Bail out if transaction can cause extent count to overflow
PATCH v15 16/16 xfs: Introduce error injection to allocate only minlen size extents for files
In reply to Chandan Babu RThis commit adds XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT error tag which helps userspace test programs to get xfs_bmap_btalloc() to always allocate minlen sized extents.
This is required for test programs which need a guarantee that minlen extents allocated for a file do not get merged with their existing neighbours in the inode's BMBT. "Inode fork extent overflow check" for Directories, Xattrs and extension of realtime inodes need this since the file offset at which the extents are being allocated cannot be explicitly controlled from userspace.
One way to use this error tag is to,
1. Consume all of the free space by sequentially writing to a file.
2. Punch alternate blocks of the file. This causes CNTBT to contain sufficient number of one block sized extent records.
3. Inject XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT error tag. After step 3, xfs_bmap_btalloc() will issue space allocation requests for minlen sized extents only.
ENOSPC error code is returned to userspace when there aren't any "one block sized" extents left in any of the AGs.
--- fs/xfs/libxfs/xfs_alloc.c | 50 ++++++++++++++ fs/xfs/libxfs/xfs_alloc.h | 3 + fs/xfs/libxfs/xfs_bmap.c | 124 ++++++++++++++++++++++++++++------- fs/xfs/libxfs/xfs_errortag.h | 4 +- fs/xfs/xfs_error.c | 3 + 5 files changed, 159 insertions(+), 25 deletions(-)
fs/xfs/libxfs/xfs_alloc.c +50 -0
@@ -2474,6 +2474,47 @@ xfs_defer_agfl_block(xfs_defer_add (tp,XFS_DEFER_OPS_TYPE_AGFL_FREE , &new->xefi_list); } +#ifdef DEBUG +/* +* Check if an AGF has a free extent record whose length is equal to +* args->minlen. +*/ +STATIC int +xfs_exact_minlen_extent_available ( +struct xfs_alloc_arg *args, +struct xfs_buf *agbp, +int *stat) +{ +struct xfs_btree_cur *cnt_cur; +xfs_agblock_t fbno; +xfs_extlen_t flen; +int error =0 ; + + cnt_cur =xfs_allocbt_init_cursor (args->mp, args->tp, agbp, + args->agno,XFS_BTNUM_CNT ); + error =xfs_alloc_lookup_ge (cnt_cur,0 , args->minlen, stat); +if (error) + goto out; + +if (*stat ==0 ) { + error = -EFSCORRUPTED ; + goto out; + } + + error =xfs_alloc_get_rec (cnt_cur, &fbno, &flen, stat); +if (error) + goto out; + +if (*stat ==1 && flen != args->minlen) + *stat =0 ; + +out: +xfs_btree_del_cursor (cnt_cur, error); + +return error; +} +#endif +/* * Decide whether to use this allocation group for this allocation. * If so, fix up the btree freelist's size.
@@ -2545,6 +2586,15 @@ xfs_alloc_fix_freelist(if (!xfs_alloc_space_available (args, need, flags)) goto out_agbp_relse; +#ifdef DEBUG +if (args->alloc_minlen_only) { +int stat; + + error =xfs_exact_minlen_extent_available (args, agbp, &stat); +if (error || !stat) + goto out_agbp_relse; + } +#endif /* * Make the freelist shorter if it's too long. *
fs/xfs/libxfs/xfs_alloc.h +3 -0
@@ -75,6 +75,9 @@ typedef struct xfs_alloc_arg {char wasfromfl;/* set if allocation is from freelist */ struct xfs_owner_info oinfo;/* owner of blocks being allocated */ enum xfs_ag_resv_type resv;/* block reservation to use */ +#ifdef DEBUG +bool alloc_minlen_only;/* allocate exact minlen extent */ +#endif } xfs_alloc_arg_t;/*
fs/xfs/libxfs/xfs_bmap.c +100 -24
150 lines not on this page · raw message
fs/xfs/libxfs/xfs_errortag.h +3 -1
@@ -57,7 +57,8 @@#define XFS_ERRTAG_IUNLINK_FALLBACK 34#define XFS_ERRTAG_BUF_IOERROR 35#define XFS_ERRTAG_REDUCE_MAX_IEXTENTS 36 -#define XFS_ERRTAG_MAX 37 +#define XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT 37 +#define XFS_ERRTAG_MAX 38/* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -99,5 +100,6 @@#define XFS_RANDOM_IUNLINK_FALLBACK (XFS_RANDOM_DEFAULT/10)#define XFS_RANDOM_BUF_IOERROR XFS_RANDOM_DEFAULT#define XFS_RANDOM_REDUCE_MAX_IEXTENTS 1 +#define XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT 1#endif /* __XFS_ERRORTAG_H_ */
fs/xfs/xfs_error.c +3 -0
@@ -55,6 +55,7 @@ static unsigned int xfs_errortag_random_default[] = {XFS_RANDOM_IUNLINK_FALLBACK ,XFS_RANDOM_BUF_IOERROR ,XFS_RANDOM_REDUCE_MAX_IEXTENTS , + XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT, }; struct xfs_errortag_attr {
@@ -166,6 +167,7 @@ XFS_ERRORTAG_ATTR_RW(bad_summary, XFS_ERRTAG_FORCE_SUMMARY_RECALC);XFS_ERRORTAG_ATTR_RW (iunlink_fallback,XFS_ERRTAG_IUNLINK_FALLBACK );XFS_ERRORTAG_ATTR_RW (buf_ioerror,XFS_ERRTAG_BUF_IOERROR );XFS_ERRORTAG_ATTR_RW (reduce_max_iextents,XFS_ERRTAG_REDUCE_MAX_IEXTENTS ); +XFS_ERRORTAG_ATTR_RW (bmap_alloc_minlen_extent,XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT );static struct attribute *xfs_errortag_attrs[] = {XFS_ERRORTAG_ATTR_LIST (noerror),
@@ -205,6 +207,7 @@ static struct attribute *xfs_errortag_attrs[] = {XFS_ERRORTAG_ATTR_LIST (iunlink_fallback),XFS_ERRORTAG_ATTR_LIST (buf_ioerror),XFS_ERRORTAG_ATTR_LIST (reduce_max_iextents), +XFS_ERRORTAG_ATTR_LIST (bmap_alloc_minlen_extent), NULL, };
Signature · 1 line
2.29.2
PATCH v15 9/16 xfs: Check for extent overflow when moving extent from cow to data fork
In reply to Chandan Babu RMoving an extent to data fork can cause a sub-interval of an existing extent to be unmapped. This will increase extent count by 1. Mapping in the new extent can increase the extent count by 1 again i.e.
| Old extent | New extent | Old extent |
Hence number of extents increases by 2.
--- fs/xfs/libxfs/xfs_inode_fork.h | 9 +++++++++ fs/xfs/xfs_reflink.c | 5 +++++ 2 files changed, 14 insertions(+)
fs/xfs/libxfs/xfs_inode_fork.h +9 -0
@@ -79,6 +79,15 @@ struct xfs_ifork {#define XFS_IEXT_WRITE_UNWRITTEN_CNT (2) +/* +* Moving an extent to data fork can cause a sub-interval of an existing extent +* to be unmapped. This will increase extent count by 1. Mapping in the new +* extent can increase the extent count by 1 again i.e. +* | Old extent | New extent | Old extent | +* Hence number of extents increases by 2. +*/ +#define XFS_IEXT_REFLINK_END_COW_CNT (2) +/* * Fork handling. */
fs/xfs/xfs_reflink.c +5 -0
@@ -628,6 +628,11 @@ xfs_reflink_end_cow_extent(xfs_ilock (ip,XFS_ILOCK_EXCL );xfs_trans_ijoin (tp, ip,0 ); + error =xfs_iext_count_may_overflow (ip,XFS_DATA_FORK , +XFS_IEXT_REFLINK_END_COW_CNT ); +if (error) + goto out_cancel; +/* * In case of racing, overlapping AIO writes no COW extents might be * left by the time I/O completes for the loser of the race. In that
Signature · 1 line
2.29.2
PATCH v15 10/16 xfs: Check for extent overflow when remapping an extent
In reply to Chandan Babu RRemapping an extent involves unmapping the existing extent and mapping in the new extent. When unmapping, an extent containing the entire unmap range can be split into two extents,
i.e. | Old extent | hole | Old extent |
Hence extent count increases by 1.
Mapping in the new extent into the destination file can increase the extent count by 1.
--- fs/xfs/xfs_reflink.c | 11 +++++++++++ 1 file changed, 11 insertions(+)
fs/xfs/xfs_reflink.c +11 -0
@@ -1006,6 +1006,7 @@ xfs_reflink_remap_extent(unsigned int resblks;bool smap_real;bool dmap_written =xfs_bmap_is_written_extent (dmap); +int iext_delta =0 ;int nimaps;int error;
@@ -1099,6 +1100,16 @@ xfs_reflink_remap_extent( goto out_cancel; } +if (smap_real) + ++iext_delta; + +if (dmap_written) + ++iext_delta; + + error =xfs_iext_count_may_overflow (ip,XFS_DATA_FORK , iext_delta); +if (error) + goto out_cancel; +if (smap_real) {/* * If the extent we're unmapping is backed by storage (written
Signature · 1 line
2.29.2
PATCH v15 12/16 xfs: Introduce error injection to reduce maximum inode fork extent count
In reply to Chandan Babu RThis commit adds XFS_ERRTAG_REDUCE_MAX_IEXTENTS error tag which enables userspace programs to test "Inode fork extent count overflow detection" by reducing maximum possible inode fork extent count to 10.
--- fs/xfs/libxfs/xfs_errortag.h | 4 +++- fs/xfs/libxfs/xfs_inode_fork.c | 4 ++++ fs/xfs/xfs_error.c | 3 +++ 3 files changed, 10 insertions(+), 1 deletion(-)
fs/xfs/libxfs/xfs_errortag.h +3 -1
@@ -56,7 +56,8 @@#define XFS_ERRTAG_FORCE_SUMMARY_RECALC 33#define XFS_ERRTAG_IUNLINK_FALLBACK 34#define XFS_ERRTAG_BUF_IOERROR 35 -#define XFS_ERRTAG_MAX 36 +#define XFS_ERRTAG_REDUCE_MAX_IEXTENTS 36 +#define XFS_ERRTAG_MAX 37/* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -97,5 +98,6 @@#define XFS_RANDOM_FORCE_SUMMARY_RECALC 1#define XFS_RANDOM_IUNLINK_FALLBACK (XFS_RANDOM_DEFAULT/10)#define XFS_RANDOM_BUF_IOERROR XFS_RANDOM_DEFAULT +#define XFS_RANDOM_REDUCE_MAX_IEXTENTS 1#endif /* __XFS_ERRORTAG_H_ */
fs/xfs/libxfs/xfs_inode_fork.c +4 -0
@@ -24,6 +24,7 @@#include "xfs_dir2_priv.h" #include "xfs_attr_leaf.h" #include "xfs_types.h" +#include "xfs_errortag.h" kmem_zone_t *xfs_ifork_zone;
@@ -745,6 +746,9 @@ xfs_iext_count_may_overflow( max_exts = (whichfork ==XFS_ATTR_FORK ) ?MAXAEXTNUM :MAXEXTNUM ; +if (XFS_TEST_ERROR (false, ip->i_mount,XFS_ERRTAG_REDUCE_MAX_IEXTENTS )) + max_exts =10 ; + nr_exts = ifp->if_nextents + nr_to_add;if (nr_exts < ifp->if_nextents || nr_exts > max_exts)return -EFBIG ;
fs/xfs/xfs_error.c +3 -0
@@ -54,6 +54,7 @@ static unsigned int xfs_errortag_random_default[] = {XFS_RANDOM_FORCE_SUMMARY_RECALC ,XFS_RANDOM_IUNLINK_FALLBACK ,XFS_RANDOM_BUF_IOERROR , + XFS_RANDOM_REDUCE_MAX_IEXTENTS, }; struct xfs_errortag_attr {
@@ -164,6 +165,7 @@ XFS_ERRORTAG_ATTR_RW(force_repair, XFS_ERRTAG_FORCE_SCRUB_REPAIR);XFS_ERRORTAG_ATTR_RW (bad_summary,XFS_ERRTAG_FORCE_SUMMARY_RECALC );XFS_ERRORTAG_ATTR_RW (iunlink_fallback,XFS_ERRTAG_IUNLINK_FALLBACK );XFS_ERRORTAG_ATTR_RW (buf_ioerror,XFS_ERRTAG_BUF_IOERROR ); +XFS_ERRORTAG_ATTR_RW (reduce_max_iextents,XFS_ERRTAG_REDUCE_MAX_IEXTENTS );static struct attribute *xfs_errortag_attrs[] = {XFS_ERRORTAG_ATTR_LIST (noerror),
@@ -202,6 +204,7 @@ static struct attribute *xfs_errortag_attrs[] = {XFS_ERRORTAG_ATTR_LIST (bad_summary),XFS_ERRORTAG_ATTR_LIST (iunlink_fallback),XFS_ERRORTAG_ATTR_LIST (buf_ioerror), +XFS_ERRORTAG_ATTR_LIST (reduce_max_iextents), NULL, };
Signature · 1 line
2.29.2
PATCH v15 15/16 xfs: Process allocated extent in a separate function
In reply to Chandan Babu RThis commit moves over the code in xfs_bmap_btalloc() which is responsible for processing an allocated extent to a new function. Apart from xfs_bmap_btalloc(), the new function will be invoked by another function introduced in a future commit.
--- fs/xfs/libxfs/xfs_bmap.c | 74 ++++++++++++++++++++++++---------------- 1 file changed, 45 insertions(+), 29 deletions(-)
fs/xfs/libxfs/xfs_bmap.c +45 -29
@@ -3510,6 +3510,48 @@ xfs_bmap_compute_alignments(return stripe_align; } +static void +xfs_bmap_process_allocated_extent ( +struct xfs_bmalloca *ap, +struct xfs_alloc_arg *args, +xfs_fileoff_t orig_offset, +xfs_extlen_t orig_length) +{ +int nullfb; + + nullfb = ap->tp->t_firstblock ==NULLFSBLOCK ; + +/* +* check the allocation happened at the same or higher AG than +* the first block that was allocated. +*/ +ASSERT (nullfb || +XFS_FSB_TO_AGNO (args->mp, ap->tp->t_firstblock) <= +XFS_FSB_TO_AGNO (args->mp, args->fsbno)); + + ap->blkno = args->fsbno; +if (nullfb) + ap->tp->t_firstblock = args->fsbno; + ap->length = args->len; +/* +* If the extent size hint is active, we tried to round the +* caller's allocation request offset down to extsz and the +* length up to another extsz boundary. If we found a free +* extent we mapped it in starting at this new offset. If the +* newly mapped space isn't long enough to cover any of the +* range of offsets that was originally requested, move the +* mapping up so that we can fill as much of the caller's +* original request as possible. Free space is apparently +* very fragmented so we're unlikely to be able to satisfy the +* hints anyway. +*/ +if (ap->length <= orig_length) + ap->offset = orig_offset; +else if (ap->offset + ap->length < orig_offset + orig_length) + ap->offset = orig_offset + orig_length - ap->length; +xfs_bmap_btalloc_accounting (ap, args); +} + STATIC intxfs_bmap_btalloc (struct xfs_bmalloca *ap)/* bmap alloc argument struct */
@@ -3702,36 +3744,10 @@ xfs_bmap_btalloc(return error; ap->tp->t_flags |=XFS_TRANS_LOWMODE ; } +if (args.fsbno !=NULLFSBLOCK ) { -/* -* check the allocation happened at the same or higher AG than -* the first block that was allocated. -*/ -ASSERT (ap->tp->t_firstblock ==NULLFSBLOCK || -XFS_FSB_TO_AGNO (mp, ap->tp->t_firstblock) <= -XFS_FSB_TO_AGNO (mp, args.fsbno)); - - ap->blkno = args.fsbno; -if (ap->tp->t_firstblock ==NULLFSBLOCK ) - ap->tp->t_firstblock = args.fsbno; - ap->length = args.len; -/* -* If the extent size hint is active, we tried to round the -* caller's allocation request offset down to extsz and the -* length up to another extsz boundary. If we found a free -* extent we mapped it in starting at this new offset. If the -* newly mapped space isn't long enough to cover any of the -* range of offsets that was originally requested, move the -* mapping up so that we can fill as much of the caller's -* original request as possible. Free space is apparently -* very fragmented so we're unlikely to be able to satisfy the -* hints anyway. -*/ -if (ap->length <= orig_length) - ap->offset = orig_offset; -else if (ap->offset + ap->length < orig_offset + orig_length) - ap->offset = orig_offset + orig_length - ap->length; -xfs_bmap_btalloc_accounting (ap, &args); +xfs_bmap_process_allocated_extent (ap, &args, orig_offset, + orig_length); }else { ap->blkno =NULLFSBLOCK ; ap->length =0 ;
Signature · 1 line
2.29.2
PATCH v15 13/16 xfs: Remove duplicate assert statement in xfs_bmap_btalloc()
In reply to Chandan Babu RThe check for verifying if the allocated extent is from an AG whose index is greater than or equal to that of tp->t_firstblock is already done a couple of statements earlier in the same function. Hence this commit removes the redundant assert statement.
--- fs/xfs/libxfs/xfs_bmap.c | 1 - 1 file changed, 1 deletion(-)
fs/xfs/libxfs/xfs_bmap.c +0 -1
@@ -3699,7 +3699,6 @@ xfs_bmap_btalloc( ap->blkno = args.fsbno;if (ap->tp->t_firstblock ==NULLFSBLOCK ) ap->tp->t_firstblock = args.fsbno; -ASSERT (nullfb || fb_agno <= args.agno); ap->length = args.len;/* * If the extent size hint is active, we tried to round the
Signature · 1 line
2.29.2
v15 cover Bail out if transaction can cause extent count to overflow
XFS does not check for possible overflow of per-inode extent counter fields when adding extents to either data or attr fork.
For e.g.
1. Insert 5 million xattrs (each having a value size of 255 bytes) and then delete 50% of them in an alternating manner.
2. On a 4k block sized XFS filesystem instance, the above causes 98511 extents to be created in the attr fork of the inode.
xfsaild/loop0 2008 [003] 1475.127209: probe:xfs_inode_to_disk: (ffffffffa43fb6b0) if_nextents=98511 i_ino=131
3. The incore inode fork extent counter is a signed 32-bit quantity. However, the on-disk extent counter is an unsigned 16-bit quantity and hence cannot hold 98511 extents.
4. The following incorrect value is stored in the xattr extent counter,
# xfs_db -f -c 'inode 131' -c 'print core.naextents' /dev/loop0 core.naextents = -32561
This patchset adds a new helper function
(i.e. xfs_iext_count_may_overflow()) to check for overflow of the per-inode data and xattr extent counters and invokes it before starting an fs operation (e.g. creating a new directory entry). With this patchset applied, XFS detects counter overflows and returns with an error rather than causing a silent corruption.
The patchset has been tested by executing xfstests with the following mkfs.xfs options,
1. -m crc=0 -b size=1k
2. -m crc=0 -b size=4k
3. -m crc=0 -b size=512
4. -m rmapbt=1,reflink=1 -b size=1k
5. -m rmapbt=1,reflink=1 -b size=4k
The patches can also be obtained from
https://github.com/chandanr/linux.git at branch xfs-reserve-extent-count-v15.
I have two patches that define the newly introduced error injection tags in xfsprogs
(https://lore.kernel.org/linux-xfs/[email protected]/).
I have also written tests
(https://lore.kernel.org/linux-xfs/[email protected]/)
for verifying the checks introduced in the kernel.
Changelog:
V14 -> V15:
1. Fix a trivial "Unused variable" warning reported by Kernel test robot. The only patch that was modified is "[PATCH V15 14/16] xfs:
Compute bmap extent alignments in a separate function".
V13 -> V14:
1. Fix incorrect comparison of xfs_iext_count_may_overflow()'s return value with -ENOSPC in xfs_bmap_del_extent_real().
Also, for quick reference, the following are the patches that need to be reviewed,
- [PATCH V14 04/16] xfs: Check for extent overflow when adding dir entries
- [PATCH V14 05/16] xfs: Check for extent overflow when removing dir entries
- [PATCH V14 06/16] xfs: Check for extent overflow when renaming dir entries
V12 -> V13:
1. xfs_rename():
- Add comment explaining why we do not check for extent count overflow for the source directory entry of a rename operation.
- Fix grammatical nit in a comment.
2. xfs_bmap_del_extent_real():
Replace explicit checks for inode's mode and fork with an assert() call since extent count overflow check here is applicable only to directory entry remove/rename operation.
V11 -> V12:
1. Rebase patches on top of Linux v5.11-rc1.
2. Revert back to using using a pseudo max inode extent count of 10. Hence the patches
- [PATCH V12 05/14] xfs: Check for extent overflow when adding/removing xattrs
- [PATCH V12 10/14] xfs: Introduce error injection to reduce maximum have been reverted back (including retaining of corresponding RVB tags) to how it was under V10 of the patchset.
V11 of the patchset had increased the max pseudo extent count to 35 to allow for "directory entry remove" operation to always succeed. However the corresponding logic was incorrect. Please refer to "[PATCH V12 04/14] xfs: Check for extent overflow when adding/removing dir entries" to find logic and explaination of the newer logic.
"[PATCH V12 04/14] xfs: Check for extent overflow when adding/removing dir entries" is the only patch yet to be reviewed.
V10 -> V11:
1. For directory/xattr insert operations we now reserve sufficient number of "extent count" so as to guarantee a future directory/xattr remove operation.
2. The pseudo max extent count value has been increased to 35.
V9 -> V10:
1. Pull back changes which cause xfs_bmap_compute_alignments() to return "stripe alignment" into 12th patch i.e. "xfs: Compute bmap extent alignments in a separate function".
V8 -> V9:
1. Enabling XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT error tag will always allocate single block sized free extents (if available).
2. xfs_bmap_compute_alignments() now returns stripe alignment as its return value.
3. Dropped Allison's RVB tag for "xfs: Compute bmap extent alignments in a separate function" and "xfs: Introduce error injection to allocate only minlen size extents for files".
V7 -> V8:
1. Rename local variable in xfs_alloc_fix_freelist() from "i" to "stat".
V6 -> V7:
1. Create new function xfs_bmap_exact_minlen_extent_alloc() (enabled only when CONFIG_XFS_DEBUG is set to y) which issues allocation requests for minlen sized extents only. In order to achieve this, common code from xfs_bmap_btalloc() have been refactored into new functions.
2. All major functions implementing logic associated with XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT error tag are compiled only when CONFIG_XFS_DEBUG is set to y.
3. Remove XFS_IEXT_REFLINK_REMAP_CNT macro and replace it with an integer which holds the number of new extents to be added to the data fork.
V5 -> V6:
1. Rebased the patchset on xfs-linux/for-next branch.
2. Drop "xfs: Set tp->t_firstblock only once during a transaction's lifetime" patch from the patchset.
3. Add a comment to xfs_bmap_btalloc() describing why it was chosen to start "free space extent search" from AG 0 when XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT is enabled and when the transaction is allocating its first extent.
4. Fix review comments associated with coding style.
V4 -> V5:
1. Introduce new error tag XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT to let user space programs to be able to guarantee that free space requests for files are satisfied by allocating minlen sized extents.
2. Change xfs_bmap_btalloc() and xfs_alloc_vextent() to allocate minlen sized extents when XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT is enabled.
3. Introduce a new patch that causes tp->t_firstblock to be assigned to a value only when its previous value is NULLFSBLOCK.
4. Replace the previously introduced MAXERRTAGEXTNUM (maximum inode fork extent count) with the hardcoded value of 10.
5. xfs_bui_item_recover(): Use XFS_IEXT_ADD_NOSPLIT_CNT when mapping an extent.
6. xfs_swap_extent_rmap(): Use xfs_bmap_is_real_extent() instead of xfs_bmap_is_update_needed() to assess if the extent really needs to be swapped.
V3 -> V4:
1. Introduce new patch which lets userspace programs to test "extent count overflow detection" by injecting an error tag. The new error tag reduces the maximum allowed extent count to 10.
2. Injecting the newly defined error tag prevents xfs_bmap_add_extent_hole_real() from merging a new extent with its neighbours to allow writing deterministic tests for testing extent count overflow for Directories, Xattr and growing realtime devices. This is required because the new extent being allocated can be contiguous with its neighbours (w.r.t both file and disk offsets).
3. Injecting the newly defined error tag forces block sized extents to be allocated for summary/bitmap files when growing a realtime device. This is required because xfs_growfs_rt_alloc() allocates as large an extent as possible for summary/bitmap files and hence it would be impossible to write deterministic tests.
4. Rename XFS_IEXT_REMOVE_CNT to XFS_IEXT_PUNCH_HOLE_CNT to reflect the actual meaning of the fs operation.
5. Fold XFS_IEXT_INSERT_HOLE_CNT code into that associated with XFS_IEXT_PUNCH_HOLE_CNT since both perform the same job.
6. xfs_swap_extent_rmap(): Check for extent overflow should be made on the source file only if the donor file extent has a valid on-disk mapping and vice versa.
V2 -> V3:
1. Move the definition of xfs_iext_count_may_overflow() from libxfs/xfs_trans_resv.c to libxfs/xfs_inode_fork.c. Also, I tried to make xfs_iext_count_may_overflow() an inline function by placing the definition in libxfs/xfs_inode_fork.h. However this required that the definition of 'struct xfs_inode' be available, since xfs_iext_count_may_overflow() uses a 'struct xfs_inode *' type variable.
2. Handle XFS_COW_FORK within xfs_iext_count_may_overflow() by returning a success value.
3. Rename XFS_IEXT_ADD_CNT to XFS_IEXT_ADD_NOSPLIT_CNT. Thanks to Darrick for the suggesting the new name.
4. Expand comments to make use of 80 columns.
V1 -> V2:
1. Rename helper function from xfs_trans_resv_ext_cnt() to xfs_iext_count_may_overflow().
2. Define and use macros to represent fs operations and the corresponding increase in extent count.
3. Split the patches based on the fs operation being performed.
Chandan Babu R (16):
xfs: Add helper for checking per-inode extent count overflow
xfs: Check for extent overflow when trivally adding a new extent
xfs: Check for extent overflow when punching a hole
xfs: Check for extent overflow when adding dir entries
xfs: Check for extent overflow when removing dir entries
xfs: Check for extent overflow when renaming dir entries
xfs: Check for extent overflow when adding/removing xattrs
xfs: Check for extent overflow when writing to unwritten extent
xfs: Check for extent overflow when moving extent from cow to data
fork
xfs: Check for extent overflow when remapping an extent
xfs: Check for extent overflow when swapping extents
xfs: Introduce error injection to reduce maximum inode fork extent
count
xfs: Remove duplicate assert statement in xfs_bmap_btalloc()
xfs: Compute bmap extent alignments in a separate function
xfs: Process allocated extent in a separate function
xfs: Introduce error injection to allocate only minlen size extents
for files
fs/xfs/libxfs/xfs_alloc.c | 50 ++++++ fs/xfs/libxfs/xfs_alloc.h | 3 + fs/xfs/libxfs/xfs_attr.c | 13 ++ fs/xfs/libxfs/xfs_bmap.c | 293 ++++++++++++++++++++++++--------- fs/xfs/libxfs/xfs_errortag.h | 6 +- fs/xfs/libxfs/xfs_inode_fork.c | 27 +++ fs/xfs/libxfs/xfs_inode_fork.h | 63 +++++++ fs/xfs/xfs_bmap_item.c | 10 ++ fs/xfs/xfs_bmap_util.c | 31 ++++ fs/xfs/xfs_dquot.c | 8 +- fs/xfs/xfs_error.c | 6 + fs/xfs/xfs_inode.c | 54 +++++- fs/xfs/xfs_iomap.c | 10 ++ fs/xfs/xfs_reflink.c | 16 ++ fs/xfs/xfs_rtalloc.c | 5 + fs/xfs/xfs_symlink.c | 5 + 16 files changed, 517 insertions(+), 83 deletions(-)
Signature · 1 line
2.29.2
PATCH v15 2/16 xfs: Check for extent overflow when trivally adding a new extent
When adding a new data extent (without modifying an inode's existing extents) the extent count increases only by 1. This commit checks for extent count overflow in such cases.
--- fs/xfs/libxfs/xfs_bmap.c | 6 ++++++ fs/xfs/libxfs/xfs_inode_fork.h | 6 ++++++ fs/xfs/xfs_bmap_item.c | 7 +++++++ fs/xfs/xfs_bmap_util.c | 5 +++++ fs/xfs/xfs_dquot.c | 8 +++++++- fs/xfs/xfs_iomap.c | 5 +++++ fs/xfs/xfs_rtalloc.c | 5 +++++ 7 files changed, 41 insertions(+), 1 deletion(-)
fs/xfs/libxfs/xfs_bmap.c +6 -0
@@ -4527,6 +4527,12 @@ xfs_bmapi_convert_delalloc(return error;xfs_ilock (ip,XFS_ILOCK_EXCL ); + + error =xfs_iext_count_may_overflow (ip, whichfork, +XFS_IEXT_ADD_NOSPLIT_CNT ); +if (error) + goto out_trans_cancel; +xfs_trans_ijoin (tp, ip,0 ); if (!xfs_iext_lookup_extent(ip, ifp, offset_fsb, &bma.icur, &bma.got) ||
fs/xfs/libxfs/xfs_inode_fork.h +6 -0
@@ -34,6 +34,12 @@ struct xfs_ifork {#define XFS_IFEXTENTS 0x02/* All extent pointers are read in */ #define XFS_IFBROOT 0x04/* i_broot points to the bmap b-tree root */ +/* +* Worst-case increase in the fork extent count when we're adding a single +* extent to a fork and there's no possibility of splitting an existing mapping. +*/ +#define XFS_IEXT_ADD_NOSPLIT_CNT (1) +/* * Fork handling. */
fs/xfs/xfs_bmap_item.c +7 -0
@@ -508,6 +508,13 @@ xfs_bui_item_recover(xfs_ilock (ip,XFS_ILOCK_EXCL );xfs_trans_ijoin (tp, ip,0 ); +if (bui_type ==XFS_BMAP_MAP ) { + error =xfs_iext_count_may_overflow (ip, whichfork, +XFS_IEXT_ADD_NOSPLIT_CNT ); +if (error) + goto err_cancel; + } + count = bmap->me_len; error = xfs_trans_log_finish_bmap_update(tp, budp, bui_type, ip, whichfork, bmap->me_startoff, bmap->me_startblock,
fs/xfs/xfs_bmap_util.c +5 -0
@@ -822,6 +822,11 @@ xfs_alloc_file_space(if (error) goto error1; + error =xfs_iext_count_may_overflow (ip,XFS_DATA_FORK , +XFS_IEXT_ADD_NOSPLIT_CNT ); +if (error) + goto error0; +xfs_trans_ijoin (tp, ip,0 ); error = xfs_bmapi_write(tp, ip, startoffset_fsb,
fs/xfs/xfs_dquot.c +7 -1
@@ -314,8 +314,14 @@ xfs_dquot_disk_alloc(return -ESRCH ; } -/* Create the block mapping. */ xfs_trans_ijoin (tp, quotip,XFS_ILOCK_EXCL ); + + error =xfs_iext_count_may_overflow (quotip,XFS_DATA_FORK , +XFS_IEXT_ADD_NOSPLIT_CNT ); +if (error) +return error; + +/* Create the block mapping. */ error =xfs_bmapi_write (tp, quotip, dqp->q_fileoffset,XFS_DQUOT_CLUSTER_SIZE_FSB ,XFS_BMAPI_METADATA ,0 , &map, &nmaps);
fs/xfs/xfs_iomap.c +5 -0
@@ -250,6 +250,11 @@ xfs_iomap_write_direct(if (error) goto out_trans_cancel; + error =xfs_iext_count_may_overflow (ip,XFS_DATA_FORK , +XFS_IEXT_ADD_NOSPLIT_CNT ); +if (error) + goto out_trans_cancel; +xfs_trans_ijoin (tp, ip,0 );/*
fs/xfs/xfs_rtalloc.c +5 -0
@@ -804,6 +804,11 @@ xfs_growfs_rt_alloc(xfs_ilock (ip,XFS_ILOCK_EXCL );xfs_trans_ijoin (tp, ip,XFS_ILOCK_EXCL ); + error =xfs_iext_count_may_overflow (ip,XFS_DATA_FORK , +XFS_IEXT_ADD_NOSPLIT_CNT ); +if (error) + goto out_trans_cancel; +/* * Allocate blocks to the bitmap file. */
Signature · 1 line
2.29.2
PATCH v15 4/16 xfs: Check for extent overflow when adding dir entries
In reply to Chandan Babu RDirectory entry addition can cause the following,
1. Data block can be added/removed.
A new extent can cause extent count to increase by 1.
2. Free disk block can be added/removed.
Same behaviour as described above for Data block.
3. Dabtree blocks.
XFS_DA_NODE_MAXDEPTH blocks can be added. Each of these can be new extents. Hence extent count can increase by XFS_DA_NODE_MAXDEPTH.
--- fs/xfs/libxfs/xfs_inode_fork.h | 13 +++++++++++++ fs/xfs/xfs_inode.c | 10 ++++++++++ fs/xfs/xfs_symlink.c | 5 +++++ 3 files changed, 28 insertions(+)
fs/xfs/libxfs/xfs_inode_fork.h +13 -0
@@ -47,6 +47,19 @@ struct xfs_ifork {*/ #define XFS_IEXT_PUNCH_HOLE_CNT (1) +/* +* Directory entry addition can cause the following, +* 1. Data block can be added/removed. +* A new extent can cause extent count to increase by 1. +* 2. Free disk block can be added/removed. +* Same behaviour as described above for Data block. +* 3. Dabtree blocks. +* XFS_DA_NODE_MAXDEPTH blocks can be added. Each of these can be new +* extents. Hence extent count can increase by XFS_DA_NODE_MAXDEPTH. +*/ +#define XFS_IEXT_DIR_MANIP_CNT (mp) \ + ((XFS_DA_NODE_MAXDEPTH + 1 + 1) * (mp)->m_dir_geo->fsbcount) +/* * Fork handling. */
fs/xfs/xfs_inode.c +10 -0
@@ -1042,6 +1042,11 @@ xfs_create(if (error) goto out_trans_cancel; + error =xfs_iext_count_may_overflow (dp,XFS_DATA_FORK , +XFS_IEXT_DIR_MANIP_CNT (mp)); +if (error) + goto out_trans_cancel; +/* * A newly created regular or special file just has one directory * entry pointing to them, but a directory also the "." entry
@@ -1258,6 +1263,11 @@ xfs_link(xfs_trans_ijoin (tp, sip,XFS_ILOCK_EXCL );xfs_trans_ijoin (tp, tdp,XFS_ILOCK_EXCL ); + error =xfs_iext_count_may_overflow (tdp,XFS_DATA_FORK , +XFS_IEXT_DIR_MANIP_CNT (mp)); +if (error) + goto error_return; +/* * If we are using project inheritance, we only allow hard link * creation in our tree when the project IDs are the same; else
fs/xfs/xfs_symlink.c +5 -0
@@ -220,6 +220,11 @@ xfs_symlink(if (error) goto out_trans_cancel; + error =xfs_iext_count_may_overflow (dp,XFS_DATA_FORK , +XFS_IEXT_DIR_MANIP_CNT (mp)); +if (error) + goto out_trans_cancel; +/* * Allocate an inode for the symlink. */
Signature · 1 line
2.29.2
PATCH v15 14/16 xfs: Compute bmap extent alignments in a separate function
In reply to Chandan Babu RThis commit moves over the code which computes stripe alignment and extent size hint alignment into a separate function. Apart from xfs_bmap_btalloc(), the new function will be used by another function introduced in a future commit.
--- fs/xfs/libxfs/xfs_bmap.c | 89 +++++++++++++++++++++++----------------- 1 file changed, 52 insertions(+), 37 deletions(-)
fs/xfs/libxfs/xfs_bmap.c +52 -37
@@ -3463,13 +3463,59 @@ xfs_bmap_btalloc_accounting( args->len); } +static int +xfs_bmap_compute_alignments ( +struct xfs_bmalloca *ap, +struct xfs_alloc_arg *args) +{ +struct xfs_mount *mp = args->mp; +xfs_extlen_t align =0 ;/* minimum allocation alignment */ +int stripe_align =0 ; + +/* stripe alignment for allocation is determined by mount parameters */ +if (mp->m_swidth && (mp->m_flags &XFS_MOUNT_SWALLOC )) + stripe_align = mp->m_swidth; +else if (mp->m_dalign) + stripe_align = mp->m_dalign; + +if (ap->flags &XFS_BMAPI_COWFORK ) + align =xfs_get_cowextsz_hint (ap->ip); +else if (ap->datatype &XFS_ALLOC_USERDATA ) + align =xfs_get_extsz_hint (ap->ip); +if (align) { +if (xfs_bmap_extsize_align (mp, &ap->got, &ap->prev, + align,0 , ap->eof,0 , ap->conv, &ap->offset, + &ap->length)) +ASSERT (0 ); + +ASSERT (ap->length); + } + +/* apply extent size hints if obtained earlier */ +if (align) { + args->prod = align; +div_u64_rem (ap->offset, args->prod, &args->mod); +if (args->mod) + args->mod = args->prod - args->mod; + }else if (mp->m_sb.sb_blocksize >=PAGE_SIZE ) { + args->prod =1 ; + args->mod =0 ; + }else { + args->prod =PAGE_SIZE >> mp->m_sb.sb_blocklog; +div_u64_rem (ap->offset, args->prod, &args->mod); +if (args->mod) + args->mod = args->prod - args->mod; + } + +return stripe_align; +} + STATIC intxfs_bmap_btalloc (struct xfs_bmalloca *ap)/* bmap alloc argument struct */ {xfs_mount_t *mp;/* mount point structure */ xfs_alloctype_t atype =0 ;/* type for allocation routines */ -xfs_extlen_t align =0 ;/* minimum allocation alignment */ xfs_agnumber_t fb_agno;/* ag number of ap->firstblock */ xfs_agnumber_t ag;xfs_alloc_arg_t args;
@@ -3489,25 +3535,11 @@ xfs_bmap_btalloc( mp = ap->ip->i_mount; -/* stripe alignment for allocation is determined by mount parameters */ - stripe_align =0 ; -if (mp->m_swidth && (mp->m_flags &XFS_MOUNT_SWALLOC )) - stripe_align = mp->m_swidth; -else if (mp->m_dalign) - stripe_align = mp->m_dalign; - -if (ap->flags &XFS_BMAPI_COWFORK ) - align =xfs_get_cowextsz_hint (ap->ip); -else if (ap->datatype &XFS_ALLOC_USERDATA ) - align =xfs_get_extsz_hint (ap->ip); -if (align) { - error =xfs_bmap_extsize_align (mp, &ap->got, &ap->prev, - align,0 , ap->eof,0 , ap->conv, - &ap->offset, &ap->length); -ASSERT (!error); -ASSERT (ap->length); - } +memset (&args,0 ,sizeof (args)); + args.tp = ap->tp; + args.mp = mp; + stripe_align =xfs_bmap_compute_alignments (ap, &args); nullfb = ap->tp->t_firstblock ==NULLFSBLOCK ; fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp,
@@ -3538,9 +3570,6 @@ xfs_bmap_btalloc(* Normal allocation, done through xfs_alloc_vextent. */ tryagain = isaligned =0 ; -memset (&args,0 ,sizeof (args)); - args.tp = ap->tp; - args.mp = mp; args.fsbno = ap->blkno; args.oinfo =XFS_RMAP_OINFO_SKIP_UPDATE ;
@@ -3571,21 +3600,7 @@ xfs_bmap_btalloc( args.total = ap->total; args.minlen = ap->minlen; } -/* apply extent size hints if obtained earlier */ -if (align) { - args.prod = align; -div_u64_rem (ap->offset, args.prod, &args.mod); -if (args.mod) - args.mod = args.prod - args.mod; - }else if (mp->m_sb.sb_blocksize >=PAGE_SIZE ) { - args.prod =1 ; - args.mod =0 ; - }else { - args.prod =PAGE_SIZE >> mp->m_sb.sb_blocklog; -div_u64_rem (ap->offset, args.prod, &args.mod); -if (args.mod) - args.mod = args.prod - args.mod; - } +/* * If we are not low on available data blocks, and the underlying * logical volume manager is a stripe, and the file offset is zero then
Signature · 1 line
2.29.2
PATCH v15 7/16 xfs: Check for extent overflow when adding/removing xattrs
In reply to Chandan Babu RAdding/removing an xattr can cause XFS_DA_NODE_MAXDEPTH extents to be added. One extra extent for dabtree in case a local attr is large enough to cause a double split. It can also cause extent count to increase proportional to the size of a remote xattr's value.
--- fs/xfs/libxfs/xfs_attr.c | 13 +++++++++++++ fs/xfs/libxfs/xfs_inode_fork.h | 10 ++++++++++ 2 files changed, 23 insertions(+)
fs/xfs/libxfs/xfs_attr.c +13 -0
@@ -396,6 +396,7 @@ xfs_attr_set(struct xfs_trans_res tres;bool rsvd = (args->attr_filter &XFS_ATTR_ROOT );int error, local; +int rmt_blks =0 ;unsigned int total;if (XFS_FORCED_SHUTDOWN (dp->i_mount))
@@ -442,11 +443,15 @@ xfs_attr_set( tres.tr_logcount =XFS_ATTRSET_LOG_COUNT ; tres.tr_logflags =XFS_TRANS_PERM_LOG_RES ; total = args->total; + +if (!local) + rmt_blks =xfs_attr3_rmt_blocks (mp, args->valuelen); }else {XFS_STATS_INC (mp, xs_attr_remove); tres =M_RES (mp)->tr_attrrm; total =XFS_ATTRRM_SPACE_RES (mp); + rmt_blks =xfs_attr3_rmt_blocks (mp,XFS_XATTR_SIZE_MAX ); }/*
@@ -460,6 +465,14 @@ xfs_attr_set(xfs_ilock (dp,XFS_ILOCK_EXCL );xfs_trans_ijoin (args->trans, dp,0 ); + +if (args->value ||xfs_inode_hasattr (dp)) { + error =xfs_iext_count_may_overflow (dp,XFS_ATTR_FORK , +XFS_IEXT_ATTR_MANIP_CNT (rmt_blks)); +if (error) + goto out_trans_cancel; + } +if (args->value) {unsigned int quota_flags =XFS_QMOPT_RES_REGBLKS ;
fs/xfs/libxfs/xfs_inode_fork.h +10 -0
@@ -60,6 +60,16 @@ struct xfs_ifork {#define XFS_IEXT_DIR_MANIP_CNT (mp) \ ((XFS_DA_NODE_MAXDEPTH + 1 + 1) * (mp)->m_dir_geo->fsbcount) +/* +* Adding/removing an xattr can cause XFS_DA_NODE_MAXDEPTH extents to +* be added. One extra extent for dabtree in case a local attr is +* large enough to cause a double split. It can also cause extent +* count to increase proportional to the size of a remote xattr's +* value. +*/ +#define XFS_IEXT_ATTR_MANIP_CNT (rmt_blks) \ + (XFS_DA_NODE_MAXDEPTH + max(1, rmt_blks)) +/* * Fork handling. */
Signature · 1 line
2.29.2
PATCH v15 8/16 xfs: Check for extent overflow when writing to unwritten extent
In reply to Chandan Babu RA write to a sub-interval of an existing unwritten extent causes the original extent to be split into 3 extents
i.e. | Unwritten | Real | Unwritten |
Hence extent count can increase by 2.
--- fs/xfs/libxfs/xfs_inode_fork.h | 9 +++++++++ fs/xfs/xfs_iomap.c | 5 +++++ 2 files changed, 14 insertions(+)
fs/xfs/libxfs/xfs_inode_fork.h +9 -0
@@ -70,6 +70,15 @@ struct xfs_ifork {#define XFS_IEXT_ATTR_MANIP_CNT (rmt_blks) \ (XFS_DA_NODE_MAXDEPTH + max(1, rmt_blks)) +/* +* A write to a sub-interval of an existing unwritten extent causes the original +* extent to be split into 3 extents +* i.e. | Unwritten | Real | Unwritten | +* Hence extent count can increase by 2. +*/ +#define XFS_IEXT_WRITE_UNWRITTEN_CNT (2) + +/* * Fork handling. */
fs/xfs/xfs_iomap.c +5 -0
@@ -566,6 +566,11 @@ xfs_iomap_write_unwritten(if (error) goto error_on_bmapi_transaction; + error =xfs_iext_count_may_overflow (ip,XFS_DATA_FORK , +XFS_IEXT_WRITE_UNWRITTEN_CNT ); +if (error) + goto error_on_bmapi_transaction; +/* * Modify the unwritten extent state of the buffer. */
Signature · 1 line
2.29.2
PATCH v15 11/16 xfs: Check for extent overflow when swapping extents
In reply to Chandan Babu RRemoving an initial range of source/donor file's extent and adding a new extent (from donor/source file) in its place will cause extent count to increase by 1.
--- fs/xfs/libxfs/xfs_inode_fork.h | 7 +++++++ fs/xfs/xfs_bmap_util.c | 16 ++++++++++++++++ 2 files changed, 23 insertions(+)
fs/xfs/libxfs/xfs_inode_fork.h +7 -0
@@ -88,6 +88,13 @@ struct xfs_ifork {*/ #define XFS_IEXT_REFLINK_END_COW_CNT (2) +/* +* Removing an initial range of source/donor file's extent and adding a new +* extent (from donor/source file) in its place will cause extent count to +* increase by 1. +*/ +#define XFS_IEXT_SWAP_RMAP_CNT (1) +/* * Fork handling. */
fs/xfs/xfs_bmap_util.c +16 -0
@@ -1399,6 +1399,22 @@ xfs_swap_extent_rmap( irec.br_blockcount);trace_xfs_swap_extent_rmap_remap_piece (tip, &uirec); +if (xfs_bmap_is_real_extent (&uirec)) { + error =xfs_iext_count_may_overflow (ip, +XFS_DATA_FORK , +XFS_IEXT_SWAP_RMAP_CNT ); +if (error) + goto out; + } + +if (xfs_bmap_is_real_extent (&irec)) { + error =xfs_iext_count_may_overflow (tip, +XFS_DATA_FORK , +XFS_IEXT_SWAP_RMAP_CNT ); +if (error) + goto out; + } +/* Remove the mapping from the donor file. */ xfs_bmap_unmap_extent (tp, tip, &uirec);
Signature · 1 line
2.29.2
PATCH v15 6/16 xfs: Check for extent overflow when renaming dir entries
In reply to Chandan Babu RA rename operation is essentially a directory entry remove operation from the perspective of parent directory (i.e. src_dp) of rename's source. Hence the only place where we check for extent count overflow for src_dp is in xfs_bmap_del_extent_real(). xfs_bmap_del_extent_real() returns -ENOSPC when it detects a possible extent count overflow and in response, the higher layers of directory handling code do the following:
1. Data/Free blocks: XFS lets these blocks linger until a future remove operation removes them.
2. Dabtree blocks: XFS swaps the blocks with the last block in the Leaf space and unmaps the last block.
For target_dp, there are two cases depending on whether the destination directory entry exists or not.
When destination directory entry does not exist (i.e. target_ip == NULL), extent count overflow check is performed only when transaction has a non-zero sized space reservation associated with it. With a zero-sized space reservation, XFS allows a rename operation to continue only when the directory has sufficient free space in its data/leaf/free space blocks to hold the new entry.
When destination directory entry exists (i.e. target_ip != NULL), all we need to do is change the inode number associated with the already existing entry. Hence there is no need to perform an extent count overflow check.
--- fs/xfs/libxfs/xfs_bmap.c | 3 +++ fs/xfs/xfs_inode.c | 44 +++++++++++++++++++++++++++++++++++++++- 2 files changed, 46 insertions(+), 1 deletion(-)
fs/xfs/libxfs/xfs_bmap.c +3 -0
@@ -5160,6 +5160,9 @@ xfs_bmap_del_extent_real(* until a future remove operation. Dabtree blocks would be * swapped with the last block in the leaf space and then the * new last block will be unmapped. +* +* The above logic also applies to the source directory entry of +* a rename operation. */ error =xfs_iext_count_may_overflow (ip, whichfork,1 );if (error) {
fs/xfs/xfs_inode.c +43 -1
64 lines not on this page · raw message
Signature · 1 line
2.29.2
PATCH v15 5/16 xfs: Check for extent overflow when removing dir entries
In reply to Chandan Babu RDirectory entry removal must always succeed; Hence XFS does the following during low disk space scenario:
1. Data/Free blocks linger until a future remove operation.
2. Dabtree blocks would be swapped with the last block in the leaf space and then the new last block will be unmapped.
This facility is reused during low inode extent count scenario i.e. this commit causes xfs_bmap_del_extent_real() to return -ENOSPC error code so that the above mentioned behaviour is exercised causing no change to the directory's extent count.
--- fs/xfs/libxfs/xfs_bmap.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)
fs/xfs/libxfs/xfs_bmap.c +18 -0
@@ -5151,6 +5151,24 @@ xfs_bmap_del_extent_real(/* * Deleting the middle of the extent. */ + +/* +* For directories, -ENOSPC is returned since a directory entry +* remove operation must not fail due to low extent count +* availability. -ENOSPC will be handled by higher layers of XFS +* by letting the corresponding empty Data/Free blocks to linger +* until a future remove operation. Dabtree blocks would be +* swapped with the last block in the leaf space and then the +* new last block will be unmapped. +*/ + error =xfs_iext_count_may_overflow (ip, whichfork,1 ); +if (error) { +ASSERT (S_ISDIR (VFS_I (ip)->i_mode) && + whichfork ==XFS_DATA_FORK ); + error = -ENOSPC ; + goto done; + } + old = got; got.br_blockcount = del->br_startoff - got.br_startoff;
Signature · 1 line
2.29.2
PATCH v15 3/16 xfs: Check for extent overflow when punching a hole
In reply to Chandan Babu RThe extent mapping the file offset at which a hole has to be inserted will be split into two extents causing extent count to increase by 1.
--- fs/xfs/libxfs/xfs_inode_fork.h | 7 +++++++ fs/xfs/xfs_bmap_item.c | 15 +++++++++------ fs/xfs/xfs_bmap_util.c | 10 ++++++++++ 3 files changed, 26 insertions(+), 6 deletions(-)
fs/xfs/libxfs/xfs_inode_fork.h +7 -0
@@ -40,6 +40,13 @@ struct xfs_ifork {*/ #define XFS_IEXT_ADD_NOSPLIT_CNT (1) +/* +* Punching out an extent from the middle of an existing extent can cause the +* extent count to increase by 1. +* i.e. | Old extent | Hole | Old extent | +*/ +#define XFS_IEXT_PUNCH_HOLE_CNT (1) +/* * Fork handling. */
fs/xfs/xfs_bmap_item.c +9 -6
@@ -471,6 +471,7 @@ xfs_bui_item_recover(xfs_exntst_t state;unsigned int bui_type;int whichfork; +int iext_delta;int error =0 ;if (!xfs_bui_validate (mp, buip)) {
@@ -508,12 +509,14 @@ xfs_bui_item_recover(xfs_ilock (ip,XFS_ILOCK_EXCL );xfs_trans_ijoin (tp, ip,0 ); -if (bui_type ==XFS_BMAP_MAP ) { - error =xfs_iext_count_may_overflow (ip, whichfork, -XFS_IEXT_ADD_NOSPLIT_CNT ); -if (error) - goto err_cancel; - } +if (bui_type ==XFS_BMAP_MAP ) + iext_delta =XFS_IEXT_ADD_NOSPLIT_CNT ; +else + iext_delta =XFS_IEXT_PUNCH_HOLE_CNT ; + + error =xfs_iext_count_may_overflow (ip, whichfork, iext_delta); +if (error) + goto err_cancel; count = bmap->me_len; error = xfs_trans_log_finish_bmap_update(tp, budp, bui_type, ip,
fs/xfs/xfs_bmap_util.c +10 -0
@@ -891,6 +891,11 @@ xfs_unmap_extent(xfs_trans_ijoin (tp, ip,0 ); + error =xfs_iext_count_may_overflow (ip,XFS_DATA_FORK , +XFS_IEXT_PUNCH_HOLE_CNT ); +if (error) + goto out_trans_cancel; + error =xfs_bunmapi (tp, ip, startoffset_fsb, len_fsb,0 ,2 , done);if (error) goto out_trans_cancel;
@@ -1168,6 +1173,11 @@ xfs_insert_file_space(xfs_ilock (ip,XFS_ILOCK_EXCL );xfs_trans_ijoin (tp, ip,0 ); + error =xfs_iext_count_may_overflow (ip,XFS_DATA_FORK , +XFS_IEXT_PUNCH_HOLE_CNT ); +if (error) + goto out_trans_cancel; +/* * The extent shifting code works on extent granularity. So, if stop_fsb * is not the starting block of extent, we need to split the extent at
Signature · 1 line
2.29.2
PATCH v15 1/16 xfs: Add helper for checking per-inode extent count overflow
In reply to Chandan Babu RXFS does not check for possible overflow of per-inode extent counter fields when adding extents to either data or attr fork.
For e.g.
1. Insert 5 million xattrs (each having a value size of 255 bytes) and then delete 50% of them in an alternating manner.
2. On a 4k block sized XFS filesystem instance, the above causes 98511 extents to be created in the attr fork of the inode.
xfsaild/loop0 2008 [003] 1475.127209: probe:xfs_inode_to_disk: (ffffffffa43fb6b0) if_nextents=98511 i_ino=131
3. The incore inode fork extent counter is a signed 32-bit quantity. However the on-disk extent counter is an unsigned 16-bit quantity and hence cannot hold 98511 extents.
4. The following incorrect value is stored in the attr extent counter,
# xfs_db -f -c 'inode 131' -c 'print core.naextents' /dev/loop0 core.naextents = -32561
This commit adds a new helper function (i.e. xfs_iext_count_may_overflow()) to check for overflow of the per-inode data and xattr extent counters. Future patches will use this function to make sure that an FS operation won't cause the extent counter to overflow.
--- fs/xfs/libxfs/xfs_inode_fork.c | 23 +++++++++++++++++++++++ fs/xfs/libxfs/xfs_inode_fork.h | 2 ++ 2 files changed, 25 insertions(+)
fs/xfs/libxfs/xfs_inode_fork.c +23 -0
@@ -23,6 +23,7 @@#include "xfs_da_btree.h" #include "xfs_dir2_priv.h" #include "xfs_attr_leaf.h" +#include "xfs_types.h" kmem_zone_t *xfs_ifork_zone;
@@ -728,3 +729,25 @@ xfs_ifork_verify_local_attr(return 0 ; } + +int +xfs_iext_count_may_overflow ( +struct xfs_inode *ip, +int whichfork, +int nr_to_add) +{ +struct xfs_ifork *ifp =XFS_IFORK_PTR (ip, whichfork); +uint64_t max_exts; +uint64_t nr_exts; + +if (whichfork ==XFS_COW_FORK ) +return 0 ; + + max_exts = (whichfork ==XFS_ATTR_FORK ) ?MAXAEXTNUM :MAXEXTNUM ; + + nr_exts = ifp->if_nextents + nr_to_add; +if (nr_exts < ifp->if_nextents || nr_exts > max_exts) +return -EFBIG ; + +return 0 ; +}
fs/xfs/libxfs/xfs_inode_fork.h +2 -0
@@ -172,5 +172,7 @@ extern void xfs_ifork_init_cow(struct xfs_inode *ip);int xfs_ifork_verify_local_data (struct xfs_inode *ip);int xfs_ifork_verify_local_attr (struct xfs_inode *ip); +int xfs_iext_count_may_overflow (struct xfs_inode *ip,int whichfork, +int nr_to_add);#endif /* __XFS_INODE_FORK_H__ */
Signature · 1 line
2.29.2
Quoted 46 lines · Chandan Babu R
XFS does not check for possible overflow of per-inode extent counter fields when adding extents to either data or attr fork.
For e.g.
1. Insert 5 million xattrs (each having a value size of 255 bytes) and then delete 50% of them in an alternating manner.2. On a 4k block sized XFS filesystem instance, the above causes 98511 extents to be created in the attr fork of the inode.
xfsaild/loop0 2008 [003] 1475.127209: probe:xfs_inode_to_disk: (ffffffffa43fb6b0) if_nextents=98511 i_ino=1313. The incore inode fork extent counter is a signed 32-bit quantity. However, the on-disk extent counter is an unsigned 16-bit quantity and hence cannot hold 98511 extents.
4. The following incorrect value is stored in the xattr extent counter,
# xfs_db -f -c 'inode 131' -c 'print core.naextents' /dev/loop0 core.naextents = -32561This patchset adds a new helper function
(i.e.xfs_iext_count_may_overflow()) to check for overflow of the per-inode data and xattr extent counters and invokes it before starting an fs operation (e.g. creating a new directory entry). With this patchset applied, XFS detects counter overflows and returns with an error rather than causing a silent corruption.The patchset has been tested by executing xfstests with the following mkfs.xfs options,
1. -m crc=0 -b size=1k
2. -m crc=0 -b size=4k
3. -m crc=0 -b size=512
4. -m rmapbt=1,reflink=1 -b size=1k
5. -m rmapbt=1,reflink=1 -b size=4kThe patches can also be obtained from
https://github.com/chandanr/linux.git at branch xfs-reserve-extent-count-v15.I have two patches that define the newly introduced error injection tags in xfsprogs
(https://lore.kernel.org/linux-xfs/[email protected]/).I have also written tests
(https://lore.kernel.org/linux-xfs/[email protected]/)
for verifying the checks introduced in the kernel.
Quoted 5 lines
Changelog:
V14 -> V15:
1. Fix a trivial "Unused variable" warning reported by Kernel test robot. The only patch that was modified is "[PATCH V15 14/16] xfs:
Compute bmap extent alignments in a separate function".
Code fixes should be against for-next, please...
--D
Quoted 191 lines
V13 -> V14:
1. Fix incorrect comparison of xfs_iext_count_may_overflow()'s return value with-ENOSPCinxfs_bmap_del_extent_real().
Also, for quick reference, the following are the patches that need to be reviewed,
- [PATCH V14 04/16] xfs: Check for extent overflow when adding dir entries
- [PATCH V14 05/16] xfs: Check for extent overflow when removing dir entries
- [PATCH V14 06/16] xfs: Check for extent overflow when renaming dir entriesV12 -> V13:
1.xfs_rename():
- Add comment explaining why we do not check for extent count overflow for the source directory entry of a rename operation.
- Fix grammatical nit in a comment.
2.xfs_bmap_del_extent_real():
Replace explicit checks for inode's mode and fork with anassert()call since extent count overflow check here is applicable only to directory entry remove/rename operation.V11 -> V12:
1. Rebase patches on top of Linux v5.11-rc1.
2. Revert back to using using a pseudo max inode extent count of 10. Hence the patches
- [PATCH V12 05/14] xfs: Check for extent overflow when adding/removing xattrs
- [PATCH V12 10/14] xfs: Introduce error injection to reduce maximum have been reverted back (including retaining of corresponding RVB tags) to how it was under V10 of the patchset.V11 of the patchset had increased the max pseudo extent count to 35 to allow for "directory entry remove" operation to always succeed. However the corresponding logic was incorrect. Please refer to "[PATCH V12 04/14] xfs: Check for extent overflow when adding/removing dir entries" to find logic and explaination of the newer logic.
"[PATCH V12 04/14] xfs: Check for extent overflow when adding/removing dir entries" is the only patch yet to be reviewed.
V10 -> V11:
1. For directory/xattr insert operations we now reserve sufficient number of "extent count" so as to guarantee a future directory/xattr remove operation.
2. The pseudo max extent count value has been increased to 35.V9 -> V10:
1. Pull back changes which causexfs_bmap_compute_alignments()to return "stripe alignment" into 12th patch i.e. "xfs: Compute bmap extent alignments in a separate function".V8 -> V9:
1. EnablingXFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENTerror tag will always allocate single block sized free extents (if available).
2.xfs_bmap_compute_alignments()now returns stripe alignment as its return value.
3. Dropped Allison's RVB tag for "xfs: Compute bmap extent alignments in a separate function" and "xfs: Introduce error injection to allocate only minlen size extents for files".V7 -> V8:
1. Rename local variable inxfs_alloc_fix_freelist()from "i" to "stat".V6 -> V7:
1. Create new functionxfs_bmap_exact_minlen_extent_alloc()(enabled only whenCONFIG_XFS_DEBUGis set to y) which issues allocation requests for minlen sized extents only. In order to achieve this, common code fromxfs_bmap_btalloc()have been refactored into new functions.
2. All major functions implementing logic associated withXFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENTerror tag are compiled only whenCONFIG_XFS_DEBUGis set to y.
3. RemoveXFS_IEXT_REFLINK_REMAP_CNTmacro and replace it with an integer which holds the number of new extents to be added to the data fork.V5 -> V6:
1. Rebased the patchset on xfs-linux/for-next branch.
2. Drop "xfs: Settp->t_firstblockonly once during a transaction's lifetime" patch from the patchset.
3. Add a comment toxfs_bmap_btalloc()describing why it was chosen to start "free space extent search" from AG 0 whenXFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENTis enabled and when the transaction is allocating its first extent.
4. Fix review comments associated with coding style.V4 -> V5:
1. Introduce new error tagXFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENTto let user space programs to be able to guarantee that free space requests for files are satisfied by allocating minlen sized extents.
2. Changexfs_bmap_btalloc()andxfs_alloc_vextent()to allocate minlen sized extents whenXFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENTis enabled.
3. Introduce a new patch that causestp->t_firstblockto be assigned to a value only when its previous value is NULLFSBLOCK.
4. Replace the previously introduced MAXERRTAGEXTNUM (maximum inode fork extent count) with the hardcoded value of 10.
5.xfs_bui_item_recover(): UseXFS_IEXT_ADD_NOSPLIT_CNTwhen mapping an extent.
6.xfs_swap_extent_rmap(): Usexfs_bmap_is_real_extent()instead ofxfs_bmap_is_update_needed()to assess if the extent really needs to be swapped.V3 -> V4:
1. Introduce new patch which lets userspace programs to test "extent count overflow detection" by injecting an error tag. The new error tag reduces the maximum allowed extent count to 10.
2. Injecting the newly defined error tag preventsxfs_bmap_add_extent_hole_real()from merging a new extent with its neighbours to allow writing deterministic tests for testing extent count overflow for Directories, Xattr and growing realtime devices. This is required because the new extent being allocated can be contiguous with its neighbours (w.r.t both file and disk offsets).
3. Injecting the newly defined error tag forces block sized extents to be allocated for summary/bitmap files when growing a realtime device. This is required becausexfs_growfs_rt_alloc()allocates as large an extent as possible for summary/bitmap files and hence it would be impossible to write deterministic tests.
4. RenameXFS_IEXT_REMOVE_CNTtoXFS_IEXT_PUNCH_HOLE_CNTto reflect the actual meaning of the fs operation.
5. FoldXFS_IEXT_INSERT_HOLE_CNTcode into that associated withXFS_IEXT_PUNCH_HOLE_CNTsince both perform the same job.
6.xfs_swap_extent_rmap(): Check for extent overflow should be made on the source file only if the donor file extent has a valid on-disk mapping and vice versa.V2 -> V3:
1. Move the definition ofxfs_iext_count_may_overflow()fromlibxfs/xfs_trans_resv.ctolibxfs/xfs_inode_fork.c. Also, I tried to makexfs_iext_count_may_overflow()an inline function by placing the definition inlibxfs/xfs_inode_fork.h. However this required that the definition of 'structxfs_inode' be available, sincexfs_iext_count_may_overflow()uses a 'structxfs_inode*' type variable.
2. HandleXFS_COW_FORKwithinxfs_iext_count_may_overflow()by returning a success value.
3. RenameXFS_IEXT_ADD_CNTtoXFS_IEXT_ADD_NOSPLIT_CNT. Thanks to Darrick for the suggesting the new name.
4. Expand comments to make use of 80 columns.V1 -> V2:
1. Rename helper function fromxfs_trans_resv_ext_cnt()toxfs_iext_count_may_overflow().
2. Define and use macros to represent fs operations and the corresponding increase in extent count.
3. Split the patches based on the fs operation being performed.Chandan Babu R (16):
xfs: Add helper for checking per-inode extent count overflow
xfs: Check for extent overflow when trivally adding a new extent
xfs: Check for extent overflow when punching a hole
xfs: Check for extent overflow when adding dir entries
xfs: Check for extent overflow when removing dir entries
xfs: Check for extent overflow when renaming dir entries
xfs: Check for extent overflow when adding/removing xattrs
xfs: Check for extent overflow when writing to unwritten extent
xfs: Check for extent overflow when moving extent from cow to data
fork
xfs: Check for extent overflow when remapping an extent
xfs: Check for extent overflow when swapping extents
xfs: Introduce error injection to reduce maximum inode fork extent
count
xfs: Remove duplicate assert statement inxfs_bmap_btalloc()
xfs: Compute bmap extent alignments in a separate function
xfs: Process allocated extent in a separate function
xfs: Introduce error injection to allocate only minlen size extents
for filesfs/xfs/libxfs/xfs_alloc.c | 50 ++++++ fs/xfs/libxfs/xfs_alloc.h | 3 + fs/xfs/libxfs/xfs_attr.c | 13 ++ fs/xfs/libxfs/xfs_bmap.c | 293 ++++++++++++++++++++++++--------- fs/xfs/libxfs/xfs_errortag.h | 6 +- fs/xfs/libxfs/xfs_inode_fork.c | 27 +++ fs/xfs/libxfs/xfs_inode_fork.h | 63 +++++++ fs/xfs/xfs_bmap_item.c | 10 ++ fs/xfs/xfs_bmap_util.c | 31 ++++ fs/xfs/xfs_dquot.c | 8 +- fs/xfs/xfs_error.c | 6 + fs/xfs/xfs_inode.c | 54 +++++- fs/xfs/xfs_iomap.c | 10 ++ fs/xfs/xfs_reflink.c | 16 ++ fs/xfs/xfs_rtalloc.c | 5 + fs/xfs/xfs_symlink.c | 5 + 16 files changed, 517 insertions(+), 83 deletions(-)Signature · 1 line
2.29.2
Re: [PATCH V15 04/16] xfs: Check for extent overflow when adding dir entries
In reply to Chandan Babu RQuoted 10 lines · Chandan Babu R
Directory entry addition can cause the following,
1. Data block can be added/removed.
A new extent can cause extent count to increase by 1.
2. Free disk block can be added/removed.
Same behaviour as described above for Data block.
3. Dabtree blocks.
XFS_DA_NODE_MAXDEPTHblocks can be added. Each of these can be new extents. Hence extent count can increase byXFS_DA_NODE_MAXDEPTH.
Quoted 2 lines
Reviewed-by Darrick J. Wong <[email protected]>Signed-off-by Chandan Babu R <[email protected]>
Looks ok to me
Quoted 75 lines
--- fs/xfs/libxfs/xfs_inode_fork.h | 13 +++++++++++++ fs/xfs/xfs_inode.c | 10 ++++++++++ fs/xfs/xfs_symlink.c | 5 +++++ 3 files changed, 28 insertions(+)fs/xfs/libxfs/xfs_inode_fork.h +13
-0@@ -47,6 +47,19 @@ struct xfs_ifork {*/ #define XFS_IEXT_PUNCH_HOLE_CNT (1) +/* +* Directory entry addition can cause the following, +* 1. Data block can be added/removed. +* A new extent can cause extent count to increase by 1. +* 2. Free disk block can be added/removed. +* Same behaviour as described above for Data block. +* 3. Dabtree blocks. +* XFS_DA_NODE_MAXDEPTH blocks can be added. Each of these can be new +* extents. Hence extent count can increase by XFS_DA_NODE_MAXDEPTH. +*/ +#define XFS_IEXT_DIR_MANIP_CNT (mp) \ + ((XFS_DA_NODE_MAXDEPTH + 1 + 1) * (mp)->m_dir_geo->fsbcount) +/* * Fork handling. */ fs/xfs/xfs_inode.c +10
-0@@ -1042,6 +1042,11 @@ xfs_create(if (error) goto out_trans_cancel; + error =xfs_iext_count_may_overflow (dp,XFS_DATA_FORK , +XFS_IEXT_DIR_MANIP_CNT (mp)); +if (error) + goto out_trans_cancel; +/* * A newly created regular or special file just has one directory * entry pointing to them, but a directory also the "." entry @@ -1258,6 +1263,11 @@ xfs_link(xfs_trans_ijoin (tp, sip,XFS_ILOCK_EXCL );xfs_trans_ijoin (tp, tdp,XFS_ILOCK_EXCL ); + error =xfs_iext_count_may_overflow (tdp,XFS_DATA_FORK , +XFS_IEXT_DIR_MANIP_CNT (mp)); +if (error) + goto error_return; +/* * If we are using project inheritance, we only allow hard link * creation in our tree when the project IDs are the same; else fs/xfs/xfs_symlink.c +5
-0@@ -220,6 +220,11 @@ xfs_symlink(if (error) goto out_trans_cancel; + error =xfs_iext_count_may_overflow (dp,XFS_DATA_FORK , +XFS_IEXT_DIR_MANIP_CNT (mp)); +if (error) + goto out_trans_cancel; +/* * Allocate an inode for the symlink. */
Re: [PATCH V15 06/16] xfs: Check for extent overflow when renaming dir entries
In reply to Chandan Babu RQuoted 21 lines · Chandan Babu R
A rename operation is essentially a directory entry remove operation from the perspective of parent directory (i.e.
src_dp) of rename's source. Hence the only place where we check for extent count overflow forsrc_dpis inxfs_bmap_del_extent_real().xfs_bmap_del_extent_real()returns-ENOSPCwhen it detects a possible extent count overflow and in response, the higher layers of directory handling code do the following:
1. Data/Free blocks: XFS lets these blocks linger until a future remove operation removes them.
2. Dabtree blocks: XFS swaps the blocks with the last block in the Leaf space and unmaps the last block.For
target_dp, there are two cases depending on whether the destination directory entry exists or not.When destination directory entry does not exist (i.e.
target_ip== NULL), extent count overflow check is performed only when transaction has a non-zero sized space reservation associated with it. With a zero-sized space reservation, XFS allows a rename operation to continue only when the directory has sufficient free space in its data/leaf/free space blocks to hold the new entry.
Quoted 7 lines
When destination directory entry exists (i.e.
target_ip!= NULL), all we need to do is change the inode number associated with the already existing entry. Hence there is no need to perform an extent count overflow check.Reviewed-by Darrick J. Wong <[email protected]>Signed-off-by Chandan Babu R <[email protected]>
Ok, thanks for all the explaining!
Quoted 91 lines
--- fs/xfs/libxfs/xfs_bmap.c | 3 +++ fs/xfs/xfs_inode.c | 44 +++++++++++++++++++++++++++++++++++++++- 2 files changed, 46 insertions(+), 1 deletion(-)fs/xfs/libxfs/xfs_bmap.c +3
-0@@ -5160,6 +5160,9 @@ xfs_bmap_del_extent_real(* until a future remove operation. Dabtree blocks would be * swapped with the last block in the leaf space and then the * new last block will be unmapped. +* +* The above logic also applies to the source directory entry of +* a rename operation. */ error =xfs_iext_count_may_overflow (ip, whichfork,1 );if (error) {fs/xfs/xfs_inode.c +43
-1@@ -3116,6 +3116,35 @@ xfs_rename(/* * Check for expected errors before we dirty the transaction * so we can return an error without a transaction abort. +* +* Extent count overflow check: +* +* From the perspective of src_dp, a rename operation is essentially a +* directory entry remove operation. Hence the only place where we check +* for extent count overflow for src_dp is in +* xfs_bmap_del_extent_real(). xfs_bmap_del_extent_real() returns +* -ENOSPC when it detects a possible extent count overflow and in +* response, the higher layers of directory handling code do the +* following: +* 1. Data/Free blocks: XFS lets these blocks linger until a +* future remove operation removes them. +* 2. Dabtree blocks: XFS swaps the blocks with the last block in the +* Leaf space and unmaps the last block. +* +* For target_dp, there are two cases depending on whether the +* destination directory entry exists or not. +* +* When destination directory entry does not exist (i.e. target_ip == +* NULL), extent count overflow check is performed only when transaction +* has a non-zero sized space reservation associated with it. With a +* zero-sized space reservation, XFS allows a rename operation to +* continue only when the directory has sufficient free space in its +* data/leaf/free space blocks to hold the new entry. +* +* When destination directory entry exists (i.e. target_ip != NULL), all +* we need to do is change the inode number associated with the already +* existing entry. Hence there is no need to perform an extent count +* overflow check. */ if (target_ip ==NULL ) {/* @@ -3126,6 +3155,12 @@ xfs_rename( error =xfs_dir_canenter (tp, target_dp, target_name);if (error) goto out_trans_cancel; + }else { + error =xfs_iext_count_may_overflow (target_dp, +XFS_DATA_FORK , +XFS_IEXT_DIR_MANIP_CNT (mp)); +if (error) + goto out_trans_cancel; } }else {/* @@ -3283,9 +3318,16 @@ xfs_rename(if (wip) { error =xfs_dir_replace (tp, src_dp, src_name, wip->i_ino, spaceres); - }else + }else { +/* +* NOTE: We don't need to check for extent count overflow here +* because the dir remove name code will leave the dir block in +* place if the extent count would overflow. +*/ error =xfs_dir_removename (tp, src_dp, src_name, src_ip->i_ino, spaceres); + } +if (error) goto out_trans_cancel;
Re: [PATCH V15 14/16] xfs: Compute bmap extent alignments in a separate function
In reply to Chandan Babu RQuoted 7 lines · Chandan Babu R
This commit moves over the code which computes stripe alignment and extent size hint alignment into a separate function. Apart from
xfs_bmap_btalloc(), the new function will be used by another function introduced in a future commit.Signed-off-by Chandan Babu R <[email protected]>
Ok, looks equivalent
Quoted 133 lines
--- fs/xfs/libxfs/xfs_bmap.c | 89 +++++++++++++++++++++++----------------- 1 file changed, 52 insertions(+), 37 deletions(-)fs/xfs/libxfs/xfs_bmap.c +52
-37@@ -3463,13 +3463,59 @@ xfs_bmap_btalloc_accounting( args->len); } +static int +xfs_bmap_compute_alignments ( +struct xfs_bmalloca *ap, +struct xfs_alloc_arg *args) +{ +struct xfs_mount *mp = args->mp; +xfs_extlen_t align =0 ;/* minimum allocation alignment */ +int stripe_align =0 ; + +/* stripe alignment for allocation is determined by mount parameters */ +if (mp->m_swidth && (mp->m_flags &XFS_MOUNT_SWALLOC )) + stripe_align = mp->m_swidth; +else if (mp->m_dalign) + stripe_align = mp->m_dalign; + +if (ap->flags &XFS_BMAPI_COWFORK ) + align =xfs_get_cowextsz_hint (ap->ip); +else if (ap->datatype &XFS_ALLOC_USERDATA ) + align =xfs_get_extsz_hint (ap->ip); +if (align) { +if (xfs_bmap_extsize_align (mp, &ap->got, &ap->prev, + align,0 , ap->eof,0 , ap->conv, &ap->offset, + &ap->length)) +ASSERT (0 ); + +ASSERT (ap->length); + } + +/* apply extent size hints if obtained earlier */ +if (align) { + args->prod = align; +div_u64_rem (ap->offset, args->prod, &args->mod); +if (args->mod) + args->mod = args->prod - args->mod; + }else if (mp->m_sb.sb_blocksize >=PAGE_SIZE ) { + args->prod =1 ; + args->mod =0 ; + }else { + args->prod =PAGE_SIZE >> mp->m_sb.sb_blocklog; +div_u64_rem (ap->offset, args->prod, &args->mod); +if (args->mod) + args->mod = args->prod - args->mod; + } + +return stripe_align; +} + STATIC intxfs_bmap_btalloc (struct xfs_bmalloca *ap)/* bmap alloc argument struct */ {xfs_mount_t *mp;/* mount point structure */ xfs_alloctype_t atype =0 ;/* type for allocation routines */ -xfs_extlen_t align =0 ;/* minimum allocation alignment */ xfs_agnumber_t fb_agno;/* ag number of ap->firstblock */ xfs_agnumber_t ag;xfs_alloc_arg_t args;@@ -3489,25 +3535,11 @@ xfs_bmap_btalloc( mp = ap->ip->i_mount; -/* stripe alignment for allocation is determined by mount parameters */ - stripe_align =0 ; -if (mp->m_swidth && (mp->m_flags &XFS_MOUNT_SWALLOC )) - stripe_align = mp->m_swidth; -else if (mp->m_dalign) - stripe_align = mp->m_dalign; - -if (ap->flags &XFS_BMAPI_COWFORK ) - align =xfs_get_cowextsz_hint (ap->ip); -else if (ap->datatype &XFS_ALLOC_USERDATA ) - align =xfs_get_extsz_hint (ap->ip); -if (align) { - error =xfs_bmap_extsize_align (mp, &ap->got, &ap->prev, - align,0 , ap->eof,0 , ap->conv, - &ap->offset, &ap->length); -ASSERT (!error); -ASSERT (ap->length); - } +memset (&args,0 ,sizeof (args)); + args.tp = ap->tp; + args.mp = mp; + stripe_align =xfs_bmap_compute_alignments (ap, &args); nullfb = ap->tp->t_firstblock ==NULLFSBLOCK ; fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp,@@ -3538,9 +3570,6 @@ xfs_bmap_btalloc(* Normal allocation, done through xfs_alloc_vextent. */ tryagain = isaligned =0 ; -memset (&args,0 ,sizeof (args)); - args.tp = ap->tp; - args.mp = mp; args.fsbno = ap->blkno; args.oinfo =XFS_RMAP_OINFO_SKIP_UPDATE ;@@ -3571,21 +3600,7 @@ xfs_bmap_btalloc( args.total = ap->total; args.minlen = ap->minlen; } -/* apply extent size hints if obtained earlier */ -if (align) { - args.prod = align; -div_u64_rem (ap->offset, args.prod, &args.mod); -if (args.mod) - args.mod = args.prod - args.mod; - }else if (mp->m_sb.sb_blocksize >=PAGE_SIZE ) { - args.prod =1 ; - args.mod =0 ; - }else { - args.prod =PAGE_SIZE >> mp->m_sb.sb_blocklog; -div_u64_rem (ap->offset, args.prod, &args.mod); -if (args.mod) - args.mod = args.prod - args.mod; - } +/* * If we are not low on available data blocks, and the underlying * logical volume manager is a stripe, and the file offset is zero then
Re: [PATCH V15 05/16] xfs: Check for extent overflow when removing dir entries
In reply to Chandan Babu RQuoted 6 lines · Chandan Babu R
Directory entry removal must always succeed; Hence XFS does the following during low disk space scenario:
1. Data/Free blocks linger until a future remove operation.
2. Dabtree blocks would be swapped with the last block in the leaf space and then the new last block will be unmapped.
Quoted 7 lines
This facility is reused during low inode extent count scenario i.e. this commit causes
xfs_bmap_del_extent_real()to return-ENOSPCerror code so that the above mentioned behaviour is exercised causing no change to the directory's extent count.Reviewed-by Darrick J. Wong <[email protected]>Signed-off-by Chandan Babu R <[email protected]>
Ok, makes sense. Thanks for the commentary!
Quoted 34 lines
--- fs/xfs/libxfs/xfs_bmap.c | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+)fs/xfs/libxfs/xfs_bmap.c +18
-0@@ -5151,6 +5151,24 @@ xfs_bmap_del_extent_real(/* * Deleting the middle of the extent. */ + +/* +* For directories, -ENOSPC is returned since a directory entry +* remove operation must not fail due to low extent count +* availability. -ENOSPC will be handled by higher layers of XFS +* by letting the corresponding empty Data/Free blocks to linger +* until a future remove operation. Dabtree blocks would be +* swapped with the last block in the leaf space and then the +* new last block will be unmapped. +*/ + error =xfs_iext_count_may_overflow (ip, whichfork,1 ); +if (error) { +ASSERT (S_ISDIR (VFS_I (ip)->i_mode) && + whichfork ==XFS_DATA_FORK ); + error = -ENOSPC ; + goto done; + } + old = got; got.br_blockcount = del->br_startoff - got.br_startoff;
Re: [PATCH V15 16/16] xfs: Introduce error injection to allocate only minlen size extents for files
In reply to Chandan Babu RQuoted 19 lines · Chandan Babu R
This commit adds
XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENTerror tag which helps userspace test programs to getxfs_bmap_btalloc()to always allocate minlen sized extents.This is required for test programs which need a guarantee that minlen extents allocated for a file do not get merged with their existing neighbours in the inode's BMBT. "Inode fork extent overflow check" for Directories, Xattrs and extension of realtime inodes need this since the file offset at which the extents are being allocated cannot be explicitly controlled from userspace.
One way to use this error tag is to,
1. Consume all of the free space by sequentially writing to a file.
2. Punch alternate blocks of the file. This causes CNTBT to contain sufficient number of one block sized extent records.
3. InjectXFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENTerror tag. After step 3,xfs_bmap_btalloc()will issue space allocation requests for minlen sized extents only.
Quoted 5 lines
ENOSPC error code is returned to userspace when there aren't any "one block sized" extents left in any of the AGs.
Reviewed-by Darrick J. Wong <[email protected]>Signed-off-by Chandan Babu R <[email protected]>
Ok, looks reasonable. Thanks!
Quoted 297 lines
--- fs/xfs/libxfs/xfs_alloc.c | 50 ++++++++++++++ fs/xfs/libxfs/xfs_alloc.h | 3 + fs/xfs/libxfs/xfs_bmap.c | 124 ++++++++++++++++++++++++++++------- fs/xfs/libxfs/xfs_errortag.h | 4 +- fs/xfs/xfs_error.c | 3 + 5 files changed, 159 insertions(+), 25 deletions(-)fs/xfs/libxfs/xfs_alloc.c +50
-0@@ -2474,6 +2474,47 @@ xfs_defer_agfl_block(xfs_defer_add (tp,XFS_DEFER_OPS_TYPE_AGFL_FREE , &new->xefi_list); } +#ifdef DEBUG +/* +* Check if an AGF has a free extent record whose length is equal to +* args->minlen. +*/ +STATIC int +xfs_exact_minlen_extent_available ( +struct xfs_alloc_arg *args, +struct xfs_buf *agbp, +int *stat) +{ +struct xfs_btree_cur *cnt_cur; +xfs_agblock_t fbno; +xfs_extlen_t flen; +int error =0 ; + + cnt_cur =xfs_allocbt_init_cursor (args->mp, args->tp, agbp, + args->agno,XFS_BTNUM_CNT ); + error =xfs_alloc_lookup_ge (cnt_cur,0 , args->minlen, stat); +if (error) + goto out; + +if (*stat ==0 ) { + error = -EFSCORRUPTED ; + goto out; + } + + error =xfs_alloc_get_rec (cnt_cur, &fbno, &flen, stat); +if (error) + goto out; + +if (*stat ==1 && flen != args->minlen) + *stat =0 ; + +out: +xfs_btree_del_cursor (cnt_cur, error); + +return error; +} +#endif +/* * Decide whether to use this allocation group for this allocation. * If so, fix up the btree freelist's size. @@ -2545,6 +2586,15 @@ xfs_alloc_fix_freelist(if (!xfs_alloc_space_available (args, need, flags)) goto out_agbp_relse; +#ifdef DEBUG +if (args->alloc_minlen_only) { +int stat; + + error =xfs_exact_minlen_extent_available (args, agbp, &stat); +if (error || !stat) + goto out_agbp_relse; + } +#endif /* * Make the freelist shorter if it's too long. * fs/xfs/libxfs/xfs_alloc.h +3
-0@@ -75,6 +75,9 @@ typedef struct xfs_alloc_arg {char wasfromfl;/* set if allocation is from freelist */ struct xfs_owner_info oinfo;/* owner of blocks being allocated */ enum xfs_ag_resv_type resv;/* block reservation to use */ +#ifdef DEBUG +bool alloc_minlen_only;/* allocate exact minlen extent */ +#endif } xfs_alloc_arg_t;/* fs/xfs/libxfs/xfs_bmap.c +100
-24@@ -3552,34 +3552,101 @@ xfs_bmap_process_allocated_extent(xfs_bmap_btalloc_accounting (ap, args); } -STATIC int -xfs_bmap_btalloc ( -struct xfs_bmalloca *ap)/* bmap alloc argument struct */ +#ifdef DEBUG +static int +xfs_bmap_exact_minlen_extent_alloc ( +struct xfs_bmalloca *ap) { -xfs_mount_t *mp;/* mount point structure */ -xfs_alloctype_t atype =0 ;/* type for allocation routines */ -xfs_agnumber_t fb_agno;/* ag number of ap->firstblock */ -xfs_agnumber_t ag; -xfs_alloc_arg_t args; -xfs_fileoff_t orig_offset; -xfs_extlen_t orig_length; -xfs_extlen_t blen; -xfs_extlen_t nextminlen =0 ; -int nullfb;/* true if ap->firstblock isn't set */ -int isaligned; -int tryagain; -int error; -int stripe_align; +struct xfs_mount *mp = ap->ip->i_mount; +struct xfs_alloc_arg args = { .tp = ap->tp, .mp = mp }; +xfs_fileoff_t orig_offset; +xfs_extlen_t orig_length; +int error;ASSERT (ap->length); + +if (ap->minlen !=1 ) { + ap->blkno =NULLFSBLOCK ; + ap->length =0 ; +return 0 ; + } + orig_offset = ap->offset; orig_length = ap->length; - mp = ap->ip->i_mount; + args.alloc_minlen_only =1 ; -memset (&args,0 ,sizeof (args)); - args.tp = ap->tp; - args.mp = mp; +xfs_bmap_compute_alignments (ap, &args); + +if (ap->tp->t_firstblock ==NULLFSBLOCK ) { +/* +* Unlike the longest extent available in an AG, we don't track +* the length of an AG's shortest extent. +* XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT is a debug only knob and +* hence we can afford to start traversing from the 0th AG since +* we need not be concerned about a drop in performance in +* "debug only" code paths. +*/ + ap->blkno =XFS_AGB_TO_FSB (mp,0 ,0 ); + }else { + ap->blkno = ap->tp->t_firstblock; + } + + args.fsbno = ap->blkno; + args.oinfo =XFS_RMAP_OINFO_SKIP_UPDATE ; + args.type =XFS_ALLOCTYPE_FIRST_AG ; + args.total = args.minlen = args.maxlen = ap->minlen; + + args.alignment =1 ; + args.minalignslop =0 ; + + args.minleft = ap->minleft; + args.wasdel = ap->wasdel; + args.resv =XFS_AG_RESV_NONE ; + args.datatype = ap->datatype; + + error =xfs_alloc_vextent (&args); +if (error) +return error; + +if (args.fsbno !=NULLFSBLOCK ) { +xfs_bmap_process_allocated_extent (ap, &args, orig_offset, + orig_length); + }else { + ap->blkno =NULLFSBLOCK ; + ap->length =0 ; + } + +return 0 ; +} +#else + +#define xfs_bmap_exact_minlen_extent_alloc (bma) (-EFSCORRUPTED) + +#endif + +STATIC int +xfs_bmap_btalloc ( +struct xfs_bmalloca *ap) +{ +struct xfs_mount *mp = ap->ip->i_mount; +struct xfs_alloc_arg args = { .tp = ap->tp, .mp = mp }; +xfs_alloctype_t atype =0 ; +xfs_agnumber_t fb_agno;/* ag number of ap->firstblock */ +xfs_agnumber_t ag; +xfs_fileoff_t orig_offset; +xfs_extlen_t orig_length; +xfs_extlen_t blen; +xfs_extlen_t nextminlen =0 ; +int nullfb;/* true if ap->firstblock isn't set */ +int isaligned; +int tryagain; +int error; +int stripe_align; + +ASSERT (ap->length); + orig_offset = ap->offset; + orig_length = ap->length; stripe_align =xfs_bmap_compute_alignments (ap, &args);@@ -4113,6 +4180,10 @@ xfs_bmap_alloc_userdata(return xfs_bmap_rtalloc (bma); } +if (unlikely (XFS_TEST_ERROR (false, mp, +XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT ))) +return xfs_bmap_exact_minlen_extent_alloc (bma); +return xfs_bmap_btalloc (bma); }@@ -4149,10 +4220,15 @@ xfs_bmapi_allocate(else bma->minlen =1 ; -if (bma->flags &XFS_BMAPI_METADATA ) - error =xfs_bmap_btalloc (bma); -else +if (bma->flags &XFS_BMAPI_METADATA ) { +if (unlikely (XFS_TEST_ERROR (false, mp, +XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT ))) + error =xfs_bmap_exact_minlen_extent_alloc (bma); +else + error =xfs_bmap_btalloc (bma); + }else { error =xfs_bmap_alloc_userdata (bma); + }if (error || bma->blkno ==NULLFSBLOCK )return error;fs/xfs/libxfs/xfs_errortag.h +3
-1@@ -57,7 +57,8 @@#define XFS_ERRTAG_IUNLINK_FALLBACK 34#define XFS_ERRTAG_BUF_IOERROR 35#define XFS_ERRTAG_REDUCE_MAX_IEXTENTS 36 -#define XFS_ERRTAG_MAX 37 +#define XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT 37 +#define XFS_ERRTAG_MAX 38/* * Random factors for above tags, 1 means always, 2 means 1/2 time, etc. @@ -99,5 +100,6 @@#define XFS_RANDOM_IUNLINK_FALLBACK (XFS_RANDOM_DEFAULT/10)#define XFS_RANDOM_BUF_IOERROR XFS_RANDOM_DEFAULT#define XFS_RANDOM_REDUCE_MAX_IEXTENTS 1 +#define XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT 1#endif /* __XFS_ERRORTAG_H_ */ fs/xfs/xfs_error.c +3
-0@@ -55,6 +55,7 @@ static unsigned int xfs_errortag_random_default[] = {XFS_RANDOM_IUNLINK_FALLBACK ,XFS_RANDOM_BUF_IOERROR ,XFS_RANDOM_REDUCE_MAX_IEXTENTS , + XFS_RANDOM_BMAP_ALLOC_MINLEN_EXTENT, }; struct xfs_errortag_attr {@@ -166,6 +167,7 @@ XFS_ERRORTAG_ATTR_RW(bad_summary, XFS_ERRTAG_FORCE_SUMMARY_RECALC);XFS_ERRORTAG_ATTR_RW (iunlink_fallback,XFS_ERRTAG_IUNLINK_FALLBACK );XFS_ERRORTAG_ATTR_RW (buf_ioerror,XFS_ERRTAG_BUF_IOERROR );XFS_ERRORTAG_ATTR_RW (reduce_max_iextents,XFS_ERRTAG_REDUCE_MAX_IEXTENTS ); +XFS_ERRORTAG_ATTR_RW (bmap_alloc_minlen_extent,XFS_ERRTAG_BMAP_ALLOC_MINLEN_EXTENT );static struct attribute *xfs_errortag_attrs[] = {XFS_ERRORTAG_ATTR_LIST (noerror),@@ -205,6 +207,7 @@ static struct attribute *xfs_errortag_attrs[] = {XFS_ERRORTAG_ATTR_LIST (iunlink_fallback),XFS_ERRORTAG_ATTR_LIST (buf_ioerror),XFS_ERRORTAG_ATTR_LIST (reduce_max_iextents), +XFS_ERRORTAG_ATTR_LIST (bmap_alloc_minlen_extent), NULL, };