From 0daaecacb83bc6b656a56393ab77a31c28139bc7 Mon Sep 17 00:00:00 2001 From: Brian Foster Date: Fri, 12 May 2017 10:44:08 -0700 Subject: xfs: fix indlen accounting error on partial delalloc conversion The delalloc -> real block conversion path uses an incorrect calculation in the case where the middle part of a delalloc extent is being converted. This is documented as a rare situation because XFS generally attempts to maximize contiguity by converting as much of a delalloc extent as possible. If this situation does occur, the indlen reservation for the two new delalloc extents left behind by the conversion of the middle range is calculated and compared with the original reservation. If more blocks are required, the delta is allocated from the global block pool. This delta value can be characterized as the difference between the new total requirement (temp + temp2) and the currently available reservation minus those blocks that have already been allocated (startblockval(PREV.br_startblock) - allocated). The problem is that the current code does not account for previously allocated blocks correctly. It subtracts the current allocation count from the (new - old) delta rather than the old indlen reservation. This means that more indlen blocks than have been allocated end up stashed in the remaining extents and free space accounting is broken as a result. Fix up the calculation to subtract the allocated block count from the original extent indlen and thus correctly allocate the reservation delta based on the difference between the new total requirement and the unused blocks from the original reservation. Also remove a bogus assert that contradicts the fact that the new indlen reservation can be larger than the original indlen reservation. Signed-off-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_bmap.c | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index f02eb7673392..8adb91b05588 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -2065,8 +2065,10 @@ xfs_bmap_add_extent_delay_real( } temp = xfs_bmap_worst_indlen(bma->ip, temp); temp2 = xfs_bmap_worst_indlen(bma->ip, temp2); - diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) - - (bma->cur ? bma->cur->bc_private.b.allocated : 0)); + diff = (int)(temp + temp2 - + (startblockval(PREV.br_startblock) - + (bma->cur ? + bma->cur->bc_private.b.allocated : 0))); if (diff > 0) { error = xfs_mod_fdblocks(bma->ip->i_mount, -((int64_t)diff), false); @@ -2123,7 +2125,6 @@ xfs_bmap_add_extent_delay_real( temp = da_new; if (bma->cur) temp += bma->cur->bc_private.b.allocated; - ASSERT(temp <= da_old); if (temp < da_old) xfs_mod_fdblocks(bma->ip->i_mount, (int64_t)(da_old - temp), false); -- cgit v1.2.3 From 6eadbf4c8ba816c10d1c97bed9aa861d9fd17809 Mon Sep 17 00:00:00 2001 From: Darrick J. Wong Date: Fri, 12 May 2017 10:44:08 -0700 Subject: xfs: BMAPX shouldn't barf on inline-format directories When we're fulfilling a BMAPX request, jump out early if the data fork is in local format. This prevents us from hitting a debugging check in bmapi_read and barfing errors back to userspace. The on-disk extent count check later isn't sufficient for IF_DELALLOC mode because da extents are in memory and not on disk. Signed-off-by: Darrick J. Wong Reviewed-by: Brian Foster Reviewed-by: Christoph Hellwig --- fs/xfs/xfs_bmap_util.c | 8 ++++++-- 1 file changed, 6 insertions(+), 2 deletions(-) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 2b954308a1d6..2e8851ee6759 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -582,9 +582,13 @@ xfs_getbmap( } break; default: + /* Local format data forks report no extents. */ + if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL) { + bmv->bmv_entries = 0; + return 0; + } if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS && - ip->i_d.di_format != XFS_DINODE_FMT_BTREE && - ip->i_d.di_format != XFS_DINODE_FMT_LOCAL) + ip->i_d.di_format != XFS_DINODE_FMT_BTREE) return -EINVAL; if (xfs_get_extsz_hint(ip) || -- cgit v1.2.3 From 6e747506dde195d3d05fe2bb8ef78aceba28a5e3 Mon Sep 17 00:00:00 2001 From: Darrick J. Wong Date: Fri, 12 May 2017 10:44:11 -0700 Subject: xfs: fix warnings about unused stack variables Reduce stack usage and get rid of compiler warnings by eliminating unused variables. Signed-off-by: Darrick J. Wong Reviewed-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_bmap.c | 2 -- 1 file changed, 2 deletions(-) diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 8adb91b05588..a7048eafa8e6 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1280,7 +1280,6 @@ xfs_bmap_read_extents( xfs_bmbt_rec_t *frp; xfs_fsblock_t nextbno; xfs_extnum_t num_recs; - xfs_extnum_t start; num_recs = xfs_btree_get_numrecs(block); if (unlikely(i + num_recs > room)) { @@ -1303,7 +1302,6 @@ xfs_bmap_read_extents( * Copy records into the extent records. */ frp = XFS_BMBT_REC_ADDR(mp, block, 1); - start = i; for (j = 0; j < num_recs; j++, i++, frp++) { xfs_bmbt_rec_host_t *trp = xfs_iext_get_ext(ifp, i); trp->l0 = be64_to_cpu(frp->l0); -- cgit v1.2.3 From 892d2a5f705723b2cb488bfb38bcbdcf83273184 Mon Sep 17 00:00:00 2001 From: Zorro Lang Date: Mon, 15 May 2017 08:40:02 -0700 Subject: xfs: bad assertion for delalloc an extent that start at i_size By run fsstress long enough time enough in RHEL-7, I find an assertion failure (harder to reproduce on linux-4.11, but problem is still there): XFS: Assertion failed: (iflags & BMV_IF_DELALLOC) != 0, file: fs/xfs/xfs_bmap_util.c The assertion is in xfs_getbmap() funciton: if (map[i].br_startblock == DELAYSTARTBLOCK && --> map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip))) ASSERT((iflags & BMV_IF_DELALLOC) != 0); When map[i].br_startoff == XFS_B_TO_FSB(mp, XFS_ISIZE(ip)), the startoff is just at EOF. But we only need to make sure delalloc extents that are within EOF, not include EOF. Signed-off-by: Zorro Lang Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_bmap_util.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 2e8851ee6759..9e3cc2146d5b 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -716,7 +716,7 @@ xfs_getbmap( * extents. */ if (map[i].br_startblock == DELAYSTARTBLOCK && - map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip))) + map[i].br_startoff < XFS_B_TO_FSB(mp, XFS_ISIZE(ip))) ASSERT((iflags & BMV_IF_DELALLOC) != 0); if (map[i].br_startblock == HOLESTARTBLOCK && -- cgit v1.2.3 From ea9a46e1c49251331dbfda19ced7114337966178 Mon Sep 17 00:00:00 2001 From: Darrick J. Wong Date: Fri, 12 May 2017 10:44:10 -0700 Subject: xfs: only return detailed fsmap info if the caller has CAP_SYS_ADMIN There were a number of handwaving complaints that one could "possibly" use inode numbers and extent maps to fingerprint a filesystem hosting multiple containers and somehow use the information to guess at the contents of other containers and attack them. Despite the total lack of any demonstration that this is actually possible, it's easier to restrict access now and broaden it later, so use the rmapbt fsmap backends only if the caller has CAP_SYS_ADMIN. Unprivileged users will just have to make do with only getting the free space and static metadata placement information. Signed-off-by: Darrick J. Wong Reviewed-by: Carlos Maiolino --- fs/xfs/xfs_fsmap.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c index 3683819887a5..814ed729881d 100644 --- a/fs/xfs/xfs_fsmap.c +++ b/fs/xfs/xfs_fsmap.c @@ -828,6 +828,7 @@ xfs_getfsmap( struct xfs_fsmap dkeys[2]; /* per-dev keys */ struct xfs_getfsmap_dev handlers[XFS_GETFSMAP_DEVS]; struct xfs_getfsmap_info info = { NULL }; + bool use_rmap; int i; int error = 0; @@ -837,12 +838,14 @@ xfs_getfsmap( !xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[1])) return -EINVAL; + use_rmap = capable(CAP_SYS_ADMIN) && + xfs_sb_version_hasrmapbt(&mp->m_sb); head->fmh_entries = 0; /* Set up our device handlers. */ memset(handlers, 0, sizeof(handlers)); handlers[0].dev = new_encode_dev(mp->m_ddev_targp->bt_dev); - if (xfs_sb_version_hasrmapbt(&mp->m_sb)) + if (use_rmap) handlers[0].fn = xfs_getfsmap_datadev_rmapbt; else handlers[0].fn = xfs_getfsmap_datadev_bnobt; -- cgit v1.2.3 From 3ecb3ac7b950ff8f6c6a61e8b7b0d6e3546429a0 Mon Sep 17 00:00:00 2001 From: Darrick J. Wong Date: Mon, 15 May 2017 19:16:15 -0700 Subject: xfs: avoid mount-time deadlock in CoW extent recovery If a malicious user corrupts the refcount btree to cause a cycle between different levels of the tree, the next mount attempt will deadlock in the CoW recovery routine while grabbing buffer locks. We can use the ability to re-grab a buffer that was previous locked to a transaction to avoid deadlocks, so do that here. Signed-off-by: Darrick J. Wong Reviewed-by: Brian Foster --- fs/xfs/libxfs/xfs_refcount.c | 43 +++++++++++++++++++++++++++++++------------ 1 file changed, 31 insertions(+), 12 deletions(-) diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index b177ef33cd4c..82a38d86ebad 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1629,13 +1629,28 @@ xfs_refcount_recover_cow_leftovers( if (mp->m_sb.sb_agblocks >= XFS_REFC_COW_START) return -EOPNOTSUPP; - error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp); + INIT_LIST_HEAD(&debris); + + /* + * In this first part, we use an empty transaction to gather up + * all the leftover CoW extents so that we can subsequently + * delete them. The empty transaction is used to avoid + * a buffer lock deadlock if there happens to be a loop in the + * refcountbt because we're allowed to re-grab a buffer that is + * already attached to our transaction. When we're done + * recording the CoW debris we cancel the (empty) transaction + * and everything goes away cleanly. + */ + error = xfs_trans_alloc_empty(mp, &tp); if (error) return error; - cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL); + + error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp); + if (error) + goto out_trans; + cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL); /* Find all the leftover CoW staging extents. */ - INIT_LIST_HEAD(&debris); memset(&low, 0, sizeof(low)); memset(&high, 0, sizeof(high)); low.rc.rc_startblock = XFS_REFC_COW_START; @@ -1645,10 +1660,11 @@ xfs_refcount_recover_cow_leftovers( if (error) goto out_cursor; xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR); - xfs_buf_relse(agbp); + xfs_trans_brelse(tp, agbp); + xfs_trans_cancel(tp); /* Now iterate the list to free the leftovers */ - list_for_each_entry(rr, &debris, rr_list) { + list_for_each_entry_safe(rr, n, &debris, rr_list) { /* Set up transaction. */ error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp); if (error) @@ -1676,8 +1692,16 @@ xfs_refcount_recover_cow_leftovers( error = xfs_trans_commit(tp); if (error) goto out_free; + + list_del(&rr->rr_list); + kmem_free(rr); } + return error; +out_defer: + xfs_defer_cancel(&dfops); +out_trans: + xfs_trans_cancel(tp); out_free: /* Free the leftover list */ list_for_each_entry_safe(rr, n, &debris, rr_list) { @@ -1688,11 +1712,6 @@ out_free: out_cursor: xfs_btree_del_cursor(cur, XFS_BTREE_ERROR); - xfs_buf_relse(agbp); - goto out_free; - -out_defer: - xfs_defer_cancel(&dfops); - xfs_trans_cancel(tp); - goto out_free; + xfs_trans_brelse(tp, agbp); + goto out_trans; } -- cgit v1.2.3 From a4d768e702de224cc85e0c8eac9311763403b368 Mon Sep 17 00:00:00 2001 From: Eric Sandeen Date: Mon, 22 May 2017 19:54:10 -0700 Subject: xfs: fix unaligned access in xfs_btree_visit_blocks This structure copy was throwing unaligned access warnings on sparc64: Kernel unaligned access at TPC[1043c088] xfs_btree_visit_blocks+0x88/0xe0 [xfs] xfs_btree_copy_ptrs does a memcpy, which avoids it. Signed-off-by: Eric Sandeen Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_btree.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c index 5392674bf893..3a673ba201aa 100644 --- a/fs/xfs/libxfs/xfs_btree.c +++ b/fs/xfs/libxfs/xfs_btree.c @@ -4395,7 +4395,7 @@ xfs_btree_visit_blocks( xfs_btree_readahead_ptr(cur, ptr, 1); /* save for the next iteration of the loop */ - lptr = *ptr; + xfs_btree_copy_ptrs(cur, &lptr, ptr, 1); } /* for each buffer in the level */ -- cgit v1.2.3 From 8affebe16d79ebefb1d9d6d56a46dc89716f9453 Mon Sep 17 00:00:00 2001 From: Eryu Guan Date: Tue, 23 May 2017 08:30:46 -0700 Subject: xfs: fix off-by-one on max nr_pages in xfs_find_get_desired_pgoff() xfs_find_get_desired_pgoff() is used to search for offset of hole or data in page range [index, end] (both inclusive), and the max number of pages to search should be at least one, if end == index. Otherwise the only page is missed and no hole or data is found, which is not correct. When block size is smaller than page size, this can be demonstrated by preallocating a file with size smaller than page size and writing data to the last block. E.g. run this xfs_io command on a 1k block size XFS on x86_64 host. # xfs_io -fc "falloc 0 3k" -c "pwrite 2k 1k" \ -c "seek -d 0" /mnt/xfs/testfile wrote 1024/1024 bytes at offset 2048 1 KiB, 1 ops; 0.0000 sec (33.675 MiB/sec and 34482.7586 ops/sec) Whence Result DATA EOF Data at offset 2k was missed, and lseek(2) returned ENXIO. This is uncovered by generic/285 subtest 07 and 08 on ppc64 host, where pagesize is 64k. Because a recent change to generic/285 reduced the preallocated file size to smaller than 64k. Cc: stable@vger.kernel.org # v3.7+ Signed-off-by: Eryu Guan Reviewed-by: Jan Kara Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index 35703a801372..aefa2134a8cb 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1049,7 +1049,7 @@ xfs_find_get_desired_pgoff( unsigned nr_pages; unsigned int i; - want = min_t(pgoff_t, end - index, PAGEVEC_SIZE); + want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1; nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want); /* -- cgit v1.2.3 From 5375023ae1266553a7baa0845e82917d8803f48c Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 18 May 2017 16:36:22 -0700 Subject: xfs: Fix missed holes in SEEK_HOLE implementation XFS SEEK_HOLE implementation could miss a hole in an unwritten extent as can be seen by the following command: xfs_io -c "falloc 0 256k" -c "pwrite 0 56k" -c "pwrite 128k 8k" -c "seek -h 0" file wrote 57344/57344 bytes at offset 0 56 KiB, 14 ops; 0.0000 sec (49.312 MiB/sec and 12623.9856 ops/sec) wrote 8192/8192 bytes at offset 131072 8 KiB, 2 ops; 0.0000 sec (70.383 MiB/sec and 18018.0180 ops/sec) Whence Result HOLE 139264 Where we can see that hole at offset 56k was just ignored by SEEK_HOLE implementation. The bug is in xfs_find_get_desired_pgoff() which does not properly detect the case when pages are not contiguous. Fix the problem by properly detecting when found page has larger offset than expected. CC: stable@vger.kernel.org Fixes: d126d43f631f996daeee5006714fed914be32368 Signed-off-by: Jan Kara Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_file.c | 29 +++++++++-------------------- 1 file changed, 9 insertions(+), 20 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index aefa2134a8cb..f1517e9928c7 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1076,17 +1076,6 @@ xfs_find_get_desired_pgoff( break; } - /* - * At lease we found one page. If this is the first time we - * step into the loop, and if the first page index offset is - * greater than the given search offset, a hole was found. - */ - if (type == HOLE_OFF && lastoff == startoff && - lastoff < page_offset(pvec.pages[0])) { - found = true; - break; - } - for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; loff_t b_offset; @@ -1098,18 +1087,18 @@ xfs_find_get_desired_pgoff( * file mapping. However, page->index will not change * because we have a reference on the page. * - * Searching done if the page index is out of range. - * If the current offset is not reaches the end of - * the specified search range, there should be a hole - * between them. + * If current page offset is beyond where we've ended, + * we've found a hole. */ - if (page->index > end) { - if (type == HOLE_OFF && lastoff < endoff) { - *offset = lastoff; - found = true; - } + if (type == HOLE_OFF && lastoff < endoff && + lastoff < page_offset(pvec.pages[i])) { + found = true; + *offset = lastoff; goto out; } + /* Searching done if the page index is out of range. */ + if (page->index > end) + goto out; lock_page(page); /* -- cgit v1.2.3 From d7fd24257aa60316bf81093f7f909dc9475ae974 Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 18 May 2017 16:36:23 -0700 Subject: xfs: Fix off-by-in in loop termination in xfs_find_get_desired_pgoff() There is an off-by-one error in loop termination conditions in xfs_find_get_desired_pgoff() since 'end' may index a page beyond end of desired range if 'endoff' is page aligned. It doesn't have any visible effects but still it is good to fix it. Signed-off-by: Jan Kara Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_file.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index f1517e9928c7..dc0e4cb7029b 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1043,7 +1043,7 @@ xfs_find_get_desired_pgoff( index = startoff >> PAGE_SHIFT; endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount); - end = endoff >> PAGE_SHIFT; + end = (endoff - 1) >> PAGE_SHIFT; do { int want; unsigned nr_pages; -- cgit v1.2.3 From a54fba8f5a0dc36161cacdf2aa90f007f702ec1a Mon Sep 17 00:00:00 2001 From: Jan Kara Date: Thu, 18 May 2017 16:36:24 -0700 Subject: xfs: Move handling of missing page into one place in xfs_find_get_desired_pgoff() Currently several places in xfs_find_get_desired_pgoff() handle the case of a missing page. Make them all handled in one place after the loop has terminated. Signed-off-by: Jan Kara Reviewed-by: Brian Foster Reviewed-by: Darrick J. Wong Signed-off-by: Darrick J. Wong --- fs/xfs/xfs_file.c | 38 ++++++++------------------------------ 1 file changed, 8 insertions(+), 30 deletions(-) diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c index dc0e4cb7029b..5fb5a0958a14 100644 --- a/fs/xfs/xfs_file.c +++ b/fs/xfs/xfs_file.c @@ -1052,29 +1052,8 @@ xfs_find_get_desired_pgoff( want = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1; nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want); - /* - * No page mapped into given range. If we are searching holes - * and if this is the first time we got into the loop, it means - * that the given offset is landed in a hole, return it. - * - * If we have already stepped through some block buffers to find - * holes but they all contains data. In this case, the last - * offset is already updated and pointed to the end of the last - * mapped page, if it does not reach the endpoint to search, - * that means there should be a hole between them. - */ - if (nr_pages == 0) { - /* Data search found nothing */ - if (type == DATA_OFF) - break; - - ASSERT(type == HOLE_OFF); - if (lastoff == startoff || lastoff < endoff) { - found = true; - *offset = lastoff; - } + if (nr_pages == 0) break; - } for (i = 0; i < nr_pages; i++) { struct page *page = pvec.pages[i]; @@ -1140,21 +1119,20 @@ xfs_find_get_desired_pgoff( /* * The number of returned pages less than our desired, search - * done. In this case, nothing was found for searching data, - * but we found a hole behind the last offset. + * done. */ - if (nr_pages < want) { - if (type == HOLE_OFF) { - *offset = lastoff; - found = true; - } + if (nr_pages < want) break; - } index = pvec.pages[i - 1]->index + 1; pagevec_release(&pvec); } while (index <= end); + /* No page at lastoff and we are not done - we found a hole. */ + if (type == HOLE_OFF && lastoff < endoff) { + *offset = lastoff; + found = true; + } out: pagevec_release(&pvec); return found; -- cgit v1.2.3