock in fd_install()
  fs:super:get_anon_bdev: fix race condition could cause dev exceed its upper limitation
  vfs: avoid creation of inode number 0 in get_next_ino
  namei: make set_root_rcu() return void
  make simple_positive() public
  ufs: use dir_pages instead of ufs_dir_pages()
  pagemap.h: move dir_pages() over there
  remove the pointless include of lglock.h
  fs: cleanup slight list_entry abuse
  xfs: Correctly lock inode when removing suid and file capabilities
  fs: Call security_ops->inode_killpriv on truncate
  fs: Provide function telling whether file_remove_privs() will do anything
  ...

1 files changed, 46 insertions, 20 deletions

diff --git a/fs/inode.c b/fs/inode.c
index 069721f0cc0e..d30640f7a193 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -841,7 +841,11 @@ unsigned int get_next_ino(void)
 	}
 #endif
 
-	*p = ++res;
+	res++;
+	/* get_next_ino should not provide a 0 inode number */
+	if (unlikely(!res))
+		res++;
+	*p = res;
 	put_cpu_var(last_ino);
 	return res;
 }
@@ -1674,7 +1678,31 @@ int should_remove_suid(struct dentry *dentry)
 }
 EXPORT_SYMBOL(should_remove_suid);
 
-static int __remove_suid(struct dentry *dentry, int kill)
+/*
+ * Return mask of changes for notify_change() that need to be done as a
+ * response to write or truncate. Return 0 if nothing has to be changed.
+ * Negative value on error (change should be denied).
+ */
+int dentry_needs_remove_privs(struct dentry *dentry)
+{
+	struct inode *inode = d_inode(dentry);
+	int mask = 0;
+	int ret;
+
+	if (IS_NOSEC(inode))
+		return 0;
+
+	mask = should_remove_suid(dentry);
+	ret = security_inode_need_killpriv(dentry);
+	if (ret < 0)
+		return ret;
+	if (ret)
+		mask |= ATTR_KILL_PRIV;
+	return mask;
+}
+EXPORT_SYMBOL(dentry_needs_remove_privs);
+
+static int __remove_privs(struct dentry *dentry, int kill)
 {
 	struct iattr newattrs;
 
@@ -1686,33 +1714,32 @@ static int __remove_suid(struct dentry *dentry, int kill)
 	return notify_change(dentry, &newattrs, NULL);
 }
 
-int file_remove_suid(struct file *file)
+/*
+ * Remove special file priviledges (suid, capabilities) when file is written
+ * to or truncated.
+ */
+int file_remove_privs(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry;
 	struct inode *inode = d_inode(dentry);
-	int killsuid;
-	int killpriv;
+	int kill;
 	int error = 0;
 
 	/* Fast path for nothing security related */
 	if (IS_NOSEC(inode))
 		return 0;
 
-	killsuid = should_remove_suid(dentry);
-	killpriv = security_inode_need_killpriv(dentry);
-
-	if (killpriv < 0)
-		return killpriv;
-	if (killpriv)
-		error = security_inode_killpriv(dentry);
-	if (!error && killsuid)
-		error = __remove_suid(dentry, killsuid);
-	if (!error && (inode->i_sb->s_flags & MS_NOSEC))
-		inode->i_flags |= S_NOSEC;
+	kill = file_needs_remove_privs(file);
+	if (kill < 0)
+		return kill;
+	if (kill)
+		error = __remove_privs(dentry, kill);
+	if (!error)
+		inode_has_no_xattr(inode);
 
 	return error;
 }
-EXPORT_SYMBOL(file_remove_suid);
+EXPORT_SYMBOL(file_remove_privs);
 
 /**
  *	file_update_time	-	update mtime and ctime time
@@ -1967,9 +1994,8 @@ EXPORT_SYMBOL(inode_dio_wait);
  * inode is being instantiated).  The reason for the cmpxchg() loop
  * --- which wouldn't be necessary if all code paths which modify
  * i_flags actually followed this rule, is that there is at least one
- * code path which doesn't today --- for example,
- * __generic_file_aio_write() calls file_remove_suid() without holding
- * i_mutex --- so we use cmpxchg() out of an abundance of caution.
+ * code path which doesn't today so we use cmpxchg() out of an abundance
+ * of caution.
  *
  * In the long run, i_mutex is overkill, and we should probably look
  * at using the i_lock spinlock to protect i_flags, and then make sure