From 774a99b47b588bf0bd9f65d3b241d5bba0b2fcb0 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 18:59:53 -0700 Subject: xfs: give xfs_bmap_intent its own perag reference Give the xfs_bmap_intent an active reference to the perag structure data. This reference will be used to enable scrub intent draining functionality in subsequent patches. Later, shrink will use these passive references to know if an AG is quiesced or not. The reason why we take a passive ref for a file mapping operation is simple: we're committing to some sort of action involving space in an AG, so we want to indicate our interest in that AG. The space is already allocated, so we need to be able to operate on AGs that are offline or being shrunk. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 1 + 1 file changed, 1 insertion(+) (limited to 'fs/xfs/libxfs/xfs_bmap.c') diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 34de6e6898c4..0b4fb3979bdc 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -6075,6 +6075,7 @@ __xfs_bmap_add( bi->bi_whichfork = whichfork; bi->bi_bmap = *bmap; + xfs_bmap_update_get_group(tp->t_mountp, bi); xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_BMAP, &bi->bi_list); return 0; } -- cgit From 6a3bd8fcf9afb47c703cb268f30f60aa2e7af86a Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 11 Apr 2023 19:00:05 -0700 Subject: xfs: complain about bad file mapping records in the ondisk bmbt Similar to what we've just done for the other btrees, create a function to log corrupt bmbt records and call it whenever we encounter a bad record in the ondisk btree. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 31 ++++++++++++++++++++++++++++++- fs/xfs/libxfs/xfs_bmap.h | 2 ++ fs/xfs/libxfs/xfs_inode_fork.c | 3 ++- 3 files changed, 34 insertions(+), 2 deletions(-) (limited to 'fs/xfs/libxfs/xfs_bmap.c') diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 0b4fb3979bdc..5e66807737c5 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1083,6 +1083,34 @@ struct xfs_iread_state { xfs_extnum_t loaded; }; +int +xfs_bmap_complain_bad_rec( + struct xfs_inode *ip, + int whichfork, + xfs_failaddr_t fa, + const struct xfs_bmbt_irec *irec) +{ + struct xfs_mount *mp = ip->i_mount; + const char *forkname; + + switch (whichfork) { + case XFS_DATA_FORK: forkname = "data"; break; + case XFS_ATTR_FORK: forkname = "attr"; break; + case XFS_COW_FORK: forkname = "CoW"; break; + default: forkname = "???"; break; + } + + xfs_warn(mp, + "Bmap BTree record corruption in inode 0x%llx %s fork detected at %pS!", + ip->i_ino, forkname, fa); + xfs_warn(mp, + "Offset 0x%llx, start block 0x%llx, block count 0x%llx state 0x%x", + irec->br_startoff, irec->br_startblock, irec->br_blockcount, + irec->br_state); + + return -EFSCORRUPTED; +} + /* Stuff every bmbt record from this block into the incore extent map. */ static int xfs_iread_bmbt_block( @@ -1125,7 +1153,8 @@ xfs_iread_bmbt_block( xfs_inode_verifier_error(ip, -EFSCORRUPTED, "xfs_iread_extents(2)", frp, sizeof(*frp), fa); - return -EFSCORRUPTED; + return xfs_bmap_complain_bad_rec(ip, whichfork, fa, + &new); } xfs_iext_insert(ip, &ir->icur, &new, xfs_bmap_fork_to_state(whichfork)); diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h index e5a492027aea..9ff030d12981 100644 --- a/fs/xfs/libxfs/xfs_bmap.h +++ b/fs/xfs/libxfs/xfs_bmap.h @@ -265,6 +265,8 @@ static inline uint32_t xfs_bmap_fork_to_state(int whichfork) xfs_failaddr_t xfs_bmap_validate_extent(struct xfs_inode *ip, int whichfork, struct xfs_bmbt_irec *irec); +int xfs_bmap_complain_bad_rec(struct xfs_inode *ip, int whichfork, + xfs_failaddr_t fa, const struct xfs_bmbt_irec *irec); int xfs_bmapi_remap(struct xfs_trans *tp, struct xfs_inode *ip, xfs_fileoff_t bno, xfs_filblks_t len, xfs_fsblock_t startblock, diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 6b21760184d9..ff37eecec4b0 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -140,7 +140,8 @@ xfs_iformat_extents( xfs_inode_verifier_error(ip, -EFSCORRUPTED, "xfs_iformat_extents(2)", dp, sizeof(*dp), fa); - return -EFSCORRUPTED; + return xfs_bmap_complain_bad_rec(ip, whichfork, + fa, &new); } xfs_iext_insert(ip, &icur, &new, state); -- cgit From c95356ca884885db702670e24933ee7f2b9f1754 Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Wed, 12 Apr 2023 15:49:10 +1000 Subject: xfs: _{attr,data}_map_shared should take ILOCK_EXCL until iread_extents is completely done While fuzzing the data fork extent count on a btree-format directory with xfs/375, I observed the following (excerpted) splat: XFS: Assertion failed: xfs_isilocked(ip, XFS_ILOCK_EXCL), file: fs/xfs/libxfs/xfs_bmap.c, line: 1208 ------------[ cut here ]------------ WARNING: CPU: 0 PID: 43192 at fs/xfs/xfs_message.c:104 assfail+0x46/0x4a [xfs] Call Trace: xfs_iread_extents+0x1af/0x210 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xchk_dir_walk+0xb8/0x190 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xchk_parent_count_parent_dentries+0x41/0x80 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xchk_parent_validate+0x199/0x2e0 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xchk_parent+0xdf/0x130 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xfs_scrub_metadata+0x2b8/0x730 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xfs_scrubv_metadata+0x38b/0x4d0 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xfs_ioc_scrubv_metadata+0x111/0x160 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] xfs_file_ioctl+0x367/0xf50 [xfs 09f66509ece4938760fac7de64732a0cbd3e39cd] __x64_sys_ioctl+0x82/0xa0 do_syscall_64+0x2b/0x80 entry_SYSCALL_64_after_hwframe+0x46/0xb0 The cause of this is a race condition in xfs_ilock_data_map_shared, which performs an unlocked access to the data fork to guess which lock mode it needs: Thread 0 Thread 1 xfs_need_iread_extents xfs_ilock(..., ILOCK_EXCL) xfs_iread_extents xfs_need_iread_extents xfs_ilock(..., ILOCK_SHARED) xfs_iunlock(..., ILOCK_EXCL) xfs_iread_extents *BOOM* Fix this race by adding a flag to the xfs_ifork structure to indicate that we have not yet read in the extent records and changing the predicate to look at the flag state, not if_height. The memory barrier ensures that the flag will not be set until the very end of the function. Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 6 ++++++ fs/xfs/libxfs/xfs_inode_fork.c | 16 +++++++++++++++- fs/xfs/libxfs/xfs_inode_fork.h | 6 ++++-- 3 files changed, 25 insertions(+), 3 deletions(-) (limited to 'fs/xfs/libxfs/xfs_bmap.c') diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 34de6e6898c4..f11ef331e5a4 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -1171,6 +1171,12 @@ xfs_iread_extents( goto out; } ASSERT(ir.loaded == xfs_iext_count(ifp)); + /* + * Use release semantics so that we can use acquire semantics in + * xfs_need_iread_extents and be guaranteed to see a valid mapping tree + * after that load. + */ + smp_store_release(&ifp->if_needextents, 0); return 0; out: xfs_iext_destroy(ifp); diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c index 6b21760184d9..1bbe5ea3f00b 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.c +++ b/fs/xfs/libxfs/xfs_inode_fork.c @@ -226,10 +226,15 @@ xfs_iformat_data_fork( /* * Initialize the extent count early, as the per-format routines may - * depend on it. + * depend on it. Use release semantics to set needextents /after/ we + * set the format. This ensures that we can use acquire semantics on + * needextents in xfs_need_iread_extents() and be guaranteed to see a + * valid format value after that load. */ ip->i_df.if_format = dip->di_format; ip->i_df.if_nextents = xfs_dfork_data_extents(dip); + smp_store_release(&ip->i_df.if_needextents, + ip->i_df.if_format == XFS_DINODE_FMT_BTREE ? 1 : 0); switch (inode->i_mode & S_IFMT) { case S_IFIFO: @@ -282,8 +287,17 @@ xfs_ifork_init_attr( enum xfs_dinode_fmt format, xfs_extnum_t nextents) { + /* + * Initialize the extent count early, as the per-format routines may + * depend on it. Use release semantics to set needextents /after/ we + * set the format. This ensures that we can use acquire semantics on + * needextents in xfs_need_iread_extents() and be guaranteed to see a + * valid format value after that load. + */ ip->i_af.if_format = format; ip->i_af.if_nextents = nextents; + smp_store_release(&ip->i_af.if_needextents, + ip->i_af.if_format == XFS_DINODE_FMT_BTREE ? 1 : 0); } void diff --git a/fs/xfs/libxfs/xfs_inode_fork.h b/fs/xfs/libxfs/xfs_inode_fork.h index d3943d6ad0b9..96d307784c85 100644 --- a/fs/xfs/libxfs/xfs_inode_fork.h +++ b/fs/xfs/libxfs/xfs_inode_fork.h @@ -24,6 +24,7 @@ struct xfs_ifork { xfs_extnum_t if_nextents; /* # of extents in this fork */ short if_broot_bytes; /* bytes allocated for root */ int8_t if_format; /* format of this fork */ + uint8_t if_needextents; /* extents have not been read */ }; /* @@ -260,9 +261,10 @@ int xfs_iext_count_upgrade(struct xfs_trans *tp, struct xfs_inode *ip, uint nr_to_add); /* returns true if the fork has extents but they are not read in yet. */ -static inline bool xfs_need_iread_extents(struct xfs_ifork *ifp) +static inline bool xfs_need_iread_extents(const struct xfs_ifork *ifp) { - return ifp->if_format == XFS_DINODE_FMT_BTREE && ifp->if_height == 0; + /* see xfs_iformat_{data,attr}_fork() for needextents semantics */ + return smp_load_acquire(&ifp->if_needextents) != 0; } #endif /* __XFS_INODE_FORK_H__ */ -- cgit From 9419092fb2630c30e4ffeb9ef61007ef0c61827a Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Thu, 27 Apr 2023 09:02:11 +1000 Subject: xfs: fix livelock in delayed allocation at ENOSPC On a filesystem with a non-zero stripe unit and a large sequential write, delayed allocation will set a minimum allocation length of the stripe unit. If allocation fails because there are no extents long enough for an aligned minlen allocation, it is supposed to fall back to unaligned allocation which allows single block extents to be allocated. When the allocator code was rewritting in the 6.3 cycle, this fallback was broken - the old code used args->fsbno as the both the allocation target and the allocation result, the new code passes the target as a separate parameter. The conversion didn't handle the aligned->unaligned fallback path correctly - it reset args->fsbno to the target fsbno on failure which broke allocation failure detection in the high level code and so it never fell back to unaligned allocations. This resulted in a loop in writeback trying to allocate an aligned block, getting a false positive success, trying to insert the result in the BMBT. This did nothing because the extent already was in the BMBT (merge results in an unchanged extent) and so it returned the prior extent to the conversion code as the current iomap. Because the iomap returned didn't cover the offset we tried to map, xfs_convert_blocks() then retries the allocation, which fails in the same way and now we have a livelock. Reported-and-tested-by: Brian Foster Fixes: 85843327094f ("xfs: factor xfs_bmap_btalloc()") Signed-off-by: Dave Chinner Reviewed-by: Darrick J. Wong --- fs/xfs/libxfs/xfs_bmap.c | 1 - 1 file changed, 1 deletion(-) (limited to 'fs/xfs/libxfs/xfs_bmap.c') diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index 1a4e446194dd..b512de0540d5 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3540,7 +3540,6 @@ xfs_bmap_btalloc_at_eof( * original non-aligned state so the caller can proceed on allocation * failure as if this function was never called. */ - args->fsbno = ap->blkno; args->alignment = 1; return 0; } -- cgit From b82a5c42a5fa7e79426ed047ced3f8482bb66fbc Mon Sep 17 00:00:00 2001 From: "Darrick J. Wong" Date: Tue, 2 May 2023 09:14:27 +1000 Subject: xfs: don't unconditionally null args->pag in xfs_bmap_btalloc_at_eof xfs/170 on a filesystem with su=128k,sw=4 produces this splat: BUG: kernel NULL pointer dereference, address: 0000000000000010 #PF: supervisor write access in kernel mode #PF: error_code(0x0002) - not-present page PGD 0 P4D 0 Oops: 0002 [#1] PREEMPT SMP CPU: 1 PID: 4022907 Comm: dd Tainted: G W 6.3.0-xfsx #2 6ebeeffbe9577d32 Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS ?-20171121_152543-x86-ol7-bu RIP: 0010:xfs_perag_rele+0x10/0x70 [xfs] RSP: 0018:ffffc90001e43858 EFLAGS: 00010217 RAX: 0000000000000000 RBX: 0000000000000000 RCX: 0000000000000100 RDX: ffffffffa054e717 RSI: 0000000000000005 RDI: 0000000000000000 RBP: ffff888194eea000 R08: 0000000000000000 R09: 0000000000000037 R10: ffff888100ac1cb0 R11: 0000000000000018 R12: 0000000000000000 R13: ffffc90001e43a38 R14: ffff888194eea000 R15: ffff888194eea000 FS: 00007f93d1a0e740(0000) GS:ffff88843fc80000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 CR2: 0000000000000010 CR3: 000000018a34f000 CR4: 00000000003506e0 Call Trace: xfs_bmap_btalloc+0x1a7/0x5d0 [xfs f85291d6841cbb3dc740083f1f331c0327394518] xfs_bmapi_allocate+0xee/0x470 [xfs f85291d6841cbb3dc740083f1f331c0327394518] xfs_bmapi_write+0x539/0x9e0 [xfs f85291d6841cbb3dc740083f1f331c0327394518] xfs_iomap_write_direct+0x1bb/0x2b0 [xfs f85291d6841cbb3dc740083f1f331c0327394518] xfs_direct_write_iomap_begin+0x51c/0x710 [xfs f85291d6841cbb3dc740083f1f331c0327394518] iomap_iter+0x132/0x2f0 __iomap_dio_rw+0x2f8/0x840 iomap_dio_rw+0xe/0x30 xfs_file_dio_write_aligned+0xad/0x180 [xfs f85291d6841cbb3dc740083f1f331c0327394518] xfs_file_write_iter+0xfb/0x190 [xfs f85291d6841cbb3dc740083f1f331c0327394518] vfs_write+0x2eb/0x410 ksys_write+0x65/0xe0 do_syscall_64+0x2b/0x80 This crash occurs under the "out_low_space" label. We grabbed a perag reference, passed it via args->pag into xfs_bmap_btalloc_at_eof, and afterwards args->pag is NULL. Fix the second function not to clobber args->pag if the caller had passed one in. Fixes: 85843327094f ("xfs: factor xfs_bmap_btalloc()") Signed-off-by: Darrick J. Wong Reviewed-by: Dave Chinner Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_bmap.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'fs/xfs/libxfs/xfs_bmap.c') diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index b512de0540d5..cd8870a16fd1 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -3494,8 +3494,10 @@ xfs_bmap_btalloc_at_eof( if (!caller_pag) args->pag = xfs_perag_get(mp, XFS_FSB_TO_AGNO(mp, ap->blkno)); error = xfs_alloc_vextent_exact_bno(args, ap->blkno); - if (!caller_pag) + if (!caller_pag) { xfs_perag_put(args->pag); + args->pag = NULL; + } if (error) return error; @@ -3505,7 +3507,6 @@ xfs_bmap_btalloc_at_eof( * Exact allocation failed. Reset to try an aligned allocation * according to the original allocation specification. */ - args->pag = NULL; args->alignment = stripe_align; args->minlen = nextminlen; args->minalignslop = 0; -- cgit From 7dfee17b13e5024c5c0ab1911859ded4182de3e5 Mon Sep 17 00:00:00 2001 From: Dave Chinner Date: Mon, 5 Jun 2023 14:48:15 +1000 Subject: xfs: validate block number being freed before adding to xefi Bad things happen in defered extent freeing operations if it is passed a bad block number in the xefi. This can come from a bogus agno/agbno pair from deferred agfl freeing, or just a bad fsbno being passed to __xfs_free_extent_later(). Either way, it's very difficult to diagnose where a null perag oops in EFI creation is coming from when the operation that queued the xefi has already been completed and there's no longer any trace of it around.... Signed-off-by: Dave Chinner Reviewed-by: Christoph Hellwig Reviewed-by: Darrick J. Wong Signed-off-by: Dave Chinner --- fs/xfs/libxfs/xfs_ag.c | 5 ++++- fs/xfs/libxfs/xfs_alloc.c | 16 +++++++++++++--- fs/xfs/libxfs/xfs_alloc.h | 6 +++--- fs/xfs/libxfs/xfs_bmap.c | 10 ++++++++-- fs/xfs/libxfs/xfs_bmap_btree.c | 7 +++++-- fs/xfs/libxfs/xfs_ialloc.c | 24 ++++++++++++++++-------- fs/xfs/libxfs/xfs_refcount.c | 13 ++++++++++--- fs/xfs/xfs_reflink.c | 4 +++- 8 files changed, 62 insertions(+), 23 deletions(-) (limited to 'fs/xfs/libxfs/xfs_bmap.c') diff --git a/fs/xfs/libxfs/xfs_ag.c b/fs/xfs/libxfs/xfs_ag.c index 9b373a0c7aaf..ee84835ebc66 100644 --- a/fs/xfs/libxfs/xfs_ag.c +++ b/fs/xfs/libxfs/xfs_ag.c @@ -984,7 +984,10 @@ xfs_ag_shrink_space( if (err2 != -ENOSPC) goto resv_err; - __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, true); + err2 = __xfs_free_extent_later(*tpp, args.fsbno, delta, NULL, + true); + if (err2) + goto resv_err; /* * Roll the transaction before trying to re-init the per-ag diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c index 643d17877832..c20fe99405d8 100644 --- a/fs/xfs/libxfs/xfs_alloc.c +++ b/fs/xfs/libxfs/xfs_alloc.c @@ -2431,7 +2431,7 @@ xfs_agfl_reset( * the real allocation can proceed. Deferring the free disconnects freeing up * the AGFL slot from freeing the block. */ -STATIC void +static int xfs_defer_agfl_block( struct xfs_trans *tp, xfs_agnumber_t agno, @@ -2450,17 +2450,21 @@ xfs_defer_agfl_block( xefi->xefi_blockcount = 1; xefi->xefi_owner = oinfo->oi_owner; + if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbno(mp, xefi->xefi_startblock))) + return -EFSCORRUPTED; + trace_xfs_agfl_free_defer(mp, agno, 0, agbno, 1); xfs_extent_free_get_group(mp, xefi); xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_AGFL_FREE, &xefi->xefi_list); + return 0; } /* * Add the extent to the list of extents to be free at transaction end. * The list is maintained sorted (by block number). */ -void +int __xfs_free_extent_later( struct xfs_trans *tp, xfs_fsblock_t bno, @@ -2487,6 +2491,9 @@ __xfs_free_extent_later( #endif ASSERT(xfs_extfree_item_cache != NULL); + if (XFS_IS_CORRUPT(mp, !xfs_verify_fsbext(mp, bno, len))) + return -EFSCORRUPTED; + xefi = kmem_cache_zalloc(xfs_extfree_item_cache, GFP_KERNEL | __GFP_NOFAIL); xefi->xefi_startblock = bno; @@ -2510,6 +2517,7 @@ __xfs_free_extent_later( xfs_extent_free_get_group(mp, xefi); xfs_defer_add(tp, XFS_DEFER_OPS_TYPE_FREE, &xefi->xefi_list); + return 0; } #ifdef DEBUG @@ -2670,7 +2678,9 @@ xfs_alloc_fix_freelist( goto out_agbp_relse; /* defer agfl frees */ - xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo); + error = xfs_defer_agfl_block(tp, args->agno, bno, &targs.oinfo); + if (error) + goto out_agbp_relse; } targs.tp = tp; diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h index 5dbb25546d0b..85ac470be0da 100644 --- a/fs/xfs/libxfs/xfs_alloc.h +++ b/fs/xfs/libxfs/xfs_alloc.h @@ -230,7 +230,7 @@ xfs_buf_to_agfl_bno( return bp->b_addr; } -void __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, +int __xfs_free_extent_later(struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo, bool skip_discard); @@ -254,14 +254,14 @@ void xfs_extent_free_get_group(struct xfs_mount *mp, #define XFS_EFI_ATTR_FORK (1U << 1) /* freeing attr fork block */ #define XFS_EFI_BMBT_BLOCK (1U << 2) /* freeing bmap btree block */ -static inline void +static inline int xfs_free_extent_later( struct xfs_trans *tp, xfs_fsblock_t bno, xfs_filblks_t len, const struct xfs_owner_info *oinfo) { - __xfs_free_extent_later(tp, bno, len, oinfo, false); + return __xfs_free_extent_later(tp, bno, len, oinfo, false); } diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c index cd8870a16fd1..fef35696adb7 100644 --- a/fs/xfs/libxfs/xfs_bmap.c +++ b/fs/xfs/libxfs/xfs_bmap.c @@ -572,8 +572,12 @@ xfs_bmap_btree_to_extents( cblock = XFS_BUF_TO_BLOCK(cbp); if ((error = xfs_btree_check_block(cur, cblock, 0, cbp))) return error; + xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, whichfork); - xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo); + error = xfs_free_extent_later(cur->bc_tp, cbno, 1, &oinfo); + if (error) + return error; + ip->i_nblocks--; xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); xfs_trans_binval(tp, cbp); @@ -5230,10 +5234,12 @@ xfs_bmap_del_extent_real( if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK) { xfs_refcount_decrease_extent(tp, del); } else { - __xfs_free_extent_later(tp, del->br_startblock, + error = __xfs_free_extent_later(tp, del->br_startblock, del->br_blockcount, NULL, (bflags & XFS_BMAPI_NODISCARD) || del->br_state == XFS_EXT_UNWRITTEN); + if (error) + goto done; } } diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c index 1b40e5f8b1ec..36564ae3084f 100644 --- a/fs/xfs/libxfs/xfs_bmap_btree.c +++ b/fs/xfs/libxfs/xfs_bmap_btree.c @@ -268,11 +268,14 @@ xfs_bmbt_free_block( struct xfs_trans *tp = cur->bc_tp; xfs_fsblock_t fsbno = XFS_DADDR_TO_FSB(mp, xfs_buf_daddr(bp)); struct xfs_owner_info oinfo; + int error; xfs_rmap_ino_bmbt_owner(&oinfo, ip->i_ino, cur->bc_ino.whichfork); - xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo); - ip->i_nblocks--; + error = xfs_free_extent_later(cur->bc_tp, fsbno, 1, &oinfo); + if (error) + return error; + ip->i_nblocks--; xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE); xfs_trans_mod_dquot_byino(tp, ip, XFS_TRANS_DQ_BCOUNT, -1L); return 0; diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c index a16d5de16933..34600f94c2f4 100644 --- a/fs/xfs/libxfs/xfs_ialloc.c +++ b/fs/xfs/libxfs/xfs_ialloc.c @@ -1834,7 +1834,7 @@ retry: * might be sparse and only free the regions that are allocated as part of the * chunk. */ -STATIC void +static int xfs_difree_inode_chunk( struct xfs_trans *tp, xfs_agnumber_t agno, @@ -1851,10 +1851,10 @@ xfs_difree_inode_chunk( if (!xfs_inobt_issparse(rec->ir_holemask)) { /* not sparse, calculate extent info directly */ - xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, sagbno), - M_IGEO(mp)->ialloc_blks, - &XFS_RMAP_OINFO_INODES); - return; + return xfs_free_extent_later(tp, + XFS_AGB_TO_FSB(mp, agno, sagbno), + M_IGEO(mp)->ialloc_blks, + &XFS_RMAP_OINFO_INODES); } /* holemask is only 16-bits (fits in an unsigned long) */ @@ -1871,6 +1871,8 @@ xfs_difree_inode_chunk( XFS_INOBT_HOLEMASK_BITS); nextbit = startidx + 1; while (startidx < XFS_INOBT_HOLEMASK_BITS) { + int error; + nextbit = find_next_zero_bit(holemask, XFS_INOBT_HOLEMASK_BITS, nextbit); /* @@ -1896,8 +1898,11 @@ xfs_difree_inode_chunk( ASSERT(agbno % mp->m_sb.sb_spino_align == 0); ASSERT(contigblk % mp->m_sb.sb_spino_align == 0); - xfs_free_extent_later(tp, XFS_AGB_TO_FSB(mp, agno, agbno), - contigblk, &XFS_RMAP_OINFO_INODES); + error = xfs_free_extent_later(tp, + XFS_AGB_TO_FSB(mp, agno, agbno), + contigblk, &XFS_RMAP_OINFO_INODES); + if (error) + return error; /* reset range to current bit and carry on... */ startidx = endidx = nextbit; @@ -1905,6 +1910,7 @@ xfs_difree_inode_chunk( next: nextbit++; } + return 0; } STATIC int @@ -2003,7 +2009,9 @@ xfs_difree_inobt( goto error0; } - xfs_difree_inode_chunk(tp, pag->pag_agno, &rec); + error = xfs_difree_inode_chunk(tp, pag->pag_agno, &rec); + if (error) + goto error0; } else { xic->deleted = false; diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c index c1c65774dcc2..b6e21433925c 100644 --- a/fs/xfs/libxfs/xfs_refcount.c +++ b/fs/xfs/libxfs/xfs_refcount.c @@ -1151,8 +1151,10 @@ xfs_refcount_adjust_extents( fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.pag->pag_agno, tmp.rc_startblock); - xfs_free_extent_later(cur->bc_tp, fsbno, + error = xfs_free_extent_later(cur->bc_tp, fsbno, tmp.rc_blockcount, NULL); + if (error) + goto out_error; } (*agbno) += tmp.rc_blockcount; @@ -1210,8 +1212,10 @@ xfs_refcount_adjust_extents( fsbno = XFS_AGB_TO_FSB(cur->bc_mp, cur->bc_ag.pag->pag_agno, ext.rc_startblock); - xfs_free_extent_later(cur->bc_tp, fsbno, + error = xfs_free_extent_later(cur->bc_tp, fsbno, ext.rc_blockcount, NULL); + if (error) + goto out_error; } skip: @@ -1976,7 +1980,10 @@ xfs_refcount_recover_cow_leftovers( rr->rr_rrec.rc_blockcount); /* Free the block. */ - xfs_free_extent_later(tp, fsb, rr->rr_rrec.rc_blockcount, NULL); + error = xfs_free_extent_later(tp, fsb, + rr->rr_rrec.rc_blockcount, NULL); + if (error) + goto out_trans; error = xfs_trans_commit(tp); if (error) diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c index f5dc46ce9803..abcc559f3c64 100644 --- a/fs/xfs/xfs_reflink.c +++ b/fs/xfs/xfs_reflink.c @@ -616,8 +616,10 @@ xfs_reflink_cancel_cow_blocks( xfs_refcount_free_cow_extent(*tpp, del.br_startblock, del.br_blockcount); - xfs_free_extent_later(*tpp, del.br_startblock, + error = xfs_free_extent_later(*tpp, del.br_startblock, del.br_blockcount, NULL); + if (error) + break; /* Roll the transaction */ error = xfs_defer_finish(tpp); -- cgit