Commit e828776a authored by Dave Chinner's avatar Dave Chinner Committed by Dave Chinner

xfs: fix extent format buffer allocation size

When formatting an inode item, we have to allocate a separate buffer
to hold extents when there are delayed allocation extents on the
inode and it is in extent format. The allocation size is derived
from the in-core data fork representation, which accounts for
delayed allocation extents, while the on-disk representation does
not contain any delalloc extents.

As a result of this mismatch, the allocated buffer can be far larger
than needed to hold the real extent list which, due to the fact the
inode is in extent format, is limited to the size of the literal
area of the inode. However, we can have thousands of delalloc
extents, resulting in an allocation size orders of magnitude larger
than is needed to hold all the real extents.

Fix this by limiting the size of the buffer being allocated to the
size of the literal area of the inodes in the filesystem (i.e. the
maximum size an inode fork can grow to).
Signed-off-by: default avatarDave Chinner <dchinner@redhat.com>
Reviewed-by: default avatarAlex Elder <aelder@sgi.com>
parent 89b3600c
...@@ -197,6 +197,41 @@ xfs_inode_item_size( ...@@ -197,6 +197,41 @@ xfs_inode_item_size(
return nvecs; return nvecs;
} }
/*
* xfs_inode_item_format_extents - convert in-core extents to on-disk form
*
* For either the data or attr fork in extent format, we need to endian convert
* the in-core extent as we place them into the on-disk inode. In this case, we
* need to do this conversion before we write the extents into the log. Because
* we don't have the disk inode to write into here, we allocate a buffer and
* format the extents into it via xfs_iextents_copy(). We free the buffer in
* the unlock routine after the copy for the log has been made.
*
* In the case of the data fork, the in-core and on-disk fork sizes can be
* different due to delayed allocation extents. We only log on-disk extents
* here, so always use the physical fork size to determine the size of the
* buffer we need to allocate.
*/
STATIC void
xfs_inode_item_format_extents(
struct xfs_inode *ip,
struct xfs_log_iovec *vecp,
int whichfork,
int type)
{
xfs_bmbt_rec_t *ext_buffer;
ext_buffer = kmem_alloc(XFS_IFORK_SIZE(ip, whichfork), KM_SLEEP);
if (whichfork == XFS_DATA_FORK)
ip->i_itemp->ili_extents_buf = ext_buffer;
else
ip->i_itemp->ili_aextents_buf = ext_buffer;
vecp->i_addr = ext_buffer;
vecp->i_len = xfs_iextents_copy(ip, ext_buffer, whichfork);
vecp->i_type = type;
}
/* /*
* This is called to fill in the vector of log iovecs for the * This is called to fill in the vector of log iovecs for the
* given inode log item. It fills the first item with an inode * given inode log item. It fills the first item with an inode
...@@ -213,7 +248,6 @@ xfs_inode_item_format( ...@@ -213,7 +248,6 @@ xfs_inode_item_format(
struct xfs_inode *ip = iip->ili_inode; struct xfs_inode *ip = iip->ili_inode;
uint nvecs; uint nvecs;
size_t data_bytes; size_t data_bytes;
xfs_bmbt_rec_t *ext_buffer;
xfs_mount_t *mp; xfs_mount_t *mp;
vecp->i_addr = &iip->ili_format; vecp->i_addr = &iip->ili_format;
...@@ -320,22 +354,8 @@ xfs_inode_item_format( ...@@ -320,22 +354,8 @@ xfs_inode_item_format(
} else } else
#endif #endif
{ {
/* xfs_inode_item_format_extents(ip, vecp,
* There are delayed allocation extents XFS_DATA_FORK, XLOG_REG_TYPE_IEXT);
* in the inode, or we need to convert
* the extents to on disk format.
* Use xfs_iextents_copy()
* to copy only the real extents into
* a separate buffer. We'll free the
* buffer in the unlock routine.
*/
ext_buffer = kmem_alloc(ip->i_df.if_bytes,
KM_SLEEP);
iip->ili_extents_buf = ext_buffer;
vecp->i_addr = ext_buffer;
vecp->i_len = xfs_iextents_copy(ip, ext_buffer,
XFS_DATA_FORK);
vecp->i_type = XLOG_REG_TYPE_IEXT;
} }
ASSERT(vecp->i_len <= ip->i_df.if_bytes); ASSERT(vecp->i_len <= ip->i_df.if_bytes);
iip->ili_format.ilf_dsize = vecp->i_len; iip->ili_format.ilf_dsize = vecp->i_len;
...@@ -445,19 +465,12 @@ xfs_inode_item_format( ...@@ -445,19 +465,12 @@ xfs_inode_item_format(
*/ */
vecp->i_addr = ip->i_afp->if_u1.if_extents; vecp->i_addr = ip->i_afp->if_u1.if_extents;
vecp->i_len = ip->i_afp->if_bytes; vecp->i_len = ip->i_afp->if_bytes;
vecp->i_type = XLOG_REG_TYPE_IATTR_EXT;
#else #else
ASSERT(iip->ili_aextents_buf == NULL); ASSERT(iip->ili_aextents_buf == NULL);
/* xfs_inode_item_format_extents(ip, vecp,
* Need to endian flip before logging XFS_ATTR_FORK, XLOG_REG_TYPE_IATTR_EXT);
*/
ext_buffer = kmem_alloc(ip->i_afp->if_bytes,
KM_SLEEP);
iip->ili_aextents_buf = ext_buffer;
vecp->i_addr = ext_buffer;
vecp->i_len = xfs_iextents_copy(ip, ext_buffer,
XFS_ATTR_FORK);
#endif #endif
vecp->i_type = XLOG_REG_TYPE_IATTR_EXT;
iip->ili_format.ilf_asize = vecp->i_len; iip->ili_format.ilf_asize = vecp->i_len;
vecp++; vecp++;
nvecs++; nvecs++;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment