xfs: current queue for 3.8

index 0ca1f0b..55bbe98 100644
@@ -1155,6 +1155,8 @@ xfs_attr_leaf_get(xfs_da_args_t *args)
 	struct xfs_buf *bp;
 	int error;
 
+	trace_xfs_attr_leaf_get(args);
+
 	args->blkno = 0;
 	error = xfs_da_read_buf(args->trans, args->dp, args->blkno, -1, &bp,
 					     XFS_ATTR_FORK);

@@ -1185,6 +1187,8 @@ xfs_attr_leaf_list(xfs_attr_list_context_t *context)
 	int error;
 	struct xfs_buf *bp;
 
+	trace_xfs_attr_leaf_list(context);
+
 	context->cursor->blkno = 0;
 	error = xfs_da_read_buf(NULL, context->dp, 0, -1, &bp, XFS_ATTR_FORK);
 	if (error)

@@ -1653,6 +1657,8 @@ xfs_attr_fillstate(xfs_da_state_t *state)
 	xfs_da_state_blk_t *blk;
 	int level;
 
+	trace_xfs_attr_fillstate(state->args);
+
 	/*
 	 * Roll down the "path" in the state structure, storing the on-disk
 	 * block number for those buffers in the "path".

@@ -1699,6 +1705,8 @@ xfs_attr_refillstate(xfs_da_state_t *state)
 	xfs_da_state_blk_t *blk;
 	int level, error;
 
+	trace_xfs_attr_refillstate(state->args);
+
 	/*
 	 * Roll down the "path" in the state structure, storing the on-disk
 	 * block number for those buffers in the "path".

@@ -1755,6 +1763,8 @@ xfs_attr_node_get(xfs_da_args_t *args)
 	int error, retval;
 	int i;
 
+	trace_xfs_attr_node_get(args);
+
 	state = xfs_da_state_alloc();
 	state->args = args;
 	state->mp = args->dp->i_mount;

@@ -1804,6 +1814,8 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	int error, i;
 	struct xfs_buf *bp;
 
+	trace_xfs_attr_node_list(context);
+
 	cursor = context->cursor;
 	cursor->initted = 1;
 

@@ -1959,6 +1971,8 @@ xfs_attr_rmtval_get(xfs_da_args_t *args)
 	int nmap, error, tmp, valuelen, blkcnt, i;
 	xfs_dablk_t lblkno;
 
+	trace_xfs_attr_rmtval_get(args);
+
 	ASSERT(!(args->flags & ATTR_KERNOVAL));
 
 	mp = args->dp->i_mount;

@@ -2014,6 +2028,8 @@ xfs_attr_rmtval_set(xfs_da_args_t *args)
 	xfs_dablk_t lblkno;
 	int blkcnt, valuelen, nmap, error, tmp, committed;
 
+	trace_xfs_attr_rmtval_set(args);
+
 	dp = args->dp;
 	mp = dp->i_mount;
 	src = args->value;

@@ -2143,6 +2159,8 @@ xfs_attr_rmtval_remove(xfs_da_args_t *args)
 	xfs_dablk_t lblkno;
 	int valuelen, blkcnt, nmap, error, done, committed;
 
+	trace_xfs_attr_rmtval_remove(args);
+
 	mp = args->dp->i_mount;
 
 	/*

index 70eec18..4bfc732 100644
@@ -57,7 +57,8 @@ STATIC int xfs_attr_leaf_create(xfs_da_args_t *args, xfs_dablk_t which_block,
 				struct xfs_buf **bpp);
 STATIC int xfs_attr_leaf_add_work(struct xfs_buf *leaf_buffer,
 				  xfs_da_args_t *args, int freemap_index);
-STATIC void xfs_attr_leaf_compact(xfs_trans_t *tp, struct xfs_buf *leaf_buffer);
+STATIC void xfs_attr_leaf_compact(struct xfs_da_args *args,
+				  struct xfs_buf *leaf_buffer);
 STATIC void xfs_attr_leaf_rebalance(xfs_da_state_t *state,
 						   xfs_da_state_blk_t *blk1,
 						   xfs_da_state_blk_t *blk2);

@@ -1071,7 +1072,7 @@ xfs_attr_leaf_add(
 	 * Compact the entries to coalesce free space.
 	 * This may change the hdr->count via dropping INCOMPLETE entries.
 	 */
-	xfs_attr_leaf_compact(args->trans, bp);
+	xfs_attr_leaf_compact(args, bp);
 
 	/*
 	 * After compaction, the block is guaranteed to have only one

@@ -1102,6 +1103,8 @@ xfs_attr_leaf_add_work(
 	xfs_mount_t *mp;
 	int tmp, i;
 
+	trace_xfs_attr_leaf_add_work(args);
+
 	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	hdr = &leaf->hdr;

@@ -1214,15 +1217,17 @@ xfs_attr_leaf_add_work(
  */
 STATIC void
 xfs_attr_leaf_compact(
-	struct xfs_trans *trans,
-	struct xfs_buf	*bp)
+	struct xfs_da_args	*args,
+	struct xfs_buf		*bp)
 {
-	xfs_attr_leafblock_t *leaf_s, *leaf_d;
-	xfs_attr_leaf_hdr_t *hdr_s, *hdr_d;
-	xfs_mount_t *mp;
-	char *tmpbuffer;
+	xfs_attr_leafblock_t	*leaf_s, *leaf_d;
+	xfs_attr_leaf_hdr_t	*hdr_s, *hdr_d;
+	struct xfs_trans	*trans = args->trans;
+	struct xfs_mount	*mp = trans->t_mountp;
+	char			*tmpbuffer;
+
+	trace_xfs_attr_leaf_compact(args);
 
-	mp = trans->t_mountp;
 	tmpbuffer = kmem_alloc(XFS_LBSIZE(mp), KM_SLEEP);
 	ASSERT(tmpbuffer != NULL);
 	memcpy(tmpbuffer, bp->b_addr, XFS_LBSIZE(mp));

@@ -1345,9 +1350,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		max  = be16_to_cpu(hdr2->firstused)
 						- sizeof(xfs_attr_leaf_hdr_t);
 		max -= be16_to_cpu(hdr2->count) * sizeof(xfs_attr_leaf_entry_t);
-		if (space > max) {
-			xfs_attr_leaf_compact(args->trans, blk2->bp);
-		}
+		if (space > max)
+			xfs_attr_leaf_compact(args, blk2->bp);
 
 		/*
 		 * Move high entries from leaf1 to low end of leaf2.

@@ -1378,9 +1382,8 @@ xfs_attr_leaf_rebalance(xfs_da_state_t *state, xfs_da_state_blk_t *blk1,
 		max  = be16_to_cpu(hdr1->firstused)
 						- sizeof(xfs_attr_leaf_hdr_t);
 		max -= be16_to_cpu(hdr1->count) * sizeof(xfs_attr_leaf_entry_t);
-		if (space > max) {
-			xfs_attr_leaf_compact(args->trans, blk1->bp);
-		}
+		if (space > max)
+			xfs_attr_leaf_compact(args, blk1->bp);
 
 		/*
 		 * Move low entries from leaf2 to high end of leaf1.

@@ -1577,6 +1580,8 @@ xfs_attr_leaf_toosmall(xfs_da_state_t *state, int *action)
 	xfs_dablk_t blkno;
 	struct xfs_buf *bp;
 
+	trace_xfs_attr_leaf_toosmall(state->args);
+
 	/*
 	 * Check for the degenerate case of the block being over 50% full.
 	 * If so, it's not worth even looking to see if we might be able

@@ -1702,6 +1707,8 @@ xfs_attr_leaf_remove(
 	int tablesize, tmp, i;
 	xfs_mount_t *mp;
 
+	trace_xfs_attr_leaf_remove(args);
+
 	leaf = bp->b_addr;
 	ASSERT(leaf->hdr.info.magic == cpu_to_be16(XFS_ATTR_LEAF_MAGIC));
 	hdr = &leaf->hdr;

index 7bfb7dd..c62e7e6 100644
@@ -779,6 +779,8 @@ xfs_da_node_toosmall(xfs_da_state_t *state, int *action)
 	xfs_dablk_t blkno;
 	struct xfs_buf *bp;
 
+	trace_xfs_da_node_toosmall(state->args);
+
 	/*
 	 * Check for the degenerate case of the block being over 50% full.
 	 * If so, it's not worth even looking to see if we might be able

@@ -900,6 +902,8 @@ xfs_da_fixhashpath(xfs_da_state_t *state, xfs_da_state_path_t *path)
 	xfs_dahash_t lasthash=0;
 	int level, count;
 
+	trace_xfs_da_fixhashpath(state->args);
+
 	level = path->active-1;
 	blk = &path->blk[ level ];
 	switch (blk->magic) {

@@ -1417,6 +1421,8 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
 	xfs_dablk_t blkno=0;
 	int level, error;
 
+	trace_xfs_da_path_shift(state->args);
+
 	/*
 	 * Roll up the Btree looking for the first block where our
 	 * current index is not at the edge of the block.  Note that

98 lines not on this page · raw message

index b9b8646..b2c63a2 100644
@@ -315,8 +315,7 @@ xfs_swap_extents(
 	 * are safe.  We don't really care if non-io related
 	 * fields change.
 	 */
-
-	xfs_tosspages(ip, 0, -1, FI_REMAPF);
+	truncate_pagecache_range(VFS_I(ip), 0, -1);
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
 	if ((error = xfs_trans_reserve(tp, 0,

index 652b875..d49de3d 100644
@@ -25,18 +25,6 @@
  * note: all filemap functions return negative error codes. These
  * need to be inverted before returning to the xfs core functions.
  */
-void
-xfs_tosspages(
-	xfs_inode_t	*ip,
-	xfs_off_t	first,
-	xfs_off_t	last,
-	int		fiopt)
-{
-	/* can't toss partial tail pages, so mask them out */
-	last &= ~(PAGE_SIZE - 1);
-	truncate_inode_pages_range(VFS_I(ip)->i_mapping, first, last - 1);
-}
-
 int
 xfs_flushinval_pages(
 	xfs_inode_t	*ip,

index c2ddd7a..f7de578 100644
@@ -2118,7 +2118,6 @@ xfs_change_file_space(
 	xfs_fsize_t	fsize;
 	int		setprealloc;
 	xfs_off_t	startoffset;
-	xfs_off_t	llen;
 	xfs_trans_t	*tp;
 	struct iattr	iattr;
 	int		prealloc_type;

@@ -2139,12 +2138,30 @@ xfs_change_file_space(
 		return XFS_ERROR(EINVAL);
 	}
 
-	llen = bf->l_len > 0 ? bf->l_len - 1 : bf->l_len;
+	/*
+	 * length of <= 0 for resv/unresv/zero is invalid.  length for
+	 * alloc/free is ignored completely and we have no idea what userspace
+	 * might have set it to, so set it to zero to allow range
+	 * checks to pass.
+	 */
+	switch (cmd) {
+	case XFS_IOC_ZERO_RANGE:
+	case XFS_IOC_RESVSP:
+	case XFS_IOC_RESVSP64:
+	case XFS_IOC_UNRESVSP:
+	case XFS_IOC_UNRESVSP64:
+		if (bf->l_len <= 0)
+			return XFS_ERROR(EINVAL);
+		break;
+	default:
+		bf->l_len = 0;
+		break;
+	}
 
 	if (bf->l_start < 0 ||
 	    bf->l_start > mp->m_super->s_maxbytes ||
-	    bf->l_start + llen < 0 ||
-	    bf->l_start + llen > mp->m_super->s_maxbytes)
+	    bf->l_start + bf->l_len < 0 ||
+	    bf->l_start + bf->l_len >= mp->m_super->s_maxbytes)
 		return XFS_ERROR(EINVAL);
 
 	bf->l_whence = 0;

@@ -2169,7 +2186,8 @@ xfs_change_file_space(
 	switch (cmd) {
 	case XFS_IOC_ZERO_RANGE:
 		prealloc_type |= XFS_BMAPI_CONVERT;
-		xfs_tosspages(ip, startoffset, startoffset + bf->l_len, 0);
+		truncate_pagecache_range(VFS_I(ip), startoffset,
+			 round_down(startoffset + bf->l_len, PAGE_SIZE) - 1);
 		/* FALLTHRU */
 	case XFS_IOC_RESVSP:
 	case XFS_IOC_RESVSP64:

index 52fafc4..d48141d 100644
@@ -48,8 +48,6 @@ int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
 int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
 int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
 		int flags, struct attrlist_cursor_kern *cursor);
-void xfs_tosspages(struct xfs_inode *inode, xfs_off_t first,
-		xfs_off_t last, int fiopt);
 int xfs_flushinval_pages(struct xfs_inode *ip, xfs_off_t first,
 		xfs_off_t last, int fiopt);
 int xfs_flush_pages(struct xfs_inode *ip, xfs_off_t first,

index b9b8646..b2c63a2 100644
@@ -315,8 +315,7 @@ xfs_swap_extents(
 	 * are safe.  We don't really care if non-io related
 	 * fields change.
 	 */
-
-	xfs_tosspages(ip, 0, -1, FI_REMAPF);
+	truncate_pagecache_range(VFS_I(ip), 0, -1);
 
 	tp = xfs_trans_alloc(mp, XFS_TRANS_SWAPEXT);
 	if ((error = xfs_trans_reserve(tp, 0,

index 652b875..d49de3d 100644
@@ -25,18 +25,6 @@
  * note: all filemap functions return negative error codes. These
  * need to be inverted before returning to the xfs core functions.
  */
-void
-xfs_tosspages(
-	xfs_inode_t	*ip,
-	xfs_off_t	first,
-	xfs_off_t	last,
-	int		fiopt)
-{
-	/* can't toss partial tail pages, so mask them out */
-	last &= ~(PAGE_SIZE - 1);
-	truncate_inode_pages_range(VFS_I(ip)->i_mapping, first, last - 1);
-}
-
 int
 xfs_flushinval_pages(
 	xfs_inode_t	*ip,

index c2ddd7a..de3702a 100644
@@ -2118,7 +2118,7 @@ xfs_change_file_space(
 	xfs_fsize_t	fsize;
 	int		setprealloc;
 	xfs_off_t	startoffset;
-	xfs_off_t	llen;
+	xfs_off_t	end;
 	xfs_trans_t	*tp;
 	struct iattr	iattr;
 	int		prealloc_type;

@@ -2139,12 +2139,30 @@ xfs_change_file_space(
 		return XFS_ERROR(EINVAL);
 	}
 
-	llen = bf->l_len > 0 ? bf->l_len - 1 : bf->l_len;
+	/*
+	 * length of <= 0 for resv/unresv/zero is invalid.  length for
+	 * alloc/free is ignored completely and we have no idea what userspace
+	 * might have set it to, so set it to zero to allow range
+	 * checks to pass.
+	 */
+	switch (cmd) {
+	case XFS_IOC_ZERO_RANGE:
+	case XFS_IOC_RESVSP:
+	case XFS_IOC_RESVSP64:
+	case XFS_IOC_UNRESVSP:
+	case XFS_IOC_UNRESVSP64:
+		if (bf->l_len <= 0)
+			return XFS_ERROR(EINVAL);
+		break;
+	default:
+		bf->l_len = 0;
+		break;
+	}
 
 	if (bf->l_start < 0 ||
 	    bf->l_start > mp->m_super->s_maxbytes ||
-	    bf->l_start + llen < 0 ||
-	    bf->l_start + llen > mp->m_super->s_maxbytes)
+	    bf->l_start + bf->l_len < 0 ||
+	    bf->l_start + bf->l_len >= mp->m_super->s_maxbytes)
 		return XFS_ERROR(EINVAL);
 
 	bf->l_whence = 0;

@@ -2169,7 +2187,9 @@ xfs_change_file_space(
 	switch (cmd) {
 	case XFS_IOC_ZERO_RANGE:
 		prealloc_type |= XFS_BMAPI_CONVERT;
-		xfs_tosspages(ip, startoffset, startoffset + bf->l_len, 0);
+		end = round_down(startoffset + bf->l_len, PAGE_SIZE) - 1;
+		if (startoffset > end)
+			truncate_pagecache_range(VFS_I(ip), startoffset, end);
 		/* FALLTHRU */
 	case XFS_IOC_RESVSP:
 	case XFS_IOC_RESVSP64:

index 52fafc4..d48141d 100644
@@ -48,8 +48,6 @@ int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
 int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
 int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
 		int flags, struct attrlist_cursor_kern *cursor);
-void xfs_tosspages(struct xfs_inode *inode, xfs_off_t first,
-		xfs_off_t last, int fiopt);
 int xfs_flushinval_pages(struct xfs_inode *ip, xfs_off_t first,
 		xfs_off_t last, int fiopt);
 int xfs_flush_pages(struct xfs_inode *ip, xfs_off_t first,

Index: xfs/fs/xfs/xfs_vnodeops.c
===================================================================
@@ -2188,7 +2188,7 @@ xfs_change_file_space(
 	case XFS_IOC_ZERO_RANGE:
 		prealloc_type |= XFS_BMAPI_CONVERT;
 		end = round_down(startoffset + bf->l_len, PAGE_SIZE) - 1;
-		if (startoffset > end)
+		if (startoffset <= end)
 			truncate_pagecache_range(VFS_I(ip), startoffset, end);
 		/* FALLTHRU */
 	case XFS_IOC_RESVSP:

index 400b187..67284ed 100644
@@ -86,7 +86,7 @@ xfs_rw_ilock_demote(
  *	valid before the operation, it will be read from disk before
  *	being partially zeroed.
  */
-STATIC int
+int
 xfs_iozero(
 	struct xfs_inode	*ip,	/* inode			*/
 	loff_t			pos,	/* offset in file		*/

110 lines not on this page · raw message

index 91a03fa..5163022 100644
@@ -49,6 +49,7 @@ int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
 int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
 		int flags, struct attrlist_cursor_kern *cursor);
 
+int xfs_iozero(struct xfs_inode *, loff_t, size_t);
 int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
 int xfs_free_eofblocks(struct xfs_mount *, struct xfs_inode *, bool);
 

index d49de3d..3365823 100644
@@ -62,23 +62,9 @@ xfs_flush_pages(
 				last == -1 ? LLONG_MAX : last);
 	if (flags & XBF_ASYNC)
 		return ret;
-	ret2 = xfs_wait_on_pages(ip, first, last);
+	ret2 = -filemap_fdatawait_range(mapping, first,
+				last == -1 ? XFS_ISIZE(ip) - 1 : last);
 	if (!ret)
 		ret = ret2;
 	return ret;
 }
-
-int
-xfs_wait_on_pages(
-	xfs_inode_t	*ip,
-	xfs_off_t	first,
-	xfs_off_t	last)
-{
-	struct address_space *mapping = VFS_I(ip)->i_mapping;
-
-	if (mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) {
-		return -filemap_fdatawait_range(mapping, first,
-					last == -1 ? XFS_ISIZE(ip) - 1 : last);
-	}
-	return 0;
-}

index d48141d..c8ad48b 100644
@@ -52,7 +52,6 @@ int xfs_flushinval_pages(struct xfs_inode *ip, xfs_off_t first,
 		xfs_off_t last, int fiopt);
 int xfs_flush_pages(struct xfs_inode *ip, xfs_off_t first,
 		xfs_off_t last, uint64_t flags, int fiopt);
-int xfs_wait_on_pages(struct xfs_inode *ip, xfs_off_t first, xfs_off_t last);
 
 int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
 int xfs_free_eofblocks(struct xfs_mount *, struct xfs_inode *, bool);

index e57e2da..71361da 100644
@@ -1641,7 +1641,7 @@ xfs_vm_bmap(
 
 	trace_xfs_vm_bmap(XFS_I(inode));
 	xfs_ilock(ip, XFS_IOLOCK_SHARED);
-	xfs_flush_pages(ip, (xfs_off_t)0, -1, 0, FI_REMAPF);
+	filemap_write_and_wait(mapping);
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 	return generic_block_bmap(mapping, block, xfs_get_blocks);
 }

index 83d0cf3..a60f3d1 100644
@@ -5599,7 +5599,7 @@ xfs_getbmap(
 	xfs_ilock(ip, XFS_IOLOCK_SHARED);
 	if (whichfork == XFS_DATA_FORK && !(iflags & BMV_IF_DELALLOC)) {
 		if (ip->i_delayed_blks || XFS_ISIZE(ip) > ip->i_d.di_size) {
-			error = xfs_flush_pages(ip, 0, -1, 0, FI_REMAPF);
+			error = -filemap_write_and_wait(VFS_I(ip)->i_mapping);
 			if (error)
 				goto out_unlock_iolock;
 		}

index 3365823..b538089 100644
@@ -44,27 +44,3 @@ xfs_flushinval_pages(
 		truncate_inode_pages_range(mapping, first, last);
 	return -ret;
 }
-
-int
-xfs_flush_pages(
-	xfs_inode_t	*ip,
-	xfs_off_t	first,
-	xfs_off_t	last,
-	uint64_t	flags,
-	int		fiopt)
-{
-	struct address_space *mapping = VFS_I(ip)->i_mapping;
-	int		ret = 0;
-	int		ret2;
-
-	xfs_iflags_clear(ip, XFS_ITRUNCATED);
-	ret = -filemap_fdatawrite_range(mapping, first,
-				last == -1 ? LLONG_MAX : last);
-	if (flags & XBF_ASYNC)
-		return ret;
-	ret2 = -filemap_fdatawait_range(mapping, first,
-				last == -1 ? XFS_ISIZE(ip) - 1 : last);
-	if (!ret)
-		ret = ret2;
-	return ret;
-}

index 81f5c49..d82efaa 100644
@@ -780,8 +780,8 @@ xfs_setattr_size(
 	 * care about here.
 	 */
 	if (oldsize != ip->i_d.di_size && newsize > ip->i_d.di_size) {
-		error = xfs_flush_pages(ip, ip->i_d.di_size, newsize, 0,
-					FI_NONE);
+		error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+						      ip->i_d.di_size, newsize);
 		if (error)
 			goto out_unlock;
 	}

index f7de578..31de73e 100644
@@ -428,8 +428,11 @@ xfs_release(
 		truncated = xfs_iflags_test_and_clear(ip, XFS_ITRUNCATED);
 		if (truncated) {
 			xfs_iflags_clear(ip, XFS_IDIRTY_RELEASE);
-			if (VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0)
-				xfs_flush_pages(ip, 0, -1, XBF_ASYNC, FI_NONE);
+			if (VN_DIRTY(VFS_I(ip)) && ip->i_delayed_blks > 0) {
+				error = -filemap_flush(VFS_I(ip)->i_mapping);
+				if (error)
+					return error;
+			}
 		}
 	}
 

index c8ad48b..73cb3cb 100644
@@ -50,8 +50,6 @@ int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
 		int flags, struct attrlist_cursor_kern *cursor);
 int xfs_flushinval_pages(struct xfs_inode *ip, xfs_off_t first,
 		xfs_off_t last, int fiopt);
-int xfs_flush_pages(struct xfs_inode *ip, xfs_off_t first,
-		xfs_off_t last, uint64_t flags, int fiopt);
 
 int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
 int xfs_free_eofblocks(struct xfs_mount *, struct xfs_inode *, bool);

index b2c63a2..d0e9c74 100644
@@ -246,12 +246,10 @@ xfs_swap_extents(
 		goto out_unlock;
 	}
 
-	if (VN_CACHED(VFS_I(tip)) != 0) {
-		error = xfs_flushinval_pages(tip, 0, -1,
-				FI_REMAPF_LOCKED);
-		if (error)
-			goto out_unlock;
-	}
+	error = -filemap_write_and_wait(VFS_I(ip)->i_mapping);
+	if (error)
+		goto out_unlock;
+	truncate_pagecache_range(VFS_I(ip), 0, -1);
 
 	/* Verify O_DIRECT for ftmp */
 	if (VN_CACHED(VFS_I(tip)) != 0) {

index daf4066..c42f99e 100644
@@ -255,15 +255,14 @@ xfs_file_aio_read(
 		xfs_buftarg_t	*target =
 			XFS_IS_REALTIME_INODE(ip) ?
 				mp->m_rtdev_targp : mp->m_ddev_targp;
-		if ((iocb->ki_pos & target->bt_smask) ||
-		    (size & target->bt_smask)) {
-			if (iocb->ki_pos == i_size_read(inode))
+		if ((pos & target->bt_smask) || (size & target->bt_smask)) {
+			if (pos == i_size_read(inode))
 				return 0;
 			return -XFS_ERROR(EINVAL);
 		}
 	}
 
-	n = mp->m_super->s_maxbytes - iocb->ki_pos;
+	n = mp->m_super->s_maxbytes - pos;
 	if (n <= 0 || size == 0)
 		return 0;
 

@@ -289,20 +288,21 @@ xfs_file_aio_read(
 		xfs_rw_ilock(ip, XFS_IOLOCK_EXCL);
 
 		if (inode->i_mapping->nrpages) {
-			ret = -xfs_flushinval_pages(ip,
-					(iocb->ki_pos & PAGE_CACHE_MASK),
-					-1, FI_REMAPF_LOCKED);
+			ret = -filemap_write_and_wait_range(
+							VFS_I(ip)->i_mapping,
+							pos, -1);
 			if (ret) {
 				xfs_rw_iunlock(ip, XFS_IOLOCK_EXCL);
 				return ret;
 			}
+			truncate_pagecache_range(VFS_I(ip), pos, -1);
 		}
 		xfs_rw_ilock_demote(ip, XFS_IOLOCK_EXCL);
 	}
 
-	trace_xfs_file_read(ip, size, iocb->ki_pos, ioflags);
+	trace_xfs_file_read(ip, size, pos, ioflags);
 
-	ret = generic_file_aio_read(iocb, iovp, nr_segs, iocb->ki_pos);
+	ret = generic_file_aio_read(iocb, iovp, nr_segs, pos);
 	if (ret > 0)
 		XFS_STATS_ADD(xs_read_bytes, ret);
 

@@ -670,10 +670,11 @@ xfs_file_dio_aio_write(
 		goto out;
 
 	if (mapping->nrpages) {
-		ret = -xfs_flushinval_pages(ip, (pos & PAGE_CACHE_MASK), -1,
-							FI_REMAPF_LOCKED);
+		ret = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+						    pos, -1);
 		if (ret)
 			goto out;
+		truncate_pagecache_range(VFS_I(ip), pos, -1);
 	}
 
 	/*

46 lines not on this page · raw message

index 31de73e..165cb92 100644
@@ -1958,12 +1958,11 @@ xfs_free_file_space(
 
 	rounding = max_t(uint, 1 << mp->m_sb.sb_blocklog, PAGE_CACHE_SIZE);
 	ioffset = offset & ~(rounding - 1);
-
-	if (VN_CACHED(VFS_I(ip)) != 0) {
-		error = xfs_flushinval_pages(ip, ioffset, -1, FI_REMAPF_LOCKED);
-		if (error)
-			goto out_unlock_iolock;
-	}
+	error = -filemap_write_and_wait_range(VFS_I(ip)->i_mapping,
+					      ioffset, -1);
+	if (error)
+		goto out_unlock_iolock;
+	truncate_pagecache_range(VFS_I(ip), ioffset, -1);
 
 	/*
 	 * Need to zero the stuff we're not freeing, on disk.

index 73cb3cb..91a03fa 100644
@@ -48,8 +48,6 @@ int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
 int xfs_attr_remove(struct xfs_inode *dp, const unsigned char *name, int flags);
 int xfs_attr_list(struct xfs_inode *dp, char *buffer, int bufsize,
 		int flags, struct attrlist_cursor_kern *cursor);
-int xfs_flushinval_pages(struct xfs_inode *ip, xfs_off_t first,
-		xfs_off_t last, int fiopt);
 
 int xfs_zero_eof(struct xfs_inode *, xfs_off_t, xfs_fsize_t);
 int xfs_free_eofblocks(struct xfs_mount *, struct xfs_inode *, bool);

index e53e317..121ea99 100644
@@ -853,18 +853,22 @@ xfs_btree_set_sibling(
 	}
 }
 
-STATIC void
+void
 xfs_btree_init_block(
-	struct xfs_btree_cur	*cur,
-	int			level,
-	int			numrecs,
-	struct xfs_btree_block	*new)	/* new block */
+	struct xfs_mount *mp,
+	struct xfs_buf	*bp,
+	__u32		magic,
+	__u16		level,
+	__u16		numrecs,
+	unsigned int	flags)
 {
-	new->bb_magic = cpu_to_be32(xfs_magics[cur->bc_btnum]);
+	struct xfs_btree_block	*new = XFS_BUF_TO_BLOCK(bp);
+
+	new->bb_magic = cpu_to_be32(magic);
 	new->bb_level = cpu_to_be16(level);
 	new->bb_numrecs = cpu_to_be16(numrecs);
 
-	if (cur->bc_flags & XFS_BTREE_LONG_PTRS) {
+	if (flags & XFS_BTREE_LONG_PTRS) {
 		new->bb_u.l.bb_leftsib = cpu_to_be64(NULLDFSBNO);
 		new->bb_u.l.bb_rightsib = cpu_to_be64(NULLDFSBNO);
 	} else {

@@ -873,6 +877,17 @@ xfs_btree_init_block(
 	}
 }
 
+STATIC void
+xfs_btree_init_block_cur(
+	struct xfs_btree_cur	*cur,
+	int			level,
+	int			numrecs,
+	struct xfs_buf		*bp)
+{
+	xfs_btree_init_block(cur->bc_mp, bp, xfs_magics[cur->bc_btnum],
+			       level, numrecs, cur->bc_flags);
+}
+
 /*
  * Return true if ptr is the last record in the btree and
  * we need to track updateѕ to this record.  The decision

@@ -2183,7 +2198,7 @@ xfs_btree_split(
 		goto error0;
 
 	/* Fill in the btree header for the new right block. */
-	xfs_btree_init_block(cur, xfs_btree_get_level(left), 0, right);
+	xfs_btree_init_block_cur(cur, xfs_btree_get_level(left), 0, rbp);
 
 	/*
 	 * Split the entries between the old and the new block evenly.

@@ -2492,7 +2507,7 @@ xfs_btree_new_root(
 		nptr = 2;
 	}
 	/* Fill in the new block's btree header and log it. */
-	xfs_btree_init_block(cur, cur->bc_nlevels, 2, new);
+	xfs_btree_init_block_cur(cur, cur->bc_nlevels, 2, nbp);
 	xfs_btree_log_block(cur, nbp, XFS_BB_ALL_BITS);
 	ASSERT(!xfs_btree_ptr_is_null(cur, &lptr) &&
 			!xfs_btree_ptr_is_null(cur, &rptr));

index 5b240de..c9cf2d0 100644
@@ -378,6 +378,17 @@ xfs_btree_reada_bufs(
 	xfs_agblock_t		agbno,	/* allocation group block number */
 	xfs_extlen_t		count);	/* count of filesystem blocks */
 
+/*
+ * Initialise a new btree block header
+ */
+void
+xfs_btree_init_block(
+	struct xfs_mount *mp,
+	struct xfs_buf	*bp,
+	__u32		magic,
+	__u16		level,
+	__u16		numrecs,
+	unsigned int	flags);
 
 /*
  * Common btree core entry points.

index 7b0a997..a5034af 100644
@@ -125,7 +125,6 @@ xfs_growfs_data_private(
 	xfs_extlen_t		agsize;
 	xfs_extlen_t		tmpsize;
 	xfs_alloc_rec_t		*arec;
-	struct xfs_btree_block	*block;
 	xfs_buf_t		*bp;
 	int			bucket;
 	int			dpct;

@@ -263,17 +262,14 @@ xfs_growfs_data_private(
 			error = ENOMEM;
 			goto error0;
 		}
-		block = XFS_BUF_TO_BLOCK(bp);
-		memset(block, 0, mp->m_sb.sb_blocksize);
-		block->bb_magic = cpu_to_be32(XFS_ABTB_MAGIC);
-		block->bb_level = 0;
-		block->bb_numrecs = cpu_to_be16(1);
-		block->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK);
-		block->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK);
-		arec = XFS_ALLOC_REC_ADDR(mp, block, 1);
+		xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+		xfs_btree_init_block(mp, bp, XFS_ABTB_MAGIC, 0, 1, 0);
+
+		arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
 		arec->ar_startblock = cpu_to_be32(XFS_PREALLOC_BLOCKS(mp));
 		arec->ar_blockcount = cpu_to_be32(
 			agsize - be32_to_cpu(arec->ar_startblock));
+
 		error = xfs_bwrite(bp);
 		xfs_buf_relse(bp);
 		if (error)

@@ -289,18 +285,15 @@ xfs_growfs_data_private(
 			error = ENOMEM;
 			goto error0;
 		}
-		block = XFS_BUF_TO_BLOCK(bp);
-		memset(block, 0, mp->m_sb.sb_blocksize);
-		block->bb_magic = cpu_to_be32(XFS_ABTC_MAGIC);
-		block->bb_level = 0;
-		block->bb_numrecs = cpu_to_be16(1);
-		block->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK);
-		block->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK);
-		arec = XFS_ALLOC_REC_ADDR(mp, block, 1);
+		xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+		xfs_btree_init_block(mp, bp, XFS_ABTC_MAGIC, 0, 1, 0);
+
+		arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
 		arec->ar_startblock = cpu_to_be32(XFS_PREALLOC_BLOCKS(mp));
 		arec->ar_blockcount = cpu_to_be32(
 			agsize - be32_to_cpu(arec->ar_startblock));
 		nfree += be32_to_cpu(arec->ar_blockcount);
+
 		error = xfs_bwrite(bp);
 		xfs_buf_relse(bp);
 		if (error)

@@ -316,13 +309,9 @@ xfs_growfs_data_private(
 			error = ENOMEM;
 			goto error0;
 		}
-		block = XFS_BUF_TO_BLOCK(bp);
-		memset(block, 0, mp->m_sb.sb_blocksize);
-		block->bb_magic = cpu_to_be32(XFS_IBT_MAGIC);
-		block->bb_level = 0;
-		block->bb_numrecs = 0;
-		block->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK);
-		block->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK);
+		xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+		xfs_btree_init_block(mp, bp, XFS_IBT_MAGIC, 0, 0, 0);
+
 		error = xfs_bwrite(bp);
 		xfs_buf_relse(bp);
 		if (error)

index a5034af..2196830 100644
@@ -114,6 +114,26 @@ xfs_fs_geometry(
 	return 0;
 }
 
+static struct xfs_buf *
+xfs_growfs_get_hdr_buf(
+	struct xfs_mount	*mp,
+	xfs_daddr_t		blkno,
+	size_t			numblks,
+	int			flags)
+{
+	struct xfs_buf		*bp;
+
+	bp = xfs_buf_get_uncached(mp->m_ddev_targp, numblks, flags);
+	if (!bp)
+		return NULL;
+
+	xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+	bp->b_bn = blkno;
+	bp->b_maps[0].bm_bn = blkno;
+
+	return bp;
+}
+
 static int
 xfs_growfs_data_private(
 	xfs_mount_t		*mp,		/* mount point for filesystem */

@@ -189,15 +209,15 @@ xfs_growfs_data_private(
 		/*
 		 * AG freelist header block
 		 */
-		bp = xfs_buf_get(mp->m_ddev_targp,
-				 XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
-				 XFS_FSS_TO_BB(mp, 1), 0);
+		bp = xfs_growfs_get_hdr_buf(mp,
+				XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
+				XFS_FSS_TO_BB(mp, 1), 0);
 		if (!bp) {
 			error = ENOMEM;
 			goto error0;
 		}
+
 		agf = XFS_BUF_TO_AGF(bp);
-		memset(agf, 0, mp->m_sb.sb_sectsize);
 		agf->agf_magicnum = cpu_to_be32(XFS_AGF_MAGIC);
 		agf->agf_versionnum = cpu_to_be32(XFS_AGF_VERSION);
 		agf->agf_seqno = cpu_to_be32(agno);

@@ -226,15 +246,15 @@ xfs_growfs_data_private(
 		/*
 		 * AG inode header block
 		 */
-		bp = xfs_buf_get(mp->m_ddev_targp,
-				 XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
-				 XFS_FSS_TO_BB(mp, 1), 0);
+		bp = xfs_growfs_get_hdr_buf(mp,
+				XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
+				XFS_FSS_TO_BB(mp, 1), 0);
 		if (!bp) {
 			error = ENOMEM;
 			goto error0;
 		}
+
 		agi = XFS_BUF_TO_AGI(bp);
-		memset(agi, 0, mp->m_sb.sb_sectsize);
 		agi->agi_magicnum = cpu_to_be32(XFS_AGI_MAGIC);
 		agi->agi_versionnum = cpu_to_be32(XFS_AGI_VERSION);
 		agi->agi_seqno = cpu_to_be32(agno);

@@ -255,16 +275,16 @@ xfs_growfs_data_private(
 		/*
 		 * BNO btree root block
 		 */
-		bp = xfs_buf_get(mp->m_ddev_targp,
-				 XFS_AGB_TO_DADDR(mp, agno, XFS_BNO_BLOCK(mp)),
-				 BTOBB(mp->m_sb.sb_blocksize), 0);
+		bp = xfs_growfs_get_hdr_buf(mp,
+				XFS_AGB_TO_DADDR(mp, agno, XFS_BNO_BLOCK(mp)),
+				BTOBB(mp->m_sb.sb_blocksize), 0);
+
 		if (!bp) {
 			error = ENOMEM;
 			goto error0;
 		}
-		xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
-		xfs_btree_init_block(mp, bp, XFS_ABTB_MAGIC, 0, 1, 0);
 
+		xfs_btree_init_block(mp, bp, XFS_ABTB_MAGIC, 0, 1, 0);
 		arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
 		arec->ar_startblock = cpu_to_be32(XFS_PREALLOC_BLOCKS(mp));
 		arec->ar_blockcount = cpu_to_be32(

@@ -278,16 +298,15 @@ xfs_growfs_data_private(
 		/*
 		 * CNT btree root block
 		 */
-		bp = xfs_buf_get(mp->m_ddev_targp,
-				 XFS_AGB_TO_DADDR(mp, agno, XFS_CNT_BLOCK(mp)),
-				 BTOBB(mp->m_sb.sb_blocksize), 0);
+		bp = xfs_growfs_get_hdr_buf(mp,
+				XFS_AGB_TO_DADDR(mp, agno, XFS_CNT_BLOCK(mp)),
+				BTOBB(mp->m_sb.sb_blocksize), 0);
 		if (!bp) {
 			error = ENOMEM;
 			goto error0;
 		}
-		xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
-		xfs_btree_init_block(mp, bp, XFS_ABTC_MAGIC, 0, 1, 0);
 
+		xfs_btree_init_block(mp, bp, XFS_ABTC_MAGIC, 0, 1, 0);
 		arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
 		arec->ar_startblock = cpu_to_be32(XFS_PREALLOC_BLOCKS(mp));
 		arec->ar_blockcount = cpu_to_be32(

@@ -302,14 +321,14 @@ xfs_growfs_data_private(
 		/*
 		 * INO btree root block
 		 */
-		bp = xfs_buf_get(mp->m_ddev_targp,
-				 XFS_AGB_TO_DADDR(mp, agno, XFS_IBT_BLOCK(mp)),
-				 BTOBB(mp->m_sb.sb_blocksize), 0);
+		bp = xfs_growfs_get_hdr_buf(mp,
+				XFS_AGB_TO_DADDR(mp, agno, XFS_IBT_BLOCK(mp)),
+				BTOBB(mp->m_sb.sb_blocksize), 0);
 		if (!bp) {
 			error = ENOMEM;
 			goto error0;
 		}
-		xfs_buf_zero(bp, 0, BBTOB(bp->b_length));
+
 		xfs_btree_init_block(mp, bp, XFS_IBT_MAGIC, 0, 0, 0);
 
 		error = xfs_bwrite(bp);

index 2196830..bd9cb7f 100644
@@ -140,6 +140,7 @@ xfs_growfs_data_private(
 	xfs_growfs_data_t	*in)		/* growfs data input struct */
 {
 	xfs_agf_t		*agf;
+	struct xfs_agfl		*agfl;
 	xfs_agi_t		*agi;
 	xfs_agnumber_t		agno;
 	xfs_extlen_t		agsize;

@@ -207,7 +208,7 @@ xfs_growfs_data_private(
 	nfree = 0;
 	for (agno = nagcount - 1; agno >= oagcount; agno--, new -= agsize) {
 		/*
-		 * AG freelist header block
+		 * AG freespace header block
 		 */
 		bp = xfs_growfs_get_hdr_buf(mp,
 				XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),

@@ -244,6 +245,26 @@ xfs_growfs_data_private(
 			goto error0;
 
 		/*
+		 * AG freelist header block
+		 */
+		bp = xfs_growfs_get_hdr_buf(mp,
+				XFS_AG_DADDR(mp, agno, XFS_AGFL_DADDR(mp)),
+				XFS_FSS_TO_BB(mp, 1), 0);
+		if (!bp) {
+			error = ENOMEM;
+			goto error0;
+		}
+
+		agfl = XFS_BUF_TO_AGFL(bp);
+		for (bucket = 0; bucket < XFS_AGFL_SIZE(mp); bucket++)
+			agfl->agfl_bno[bucket] = cpu_to_be32(NULLAGBLOCK);
+
+		error = xfs_bwrite(bp);
+		xfs_buf_relse(bp);
+		if (error)
+			goto error0;
+
+		/*
 		 * AG inode header block
 		 */
 		bp = xfs_growfs_get_hdr_buf(mp,

index 3cd7542..34dcb7c 100644
@@ -447,7 +447,7 @@ xfs_alloc_read_agfl(
 	error = xfs_trans_read_buf(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGFL_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1), 0, &bp);
+			XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
 	if (error)
 		return error;
 	ASSERT(!xfs_buf_geterror(bp));

@@ -2110,7 +2110,7 @@ xfs_read_agf(
 	error = xfs_trans_read_buf(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1), flags, bpp);
+			XFS_FSS_TO_BB(mp, 1), flags, bpp, NULL);
 	if (error)
 		return error;
 	if (!*bpp)

index 55bbe98..474c57a 100644
@@ -1994,7 +1994,7 @@ xfs_attr_rmtval_get(xfs_da_args_t *args)
 			dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
 			blkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
 			error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
-						   dblkno, blkcnt, 0, &bp);
+						   dblkno, blkcnt, 0, &bp, NULL);
 			if (error)
 				return(error);
 

index 121ea99..7e79116 100644
@@ -266,9 +266,12 @@ xfs_btree_dup_cursor(
 	for (i = 0; i < new->bc_nlevels; i++) {
 		new->bc_ptrs[i] = cur->bc_ptrs[i];
 		new->bc_ra[i] = cur->bc_ra[i];
-		if ((bp = cur->bc_bufs[i])) {
-			if ((error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
-				XFS_BUF_ADDR(bp), mp->m_bsize, 0, &bp))) {
+		bp = cur->bc_bufs[i];
+		if (bp) {
+			error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
+						   XFS_BUF_ADDR(bp), mp->m_bsize,
+						   0, &bp, NULL);
+			if (error) {
 				xfs_btree_del_cursor(new, error);
 				*ncur = NULL;
 				return error;

@@ -624,10 +627,10 @@ xfs_btree_read_bufl(
 
 	ASSERT(fsbno != NULLFSBLOCK);
 	d = XFS_FSB_TO_DADDR(mp, fsbno);
-	if ((error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, d,
-			mp->m_bsize, lock, &bp))) {
+	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, d,
+				   mp->m_bsize, lock, &bp, NULL);
+	if (error)
 		return error;
-	}
 	ASSERT(!xfs_buf_geterror(bp));
 	if (bp)
 		xfs_buf_set_ref(bp, refval);

@@ -650,7 +653,7 @@ xfs_btree_reada_bufl(
 
 	ASSERT(fsbno != NULLFSBLOCK);
 	d = XFS_FSB_TO_DADDR(mp, fsbno);
-	xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count);
+	xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count, NULL);
 }
 
 /*

@@ -670,7 +673,7 @@ xfs_btree_reada_bufs(
 	ASSERT(agno != NULLAGNUMBER);
 	ASSERT(agbno != NULLAGBLOCK);
 	d = XFS_AGB_TO_DADDR(mp, agno, agbno);
-	xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count);
+	xfs_buf_readahead(mp->m_ddev_targp, d, mp->m_bsize * count, NULL);
 }
 
 STATIC int

@@ -1013,7 +1016,7 @@ xfs_btree_read_buf_block(
 
 	d = xfs_btree_ptr_to_daddr(cur, ptr);
 	error = xfs_trans_read_buf(mp, cur->bc_tp, mp->m_ddev_targp, d,
-				   mp->m_bsize, flags, bpp);
+				   mp->m_bsize, flags, bpp, NULL);
 	if (error)
 		return error;
 

index 4b0b8dd..0298dd6 100644
@@ -654,7 +654,8 @@ xfs_buf_read_map(
 	struct xfs_buftarg	*target,
 	struct xfs_buf_map	*map,
 	int			nmaps,
-	xfs_buf_flags_t		flags)
+	xfs_buf_flags_t		flags,
+	xfs_buf_iodone_t	verify)
 {
 	struct xfs_buf		*bp;
 

@@ -666,6 +667,7 @@ xfs_buf_read_map(
 
 		if (!XFS_BUF_ISDONE(bp)) {
 			XFS_STATS_INC(xb_get_read);
+			bp->b_iodone = verify;
 			_xfs_buf_read(bp, flags);
 		} else if (flags & XBF_ASYNC) {
 			/*

@@ -691,13 +693,14 @@ void
 xfs_buf_readahead_map(
 	struct xfs_buftarg	*target,
 	struct xfs_buf_map	*map,
-	int			nmaps)
+	int			nmaps,
+	xfs_buf_iodone_t	verify)
 {
 	if (bdi_read_congested(target->bt_bdi))
 		return;
 
 	xfs_buf_read_map(target, map, nmaps,
-		     XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD);
+		     XBF_TRYLOCK|XBF_ASYNC|XBF_READ_AHEAD, verify);
 }
 
 /*

@@ -709,7 +712,8 @@ xfs_buf_read_uncached(
 	struct xfs_buftarg	*target,
 	xfs_daddr_t		daddr,
 	size_t			numblks,
-	int			flags)
+	int			flags,
+	xfs_buf_iodone_t	verify)
 {
 	xfs_buf_t		*bp;
 	int			error;

@@ -723,6 +727,7 @@ xfs_buf_read_uncached(
 	bp->b_bn = daddr;
 	bp->b_maps[0].bm_bn = daddr;
 	bp->b_flags |= XBF_READ;
+	bp->b_iodone = verify;
 
 	xfsbdstrat(target->bt_mount, bp);
 	error = xfs_buf_iowait(bp);

index 7c0b6a0..677b1dc 100644
@@ -100,6 +100,7 @@ typedef struct xfs_buftarg {
 struct xfs_buf;
 typedef void (*xfs_buf_iodone_t)(struct xfs_buf *);
 
+
 #define XB_PAGES	2
 
 struct xfs_buf_map {

@@ -159,7 +160,6 @@ typedef struct xfs_buf {
 #endif
 } xfs_buf_t;
 
-
 /* Finding and Reading Buffers */
 struct xfs_buf *_xfs_buf_find(struct xfs_buftarg *target,
 			      struct xfs_buf_map *map, int nmaps,

@@ -196,9 +196,10 @@ struct xfs_buf *xfs_buf_get_map(struct xfs_buftarg *target,
 			       xfs_buf_flags_t flags);
 struct xfs_buf *xfs_buf_read_map(struct xfs_buftarg *target,
 			       struct xfs_buf_map *map, int nmaps,
-			       xfs_buf_flags_t flags);
+			       xfs_buf_flags_t flags, xfs_buf_iodone_t verify);
 void xfs_buf_readahead_map(struct xfs_buftarg *target,
-			       struct xfs_buf_map *map, int nmaps);
+			       struct xfs_buf_map *map, int nmaps,
+			       xfs_buf_iodone_t verify);
 
 static inline struct xfs_buf *
 xfs_buf_get(

@@ -216,20 +217,22 @@ xfs_buf_read(
 	struct xfs_buftarg	*target,
 	xfs_daddr_t		blkno,
 	size_t			numblks,
-	xfs_buf_flags_t		flags)
+	xfs_buf_flags_t		flags,
+	xfs_buf_iodone_t	verify)
 {
 	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
-	return xfs_buf_read_map(target, &map, 1, flags);
+	return xfs_buf_read_map(target, &map, 1, flags, verify);
 }
 
 static inline void
 xfs_buf_readahead(
 	struct xfs_buftarg	*target,
 	xfs_daddr_t		blkno,
-	size_t			numblks)
+	size_t			numblks,
+	xfs_buf_iodone_t	verify)
 {
 	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
-	return xfs_buf_readahead_map(target, &map, 1);
+	return xfs_buf_readahead_map(target, &map, 1, verify);
 }
 
 struct xfs_buf *xfs_buf_get_empty(struct xfs_buftarg *target, size_t numblks);

@@ -239,7 +242,8 @@ int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length);
 struct xfs_buf *xfs_buf_get_uncached(struct xfs_buftarg *target, size_t numblks,
 				int flags);
 struct xfs_buf *xfs_buf_read_uncached(struct xfs_buftarg *target,
-				xfs_daddr_t daddr, size_t numblks, int flags);
+				xfs_daddr_t daddr, size_t numblks, int flags,
+				xfs_buf_iodone_t verify);
 void xfs_buf_hold(struct xfs_buf *bp);
 
 /* Releasing Buffers */

index c62e7e6..4af8bad 100644
@@ -2161,7 +2161,7 @@ xfs_da_read_buf(
 
 	error = xfs_trans_read_buf_map(dp->i_mount, trans,
 					dp->i_mount->m_ddev_targp,
-					mapp, nmap, 0, &bp);
+					mapp, nmap, 0, &bp, NULL);
 	if (error)
 		goto out_free;
 

@@ -2237,7 +2237,7 @@ xfs_da_reada_buf(
 	}
 
 	mappedbno = mapp[0].bm_bn;
-	xfs_buf_readahead_map(dp->i_mount->m_ddev_targp, mapp, nmap);
+	xfs_buf_readahead_map(dp->i_mount->m_ddev_targp, mapp, nmap, NULL);
 
 out_free:
 	if (mapp != &map)

index 0b29625..bac8698 100644
@@ -926,7 +926,7 @@ xfs_dir2_leaf_readbuf(
 				XFS_FSB_TO_DADDR(mp,
 					map[mip->ra_index].br_startblock +
 							mip->ra_offset),
-				(int)BTOBB(mp->m_dirblksize));
+				(int)BTOBB(mp->m_dirblksize), NULL);
 			mip->ra_current = i;
 		}
 

index bf27fcc..e95f800 100644
@@ -439,7 +439,7 @@ xfs_qm_dqtobp(
 		error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 					   dqp->q_blkno,
 					   mp->m_quotainfo->qi_dqchunklen,
-					   0, &bp);
+					   0, &bp, NULL);
 		if (error || !bp)
 			return XFS_ERROR(error);
 	}

@@ -920,7 +920,7 @@ xfs_qm_dqflush(
 	 * Get the buffer containing the on-disk dquot
 	 */
 	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dqp->q_blkno,
-				   mp->m_quotainfo->qi_dqchunklen, 0, &bp);
+				   mp->m_quotainfo->qi_dqchunklen, 0, &bp, NULL);
 	if (error)
 		goto out_unlock;
 

index bd9cb7f..5440768 100644
@@ -168,7 +168,7 @@ xfs_growfs_data_private(
 	dpct = pct - mp->m_sb.sb_imax_pct;
 	bp = xfs_buf_read_uncached(mp->m_ddev_targp,
 				XFS_FSB_TO_BB(mp, nb) - XFS_FSS_TO_BB(mp, 1),
-				XFS_FSS_TO_BB(mp, 1), 0);
+				XFS_FSS_TO_BB(mp, 1), 0, NULL);
 	if (!bp)
 		return EIO;
 	xfs_buf_relse(bp);

@@ -439,7 +439,7 @@ xfs_growfs_data_private(
 		if (agno < oagcount) {
 			error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
 				  XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
-				  XFS_FSS_TO_BB(mp, 1), 0, &bp);
+				  XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
 		} else {
 			bp = xfs_trans_get_buf(NULL, mp->m_ddev_targp,
 				  XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),

index 37753e1..12e3dea 100644
@@ -1490,7 +1490,7 @@ xfs_read_agi(
 
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1), 0, bpp);
+			XFS_FSS_TO_BB(mp, 1), 0, bpp, NULL);
 	if (error)
 		return error;
 

index 7449cb9..8d69630 100644
@@ -408,7 +408,7 @@ xfs_imap_to_bp(
 
 	buf_flags |= XBF_UNMAPPED;
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
-				   (int)imap->im_len, buf_flags, &bp);
+				   (int)imap->im_len, buf_flags, &bp, NULL);
 	if (error) {
 		if (error != EAGAIN) {
 			xfs_warn(mp,

index 46b6986..1d6d2ee 100644
@@ -1129,8 +1129,7 @@ xlog_iodone(xfs_buf_t *bp)
 	 * with it being freed after writing the unmount record to the
 	 * log.
 	 */
-
-}	/* xlog_iodone */
+}
 
 /*
  * Return size of each in-core log record buffer.

index 3e06333..eb1e29f 100644
@@ -2144,7 +2144,7 @@ xlog_recover_buffer_pass2(
 		buf_flags |= XBF_UNMAPPED;
 
 	bp = xfs_buf_read(mp->m_ddev_targp, buf_f->blf_blkno, buf_f->blf_len,
-			  buf_flags);
+			  buf_flags, NULL);
 	if (!bp)
 		return XFS_ERROR(ENOMEM);
 	error = bp->b_error;

@@ -2237,7 +2237,8 @@ xlog_recover_inode_pass2(
 	}
 	trace_xfs_log_recover_inode_recover(log, in_f);
 
-	bp = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len, 0);
+	bp = xfs_buf_read(mp->m_ddev_targp, in_f->ilf_blkno, in_f->ilf_len, 0,
+			  NULL);
 	if (!bp) {
 		error = ENOMEM;
 		goto error;

@@ -2548,7 +2549,8 @@ xlog_recover_dquot_pass2(
 	ASSERT(dq_f->qlf_len == 1);
 
 	error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp, dq_f->qlf_blkno,
-				   XFS_FSB_TO_BB(mp, dq_f->qlf_len), 0, &bp);
+				   XFS_FSB_TO_BB(mp, dq_f->qlf_len), 0, &bp,
+				   NULL);
 	if (error)
 		return error;
 

index 41ae7e1..d5402b0 100644
@@ -652,7 +652,7 @@ xfs_readsb(xfs_mount_t *mp, int flags)
 
 reread:
 	bp = xfs_buf_read_uncached(mp->m_ddev_targp, XFS_SB_DADDR,
-					BTOBB(sector_size), 0);
+					BTOBB(sector_size), 0, NULL);
 	if (!bp) {
 		if (loud)
 			xfs_warn(mp, "SB buffer read failed");

@@ -1002,7 +1002,7 @@ xfs_check_sizes(xfs_mount_t *mp)
 	}
 	bp = xfs_buf_read_uncached(mp->m_ddev_targp,
 					d - XFS_FSS_TO_BB(mp, 1),
-					XFS_FSS_TO_BB(mp, 1), 0);
+					XFS_FSS_TO_BB(mp, 1), 0, NULL);
 	if (!bp) {
 		xfs_warn(mp, "last sector read failed");
 		return EIO;

@@ -1017,7 +1017,7 @@ xfs_check_sizes(xfs_mount_t *mp)
 		}
 		bp = xfs_buf_read_uncached(mp->m_logdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_BB(mp, 1), 0);
+					XFS_FSB_TO_BB(mp, 1), 0, NULL);
 		if (!bp) {
 			xfs_warn(mp, "log device read failed");
 			return EIO;

index 48c750b..688f608 100644
@@ -892,7 +892,7 @@ xfs_qm_dqiter_bufs(
 	while (blkcnt--) {
 		error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
 			      XFS_FSB_TO_DADDR(mp, bno),
-			      mp->m_quotainfo->qi_dqchunklen, 0, &bp);
+			      mp->m_quotainfo->qi_dqchunklen, 0, &bp, NULL);
 		if (error)
 			break;
 

@@ -979,7 +979,8 @@ xfs_qm_dqiterate(
 				while (rablkcnt--) {
 					xfs_buf_readahead(mp->m_ddev_targp,
 					       XFS_FSB_TO_DADDR(mp, rablkno),
-					       mp->m_quotainfo->qi_dqchunklen);
+					       mp->m_quotainfo->qi_dqchunklen,
+					       NULL);
 					rablkno++;
 				}
 			}

index a69e0b4..b271ed9 100644
@@ -870,7 +870,7 @@ xfs_rtbuf_get(
 	ASSERT(map.br_startblock != NULLFSBLOCK);
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 				   XFS_FSB_TO_DADDR(mp, map.br_startblock),
-				   mp->m_bsize, 0, &bp);
+				   mp->m_bsize, 0, &bp, NULL);
 	if (error)
 		return error;
 	ASSERT(!xfs_buf_geterror(bp));

@@ -1873,7 +1873,7 @@ xfs_growfs_rt(
 	 */
 	bp = xfs_buf_read_uncached(mp->m_rtdev_targp,
 				XFS_FSB_TO_BB(mp, nrblocks - 1),
-				XFS_FSB_TO_BB(mp, 1), 0);
+				XFS_FSB_TO_BB(mp, 1), 0, NULL);
 	if (!bp)
 		return EIO;
 	xfs_buf_relse(bp);

@@ -2220,7 +2220,7 @@ xfs_rtmount_init(
 	}
 	bp = xfs_buf_read_uncached(mp->m_rtdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
-					XFS_FSB_TO_BB(mp, 1), 0);
+					XFS_FSB_TO_BB(mp, 1), 0, NULL);
 	if (!bp) {
 		xfs_warn(mp, "realtime device size check failed");
 		return EIO;

index db05654..f02d402 100644
@@ -464,10 +464,7 @@ xfs_trans_get_buf(
 	int			numblks,
 	uint			flags)
 {
-	struct xfs_buf_map	map = {
-		.bm_bn = blkno,
-		.bm_len = numblks,
-	};
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
 	return xfs_trans_get_buf_map(tp, target, &map, 1, flags);
 }
 

@@ -476,7 +473,8 @@ int		xfs_trans_read_buf_map(struct xfs_mount *mp,
 				       struct xfs_buftarg *target,
 				       struct xfs_buf_map *map, int nmaps,
 				       xfs_buf_flags_t flags,
-				       struct xfs_buf **bpp);
+				       struct xfs_buf **bpp,
+				       xfs_buf_iodone_t verify);
 
 static inline int
 xfs_trans_read_buf(

@@ -486,13 +484,12 @@ xfs_trans_read_buf(
 	xfs_daddr_t		blkno,
 	int			numblks,
 	xfs_buf_flags_t		flags,
-	struct xfs_buf		**bpp)
+	struct xfs_buf		**bpp,
+	xfs_buf_iodone_t	verify)
 {
-	struct xfs_buf_map	map = {
-		.bm_bn = blkno,
-		.bm_len = numblks,
-	};
-	return xfs_trans_read_buf_map(mp, tp, target, &map, 1, flags, bpp);
+	DEFINE_SINGLE_BUF_MAP(map, blkno, numblks);
+	return xfs_trans_read_buf_map(mp, tp, target, &map, 1,
+				      flags, bpp, verify);
 }
 
 struct xfs_buf	*xfs_trans_getsb(xfs_trans_t *, struct xfs_mount *, int);

index 6311b99..9776282 100644
@@ -257,7 +257,8 @@ xfs_trans_read_buf_map(
 	struct xfs_buf_map	*map,
 	int			nmaps,
 	xfs_buf_flags_t		flags,
-	struct xfs_buf		**bpp)
+	struct xfs_buf		**bpp,
+	xfs_buf_iodone_t	verify)
 {
 	xfs_buf_t		*bp;
 	xfs_buf_log_item_t	*bip;

@@ -265,7 +266,7 @@ xfs_trans_read_buf_map(
 
 	*bpp = NULL;
 	if (!tp) {
-		bp = xfs_buf_read_map(target, map, nmaps, flags);
+		bp = xfs_buf_read_map(target, map, nmaps, flags, verify);
 		if (!bp)
 			return (flags & XBF_TRYLOCK) ?
 					EAGAIN : XFS_ERROR(ENOMEM);

@@ -312,7 +313,9 @@ xfs_trans_read_buf_map(
 		if (!(XFS_BUF_ISDONE(bp))) {
 			trace_xfs_trans_read_buf_io(bp, _RET_IP_);
 			ASSERT(!XFS_BUF_ISASYNC(bp));
+			ASSERT(bp->b_iodone == NULL);
 			XFS_BUF_READ(bp);
+			bp->b_iodone = verify;
 			xfsbdstrat(tp->t_mountp, bp);
 			error = xfs_buf_iowait(bp);
 			if (error) {

@@ -349,7 +352,7 @@ xfs_trans_read_buf_map(
 		return 0;
 	}
 
-	bp = xfs_buf_read_map(target, map, nmaps, flags);
+	bp = xfs_buf_read_map(target, map, nmaps, flags, verify);
 	if (bp == NULL) {
 		*bpp = NULL;
 		return (flags & XBF_TRYLOCK) ?

index 165cb92..bc70446 100644
@@ -80,7 +80,7 @@ xfs_readlink_bmap(
 		d = XFS_FSB_TO_DADDR(mp, mval[n].br_startblock);
 		byte_cnt = XFS_FSB_TO_B(mp, mval[n].br_blockcount);
 
-		bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0);
+		bp = xfs_buf_read(mp->m_ddev_targp, d, BTOBB(byte_cnt), 0, NULL);
 		if (!bp)
 			return XFS_ERROR(ENOMEM);
 		error = bp->b_error;

index 0298dd6..fbc965f 100644
@@ -715,8 +715,7 @@ xfs_buf_read_uncached(
 	int			flags,
 	xfs_buf_iodone_t	verify)
 {
-	xfs_buf_t		*bp;
-	int			error;
+	struct xfs_buf		*bp;
 
 	bp = xfs_buf_get_uncached(target, numblks, flags);
 	if (!bp)

@@ -730,11 +729,7 @@ xfs_buf_read_uncached(
 	bp->b_iodone = verify;
 
 	xfsbdstrat(target->bt_mount, bp);
-	error = xfs_buf_iowait(bp);
-	if (error) {
-		xfs_buf_relse(bp);
-		return NULL;
-	}
+	xfs_buf_iowait(bp);
 	return bp;
 }
 

index 5440768..f35f8d7 100644
@@ -171,6 +171,11 @@ xfs_growfs_data_private(
 				XFS_FSS_TO_BB(mp, 1), 0, NULL);
 	if (!bp)
 		return EIO;
+	if (bp->b_error) {
+		int	error = bp->b_error;
+		xfs_buf_relse(bp);
+		return error;
+	}
 	xfs_buf_relse(bp);
 
 	new = nb;	/* use new as a temporary here */

index d5402b0..df6d0b2 100644
@@ -658,6 +658,12 @@ reread:
 			xfs_warn(mp, "SB buffer read failed");
 		return EIO;
 	}
+	if (bp->b_error) {
+		error = bp->b_error;
+		if (loud)
+			xfs_warn(mp, "SB validate failed");
+		goto release_buf;
+	}
 
 	/*
 	 * Initialize the mount structure from the superblock.

index b271ed9..98dc670 100644
@@ -1876,6 +1876,11 @@ xfs_growfs_rt(
 				XFS_FSB_TO_BB(mp, 1), 0, NULL);
 	if (!bp)
 		return EIO;
+	if (bp->b_error) {
+		error = bp->b_error;
+		xfs_buf_relse(bp);
+		return error;
+	}
 	xfs_buf_relse(bp);
 
 	/*

@@ -2221,8 +2226,10 @@ xfs_rtmount_init(
 	bp = xfs_buf_read_uncached(mp->m_rtdev_targp,
 					d - XFS_FSB_TO_BB(mp, 1),
 					XFS_FSB_TO_BB(mp, 1), 0, NULL);
-	if (!bp) {
+	if (!bp || bp->b_error) {
 		xfs_warn(mp, "realtime device size check failed");
+		if (bp)
+			xfs_buf_relse(bp);
 		return EIO;
 	}
 	xfs_buf_relse(bp);

index f35f8d7..cb65b06 100644
@@ -444,7 +444,8 @@ xfs_growfs_data_private(
 		if (agno < oagcount) {
 			error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
 				  XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),
-				  XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
+				  XFS_FSS_TO_BB(mp, 1), 0, &bp,
+				  xfs_sb_read_verify);
 		} else {
 			bp = xfs_trans_get_buf(NULL, mp->m_ddev_targp,
 				  XFS_AGB_TO_DADDR(mp, agno, XFS_SB_BLOCK(mp)),

@@ -462,6 +463,7 @@ xfs_growfs_data_private(
 			break;
 		}
 		xfs_sb_to_disk(XFS_BUF_TO_SBP(bp), &mp->m_sb, XFS_SB_ALL_BITS);
+
 		/*
 		 * If we get an error writing out the alternate superblocks,
 		 * just issue a warning and continue.  The real work is

index eb1e29f..924a4bc 100644
@@ -3692,13 +3692,14 @@ xlog_do_recover(
 
 	/*
 	 * Now that we've finished replaying all buffer and inode
-	 * updates, re-read in the superblock.
+	 * updates, re-read in the superblock and reverify it.
 	 */
 	bp = xfs_getsb(log->l_mp, 0);
 	XFS_BUF_UNDONE(bp);
 	ASSERT(!(XFS_BUF_ISWRITE(bp)));
 	XFS_BUF_READ(bp);
 	XFS_BUF_UNASYNC(bp);
+	bp->b_iodone = xfs_sb_read_verify;
 	xfsbdstrat(log->l_mp, bp);
 	error = xfs_buf_iowait(bp);
 	if (error) {

@@ -3710,7 +3711,7 @@ xlog_do_recover(
 
 	/* Convert superblock from on-disk format */
 	sbp = &log->l_mp->m_sb;
-	xfs_sb_from_disk(log->l_mp, XFS_BUF_TO_SBP(bp));
+	xfs_sb_from_disk(sbp, XFS_BUF_TO_SBP(bp));
 	ASSERT(sbp->sb_magicnum == XFS_SB_MAGIC);
 	ASSERT(xfs_sb_good_version(sbp));
 	xfs_buf_relse(bp);

190 lines not on this page · raw message

index dc306a0..de9089a 100644
@@ -385,10 +385,11 @@ extern void	xfs_set_low_space_thresholds(struct xfs_mount *);
 
 #endif	/* __KERNEL__ */
 
+extern void	xfs_sb_read_verify(struct xfs_buf *);
 extern void	xfs_mod_sb(struct xfs_trans *, __int64_t);
 extern int	xfs_initialize_perag(struct xfs_mount *, xfs_agnumber_t,
 					xfs_agnumber_t *);
-extern void	xfs_sb_from_disk(struct xfs_mount *, struct xfs_dsb *);
+extern void	xfs_sb_from_disk(struct xfs_sb *, struct xfs_dsb *);
 extern void	xfs_sb_to_disk(struct xfs_dsb *, struct xfs_sb *, __int64_t);
 
 #endif	/* __XFS_MOUNT_H__ */

index 34dcb7c..cebac40 100644
@@ -2091,6 +2091,48 @@ xfs_alloc_put_freelist(
 	return 0;
 }
 
+static void
+xfs_agf_read_verify(
+	struct xfs_buf	*bp)
+ {
+	struct xfs_mount *mp = bp->b_target->bt_mount;
+	struct xfs_agf	*agf;
+	int		agf_ok;
+
+	agf = XFS_BUF_TO_AGF(bp);
+
+	agf_ok = agf->agf_magicnum == cpu_to_be32(XFS_AGF_MAGIC) &&
+		XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
+		be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) &&
+		be32_to_cpu(agf->agf_flfirst) < XFS_AGFL_SIZE(mp) &&
+		be32_to_cpu(agf->agf_fllast) < XFS_AGFL_SIZE(mp) &&
+		be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp) &&
+		be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp);
+
+	/*
+	 * during growfs operations, the perag is not fully initialised,
+	 * so we can't use it for any useful checking. growfs ensures we can't
+	 * use it by using uncached buffers that don't have the perag attached
+	 * so we can detect and avoid this problem.
+	 */
+	if (bp->b_pag)
+		agf_ok = agf_ok && be32_to_cpu(agf->agf_seqno) ==
+						bp->b_pag->pag_agno;
+
+	if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+		agf_ok = agf_ok && be32_to_cpu(agf->agf_btreeblks) <=
+						be32_to_cpu(agf->agf_length);
+
+	if (unlikely(XFS_TEST_ERROR(!agf_ok, mp, XFS_ERRTAG_ALLOC_READ_AGF,
+			XFS_RANDOM_ALLOC_READ_AGF))) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, agf);
+		xfs_buf_ioerror(bp, EFSCORRUPTED);
+	}
+
+	bp->b_iodone = NULL;
+	xfs_buf_ioend(bp, 0);
+}
+
 /*
  * Read in the allocation group header (free/alloc section).
  */

@@ -2102,44 +2144,19 @@ xfs_read_agf(
 	int			flags,	/* XFS_BUF_ */
 	struct xfs_buf		**bpp)	/* buffer for the ag freelist header */
 {
-	struct xfs_agf	*agf;		/* ag freelist header */
-	int		agf_ok;		/* set if agf is consistent */
 	int		error;
 
 	ASSERT(agno != NULLAGNUMBER);
 	error = xfs_trans_read_buf(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1), flags, bpp, NULL);
+			XFS_FSS_TO_BB(mp, 1), flags, bpp, xfs_agf_read_verify);
 	if (error)
 		return error;
 	if (!*bpp)
 		return 0;
 
 	ASSERT(!(*bpp)->b_error);
-	agf = XFS_BUF_TO_AGF(*bpp);
-
-	/*
-	 * Validate the magic number of the agf block.
-	 */
-	agf_ok =
-		agf->agf_magicnum == cpu_to_be32(XFS_AGF_MAGIC) &&
-		XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
-		be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) &&
-		be32_to_cpu(agf->agf_flfirst) < XFS_AGFL_SIZE(mp) &&
-		be32_to_cpu(agf->agf_fllast) < XFS_AGFL_SIZE(mp) &&
-		be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp) &&
-		be32_to_cpu(agf->agf_seqno) == agno;
-	if (xfs_sb_version_haslazysbcount(&mp->m_sb))
-		agf_ok = agf_ok && be32_to_cpu(agf->agf_btreeblks) <=
-						be32_to_cpu(agf->agf_length);
-	if (unlikely(XFS_TEST_ERROR(!agf_ok, mp, XFS_ERRTAG_ALLOC_READ_AGF,
-			XFS_RANDOM_ALLOC_READ_AGF))) {
-		XFS_CORRUPTION_ERROR("xfs_alloc_read_agf",
-				     XFS_ERRLEVEL_LOW, mp, agf);
-		xfs_trans_brelse(tp, *bpp);
-		return XFS_ERROR(EFSCORRUPTED);
-	}
 	xfs_buf_set_ref(*bpp, XFS_AGF_REF);
 	return 0;
 }

index 34dcb7c..c916e7e 100644
@@ -2091,6 +2091,47 @@ xfs_alloc_put_freelist(
 	return 0;
 }
 
+static void
+xfs_agf_read_verify(
+	struct xfs_buf	*bp)
+ {
+	struct xfs_mount *mp = bp->b_target->bt_mount;
+	struct xfs_agf	*agf;
+	int		agf_ok;
+
+	agf = XFS_BUF_TO_AGF(bp);
+
+	agf_ok = agf->agf_magicnum == cpu_to_be32(XFS_AGF_MAGIC) &&
+		XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
+		be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) &&
+		be32_to_cpu(agf->agf_flfirst) < XFS_AGFL_SIZE(mp) &&
+		be32_to_cpu(agf->agf_fllast) < XFS_AGFL_SIZE(mp) &&
+		be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp);
+
+	/*
+	 * during growfs operations, the perag is not fully initialised,
+	 * so we can't use it for any useful checking. growfs ensures we can't
+	 * use it by using uncached buffers that don't have the perag attached
+	 * so we can detect and avoid this problem.
+	 */
+	if (bp->b_pag)
+		agf_ok = agf_ok && be32_to_cpu(agf->agf_seqno) ==
+						bp->b_pag->pag_agno;
+
+	if (xfs_sb_version_haslazysbcount(&mp->m_sb))
+		agf_ok = agf_ok && be32_to_cpu(agf->agf_btreeblks) <=
+						be32_to_cpu(agf->agf_length);
+
+	if (unlikely(XFS_TEST_ERROR(!agf_ok, mp, XFS_ERRTAG_ALLOC_READ_AGF,
+			XFS_RANDOM_ALLOC_READ_AGF))) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, agf);
+		xfs_buf_ioerror(bp, EFSCORRUPTED);
+	}
+
+	bp->b_iodone = NULL;
+	xfs_buf_ioend(bp, 0);
+}
+
 /*
  * Read in the allocation group header (free/alloc section).
  */

@@ -2102,44 +2143,19 @@ xfs_read_agf(
 	int			flags,	/* XFS_BUF_ */
 	struct xfs_buf		**bpp)	/* buffer for the ag freelist header */
 {
-	struct xfs_agf	*agf;		/* ag freelist header */
-	int		agf_ok;		/* set if agf is consistent */
 	int		error;
 
 	ASSERT(agno != NULLAGNUMBER);
 	error = xfs_trans_read_buf(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGF_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1), flags, bpp, NULL);
+			XFS_FSS_TO_BB(mp, 1), flags, bpp, xfs_agf_read_verify);
 	if (error)
 		return error;
 	if (!*bpp)
 		return 0;
 
 	ASSERT(!(*bpp)->b_error);
-	agf = XFS_BUF_TO_AGF(*bpp);
-
-	/*
-	 * Validate the magic number of the agf block.
-	 */
-	agf_ok =
-		agf->agf_magicnum == cpu_to_be32(XFS_AGF_MAGIC) &&
-		XFS_AGF_GOOD_VERSION(be32_to_cpu(agf->agf_versionnum)) &&
-		be32_to_cpu(agf->agf_freeblks) <= be32_to_cpu(agf->agf_length) &&
-		be32_to_cpu(agf->agf_flfirst) < XFS_AGFL_SIZE(mp) &&
-		be32_to_cpu(agf->agf_fllast) < XFS_AGFL_SIZE(mp) &&
-		be32_to_cpu(agf->agf_flcount) <= XFS_AGFL_SIZE(mp) &&
-		be32_to_cpu(agf->agf_seqno) == agno;
-	if (xfs_sb_version_haslazysbcount(&mp->m_sb))
-		agf_ok = agf_ok && be32_to_cpu(agf->agf_btreeblks) <=
-						be32_to_cpu(agf->agf_length);
-	if (unlikely(XFS_TEST_ERROR(!agf_ok, mp, XFS_ERRTAG_ALLOC_READ_AGF,
-			XFS_RANDOM_ALLOC_READ_AGF))) {
-		XFS_CORRUPTION_ERROR("xfs_alloc_read_agf",
-				     XFS_ERRLEVEL_LOW, mp, agf);
-		xfs_trans_brelse(tp, *bpp);
-		return XFS_ERROR(EFSCORRUPTED);
-	}
 	xfs_buf_set_ref(*bpp, XFS_AGF_REF);
 	return 0;
 }

index 12e3dea..5bd255e 100644
@@ -1472,6 +1472,40 @@ xfs_check_agi_unlinked(
 #define xfs_check_agi_unlinked(agi)
 #endif
 
+static void
+xfs_agi_read_verify(
+	struct xfs_buf	*bp)
+{
+	struct xfs_mount *mp = bp->b_target->bt_mount;
+	struct xfs_agi	*agi = XFS_BUF_TO_AGI(bp);
+	int		agi_ok;
+
+	/*
+	 * Validate the magic number of the agi block.
+	 */
+	agi_ok = agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC) &&
+		XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum));
+
+	/*
+	 * during growfs operations, the perag is not fully initialised,
+	 * so we can't use it for any useful checking. growfs ensures we can't
+	 * use it by using uncached buffers that don't have the perag attached
+	 * so we can detect and avoid this problem.
+	 */
+	if (bp->b_pag)
+		agi_ok = agi_ok && be32_to_cpu(agi->agi_seqno) ==
+						bp->b_pag->pag_agno;
+
+	if (unlikely(XFS_TEST_ERROR(!agi_ok, mp, XFS_ERRTAG_IALLOC_READ_AGI,
+			XFS_RANDOM_IALLOC_READ_AGI))) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, agi);
+		xfs_buf_ioerror(bp, EFSCORRUPTED);
+	}
+	xfs_check_agi_unlinked(agi);
+	bp->b_iodone = NULL;
+	xfs_buf_ioend(bp, 0);
+}
+
 /*
  * Read in the allocation group header (inode allocation section)
  */

@@ -1482,38 +1516,18 @@ xfs_read_agi(
 	xfs_agnumber_t		agno,	/* allocation group number */
 	struct xfs_buf		**bpp)	/* allocation group hdr buf */
 {
-	struct xfs_agi		*agi;	/* allocation group header */
-	int			agi_ok;	/* agi is consistent */
 	int			error;
 
 	ASSERT(agno != NULLAGNUMBER);
 
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGI_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1), 0, bpp, NULL);
+			XFS_FSS_TO_BB(mp, 1), 0, bpp, xfs_agi_read_verify);
 	if (error)
 		return error;
 
 	ASSERT(!xfs_buf_geterror(*bpp));
-	agi = XFS_BUF_TO_AGI(*bpp);
-
-	/*
-	 * Validate the magic number of the agi block.
-	 */
-	agi_ok = agi->agi_magicnum == cpu_to_be32(XFS_AGI_MAGIC) &&
-		XFS_AGI_GOOD_VERSION(be32_to_cpu(agi->agi_versionnum)) &&
-		be32_to_cpu(agi->agi_seqno) == agno;
-	if (unlikely(XFS_TEST_ERROR(!agi_ok, mp, XFS_ERRTAG_IALLOC_READ_AGI,
-			XFS_RANDOM_IALLOC_READ_AGI))) {
-		XFS_CORRUPTION_ERROR("xfs_read_agi", XFS_ERRLEVEL_LOW,
-				     mp, agi);
-		xfs_trans_brelse(tp, *bpp);
-		return XFS_ERROR(EFSCORRUPTED);
-	}
-
 	xfs_buf_set_ref(*bpp, XFS_AGI_REF);
-
-	xfs_check_agi_unlinked(agi);
 	return 0;
 }
 

index cebac40..506b346 100644
@@ -430,6 +430,43 @@ xfs_alloc_fixup_trees(
 	return 0;
 }
 
+void
+xfs_agfl_read_verify(
+	struct xfs_buf	*bp)
+{
+#ifdef WHEN_CRCS_COME_ALONG
+	/*
+	 * we cannot actually do any verification of the AGFL because mkfs does
+	 * not initialise the AGFL to zero or NULL. Hence the only valid part of
+	 * the AGFL is what the AGF says is active. We can't get to the AGF, so
+	 * we can't verify just those entries are valid.
+	 *
+	 * This problem goes away when the CRC format change comes along as that
+	 * requires the AGFL to be initialised by mkfs. At that point, we can
+	 * verify the blocks in the agfl -active or not- lie within the bounds
+	 * of the AG. Until then, just leave this check ifdef'd out.
+	 */
+	struct xfs_mount *mp = bp->b_target->bt_mount;
+	struct xfs_agfl	*agfl = XFS_BUF_TO_AGFL(bp);
+	int		agfl_ok = 1;
+
+	int		i;
+
+	for (i = 0; i < XFS_AGFL_SIZE(mp); i++) {
+		if (be32_to_cpu(agfl->agfl_bno[i]) == NULLAGBLOCK ||
+		    be32_to_cpu(agfl->agfl_bno[i]) >= mp->m_sb.sb_agblocks)
+			agfl_ok = 0;
+	}
+
+	if (!agfl_ok) {
+		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, agfl);
+		xfs_buf_ioerror(bp, EFSCORRUPTED);
+	}
+#endif
+	bp->b_iodone = NULL;
+	xfs_buf_ioend(bp, 0);
+}
+
 /*
  * Read in the allocation group free block array.
  */

@@ -447,7 +484,7 @@ xfs_alloc_read_agfl(
 	error = xfs_trans_read_buf(
 			mp, tp, mp->m_ddev_targp,
 			XFS_AG_DADDR(mp, agno, XFS_AGFL_DADDR(mp)),
-			XFS_FSS_TO_BB(mp, 1), 0, &bp, NULL);
+			XFS_FSS_TO_BB(mp, 1), 0, &bp, xfs_agfl_read_verify);
 	if (error)
 		return error;
 	ASSERT(!xfs_buf_geterror(bp));

index 8d69630..514eac9 100644
@@ -382,6 +382,46 @@ xfs_inobp_check(
 }
 #endif
 
+static void
+xfs_inode_buf_verify(
+	struct xfs_buf	*bp)
+{
+	struct xfs_mount *mp = bp->b_target->bt_mount;
+	int		i;
+	int		ni;
+
+	/*
+	 * Validate the magic number and version of every inode in the buffer
+	 */
+	ni = XFS_BB_TO_FSB(mp, bp->b_length) * mp->m_sb.sb_inopblock;
+	for (i = 0; i < ni; i++) {
+		int		di_ok;
+		xfs_dinode_t	*dip;
+
+		dip = (struct xfs_dinode *)xfs_buf_offset(bp,
+					(i << mp->m_sb.sb_inodelog));
+		di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
+			    XFS_DINODE_GOOD_VERSION(dip->di_version);
+		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
+						XFS_ERRTAG_ITOBP_INOTOBP,
+						XFS_RANDOM_ITOBP_INOTOBP))) {
+			xfs_buf_ioerror(bp, EFSCORRUPTED);
+			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
+					     mp, dip);
+#ifdef DEBUG
+			xfs_emerg(mp,
+				"bad inode magic/vsn daddr %lld #%d (magic=%x)",
+				(unsigned long long)bp->b_bn, i,
+				be16_to_cpu(dip->di_magic));
+			ASSERT(0);
+#endif
+		}
+	}
+	xfs_inobp_check(mp, bp);
+	bp->b_iodone = NULL;
+	xfs_buf_ioend(bp, 0);
+}
+
 /*
  * This routine is called to map an inode to the buffer containing the on-disk
  * version of the inode.  It returns a pointer to the buffer containing the

@@ -396,71 +436,33 @@ xfs_imap_to_bp(
 	struct xfs_mount	*mp,
 	struct xfs_trans	*tp,
 	struct xfs_imap		*imap,
-	struct xfs_dinode	**dipp,
+	struct xfs_dinode       **dipp,
 	struct xfs_buf		**bpp,
 	uint			buf_flags,
 	uint			iget_flags)
 {
 	struct xfs_buf		*bp;
 	int			error;
-	int			i;
-	int			ni;
 
 	buf_flags |= XBF_UNMAPPED;
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, imap->im_blkno,
-				   (int)imap->im_len, buf_flags, &bp, NULL);
+				   (int)imap->im_len, buf_flags, &bp,
+				   xfs_inode_buf_verify);
 	if (error) {
-		if (error != EAGAIN) {
-			xfs_warn(mp,
-				"%s: xfs_trans_read_buf() returned error %d.",
-				__func__, error);
-		} else {
+		if (error == EAGAIN) {
 			ASSERT(buf_flags & XBF_TRYLOCK);
+			return error;
 		}
-		return error;
-	}
 
-	/*
-	 * Validate the magic number and version of every inode in the buffer
-	 * (if DEBUG kernel) or the first inode in the buffer, otherwise.
-	 */
-#ifdef DEBUG
-	ni = BBTOB(imap->im_len) >> mp->m_sb.sb_inodelog;
-#else	/* usual case */
-	ni = 1;
-#endif
+		if (error == EFSCORRUPTED &&
+		    (iget_flags & XFS_IGET_UNTRUSTED))
+			return XFS_ERROR(EINVAL);
 
-	for (i = 0; i < ni; i++) {
-		int		di_ok;
-		xfs_dinode_t	*dip;
-
-		dip = (xfs_dinode_t *)xfs_buf_offset(bp,
-					(i << mp->m_sb.sb_inodelog));
-		di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
-			    XFS_DINODE_GOOD_VERSION(dip->di_version);
-		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
-						XFS_ERRTAG_ITOBP_INOTOBP,
-						XFS_RANDOM_ITOBP_INOTOBP))) {
-			if (iget_flags & XFS_IGET_UNTRUSTED) {
-				xfs_trans_brelse(tp, bp);
-				return XFS_ERROR(EINVAL);
-			}
-			XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_HIGH,
-					     mp, dip);
-#ifdef DEBUG
-			xfs_emerg(mp,
-				"bad inode magic/vsn daddr %lld #%d (magic=%x)",
-				(unsigned long long)imap->im_blkno, i,
-				be16_to_cpu(dip->di_magic));
-			ASSERT(0);
-#endif
-			xfs_trans_brelse(tp, bp);
-			return XFS_ERROR(EFSCORRUPTED);
-		}
+		xfs_warn(mp, "%s: xfs_trans_read_buf() returned error %d.",
+			__func__, error);
+		return error;
 	}
 
-	xfs_inobp_check(mp, bp);
-
 	*bpp = bp;
 	*dipp = (struct xfs_dinode *)xfs_buf_offset(bp, imap->im_boffset);
 	return 0;

index f7876c6..46961e5 100644
@@ -272,6 +272,66 @@ xfs_allocbt_key_diff(
 	return (__int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
 }
 
+void
+xfs_allocbt_read_verify(
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = bp->b_target->bt_mount;
+	struct xfs_btree_block	*block = XFS_BUF_TO_BLOCK(bp);
+	struct xfs_perag	*pag = bp->b_pag;
+	unsigned int		level;
+	int			sblock_ok; /* block passes checks */
+
+	/*
+	 * magic number and level verification
+	 *
+	 * During growfs operations, we can't verify the exact level as the
+	 * perag is not fully initialised and hence not attached to the buffer.
+	 * In this case, check against the maximum tree depth.
+	 */
+	level = be16_to_cpu(block->bb_level);
+	switch (block->bb_magic) {
+	case cpu_to_be32(XFS_ABTB_MAGIC):
+		if (pag)
+			sblock_ok = level < pag->pagf_levels[XFS_BTNUM_BNOi];
+		else
+			sblock_ok = level < mp->m_ag_maxlevels;
+		break;
+	case cpu_to_be32(XFS_ABTC_MAGIC):
+		if (pag)
+			sblock_ok = level < pag->pagf_levels[XFS_BTNUM_CNTi];
+		else
+			sblock_ok = level < mp->m_ag_maxlevels;
+		break;
+	default:
+		sblock_ok = 0;
+		break;
+	}
+
+	/* numrecs verification */
+	sblock_ok = sblock_ok &&
+		be16_to_cpu(block->bb_numrecs) <= mp->m_alloc_mxr[level != 0];
+
+	/* sibling pointer verification */
+	sblock_ok = sblock_ok &&
+		(block->bb_u.s.bb_leftsib == cpu_to_be32(NULLAGBLOCK) ||
+		 be32_to_cpu(block->bb_u.s.bb_leftsib) < mp->m_sb.sb_agblocks) &&
+		block->bb_u.s.bb_leftsib &&
+		(block->bb_u.s.bb_rightsib == cpu_to_be32(NULLAGBLOCK) ||
+		 be32_to_cpu(block->bb_u.s.bb_rightsib) < mp->m_sb.sb_agblocks) &&
+		block->bb_u.s.bb_rightsib;
+
+	if (!sblock_ok) {
+		trace_xfs_btree_corrupt(bp, _RET_IP_);
+		XFS_CORRUPTION_ERROR("xfs_allocbt_read_verify",
+					XFS_ERRLEVEL_LOW, mp, block);
+		xfs_buf_ioerror(bp, EFSCORRUPTED);
+	}
+
+	bp->b_iodone = NULL;
+	xfs_buf_ioend(bp, 0);
+}
+
 #ifdef DEBUG
 STATIC int
 xfs_allocbt_keys_inorder(