From d84d6c1a7f1e2de9e601703a326a4c1b7b421943 Mon Sep 17 00:00:00 2001 From: Norbert Szetei Date: Wed, 7 Oct 2026 16:43:22 +0200 Subject: [PATCH 1/2] xfs: stop exchanging reflink flags when exchanging mappings When an exchange covers both files from offset 0 to i_disk_size, xmi_can_exchange_reflink_flags() assumes every mapping moved and hands the reflink flag over to the other file. That assumption is wrong. A file can still own shared blocks past i_disk_size, e.g. after EXCHANGE_RANGE_TO_EOF sets a smaller size without unmapping anything. The flag is cleared anyway, and the next write to such a block happens in place instead of CoW, corrupting the other file that shares it. Commit a23eca88448e ("xfs: fix exchange-range reflink flag clearing issue with INO1_WRITTEN") fixed one instance of this. Rather than add another special case, stop moving the flags. xfs_exchmaps_ensure_reflink() already sets the flag on both inodes before the exchange, so both just keep it. Nothing sets CLEAR_INO{1,2}_REFLINK anymore. Intents logged by older kernels may still carry them; recovery already masks them off, so they stay in the log format mask and are ignored. XFS_IOC_SWAPEXT has the same problem: it moves the reflink flag from one inode to the other along with the extents. Just removing that is not enough here: the exchange path flags both inodes up front in xfs_exchmaps_ensure_reflink(), but swapext has no such step, so the inode receiving the shared extents would be left without the flag. Set it on both inodes instead, and make sure both have a CoW fork, since an inode with the reflink flag is expected to have one. The flag now stays until FALLOC_FL_UNSHARE_RANGE, xfs_scrub, or a truncate to zero removes it. Fixes: 966ceafc7a43 ("xfs: create deferred log items for file mapping exchanges") Fixes: f0bc4d134b46 ("xfs: swap inode reflink flags when swapping inode extents") Cc: stable@vger.kernel.org # v6.10 Assisted-by: LLM Signed-off-by: Norbert Szetei Reviewed-by: Dave Chinner Reviewed-by: Darrick J. Wong Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_exchmaps.c | 80 ++-------------------------------- fs/xfs/libxfs/xfs_log_format.h | 4 +- fs/xfs/xfs_bmap_util.c | 15 +++---- 3 files changed, 10 insertions(+), 89 deletions(-) diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c index 6a66b6075e0a..7af8ee35c89d 100644 --- a/fs/xfs/libxfs/xfs_exchmaps.c +++ b/fs/xfs/libxfs/xfs_exchmaps.c @@ -49,7 +49,7 @@ struct xfs_exchmaps_adjacent { .right2 = { .br_startblock = HOLESTARTBLOCK }, \ } -/* Information to reset reflink flag / CoW fork state after an exchange. */ +/* Information to reset CoW fork state after an exchange. */ /* * If the reflink flag is set on either inode, make sure it has an incore CoW @@ -127,9 +127,7 @@ xmi_has_more_exchange_work(const struct xfs_exchmaps_intent *xmi) static inline bool xmi_has_postop_work(const struct xfs_exchmaps_intent *xmi) { - return xmi->xmi_flags & (XFS_EXCHMAPS_CLEAR_INO1_REFLINK | - XFS_EXCHMAPS_CLEAR_INO2_REFLINK | - __XFS_EXCHMAPS_INO2_SHORTFORM); + return xmi->xmi_flags & __XFS_EXCHMAPS_INO2_SHORTFORM; } /* Check all mappings to make sure we can actually exchange them. */ @@ -525,18 +523,6 @@ free: return error; } -/* Clear the reflink flag after an exchange. */ -static inline void -xfs_exchmaps_clear_reflink( - struct xfs_trans *tp, - struct xfs_inode *ip) -{ - trace_xfs_reflink_unset_inode_flag(ip); - - ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; - xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); -} - /* Finish whatever work might come after an exchange operation. */ static int xfs_exchmaps_do_postop_work( @@ -557,16 +543,6 @@ xfs_exchmaps_do_postop_work( return error; } - if (xmi->xmi_flags & XFS_EXCHMAPS_CLEAR_INO1_REFLINK) { - xfs_exchmaps_clear_reflink(tp, xmi->xmi_ip1); - xmi->xmi_flags &= ~XFS_EXCHMAPS_CLEAR_INO1_REFLINK; - } - - if (xmi->xmi_flags & XFS_EXCHMAPS_CLEAR_INO2_REFLINK) { - xfs_exchmaps_clear_reflink(tp, xmi->xmi_ip2); - xmi->xmi_flags &= ~XFS_EXCHMAPS_CLEAR_INO2_REFLINK; - } - return 0; } @@ -948,46 +924,13 @@ xfs_exchmaps_intent_destroy_cache(void) } /* - * Decide if we will exchange the reflink flags between the two files after the - * exchange. The only time we want to do this is if we're exchanging all - * mappings under EOF and the inode reflink flags have different states. + * Allocate and initialize a new incore intent item from a request. */ -static inline bool -xmi_can_exchange_reflink_flags( - const struct xfs_exchmaps_req *req, - unsigned int reflink_state) -{ - struct xfs_mount *mp = req->ip1->i_mount; - - /* - * The INO1_WRITTEN optimization can skip exchanging hole and - * unwritten mappings, which means we cannot guarantee that all - * shared extents actually moved to the other file. Clearing the - * reflink flag of an inode that still holds shared extents breaks - * the CoW write path, so refuse to exchange the flags in that case. - */ - if (req->flags & XFS_EXCHMAPS_INO1_WRITTEN) - return false; - - if (hweight32(reflink_state) != 1) - return false; - if (req->startoff1 != 0 || req->startoff2 != 0) - return false; - if (req->blockcount != XFS_B_TO_FSB(mp, req->ip1->i_disk_size)) - return false; - if (req->blockcount != XFS_B_TO_FSB(mp, req->ip2->i_disk_size)) - return false; - return true; -} - - -/* Allocate and initialize a new incore intent item from a request. */ struct xfs_exchmaps_intent * xfs_exchmaps_init_intent( const struct xfs_exchmaps_req *req) { struct xfs_exchmaps_intent *xmi; - unsigned int rs = 0; xmi = kmem_cache_zalloc(xfs_exchmaps_intent_cache, GFP_NOFS | __GFP_NOFAIL); @@ -1011,23 +954,6 @@ xfs_exchmaps_init_intent( xmi->xmi_isize2 = req->ip1->i_disk_size; } - /* Record the state of each inode's reflink flag before the op. */ - if (xfs_is_reflink_inode(req->ip1)) - rs |= 1; - if (xfs_is_reflink_inode(req->ip2)) - rs |= 2; - - /* - * Figure out if we're clearing the reflink flags (which effectively - * exchanges them) after the operation. - */ - if (xmi_can_exchange_reflink_flags(req, rs)) { - if (rs & 1) - xmi->xmi_flags |= XFS_EXCHMAPS_CLEAR_INO1_REFLINK; - if (rs & 2) - xmi->xmi_flags |= XFS_EXCHMAPS_CLEAR_INO2_REFLINK; - } - if (S_ISDIR(VFS_I(xmi->xmi_ip2)->i_mode) || S_ISLNK(VFS_I(xmi->xmi_ip2)->i_mode)) xmi->xmi_flags |= __XFS_EXCHMAPS_INO2_SHORTFORM; diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h index a4e1b3eb425c..6e620380d5dc 100644 --- a/fs/xfs/libxfs/xfs_log_format.h +++ b/fs/xfs/libxfs/xfs_log_format.h @@ -927,10 +927,8 @@ struct xfs_xmi_log_format { */ #define XFS_EXCHMAPS_INO1_WRITTEN (1ULL << 2) -/* Clear the reflink flag from inode1 after the operation. */ +/* No longer set, but older intents may carry them; keep them valid. */ #define XFS_EXCHMAPS_CLEAR_INO1_REFLINK (1ULL << 3) - -/* Clear the reflink flag from inode2 after the operation. */ #define XFS_EXCHMAPS_CLEAR_INO2_REFLINK (1ULL << 4) #define XFS_EXCHMAPS_LOGGED_FLAGS (XFS_EXCHMAPS_ATTR_FORK | \ diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c index 268d159339d0..865aec3ae5ab 100644 --- a/fs/xfs/xfs_bmap_util.c +++ b/fs/xfs/xfs_bmap_util.c @@ -1544,7 +1544,6 @@ xfs_swap_extents( struct xfs_bstat *sbp = &sxp->sx_stat; int src_log_flags, target_log_flags; int error = 0; - uint64_t f; int resblks = 0; unsigned int flags = 0; struct timespec64 ctime, mtime; @@ -1700,14 +1699,12 @@ xfs_swap_extents( if (error) goto out_trans_cancel; - /* Do we have to swap reflink flags? */ - if ((ip->i_diflags2 & XFS_DIFLAG2_REFLINK) ^ - (tip->i_diflags2 & XFS_DIFLAG2_REFLINK)) { - f = ip->i_diflags2 & XFS_DIFLAG2_REFLINK; - ip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; - ip->i_diflags2 |= tip->i_diflags2 & XFS_DIFLAG2_REFLINK; - tip->i_diflags2 &= ~XFS_DIFLAG2_REFLINK; - tip->i_diflags2 |= f & XFS_DIFLAG2_REFLINK; + /* Either inode may now own shared blocks; flag both, with CoW forks. */ + if ((ip->i_diflags2 | tip->i_diflags2) & XFS_DIFLAG2_REFLINK) { + ip->i_diflags2 |= XFS_DIFLAG2_REFLINK; + tip->i_diflags2 |= XFS_DIFLAG2_REFLINK; + xfs_ifork_init_cow(ip); + xfs_ifork_init_cow(tip); } /* Swap the cow forks. */ From 7dfb218c829c1acb626e0fe92c5fddb9a26a03e9 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 7 Oct 2026 10:02:27 -0700 Subject: [PATCH 2/2] xfs: fix exchange-range-to-eof file size exchange Norbert Szetei posted a patch containing an incomplete description of a bug in XFS_IOC_EXCHANGE_RANGE's TO_EOF flag. The bug tricks exchange-range into modifying a file so that it has shared blocks starting beyond EOF, which is never allowed because files never have written data beyond EOF, and you can only share written data blocks. This is key to all the incorrect behavior that follows. Eventually I got from Norbert a description of what's going wrong: > Fair. Here it is with physical block numbers, 4k blocks. peer is the file > that gets rewritten and file1 is the one that ends up with the flag > cleared. > > Start, nothing shared: > > peer size 4096 -> [100] > file1 size 12288 -> [200] [201] [202] > donor1 size 4096 -> [300] > donor2 size 4096 -> [400] > > 1. FICLONERANGE peer's block into file1's middle slot: > > peer size 4096 -> [100] > file1 size 12288 -> [200] [100] [202] reflink flag set > ^^^^^ both files own block 100 > > 2. XFS_IOC_EXCHANGE_RANGE file1 against donor1, file1_offset 0, > file2_offset 8192, length 0, TO_EOF. One block is exchanged, and the sizes > are exchanged with it: > > file1 size 4096 -> [200] [100] [300] reflink flag set > ^^^^^^^^^^^ still owned, now past the size > donor1 size 12288 -> [202] > > file1 says it is one block long while it still owns three. Nothing was > unmapped. file2_offset is block 2, so this exchange cannot clear a flag. > > 3. XFS_IOC_EXCHANGE_RANGE file1 against donor2, both offsets 0, length 4096. > By i_disk_size this is two one-block files exchanging everything, so > xmi_can_exchange_reflink_flags() agrees and the flag is cleared: > > file1 size 4096 -> [400] [100] [300] reflink flag CLEARED > donor2 size 4096 -> [200] > > Block 100 is still shared with peer. > > 4. pwrite(file1, 4096, 4096), which is file1's second slot, block 100. > xfs_is_cow_inode(file1) is false, so no CoW: > > peer size 4096 -> [100] same block, new contents > > Block 100 is the only one that matters here. PoC below, it reads a file > called peer in the current directory. The filesystem needs reflink and > exchange-range, which mkfs.xfs 7.x turns on by default. So yes, TO_EOF is screwing up the file size even if it's actually exchanging the data block correctly. The following is the intended behavior of XFS_EXCHANGE_RANGE_TO_EOF, as described by its manpage: "Ignore the length parameter. All bytes in file1_fd from file1_offset to EOF are moved to file2_fd, and file2's size is set to (file2_offset+(file1_length-file1_offset)). Meanwhile, all bytes in file2 from file2_offset to EOF are moved to file1 and file1's size is set to (file1_offset+(file2_length-file2_offset))." In other words, if we only exchange a portion of the file data, then we should only exchange the portion of the file size that relates to the exchanged data. Unfortunately, the code swaps the ondisk file size and the incore file sizes, which is incorrect if the caller passes in a nonzero offset. Having confused the file sizes, the PoC uses a second exchange-range call on what looks like a non-reflinked single-block file. Because the file size is set incorrectly, exchange-range thinks it's exchanging the full contents of two files and clears the reflink flag on the broken file. That enables an extending write of the broken file to rewrite the shared block that's just past EOF. This has become known colloquially as refluxfs. Once the file sizes are set correctly, the second exchange-range no longer thinks that it's doing a full-contents swap, so it won't clear the reflink flag on either of its file arguments. Norbert followed up to an earlier version of this patch with a second complaint about us not handling the i_disk_size state correctly: > The offsets are bounded against the incore i_size but subtracted from > the ondisk i_disk_size, so a file that has not been written back gives > xmi_isize1 = 0 + (0 - 12288). > > For instance, you can do: > > $ xfs_io -f -c "pwrite -q 0 4096" -c fsync file1 > $ xfs_io -f -c "pwrite -q 0 12288" \ > -c "exchangerange -s 0 -d 12288 file1" dirty > $ stat -c %s file1 > 0 > $ stat -c %i file1 > 131 > $ sudo xfs_io -r -c "bulkstat_single 131" . | grep bs_size > bs_size = 18446744073709539328 That's wrong, and the new file size update logic depends on the ondisk i_disk_size matching the incore i_size, so flush the pagecache as needed to push it upwards. Link: https://lore.kernel.org/linux-xfs/1E196589-DEBE-40AC-AFEA-D420DAAB067F@doyensec.com/ Reported-by: Norbert Szetei Cc: stable@vger.kernel.org # v6.10 Fixes: 966ceafc7a4371 ("xfs: create deferred log items for file mapping exchanges") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Carlos Maiolino --- fs/xfs/libxfs/xfs_exchmaps.c | 13 +++++++-- fs/xfs/xfs_exchrange.c | 51 ++++++++++++++++++++++++++---------- 2 files changed, 48 insertions(+), 16 deletions(-) diff --git a/fs/xfs/libxfs/xfs_exchmaps.c b/fs/xfs/libxfs/xfs_exchmaps.c index 7af8ee35c89d..f527fce46def 100644 --- a/fs/xfs/libxfs/xfs_exchmaps.c +++ b/fs/xfs/libxfs/xfs_exchmaps.c @@ -931,6 +931,7 @@ xfs_exchmaps_init_intent( const struct xfs_exchmaps_req *req) { struct xfs_exchmaps_intent *xmi; + struct xfs_mount *mp = req->ip1->i_mount; xmi = kmem_cache_zalloc(xfs_exchmaps_intent_cache, GFP_NOFS | __GFP_NOFAIL); @@ -948,10 +949,18 @@ xfs_exchmaps_init_intent( return xmi; } + /* + * If the caller wanted, set each file's size to that file's exchange + * offset + length exchanged from the other file because the ranges in + * each file might be different lengths. + */ if (req->flags & XFS_EXCHMAPS_SET_SIZES) { + loff_t off1 = XFS_FSB_TO_B(mp, xmi->xmi_startoff1); + loff_t off2 = XFS_FSB_TO_B(mp, xmi->xmi_startoff2); + xmi->xmi_flags |= XFS_EXCHMAPS_SET_SIZES; - xmi->xmi_isize1 = req->ip2->i_disk_size; - xmi->xmi_isize2 = req->ip1->i_disk_size; + xmi->xmi_isize1 = off1 + (req->ip2->i_disk_size - off2); + xmi->xmi_isize2 = off2 + (req->ip1->i_disk_size - off1); } if (S_ISDIR(VFS_I(xmi->xmi_ip2)->i_mode) || diff --git a/fs/xfs/xfs_exchrange.c b/fs/xfs/xfs_exchrange.c index fafb4e3f065c..935b561dfd3c 100644 --- a/fs/xfs/xfs_exchrange.c +++ b/fs/xfs/xfs_exchrange.c @@ -290,17 +290,20 @@ retry: goto out_unlock; /* - * If the caller wanted us to exchange the contents of two complete - * files of unequal length, exchange the incore sizes now. This should - * be safe because we flushed both files' page caches, exchanged all - * the mappings, and updated the ondisk sizes. + * If the caller wanted, set each file's size to that file's exchange + * offset + length exchanged from the other file because the ranges in + * each file might be different lengths. This should be safe because + * we flushed both files' page caches, exchanged all the mappings, and + * updated the ondisk sizes. */ if (fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF) { - loff_t temp; + loff_t old_ip1_size = i_size_read(VFS_I(ip1)); + loff_t old_ip2_size = i_size_read(VFS_I(ip2)); - temp = i_size_read(VFS_I(ip2)); - i_size_write(VFS_I(ip2), i_size_read(VFS_I(ip1))); - i_size_write(VFS_I(ip1), temp); + i_size_write(VFS_I(ip2), fxr->file2_offset + + (old_ip1_size - fxr->file1_offset)); + i_size_write(VFS_I(ip1), fxr->file1_offset + + (old_ip2_size - fxr->file2_offset)); } out_unlock: @@ -445,6 +448,30 @@ xfs_exchange_range_checks( return blen == fxr->length ? 0 : -EINVAL; } +/* Flush all relevant dirty pagecache near the range to be exchanged. */ +static inline int +xfs_exchange_range_flush( + struct xfs_inode *ip, + const struct xfs_exchrange *fxr, + loff_t offset) +{ + /* + * If TO_EOF is set, the ondisk file size update logic depends on the + * ondisk file size matching the incore file size. Flush everything. + */ + if (fxr->flags & XFS_EXCHANGE_RANGE_TO_EOF) + return filemap_write_and_wait(VFS_I(ip)->i_mapping); + + /* + * Because we're updating the ondisk mappings, flush all dirty data + * between the ondisk size and the exchange offset to reduce the chance + * of zeroed file contents in that gap after a crash. + */ + return filemap_write_and_wait_range(VFS_I(ip)->i_mapping, + min(offset, ip->i_disk_size), + offset + fxr->length - 1); +} + /* * Check that the two inodes are eligible for range exchanges, the ranges make * sense, and then flush all dirty data. Caller must ensure that the inodes @@ -470,15 +497,11 @@ xfs_exchange_range_prep( if (!same_inode) inode_dio_wait(inode2); - error = filemap_write_and_wait_range(inode1->i_mapping, - fxr->file1_offset, - fxr->file1_offset + fxr->length - 1); + error = xfs_exchange_range_flush(XFS_I(inode1), fxr, fxr->file1_offset); if (error) return error; - error = filemap_write_and_wait_range(inode2->i_mapping, - fxr->file2_offset, - fxr->file2_offset + fxr->length - 1); + error = xfs_exchange_range_flush(XFS_I(inode2), fxr, fxr->file2_offset); if (error) return error;