Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Conflicts were easy to resolve using immediate context mostly,
except the cls_u32.c one where I simply too the entire HEAD
chunk.

Signed-off-by: David S. Miller <davem@davemloft.net>

fs/afs/cell.c

@@ -514,6 +514,8 @@ static int afs_alloc_anon_key(struct afs_cell *cell)
  */
 static int afs_activate_cell(struct afs_net *net, struct afs_cell *cell)
 {
+	struct hlist_node **p;
+	struct afs_cell *pcell;
 	int ret;
 
 	if (!cell->anonymous_key) {
@@ -534,7 +536,18 @@ static int afs_activate_cell(struct afs_net *net, struct afs_cell *cell)
 		return ret;
 
 	mutex_lock(&net->proc_cells_lock);
-	list_add_tail(&cell->proc_link, &net->proc_cells);
+	for (p = &net->proc_cells.first; *p; p = &(*p)->next) {
+		pcell = hlist_entry(*p, struct afs_cell, proc_link);
+		if (strcmp(cell->name, pcell->name) < 0)
+			break;
+	}
+
+	cell->proc_link.pprev = p;
+	cell->proc_link.next = *p;
+	rcu_assign_pointer(*p, &cell->proc_link.next);
+	if (cell->proc_link.next)
+		cell->proc_link.next->pprev = &cell->proc_link.next;
+
 	afs_dynroot_mkdir(net, cell);
 	mutex_unlock(&net->proc_cells_lock);
 	return 0;
@@ -550,7 +563,7 @@ static void afs_deactivate_cell(struct afs_net *net, struct afs_cell *cell)
 	afs_proc_cell_remove(cell);
 
 	mutex_lock(&net->proc_cells_lock);
-	list_del_init(&cell->proc_link);
+	hlist_del_rcu(&cell->proc_link);
 	afs_dynroot_rmdir(net, cell);
 	mutex_unlock(&net->proc_cells_lock);
 

fs/afs/dynroot.c

@@ -265,7 +265,7 @@ int afs_dynroot_populate(struct super_block *sb)
 		return -ERESTARTSYS;
 
 	net->dynroot_sb = sb;
-	list_for_each_entry(cell, &net->proc_cells, proc_link) {
+	hlist_for_each_entry(cell, &net->proc_cells, proc_link) {
 		ret = afs_dynroot_mkdir(net, cell);
 		if (ret < 0)
 			goto error;

fs/afs/internal.h

@@ -244,7 +244,7 @@ struct afs_net {
 	seqlock_t		cells_lock;
 
 	struct mutex		proc_cells_lock;
-	struct list_head	proc_cells;
+	struct hlist_head	proc_cells;
 
 	/* Known servers.  Theoretically each fileserver can only be in one
 	 * cell, but in practice, people create aliases and subsets and there's
@@ -322,7 +322,7 @@ struct afs_cell {
 	struct afs_net		*net;
 	struct key		*anonymous_key;	/* anonymous user key for this cell */
 	struct work_struct	manager;	/* Manager for init/deinit/dns */
-	struct list_head	proc_link;	/* /proc cell list link */
+	struct hlist_node	proc_link;	/* /proc cell list link */
 #ifdef CONFIG_AFS_FSCACHE
 	struct fscache_cookie	*cache;		/* caching cookie */
 #endif

fs/afs/main.c

@@ -87,7 +87,7 @@ static int __net_init afs_net_init(struct net *net_ns)
 	timer_setup(&net->cells_timer, afs_cells_timer, 0);
 
 	mutex_init(&net->proc_cells_lock);
-	INIT_LIST_HEAD(&net->proc_cells);
+	INIT_HLIST_HEAD(&net->proc_cells);
 
 	seqlock_init(&net->fs_lock);
 	net->fs_servers = RB_ROOT;

fs/afs/proc.c

@@ -33,9 +33,8 @@ static inline struct afs_net *afs_seq2net_single(struct seq_file *m)
 static int afs_proc_cells_show(struct seq_file *m, void *v)
 {
 	struct afs_cell *cell = list_entry(v, struct afs_cell, proc_link);
-	struct afs_net *net = afs_seq2net(m);
 
-	if (v == &net->proc_cells) {
+	if (v == SEQ_START_TOKEN) {
 		/* display header on line 1 */
 		seq_puts(m, "USE NAME\n");
 		return 0;
@@ -50,12 +49,12 @@ static void *afs_proc_cells_start(struct seq_file *m, loff_t *_pos)
 	__acquires(rcu)
 {
 	rcu_read_lock();
-	return seq_list_start_head(&afs_seq2net(m)->proc_cells, *_pos);
+	return seq_hlist_start_head_rcu(&afs_seq2net(m)->proc_cells, *_pos);
 }
 
 static void *afs_proc_cells_next(struct seq_file *m, void *v, loff_t *pos)
 {
-	return seq_list_next(v, &afs_seq2net(m)->proc_cells, pos);
+	return seq_hlist_next_rcu(v, &afs_seq2net(m)->proc_cells, pos);
 }
 
 static void afs_proc_cells_stop(struct seq_file *m, void *v)

fs/afs/server.c

@@ -199,9 +199,11 @@ static struct afs_server *afs_install_server(struct afs_net *net,
 
 	write_sequnlock(&net->fs_addr_lock);
 	ret = 0;
+	goto out;
 
 exists:
 	afs_get_server(server);
+out:
 	write_sequnlock(&net->fs_lock);
 	return server;
 }

fs/gfs2/bmap.c

@@ -975,6 +975,10 @@ static void gfs2_iomap_journaled_page_done(struct inode *inode, loff_t pos,
 {
 	struct gfs2_inode *ip = GFS2_I(inode);
 
+	if (!page_has_buffers(page)) {
+		create_empty_buffers(page, inode->i_sb->s_blocksize,
+				     (1 << BH_Dirty)|(1 << BH_Uptodate));
+	}
 	gfs2_page_add_databufs(ip, page, offset_in_page(pos), copied);
 }
 

fs/xfs/xfs_reflink.c

@@ -1220,35 +1220,92 @@ retry:
 	return 0;
 }
 
+/* Unlock both inodes after they've been prepped for a range clone. */
+STATIC void
+xfs_reflink_remap_unlock(
+	struct file		*file_in,
+	struct file		*file_out)
+{
+	struct inode		*inode_in = file_inode(file_in);
+	struct xfs_inode	*src = XFS_I(inode_in);
+	struct inode		*inode_out = file_inode(file_out);
+	struct xfs_inode	*dest = XFS_I(inode_out);
+	bool			same_inode = (inode_in == inode_out);
+
+	xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
+	if (!same_inode)
+		xfs_iunlock(src, XFS_MMAPLOCK_SHARED);
+	inode_unlock(inode_out);
+	if (!same_inode)
+		inode_unlock_shared(inode_in);
+}
+
 /*
- * Link a range of blocks from one file to another.
+ * If we're reflinking to a point past the destination file's EOF, we must
+ * zero any speculative post-EOF preallocations that sit between the old EOF
+ * and the destination file offset.
  */
-int
-xfs_reflink_remap_range(
+static int
+xfs_reflink_zero_posteof(
+	struct xfs_inode	*ip,
+	loff_t			pos)
+{
+	loff_t			isize = i_size_read(VFS_I(ip));
+
+	if (pos <= isize)
+		return 0;
+
+	trace_xfs_zero_eof(ip, isize, pos - isize);
+	return iomap_zero_range(VFS_I(ip), isize, pos - isize, NULL,
+			&xfs_iomap_ops);
+}
+
+/*
+ * Prepare two files for range cloning.  Upon a successful return both inodes
+ * will have the iolock and mmaplock held, the page cache of the out file will
+ * be truncated, and any leases on the out file will have been broken.  This
+ * function borrows heavily from xfs_file_aio_write_checks.
+ *
+ * The VFS allows partial EOF blocks to "match" for dedupe even though it hasn't
+ * checked that the bytes beyond EOF physically match. Hence we cannot use the
+ * EOF block in the source dedupe range because it's not a complete block match,
+ * hence can introduce a corruption into the file that has it's block replaced.
+ *
+ * In similar fashion, the VFS file cloning also allows partial EOF blocks to be
+ * "block aligned" for the purposes of cloning entire files.  However, if the
+ * source file range includes the EOF block and it lands within the existing EOF
+ * of the destination file, then we can expose stale data from beyond the source
+ * file EOF in the destination file.
+ *
+ * XFS doesn't support partial block sharing, so in both cases we have check
+ * these cases ourselves. For dedupe, we can simply round the length to dedupe
+ * down to the previous whole block and ignore the partial EOF block. While this
+ * means we can't dedupe the last block of a file, this is an acceptible
+ * tradeoff for simplicity on implementation.
+ *
+ * For cloning, we want to share the partial EOF block if it is also the new EOF
+ * block of the destination file. If the partial EOF block lies inside the
+ * existing destination EOF, then we have to abort the clone to avoid exposing
+ * stale data in the destination file. Hence we reject these clone attempts with
+ * -EINVAL in this case.
+ */
+STATIC int
+xfs_reflink_remap_prep(
 	struct file		*file_in,
 	loff_t			pos_in,
 	struct file		*file_out,
 	loff_t			pos_out,
-	u64			len,
+	u64			*len,
 	bool			is_dedupe)
 {
 	struct inode		*inode_in = file_inode(file_in);
 	struct xfs_inode	*src = XFS_I(inode_in);
 	struct inode		*inode_out = file_inode(file_out);
 	struct xfs_inode	*dest = XFS_I(inode_out);
-	struct xfs_mount	*mp = src->i_mount;
 	bool			same_inode = (inode_in == inode_out);
-	xfs_fileoff_t		sfsbno, dfsbno;
-	xfs_filblks_t		fsblen;
-	xfs_extlen_t		cowextsize;
+	u64			blkmask = i_blocksize(inode_in) - 1;
 	ssize_t			ret;
 
-	if (!xfs_sb_version_hasreflink(&mp->m_sb))
-		return -EOPNOTSUPP;
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
 	/* Lock both files against IO */
 	ret = xfs_iolock_two_inodes_and_break_layout(inode_in, inode_out);
 	if (ret)
@@ -1270,33 +1327,115 @@ xfs_reflink_remap_range(
 		goto out_unlock;
 
 	ret = vfs_clone_file_prep_inodes(inode_in, pos_in, inode_out, pos_out,
-			&len, is_dedupe);
+			len, is_dedupe);
 	if (ret <= 0)
 		goto out_unlock;
 
+	/*
+	 * If the dedupe data matches, chop off the partial EOF block
+	 * from the source file so we don't try to dedupe the partial
+	 * EOF block.
+	 */
+	if (is_dedupe) {
+		*len &= ~blkmask;
+	} else if (*len & blkmask) {
+		/*
+		 * The user is attempting to share a partial EOF block,
+		 * if it's inside the destination EOF then reject it.
+		 */
+		if (pos_out + *len < i_size_read(inode_out)) {
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+	}
+
 	/* Attach dquots to dest inode before changing block map */
 	ret = xfs_qm_dqattach(dest);
 	if (ret)
 		goto out_unlock;
 
-	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
-
 	/*
-	 * Clear out post-eof preallocations because we don't have page cache
-	 * backing the delayed allocations and they'll never get freed on
-	 * their own.
+	 * Zero existing post-eof speculative preallocations in the destination
+	 * file.
 	 */
-	if (xfs_can_free_eofblocks(dest, true)) {
-		ret = xfs_free_eofblocks(dest);
-		if (ret)
-			goto out_unlock;
-	}
+	ret = xfs_reflink_zero_posteof(dest, pos_out);
+	if (ret)
+		goto out_unlock;
 
 	/* Set flags and remap blocks. */
 	ret = xfs_reflink_set_inode_flag(src, dest);
 	if (ret)
 		goto out_unlock;
 
+	/* Zap any page cache for the destination file's range. */
+	truncate_inode_pages_range(&inode_out->i_data, pos_out,
+				   PAGE_ALIGN(pos_out + *len) - 1);
+
+	/* If we're altering the file contents... */
+	if (!is_dedupe) {
+		/*
+		 * ...update the timestamps (which will grab the ilock again
+		 * from xfs_fs_dirty_inode, so we have to call it before we
+		 * take the ilock).
+		 */
+		if (!(file_out->f_mode & FMODE_NOCMTIME)) {
+			ret = file_update_time(file_out);
+			if (ret)
+				goto out_unlock;
+		}
+
+		/*
+		 * ...clear the security bits if the process is not being run
+		 * by root.  This keeps people from modifying setuid and setgid
+		 * binaries.
+		 */
+		ret = file_remove_privs(file_out);
+		if (ret)
+			goto out_unlock;
+	}
+
+	return 1;
+out_unlock:
+	xfs_reflink_remap_unlock(file_in, file_out);
+	return ret;
+}
+
+/*
+ * Link a range of blocks from one file to another.
+ */
+int
+xfs_reflink_remap_range(
+	struct file		*file_in,
+	loff_t			pos_in,
+	struct file		*file_out,
+	loff_t			pos_out,
+	u64			len,
+	bool			is_dedupe)
+{
+	struct inode		*inode_in = file_inode(file_in);
+	struct xfs_inode	*src = XFS_I(inode_in);
+	struct inode		*inode_out = file_inode(file_out);
+	struct xfs_inode	*dest = XFS_I(inode_out);
+	struct xfs_mount	*mp = src->i_mount;
+	xfs_fileoff_t		sfsbno, dfsbno;
+	xfs_filblks_t		fsblen;
+	xfs_extlen_t		cowextsize;
+	ssize_t			ret;
+
+	if (!xfs_sb_version_hasreflink(&mp->m_sb))
+		return -EOPNOTSUPP;
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
+
+	/* Prepare and then clone file data. */
+	ret = xfs_reflink_remap_prep(file_in, pos_in, file_out, pos_out,
+			&len, is_dedupe);
+	if (ret <= 0)
+		return ret;
+
+	trace_xfs_reflink_remap_range(src, pos_in, len, dest, pos_out);
+
 	dfsbno = XFS_B_TO_FSBT(mp, pos_out);
 	sfsbno = XFS_B_TO_FSBT(mp, pos_in);
 	fsblen = XFS_B_TO_FSB(mp, len);
@@ -1305,10 +1444,6 @@ xfs_reflink_remap_range(
 	if (ret)
 		goto out_unlock;
 
-	/* Zap any page cache for the destination file's range. */
-	truncate_inode_pages_range(&inode_out->i_data, pos_out,
-				   PAGE_ALIGN(pos_out + len) - 1);
-
 	/*
 	 * Carry the cowextsize hint from src to dest if we're sharing the
 	 * entire source file to the entire destination file, the source file
@@ -1325,12 +1460,7 @@ xfs_reflink_remap_range(
 			is_dedupe);
 
 out_unlock:
-	xfs_iunlock(dest, XFS_MMAPLOCK_EXCL);
-	if (!same_inode)
-		xfs_iunlock(src, XFS_MMAPLOCK_SHARED);
-	inode_unlock(inode_out);
-	if (!same_inode)
-		inode_unlock_shared(inode_in);
+	xfs_reflink_remap_unlock(file_in, file_out);
 	if (ret)
 		trace_xfs_reflink_remap_range_error(dest, ret, _RET_IP_);
 	return ret;