From f1ccd2955157e1aff992f6aaaba0944209076220 Mon Sep 17 00:00:00 2001 From: Lachlan McIlroy Date: Fri, 26 Sep 2008 12:16:46 +1000 Subject: [XFS] Fix extent list corruption in xfs_iext_irec_compact_full(). If we don't move all the records from the next buffer into the current buffer then we need to update the er_extoff field of the next buffer as we shift the remaining records to the start of the buffer. SGI-PV: 987159 SGI-Modid: xfs-linux-melb:xfs-kern:32165a Signed-off-by: Lachlan McIlroy Signed-off-by: Eric Sandeen Signed-off-by: Russell Cattelan --- fs/xfs/xfs_inode.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs') diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 00e80df..419cfc2 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -4584,6 +4584,7 @@ xfs_iext_irec_compact_full( (XFS_LINEAR_EXTS - erp_next->er_extcount) * sizeof(xfs_bmbt_rec_t)); + erp_next->er_extoff += ext_diff; } } -- cgit v1.1 From 71a8c87fb300b601eacf7a86cc6c6322fe827bfd Mon Sep 17 00:00:00 2001 From: Lachlan McIlroy Date: Fri, 26 Sep 2008 12:17:57 +1000 Subject: [XFS] Remove xfs_iext_irec_compact_full() Yet another bug was found in xfs_iext_irec_compact_full() and while the source of the bug was found it wasn't an easy task to track it down because the conditions are very difficult to reproduce. A HUGE thank-you goes to Russell Cattelan and Eric Sandeen for their significant effort in tracking down the source of this corruption. xfs_iext_irec_compact_full() and xfs_iext_irec_compact_pages() are almost identical - they both compact indirect extent lists by moving extents from subsequent buffers into earlier ones. xfs_iext_irec_compact_pages() only moves extents if all of the extents in the next buffer will fit into the empty space in the buffer before it. xfs_iext_irec_compact_full() will go a step further and move part of the next buffer if all the extents wont fit. It will then shift the remaining extents in the next buffer up to the start of the buffer. The bug here was that we did not update er_extoff and this caused extent list corruption. It does not appear that this extra functionality gains us much. Calling xfs_iext_irec_compact_pages() instead will do a good enough job at compacting the indirect list and will be quicker too. For the case in xfs_iext_indirect_to_direct() the total number of extents in the indirect list will fit into one buffer so we will never need the extra functionality of xfs_iext_irec_compact_full() there. Also xfs_iext_irec_compact_pages() doesn't need to do a memmove() (the buffers will never overlap) so we don't want the performance hit that can incur. SGI-PV: 987159 SGI-Modid: xfs-linux-melb:xfs-kern:32166a Signed-off-by: Lachlan McIlroy Signed-off-by: Eric Sandeen --- fs/xfs/xfs_inode.c | 95 ++---------------------------------------------------- 1 file changed, 3 insertions(+), 92 deletions(-) (limited to 'fs') diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c index 419cfc2..dbd9cef 100644 --- a/fs/xfs/xfs_inode.c +++ b/fs/xfs/xfs_inode.c @@ -4118,7 +4118,7 @@ xfs_iext_indirect_to_direct( ASSERT(nextents <= XFS_LINEAR_EXTS); size = nextents * sizeof(xfs_bmbt_rec_t); - xfs_iext_irec_compact_full(ifp); + xfs_iext_irec_compact_pages(ifp); ASSERT(ifp->if_real_bytes == XFS_IEXT_BUFSZ); ep = ifp->if_u1.if_ext_irec->er_extbuf; @@ -4449,8 +4449,7 @@ xfs_iext_irec_remove( * compaction policy is as follows: * * Full Compaction: Extents fit into a single page (or inline buffer) - * Full Compaction: Extents occupy less than 10% of allocated space - * Partial Compaction: Extents occupy > 10% and < 50% of allocated space + * Partial Compaction: Extents occupy less than 50% of allocated space * No Compaction: Extents occupy at least 50% of allocated space */ void @@ -4471,8 +4470,6 @@ xfs_iext_irec_compact( xfs_iext_direct_to_inline(ifp, nextents); } else if (nextents <= XFS_LINEAR_EXTS) { xfs_iext_indirect_to_direct(ifp); - } else if (nextents < (nlists * XFS_LINEAR_EXTS) >> 3) { - xfs_iext_irec_compact_full(ifp); } else if (nextents < (nlists * XFS_LINEAR_EXTS) >> 1) { xfs_iext_irec_compact_pages(ifp); } @@ -4496,7 +4493,7 @@ xfs_iext_irec_compact_pages( erp_next = erp + 1; if (erp_next->er_extcount <= (XFS_LINEAR_EXTS - erp->er_extcount)) { - memmove(&erp->er_extbuf[erp->er_extcount], + memcpy(&erp->er_extbuf[erp->er_extcount], erp_next->er_extbuf, erp_next->er_extcount * sizeof(xfs_bmbt_rec_t)); erp->er_extcount += erp_next->er_extcount; @@ -4516,92 +4513,6 @@ xfs_iext_irec_compact_pages( } /* - * Fully compact the extent records managed by the indirection array. - */ -void -xfs_iext_irec_compact_full( - xfs_ifork_t *ifp) /* inode fork pointer */ -{ - xfs_bmbt_rec_host_t *ep, *ep_next; /* extent record pointers */ - xfs_ext_irec_t *erp, *erp_next; /* extent irec pointers */ - int erp_idx = 0; /* extent irec index */ - int ext_avail; /* empty entries in ex list */ - int ext_diff; /* number of exts to add */ - int nlists; /* number of irec's (ex lists) */ - - ASSERT(ifp->if_flags & XFS_IFEXTIREC); - - nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ; - erp = ifp->if_u1.if_ext_irec; - ep = &erp->er_extbuf[erp->er_extcount]; - erp_next = erp + 1; - ep_next = erp_next->er_extbuf; - - while (erp_idx < nlists - 1) { - /* - * Check how many extent records are available in this irec. - * If there is none skip the whole exercise. - */ - ext_avail = XFS_LINEAR_EXTS - erp->er_extcount; - if (ext_avail) { - - /* - * Copy over as many as possible extent records into - * the previous page. - */ - ext_diff = MIN(ext_avail, erp_next->er_extcount); - memcpy(ep, ep_next, ext_diff * sizeof(xfs_bmbt_rec_t)); - erp->er_extcount += ext_diff; - erp_next->er_extcount -= ext_diff; - - /* - * If the next irec is empty now we can simply - * remove it. - */ - if (erp_next->er_extcount == 0) { - /* - * Free page before removing extent record - * so er_extoffs don't get modified in - * xfs_iext_irec_remove. - */ - kmem_free(erp_next->er_extbuf); - erp_next->er_extbuf = NULL; - xfs_iext_irec_remove(ifp, erp_idx + 1); - erp = &ifp->if_u1.if_ext_irec[erp_idx]; - nlists = ifp->if_real_bytes / XFS_IEXT_BUFSZ; - - /* - * If the next irec is not empty move up the content - * that has not been copied to the previous page to - * the beggining of this one. - */ - } else { - memmove(erp_next->er_extbuf, &ep_next[ext_diff], - erp_next->er_extcount * - sizeof(xfs_bmbt_rec_t)); - ep_next = erp_next->er_extbuf; - memset(&ep_next[erp_next->er_extcount], 0, - (XFS_LINEAR_EXTS - - erp_next->er_extcount) * - sizeof(xfs_bmbt_rec_t)); - erp_next->er_extoff += ext_diff; - } - } - - if (erp->er_extcount == XFS_LINEAR_EXTS) { - erp_idx++; - if (erp_idx < nlists) - erp = &ifp->if_u1.if_ext_irec[erp_idx]; - else - break; - } - ep = &erp->er_extbuf[erp->er_extcount]; - erp_next = erp + 1; - ep_next = erp_next->er_extbuf; - } -} - -/* * This is called to update the er_extoff field in the indirection * array when extents have been added or removed from one of the * extent lists. erp_idx contains the irec index to begin updating -- cgit v1.1